Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 9a9c7a6..43a81d0 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -14,12 +14,6 @@
config STACKTRACE_SUPPORT
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- bool
-
-config RWSEM_XCHGADD_ALGORITHM
- def_bool y
-
config ARCH_HAS_ILOG2_U32
def_bool n
@@ -36,7 +30,7 @@
def_bool y
config GENERIC_LOCKBREAK
- def_bool y if SMP && PREEMPT
+ def_bool y if PREEMPT
config PGSTE
def_bool y if KVM
@@ -56,6 +50,12 @@
config ARCH_SUPPORTS_UPROBES
def_bool y
+config KASAN_SHADOW_OFFSET
+ hex
+ depends on KASAN
+ default 0x18000000000000 if KASAN_S390_4_LEVEL_PAGING
+ default 0x30000000000
+
config S390
def_bool y
select ARCH_BINFMT_ELF_STATE
@@ -63,13 +63,14 @@
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE
select ARCH_HAS_KCOV
+ select ARCH_HAS_MEM_ENCRYPT
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SET_MEMORY
- select ARCH_HAS_SG_CHAIN
select ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_HAS_STRICT_MODULE_RWX
+ select ARCH_HAS_SYSCALL_WRAPPER
select ARCH_HAS_UBSAN_SANITIZE_ALL
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_INLINE_READ_LOCK
@@ -100,7 +101,9 @@
select ARCH_INLINE_WRITE_UNLOCK_BH
select ARCH_INLINE_WRITE_UNLOCK_IRQ
select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+ select ARCH_KEEP_MEMBLOCK
select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+ select ARCH_STACKWALK
select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_USE_BUILTIN_BSWAP
@@ -112,7 +115,6 @@
select DYNAMIC_FTRACE if FUNCTION_TRACER
select GENERIC_CLOCKEVENTS
select GENERIC_CPU_AUTOPROBE
- select GENERIC_CPU_DEVICES if !SMP
select GENERIC_CPU_VULNERABILITIES
select GENERIC_FIND_FIRST_BIT
select GENERIC_SMP_IDLE_THREAD
@@ -120,20 +122,24 @@
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL_RELATIVE
+ select HAVE_ARCH_KASAN
select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_SOFT_DIRTY
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_ARCH_VMAP_STACK
+ select HAVE_ASM_MODVERSIONS
select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
select HAVE_COPY_THREAD_TLS
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
- select DMA_DIRECT_OPS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
+ select HAVE_FAST_GUP
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_FENTRY
select HAVE_FTRACE_MCOUNT_RECORD
@@ -154,29 +160,38 @@
select HAVE_LIVEPATCH
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
- select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_MEMBLOCK_PHYS_MAP
+ select HAVE_MMU_GATHER_NO_GATHER
select HAVE_MOD_ARCH_SPECIFIC
select HAVE_NOP_MCOUNT
select HAVE_OPROFILE
+ select HAVE_PCI
select HAVE_PERF_EVENTS
+ select HAVE_RCU_TABLE_FREE
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RSEQ
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING
+ select IOMMU_HELPER if PCI
+ select IOMMU_SUPPORT if PCI
select MODULES_USE_ELF_RELA
- select NO_BOOTMEM
+ select NEED_DMA_MAP_STATE if PCI
+ select NEED_SG_DMA_LENGTH if PCI
select OLD_SIGACTION
select OLD_SIGSUSPEND3
+ select PCI_DOMAINS if PCI
+ select PCI_MSI if PCI
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
select TTY
select VIRT_CPU_ACCOUNTING
select ARCH_HAS_SCALED_CPUTIME
- select VIRT_TO_BUS
select HAVE_NMI
+ select ARCH_HAS_FORCE_DMA_UNENCRYPTED
+ select SWIOTLB
+ select GENERIC_ALLOCATOR
config SCHED_OMIT_FRAME_POINTER
@@ -221,12 +236,17 @@
def_bool n
select HAVE_MARCH_Z13_FEATURES
+config HAVE_MARCH_Z15_FEATURES
+ def_bool n
+ select HAVE_MARCH_Z14_FEATURES
+
choice
prompt "Processor type"
default MARCH_Z196
config MARCH_Z900
bool "IBM zSeries model z800 and z900"
+ depends on !CC_IS_CLANG
select HAVE_MARCH_Z900_FEATURES
help
Select this to enable optimizations for model z800/z900 (2064 and
@@ -235,6 +255,7 @@
config MARCH_Z990
bool "IBM zSeries model z890 and z990"
+ depends on !CC_IS_CLANG
select HAVE_MARCH_Z990_FEATURES
help
Select this to enable optimizations for model z890/z990 (2084 and
@@ -243,6 +264,7 @@
config MARCH_Z9_109
bool "IBM System z9"
+ depends on !CC_IS_CLANG
select HAVE_MARCH_Z9_109_FEATURES
help
Select this to enable optimizations for IBM System z9 (2094 and
@@ -289,6 +311,14 @@
and 3906 series). The kernel will be slightly faster but will not
work on older machines.
+config MARCH_Z15
+ bool "IBM z15"
+ select HAVE_MARCH_Z15_FEATURES
+ help
+ Select this to enable optimizations for IBM z15 (8562
+ and 8561 series). The kernel will be slightly faster but will not
+ work on older machines.
+
endchoice
config MARCH_Z900_TUNE
@@ -315,6 +345,9 @@
config MARCH_Z14_TUNE
def_bool TUNE_Z14 || MARCH_Z14 && TUNE_DEFAULT
+config MARCH_Z15_TUNE
+ def_bool TUNE_Z15 || MARCH_Z15 && TUNE_DEFAULT
+
choice
prompt "Tune code generation"
default TUNE_DEFAULT
@@ -334,12 +367,15 @@
config TUNE_Z900
bool "IBM zSeries model z800 and z900"
+ depends on !CC_IS_CLANG
config TUNE_Z990
bool "IBM zSeries model z890 and z990"
+ depends on !CC_IS_CLANG
config TUNE_Z9_109
bool "IBM System z9"
+ depends on !CC_IS_CLANG
config TUNE_Z10
bool "IBM System z10"
@@ -356,6 +392,9 @@
config TUNE_Z14
bool "IBM z14"
+config TUNE_Z15
+ bool "IBM z15"
+
endchoice
config 64BIT
@@ -367,6 +406,7 @@
select COMPAT_BINFMT_ELF if BINFMT_ELF
select ARCH_WANT_OLD_COMPAT_IPC
select COMPAT_OLD_SIGACTION
+ select HAVE_UID16
depends on MULTIUSER
help
Select this option if you want to enable your system kernel to
@@ -374,32 +414,18 @@
(and some other stuff like libraries and such) is needed for
executing 31 bit applications. It is safe to say "Y".
+config COMPAT_VDSO
+ def_bool COMPAT && !CC_IS_CLANG
+
config SYSVIPC_COMPAT
def_bool y if COMPAT && SYSVIPC
config SMP
def_bool y
- prompt "Symmetric multi-processing support"
- ---help---
- This enables support for systems with more than one CPU. If you have
- a system with only one CPU, like most personal computers, say N. If
- you have a system with more than one CPU, say Y.
-
- If you say N here, the kernel will run on uni- and multiprocessor
- machines, but will use only one CPU of a multiprocessor machine. If
- you say Y here, the kernel will run on many, but not all,
- uniprocessor machines. On a uniprocessor machine, the kernel
- will run faster if you say N here.
-
- See also the SMP-HOWTO available at
- <http://www.tldp.org/docs.html#howto>.
-
- Even if you don't know what to do here, say Y.
config NR_CPUS
int "Maximum number of CPUs (2-512)"
range 2 512
- depends on SMP
default "64"
help
This allows you to specify the maximum number of CPUs which this
@@ -411,12 +437,6 @@
config HOTPLUG_CPU
def_bool y
- prompt "Support for hot-pluggable CPUs"
- depends on SMP
- help
- Say Y here to be able to turn CPUs off and on. CPUs
- can be controlled through /sys/devices/system/cpu/cpu#.
- Say N if you want to disable CPU hotplug.
# Some NUMA nodes have memory ranges that span
# other nodes. Even though a pfn is valid and
@@ -428,7 +448,7 @@
config NUMA
bool "NUMA support"
- depends on SMP && SCHED_TOPOLOGY
+ depends on SCHED_TOPOLOGY
default n
help
Enable NUMA support
@@ -503,7 +523,6 @@
config SCHED_TOPOLOGY
def_bool y
prompt "Topology scheduler support"
- depends on SMP
select SCHED_SMT
select SCHED_MC
select SCHED_BOOK
@@ -513,7 +532,7 @@
making when dealing with machines that have multi-threading,
multiple cores or multiple books.
-source kernel/Kconfig.hz
+source "kernel/Kconfig.hz"
config KEXEC
def_bool y
@@ -535,6 +554,17 @@
def_bool y
depends on KEXEC_FILE
+config KEXEC_SIG
+ bool "Verify kernel signature during kexec_file_load() syscall"
+ depends on KEXEC_FILE && MODULE_SIG_FORMAT
+ help
+ This option makes kernel signature verification mandatory for
+ the kexec_file_load() syscall.
+
+ In addition to that option, you need to enable signature
+ verification for the corresponding kernel image type being
+ loaded in order for this to work.
+
config ARCH_RANDOM
def_bool y
prompt "s390 architectural random number generation API"
@@ -595,6 +625,29 @@
endchoice
+config RELOCATABLE
+ bool "Build a relocatable kernel"
+ select MODULE_REL_CRCS if MODVERSIONS
+ default y
+ help
+ This builds a kernel image that retains relocation information
+ so it can be loaded at an arbitrary address.
+ The kernel is linked as a position-independent executable (PIE)
+ and contains dynamic relocations which are processed early in the
+ bootup process.
+ The relocations make the kernel image about 15% larger (compressed
+ 10%), but are discarded at runtime.
+
+config RANDOMIZE_BASE
+ bool "Randomize the address of the kernel image (KASLR)"
+ depends on RELOCATABLE
+ default y
+ help
+ In support of Kernel Address Space Layout Randomization (KASLR),
+ this randomizes the address at which the kernel image is loaded,
+ as a security feature that deters exploit attempts relying on
+ knowledge of the location of kernel internals.
+
endmenu
menu "Memory setup"
@@ -607,9 +660,6 @@
config ARCH_SPARSEMEM_DEFAULT
def_bool y
-config ARCH_SELECT_MEMORY_MODEL
- def_bool y
-
config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y if SPARSEMEM
@@ -649,6 +699,7 @@
config CHECK_STACK
def_bool y
+ depends on !VMAP_STACK
prompt "Detect kernel stack overflow"
help
This option enables the compiler option -mstack-guard and
@@ -698,17 +749,6 @@
If unsure, say Y.
-menuconfig PCI
- bool "PCI support"
- select PCI_MSI
- select IOMMU_HELPER
- select IOMMU_SUPPORT
- select NEED_DMA_MAP_STATE
- select NEED_SG_DMA_LENGTH
-
- help
- Enable PCI support.
-
if PCI
config PCI_NR_FUNCTIONS
@@ -719,12 +759,7 @@
This allows you to specify the maximum number of PCI functions which
this kernel will support.
-source "drivers/pci/Kconfig"
-
-endif # PCI
-
-config PCI_DOMAINS
- def_bool PCI
+endif # PCI
config HAS_IOMEM
def_bool PCI
@@ -773,22 +808,32 @@
To compile this driver as a module, choose M here: the
module will be called vfio_ccw.
+config VFIO_AP
+ def_tristate n
+ prompt "VFIO support for AP devices"
+ depends on S390_AP_IOMMU && VFIO_MDEV_DEVICE && KVM
+ help
+ This driver grants access to Adjunct Processor (AP) devices
+ via the VFIO mediated device interface.
+
+ To compile this driver as a module, choose M here: the module
+ will be called vfio_ap.
+
endmenu
menu "Dump support"
config CRASH_DUMP
bool "kernel crash dumps"
- depends on SMP
select KEXEC
help
Generate crash dump after being started by kexec.
Crash dump kernels are loaded in the main kernel with kexec-tools
into a specially reserved region and then later executed after
a crash by kdump/kexec.
- Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this.
+ Refer to <file:Documentation/s390/zfcpdump.rst> for more details on this.
This option also enables s390 zfcpdump.
- See also <file:Documentation/s390/zfcpdump.txt>
+ See also <file:Documentation/s390/zfcpdump.rst>
endmenu
@@ -818,9 +863,6 @@
endmenu
-config PCMCIA
- def_bool n
-
config CCW
def_bool y
@@ -830,6 +872,17 @@
menu "Virtualization"
+config PROTECTED_VIRTUALIZATION_GUEST
+ def_bool n
+ prompt "Protected virtualization guest support"
+ help
+ Select this option, if you want to be able to run this
+ kernel as a protected virtualization KVM guest.
+ Protected virtualization capable machines have a mini hypervisor
+ located at machine level (an ultravisor). With help of the
+ Ultravisor, KVM will be able to run "protected" VMs, special
+ VMs whose memory and management data are unavailable to KVM.
+
config PFAULT
def_bool y
prompt "Pseudo page fault support"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index ee65185..478b645 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -16,18 +16,23 @@
KBUILD_CFLAGS_MODULE += -fPIC
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
+ifeq ($(CONFIG_RELOCATABLE),y)
+KBUILD_CFLAGS += -fPIE
+LDFLAGS_vmlinux := -pie
+endif
aflags_dwarf := -Wa,-gdwarf-2
-KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
+KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
-KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2
+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-asynchronous-unwind-tables
KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding)
+KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member)
KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
UTS_MACHINE := s390x
-STACK_SIZE := 16384
+STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384)
CHECKFLAGS += -D__s390__ -D__s390x__
export LD_BFD
@@ -40,6 +45,7 @@
mflags-$(CONFIG_MARCH_ZEC12) := -march=zEC12
mflags-$(CONFIG_MARCH_Z13) := -march=z13
mflags-$(CONFIG_MARCH_Z14) := -march=z14
+mflags-$(CONFIG_MARCH_Z15) := -march=z15
export CC_FLAGS_MARCH := $(mflags-y)
@@ -54,6 +60,7 @@
cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12
cflags-$(CONFIG_MARCH_Z13_TUNE) += -mtune=z13
cflags-$(CONFIG_MARCH_Z14_TUNE) += -mtune=z14
+cflags-$(CONFIG_MARCH_Z15_TUNE) += -mtune=z15
cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include
@@ -111,7 +118,7 @@
cfi := $(call as-instr,.cfi_startproc\n.cfi_val_offset 15$(comma)-160\n.cfi_endproc,-DCONFIG_AS_CFI_VAL_OFFSET=1)
KBUILD_CFLAGS += -mbackchain -msoft-float $(cflags-y)
-KBUILD_CFLAGS += -pipe -fno-strength-reduce -Wno-sign-compare
+KBUILD_CFLAGS += -pipe -Wno-sign-compare
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables $(cfi)
KBUILD_AFLAGS += $(aflags-y) $(cfi)
export KBUILD_AFLAGS_DECOMPRESSOR
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 9bf8489..aa738ca 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -137,6 +137,14 @@
mutex_unlock(&appldata_ops_mutex);
}
+static struct appldata_product_id appldata_id = {
+ .prod_nr = {0xD3, 0xC9, 0xD5, 0xE4,
+ 0xE7, 0xD2, 0xD9}, /* "LINUXKR" */
+ .prod_fn = 0xD5D3, /* "NL" */
+ .version_nr = 0xF2F6, /* "26" */
+ .release_nr = 0xF0F1, /* "01" */
+};
+
/*
* appldata_diag()
*
@@ -145,17 +153,22 @@
int appldata_diag(char record_nr, u16 function, unsigned long buffer,
u16 length, char *mod_lvl)
{
- struct appldata_product_id id = {
- .prod_nr = {0xD3, 0xC9, 0xD5, 0xE4,
- 0xE7, 0xD2, 0xD9}, /* "LINUXKR" */
- .prod_fn = 0xD5D3, /* "NL" */
- .version_nr = 0xF2F6, /* "26" */
- .release_nr = 0xF0F1, /* "01" */
- };
+ struct appldata_parameter_list *parm_list;
+ struct appldata_product_id *id;
+ int rc;
- id.record_nr = record_nr;
- id.mod_lvl = (mod_lvl[0]) << 8 | mod_lvl[1];
- return appldata_asm(&id, function, (void *) buffer, length);
+ parm_list = kmalloc(sizeof(*parm_list), GFP_KERNEL);
+ id = kmemdup(&appldata_id, sizeof(appldata_id), GFP_KERNEL);
+ rc = -ENOMEM;
+ if (parm_list && id) {
+ id->record_nr = record_nr;
+ id->mod_lvl = (mod_lvl[0]) << 8 | mod_lvl[1];
+ rc = appldata_asm(parm_list, id, function,
+ (void *) buffer, length);
+ }
+ kfree(id);
+ kfree(parm_list);
+ return rc;
}
/************************ timer, work, DIAG <END> ****************************/
@@ -207,15 +220,13 @@
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int timer_active = appldata_timer_active;
- int zero = 0;
- int one = 1;
int rc;
struct ctl_table ctl_entry = {
.procname = ctl->procname,
.data = &timer_active,
.maxlen = sizeof(int),
- .extra1 = &zero,
- .extra2 = &one,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
};
rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
@@ -242,13 +253,12 @@
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int interval = appldata_interval;
- int one = 1;
int rc;
struct ctl_table ctl_entry = {
.procname = ctl->procname,
.data = &interval,
.maxlen = sizeof(int),
- .extra1 = &one,
+ .extra1 = SYSCTL_ONE,
};
rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
@@ -276,13 +286,11 @@
struct list_head *lh;
int rc, found;
int active;
- int zero = 0;
- int one = 1;
struct ctl_table ctl_entry = {
.data = &active,
.maxlen = sizeof(int),
- .extra1 = &zero,
- .extra2 = &one,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
};
found = 0;
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 433a994..54f3756 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -25,10 +25,6 @@
#include "appldata.h"
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
/*
* OS data
*
diff --git a/arch/s390/boot/.gitignore b/arch/s390/boot/.gitignore
index 017d591..16ff906 100644
--- a/arch/s390/boot/.gitignore
+++ b/arch/s390/boot/.gitignore
@@ -1,2 +1,3 @@
image
bzImage
+section_cmp.*
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 9e6668e..e2c47d3 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -6,42 +6,67 @@
KCOV_INSTRUMENT := n
GCOV_PROFILE := n
UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
#
-# Use -march=z900 for als.c to be able to print an error
+# Use minimum architecture for als.c to be able to print an error
# message if the kernel is started on a machine which is too old
#
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
+ifndef CONFIG_CC_IS_CLANG
+CC_FLAGS_MARCH_MINIMUM := -march=z900
+else
+CC_FLAGS_MARCH_MINIMUM := -march=z10
+endif
+
+ifneq ($(CC_FLAGS_MARCH),$(CC_FLAGS_MARCH_MINIMUM))
AFLAGS_REMOVE_head.o += $(CC_FLAGS_MARCH)
-AFLAGS_head.o += -march=z900
+AFLAGS_head.o += $(CC_FLAGS_MARCH_MINIMUM)
AFLAGS_REMOVE_mem.o += $(CC_FLAGS_MARCH)
-AFLAGS_mem.o += -march=z900
+AFLAGS_mem.o += $(CC_FLAGS_MARCH_MINIMUM)
CFLAGS_REMOVE_als.o += $(CC_FLAGS_MARCH)
-CFLAGS_als.o += -march=z900
+CFLAGS_als.o += $(CC_FLAGS_MARCH_MINIMUM)
CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o += -march=z900
+CFLAGS_sclp_early_core.o += $(CC_FLAGS_MARCH_MINIMUM)
endif
CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
-obj-y := head.o als.o ebcdic.o sclp_early_core.o mem.o
-targets := bzImage startup.a $(obj-y)
+obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o
+obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
+obj-y += version.o pgm_check_info.o ctype.o text_dma.o
+obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) += uv.o
+obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o
+obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
+targets := bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y)
subdir- := compressed
OBJECTS := $(addprefix $(obj)/,$(obj-y))
-$(obj)/bzImage: $(obj)/compressed/vmlinux FORCE
+quiet_cmd_section_cmp = SECTCMP $*
+define cmd_section_cmp
+ s1=`$(OBJDUMP) -t -j "$*" "$<" | sort | \
+ sed -n "/0000000000000000/! s/.*\s$*\s\+//p" | sha256sum`; \
+ s2=`$(OBJDUMP) -t -j "$*" "$(word 2,$^)" | sort | \
+ sed -n "/0000000000000000/! s/.*\s$*\s\+//p" | sha256sum`; \
+ if [ "$$s1" != "$$s2" ]; then \
+ echo "error: section $* differs between $< and $(word 2,$^)" >&2; \
+ exit 1; \
+ fi; \
+ touch $@
+endef
+
+$(obj)/bzImage: $(obj)/compressed/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.boot.preserved.data FORCE
$(call if_changed,objcopy)
+$(obj)/section_cmp%: vmlinux $(obj)/compressed/vmlinux FORCE
+ $(call if_changed,section_cmp)
+
$(obj)/compressed/vmlinux: $(obj)/startup.a FORCE
$(Q)$(MAKE) $(build)=$(obj)/compressed $@
-quiet_cmd_ar = AR $@
- cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter $(OBJECTS), $^)
-
$(obj)/startup.a: $(OBJECTS) FORCE
$(call if_changed,ar)
@@ -49,6 +74,6 @@
sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
System.map "$(INSTALL_PATH)"
-chkbss := $(OBJECTS)
-chkbss-target := $(obj)/startup.a
+chkbss := $(obj-y)
+chkbss-target := startup.a
include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/boot/als.c b/arch/s390/boot/als.c
index d592e0d..ff6801d 100644
--- a/arch/s390/boot/als.c
+++ b/arch/s390/boot/als.c
@@ -7,6 +7,7 @@
#include <asm/facility.h>
#include <asm/lowcore.h>
#include <asm/sclp.h>
+#include "boot.h"
/*
* The code within this file will be called very early. It may _not_
@@ -58,7 +59,7 @@
*str = '\0';
}
-static void print_missing_facilities(void)
+void print_missing_facilities(void)
{
static char als_str[80] = "Missing facilities: ";
unsigned long val;
@@ -90,7 +91,6 @@
}
strcat(als_str, "\n");
sclp_early_printk(als_str);
- sclp_early_printk("See Principles of Operations for facility bits\n");
}
static void facility_mismatch(void)
@@ -98,27 +98,15 @@
sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
print_machine_type();
print_missing_facilities();
- disabled_wait(0x8badcccc);
+ sclp_early_printk("See Principles of Operations for facility bits\n");
+ disabled_wait();
}
void verify_facilities(void)
{
int i;
- for (i = 0; i < ARRAY_SIZE(S390_lowcore.stfle_fac_list); i++)
- S390_lowcore.stfle_fac_list[i] = 0;
- asm volatile(
- " stfl 0(0)\n"
- : "=m" (S390_lowcore.stfl_fac_list));
- S390_lowcore.stfle_fac_list[0] = (u64)S390_lowcore.stfl_fac_list << 32;
- if (S390_lowcore.stfl_fac_list & 0x01000000) {
- register unsigned long reg0 asm("0") = ARRAY_SIZE(als) - 1;
-
- asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
- : "+d" (reg0)
- : "a" (&S390_lowcore.stfle_fac_list)
- : "memory", "cc");
- }
+ __stfle(S390_lowcore.stfle_fac_list, ARRAY_SIZE(S390_lowcore.stfle_fac_list));
for (i = 0; i < ARRAY_SIZE(als); i++) {
if ((S390_lowcore.stfle_fac_list[i] & als[i]) != als[i])
facility_mismatch();
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
new file mode 100644
index 0000000..2ea603f
--- /dev/null
+++ b/arch/s390/boot/boot.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BOOT_BOOT_H
+#define BOOT_BOOT_H
+
+void startup_kernel(void);
+void detect_memory(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);
+
+extern int kaslr_enabled;
+extern const char kernel_version[];
+
+unsigned long read_ipl_report(unsigned long safe_offset);
+
+#endif /* BOOT_BOOT_H */
diff --git a/arch/s390/boot/cmdline.c b/arch/s390/boot/cmdline.c
new file mode 100644
index 0000000..73d826c
--- /dev/null
+++ b/arch/s390/boot/cmdline.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../lib/cmdline.c"
diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore
index 45aeb4f..e72fcd7 100644
--- a/arch/s390/boot/compressed/.gitignore
+++ b/arch/s390/boot/compressed/.gitignore
@@ -1,5 +1,2 @@
-sizes.h
vmlinux
vmlinux.lds
-vmlinux.scr.lds
-vmlinux.bin.full
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index b375c6c..fa529c5 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -8,14 +8,16 @@
KCOV_INSTRUMENT := n
GCOV_PROFILE := n
UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
-obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,head.o misc.o) piggy.o
+obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) piggy.o info.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 += vmlinux.scr.lds $(obj-y) $(if $(CONFIG_KERNEL_UNCOMPRESSED),,sizes.h)
+targets += info.bin $(obj-y)
KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
+OBJCOPYFLAGS :=
OBJECTS := $(addprefix $(obj)/,$(obj-y))
@@ -23,23 +25,16 @@
$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE
$(call if_changed,ld)
-# extract required uncompressed vmlinux symbols and adjust them to reflect offsets inside vmlinux.bin
-sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - 0x100000)/p'
+OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load
+$(obj)/info.bin: vmlinux FORCE
+ $(call if_changed,objcopy)
-quiet_cmd_sizes = GEN $@
- cmd_sizes = $(NM) $< | sed -n $(sed-sizes) > $@
+OBJCOPYFLAGS_info.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.info
+$(obj)/info.o: $(obj)/info.bin FORCE
+ $(call if_changed,objcopy)
-$(obj)/sizes.h: vmlinux
- $(call if_changed,sizes)
-
-AFLAGS_head.o += -I$(objtree)/$(obj)
-$(obj)/head.o: $(obj)/sizes.h
-
-CFLAGS_misc.o += -I$(objtree)/$(obj)
-$(obj)/misc.o: $(obj)/sizes.h
-
-OBJCOPYFLAGS_vmlinux.bin := -R .comment -S
-$(obj)/vmlinux.bin: vmlinux
+OBJCOPYFLAGS_vmlinux.bin := -O binary --remove-section=.comment --remove-section=.vmlinux.info -S
+$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
vmlinux.bin.all-y := $(obj)/vmlinux.bin
@@ -64,10 +59,10 @@
$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
$(call if_changed,xzkern)
-LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
-$(obj)/piggy.o: $(obj)/vmlinux.scr.lds $(obj)/vmlinux.bin$(suffix-y)
- $(call if_changed,ld)
+OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed
+$(obj)/piggy.o: $(obj)/vmlinux.bin$(suffix-y) FORCE
+ $(call if_changed,objcopy)
-chkbss := $(filter-out $(obj)/misc.o $(obj)/piggy.o,$(OBJECTS))
-chkbss-target := $(obj)/vmlinux.bin
+chkbss := $(filter-out piggy.o info.o, $(obj-y))
+chkbss-target := vmlinux.bin
include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c
new file mode 100644
index 0000000..4504663
--- /dev/null
+++ b/arch/s390/boot/compressed/decompressor.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Definitions and wrapper functions for kernel decompressor
+ *
+ * Copyright IBM Corp. 2010
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/page.h>
+#include "decompressor.h"
+
+/*
+ * gzip declarations
+ */
+#define STATIC static
+#define STATIC_RW_DATA static __section(.data)
+
+#undef memset
+#undef memcpy
+#undef memmove
+#define memmove memmove
+#define memzero(s, n) memset((s), 0, (n))
+
+/* Symbols defined by linker scripts */
+extern char _end[];
+extern unsigned char _compressed_start[];
+extern unsigned char _compressed_end[];
+
+#ifdef CONFIG_HAVE_KERNEL_BZIP2
+#define HEAP_SIZE 0x400000
+#else
+#define HEAP_SIZE 0x10000
+#endif
+
+static unsigned long free_mem_ptr = (unsigned long) _end;
+static unsigned long free_mem_end_ptr = (unsigned long) _end + HEAP_SIZE;
+
+#ifdef CONFIG_KERNEL_GZIP
+#include "../../../../lib/decompress_inflate.c"
+#endif
+
+#ifdef CONFIG_KERNEL_BZIP2
+#include "../../../../lib/decompress_bunzip2.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZ4
+#include "../../../../lib/decompress_unlz4.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZMA
+#include "../../../../lib/decompress_unlzma.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZO
+#include "../../../../lib/decompress_unlzo.c"
+#endif
+
+#ifdef CONFIG_KERNEL_XZ
+#include "../../../../lib/decompress_unxz.c"
+#endif
+
+#define decompress_offset ALIGN((unsigned long)_end + HEAP_SIZE, PAGE_SIZE)
+
+unsigned long mem_safe_offset(void)
+{
+ /*
+ * due to 4MB HEAD_SIZE for bzip2
+ * 'decompress_offset + vmlinux.image_size' could be larger than
+ * kernel at final position + its .bss, so take the larger of two
+ */
+ return max(decompress_offset + vmlinux.image_size,
+ vmlinux.default_lma + vmlinux.image_size + vmlinux.bss_size);
+}
+
+void *decompress_kernel(void)
+{
+ void *output = (void *)decompress_offset;
+
+ __decompress(_compressed_start, _compressed_end - _compressed_start,
+ NULL, NULL, output, 0, NULL, error);
+ return output;
+}
diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h
new file mode 100644
index 0000000..c15eb71
--- /dev/null
+++ b/arch/s390/boot/compressed/decompressor.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BOOT_COMPRESSED_DECOMPRESSOR_H
+#define BOOT_COMPRESSED_DECOMPRESSOR_H
+
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
+static inline void *decompress_kernel(void) {}
+#else
+void *decompress_kernel(void);
+#endif
+unsigned long mem_safe_offset(void);
+void error(char *m);
+
+struct vmlinux_info {
+ unsigned long default_lma;
+ void (*entry)(void);
+ unsigned long image_size; /* does not include .bss */
+ unsigned long bss_size; /* uncompressed image .bss size */
+ unsigned long bootdata_off;
+ unsigned long bootdata_size;
+ unsigned long bootdata_preserved_off;
+ unsigned long bootdata_preserved_size;
+ unsigned long dynsym_start;
+ unsigned long rela_dyn_start;
+ unsigned long rela_dyn_end;
+};
+
+extern char _vmlinux_info[];
+#define vmlinux (*(struct vmlinux_info *)_vmlinux_info)
+
+#endif /* BOOT_COMPRESSED_DECOMPRESSOR_H */
diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S
deleted file mode 100644
index df8dbbc..0000000
--- a/arch/s390/boot/compressed/head.S
+++ /dev/null
@@ -1,52 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Startup glue code to uncompress the kernel
- *
- * Copyright IBM Corp. 2010
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/page.h>
-#include "sizes.h"
-
-__HEAD
-ENTRY(startup_decompressor)
- basr %r13,0 # get base
-.LPG1:
- # setup stack
- lg %r15,.Lstack-.LPG1(%r13)
- aghi %r15,-160
- brasl %r14,decompress_kernel
- # Set up registers for memory mover. We move the decompressed image to
- # 0x100000, where startup_continue of the decompressed image is supposed
- # to be.
- lgr %r4,%r2
- lg %r2,.Loffset-.LPG1(%r13)
- lg %r3,.Lmvsize-.LPG1(%r13)
- lgr %r5,%r3
- # Move the memory mover someplace safe so it doesn't overwrite itself.
- la %r1,0x200
- mvc 0(mover_end-mover,%r1),mover-.LPG1(%r13)
- # When the memory mover is done we pass control to
- # arch/s390/kernel/head64.S:startup_continue which lives at 0x100000 in
- # the decompressed image.
- lgr %r6,%r2
- br %r1
-mover:
- mvcle %r2,%r4,0
- jo mover
- br %r6
-mover_end:
-
- .align 8
-.Lstack:
- .quad 0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
-.Loffset:
- .quad 0x100000
-.Lmvsize:
- .quad SZ__bss_start
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
deleted file mode 100644
index f66ad73..0000000
--- a/arch/s390/boot/compressed/misc.c
+++ /dev/null
@@ -1,116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Definitions and wrapper functions for kernel decompressor
- *
- * Copyright IBM Corp. 2010
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-
-#include <linux/uaccess.h>
-#include <asm/page.h>
-#include <asm/sclp.h>
-#include <asm/ipl.h>
-#include "sizes.h"
-
-/*
- * gzip declarations
- */
-#define STATIC static
-
-#undef memset
-#undef memcpy
-#undef memmove
-#define memmove memmove
-#define memzero(s, n) memset((s), 0, (n))
-
-/* Symbols defined by linker scripts */
-extern char input_data[];
-extern int input_len;
-extern char _end[];
-extern char _bss[], _ebss[];
-
-static void error(char *m);
-
-static unsigned long free_mem_ptr;
-static unsigned long free_mem_end_ptr;
-
-#ifdef CONFIG_HAVE_KERNEL_BZIP2
-#define HEAP_SIZE 0x400000
-#else
-#define HEAP_SIZE 0x10000
-#endif
-
-#ifdef CONFIG_KERNEL_GZIP
-#include "../../../../lib/decompress_inflate.c"
-#endif
-
-#ifdef CONFIG_KERNEL_BZIP2
-#include "../../../../lib/decompress_bunzip2.c"
-#endif
-
-#ifdef CONFIG_KERNEL_LZ4
-#include "../../../../lib/decompress_unlz4.c"
-#endif
-
-#ifdef CONFIG_KERNEL_LZMA
-#include "../../../../lib/decompress_unlzma.c"
-#endif
-
-#ifdef CONFIG_KERNEL_LZO
-#include "../../../../lib/decompress_unlzo.c"
-#endif
-
-#ifdef CONFIG_KERNEL_XZ
-#include "../../../../lib/decompress_unxz.c"
-#endif
-
-static int puts(const char *s)
-{
- sclp_early_printk(s);
- return 0;
-}
-
-static void error(char *x)
-{
- unsigned long long psw = 0x000a0000deadbeefULL;
-
- puts("\n\n");
- puts(x);
- puts("\n\n -- System halted");
-
- asm volatile("lpsw %0" : : "Q" (psw));
-}
-
-unsigned long decompress_kernel(void)
-{
- void *output, *kernel_end;
-
- output = (void *) ALIGN((unsigned long) _end + HEAP_SIZE, PAGE_SIZE);
- kernel_end = output + SZ__bss_start;
-
-#ifdef CONFIG_BLK_DEV_INITRD
- /*
- * Move the initrd right behind the end of the decompressed
- * kernel image. This also prevents initrd corruption caused by
- * bss clearing since kernel_end will always be located behind the
- * current bss section..
- */
- if (INITRD_START && INITRD_SIZE && kernel_end > (void *) INITRD_START) {
- memmove(kernel_end, (void *) INITRD_START, INITRD_SIZE);
- INITRD_START = (unsigned long) kernel_end;
- }
-#endif
-
- /*
- * Clear bss section. free_mem_ptr and free_mem_end_ptr need to be
- * initialized afterwards since they reside in bss.
- */
- memset(_bss, 0, _ebss - _bss);
- free_mem_ptr = (unsigned long) _end;
- free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
-
- __decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error);
- return (unsigned long) output;
-}
-
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index b16ac8b..44561b2 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -1,5 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
OUTPUT_ARCH(s390:64-bit)
@@ -8,9 +9,6 @@
SECTIONS
{
- /* Be careful parts of head_64.S assume startup_32 is at
- * address 0.
- */
. = 0;
.head.text : {
_head = . ;
@@ -26,7 +24,7 @@
.rodata : {
_rodata = . ;
*(.rodata) /* read-only data */
- *(EXCLUDE_FILE (*piggy.o) .rodata.compressed)
+ *(.rodata.*)
_erodata = . ;
}
.data : {
@@ -35,14 +33,53 @@
*(.data.*)
_edata = . ;
}
- startup_continue = 0x100000;
+ /*
+ * .dma section for code, data, ex_table that need to stay below 2 GB,
+ * even when the kernel is relocate: above 2 GB.
+ */
+ . = ALIGN(PAGE_SIZE);
+ _sdma = .;
+ .dma.text : {
+ _stext_dma = .;
+ *(.dma.text)
+ . = ALIGN(PAGE_SIZE);
+ _etext_dma = .;
+ }
+ . = ALIGN(16);
+ .dma.ex_table : {
+ _start_dma_ex_table = .;
+ KEEP(*(.dma.ex_table))
+ _stop_dma_ex_table = .;
+ }
+ .dma.data : { *(.dma.data) }
+ . = ALIGN(PAGE_SIZE);
+ _edma = .;
+
+ BOOT_DATA
+ BOOT_DATA_PRESERVED
+
+ /*
+ * uncompressed image info used by the decompressor it should match
+ * struct vmlinux_info. It comes from .vmlinux.info section of
+ * uncompressed vmlinux in a form of info.o
+ */
+ . = ALIGN(8);
+ .vmlinux.info : {
+ _vmlinux_info = .;
+ *(.vmlinux.info)
+ }
+
#ifdef CONFIG_KERNEL_UNCOMPRESSED
. = 0x100000;
#else
. = ALIGN(8);
#endif
.rodata.compressed : {
- *(.rodata.compressed)
+ _compressed_start = .;
+ *(.vmlinux.bin.compressed)
+ _compressed_end = .;
+ FILL(0xff);
+ . = ALIGN(4096);
}
. = ALIGN(256);
.bss : {
diff --git a/arch/s390/boot/compressed/vmlinux.scr.lds.S b/arch/s390/boot/compressed/vmlinux.scr.lds.S
deleted file mode 100644
index ff01d18..0000000
--- a/arch/s390/boot/compressed/vmlinux.scr.lds.S
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-SECTIONS
-{
- .rodata.compressed : {
-#ifndef CONFIG_KERNEL_UNCOMPRESSED
- input_len = .;
- LONG(input_data_end - input_data) input_data = .;
-#endif
- *(.data)
-#ifndef CONFIG_KERNEL_UNCOMPRESSED
- output_len = . - 4;
- input_data_end = .;
-#endif
- }
-}
diff --git a/arch/s390/boot/ctype.c b/arch/s390/boot/ctype.c
new file mode 100644
index 0000000..2495810
--- /dev/null
+++ b/arch/s390/boot/ctype.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../lib/ctype.c"
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index f721913..4b86a8d 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -60,6 +60,11 @@
.long 0x02000690,0x60000050
.long 0x020006e0,0x20000050
+ .org __LC_RST_NEW_PSW # 0x1a0
+ .quad 0,iplstart
+ .org __LC_PGM_NEW_PSW # 0x1d0
+ .quad 0x0000000180000000,startup_pgm_check_handler
+
.org 0x200
#
@@ -302,39 +307,97 @@
xc 0x300(256),0x300
xc 0xe00(256),0xe00
xc 0xf00(256),0xf00
- lctlg %c0,%c15,0x200(%r0) # initialize control registers
+ lctlg %c0,%c15,.Lctl-.LPG0(%r13) # load control registers
stcke __LC_BOOT_CLOCK
mvc __LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
spt 6f-.LPG0(%r13)
mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
l %r15,.Lstack-.LPG0(%r13)
- ahi %r15,-STACK_FRAME_OVERHEAD
brasl %r14,verify_facilities
-#ifdef CONFIG_KERNEL_UNCOMPRESSED
- jg startup_continue
-#else
- jg startup_decompressor
-#endif
+ brasl %r14,startup_kernel
.Lstack:
- .long 0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
+ .long 0x8000 + (1<<(PAGE_SHIFT+BOOT_STACK_ORDER)) - STACK_FRAME_OVERHEAD
.align 8
6: .long 0x7fffffff,0xffffffff
+.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space
+ .quad 0 # cr1: primary space segment table
+ .quad .Lduct # cr2: dispatchable unit control table
+ .quad 0 # cr3: instruction authorization
+ .quad 0xffff # cr4: instruction authorization
+ .quad .Lduct # cr5: primary-aste origin
+ .quad 0 # cr6: I/O interrupts
+ .quad 0 # cr7: secondary space segment table
+ .quad 0 # cr8: access registers translation
+ .quad 0 # cr9: tracing off
+ .quad 0 # cr10: tracing off
+ .quad 0 # cr11: tracing off
+ .quad 0 # cr12: tracing off
+ .quad 0 # cr13: home space segment table
+ .quad 0xc0000000 # cr14: machine check handling off
+ .quad .Llinkage_stack # cr15: linkage stack operations
+
+ .section .dma.data,"aw",@progbits
+.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0
+ .long 0,0,0,0,0,0,0,0
+.Llinkage_stack:
+ .long 0,0,0x89000000,0,0,0,0x8a000000,0
+ .align 64
+.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0
+ .align 128
+.Lduald:.rept 8
+ .long 0x80000000,0,0,0 # invalid access-list entries
+ .endr
+ .previous
+
#include "head_kdump.S"
#
+# This program check is active immediately after kernel start
+# and until early_pgm_check_handler is set in kernel/early.c
+# 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)
+ stmg %r0,%r15,__LC_SAVE_AREA_SYNC
+ la %r1,4095
+ stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r1)
+ mvc __LC_GPREGS_SAVE_AREA-4095(128,%r1),__LC_SAVE_AREA_SYNC
+ mvc __LC_PSW_SAVE_AREA-4095(16,%r1),__LC_PGM_OLD_PSW
+ mvc __LC_RETURN_PSW(16),__LC_PGM_OLD_PSW
+ ni __LC_RETURN_PSW,0xfc # remove IO and EX bits
+ ni __LC_RETURN_PSW+1,0xfb # remove MCHK bit
+ oi __LC_RETURN_PSW+1,0x2 # set wait state bit
+ larl %r2,.Lold_psw_disabled_wait
+ stg %r2,__LC_PGM_NEW_PSW+8
+ l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r2)
+ brasl %r14,print_pgm_check_info
+.Lold_psw_disabled_wait:
+ la %r1,4095
+ lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
+ lpswe __LC_RETURN_PSW # disabled wait
+.Ldump_info_stack:
+ .long 0x5000 + PAGE_SIZE - STACK_FRAME_OVERHEAD
+ENDPROC(startup_pgm_check_handler)
+
+#
# params at 10400 (setup.h)
+# Must be keept in sync with struct parmarea in setup.h
#
.org PARMAREA
- .long 0,0 # IPL_DEVICE
- .long 0,0 # INITRD_START
- .long 0,0 # INITRD_SIZE
- .long 0,0 # OLDMEM_BASE
- .long 0,0 # OLDMEM_SIZE
+ .quad 0 # IPL_DEVICE
+ .quad 0 # INITRD_START
+ .quad 0 # INITRD_SIZE
+ .quad 0 # OLDMEM_BASE
+ .quad 0 # OLDMEM_SIZE
+ .quad kernel_version # points to kernel version string
.org COMMAND_LINE
.byte "root=/dev/ram0 ro"
.byte 0
- .org 0x11000
+ .org EARLY_SCCB_OFFSET
+ .fill 4096
+
+ .org HEAD_END
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
new file mode 100644
index 0000000..24ef67e
--- /dev/null
+++ b/arch/s390/boot/ipl_parm.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/ctype.h>
+#include <asm/ebcdic.h>
+#include <asm/sclp.h>
+#include <asm/sections.h>
+#include <asm/boot_data.h>
+#include <asm/facility.h>
+#include <asm/pgtable.h>
+#include <asm/uv.h>
+#include "boot.h"
+
+char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
+struct ipl_parameter_block __bootdata_preserved(ipl_block);
+int __bootdata_preserved(ipl_block_valid);
+
+unsigned long __bootdata(vmalloc_size) = VMALLOC_DEFAULT_SIZE;
+unsigned long __bootdata(memory_end);
+int __bootdata(memory_end_set);
+int __bootdata(noexec_disabled);
+
+int kaslr_enabled __section(.data);
+
+static inline int __diag308(unsigned long subcode, void *addr)
+{
+ register unsigned long _addr asm("0") = (unsigned long)addr;
+ register unsigned long _rc asm("1") = 0;
+ unsigned long reg1, reg2;
+ psw_t old = S390_lowcore.program_new_psw;
+
+ asm volatile(
+ " epsw %0,%1\n"
+ " st %0,%[psw_pgm]\n"
+ " st %1,%[psw_pgm]+4\n"
+ " larl %0,1f\n"
+ " stg %0,%[psw_pgm]+8\n"
+ " diag %[addr],%[subcode],0x308\n"
+ "1: nopr %%r7\n"
+ : "=&d" (reg1), "=&a" (reg2),
+ [psw_pgm] "=Q" (S390_lowcore.program_new_psw),
+ [addr] "+d" (_addr), "+d" (_rc)
+ : [subcode] "d" (subcode)
+ : "cc", "memory");
+ S390_lowcore.program_new_psw = old;
+ return _rc;
+}
+
+void store_ipl_parmblock(void)
+{
+ int rc;
+
+ rc = __diag308(DIAG308_STORE, &ipl_block);
+ if (rc == DIAG308_RC_OK &&
+ ipl_block.hdr.version <= IPL_MAX_SUPPORTED_VERSION)
+ ipl_block_valid = 1;
+}
+
+static size_t scpdata_length(const u8 *buf, size_t count)
+{
+ while (count) {
+ if (buf[count - 1] != '\0' && buf[count - 1] != ' ')
+ break;
+ count--;
+ }
+ return count;
+}
+
+static size_t ipl_block_get_ascii_scpdata(char *dest, size_t size,
+ const struct ipl_parameter_block *ipb)
+{
+ size_t count;
+ size_t i;
+ int has_lowercase;
+
+ count = min(size - 1, scpdata_length(ipb->fcp.scp_data,
+ ipb->fcp.scp_data_len));
+ if (!count)
+ goto out;
+
+ has_lowercase = 0;
+ for (i = 0; i < count; i++) {
+ if (!isascii(ipb->fcp.scp_data[i])) {
+ count = 0;
+ goto out;
+ }
+ if (!has_lowercase && islower(ipb->fcp.scp_data[i]))
+ has_lowercase = 1;
+ }
+
+ if (has_lowercase)
+ memcpy(dest, ipb->fcp.scp_data, count);
+ else
+ for (i = 0; i < count; i++)
+ dest[i] = tolower(ipb->fcp.scp_data[i]);
+out:
+ dest[count] = '\0';
+ return count;
+}
+
+static void append_ipl_block_parm(void)
+{
+ char *parm, *delim;
+ size_t len, rc = 0;
+
+ len = strlen(early_command_line);
+
+ delim = early_command_line + len; /* '\0' character position */
+ parm = early_command_line + len + 1; /* append right after '\0' */
+
+ switch (ipl_block.pb0_hdr.pbt) {
+ case IPL_PBT_CCW:
+ rc = ipl_block_get_ascii_vmparm(
+ parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
+ break;
+ case IPL_PBT_FCP:
+ rc = ipl_block_get_ascii_scpdata(
+ parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
+ break;
+ }
+ if (rc) {
+ if (*parm == '=')
+ memmove(early_command_line, parm + 1, rc);
+ else
+ *delim = ' '; /* replace '\0' with space */
+ }
+}
+
+static inline int has_ebcdic_char(const char *str)
+{
+ int i;
+
+ for (i = 0; str[i]; i++)
+ if (str[i] & 0x80)
+ return 1;
+ return 0;
+}
+
+void setup_boot_command_line(void)
+{
+ COMMAND_LINE[ARCH_COMMAND_LINE_SIZE - 1] = 0;
+ /* convert arch command line to ascii if necessary */
+ if (has_ebcdic_char(COMMAND_LINE))
+ EBCASC(COMMAND_LINE, ARCH_COMMAND_LINE_SIZE);
+ /* copy arch command line */
+ strcpy(early_command_line, strim(COMMAND_LINE));
+
+ /* append IPL PARM data to the boot command line */
+ if (!is_prot_virt_guest() && ipl_block_valid)
+ append_ipl_block_parm();
+}
+
+static void modify_facility(unsigned long nr, bool clear)
+{
+ if (clear)
+ __clear_facility(nr, S390_lowcore.stfle_fac_list);
+ else
+ __set_facility(nr, S390_lowcore.stfle_fac_list);
+}
+
+static void check_cleared_facilities(void)
+{
+ unsigned long als[] = { FACILITIES_ALS };
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(als); i++) {
+ if ((S390_lowcore.stfle_fac_list[i] & als[i]) != als[i]) {
+ sclp_early_printk("Warning: The Linux kernel requires facilities cleared via command line option\n");
+ print_missing_facilities();
+ break;
+ }
+ }
+}
+
+static void modify_fac_list(char *str)
+{
+ unsigned long val, endval;
+ char *endp;
+ bool clear;
+
+ while (*str) {
+ clear = false;
+ if (*str == '!') {
+ clear = true;
+ str++;
+ }
+ val = simple_strtoull(str, &endp, 0);
+ if (str == endp)
+ break;
+ str = endp;
+ if (*str == '-') {
+ str++;
+ endval = simple_strtoull(str, &endp, 0);
+ if (str == endp)
+ break;
+ str = endp;
+ while (val <= endval) {
+ modify_facility(val, clear);
+ val++;
+ }
+ } else {
+ modify_facility(val, clear);
+ }
+ if (*str != ',')
+ break;
+ str++;
+ }
+ check_cleared_facilities();
+}
+
+static char command_line_buf[COMMAND_LINE_SIZE] __section(.data);
+void parse_boot_command_line(void)
+{
+ char *param, *val;
+ bool enabled;
+ char *args;
+ int rc;
+
+ kaslr_enabled = IS_ENABLED(CONFIG_RANDOMIZE_BASE);
+ args = strcpy(command_line_buf, early_command_line);
+ while (*args) {
+ args = next_arg(args, ¶m, &val);
+
+ if (!strcmp(param, "mem") && val) {
+ memory_end = round_down(memparse(val, NULL), PAGE_SIZE);
+ memory_end_set = 1;
+ }
+
+ if (!strcmp(param, "vmalloc") && val)
+ vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE);
+
+ if (!strcmp(param, "noexec")) {
+ rc = kstrtobool(val, &enabled);
+ if (!rc && !enabled)
+ noexec_disabled = 1;
+ }
+
+ if (!strcmp(param, "facilities") && val)
+ modify_fac_list(val);
+
+ if (!strcmp(param, "nokaslr"))
+ kaslr_enabled = 0;
+ }
+}
+
+void setup_memory_end(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+ if (OLDMEM_BASE) {
+ kaslr_enabled = 0;
+ } else if (ipl_block_valid &&
+ ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
+ ipl_block.fcp.opt == IPL_PB0_FCP_OPT_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/ipl_report.c b/arch/s390/boot/ipl_report.c
new file mode 100644
index 0000000..0b49655
--- /dev/null
+++ b/arch/s390/boot/ipl_report.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/ctype.h>
+#include <asm/ebcdic.h>
+#include <asm/sclp.h>
+#include <asm/sections.h>
+#include <asm/boot_data.h>
+#include <uapi/asm/ipl.h>
+#include "boot.h"
+
+int __bootdata_preserved(ipl_secure_flag);
+
+unsigned long __bootdata_preserved(ipl_cert_list_addr);
+unsigned long __bootdata_preserved(ipl_cert_list_size);
+
+unsigned long __bootdata(early_ipl_comp_list_addr);
+unsigned long __bootdata(early_ipl_comp_list_size);
+
+#define for_each_rb_entry(entry, rb) \
+ for (entry = rb->entries; \
+ (void *) entry + sizeof(*entry) <= (void *) rb + rb->len; \
+ entry++)
+
+static inline bool intersects(unsigned long addr0, unsigned long size0,
+ unsigned long addr1, unsigned long size1)
+{
+ return addr0 + size0 > addr1 && addr1 + size1 > addr0;
+}
+
+static unsigned long find_bootdata_space(struct ipl_rb_components *comps,
+ struct ipl_rb_certificates *certs,
+ unsigned long safe_addr)
+{
+ struct ipl_rb_certificate_entry *cert;
+ struct ipl_rb_component_entry *comp;
+ size_t size;
+
+ /*
+ * Find the length for the IPL report boot data
+ */
+ early_ipl_comp_list_size = 0;
+ for_each_rb_entry(comp, comps)
+ early_ipl_comp_list_size += sizeof(*comp);
+ ipl_cert_list_size = 0;
+ for_each_rb_entry(cert, certs)
+ ipl_cert_list_size += sizeof(unsigned int) + cert->len;
+ size = ipl_cert_list_size + early_ipl_comp_list_size;
+
+ /*
+ * Start from safe_addr to find a free memory area large
+ * enough for the IPL report boot data. This area is used
+ * for ipl_cert_list_addr/ipl_cert_list_size and
+ * early_ipl_comp_list_addr/early_ipl_comp_list_size. It must
+ * not overlap with any component or any certificate.
+ */
+repeat:
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
+ intersects(INITRD_START, INITRD_SIZE, safe_addr, size))
+ safe_addr = INITRD_START + INITRD_SIZE;
+ for_each_rb_entry(comp, comps)
+ if (intersects(safe_addr, size, comp->addr, comp->len)) {
+ safe_addr = comp->addr + comp->len;
+ goto repeat;
+ }
+ for_each_rb_entry(cert, certs)
+ if (intersects(safe_addr, size, cert->addr, cert->len)) {
+ safe_addr = cert->addr + cert->len;
+ goto repeat;
+ }
+ early_ipl_comp_list_addr = safe_addr;
+ ipl_cert_list_addr = safe_addr + early_ipl_comp_list_size;
+
+ return safe_addr + size;
+}
+
+static void copy_components_bootdata(struct ipl_rb_components *comps)
+{
+ struct ipl_rb_component_entry *comp, *ptr;
+
+ ptr = (struct ipl_rb_component_entry *) early_ipl_comp_list_addr;
+ for_each_rb_entry(comp, comps)
+ memcpy(ptr++, comp, sizeof(*ptr));
+}
+
+static void copy_certificates_bootdata(struct ipl_rb_certificates *certs)
+{
+ struct ipl_rb_certificate_entry *cert;
+ void *ptr;
+
+ ptr = (void *) ipl_cert_list_addr;
+ for_each_rb_entry(cert, certs) {
+ *(unsigned int *) ptr = cert->len;
+ ptr += sizeof(unsigned int);
+ memcpy(ptr, (void *) cert->addr, cert->len);
+ ptr += cert->len;
+ }
+}
+
+unsigned long read_ipl_report(unsigned long safe_addr)
+{
+ struct ipl_rb_certificates *certs;
+ struct ipl_rb_components *comps;
+ struct ipl_pl_hdr *pl_hdr;
+ struct ipl_rl_hdr *rl_hdr;
+ struct ipl_rb_hdr *rb_hdr;
+ unsigned long tmp;
+ void *rl_end;
+
+ /*
+ * Check if there is a IPL report by looking at the copy
+ * of the IPL parameter information block.
+ */
+ if (!ipl_block_valid ||
+ !(ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR))
+ return safe_addr;
+ ipl_secure_flag = !!(ipl_block.hdr.flags & IPL_PL_FLAG_SIPL);
+ /*
+ * There is an IPL report, to find it load the pointer to the
+ * IPL parameter information block from lowcore and skip past
+ * the IPL parameter list, then align the address to a double
+ * word boundary.
+ */
+ tmp = (unsigned long) S390_lowcore.ipl_parmblock_ptr;
+ pl_hdr = (struct ipl_pl_hdr *) tmp;
+ tmp = (tmp + pl_hdr->len + 7) & -8UL;
+ rl_hdr = (struct ipl_rl_hdr *) tmp;
+ /* Walk through the IPL report blocks in the IPL Report list */
+ certs = NULL;
+ comps = NULL;
+ rl_end = (void *) rl_hdr + rl_hdr->len;
+ rb_hdr = (void *) rl_hdr + sizeof(*rl_hdr);
+ while ((void *) rb_hdr + sizeof(*rb_hdr) < rl_end &&
+ (void *) rb_hdr + rb_hdr->len <= rl_end) {
+
+ switch (rb_hdr->rbt) {
+ case IPL_RBT_CERTIFICATES:
+ certs = (struct ipl_rb_certificates *) rb_hdr;
+ break;
+ case IPL_RBT_COMPONENTS:
+ comps = (struct ipl_rb_components *) rb_hdr;
+ break;
+ default:
+ break;
+ }
+
+ rb_hdr = (void *) rb_hdr + rb_hdr->len;
+ }
+
+ /*
+ * With either the component list or the certificate list
+ * missing the kernel will stay ignorant of secure IPL.
+ */
+ if (!comps || !certs)
+ return safe_addr;
+
+ /*
+ * Copy component and certificate list to a safe area
+ * where the decompressed kernel can find them.
+ */
+ safe_addr = find_bootdata_space(comps, certs, safe_addr);
+ copy_components_bootdata(comps);
+ copy_certificates_bootdata(certs);
+
+ return safe_addr;
+}
diff --git a/arch/s390/boot/ipl_vmparm.c b/arch/s390/boot/ipl_vmparm.c
new file mode 100644
index 0000000..8dacd5f
--- /dev/null
+++ b/arch/s390/boot/ipl_vmparm.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/ipl_vmparm.c"
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
new file mode 100644
index 0000000..5d12352
--- /dev/null
+++ b/arch/s390/boot/kaslr.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2019
+ */
+#include <asm/mem_detect.h>
+#include <asm/pgtable.h>
+#include <asm/cpacf.h>
+#include <asm/timex.h>
+#include <asm/sclp.h>
+#include "compressed/decompressor.h"
+#include "boot.h"
+
+#define PRNG_MODE_TDES 1
+#define PRNG_MODE_SHA512 2
+#define PRNG_MODE_TRNG 3
+
+struct prno_parm {
+ u32 res;
+ u32 reseed_counter;
+ u64 stream_bytes;
+ u8 V[112];
+ u8 C[112];
+};
+
+struct prng_parm {
+ u8 parm_block[32];
+ u32 reseed_counter;
+ u64 byte_counter;
+};
+
+static int check_prng(void)
+{
+ if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG)) {
+ sclp_early_printk("KASLR disabled: CPU has no PRNG\n");
+ return 0;
+ }
+ if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+ return PRNG_MODE_TRNG;
+ if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN))
+ return PRNG_MODE_SHA512;
+ else
+ return PRNG_MODE_TDES;
+}
+
+static unsigned long get_random(unsigned long limit)
+{
+ struct prng_parm prng = {
+ /* initial parameter block for tdes mode, copied from libica */
+ .parm_block = {
+ 0x0F, 0x2B, 0x8E, 0x63, 0x8C, 0x8E, 0xD2, 0x52,
+ 0x64, 0xB7, 0xA0, 0x7B, 0x75, 0x28, 0xB8, 0xF4,
+ 0x75, 0x5F, 0xD2, 0xA6, 0x8D, 0x97, 0x11, 0xFF,
+ 0x49, 0xD8, 0x23, 0xF3, 0x7E, 0x21, 0xEC, 0xA0
+ },
+ };
+ unsigned long seed, random;
+ struct prno_parm prno;
+ __u64 entropy[4];
+ int mode, i;
+
+ mode = check_prng();
+ seed = get_tod_clock_fast();
+ switch (mode) {
+ case PRNG_MODE_TRNG:
+ cpacf_trng(NULL, 0, (u8 *) &random, sizeof(random));
+ break;
+ case PRNG_MODE_SHA512:
+ cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED, &prno, NULL, 0,
+ (u8 *) &seed, sizeof(seed));
+ cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN, &prno, (u8 *) &random,
+ sizeof(random), NULL, 0);
+ break;
+ case PRNG_MODE_TDES:
+ /* add entropy */
+ *(unsigned long *) prng.parm_block ^= seed;
+ for (i = 0; i < 16; i++) {
+ cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block,
+ (char *) entropy, (char *) entropy,
+ sizeof(entropy));
+ memcpy(prng.parm_block, entropy, sizeof(entropy));
+ }
+ random = seed;
+ cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block, (u8 *) &random,
+ (u8 *) &random, sizeof(random));
+ break;
+ default:
+ random = 0;
+ }
+ return random % limit;
+}
+
+unsigned long get_random_base(unsigned long safe_addr)
+{
+ unsigned long memory_limit = memory_end_set ? memory_end : 0;
+ unsigned long base, start, end, kernel_size;
+ unsigned long block_sum, offset;
+ unsigned long kasan_needs;
+ int i;
+
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) {
+ if (safe_addr < INITRD_START + INITRD_SIZE)
+ safe_addr = INITRD_START + INITRD_SIZE;
+ }
+ 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;
+ block_sum = 0;
+ for_each_mem_detect_block(i, &start, &end) {
+ if (memory_limit) {
+ if (start >= memory_limit)
+ break;
+ if (end > memory_limit)
+ end = memory_limit;
+ }
+ if (end - start < kernel_size)
+ continue;
+ block_sum += end - start - kernel_size;
+ }
+ if (!block_sum) {
+ sclp_early_printk("KASLR disabled: not enough memory\n");
+ return 0;
+ }
+
+ base = get_random(block_sum);
+ if (base == 0)
+ return 0;
+ if (base < safe_addr)
+ base = safe_addr;
+ block_sum = offset = 0;
+ for_each_mem_detect_block(i, &start, &end) {
+ if (memory_limit) {
+ if (start >= memory_limit)
+ break;
+ if (end > memory_limit)
+ end = memory_limit;
+ }
+ if (end - start < kernel_size)
+ continue;
+ block_sum += end - start - kernel_size;
+ if (base <= block_sum) {
+ base = start + base - offset;
+ base = ALIGN_DOWN(base, THREAD_SIZE);
+ break;
+ }
+ offset = block_sum;
+ }
+ return base;
+}
diff --git a/arch/s390/boot/machine_kexec_reloc.c b/arch/s390/boot/machine_kexec_reloc.c
new file mode 100644
index 0000000..b7a5d0f
--- /dev/null
+++ b/arch/s390/boot/machine_kexec_reloc.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/machine_kexec_reloc.c"
diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c
new file mode 100644
index 0000000..62e7c13
--- /dev/null
+++ b/arch/s390/boot/mem_detect.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <asm/sclp.h>
+#include <asm/sections.h>
+#include <asm/mem_detect.h>
+#include <asm/sparsemem.h>
+#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 */
+#define ENTRIES_EXTENDED_MAX \
+ (256 * (1020 / 2) * sizeof(struct mem_detect_block))
+
+/*
+ * To avoid corrupting old kernel memory during dump, find lowest memory
+ * chunk possible either right after the kernel end (decompressed kernel) or
+ * after initrd (if it is present and there is no hole between the kernel end
+ * and initrd)
+ */
+static void *mem_detect_alloc_extended(void)
+{
+ unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64));
+
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
+ INITRD_START < offset + ENTRIES_EXTENDED_MAX)
+ offset = ALIGN(INITRD_START + INITRD_SIZE, sizeof(u64));
+
+ return (void *)offset;
+}
+
+static struct mem_detect_block *__get_mem_detect_block_ptr(u32 n)
+{
+ if (n < MEM_INLINED_ENTRIES)
+ return &mem_detect.entries[n];
+ if (unlikely(!mem_detect.entries_extended))
+ mem_detect.entries_extended = mem_detect_alloc_extended();
+ return &mem_detect.entries_extended[n - MEM_INLINED_ENTRIES];
+}
+
+/*
+ * sequential calls to add_mem_detect_block with adjacent memory areas
+ * are merged together into single memory block.
+ */
+void add_mem_detect_block(u64 start, u64 end)
+{
+ struct mem_detect_block *block;
+
+ if (mem_detect.count) {
+ block = __get_mem_detect_block_ptr(mem_detect.count - 1);
+ if (block->end == start) {
+ block->end = end;
+ return;
+ }
+ }
+
+ block = __get_mem_detect_block_ptr(mem_detect.count);
+ block->start = start;
+ block->end = end;
+ mem_detect.count++;
+}
+
+static int __diag260(unsigned long rx1, unsigned long rx2)
+{
+ register unsigned long _rx1 asm("2") = rx1;
+ register unsigned long _rx2 asm("3") = rx2;
+ register unsigned long _ry asm("4") = 0x10; /* storage configuration */
+ int rc = -1; /* fail */
+ unsigned long reg1, reg2;
+ psw_t old = S390_lowcore.program_new_psw;
+
+ asm volatile(
+ " epsw %0,%1\n"
+ " st %0,%[psw_pgm]\n"
+ " st %1,%[psw_pgm]+4\n"
+ " larl %0,1f\n"
+ " stg %0,%[psw_pgm]+8\n"
+ " diag %[rx],%[ry],0x260\n"
+ " ipm %[rc]\n"
+ " srl %[rc],28\n"
+ "1:\n"
+ : "=&d" (reg1), "=&a" (reg2),
+ [psw_pgm] "=Q" (S390_lowcore.program_new_psw),
+ [rc] "+&d" (rc), [ry] "+d" (_ry)
+ : [rx] "d" (_rx1), "d" (_rx2)
+ : "cc", "memory");
+ S390_lowcore.program_new_psw = old;
+ return rc == 0 ? _ry : -1;
+}
+
+static int diag260(void)
+{
+ int rc, i;
+
+ struct {
+ unsigned long start;
+ unsigned long end;
+ } storage_extents[8] __aligned(16); /* VM supports up to 8 extends */
+
+ memset(storage_extents, 0, sizeof(storage_extents));
+ rc = __diag260((unsigned long)storage_extents, sizeof(storage_extents));
+ if (rc == -1)
+ return -1;
+
+ for (i = 0; i < min_t(int, rc, ARRAY_SIZE(storage_extents)); i++)
+ add_mem_detect_block(storage_extents[i].start, storage_extents[i].end + 1);
+ return 0;
+}
+
+static int tprot(unsigned long addr)
+{
+ unsigned long pgm_addr;
+ int rc = -EFAULT;
+ psw_t old = S390_lowcore.program_new_psw;
+
+ S390_lowcore.program_new_psw.mask = __extract_psw();
+ asm volatile(
+ " larl %[pgm_addr],1f\n"
+ " stg %[pgm_addr],%[psw_pgm_addr]\n"
+ " tprot 0(%[addr]),0\n"
+ " ipm %[rc]\n"
+ " srl %[rc],28\n"
+ "1:\n"
+ : [pgm_addr] "=&d"(pgm_addr),
+ [psw_pgm_addr] "=Q"(S390_lowcore.program_new_psw.addr),
+ [rc] "+&d"(rc)
+ : [addr] "a"(addr)
+ : "cc", "memory");
+ S390_lowcore.program_new_psw = old;
+ return rc;
+}
+
+static void search_mem_end(void)
+{
+ unsigned long range = 1 << (MAX_PHYSMEM_BITS - 20); /* in 1MB blocks */
+ unsigned long offset = 0;
+ unsigned long pivot;
+
+ while (range > 1) {
+ range >>= 1;
+ pivot = offset + range;
+ if (!tprot(pivot << 20))
+ offset = pivot;
+ }
+
+ add_mem_detect_block(0, (offset + 1) << 20);
+}
+
+void detect_memory(void)
+{
+ sclp_early_get_memsize(&max_physmem_end);
+
+ if (!sclp_early_read_storage_info()) {
+ mem_detect.info_source = MEM_DETECT_SCLP_STOR_INFO;
+ return;
+ }
+
+ if (!diag260()) {
+ mem_detect.info_source = MEM_DETECT_DIAG260;
+ return;
+ }
+
+ if (max_physmem_end) {
+ add_mem_detect_block(0, max_physmem_end);
+ mem_detect.info_source = MEM_DETECT_SCLP_READ_INFO;
+ return;
+ }
+
+ search_mem_end();
+ mem_detect.info_source = MEM_DETECT_BIN_SEARCH;
+ max_physmem_end = get_mem_detect_end();
+}
diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c
new file mode 100644
index 0000000..83b5b79
--- /dev/null
+++ b/arch/s390/boot/pgm_check_info.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/lowcore.h>
+#include <asm/sclp.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 *__add_val_as_hex(char *dst, const unsigned char *src, size_t count)
+{
+ while (count--)
+ dst = hex_byte_pack(dst, *src++);
+ return dst;
+}
+
+static char *add_str(char *dst, char *src)
+{
+ strcpy(dst, src);
+ return dst + strlen(dst);
+}
+
+void print_pgm_check_info(void)
+{
+ 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;
+ char *p;
+
+ add_str(buf, "Linux version ");
+ strlcat(buf, kernel_version, sizeof(buf));
+ sclp_early_printk(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);
+
+ 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");
+ 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);
+
+ 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);
+ }
+}
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
new file mode 100644
index 0000000..5367950
--- /dev/null
+++ b/arch/s390/boot/startup.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/string.h>
+#include <linux/elf.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/kexec.h>
+#include <asm/sclp.h>
+#include <asm/diag.h>
+#include <asm/uv.h>
+#include "compressed/decompressor.h"
+#include "boot.h"
+
+extern char __boot_data_start[], __boot_data_end[];
+extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
+unsigned long __bootdata_preserved(__kaslr_offset);
+
+/*
+ * Some code and data needs to stay below 2 GB, even when the kernel would be
+ * relocated above 2 GB, because it has to use 31 bit addresses.
+ * Such code and data is part of the .dma section, and its location is passed
+ * over to the decompressed / relocated kernel via the .boot.preserved.data
+ * section.
+ */
+extern char _sdma[], _edma[];
+extern char _stext_dma[], _etext_dma[];
+extern struct exception_table_entry _start_dma_ex_table[];
+extern struct exception_table_entry _stop_dma_ex_table[];
+unsigned long __bootdata_preserved(__sdma) = __pa(&_sdma);
+unsigned long __bootdata_preserved(__edma) = __pa(&_edma);
+unsigned long __bootdata_preserved(__stext_dma) = __pa(&_stext_dma);
+unsigned long __bootdata_preserved(__etext_dma) = __pa(&_etext_dma);
+struct exception_table_entry *
+ __bootdata_preserved(__start_dma_ex_table) = _start_dma_ex_table;
+struct exception_table_entry *
+ __bootdata_preserved(__stop_dma_ex_table) = _stop_dma_ex_table;
+
+int _diag210_dma(struct diag210 *addr);
+int _diag26c_dma(void *req, void *resp, enum diag26c_sc subcode);
+int _diag14_dma(unsigned long rx, unsigned long ry1, unsigned long subcode);
+void _diag0c_dma(struct hypfs_diag0c_entry *entry);
+void _diag308_reset_dma(void);
+struct diag_ops __bootdata_preserved(diag_dma_ops) = {
+ .diag210 = _diag210_dma,
+ .diag26c = _diag26c_dma,
+ .diag14 = _diag14_dma,
+ .diag0c = _diag0c_dma,
+ .diag308_reset = _diag308_reset_dma
+};
+static struct diag210 _diag210_tmp_dma __section(".dma.data");
+struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
+void _swsusp_reset_dma(void);
+unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma);
+
+void error(char *x)
+{
+ sclp_early_printk("\n\n");
+ sclp_early_printk(x);
+ sclp_early_printk("\n\n -- System halted");
+
+ disabled_wait();
+}
+
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
+unsigned long mem_safe_offset(void)
+{
+ return vmlinux.default_lma + vmlinux.image_size + vmlinux.bss_size;
+}
+#endif
+
+static void rescue_initrd(unsigned long addr)
+{
+ if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD))
+ return;
+ if (!INITRD_START || !INITRD_SIZE)
+ return;
+ if (addr <= INITRD_START)
+ return;
+ memmove((void *)addr, (void *)INITRD_START, INITRD_SIZE);
+ INITRD_START = addr;
+}
+
+static void copy_bootdata(void)
+{
+ if (__boot_data_end - __boot_data_start != vmlinux.bootdata_size)
+ error(".boot.data section size mismatch");
+ memcpy((void *)vmlinux.bootdata_off, __boot_data_start, vmlinux.bootdata_size);
+ if (__boot_data_preserved_end - __boot_data_preserved_start != vmlinux.bootdata_preserved_size)
+ error(".boot.preserved.data section size mismatch");
+ memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size);
+}
+
+static void handle_relocs(unsigned long offset)
+{
+ Elf64_Rela *rela_start, *rela_end, *rela;
+ int r_type, r_sym, rc;
+ Elf64_Addr loc, val;
+ Elf64_Sym *dynsym;
+
+ rela_start = (Elf64_Rela *) vmlinux.rela_dyn_start;
+ rela_end = (Elf64_Rela *) vmlinux.rela_dyn_end;
+ dynsym = (Elf64_Sym *) vmlinux.dynsym_start;
+ for (rela = rela_start; rela < rela_end; rela++) {
+ loc = rela->r_offset + offset;
+ val = rela->r_addend;
+ r_sym = ELF64_R_SYM(rela->r_info);
+ if (r_sym) {
+ if (dynsym[r_sym].st_shndx != SHN_UNDEF)
+ val += dynsym[r_sym].st_value + offset;
+ } else {
+ /*
+ * 0 == undefined symbol table index (STN_UNDEF),
+ * used for R_390_RELATIVE, only add KASLR offset
+ */
+ val += offset;
+ }
+ r_type = ELF64_R_TYPE(rela->r_info);
+ rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0);
+ if (rc)
+ error("Unknown relocation type");
+ }
+}
+
+static void clear_bss_section(void)
+{
+ memset((void *)vmlinux.default_lma + vmlinux.image_size, 0, vmlinux.bss_size);
+}
+
+void startup_kernel(void)
+{
+ unsigned long random_lma;
+ unsigned long safe_addr;
+ void *img;
+
+ store_ipl_parmblock();
+ safe_addr = mem_safe_offset();
+ safe_addr = read_ipl_report(safe_addr);
+ uv_query_info();
+ rescue_initrd(safe_addr);
+ sclp_early_read_info();
+ setup_boot_command_line();
+ parse_boot_command_line();
+ setup_memory_end();
+ detect_memory();
+
+ random_lma = __kaslr_offset = 0;
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) {
+ random_lma = get_random_base(safe_addr);
+ if (random_lma) {
+ __kaslr_offset = random_lma - vmlinux.default_lma;
+ img = (void *)vmlinux.default_lma;
+ vmlinux.default_lma += __kaslr_offset;
+ vmlinux.entry += __kaslr_offset;
+ vmlinux.bootdata_off += __kaslr_offset;
+ vmlinux.bootdata_preserved_off += __kaslr_offset;
+ vmlinux.rela_dyn_start += __kaslr_offset;
+ vmlinux.rela_dyn_end += __kaslr_offset;
+ vmlinux.dynsym_start += __kaslr_offset;
+ }
+ }
+
+ if (!IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) {
+ img = decompress_kernel();
+ memmove((void *)vmlinux.default_lma, img, vmlinux.image_size);
+ } else if (__kaslr_offset)
+ memcpy((void *)vmlinux.default_lma, img, vmlinux.image_size);
+
+ clear_bss_section();
+ copy_bootdata();
+ if (IS_ENABLED(CONFIG_RELOCATABLE))
+ handle_relocs(__kaslr_offset);
+
+ if (__kaslr_offset) {
+ /* Clear non-relocated kernel */
+ if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED))
+ memset(img, 0, vmlinux.image_size);
+ }
+ vmlinux.entry();
+}
diff --git a/arch/s390/boot/string.c b/arch/s390/boot/string.c
new file mode 100644
index 0000000..b11e810
--- /dev/null
+++ b/arch/s390/boot/string.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#undef CONFIG_KASAN
+#include "../lib/string.c"
+
+int strncmp(const char *cs, const char *ct, size_t count)
+{
+ unsigned char c1, c2;
+
+ while (count) {
+ c1 = *cs++;
+ c2 = *ct++;
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (!c1)
+ break;
+ count--;
+ }
+ return 0;
+}
+
+char *skip_spaces(const char *str)
+{
+ while (isspace(*str))
+ ++str;
+ return (char *)str;
+}
+
+char *strim(char *s)
+{
+ size_t size;
+ char *end;
+
+ size = strlen(s);
+ if (!size)
+ return s;
+
+ end = s + size - 1;
+ while (end >= s && isspace(*end))
+ end--;
+ *(end + 1) = '\0';
+
+ return skip_spaces(s);
+}
+
+/* Works only for digits and letters, but small and fast */
+#define TOLOWER(x) ((x) | 0x20)
+
+static unsigned int simple_guess_base(const char *cp)
+{
+ if (cp[0] == '0') {
+ if (TOLOWER(cp[1]) == 'x' && isxdigit(cp[2]))
+ return 16;
+ else
+ return 8;
+ } else {
+ return 10;
+ }
+}
+
+/**
+ * simple_strtoull - convert a string to an unsigned long long
+ * @cp: The start of the string
+ * @endp: A pointer to the end of the parsed string will be placed here
+ * @base: The number base to use
+ */
+
+unsigned long long simple_strtoull(const char *cp, char **endp,
+ unsigned int base)
+{
+ unsigned long long result = 0;
+
+ if (!base)
+ base = simple_guess_base(cp);
+
+ if (base == 16 && cp[0] == '0' && TOLOWER(cp[1]) == 'x')
+ cp += 2;
+
+ while (isxdigit(*cp)) {
+ unsigned int value;
+
+ value = isdigit(*cp) ? *cp - '0' : TOLOWER(*cp) - 'a' + 10;
+ if (value >= base)
+ break;
+ result = result * base + value;
+ cp++;
+ }
+ if (endp)
+ *endp = (char *)cp;
+
+ return result;
+}
+
+long simple_strtol(const char *cp, char **endp, unsigned int base)
+{
+ if (*cp == '-')
+ return -simple_strtoull(cp + 1, endp, base);
+
+ return simple_strtoull(cp, endp, base);
+}
+
+int kstrtobool(const char *s, bool *res)
+{
+ if (!s)
+ return -EINVAL;
+
+ switch (s[0]) {
+ case 'y':
+ case 'Y':
+ case '1':
+ *res = true;
+ return 0;
+ case 'n':
+ case 'N':
+ case '0':
+ *res = false;
+ return 0;
+ case 'o':
+ case 'O':
+ switch (s[1]) {
+ case 'n':
+ case 'N':
+ *res = true;
+ return 0;
+ case 'f':
+ case 'F':
+ *res = false;
+ return 0;
+ default:
+ break;
+ }
+ default:
+ break;
+ }
+
+ return -EINVAL;
+}
diff --git a/arch/s390/boot/text_dma.S b/arch/s390/boot/text_dma.S
new file mode 100644
index 0000000..9715715
--- /dev/null
+++ b/arch/s390/boot/text_dma.S
@@ -0,0 +1,184 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Code that needs to run below 2 GB.
+ *
+ * Copyright IBM Corp. 2019
+ */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/sigp.h>
+
+#ifdef CC_USING_EXPOLINE
+ .pushsection .dma.text.__s390_indirect_jump_r14,"axG"
+__dma__s390_indirect_jump_r14:
+ larl %r1,0f
+ ex 0,0(%r1)
+ j .
+0: br %r14
+ .popsection
+#endif
+
+ .section .dma.text,"ax"
+/*
+ * Simplified version of expoline thunk. The normal thunks can not be used here,
+ * because they might be more than 2 GB away, and not reachable by the relative
+ * branch. No comdat, exrl, etc. optimizations used here, because it only
+ * affects a few functions that are not performance-relevant.
+ */
+ .macro BR_EX_DMA_r14
+#ifdef CC_USING_EXPOLINE
+ jg __dma__s390_indirect_jump_r14
+#else
+ br %r14
+#endif
+ .endm
+
+/*
+ * int _diag14_dma(unsigned long rx, unsigned long ry1, unsigned long subcode)
+ */
+ENTRY(_diag14_dma)
+ lgr %r1,%r2
+ lgr %r2,%r3
+ lgr %r3,%r4
+ lhi %r5,-EIO
+ sam31
+ diag %r1,%r2,0x14
+.Ldiag14_ex:
+ ipm %r5
+ srl %r5,28
+.Ldiag14_fault:
+ sam64
+ lgfr %r2,%r5
+ BR_EX_DMA_r14
+ EX_TABLE_DMA(.Ldiag14_ex, .Ldiag14_fault)
+ENDPROC(_diag14_dma)
+
+/*
+ * int _diag210_dma(struct diag210 *addr)
+ */
+ENTRY(_diag210_dma)
+ lgr %r1,%r2
+ lhi %r2,-1
+ sam31
+ diag %r1,%r0,0x210
+.Ldiag210_ex:
+ ipm %r2
+ srl %r2,28
+.Ldiag210_fault:
+ sam64
+ lgfr %r2,%r2
+ BR_EX_DMA_r14
+ EX_TABLE_DMA(.Ldiag210_ex, .Ldiag210_fault)
+ENDPROC(_diag210_dma)
+
+/*
+ * int _diag26c_dma(void *req, void *resp, enum diag26c_sc subcode)
+ */
+ENTRY(_diag26c_dma)
+ lghi %r5,-EOPNOTSUPP
+ sam31
+ diag %r2,%r4,0x26c
+.Ldiag26c_ex:
+ sam64
+ lgfr %r2,%r5
+ BR_EX_DMA_r14
+ EX_TABLE_DMA(.Ldiag26c_ex, .Ldiag26c_ex)
+ENDPROC(_diag26c_dma)
+
+/*
+ * void _diag0c_dma(struct hypfs_diag0c_entry *entry)
+ */
+ENTRY(_diag0c_dma)
+ sam31
+ diag %r2,%r2,0x0c
+ sam64
+ BR_EX_DMA_r14
+ENDPROC(_diag0c_dma)
+
+/*
+ * void _swsusp_reset_dma(void)
+ */
+ENTRY(_swsusp_reset_dma)
+ larl %r1,restart_entry
+ larl %r2,.Lrestart_diag308_psw
+ og %r1,0(%r2)
+ stg %r1,0(%r0)
+ lghi %r0,0
+ diag %r0,%r0,0x308
+restart_entry:
+ lhi %r1,1
+ sigp %r1,%r0,SIGP_SET_ARCHITECTURE
+ sam64
+ BR_EX_DMA_r14
+ENDPROC(_swsusp_reset_dma)
+
+/*
+ * void _diag308_reset_dma(void)
+ *
+ * Calls diag 308 subcode 1 and continues execution
+ */
+ENTRY(_diag308_reset_dma)
+ larl %r4,.Lctlregs # Save control registers
+ stctg %c0,%c15,0(%r4)
+ lg %r2,0(%r4) # Disable lowcore protection
+ nilh %r2,0xefff
+ larl %r4,.Lctlreg0
+ stg %r2,0(%r4)
+ lctlg %c0,%c0,0(%r4)
+ larl %r4,.Lfpctl # Floating point control register
+ stfpc 0(%r4)
+ larl %r4,.Lprefix # Save prefix register
+ stpx 0(%r4)
+ larl %r4,.Lprefix_zero # Set prefix register to 0
+ spx 0(%r4)
+ larl %r4,.Lcontinue_psw # Save PSW flags
+ epsw %r2,%r3
+ stm %r2,%r3,0(%r4)
+ larl %r4,restart_part2 # Setup restart PSW at absolute 0
+ larl %r3,.Lrestart_diag308_psw
+ og %r4,0(%r3) # Save PSW
+ lghi %r3,0
+ sturg %r4,%r3 # Use sturg, because of large pages
+ lghi %r1,1
+ lghi %r0,0
+ diag %r0,%r1,0x308
+restart_part2:
+ lhi %r0,0 # Load r0 with zero
+ lhi %r1,2 # Use mode 2 = ESAME (dump)
+ sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to ESAME mode
+ sam64 # Switch to 64 bit addressing mode
+ larl %r4,.Lctlregs # Restore control registers
+ lctlg %c0,%c15,0(%r4)
+ larl %r4,.Lfpctl # Restore floating point ctl register
+ lfpc 0(%r4)
+ larl %r4,.Lprefix # Restore prefix register
+ spx 0(%r4)
+ larl %r4,.Lcontinue_psw # Restore PSW flags
+ lpswe 0(%r4)
+.Lcontinue:
+ BR_EX_DMA_r14
+ENDPROC(_diag308_reset_dma)
+
+ .section .dma.data,"aw",@progbits
+.align 8
+.Lrestart_diag308_psw:
+ .long 0x00080000,0x80000000
+
+.align 8
+.Lcontinue_psw:
+ .quad 0,.Lcontinue
+
+.align 8
+.Lctlreg0:
+ .quad 0
+.Lctlregs:
+ .rept 16
+ .quad 0
+ .endr
+.Lfpctl:
+ .long 0
+.Lprefix:
+ .long 0
+.Lprefix_zero:
+ .long 0
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
new file mode 100644
index 0000000..ed007f4
--- /dev/null
+++ b/arch/s390/boot/uv.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <asm/uv.h>
+#include <asm/facility.h>
+#include <asm/sections.h>
+
+int __bootdata_preserved(prot_virt_guest);
+
+void uv_query_info(void)
+{
+ struct uv_cb_qui uvcb = {
+ .header.cmd = UVC_CMD_QUI,
+ .header.len = sizeof(uvcb)
+ };
+
+ if (!test_facility(158))
+ return;
+
+ if (uv_call(0, (uint64_t)&uvcb))
+ return;
+
+ if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
+ test_bit_inv(BIT_UVC_CMD_REMOVE_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list))
+ prot_virt_guest = 1;
+}
diff --git a/arch/s390/boot/version.c b/arch/s390/boot/version.c
new file mode 100644
index 0000000..d32e58b
--- /dev/null
+++ b/arch/s390/boot/version.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <generated/utsrelease.h>
+#include <generated/compile.h>
+#include "boot.h"
+
+const char kernel_version[] = UTS_RELEASE
+ " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") " UTS_VERSION;
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 941d8cc..38d6403 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -3,6 +3,7 @@
CONFIG_AUDIT=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
@@ -18,52 +19,73 @@
CONFIG_CFS_BANDWIDTH=y
CONFIG_RT_GROUP_SCHED=y
CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_HUGETLB=y
CONFIG_CPUSETS=y
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_BPF=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
+CONFIG_LIVEPATCH=y
+CONFIG_TUNE_ZEC12=y
+CONFIG_NR_CPUS=512
+CONFIG_NUMA=y
+CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_SIG=y
+CONFIG_EXPOLINE=y
+CONFIG_EXPOLINE_AUTO=y
+CONFIG_CHSC_SCH=y
+CONFIG_VFIO_CCW=m
+CONFIG_VFIO_AP=m
+CONFIG_CRASH_DUMP=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
+CONFIG_CMM=m
+CONFIG_APPLDATA_BASE=y
+CONFIG_KVM=m
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
CONFIG_OPROFILE=m
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
CONFIG_STATIC_KEYS_SELFTEST=y
+CONFIG_REFCOUNT_FULL=y
+CONFIG_LOCK_EVENT_COUNTS=y
CONFIG_MODULES=y
CONFIG_MODULE_FORCE_LOAD=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG_SHA256=y
+CONFIG_UNUSED_SYMBOLS=y
CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
-CONFIG_BLK_WBT_SQ=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_IOCOST=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_BSD_DISKLABEL=y
CONFIG_MINIX_SUBPARTITION=y
CONFIG_SOLARIS_X86_PARTITION=y
CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_CFQ_GROUP_IOSCHED=y
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=512
-CONFIG_NUMA=y
-CONFIG_PREEMPT=y
-CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
+CONFIG_IOSCHED_BFQ=y
+CONFIG_BFQ_GROUP_IOSCHED=y
+CONFIG_BINFMT_MISC=m
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
@@ -79,14 +101,8 @@
CONFIG_ZSMALLOC_STAT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_PCI=y
-CONFIG_PCI_DEBUG=y
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_S390=y
-CONFIG_CHSC_SCH=y
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
+CONFIG_PERCPU_STATS=y
+CONFIG_GUP_BENCHMARK=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_PACKET_DIAG=m
@@ -115,9 +131,6 @@
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
CONFIG_TCP_CONG_ADVANCED=y
@@ -133,10 +146,6 @@
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_SIT=m
CONFIG_IPV6_GRE=m
@@ -161,8 +170,6 @@
CONFIG_NF_CT_NETLINK=m
CONFIG_NF_CT_NETLINK_TIMEOUT=m
CONFIG_NF_TABLES=m
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
CONFIG_NFT_CT=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
@@ -260,11 +267,8 @@
CONFIG_IP_VS_NQ=m
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NF_TABLES_IPV4=y
-CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=y
-CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_MATCH_ECN=m
@@ -283,10 +287,7 @@
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_TABLES_IPV6=y
-CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -305,7 +306,7 @@
CONFIG_IP6_NF_SECURITY=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=y
+CONFIG_NF_TABLES_BRIDGE=m
CONFIG_RDS=m
CONFIG_RDS_RDMA=m
CONFIG_RDS_TCP=m
@@ -365,13 +366,18 @@
CONFIG_NET_ACT_CSUM=m
CONFIG_DNS_RESOLVER=y
CONFIG_OPENVSWITCH=m
+CONFIG_VSOCKETS=m
+CONFIG_VIRTIO_VSOCKETS=m
CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
+# CONFIG_NET_DROP_MONITOR is not set
+CONFIG_PCI=y
+CONFIG_PCI_DEBUG=y
+CONFIG_HOTPLUG_PCI=y
+CONFIG_HOTPLUG_PCI_S390=y
CONFIG_DEVTMPFS=y
-CONFIG_DMA_CMA=y
-CONFIG_CMA_SIZE_MBYTES=0
CONFIG_CONNECTOR=y
CONFIG_ZRAM=m
CONFIG_BLK_DEV_LOOP=m
@@ -389,7 +395,6 @@
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
CONFIG_BLK_DEV_SR=m
CONFIG_CHR_DEV_SG=y
CONFIG_CHR_DEV_SCH=m
@@ -409,17 +414,20 @@
CONFIG_SCSI_DH_HP_SW=m
CONFIG_SCSI_DH_EMC=m
CONFIG_SCSI_DH_ALUA=m
-CONFIG_SCSI_OSD_INITIATOR=m
-CONFIG_SCSI_OSD_ULD=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
CONFIG_MD_LINEAR=m
CONFIG_MD_MULTIPATH=m
CONFIG_MD_FAULTY=m
+CONFIG_MD_CLUSTER=m
+CONFIG_BCACHE=m
CONFIG_BLK_DEV_DM=m
+CONFIG_DM_UNSTRIPED=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
+CONFIG_DM_CLONE=m
CONFIG_DM_MIRROR=m
CONFIG_DM_LOG_USERSPACE=m
CONFIG_DM_RAID=m
@@ -431,6 +439,7 @@
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
+CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
CONFIG_DM_SWITCH=m
CONFIG_NETDEVICES=y
CONFIG_BONDING=m
@@ -439,60 +448,124 @@
CONFIG_IFB=m
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
-CONFIG_VXLAN=m
CONFIG_TUN=m
CONFIG_VETH=m
CONFIG_VIRTIO_NET=m
CONFIG_NLMON=m
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ADAPTEC is not set
+# CONFIG_NET_VENDOR_AGERE is not set
+# CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_ALTEON is not set
+# CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ATHEROS is not set
+# CONFIG_NET_VENDOR_AURORA is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
+# CONFIG_NET_VENDOR_CADENCE is not set
+# CONFIG_NET_VENDOR_CAVIUM is not set
# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CISCO is not set
+# CONFIG_NET_VENDOR_CORTINA is not set
+# CONFIG_NET_VENDOR_DEC is not set
+# CONFIG_NET_VENDOR_DLINK is not set
+# CONFIG_NET_VENDOR_EMULEX is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
+# CONFIG_NET_VENDOR_GOOGLE is not set
+# CONFIG_NET_VENDOR_HP is not set
+# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
CONFIG_MLX5_CORE_EN=y
+# CONFIG_MLXFW is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROCHIP is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
+# CONFIG_NET_VENDOR_MYRI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETERION is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
+# CONFIG_NET_VENDOR_NVIDIA is not set
+# CONFIG_NET_VENDOR_OKI is not set
+# CONFIG_NET_VENDOR_PACKET_ENGINES is not set
+# CONFIG_NET_VENDOR_PENSANDO is not set
+# CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
+# CONFIG_NET_VENDOR_ROCKER is not set
+# CONFIG_NET_VENDOR_SAMSUNG is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
+# CONFIG_NET_VENDOR_SILAN is not set
+# CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_SOCIONEXT is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
+# CONFIG_NET_VENDOR_TEHUTI is not set
+# CONFIG_NET_VENDOR_TI is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_FILTER=y
CONFIG_PPP_MPPE=m
+CONFIG_PPP_MULTILINK=y
CONFIG_PPPOE=m
CONFIG_PPTP=m
CONFIG_PPPOL2TP=m
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
+CONFIG_ISM=m
CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
+CONFIG_NULL_TTY=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
+CONFIG_PPS=m
+# CONFIG_PTP_1588_CLOCK is not set
# CONFIG_HWMON is not set
CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
-CONFIG_DRM=y
-CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
# CONFIG_HID is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_ACCESS=m
CONFIG_MLX4_INFINIBAND=m
CONFIG_MLX5_INFINIBAND=m
+CONFIG_SYNC_FILE=y
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
+CONFIG_VFIO_MDEV=m
+CONFIG_VFIO_MDEV_DEVICE=m
CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
+CONFIG_S390_CCW_IOMMU=y
+CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
-CONFIG_EXT4_ENCRYPTION=y
CONFIG_JBD2_DEBUG=y
CONFIG_JFS_FS=m
CONFIG_JFS_POSIX_ACL=y
@@ -509,9 +582,13 @@
CONFIG_BTRFS_FS=y
CONFIG_BTRFS_FS_POSIX_ACL=y
CONFIG_BTRFS_DEBUG=y
+CONFIG_BTRFS_ASSERT=y
CONFIG_NILFS2_FS=m
CONFIG_FS_DAX=y
CONFIG_EXPORTFS_BLOCK_OPS=y
+CONFIG_FS_ENCRYPTION=y
+CONFIG_FS_VERITY=y
+CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y
CONFIG_FANOTIFY=y
CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
@@ -521,6 +598,7 @@
CONFIG_AUTOFS4_FS=m
CONFIG_FUSE_FS=y
CONFIG_CUSE=m
+CONFIG_VIRTIO_FS=m
CONFIG_OVERLAY_FS=m
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
@@ -541,8 +619,10 @@
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
CONFIG_SQUASHFS_XATTR=y
+CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_LZO=y
CONFIG_SQUASHFS_XZ=y
+CONFIG_SQUASHFS_ZSTD=y
CONFIG_ROMFS_FS=m
CONFIG_NFS_FS=m
CONFIG_NFS_V3_ACL=y
@@ -553,7 +633,6 @@
CONFIG_NFSD_V4=y
CONFIG_NFSD_V4_SECURITY_LABEL=y
CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
CONFIG_CIFS_STATS2=y
CONFIG_CIFS_WEAK_PW_HASH=y
CONFIG_CIFS_UPCALL=y
@@ -569,18 +648,112 @@
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_UTF8=m
CONFIG_DLM=m
+CONFIG_UNICODE=y
+CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
+CONFIG_ENCRYPTED_KEYS=m
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_FORTIFY_SOURCE=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_LOCKDOWN_LSM=y
+CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
+CONFIG_INTEGRITY_SIGNATURE=y
+CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_IMA=y
+CONFIG_IMA_DEFAULT_HASH_SHA256=y
+CONFIG_IMA_WRITE_POLICY=y
+CONFIG_IMA_APPRAISE=y
+CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
+CONFIG_CRYPTO_USER=m
+# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_PCRYPT=m
+CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
+CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_XCBC=m
+CONFIG_CRYPTO_VMAC=m
+CONFIG_CRYPTO_CRC32=m
+CONFIG_CRYPTO_XXHASH=m
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_RMD128=m
+CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_RMD256=m
+CONFIG_CRYPTO_RMD320=m
+CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
+CONFIG_CRYPTO_TGR192=m
+CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAMELLIA=m
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_FCRYPT=m
+CONFIG_CRYPTO_KHAZAD=m
+CONFIG_CRYPTO_SALSA20=m
+CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_842=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_USER_API_SKCIPHER=m
+CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
+CONFIG_CRYPTO_STATS=y
+CONFIG_ZCRYPT=m
+CONFIG_PKEY=m
+CONFIG_CRYPTO_PAES_S390=m
+CONFIG_CRYPTO_SHA1_S390=m
+CONFIG_CRYPTO_SHA256_S390=m
+CONFIG_CRYPTO_SHA512_S390=m
+CONFIG_CRYPTO_SHA3_256_S390=m
+CONFIG_CRYPTO_SHA3_512_S390=m
+CONFIG_CRYPTO_DES_S390=m
+CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_GHASH_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CORDIC=m
+CONFIG_CRC32_SELFTEST=y
+CONFIG_CRC4=m
+CONFIG_CRC7=m
+CONFIG_CRC8=m
+CONFIG_RANDOM32_SELFTEST=y
+CONFIG_DMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
+CONFIG_DMA_API_DEBUG=y
+CONFIG_STRING_SELFTEST=y
CONFIG_PRINTK_TIME=y
CONFIG_DYNAMIC_DEBUG=y
CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_GDB_SCRIPTS=y
CONFIG_FRAME_WARN=1024
-CONFIG_READABLE_ASM=y
-CONFIG_UNUSED_SYMBOLS=y
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_PAGE_OWNER=y
CONFIG_DEBUG_RODATA_TEST=y
CONFIG_DEBUG_OBJECTS=y
CONFIG_DEBUG_OBJECTS_SELFTEST=y
@@ -615,7 +788,6 @@
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=300
CONFIG_NOTIFIER_ERROR_INJECTION=m
-CONFIG_PM_NOTIFIER_ERROR_INJECT=m
CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
CONFIG_FAULT_INJECTION=y
CONFIG_FAILSLAB=y
@@ -634,7 +806,6 @@
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_HIST_TRIGGERS=y
-CONFIG_DMA_API_DEBUG=y
CONFIG_LKDTM=m
CONFIG_TEST_LIST_SORT=y
CONFIG_TEST_SORT=y
@@ -646,85 +817,3 @@
CONFIG_TEST_BPF=m
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_S390_PTDUMP=y
-CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
-CONFIG_ENCRYPTED_KEYS=m
-CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
-CONFIG_FORTIFY_SOURCE=y
-CONFIG_SECURITY_SELINUX=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
-CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_INTEGRITY_SIGNATURE=y
-CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
-CONFIG_IMA=y
-CONFIG_IMA_DEFAULT_HASH_SHA256=y
-CONFIG_IMA_WRITE_POLICY=y
-CONFIG_IMA_APPRAISE=y
-CONFIG_CRYPTO_DH=m
-CONFIG_CRYPTO_ECDH=m
-CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
-CONFIG_CRYPTO_PCRYPT=m
-CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_MCRYPTD=m
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_CHACHA20POLY1305=m
-CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_KEYWRAP=m
-CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
-CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_AES_TI=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
-CONFIG_CRYPTO_CAST5=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SEED=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_842=m
-CONFIG_CRYPTO_LZ4=m
-CONFIG_CRYPTO_LZ4HC=m
-CONFIG_CRYPTO_ANSI_CPRNG=m
-CONFIG_CRYPTO_USER_API_HASH=m
-CONFIG_CRYPTO_USER_API_SKCIPHER=m
-CONFIG_CRYPTO_USER_API_RNG=m
-CONFIG_CRYPTO_USER_API_AEAD=m
-CONFIG_ZCRYPT=m
-CONFIG_PKEY=m
-CONFIG_CRYPTO_PAES_S390=m
-CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
-CONFIG_CRYPTO_SHA512_S390=m
-CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_PKCS7_MESSAGE_PARSER=y
-CONFIG_SYSTEM_TRUSTED_KEYRING=y
-CONFIG_CRC7=m
-CONFIG_CRC8=m
-CONFIG_RANDOM32_SELFTEST=y
-CONFIG_CORDIC=m
-CONFIG_CMM=m
-CONFIG_APPLDATA_BASE=y
-CONFIG_KVM=m
-CONFIG_KVM_S390_UCONTROL=y
-CONFIG_VHOST_NET=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/defconfig
similarity index 80%
rename from arch/s390/configs/performance_defconfig
rename to arch/s390/configs/defconfig
index eb6f75f..25f7998 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/defconfig
@@ -12,30 +12,52 @@
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_NUMA_BALANCING=y
-# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
CONFIG_BLK_CGROUP=y
CONFIG_CFS_BANDWIDTH=y
CONFIG_RT_GROUP_SCHED=y
CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_HUGETLB=y
CONFIG_CPUSETS=y
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_BPF=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
+CONFIG_LIVEPATCH=y
+CONFIG_TUNE_ZEC12=y
+CONFIG_NR_CPUS=512
+CONFIG_NUMA=y
+# CONFIG_NUMA_EMU is not set
+CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_SIG=y
+CONFIG_EXPOLINE=y
+CONFIG_EXPOLINE_AUTO=y
+CONFIG_CHSC_SCH=y
+CONFIG_VFIO_CCW=m
+CONFIG_VFIO_AP=m
+CONFIG_CRASH_DUMP=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
+CONFIG_CMM=m
+CONFIG_APPLDATA_BASE=y
+CONFIG_KVM=m
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
CONFIG_OPROFILE=m
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
@@ -45,26 +67,21 @@
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG=y
CONFIG_MODULE_SIG_SHA256=y
-CONFIG_BLK_DEV_INTEGRITY=y
+CONFIG_UNUSED_SYMBOLS=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
-CONFIG_BLK_WBT_SQ=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_IOCOST=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_BSD_DISKLABEL=y
CONFIG_MINIX_SUBPARTITION=y
CONFIG_SOLARIS_X86_PARTITION=y
CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_CFQ_GROUP_IOSCHED=y
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=512
-CONFIG_NUMA=y
-CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
+CONFIG_IOSCHED_BFQ=y
+CONFIG_BFQ_GROUP_IOSCHED=y
+CONFIG_BINFMT_MISC=m
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
@@ -78,13 +95,8 @@
CONFIG_ZSMALLOC_STAT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_PCI=y
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_S390=y
-CONFIG_CHSC_SCH=y
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
+CONFIG_PERCPU_STATS=y
+CONFIG_GUP_BENCHMARK=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_PACKET_DIAG=m
@@ -113,9 +125,6 @@
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
CONFIG_TCP_CONG_ADVANCED=y
@@ -131,10 +140,6 @@
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_SIT=m
CONFIG_IPV6_GRE=m
@@ -159,8 +164,6 @@
CONFIG_NF_CT_NETLINK=m
CONFIG_NF_CT_NETLINK_TIMEOUT=m
CONFIG_NF_TABLES=m
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
CONFIG_NFT_CT=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
@@ -258,11 +261,8 @@
CONFIG_IP_VS_NQ=m
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NF_TABLES_IPV4=y
-CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=y
-CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_MATCH_ECN=m
@@ -281,10 +281,7 @@
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_TABLES_IPV6=y
-CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -303,7 +300,7 @@
CONFIG_IP6_NF_SECURITY=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=y
+CONFIG_NF_TABLES_BRIDGE=m
CONFIG_RDS=m
CONFIG_RDS_RDMA=m
CONFIG_RDS_TCP=m
@@ -362,13 +359,18 @@
CONFIG_NET_ACT_CSUM=m
CONFIG_DNS_RESOLVER=y
CONFIG_OPENVSWITCH=m
+CONFIG_VSOCKETS=m
+CONFIG_VIRTIO_VSOCKETS=m
CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
+# CONFIG_NET_DROP_MONITOR is not set
+CONFIG_PCI=y
+CONFIG_HOTPLUG_PCI=y
+CONFIG_HOTPLUG_PCI_S390=y
+CONFIG_UEVENT_HELPER=y
CONFIG_DEVTMPFS=y
-CONFIG_DMA_CMA=y
-CONFIG_CMA_SIZE_MBYTES=0
CONFIG_CONNECTOR=y
CONFIG_ZRAM=m
CONFIG_BLK_DEV_LOOP=m
@@ -377,6 +379,7 @@
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=32768
+# CONFIG_BLK_DEV_XPRAM is not set
CONFIG_VIRTIO_BLK=y
CONFIG_BLK_DEV_RBD=m
CONFIG_BLK_DEV_NVME=m
@@ -386,7 +389,6 @@
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
CONFIG_BLK_DEV_SR=m
CONFIG_CHR_DEV_SG=y
CONFIG_CHR_DEV_SCH=m
@@ -406,17 +408,20 @@
CONFIG_SCSI_DH_HP_SW=m
CONFIG_SCSI_DH_EMC=m
CONFIG_SCSI_DH_ALUA=m
-CONFIG_SCSI_OSD_INITIATOR=m
-CONFIG_SCSI_OSD_ULD=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
CONFIG_MD_LINEAR=m
CONFIG_MD_MULTIPATH=m
CONFIG_MD_FAULTY=m
+CONFIG_MD_CLUSTER=m
+CONFIG_BCACHE=m
CONFIG_BLK_DEV_DM=m
+CONFIG_DM_UNSTRIPED=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
+CONFIG_DM_CLONE=m
CONFIG_DM_MIRROR=m
CONFIG_DM_LOG_USERSPACE=m
CONFIG_DM_RAID=m
@@ -428,7 +433,9 @@
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
+CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
CONFIG_DM_SWITCH=m
+CONFIG_DM_INTEGRITY=m
CONFIG_NETDEVICES=y
CONFIG_BONDING=m
CONFIG_DUMMY=m
@@ -436,60 +443,124 @@
CONFIG_IFB=m
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
-CONFIG_VXLAN=m
CONFIG_TUN=m
CONFIG_VETH=m
CONFIG_VIRTIO_NET=m
CONFIG_NLMON=m
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ADAPTEC is not set
+# CONFIG_NET_VENDOR_AGERE is not set
+# CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_ALTEON is not set
+# CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ATHEROS is not set
+# CONFIG_NET_VENDOR_AURORA is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
+# CONFIG_NET_VENDOR_CADENCE is not set
+# CONFIG_NET_VENDOR_CAVIUM is not set
# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CISCO is not set
+# CONFIG_NET_VENDOR_CORTINA is not set
+# CONFIG_NET_VENDOR_DEC is not set
+# CONFIG_NET_VENDOR_DLINK is not set
+# CONFIG_NET_VENDOR_EMULEX is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
+# CONFIG_NET_VENDOR_GOOGLE is not set
+# CONFIG_NET_VENDOR_HP is not set
+# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
CONFIG_MLX5_CORE_EN=y
+# CONFIG_MLXFW is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROCHIP is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
+# CONFIG_NET_VENDOR_MYRI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETERION is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
+# CONFIG_NET_VENDOR_NVIDIA is not set
+# CONFIG_NET_VENDOR_OKI is not set
+# CONFIG_NET_VENDOR_PACKET_ENGINES is not set
+# CONFIG_NET_VENDOR_PENSANDO is not set
+# CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
+# CONFIG_NET_VENDOR_ROCKER is not set
+# CONFIG_NET_VENDOR_SAMSUNG is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
+# CONFIG_NET_VENDOR_SILAN is not set
+# CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_SOCIONEXT is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
+# CONFIG_NET_VENDOR_TEHUTI is not set
+# CONFIG_NET_VENDOR_TI is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_FILTER=y
CONFIG_PPP_MPPE=m
+CONFIG_PPP_MULTILINK=y
CONFIG_PPPOE=m
CONFIG_PPTP=m
CONFIG_PPPOL2TP=m
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
+CONFIG_ISM=m
CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
+CONFIG_NULL_TTY=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
+# CONFIG_PTP_1588_CLOCK is not set
# CONFIG_HWMON is not set
CONFIG_WATCHDOG=y
+CONFIG_WATCHDOG_CORE=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
-CONFIG_DRM=y
-CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FB=y
CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
# CONFIG_HID is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_ACCESS=m
CONFIG_MLX4_INFINIBAND=m
CONFIG_MLX5_INFINIBAND=m
+CONFIG_SYNC_FILE=y
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
+CONFIG_VFIO_MDEV=m
+CONFIG_VFIO_MDEV_DEVICE=m
CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
+CONFIG_S390_CCW_IOMMU=y
+CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
-CONFIG_EXT4_ENCRYPTION=y
CONFIG_JBD2_DEBUG=y
CONFIG_JFS_FS=m
CONFIG_JFS_POSIX_ACL=y
@@ -507,6 +578,9 @@
CONFIG_NILFS2_FS=m
CONFIG_FS_DAX=y
CONFIG_EXPORTFS_BLOCK_OPS=y
+CONFIG_FS_ENCRYPTION=y
+CONFIG_FS_VERITY=y
+CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y
CONFIG_FANOTIFY=y
CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
@@ -515,6 +589,7 @@
CONFIG_AUTOFS4_FS=m
CONFIG_FUSE_FS=y
CONFIG_CUSE=m
+CONFIG_VIRTIO_FS=m
CONFIG_OVERLAY_FS=m
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
@@ -535,8 +610,10 @@
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
CONFIG_SQUASHFS_XATTR=y
+CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_LZO=y
CONFIG_SQUASHFS_XZ=y
+CONFIG_SQUASHFS_ZSTD=y
CONFIG_ROMFS_FS=m
CONFIG_NFS_FS=m
CONFIG_NFS_V3_ACL=y
@@ -547,7 +624,6 @@
CONFIG_NFSD_V4=y
CONFIG_NFSD_V4_SECURITY_LABEL=y
CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
CONFIG_CIFS_STATS2=y
CONFIG_CIFS_WEAK_PW_HASH=y
CONFIG_CIFS_UPCALL=y
@@ -563,13 +639,103 @@
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_UTF8=m
CONFIG_DLM=m
+CONFIG_UNICODE=y
+CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
+CONFIG_ENCRYPTED_KEYS=m
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_LOCKDOWN_LSM=y
+CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
+CONFIG_INTEGRITY_SIGNATURE=y
+CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_IMA=y
+CONFIG_IMA_DEFAULT_HASH_SHA256=y
+CONFIG_IMA_WRITE_POLICY=y
+CONFIG_IMA_APPRAISE=y
+CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
+CONFIG_CRYPTO_FIPS=y
+CONFIG_CRYPTO_USER=m
+# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_PCRYPT=m
+CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
+CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_OFB=m
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_XCBC=m
+CONFIG_CRYPTO_VMAC=m
+CONFIG_CRYPTO_CRC32=m
+CONFIG_CRYPTO_XXHASH=m
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_RMD128=m
+CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_RMD256=m
+CONFIG_CRYPTO_RMD320=m
+CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
+CONFIG_CRYPTO_TGR192=m
+CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAMELLIA=m
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_FCRYPT=m
+CONFIG_CRYPTO_KHAZAD=m
+CONFIG_CRYPTO_SALSA20=m
+CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_842=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_USER_API_SKCIPHER=m
+CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
+CONFIG_CRYPTO_STATS=y
+CONFIG_ZCRYPT=m
+CONFIG_PKEY=m
+CONFIG_CRYPTO_PAES_S390=m
+CONFIG_CRYPTO_SHA1_S390=m
+CONFIG_CRYPTO_SHA256_S390=m
+CONFIG_CRYPTO_SHA512_S390=m
+CONFIG_CRYPTO_SHA3_256_S390=m
+CONFIG_CRYPTO_SHA3_512_S390=m
+CONFIG_CRYPTO_DES_S390=m
+CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_GHASH_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CORDIC=m
+CONFIG_CRC4=m
+CONFIG_CRC7=m
+CONFIG_CRC8=m
+CONFIG_DMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_GDB_SCRIPTS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_FRAME_WARN=1024
-CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_PANIC_ON_OOPS=y
@@ -588,82 +754,3 @@
CONFIG_TEST_BPF=m
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_S390_PTDUMP=y
-CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
-CONFIG_ENCRYPTED_KEYS=m
-CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
-CONFIG_SECURITY_SELINUX=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
-CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_INTEGRITY_SIGNATURE=y
-CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
-CONFIG_IMA=y
-CONFIG_IMA_DEFAULT_HASH_SHA256=y
-CONFIG_IMA_WRITE_POLICY=y
-CONFIG_IMA_APPRAISE=y
-CONFIG_CRYPTO_FIPS=y
-CONFIG_CRYPTO_DH=m
-CONFIG_CRYPTO_ECDH=m
-CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
-CONFIG_CRYPTO_PCRYPT=m
-CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_MCRYPTD=m
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_CHACHA20POLY1305=m
-CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_KEYWRAP=m
-CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
-CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_AES_TI=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
-CONFIG_CRYPTO_CAST5=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SEED=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_842=m
-CONFIG_CRYPTO_LZ4=m
-CONFIG_CRYPTO_LZ4HC=m
-CONFIG_CRYPTO_ANSI_CPRNG=m
-CONFIG_CRYPTO_USER_API_HASH=m
-CONFIG_CRYPTO_USER_API_SKCIPHER=m
-CONFIG_CRYPTO_USER_API_RNG=m
-CONFIG_CRYPTO_USER_API_AEAD=m
-CONFIG_ZCRYPT=m
-CONFIG_PKEY=m
-CONFIG_CRYPTO_PAES_S390=m
-CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
-CONFIG_CRYPTO_SHA512_S390=m
-CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_CRC7=m
-CONFIG_CRC8=m
-CONFIG_CORDIC=m
-CONFIG_CMM=m
-CONFIG_APPLDATA_BASE=y
-CONFIG_KVM=m
-CONFIG_KVM_S390_UCONTROL=y
-CONFIG_VHOST_NET=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 7dc7f58..20c51e5 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -1,30 +1,35 @@
# CONFIG_SWAP is not set
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+# CONFIG_CPU_ISOLATION is not set
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
# CONFIG_COMPAT_BRK is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
-CONFIG_DEFAULT_DEADLINE=y
CONFIG_TUNE_ZEC12=y
# CONFIG_COMPAT is not set
CONFIG_NR_CPUS=2
-# CONFIG_HOTPLUG_CPU is not set
CONFIG_HZ_100=y
# CONFIG_ARCH_RANDOM is not set
-# CONFIG_COMPACTION is not set
-# CONFIG_MIGRATION is not set
-# CONFIG_BOUNCE is not set
-# CONFIG_CHECK_STACK is not set
+# CONFIG_RELOCATABLE is not set
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
CONFIG_CRASH_DUMP=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_SECCOMP is not set
+# CONFIG_PFAULT is not set
+# CONFIG_S390_HYPFS_FS is not set
+# CONFIG_VIRTUALIZATION is not set
+# CONFIG_S390_GUEST is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_IBM_PARTITION=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_COMPACTION is not set
+# CONFIG_MIGRATION is not set
+# CONFIG_BOUNCE is not set
CONFIG_NET=y
# CONFIG_IUCV is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_BLK_DEV_RAM=y
# CONFIG_BLK_DEV_XPRAM is not set
@@ -44,7 +49,6 @@
# CONFIG_HVC_IUCV is not set
# CONFIG_HW_RANDOM_S390 is not set
CONFIG_RAW_DRIVER=y
-# CONFIG_SCLP_ASYNC is not set
# CONFIG_HMC_DRV is not set
# CONFIG_S390_TAPE is not set
# CONFIG_VMCP is not set
@@ -57,6 +61,7 @@
CONFIG_CONFIGFS_FS=y
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_LSM="yama,loadpin,safesetid,integrity"
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_FS=y
@@ -65,7 +70,4 @@
# CONFIG_SCHED_DEBUG is not set
CONFIG_RCU_CPU_STALL_TIMEOUT=60
# CONFIG_FTRACE is not set
-# CONFIG_PFAULT is not set
-# CONFIG_S390_HYPFS_FS is not set
-# CONFIG_VIRTUALIZATION is not set
-# CONFIG_S390_GUEST is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile
index a51010e..12889d4 100644
--- a/arch/s390/crypto/Makefile
+++ b/arch/s390/crypto/Makefile
@@ -6,6 +6,8 @@
obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o sha_common.o
obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o sha_common.o
obj-$(CONFIG_CRYPTO_SHA512_S390) += sha512_s390.o sha_common.o
+obj-$(CONFIG_CRYPTO_SHA3_256_S390) += sha3_256_s390.o sha_common.o
+obj-$(CONFIG_CRYPTO_SHA3_512_S390) += sha3_512_s390.o sha_common.o
obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o
obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o
obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index c54cb26..9803e96 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -27,14 +27,14 @@
#include <linux/module.h>
#include <linux/cpufeature.h>
#include <linux/init.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
#include <linux/fips.h>
#include <linux/string.h>
#include <crypto/xts.h>
#include <asm/cpacf.h>
static u8 *ctrblk;
-static DEFINE_SPINLOCK(ctrblk_lock);
+static DEFINE_MUTEX(ctrblk_lock);
static cpacf_mask_t km_functions, kmc_functions, kmctr_functions,
kma_functions;
@@ -44,7 +44,7 @@
int key_len;
unsigned long fc;
union {
- struct crypto_skcipher *blk;
+ struct crypto_sync_skcipher *blk;
struct crypto_cipher *cip;
} fallback;
};
@@ -54,7 +54,7 @@
u8 pcc_key[32];
int key_len;
unsigned long fc;
- struct crypto_skcipher *fallback;
+ struct crypto_sync_skcipher *fallback;
};
struct gcm_sg_walk {
@@ -108,7 +108,7 @@
return 0;
}
-static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+static void crypto_aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
@@ -119,7 +119,7 @@
cpacf_km(sctx->fc, &sctx->key, out, in, AES_BLOCK_SIZE);
}
-static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+static void crypto_aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
@@ -137,7 +137,7 @@
struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
sctx->fallback.cip = crypto_alloc_cipher(name, 0,
- CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+ CRYPTO_ALG_NEED_FALLBACK);
if (IS_ERR(sctx->fallback.cip)) {
pr_err("Allocating AES fallback algorithm %s failed\n",
@@ -172,8 +172,8 @@
.cia_min_keysize = AES_MIN_KEY_SIZE,
.cia_max_keysize = AES_MAX_KEY_SIZE,
.cia_setkey = aes_set_key,
- .cia_encrypt = aes_encrypt,
- .cia_decrypt = aes_decrypt,
+ .cia_encrypt = crypto_aes_encrypt,
+ .cia_decrypt = crypto_aes_decrypt,
}
}
};
@@ -184,14 +184,15 @@
struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
unsigned int ret;
- crypto_skcipher_clear_flags(sctx->fallback.blk, CRYPTO_TFM_REQ_MASK);
- crypto_skcipher_set_flags(sctx->fallback.blk, tfm->crt_flags &
+ crypto_sync_skcipher_clear_flags(sctx->fallback.blk,
+ CRYPTO_TFM_REQ_MASK);
+ crypto_sync_skcipher_set_flags(sctx->fallback.blk, tfm->crt_flags &
CRYPTO_TFM_REQ_MASK);
- ret = crypto_skcipher_setkey(sctx->fallback.blk, key, len);
+ ret = crypto_sync_skcipher_setkey(sctx->fallback.blk, key, len);
tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
- tfm->crt_flags |= crypto_skcipher_get_flags(sctx->fallback.blk) &
+ tfm->crt_flags |= crypto_sync_skcipher_get_flags(sctx->fallback.blk) &
CRYPTO_TFM_RES_MASK;
return ret;
@@ -204,9 +205,9 @@
unsigned int ret;
struct crypto_blkcipher *tfm = desc->tfm;
struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm);
- SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
+ SYNC_SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
- skcipher_request_set_tfm(req, sctx->fallback.blk);
+ skcipher_request_set_sync_tfm(req, sctx->fallback.blk);
skcipher_request_set_callback(req, desc->flags, NULL, NULL);
skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
@@ -223,9 +224,9 @@
unsigned int ret;
struct crypto_blkcipher *tfm = desc->tfm;
struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm);
- SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
+ SYNC_SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
- skcipher_request_set_tfm(req, sctx->fallback.blk);
+ skcipher_request_set_sync_tfm(req, sctx->fallback.blk);
skcipher_request_set_callback(req, desc->flags, NULL, NULL);
skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
@@ -306,8 +307,7 @@
const char *name = tfm->__crt_alg->cra_name;
struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
- sctx->fallback.blk = crypto_alloc_skcipher(name, 0,
- CRYPTO_ALG_ASYNC |
+ sctx->fallback.blk = crypto_alloc_sync_skcipher(name, 0,
CRYPTO_ALG_NEED_FALLBACK);
if (IS_ERR(sctx->fallback.blk)) {
@@ -323,7 +323,7 @@
{
struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
- crypto_free_skcipher(sctx->fallback.blk);
+ crypto_free_sync_skcipher(sctx->fallback.blk);
}
static struct crypto_alg ecb_aes_alg = {
@@ -453,14 +453,15 @@
struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
unsigned int ret;
- crypto_skcipher_clear_flags(xts_ctx->fallback, CRYPTO_TFM_REQ_MASK);
- crypto_skcipher_set_flags(xts_ctx->fallback, tfm->crt_flags &
+ crypto_sync_skcipher_clear_flags(xts_ctx->fallback,
+ CRYPTO_TFM_REQ_MASK);
+ crypto_sync_skcipher_set_flags(xts_ctx->fallback, tfm->crt_flags &
CRYPTO_TFM_REQ_MASK);
- ret = crypto_skcipher_setkey(xts_ctx->fallback, key, len);
+ ret = crypto_sync_skcipher_setkey(xts_ctx->fallback, key, len);
tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
- tfm->crt_flags |= crypto_skcipher_get_flags(xts_ctx->fallback) &
+ tfm->crt_flags |= crypto_sync_skcipher_get_flags(xts_ctx->fallback) &
CRYPTO_TFM_RES_MASK;
return ret;
@@ -472,10 +473,10 @@
{
struct crypto_blkcipher *tfm = desc->tfm;
struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm);
- SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
+ SYNC_SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
unsigned int ret;
- skcipher_request_set_tfm(req, xts_ctx->fallback);
+ skcipher_request_set_sync_tfm(req, xts_ctx->fallback);
skcipher_request_set_callback(req, desc->flags, NULL, NULL);
skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
@@ -491,10 +492,10 @@
{
struct crypto_blkcipher *tfm = desc->tfm;
struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm);
- SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
+ SYNC_SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
unsigned int ret;
- skcipher_request_set_tfm(req, xts_ctx->fallback);
+ skcipher_request_set_sync_tfm(req, xts_ctx->fallback);
skcipher_request_set_callback(req, desc->flags, NULL, NULL);
skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
@@ -511,7 +512,7 @@
unsigned long fc;
int err;
- err = xts_check_key(tfm, in_key, key_len);
+ err = xts_fallback_setkey(tfm, in_key, key_len);
if (err)
return err;
@@ -528,7 +529,7 @@
/* Check if the function code is available */
xts_ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
if (!xts_ctx->fc)
- return xts_fallback_setkey(tfm, in_key, key_len);
+ return 0;
/* Split the XTS key into the two subkeys */
key_len = key_len / 2;
@@ -585,7 +586,10 @@
struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
- if (unlikely(!xts_ctx->fc))
+ if (!nbytes)
+ return -EINVAL;
+
+ if (unlikely(!xts_ctx->fc || (nbytes % XTS_BLOCK_SIZE) != 0))
return xts_fallback_encrypt(desc, dst, src, nbytes);
blkcipher_walk_init(&walk, dst, src, nbytes);
@@ -599,7 +603,10 @@
struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
- if (unlikely(!xts_ctx->fc))
+ if (!nbytes)
+ return -EINVAL;
+
+ if (unlikely(!xts_ctx->fc || (nbytes % XTS_BLOCK_SIZE) != 0))
return xts_fallback_decrypt(desc, dst, src, nbytes);
blkcipher_walk_init(&walk, dst, src, nbytes);
@@ -611,8 +618,7 @@
const char *name = tfm->__crt_alg->cra_name;
struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
- xts_ctx->fallback = crypto_alloc_skcipher(name, 0,
- CRYPTO_ALG_ASYNC |
+ xts_ctx->fallback = crypto_alloc_sync_skcipher(name, 0,
CRYPTO_ALG_NEED_FALLBACK);
if (IS_ERR(xts_ctx->fallback)) {
@@ -627,7 +633,7 @@
{
struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
- crypto_free_skcipher(xts_ctx->fallback);
+ crypto_free_sync_skcipher(xts_ctx->fallback);
}
static struct crypto_alg xts_aes_alg = {
@@ -698,7 +704,7 @@
unsigned int n, nbytes;
int ret, locked;
- locked = spin_trylock(&ctrblk_lock);
+ locked = mutex_trylock(&ctrblk_lock);
ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
@@ -716,7 +722,7 @@
ret = blkcipher_walk_done(desc, walk, nbytes - n);
}
if (locked)
- spin_unlock(&ctrblk_lock);
+ mutex_unlock(&ctrblk_lock);
/*
* final block may be < AES_BLOCK_SIZE, copy only nbytes
*/
@@ -826,19 +832,45 @@
return 0;
}
-static void gcm_sg_walk_start(struct gcm_sg_walk *gw, struct scatterlist *sg,
- unsigned int len)
+static void gcm_walk_start(struct gcm_sg_walk *gw, struct scatterlist *sg,
+ unsigned int len)
{
memset(gw, 0, sizeof(*gw));
gw->walk_bytes_remain = len;
scatterwalk_start(&gw->walk, sg);
}
-static int gcm_sg_walk_go(struct gcm_sg_walk *gw, unsigned int minbytesneeded)
+static inline unsigned int _gcm_sg_clamp_and_map(struct gcm_sg_walk *gw)
+{
+ struct scatterlist *nextsg;
+
+ gw->walk_bytes = scatterwalk_clamp(&gw->walk, gw->walk_bytes_remain);
+ while (!gw->walk_bytes) {
+ nextsg = sg_next(gw->walk.sg);
+ if (!nextsg)
+ return 0;
+ scatterwalk_start(&gw->walk, nextsg);
+ gw->walk_bytes = scatterwalk_clamp(&gw->walk,
+ gw->walk_bytes_remain);
+ }
+ gw->walk_ptr = scatterwalk_map(&gw->walk);
+ return gw->walk_bytes;
+}
+
+static inline void _gcm_sg_unmap_and_advance(struct gcm_sg_walk *gw,
+ unsigned int nbytes)
+{
+ gw->walk_bytes_remain -= nbytes;
+ scatterwalk_unmap(&gw->walk);
+ scatterwalk_advance(&gw->walk, nbytes);
+ scatterwalk_done(&gw->walk, 0, gw->walk_bytes_remain);
+ gw->walk_ptr = NULL;
+}
+
+static int gcm_in_walk_go(struct gcm_sg_walk *gw, unsigned int minbytesneeded)
{
int n;
- /* minbytesneeded <= AES_BLOCK_SIZE */
if (gw->buf_bytes && gw->buf_bytes >= minbytesneeded) {
gw->ptr = gw->buf;
gw->nbytes = gw->buf_bytes;
@@ -851,13 +883,11 @@
goto out;
}
- gw->walk_bytes = scatterwalk_clamp(&gw->walk, gw->walk_bytes_remain);
- if (!gw->walk_bytes) {
- scatterwalk_start(&gw->walk, sg_next(gw->walk.sg));
- gw->walk_bytes = scatterwalk_clamp(&gw->walk,
- gw->walk_bytes_remain);
+ if (!_gcm_sg_clamp_and_map(gw)) {
+ gw->ptr = NULL;
+ gw->nbytes = 0;
+ goto out;
}
- gw->walk_ptr = scatterwalk_map(&gw->walk);
if (!gw->buf_bytes && gw->walk_bytes >= minbytesneeded) {
gw->ptr = gw->walk_ptr;
@@ -869,51 +899,90 @@
n = min(gw->walk_bytes, AES_BLOCK_SIZE - gw->buf_bytes);
memcpy(gw->buf + gw->buf_bytes, gw->walk_ptr, n);
gw->buf_bytes += n;
- gw->walk_bytes_remain -= n;
- scatterwalk_unmap(&gw->walk);
- scatterwalk_advance(&gw->walk, n);
- scatterwalk_done(&gw->walk, 0, gw->walk_bytes_remain);
-
+ _gcm_sg_unmap_and_advance(gw, n);
if (gw->buf_bytes >= minbytesneeded) {
gw->ptr = gw->buf;
gw->nbytes = gw->buf_bytes;
goto out;
}
-
- gw->walk_bytes = scatterwalk_clamp(&gw->walk,
- gw->walk_bytes_remain);
- if (!gw->walk_bytes) {
- scatterwalk_start(&gw->walk, sg_next(gw->walk.sg));
- gw->walk_bytes = scatterwalk_clamp(&gw->walk,
- gw->walk_bytes_remain);
+ if (!_gcm_sg_clamp_and_map(gw)) {
+ gw->ptr = NULL;
+ gw->nbytes = 0;
+ goto out;
}
- gw->walk_ptr = scatterwalk_map(&gw->walk);
}
out:
return gw->nbytes;
}
-static void gcm_sg_walk_done(struct gcm_sg_walk *gw, unsigned int bytesdone)
+static int gcm_out_walk_go(struct gcm_sg_walk *gw, unsigned int minbytesneeded)
{
- int n;
+ if (gw->walk_bytes_remain == 0) {
+ gw->ptr = NULL;
+ gw->nbytes = 0;
+ goto out;
+ }
+ if (!_gcm_sg_clamp_and_map(gw)) {
+ gw->ptr = NULL;
+ gw->nbytes = 0;
+ goto out;
+ }
+
+ if (gw->walk_bytes >= minbytesneeded) {
+ gw->ptr = gw->walk_ptr;
+ gw->nbytes = gw->walk_bytes;
+ goto out;
+ }
+
+ scatterwalk_unmap(&gw->walk);
+ gw->walk_ptr = NULL;
+
+ gw->ptr = gw->buf;
+ gw->nbytes = sizeof(gw->buf);
+
+out:
+ return gw->nbytes;
+}
+
+static int gcm_in_walk_done(struct gcm_sg_walk *gw, unsigned int bytesdone)
+{
if (gw->ptr == NULL)
- return;
+ return 0;
if (gw->ptr == gw->buf) {
- n = gw->buf_bytes - bytesdone;
+ int n = gw->buf_bytes - bytesdone;
if (n > 0) {
memmove(gw->buf, gw->buf + bytesdone, n);
- gw->buf_bytes -= n;
+ gw->buf_bytes = n;
} else
gw->buf_bytes = 0;
- } else {
- gw->walk_bytes_remain -= bytesdone;
- scatterwalk_unmap(&gw->walk);
- scatterwalk_advance(&gw->walk, bytesdone);
- scatterwalk_done(&gw->walk, 0, gw->walk_bytes_remain);
- }
+ } else
+ _gcm_sg_unmap_and_advance(gw, bytesdone);
+
+ return bytesdone;
+}
+
+static int gcm_out_walk_done(struct gcm_sg_walk *gw, unsigned int bytesdone)
+{
+ int i, n;
+
+ if (gw->ptr == NULL)
+ return 0;
+
+ if (gw->ptr == gw->buf) {
+ for (i = 0; i < bytesdone; i += n) {
+ if (!_gcm_sg_clamp_and_map(gw))
+ return i;
+ n = min(gw->walk_bytes, bytesdone - i);
+ memcpy(gw->walk_ptr, gw->buf + i, n);
+ _gcm_sg_unmap_and_advance(gw, n);
+ }
+ } else
+ _gcm_sg_unmap_and_advance(gw, bytesdone);
+
+ return bytesdone;
}
static int gcm_aes_crypt(struct aead_request *req, unsigned int flags)
@@ -926,7 +995,7 @@
unsigned int pclen = req->cryptlen;
int ret = 0;
- unsigned int len, in_bytes, out_bytes,
+ unsigned int n, len, in_bytes, out_bytes,
min_bytes, bytes, aad_bytes, pc_bytes;
struct gcm_sg_walk gw_in, gw_out;
u8 tag[GHASH_DIGEST_SIZE];
@@ -963,14 +1032,14 @@
*(u32 *)(param.j0 + ivsize) = 1;
memcpy(param.k, ctx->key, ctx->key_len);
- gcm_sg_walk_start(&gw_in, req->src, len);
- gcm_sg_walk_start(&gw_out, req->dst, len);
+ gcm_walk_start(&gw_in, req->src, len);
+ gcm_walk_start(&gw_out, req->dst, len);
do {
min_bytes = min_t(unsigned int,
aadlen > 0 ? aadlen : pclen, AES_BLOCK_SIZE);
- in_bytes = gcm_sg_walk_go(&gw_in, min_bytes);
- out_bytes = gcm_sg_walk_go(&gw_out, min_bytes);
+ in_bytes = gcm_in_walk_go(&gw_in, min_bytes);
+ out_bytes = gcm_out_walk_go(&gw_out, min_bytes);
bytes = min(in_bytes, out_bytes);
if (aadlen + pclen <= bytes) {
@@ -997,8 +1066,11 @@
gw_in.ptr + aad_bytes, pc_bytes,
gw_in.ptr, aad_bytes);
- gcm_sg_walk_done(&gw_in, aad_bytes + pc_bytes);
- gcm_sg_walk_done(&gw_out, aad_bytes + pc_bytes);
+ n = aad_bytes + pc_bytes;
+ if (gcm_in_walk_done(&gw_in, n) != n)
+ return -ENOMEM;
+ if (gcm_out_walk_done(&gw_out, n) != n)
+ return -ENOMEM;
aadlen -= aad_bytes;
pclen -= pc_bytes;
} while (aadlen + pclen > 0);
diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.S
index 2bf01ba..0099044 100644
--- a/arch/s390/crypto/crc32be-vx.S
+++ b/arch/s390/crypto/crc32be-vx.S
@@ -207,5 +207,6 @@
.Ldone:
VLGVF %r2,%v2,3
BR_EX %r14
+ENDPROC(crc32_be_vgfm_16)
.previous
diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.S
index 7d6f568..71caf0f 100644
--- a/arch/s390/crypto/crc32le-vx.S
+++ b/arch/s390/crypto/crc32le-vx.S
@@ -105,13 +105,14 @@
ENTRY(crc32_le_vgfm_16)
larl %r5,.Lconstants_CRC_32_LE
j crc32_le_vgfm_generic
+ENDPROC(crc32_le_vgfm_16)
ENTRY(crc32c_le_vgfm_16)
larl %r5,.Lconstants_CRC_32C_LE
j crc32_le_vgfm_generic
+ENDPROC(crc32c_le_vgfm_16)
-
-crc32_le_vgfm_generic:
+ENTRY(crc32_le_vgfm_generic)
/* Load CRC-32 constants */
VLM CONST_PERM_LE2BE,CONST_CRC_POLY,0,%r5
@@ -267,5 +268,6 @@
.Ldone:
VLGVF %r2,%v2,2
BR_EX %r14
+ENDPROC(crc32_le_vgfm_generic)
.previous
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 5346b5a..439b100 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -14,14 +14,15 @@
#include <linux/cpufeature.h>
#include <linux/crypto.h>
#include <linux/fips.h>
+#include <linux/mutex.h>
#include <crypto/algapi.h>
-#include <crypto/des.h>
+#include <crypto/internal/des.h>
#include <asm/cpacf.h>
#define DES3_KEY_SIZE (3 * DES_KEY_SIZE)
static u8 *ctrblk;
-static DEFINE_SPINLOCK(ctrblk_lock);
+static DEFINE_MUTEX(ctrblk_lock);
static cpacf_mask_t km_functions, kmc_functions, kmctr_functions;
@@ -34,27 +35,24 @@
unsigned int key_len)
{
struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm);
- u32 tmp[DES_EXPKEY_WORDS];
+ int err;
- /* check for weak keys */
- if (!des_ekey(tmp, key) &&
- (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
- tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
- return -EINVAL;
- }
+ err = crypto_des_verify_key(tfm, key);
+ if (err)
+ return err;
memcpy(ctx->key, key, key_len);
return 0;
}
-static void des_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+static void s390_des_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm);
cpacf_km(CPACF_KM_DEA, ctx->key, out, in, DES_BLOCK_SIZE);
}
-static void des_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+static void s390_des_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -75,8 +73,8 @@
.cia_min_keysize = DES_KEY_SIZE,
.cia_max_keysize = DES_KEY_SIZE,
.cia_setkey = des_setkey,
- .cia_encrypt = des_encrypt,
- .cia_decrypt = des_decrypt,
+ .cia_encrypt = s390_des_encrypt,
+ .cia_decrypt = s390_des_decrypt,
}
}
};
@@ -224,24 +222,11 @@
unsigned int key_len)
{
struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm);
+ int err;
- if (!(crypto_memneq(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) &&
- crypto_memneq(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2],
- DES_KEY_SIZE)) &&
- (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
- tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
- return -EINVAL;
- }
-
- /* in fips mode, ensure k1 != k2 and k2 != k3 and k1 != k3 */
- if (fips_enabled &&
- !(crypto_memneq(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) &&
- crypto_memneq(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2],
- DES_KEY_SIZE) &&
- crypto_memneq(key, &key[DES_KEY_SIZE * 2], DES_KEY_SIZE))) {
- tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
- return -EINVAL;
- }
+ err = crypto_des3_ede_verify_key(tfm, key);
+ if (err)
+ return err;
memcpy(ctx->key, key, key_len);
return 0;
@@ -387,7 +372,7 @@
unsigned int n, nbytes;
int ret, locked;
- locked = spin_trylock(&ctrblk_lock);
+ locked = mutex_trylock(&ctrblk_lock);
ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE);
while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
@@ -404,7 +389,7 @@
ret = blkcipher_walk_done(desc, walk, nbytes - n);
}
if (locked)
- spin_unlock(&ctrblk_lock);
+ mutex_unlock(&ctrblk_lock);
/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
if (nbytes) {
cpacf_kmctr(fc, ctx->key, buf, walk->src.virt.addr,
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index 86aed30..a3e7400 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -137,7 +137,7 @@
static int __init ghash_mod_init(void)
{
if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_GHASH))
- return -EOPNOTSUPP;
+ return -ENODEV;
return crypto_register_shash(&ghash_alg);
}
@@ -153,4 +153,4 @@
MODULE_ALIAS_CRYPTO("ghash");
MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation");
+MODULE_DESCRIPTION("GHASH hash function, s390 implementation");
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index ab9a0eb..6184dce 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -5,7 +5,7 @@
* s390 implementation of the AES Cipher Algorithm with protected keys.
*
* s390 Version:
- * Copyright IBM Corp. 2017
+ * Copyright IBM Corp. 2017,2019
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
* Harald Freudenberger <freude@de.ibm.com>
*/
@@ -25,31 +25,79 @@
#include <asm/cpacf.h>
#include <asm/pkey.h>
+/*
+ * Key blobs smaller/bigger than these defines are rejected
+ * by the common code even before the individual setkey function
+ * is called. As paes can handle different kinds of key blobs
+ * and padding is also possible, the limits need to be generous.
+ */
+#define PAES_MIN_KEYSIZE 64
+#define PAES_MAX_KEYSIZE 256
+
static u8 *ctrblk;
static DEFINE_SPINLOCK(ctrblk_lock);
static cpacf_mask_t km_functions, kmc_functions, kmctr_functions;
+struct key_blob {
+ /*
+ * Small keys will be stored in the keybuf. Larger keys are
+ * stored in extra allocated memory. In both cases does
+ * key point to the memory where the key is stored.
+ * The code distinguishes by checking keylen against
+ * sizeof(keybuf). See the two following helper functions.
+ */
+ u8 *key;
+ u8 keybuf[128];
+ unsigned int keylen;
+};
+
+static inline int _copy_key_to_kb(struct key_blob *kb,
+ const u8 *key,
+ unsigned int keylen)
+{
+ if (keylen <= sizeof(kb->keybuf))
+ kb->key = kb->keybuf;
+ else {
+ kb->key = kmalloc(keylen, GFP_KERNEL);
+ if (!kb->key)
+ return -ENOMEM;
+ }
+ memcpy(kb->key, key, keylen);
+ kb->keylen = keylen;
+
+ return 0;
+}
+
+static inline void _free_kb_keybuf(struct key_blob *kb)
+{
+ if (kb->key && kb->key != kb->keybuf
+ && kb->keylen > sizeof(kb->keybuf)) {
+ kfree(kb->key);
+ kb->key = NULL;
+ }
+}
+
struct s390_paes_ctx {
- struct pkey_seckey sk;
+ struct key_blob kb;
struct pkey_protkey pk;
unsigned long fc;
};
struct s390_pxts_ctx {
- struct pkey_seckey sk[2];
+ struct key_blob kb[2];
struct pkey_protkey pk[2];
unsigned long fc;
};
-static inline int __paes_convert_key(struct pkey_seckey *sk,
+static inline int __paes_convert_key(struct key_blob *kb,
struct pkey_protkey *pk)
{
int i, ret;
/* try three times in case of failure */
for (i = 0; i < 3; i++) {
- ret = pkey_skey2pkey(sk, pk);
+ ret = pkey_keyblob2pkey(kb->key, kb->keylen, pk);
if (ret == 0)
break;
}
@@ -61,7 +109,7 @@
{
unsigned long fc;
- if (__paes_convert_key(&ctx->sk, &ctx->pk))
+ if (__paes_convert_key(&ctx->kb, &ctx->pk))
return -EINVAL;
/* Pick the correct function code based on the protected key type */
@@ -75,15 +123,33 @@
return ctx->fc ? 0 : -EINVAL;
}
-static int ecb_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
- unsigned int key_len)
+static int ecb_paes_init(struct crypto_tfm *tfm)
{
struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
- if (key_len != SECKEYBLOBSIZE)
- return -EINVAL;
+ ctx->kb.key = NULL;
- memcpy(ctx->sk.seckey, in_key, SECKEYBLOBSIZE);
+ return 0;
+}
+
+static void ecb_paes_exit(struct crypto_tfm *tfm)
+{
+ struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ _free_kb_keybuf(&ctx->kb);
+}
+
+static int ecb_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ int rc;
+ struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ _free_kb_keybuf(&ctx->kb);
+ rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
+ if (rc)
+ return rc;
+
if (__paes_set_key(ctx)) {
tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
@@ -145,10 +211,12 @@
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_list = LIST_HEAD_INIT(ecb_paes_alg.cra_list),
+ .cra_init = ecb_paes_init,
+ .cra_exit = ecb_paes_exit,
.cra_u = {
.blkcipher = {
- .min_keysize = SECKEYBLOBSIZE,
- .max_keysize = SECKEYBLOBSIZE,
+ .min_keysize = PAES_MIN_KEYSIZE,
+ .max_keysize = PAES_MAX_KEYSIZE,
.setkey = ecb_paes_set_key,
.encrypt = ecb_paes_encrypt,
.decrypt = ecb_paes_decrypt,
@@ -156,11 +224,27 @@
}
};
+static int cbc_paes_init(struct crypto_tfm *tfm)
+{
+ struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ ctx->kb.key = NULL;
+
+ return 0;
+}
+
+static void cbc_paes_exit(struct crypto_tfm *tfm)
+{
+ struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ _free_kb_keybuf(&ctx->kb);
+}
+
static int __cbc_paes_set_key(struct s390_paes_ctx *ctx)
{
unsigned long fc;
- if (__paes_convert_key(&ctx->sk, &ctx->pk))
+ if (__paes_convert_key(&ctx->kb, &ctx->pk))
return -EINVAL;
/* Pick the correct function code based on the protected key type */
@@ -177,9 +261,14 @@
static int cbc_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
unsigned int key_len)
{
+ int rc;
struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
- memcpy(ctx->sk.seckey, in_key, SECKEYBLOBSIZE);
+ _free_kb_keybuf(&ctx->kb);
+ rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
+ if (rc)
+ return rc;
+
if (__cbc_paes_set_key(ctx)) {
tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
@@ -248,10 +337,12 @@
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_list = LIST_HEAD_INIT(cbc_paes_alg.cra_list),
+ .cra_init = cbc_paes_init,
+ .cra_exit = cbc_paes_exit,
.cra_u = {
.blkcipher = {
- .min_keysize = SECKEYBLOBSIZE,
- .max_keysize = SECKEYBLOBSIZE,
+ .min_keysize = PAES_MIN_KEYSIZE,
+ .max_keysize = PAES_MAX_KEYSIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = cbc_paes_set_key,
.encrypt = cbc_paes_encrypt,
@@ -260,12 +351,30 @@
}
};
+static int xts_paes_init(struct crypto_tfm *tfm)
+{
+ struct s390_pxts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ ctx->kb[0].key = NULL;
+ ctx->kb[1].key = NULL;
+
+ return 0;
+}
+
+static void xts_paes_exit(struct crypto_tfm *tfm)
+{
+ struct s390_pxts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ _free_kb_keybuf(&ctx->kb[0]);
+ _free_kb_keybuf(&ctx->kb[1]);
+}
+
static int __xts_paes_set_key(struct s390_pxts_ctx *ctx)
{
unsigned long fc;
- if (__paes_convert_key(&ctx->sk[0], &ctx->pk[0]) ||
- __paes_convert_key(&ctx->sk[1], &ctx->pk[1]))
+ if (__paes_convert_key(&ctx->kb[0], &ctx->pk[0]) ||
+ __paes_convert_key(&ctx->kb[1], &ctx->pk[1]))
return -EINVAL;
if (ctx->pk[0].type != ctx->pk[1].type)
@@ -283,14 +392,27 @@
}
static int xts_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
- unsigned int key_len)
+ unsigned int xts_key_len)
{
+ int rc;
struct s390_pxts_ctx *ctx = crypto_tfm_ctx(tfm);
u8 ckey[2 * AES_MAX_KEY_SIZE];
- unsigned int ckey_len;
+ unsigned int ckey_len, key_len;
- memcpy(ctx->sk[0].seckey, in_key, SECKEYBLOBSIZE);
- memcpy(ctx->sk[1].seckey, in_key + SECKEYBLOBSIZE, SECKEYBLOBSIZE);
+ if (xts_key_len % 2)
+ return -EINVAL;
+
+ key_len = xts_key_len / 2;
+
+ _free_kb_keybuf(&ctx->kb[0]);
+ _free_kb_keybuf(&ctx->kb[1]);
+ rc = _copy_key_to_kb(&ctx->kb[0], in_key, key_len);
+ if (rc)
+ return rc;
+ rc = _copy_key_to_kb(&ctx->kb[1], in_key + key_len, key_len);
+ if (rc)
+ return rc;
+
if (__xts_paes_set_key(ctx)) {
tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
@@ -384,10 +506,12 @@
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_list = LIST_HEAD_INIT(xts_paes_alg.cra_list),
+ .cra_init = xts_paes_init,
+ .cra_exit = xts_paes_exit,
.cra_u = {
.blkcipher = {
- .min_keysize = 2 * SECKEYBLOBSIZE,
- .max_keysize = 2 * SECKEYBLOBSIZE,
+ .min_keysize = 2 * PAES_MIN_KEYSIZE,
+ .max_keysize = 2 * PAES_MAX_KEYSIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = xts_paes_set_key,
.encrypt = xts_paes_encrypt,
@@ -396,11 +520,27 @@
}
};
+static int ctr_paes_init(struct crypto_tfm *tfm)
+{
+ struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ ctx->kb.key = NULL;
+
+ return 0;
+}
+
+static void ctr_paes_exit(struct crypto_tfm *tfm)
+{
+ struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ _free_kb_keybuf(&ctx->kb);
+}
+
static int __ctr_paes_set_key(struct s390_paes_ctx *ctx)
{
unsigned long fc;
- if (__paes_convert_key(&ctx->sk, &ctx->pk))
+ if (__paes_convert_key(&ctx->kb, &ctx->pk))
return -EINVAL;
/* Pick the correct function code based on the protected key type */
@@ -418,9 +558,14 @@
static int ctr_paes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
unsigned int key_len)
{
+ int rc;
struct s390_paes_ctx *ctx = crypto_tfm_ctx(tfm);
- memcpy(ctx->sk.seckey, in_key, key_len);
+ _free_kb_keybuf(&ctx->kb);
+ rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
+ if (rc)
+ return rc;
+
if (__ctr_paes_set_key(ctx)) {
tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
@@ -530,10 +675,12 @@
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_list = LIST_HEAD_INIT(ctr_paes_alg.cra_list),
+ .cra_init = ctr_paes_init,
+ .cra_exit = ctr_paes_exit,
.cra_u = {
.blkcipher = {
- .min_keysize = SECKEYBLOBSIZE,
- .max_keysize = SECKEYBLOBSIZE,
+ .min_keysize = PAES_MIN_KEYSIZE,
+ .max_keysize = PAES_MAX_KEYSIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = ctr_paes_set_key,
.encrypt = ctr_paes_encrypt,
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index a97a180..d977643 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -61,6 +61,7 @@
module_param_named(reseed_limit, prng_reseed_limit, int, 0);
MODULE_PARM_DESC(prng_reseed_limit, "PRNG reseed limit");
+static bool trng_available;
/*
* Any one who considers arithmetical methods of producing random digits is,
@@ -115,46 +116,68 @@
/*
* generate_entropy:
- * This algorithm produces 64 bytes of entropy data based on 1024
- * individual stckf() invocations assuming that each stckf() value
- * contributes 0.25 bits of entropy. So the caller gets 256 bit
- * entropy per 64 byte or 4 bits entropy per byte.
+ * This function fills a given buffer with random bytes. The entropy within
+ * the random bytes given back is assumed to have at least 50% - meaning
+ * a 64 bytes buffer has at least 64 * 8 / 2 = 256 bits of entropy.
+ * Within the function the entropy generation is done in junks of 64 bytes.
+ * So the caller should also ask for buffer fill in multiples of 64 bytes.
+ * The generation of the entropy is based on the assumption that every stckf()
+ * invocation produces 0.5 bits of entropy. To accumulate 256 bits of entropy
+ * at least 512 stckf() values are needed. The entropy relevant part of the
+ * stckf value is bit 51 (counting starts at the left with bit nr 0) so
+ * here we use the lower 4 bytes and exor the values into 2k of bufferspace.
+ * To be on the save side, if there is ever a problem with stckf() the
+ * other half of the page buffer is filled with bytes from urandom via
+ * get_random_bytes(), so this function consumes 2k of urandom for each
+ * requested 64 bytes output data. Finally the buffer page is condensed into
+ * a 64 byte value by hashing with a SHA512 hash.
*/
static int generate_entropy(u8 *ebuf, size_t nbytes)
{
int n, ret = 0;
- u8 *pg, *h, hash[64];
+ u8 *pg, pblock[80] = {
+ /* 8 x 64 bit init values */
+ 0x6A, 0x09, 0xE6, 0x67, 0xF3, 0xBC, 0xC9, 0x08,
+ 0xBB, 0x67, 0xAE, 0x85, 0x84, 0xCA, 0xA7, 0x3B,
+ 0x3C, 0x6E, 0xF3, 0x72, 0xFE, 0x94, 0xF8, 0x2B,
+ 0xA5, 0x4F, 0xF5, 0x3A, 0x5F, 0x1D, 0x36, 0xF1,
+ 0x51, 0x0E, 0x52, 0x7F, 0xAD, 0xE6, 0x82, 0xD1,
+ 0x9B, 0x05, 0x68, 0x8C, 0x2B, 0x3E, 0x6C, 0x1F,
+ 0x1F, 0x83, 0xD9, 0xAB, 0xFB, 0x41, 0xBD, 0x6B,
+ 0x5B, 0xE0, 0xCD, 0x19, 0x13, 0x7E, 0x21, 0x79,
+ /* 128 bit counter total message bit length */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x00 };
- /* allocate 2 pages */
- pg = (u8 *) __get_free_pages(GFP_KERNEL, 1);
+ /* allocate one page stckf buffer */
+ pg = (u8 *) __get_free_page(GFP_KERNEL);
if (!pg) {
prng_errorflag = PRNG_GEN_ENTROPY_FAILED;
return -ENOMEM;
}
+ /* fill the ebuf in chunks of 64 byte each */
while (nbytes) {
- /* fill pages with urandom bytes */
- get_random_bytes(pg, 2*PAGE_SIZE);
- /* exor pages with 1024 stckf values */
- for (n = 0; n < 2 * PAGE_SIZE / sizeof(u64); n++) {
- u64 *p = ((u64 *)pg) + n;
+ /* fill lower 2k with urandom bytes */
+ get_random_bytes(pg, PAGE_SIZE / 2);
+ /* exor upper 2k with 512 stckf values, offset 4 bytes each */
+ for (n = 0; n < 512; n++) {
+ int offset = (PAGE_SIZE / 2) + (n * 4) - 4;
+ u64 *p = (u64 *)(pg + offset);
*p ^= get_tod_clock_fast();
}
- n = (nbytes < sizeof(hash)) ? nbytes : sizeof(hash);
- if (n < sizeof(hash))
- h = hash;
- else
- h = ebuf;
- /* hash over the filled pages */
- cpacf_kimd(CPACF_KIMD_SHA_512, h, pg, 2*PAGE_SIZE);
- if (n < sizeof(hash))
- memcpy(ebuf, hash, n);
+ /* hash over the filled page */
+ cpacf_klmd(CPACF_KLMD_SHA_512, pblock, pg, PAGE_SIZE);
+ n = (nbytes < 64) ? nbytes : 64;
+ memcpy(ebuf, pblock, n);
ret += n;
ebuf += n;
nbytes -= n;
}
- free_pages((unsigned long)pg, 1);
+ memzero_explicit(pblock, sizeof(pblock));
+ memzero_explicit(pg, PAGE_SIZE);
+ free_page((unsigned long)pg);
return ret;
}
@@ -344,8 +367,8 @@
static int __init prng_sha512_instantiate(void)
{
- int ret, datalen;
- u8 seed[64 + 32 + 16];
+ int ret, datalen, seedlen;
+ u8 seed[128 + 16];
pr_debug("prng runs in SHA-512 mode "
"with chunksize=%d and reseed_limit=%u\n",
@@ -368,16 +391,36 @@
if (ret)
goto outfree;
- /* generate initial seed bytestring, with 256 + 128 bits entropy */
- ret = generate_entropy(seed, 64 + 32);
- if (ret != 64 + 32)
- goto outfree;
- /* followed by 16 bytes of unique nonce */
- get_tod_clock_ext(seed + 64 + 32);
+ /* generate initial seed, we need at least 256 + 128 bits entropy. */
+ if (trng_available) {
+ /*
+ * Trng available, so use it. The trng works in chunks of
+ * 32 bytes and produces 100% entropy. So we pull 64 bytes
+ * which gives us 512 bits entropy.
+ */
+ seedlen = 2 * 32;
+ cpacf_trng(NULL, 0, seed, seedlen);
+ } else {
+ /*
+ * No trng available, so use the generate_entropy() function.
+ * This function works in 64 byte junks and produces
+ * 50% entropy. So we pull 2*64 bytes which gives us 512 bits
+ * of entropy.
+ */
+ seedlen = 2 * 64;
+ ret = generate_entropy(seed, seedlen);
+ if (ret != seedlen)
+ goto outfree;
+ }
- /* initial seed of the prno drng */
+ /* append the seed by 16 bytes of unique nonce */
+ get_tod_clock_ext(seed + seedlen);
+ seedlen += 16;
+
+ /* now initial seed of the prno drng */
cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
- &prng_data->prnows, NULL, 0, seed, sizeof(seed));
+ &prng_data->prnows, NULL, 0, seed, seedlen);
+ memzero_explicit(seed, sizeof(seed));
/* if fips mode is enabled, generate a first block of random
bytes for the FIPS 140-2 Conditional Self Test */
@@ -405,17 +448,26 @@
static int prng_sha512_reseed(void)
{
- int ret;
+ int ret, seedlen;
u8 seed[64];
- /* fetch 256 bits of fresh entropy */
- ret = generate_entropy(seed, sizeof(seed));
- if (ret != sizeof(seed))
- return ret;
+ /* We need at least 256 bits of fresh entropy for reseeding */
+ if (trng_available) {
+ /* trng produces 256 bits entropy in 32 bytes */
+ seedlen = 32;
+ cpacf_trng(NULL, 0, seed, seedlen);
+ } else {
+ /* generate_entropy() produces 256 bits entropy in 64 bytes */
+ seedlen = 64;
+ ret = generate_entropy(seed, seedlen);
+ if (ret != sizeof(seed))
+ return ret;
+ }
/* do a reseed of the prno drng with this bytestring */
cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
- &prng_data->prnows, NULL, 0, seed, sizeof(seed));
+ &prng_data->prnows, NULL, 0, seed, seedlen);
+ memzero_explicit(seed, sizeof(seed));
return 0;
}
@@ -592,6 +644,7 @@
ret = -EFAULT;
break;
}
+ memzero_explicit(p, n);
ubuf += n;
nbytes -= n;
ret += n;
@@ -771,7 +824,11 @@
/* check if the CPU has a PRNG */
if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG))
- return -EOPNOTSUPP;
+ return -ENODEV;
+
+ /* check if TRNG subfunction is available */
+ if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+ trng_available = true;
/* choose prng mode */
if (prng_mode != PRNG_MODE_TDES) {
@@ -780,7 +837,7 @@
if (prng_mode == PRNG_MODE_SHA512) {
pr_err("The prng module cannot "
"start in SHA-512 mode\n");
- return -EOPNOTSUPP;
+ return -ENODEV;
}
prng_mode = PRNG_MODE_TDES;
} else
diff --git a/arch/s390/crypto/sha.h b/arch/s390/crypto/sha.h
index d6f8258..ada2f98 100644
--- a/arch/s390/crypto/sha.h
+++ b/arch/s390/crypto/sha.h
@@ -12,15 +12,17 @@
#include <linux/crypto.h>
#include <crypto/sha.h>
+#include <crypto/sha3.h>
/* must be big enough for the largest SHA variant */
-#define SHA_MAX_STATE_SIZE (SHA512_DIGEST_SIZE / 4)
-#define SHA_MAX_BLOCK_SIZE SHA512_BLOCK_SIZE
+#define SHA3_STATE_SIZE 200
+#define CPACF_MAX_PARMBLOCK_SIZE SHA3_STATE_SIZE
+#define SHA_MAX_BLOCK_SIZE SHA3_224_BLOCK_SIZE
struct s390_sha_ctx {
- u64 count; /* message length in bytes */
- u32 state[SHA_MAX_STATE_SIZE];
- u8 buf[2 * SHA_MAX_BLOCK_SIZE];
+ u64 count; /* message length in bytes */
+ u32 state[CPACF_MAX_PARMBLOCK_SIZE / sizeof(u32)];
+ u8 buf[SHA_MAX_BLOCK_SIZE];
int func; /* KIMD function to use */
};
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index 009572e..7c15542 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -86,7 +86,7 @@
static int __init sha1_s390_init(void)
{
if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA_1))
- return -EOPNOTSUPP;
+ return -ENODEV;
return crypto_register_shash(&alg);
}
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index 62833a1..b52c87e 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -17,7 +17,7 @@
#include "sha.h"
-static int sha256_init(struct shash_desc *desc)
+static int s390_sha256_init(struct shash_desc *desc)
{
struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
@@ -60,7 +60,7 @@
static struct shash_alg sha256_alg = {
.digestsize = SHA256_DIGEST_SIZE,
- .init = sha256_init,
+ .init = s390_sha256_init,
.update = s390_sha_update,
.final = s390_sha_final,
.export = sha256_export,
@@ -76,7 +76,7 @@
}
};
-static int sha224_init(struct shash_desc *desc)
+static int s390_sha224_init(struct shash_desc *desc)
{
struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
@@ -96,7 +96,7 @@
static struct shash_alg sha224_alg = {
.digestsize = SHA224_DIGEST_SIZE,
- .init = sha224_init,
+ .init = s390_sha224_init,
.update = s390_sha_update,
.final = s390_sha_final,
.export = sha256_export,
@@ -117,7 +117,7 @@
int ret;
if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA_256))
- return -EOPNOTSUPP;
+ return -ENODEV;
ret = crypto_register_shash(&sha256_alg);
if (ret < 0)
goto out;
diff --git a/arch/s390/crypto/sha3_256_s390.c b/arch/s390/crypto/sha3_256_s390.c
new file mode 100644
index 0000000..460cbbb
--- /dev/null
+++ b/arch/s390/crypto/sha3_256_s390.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Cryptographic API.
+ *
+ * s390 implementation of the SHA256 and SHA224 Secure Hash Algorithm.
+ *
+ * s390 Version:
+ * Copyright IBM Corp. 2019
+ * Author(s): Joerg Schmidbauer (jschmidb@de.ibm.com)
+ */
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <crypto/sha.h>
+#include <crypto/sha3.h>
+#include <asm/cpacf.h>
+
+#include "sha.h"
+
+static int sha3_256_init(struct shash_desc *desc)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+
+ memset(sctx->state, 0, sizeof(sctx->state));
+ sctx->count = 0;
+ sctx->func = CPACF_KIMD_SHA3_256;
+
+ return 0;
+}
+
+static int sha3_256_export(struct shash_desc *desc, void *out)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+ struct sha3_state *octx = out;
+
+ octx->rsiz = sctx->count;
+ memcpy(octx->st, sctx->state, sizeof(octx->st));
+ memcpy(octx->buf, sctx->buf, sizeof(octx->buf));
+
+ return 0;
+}
+
+static int sha3_256_import(struct shash_desc *desc, const void *in)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+ const struct sha3_state *ictx = in;
+
+ sctx->count = ictx->rsiz;
+ memcpy(sctx->state, ictx->st, sizeof(ictx->st));
+ memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
+ sctx->func = CPACF_KIMD_SHA3_256;
+
+ return 0;
+}
+
+static int sha3_224_import(struct shash_desc *desc, const void *in)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+ const struct sha3_state *ictx = in;
+
+ sctx->count = ictx->rsiz;
+ memcpy(sctx->state, ictx->st, sizeof(ictx->st));
+ memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
+ sctx->func = CPACF_KIMD_SHA3_224;
+
+ return 0;
+}
+
+static struct shash_alg sha3_256_alg = {
+ .digestsize = SHA3_256_DIGEST_SIZE, /* = 32 */
+ .init = sha3_256_init,
+ .update = s390_sha_update,
+ .final = s390_sha_final,
+ .export = sha3_256_export,
+ .import = sha3_256_import,
+ .descsize = sizeof(struct s390_sha_ctx),
+ .statesize = sizeof(struct sha3_state),
+ .base = {
+ .cra_name = "sha3-256",
+ .cra_driver_name = "sha3-256-s390",
+ .cra_priority = 300,
+ .cra_blocksize = SHA3_256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int sha3_224_init(struct shash_desc *desc)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+
+ memset(sctx->state, 0, sizeof(sctx->state));
+ sctx->count = 0;
+ sctx->func = CPACF_KIMD_SHA3_224;
+
+ return 0;
+}
+
+static struct shash_alg sha3_224_alg = {
+ .digestsize = SHA3_224_DIGEST_SIZE,
+ .init = sha3_224_init,
+ .update = s390_sha_update,
+ .final = s390_sha_final,
+ .export = sha3_256_export, /* same as for 256 */
+ .import = sha3_224_import, /* function code different! */
+ .descsize = sizeof(struct s390_sha_ctx),
+ .statesize = sizeof(struct sha3_state),
+ .base = {
+ .cra_name = "sha3-224",
+ .cra_driver_name = "sha3-224-s390",
+ .cra_priority = 300,
+ .cra_blocksize = SHA3_224_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init sha3_256_s390_init(void)
+{
+ int ret;
+
+ if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA3_256))
+ return -ENODEV;
+
+ ret = crypto_register_shash(&sha3_256_alg);
+ if (ret < 0)
+ goto out;
+
+ ret = crypto_register_shash(&sha3_224_alg);
+ if (ret < 0)
+ crypto_unregister_shash(&sha3_256_alg);
+out:
+ return ret;
+}
+
+static void __exit sha3_256_s390_fini(void)
+{
+ crypto_unregister_shash(&sha3_224_alg);
+ crypto_unregister_shash(&sha3_256_alg);
+}
+
+module_cpu_feature_match(MSA, sha3_256_s390_init);
+module_exit(sha3_256_s390_fini);
+
+MODULE_ALIAS_CRYPTO("sha3-256");
+MODULE_ALIAS_CRYPTO("sha3-224");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA3-256 and SHA3-224 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha3_512_s390.c b/arch/s390/crypto/sha3_512_s390.c
new file mode 100644
index 0000000..72cf460
--- /dev/null
+++ b/arch/s390/crypto/sha3_512_s390.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Cryptographic API.
+ *
+ * s390 implementation of the SHA512 and SHA384 Secure Hash Algorithm.
+ *
+ * Copyright IBM Corp. 2019
+ * Author(s): Joerg Schmidbauer (jschmidb@de.ibm.com)
+ */
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <crypto/sha.h>
+#include <crypto/sha3.h>
+#include <asm/cpacf.h>
+
+#include "sha.h"
+
+static int sha3_512_init(struct shash_desc *desc)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+
+ memset(sctx->state, 0, sizeof(sctx->state));
+ sctx->count = 0;
+ sctx->func = CPACF_KIMD_SHA3_512;
+
+ return 0;
+}
+
+static int sha3_512_export(struct shash_desc *desc, void *out)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+ struct sha3_state *octx = out;
+
+ octx->rsiz = sctx->count;
+ octx->rsizw = sctx->count >> 32;
+
+ memcpy(octx->st, sctx->state, sizeof(octx->st));
+ memcpy(octx->buf, sctx->buf, sizeof(octx->buf));
+
+ return 0;
+}
+
+static int sha3_512_import(struct shash_desc *desc, const void *in)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+ const struct sha3_state *ictx = in;
+
+ if (unlikely(ictx->rsizw))
+ return -ERANGE;
+ sctx->count = ictx->rsiz;
+
+ memcpy(sctx->state, ictx->st, sizeof(ictx->st));
+ memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
+ sctx->func = CPACF_KIMD_SHA3_512;
+
+ return 0;
+}
+
+static int sha3_384_import(struct shash_desc *desc, const void *in)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+ const struct sha3_state *ictx = in;
+
+ if (unlikely(ictx->rsizw))
+ return -ERANGE;
+ sctx->count = ictx->rsiz;
+
+ memcpy(sctx->state, ictx->st, sizeof(ictx->st));
+ memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
+ sctx->func = CPACF_KIMD_SHA3_384;
+
+ return 0;
+}
+
+static struct shash_alg sha3_512_alg = {
+ .digestsize = SHA3_512_DIGEST_SIZE,
+ .init = sha3_512_init,
+ .update = s390_sha_update,
+ .final = s390_sha_final,
+ .export = sha3_512_export,
+ .import = sha3_512_import,
+ .descsize = sizeof(struct s390_sha_ctx),
+ .statesize = sizeof(struct sha3_state),
+ .base = {
+ .cra_name = "sha3-512",
+ .cra_driver_name = "sha3-512-s390",
+ .cra_priority = 300,
+ .cra_blocksize = SHA3_512_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+MODULE_ALIAS_CRYPTO("sha3-512");
+
+static int sha3_384_init(struct shash_desc *desc)
+{
+ struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
+
+ memset(sctx->state, 0, sizeof(sctx->state));
+ sctx->count = 0;
+ sctx->func = CPACF_KIMD_SHA3_384;
+
+ return 0;
+}
+
+static struct shash_alg sha3_384_alg = {
+ .digestsize = SHA3_384_DIGEST_SIZE,
+ .init = sha3_384_init,
+ .update = s390_sha_update,
+ .final = s390_sha_final,
+ .export = sha3_512_export, /* same as for 512 */
+ .import = sha3_384_import, /* function code different! */
+ .descsize = sizeof(struct s390_sha_ctx),
+ .statesize = sizeof(struct sha3_state),
+ .base = {
+ .cra_name = "sha3-384",
+ .cra_driver_name = "sha3-384-s390",
+ .cra_priority = 300,
+ .cra_blocksize = SHA3_384_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct s390_sha_ctx),
+ .cra_module = THIS_MODULE,
+ }
+};
+
+MODULE_ALIAS_CRYPTO("sha3-384");
+
+static int __init init(void)
+{
+ int ret;
+
+ if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA3_512))
+ return -ENODEV;
+ ret = crypto_register_shash(&sha3_512_alg);
+ if (ret < 0)
+ goto out;
+ ret = crypto_register_shash(&sha3_384_alg);
+ if (ret < 0)
+ crypto_unregister_shash(&sha3_512_alg);
+out:
+ return ret;
+}
+
+static void __exit fini(void)
+{
+ crypto_unregister_shash(&sha3_512_alg);
+ crypto_unregister_shash(&sha3_384_alg);
+}
+
+module_cpu_feature_match(MSA, init);
+module_exit(fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA3-512 and SHA3-384 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index be589c3..ad29db0 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -127,7 +127,7 @@
int ret;
if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA_512))
- return -EOPNOTSUPP;
+ return -ENODEV;
if ((ret = crypto_register_shash(&sha512_alg)) < 0)
goto out;
if ((ret = crypto_register_shash(&sha384_alg)) < 0)
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index cf0718d..d39e0f0 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -20,7 +20,7 @@
unsigned int index, n;
/* how much is already in the buffer? */
- index = ctx->count & (bsize - 1);
+ index = ctx->count % bsize;
ctx->count += len;
if ((index + len) < bsize)
@@ -37,7 +37,7 @@
/* process as many blocks as possible */
if (len >= bsize) {
- n = len & ~(bsize - 1);
+ n = (len / bsize) * bsize;
cpacf_kimd(ctx->func, ctx->state, data, n);
data += n;
len -= n;
@@ -50,34 +50,63 @@
}
EXPORT_SYMBOL_GPL(s390_sha_update);
+static int s390_crypto_shash_parmsize(int func)
+{
+ switch (func) {
+ case CPACF_KLMD_SHA_1:
+ return 20;
+ case CPACF_KLMD_SHA_256:
+ return 32;
+ case CPACF_KLMD_SHA_512:
+ return 64;
+ case CPACF_KLMD_SHA3_224:
+ case CPACF_KLMD_SHA3_256:
+ case CPACF_KLMD_SHA3_384:
+ case CPACF_KLMD_SHA3_512:
+ return 200;
+ default:
+ return -EINVAL;
+ }
+}
+
int s390_sha_final(struct shash_desc *desc, u8 *out)
{
struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
unsigned int bsize = crypto_shash_blocksize(desc->tfm);
u64 bits;
- unsigned int index, end, plen;
+ unsigned int n, mbl_offset;
- /* SHA-512 uses 128 bit padding length */
- plen = (bsize > SHA256_BLOCK_SIZE) ? 16 : 8;
-
- /* must perform manual padding */
- index = ctx->count & (bsize - 1);
- end = (index < bsize - plen) ? bsize : (2 * bsize);
-
- /* start pad with 1 */
- ctx->buf[index] = 0x80;
- index++;
-
- /* pad with zeros */
- memset(ctx->buf + index, 0x00, end - index - 8);
-
- /*
- * Append message length. Well, SHA-512 wants a 128 bit length value,
- * nevertheless we use u64, should be enough for now...
- */
+ n = ctx->count % bsize;
bits = ctx->count * 8;
- memcpy(ctx->buf + end - 8, &bits, sizeof(bits));
- cpacf_kimd(ctx->func, ctx->state, ctx->buf, end);
+ mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32);
+ if (mbl_offset < 0)
+ return -EINVAL;
+
+ /* set total msg bit length (mbl) in CPACF parmblock */
+ switch (ctx->func) {
+ case CPACF_KLMD_SHA_1:
+ case CPACF_KLMD_SHA_256:
+ memcpy(ctx->state + mbl_offset, &bits, sizeof(bits));
+ break;
+ case CPACF_KLMD_SHA_512:
+ /*
+ * the SHA512 parmblock has a 128-bit mbl field, clear
+ * high-order u64 field, copy bits to low-order u64 field
+ */
+ memset(ctx->state + mbl_offset, 0x00, sizeof(bits));
+ mbl_offset += sizeof(u64) / sizeof(u32);
+ memcpy(ctx->state + mbl_offset, &bits, sizeof(bits));
+ break;
+ case CPACF_KLMD_SHA3_224:
+ case CPACF_KLMD_SHA3_256:
+ case CPACF_KLMD_SHA3_384:
+ case CPACF_KLMD_SHA3_512:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ cpacf_klmd(ctx->func, ctx->state, ctx->buf, n);
/* copy digest to out */
memcpy(out, ctx->state, crypto_shash_digestsize(desc->tfm));
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
deleted file mode 100644
index 5134c71..0000000
--- a/arch/s390/defconfig
+++ /dev/null
@@ -1,249 +0,0 @@
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_USELIB=y
-CONFIG_AUDIT=y
-CONFIG_NO_HZ_IDLE=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_XACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-# CONFIG_CPU_ISOLATION is not set
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_CGROUPS=y
-CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
-CONFIG_BLK_CGROUP=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_RT_GROUP_SCHED=y
-CONFIG_CGROUP_PIDS=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_HUGETLB=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_CGROUP_PERF=y
-CONFIG_NAMESPACES=y
-CONFIG_USER_NS=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_CHECKPOINT_RESTORE=y
-CONFIG_BPF_SYSCALL=y
-CONFIG_USERFAULTFD=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
-CONFIG_KPROBES=y
-CONFIG_JUMP_LABEL=y
-CONFIG_STATIC_KEYS_SELFTEST=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_BLK_DEV_INTEGRITY=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_NR_CPUS=256
-CONFIG_NUMA=y
-CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
-CONFIG_MEMORY_HOTPLUG=y
-CONFIG_MEMORY_HOTREMOVE=y
-CONFIG_KSM=y
-CONFIG_TRANSPARENT_HUGEPAGE=y
-CONFIG_CLEANCACHE=y
-CONFIG_FRONTSWAP=y
-CONFIG_ZSWAP=y
-CONFIG_ZBUD=m
-CONFIG_ZSMALLOC=m
-CONFIG_ZSMALLOC_STAT=y
-CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_L2TP=m
-CONFIG_L2TP_DEBUGFS=m
-CONFIG_VLAN_8021Q=y
-CONFIG_NET_SCHED=y
-CONFIG_NET_SCH_CBQ=m
-CONFIG_NET_SCH_PRIO=m
-CONFIG_NET_SCH_RED=m
-CONFIG_NET_SCH_SFQ=m
-CONFIG_NET_SCH_TEQL=m
-CONFIG_NET_SCH_TBF=m
-CONFIG_NET_SCH_GRED=m
-CONFIG_NET_SCH_DSMARK=m
-CONFIG_NET_CLS_TCINDEX=m
-CONFIG_NET_CLS_ROUTE4=m
-CONFIG_NET_CLS_FW=m
-CONFIG_NET_CLS_U32=m
-CONFIG_CLS_U32_MARK=y
-CONFIG_NET_CLS_RSVP=m
-CONFIG_NET_CLS_RSVP6=m
-CONFIG_NET_CLS_ACT=y
-CONFIG_NET_ACT_POLICE=y
-CONFIG_BPF_JIT=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_BLK_DEV_SR_VENDOR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_SCSI_FC_ATTRS=y
-CONFIG_ZFCP=y
-CONFIG_SCSI_VIRTIO=y
-CONFIG_MD=y
-CONFIG_MD_LINEAR=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_BLK_DEV_DM=y
-CONFIG_DM_CRYPT=m
-CONFIG_DM_SNAPSHOT=m
-CONFIG_DM_MIRROR=m
-CONFIG_DM_LOG_USERSPACE=m
-CONFIG_DM_RAID=m
-CONFIG_DM_ZERO=m
-CONFIG_DM_MULTIPATH=m
-CONFIG_DM_MULTIPATH_QL=m
-CONFIG_DM_MULTIPATH_ST=m
-CONFIG_DM_UEVENT=y
-CONFIG_DM_VERITY=m
-CONFIG_DM_SWITCH=m
-CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_EQUALIZER=m
-CONFIG_TUN=m
-CONFIG_VIRTIO_NET=y
-# CONFIG_NET_VENDOR_ALACRITECH is not set
-# CONFIG_NET_VENDOR_CORTINA is not set
-# CONFIG_NET_VENDOR_SOLARFLARE is not set
-# CONFIG_NET_VENDOR_SOCIONEXT is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_DEVKMEM=y
-CONFIG_RAW_DRIVER=m
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_EXT4_FS_SECURITY=y
-CONFIG_XFS_FS=y
-CONFIG_XFS_QUOTA=y
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_XFS_RT=y
-CONFIG_BTRFS_FS=y
-CONFIG_BTRFS_FS_POSIX_ACL=y
-CONFIG_FANOTIFY=y
-CONFIG_FUSE_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_HUGETLBFS=y
-# CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_DWARF4=y
-CONFIG_GDB_SCRIPTS=y
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_DEBUG_SECTION_MISMATCH=y
-CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_PAGEALLOC=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_PANIC_ON_OOPS=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_LOCK_STAT=y
-CONFIG_DEBUG_LOCKDEP=y
-CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_SG=y
-CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_RCU_CPU_STALL_TIMEOUT=60
-CONFIG_LATENCYTOP=y
-CONFIG_SCHED_TRACER=y
-CONFIG_FTRACE_SYSCALLS=y
-CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
-CONFIG_STACK_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_FUNCTION_PROFILER=y
-# CONFIG_RUNTIME_TESTING_MENU is not set
-CONFIG_S390_PTDUMP=y
-CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_AUTHENC=m
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_CCM=m
-CONFIG_CRYPTO_GCM=m
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_CFB=m
-CONFIG_CRYPTO_CTS=m
-CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_XTS=m
-CONFIG_CRYPTO_CMAC=m
-CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_MD4=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
-CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_SHA256=y
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
-CONFIG_CRYPTO_CAST5=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SEED=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_SM4=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_DEFLATE=m
-CONFIG_CRYPTO_LZ4=m
-CONFIG_CRYPTO_LZ4HC=m
-CONFIG_CRYPTO_ANSI_CPRNG=m
-CONFIG_CRYPTO_USER_API_HASH=m
-CONFIG_CRYPTO_USER_API_SKCIPHER=m
-CONFIG_CRYPTO_USER_API_RNG=m
-CONFIG_ZCRYPT=m
-CONFIG_PKEY=m
-CONFIG_CRYPTO_PAES_S390=m
-CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
-CONFIG_CRYPTO_SHA512_S390=m
-CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_CRC7=m
-# CONFIG_XZ_DEC_X86 is not set
-# CONFIG_XZ_DEC_POWERPC is not set
-# CONFIG_XZ_DEC_IA64 is not set
-# CONFIG_XZ_DEC_ARM is not set
-# CONFIG_XZ_DEC_ARMTHUMB is not set
-# CONFIG_XZ_DEC_SPARC is not set
-CONFIG_CMM=m
diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h
index 52348e0..05f3f9a 100644
--- a/arch/s390/hypfs/hypfs.h
+++ b/arch/s390/hypfs/hypfs.h
@@ -43,7 +43,7 @@
void hypfs_diag0c_exit(void);
/* Set Partition-Resource Parameter */
-int hypfs_sprp_init(void);
+void hypfs_sprp_init(void);
void hypfs_sprp_exit(void);
/* debugfs interface */
@@ -69,9 +69,9 @@
struct dentry *dentry;
};
-extern int hypfs_dbfs_init(void);
+extern void hypfs_dbfs_init(void);
extern void hypfs_dbfs_exit(void);
-extern int hypfs_dbfs_create_file(struct hypfs_dbfs_file *df);
+extern void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df);
extern void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df);
#endif /* _HYPFS_H_ */
diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c
index b9bdf5c..f4c7dbf 100644
--- a/arch/s390/hypfs/hypfs_dbfs.c
+++ b/arch/s390/hypfs/hypfs_dbfs.c
@@ -78,14 +78,11 @@
.unlocked_ioctl = dbfs_ioctl,
};
-int hypfs_dbfs_create_file(struct hypfs_dbfs_file *df)
+void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df)
{
df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df,
&dbfs_ops);
- if (IS_ERR(df->dentry))
- return PTR_ERR(df->dentry);
mutex_init(&df->lock);
- return 0;
}
void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df)
@@ -93,10 +90,9 @@
debugfs_remove(df->dentry);
}
-int hypfs_dbfs_init(void)
+void hypfs_dbfs_init(void)
{
dbfs_dir = debugfs_create_dir("s390_hypfs", NULL);
- return PTR_ERR_OR_ZERO(dbfs_dir);
}
void hypfs_dbfs_exit(void)
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 3452e18..f0bc4dc 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -440,11 +440,10 @@
pr_err("The hardware system does not support hypfs\n");
return -ENODATA;
}
- if (diag204_info_type == DIAG204_INFO_EXT) {
- rc = hypfs_dbfs_create_file(&dbfs_file_d204);
- if (rc)
- return rc;
- }
+
+ if (diag204_info_type == DIAG204_INFO_EXT)
+ hypfs_dbfs_create_file(&dbfs_file_d204);
+
if (MACHINE_IS_LPAR) {
rc = diag224_get_name_table();
if (rc) {
diff --git a/arch/s390/hypfs/hypfs_diag0c.c b/arch/s390/hypfs/hypfs_diag0c.c
index cebf051..3235e4d 100644
--- a/arch/s390/hypfs/hypfs_diag0c.c
+++ b/arch/s390/hypfs/hypfs_diag0c.c
@@ -16,26 +16,12 @@
#define DBFS_D0C_HDR_VERSION 0
/*
- * Execute diagnose 0c in 31 bit mode
- */
-static void diag0c(struct hypfs_diag0c_entry *entry)
-{
- diag_stat_inc(DIAG_STAT_X00C);
- asm volatile (
- " sam31\n"
- " diag %0,%0,0x0c\n"
- " sam64\n"
- : /* no output register */
- : "a" (entry)
- : "memory");
-}
-
-/*
* Get hypfs_diag0c_entry from CPU vector and store diag0c data
*/
static void diag0c_fn(void *data)
{
- diag0c(((void **) data)[smp_processor_id()]);
+ diag_stat_inc(DIAG_STAT_X00C);
+ diag_dma_ops.diag0c(((void **) data)[smp_processor_id()]);
}
/*
@@ -54,8 +40,7 @@
if (!cpu_vec)
goto fail_put_online_cpus;
/* Note: Diag 0c needs 8 byte alignment and real storage */
- diag0c_data = kzalloc(sizeof(struct hypfs_diag0c_hdr) +
- cpu_count * sizeof(struct hypfs_diag0c_entry),
+ diag0c_data = kzalloc(struct_size(diag0c_data, entry, cpu_count),
GFP_KERNEL | GFP_DMA);
if (!diag0c_data)
goto fail_kfree_cpu_vec;
@@ -125,7 +110,8 @@
{
if (!MACHINE_IS_VM)
return 0;
- return hypfs_dbfs_create_file(&dbfs_file_0c);
+ hypfs_dbfs_create_file(&dbfs_file_0c);
+ return 0;
}
/*
diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c
index 5d85a03..7d9fb49 100644
--- a/arch/s390/hypfs/hypfs_sprp.c
+++ b/arch/s390/hypfs/hypfs_sprp.c
@@ -68,40 +68,44 @@
static int __hypfs_sprp_ioctl(void __user *user_area)
{
- struct hypfs_diag304 diag304;
+ struct hypfs_diag304 *diag304;
unsigned long cmd;
void __user *udata;
void *data;
int rc;
- if (copy_from_user(&diag304, user_area, sizeof(diag304)))
- return -EFAULT;
- if ((diag304.args[0] >> 8) != 0 || diag304.args[1] > DIAG304_CMD_MAX)
- return -EINVAL;
-
+ rc = -ENOMEM;
data = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
- if (!data)
- return -ENOMEM;
+ diag304 = kzalloc(sizeof(*diag304), GFP_KERNEL);
+ if (!data || !diag304)
+ goto out;
- udata = (void __user *)(unsigned long) diag304.data;
- if (diag304.args[1] == DIAG304_SET_WEIGHTS ||
- diag304.args[1] == DIAG304_SET_CAPPING)
- if (copy_from_user(data, udata, PAGE_SIZE)) {
- rc = -EFAULT;
+ rc = -EFAULT;
+ if (copy_from_user(diag304, user_area, sizeof(*diag304)))
+ goto out;
+ rc = -EINVAL;
+ if ((diag304->args[0] >> 8) != 0 || diag304->args[1] > DIAG304_CMD_MAX)
+ goto out;
+
+ rc = -EFAULT;
+ udata = (void __user *)(unsigned long) diag304->data;
+ if (diag304->args[1] == DIAG304_SET_WEIGHTS ||
+ diag304->args[1] == DIAG304_SET_CAPPING)
+ if (copy_from_user(data, udata, PAGE_SIZE))
goto out;
- }
- cmd = *(unsigned long *) &diag304.args[0];
- diag304.rc = hypfs_sprp_diag304(data, cmd);
+ cmd = *(unsigned long *) &diag304->args[0];
+ diag304->rc = hypfs_sprp_diag304(data, cmd);
- if (diag304.args[1] == DIAG304_QUERY_PRP)
+ if (diag304->args[1] == DIAG304_QUERY_PRP)
if (copy_to_user(udata, data, PAGE_SIZE)) {
rc = -EFAULT;
goto out;
}
- rc = copy_to_user(user_area, &diag304, sizeof(diag304)) ? -EFAULT : 0;
+ rc = copy_to_user(user_area, diag304, sizeof(*diag304)) ? -EFAULT : 0;
out:
+ kfree(diag304);
free_page((unsigned long) data);
return rc;
}
@@ -133,11 +137,11 @@
.unlocked_ioctl = hypfs_sprp_ioctl,
};
-int hypfs_sprp_init(void)
+void hypfs_sprp_init(void)
{
if (!sclp.has_sprp)
- return 0;
- return hypfs_dbfs_create_file(&hypfs_sprp_file);
+ return;
+ hypfs_dbfs_create_file(&hypfs_sprp_file);
}
void hypfs_sprp_exit(void)
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index c4b7b68..e1fcc03 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -118,7 +118,7 @@
return PTR_ERR(rc); \
} while(0)
-static int hpyfs_vm_create_guest(struct dentry *systems_dir,
+static int hypfs_vm_create_guest(struct dentry *systems_dir,
struct diag2fc_data *data)
{
char guest_name[NAME_LEN + 1] = {};
@@ -219,7 +219,7 @@
}
for (i = 0; i < count; i++) {
- rc = hpyfs_vm_create_guest(dir, &(data[i]));
+ rc = hypfs_vm_create_guest(dir, &(data[i]));
if (rc)
goto failed;
}
@@ -279,7 +279,8 @@
guest_query = local_guest;
else
return -EACCES;
- return hypfs_dbfs_create_file(&dbfs_file_2fc);
+ hypfs_dbfs_create_file(&dbfs_file_2fc);
+ return 0;
}
void hypfs_vm_exit(void)
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index c681329..70139d0 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -12,17 +12,17 @@
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/namei.h>
#include <linux/vfs.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/time.h>
-#include <linux/parser.h>
#include <linux/sysfs.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/seq_file.h>
-#include <linux/mount.h>
#include <linux/uio.h>
#include <asm/ebcdic.h>
#include "hypfs.h"
@@ -76,7 +76,7 @@
else
simple_unlink(d_inode(parent), dentry);
}
- d_delete(dentry);
+ d_drop(dentry);
dput(dentry);
inode_unlock(d_inode(parent));
}
@@ -207,52 +207,44 @@
return 0;
}
-enum { opt_uid, opt_gid, opt_err };
+enum { Opt_uid, Opt_gid, };
-static const match_table_t hypfs_tokens = {
- {opt_uid, "uid=%u"},
- {opt_gid, "gid=%u"},
- {opt_err, NULL}
+static const struct fs_parameter_spec hypfs_param_specs[] = {
+ fsparam_u32("gid", Opt_gid),
+ fsparam_u32("uid", Opt_uid),
+ {}
};
-static int hypfs_parse_options(char *options, struct super_block *sb)
+static const struct fs_parameter_description hypfs_fs_parameters = {
+ .name = "hypfs",
+ .specs = hypfs_param_specs,
+};
+
+static int hypfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
- char *str;
- substring_t args[MAX_OPT_ARGS];
+ struct hypfs_sb_info *hypfs_info = fc->s_fs_info;
+ struct fs_parse_result result;
kuid_t uid;
kgid_t gid;
+ int opt;
- if (!options)
- return 0;
- while ((str = strsep(&options, ",")) != NULL) {
- int token, option;
- struct hypfs_sb_info *hypfs_info = sb->s_fs_info;
+ opt = fs_parse(fc, &hypfs_fs_parameters, param, &result);
+ if (opt < 0)
+ return opt;
- if (!*str)
- continue;
- token = match_token(str, hypfs_tokens, args);
- switch (token) {
- case opt_uid:
- if (match_int(&args[0], &option))
- return -EINVAL;
- uid = make_kuid(current_user_ns(), option);
- if (!uid_valid(uid))
- return -EINVAL;
- hypfs_info->uid = uid;
- break;
- case opt_gid:
- if (match_int(&args[0], &option))
- return -EINVAL;
- gid = make_kgid(current_user_ns(), option);
- if (!gid_valid(gid))
- return -EINVAL;
- hypfs_info->gid = gid;
- break;
- case opt_err:
- default:
- pr_err("%s is not a valid mount option\n", str);
- return -EINVAL;
- }
+ switch (opt) {
+ case Opt_uid:
+ uid = make_kuid(current_user_ns(), result.uint_32);
+ if (!uid_valid(uid))
+ return invalf(fc, "Unknown uid");
+ hypfs_info->uid = uid;
+ break;
+ case Opt_gid:
+ gid = make_kgid(current_user_ns(), result.uint_32);
+ if (!gid_valid(gid))
+ return invalf(fc, "Unknown gid");
+ hypfs_info->gid = gid;
+ break;
}
return 0;
}
@@ -266,26 +258,18 @@
return 0;
}
-static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
+static int hypfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
+ struct hypfs_sb_info *sbi = sb->s_fs_info;
struct inode *root_inode;
- struct dentry *root_dentry;
- int rc = 0;
- struct hypfs_sb_info *sbi;
+ struct dentry *root_dentry, *update_file;
+ int rc;
- sbi = kzalloc(sizeof(struct hypfs_sb_info), GFP_KERNEL);
- if (!sbi)
- return -ENOMEM;
- mutex_init(&sbi->lock);
- sbi->uid = current_uid();
- sbi->gid = current_gid();
- sb->s_fs_info = sbi;
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = HYPFS_MAGIC;
sb->s_op = &hypfs_s_ops;
- if (hypfs_parse_options(data, sb))
- return -EINVAL;
+
root_inode = hypfs_make_inode(sb, S_IFDIR | 0755);
if (!root_inode)
return -ENOMEM;
@@ -300,18 +284,46 @@
rc = hypfs_diag_create_files(root_dentry);
if (rc)
return rc;
- sbi->update_file = hypfs_create_update_file(root_dentry);
- if (IS_ERR(sbi->update_file))
- return PTR_ERR(sbi->update_file);
+ update_file = hypfs_create_update_file(root_dentry);
+ if (IS_ERR(update_file))
+ return PTR_ERR(update_file);
+ sbi->update_file = update_file;
hypfs_update_update(sb);
pr_info("Hypervisor filesystem mounted\n");
return 0;
}
-static struct dentry *hypfs_mount(struct file_system_type *fst, int flags,
- const char *devname, void *data)
+static int hypfs_get_tree(struct fs_context *fc)
{
- return mount_single(fst, flags, data, hypfs_fill_super);
+ return get_tree_single(fc, hypfs_fill_super);
+}
+
+static void hypfs_free_fc(struct fs_context *fc)
+{
+ kfree(fc->s_fs_info);
+}
+
+static const struct fs_context_operations hypfs_context_ops = {
+ .free = hypfs_free_fc,
+ .parse_param = hypfs_parse_param,
+ .get_tree = hypfs_get_tree,
+};
+
+static int hypfs_init_fs_context(struct fs_context *fc)
+{
+ struct hypfs_sb_info *sbi;
+
+ sbi = kzalloc(sizeof(struct hypfs_sb_info), GFP_KERNEL);
+ if (!sbi)
+ return -ENOMEM;
+
+ mutex_init(&sbi->lock);
+ sbi->uid = current_uid();
+ sbi->gid = current_gid();
+
+ fc->s_fs_info = sbi;
+ fc->ops = &hypfs_context_ops;
+ return 0;
}
static void hypfs_kill_super(struct super_block *sb)
@@ -442,7 +454,8 @@
static struct file_system_type hypfs_type = {
.owner = THIS_MODULE,
.name = "s390_hypfs",
- .mount = hypfs_mount,
+ .init_fs_context = hypfs_init_fs_context,
+ .parameters = &hypfs_fs_parameters,
.kill_sb = hypfs_kill_super
};
@@ -456,9 +469,8 @@
{
int rc;
- rc = hypfs_dbfs_init();
- if (rc)
- return rc;
+ hypfs_dbfs_init();
+
if (hypfs_diag_init()) {
rc = -ENODATA;
goto fail_dbfs_exit;
@@ -467,10 +479,7 @@
rc = -ENODATA;
goto fail_hypfs_diag_exit;
}
- if (hypfs_sprp_init()) {
- rc = -ENODATA;
- goto fail_hypfs_vm_exit;
- }
+ hypfs_sprp_init();
if (hypfs_diag0c_init()) {
rc = -ENODATA;
goto fail_hypfs_sprp_exit;
@@ -489,7 +498,6 @@
hypfs_diag0c_exit();
fail_hypfs_sprp_exit:
hypfs_sprp_exit();
-fail_hypfs_vm_exit:
hypfs_vm_exit();
fail_hypfs_diag_exit:
hypfs_diag_exit();
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index e323977..2531f67 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -20,8 +20,7 @@
generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
-generic-y += preempt.h
-generic-y += rwsem.h
+generic-y += mmiowb.h
generic-y += trace_clock.h
generic-y += unaligned.h
generic-y += word-at-a-time.h
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index fcf539e..01936fd 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -11,10 +11,11 @@
#define _ASM_S390_AIRQ_H
#include <linux/bit_spinlock.h>
+#include <linux/dma-mapping.h>
struct airq_struct {
struct hlist_node list; /* Handler queueing. */
- void (*handler)(struct airq_struct *); /* Thin-interrupt handler */
+ void (*handler)(struct airq_struct *airq, bool floating);
u8 *lsi_ptr; /* Local-Summary-Indicator pointer */
u8 lsi_mask; /* Local-Summary-Indicator mask */
u8 isc; /* Interrupt-subclass */
@@ -29,19 +30,22 @@
/* Adapter interrupt bit vector */
struct airq_iv {
unsigned long *vector; /* Adapter interrupt bit vector */
+ dma_addr_t vector_dma; /* Adapter interrupt bit vector dma */
unsigned long *avail; /* Allocation bit mask for the bit vector */
unsigned long *bitlock; /* Lock bit mask for the bit vector */
unsigned long *ptr; /* Pointer associated with each bit */
unsigned int *data; /* 32 bit value associated with each bit */
unsigned long bits; /* Number of bits in the vector */
unsigned long end; /* Number of highest allocated bit + 1 */
+ unsigned long flags; /* Allocation flags */
spinlock_t lock; /* Lock to protect alloc & free */
};
-#define AIRQ_IV_ALLOC 1 /* Use an allocation bit mask */
-#define AIRQ_IV_BITLOCK 2 /* Allocate the lock bit mask */
-#define AIRQ_IV_PTR 4 /* Allocate the ptr array */
-#define AIRQ_IV_DATA 8 /* Allocate the data array */
+#define AIRQ_IV_ALLOC 1 /* Use an allocation bit mask */
+#define AIRQ_IV_BITLOCK 2 /* Allocate the lock bit mask */
+#define AIRQ_IV_PTR 4 /* Allocate the ptr array */
+#define AIRQ_IV_DATA 8 /* Allocate the data array */
+#define AIRQ_IV_CACHELINE 16 /* Cacheline alignment for the vector */
struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
void airq_iv_release(struct airq_iv *iv);
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index 8c00fd5..aea32dd 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -160,8 +160,8 @@
unsigned char Nd; /* max # of Domains - 1 */
unsigned char _reserved3[10];
unsigned int apm[8]; /* AP ID mask */
- unsigned int aqm[8]; /* AP queue mask */
- unsigned int adm[8]; /* AP domain mask */
+ unsigned int aqm[8]; /* AP (usage) queue mask */
+ unsigned int adm[8]; /* AP (control) domain mask */
unsigned char _reserved4[16];
} __aligned(8);
@@ -221,16 +221,22 @@
void *ind)
{
register unsigned long reg0 asm ("0") = qid | (3UL << 24);
- register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
- register struct ap_queue_status reg1_out asm ("1");
+ register union {
+ unsigned long value;
+ struct ap_qirq_ctrl qirqctrl;
+ struct ap_queue_status status;
+ } reg1 asm ("1");
register void *reg2 asm ("2") = ind;
+ reg1.qirqctrl = qirqctrl;
+
asm volatile(
".long 0xb2af0000" /* PQAP(AQIC) */
- : "=d" (reg1_out)
- : "d" (reg0), "d" (reg1_in), "d" (reg2)
+ : "+d" (reg1)
+ : "d" (reg0), "d" (reg2)
: "cc");
- return reg1_out;
+
+ return reg1.status;
}
/*
@@ -264,17 +270,21 @@
{
register unsigned long reg0 asm ("0") = qid | (5UL << 24)
| ((ifbit & 0x01) << 22);
- register unsigned long reg1_in asm ("1") = apinfo->val;
- register struct ap_queue_status reg1_out asm ("1");
+ register union {
+ unsigned long value;
+ struct ap_queue_status status;
+ } reg1 asm ("1");
register unsigned long reg2 asm ("2");
+ reg1.value = apinfo->val;
+
asm volatile(
".long 0xb2af0000" /* PQAP(QACT) */
- : "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2)
+ : "+d" (reg1), "=d" (reg2)
: "d" (reg0)
: "cc");
apinfo->val = reg2;
- return reg1_out;
+ return reg1.status;
}
/**
@@ -350,4 +360,15 @@
return reg1;
}
+/*
+ * Interface to tell the AP bus code that a configuration
+ * change has happened. The bus code should at least do
+ * an ap bus resource rescan.
+ */
+#if IS_ENABLED(CONFIG_ZCRYPT)
+void ap_bus_cfg_chg(void);
+#else
+static inline void ap_bus_cfg_chg(void){};
+#endif
+
#endif /* _ASM_S390_AP_H_ */
diff --git a/arch/s390/include/asm/appldata.h b/arch/s390/include/asm/appldata.h
index 4afbb59..c5bd9f4 100644
--- a/arch/s390/include/asm/appldata.h
+++ b/arch/s390/include/asm/appldata.h
@@ -40,26 +40,27 @@
u16 mod_lvl; /* modification level */
} __attribute__ ((packed));
-static inline int appldata_asm(struct appldata_product_id *id,
+
+static inline int appldata_asm(struct appldata_parameter_list *parm_list,
+ struct appldata_product_id *id,
unsigned short fn, void *buffer,
unsigned short length)
{
- struct appldata_parameter_list parm_list;
int ry;
if (!MACHINE_IS_VM)
return -EOPNOTSUPP;
- parm_list.diag = 0xdc;
- parm_list.function = fn;
- parm_list.parlist_length = sizeof(parm_list);
- parm_list.buffer_length = length;
- parm_list.product_id_addr = (unsigned long) id;
- parm_list.buffer_addr = virt_to_phys(buffer);
+ parm_list->diag = 0xdc;
+ parm_list->function = fn;
+ parm_list->parlist_length = sizeof(*parm_list);
+ parm_list->buffer_length = length;
+ parm_list->product_id_addr = (unsigned long) id;
+ parm_list->buffer_addr = virt_to_phys(buffer);
diag_stat_inc(DIAG_STAT_X0DC);
asm volatile(
" diag %1,%0,0xdc"
: "=d" (ry)
- : "d" (&parm_list), "m" (parm_list), "m" (*id)
+ : "d" (parm_list), "m" (*parm_list), "m" (*id)
: "cc");
return ry;
}
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index fd20ab5..491ad53 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -84,9 +84,9 @@
#define ATOMIC64_INIT(i) { (i) }
-static inline long atomic64_read(const atomic64_t *v)
+static inline s64 atomic64_read(const atomic64_t *v)
{
- long c;
+ s64 c;
asm volatile(
" lg %0,%1\n"
@@ -94,49 +94,49 @@
return c;
}
-static inline void atomic64_set(atomic64_t *v, long i)
+static inline void atomic64_set(atomic64_t *v, s64 i)
{
asm volatile(
" stg %1,%0\n"
: "=Q" (v->counter) : "d" (i));
}
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static inline s64 atomic64_add_return(s64 i, atomic64_t *v)
{
- return __atomic64_add_barrier(i, &v->counter) + i;
+ return __atomic64_add_barrier(i, (long *)&v->counter) + i;
}
-static inline long atomic64_fetch_add(long i, atomic64_t *v)
+static inline s64 atomic64_fetch_add(s64 i, atomic64_t *v)
{
- return __atomic64_add_barrier(i, &v->counter);
+ return __atomic64_add_barrier(i, (long *)&v->counter);
}
-static inline void atomic64_add(long i, atomic64_t *v)
+static inline void atomic64_add(s64 i, atomic64_t *v)
{
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
- __atomic64_add_const(i, &v->counter);
+ __atomic64_add_const(i, (long *)&v->counter);
return;
}
#endif
- __atomic64_add(i, &v->counter);
+ __atomic64_add(i, (long *)&v->counter);
}
#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+static inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
- return __atomic64_cmpxchg(&v->counter, old, new);
+ return __atomic64_cmpxchg((long *)&v->counter, old, new);
}
#define ATOMIC64_OPS(op) \
-static inline void atomic64_##op(long i, atomic64_t *v) \
+static inline void atomic64_##op(s64 i, atomic64_t *v) \
{ \
- __atomic64_##op(i, &v->counter); \
+ __atomic64_##op(i, (long *)&v->counter); \
} \
-static inline long atomic64_fetch_##op(long i, atomic64_t *v) \
+static inline long atomic64_fetch_##op(s64 i, atomic64_t *v) \
{ \
- return __atomic64_##op##_barrier(i, &v->counter); \
+ return __atomic64_##op##_barrier(i, (long *)&v->counter); \
}
ATOMIC64_OPS(and)
@@ -145,8 +145,8 @@
#undef ATOMIC64_OPS
-#define atomic64_sub_return(_i, _v) atomic64_add_return(-(long)(_i), _v)
-#define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(long)(_i), _v)
-#define atomic64_sub(_i, _v) atomic64_add(-(long)(_i), _v)
+#define atomic64_sub_return(_i, _v) atomic64_add_return(-(s64)(_i), _v)
+#define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(s64)(_i), _v)
+#define atomic64_sub(_i, _v) atomic64_add(-(s64)(_i), _v)
#endif /* __ARCH_S390_ATOMIC__ */
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index d3f0952..61467b9 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -41,7 +41,7 @@
#undef __ATOMIC_OP
#define __ATOMIC_CONST_OP(op_name, op_type, op_string, op_barrier) \
-static inline void op_name(op_type val, op_type *ptr) \
+static __always_inline void op_name(op_type val, op_type *ptr) \
{ \
asm volatile( \
op_string " %[ptr],%[val]\n" \
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 86e5b2f..eb7eed4 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -35,6 +35,7 @@
#include <linux/typecheck.h>
#include <linux/compiler.h>
+#include <linux/types.h>
#include <asm/atomic_ops.h>
#include <asm/barrier.h>
@@ -55,7 +56,7 @@
return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
}
-static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long mask;
@@ -73,10 +74,10 @@
}
#endif
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- __atomic64_or(mask, addr);
+ __atomic64_or(mask, (long *)addr);
}
-static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long mask;
@@ -94,10 +95,11 @@
}
#endif
mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
- __atomic64_and(mask, addr);
+ __atomic64_and(mask, (long *)addr);
}
-static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void arch_change_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long mask;
@@ -115,66 +117,67 @@
}
#endif
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- __atomic64_xor(mask, addr);
+ __atomic64_xor(mask, (long *)addr);
}
-static inline int
-test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch_test_and_set_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long old, mask;
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- old = __atomic64_or_barrier(mask, addr);
+ old = __atomic64_or_barrier(mask, (long *)addr);
return (old & mask) != 0;
}
-static inline int
-test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch_test_and_clear_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long old, mask;
mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
- old = __atomic64_and_barrier(mask, addr);
+ old = __atomic64_and_barrier(mask, (long *)addr);
return (old & ~mask) != 0;
}
-static inline int
-test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch_test_and_change_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long old, mask;
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- old = __atomic64_xor_barrier(mask, addr);
+ old = __atomic64_xor_barrier(mask, (long *)addr);
return (old & mask) != 0;
}
-static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch___set_bit(unsigned long nr, volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
*addr |= 1 << (nr & 7);
}
-static inline void
-__clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch___clear_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
*addr &= ~(1 << (nr & 7));
}
-static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch___change_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
*addr ^= 1 << (nr & 7);
}
-static inline int
-__test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch___test_and_set_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
unsigned char ch;
@@ -184,8 +187,8 @@
return (ch >> (nr & 7)) & 1;
}
-static inline int
-__test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch___test_and_clear_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
unsigned char ch;
@@ -195,8 +198,8 @@
return (ch >> (nr & 7)) & 1;
}
-static inline int
-__test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch___test_and_change_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
unsigned char ch;
@@ -206,7 +209,8 @@
return (ch >> (nr & 7)) & 1;
}
-static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr)
+static inline bool arch_test_bit(unsigned long nr,
+ const volatile unsigned long *ptr)
{
const volatile unsigned char *addr;
@@ -215,28 +219,30 @@
return (*addr >> (nr & 7)) & 1;
}
-static inline int test_and_set_bit_lock(unsigned long nr,
- volatile unsigned long *ptr)
+static inline bool arch_test_and_set_bit_lock(unsigned long nr,
+ volatile unsigned long *ptr)
{
- if (test_bit(nr, ptr))
+ if (arch_test_bit(nr, ptr))
return 1;
- return test_and_set_bit(nr, ptr);
+ return arch_test_and_set_bit(nr, ptr);
}
-static inline void clear_bit_unlock(unsigned long nr,
- volatile unsigned long *ptr)
+static inline void arch_clear_bit_unlock(unsigned long nr,
+ volatile unsigned long *ptr)
{
smp_mb__before_atomic();
- clear_bit(nr, ptr);
+ arch_clear_bit(nr, ptr);
}
-static inline void __clear_bit_unlock(unsigned long nr,
- volatile unsigned long *ptr)
+static inline void arch___clear_bit_unlock(unsigned long nr,
+ volatile unsigned long *ptr)
{
smp_mb();
- __clear_bit(nr, ptr);
+ arch___clear_bit(nr, ptr);
}
+#include <asm-generic/bitops-instrumented.h>
+
/*
* Functions which use MSB0 bit numbering.
* The bits are numbered:
@@ -261,7 +267,8 @@
return clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
-static inline int test_and_clear_bit_inv(unsigned long nr, volatile unsigned long *ptr)
+static inline bool test_and_clear_bit_inv(unsigned long nr,
+ volatile unsigned long *ptr)
{
return test_and_clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
@@ -276,8 +283,8 @@
return __clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
-static inline int test_bit_inv(unsigned long nr,
- const volatile unsigned long *ptr)
+static inline bool test_bit_inv(unsigned long nr,
+ const volatile unsigned long *ptr)
{
return test_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
@@ -397,9 +404,9 @@
* This is defined the same way as ffs.
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
*/
-static inline int fls(int word)
+static inline int fls(unsigned int word)
{
- return fls64((unsigned int)word);
+ return fls64(word);
}
#else /* CONFIG_HAVE_MARCH_Z9_109_FEATURES */
diff --git a/arch/s390/include/asm/boot_data.h b/arch/s390/include/asm/boot_data.h
new file mode 100644
index 0000000..f7eed27
--- /dev/null
+++ b/arch/s390/include/asm/boot_data.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_BOOT_DATA_H
+
+#include <asm/setup.h>
+#include <asm/ipl.h>
+
+extern char early_command_line[COMMAND_LINE_SIZE];
+extern struct ipl_parameter_block ipl_block;
+extern int ipl_block_valid;
+extern int ipl_secure_flag;
+
+extern unsigned long ipl_cert_list_addr;
+extern unsigned long ipl_cert_list_size;
+
+extern unsigned long early_ipl_comp_list_addr;
+extern unsigned long early_ipl_comp_list_size;
+
+#endif /* _ASM_S390_BOOT_DATA_H */
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index 429f43a..713fc97 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -15,7 +15,7 @@
".section .rodata.str,\"aMS\",@progbits,1\n" \
"2: .asciz \""__FILE__"\"\n" \
".previous\n" \
- ".section __bug_table,\"aw\"\n" \
+ ".section __bug_table,\"awM\",@progbits,%2\n" \
"3: .long 1b-3b,2b-3b\n" \
" .short %0,%1\n" \
" .org 3b+%2\n" \
@@ -27,17 +27,17 @@
#else /* CONFIG_DEBUG_BUGVERBOSE */
-#define __EMIT_BUG(x) do { \
- asm volatile( \
- "0: j 0b+2\n" \
- "1:\n" \
- ".section __bug_table,\"aw\"\n" \
- "2: .long 1b-2b\n" \
- " .short %0\n" \
- " .org 2b+%1\n" \
- ".previous\n" \
- : : "i" (x), \
- "i" (sizeof(struct bug_entry))); \
+#define __EMIT_BUG(x) do { \
+ asm volatile( \
+ "0: j 0b+2\n" \
+ "1:\n" \
+ ".section __bug_table,\"awM\",@progbits,%1\n" \
+ "2: .long 1b-2b\n" \
+ " .short %0\n" \
+ " .org 2b+%1\n" \
+ ".previous\n" \
+ : : "i" (x), \
+ "i" (sizeof(struct bug_entry))); \
} while (0)
#endif /* CONFIG_DEBUG_BUGVERBOSE */
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index a29dd43..865ce1c 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -226,6 +226,10 @@
extern void ccw_device_wait_idle(struct ccw_device *);
extern int ccw_device_force_console(struct ccw_device *);
+extern void *ccw_device_dma_zalloc(struct ccw_device *cdev, size_t size);
+extern void ccw_device_dma_free(struct ccw_device *cdev,
+ void *cpu_addr, size_t size);
+
int ccw_device_siosl(struct ccw_device *);
extern void ccw_device_get_schid(struct ccw_device *, struct subchannel_id *);
diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h
index 860cab7..7293c13 100644
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -64,6 +64,8 @@
extern void ccwgroup_driver_unregister (struct ccwgroup_driver *cdriver);
int ccwgroup_create_dev(struct device *root, struct ccwgroup_driver *gdrv,
int num_devices, const char *buf);
+struct ccwgroup_device *get_ccwgroupdev_by_busid(struct ccwgroup_driver *gdrv,
+ char *bus_id);
extern int ccwgroup_set_online(struct ccwgroup_device *gdev);
extern int ccwgroup_set_offline(struct ccwgroup_device *gdev);
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index 2256676..b5bfb31 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -7,6 +7,7 @@
#include <linux/spinlock.h>
#include <linux/bitops.h>
+#include <linux/genalloc.h>
#include <asm/types.h>
#define LPM_ANYPATH 0xff
@@ -264,6 +265,36 @@
#define CIW_TYPE_RNI 0x2 /* read node identifier */
/*
+ * Node Descriptor as defined in SA22-7204, "Common I/O-Device Commands"
+ */
+
+#define ND_VALIDITY_VALID 0
+#define ND_VALIDITY_OUTDATED 1
+#define ND_VALIDITY_INVALID 2
+
+struct node_descriptor {
+ /* Flags. */
+ union {
+ struct {
+ u32 validity:3;
+ u32 reserved:5;
+ } __packed;
+ u8 byte0;
+ } __packed;
+
+ /* Node parameters. */
+ u32 params:24;
+
+ /* Node ID. */
+ char type[6];
+ char model[3];
+ char manufacturer[3];
+ char plant[2];
+ char seq[12];
+ u16 tag;
+} __packed;
+
+/*
* Flags used as input parameters for do_IO()
*/
#define DOIO_ALLOW_SUSPEND 0x0001 /* allow for channel prog. suspend */
@@ -328,8 +359,19 @@
void channel_subsystem_reinit(void);
extern void css_schedule_reprobe(void);
+extern void *cio_dma_zalloc(size_t size);
+extern void cio_dma_free(void *cpu_addr, size_t size);
+extern struct device *cio_get_dma_css_dev(void);
+
+void *cio_gp_dma_zalloc(struct gen_pool *gp_dma, struct device *dma_dev,
+ size_t size);
+void cio_gp_dma_free(struct gen_pool *gp_dma, void *cpu_addr, size_t size);
+void cio_gp_dma_destroy(struct gen_pool *gp_dma, struct device *dma_dev);
+struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages);
+
/* Function from drivers/s390/cio/chsc.c */
int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta);
int chsc_sstpi(void *page, void *result, size_t size);
+int chsc_sgib(u32 origin);
#endif
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 97db2fb..63b46e3 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -9,6 +9,8 @@
#include <linux/sched/task_stack.h>
#include <linux/thread_info.h>
+#include <asm-generic/compat.h>
+
#define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p( \
typeof(0?(__force t)0:0ULL), u64))
@@ -51,34 +53,18 @@
#define COMPAT_USER_HZ 100
#define COMPAT_UTS_MACHINE "s390\0\0\0\0"
-typedef u32 compat_size_t;
-typedef s32 compat_ssize_t;
-typedef s32 compat_clock_t;
-typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
typedef u16 __compat_gid_t;
typedef u32 __compat_uid32_t;
typedef u32 __compat_gid32_t;
typedef u16 compat_mode_t;
-typedef u32 compat_ino_t;
typedef u16 compat_dev_t;
-typedef s32 compat_off_t;
-typedef s64 compat_loff_t;
typedef u16 compat_nlink_t;
typedef u16 compat_ipc_pid_t;
-typedef s32 compat_daddr_t;
typedef u32 compat_caddr_t;
typedef __kernel_fsid_t compat_fsid_t;
-typedef s32 compat_key_t;
-typedef s32 compat_timer_t;
-
-typedef s32 compat_int_t;
-typedef s32 compat_long_t;
typedef s64 compat_s64;
-typedef u32 compat_uint_t;
-typedef u32 compat_ulong_t;
typedef u64 compat_u64;
-typedef u32 compat_uptr_t;
typedef struct {
u32 mask;
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index 3cc52e3..c0f3bfe 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -28,6 +28,7 @@
#define CPACF_KMCTR 0xb92d /* MSA4 */
#define CPACF_PRNO 0xb93c /* MSA5 */
#define CPACF_KMA 0xb929 /* MSA8 */
+#define CPACF_KDSA 0xb93a /* MSA9 */
/*
* En/decryption modifier bits
@@ -92,6 +93,10 @@
#define CPACF_KIMD_SHA_1 0x01
#define CPACF_KIMD_SHA_256 0x02
#define CPACF_KIMD_SHA_512 0x03
+#define CPACF_KIMD_SHA3_224 0x20
+#define CPACF_KIMD_SHA3_256 0x21
+#define CPACF_KIMD_SHA3_384 0x22
+#define CPACF_KIMD_SHA3_512 0x23
#define CPACF_KIMD_GHASH 0x41
/*
@@ -102,6 +107,10 @@
#define CPACF_KLMD_SHA_1 0x01
#define CPACF_KLMD_SHA_256 0x02
#define CPACF_KLMD_SHA_512 0x03
+#define CPACF_KLMD_SHA3_224 0x20
+#define CPACF_KLMD_SHA3_256 0x21
+#define CPACF_KLMD_SHA3_384 0x22
+#define CPACF_KLMD_SHA3_512 0x23
/*
* function codes for the KMAC (COMPUTE MESSAGE AUTHENTICATION CODE)
@@ -162,7 +171,7 @@
*
* Returns 1 if @func is available for @opcode, 0 otherwise
*/
-static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
+static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
{
register unsigned long r0 asm("0") = 0; /* query function */
register unsigned long r1 asm("1") = (unsigned long) mask;
@@ -177,7 +186,7 @@
: "cc");
}
-static inline int __cpacf_check_opcode(unsigned int opcode)
+static __always_inline int __cpacf_check_opcode(unsigned int opcode)
{
switch (opcode) {
case CPACF_KMAC:
@@ -202,7 +211,7 @@
}
}
-static inline int cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
+static __always_inline int cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
{
if (__cpacf_check_opcode(opcode)) {
__cpacf_query(opcode, mask);
@@ -217,7 +226,7 @@
return (mask->bytes[func >> 3] & (0x80 >> (func & 7))) != 0;
}
-static inline int cpacf_query_func(unsigned int opcode, unsigned int func)
+static __always_inline int cpacf_query_func(unsigned int opcode, unsigned int func)
{
cpacf_mask_t mask;
diff --git a/arch/s390/include/asm/cpu_mcf.h b/arch/s390/include/asm/cpu_mcf.h
new file mode 100644
index 0000000..649b9fc
--- /dev/null
+++ b/arch/s390/include/asm/cpu_mcf.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Counter facility support definitions for the Linux perf
+ *
+ * Copyright IBM Corp. 2019
+ * Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
+ */
+#ifndef _ASM_S390_CPU_MCF_H
+#define _ASM_S390_CPU_MCF_H
+
+#include <linux/perf_event.h>
+#include <asm/cpu_mf.h>
+
+enum cpumf_ctr_set {
+ CPUMF_CTR_SET_BASIC = 0, /* Basic Counter Set */
+ CPUMF_CTR_SET_USER = 1, /* Problem-State Counter Set */
+ CPUMF_CTR_SET_CRYPTO = 2, /* Crypto-Activity Counter Set */
+ CPUMF_CTR_SET_EXT = 3, /* Extended Counter Set */
+ CPUMF_CTR_SET_MT_DIAG = 4, /* MT-diagnostic Counter Set */
+
+ /* Maximum number of counter sets */
+ CPUMF_CTR_SET_MAX,
+};
+
+#define CPUMF_LCCTL_ENABLE_SHIFT 16
+#define CPUMF_LCCTL_ACTCTL_SHIFT 0
+static const u64 cpumf_ctr_ctl[CPUMF_CTR_SET_MAX] = {
+ [CPUMF_CTR_SET_BASIC] = 0x02,
+ [CPUMF_CTR_SET_USER] = 0x04,
+ [CPUMF_CTR_SET_CRYPTO] = 0x08,
+ [CPUMF_CTR_SET_EXT] = 0x01,
+ [CPUMF_CTR_SET_MT_DIAG] = 0x20,
+};
+
+static inline void ctr_set_enable(u64 *state, int ctr_set)
+{
+ *state |= cpumf_ctr_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT;
+}
+static inline void ctr_set_disable(u64 *state, int ctr_set)
+{
+ *state &= ~(cpumf_ctr_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT);
+}
+static inline void ctr_set_start(u64 *state, int ctr_set)
+{
+ *state |= cpumf_ctr_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT;
+}
+static inline void ctr_set_stop(u64 *state, int ctr_set)
+{
+ *state &= ~(cpumf_ctr_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT);
+}
+
+static inline void ctr_set_multiple_enable(u64 *state, u64 ctrsets)
+{
+ *state |= ctrsets << CPUMF_LCCTL_ENABLE_SHIFT;
+}
+
+static inline void ctr_set_multiple_disable(u64 *state, u64 ctrsets)
+{
+ *state &= ~(ctrsets << CPUMF_LCCTL_ENABLE_SHIFT);
+}
+
+static inline void ctr_set_multiple_start(u64 *state, u64 ctrsets)
+{
+ *state |= ctrsets << CPUMF_LCCTL_ACTCTL_SHIFT;
+}
+
+static inline void ctr_set_multiple_stop(u64 *state, u64 ctrsets)
+{
+ *state &= ~(ctrsets << CPUMF_LCCTL_ACTCTL_SHIFT);
+}
+
+static inline int ctr_stcctm(enum cpumf_ctr_set set, u64 range, u64 *dest)
+{
+ switch (set) {
+ case CPUMF_CTR_SET_BASIC:
+ return stcctm(BASIC, range, dest);
+ case CPUMF_CTR_SET_USER:
+ return stcctm(PROBLEM_STATE, range, dest);
+ case CPUMF_CTR_SET_CRYPTO:
+ return stcctm(CRYPTO_ACTIVITY, range, dest);
+ case CPUMF_CTR_SET_EXT:
+ return stcctm(EXTENDED, range, dest);
+ case CPUMF_CTR_SET_MT_DIAG:
+ return stcctm(MT_DIAG_CLEARING, range, dest);
+ case CPUMF_CTR_SET_MAX:
+ return 3;
+ }
+ return 3;
+}
+
+struct cpu_cf_events {
+ struct cpumf_ctr_info info;
+ atomic_t ctr_set[CPUMF_CTR_SET_MAX];
+ atomic64_t alert;
+ u64 state, tx_state;
+ unsigned int flags;
+ unsigned int txn_flags;
+};
+DECLARE_PER_CPU(struct cpu_cf_events, cpu_cf_events);
+
+bool kernel_cpumcf_avail(void);
+int __kernel_cpumcf_begin(void);
+unsigned long kernel_cpumcf_alert(int clear);
+void __kernel_cpumcf_end(void);
+
+static inline int kernel_cpumcf_begin(void)
+{
+ if (!cpum_cf_avail())
+ return -ENODEV;
+
+ preempt_disable();
+ return __kernel_cpumcf_begin();
+}
+static inline void kernel_cpumcf_end(void)
+{
+ __kernel_cpumcf_end();
+ preempt_enable();
+}
+
+/* Return true if store counter set multiple instruction is available */
+static inline int stccm_avail(void)
+{
+ return test_facility(142);
+}
+
+#endif /* _ASM_S390_CPU_MCF_H */
diff --git a/arch/s390/include/asm/cpu_mf-insn.h b/arch/s390/include/asm/cpu_mf-insn.h
new file mode 100644
index 0000000..a68b362
--- /dev/null
+++ b/arch/s390/include/asm/cpu_mf-insn.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Support for CPU-MF instructions
+ *
+ * Copyright IBM Corp. 2019
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+#ifndef _ASM_S390_CPU_MF_INSN_H
+#define _ASM_S390_CPU_MF_INSN_H
+
+#ifdef __ASSEMBLY__
+
+/* Macro to generate the STCCTM instruction with a customized
+ * M3 field designating the counter set.
+ */
+.macro STCCTM r1 m3 db2
+ .insn rsy,0xeb0000000017,\r1,\m3 & 0xf,\db2
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index bf2cbff..819803a 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -12,6 +12,8 @@
#include <linux/errno.h>
#include <asm/facility.h>
+asm(".include \"asm/cpu_mf-insn.h\"\n");
+
#define CPU_MF_INT_SF_IAE (1 << 31) /* invalid entry address */
#define CPU_MF_INT_SF_ISE (1 << 30) /* incorrect SDBT entry */
#define CPU_MF_INT_SF_PRA (1 << 29) /* program request alert */
@@ -26,6 +28,8 @@
CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA| \
CPU_MF_INT_SF_LSDA)
+#define CPU_MF_SF_RIBM_NOTAV 0x1 /* Sampling unavailable */
+
/* CPU measurement facility support */
static inline int cpum_cf_avail(void)
{
@@ -67,8 +71,9 @@
unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
unsigned long tear; /* 24-31: TEAR contents */
unsigned long dear; /* 32-39: DEAR contents */
- unsigned int rsvrd0; /* 40-43: reserved */
- unsigned int cpu_speed; /* 44-47: CPU speed */
+ unsigned int rsvrd0:24; /* 40-42: reserved */
+ unsigned int ribm:8; /* 43: Reserved by IBM */
+ unsigned int cpu_speed; /* 44-47: CPU speed */
unsigned long long rsvrd1; /* 48-55: reserved */
unsigned long long rsvrd2; /* 56-63: reserved */
} __packed;
@@ -87,10 +92,10 @@
unsigned long tear; /* 16-23: TEAR contents */
unsigned long dear; /* 24-31: DEAR contents */
/* 32-63: */
- unsigned long rsvrd1; /* reserved */
- unsigned long rsvrd2; /* reserved */
- unsigned long rsvrd3; /* reserved */
- unsigned long rsvrd4; /* reserved */
+ unsigned long rsvrd1; /* reserved */
+ unsigned long rsvrd2; /* reserved */
+ unsigned long rsvrd3; /* reserved */
+ unsigned long rsvrd4; /* reserved */
} __packed;
struct hws_basic_entry {
@@ -209,17 +214,26 @@
return cc;
}
-/* Store CPU counter multiple for the MT utilization counter set */
-static inline int stcctm5(u64 num, u64 *val)
+/* Store CPU counter multiple for a particular counter set */
+enum stcctm_ctr_set {
+ EXTENDED = 0,
+ BASIC = 1,
+ PROBLEM_STATE = 2,
+ CRYPTO_ACTIVITY = 3,
+ MT_DIAG = 5,
+ MT_DIAG_CLEARING = 9, /* clears loss-of-MT-ctr-data alert */
+};
+
+static __always_inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest)
{
int cc;
asm volatile (
- " .insn rsy,0xeb0000000017,%2,5,%1\n"
+ " STCCTM %2,%3,%1\n"
" ipm %0\n"
" srl %0,28\n"
: "=d" (cc)
- : "Q" (*val), "d" (num)
+ : "Q" (*dest), "d" (range), "i" (set)
: "cc", "memory");
return cc;
}
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index 4600453..60f9075 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -8,27 +8,27 @@
#ifndef __ASM_CTL_REG_H
#define __ASM_CTL_REG_H
-#include <linux/const.h>
+#include <linux/bits.h>
-#define CR0_CLOCK_COMPARATOR_SIGN _BITUL(63 - 10)
-#define CR0_EMERGENCY_SIGNAL_SUBMASK _BITUL(63 - 49)
-#define CR0_EXTERNAL_CALL_SUBMASK _BITUL(63 - 50)
-#define CR0_CLOCK_COMPARATOR_SUBMASK _BITUL(63 - 52)
-#define CR0_CPU_TIMER_SUBMASK _BITUL(63 - 53)
-#define CR0_SERVICE_SIGNAL_SUBMASK _BITUL(63 - 54)
-#define CR0_UNUSED_56 _BITUL(63 - 56)
-#define CR0_INTERRUPT_KEY_SUBMASK _BITUL(63 - 57)
-#define CR0_MEASUREMENT_ALERT_SUBMASK _BITUL(63 - 58)
+#define CR0_CLOCK_COMPARATOR_SIGN BIT(63 - 10)
+#define CR0_EMERGENCY_SIGNAL_SUBMASK BIT(63 - 49)
+#define CR0_EXTERNAL_CALL_SUBMASK BIT(63 - 50)
+#define CR0_CLOCK_COMPARATOR_SUBMASK BIT(63 - 52)
+#define CR0_CPU_TIMER_SUBMASK BIT(63 - 53)
+#define CR0_SERVICE_SIGNAL_SUBMASK BIT(63 - 54)
+#define CR0_UNUSED_56 BIT(63 - 56)
+#define CR0_INTERRUPT_KEY_SUBMASK BIT(63 - 57)
+#define CR0_MEASUREMENT_ALERT_SUBMASK BIT(63 - 58)
-#define CR2_GUARDED_STORAGE _BITUL(63 - 59)
+#define CR2_GUARDED_STORAGE BIT(63 - 59)
-#define CR14_UNUSED_32 _BITUL(63 - 32)
-#define CR14_UNUSED_33 _BITUL(63 - 33)
-#define CR14_CHANNEL_REPORT_SUBMASK _BITUL(63 - 35)
-#define CR14_RECOVERY_SUBMASK _BITUL(63 - 36)
-#define CR14_DEGRADATION_SUBMASK _BITUL(63 - 37)
-#define CR14_EXTERNAL_DAMAGE_SUBMASK _BITUL(63 - 38)
-#define CR14_WARNING_SUBMASK _BITUL(63 - 39)
+#define CR14_UNUSED_32 BIT(63 - 32)
+#define CR14_UNUSED_33 BIT(63 - 33)
+#define CR14_CHANNEL_REPORT_SUBMASK BIT(63 - 35)
+#define CR14_RECOVERY_SUBMASK BIT(63 - 36)
+#define CR14_DEGRADATION_SUBMASK BIT(63 - 37)
+#define CR14_EXTERNAL_DAMAGE_SUBMASK BIT(63 - 38)
+#define CR14_WARNING_SUBMASK BIT(63 - 39)
#ifndef __ASSEMBLY__
@@ -55,7 +55,7 @@
: "i" (low), "i" (high)); \
} while (0)
-static inline void __ctl_set_bit(unsigned int cr, unsigned int bit)
+static __always_inline void __ctl_set_bit(unsigned int cr, unsigned int bit)
{
unsigned long reg;
@@ -64,7 +64,7 @@
__ctl_load(reg, cr, cr);
}
-static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
+static __always_inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
{
unsigned long reg;
@@ -112,13 +112,8 @@
};
};
-#ifdef CONFIG_SMP
-# define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
-# define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
-#else
-# define ctl_set_bit(cr, bit) __ctl_set_bit(cr, bit)
-# define ctl_clear_bit(cr, bit) __ctl_clear_bit(cr, bit)
-#endif
+#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
+#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
#endif /* __ASSEMBLY__ */
#endif /* __ASM_CTL_REG_H */
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index c305d39..3101340 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -107,13 +107,37 @@
void debug_set_level(debug_info_t *id, int new_level);
void debug_set_critical(void);
+
void debug_stop_all(void);
+/**
+ * debug_level_enabled() - Returns true if debug events for the specified
+ * level would be logged. Otherwise returns false.
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ *
+ * Return:
+ * - %true if level is less or equal to the current debug level.
+ */
static inline bool debug_level_enabled(debug_info_t *id, int level)
{
return level <= id->level;
}
+/**
+ * debug_event() - writes binary debug entry to active debug area
+ * (if level <= actual debug level)
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ * @data: pointer to data for debug entry
+ * @length: length of data in bytes
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ */
static inline debug_entry_t *debug_event(debug_info_t *id, int level,
void *data, int length)
{
@@ -122,6 +146,18 @@
return debug_event_common(id, level, data, length);
}
+/**
+ * debug_int_event() - writes unsigned integer debug entry to active debug area
+ * (if level <= actual debug level)
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ * @tag: integer value for debug entry
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ */
static inline debug_entry_t *debug_int_event(debug_info_t *id, int level,
unsigned int tag)
{
@@ -132,6 +168,18 @@
return debug_event_common(id, level, &t, sizeof(unsigned int));
}
+/**
+ * debug_long_event() - writes unsigned long debug entry to active debug area
+ * (if level <= actual debug level)
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ * @tag: long integer value for debug entry
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ */
static inline debug_entry_t *debug_long_event(debug_info_t *id, int level,
unsigned long tag)
{
@@ -142,6 +190,18 @@
return debug_event_common(id, level, &t, sizeof(unsigned long));
}
+/**
+ * debug_text_event() - writes string debug entry in ascii format to active
+ * debug area (if level <= actual debug level)
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ * @txt: string for debug entry
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ */
static inline debug_entry_t *debug_text_event(debug_info_t *id, int level,
const char *txt)
{
@@ -152,12 +212,28 @@
/*
* IMPORTANT: Use "%s" in sprintf format strings with care! Only pointers are
- * stored in the s390dbf. See Documentation/s390/s390dbf.txt for more details!
+ * stored in the s390dbf. See Documentation/s390/s390dbf.rst for more details!
*/
extern debug_entry_t *
__debug_sprintf_event(debug_info_t *id, int level, char *string, ...)
__attribute__ ((format(printf, 3, 4)));
+/**
+ * debug_sprintf_event() - writes debug entry with format string
+ * and varargs (longs) to active debug area
+ * (if level $<=$ actual debug level).
+ *
+ * @_id: handle for debug log
+ * @_level: debug level
+ * @_fmt: format string for debug entry
+ * @...: varargs used as in sprintf()
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ *
+ * floats and long long datatypes cannot be used as varargs.
+ */
#define debug_sprintf_event(_id, _level, _fmt, ...) \
({ \
debug_entry_t *__ret; \
@@ -172,6 +248,20 @@
__ret; \
})
+/**
+ * debug_exception() - writes binary debug entry to active debug area
+ * (if level <= actual debug level)
+ * and switches to next debug area
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ * @data: pointer to data for debug entry
+ * @length: length of data in bytes
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ */
static inline debug_entry_t *debug_exception(debug_info_t *id, int level,
void *data, int length)
{
@@ -180,6 +270,19 @@
return debug_exception_common(id, level, data, length);
}
+/**
+ * debug_int_exception() - writes unsigned int debug entry to active debug area
+ * (if level <= actual debug level)
+ * and switches to next debug area
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ * @tag: integer value for debug entry
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ */
static inline debug_entry_t *debug_int_exception(debug_info_t *id, int level,
unsigned int tag)
{
@@ -190,6 +293,19 @@
return debug_exception_common(id, level, &t, sizeof(unsigned int));
}
+/**
+ * debug_long_exception() - writes long debug entry to active debug area
+ * (if level <= actual debug level)
+ * and switches to next debug area
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ * @tag: long integer value for debug entry
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ */
static inline debug_entry_t *debug_long_exception (debug_info_t *id, int level,
unsigned long tag)
{
@@ -200,6 +316,20 @@
return debug_exception_common(id, level, &t, sizeof(unsigned long));
}
+/**
+ * debug_text_exception() - writes string debug entry in ascii format to active
+ * debug area (if level <= actual debug level)
+ * and switches to next debug area
+ * area
+ *
+ * @id: handle for debug log
+ * @level: debug level
+ * @txt: string for debug entry
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ */
static inline debug_entry_t *debug_text_exception(debug_info_t *id, int level,
const char *txt)
{
@@ -210,12 +340,30 @@
/*
* IMPORTANT: Use "%s" in sprintf format strings with care! Only pointers are
- * stored in the s390dbf. See Documentation/s390/s390dbf.txt for more details!
+ * stored in the s390dbf. See Documentation/s390/s390dbf.rst for more details!
*/
extern debug_entry_t *
__debug_sprintf_exception(debug_info_t *id, int level, char *string, ...)
__attribute__ ((format(printf, 3, 4)));
+
+/**
+ * debug_sprintf_exception() - writes debug entry with format string and
+ * varargs (longs) to active debug area
+ * (if level <= actual debug level)
+ * and switches to next debug area.
+ *
+ * @_id: handle for debug log
+ * @_level: debug level
+ * @_fmt: format string for debug entry
+ * @...: varargs used as in sprintf()
+ *
+ * Return:
+ * - Address of written debug entry
+ * - %NULL if error
+ *
+ * floats and long long datatypes cannot be used as varargs.
+ */
#define debug_sprintf_exception(_id, _level, _fmt, ...) \
({ \
debug_entry_t *__ret; \
@@ -231,6 +379,7 @@
})
int debug_register_view(debug_info_t *id, struct debug_view *view);
+
int debug_unregister_view(debug_info_t *id, struct debug_view *view);
/*
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index cdbaad5..0036eab 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -32,6 +32,7 @@
DIAG_STAT_X2FC,
DIAG_STAT_X304,
DIAG_STAT_X308,
+ DIAG_STAT_X318,
DIAG_STAT_X500,
NR_DIAG_STAT
};
@@ -293,7 +294,31 @@
u8 res[2];
} __aligned(8);
+#define CPNC_LINUX 0x4
+union diag318_info {
+ unsigned long val;
+ struct {
+ unsigned int cpnc : 8;
+ unsigned int cpvc_linux : 24;
+ unsigned char cpvc_distro[3];
+ unsigned char zero;
+ };
+};
+
int diag204(unsigned long subcode, unsigned long size, void *addr);
int diag224(void *ptr);
int diag26c(void *req, void *resp, enum diag26c_sc subcode);
+
+struct hypfs_diag0c_entry;
+
+struct diag_ops {
+ int (*diag210)(struct diag210 *addr);
+ int (*diag26c)(void *req, void *resp, enum diag26c_sc subcode);
+ int (*diag14)(unsigned long rx, unsigned long ry1, unsigned long subcode);
+ void (*diag0c)(struct hypfs_diag0c_entry *entry);
+ void (*diag308_reset)(void);
+};
+
+extern struct diag_ops diag_dma_ops;
+extern struct diag210 *__diag210_tmp_dma;
#endif /* _ASM_S390_DIAG_H */
diff --git a/arch/s390/include/asm/ebcdic.h b/arch/s390/include/asm/ebcdic.h
index 29441be..efb50fc 100644
--- a/arch/s390/include/asm/ebcdic.h
+++ b/arch/s390/include/asm/ebcdic.h
@@ -20,7 +20,7 @@
extern __u8 _ebc_toupper[256]; /* EBCDIC -> uppercase */
static inline void
-codepage_convert(const __u8 *codepage, volatile __u8 * addr, unsigned long nr)
+codepage_convert(const __u8 *codepage, volatile char *addr, unsigned long nr)
{
if (nr-- <= 0)
return;
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 7d22a47..5775fc2 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -107,6 +107,10 @@
#define HWCAP_S390_VXRS_BCD 4096
#define HWCAP_S390_VXRS_EXT 8192
#define HWCAP_S390_GS 16384
+#define HWCAP_S390_VXRS_EXT2 32768
+#define HWCAP_S390_VXRS_PDE 65536
+#define HWCAP_S390_SORT 131072
+#define HWCAP_S390_DFLT 262144
/* Internal bits, not exposed via elf */
#define HWCAP_INT_SIE 1UL
@@ -252,11 +256,14 @@
/*
* Cache aliasing on the latest machines calls for a mapping granularity
- * of 512KB. For 64-bit processes use a 512KB alignment and a randomization
- * of up to 1GB. For 31-bit processes the virtual address space is limited,
- * use no alignment and limit the randomization to 8MB.
+ * of 512KB for the anonymous mapping base. For 64-bit processes use a
+ * 512KB alignment and a randomization of up to 1GB. For 31-bit processes
+ * the virtual address space is limited, use no alignment and limit the
+ * randomization to 8MB.
+ * For the additional randomization of the program break use 32MB for
+ * 64-bit and 8MB for 31-bit.
*/
-#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ffffUL)
+#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x1fffUL)
#define MMAP_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ff80UL)
#define MMAP_ALIGN_MASK (is_compat_task() ? 0 : 0x7fUL)
#define STACK_RND_MASK MMAP_RND_MASK
diff --git a/arch/s390/include/asm/extable.h b/arch/s390/include/asm/extable.h
index 80a4e5a..ae27f75 100644
--- a/arch/s390/include/asm/extable.h
+++ b/arch/s390/include/asm/extable.h
@@ -19,6 +19,11 @@
int insn, fixup;
};
+extern struct exception_table_entry *__start_dma_ex_table;
+extern struct exception_table_entry *__stop_dma_ex_table;
+
+const struct exception_table_entry *s390_search_extables(unsigned long addr);
+
static inline unsigned long extable_fixup(const struct exception_table_entry *x)
{
return (unsigned long)&x->fixup + x->fixup;
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 99c8ce3..68c476b 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -59,16 +59,27 @@
return __test_facility(nr, &S390_lowcore.stfle_fac_list);
}
+static inline unsigned long __stfle_asm(u64 *stfle_fac_list, int size)
+{
+ register unsigned long reg0 asm("0") = size - 1;
+
+ asm volatile(
+ ".insn s,0xb2b00000,0(%1)" /* stfle */
+ : "+d" (reg0)
+ : "a" (stfle_fac_list)
+ : "memory", "cc");
+ return reg0;
+}
+
/**
* stfle - Store facility list extended
* @stfle_fac_list: array where facility list can be stored
* @size: size of passed in array in double words
*/
-static inline void stfle(u64 *stfle_fac_list, int size)
+static inline void __stfle(u64 *stfle_fac_list, int size)
{
unsigned long nr;
- preempt_disable();
asm volatile(
" stfl 0(0)\n"
: "=m" (S390_lowcore.stfl_fac_list));
@@ -76,15 +87,16 @@
memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
if (S390_lowcore.stfl_fac_list & 0x01000000) {
/* More facility bits available with stfle */
- register unsigned long reg0 asm("0") = size - 1;
-
- asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
- : "+d" (reg0)
- : "a" (stfle_fac_list)
- : "memory", "cc");
- nr = (reg0 + 1) * 8; /* # bytes stored by stfle */
+ nr = __stfle_asm(stfle_fac_list, size);
+ nr = min_t(unsigned long, (nr + 1) * 8, size * 8);
}
memset((char *) stfle_fac_list + nr, 0, size * 8 - nr);
+}
+
+static inline void stfle(u64 *stfle_fac_list, int size)
+{
+ preempt_disable();
+ __stfle(stfle_fac_list, size);
preempt_enable();
}
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 8ea270f..68d362f 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -11,9 +11,16 @@
#define MCOUNT_RETURN_FIXUP 18
#endif
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
#ifndef __ASSEMBLY__
+#ifdef CONFIG_CC_IS_CLANG
+/* https://bugs.llvm.org/show_bug.cgi?id=41424 */
+#define ftrace_return_address(n) 0UL
+#else
#define ftrace_return_address(n) __builtin_return_address(n)
+#endif
void _mcount(void);
void ftrace_caller(void);
@@ -81,5 +88,30 @@
#endif
}
+/*
+ * Even though the system call numbers are identical for s390/s390x a
+ * different system call table is used for compat tasks. This may lead
+ * to e.g. incorrect or missing trace event sysfs files.
+ * Therefore simply do not trace compat system calls at all.
+ * See kernel/trace/trace_syscalls.c.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+ return is_compat_task();
+}
+
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym,
+ const char *name)
+{
+ /*
+ * Skip __s390_ and __s390x_ prefix - due to compat wrappers
+ * and aliasing some symbols of 64 bit system call functions
+ * may get the __s390_ prefix instead of the __s390x_ prefix.
+ */
+ return !strcmp(sym + 7, name) || !strcmp(sym + 8, name);
+}
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_S390_FTRACE_H */
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index fcbd638..37f96b6 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -9,6 +9,8 @@
#ifndef _ASM_S390_GMAP_H
#define _ASM_S390_GMAP_H
+#include <linux/refcount.h>
+
/* Generic bits for GMAP notification on DAT table entry changes. */
#define GMAP_NOTIFY_SHADOW 0x2
#define GMAP_NOTIFY_MPROT 0x1
@@ -46,7 +48,7 @@
struct radix_tree_root guest_to_host;
struct radix_tree_root host_to_guest;
spinlock_t guest_table_lock;
- atomic_t ref_count;
+ refcount_t ref_count;
unsigned long *table;
unsigned long asce;
unsigned long asce_end;
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 2d1afa5..de8f0bf 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -12,8 +12,6 @@
#include <asm/page.h>
#include <asm/pgtable.h>
-
-#define is_hugepage_only_range(mm, addr, len) 0
#define hugetlb_free_pgd_range free_pgd_range
#define hugepages_supported() (MACHINE_HAS_EDAT1)
@@ -23,6 +21,13 @@
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep);
+static inline bool is_hugepage_only_range(struct mm_struct *mm,
+ unsigned long addr,
+ unsigned long len)
+{
+ return false;
+}
+
/*
* If the arch doesn't supply something else, assume that hugepage
* size aligned regions are ok without further preparation.
@@ -116,7 +121,9 @@
return pte_modify(pte, newprot);
}
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
+static inline bool gigantic_page_runtime_supported(void)
+{
+ return true;
+}
+
#endif /* _ASM_S390_HUGETLB_H */
diff --git a/arch/s390/include/asm/idals.h b/arch/s390/include/asm/idals.h
index 15578fd..6fb7ace 100644
--- a/arch/s390/include/asm/idals.h
+++ b/arch/s390/include/asm/idals.h
@@ -122,8 +122,7 @@
nr_ptrs = (size + IDA_BLOCK_SIZE - 1) >> IDA_SIZE_LOG;
nr_chunks = (4096 << page_order) >> IDA_SIZE_LOG;
- ib = kmalloc(sizeof(struct idal_buffer) + nr_ptrs*sizeof(void *),
- GFP_DMA | GFP_KERNEL);
+ ib = kmalloc(struct_size(ib, data, nr_ptrs), GFP_DMA | GFP_KERNEL);
if (ib == NULL)
return ERR_PTR(-ENOMEM);
ib->size = size;
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index f34d729..ca42161 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -30,14 +30,8 @@
#define ioremap_wc ioremap_nocache
#define ioremap_wt ioremap_nocache
-static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
-{
- return (void __iomem *) offset;
-}
-
-static inline void iounmap(volatile void __iomem *addr)
-{
-}
+void __iomem *ioremap(unsigned long offset, unsigned long size);
+void iounmap(volatile void __iomem *addr);
static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
{
@@ -57,14 +51,17 @@
* the corresponding device and create the mapping cookie.
*/
#define pci_iomap pci_iomap
+#define pci_iomap_range pci_iomap_range
#define pci_iounmap pci_iounmap
-#define pci_iomap_wc pci_iomap
-#define pci_iomap_wc_range pci_iomap_range
+#define pci_iomap_wc pci_iomap_wc
+#define pci_iomap_wc_range pci_iomap_wc_range
#define memcpy_fromio(dst, src, count) zpci_memcpy_fromio(dst, src, count)
#define memcpy_toio(dst, src, count) zpci_memcpy_toio(dst, src, count)
#define memset_io(dst, val, count) zpci_memset_io(dst, val, count)
+#define mmiowb() zpci_barrier()
+
#define __raw_readb zpci_read_u8
#define __raw_readw zpci_read_u16
#define __raw_readl zpci_read_u32
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index ae51357..084e71b 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -12,74 +12,36 @@
#include <asm/types.h>
#include <asm/cio.h>
#include <asm/setup.h>
+#include <uapi/asm/ipl.h>
-#define NSS_NAME_SIZE 8
+struct ipl_parameter_block {
+ struct ipl_pl_hdr hdr;
+ union {
+ struct ipl_pb_hdr pb0_hdr;
+ struct ipl_pb0_common common;
+ struct ipl_pb0_fcp fcp;
+ struct ipl_pb0_ccw ccw;
+ char raw[PAGE_SIZE - sizeof(struct ipl_pl_hdr)];
+ };
+} __packed __aligned(PAGE_SIZE);
-#define IPL_PARM_BLK_FCP_LEN (sizeof(struct ipl_list_hdr) + \
- sizeof(struct ipl_block_fcp))
+#define NSS_NAME_SIZE 8
-#define IPL_PARM_BLK0_FCP_LEN (sizeof(struct ipl_block_fcp) + 16)
-
-#define IPL_PARM_BLK_CCW_LEN (sizeof(struct ipl_list_hdr) + \
- sizeof(struct ipl_block_ccw))
-
-#define IPL_PARM_BLK0_CCW_LEN (sizeof(struct ipl_block_ccw) + 16)
+#define IPL_BP_FCP_LEN (sizeof(struct ipl_pl_hdr) + \
+ sizeof(struct ipl_pb0_fcp))
+#define IPL_BP0_FCP_LEN (sizeof(struct ipl_pb0_fcp))
+#define IPL_BP_CCW_LEN (sizeof(struct ipl_pl_hdr) + \
+ sizeof(struct ipl_pb0_ccw))
+#define IPL_BP0_CCW_LEN (sizeof(struct ipl_pb0_ccw))
#define IPL_MAX_SUPPORTED_VERSION (0)
-struct ipl_list_hdr {
- u32 len;
- u8 reserved1[3];
- u8 version;
- u32 blk0_len;
- u8 pbt;
- u8 flags;
- u16 reserved2;
- u8 loadparm[8];
-} __attribute__((packed));
+#define IPL_RB_CERT_UNKNOWN ((unsigned short)-1)
-struct ipl_block_fcp {
- u8 reserved1[305-1];
- u8 opt;
- u8 reserved2[3];
- u16 reserved3;
- u16 devno;
- u8 reserved4[4];
- u64 wwpn;
- u64 lun;
- u32 bootprog;
- u8 reserved5[12];
- u64 br_lba;
- u32 scp_data_len;
- u8 reserved6[260];
- u8 scp_data[];
-} __attribute__((packed));
-
-#define DIAG308_VMPARM_SIZE 64
-#define DIAG308_SCPDATA_SIZE (PAGE_SIZE - (sizeof(struct ipl_list_hdr) + \
- offsetof(struct ipl_block_fcp, scp_data)))
-
-struct ipl_block_ccw {
- u8 reserved1[84];
- u16 reserved2 : 13;
- u8 ssid : 3;
- u16 devno;
- u8 vm_flags;
- u8 reserved3[3];
- u32 vm_parm_len;
- u8 nss_name[8];
- u8 vm_parm[DIAG308_VMPARM_SIZE];
- u8 reserved4[8];
-} __attribute__((packed));
-
-struct ipl_parameter_block {
- struct ipl_list_hdr hdr;
- union {
- struct ipl_block_fcp fcp;
- struct ipl_block_ccw ccw;
- char raw[PAGE_SIZE - sizeof(struct ipl_list_hdr)];
- } ipl_info;
-} __packed __aligned(PAGE_SIZE);
+#define DIAG308_VMPARM_SIZE (64)
+#define DIAG308_SCPDATA_OFFSET offsetof(struct ipl_parameter_block, \
+ fcp.scp_data)
+#define DIAG308_SCPDATA_SIZE (PAGE_SIZE - DIAG308_SCPDATA_OFFSET)
struct save_area;
struct save_area * __init save_area_alloc(bool is_boot_cpu);
@@ -88,9 +50,8 @@
void __init save_area_add_vxrs(struct save_area *, __vector128 *vxrs);
extern void s390_reset_system(void);
-extern void ipl_store_parameters(void);
-extern size_t append_ipl_vmparm(char *, size_t);
-extern size_t append_ipl_scpdata(char *, size_t);
+extern size_t ipl_block_get_ascii_vmparm(char *dest, size_t size,
+ const struct ipl_parameter_block *ipb);
enum ipl_type {
IPL_TYPE_UNKNOWN = 1,
@@ -122,6 +83,33 @@
extern void setup_ipl(void);
extern void set_os_info_reipl_block(void);
+struct ipl_report {
+ struct ipl_parameter_block *ipib;
+ struct list_head components;
+ struct list_head certificates;
+ size_t size;
+};
+
+struct ipl_report_component {
+ struct list_head list;
+ struct ipl_rb_component_entry entry;
+};
+
+struct ipl_report_certificate {
+ struct list_head list;
+ struct ipl_rb_certificate_entry entry;
+ void *key;
+};
+
+struct kexec_buf;
+struct ipl_report *ipl_report_init(struct ipl_parameter_block *ipib);
+void *ipl_report_finish(struct ipl_report *report);
+int ipl_report_free(struct ipl_report *report);
+int ipl_report_add_component(struct ipl_report *report, struct kexec_buf *kbuf,
+ unsigned char flags, unsigned short cert);
+int ipl_report_add_certificate(struct ipl_report *report, void *key,
+ unsigned long addr, unsigned long len);
+
/*
* DIAG 308 support
*/
@@ -133,32 +121,12 @@
DIAG308_STORE = 6,
};
-enum diag308_ipl_type {
- DIAG308_IPL_TYPE_FCP = 0,
- DIAG308_IPL_TYPE_CCW = 2,
-};
-
-enum diag308_opt {
- DIAG308_IPL_OPT_IPL = 0x10,
- DIAG308_IPL_OPT_DUMP = 0x20,
-};
-
-enum diag308_flags {
- DIAG308_FLAGS_LP_VALID = 0x80,
-};
-
-enum diag308_vm_flags {
- DIAG308_VM_FLAGS_NSS_VALID = 0x80,
- DIAG308_VM_FLAGS_VP_VALID = 0x40,
-};
-
enum diag308_rc {
DIAG308_RC_OK = 0x0001,
DIAG308_RC_NOCONFIG = 0x0102,
};
extern int diag308(unsigned long subcode, void *addr);
-extern void diag308_reset(void);
extern void store_status(void (*fn)(void *), void *data);
extern void lgr_info_log(void);
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 2f7f27e..9f75d67 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -47,7 +47,6 @@
IRQEXT_CMC,
IRQEXT_FTP,
IRQIO_CIO,
- IRQIO_QAI,
IRQIO_DAS,
IRQIO_C15,
IRQIO_C70,
@@ -55,13 +54,16 @@
IRQIO_VMR,
IRQIO_LCS,
IRQIO_CTC,
- IRQIO_APB,
IRQIO_ADM,
IRQIO_CSC,
- IRQIO_PCI,
- IRQIO_MSI,
IRQIO_VIR,
+ IRQIO_QAI,
+ IRQIO_APB,
+ IRQIO_PCF,
+ IRQIO_PCD,
+ IRQIO_MSI,
IRQIO_VAI,
+ IRQIO_GAL,
NMI_NMI,
CPU_RST,
NR_ARCH_IRQS
diff --git a/arch/s390/include/asm/isc.h b/arch/s390/include/asm/isc.h
index 6cb9e2e..b2cc1ec 100644
--- a/arch/s390/include/asm/isc.h
+++ b/arch/s390/include/asm/isc.h
@@ -21,6 +21,7 @@
/* Adapter interrupts. */
#define QDIO_AIRQ_ISC IO_SCH_ISC /* I/O subchannel in qdio mode */
#define PCI_ISC 2 /* PCI I/O subchannels */
+#define GAL_ISC 5 /* GIB alert */
#define AP_ISC 6 /* adjunct processor (crypto) devices */
/* Functions for registration of I/O interruption subclasses */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 40f6512..39f747d 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -10,19 +10,25 @@
#define JUMP_LABEL_NOP_SIZE 6
#define JUMP_LABEL_NOP_OFFSET 2
+#if __GNUC__ < 9
+#define JUMP_LABEL_STATIC_KEY_CONSTRAINT "X"
+#else
+#define JUMP_LABEL_STATIC_KEY_CONSTRAINT "jdd"
+#endif
+
/*
* We use a brcl 0,2 instruction for jump labels at compile time so it
* can be easily distinguished from a hotpatch generated instruction.
*/
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
- ".pushsection __jump_table, \"aw\"\n"
- ".balign 8\n"
- ".quad 0b, %l[label], %0\n"
- ".popsection\n"
- : : "X" (&((char *)key)[branch]) : : label);
-
+ asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
+ ".pushsection __jump_table,\"aw\"\n"
+ ".balign 8\n"
+ ".long 0b-.,%l[label]-.\n"
+ ".quad %0+%1-.\n"
+ ".popsection\n"
+ : : JUMP_LABEL_STATIC_KEY_CONSTRAINT (key), "i" (branch) : : label);
return false;
label:
return true;
@@ -30,25 +36,17 @@
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("0: brcl 15, %l[label]\n"
- ".pushsection __jump_table, \"aw\"\n"
- ".balign 8\n"
- ".quad 0b, %l[label], %0\n"
- ".popsection\n"
- : : "X" (&((char *)key)[branch]) : : label);
-
+ asm_volatile_goto("0: brcl 15,%l[label]\n"
+ ".pushsection __jump_table,\"aw\"\n"
+ ".balign 8\n"
+ ".long 0b-.,%l[label]-.\n"
+ ".quad %0+%1-.\n"
+ ".popsection\n"
+ : : JUMP_LABEL_STATIC_KEY_CONSTRAINT (key), "i" (branch) : : label);
return false;
label:
return true;
}
-typedef unsigned long jump_label_t;
-
-struct jump_entry {
- jump_label_t code;
- jump_label_t target;
- jump_label_t key;
-};
-
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/s390/include/asm/kasan.h b/arch/s390/include/asm/kasan.h
new file mode 100644
index 0000000..70930fe
--- /dev/null
+++ b/arch/s390/include/asm/kasan.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#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_free_early_identity(void);
+#else
+static inline void kasan_early_init(void) { }
+static inline void kasan_copy_shadow(pgd_t *dst) { }
+static inline void kasan_free_early_identity(void) { }
+#endif
+
+#endif
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 825dd0f..ea398a0 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -11,6 +11,7 @@
#include <asm/processor.h>
#include <asm/page.h>
+#include <asm/setup.h>
/*
* KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
* I.e. Maximum page that is mapped directly into kernel memory,
@@ -42,6 +43,9 @@
/* The native architecture */
#define KEXEC_ARCH KEXEC_ARCH_S390
+/* Allow kexec_file to load a segment to 0 */
+#define KEXEC_BUF_MEM_UNKNOWN -1
+
/* Provide a dummy definition to avoid build failures. */
static inline void crash_setup_regs(struct pt_regs *newregs,
struct pt_regs *oldregs) { }
@@ -51,20 +55,24 @@
/* Pointer to the kernel buffer. Used to register cmdline etc.. */
void *kernel_buf;
+ /* Load address of the kernel_buf. */
+ unsigned long kernel_mem;
+
+ /* Parmarea in the kernel buffer. */
+ struct parmarea *parm;
+
/* Total size of loaded segments in memory. Used as an offset. */
size_t memsz;
- /* Load address of initrd. Used to register INITRD_START in kernel. */
- unsigned long initrd_load_addr;
+ struct ipl_report *report;
};
-int kexec_file_add_purgatory(struct kimage *image,
- struct s390_load_data *data);
-int kexec_file_add_initrd(struct kimage *image,
- struct s390_load_data *data,
- char *initrd, unsigned long initrd_len);
-int *kexec_file_update_kernel(struct kimage *iamge,
- struct s390_load_data *data);
+int s390_verify_sig(const char *kernel, unsigned long kernel_len);
+void *kexec_file_add_components(struct kimage *image,
+ int (*add_kernel)(struct kimage *image,
+ struct s390_load_data *data));
+int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
+ unsigned long addr);
extern const struct kexec_file_ops s390_kexec_image_ops;
extern const struct kexec_file_ops s390_kexec_elf_ops;
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 29c940b..abe6026 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -18,6 +18,7 @@
#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/seqlock.h>
+#include <linux/module.h>
#include <asm/debug.h>
#include <asm/cpu.h>
#include <asm/fpu/api.h>
@@ -36,7 +37,7 @@
*/
#define KVM_NR_IRQCHIPS 1
#define KVM_IRQCHIP_NUM_PINS 4096
-#define KVM_HALT_POLL_NS_DEFAULT 80000
+#define KVM_HALT_POLL_NS_DEFAULT 50000
/* s390-specific vcpu->requests bit members */
#define KVM_REQ_ENABLE_IBS KVM_ARCH_REQ(0)
@@ -44,6 +45,7 @@
#define KVM_REQ_ICPT_OPEREXC KVM_ARCH_REQ(2)
#define KVM_REQ_START_MIGRATION KVM_ARCH_REQ(3)
#define KVM_REQ_STOP_MIGRATION KVM_ARCH_REQ(4)
+#define KVM_REQ_VSIE_RESTART KVM_ARCH_REQ(5)
#define SIGP_CTRL_C 0x80
#define SIGP_CTRL_SCN_MASK 0x3f
@@ -186,6 +188,7 @@
#define ECA_AIV 0x00200000
#define ECA_VX 0x00020000
#define ECA_PROTEXCI 0x00002000
+#define ECA_APIE 0x00000008
#define ECA_SII 0x00000001
__u32 eca; /* 0x004c */
#define ICPT_INST 0x04
@@ -237,7 +240,11 @@
psw_t gpsw; /* 0x0090 */
__u64 gg14; /* 0x00a0 */
__u64 gg15; /* 0x00a8 */
- __u8 reservedb0[20]; /* 0x00b0 */
+ __u8 reservedb0[8]; /* 0x00b0 */
+#define HPID_KVM 0x4
+#define HPID_VSIE 0x5
+ __u8 hpid; /* 0x00b8 */
+ __u8 reservedb9[11]; /* 0x00b9 */
__u16 extcpuaddr; /* 0x00c4 */
__u16 eic; /* 0x00c6 */
__u32 reservedc8; /* 0x00c8 */
@@ -255,6 +262,8 @@
__u8 reservede4[4]; /* 0x00e4 */
__u64 tecmc; /* 0x00e8 */
__u8 reservedf0[12]; /* 0x00f0 */
+#define CRYCB_FORMAT_MASK 0x00000003
+#define CRYCB_FORMAT0 0x00000000
#define CRYCB_FORMAT1 0x00000001
#define CRYCB_FORMAT2 0x00000003
__u32 crycbd; /* 0x00fc */
@@ -270,6 +279,7 @@
#define ECD_HOSTREGMGMT 0x20000000
#define ECD_MEF 0x08000000
#define ECD_ETOKENF 0x02000000
+#define ECD_ECC 0x00200000
__u32 ecd; /* 0x01c8 */
__u8 reserved1cc[18]; /* 0x01cc */
__u64 pp; /* 0x01de */
@@ -304,6 +314,7 @@
u64 halt_successful_poll;
u64 halt_attempted_poll;
u64 halt_poll_invalid;
+ u64 halt_no_poll_steal;
u64 halt_wakeup;
u64 instruction_lctl;
u64 instruction_lctlg;
@@ -583,7 +594,6 @@
struct kvm_s390_mchk_info mchk;
struct kvm_s390_ext_info srv_signal;
int next_rr_cpu;
- unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
struct mutex ais_lock;
u8 simm;
u8 nimm;
@@ -704,17 +714,25 @@
struct kvm_s390_cpu_model {
/* facility mask supported by kvm & hosting machine */
__u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64];
+ struct kvm_s390_vm_cpu_subfunc subfuncs;
/* facility list requested by guest (in dma page) */
__u64 *fac_list;
u64 cpuid;
unsigned short ibc;
};
+struct kvm_s390_module_hook {
+ int (*hook)(struct kvm_vcpu *vcpu);
+ struct module *owner;
+};
+
struct kvm_s390_crypto {
struct kvm_s390_crypto_cb *crycb;
+ struct kvm_s390_module_hook *pqap_hook;
__u32 crycbd;
__u8 aes_kw;
__u8 dea_kw;
+ __u8 apie;
};
#define APCB0_MASK_SIZE 1
@@ -773,9 +791,21 @@
u8 reserved03[11];
u32 airq_count;
} g1;
+ struct {
+ u64 word[4];
+ } u64;
};
};
+struct kvm_s390_gib {
+ u32 alert_list_origin;
+ u32 reserved01;
+ u8:5;
+ u8 nisc:3;
+ u8 reserved03[3];
+ u32 reserved04[5];
+};
+
/*
* sie_page2 has to be allocated as DMA because fac_list, crycb and
* gisa need 31bit addresses in the sie control block.
@@ -784,7 +814,8 @@
__u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */
struct kvm_s390_crypto_cb crycb; /* 0x0800 */
struct kvm_s390_gisa gisa; /* 0x0900 */
- u8 reserved920[0x1000 - 0x920]; /* 0x0920 */
+ struct kvm *kvm; /* 0x0920 */
+ u8 reserved928[0x1000 - 0x928]; /* 0x0928 */
};
struct kvm_s390_vsie {
@@ -795,6 +826,20 @@
struct page *pages[KVM_MAX_VCPUS];
};
+struct kvm_s390_gisa_iam {
+ u8 mask;
+ spinlock_t ref_lock;
+ u32 ref_count[MAX_ISC + 1];
+};
+
+struct kvm_s390_gisa_interrupt {
+ struct kvm_s390_gisa *origin;
+ struct kvm_s390_gisa_iam alert;
+ struct hrtimer timer;
+ u64 expires;
+ DECLARE_BITMAP(kicked_mask, KVM_MAX_VCPUS);
+};
+
struct kvm_arch{
void *sca;
int use_esca;
@@ -828,7 +873,8 @@
atomic64_t cmma_dirty_pages;
/* subset of available cpu features enabled by user space */
DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
- struct kvm_s390_gisa *gisa;
+ DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS);
+ struct kvm_s390_gisa_interrupt gisa_int;
};
#define KVM_HVA_ERR_BAD (-1UL)
@@ -855,17 +901,23 @@
void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
+void kvm_arch_crypto_clear_masks(struct kvm *kvm);
+void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm,
+ unsigned long *aqm, unsigned long *adm);
+
extern int sie64a(struct kvm_s390_sie_block *, u64 *);
extern char sie_exit;
+extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc);
+extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc);
+
static inline void kvm_arch_hardware_disable(void) {}
-static inline void kvm_arch_check_processor_compat(void *rtn) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_free_memslot(struct kvm *kvm,
struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot) {}
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index 1b95da3..7f22262 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -28,5 +28,12 @@
.long (_target) - . ; \
.previous
+#define EX_TABLE_DMA(_fault, _target) \
+ .section .dma.ex_table, "a" ; \
+ .align 4 ; \
+ .long (_fault) - . ; \
+ .long (_target) - . ; \
+ .previous
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h
index 672f95b..818612b 100644
--- a/arch/s390/include/asm/livepatch.h
+++ b/arch/s390/include/asm/livepatch.h
@@ -13,11 +13,6 @@
#include <asm/ptrace.h>
-static inline int klp_check_compiler_support(void)
-{
- return 0;
-}
-
static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
{
regs->psw.addr = ip;
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 406d940..237ee0c 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -91,52 +91,53 @@
__u64 hardirq_timer; /* 0x02e8 */
__u64 softirq_timer; /* 0x02f0 */
__u64 steal_timer; /* 0x02f8 */
- __u64 last_update_timer; /* 0x0300 */
- __u64 last_update_clock; /* 0x0308 */
- __u64 int_clock; /* 0x0310 */
- __u64 mcck_clock; /* 0x0318 */
- __u64 clock_comparator; /* 0x0320 */
- __u64 boot_clock[2]; /* 0x0328 */
+ __u64 avg_steal_timer; /* 0x0300 */
+ __u64 last_update_timer; /* 0x0308 */
+ __u64 last_update_clock; /* 0x0310 */
+ __u64 int_clock; /* 0x0318*/
+ __u64 mcck_clock; /* 0x0320 */
+ __u64 clock_comparator; /* 0x0328 */
+ __u64 boot_clock[2]; /* 0x0330 */
/* Current process. */
- __u64 current_task; /* 0x0338 */
- __u64 kernel_stack; /* 0x0340 */
+ __u64 current_task; /* 0x0340 */
+ __u64 kernel_stack; /* 0x0348 */
- /* Interrupt, panic and restart stack. */
- __u64 async_stack; /* 0x0348 */
- __u64 panic_stack; /* 0x0350 */
- __u64 restart_stack; /* 0x0358 */
+ /* Interrupt, DAT-off and restartstack. */
+ __u64 async_stack; /* 0x0350 */
+ __u64 nodat_stack; /* 0x0358 */
+ __u64 restart_stack; /* 0x0360 */
/* Restart function and parameter. */
- __u64 restart_fn; /* 0x0360 */
- __u64 restart_data; /* 0x0368 */
- __u64 restart_source; /* 0x0370 */
+ __u64 restart_fn; /* 0x0368 */
+ __u64 restart_data; /* 0x0370 */
+ __u64 restart_source; /* 0x0378 */
/* Address space pointer. */
- __u64 kernel_asce; /* 0x0378 */
- __u64 user_asce; /* 0x0380 */
- __u64 vdso_asce; /* 0x0388 */
+ __u64 kernel_asce; /* 0x0380 */
+ __u64 user_asce; /* 0x0388 */
+ __u64 vdso_asce; /* 0x0390 */
/*
* The lpp and current_pid fields form a
* 64-bit value that is set as program
* parameter with the LPP instruction.
*/
- __u32 lpp; /* 0x0390 */
- __u32 current_pid; /* 0x0394 */
+ __u32 lpp; /* 0x0398 */
+ __u32 current_pid; /* 0x039c */
/* SMP info area */
- __u32 cpu_nr; /* 0x0398 */
- __u32 softirq_pending; /* 0x039c */
- __u32 preempt_count; /* 0x03a0 */
- __u32 spinlock_lockval; /* 0x03a4 */
- __u32 spinlock_index; /* 0x03a8 */
- __u32 fpu_flags; /* 0x03ac */
- __u64 percpu_offset; /* 0x03b0 */
- __u64 vdso_per_cpu_data; /* 0x03b8 */
- __u64 machine_flags; /* 0x03c0 */
- __u64 gmap; /* 0x03c8 */
- __u8 pad_0x03d0[0x0400-0x03d0]; /* 0x03d0 */
+ __u32 cpu_nr; /* 0x03a0 */
+ __u32 softirq_pending; /* 0x03a4 */
+ __s32 preempt_count; /* 0x03a8 */
+ __u32 spinlock_lockval; /* 0x03ac */
+ __u32 spinlock_index; /* 0x03b0 */
+ __u32 fpu_flags; /* 0x03b4 */
+ __u64 percpu_offset; /* 0x03b8 */
+ __u64 vdso_per_cpu_data; /* 0x03c0 */
+ __u64 machine_flags; /* 0x03c8 */
+ __u64 gmap; /* 0x03d0 */
+ __u8 pad_0x03d8[0x0400-0x03d8]; /* 0x03d8 */
/* br %r1 trampoline */
__u16 br_r1_trampoline; /* 0x0400 */
diff --git a/arch/s390/include/asm/mem_detect.h b/arch/s390/include/asm/mem_detect.h
new file mode 100644
index 0000000..a7c922a
--- /dev/null
+++ b/arch/s390/include/asm/mem_detect.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_MEM_DETECT_H
+#define _ASM_S390_MEM_DETECT_H
+
+#include <linux/types.h>
+
+enum mem_info_source {
+ MEM_DETECT_NONE = 0,
+ MEM_DETECT_SCLP_STOR_INFO,
+ MEM_DETECT_DIAG260,
+ MEM_DETECT_SCLP_READ_INFO,
+ MEM_DETECT_BIN_SEARCH
+};
+
+struct mem_detect_block {
+ u64 start;
+ u64 end;
+};
+
+/*
+ * Storage element id is defined as 1 byte (up to 256 storage elements).
+ * In practise only storage element id 0 and 1 are used).
+ * According to architecture one storage element could have as much as
+ * 1020 subincrements. 255 mem_detect_blocks are embedded in mem_detect_info.
+ * If more mem_detect_blocks are required, a block of memory from already
+ * known mem_detect_block is taken (entries_extended points to it).
+ */
+#define MEM_INLINED_ENTRIES 255 /* (PAGE_SIZE - 16) / 16 */
+
+struct mem_detect_info {
+ u32 count;
+ u8 info_source;
+ struct mem_detect_block entries[MEM_INLINED_ENTRIES];
+ struct mem_detect_block *entries_extended;
+};
+extern struct mem_detect_info mem_detect;
+
+void add_mem_detect_block(u64 start, u64 end);
+
+static inline int __get_mem_detect_block(u32 n, unsigned long *start,
+ unsigned long *end)
+{
+ if (n >= mem_detect.count) {
+ *start = 0;
+ *end = 0;
+ return -1;
+ }
+
+ if (n < MEM_INLINED_ENTRIES) {
+ *start = (unsigned long)mem_detect.entries[n].start;
+ *end = (unsigned long)mem_detect.entries[n].end;
+ } else {
+ *start = (unsigned long)mem_detect.entries_extended[n - MEM_INLINED_ENTRIES].start;
+ *end = (unsigned long)mem_detect.entries_extended[n - MEM_INLINED_ENTRIES].end;
+ }
+ return 0;
+}
+
+/**
+ * for_each_mem_detect_block - early online memory range iterator
+ * @i: an integer used as loop variable
+ * @p_start: ptr to unsigned long for start address of the range
+ * @p_end: ptr to unsigned long for end address of the range
+ *
+ * Walks over detected online memory ranges.
+ */
+#define for_each_mem_detect_block(i, p_start, p_end) \
+ for (i = 0, __get_mem_detect_block(i, p_start, p_end); \
+ i < mem_detect.count; \
+ i++, __get_mem_detect_block(i, p_start, p_end))
+
+static inline void get_mem_detect_reserved(unsigned long *start,
+ unsigned long *size)
+{
+ *start = (unsigned long)mem_detect.entries_extended;
+ if (mem_detect.count > MEM_INLINED_ENTRIES)
+ *size = (mem_detect.count - MEM_INLINED_ENTRIES) * sizeof(struct mem_detect_block);
+ else
+ *size = 0;
+}
+
+static inline unsigned long get_mem_detect_end(void)
+{
+ unsigned long start;
+ unsigned long end;
+
+ if (mem_detect.count) {
+ __get_mem_detect_block(mem_detect.count - 1, &start, &end);
+ return end;
+ }
+ return 0;
+}
+
+#endif
diff --git a/arch/s390/include/asm/mem_encrypt.h b/arch/s390/include/asm/mem_encrypt.h
new file mode 100644
index 0000000..2542cbf
--- /dev/null
+++ b/arch/s390/include/asm/mem_encrypt.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef S390_MEM_ENCRYPT_H__
+#define S390_MEM_ENCRYPT_H__
+
+#ifndef __ASSEMBLY__
+
+static inline bool mem_encrypt_active(void) { return false; }
+
+int set_memory_encrypted(unsigned long addr, int numpages);
+int set_memory_decrypted(unsigned long addr, int numpages);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* S390_MEM_ENCRYPT_H__ */
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index a8418e1..bcfb637 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -32,6 +32,8 @@
unsigned int uses_cmm:1;
/* The gmaps associated with this context are allowed to use huge pages. */
unsigned int allow_gmap_hpage_1m:1;
+ /* The mmu context is for compat task */
+ unsigned int compat_mm:1;
} mm_context_t;
#define INIT_MM_CONTEXT(name) \
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index f1ab942..8d04e6f 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -25,6 +25,7 @@
atomic_set(&mm->context.flush_count, 0);
mm->context.gmap_asce = 0;
mm->context.flush_mm = 0;
+ mm->context.compat_mm = test_thread_flag(TIF_31BIT);
#ifdef CONFIG_PGSTE
mm->context.alloc_pgste = page_table_allocate_pgste ||
test_thread_flag(TIF_PGSTE) ||
@@ -89,8 +90,6 @@
{
int cpu = smp_processor_id();
- if (prev == next)
- return;
S390_lowcore.user_asce = next->context.asce;
cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
/* Clear previous user-ASCE from CR1 and CR7 */
@@ -102,7 +101,8 @@
__ctl_load(S390_lowcore.vdso_asce, 7, 7);
clear_cpu_flag(CIF_ASCE_SECONDARY);
}
- cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+ if (prev != next)
+ cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
}
#define finish_arch_post_lock_switch finish_arch_post_lock_switch
diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h
index 1e5dc45..b160da8 100644
--- a/arch/s390/include/asm/nmi.h
+++ b/arch/s390/include/asm/nmi.h
@@ -12,7 +12,7 @@
#ifndef _ASM_S390_NMI_H
#define _ASM_S390_NMI_H
-#include <linux/const.h>
+#include <linux/bits.h>
#include <linux/types.h>
#define MCIC_SUBCLASS_MASK (1ULL<<63 | 1ULL<<62 | 1ULL<<61 | \
@@ -20,15 +20,15 @@
1ULL<<55 | 1ULL<<54 | 1ULL<<53 | \
1ULL<<52 | 1ULL<<47 | 1ULL<<46 | \
1ULL<<45 | 1ULL<<44)
-#define MCCK_CODE_SYSTEM_DAMAGE _BITUL(63)
-#define MCCK_CODE_EXT_DAMAGE _BITUL(63 - 5)
-#define MCCK_CODE_CP _BITUL(63 - 9)
-#define MCCK_CODE_CPU_TIMER_VALID _BITUL(63 - 46)
-#define MCCK_CODE_PSW_MWP_VALID _BITUL(63 - 20)
-#define MCCK_CODE_PSW_IA_VALID _BITUL(63 - 23)
-#define MCCK_CODE_CR_VALID _BITUL(63 - 29)
-#define MCCK_CODE_GS_VALID _BITUL(63 - 36)
-#define MCCK_CODE_FC_VALID _BITUL(63 - 43)
+#define MCCK_CODE_SYSTEM_DAMAGE BIT(63)
+#define MCCK_CODE_EXT_DAMAGE BIT(63 - 5)
+#define MCCK_CODE_CP BIT(63 - 9)
+#define MCCK_CODE_CPU_TIMER_VALID BIT(63 - 46)
+#define MCCK_CODE_PSW_MWP_VALID BIT(63 - 20)
+#define MCCK_CODE_PSW_IA_VALID BIT(63 - 23)
+#define MCCK_CODE_CR_VALID BIT(63 - 29)
+#define MCCK_CODE_GS_VALID BIT(63 - 36)
+#define MCCK_CODE_FC_VALID BIT(63 - 43)
#ifndef __ASSEMBLY__
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
index 123dac3..0033dcd 100644
--- a/arch/s390/include/asm/nospec-insn.h
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -32,23 +32,23 @@
.endm
.macro __THUNK_PROLOG_BR r1,r2
- __THUNK_PROLOG_NAME __s390x_indirect_jump_r\r2\()use_r\r1
+ __THUNK_PROLOG_NAME __s390_indirect_jump_r\r2\()use_r\r1
.endm
.macro __THUNK_PROLOG_BC d0,r1,r2
- __THUNK_PROLOG_NAME __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+ __THUNK_PROLOG_NAME __s390_indirect_branch_\d0\()_\r2\()use_\r1
.endm
.macro __THUNK_BR r1,r2
- jg __s390x_indirect_jump_r\r2\()use_r\r1
+ jg __s390_indirect_jump_r\r2\()use_r\r1
.endm
.macro __THUNK_BC d0,r1,r2
- jg __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+ jg __s390_indirect_branch_\d0\()_\r2\()use_\r1
.endm
.macro __THUNK_BRASL r1,r2,r3
- brasl \r1,__s390x_indirect_jump_r\r3\()use_r\r2
+ brasl \r1,__s390_indirect_jump_r\r3\()use_r\r2
.endm
.macro __DECODE_RR expand,reg,ruse
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 41e3908..823578c 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -161,6 +161,7 @@
#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT)
#define pfn_to_virt(pfn) __va((pfn) << PAGE_SHIFT)
+#define pfn_to_kaddr(pfn) pfn_to_virt(pfn)
#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr))
#define page_to_virt(page) pfn_to_virt(page_to_pfn(page))
@@ -176,6 +177,8 @@
#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define ARCH_ZONE_DMA_BITS 31
+
#include <asm-generic/memory_model.h>
#include <asm-generic/getorder.h>
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 10fe982..a2399ef 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -26,6 +26,9 @@
#define ZPCI_BUS_NR 0 /* default bus number */
#define ZPCI_DEVFN 0 /* default device number */
+#define ZPCI_NR_DMA_SPACES 1
+#define ZPCI_NR_DEVICES CONFIG_PCI_NR_FUNCTIONS
+
/* PCI Function Controls */
#define ZPCI_FC_FN_ENABLED 0x80
#define ZPCI_FC_ERROR 0x40
@@ -83,6 +86,8 @@
struct zpci_bar_struct {
struct resource *res; /* bus resource */
+ void __iomem *mio_wb;
+ void __iomem *mio_wt;
u32 val; /* bar start & 3 flag bits */
u16 map_idx; /* index into bar mapping array */
u8 size; /* order 2 exponent */
@@ -112,6 +117,8 @@
/* IRQ stuff */
u64 msi_addr; /* MSI address */
unsigned int max_msi; /* maximum number of MSI's */
+ unsigned int msi_first_bit;
+ unsigned int msi_nr_irqs;
struct airq_iv *aibv; /* adapter interrupt bit vector */
unsigned long aisb; /* number of the summary bit */
@@ -130,6 +137,7 @@
struct iommu_device iommu_dev; /* IOMMU core handle */
char res_name[16];
+ bool mio_capable;
struct zpci_bar_struct bars[PCI_BAR_COUNT];
u64 start_dma; /* Start of available DMA addresses */
@@ -148,7 +156,6 @@
enum pci_bus_speed max_bus_speed;
struct dentry *debugfs_dev;
- struct dentry *debugfs_perf;
struct s390_domain *s390_domain; /* s390 IOMMU domain data */
};
@@ -159,6 +166,7 @@
}
extern const struct attribute_group *zpci_attr_groups[];
+extern unsigned int s390_pci_force_floating __initdata;
/* -----------------------------------------------------------------------------
Prototypes
@@ -186,6 +194,11 @@
void zpci_destroy_iommu(struct zpci_dev *zdev);
#ifdef CONFIG_PCI
+static inline bool zpci_use_mio(struct zpci_dev *zdev)
+{
+ return static_branch_likely(&have_mio) && zdev->mio_capable;
+}
+
/* Error handling and recovery */
void zpci_event_error(void *);
void zpci_event_availability(void *);
@@ -220,6 +233,9 @@
int zpci_dma_init(void);
void zpci_dma_exit(void);
+int __init zpci_irq_init(void);
+void __init zpci_irq_exit(void);
+
/* FMB */
int zpci_fmb_enable_device(struct zpci_dev *);
int zpci_fmb_disable_device(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index b3b31b3..5035917 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -43,6 +43,8 @@
#define CLP_SET_ENABLE_PCI_FN 0 /* Yes, 0 enables it */
#define CLP_SET_DISABLE_PCI_FN 1 /* Yes, 1 disables it */
+#define CLP_SET_ENABLE_MIO 2
+#define CLP_SET_DISABLE_MIO 3
#define CLP_UTIL_STR_LEN 64
#define CLP_PFIP_NR_SEGMENTS 4
@@ -68,6 +70,17 @@
struct clp_fh_list_entry fh_list[CLP_FH_LIST_NR_ENTRIES];
} __packed;
+struct mio_info {
+ u32 valid : 6;
+ u32 : 26;
+ u32 : 32;
+ struct {
+ u64 wb;
+ u64 wt;
+ } addr[PCI_BAR_COUNT];
+ u32 reserved[6];
+} __packed;
+
/* Query PCI function request */
struct clp_req_query_pci {
struct clp_req_hdr hdr;
@@ -80,7 +93,8 @@
struct clp_rsp_query_pci {
struct clp_rsp_hdr hdr;
u16 vfn; /* virtual fn number */
- u16 : 7;
+ u16 : 6;
+ u16 mio_addr_avail : 1;
u16 util_str_avail : 1; /* utility string available? */
u16 pfgid : 8; /* pci function group id */
u32 fid; /* pci function id */
@@ -96,6 +110,8 @@
u32 reserved[11];
u32 uid; /* user defined id */
u8 util_str[CLP_UTIL_STR_LEN]; /* utility string */
+ u32 reserved2[16];
+ struct mio_info mio;
} __packed;
/* Query PCI function group request */
@@ -118,7 +134,11 @@
u8 refresh : 1; /* TLB refresh mode */
u16 reserved2;
u16 mui;
- u64 reserved3;
+ u16 : 16;
+ u16 maxfaal;
+ u16 : 4;
+ u16 dnoi : 12;
+ u16 maxcpu;
u64 dasm; /* dma address space mask */
u64 msia; /* MSI address */
u64 reserved4;
@@ -139,8 +159,9 @@
struct clp_rsp_set_pci {
struct clp_rsp_hdr hdr;
u32 fh; /* function handle */
- u32 reserved3;
- u64 reserved4;
+ u32 reserved1;
+ u64 reserved2;
+ struct mio_info mio;
} __packed;
/* Combined request/response block structures used by clp insn */
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index ba22a6e..61cf953 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -2,6 +2,8 @@
#ifndef _ASM_S390_PCI_INSN_H
#define _ASM_S390_PCI_INSN_H
+#include <linux/jump_label.h>
+
/* Load/Store status codes */
#define ZPCI_PCI_ST_FUNC_NOT_ENABLED 4
#define ZPCI_PCI_ST_FUNC_IN_ERR 8
@@ -38,6 +40,8 @@
#define ZPCI_MOD_FC_RESET_ERROR 7
#define ZPCI_MOD_FC_RESET_BLOCK 9
#define ZPCI_MOD_FC_SET_MEASURE 10
+#define ZPCI_MOD_FC_REG_INT_D 16
+#define ZPCI_MOD_FC_DEREG_INT_D 17
/* FIB function controls */
#define ZPCI_FIB_FC_ENABLED 0x80
@@ -51,16 +55,7 @@
#define ZPCI_FIB_FC_LS_BLOCKED 0x20
#define ZPCI_FIB_FC_DMAAS_REG 0x10
-/* Function Information Block */
-struct zpci_fib {
- u32 fmt : 8; /* format */
- u32 : 24;
- u32 : 32;
- u8 fc; /* function controls */
- u64 : 56;
- u64 pba; /* PCI base address */
- u64 pal; /* PCI address limit */
- u64 iota; /* I/O Translation Anchor */
+struct zpci_fib_fmt0 {
u32 : 1;
u32 isc : 3; /* Interrupt subclass */
u32 noi : 12; /* Number of interrupts */
@@ -72,16 +67,80 @@
u32 : 32;
u64 aibv; /* Adapter int bit vector address */
u64 aisb; /* Adapter int summary bit address */
+};
+
+struct zpci_fib_fmt1 {
+ u32 : 4;
+ u32 noi : 12;
+ u32 : 16;
+ u32 dibvo : 16;
+ u32 : 16;
+ u64 : 64;
+ u64 : 64;
+};
+
+/* Function Information Block */
+struct zpci_fib {
+ u32 fmt : 8; /* format */
+ u32 : 24;
+ u32 : 32;
+ u8 fc; /* function controls */
+ u64 : 56;
+ u64 pba; /* PCI base address */
+ u64 pal; /* PCI address limit */
+ u64 iota; /* I/O Translation Anchor */
+ union {
+ struct zpci_fib_fmt0 fmt0;
+ struct zpci_fib_fmt1 fmt1;
+ };
u64 fmb_addr; /* Function measurement block address and key */
u32 : 32;
u32 gd;
} __packed __aligned(8);
+/* directed interruption information block */
+struct zpci_diib {
+ u32 : 1;
+ u32 isc : 3;
+ u32 : 28;
+ u16 : 16;
+ u16 nr_cpus;
+ u64 disb_addr;
+ u64 : 64;
+ u64 : 64;
+} __packed __aligned(8);
+
+/* cpu directed interruption information block */
+struct zpci_cdiib {
+ u64 : 64;
+ u64 dibv_addr;
+ u64 : 64;
+ u64 : 64;
+ u64 : 64;
+} __packed __aligned(8);
+
+union zpci_sic_iib {
+ struct zpci_diib diib;
+ struct zpci_cdiib cdiib;
+};
+
+DECLARE_STATIC_KEY_FALSE(have_mio);
+
u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status);
int zpci_refresh_trans(u64 fn, u64 addr, u64 range);
-int zpci_load(u64 *data, u64 req, u64 offset);
-int zpci_store(u64 data, u64 req, u64 offset);
-int zpci_store_block(const u64 *data, u64 req, u64 offset);
-int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc);
+int __zpci_load(u64 *data, u64 req, u64 offset);
+int zpci_load(u64 *data, const volatile void __iomem *addr, unsigned long len);
+int __zpci_store(u64 data, u64 req, u64 offset);
+int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len);
+int __zpci_store_block(const u64 *data, u64 req, u64 offset);
+void zpci_barrier(void);
+int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib);
+
+static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc)
+{
+ union zpci_sic_iib iib = {{0}};
+
+ return __zpci_set_irq_ctrl(ctl, isc, &iib);
+}
#endif
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index cbb9cb9..cd060b5 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -37,12 +37,10 @@
#define zpci_read(LENGTH, RETTYPE) \
static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr) \
{ \
- struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)]; \
- u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH); \
u64 data; \
int rc; \
\
- rc = zpci_load(&data, req, ZPCI_OFFSET(addr)); \
+ rc = zpci_load(&data, addr, LENGTH); \
if (rc) \
data = -1ULL; \
return (RETTYPE) data; \
@@ -52,11 +50,9 @@
static inline void zpci_write_##VALTYPE(VALTYPE val, \
const volatile void __iomem *addr) \
{ \
- struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)]; \
- u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH); \
u64 data = (VALTYPE) val; \
\
- zpci_store(data, req, ZPCI_OFFSET(addr)); \
+ zpci_store(addr, data, LENGTH); \
}
zpci_read(8, u64)
@@ -68,36 +64,38 @@
zpci_write(2, u16)
zpci_write(1, u8)
-static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len)
+static inline int zpci_write_single(volatile void __iomem *dst, const void *src,
+ unsigned long len)
{
u64 val;
switch (len) {
case 1:
- val = (u64) *((u8 *) data);
+ val = (u64) *((u8 *) src);
break;
case 2:
- val = (u64) *((u16 *) data);
+ val = (u64) *((u16 *) src);
break;
case 4:
- val = (u64) *((u32 *) data);
+ val = (u64) *((u32 *) src);
break;
case 8:
- val = (u64) *((u64 *) data);
+ val = (u64) *((u64 *) src);
break;
default:
val = 0; /* let FW report error */
break;
}
- return zpci_store(val, req, offset);
+ return zpci_store(dst, val, len);
}
-static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
+static inline int zpci_read_single(void *dst, const volatile void __iomem *src,
+ unsigned long len)
{
u64 data;
int cc;
- cc = zpci_load(&data, req, offset);
+ cc = zpci_load(&data, src, len);
if (cc)
goto out;
@@ -119,10 +117,8 @@
return cc;
}
-static inline int zpci_write_block(u64 req, const u64 *data, u64 offset)
-{
- return zpci_store_block(data, req, offset);
-}
+int zpci_write_block(volatile void __iomem *dst, const void *src,
+ unsigned long len);
static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
{
@@ -140,18 +136,15 @@
const volatile void __iomem *src,
unsigned long n)
{
- struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(src)];
- u64 req, offset = ZPCI_OFFSET(src);
int size, rc = 0;
while (n > 0) {
size = zpci_get_max_write_size((u64 __force) src,
(u64) dst, n, 8);
- req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
- rc = zpci_read_single(req, dst, offset, size);
+ rc = zpci_read_single(dst, src, size);
if (rc)
break;
- offset += size;
+ src += size;
dst += size;
n -= size;
}
@@ -161,8 +154,6 @@
static inline int zpci_memcpy_toio(volatile void __iomem *dst,
const void *src, unsigned long n)
{
- struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(dst)];
- u64 req, offset = ZPCI_OFFSET(dst);
int size, rc = 0;
if (!src)
@@ -171,16 +162,14 @@
while (n > 0) {
size = zpci_get_max_write_size((u64 __force) dst,
(u64) src, n, 128);
- req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
-
if (size > 8) /* main path */
- rc = zpci_write_block(req, src, offset);
+ rc = zpci_write_block(dst, src, size);
else
- rc = zpci_write_single(req, src, offset, size);
+ rc = zpci_write_single(dst, src, size);
if (rc)
break;
- offset += size;
src += size;
+ dst += size;
n -= size;
}
return rc;
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 0095ddb..50b4ce8 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -16,7 +16,7 @@
* per cpu area, use weak definitions to force the compiler to
* generate external references.
*/
-#if defined(CONFIG_SMP) && defined(MODULE)
+#if defined(MODULE)
#define ARCH_NEEDS_WEAK_PER_CPU
#endif
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index b9c0e36..4652fff 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -12,7 +12,6 @@
#include <linux/perf_event.h>
#include <linux/device.h>
-#include <asm/cpu_mf.h>
/* Per-CPU flags for PMU states */
#define PMU_F_RESERVED 0x1000
@@ -55,11 +54,13 @@
#define PERF_CPUM_SF_MAX_CTR 2
#define PERF_EVENT_CPUM_SF 0xB0000UL /* Event: Basic-sampling */
#define PERF_EVENT_CPUM_SF_DIAG 0xBD000UL /* Event: Combined-sampling */
+#define PERF_EVENT_CPUM_CF_DIAG 0xBC000UL /* Event: Counter sets */
#define PERF_CPUM_SF_BASIC_MODE 0x0001 /* Basic-sampling flag */
#define PERF_CPUM_SF_DIAG_MODE 0x0002 /* Diagnostic-sampling flag */
#define PERF_CPUM_SF_MODE_MASK (PERF_CPUM_SF_BASIC_MODE| \
PERF_CPUM_SF_DIAG_MODE)
#define PERF_CPUM_SF_FULL_BLOCKS 0x0004 /* Process full SDBs only */
+#define PERF_CPUM_SF_FREQ_MODE 0x0008 /* Sampling with frequency */
#define REG_NONE 0
#define REG_OVERFLOW 1
@@ -70,5 +71,6 @@
#define SAMPL_FLAGS(hwc) ((hwc)->config_base)
#define SAMPL_DIAG_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE)
#define SDB_FULL_BLOCKS(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FULL_BLOCKS)
+#define SAMPLE_FREQ_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FREQ_MODE)
#endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 5ee7337..bccb8f4 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -139,8 +139,8 @@
/*
* page table entry allocation/free routines.
*/
-#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
-#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
+#define pte_alloc_one_kernel(mm) ((pte_t *)page_table_alloc(mm))
+#define pte_alloc_one(mm) ((pte_t *)page_table_alloc(mm))
#define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
#define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index de05466..5ff98d7 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -86,6 +86,7 @@
*/
extern unsigned long VMALLOC_START;
extern unsigned long VMALLOC_END;
+#define VMALLOC_DEFAULT_SIZE ((128UL << 30) - MODULES_LEN)
extern struct page *vmemmap;
#define VMEM_MAX_PHYS ((unsigned long) vmemmap)
@@ -238,7 +239,7 @@
#define _REGION_ENTRY_NOEXEC 0x100 /* region no-execute bit */
#define _REGION_ENTRY_OFFSET 0xc0 /* region table offset */
#define _REGION_ENTRY_INVALID 0x20 /* invalid region table entry */
-#define _REGION_ENTRY_TYPE_MASK 0x0c /* region/segment table type mask */
+#define _REGION_ENTRY_TYPE_MASK 0x0c /* region table type mask */
#define _REGION_ENTRY_TYPE_R1 0x0c /* region first table type */
#define _REGION_ENTRY_TYPE_R2 0x08 /* region second table type */
#define _REGION_ENTRY_TYPE_R3 0x04 /* region third table type */
@@ -277,6 +278,7 @@
#define _SEGMENT_ENTRY_PROTECT 0x200 /* segment protection bit */
#define _SEGMENT_ENTRY_NOEXEC 0x100 /* segment no-execute bit */
#define _SEGMENT_ENTRY_INVALID 0x20 /* invalid segment table entry */
+#define _SEGMENT_ENTRY_TYPE_MASK 0x0c /* segment table type mask */
#define _SEGMENT_ENTRY (0)
#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INVALID)
@@ -341,6 +343,8 @@
#define PTRS_PER_P4D _CRST_ENTRIES
#define PTRS_PER_PGD _CRST_ENTRIES
+#define MAX_PTRS_PER_P4D PTRS_PER_P4D
+
/*
* Segment table and region3 table entry encoding
* (R = read-only, I = invalid, y = young bit):
@@ -466,6 +470,12 @@
_SEGMENT_ENTRY_YOUNG | \
_SEGMENT_ENTRY_PROTECT | \
_SEGMENT_ENTRY_NOEXEC)
+#define SEGMENT_KERNEL_EXEC __pgprot(_SEGMENT_ENTRY | \
+ _SEGMENT_ENTRY_LARGE | \
+ _SEGMENT_ENTRY_READ | \
+ _SEGMENT_ENTRY_WRITE | \
+ _SEGMENT_ENTRY_YOUNG | \
+ _SEGMENT_ENTRY_DIRTY)
/*
* Region3 entry (large page) protection definitions.
@@ -606,15 +616,17 @@
static inline int pgd_bad(pgd_t pgd)
{
- /*
- * With dynamic page table levels the pgd can be a region table
- * entry or a segment table entry. Check for the bit that are
- * invalid for either table entry.
- */
- unsigned long mask =
- ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
- ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
- return (pgd_val(pgd) & mask) != 0;
+ if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R1)
+ return 0;
+ return (pgd_val(pgd) & ~_REGION_ENTRY_BITS) != 0;
+}
+
+static inline unsigned long pgd_pfn(pgd_t pgd)
+{
+ unsigned long origin_mask;
+
+ origin_mask = _REGION_ENTRY_ORIGIN;
+ return (pgd_val(pgd) & origin_mask) >> PAGE_SHIFT;
}
static inline int p4d_folded(p4d_t p4d)
@@ -687,6 +699,8 @@
static inline int pmd_bad(pmd_t pmd)
{
+ if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0)
+ return 1;
if (pmd_large(pmd))
return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
@@ -694,8 +708,12 @@
static inline int pud_bad(pud_t pud)
{
- if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
- return pmd_bad(__pmd(pud_val(pud)));
+ unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK;
+
+ if (type > _REGION_ENTRY_TYPE_R3)
+ return 1;
+ if (type < _REGION_ENTRY_TYPE_R3)
+ return 0;
if (pud_large(pud))
return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0;
return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
@@ -703,8 +721,12 @@
static inline int p4d_bad(p4d_t p4d)
{
- if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
- return pud_bad(__pud(p4d_val(p4d)));
+ unsigned long type = p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK;
+
+ if (type > _REGION_ENTRY_TYPE_R2)
+ return 1;
+ if (type < _REGION_ENTRY_TYPE_R2)
+ return 0;
return (p4d_val(p4d) & ~_REGION_ENTRY_BITS) != 0;
}
@@ -975,9 +997,9 @@
#define IPTE_NODAT 0x400
#define IPTE_GUEST_ASCE 0x800
-static inline void __ptep_ipte(unsigned long address, pte_t *ptep,
- unsigned long opt, unsigned long asce,
- int local)
+static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep,
+ unsigned long opt, unsigned long asce,
+ int local)
{
unsigned long pto = (unsigned long) ptep;
@@ -998,8 +1020,8 @@
: [r1] "a" (pto), [m4] "i" (local) : "memory");
}
-static inline void __ptep_ipte_range(unsigned long address, int nr,
- pte_t *ptep, int local)
+static __always_inline void __ptep_ipte_range(unsigned long address, int nr,
+ pte_t *ptep, int local)
{
unsigned long pto = (unsigned long) ptep;
@@ -1053,8 +1075,9 @@
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
-pte_t ptep_modify_prot_start(struct mm_struct *, unsigned long, pte_t *);
-void ptep_modify_prot_commit(struct mm_struct *, unsigned long, pte_t *, pte_t);
+pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
+ pte_t *, pte_t, pte_t);
#define __HAVE_ARCH_PTEP_CLEAR_FLUSH
static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
@@ -1187,54 +1210,82 @@
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1))
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-
#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
#define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
#define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
+/*
+ * The pgd_offset function *always* adds the index for the top-level
+ * region/segment table. This is done to get a sequence like the
+ * following to work:
+ * pgdp = pgd_offset(current->mm, addr);
+ * pgd = READ_ONCE(*pgdp);
+ * p4dp = p4d_offset(&pgd, addr);
+ * ...
+ * The subsequent p4d_offset, pud_offset and pmd_offset functions
+ * only add an index if they dereferenced the pointer.
+ */
+static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address)
+{
+ unsigned long rste;
+ unsigned int shift;
+
+ /* Get the first entry of the top level table */
+ rste = pgd_val(*pgd);
+ /* Pick up the shift from the table type of the first entry */
+ shift = ((rste & _REGION_ENTRY_TYPE_MASK) >> 2) * 11 + 20;
+ return pgd + ((address >> shift) & (PTRS_PER_PGD - 1));
+}
+
+#define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
{
- p4d_t *p4d = (p4d_t *) pgd;
-
- if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
- p4d = (p4d_t *) pgd_deref(*pgd);
- return p4d + p4d_index(address);
+ if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+ return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
+ return (p4d_t *) pgd;
}
static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
{
- pud_t *pud = (pud_t *) p4d;
-
- if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
- pud = (pud_t *) p4d_deref(*p4d);
- return pud + pud_index(address);
+ if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+ return (pud_t *) p4d_deref(*p4d) + pud_index(address);
+ return (pud_t *) p4d;
}
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
- pmd_t *pmd = (pmd_t *) pud;
-
- if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
- pmd = (pmd_t *) pud_deref(*pud);
- return pmd + pmd_index(address);
+ if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+ return (pmd_t *) pud_deref(*pud) + pmd_index(address);
+ return (pmd_t *) pud;
}
+static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
+{
+ return (pte_t *) pmd_deref(*pmd) + pte_index(address);
+}
+
+#define pte_offset_kernel(pmd, address) pte_offset(pmd, address)
+#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
+
+static inline void pte_unmap(pte_t *pte) { }
+
+static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
+{
+ return end <= current->mm->context.asce_limit;
+}
+#define gup_fast_permitted gup_fast_permitted
+
#define pfn_pte(pfn,pgprot) mk_pte_phys(__pa((pfn) << PAGE_SHIFT),(pgprot))
#define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT)
#define pte_page(x) pfn_to_page(pte_pfn(x))
#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd))
#define pud_page(pud) pfn_to_page(pud_pfn(pud))
-#define p4d_page(pud) pfn_to_page(p4d_pfn(p4d))
-
-/* Find an entry in the lowest level page table.. */
-#define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr))
-#define pte_offset_kernel(pmd, address) pte_offset(pmd,address)
-#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
-#define pte_unmap(pte) do { } while (0)
+#define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d))
+#define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd))
static inline pmd_t pmd_wrprotect(pmd_t pmd)
{
@@ -1385,9 +1436,9 @@
#define IDTE_NODAT 0x1000
#define IDTE_GUEST_ASCE 0x2000
-static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
- unsigned long opt, unsigned long asce,
- int local)
+static __always_inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
+ unsigned long opt, unsigned long asce,
+ int local)
{
unsigned long sto;
@@ -1411,9 +1462,9 @@
}
}
-static inline void __pudp_idte(unsigned long addr, pud_t *pudp,
- unsigned long opt, unsigned long asce,
- int local)
+static __always_inline void __pudp_idte(unsigned long addr, pud_t *pudp,
+ unsigned long opt, unsigned long asce,
+ int local)
{
unsigned long r3o;
@@ -1632,12 +1683,6 @@
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
-/*
- * No page table caches to initialise
- */
-static inline void pgtable_cache_init(void) { }
-static inline void check_pgt_cache(void) { }
-
#include <asm-generic/pgtable.h>
#endif /* _S390_PAGE_H */
diff --git a/arch/s390/include/asm/pkey.h b/arch/s390/include/asm/pkey.h
index 053117b..dd3d20c 100644
--- a/arch/s390/include/asm/pkey.h
+++ b/arch/s390/include/asm/pkey.h
@@ -2,7 +2,7 @@
/*
* Kernelspace interface to the pkey device driver
*
- * Copyright IBM Corp. 2016
+ * Copyright IBM Corp. 2016,2019
*
* Author: Harald Freudenberger <freude@de.ibm.com>
*
@@ -16,97 +16,13 @@
#include <uapi/asm/pkey.h>
/*
- * Generate (AES) random secure key.
- * @param cardnr may be -1 (use default card)
- * @param domain may be -1 (use default domain)
- * @param keytype one of the PKEY_KEYTYPE values
- * @param seckey pointer to buffer receiving the secure key
+ * In-kernel API: Transform an key blob (of any type) into a protected key.
+ * @param key pointer to a buffer containing the key blob
+ * @param keylen size of the key blob in bytes
+ * @param protkey pointer to buffer receiving the protected key
* @return 0 on success, negative errno value on failure
*/
-int pkey_genseckey(__u16 cardnr, __u16 domain,
- __u32 keytype, struct pkey_seckey *seckey);
-
-/*
- * Generate (AES) secure key with given key value.
- * @param cardnr may be -1 (use default card)
- * @param domain may be -1 (use default domain)
- * @param keytype one of the PKEY_KEYTYPE values
- * @param clrkey pointer to buffer with clear key data
- * @param seckey pointer to buffer receiving the secure key
- * @return 0 on success, negative errno value on failure
- */
-int pkey_clr2seckey(__u16 cardnr, __u16 domain, __u32 keytype,
- const struct pkey_clrkey *clrkey,
- struct pkey_seckey *seckey);
-
-/*
- * Derive (AES) proteced key from the (AES) secure key blob.
- * @param cardnr may be -1 (use default card)
- * @param domain may be -1 (use default domain)
- * @param seckey pointer to buffer with the input secure key
- * @param protkey pointer to buffer receiving the protected key and
- * additional info (type, length)
- * @return 0 on success, negative errno value on failure
- */
-int pkey_sec2protkey(__u16 cardnr, __u16 domain,
- const struct pkey_seckey *seckey,
- struct pkey_protkey *protkey);
-
-/*
- * Derive (AES) protected key from a given clear key value.
- * @param keytype one of the PKEY_KEYTYPE values
- * @param clrkey pointer to buffer with clear key data
- * @param protkey pointer to buffer receiving the protected key and
- * additional info (type, length)
- * @return 0 on success, negative errno value on failure
- */
-int pkey_clr2protkey(__u32 keytype,
- const struct pkey_clrkey *clrkey,
- struct pkey_protkey *protkey);
-
-/*
- * Search for a matching crypto card based on the Master Key
- * Verification Pattern provided inside a secure key.
- * @param seckey pointer to buffer with the input secure key
- * @param cardnr pointer to cardnr, receives the card number on success
- * @param domain pointer to domain, receives the domain number on success
- * @param verify if set, always verify by fetching verification pattern
- * from card
- * @return 0 on success, negative errno value on failure. If no card could be
- * found, -ENODEV is returned.
- */
-int pkey_findcard(const struct pkey_seckey *seckey,
- __u16 *cardnr, __u16 *domain, int verify);
-
-/*
- * Find card and transform secure key to protected key.
- * @param seckey pointer to buffer with the input secure key
- * @param protkey pointer to buffer receiving the protected key and
- * additional info (type, length)
- * @return 0 on success, negative errno value on failure
- */
-int pkey_skey2pkey(const struct pkey_seckey *seckey,
- struct pkey_protkey *protkey);
-
-/*
- * Verify the given secure key for being able to be useable with
- * the pkey module. Check for correct key type and check for having at
- * least one crypto card being able to handle this key (master key
- * or old master key verification pattern matches).
- * Return some info about the key: keysize in bits, keytype (currently
- * only AES), flag if key is wrapped with an old MKVP.
- * @param seckey pointer to buffer with the input secure key
- * @param pcardnr pointer to cardnr, receives the card number on success
- * @param pdomain pointer to domain, receives the domain number on success
- * @param pkeysize pointer to keysize, receives the bitsize of the key
- * @param pattributes pointer to attributes, receives additional info
- * PKEY_VERIFY_ATTR_AES if the key is an AES key
- * PKEY_VERIFY_ATTR_OLD_MKVP if key has old mkvp stored in
- * @return 0 on success, negative errno value on failure. If no card could
- * be found which is able to handle this key, -ENODEV is returned.
- */
-int pkey_verifykey(const struct pkey_seckey *seckey,
- u16 *pcardnr, u16 *pdomain,
- u16 *pkeysize, u32 *pattributes);
+int pkey_keyblob2pkey(const u8 *key, u32 keylen,
+ struct pkey_protkey *protkey);
#endif /* _KAPI_PKEY_H */
diff --git a/arch/s390/include/asm/pnet.h b/arch/s390/include/asm/pnet.h
index 6e27858..5739276 100644
--- a/arch/s390/include/asm/pnet.h
+++ b/arch/s390/include/asm/pnet.h
@@ -11,13 +11,5 @@
#include <linux/device.h>
#include <linux/types.h>
-#define PNETIDS_LEN 64 /* Total utility string length in bytes
- * to cover up to 4 PNETIDs of 16 bytes
- * for up to 4 device ports
- */
-#define MAX_PNETID_LEN 16 /* Max.length of a single port PNETID */
-#define MAX_PNETID_PORTS (PNETIDS_LEN / MAX_PNETID_LEN)
- /* Max. # of ports with a PNETID */
-
int pnet_id_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid);
#endif /* _ASM_S390_PNET_H */
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index 23a14d1..b5ea9e1 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -8,6 +8,8 @@
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+/* We use the MSB mostly because its available */
+#define PREEMPT_NEED_RESCHED 0x80000000
#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED)
static inline int preempt_count(void)
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 7f2953c..51a0e4a 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -12,7 +12,7 @@
#ifndef __ASM_S390_PROCESSOR_H
#define __ASM_S390_PROCESSOR_H
-#include <linux/const.h>
+#include <linux/bits.h>
#define CIF_MCCK_PENDING 0 /* machine check handling is pending */
#define CIF_ASCE_PRIMARY 1 /* primary asce needs fixup / uaccess */
@@ -24,18 +24,19 @@
#define CIF_MCCK_GUEST 7 /* machine check happening in guest */
#define CIF_DEDICATED_CPU 8 /* this CPU is dedicated */
-#define _CIF_MCCK_PENDING _BITUL(CIF_MCCK_PENDING)
-#define _CIF_ASCE_PRIMARY _BITUL(CIF_ASCE_PRIMARY)
-#define _CIF_ASCE_SECONDARY _BITUL(CIF_ASCE_SECONDARY)
-#define _CIF_NOHZ_DELAY _BITUL(CIF_NOHZ_DELAY)
-#define _CIF_FPU _BITUL(CIF_FPU)
-#define _CIF_IGNORE_IRQ _BITUL(CIF_IGNORE_IRQ)
-#define _CIF_ENABLED_WAIT _BITUL(CIF_ENABLED_WAIT)
-#define _CIF_MCCK_GUEST _BITUL(CIF_MCCK_GUEST)
-#define _CIF_DEDICATED_CPU _BITUL(CIF_DEDICATED_CPU)
+#define _CIF_MCCK_PENDING BIT(CIF_MCCK_PENDING)
+#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)
+#define _CIF_ENABLED_WAIT BIT(CIF_ENABLED_WAIT)
+#define _CIF_MCCK_GUEST BIT(CIF_MCCK_GUEST)
+#define _CIF_DEDICATED_CPU BIT(CIF_DEDICATED_CPU)
#ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
#include <linux/linkage.h>
#include <linux/irqflags.h>
#include <asm/cpu.h>
@@ -73,12 +74,6 @@
#define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
-/*
- * Default implementation of macro that returns current
- * instruction pointer ("program counter").
- */
-#define current_text_addr() ({ void *pc; asm("basr %0,0" : "=a" (pc)); pc; })
-
static inline void get_cpu_id(struct cpuid *ptr)
{
asm volatile("stidp %0" : "=Q" (*ptr));
@@ -162,25 +157,6 @@
typedef struct thread_struct thread_struct;
-/*
- * Stack layout of a C stack frame.
- */
-#ifndef __PACK_STACK
-struct stack_frame {
- unsigned long back_chain;
- unsigned long empty1[5];
- unsigned long gprs[10];
- unsigned int empty2[8];
-};
-#else
-struct stack_frame {
- unsigned long empty1[5];
- unsigned int empty2[8];
- unsigned long gprs[10];
- unsigned long back_chain;
-};
-#endif
-
#define ARCH_MIN_TASKALIGN 8
#define INIT_THREAD { \
@@ -212,11 +188,7 @@
struct seq_file;
struct pt_regs;
-typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable);
-void dump_trace(dump_trace_func_t func, void *data,
- struct task_struct *task, unsigned long sp);
void show_registers(struct pt_regs *regs);
-
void show_cacheinfo(struct seq_file *m);
/* Free all resources held by a thread. */
@@ -242,7 +214,7 @@
return sp;
}
-static inline unsigned short stap(void)
+static __no_kasan_or_inline unsigned short stap(void)
{
unsigned short cpu_address;
@@ -250,12 +222,6 @@
return cpu_address;
}
-/*
- * Give up the time slice of the virtual PU.
- */
-#define cpu_relax_yield cpu_relax_yield
-void cpu_relax_yield(void);
-
#define cpu_relax() barrier()
#define ECAG_CACHE_ATTRIBUTE 0
@@ -287,7 +253,7 @@
* Set PSW mask to specified value, while leaving the
* PSW addr pointing to the next instruction.
*/
-static inline void __load_psw_mask(unsigned long mask)
+static __no_kasan_or_inline void __load_psw_mask(unsigned long mask)
{
unsigned long addr;
psw_t psw;
@@ -296,10 +262,10 @@
asm volatile(
" larl %0,1f\n"
- " stg %0,%O1+8(%R1)\n"
- " lpswe %1\n"
+ " stg %0,%1\n"
+ " lpswe %2\n"
"1:"
- : "=&d" (addr), "=Q" (psw) : "Q" (psw) : "memory", "cc");
+ : "=&d" (addr), "=Q" (psw.addr) : "Q" (psw) : "memory", "cc");
}
/*
@@ -344,12 +310,12 @@
/*
* Function to drop a processor into disabled wait state
*/
-static inline void __noreturn disabled_wait(unsigned long code)
+static inline void __noreturn disabled_wait(void)
{
psw_t psw;
psw.mask = PSW_MASK_BASE | PSW_MASK_WAIT | PSW_MASK_BA | PSW_MASK_EA;
- psw.addr = code;
+ psw.addr = _THIS_IP_;
__load_psw(psw);
while (1);
}
@@ -358,11 +324,9 @@
* Basic Machine Check/Program Check Handler.
*/
-extern void s390_base_mcck_handler(void);
extern void s390_base_pgm_handler(void);
extern void s390_base_ext_handler(void);
-extern void (*s390_base_mcck_handler_fn)(void);
extern void (*s390_base_pgm_handler_fn)(void);
extern void (*s390_base_ext_handler_fn)(void);
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 6f70d81..f009a13 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -7,7 +7,7 @@
#ifndef _S390_PTRACE_H
#define _S390_PTRACE_H
-#include <linux/const.h>
+#include <linux/bits.h>
#include <uapi/asm/ptrace.h>
#define PIF_SYSCALL 0 /* inside a system call */
@@ -15,10 +15,10 @@
#define PIF_SYSCALL_RESTART 2 /* restart the current system call */
#define PIF_GUEST_FAULT 3 /* indicates program check in sie64a */
-#define _PIF_SYSCALL _BITUL(PIF_SYSCALL)
-#define _PIF_PER_TRAP _BITUL(PIF_PER_TRAP)
-#define _PIF_SYSCALL_RESTART _BITUL(PIF_SYSCALL_RESTART)
-#define _PIF_GUEST_FAULT _BITUL(PIF_GUEST_FAULT)
+#define _PIF_SYSCALL BIT(PIF_SYSCALL)
+#define _PIF_PER_TRAP BIT(PIF_PER_TRAP)
+#define _PIF_SYSCALL_RESTART BIT(PIF_SYSCALL_RESTART)
+#define _PIF_GUEST_FAULT BIT(PIF_GUEST_FAULT)
#ifndef __ASSEMBLY__
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 9c9970a..e3f238e 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -16,6 +16,7 @@
#define QDIO_MAX_QUEUES_PER_IRQ 4
#define QDIO_MAX_BUFFERS_PER_Q 128
#define QDIO_MAX_BUFFERS_MASK (QDIO_MAX_BUFFERS_PER_Q - 1)
+#define QDIO_BUFNR(num) ((num) & QDIO_MAX_BUFFERS_MASK)
#define QDIO_MAX_ELEMENTS_PER_BUFFER 16
#define QDIO_SBAL_SIZE 256
@@ -28,7 +29,7 @@
* @sliba: storage list information block address
* @sla: storage list address
* @slsba: storage list state block address
- * @akey: access key for DLIB
+ * @akey: access key for SLIB
* @bkey: access key for SL
* @ckey: access key for SBALs
* @dkey: access key for SLSB
@@ -50,11 +51,10 @@
/**
* struct qdr - queue description record (QDR)
* @qfmt: queue format
- * @pfmt: implementation dependent parameter format
* @ac: adapter characteristics
* @iqdcnt: input queue descriptor count
* @oqdcnt: output queue descriptor count
- * @iqdsz: inpout queue descriptor size
+ * @iqdsz: input queue descriptor size
* @oqdsz: output queue descriptor size
* @qiba: queue information block address
* @qkey: queue information block key
@@ -62,8 +62,7 @@
*/
struct qdr {
u32 qfmt : 8;
- u32 pfmt : 8;
- u32 : 8;
+ u32 : 16;
u32 ac : 8;
u32 : 8;
u32 iqdcnt : 8;
@@ -112,7 +111,7 @@
/* private: */
u8 res[88];
/* public: */
- u8 parm[QDIO_MAX_BUFFERS_PER_Q];
+ u8 parm[128];
} __attribute__ ((packed, aligned(256)));
/**
@@ -252,13 +251,11 @@
* (for communication with upper layer programs)
* (only required for use with completion queues)
* @flags: flags indicating state of buffer
- * @aob: pointer to QAOB used for the particular SBAL
* @user: pointer to upper layer program's state information related to SBAL
* (stored in user1 data of QAOB)
*/
struct qdio_outbuf_state {
u8 flags;
- struct qaob *aob;
void *user;
};
@@ -329,6 +326,7 @@
* struct qdio_initialize - qdio initialization data
* @cdev: associated ccw device
* @q_format: queue format
+ * @qdr_ac: feature flags to set
* @adapter_name: name for the adapter
* @qib_param_field_format: format for qib_parm_field
* @qib_param_field: pointer to 128 bytes or NULL, if no param field
@@ -340,6 +338,7 @@
* @input_handler: handler to be called for input queues
* @output_handler: handler to be called for output queues
* @queue_start_poll_array: polling handlers (one per input queue or NULL)
+ * @scan_threshold: # of in-use buffers that triggers scan on output queue
* @int_parm: interruption parameter
* @input_sbal_addr_array: address of no_input_qs * 128 pointers
* @output_sbal_addr_array: address of no_output_qs * 128 pointers
@@ -361,10 +360,10 @@
qdio_handler_t *output_handler;
void (**queue_start_poll_array) (struct ccw_device *, int,
unsigned long);
- int scan_threshold;
+ unsigned int scan_threshold;
unsigned long int_parm;
- void **input_sbal_addr_array;
- void **output_sbal_addr_array;
+ struct qdio_buffer **input_sbal_addr_array;
+ struct qdio_buffer **output_sbal_addr_array;
struct qdio_outbuf_state *output_sbal_state_array;
};
@@ -418,6 +417,9 @@
extern int qdio_start_irq(struct ccw_device *, int);
extern int qdio_stop_irq(struct ccw_device *, int);
extern int qdio_get_next_buffers(struct ccw_device *, int, int *, int *);
+extern int qdio_inspect_queue(struct ccw_device *cdev, unsigned int nr,
+ bool is_input, unsigned int *bufnr,
+ unsigned int *error);
extern int qdio_shutdown(struct ccw_device *, int);
extern int qdio_free(struct ccw_device *);
extern int qdio_get_ssqd_desc(struct ccw_device *, struct qdio_ssqd_desc *);
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index e44a8d7..c563f83 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -78,6 +78,9 @@
unsigned char has_skey : 1;
unsigned char has_kss : 1;
unsigned char has_gisaf : 1;
+ unsigned char has_diag318 : 1;
+ unsigned char has_sipl : 1;
+ unsigned char has_dirq : 1;
unsigned int ibc;
unsigned int mtid;
unsigned int mtid_cp;
@@ -95,6 +98,7 @@
struct zpci_report_error_header {
u8 version; /* Interface version byte */
u8 action; /* Action qualifier byte
+ * 0: Adapter Reset Request
* 1: Deconfigure and repair action requested
* (OpenCrypto Problem Call Home)
* 2: Informational Report
@@ -104,6 +108,8 @@
u8 data[0]; /* Subsequent Data passed verbatim to SCLP ET 24 */
} __packed;
+int sclp_early_read_info(void);
+int sclp_early_read_storage_info(void);
int sclp_early_get_core_info(struct sclp_core_info *info);
void sclp_early_get_ipl_info(struct sclp_ipl_info *info);
void sclp_early_detect(void);
@@ -111,6 +117,8 @@
void sclp_early_printk_force(const char *s);
void __sclp_early_printk(const char *s, unsigned int len, unsigned int force);
+int sclp_early_get_memsize(unsigned long *mem);
+int sclp_early_get_hsa_size(unsigned long *hsa_size);
int _sclp_get_core_info(struct sclp_core_info *info);
int sclp_core_configure(u8 core);
int sclp_core_deconfigure(u8 core);
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 724faed..42de04a 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -2,6 +2,40 @@
#ifndef _S390_SECTIONS_H
#define _S390_SECTIONS_H
+#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed
+
#include <asm-generic/sections.h>
+extern bool initmem_freed;
+
+static inline int arch_is_kernel_initmem_freed(unsigned long addr)
+{
+ if (!initmem_freed)
+ return 0;
+ return addr >= (unsigned long)__init_begin &&
+ addr < (unsigned long)__init_end;
+}
+
+/*
+ * .boot.data section contains variables "shared" between the decompressor and
+ * the decompressed kernel. The decompressor will store values in them, and
+ * copy over to the decompressed image before starting it.
+ *
+ * Each variable end up in its own intermediate section .boot.data.<var name>,
+ * those sections are later sorted by alignment + name and merged together into
+ * final .boot.data section, which should be identical in the decompressor and
+ * the decompressed kernel (that is checked during the build).
+ */
+#define __bootdata(var) __section(.boot.data.var) var
+
+/*
+ * .boot.preserved.data is similar to .boot.data, but it is not part of the
+ * .init section and thus will be preserved for later use in the decompressed
+ * kernel.
+ */
+#define __bootdata_preserved(var) __section(.boot.preserved.data.var) var
+
+extern unsigned long __sdma, __edma;
+extern unsigned long __stext_dma, __etext_dma;
+
#endif
diff --git a/arch/s390/include/asm/segment.h b/arch/s390/include/asm/segment.h
deleted file mode 100644
index 97a0582..0000000
--- a/arch/s390/include/asm/segment.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_SEGMENT_H
-#define _ASM_SEGMENT_H
-
-#endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 1d66016..6dc6c4f 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -6,37 +6,40 @@
#ifndef _ASM_S390_SETUP_H
#define _ASM_S390_SETUP_H
-#include <linux/const.h>
+#include <linux/bits.h>
#include <uapi/asm/setup.h>
#define EP_OFFSET 0x10008
#define EP_STRING "S390EP"
#define PARMAREA 0x10400
-#define PARMAREA_END 0x11000
+#define EARLY_SCCB_OFFSET 0x11000
+#define HEAD_END 0x12000
+
+#define EARLY_SCCB_SIZE PAGE_SIZE
/*
* Machine features detected in early.c
*/
-#define MACHINE_FLAG_VM _BITUL(0)
-#define MACHINE_FLAG_KVM _BITUL(1)
-#define MACHINE_FLAG_LPAR _BITUL(2)
-#define MACHINE_FLAG_DIAG9C _BITUL(3)
-#define MACHINE_FLAG_ESOP _BITUL(4)
-#define MACHINE_FLAG_IDTE _BITUL(5)
-#define MACHINE_FLAG_DIAG44 _BITUL(6)
-#define MACHINE_FLAG_EDAT1 _BITUL(7)
-#define MACHINE_FLAG_EDAT2 _BITUL(8)
-#define MACHINE_FLAG_TOPOLOGY _BITUL(10)
-#define MACHINE_FLAG_TE _BITUL(11)
-#define MACHINE_FLAG_TLB_LC _BITUL(12)
-#define MACHINE_FLAG_VX _BITUL(13)
-#define MACHINE_FLAG_TLB_GUEST _BITUL(14)
-#define MACHINE_FLAG_NX _BITUL(15)
-#define MACHINE_FLAG_GS _BITUL(16)
-#define MACHINE_FLAG_SCC _BITUL(17)
+#define MACHINE_FLAG_VM BIT(0)
+#define MACHINE_FLAG_KVM BIT(1)
+#define MACHINE_FLAG_LPAR BIT(2)
+#define MACHINE_FLAG_DIAG9C BIT(3)
+#define MACHINE_FLAG_ESOP BIT(4)
+#define MACHINE_FLAG_IDTE BIT(5)
+#define MACHINE_FLAG_DIAG44 BIT(6)
+#define MACHINE_FLAG_EDAT1 BIT(7)
+#define MACHINE_FLAG_EDAT2 BIT(8)
+#define MACHINE_FLAG_TOPOLOGY BIT(10)
+#define MACHINE_FLAG_TE BIT(11)
+#define MACHINE_FLAG_TLB_LC BIT(12)
+#define MACHINE_FLAG_VX BIT(13)
+#define MACHINE_FLAG_TLB_GUEST BIT(14)
+#define MACHINE_FLAG_NX BIT(15)
+#define MACHINE_FLAG_GS BIT(16)
+#define MACHINE_FLAG_SCC BIT(17)
-#define LPP_MAGIC _BITUL(31)
+#define LPP_MAGIC BIT(31)
#define LPP_PID_MASK _AC(0xffffffff, UL)
/* Offsets to entry points in kernel/head.S */
@@ -51,6 +54,7 @@
#define INITRD_SIZE_OFFSET 0x10410
#define OLDMEM_BASE_OFFSET 0x10418
#define OLDMEM_SIZE_OFFSET 0x10420
+#define KERNEL_VERSION_OFFSET 0x10428
#define COMMAND_LINE_OFFSET 0x10480
#ifndef __ASSEMBLY__
@@ -65,11 +69,23 @@
#define OLDMEM_SIZE (*(unsigned long *) (OLDMEM_SIZE_OFFSET))
#define COMMAND_LINE ((char *) (COMMAND_LINE_OFFSET))
+struct parmarea {
+ unsigned long ipl_device; /* 0x10400 */
+ unsigned long initrd_start; /* 0x10408 */
+ unsigned long initrd_size; /* 0x10410 */
+ unsigned long oldmem_base; /* 0x10418 */
+ unsigned long oldmem_size; /* 0x10420 */
+ unsigned long kernel_version; /* 0x10428 */
+ char pad1[0x10480 - 0x10430]; /* 0x10430 - 0x10480 */
+ char command_line[ARCH_COMMAND_LINE_SIZE]; /* 0x10480 */
+};
+
+extern int noexec_disabled;
extern int memory_end_set;
extern unsigned long memory_end;
+extern unsigned long vmalloc_size;
extern unsigned long max_physmem_end;
-
-extern void detect_memory_memblock(void);
+extern unsigned long __swsusp_reset_dma;
#define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM)
#define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -135,6 +151,12 @@
extern void (*_machine_halt)(void);
extern void (*_machine_power_off)(void);
+extern unsigned long __kaslr_offset;
+static inline unsigned long kaslr_offset(void)
+{
+ return __kaslr_offset;
+}
+
#else /* __ASSEMBLY__ */
#define IPL_DEVICE (IPL_DEVICE_OFFSET)
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 3907ead..b157a81 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -9,9 +9,6 @@
#define __ASM_SMP_H
#include <asm/sigp.h>
-
-#ifdef CONFIG_SMP
-
#include <asm/lowcore.h>
#define raw_smp_processor_id() (S390_lowcore.cpu_nr)
@@ -40,33 +37,6 @@
extern void smp_fill_possible_mask(void);
extern void smp_detect_cpus(void);
-#else /* CONFIG_SMP */
-
-#define smp_cpu_mtid 0
-
-static inline void smp_call_ipl_cpu(void (*func)(void *), void *data)
-{
- func(data);
-}
-
-static inline void smp_call_online_cpu(void (*func)(void *), void *data)
-{
- func(data);
-}
-
-static inline void smp_emergency_stop(void)
-{
-}
-
-static inline int smp_find_processor_id(u16 address) { return 0; }
-static inline int smp_store_status(int cpu) { return 0; }
-static inline int smp_vcpu_scheduled(int cpu) { return 1; }
-static inline void smp_yield_cpu(int cpu) { }
-static inline void smp_fill_possible_mask(void) { }
-static inline void smp_detect_cpus(void) { }
-
-#endif /* CONFIG_SMP */
-
static inline void smp_stop_cpu(void)
{
u16 pcpu = stap();
@@ -83,14 +53,9 @@
return cpu - (cpu % (smp_cpu_mtid + 1));
}
-#ifdef CONFIG_HOTPLUG_CPU
extern int smp_rescan_cpus(void);
extern void __noreturn cpu_die(void);
extern void __cpu_die(unsigned int cpu);
extern int __cpu_disable(void);
-#else
-static inline int smp_rescan_cpus(void) { return 0; }
-static inline void cpu_die(void) { }
-#endif
#endif /* __ASM_SMP_H */
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 0a29588..c02bff3 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -20,11 +20,7 @@
extern int spin_retry;
-#ifndef CONFIG_SMP
-static inline bool arch_vcpu_is_preempted(int cpu) { return false; }
-#else
bool arch_vcpu_is_preempted(int cpu);
-#endif
#define vcpu_is_preempted arch_vcpu_is_preempted
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
new file mode 100644
index 0000000..0ae4bbf
--- /dev/null
+++ b/arch/s390/include/asm/stacktrace.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_STACKTRACE_H
+#define _ASM_S390_STACKTRACE_H
+
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+#include <asm/switch_to.h>
+
+enum stack_type {
+ STACK_TYPE_UNKNOWN,
+ STACK_TYPE_TASK,
+ STACK_TYPE_IRQ,
+ STACK_TYPE_NODAT,
+ STACK_TYPE_RESTART,
+};
+
+struct stack_info {
+ enum stack_type type;
+ unsigned long begin, end;
+};
+
+const char *stack_type_name(enum stack_type type);
+int get_stack_info(unsigned long sp, struct task_struct *task,
+ struct stack_info *info, unsigned long *visit_mask);
+
+static inline bool on_stack(struct stack_info *info,
+ unsigned long addr, size_t len)
+{
+ if (info->type == STACK_TYPE_UNKNOWN)
+ return false;
+ if (addr + len < addr)
+ return false;
+ return addr >= info->begin && addr + len <= info->end;
+}
+
+static inline unsigned long get_stack_pointer(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if (regs)
+ return (unsigned long) kernel_stack_pointer(regs);
+ if (task == current)
+ return current_stack_pointer();
+ return (unsigned long) task->thread.ksp;
+}
+
+/*
+ * Stack layout of a C stack frame.
+ */
+#ifndef __PACK_STACK
+struct stack_frame {
+ unsigned long back_chain;
+ unsigned long empty1[5];
+ unsigned long gprs[10];
+ unsigned int empty2[8];
+};
+#else
+struct stack_frame {
+ unsigned long empty1[5];
+ unsigned int empty2[8];
+ unsigned long gprs[10];
+ unsigned long back_chain;
+};
+#endif
+
+#define CALL_ARGS_0() \
+ register unsigned long r2 asm("2")
+#define CALL_ARGS_1(arg1) \
+ register unsigned long r2 asm("2") = (unsigned long)(arg1)
+#define CALL_ARGS_2(arg1, arg2) \
+ CALL_ARGS_1(arg1); \
+ register unsigned long r3 asm("3") = (unsigned long)(arg2)
+#define CALL_ARGS_3(arg1, arg2, arg3) \
+ CALL_ARGS_2(arg1, arg2); \
+ register unsigned long r4 asm("4") = (unsigned long)(arg3)
+#define CALL_ARGS_4(arg1, arg2, arg3, arg4) \
+ CALL_ARGS_3(arg1, arg2, arg3); \
+ register unsigned long r4 asm("5") = (unsigned long)(arg4)
+#define CALL_ARGS_5(arg1, arg2, arg3, arg4, arg5) \
+ CALL_ARGS_4(arg1, arg2, arg3, arg4); \
+ register unsigned long r4 asm("6") = (unsigned long)(arg5)
+
+#define CALL_FMT_0 "=&d" (r2) :
+#define CALL_FMT_1 "+&d" (r2) :
+#define CALL_FMT_2 CALL_FMT_1 "d" (r3),
+#define CALL_FMT_3 CALL_FMT_2 "d" (r4),
+#define CALL_FMT_4 CALL_FMT_3 "d" (r5),
+#define CALL_FMT_5 CALL_FMT_4 "d" (r6),
+
+#define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory"
+#define CALL_CLOBBER_4 CALL_CLOBBER_5
+#define CALL_CLOBBER_3 CALL_CLOBBER_4, "5"
+#define CALL_CLOBBER_2 CALL_CLOBBER_3, "4"
+#define CALL_CLOBBER_1 CALL_CLOBBER_2, "3"
+#define CALL_CLOBBER_0 CALL_CLOBBER_1
+
+#define CALL_ON_STACK(fn, stack, nr, args...) \
+({ \
+ CALL_ARGS_##nr(args); \
+ unsigned long prev; \
+ \
+ asm volatile( \
+ " la %[_prev],0(15)\n" \
+ " la 15,0(%[_stack])\n" \
+ " stg %[_prev],%[_bc](15)\n" \
+ " brasl 14,%[_fn]\n" \
+ " la 15,0(%[_prev])\n" \
+ : [_prev] "=&a" (prev), CALL_FMT_##nr \
+ [_stack] "a" (stack), \
+ [_bc] "i" (offsetof(struct stack_frame, back_chain)), \
+ [_fn] "X" (fn) : CALL_CLOBBER_##nr); \
+ r2; \
+})
+
+#endif /* _ASM_S390_STACKTRACE_H */
diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h
index 50f26fc..4c0690f 100644
--- a/arch/s390/include/asm/string.h
+++ b/arch/s390/include/asm/string.h
@@ -12,15 +12,21 @@
#include <linux/types.h>
#endif
-#define __HAVE_ARCH_MEMCHR /* inline & arch function */
-#define __HAVE_ARCH_MEMCMP /* arch function */
#define __HAVE_ARCH_MEMCPY /* gcc builtin & arch function */
#define __HAVE_ARCH_MEMMOVE /* gcc builtin & arch function */
-#define __HAVE_ARCH_MEMSCAN /* inline & arch function */
#define __HAVE_ARCH_MEMSET /* gcc builtin & arch function */
#define __HAVE_ARCH_MEMSET16 /* arch function */
#define __HAVE_ARCH_MEMSET32 /* arch function */
#define __HAVE_ARCH_MEMSET64 /* arch function */
+
+void *memcpy(void *dest, const void *src, size_t n);
+void *memset(void *s, int c, size_t n);
+void *memmove(void *dest, const void *src, size_t n);
+
+#ifndef CONFIG_KASAN
+#define __HAVE_ARCH_MEMCHR /* inline & arch function */
+#define __HAVE_ARCH_MEMCMP /* arch function */
+#define __HAVE_ARCH_MEMSCAN /* inline & arch function */
#define __HAVE_ARCH_STRCAT /* inline & arch function */
#define __HAVE_ARCH_STRCMP /* arch function */
#define __HAVE_ARCH_STRCPY /* inline & arch function */
@@ -35,9 +41,6 @@
/* Prototypes for non-inlined arch strings functions. */
int memcmp(const void *s1, const void *s2, size_t n);
-void *memcpy(void *dest, const void *src, size_t n);
-void *memset(void *s, int c, size_t n);
-void *memmove(void *dest, const void *src, size_t n);
int strcmp(const char *s1, const char *s2);
size_t strlcat(char *dest, const char *src, size_t n);
size_t strlcpy(char *dest, const char *src, size_t size);
@@ -45,6 +48,7 @@
char *strncpy(char *dest, const char *src, size_t n);
char *strrchr(const char *s, int c);
char *strstr(const char *s1, const char *s2);
+#endif /* !CONFIG_KASAN */
#undef __HAVE_ARCH_STRCHR
#undef __HAVE_ARCH_STRNCHR
@@ -53,6 +57,32 @@
#undef __HAVE_ARCH_STRSEP
#undef __HAVE_ARCH_STRSPN
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+
+extern void *__memcpy(void *dest, const void *src, size_t n);
+extern void *__memset(void *s, int c, size_t n);
+extern void *__memmove(void *dest, const void *src, size_t n);
+
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+#define strlen(s) __strlen(s)
+
+#define __no_sanitize_prefix_strfunc(x) __##x
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
+#else
+#define __no_sanitize_prefix_strfunc(x) x
+#endif /* defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) */
+
void *__memset16(uint16_t *s, uint16_t v, size_t count);
void *__memset32(uint32_t *s, uint32_t v, size_t count);
void *__memset64(uint64_t *s, uint64_t v, size_t count);
@@ -74,6 +104,7 @@
#if !defined(IN_ARCH_STRING_C) && (!defined(CONFIG_FORTIFY_SOURCE) || defined(__NO_FORTIFY))
+#ifdef __HAVE_ARCH_MEMCHR
static inline void *memchr(const void * s, int c, size_t n)
{
register int r0 asm("0") = (char) c;
@@ -88,7 +119,9 @@
: "+a" (ret), "+&a" (s) : "d" (r0) : "cc", "memory");
return (void *) ret;
}
+#endif
+#ifdef __HAVE_ARCH_MEMSCAN
static inline void *memscan(void *s, int c, size_t n)
{
register int r0 asm("0") = (char) c;
@@ -100,7 +133,9 @@
: "+a" (ret), "+&a" (s) : "d" (r0) : "cc", "memory");
return (void *) ret;
}
+#endif
+#ifdef __HAVE_ARCH_STRCAT
static inline char *strcat(char *dst, const char *src)
{
register int r0 asm("0") = 0;
@@ -116,7 +151,9 @@
: "d" (r0), "0" (0) : "cc", "memory" );
return ret;
}
+#endif
+#ifdef __HAVE_ARCH_STRCPY
static inline char *strcpy(char *dst, const char *src)
{
register int r0 asm("0") = 0;
@@ -129,8 +166,10 @@
: "cc", "memory");
return ret;
}
+#endif
-static inline size_t strlen(const char *s)
+#if defined(__HAVE_ARCH_STRLEN) || (defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__))
+static inline size_t __no_sanitize_prefix_strfunc(strlen)(const char *s)
{
register unsigned long r0 asm("0") = 0;
const char *tmp = s;
@@ -141,7 +180,9 @@
: "+d" (r0), "+a" (tmp) : : "cc", "memory");
return r0 - (unsigned long) s;
}
+#endif
+#ifdef __HAVE_ARCH_STRNLEN
static inline size_t strnlen(const char * s, size_t n)
{
register int r0 asm("0") = 0;
@@ -154,6 +195,7 @@
: "+a" (end), "+a" (tmp) : "d" (r0) : "cc", "memory");
return end - s;
}
+#endif
#else /* IN_ARCH_STRING_C */
void *memchr(const void * s, int c, size_t n);
void *memscan(void *s, int c, size_t n);
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 96f9a91..f073292 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -14,13 +14,8 @@
#include <linux/err.h>
#include <asm/ptrace.h>
-/*
- * The syscall table always contains 32 bit pointers since we know that the
- * address of the function to be called is (way) below 4GB. So the "int"
- * type here is what we want [need] for both 32 bit and 64 bit systems.
- */
-extern const unsigned int sys_call_table[];
-extern const unsigned int sys_call_table_emu[];
+extern const unsigned long sys_call_table[];
+extern const unsigned long sys_call_table_emu[];
static inline long syscall_get_nr(struct task_struct *task,
struct pt_regs *regs)
@@ -56,46 +51,38 @@
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
unsigned long mask = -1UL;
+ unsigned int n = 6;
- /*
- * No arguments for this syscall, there's nothing to do.
- */
- if (!n)
- return;
-
- BUG_ON(i + n > 6);
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_31BIT))
mask = 0xffffffff;
#endif
while (n-- > 0)
- if (i + n > 0)
- args[n] = regs->gprs[2 + i + n] & mask;
- if (i == 0)
- args[0] = regs->orig_gpr2 & mask;
+ if (n > 0)
+ args[n] = regs->gprs[2 + n] & mask;
+
+ args[0] = regs->orig_gpr2 & mask;
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
+ unsigned int n = 6;
+
while (n-- > 0)
- if (i + n > 0)
- regs->gprs[2 + i + n] = args[n];
- if (i == 0)
- regs->orig_gpr2 = args[0];
+ if (n > 0)
+ regs->gprs[2 + n] = args[n];
+ regs->orig_gpr2 = args[0];
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
#ifdef CONFIG_COMPAT
- if (test_tsk_thread_flag(current, TIF_31BIT))
+ if (test_tsk_thread_flag(task, TIF_31BIT))
return AUDIT_ARCH_S390;
#endif
return AUDIT_ARCH_S390X;
diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h
new file mode 100644
index 0000000..3c3d6fe
--- /dev/null
+++ b/arch/s390/include/asm/syscall_wrapper.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * syscall_wrapper.h - s390 specific wrappers to syscall definitions
+ *
+ */
+
+#ifndef _ASM_S390_SYSCALL_WRAPPER_H
+#define _ASM_S390_SYSCALL_WRAPPER_H
+
+#ifdef CONFIG_COMPAT
+#define __SC_COMPAT_TYPE(t, a) \
+ __typeof(__builtin_choose_expr(sizeof(t) > 4, 0L, (t)0)) a
+
+#define __SC_COMPAT_CAST(t, a) \
+({ \
+ long __ReS = a; \
+ \
+ BUILD_BUG_ON((sizeof(t) > 4) && !__TYPE_IS_L(t) && \
+ !__TYPE_IS_UL(t) && !__TYPE_IS_PTR(t) && \
+ !__TYPE_IS_LL(t)); \
+ if (__TYPE_IS_L(t)) \
+ __ReS = (s32)a; \
+ if (__TYPE_IS_UL(t)) \
+ __ReS = (u32)a; \
+ if (__TYPE_IS_PTR(t)) \
+ __ReS = a & 0x7fffffff; \
+ if (__TYPE_IS_LL(t)) \
+ return -ENOSYS; \
+ (t)__ReS; \
+})
+
+#define __S390_SYS_STUBx(x, name, ...) \
+ asmlinkage long __s390_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))\
+ ALLOW_ERROR_INJECTION(__s390_sys##name, ERRNO); \
+ asmlinkage long __s390_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))\
+ { \
+ long ret = __s390x_sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__));\
+ __MAP(x,__SC_TEST,__VA_ARGS__); \
+ return ret; \
+ }
+
+/*
+ * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias
+ * named __s390x_sys_*()
+ */
+#define COMPAT_SYSCALL_DEFINE0(sname) \
+ SYSCALL_METADATA(_##sname, 0); \
+ asmlinkage long __s390_compat_sys_##sname(void); \
+ ALLOW_ERROR_INJECTION(__s390_compat__sys_##sname, ERRNO); \
+ asmlinkage long __s390_compat_sys_##sname(void)
+
+#define SYSCALL_DEFINE0(sname) \
+ SYSCALL_METADATA(_##sname, 0); \
+ asmlinkage long __s390x_sys_##sname(void); \
+ ALLOW_ERROR_INJECTION(__s390x_sys_##sname, ERRNO); \
+ asmlinkage long __s390_sys_##sname(void) \
+ __attribute__((alias(__stringify(__s390x_sys_##sname)))); \
+ asmlinkage long __s390x_sys_##sname(void)
+
+#define COND_SYSCALL(name) \
+ cond_syscall(__s390x_sys_##name); \
+ cond_syscall(__s390_sys_##name)
+
+#define SYS_NI(name) \
+ SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers); \
+ SYSCALL_ALIAS(__s390_sys_##name, sys_ni_posix_timers)
+
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
+ __diag_push(); \
+ __diag_ignore(GCC, 8, "-Wattribute-alias", \
+ "Type aliasing is used to sanitize syscall arguments");\
+ asmlinkage long __s390_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
+ asmlinkage long __s390_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
+ __attribute__((alias(__stringify(__se_compat_sys##name)))); \
+ ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \
+ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
+ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
+ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
+ { \
+ long ret = __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
+ __MAP(x,__SC_TEST,__VA_ARGS__); \
+ return ret; \
+ } \
+ __diag_pop(); \
+ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+/*
+ * As some compat syscalls may not be implemented, we need to expand
+ * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in
+ * kernel/time/posix-stubs.c to cover this case as well.
+ */
+#define COND_SYSCALL_COMPAT(name) \
+ cond_syscall(__s390_compat_sys_##name)
+
+#define COMPAT_SYS_NI(name) \
+ SYSCALL_ALIAS(__s390_compat_sys_##name, sys_ni_posix_timers)
+
+#else /* CONFIG_COMPAT */
+
+#define __S390_SYS_STUBx(x, fullname, name, ...)
+
+#define SYSCALL_DEFINE0(sname) \
+ SYSCALL_METADATA(_##sname, 0); \
+ asmlinkage long __s390x_sys_##sname(void); \
+ ALLOW_ERROR_INJECTION(__s390x_sys_##sname, ERRNO); \
+ asmlinkage long __s390x_sys_##sname(void)
+
+#define COND_SYSCALL(name) \
+ cond_syscall(__s390x_sys_##name)
+
+#define SYS_NI(name) \
+ SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers);
+
+#endif /* CONFIG_COMPAT */
+
+#define __SYSCALL_DEFINEx(x, name, ...) \
+ __diag_push(); \
+ __diag_ignore(GCC, 8, "-Wattribute-alias", \
+ "Type aliasing is used to sanitize syscall arguments");\
+ asmlinkage long __s390x_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
+ __attribute__((alias(__stringify(__se_sys##name)))); \
+ ALLOW_ERROR_INJECTION(__s390x_sys##name, ERRNO); \
+ long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
+ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
+ __S390_SYS_STUBx(x, name, __VA_ARGS__) \
+ asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
+ { \
+ long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \
+ __MAP(x,__SC_TEST,__VA_ARGS__); \
+ return ret; \
+ } \
+ __diag_pop(); \
+ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#endif /* _ASM_X86_SYSCALL_WRAPPER_H */
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 3c883c3..e582fbe 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -8,22 +8,27 @@
#ifndef _ASM_THREAD_INFO_H
#define _ASM_THREAD_INFO_H
-#include <linux/const.h>
+#include <linux/bits.h>
/*
- * Size of kernel stack for each process
+ * General size of kernel stacks
*/
+#ifdef CONFIG_KASAN
+#define THREAD_SIZE_ORDER 4
+#else
#define THREAD_SIZE_ORDER 2
-#define ASYNC_ORDER 2
-
+#endif
+#define BOOT_STACK_ORDER 2
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
-#define ASYNC_SIZE (PAGE_SIZE << ASYNC_ORDER)
#ifndef __ASSEMBLY__
#include <asm/lowcore.h>
#include <asm/page.h>
#include <asm/processor.h>
+#define STACK_INIT_OFFSET \
+ (THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs))
+
/*
* low level task data that entry.S needs immediate access to
* - this struct should fit entirely inside of one cache line
@@ -77,21 +82,21 @@
#define TIF_SECCOMP 26 /* secure computing */
#define TIF_SYSCALL_TRACEPOINT 27 /* syscall tracepoint instrumentation */
-#define _TIF_NOTIFY_RESUME _BITUL(TIF_NOTIFY_RESUME)
-#define _TIF_SIGPENDING _BITUL(TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED _BITUL(TIF_NEED_RESCHED)
-#define _TIF_UPROBE _BITUL(TIF_UPROBE)
-#define _TIF_GUARDED_STORAGE _BITUL(TIF_GUARDED_STORAGE)
-#define _TIF_PATCH_PENDING _BITUL(TIF_PATCH_PENDING)
-#define _TIF_ISOLATE_BP _BITUL(TIF_ISOLATE_BP)
-#define _TIF_ISOLATE_BP_GUEST _BITUL(TIF_ISOLATE_BP_GUEST)
+#define _TIF_NOTIFY_RESUME BIT(TIF_NOTIFY_RESUME)
+#define _TIF_SIGPENDING BIT(TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED BIT(TIF_NEED_RESCHED)
+#define _TIF_UPROBE BIT(TIF_UPROBE)
+#define _TIF_GUARDED_STORAGE BIT(TIF_GUARDED_STORAGE)
+#define _TIF_PATCH_PENDING BIT(TIF_PATCH_PENDING)
+#define _TIF_ISOLATE_BP BIT(TIF_ISOLATE_BP)
+#define _TIF_ISOLATE_BP_GUEST BIT(TIF_ISOLATE_BP_GUEST)
-#define _TIF_31BIT _BITUL(TIF_31BIT)
-#define _TIF_SINGLE_STEP _BITUL(TIF_SINGLE_STEP)
+#define _TIF_31BIT BIT(TIF_31BIT)
+#define _TIF_SINGLE_STEP BIT(TIF_SINGLE_STEP)
-#define _TIF_SYSCALL_TRACE _BITUL(TIF_SYSCALL_TRACE)
-#define _TIF_SYSCALL_AUDIT _BITUL(TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP _BITUL(TIF_SECCOMP)
-#define _TIF_SYSCALL_TRACEPOINT _BITUL(TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SYSCALL_TRACE BIT(TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_AUDIT BIT(TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP BIT(TIF_SECCOMP)
+#define _TIF_SYSCALL_TRACEPOINT BIT(TIF_SYSCALL_TRACEPOINT)
#endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b31c779..aa406c0 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -22,98 +22,39 @@
* Pages used for the page tables is a different story. FIXME: more
*/
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/processor.h>
+void __tlb_remove_table(void *_table);
+static inline void tlb_flush(struct mmu_gather *tlb);
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size);
+
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#define tlb_end_vma(tlb, vma) do { } while (0)
+
+#define tlb_flush tlb_flush
+#define pte_free_tlb pte_free_tlb
+#define pmd_free_tlb pmd_free_tlb
+#define p4d_free_tlb p4d_free_tlb
+#define pud_free_tlb pud_free_tlb
+
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
-
-struct mmu_gather {
- struct mm_struct *mm;
- struct mmu_table_batch *batch;
- unsigned int fullmm;
- unsigned long start, end;
-};
-
-struct mmu_table_batch {
- struct rcu_head rcu;
- unsigned int nr;
- void *tables[0];
-};
-
-#define MAX_TABLE_BATCH \
- ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
- tlb->start = start;
- tlb->end = end;
- tlb->fullmm = !(start | (end+1));
- tlb->batch = NULL;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
- __tlb_flush_mm_lazy(tlb->mm);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
- tlb_table_flush(tlb);
-}
-
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
- tlb_flush_mmu_tlbonly(tlb);
- tlb_flush_mmu_free(tlb);
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
-{
- if (force) {
- tlb->start = start;
- tlb->end = end;
- }
-
- tlb_flush_mmu(tlb);
-}
+#include <asm-generic/tlb.h>
/*
* Release the page cache reference for a pte removed by
* tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
* has already been freed, so just do free_page_and_swap_cache.
*/
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- free_page_and_swap_cache(page);
- return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- free_page_and_swap_cache(page);
-}
-
static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size)
{
- return __tlb_remove_page(tlb, page);
+ free_page_and_swap_cache(page);
+ return false;
}
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
+static inline void tlb_flush(struct mmu_gather *tlb)
{
- return tlb_remove_page(tlb, page);
+ __tlb_flush_mm_lazy(tlb->mm);
}
/*
@@ -121,8 +62,17 @@
* page table from the tlb.
*/
static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
- unsigned long address)
+ unsigned long address)
{
+ __tlb_adjust_range(tlb, address, PAGE_SIZE);
+ tlb->mm->context.flush_mm = 1;
+ tlb->freed_tables = 1;
+ tlb->cleared_ptes = 1;
+ /*
+ * page_table_free_rcu takes care of the allocation bit masks
+ * of the 2K table fragments in the 4K page table page,
+ * then calls tlb_remove_table.
+ */
page_table_free_rcu(tlb, (unsigned long *) pte, address);
}
@@ -139,6 +89,10 @@
if (mm_pmd_folded(tlb->mm))
return;
pgtable_pmd_page_dtor(virt_to_page(pmd));
+ __tlb_adjust_range(tlb, address, PAGE_SIZE);
+ tlb->mm->context.flush_mm = 1;
+ tlb->freed_tables = 1;
+ tlb->cleared_puds = 1;
tlb_remove_table(tlb, pmd);
}
@@ -154,6 +108,10 @@
{
if (mm_p4d_folded(tlb->mm))
return;
+ __tlb_adjust_range(tlb, address, PAGE_SIZE);
+ tlb->mm->context.flush_mm = 1;
+ tlb->freed_tables = 1;
+ tlb->cleared_p4ds = 1;
tlb_remove_table(tlb, p4d);
}
@@ -169,21 +127,11 @@
{
if (mm_pud_folded(tlb->mm))
return;
+ tlb->mm->context.flush_mm = 1;
+ tlb->freed_tables = 1;
+ tlb->cleared_puds = 1;
tlb_remove_table(tlb, pud);
}
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define tlb_remove_tlb_entry(tlb, ptep, addr) do { } while (0)
-#define tlb_remove_pmd_tlb_entry(tlb, pmdp, addr) do { } while (0)
-#define tlb_migrate_finish(mm) do { } while (0)
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
- tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
- unsigned int page_size)
-{
-}
#endif /* _S390_TLB_H */
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index 8c840f0..82703e0 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -32,7 +32,6 @@
: : "a" (opt), "a" (asce) : "cc");
}
-#ifdef CONFIG_SMP
void smp_ptlb_all(void);
/*
@@ -83,22 +82,6 @@
else
__tlb_flush_global();
}
-#else
-#define __tlb_flush_global() __tlb_flush_local()
-
-/*
- * Flush TLB entries for a specific ASCE on all CPUs.
- */
-static inline void __tlb_flush_mm(struct mm_struct *mm)
-{
- __tlb_flush_local();
-}
-
-static inline void __tlb_flush_kernel(void)
-{
- __tlb_flush_local();
-}
-#endif
static inline void __tlb_flush_mm_lazy(struct mm_struct * mm)
{
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index ad6b910..a470f1f 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -31,7 +31,6 @@
#define USER_DS (2)
#define USER_DS_SACF (3)
-#define get_ds() (KERNEL_DS)
#define get_fs() (current->thread.mm_segment)
#define segment_eq(a,b) (((a) & 2) == ((b) & 2))
@@ -48,7 +47,7 @@
__range_ok((unsigned long)(addr), (size)); \
})
-#define access_ok(type, addr, size) __access_ok(addr, size)
+#define access_ok(addr, size) __access_ok(addr, size)
unsigned long __must_check
raw_copy_from_user(void *to, const void __user *from, unsigned long n);
@@ -56,8 +55,10 @@
unsigned long __must_check
raw_copy_to_user(void __user *to, const void *from, unsigned long n);
+#ifndef CONFIG_KASAN
#define INLINE_COPY_FROM_USER
#define INLINE_COPY_TO_USER
+#endif
#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
@@ -82,7 +83,7 @@
__rc; \
})
-static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
+static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
{
unsigned long spec = 0x010000UL;
int rc;
@@ -112,7 +113,7 @@
return rc;
}
-static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
+static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
{
unsigned long spec = 0x01UL;
int rc;
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index fd79c0d..9e9f75e 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -10,11 +10,7 @@
#include <uapi/asm/unistd.h>
#include <asm/unistd_nr.h>
-#define __IGNORE_time
-#define __IGNORE_pkey_mprotect
-#define __IGNORE_pkey_alloc
-#define __IGNORE_pkey_free
-
+#define __ARCH_WANT_NEW_STAT
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_SYS_ALARM
#define __ARCH_WANT_SYS_GETHOSTNAME
@@ -25,7 +21,6 @@
#define __ARCH_WANT_SYS_IPC
#define __ARCH_WANT_SYS_FADVISE64
#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
#define __ARCH_WANT_SYS_NICE
#define __ARCH_WANT_SYS_OLD_GETRLIMIT
#define __ARCH_WANT_SYS_OLD_MMAP
@@ -33,10 +28,12 @@
#define __ARCH_WANT_SYS_SIGPENDING
#define __ARCH_WANT_SYS_SIGPROCMASK
# ifdef CONFIG_COMPAT
-# define __ARCH_WANT_COMPAT_SYS_TIME
+# define __ARCH_WANT_SYS_TIME32
+# define __ARCH_WANT_SYS_UTIME32
# endif
#define __ARCH_WANT_SYS_FORK
#define __ARCH_WANT_SYS_VFORK
#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
#endif /* _ASM_S390_UNISTD_H_ */
diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h
new file mode 100644
index 0000000..eaaefec
--- /dev/null
+++ b/arch/s390/include/asm/unwind.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_UNWIND_H
+#define _ASM_S390_UNWIND_H
+
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+
+/*
+ * To use the stack unwinder it has to be initialized with unwind_start.
+ * There four combinations for task and regs:
+ * 1) task==NULL, regs==NULL: the unwind starts for the task that is currently
+ * running, sp/ip picked up from the CPU registers
+ * 2) task==NULL, regs!=NULL: the unwind starts from the sp/ip found in
+ * the struct pt_regs of an interrupt frame for the current task
+ * 3) task!=NULL, regs==NULL: the unwind starts for an inactive task with
+ * the sp picked up from task->thread.ksp and the ip picked up from the
+ * return address stored by __switch_to
+ * 4) task!=NULL, regs!=NULL: the sp/ip are picked up from the interrupt
+ * frame 'regs' of a inactive task
+ * If 'first_frame' is not zero unwind_start skips unwind frames until it
+ * reaches the specified stack pointer.
+ * The end of the unwinding is indicated with unwind_done, this can be true
+ * right after unwind_start, e.g. with first_frame!=0 that can not be found.
+ * unwind_next_frame skips to the next frame.
+ * Once the unwind is completed unwind_error() can be used to check if there
+ * has been a situation where the unwinder could not correctly understand
+ * the tasks call chain.
+ */
+
+struct unwind_state {
+ struct stack_info stack_info;
+ unsigned long stack_mask;
+ struct task_struct *task;
+ struct pt_regs *regs;
+ unsigned long sp, ip;
+ bool reuse_sp;
+ int graph_idx;
+ bool reliable;
+ bool error;
+};
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs, unsigned long first_frame);
+bool unwind_next_frame(struct unwind_state *state);
+unsigned long unwind_get_return_address(struct unwind_state *state);
+
+static inline bool unwind_done(struct unwind_state *state)
+{
+ return state->stack_info.type == STACK_TYPE_UNKNOWN;
+}
+
+static inline bool unwind_error(struct unwind_state *state)
+{
+ return state->error;
+}
+
+static inline void unwind_start(struct unwind_state *state,
+ struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned long sp)
+{
+ sp = sp ? : get_stack_pointer(task, regs);
+ __unwind_start(state, task, regs, sp);
+}
+
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+ return unwind_done(state) ? NULL : state->regs;
+}
+
+#define unwind_for_each_frame(state, task, regs, first_frame) \
+ for (unwind_start(state, task, regs, first_frame); \
+ !unwind_done(state); \
+ unwind_next_frame(state))
+
+static inline void unwind_init(void) {}
+static inline void unwind_module_init(struct module *mod, void *orc_ip,
+ size_t orc_ip_size, void *orc,
+ size_t orc_size) {}
+
+#endif /* _ASM_S390_UNWIND_H */
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
new file mode 100644
index 0000000..ef3c00b
--- /dev/null
+++ b/arch/s390/include/asm/uv.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ultravisor Interfaces
+ *
+ * Copyright IBM Corp. 2019
+ *
+ * Author(s):
+ * Vasily Gorbik <gor@linux.ibm.com>
+ * Janosch Frank <frankja@linux.ibm.com>
+ */
+#ifndef _ASM_S390_UV_H
+#define _ASM_S390_UV_H
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/bug.h>
+#include <asm/page.h>
+
+#define UVC_RC_EXECUTED 0x0001
+#define UVC_RC_INV_CMD 0x0002
+#define UVC_RC_INV_STATE 0x0003
+#define UVC_RC_INV_LEN 0x0005
+#define UVC_RC_NO_RESUME 0x0007
+
+#define UVC_CMD_QUI 0x0001
+#define UVC_CMD_SET_SHARED_ACCESS 0x1000
+#define UVC_CMD_REMOVE_SHARED_ACCESS 0x1001
+
+/* Bits in installed uv calls */
+enum uv_cmds_inst {
+ BIT_UVC_CMD_QUI = 0,
+ BIT_UVC_CMD_SET_SHARED_ACCESS = 8,
+ BIT_UVC_CMD_REMOVE_SHARED_ACCESS = 9,
+};
+
+struct uv_cb_header {
+ u16 len;
+ u16 cmd; /* Command Code */
+ u16 rc; /* Response Code */
+ u16 rrc; /* Return Reason Code */
+} __packed __aligned(8);
+
+struct uv_cb_qui {
+ struct uv_cb_header header;
+ u64 reserved08;
+ u64 inst_calls_list[4];
+ u64 reserved30[15];
+} __packed __aligned(8);
+
+struct uv_cb_share {
+ struct uv_cb_header header;
+ u64 reserved08[3];
+ u64 paddr;
+ u64 reserved28;
+} __packed __aligned(8);
+
+static inline int uv_call(unsigned long r1, unsigned long r2)
+{
+ int cc;
+
+ asm volatile(
+ "0: .insn rrf,0xB9A40000,%[r1],%[r2],0,0\n"
+ " brc 3,0b\n"
+ " ipm %[cc]\n"
+ " srl %[cc],28\n"
+ : [cc] "=d" (cc)
+ : [r1] "a" (r1), [r2] "a" (r2)
+ : "memory", "cc");
+ return cc;
+}
+
+#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
+extern int prot_virt_guest;
+
+static inline int is_prot_virt_guest(void)
+{
+ return prot_virt_guest;
+}
+
+static inline int share(unsigned long addr, u16 cmd)
+{
+ struct uv_cb_share uvcb = {
+ .header.cmd = cmd,
+ .header.len = sizeof(uvcb),
+ .paddr = addr
+ };
+
+ if (!is_prot_virt_guest())
+ return -ENOTSUPP;
+ /*
+ * Sharing is page wise, if we encounter addresses that are
+ * not page aligned, we assume something went wrong. If
+ * malloced structs are passed to this function, we could leak
+ * data to the hypervisor.
+ */
+ BUG_ON(addr & ~PAGE_MASK);
+
+ if (!uv_call(0, (u64)&uvcb))
+ return 0;
+ return -EINVAL;
+}
+
+/*
+ * Guest 2 request to the Ultravisor to make a page shared with the
+ * hypervisor for IO.
+ *
+ * @addr: Real or absolute address of the page to be shared
+ */
+static inline int uv_set_shared(unsigned long addr)
+{
+ return share(addr, UVC_CMD_SET_SHARED_ACCESS);
+}
+
+/*
+ * Guest 2 request to the Ultravisor to make a page unshared.
+ *
+ * @addr: Real or absolute address of the page to be unshared
+ */
+static inline int uv_remove_shared(unsigned long addr)
+{
+ return share(addr, UVC_CMD_REMOVE_SHARED_ACCESS);
+}
+
+void uv_query_info(void);
+#else
+#define is_prot_virt_guest() 0
+static inline int uv_set_shared(unsigned long addr) { return 0; }
+static inline int uv_remove_shared(unsigned long addr) { return 0; }
+static inline void uv_query_info(void) {}
+#endif
+
+#endif /* _ASM_S390_UV_H */
diff --git a/arch/s390/include/asm/vmlinux.lds.h b/arch/s390/include/asm/vmlinux.lds.h
new file mode 100644
index 0000000..cbe670a
--- /dev/null
+++ b/arch/s390/include/asm/vmlinux.lds.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/page.h>
+
+/*
+ * .boot.data section is shared between the decompressor code and the
+ * decompressed kernel. The decompressor will store values in it, and copy
+ * over to the decompressed image before starting it.
+ *
+ * .boot.data variables are kept in separate .boot.data.<var name> sections,
+ * which are sorted by alignment first, then by name before being merged
+ * into single .boot.data section. This way big holes cased by page aligned
+ * structs are avoided and linker produces consistent result.
+ */
+#define BOOT_DATA \
+ . = ALIGN(PAGE_SIZE); \
+ .boot.data : { \
+ __boot_data_start = .; \
+ *(SORT_BY_ALIGNMENT(SORT_BY_NAME(.boot.data*))) \
+ __boot_data_end = .; \
+ }
+
+/*
+ * .boot.preserved.data is similar to .boot.data, but it is not part of the
+ * .init section and thus will be preserved for later use in the decompressed
+ * kernel.
+ */
+#define BOOT_DATA_PRESERVED \
+ . = ALIGN(PAGE_SIZE); \
+ .boot.preserved.data : { \
+ __boot_data_preserved_start = .; \
+ *(SORT_BY_ALIGNMENT(SORT_BY_NAME(.boot.preserved.data*))) \
+ __boot_data_preserved_end = .; \
+ }
diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h
index 266a723..0c05a67 100644
--- a/arch/s390/include/asm/vx-insn.h
+++ b/arch/s390/include/asm/vx-insn.h
@@ -363,23 +363,23 @@
.endm
/* VECTOR LOAD MULTIPLE */
-.macro VLM vfrom, vto, disp, base
+.macro VLM vfrom, vto, disp, base, hint=3
VX_NUM v1, \vfrom
VX_NUM v3, \vto
GR_NUM b2, \base /* Base register */
.word 0xE700 | ((v1&15) << 4) | (v3&15)
.word (b2 << 12) | (\disp)
- MRXBOPC 0, 0x36, v1, v3
+ MRXBOPC \hint, 0x36, v1, v3
.endm
/* VECTOR STORE MULTIPLE */
-.macro VSTM vfrom, vto, disp, base
+.macro VSTM vfrom, vto, disp, base, hint=3
VX_NUM v1, \vfrom
VX_NUM v3, \vto
GR_NUM b2, \base /* Base register */
.word 0xE700 | ((v1&15) << 4) | (v3&15)
.word (b2 << 12) | (\disp)
- MRXBOPC 0, 0x3E, v1, v3
+ MRXBOPC \hint, 0x3E, v1, v3
.endm
/* VECTOR PERMUTE */
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index e364873..46c1ff0 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -1,20 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
-# UAPI Header export list
-include include/uapi/asm-generic/Kbuild.asm
generated-y += unistd_32.h
generated-y += unistd_64.h
-
-generic-y += errno.h
-generic-y += fcntl.h
-generic-y += ioctl.h
-generic-y += mman.h
-generic-y += msgbuf.h
-generic-y += param.h
-generic-y += poll.h
-generic-y += resource.h
-generic-y += sembuf.h
-generic-y += shmbuf.h
-generic-y += sockios.h
-generic-y += swab.h
-generic-y += termbits.h
diff --git a/arch/s390/include/uapi/asm/bpf_perf_event.h b/arch/s390/include/uapi/asm/bpf_perf_event.h
index cefe7c7..3ed42ff 100644
--- a/arch/s390/include/uapi/asm/bpf_perf_event.h
+++ b/arch/s390/include/uapi/asm/bpf_perf_event.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
#define _UAPI__ASM_BPF_PERF_EVENT_H__
diff --git a/arch/s390/include/uapi/asm/dasd.h b/arch/s390/include/uapi/asm/dasd.h
index 832be5c..9ec86fa 100644
--- a/arch/s390/include/uapi/asm/dasd.h
+++ b/arch/s390/include/uapi/asm/dasd.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
+/*
* Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
* Bugreports.to..: <Linux390@de.ibm.com>
* Copyright IBM Corp. 1999, 2000
@@ -21,40 +21,40 @@
#define DASD_API_VERSION 6
-/*
+/*
* struct dasd_information2_t
* represents any data about the device, which is visible to userspace.
* including foramt and featueres.
*/
typedef struct dasd_information2_t {
- unsigned int devno; /* S/390 devno */
- unsigned int real_devno; /* for aliases */
- unsigned int schid; /* S/390 subchannel identifier */
- unsigned int cu_type : 16; /* from SenseID */
- unsigned int cu_model : 8; /* from SenseID */
- unsigned int dev_type : 16; /* from SenseID */
- unsigned int dev_model : 8; /* from SenseID */
- unsigned int open_count;
- unsigned int req_queue_len;
- unsigned int chanq_len; /* length of chanq */
- char type[4]; /* from discipline.name, 'none' for unknown */
- unsigned int status; /* current device level */
- unsigned int label_block; /* where to find the VOLSER */
- unsigned int FBA_layout; /* fixed block size (like AIXVOL) */
- unsigned int characteristics_size;
- unsigned int confdata_size;
- char characteristics[64]; /* from read_device_characteristics */
- char configuration_data[256]; /* from read_configuration_data */
- unsigned int format; /* format info like formatted/cdl/ldl/... */
- unsigned int features; /* dasd features like 'ro',... */
- unsigned int reserved0; /* reserved for further use ,... */
- unsigned int reserved1; /* reserved for further use ,... */
- unsigned int reserved2; /* reserved for further use ,... */
- unsigned int reserved3; /* reserved for further use ,... */
- unsigned int reserved4; /* reserved for further use ,... */
- unsigned int reserved5; /* reserved for further use ,... */
- unsigned int reserved6; /* reserved for further use ,... */
- unsigned int reserved7; /* reserved for further use ,... */
+ unsigned int devno; /* S/390 devno */
+ unsigned int real_devno; /* for aliases */
+ unsigned int schid; /* S/390 subchannel identifier */
+ unsigned int cu_type : 16; /* from SenseID */
+ unsigned int cu_model : 8; /* from SenseID */
+ unsigned int dev_type : 16; /* from SenseID */
+ unsigned int dev_model : 8; /* from SenseID */
+ unsigned int open_count;
+ unsigned int req_queue_len;
+ unsigned int chanq_len; /* length of chanq */
+ char type[4]; /* from discipline.name, 'none' for unknown */
+ unsigned int status; /* current device level */
+ unsigned int label_block; /* where to find the VOLSER */
+ unsigned int FBA_layout; /* fixed block size (like AIXVOL) */
+ unsigned int characteristics_size;
+ unsigned int confdata_size;
+ char characteristics[64]; /* from read_device_characteristics */
+ char configuration_data[256]; /* from read_configuration_data */
+ unsigned int format; /* format info like formatted/cdl/ldl/... */
+ unsigned int features; /* dasd features like 'ro',... */
+ unsigned int reserved0; /* reserved for further use ,... */
+ unsigned int reserved1; /* reserved for further use ,... */
+ unsigned int reserved2; /* reserved for further use ,... */
+ unsigned int reserved3; /* reserved for further use ,... */
+ unsigned int reserved4; /* reserved for further use ,... */
+ unsigned int reserved5; /* reserved for further use ,... */
+ unsigned int reserved6; /* reserved for further use ,... */
+ unsigned int reserved7; /* reserved for further use ,... */
} dasd_information2_t;
/*
@@ -92,34 +92,34 @@
#define DASD_PARTN_BITS 2
-/*
+/*
* struct dasd_information_t
* represents any data about the data, which is visible to userspace
*/
typedef struct dasd_information_t {
- unsigned int devno; /* S/390 devno */
- unsigned int real_devno; /* for aliases */
- unsigned int schid; /* S/390 subchannel identifier */
- unsigned int cu_type : 16; /* from SenseID */
- unsigned int cu_model : 8; /* from SenseID */
- unsigned int dev_type : 16; /* from SenseID */
- unsigned int dev_model : 8; /* from SenseID */
- unsigned int open_count;
- unsigned int req_queue_len;
- unsigned int chanq_len; /* length of chanq */
- char type[4]; /* from discipline.name, 'none' for unknown */
- unsigned int status; /* current device level */
- unsigned int label_block; /* where to find the VOLSER */
- unsigned int FBA_layout; /* fixed block size (like AIXVOL) */
- unsigned int characteristics_size;
- unsigned int confdata_size;
- char characteristics[64]; /* from read_device_characteristics */
- char configuration_data[256]; /* from read_configuration_data */
+ unsigned int devno; /* S/390 devno */
+ unsigned int real_devno; /* for aliases */
+ unsigned int schid; /* S/390 subchannel identifier */
+ unsigned int cu_type : 16; /* from SenseID */
+ unsigned int cu_model : 8; /* from SenseID */
+ unsigned int dev_type : 16; /* from SenseID */
+ unsigned int dev_model : 8; /* from SenseID */
+ unsigned int open_count;
+ unsigned int req_queue_len;
+ unsigned int chanq_len; /* length of chanq */
+ char type[4]; /* from discipline.name, 'none' for unknown */
+ unsigned int status; /* current device level */
+ unsigned int label_block; /* where to find the VOLSER */
+ unsigned int FBA_layout; /* fixed block size (like AIXVOL) */
+ unsigned int characteristics_size;
+ unsigned int confdata_size;
+ char characteristics[64]; /* from read_device_characteristics */
+ char configuration_data[256]; /* from read_configuration_data */
} dasd_information_t;
/*
* Read Subsystem Data - Performance Statistics
- */
+ */
typedef struct dasd_rssd_perf_stats_t {
unsigned char invalid:1;
unsigned char format:3;
@@ -154,21 +154,21 @@
unsigned char reseved2[96];
} __attribute__((packed)) dasd_rssd_perf_stats_t;
-/*
+/*
* struct profile_info_t
- * holds the profinling information
+ * holds the profinling information
*/
typedef struct dasd_profile_info_t {
- unsigned int dasd_io_reqs; /* number of requests processed at all */
- unsigned int dasd_io_sects; /* number of sectors processed at all */
- unsigned int dasd_io_secs[32]; /* histogram of request's sizes */
- unsigned int dasd_io_times[32]; /* histogram of requests's times */
- unsigned int dasd_io_timps[32]; /* histogram of requests's times per sector */
- unsigned int dasd_io_time1[32]; /* histogram of time from build to start */
- unsigned int dasd_io_time2[32]; /* histogram of time from start to irq */
- unsigned int dasd_io_time2ps[32]; /* histogram of time from start to irq */
- unsigned int dasd_io_time3[32]; /* histogram of time from irq to end */
- unsigned int dasd_io_nr_req[32]; /* histogram of # of requests in chanq */
+ unsigned int dasd_io_reqs; /* number of requests processed at all */
+ unsigned int dasd_io_sects; /* number of sectors processed at all */
+ unsigned int dasd_io_secs[32]; /* histogram of request's sizes */
+ unsigned int dasd_io_times[32]; /* histogram of requests's times */
+ unsigned int dasd_io_timps[32]; /* histogram of requests's times per sector */
+ unsigned int dasd_io_time1[32]; /* histogram of time from build to start */
+ unsigned int dasd_io_time2[32]; /* histogram of time from start to irq */
+ unsigned int dasd_io_time2ps[32]; /* histogram of time from start to irq */
+ unsigned int dasd_io_time3[32]; /* histogram of time from irq to end */
+ unsigned int dasd_io_nr_req[32]; /* histogram of # of requests in chanq */
} dasd_profile_info_t;
/*
@@ -189,10 +189,12 @@
* 3/11: also write home address
* 4/12: invalidate track
*/
-#define DASD_FMT_INT_FMT_R0 1 /* write record zero */
-#define DASD_FMT_INT_FMT_HA 2 /* write home address, also set FMT_R0 ! */
-#define DASD_FMT_INT_INVAL 4 /* invalidate tracks */
-#define DASD_FMT_INT_COMPAT 8 /* use OS/390 compatible disk layout */
+#define DASD_FMT_INT_FMT_R0 1 /* write record zero */
+#define DASD_FMT_INT_FMT_HA 2 /* write home address, also set FMT_R0 ! */
+#define DASD_FMT_INT_INVAL 4 /* invalidate tracks */
+#define DASD_FMT_INT_COMPAT 8 /* use OS/390 compatible disk layout */
+#define DASD_FMT_INT_FMT_NOR0 16 /* remove permission to write record zero */
+#define DASD_FMT_INT_ESE_FULL 32 /* release space for entire volume */
/*
* struct format_check_t
@@ -225,7 +227,7 @@
/* If key-length was != 0 */
#define DASD_FMT_ERR_KEY_LENGTH 5
-/*
+/*
* struct attrib_data_t
* represents the operation (cache) bits for the device.
* Used in DE to influence caching of the DASD.
@@ -281,13 +283,13 @@
* Here ist how the ioctl-nr should be used:
* 0 - 31 DASD driver itself
* 32 - 239 still open
- * 240 - 255 reserved for EMC
+ * 240 - 255 reserved for EMC
*******************************************************************************/
/* Disable the volume (for Linux) */
-#define BIODASDDISABLE _IO(DASD_IOCTL_LETTER,0)
+#define BIODASDDISABLE _IO(DASD_IOCTL_LETTER,0)
/* Enable the volume (for Linux) */
-#define BIODASDENABLE _IO(DASD_IOCTL_LETTER,1)
+#define BIODASDENABLE _IO(DASD_IOCTL_LETTER,1)
/* Issue a reserve/release command, rsp. */
#define BIODASDRSRV _IO(DASD_IOCTL_LETTER,2) /* reserve */
#define BIODASDRLSE _IO(DASD_IOCTL_LETTER,3) /* release */
@@ -295,9 +297,9 @@
/* reset profiling information of a device */
#define BIODASDPRRST _IO(DASD_IOCTL_LETTER,5)
/* Quiesce IO on device */
-#define BIODASDQUIESCE _IO(DASD_IOCTL_LETTER,6)
+#define BIODASDQUIESCE _IO(DASD_IOCTL_LETTER,6)
/* Resume IO on device */
-#define BIODASDRESUME _IO(DASD_IOCTL_LETTER,7)
+#define BIODASDRESUME _IO(DASD_IOCTL_LETTER,7)
/* Abort all I/O on a device */
#define BIODASDABORTIO _IO(DASD_IOCTL_LETTER, 240)
/* Allow I/O on a device */
@@ -315,13 +317,15 @@
/* Performance Statistics Read */
#define BIODASDPSRD _IOR(DASD_IOCTL_LETTER,4,dasd_rssd_perf_stats_t)
/* Get Attributes (cache operations) */
-#define BIODASDGATTR _IOR(DASD_IOCTL_LETTER,5,attrib_data_t)
+#define BIODASDGATTR _IOR(DASD_IOCTL_LETTER,5,attrib_data_t)
/* #define BIODASDFORMAT _IOW(IOCTL_LETTER,0,format_data_t) , deprecated */
-#define BIODASDFMT _IOW(DASD_IOCTL_LETTER,1,format_data_t)
+#define BIODASDFMT _IOW(DASD_IOCTL_LETTER,1,format_data_t)
/* Set Attributes (cache operations) */
-#define BIODASDSATTR _IOW(DASD_IOCTL_LETTER,2,attrib_data_t)
+#define BIODASDSATTR _IOW(DASD_IOCTL_LETTER,2,attrib_data_t)
+/* Release Allocated Space */
+#define BIODASDRAS _IOW(DASD_IOCTL_LETTER, 3, format_data_t)
/* Get Sense Path Group ID (SNID) data */
#define BIODASDSNID _IOWR(DASD_IOCTL_LETTER, 1, struct dasd_snid_ioctl_data)
diff --git a/arch/s390/include/uapi/asm/ipl.h b/arch/s390/include/uapi/asm/ipl.h
new file mode 100644
index 0000000..451ba7d
--- /dev/null
+++ b/arch/s390/include/uapi/asm/ipl.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_S390_UAPI_IPL_H
+#define _ASM_S390_UAPI_IPL_H
+
+#include <linux/types.h>
+
+/* IPL Parameter List header */
+struct ipl_pl_hdr {
+ __u32 len;
+ __u8 flags;
+ __u8 reserved1[2];
+ __u8 version;
+} __packed;
+
+#define IPL_PL_FLAG_IPLPS 0x80
+#define IPL_PL_FLAG_SIPL 0x40
+#define IPL_PL_FLAG_IPLSR 0x20
+
+/* IPL Parameter Block header */
+struct ipl_pb_hdr {
+ __u32 len;
+ __u8 pbt;
+} __packed;
+
+/* IPL Parameter Block types */
+enum ipl_pbt {
+ IPL_PBT_FCP = 0,
+ IPL_PBT_SCP_DATA = 1,
+ IPL_PBT_CCW = 2,
+};
+
+/* IPL Parameter Block 0 with common fields */
+struct ipl_pb0_common {
+ __u32 len;
+ __u8 pbt;
+ __u8 flags;
+ __u8 reserved1[2];
+ __u8 loadparm[8];
+ __u8 reserved2[84];
+} __packed;
+
+#define IPL_PB0_FLAG_LOADPARM 0x80
+
+/* IPL Parameter Block 0 for FCP */
+struct ipl_pb0_fcp {
+ __u32 len;
+ __u8 pbt;
+ __u8 reserved1[3];
+ __u8 loadparm[8];
+ __u8 reserved2[304];
+ __u8 opt;
+ __u8 reserved3[3];
+ __u8 cssid;
+ __u8 reserved4[1];
+ __u16 devno;
+ __u8 reserved5[4];
+ __u64 wwpn;
+ __u64 lun;
+ __u32 bootprog;
+ __u8 reserved6[12];
+ __u64 br_lba;
+ __u32 scp_data_len;
+ __u8 reserved7[260];
+ __u8 scp_data[];
+} __packed;
+
+#define IPL_PB0_FCP_OPT_IPL 0x10
+#define IPL_PB0_FCP_OPT_DUMP 0x20
+
+/* IPL Parameter Block 0 for CCW */
+struct ipl_pb0_ccw {
+ __u32 len;
+ __u8 pbt;
+ __u8 flags;
+ __u8 reserved1[2];
+ __u8 loadparm[8];
+ __u8 reserved2[84];
+ __u16 reserved3 : 13;
+ __u8 ssid : 3;
+ __u16 devno;
+ __u8 vm_flags;
+ __u8 reserved4[3];
+ __u32 vm_parm_len;
+ __u8 nss_name[8];
+ __u8 vm_parm[64];
+ __u8 reserved5[8];
+} __packed;
+
+#define IPL_PB0_CCW_VM_FLAG_NSS 0x80
+#define IPL_PB0_CCW_VM_FLAG_VP 0x40
+
+/* IPL Parameter Block 1 for additional SCP data */
+struct ipl_pb1_scp_data {
+ __u32 len;
+ __u8 pbt;
+ __u8 scp_data[];
+} __packed;
+
+/* IPL Report List header */
+struct ipl_rl_hdr {
+ __u32 len;
+ __u8 flags;
+ __u8 reserved1[2];
+ __u8 version;
+ __u8 reserved2[8];
+} __packed;
+
+/* IPL Report Block header */
+struct ipl_rb_hdr {
+ __u32 len;
+ __u8 rbt;
+ __u8 reserved1[11];
+} __packed;
+
+/* IPL Report Block types */
+enum ipl_rbt {
+ IPL_RBT_CERTIFICATES = 1,
+ IPL_RBT_COMPONENTS = 2,
+};
+
+/* IPL Report Block for the certificate list */
+struct ipl_rb_certificate_entry {
+ __u64 addr;
+ __u64 len;
+} __packed;
+
+struct ipl_rb_certificates {
+ __u32 len;
+ __u8 rbt;
+ __u8 reserved1[11];
+ struct ipl_rb_certificate_entry entries[];
+} __packed;
+
+/* IPL Report Block for the component list */
+struct ipl_rb_component_entry {
+ __u64 addr;
+ __u64 len;
+ __u8 flags;
+ __u8 reserved1[5];
+ __u16 certificate_index;
+ __u8 reserved2[8];
+};
+
+#define IPL_RB_COMPONENT_FLAG_SIGNED 0x80
+#define IPL_RB_COMPONENT_FLAG_VERIFIED 0x40
+
+struct ipl_rb_components {
+ __u32 len;
+ __u8 rbt;
+ __u8 reserved1[11];
+ struct ipl_rb_component_entry entries[];
+} __packed;
+
+#endif
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 9a50f02..436ec76 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -152,7 +152,10 @@
__u8 pcc[16]; /* with MSA4 */
__u8 ppno[16]; /* with MSA5 */
__u8 kma[16]; /* with MSA8 */
- __u8 reserved[1808];
+ __u8 kdsa[16]; /* with MSA9 */
+ __u8 sortl[32]; /* with STFLE.150 */
+ __u8 dfltcc[32]; /* with STFLE.151 */
+ __u8 reserved[1728];
};
/* kvm attributes for crypto */
@@ -160,6 +163,8 @@
#define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW 1
#define KVM_S390_VM_CRYPTO_DISABLE_AES_KW 2
#define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW 3
+#define KVM_S390_VM_CRYPTO_ENABLE_APIE 4
+#define KVM_S390_VM_CRYPTO_DISABLE_APIE 5
/* kvm attributes for migration mode */
#define KVM_S390_VM_MIGRATION_STOP 0
@@ -226,6 +231,12 @@
#define KVM_SYNC_GSCB (1UL << 9)
#define KVM_SYNC_BPBC (1UL << 10)
#define KVM_SYNC_ETOKEN (1UL << 11)
+
+#define KVM_SYNC_S390_VALID_FIELDS \
+ (KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | \
+ KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_VRS | KVM_SYNC_RICCB | \
+ KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN)
+
/* length and alignment of the sdnx as a power of two */
#define SDNXC 8
#define SDNXL (1UL << SDNXC)
diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h
index 6f84a53..e22f072 100644
--- a/arch/s390/include/uapi/asm/pkey.h
+++ b/arch/s390/include/uapi/asm/pkey.h
@@ -2,7 +2,7 @@
/*
* Userspace interface to the pkey device driver
*
- * Copyright IBM Corp. 2017
+ * Copyright IBM Corp. 2017, 2019
*
* Author: Harald Freudenberger <freude@de.ibm.com>
*
@@ -20,34 +20,74 @@
#define PKEY_IOCTL_MAGIC 'p'
-#define SECKEYBLOBSIZE 64 /* secure key blob size is always 64 bytes */
-#define MAXPROTKEYSIZE 64 /* a protected key blob may be up to 64 bytes */
-#define MAXCLRKEYSIZE 32 /* a clear key value may be up to 32 bytes */
+#define SECKEYBLOBSIZE 64 /* secure key blob size is always 64 bytes */
+#define PROTKEYBLOBSIZE 80 /* protected key blob size is always 80 bytes */
+#define MAXPROTKEYSIZE 64 /* a protected key blob may be up to 64 bytes */
+#define MAXCLRKEYSIZE 32 /* a clear key value may be up to 32 bytes */
+#define MAXAESCIPHERKEYSIZE 136 /* our aes cipher keys have always 136 bytes */
+
+/* Minimum and maximum size of a key blob */
+#define MINKEYBLOBSIZE SECKEYBLOBSIZE
+#define MAXKEYBLOBSIZE MAXAESCIPHERKEYSIZE
/* defines for the type field within the pkey_protkey struct */
-#define PKEY_KEYTYPE_AES_128 1
-#define PKEY_KEYTYPE_AES_192 2
-#define PKEY_KEYTYPE_AES_256 3
+#define PKEY_KEYTYPE_AES_128 1
+#define PKEY_KEYTYPE_AES_192 2
+#define PKEY_KEYTYPE_AES_256 3
-/* Struct to hold a secure key blob */
+/* the newer ioctls use a pkey_key_type enum for type information */
+enum pkey_key_type {
+ PKEY_TYPE_CCA_DATA = (__u32) 1,
+ PKEY_TYPE_CCA_CIPHER = (__u32) 2,
+};
+
+/* the newer ioctls use a pkey_key_size enum for key size information */
+enum pkey_key_size {
+ PKEY_SIZE_AES_128 = (__u32) 128,
+ PKEY_SIZE_AES_192 = (__u32) 192,
+ PKEY_SIZE_AES_256 = (__u32) 256,
+ PKEY_SIZE_UNKNOWN = (__u32) 0xFFFFFFFF,
+};
+
+/* some of the newer ioctls use these flags */
+#define PKEY_FLAGS_MATCH_CUR_MKVP 0x00000002
+#define PKEY_FLAGS_MATCH_ALT_MKVP 0x00000004
+
+/* keygenflags defines for CCA AES cipher keys */
+#define PKEY_KEYGEN_XPRT_SYM 0x00008000
+#define PKEY_KEYGEN_XPRT_UASY 0x00004000
+#define PKEY_KEYGEN_XPRT_AASY 0x00002000
+#define PKEY_KEYGEN_XPRT_RAW 0x00001000
+#define PKEY_KEYGEN_XPRT_CPAC 0x00000800
+#define PKEY_KEYGEN_XPRT_DES 0x00000080
+#define PKEY_KEYGEN_XPRT_AES 0x00000040
+#define PKEY_KEYGEN_XPRT_RSA 0x00000008
+
+/* Struct to hold apqn target info (card/domain pair) */
+struct pkey_apqn {
+ __u16 card;
+ __u16 domain;
+};
+
+/* Struct to hold a CCA AES secure key blob */
struct pkey_seckey {
__u8 seckey[SECKEYBLOBSIZE]; /* the secure key blob */
};
/* Struct to hold protected key and length info */
struct pkey_protkey {
- __u32 type; /* key type, one of the PKEY_KEYTYPE values */
+ __u32 type; /* key type, one of the PKEY_KEYTYPE_AES values */
__u32 len; /* bytes actually stored in protkey[] */
__u8 protkey[MAXPROTKEYSIZE]; /* the protected key blob */
};
-/* Struct to hold a clear key value */
+/* Struct to hold an AES clear key value */
struct pkey_clrkey {
__u8 clrkey[MAXCLRKEYSIZE]; /* 16, 24, or 32 byte clear key value */
};
/*
- * Generate secure key
+ * Generate CCA AES secure key.
*/
struct pkey_genseck {
__u16 cardnr; /* in: card to use or FFFF for any */
@@ -58,7 +98,7 @@
#define PKEY_GENSECK _IOWR(PKEY_IOCTL_MAGIC, 0x01, struct pkey_genseck)
/*
- * Construct secure key from clear key value
+ * Construct CCA AES secure key from clear key value
*/
struct pkey_clr2seck {
__u16 cardnr; /* in: card to use or FFFF for any */
@@ -70,7 +110,7 @@
#define PKEY_CLR2SECK _IOWR(PKEY_IOCTL_MAGIC, 0x02, struct pkey_clr2seck)
/*
- * Fabricate protected key from a secure key
+ * Fabricate AES protected key from a CCA AES secure key
*/
struct pkey_sec2protk {
__u16 cardnr; /* in: card to use or FFFF for any */
@@ -81,7 +121,7 @@
#define PKEY_SEC2PROTK _IOWR(PKEY_IOCTL_MAGIC, 0x03, struct pkey_sec2protk)
/*
- * Fabricate protected key from an clear key value
+ * Fabricate AES protected key from clear key value
*/
struct pkey_clr2protk {
__u32 keytype; /* in: key type to generate */
@@ -92,7 +132,7 @@
/*
* Search for matching crypto card based on the Master Key
- * Verification Pattern provided inside a secure key.
+ * Verification Pattern provided inside a CCA AES secure key.
*/
struct pkey_findcard {
struct pkey_seckey seckey; /* in: the secure key blob */
@@ -111,7 +151,7 @@
#define PKEY_SKEY2PKEY _IOWR(PKEY_IOCTL_MAGIC, 0x06, struct pkey_skey2pkey)
/*
- * Verify the given secure key for being able to be useable with
+ * Verify the given CCA AES secure key for being able to be useable with
* the pkey module. Check for correct key type and check for having at
* least one crypto card being able to handle this key (master key
* or old master key verification pattern matches).
@@ -129,4 +169,211 @@
#define PKEY_VERIFY_ATTR_AES 0x00000001 /* key is an AES key */
#define PKEY_VERIFY_ATTR_OLD_MKVP 0x00000100 /* key has old MKVP value */
+/*
+ * Generate AES random protected key.
+ */
+struct pkey_genprotk {
+ __u32 keytype; /* in: key type to generate */
+ struct pkey_protkey protkey; /* out: the protected key */
+};
+
+#define PKEY_GENPROTK _IOWR(PKEY_IOCTL_MAGIC, 0x08, struct pkey_genprotk)
+
+/*
+ * Verify an AES protected key.
+ */
+struct pkey_verifyprotk {
+ struct pkey_protkey protkey; /* in: the protected key to verify */
+};
+
+#define PKEY_VERIFYPROTK _IOW(PKEY_IOCTL_MAGIC, 0x09, struct pkey_verifyprotk)
+
+/*
+ * Transform an key blob (of any type) into a protected key
+ */
+struct pkey_kblob2pkey {
+ __u8 __user *key; /* in: the key blob */
+ __u32 keylen; /* in: the key blob length */
+ struct pkey_protkey protkey; /* out: the protected key */
+};
+#define PKEY_KBLOB2PROTK _IOWR(PKEY_IOCTL_MAGIC, 0x0A, struct pkey_kblob2pkey)
+
+/*
+ * Generate secure key, version 2.
+ * Generate either a CCA AES secure key or a CCA AES cipher key.
+ * There needs to be a list of apqns given with at least one entry in there.
+ * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain
+ * is not supported. The implementation walks through the list of apqns and
+ * tries to send the request to each apqn without any further checking (like
+ * card type or online state). If the apqn fails, simple the next one in the
+ * list is tried until success (return 0) or the end of the list is reached
+ * (return -1 with errno ENODEV). You may use the PKEY_APQNS4KT ioctl to
+ * generate a list of apqns based on the key type to generate.
+ * The keygenflags argument is passed to the low level generation functions
+ * individual for the key type and has a key type specific meaning. Currently
+ * only CCA AES cipher keys react to this parameter: Use one or more of the
+ * PKEY_KEYGEN_* flags to widen the export possibilities. By default a cipher
+ * key is only exportable for CPACF (PKEY_KEYGEN_XPRT_CPAC).
+ */
+struct pkey_genseck2 {
+ struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets*/
+ __u32 apqn_entries; /* in: # of apqn target list entries */
+ enum pkey_key_type type; /* in: key type to generate */
+ enum pkey_key_size size; /* in: key size to generate */
+ __u32 keygenflags; /* in: key generation flags */
+ __u8 __user *key; /* in: pointer to key blob buffer */
+ __u32 keylen; /* in: available key blob buffer size */
+ /* out: actual key blob size */
+};
+#define PKEY_GENSECK2 _IOWR(PKEY_IOCTL_MAGIC, 0x11, struct pkey_genseck2)
+
+/*
+ * Generate secure key from clear key value, version 2.
+ * Construct a CCA AES secure key or CCA AES cipher key from a given clear key
+ * value.
+ * There needs to be a list of apqns given with at least one entry in there.
+ * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain
+ * is not supported. The implementation walks through the list of apqns and
+ * tries to send the request to each apqn without any further checking (like
+ * card type or online state). If the apqn fails, simple the next one in the
+ * list is tried until success (return 0) or the end of the list is reached
+ * (return -1 with errno ENODEV). You may use the PKEY_APQNS4KT ioctl to
+ * generate a list of apqns based on the key type to generate.
+ * The keygenflags argument is passed to the low level generation functions
+ * individual for the key type and has a key type specific meaning. Currently
+ * only CCA AES cipher keys react to this parameter: Use one or more of the
+ * PKEY_KEYGEN_* flags to widen the export possibilities. By default a cipher
+ * key is only exportable for CPACF (PKEY_KEYGEN_XPRT_CPAC).
+ */
+struct pkey_clr2seck2 {
+ struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets */
+ __u32 apqn_entries; /* in: # of apqn target list entries */
+ enum pkey_key_type type; /* in: key type to generate */
+ enum pkey_key_size size; /* in: key size to generate */
+ __u32 keygenflags; /* in: key generation flags */
+ struct pkey_clrkey clrkey; /* in: the clear key value */
+ __u8 __user *key; /* in: pointer to key blob buffer */
+ __u32 keylen; /* in: available key blob buffer size */
+ /* out: actual key blob size */
+};
+#define PKEY_CLR2SECK2 _IOWR(PKEY_IOCTL_MAGIC, 0x12, struct pkey_clr2seck2)
+
+/*
+ * Verify the given secure key, version 2.
+ * Check for correct key type. If cardnr and domain are given (are not
+ * 0xFFFF) also check if this apqn is able to handle this type of key.
+ * If cardnr and/or domain is 0xFFFF, on return these values are filled
+ * with one apqn able to handle this key.
+ * The function also checks for the master key verification patterns
+ * of the key matching to the current or alternate mkvp of the apqn.
+ * Currently CCA AES secure keys and CCA AES cipher keys are supported.
+ * The flags field is updated with some additional info about the apqn mkvp
+ * match: If the current mkvp matches to the key's mkvp then the
+ * PKEY_FLAGS_MATCH_CUR_MKVP bit is set, if the alternate mkvp matches to
+ * the key's mkvp the PKEY_FLAGS_MATCH_ALT_MKVP is set. For CCA keys the
+ * alternate mkvp is the old master key verification pattern.
+ * CCA AES secure keys are also checked to have the CPACF export allowed
+ * bit enabled (XPRTCPAC) in the kmf1 field.
+ * The ioctl returns 0 as long as the given or found apqn matches to
+ * matches with the current or alternate mkvp to the key's mkvp. If the given
+ * apqn does not match or there is no such apqn found, -1 with errno
+ * ENODEV is returned.
+ */
+struct pkey_verifykey2 {
+ __u8 __user *key; /* in: pointer to key blob */
+ __u32 keylen; /* in: key blob size */
+ __u16 cardnr; /* in/out: card number */
+ __u16 domain; /* in/out: domain number */
+ enum pkey_key_type type; /* out: the key type */
+ enum pkey_key_size size; /* out: the key size */
+ __u32 flags; /* out: additional key info flags */
+};
+#define PKEY_VERIFYKEY2 _IOWR(PKEY_IOCTL_MAGIC, 0x17, struct pkey_verifykey2)
+
+/*
+ * Transform a key blob (of any type) into a protected key, version 2.
+ * There needs to be a list of apqns given with at least one entry in there.
+ * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain
+ * is not supported. The implementation walks through the list of apqns and
+ * tries to send the request to each apqn without any further checking (like
+ * card type or online state). If the apqn fails, simple the next one in the
+ * list is tried until success (return 0) or the end of the list is reached
+ * (return -1 with errno ENODEV). You may use the PKEY_APQNS4K ioctl to
+ * generate a list of apqns based on the key.
+ */
+struct pkey_kblob2pkey2 {
+ __u8 __user *key; /* in: pointer to key blob */
+ __u32 keylen; /* in: key blob size */
+ struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets */
+ __u32 apqn_entries; /* in: # of apqn target list entries */
+ struct pkey_protkey protkey; /* out: the protected key */
+};
+#define PKEY_KBLOB2PROTK2 _IOWR(PKEY_IOCTL_MAGIC, 0x1A, struct pkey_kblob2pkey2)
+
+/*
+ * Build a list of APQNs based on a key blob given.
+ * Is able to find out which type of secure key is given (CCA AES secure
+ * key or CCA AES cipher key) and tries to find all matching crypto cards
+ * based on the MKVP and maybe other criterias (like CCA AES cipher keys
+ * need a CEX5C or higher). The list of APQNs is further filtered by the key's
+ * mkvp which needs to match to either the current mkvp or the alternate mkvp
+ * (which is the old mkvp on CCA adapters) of the apqns. The flags argument may
+ * be used to limit the matching apqns. If the PKEY_FLAGS_MATCH_CUR_MKVP is
+ * given, only the current mkvp of each apqn is compared. Likewise with the
+ * PKEY_FLAGS_MATCH_ALT_MKVP. If both are given, it is assumed to
+ * return apqns where either the current or the alternate mkvp
+ * matches. At least one of the matching flags needs to be given.
+ * The list of matching apqns is stored into the space given by the apqns
+ * argument and the number of stored entries goes into apqn_entries. If the list
+ * is empty (apqn_entries is 0) the apqn_entries field is updated to the number
+ * of apqn targets found and the ioctl returns with 0. If apqn_entries is > 0
+ * but the number of apqn targets does not fit into the list, the apqn_targets
+ * field is updatedd with the number of reqired entries but there are no apqn
+ * values stored in the list and the ioctl returns with ENOSPC. If no matching
+ * APQN is found, the ioctl returns with 0 but the apqn_entries value is 0.
+ */
+struct pkey_apqns4key {
+ __u8 __user *key; /* in: pointer to key blob */
+ __u32 keylen; /* in: key blob size */
+ __u32 flags; /* in: match controlling flags */
+ struct pkey_apqn __user *apqns; /* in/out: ptr to list of apqn targets*/
+ __u32 apqn_entries; /* in: max # of apqn entries in the list */
+ /* out: # apqns stored into the list */
+};
+#define PKEY_APQNS4K _IOWR(PKEY_IOCTL_MAGIC, 0x1B, struct pkey_apqns4key)
+
+/*
+ * Build a list of APQNs based on a key type given.
+ * Build a list of APQNs based on a given key type and maybe further
+ * restrict the list by given master key verification patterns.
+ * For different key types there may be different ways to match the
+ * master key verification patterns. For CCA keys (CCA data key and CCA
+ * cipher key) the first 8 bytes of cur_mkvp refer to the current mkvp value
+ * of the apqn and the first 8 bytes of the alt_mkvp refer to the old mkvp.
+ * The flags argument controls if the apqns current and/or alternate mkvp
+ * should match. If the PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current
+ * mkvp of each apqn is compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP.
+ * If both are given, it is assumed to return apqns where either the
+ * current or the alternate mkvp matches. If no match flag is given
+ * (flags is 0) the mkvp values are ignored for the match process.
+ * The list of matching apqns is stored into the space given by the apqns
+ * argument and the number of stored entries goes into apqn_entries. If the list
+ * is empty (apqn_entries is 0) the apqn_entries field is updated to the number
+ * of apqn targets found and the ioctl returns with 0. If apqn_entries is > 0
+ * but the number of apqn targets does not fit into the list, the apqn_targets
+ * field is updatedd with the number of reqired entries but there are no apqn
+ * values stored in the list and the ioctl returns with ENOSPC. If no matching
+ * APQN is found, the ioctl returns with 0 but the apqn_entries value is 0.
+ */
+struct pkey_apqns4keytype {
+ enum pkey_key_type type; /* in: key type */
+ __u8 cur_mkvp[32]; /* in: current mkvp */
+ __u8 alt_mkvp[32]; /* in: alternate mkvp */
+ __u32 flags; /* in: match controlling flags */
+ struct pkey_apqn __user *apqns; /* in/out: ptr to list of apqn targets*/
+ __u32 apqn_entries; /* in: max # of apqn entries in the list */
+ /* out: # apqns stored into the list */
+};
+#define PKEY_APQNS4KT _IOWR(PKEY_IOCTL_MAGIC, 0x1C, struct pkey_apqns4keytype)
+
#endif /* _UAPI_PKEY_H */
diff --git a/arch/s390/include/uapi/asm/posix_types.h b/arch/s390/include/uapi/asm/posix_types.h
index 2a3fc63..1913613 100644
--- a/arch/s390/include/uapi/asm/posix_types.h
+++ b/arch/s390/include/uapi/asm/posix_types.h
@@ -20,6 +20,12 @@
typedef unsigned short __kernel_old_dev_t;
#define __kernel_old_dev_t __kernel_old_dev_t
+#ifdef __KERNEL__
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
+#endif
+
#ifndef __s390x__
typedef unsigned long __kernel_ino_t;
diff --git a/arch/s390/include/uapi/asm/runtime_instr.h b/arch/s390/include/uapi/asm/runtime_instr.h
index 45c9ec9..455da46 100644
--- a/arch/s390/include/uapi/asm/runtime_instr.h
+++ b/arch/s390/include/uapi/asm/runtime_instr.h
@@ -57,7 +57,7 @@
__u64 sf;
__u64 rsic;
__u64 reserved8;
-} __packed __aligned(8);
+} __attribute__((__packed__, __aligned__(8)));
static inline void load_runtime_instr_cb(struct runtime_instr_cb *cb)
{
diff --git a/arch/s390/include/uapi/asm/siginfo.h b/arch/s390/include/uapi/asm/siginfo.h
deleted file mode 100644
index 6984820..0000000
--- a/arch/s390/include/uapi/asm/siginfo.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * S390 version
- *
- * Derived from "include/asm-i386/siginfo.h"
- */
-
-#ifndef _S390_SIGINFO_H
-#define _S390_SIGINFO_H
-
-#ifdef __s390x__
-#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
-#endif
-
-#include <asm-generic/siginfo.h>
-
-#endif
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
deleted file mode 100644
index 39d9014..0000000
--- a/arch/s390/include/uapi/asm/socket.h
+++ /dev/null
@@ -1,117 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * S390 version
- *
- * Derived from "include/asm-i386/socket.h"
- */
-
-#ifndef _ASM_SOCKET_H
-#define _ASM_SOCKET_H
-
-#include <asm/sockios.h>
-
-/* For setsockopt(2) */
-#define SOL_SOCKET 1
-
-#define SO_DEBUG 1
-#define SO_REUSEADDR 2
-#define SO_TYPE 3
-#define SO_ERROR 4
-#define SO_DONTROUTE 5
-#define SO_BROADCAST 6
-#define SO_SNDBUF 7
-#define SO_RCVBUF 8
-#define SO_SNDBUFFORCE 32
-#define SO_RCVBUFFORCE 33
-#define SO_KEEPALIVE 9
-#define SO_OOBINLINE 10
-#define SO_NO_CHECK 11
-#define SO_PRIORITY 12
-#define SO_LINGER 13
-#define SO_BSDCOMPAT 14
-#define SO_REUSEPORT 15
-#define SO_PASSCRED 16
-#define SO_PEERCRED 17
-#define SO_RCVLOWAT 18
-#define SO_SNDLOWAT 19
-#define SO_RCVTIMEO 20
-#define SO_SNDTIMEO 21
-
-/* Security levels - as per NRL IPv6 - don't actually do anything */
-#define SO_SECURITY_AUTHENTICATION 22
-#define SO_SECURITY_ENCRYPTION_TRANSPORT 23
-#define SO_SECURITY_ENCRYPTION_NETWORK 24
-
-#define SO_BINDTODEVICE 25
-
-/* Socket filtering */
-#define SO_ATTACH_FILTER 26
-#define SO_DETACH_FILTER 27
-#define SO_GET_FILTER SO_ATTACH_FILTER
-
-#define SO_PEERNAME 28
-#define SO_TIMESTAMP 29
-#define SCM_TIMESTAMP SO_TIMESTAMP
-
-#define SO_ACCEPTCONN 30
-
-#define SO_PEERSEC 31
-#define SO_PASSSEC 34
-#define SO_TIMESTAMPNS 35
-#define SCM_TIMESTAMPNS SO_TIMESTAMPNS
-
-#define SO_MARK 36
-
-#define SO_TIMESTAMPING 37
-#define SCM_TIMESTAMPING SO_TIMESTAMPING
-
-#define SO_PROTOCOL 38
-#define SO_DOMAIN 39
-
-#define SO_RXQ_OVFL 40
-
-#define SO_WIFI_STATUS 41
-#define SCM_WIFI_STATUS SO_WIFI_STATUS
-#define SO_PEEK_OFF 42
-
-/* Instruct lower device to use last 4-bytes of skb data as FCS */
-#define SO_NOFCS 43
-
-#define SO_LOCK_FILTER 44
-
-#define SO_SELECT_ERR_QUEUE 45
-
-#define SO_BUSY_POLL 46
-
-#define SO_MAX_PACING_RATE 47
-
-#define SO_BPF_EXTENSIONS 48
-
-#define SO_INCOMING_CPU 49
-
-#define SO_ATTACH_BPF 50
-#define SO_DETACH_BPF SO_DETACH_FILTER
-
-#define SO_ATTACH_REUSEPORT_CBPF 51
-#define SO_ATTACH_REUSEPORT_EBPF 52
-
-#define SO_CNX_ADVICE 53
-
-#define SCM_TIMESTAMPING_OPT_STATS 54
-
-#define SO_MEMINFO 55
-
-#define SO_INCOMING_NAPI_ID 56
-
-#define SO_COOKIE 57
-
-#define SCM_TIMESTAMPING_PKTINFO 58
-
-#define SO_PEERGROUPS 59
-
-#define SO_ZEROCOPY 60
-
-#define SO_TXTIME 61
-#define SCM_TXTIME SO_TXTIME
-
-#endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h
index 2bb1f3b..f9e5e1f 100644
--- a/arch/s390/include/uapi/asm/zcrypt.h
+++ b/arch/s390/include/uapi/asm/zcrypt.h
@@ -2,9 +2,9 @@
/*
* include/asm-s390/zcrypt.h
*
- * zcrypt 2.1.0 (user-visible header)
+ * zcrypt 2.2.1 (user-visible header)
*
- * Copyright IBM Corp. 2001, 2006
+ * Copyright IBM Corp. 2001, 2019
* Author(s): Robert Burroughs
* Eric Rossman (edrossma@us.ibm.com)
*
@@ -15,11 +15,15 @@
#define __ASM_S390_ZCRYPT_H
#define ZCRYPT_VERSION 2
-#define ZCRYPT_RELEASE 1
+#define ZCRYPT_RELEASE 2
#define ZCRYPT_VARIANT 1
#include <linux/ioctl.h>
#include <linux/compiler.h>
+#include <linux/types.h>
+
+/* Name of the zcrypt device driver. */
+#define ZCRYPT_NAME "zcrypt"
/**
* struct ica_rsa_modexpo
@@ -147,8 +151,8 @@
* @cprb_len: CPRB header length [0x0020]
* @cprb_ver_id: CPRB version id. [0x04]
* @pad_000: Alignment pad bytes
- * @flags: Admin cmd [0x80] or functional cmd [0x00]
- * @func_id: Function id / subtype [0x5434]
+ * @flags: Admin bit [0x80], Special bit [0x20]
+ * @func_id: Function id / subtype [0x5434] "T4"
* @source_id: Source id [originator id]
* @target_id: Target id [usage/ctrl domain id]
* @ret_code: Return code
@@ -157,17 +161,17 @@
* @payload_len: Payload length
*/
struct ep11_cprb {
- uint16_t cprb_len;
+ __u16 cprb_len;
unsigned char cprb_ver_id;
unsigned char pad_000[2];
unsigned char flags;
unsigned char func_id[2];
- uint32_t source_id;
- uint32_t target_id;
- uint32_t ret_code;
- uint32_t reserved1;
- uint32_t reserved2;
- uint32_t payload_len;
+ __u32 source_id;
+ __u32 target_id;
+ __u32 ret_code;
+ __u32 reserved1;
+ __u32 reserved2;
+ __u32 payload_len;
} __attribute__((packed));
/**
@@ -176,8 +180,8 @@
* @dom_id: Usage domain id
*/
struct ep11_target_dev {
- uint16_t ap_id;
- uint16_t dom_id;
+ __u16 ap_id;
+ __u16 dom_id;
};
/**
@@ -192,14 +196,14 @@
* @resp: Addr to response block
*/
struct ep11_urb {
- uint16_t targets_num;
- uint64_t targets;
- uint64_t weight;
- uint64_t req_no;
- uint64_t req_len;
- uint64_t req;
- uint64_t resp_len;
- uint64_t resp;
+ __u16 targets_num;
+ __u64 targets;
+ __u64 weight;
+ __u64 req_no;
+ __u64 req_len;
+ __u64 req;
+ __u64 resp_len;
+ __u64 resp;
} __attribute__((packed));
/**
@@ -282,7 +286,7 @@
* 0x08: CEX3A
* 0x0a: CEX4
* 0x0b: CEX5
- * 0x0c: CEX6
+ * 0x0c: CEX6 and CEX7
* 0x0d: device is disabled
*
* ZCRYPT_QDEPTH_MASK
@@ -310,6 +314,16 @@
#define ZCRYPT_PERDEV_REQCNT _IOR(ZCRYPT_IOCTL_MAGIC, 0x5a, int[MAX_ZDEV_CARDIDS_EXT])
/*
+ * Support for multiple zcrypt device nodes.
+ */
+
+/* Nr of minor device node numbers to allocate. */
+#define ZCRYPT_MAX_MINOR_NODES 256
+
+/* Max amount of possible ioctls */
+#define MAX_ZDEV_IOCTLS (1 << _IOC_NRBITS)
+
+/*
* Only deprecated defines, structs and ioctls below this line.
*/
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index dbfd173..7edbbcd 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -10,18 +10,14 @@
# Do not trace early setup code
CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_early_nobss.o = $(CC_FLAGS_FTRACE)
endif
GCOV_PROFILE_early.o := n
-GCOV_PROFILE_early_nobss.o := n
-
KCOV_INSTRUMENT_early.o := n
-KCOV_INSTRUMENT_early_nobss.o := n
-
UBSAN_SANITIZE_early.o := n
-UBSAN_SANITIZE_early_nobss.o := n
+KASAN_SANITIZE_ipl.o := n
+KASAN_SANITIZE_machine_kexec.o := n
#
# Passing null pointers is ok for smp code, since we access the lowcore here.
@@ -35,6 +31,7 @@
#
CFLAGS_stacktrace.o += -fno-optimize-sibling-calls
CFLAGS_dumpstack.o += -fno-optimize-sibling-calls
+CFLAGS_unwind_bc.o += -fno-optimize-sibling-calls
#
# Pass UTS_MACHINE for user_regset definition
@@ -43,11 +40,12 @@
obj-y := traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o
-obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
+obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o
+obj-y += sysinfo.o lgr.o os_info.o machine_kexec.o pgm_check.o
obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
-obj-y += nospec-branch.o
+obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
+obj-y += smp.o
extra-y += head64.o vmlinux.lds
@@ -55,31 +53,32 @@
CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE)
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SCHED_TOPOLOGY) += topology.o
obj-$(CONFIG_HIBERNATION) += suspend.o swsusp.o
obj-$(CONFIG_AUDIT) += audit.o
compat-obj-$(CONFIG_AUDIT) += compat_audit.o
obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o
-obj-$(CONFIG_COMPAT) += compat_wrapper.o $(compat-obj-y)
+obj-$(CONFIG_COMPAT) += $(compat-obj-y)
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_JUMP_LABEL) += jump_label.o
obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o
obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o
-obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o perf_cpum_sf.o
+obj-$(CONFIG_IMA) += ima_arch.o
+
+obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf_common.o
+obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf.o perf_cpum_sf.o
obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o
+obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_diag.o
obj-$(CONFIG_TRACEPOINTS) += trace.o
# vdso
obj-y += vdso64/
-obj-$(CONFIG_COMPAT) += vdso32/
-
-chkbss := head64.o early_nobss.o
-include $(srctree)/arch/s390/scripts/Makefile.chkbss
+obj-$(CONFIG_COMPAT_VDSO) += vdso32/
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 66e830f..41ac4ad 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -16,6 +16,7 @@
#include <asm/pgtable.h>
#include <asm/gmap.h>
#include <asm/nmi.h>
+#include <asm/stacktrace.h>
int main(void)
{
@@ -159,7 +160,7 @@
OFFSET(__LC_CURRENT, lowcore, current_task);
OFFSET(__LC_KERNEL_STACK, lowcore, kernel_stack);
OFFSET(__LC_ASYNC_STACK, lowcore, async_stack);
- OFFSET(__LC_PANIC_STACK, lowcore, panic_stack);
+ OFFSET(__LC_NODAT_STACK, lowcore, nodat_stack);
OFFSET(__LC_RESTART_STACK, lowcore, restart_stack);
OFFSET(__LC_RESTART_FN, lowcore, restart_fn);
OFFSET(__LC_RESTART_DATA, lowcore, restart_data);
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index b65874b..b79e0fd 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -16,26 +16,6 @@
GEN_BR_THUNK %r9
GEN_BR_THUNK %r14
-ENTRY(s390_base_mcck_handler)
- basr %r13,0
-0: lg %r15,__LC_PANIC_STACK # load panic stack
- aghi %r15,-STACK_FRAME_OVERHEAD
- larl %r1,s390_base_mcck_handler_fn
- lg %r9,0(%r1)
- ltgr %r9,%r9
- jz 1f
- BASR_EX %r14,%r9
-1: la %r1,4095
- lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
- lpswe __LC_MCK_OLD_PSW
-
- .section .bss
- .align 8
- .globl s390_base_mcck_handler_fn
-s390_base_mcck_handler_fn:
- .quad 0
- .previous
-
ENTRY(s390_base_ext_handler)
stmg %r0,%r15,__LC_SAVE_AREA_ASYNC
basr %r13,0
@@ -48,6 +28,7 @@
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
@@ -68,6 +49,7 @@
lmg %r0,%r15,__LC_SAVE_AREA_SYNC
lpswe __LC_PGM_OLD_PSW
1: lpswe disabled_wait_psw-0b(%r13)
+ENDPROC(s390_base_pgm_handler)
.align 8
disabled_wait_psw:
@@ -79,71 +61,3 @@
s390_base_pgm_handler_fn:
.quad 0
.previous
-
-#
-# Calls diag 308 subcode 1 and continues execution
-#
-ENTRY(diag308_reset)
- larl %r4,.Lctlregs # Save control registers
- stctg %c0,%c15,0(%r4)
- lg %r2,0(%r4) # Disable lowcore protection
- nilh %r2,0xefff
- larl %r4,.Lctlreg0
- stg %r2,0(%r4)
- lctlg %c0,%c0,0(%r4)
- larl %r4,.Lfpctl # Floating point control register
- stfpc 0(%r4)
- larl %r4,.Lprefix # Save prefix register
- stpx 0(%r4)
- larl %r4,.Lprefix_zero # Set prefix register to 0
- spx 0(%r4)
- larl %r4,.Lcontinue_psw # Save PSW flags
- epsw %r2,%r3
- stm %r2,%r3,0(%r4)
- larl %r4,.Lrestart_psw # Setup restart PSW at absolute 0
- lghi %r3,0
- lg %r4,0(%r4) # Save PSW
- sturg %r4,%r3 # Use sturg, because of large pages
- lghi %r1,1
- lghi %r0,0
- diag %r0,%r1,0x308
-.Lrestart_part2:
- lhi %r0,0 # Load r0 with zero
- lhi %r1,2 # Use mode 2 = ESAME (dump)
- sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to ESAME mode
- sam64 # Switch to 64 bit addressing mode
- larl %r4,.Lctlregs # Restore control registers
- lctlg %c0,%c15,0(%r4)
- larl %r4,.Lfpctl # Restore floating point ctl register
- lfpc 0(%r4)
- larl %r4,.Lprefix # Restore prefix register
- spx 0(%r4)
- larl %r4,.Lcontinue_psw # Restore PSW flags
- lpswe 0(%r4)
-.Lcontinue:
- BR_EX %r14
-.align 16
-.Lrestart_psw:
- .long 0x00080000,0x80000000 + .Lrestart_part2
-
- .section .data..nosave,"aw",@progbits
-.align 8
-.Lcontinue_psw:
- .quad 0,.Lcontinue
- .previous
-
- .section .bss
-.align 8
-.Lctlreg0:
- .quad 0
-.Lctlregs:
- .rept 16
- .quad 0
- .endr
-.Lfpctl:
- .long 0
-.Lprefix:
- .long 0
-.Lprefix_zero:
- .long 0
- .previous
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 8ac38d5..f9d418d 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -34,7 +34,6 @@
#include <linux/stat.h>
#include <linux/filter.h>
#include <linux/highmem.h>
-#include <linux/highuid.h>
#include <linux/mman.h>
#include <linux/ipv6.h>
#include <linux/in.h>
@@ -58,245 +57,13 @@
#include "compat_linux.h"
-/* For this source file, we want overflow handling. */
-
-#undef high2lowuid
-#undef high2lowgid
-#undef low2highuid
-#undef low2highgid
-#undef SET_UID16
-#undef SET_GID16
-#undef NEW_TO_OLD_UID
-#undef NEW_TO_OLD_GID
-#undef SET_OLDSTAT_UID
-#undef SET_OLDSTAT_GID
-#undef SET_STAT_UID
-#undef SET_STAT_GID
-
-#define high2lowuid(uid) ((uid) > 65535) ? (u16)overflowuid : (u16)(uid)
-#define high2lowgid(gid) ((gid) > 65535) ? (u16)overflowgid : (u16)(gid)
-#define low2highuid(uid) ((uid) == (u16)-1) ? (uid_t)-1 : (uid_t)(uid)
-#define low2highgid(gid) ((gid) == (u16)-1) ? (gid_t)-1 : (gid_t)(gid)
-#define SET_UID16(var, uid) var = high2lowuid(uid)
-#define SET_GID16(var, gid) var = high2lowgid(gid)
-#define NEW_TO_OLD_UID(uid) high2lowuid(uid)
-#define NEW_TO_OLD_GID(gid) high2lowgid(gid)
-#define SET_OLDSTAT_UID(stat, uid) (stat).st_uid = high2lowuid(uid)
-#define SET_OLDSTAT_GID(stat, gid) (stat).st_gid = high2lowgid(gid)
-#define SET_STAT_UID(stat, uid) (stat).st_uid = high2lowuid(uid)
-#define SET_STAT_GID(stat, gid) (stat).st_gid = high2lowgid(gid)
-
-COMPAT_SYSCALL_DEFINE3(s390_chown16, const char __user *, filename,
- u16, user, u16, group)
-{
- return ksys_chown(filename, low2highuid(user), low2highgid(group));
-}
-
-COMPAT_SYSCALL_DEFINE3(s390_lchown16, const char __user *,
- filename, u16, user, u16, group)
-{
- return ksys_lchown(filename, low2highuid(user), low2highgid(group));
-}
-
-COMPAT_SYSCALL_DEFINE3(s390_fchown16, unsigned int, fd, u16, user, u16, group)
-{
- return ksys_fchown(fd, low2highuid(user), low2highgid(group));
-}
-
-COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid)
-{
- return sys_setregid(low2highgid(rgid), low2highgid(egid));
-}
-
-COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid)
-{
- return sys_setgid(low2highgid(gid));
-}
-
-COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid)
-{
- return sys_setreuid(low2highuid(ruid), low2highuid(euid));
-}
-
-COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid)
-{
- return sys_setuid(low2highuid(uid));
-}
-
-COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid)
-{
- return sys_setresuid(low2highuid(ruid), low2highuid(euid),
- low2highuid(suid));
-}
-
-COMPAT_SYSCALL_DEFINE3(s390_getresuid16, u16 __user *, ruidp,
- u16 __user *, euidp, u16 __user *, suidp)
-{
- const struct cred *cred = current_cred();
- int retval;
- u16 ruid, euid, suid;
-
- ruid = high2lowuid(from_kuid_munged(cred->user_ns, cred->uid));
- euid = high2lowuid(from_kuid_munged(cred->user_ns, cred->euid));
- suid = high2lowuid(from_kuid_munged(cred->user_ns, cred->suid));
-
- if (!(retval = put_user(ruid, ruidp)) &&
- !(retval = put_user(euid, euidp)))
- retval = put_user(suid, suidp);
-
- return retval;
-}
-
-COMPAT_SYSCALL_DEFINE3(s390_setresgid16, u16, rgid, u16, egid, u16, sgid)
-{
- return sys_setresgid(low2highgid(rgid), low2highgid(egid),
- low2highgid(sgid));
-}
-
-COMPAT_SYSCALL_DEFINE3(s390_getresgid16, u16 __user *, rgidp,
- u16 __user *, egidp, u16 __user *, sgidp)
-{
- const struct cred *cred = current_cred();
- int retval;
- u16 rgid, egid, sgid;
-
- rgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->gid));
- egid = high2lowgid(from_kgid_munged(cred->user_ns, cred->egid));
- sgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->sgid));
-
- if (!(retval = put_user(rgid, rgidp)) &&
- !(retval = put_user(egid, egidp)))
- retval = put_user(sgid, sgidp);
-
- return retval;
-}
-
-COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid)
-{
- return sys_setfsuid(low2highuid(uid));
-}
-
-COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid)
-{
- return sys_setfsgid(low2highgid(gid));
-}
-
-static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info)
-{
- struct user_namespace *user_ns = current_user_ns();
- int i;
- u16 group;
- kgid_t kgid;
-
- for (i = 0; i < group_info->ngroups; i++) {
- kgid = group_info->gid[i];
- group = (u16)from_kgid_munged(user_ns, kgid);
- if (put_user(group, grouplist+i))
- return -EFAULT;
- }
-
- return 0;
-}
-
-static int groups16_from_user(struct group_info *group_info, u16 __user *grouplist)
-{
- struct user_namespace *user_ns = current_user_ns();
- int i;
- u16 group;
- kgid_t kgid;
-
- for (i = 0; i < group_info->ngroups; i++) {
- if (get_user(group, grouplist+i))
- return -EFAULT;
-
- kgid = make_kgid(user_ns, (gid_t)group);
- if (!gid_valid(kgid))
- return -EINVAL;
-
- group_info->gid[i] = kgid;
- }
-
- return 0;
-}
-
-COMPAT_SYSCALL_DEFINE2(s390_getgroups16, int, gidsetsize, u16 __user *, grouplist)
-{
- const struct cred *cred = current_cred();
- int i;
-
- if (gidsetsize < 0)
- return -EINVAL;
-
- get_group_info(cred->group_info);
- i = cred->group_info->ngroups;
- if (gidsetsize) {
- if (i > gidsetsize) {
- i = -EINVAL;
- goto out;
- }
- if (groups16_to_user(grouplist, cred->group_info)) {
- i = -EFAULT;
- goto out;
- }
- }
-out:
- put_group_info(cred->group_info);
- return i;
-}
-
-COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplist)
-{
- struct group_info *group_info;
- int retval;
-
- if (!may_setgroups())
- return -EPERM;
- if ((unsigned)gidsetsize > NGROUPS_MAX)
- return -EINVAL;
-
- group_info = groups_alloc(gidsetsize);
- if (!group_info)
- return -ENOMEM;
- retval = groups16_from_user(group_info, grouplist);
- if (retval) {
- put_group_info(group_info);
- return retval;
- }
-
- groups_sort(group_info);
- retval = set_current_groups(group_info);
- put_group_info(group_info);
-
- return retval;
-}
-
-COMPAT_SYSCALL_DEFINE0(s390_getuid16)
-{
- return high2lowuid(from_kuid_munged(current_user_ns(), current_uid()));
-}
-
-COMPAT_SYSCALL_DEFINE0(s390_geteuid16)
-{
- return high2lowuid(from_kuid_munged(current_user_ns(), current_euid()));
-}
-
-COMPAT_SYSCALL_DEFINE0(s390_getgid16)
-{
- return high2lowgid(from_kgid_munged(current_user_ns(), current_gid()));
-}
-
-COMPAT_SYSCALL_DEFINE0(s390_getegid16)
-{
- return high2lowgid(from_kgid_munged(current_user_ns(), current_egid()));
-}
-
#ifdef CONFIG_SYSVIPC
COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, compat_ulong_t, second,
compat_ulong_t, third, compat_uptr_t, ptr)
{
if (call >> 16) /* hack for backward compatibility */
return -EINVAL;
- return compat_sys_ipc(call, first, second, third, ptr, third);
+ return compat_ksys_ipc(call, first, second, third, ptr, third);
}
#endif
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 6f2a193..38d4bdb 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -194,7 +194,7 @@
load_sigregs();
return regs->gprs[2];
badframe:
- force_sig(SIGSEGV, current);
+ force_sig(SIGSEGV);
return 0;
}
@@ -217,7 +217,7 @@
load_sigregs();
return regs->gprs[2];
badframe:
- force_sig(SIGSEGV, current);
+ force_sig(SIGSEGV);
return 0;
}
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
deleted file mode 100644
index 2ce28bf..0000000
--- a/arch/s390/kernel/compat_wrapper.c
+++ /dev/null
@@ -1,186 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Compat system call wrappers.
- *
- * Copyright IBM Corp. 2014
- */
-
-#include <linux/syscalls.h>
-#include <linux/compat.h>
-#include "entry.h"
-
-#define COMPAT_SYSCALL_WRAP1(name, ...) \
- COMPAT_SYSCALL_WRAPx(1, _##name, __VA_ARGS__)
-#define COMPAT_SYSCALL_WRAP2(name, ...) \
- COMPAT_SYSCALL_WRAPx(2, _##name, __VA_ARGS__)
-#define COMPAT_SYSCALL_WRAP3(name, ...) \
- COMPAT_SYSCALL_WRAPx(3, _##name, __VA_ARGS__)
-#define COMPAT_SYSCALL_WRAP4(name, ...) \
- COMPAT_SYSCALL_WRAPx(4, _##name, __VA_ARGS__)
-#define COMPAT_SYSCALL_WRAP5(name, ...) \
- COMPAT_SYSCALL_WRAPx(5, _##name, __VA_ARGS__)
-#define COMPAT_SYSCALL_WRAP6(name, ...) \
- COMPAT_SYSCALL_WRAPx(6, _##name, __VA_ARGS__)
-
-#define __SC_COMPAT_TYPE(t, a) \
- __typeof(__builtin_choose_expr(sizeof(t) > 4, 0L, (t)0)) a
-
-#define __SC_COMPAT_CAST(t, a) \
-({ \
- long __ReS = a; \
- \
- BUILD_BUG_ON((sizeof(t) > 4) && !__TYPE_IS_L(t) && \
- !__TYPE_IS_UL(t) && !__TYPE_IS_PTR(t)); \
- if (__TYPE_IS_L(t)) \
- __ReS = (s32)a; \
- if (__TYPE_IS_UL(t)) \
- __ReS = (u32)a; \
- if (__TYPE_IS_PTR(t)) \
- __ReS = a & 0x7fffffff; \
- (t)__ReS; \
-})
-
-/*
- * The COMPAT_SYSCALL_WRAP macro generates system call wrappers to be used by
- * compat tasks. These wrappers will only be used for system calls where only
- * the system call arguments need sign or zero extension or zeroing of the upper
- * 33 bits of pointers.
- * Note: since the wrapper function will afterwards call a system call which
- * again performs zero and sign extension for all system call arguments with
- * a size of less than eight bytes, these compat wrappers only touch those
- * system call arguments with a size of eight bytes ((unsigned) long and
- * pointers). Zero and sign extension for e.g. int parameters will be done by
- * the regular system call wrappers.
- */
-#define COMPAT_SYSCALL_WRAPx(x, name, ...) \
-asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
-asmlinkage long notrace compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__));\
-asmlinkage long notrace compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__)) \
-{ \
- return sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__)); \
-}
-
-COMPAT_SYSCALL_WRAP2(creat, const char __user *, pathname, umode_t, mode);
-COMPAT_SYSCALL_WRAP2(link, const char __user *, oldname, const char __user *, newname);
-COMPAT_SYSCALL_WRAP1(unlink, const char __user *, pathname);
-COMPAT_SYSCALL_WRAP1(chdir, const char __user *, filename);
-COMPAT_SYSCALL_WRAP3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev);
-COMPAT_SYSCALL_WRAP2(chmod, const char __user *, filename, umode_t, mode);
-COMPAT_SYSCALL_WRAP1(oldumount, char __user *, name);
-COMPAT_SYSCALL_WRAP2(access, const char __user *, filename, int, mode);
-COMPAT_SYSCALL_WRAP2(rename, const char __user *, oldname, const char __user *, newname);
-COMPAT_SYSCALL_WRAP2(mkdir, const char __user *, pathname, umode_t, mode);
-COMPAT_SYSCALL_WRAP1(rmdir, const char __user *, pathname);
-COMPAT_SYSCALL_WRAP1(pipe, int __user *, fildes);
-COMPAT_SYSCALL_WRAP1(brk, unsigned long, brk);
-COMPAT_SYSCALL_WRAP2(signal, int, sig, __sighandler_t, handler);
-COMPAT_SYSCALL_WRAP1(acct, const char __user *, name);
-COMPAT_SYSCALL_WRAP2(umount, char __user *, name, int, flags);
-COMPAT_SYSCALL_WRAP1(chroot, const char __user *, filename);
-COMPAT_SYSCALL_WRAP3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask);
-COMPAT_SYSCALL_WRAP2(sethostname, char __user *, name, int, len);
-COMPAT_SYSCALL_WRAP2(symlink, const char __user *, old, const char __user *, new);
-COMPAT_SYSCALL_WRAP3(readlink, const char __user *, path, char __user *, buf, int, bufsiz);
-COMPAT_SYSCALL_WRAP1(uselib, const char __user *, library);
-COMPAT_SYSCALL_WRAP2(swapon, const char __user *, specialfile, int, swap_flags);
-COMPAT_SYSCALL_WRAP4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg);
-COMPAT_SYSCALL_WRAP2(munmap, unsigned long, addr, size_t, len);
-COMPAT_SYSCALL_WRAP3(syslog, int, type, char __user *, buf, int, len);
-COMPAT_SYSCALL_WRAP1(swapoff, const char __user *, specialfile);
-COMPAT_SYSCALL_WRAP2(setdomainname, char __user *, name, int, len);
-COMPAT_SYSCALL_WRAP1(newuname, struct new_utsname __user *, name);
-COMPAT_SYSCALL_WRAP3(mprotect, unsigned long, start, size_t, len, unsigned long, prot);
-COMPAT_SYSCALL_WRAP3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs);
-COMPAT_SYSCALL_WRAP2(delete_module, const char __user *, name_user, unsigned int, flags);
-COMPAT_SYSCALL_WRAP4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr);
-COMPAT_SYSCALL_WRAP2(bdflush, int, func, long, data);
-COMPAT_SYSCALL_WRAP3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2);
-COMPAT_SYSCALL_WRAP5(llseek, unsigned int, fd, unsigned long, high, unsigned long, low, loff_t __user *, result, unsigned int, whence);
-COMPAT_SYSCALL_WRAP3(msync, unsigned long, start, size_t, len, int, flags);
-COMPAT_SYSCALL_WRAP2(mlock, unsigned long, start, size_t, len);
-COMPAT_SYSCALL_WRAP2(munlock, unsigned long, start, size_t, len);
-COMPAT_SYSCALL_WRAP2(sched_setparam, pid_t, pid, struct sched_param __user *, param);
-COMPAT_SYSCALL_WRAP2(sched_getparam, pid_t, pid, struct sched_param __user *, param);
-COMPAT_SYSCALL_WRAP3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param);
-COMPAT_SYSCALL_WRAP5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long, new_len, unsigned long, flags, unsigned long, new_addr);
-COMPAT_SYSCALL_WRAP3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout);
-COMPAT_SYSCALL_WRAP5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5);
-COMPAT_SYSCALL_WRAP2(getcwd, char __user *, buf, unsigned long, size);
-COMPAT_SYSCALL_WRAP2(capget, cap_user_header_t, header, cap_user_data_t, dataptr);
-COMPAT_SYSCALL_WRAP2(capset, cap_user_header_t, header, const cap_user_data_t, data);
-COMPAT_SYSCALL_WRAP3(lchown, const char __user *, filename, uid_t, user, gid_t, group);
-COMPAT_SYSCALL_WRAP2(getgroups, int, gidsetsize, gid_t __user *, grouplist);
-COMPAT_SYSCALL_WRAP2(setgroups, int, gidsetsize, gid_t __user *, grouplist);
-COMPAT_SYSCALL_WRAP3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid);
-COMPAT_SYSCALL_WRAP3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid);
-COMPAT_SYSCALL_WRAP3(chown, const char __user *, filename, uid_t, user, gid_t, group);
-COMPAT_SYSCALL_WRAP2(pivot_root, const char __user *, new_root, const char __user *, put_old);
-COMPAT_SYSCALL_WRAP3(mincore, unsigned long, start, size_t, len, unsigned char __user *, vec);
-COMPAT_SYSCALL_WRAP3(madvise, unsigned long, start, size_t, len, int, behavior);
-COMPAT_SYSCALL_WRAP5(setxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
-COMPAT_SYSCALL_WRAP5(lsetxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
-COMPAT_SYSCALL_WRAP5(fsetxattr, int, fd, const char __user *, name, const void __user *, value, size_t, size, int, flags);
-COMPAT_SYSCALL_WRAP3(getdents64, unsigned int, fd, struct linux_dirent64 __user *, dirent, unsigned int, count);
-COMPAT_SYSCALL_WRAP4(getxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
-COMPAT_SYSCALL_WRAP4(lgetxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
-COMPAT_SYSCALL_WRAP4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size);
-COMPAT_SYSCALL_WRAP3(listxattr, const char __user *, path, char __user *, list, size_t, size);
-COMPAT_SYSCALL_WRAP3(llistxattr, const char __user *, path, char __user *, list, size_t, size);
-COMPAT_SYSCALL_WRAP3(flistxattr, int, fd, char __user *, list, size_t, size);
-COMPAT_SYSCALL_WRAP2(removexattr, const char __user *, path, const char __user *, name);
-COMPAT_SYSCALL_WRAP2(lremovexattr, const char __user *, path, const char __user *, name);
-COMPAT_SYSCALL_WRAP2(fremovexattr, int, fd, const char __user *, name);
-COMPAT_SYSCALL_WRAP1(set_tid_address, int __user *, tidptr);
-COMPAT_SYSCALL_WRAP4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event);
-COMPAT_SYSCALL_WRAP4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout);
-COMPAT_SYSCALL_WRAP1(io_destroy, aio_context_t, ctx);
-COMPAT_SYSCALL_WRAP3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result);
-COMPAT_SYSCALL_WRAP1(mq_unlink, const char __user *, name);
-COMPAT_SYSCALL_WRAP5(add_key, const char __user *, tp, const char __user *, dsc, const void __user *, pld, size_t, len, key_serial_t, id);
-COMPAT_SYSCALL_WRAP4(request_key, const char __user *, tp, const char __user *, dsc, const char __user *, info, key_serial_t, id);
-COMPAT_SYSCALL_WRAP5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags);
-COMPAT_SYSCALL_WRAP3(inotify_add_watch, int, fd, const char __user *, path, u32, mask);
-COMPAT_SYSCALL_WRAP3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode);
-COMPAT_SYSCALL_WRAP4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned, dev);
-COMPAT_SYSCALL_WRAP5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag);
-COMPAT_SYSCALL_WRAP3(unlinkat, int, dfd, const char __user *, pathname, int, flag);
-COMPAT_SYSCALL_WRAP4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname);
-COMPAT_SYSCALL_WRAP5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags);
-COMPAT_SYSCALL_WRAP3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname);
-COMPAT_SYSCALL_WRAP4(readlinkat, int, dfd, const char __user *, path, char __user *, buf, int, bufsiz);
-COMPAT_SYSCALL_WRAP3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode);
-COMPAT_SYSCALL_WRAP3(faccessat, int, dfd, const char __user *, filename, int, mode);
-COMPAT_SYSCALL_WRAP1(unshare, unsigned long, unshare_flags);
-COMPAT_SYSCALL_WRAP6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
-COMPAT_SYSCALL_WRAP4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags);
-COMPAT_SYSCALL_WRAP3(getcpu, unsigned __user *, cpu, unsigned __user *, node, struct getcpu_cache __user *, cache);
-COMPAT_SYSCALL_WRAP2(pipe2, int __user *, fildes, int, flags);
-COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags);
-COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls);
-COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim);
-COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag);
-COMPAT_SYSCALL_WRAP5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2);
-COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, flags);
-COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags);
-COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags);
-COMPAT_SYSCALL_WRAP5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags);
-COMPAT_SYSCALL_WRAP3(seccomp, unsigned int, op, unsigned int, flags, const char __user *, uargs)
-COMPAT_SYSCALL_WRAP3(getrandom, char __user *, buf, size_t, count, unsigned int, flags)
-COMPAT_SYSCALL_WRAP2(memfd_create, const char __user *, uname, unsigned int, flags)
-COMPAT_SYSCALL_WRAP3(bpf, int, cmd, union bpf_attr *, attr, unsigned int, size);
-COMPAT_SYSCALL_WRAP3(s390_pci_mmio_write, const unsigned long, mmio_addr, const void __user *, user_buffer, const size_t, length);
-COMPAT_SYSCALL_WRAP3(s390_pci_mmio_read, const unsigned long, mmio_addr, void __user *, user_buffer, const size_t, length);
-COMPAT_SYSCALL_WRAP4(socketpair, int, family, int, type, int, protocol, int __user *, usockvec);
-COMPAT_SYSCALL_WRAP3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen);
-COMPAT_SYSCALL_WRAP3(connect, int, fd, struct sockaddr __user *, uservaddr, int, addrlen);
-COMPAT_SYSCALL_WRAP4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen, int, flags);
-COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len);
-COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len);
-COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len);
-COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags);
-COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
-COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb);
-COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
-COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags);
-COMPAT_SYSCALL_WRAP5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags)
-COMPAT_SYSCALL_WRAP4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig)
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 376f6b6..f96a585 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -13,10 +13,9 @@
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/slab.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/elf.h>
#include <asm/asm-offsets.h>
-#include <linux/memblock.h>
#include <asm/os_info.h>
#include <asm/elf.h>
#include <asm/ipl.h>
@@ -61,7 +60,10 @@
{
struct save_area *sa;
- sa = (void *) memblock_alloc(sizeof(*sa), 8);
+ sa = (void *) memblock_phys_alloc(sizeof(*sa), 8);
+ if (!sa)
+ panic("Failed to allocate save area\n");
+
if (is_boot_cpu)
list_add(&sa->list, &dump_save_areas);
else
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index d374f9b..6d321f5 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -647,11 +647,23 @@
return 0; /* success */
}
-/*
- * debug_register_mode:
- * - Creates and initializes debug area for the caller
- * The mode parameter allows to specify access rights for the s390dbf files
- * - Returns handle for debug area
+/**
+ * debug_register_mode() - creates and initializes debug area.
+ *
+ * @name: Name of debug log (e.g. used for debugfs entry)
+ * @pages_per_area: Number of pages, which will be allocated per area
+ * @nr_areas: Number of debug areas
+ * @buf_size: Size of data area in each debug entry
+ * @mode: File mode for debugfs files. E.g. S_IRWXUGO
+ * @uid: User ID for debugfs files. Currently only 0 is supported.
+ * @gid: Group ID for debugfs files. Currently only 0 is supported.
+ *
+ * Return:
+ * - Handle for generated debug area
+ * - %NULL if register failed
+ *
+ * Allocates memory for a debug log.
+ * Must not be called within an interrupt handler.
*/
debug_info_t *debug_register_mode(const char *name, int pages_per_area,
int nr_areas, int buf_size, umode_t mode,
@@ -681,10 +693,21 @@
}
EXPORT_SYMBOL(debug_register_mode);
-/*
- * debug_register:
- * - creates and initializes debug area for the caller
- * - returns handle for debug area
+/**
+ * debug_register() - creates and initializes debug area with default file mode.
+ *
+ * @name: Name of debug log (e.g. used for debugfs entry)
+ * @pages_per_area: Number of pages, which will be allocated per area
+ * @nr_areas: Number of debug areas
+ * @buf_size: Size of data area in each debug entry
+ *
+ * Return:
+ * - Handle for generated debug area
+ * - %NULL if register failed
+ *
+ * Allocates memory for a debug log.
+ * The debugfs file mode access permissions are read and write for user.
+ * Must not be called within an interrupt handler.
*/
debug_info_t *debug_register(const char *name, int pages_per_area,
int nr_areas, int buf_size)
@@ -694,9 +717,13 @@
}
EXPORT_SYMBOL(debug_register);
-/*
- * debug_unregister:
- * - give back debug area
+/**
+ * debug_unregister() - give back debug area.
+ *
+ * @id: handle for debug log
+ *
+ * Return:
+ * none
*/
void debug_unregister(debug_info_t *id)
{
@@ -745,9 +772,14 @@
return rc;
}
-/*
- * debug_set_level:
- * - set actual debug level
+/**
+ * debug_set_level() - Sets new actual debug level if new_level is valid.
+ *
+ * @id: handle for debug log
+ * @new_level: new debug level
+ *
+ * Return:
+ * none
*/
void debug_set_level(debug_info_t *id, int new_level)
{
@@ -873,6 +905,14 @@
static struct ctl_table_header *s390dbf_sysctl_header;
+/**
+ * debug_stop_all() - stops the debug feature if stopping is allowed.
+ *
+ * Return:
+ * - none
+ *
+ * Currently used in case of a kernel oops.
+ */
void debug_stop_all(void)
{
if (debug_stoppable)
@@ -880,6 +920,17 @@
}
EXPORT_SYMBOL(debug_stop_all);
+/**
+ * debug_set_critical() - event/exception functions try lock instead of spin.
+ *
+ * Return:
+ * - none
+ *
+ * Currently used in case of stopping all CPUs but the current one.
+ * Once in this state, functions to write a debug entry for an
+ * event or exception no longer spin on the debug area lock,
+ * but only try to get it and fail if they do not get the lock.
+ */
void debug_set_critical(void)
{
debug_critical = 1;
@@ -1036,8 +1087,16 @@
}
EXPORT_SYMBOL(__debug_sprintf_exception);
-/*
- * debug_register_view:
+/**
+ * debug_register_view() - registers new debug view and creates debugfs
+ * dir entry
+ *
+ * @id: handle for debug log
+ * @view: pointer to debug view struct
+ *
+ * Return:
+ * - 0 : ok
+ * - < 0: Error
*/
int debug_register_view(debug_info_t *id, struct debug_view *view)
{
@@ -1056,12 +1115,6 @@
mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH);
pde = debugfs_create_file(view->name, mode, id->debugfs_root_entry,
id, &debug_file_ops);
- if (!pde) {
- pr_err("Registering view %s/%s failed due to out of "
- "memory\n", id->name, view->name);
- rc = -1;
- goto out;
- }
spin_lock_irqsave(&id->lock, flags);
for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
if (!id->views[i])
@@ -1083,8 +1136,16 @@
}
EXPORT_SYMBOL(debug_register_view);
-/*
- * debug_unregister_view:
+/**
+ * debug_unregister_view() - unregisters debug view and removes debugfs
+ * dir entry
+ *
+ * @id: handle for debug log
+ * @view: pointer to debug view struct
+ *
+ * Return:
+ * - 0 : ok
+ * - < 0: Error
*/
int debug_unregister_view(debug_info_t *id, struct debug_view *view)
{
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index 53a5316..e9dac9a 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -13,6 +13,7 @@
#include <linux/debugfs.h>
#include <asm/diag.h>
#include <asm/trace/diag.h>
+#include <asm/sections.h>
struct diag_stat {
unsigned int counter[NR_DIAG_STAT];
@@ -45,9 +46,13 @@
[DIAG_STAT_X2FC] = { .code = 0x2fc, .name = "Guest Performance Data" },
[DIAG_STAT_X304] = { .code = 0x304, .name = "Partition-Resource Service" },
[DIAG_STAT_X308] = { .code = 0x308, .name = "List-Directed IPL" },
+ [DIAG_STAT_X318] = { .code = 0x318, .name = "CP Name and Version Codes" },
[DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" },
};
+struct diag_ops __bootdata_preserved(diag_dma_ops);
+struct diag210 *__bootdata_preserved(__diag210_tmp_dma);
+
static int show_diag_stat(struct seq_file *m, void *v)
{
struct diag_stat *stat;
@@ -138,30 +143,10 @@
/*
* Diagnose 14: Input spool file manipulation
*/
-static inline int __diag14(unsigned long rx, unsigned long ry1,
- unsigned long subcode)
-{
- register unsigned long _ry1 asm("2") = ry1;
- register unsigned long _ry2 asm("3") = subcode;
- int rc = 0;
-
- asm volatile(
- " sam31\n"
- " diag %2,2,0x14\n"
- " sam64\n"
- " ipm %0\n"
- " srl %0,28\n"
- : "=d" (rc), "+d" (_ry2)
- : "d" (rx), "d" (_ry1)
- : "cc");
-
- return rc;
-}
-
int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode)
{
diag_stat_inc(DIAG_STAT_X014);
- return __diag14(rx, ry1, subcode);
+ return diag_dma_ops.diag14(rx, ry1, subcode);
}
EXPORT_SYMBOL(diag14);
@@ -194,30 +179,17 @@
*/
int diag210(struct diag210 *addr)
{
- /*
- * diag 210 needs its data below the 2GB border, so we
- * use a static data area to be sure
- */
- static struct diag210 diag210_tmp;
static DEFINE_SPINLOCK(diag210_lock);
unsigned long flags;
int ccode;
spin_lock_irqsave(&diag210_lock, flags);
- diag210_tmp = *addr;
+ *__diag210_tmp_dma = *addr;
diag_stat_inc(DIAG_STAT_X210);
- asm volatile(
- " lhi %0,-1\n"
- " sam31\n"
- " diag %1,0,0x210\n"
- "0: ipm %0\n"
- " srl %0,28\n"
- "1: sam64\n"
- EX_TABLE(0b, 1b)
- : "=&d" (ccode) : "a" (&diag210_tmp) : "cc", "memory");
+ ccode = diag_dma_ops.diag210(__diag210_tmp_dma);
- *addr = diag210_tmp;
+ *addr = *__diag210_tmp_dma;
spin_unlock_irqrestore(&diag210_lock, flags);
return ccode;
@@ -242,27 +214,9 @@
/*
* Diagnose 26C: Access Certain System Information
*/
-static inline int __diag26c(void *req, void *resp, enum diag26c_sc subcode)
-{
- register unsigned long _req asm("2") = (addr_t) req;
- register unsigned long _resp asm("3") = (addr_t) resp;
- register unsigned long _subcode asm("4") = subcode;
- register unsigned long _rc asm("5") = -EOPNOTSUPP;
-
- asm volatile(
- " sam31\n"
- " diag %[rx],%[ry],0x26c\n"
- "0: sam64\n"
- EX_TABLE(0b,0b)
- : "+d" (_rc)
- : [rx] "d" (_req), "d" (_resp), [ry] "d" (_subcode)
- : "cc", "memory");
- return _rc;
-}
-
int diag26c(void *req, void *resp, enum diag26c_sc subcode)
{
diag_stat_inc(DIAG_STAT_X26C);
- return __diag26c(req, resp, subcode);
+ return diag_dma_ops.diag26c(req, resp, subcode);
}
EXPORT_SYMBOL(diag26c);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index b2c68fb..7abe6ae 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -242,6 +242,7 @@
[INSTR_RRF_U0FF] = { F_24, U4_16, F_28, 0, 0, 0 },
[INSTR_RRF_U0RF] = { R_24, U4_16, F_28, 0, 0, 0 },
[INSTR_RRF_U0RR] = { R_24, R_28, U4_16, 0, 0, 0 },
+ [INSTR_RRF_URR] = { R_24, R_28, U8_16, 0, 0, 0 },
[INSTR_RRF_UUFF] = { F_24, U4_16, F_28, U4_20, 0, 0 },
[INSTR_RRF_UUFR] = { F_24, U4_16, R_28, U4_20, 0, 0 },
[INSTR_RRF_UURF] = { R_24, U4_16, F_28, U4_20, 0, 0 },
@@ -306,7 +307,7 @@
[INSTR_VRI_VVV0UU2] = { V_8, V_12, V_16, U8_28, U4_24, 0 },
[INSTR_VRR_0V] = { V_12, 0, 0, 0, 0, 0 },
[INSTR_VRR_0VV0U] = { V_12, V_16, U4_24, 0, 0, 0 },
- [INSTR_VRR_RV0U] = { R_8, V_12, U4_24, 0, 0, 0 },
+ [INSTR_VRR_RV0UU] = { R_8, V_12, U4_24, U4_28, 0, 0 },
[INSTR_VRR_VRR] = { V_8, R_12, R_16, 0, 0, 0 },
[INSTR_VRR_VV] = { V_8, V_12, 0, 0, 0, 0 },
[INSTR_VRR_VV0U] = { V_8, V_12, U4_32, 0, 0, 0 },
@@ -326,10 +327,8 @@
[INSTR_VRS_RVRDU] = { R_8, V_12, D_20, B_16, U4_32, 0 },
[INSTR_VRS_VRRD] = { V_8, R_12, D_20, B_16, 0, 0 },
[INSTR_VRS_VRRDU] = { V_8, R_12, D_20, B_16, U4_32, 0 },
- [INSTR_VRS_VVRD] = { V_8, V_12, D_20, B_16, 0, 0 },
[INSTR_VRS_VVRDU] = { V_8, V_12, D_20, B_16, U4_32, 0 },
[INSTR_VRV_VVXRDU] = { V_8, D_20, VX_12, B_16, U4_32, 0 },
- [INSTR_VRX_VRRD] = { V_8, D_20, X_12, B_16, 0, 0 },
[INSTR_VRX_VRRDU] = { V_8, D_20, X_12, B_16, U4_32, 0 },
[INSTR_VRX_VV] = { V_8, V_12, 0, 0, 0, 0 },
[INSTR_VSI_URDV] = { V_32, D_20, B_16, U8_8, 0, 0 },
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 5b23c4f..34bdc60 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -21,95 +21,120 @@
#include <asm/debug.h>
#include <asm/dis.h>
#include <asm/ipl.h>
+#include <asm/unwind.h>
-/*
- * For dump_trace we have tree different stack to consider:
- * - the panic stack which is used if the kernel stack has overflown
- * - the asynchronous interrupt stack (cpu related)
- * - the synchronous kernel stack (process related)
- * The stack trace can start at any of the three stacks and can potentially
- * touch all of them. The order is: panic stack, async stack, sync stack.
- */
-static unsigned long
-__dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
- unsigned long low, unsigned long high)
+const char *stack_type_name(enum stack_type type)
{
- struct stack_frame *sf;
- struct pt_regs *regs;
-
- while (1) {
- if (sp < low || sp > high - sizeof(*sf))
- return sp;
- sf = (struct stack_frame *) sp;
- if (func(data, sf->gprs[8], 0))
- return sp;
- /* Follow the backchain. */
- while (1) {
- low = sp;
- sp = sf->back_chain;
- if (!sp)
- break;
- if (sp <= low || sp > high - sizeof(*sf))
- return sp;
- sf = (struct stack_frame *) sp;
- if (func(data, sf->gprs[8], 1))
- return sp;
- }
- /* Zero backchain detected, check for interrupt frame. */
- sp = (unsigned long) (sf + 1);
- if (sp <= low || sp > high - sizeof(*regs))
- return sp;
- regs = (struct pt_regs *) sp;
- if (!user_mode(regs)) {
- if (func(data, regs->psw.addr, 1))
- return sp;
- }
- low = sp;
- sp = regs->gprs[15];
+ switch (type) {
+ case STACK_TYPE_TASK:
+ return "task";
+ case STACK_TYPE_IRQ:
+ return "irq";
+ case STACK_TYPE_NODAT:
+ return "nodat";
+ case STACK_TYPE_RESTART:
+ return "restart";
+ default:
+ return "unknown";
}
}
-void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task,
- unsigned long sp)
+static inline bool in_stack(unsigned long sp, struct stack_info *info,
+ enum stack_type type, unsigned long low,
+ unsigned long high)
{
- unsigned long frame_size;
+ if (sp < low || sp >= high)
+ return false;
+ info->type = type;
+ info->begin = low;
+ info->end = high;
+ return true;
+}
+
+static bool in_task_stack(unsigned long sp, struct task_struct *task,
+ struct stack_info *info)
+{
+ unsigned long stack;
+
+ stack = (unsigned long) task_stack_page(task);
+ return in_stack(sp, info, STACK_TYPE_TASK, stack, stack + THREAD_SIZE);
+}
+
+static bool in_irq_stack(unsigned long sp, struct stack_info *info)
+{
+ unsigned long frame_size, top;
frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
-#ifdef CONFIG_CHECK_STACK
- sp = __dump_trace(func, data, sp,
- S390_lowcore.panic_stack + frame_size - PAGE_SIZE,
- S390_lowcore.panic_stack + frame_size);
-#endif
- sp = __dump_trace(func, data, sp,
- S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
- S390_lowcore.async_stack + frame_size);
- task = task ?: current;
- __dump_trace(func, data, sp,
- (unsigned long)task_stack_page(task),
- (unsigned long)task_stack_page(task) + THREAD_SIZE);
+ top = S390_lowcore.async_stack + frame_size;
+ return in_stack(sp, info, STACK_TYPE_IRQ, top - THREAD_SIZE, top);
}
-EXPORT_SYMBOL_GPL(dump_trace);
-static int show_address(void *data, unsigned long address, int reliable)
+static bool in_nodat_stack(unsigned long sp, struct stack_info *info)
{
- if (reliable)
- printk(" [<%016lx>] %pSR \n", address, (void *)address);
- else
- printk("([<%016lx>] %pSR)\n", address, (void *)address);
+ unsigned long frame_size, top;
+
+ frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+ top = S390_lowcore.nodat_stack + frame_size;
+ return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top);
+}
+
+static bool in_restart_stack(unsigned long sp, struct stack_info *info)
+{
+ unsigned long frame_size, top;
+
+ frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+ top = S390_lowcore.restart_stack + frame_size;
+ return in_stack(sp, info, STACK_TYPE_RESTART, top - THREAD_SIZE, top);
+}
+
+int get_stack_info(unsigned long sp, struct task_struct *task,
+ struct stack_info *info, unsigned long *visit_mask)
+{
+ if (!sp)
+ goto unknown;
+
+ task = task ? : current;
+
+ /* Check per-task stack */
+ if (in_task_stack(sp, task, info))
+ goto recursion_check;
+
+ if (task != current)
+ goto unknown;
+
+ /* Check per-cpu stacks */
+ if (!in_irq_stack(sp, info) &&
+ !in_nodat_stack(sp, info) &&
+ !in_restart_stack(sp, info))
+ goto unknown;
+
+recursion_check:
+ /*
+ * Make sure we don't iterate through any given stack more than once.
+ * If it comes up a second time then there's something wrong going on:
+ * just break out and report an unknown stack type.
+ */
+ if (*visit_mask & (1UL << info->type))
+ goto unknown;
+ *visit_mask |= 1UL << info->type;
return 0;
+unknown:
+ info->type = STACK_TYPE_UNKNOWN;
+ return -EINVAL;
}
void show_stack(struct task_struct *task, unsigned long *stack)
{
- unsigned long sp = (unsigned long) stack;
+ struct unwind_state state;
- if (!sp)
- sp = task ? task->thread.ksp : current_stack_pointer();
printk("Call Trace:\n");
- dump_trace(show_address, NULL, task, sp);
if (!task)
task = current;
- debug_show_held_locks(task);
+ unwind_for_each_frame(&state, task, NULL, (unsigned long) stack)
+ printk(state.reliable ? " [<%016lx>] %pSR \n" :
+ "([<%016lx>] %pSR)\n",
+ state.ip, (void *) state.ip);
+ debug_show_held_locks(task ? : current);
}
static void show_last_breaking_event(struct pt_regs *regs)
@@ -124,7 +149,7 @@
char *mode;
mode = user_mode(regs) ? "User" : "Krnl";
- printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr);
+ printk("%s PSW : %px %px", mode, (void *)regs->psw.mask, (void *)regs->psw.addr);
if (!user_mode(regs))
pr_cont(" (%pSR)", (void *)regs->psw.addr);
pr_cont("\n");
@@ -170,9 +195,7 @@
#ifdef CONFIG_PREEMPT
pr_cont("PREEMPT ");
#endif
-#ifdef CONFIG_SMP
pr_cont("SMP ");
-#endif
if (debug_pagealloc_enabled())
pr_cont("DEBUG_PAGEALLOC");
pr_cont("\n");
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 5b28b43..b432d63 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -29,9 +29,23 @@
#include <asm/cpcmd.h>
#include <asm/sclp.h>
#include <asm/facility.h>
+#include <asm/boot_data.h>
#include "entry.h"
-static void __init setup_boot_command_line(void);
+static void __init reset_tod_clock(void)
+{
+ u64 time;
+
+ if (store_tod_clock(&time) == 0)
+ return;
+ /* TOD clock not running. Set the clock to Unix Epoch. */
+ if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
+ disabled_wait();
+
+ memset(tod_clock_base, 0, 16);
+ *(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
+ S390_lowcore.last_update_clock = TOD_UNIX_EPOCH;
+}
/*
* Initialize storage key for kernel pages
@@ -64,10 +78,10 @@
if (stsi(vmms, 3, 2, 2) || !vmms->count)
return;
- /* Running under KVM? If not we assume z/VM */
+ /* Detect known hypervisors */
if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
S390_lowcore.machine_flags |= MACHINE_FLAG_KVM;
- else
+ else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
}
@@ -139,9 +153,9 @@
unsigned long addr;
addr = S390_lowcore.program_old_psw.addr;
- fixup = search_exception_tables(addr);
+ fixup = s390_search_extables(addr);
if (!fixup)
- disabled_wait(0);
+ disabled_wait();
/* Disable low address protection before storing into lowcore. */
__ctl_store(cr0, 0, 0);
cr0_new = cr0 & ~(1UL << 28);
@@ -165,8 +179,6 @@
static noinline __init void setup_facility_list(void)
{
- stfle(S390_lowcore.stfle_fac_list,
- ARRAY_SIZE(S390_lowcore.stfle_fac_list));
memcpy(S390_lowcore.alt_stfle_fac_list,
S390_lowcore.stfle_fac_list,
sizeof(S390_lowcore.alt_stfle_fac_list));
@@ -284,51 +296,11 @@
}
early_param("cad", cad_setup);
-/* Set up boot command line */
-static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t))
-{
- char *parm, *delim;
- size_t rc, len;
-
- len = strlen(boot_command_line);
-
- delim = boot_command_line + len; /* '\0' character position */
- parm = boot_command_line + len + 1; /* append right after '\0' */
-
- rc = ipl_data(parm, COMMAND_LINE_SIZE - len - 1);
- if (rc) {
- if (*parm == '=')
- memmove(boot_command_line, parm + 1, rc);
- else
- *delim = ' '; /* replace '\0' with space */
- }
-}
-
-static inline int has_ebcdic_char(const char *str)
-{
- int i;
-
- for (i = 0; str[i]; i++)
- if (str[i] & 0x80)
- return 1;
- return 0;
-}
-
+char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
static void __init setup_boot_command_line(void)
{
- COMMAND_LINE[ARCH_COMMAND_LINE_SIZE - 1] = 0;
- /* convert arch command line to ascii if necessary */
- if (has_ebcdic_char(COMMAND_LINE))
- EBCASC(COMMAND_LINE, ARCH_COMMAND_LINE_SIZE);
/* copy arch command line */
- strlcpy(boot_command_line, strstrip(COMMAND_LINE),
- ARCH_COMMAND_LINE_SIZE);
-
- /* append IPL PARM data to the boot command line */
- if (MACHINE_IS_VM)
- append_to_cmdline(append_ipl_vmparm);
-
- append_to_cmdline(append_ipl_scpdata);
+ strlcpy(boot_command_line, early_command_line, ARCH_COMMAND_LINE_SIZE);
}
static void __init check_image_bootable(void)
@@ -339,11 +311,12 @@
sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n");
sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n");
sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n");
- disabled_wait(0xbadb007);
+ disabled_wait();
}
void __init startup_init(void)
{
+ reset_tod_clock();
check_image_bootable();
time_early_init();
init_kernel_storage_key();
@@ -352,7 +325,6 @@
setup_facility_list();
detect_machine_type();
setup_arch_string();
- ipl_store_parameters();
setup_boot_command_line();
detect_diag9c();
detect_diag44();
diff --git a/arch/s390/kernel/early_nobss.c b/arch/s390/kernel/early_nobss.c
deleted file mode 100644
index 2d84fc4..0000000
--- a/arch/s390/kernel/early_nobss.c
+++ /dev/null
@@ -1,65 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright IBM Corp. 2007, 2018
- */
-
-/*
- * Early setup functions which may not rely on an initialized bss
- * section. The last thing that is supposed to happen here is
- * initialization of the bss section.
- */
-
-#include <linux/processor.h>
-#include <linux/string.h>
-#include <asm/sections.h>
-#include <asm/lowcore.h>
-#include <asm/setup.h>
-#include <asm/timex.h>
-#include "entry.h"
-
-static void __init reset_tod_clock(void)
-{
- u64 time;
-
- if (store_tod_clock(&time) == 0)
- return;
- /* TOD clock not running. Set the clock to Unix Epoch. */
- if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
- disabled_wait(0);
-
- memset(tod_clock_base, 0, 16);
- *(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
- S390_lowcore.last_update_clock = TOD_UNIX_EPOCH;
-}
-
-static void __init rescue_initrd(void)
-{
- unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
-
- /*
- * Just like in case of IPL from VM reader we make sure there is a
- * gap of 4MB between end of kernel and start of initrd.
- * That way we can also be sure that saving an NSS will succeed,
- * which however only requires different segments.
- */
- if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD))
- return;
- if (!INITRD_START || !INITRD_SIZE)
- return;
- if (INITRD_START >= min_initrd_addr)
- return;
- memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
- INITRD_START = min_initrd_addr;
-}
-
-static void __init clear_bss_section(void)
-{
- memset(__bss_start, 0, __bss_stop - __bss_start);
-}
-
-void __init startup_init_nobss(void)
-{
- reset_tod_clock();
- rescue_initrd();
- clear_bss_section();
-}
diff --git a/arch/s390/kernel/early_printk.c b/arch/s390/kernel/early_printk.c
index 40c1dfe..6f24d83 100644
--- a/arch/s390/kernel/early_printk.c
+++ b/arch/s390/kernel/early_printk.c
@@ -25,7 +25,7 @@
if (early_console)
return 0;
/* Accept only "earlyprintk" and "earlyprintk=sclp" */
- if (buf && strncmp(buf, "sclp", 4))
+ if (buf && !str_has_prefix(buf, "sclp"))
return 0;
if (!sclp.has_linemode && !sclp.has_vt220)
return 0;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 150130c..270d1d1 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -85,14 +85,34 @@
#endif
.endm
- .macro CHECK_STACK stacksize,savearea
+ .macro CHECK_STACK savearea
#ifdef CONFIG_CHECK_STACK
- tml %r15,\stacksize - CONFIG_STACK_GUARD
+ tml %r15,STACK_SIZE - CONFIG_STACK_GUARD
lghi %r14,\savearea
jz stack_overflow
#endif
.endm
+ .macro CHECK_VMAP_STACK savearea,oklabel
+#ifdef CONFIG_VMAP_STACK
+ lgr %r14,%r15
+ nill %r14,0x10000 - STACK_SIZE
+ oill %r14,STACK_INIT
+ clg %r14,__LC_KERNEL_STACK
+ je \oklabel
+ clg %r14,__LC_ASYNC_STACK
+ je \oklabel
+ clg %r14,__LC_NODAT_STACK
+ je \oklabel
+ clg %r14,__LC_RESTART_STACK
+ je \oklabel
+ lghi %r14,\savearea
+ j stack_overflow
+#else
+ j \oklabel
+#endif
+ .endm
+
.macro SWITCH_ASYNC savearea,timer
tmhh %r8,0x0001 # interrupting from user ?
jnz 1f
@@ -104,11 +124,11 @@
brasl %r14,cleanup_critical
tmhh %r8,0x0001 # retest problem state after cleanup
jnz 1f
-0: lg %r14,__LC_ASYNC_STACK # are we already on the async stack?
+0: lg %r14,__LC_ASYNC_STACK # are we already on the target stack?
slgr %r14,%r15
srag %r14,%r14,STACK_SHIFT
jnz 2f
- CHECK_STACK 1<<STACK_SHIFT,\savearea
+ CHECK_STACK \savearea
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
j 3f
1: UPDATE_VTIME %r14,%r15,\timer
@@ -204,6 +224,7 @@
.globl __bpon
BPON
BR_EX %r14
+ENDPROC(__bpon)
/*
* Scheduler resume function, called by switch_to
@@ -216,10 +237,10 @@
stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task
lghi %r4,__TASK_stack
lghi %r1,__TASK_thread
- lg %r5,0(%r4,%r3) # start of kernel stack of next
+ llill %r5,STACK_INIT
stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev
- lgr %r15,%r5
- aghi %r15,STACK_INIT # end of kernel stack of next
+ lg %r15,0(%r4,%r3) # start of kernel stack of next
+ agr %r15,%r5 # end of kernel stack of next
stg %r3,__LC_CURRENT # store task struct of next
stg %r15,__LC_KERNEL_STACK # store end of kernel stack
lg %r15,__THREAD_ksp(%r1,%r3) # load kernel stack of next
@@ -228,6 +249,7 @@
lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task
ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40
BR_EX %r14
+ENDPROC(__switch_to)
.L__critical_start:
@@ -304,6 +326,7 @@
EX_TABLE(.Lrewind_pad4,.Lsie_fault)
EX_TABLE(.Lrewind_pad2,.Lsie_fault)
EX_TABLE(sie_exit,.Lsie_fault)
+ENDPROC(sie64a)
EXPORT_SYMBOL(sie64a)
EXPORT_SYMBOL(sie_exit)
#endif
@@ -338,19 +361,19 @@
# load address of system call table
lg %r10,__THREAD_sysc_table(%r13,%r12)
llgh %r8,__PT_INT_CODE+2(%r11)
- slag %r8,%r8,2 # shift and test for svc 0
+ slag %r8,%r8,3 # shift and test for svc 0
jnz .Lsysc_nr_ok
# svc 0: system call number in %r1
llgfr %r1,%r1 # clear high word in r1
cghi %r1,NR_syscalls
jnl .Lsysc_nr_ok
sth %r1,__PT_INT_CODE+2(%r11)
- slag %r8,%r1,2
+ slag %r8,%r1,3
.Lsysc_nr_ok:
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
stg %r2,__PT_ORIG_GPR2(%r11)
stg %r7,STACK_FRAME_OVERHEAD(%r15)
- lgf %r9,0(%r8,%r10) # get system call add.
+ lg %r9,0(%r8,%r10) # get system call add.
TSTMSK __TI_flags(%r12),_TIF_TRACE
jnz .Lsysc_tracesys
BASR_EX %r14,%r9 # call sys_xxxx
@@ -536,8 +559,8 @@
lghi %r0,NR_syscalls
clgr %r0,%r2
jnh .Lsysc_tracenogo
- sllg %r8,%r2,2
- lgf %r9,0(%r8,%r10)
+ sllg %r8,%r2,3
+ lg %r9,0(%r8,%r10)
.Lsysc_tracego:
lmg %r3,%r7,__PT_R3(%r11)
stg %r7,STACK_FRAME_OVERHEAD(%r15)
@@ -550,6 +573,7 @@
lgr %r2,%r11 # pass pointer to pt_regs
larl %r14,.Lsysc_return
jg do_syscall_trace_exit
+ENDPROC(system_call)
#
# a new process exits the kernel with ret_from_fork
@@ -564,10 +588,16 @@
jne .Lsysc_tracenogo
# it's a kernel thread
lmg %r9,%r10,__PT_R9(%r11) # load gprs
+ la %r2,0(%r10)
+ BASR_EX %r14,%r9
+ j .Lsysc_tracenogo
+ENDPROC(ret_from_fork)
+
ENTRY(kernel_thread_starter)
la %r2,0(%r10)
BASR_EX %r14,%r9
j .Lsysc_tracenogo
+ENDPROC(kernel_thread_starter)
/*
* Program check handler routine
@@ -600,9 +630,10 @@
jnz 1f # -> enabled, can't be a double fault
tm __LC_PGM_ILC+3,0x80 # check for per exception
jnz .Lpgm_svcper # -> single stepped svc
-1: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
+1: CHECK_STACK __LC_SAVE_AREA_SYNC
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- j 4f
+ # CHECK_VMAP_STACK branches to stack_overflow or 4f
+ CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,4f
2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
lg %r15,__LC_KERNEL_STACK
@@ -644,9 +675,9 @@
larl %r1,pgm_check_table
llgh %r10,__PT_INT_CODE+2(%r11)
nill %r10,0x007f
- sll %r10,2
+ sll %r10,3
je .Lpgm_return
- lgf %r9,0(%r10,%r1) # load address of handler routine
+ lg %r9,0(%r10,%r1) # load address of handler routine
lgr %r2,%r11 # pass pointer to pt_regs
BASR_EX %r14,%r9 # branch to interrupt-handler
.Lpgm_return:
@@ -677,6 +708,7 @@
stg %r14,__LC_RETURN_PSW+8
lghi %r14,_PIF_SYSCALL | _PIF_PER_TRAP
lpswe __LC_RETURN_PSW # branch to .Lsysc_per and enable irqs
+ENDPROC(pgm_check_handler)
/*
* IO interrupt handler routine
@@ -905,6 +937,7 @@
ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts
TRACE_IRQS_OFF
j .Lio_return
+ENDPROC(io_int_handler)
/*
* External interrupt handler routine
@@ -944,6 +977,7 @@
lghi %r3,EXT_INTERRUPT
brasl %r14,do_IRQ
j .Lio_return
+ENDPROC(ext_int_handler)
/*
* Load idle PSW. The second "half" of this function is in .Lcleanup_idle.
@@ -952,14 +986,12 @@
stg %r3,__SF_EMPTY(%r15)
larl %r1,.Lpsw_idle_lpsw+4
stg %r1,__SF_EMPTY+8(%r15)
-#ifdef CONFIG_SMP
larl %r1,smp_cpu_mtid
llgf %r1,0(%r1)
ltgr %r1,%r1
jz .Lpsw_idle_stcctm
.insn rsy,0xeb0000000017,%r1,5,__SF_EMPTY+16(%r15)
.Lpsw_idle_stcctm:
-#endif
oi __LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT
BPON
STCK __CLOCK_IDLE_ENTER(%r2)
@@ -968,6 +1000,7 @@
lpswe __SF_EMPTY(%r15)
BR_EX %r14
.Lpsw_idle_end:
+ENDPROC(psw_idle)
/*
* Store floating-point controls and floating-point or vector register
@@ -1010,6 +1043,7 @@
.Lsave_fpu_regs_exit:
BR_EX %r14
.Lsave_fpu_regs_end:
+ENDPROC(save_fpu_regs)
EXPORT_SYMBOL(save_fpu_regs)
/*
@@ -1056,6 +1090,7 @@
.Lload_fpu_regs_exit:
BR_EX %r14
.Lload_fpu_regs_end:
+ENDPROC(load_fpu_regs)
.L__critical_end:
@@ -1136,7 +1171,8 @@
jnz 4f
TSTMSK __LC_MCCK_CODE,MCCK_CODE_PSW_IA_VALID
jno .Lmcck_panic
-4: SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_MCCK_ENTER_TIMER
+4: ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off
+ SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_MCCK_ENTER_TIMER
.Lmcck_skip:
lghi %r14,__LC_GPREGS_SAVE_AREA+64
stmg %r0,%r7,__PT_R0(%r11)
@@ -1163,7 +1199,6 @@
xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
la %r11,STACK_FRAME_OVERHEAD(%r1)
lgr %r15,%r1
- ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off
TSTMSK __LC_CPU_FLAGS,_CIF_MCCK_PENDING
jno .Lmcck_return
TRACE_IRQS_OFF
@@ -1182,9 +1217,10 @@
lpswe __LC_RETURN_MCCK_PSW
.Lmcck_panic:
- lg %r15,__LC_PANIC_STACK
+ lg %r15,__LC_NODAT_STACK
la %r11,STACK_FRAME_OVERHEAD(%r15)
j .Lmcck_skip
+ENDPROC(mcck_int_handler)
#
# PSW restart interrupt handler
@@ -1193,12 +1229,10 @@
ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40
stg %r15,__LC_SAVE_AREA_RESTART
lg %r15,__LC_RESTART_STACK
- aghi %r15,-__PT_SIZE # create pt_regs on stack
- xc 0(__PT_SIZE,%r15),0(%r15)
- stmg %r0,%r14,__PT_R0(%r15)
- mvc __PT_R15(8,%r15),__LC_SAVE_AREA_RESTART
- mvc __PT_PSW(16,%r15),__LC_RST_OLD_PSW # store restart old psw
- aghi %r15,-STACK_FRAME_OVERHEAD # create stack frame on stack
+ xc STACK_FRAME_OVERHEAD(__PT_SIZE,%r15),STACK_FRAME_OVERHEAD(%r15)
+ stmg %r0,%r14,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
+ mvc STACK_FRAME_OVERHEAD+__PT_R15(8,%r15),__LC_SAVE_AREA_RESTART
+ mvc STACK_FRAME_OVERHEAD+__PT_PSW(16,%r15),__LC_RST_OLD_PSW
xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15)
lg %r1,__LC_RESTART_FN # load fn, parm & source cpu
lg %r2,__LC_RESTART_DATA
@@ -1213,17 +1247,18 @@
2: sigp %r4,%r3,SIGP_STOP # sigp stop to current cpu
brc 2,2b
3: j 3b
+ENDPROC(restart_int_handler)
.section .kprobes.text, "ax"
-#ifdef CONFIG_CHECK_STACK
+#if defined(CONFIG_CHECK_STACK) || defined(CONFIG_VMAP_STACK)
/*
* The synchronous or the asynchronous stack overflowed. We are dead.
* No need to properly save the registers, we are going to panic anyway.
* Setup a pt_regs so that show_trace can provide a good call trace.
*/
-stack_overflow:
- lg %r15,__LC_PANIC_STACK # change to panic stack
+ENTRY(stack_overflow)
+ lg %r15,__LC_NODAT_STACK # change to panic stack
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
stmg %r8,%r9,__PT_PSW(%r11)
@@ -1232,9 +1267,10 @@
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
jg kernel_stack_overflow
+ENDPROC(stack_overflow)
#endif
-cleanup_critical:
+ENTRY(cleanup_critical)
#if IS_ENABLED(CONFIG_KVM)
clg %r9,BASED(.Lcleanup_table_sie) # .Lsie_gmap
jl 0f
@@ -1270,6 +1306,7 @@
clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end
jl .Lcleanup_load_fpu_regs
0: BR_EX %r14,%r11
+ENDPROC(cleanup_critical)
.align 8
.Lcleanup_table:
@@ -1429,7 +1466,6 @@
mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2)
mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2)
1: # calculate idle cycles
-#ifdef CONFIG_SMP
clg %r9,BASED(.Lcleanup_idle_insn)
jl 3f
larl %r1,smp_cpu_mtid
@@ -1447,7 +1483,6 @@
la %r3,8(%r3)
la %r4,8(%r4)
brct %r1,2b
-#endif
3: # account system time going idle
lg %r9,__LC_STEAL_TIMER
alg %r9,__CLOCK_IDLE_ENTER(%r2)
@@ -1493,7 +1528,7 @@
.quad .Lsie_skip - .Lsie_entry
#endif
.section .rodata, "a"
-#define SYSCALL(esame,emu) .long esame
+#define SYSCALL(esame,emu) .quad __s390x_ ## esame
.globl sys_call_table
sys_call_table:
#include "asm/syscall_table.h"
@@ -1501,7 +1536,7 @@
#ifdef CONFIG_COMPAT
-#define SYSCALL(esame,emu) .long emu
+#define SYSCALL(esame,emu) .quad __s390_ ## emu
.globl sys_call_table_emu
sys_call_table_emu:
#include "asm/syscall_table.h"
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 472fa2f..b2956d4 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -63,9 +63,8 @@
void die(struct pt_regs *regs, const char *str);
int setup_profiling_timer(unsigned int multiplier);
void __init time_init(void);
-int pfn_is_nosave(unsigned long);
void s390_early_resume(void);
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip);
struct s390_mmap_arg_struct;
struct fadvise64_64_args;
@@ -86,4 +85,7 @@
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);
+
#endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index 594464f..0da378e 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -23,7 +23,7 @@
if (flags & KERNEL_FPC)
/* Save floating point control */
- asm volatile("stfpc %0" : "=m" (state->fpc));
+ asm volatile("stfpc %0" : "=Q" (state->fpc));
if (!MACHINE_HAS_VX) {
if (flags & KERNEL_VXR_V0V7) {
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 39b13d7..1bb85f6 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -201,17 +201,18 @@
* Hook the return address and push it in the stack of return addresses
* in current thread info.
*/
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
+unsigned long prepare_ftrace_return(unsigned long ra, unsigned long sp,
+ unsigned long ip)
{
if (unlikely(ftrace_graph_is_dead()))
goto out;
if (unlikely(atomic_read(¤t->tracing_graph_pause)))
goto out;
ip -= MCOUNT_INSN_SIZE;
- if (!function_graph_enter(parent, ip, 0, NULL))
- parent = (unsigned long) return_to_handler;
+ if (!function_graph_enter(ra, ip, 0, (void *) sp))
+ ra = (unsigned long) return_to_handler;
out:
- return parent;
+ return ra;
}
NOKPROBE_SYMBOL(prepare_ftrace_return);
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 6d14ad4..0d9ee19 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -14,6 +14,7 @@
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/page.h>
+#include <asm/ptrace.h>
__HEAD
ENTRY(startup_continue)
@@ -25,9 +26,6 @@
0: larl %r1,tod_clock_base
mvc 0(16,%r1),__LC_BOOT_CLOCK
larl %r13,.LPG1 # get base
- lctlg %c0,%c15,.Lctl-.LPG1(%r13) # load control registers
- lg %r12,.Lparmaddr-.LPG1(%r13) # pointer to parameter area
- # move IPL device to lowcore
larl %r0,boot_vdso_data
stg %r0,__LC_VDSO_PER_CPU
#
@@ -35,15 +33,10 @@
#
larl %r14,init_task
stg %r14,__LC_CURRENT
- larl %r15,init_thread_union
- aghi %r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER) # init_task_union + THREAD_SIZE
- stg %r15,__LC_KERNEL_STACK # set end of kernel stack
- aghi %r15,-160
-#
-# Early setup functions that may not rely on an initialized bss section,
-# like moving the initrd. Returns with an initialized bss section.
-#
- brasl %r14,startup_init_nobss
+ larl %r15,init_thread_union+THREAD_SIZE-STACK_FRAME_OVERHEAD
+#ifdef CONFIG_KASAN
+ brasl %r14,kasan_early_init
+#endif
#
# Early machine initialization and detection functions.
#
@@ -65,37 +58,5 @@
.align 16
.LPG1:
-.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space
- .quad 0 # cr1: primary space segment table
- .quad .Lduct # cr2: dispatchable unit control table
- .quad 0 # cr3: instruction authorization
- .quad 0xffff # cr4: instruction authorization
- .quad .Lduct # cr5: primary-aste origin
- .quad 0 # cr6: I/O interrupts
- .quad 0 # cr7: secondary space segment table
- .quad 0 # cr8: access registers translation
- .quad 0 # cr9: tracing off
- .quad 0 # cr10: tracing off
- .quad 0 # cr11: tracing off
- .quad 0 # cr12: tracing off
- .quad 0 # cr13: home space segment table
- .quad 0xc0000000 # cr14: machine check handling off
- .quad .Llinkage_stack # cr15: linkage stack operations
-.Lpcmsk:.quad 0x0000000180000000
-.L4malign:.quad 0xffffffffffc00000
-.Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8
-.Lnop: .long 0x07000700
-.Lparmaddr:
- .quad PARMAREA
- .align 64
-.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0
- .long 0,0,0,0,0,0,0,0
-.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0
- .align 128
-.Lduald:.rept 8
- .long 0x80000000,0,0,0 # invalid access-list entries
- .endr
-.Llinkage_stack:
- .long 0,0,0x89000000,0,0,0,0x8a000000,0
.Ldw: .quad 0x0002000180000000,0x0000000000000000
.Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index b9d8fe4..8f84568 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -69,18 +69,26 @@
static ssize_t show_idle_time(struct device *dev,
struct device_attribute *attr, char *buf)
{
+ unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
- unsigned long long now, idle_time, idle_enter, idle_exit;
unsigned int seq;
do {
- now = get_tod_clock();
seq = read_seqcount_begin(&idle->seqcount);
idle_time = READ_ONCE(idle->idle_time);
idle_enter = READ_ONCE(idle->clock_idle_enter);
idle_exit = READ_ONCE(idle->clock_idle_exit);
} while (read_seqcount_retry(&idle->seqcount, seq));
- idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
+ in_idle = 0;
+ now = get_tod_clock();
+ if (idle_enter) {
+ if (idle_exit) {
+ in_idle = idle_exit - idle_enter;
+ } else if (now > idle_enter) {
+ in_idle = now - idle_enter;
+ }
+ }
+ idle_time += in_idle;
return sprintf(buf, "%llu\n", idle_time >> 12);
}
DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
@@ -88,17 +96,24 @@
u64 arch_cpu_idle_time(int cpu)
{
struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
- unsigned long long now, idle_enter, idle_exit;
+ unsigned long long now, idle_enter, idle_exit, in_idle;
unsigned int seq;
do {
- now = get_tod_clock();
seq = read_seqcount_begin(&idle->seqcount);
idle_enter = READ_ONCE(idle->clock_idle_enter);
idle_exit = READ_ONCE(idle->clock_idle_exit);
} while (read_seqcount_retry(&idle->seqcount, seq));
-
- return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0);
+ in_idle = 0;
+ now = get_tod_clock();
+ if (idle_enter) {
+ if (idle_exit) {
+ in_idle = idle_exit - idle_enter;
+ } else if (now > idle_enter) {
+ in_idle = now - idle_enter;
+ }
+ }
+ return cputime_to_nsecs(in_idle);
}
void arch_cpu_idle_enter(void)
diff --git a/arch/s390/kernel/ima_arch.c b/arch/s390/kernel/ima_arch.c
new file mode 100644
index 0000000..f3c3e6e
--- /dev/null
+++ b/arch/s390/kernel/ima_arch.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ima.h>
+#include <asm/boot_data.h>
+
+bool arch_ima_get_secureboot(void)
+{
+ return ipl_secure_flag;
+}
+
+const char * const *arch_get_ima_policy(void)
+{
+ return NULL;
+}
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 4296d7e..6837aff 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -29,6 +29,8 @@
#include <asm/checksum.h>
#include <asm/debug.h>
#include <asm/os_info.h>
+#include <asm/sections.h>
+#include <asm/boot_data.h>
#include "entry.h"
#define IPL_PARM_BLOCK_VERSION 0
@@ -117,8 +119,15 @@
}
}
-static int ipl_block_valid;
-static struct ipl_parameter_block ipl_block;
+int __bootdata_preserved(ipl_block_valid);
+struct ipl_parameter_block __bootdata_preserved(ipl_block);
+int __bootdata_preserved(ipl_secure_flag);
+
+unsigned long __bootdata_preserved(ipl_cert_list_addr);
+unsigned long __bootdata_preserved(ipl_cert_list_size);
+
+unsigned long __bootdata(early_ipl_comp_list_addr);
+unsigned long __bootdata(early_ipl_comp_list_size);
static int reipl_capabilities = IPL_TYPE_UNKNOWN;
@@ -151,6 +160,8 @@
int diag308(unsigned long subcode, void *addr)
{
+ if (IS_ENABLED(CONFIG_KASAN))
+ __arch_local_irq_stosm(0x04); /* enable DAT */
diag_stat_inc(DIAG_STAT_X308);
return __diag308(subcode, addr);
}
@@ -239,11 +250,11 @@
if (!ipl_block_valid)
return IPL_TYPE_UNKNOWN;
- switch (ipl_block.hdr.pbt) {
- case DIAG308_IPL_TYPE_CCW:
+ switch (ipl_block.pb0_hdr.pbt) {
+ case IPL_PBT_CCW:
return IPL_TYPE_CCW;
- case DIAG308_IPL_TYPE_FCP:
- if (ipl_block.ipl_info.fcp.opt == DIAG308_IPL_OPT_DUMP)
+ case IPL_PBT_FCP:
+ if (ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP)
return IPL_TYPE_FCP_DUMP;
else
return IPL_TYPE_FCP;
@@ -262,115 +273,34 @@
static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type);
-/* VM IPL PARM routines */
-static size_t reipl_get_ascii_vmparm(char *dest, size_t size,
- const struct ipl_parameter_block *ipb)
+static ssize_t ipl_secure_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *page)
{
- int i;
- size_t len;
- char has_lowercase = 0;
-
- len = 0;
- if ((ipb->ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID) &&
- (ipb->ipl_info.ccw.vm_parm_len > 0)) {
-
- len = min_t(size_t, size - 1, ipb->ipl_info.ccw.vm_parm_len);
- memcpy(dest, ipb->ipl_info.ccw.vm_parm, len);
- /* If at least one character is lowercase, we assume mixed
- * case; otherwise we convert everything to lowercase.
- */
- for (i = 0; i < len; i++)
- if ((dest[i] > 0x80 && dest[i] < 0x8a) || /* a-i */
- (dest[i] > 0x90 && dest[i] < 0x9a) || /* j-r */
- (dest[i] > 0xa1 && dest[i] < 0xaa)) { /* s-z */
- has_lowercase = 1;
- break;
- }
- if (!has_lowercase)
- EBC_TOLOWER(dest, len);
- EBCASC(dest, len);
- }
- dest[len] = 0;
-
- return len;
+ return sprintf(page, "%i\n", !!ipl_secure_flag);
}
-size_t append_ipl_vmparm(char *dest, size_t size)
-{
- size_t rc;
+static struct kobj_attribute sys_ipl_secure_attr =
+ __ATTR(secure, 0444, ipl_secure_show, NULL);
- rc = 0;
- if (ipl_block_valid && ipl_block.hdr.pbt == DIAG308_IPL_TYPE_CCW)
- rc = reipl_get_ascii_vmparm(dest, size, &ipl_block);
- else
- dest[0] = 0;
- return rc;
+static ssize_t ipl_has_secure_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *page)
+{
+ return sprintf(page, "%i\n", !!sclp.has_sipl);
}
+static struct kobj_attribute sys_ipl_has_secure_attr =
+ __ATTR(has_secure, 0444, ipl_has_secure_show, NULL);
+
static ssize_t ipl_vm_parm_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
char parm[DIAG308_VMPARM_SIZE + 1] = {};
- append_ipl_vmparm(parm, sizeof(parm));
+ if (ipl_block_valid && (ipl_block.pb0_hdr.pbt == IPL_PBT_CCW))
+ ipl_block_get_ascii_vmparm(parm, sizeof(parm), &ipl_block);
return sprintf(page, "%s\n", parm);
}
-static size_t scpdata_length(const char* buf, size_t count)
-{
- while (count) {
- if (buf[count - 1] != '\0' && buf[count - 1] != ' ')
- break;
- count--;
- }
- return count;
-}
-
-static size_t reipl_append_ascii_scpdata(char *dest, size_t size,
- const struct ipl_parameter_block *ipb)
-{
- size_t count;
- size_t i;
- int has_lowercase;
-
- count = min(size - 1, scpdata_length(ipb->ipl_info.fcp.scp_data,
- ipb->ipl_info.fcp.scp_data_len));
- if (!count)
- goto out;
-
- has_lowercase = 0;
- for (i = 0; i < count; i++) {
- if (!isascii(ipb->ipl_info.fcp.scp_data[i])) {
- count = 0;
- goto out;
- }
- if (!has_lowercase && islower(ipb->ipl_info.fcp.scp_data[i]))
- has_lowercase = 1;
- }
-
- if (has_lowercase)
- memcpy(dest, ipb->ipl_info.fcp.scp_data, count);
- else
- for (i = 0; i < count; i++)
- dest[i] = tolower(ipb->ipl_info.fcp.scp_data[i]);
-out:
- dest[count] = '\0';
- return count;
-}
-
-size_t append_ipl_scpdata(char *dest, size_t len)
-{
- size_t rc;
-
- rc = 0;
- if (ipl_block_valid && ipl_block.hdr.pbt == DIAG308_IPL_TYPE_FCP)
- rc = reipl_append_ascii_scpdata(dest, len, &ipl_block);
- else
- dest[0] = 0;
- return rc;
-}
-
-
static struct kobj_attribute sys_ipl_vm_parm_attr =
__ATTR(parm, S_IRUGO, ipl_vm_parm_show, NULL);
@@ -379,12 +309,11 @@
{
switch (ipl_info.type) {
case IPL_TYPE_CCW:
- return sprintf(page, "0.%x.%04x\n", ipl_block.ipl_info.ccw.ssid,
- ipl_block.ipl_info.ccw.devno);
+ return sprintf(page, "0.%x.%04x\n", ipl_block.ccw.ssid,
+ ipl_block.ccw.devno);
case IPL_TYPE_FCP:
case IPL_TYPE_FCP_DUMP:
- return sprintf(page, "0.0.%04x\n",
- ipl_block.ipl_info.fcp.devno);
+ return sprintf(page, "0.0.%04x\n", ipl_block.fcp.devno);
default:
return 0;
}
@@ -408,8 +337,8 @@
struct bin_attribute *attr, char *buf,
loff_t off, size_t count)
{
- unsigned int size = ipl_block.ipl_info.fcp.scp_data_len;
- void *scp_data = &ipl_block.ipl_info.fcp.scp_data;
+ unsigned int size = ipl_block.fcp.scp_data_len;
+ void *scp_data = &ipl_block.fcp.scp_data;
return memory_read_from_buffer(buf, count, &off, scp_data, size);
}
@@ -425,13 +354,13 @@
/* FCP ipl device attributes */
DEFINE_IPL_ATTR_RO(ipl_fcp, wwpn, "0x%016llx\n",
- (unsigned long long)ipl_block.ipl_info.fcp.wwpn);
+ (unsigned long long)ipl_block.fcp.wwpn);
DEFINE_IPL_ATTR_RO(ipl_fcp, lun, "0x%016llx\n",
- (unsigned long long)ipl_block.ipl_info.fcp.lun);
+ (unsigned long long)ipl_block.fcp.lun);
DEFINE_IPL_ATTR_RO(ipl_fcp, bootprog, "%lld\n",
- (unsigned long long)ipl_block.ipl_info.fcp.bootprog);
+ (unsigned long long)ipl_block.fcp.bootprog);
DEFINE_IPL_ATTR_RO(ipl_fcp, br_lba, "%lld\n",
- (unsigned long long)ipl_block.ipl_info.fcp.br_lba);
+ (unsigned long long)ipl_block.fcp.br_lba);
static ssize_t ipl_ccw_loadparm_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
@@ -457,6 +386,8 @@
&sys_ipl_fcp_bootprog_attr.attr,
&sys_ipl_fcp_br_lba_attr.attr,
&sys_ipl_ccw_loadparm_attr.attr,
+ &sys_ipl_secure_attr.attr,
+ &sys_ipl_has_secure_attr.attr,
NULL,
};
@@ -472,6 +403,8 @@
&sys_ipl_device_attr.attr,
&sys_ipl_ccw_loadparm_attr.attr,
&sys_ipl_vm_parm_attr.attr,
+ &sys_ipl_secure_attr.attr,
+ &sys_ipl_has_secure_attr.attr,
NULL,
};
@@ -479,6 +412,8 @@
&sys_ipl_type_attr.attr,
&sys_ipl_device_attr.attr,
&sys_ipl_ccw_loadparm_attr.attr,
+ &sys_ipl_secure_attr.attr,
+ &sys_ipl_has_secure_attr.attr,
NULL,
};
@@ -564,7 +499,7 @@
{
char vmparm[DIAG308_VMPARM_SIZE + 1] = {};
- reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb);
+ ipl_block_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb);
return sprintf(page, "%s\n", vmparm);
}
@@ -587,14 +522,14 @@
if (!(isalnum(buf[i]) || isascii(buf[i]) || isprint(buf[i])))
return -EINVAL;
- memset(ipb->ipl_info.ccw.vm_parm, 0, DIAG308_VMPARM_SIZE);
- ipb->ipl_info.ccw.vm_parm_len = ip_len;
+ memset(ipb->ccw.vm_parm, 0, DIAG308_VMPARM_SIZE);
+ ipb->ccw.vm_parm_len = ip_len;
if (ip_len > 0) {
- ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID;
- memcpy(ipb->ipl_info.ccw.vm_parm, buf, ip_len);
- ASCEBC(ipb->ipl_info.ccw.vm_parm, ip_len);
+ ipb->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_VP;
+ memcpy(ipb->ccw.vm_parm, buf, ip_len);
+ ASCEBC(ipb->ccw.vm_parm, ip_len);
} else {
- ipb->ipl_info.ccw.vm_flags &= ~DIAG308_VM_FLAGS_VP_VALID;
+ ipb->ccw.vm_flags &= ~IPL_PB0_CCW_VM_FLAG_VP;
}
return len;
@@ -641,8 +576,8 @@
struct bin_attribute *attr,
char *buf, loff_t off, size_t count)
{
- size_t size = reipl_block_fcp->ipl_info.fcp.scp_data_len;
- void *scp_data = reipl_block_fcp->ipl_info.fcp.scp_data;
+ size_t size = reipl_block_fcp->fcp.scp_data_len;
+ void *scp_data = reipl_block_fcp->fcp.scp_data;
return memory_read_from_buffer(buf, count, &off, scp_data, size);
}
@@ -658,17 +593,17 @@
if (off)
return -EINVAL;
- memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf, count);
+ memcpy(reipl_block_fcp->fcp.scp_data, buf, count);
if (scpdata_len % 8) {
padding = 8 - (scpdata_len % 8);
- memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len,
+ memset(reipl_block_fcp->fcp.scp_data + scpdata_len,
0, padding);
scpdata_len += padding;
}
- reipl_block_fcp->ipl_info.fcp.scp_data_len = scpdata_len;
- reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN + scpdata_len;
- reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN + scpdata_len;
+ reipl_block_fcp->hdr.len = IPL_BP_FCP_LEN + scpdata_len;
+ reipl_block_fcp->fcp.len = IPL_BP0_FCP_LEN + scpdata_len;
+ reipl_block_fcp->fcp.scp_data_len = scpdata_len;
return count;
}
@@ -682,20 +617,20 @@
};
DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n",
- reipl_block_fcp->ipl_info.fcp.wwpn);
+ reipl_block_fcp->fcp.wwpn);
DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\n",
- reipl_block_fcp->ipl_info.fcp.lun);
+ reipl_block_fcp->fcp.lun);
DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n",
- reipl_block_fcp->ipl_info.fcp.bootprog);
+ reipl_block_fcp->fcp.bootprog);
DEFINE_IPL_ATTR_RW(reipl_fcp, br_lba, "%lld\n", "%lld\n",
- reipl_block_fcp->ipl_info.fcp.br_lba);
+ reipl_block_fcp->fcp.br_lba);
DEFINE_IPL_ATTR_RW(reipl_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
- reipl_block_fcp->ipl_info.fcp.devno);
+ reipl_block_fcp->fcp.devno);
static void reipl_get_ascii_loadparm(char *loadparm,
struct ipl_parameter_block *ibp)
{
- memcpy(loadparm, ibp->hdr.loadparm, LOADPARM_LEN);
+ memcpy(loadparm, ibp->common.loadparm, LOADPARM_LEN);
EBCASC(loadparm, LOADPARM_LEN);
loadparm[LOADPARM_LEN] = 0;
strim(loadparm);
@@ -730,11 +665,11 @@
return -EINVAL;
}
/* initialize loadparm with blanks */
- memset(ipb->hdr.loadparm, ' ', LOADPARM_LEN);
+ memset(ipb->common.loadparm, ' ', LOADPARM_LEN);
/* copy and convert to ebcdic */
- memcpy(ipb->hdr.loadparm, buf, lp_len);
- ASCEBC(ipb->hdr.loadparm, LOADPARM_LEN);
- ipb->hdr.flags |= DIAG308_FLAGS_LP_VALID;
+ memcpy(ipb->common.loadparm, buf, lp_len);
+ ASCEBC(ipb->common.loadparm, LOADPARM_LEN);
+ ipb->common.flags |= IPL_PB0_FLAG_LOADPARM;
return len;
}
@@ -772,7 +707,7 @@
};
/* CCW reipl device attributes */
-DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ipl_info.ccw);
+DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ccw);
/* NSS wrapper */
static ssize_t reipl_nss_loadparm_show(struct kobject *kobj,
@@ -834,7 +769,7 @@
static void reipl_get_ascii_nss_name(char *dst,
struct ipl_parameter_block *ipb)
{
- memcpy(dst, ipb->ipl_info.ccw.nss_name, NSS_NAME_SIZE);
+ memcpy(dst, ipb->ccw.nss_name, NSS_NAME_SIZE);
EBCASC(dst, NSS_NAME_SIZE);
dst[NSS_NAME_SIZE] = 0;
}
@@ -862,16 +797,14 @@
if (nss_len > NSS_NAME_SIZE)
return -EINVAL;
- memset(reipl_block_nss->ipl_info.ccw.nss_name, 0x40, NSS_NAME_SIZE);
+ memset(reipl_block_nss->ccw.nss_name, 0x40, NSS_NAME_SIZE);
if (nss_len > 0) {
- reipl_block_nss->ipl_info.ccw.vm_flags |=
- DIAG308_VM_FLAGS_NSS_VALID;
- memcpy(reipl_block_nss->ipl_info.ccw.nss_name, buf, nss_len);
- ASCEBC(reipl_block_nss->ipl_info.ccw.nss_name, nss_len);
- EBC_TOUPPER(reipl_block_nss->ipl_info.ccw.nss_name, nss_len);
+ reipl_block_nss->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_NSS;
+ memcpy(reipl_block_nss->ccw.nss_name, buf, nss_len);
+ ASCEBC(reipl_block_nss->ccw.nss_name, nss_len);
+ EBC_TOUPPER(reipl_block_nss->ccw.nss_name, nss_len);
} else {
- reipl_block_nss->ipl_info.ccw.vm_flags &=
- ~DIAG308_VM_FLAGS_NSS_VALID;
+ reipl_block_nss->ccw.vm_flags &= ~IPL_PB0_CCW_VM_FLAG_NSS;
}
return len;
@@ -975,7 +908,7 @@
case IPL_TYPE_FCP_DUMP:
break;
}
- disabled_wait((unsigned long) __builtin_return_address(0));
+ disabled_wait();
}
static void reipl_run(struct shutdown_trigger *trigger)
@@ -985,10 +918,10 @@
static void reipl_block_ccw_init(struct ipl_parameter_block *ipb)
{
- ipb->hdr.len = IPL_PARM_BLK_CCW_LEN;
+ ipb->hdr.len = IPL_BP_CCW_LEN;
ipb->hdr.version = IPL_PARM_BLOCK_VERSION;
- ipb->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN;
- ipb->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+ ipb->pb0_hdr.len = IPL_BP0_CCW_LEN;
+ ipb->pb0_hdr.pbt = IPL_PBT_CCW;
}
static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb)
@@ -996,21 +929,20 @@
/* LOADPARM */
/* check if read scp info worked and set loadparm */
if (sclp_ipl_info.is_valid)
- memcpy(ipb->hdr.loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
+ memcpy(ipb->ccw.loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
else
/* read scp info failed: set empty loadparm (EBCDIC blanks) */
- memset(ipb->hdr.loadparm, 0x40, LOADPARM_LEN);
- ipb->hdr.flags = DIAG308_FLAGS_LP_VALID;
+ memset(ipb->ccw.loadparm, 0x40, LOADPARM_LEN);
+ ipb->ccw.flags = IPL_PB0_FLAG_LOADPARM;
/* VM PARM */
if (MACHINE_IS_VM && ipl_block_valid &&
- (ipl_block.ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID)) {
+ (ipl_block.ccw.vm_flags & IPL_PB0_CCW_VM_FLAG_VP)) {
- ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID;
- ipb->ipl_info.ccw.vm_parm_len =
- ipl_block.ipl_info.ccw.vm_parm_len;
- memcpy(ipb->ipl_info.ccw.vm_parm,
- ipl_block.ipl_info.ccw.vm_parm, DIAG308_VMPARM_SIZE);
+ ipb->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_VP;
+ ipb->ccw.vm_parm_len = ipl_block.ccw.vm_parm_len;
+ memcpy(ipb->ccw.vm_parm,
+ ipl_block.ccw.vm_parm, DIAG308_VMPARM_SIZE);
}
}
@@ -1050,8 +982,8 @@
reipl_block_ccw_init(reipl_block_ccw);
if (ipl_info.type == IPL_TYPE_CCW) {
- reipl_block_ccw->ipl_info.ccw.ssid = ipl_block.ipl_info.ccw.ssid;
- reipl_block_ccw->ipl_info.ccw.devno = ipl_block.ipl_info.ccw.devno;
+ reipl_block_ccw->ccw.ssid = ipl_block.ccw.ssid;
+ reipl_block_ccw->ccw.devno = ipl_block.ccw.devno;
reipl_block_ccw_fill_parms(reipl_block_ccw);
}
@@ -1089,14 +1021,14 @@
* is invalid in the SCSI IPL parameter block, so take it
* always from sclp_ipl_info.
*/
- memcpy(reipl_block_fcp->hdr.loadparm, sclp_ipl_info.loadparm,
+ memcpy(reipl_block_fcp->fcp.loadparm, sclp_ipl_info.loadparm,
LOADPARM_LEN);
} else {
- reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN;
+ reipl_block_fcp->hdr.len = IPL_BP_FCP_LEN;
reipl_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION;
- reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN;
- reipl_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP;
- reipl_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_IPL;
+ reipl_block_fcp->fcp.len = IPL_BP0_FCP_LEN;
+ reipl_block_fcp->fcp.pbt = IPL_PBT_FCP;
+ reipl_block_fcp->fcp.opt = IPL_PB0_FCP_OPT_IPL;
}
reipl_capabilities |= IPL_TYPE_FCP;
return 0;
@@ -1114,10 +1046,10 @@
/*
* If we have an OS info reipl block, this will be used
*/
- if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_FCP) {
+ if (reipl_block->pb0_hdr.pbt == IPL_PBT_FCP) {
memcpy(reipl_block_fcp, reipl_block, size);
reipl_type = IPL_TYPE_FCP;
- } else if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_CCW) {
+ } else if (reipl_block->pb0_hdr.pbt == IPL_PBT_CCW) {
memcpy(reipl_block_ccw, reipl_block, size);
reipl_type = IPL_TYPE_CCW;
}
@@ -1162,15 +1094,15 @@
/* FCP dump device attributes */
DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n",
- dump_block_fcp->ipl_info.fcp.wwpn);
+ dump_block_fcp->fcp.wwpn);
DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\n",
- dump_block_fcp->ipl_info.fcp.lun);
+ dump_block_fcp->fcp.lun);
DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n",
- dump_block_fcp->ipl_info.fcp.bootprog);
+ dump_block_fcp->fcp.bootprog);
DEFINE_IPL_ATTR_RW(dump_fcp, br_lba, "%lld\n", "%lld\n",
- dump_block_fcp->ipl_info.fcp.br_lba);
+ dump_block_fcp->fcp.br_lba);
DEFINE_IPL_ATTR_RW(dump_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
- dump_block_fcp->ipl_info.fcp.devno);
+ dump_block_fcp->fcp.devno);
static struct attribute *dump_fcp_attrs[] = {
&sys_dump_fcp_device_attr.attr,
@@ -1187,7 +1119,7 @@
};
/* CCW dump device attributes */
-DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ipl_info.ccw);
+DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ccw);
static struct attribute *dump_ccw_attrs[] = {
&sys_dump_ccw_device_attr.attr,
@@ -1279,10 +1211,10 @@
free_page((unsigned long)dump_block_ccw);
return rc;
}
- dump_block_ccw->hdr.len = IPL_PARM_BLK_CCW_LEN;
+ dump_block_ccw->hdr.len = IPL_BP_CCW_LEN;
dump_block_ccw->hdr.version = IPL_PARM_BLOCK_VERSION;
- dump_block_ccw->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN;
- dump_block_ccw->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+ dump_block_ccw->ccw.len = IPL_BP0_CCW_LEN;
+ dump_block_ccw->ccw.pbt = IPL_PBT_CCW;
dump_capabilities |= DUMP_TYPE_CCW;
return 0;
}
@@ -1301,11 +1233,11 @@
free_page((unsigned long)dump_block_fcp);
return rc;
}
- dump_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN;
+ dump_block_fcp->hdr.len = IPL_BP_FCP_LEN;
dump_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION;
- dump_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN;
- dump_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP;
- dump_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_DUMP;
+ dump_block_fcp->fcp.len = IPL_BP0_FCP_LEN;
+ dump_block_fcp->fcp.pbt = IPL_PBT_FCP;
+ dump_block_fcp->fcp.opt = IPL_PB0_FCP_OPT_DUMP;
dump_capabilities |= DUMP_TYPE_FCP;
return 0;
}
@@ -1429,7 +1361,7 @@
{
if (strcmp(trigger->name, ON_PANIC_STR) == 0 ||
strcmp(trigger->name, ON_RESTART_STR) == 0)
- disabled_wait((unsigned long) __builtin_return_address(0));
+ disabled_wait();
smp_stop_cpu();
}
@@ -1664,7 +1596,7 @@
* READ SCP info provides the correct value.
*/
if (memcmp(sclp_ipl_info.loadparm, str, sizeof(str)) == 0 && ipl_block_valid)
- memcpy(sclp_ipl_info.loadparm, ipl_block.hdr.loadparm, LOADPARM_LEN);
+ memcpy(sclp_ipl_info.loadparm, ipl_block.ccw.loadparm, LOADPARM_LEN);
shutdown_actions_init();
shutdown_triggers_init();
return 0;
@@ -1749,15 +1681,15 @@
ipl_info.type = get_ipl_type();
switch (ipl_info.type) {
case IPL_TYPE_CCW:
- ipl_info.data.ccw.dev_id.ssid = ipl_block.ipl_info.ccw.ssid;
- ipl_info.data.ccw.dev_id.devno = ipl_block.ipl_info.ccw.devno;
+ ipl_info.data.ccw.dev_id.ssid = ipl_block.ccw.ssid;
+ ipl_info.data.ccw.dev_id.devno = ipl_block.ccw.devno;
break;
case IPL_TYPE_FCP:
case IPL_TYPE_FCP_DUMP:
ipl_info.data.fcp.dev_id.ssid = 0;
- ipl_info.data.fcp.dev_id.devno = ipl_block.ipl_info.fcp.devno;
- ipl_info.data.fcp.wwpn = ipl_block.ipl_info.fcp.wwpn;
- ipl_info.data.fcp.lun = ipl_block.ipl_info.fcp.lun;
+ ipl_info.data.fcp.dev_id.devno = ipl_block.fcp.devno;
+ ipl_info.data.fcp.wwpn = ipl_block.fcp.wwpn;
+ ipl_info.data.fcp.lun = ipl_block.fcp.lun;
break;
case IPL_TYPE_NSS:
case IPL_TYPE_UNKNOWN:
@@ -1767,15 +1699,6 @@
atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb);
}
-void __init ipl_store_parameters(void)
-{
- int rc;
-
- rc = diag308(DIAG308_STORE, &ipl_block);
- if (rc == DIAG308_RC_OK && ipl_block.hdr.version <= IPL_MAX_SUPPORTED_VERSION)
- ipl_block_valid = 1;
-}
-
void s390_reset_system(void)
{
/* Disable prefixing */
@@ -1783,5 +1706,139 @@
/* Disable lowcore protection */
__ctl_clear_bit(0, 28);
- diag308_reset();
+ diag_dma_ops.diag308_reset();
}
+
+#ifdef CONFIG_KEXEC_FILE
+
+int ipl_report_add_component(struct ipl_report *report, struct kexec_buf *kbuf,
+ unsigned char flags, unsigned short cert)
+{
+ struct ipl_report_component *comp;
+
+ comp = vzalloc(sizeof(*comp));
+ if (!comp)
+ return -ENOMEM;
+ list_add_tail(&comp->list, &report->components);
+
+ comp->entry.addr = kbuf->mem;
+ comp->entry.len = kbuf->memsz;
+ comp->entry.flags = flags;
+ comp->entry.certificate_index = cert;
+
+ report->size += sizeof(comp->entry);
+
+ return 0;
+}
+
+int ipl_report_add_certificate(struct ipl_report *report, void *key,
+ unsigned long addr, unsigned long len)
+{
+ struct ipl_report_certificate *cert;
+
+ cert = vzalloc(sizeof(*cert));
+ if (!cert)
+ return -ENOMEM;
+ list_add_tail(&cert->list, &report->certificates);
+
+ cert->entry.addr = addr;
+ cert->entry.len = len;
+ cert->key = key;
+
+ report->size += sizeof(cert->entry);
+ report->size += cert->entry.len;
+
+ return 0;
+}
+
+struct ipl_report *ipl_report_init(struct ipl_parameter_block *ipib)
+{
+ struct ipl_report *report;
+
+ report = vzalloc(sizeof(*report));
+ if (!report)
+ return ERR_PTR(-ENOMEM);
+
+ report->ipib = ipib;
+ INIT_LIST_HEAD(&report->components);
+ INIT_LIST_HEAD(&report->certificates);
+
+ report->size = ALIGN(ipib->hdr.len, 8);
+ report->size += sizeof(struct ipl_rl_hdr);
+ report->size += sizeof(struct ipl_rb_components);
+ report->size += sizeof(struct ipl_rb_certificates);
+
+ return report;
+}
+
+void *ipl_report_finish(struct ipl_report *report)
+{
+ struct ipl_report_certificate *cert;
+ struct ipl_report_component *comp;
+ struct ipl_rb_certificates *certs;
+ struct ipl_parameter_block *ipib;
+ struct ipl_rb_components *comps;
+ struct ipl_rl_hdr *rl_hdr;
+ void *buf, *ptr;
+
+ buf = vzalloc(report->size);
+ if (!buf)
+ return ERR_PTR(-ENOMEM);
+ ptr = buf;
+
+ memcpy(ptr, report->ipib, report->ipib->hdr.len);
+ ipib = ptr;
+ if (ipl_secure_flag)
+ ipib->hdr.flags |= IPL_PL_FLAG_SIPL;
+ ipib->hdr.flags |= IPL_PL_FLAG_IPLSR;
+ ptr += report->ipib->hdr.len;
+ ptr = PTR_ALIGN(ptr, 8);
+
+ rl_hdr = ptr;
+ ptr += sizeof(*rl_hdr);
+
+ comps = ptr;
+ comps->rbt = IPL_RBT_COMPONENTS;
+ ptr += sizeof(*comps);
+ list_for_each_entry(comp, &report->components, list) {
+ memcpy(ptr, &comp->entry, sizeof(comp->entry));
+ ptr += sizeof(comp->entry);
+ }
+ comps->len = ptr - (void *)comps;
+
+ certs = ptr;
+ certs->rbt = IPL_RBT_CERTIFICATES;
+ ptr += sizeof(*certs);
+ list_for_each_entry(cert, &report->certificates, list) {
+ memcpy(ptr, &cert->entry, sizeof(cert->entry));
+ ptr += sizeof(cert->entry);
+ }
+ certs->len = ptr - (void *)certs;
+ rl_hdr->len = ptr - (void *)rl_hdr;
+
+ list_for_each_entry(cert, &report->certificates, list) {
+ memcpy(ptr, cert->key, cert->entry.len);
+ ptr += cert->entry.len;
+ }
+
+ BUG_ON(ptr > buf + report->size);
+ return buf;
+}
+
+int ipl_report_free(struct ipl_report *report)
+{
+ struct ipl_report_component *comp, *ncomp;
+ struct ipl_report_certificate *cert, *ncert;
+
+ list_for_each_entry_safe(comp, ncomp, &report->components, list)
+ vfree(comp);
+
+ list_for_each_entry_safe(cert, ncert, &report->certificates, list)
+ vfree(cert);
+
+ vfree(report);
+
+ return 0;
+}
+
+#endif
diff --git a/arch/s390/kernel/ipl_vmparm.c b/arch/s390/kernel/ipl_vmparm.c
new file mode 100644
index 0000000..af43535
--- /dev/null
+++ b/arch/s390/kernel/ipl_vmparm.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <asm/ebcdic.h>
+#include <asm/ipl.h>
+
+/* VM IPL PARM routines */
+size_t ipl_block_get_ascii_vmparm(char *dest, size_t size,
+ const struct ipl_parameter_block *ipb)
+{
+ int i;
+ size_t len;
+ char has_lowercase = 0;
+
+ len = 0;
+ if ((ipb->ccw.vm_flags & IPL_PB0_CCW_VM_FLAG_VP) &&
+ (ipb->ccw.vm_parm_len > 0)) {
+
+ len = min_t(size_t, size - 1, ipb->ccw.vm_parm_len);
+ memcpy(dest, ipb->ccw.vm_parm, len);
+ /* If at least one character is lowercase, we assume mixed
+ * case; otherwise we convert everything to lowercase.
+ */
+ for (i = 0; i < len; i++)
+ if ((dest[i] > 0x80 && dest[i] < 0x8a) || /* a-i */
+ (dest[i] > 0x90 && dest[i] < 0x9a) || /* j-r */
+ (dest[i] > 0xa1 && dest[i] < 0xaa)) { /* s-z */
+ has_lowercase = 1;
+ break;
+ }
+ if (!has_lowercase)
+ EBC_TOLOWER(dest, len);
+ EBCASC(dest, len);
+ }
+ dest[len] = 0;
+
+ return len;
+}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 3d17c41..8371855 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -26,6 +26,7 @@
#include <asm/lowcore.h>
#include <asm/irq.h>
#include <asm/hw_irq.h>
+#include <asm/stacktrace.h>
#include "entry.h"
DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
@@ -73,7 +74,6 @@
{.irq = IRQEXT_CMC, .name = "CMC", .desc = "[EXT] CPU-Measurement: Counter"},
{.irq = IRQEXT_FTP, .name = "FTP", .desc = "[EXT] HMC FTP Service"},
{.irq = IRQIO_CIO, .name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt"},
- {.irq = IRQIO_QAI, .name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt"},
{.irq = IRQIO_DAS, .name = "DAS", .desc = "[I/O] DASD"},
{.irq = IRQIO_C15, .name = "C15", .desc = "[I/O] 3215"},
{.irq = IRQIO_C70, .name = "C70", .desc = "[I/O] 3270"},
@@ -81,13 +81,16 @@
{.irq = IRQIO_VMR, .name = "VMR", .desc = "[I/O] Unit Record Devices"},
{.irq = IRQIO_LCS, .name = "LCS", .desc = "[I/O] LCS"},
{.irq = IRQIO_CTC, .name = "CTC", .desc = "[I/O] CTC"},
- {.irq = IRQIO_APB, .name = "APB", .desc = "[I/O] AP Bus"},
{.irq = IRQIO_ADM, .name = "ADM", .desc = "[I/O] EADM Subchannel"},
{.irq = IRQIO_CSC, .name = "CSC", .desc = "[I/O] CHSC Subchannel"},
- {.irq = IRQIO_PCI, .name = "PCI", .desc = "[I/O] PCI Interrupt" },
- {.irq = IRQIO_MSI, .name = "MSI", .desc = "[I/O] MSI Interrupt" },
{.irq = IRQIO_VIR, .name = "VIR", .desc = "[I/O] Virtual I/O Devices"},
- {.irq = IRQIO_VAI, .name = "VAI", .desc = "[I/O] Virtual I/O Devices AI"},
+ {.irq = IRQIO_QAI, .name = "QAI", .desc = "[AIO] QDIO Adapter Interrupt"},
+ {.irq = IRQIO_APB, .name = "APB", .desc = "[AIO] AP Bus"},
+ {.irq = IRQIO_PCF, .name = "PCF", .desc = "[AIO] PCI Floating Interrupt"},
+ {.irq = IRQIO_PCD, .name = "PCD", .desc = "[AIO] PCI Directed Interrupt"},
+ {.irq = IRQIO_MSI, .name = "MSI", .desc = "[AIO] MSI Interrupt"},
+ {.irq = IRQIO_VAI, .name = "VAI", .desc = "[AIO] Virtual I/O Devices AI"},
+ {.irq = IRQIO_GAL, .name = "GAL", .desc = "[AIO] GIB Alert"},
{.irq = NMI_NMI, .name = "NMI", .desc = "[NMI] Machine Check"},
{.irq = CPU_RST, .name = "RST", .desc = "[CPU] CPU Restart"},
};
@@ -115,6 +118,34 @@
set_irq_regs(old_regs);
}
+static void show_msi_interrupt(struct seq_file *p, int irq)
+{
+ struct irq_desc *desc;
+ unsigned long flags;
+ int cpu;
+
+ irq_lock_sparse();
+ desc = irq_to_desc(irq);
+ if (!desc)
+ goto out;
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+ seq_printf(p, "%3d: ", irq);
+ for_each_online_cpu(cpu)
+ seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+
+ if (desc->irq_data.chip)
+ seq_printf(p, " %8s", desc->irq_data.chip->name);
+
+ if (desc->action)
+ seq_printf(p, " %s", desc->action->name);
+
+ seq_putc(p, '\n');
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+out:
+ irq_unlock_sparse();
+}
+
/*
* show_interrupts is needed by /proc/interrupts.
*/
@@ -127,7 +158,7 @@
if (index == 0) {
seq_puts(p, " ");
for_each_online_cpu(cpu)
- seq_printf(p, "CPU%d ", cpu);
+ seq_printf(p, "CPU%-8d", cpu);
seq_putc(p, '\n');
}
if (index < NR_IRQS_BASE) {
@@ -138,9 +169,10 @@
seq_putc(p, '\n');
goto out;
}
- if (index > NR_IRQS_BASE)
+ if (index < nr_irqs) {
+ show_msi_interrupt(p, index);
goto out;
-
+ }
for (index = 0; index < NR_ARCH_IRQS; index++) {
seq_printf(p, "%s: ", irqclass_sub_desc[index].name);
irq = irqclass_sub_desc[index].irq;
@@ -172,15 +204,7 @@
/* Check against async. stack address range. */
new = S390_lowcore.async_stack;
if (((new - old) >> (PAGE_SHIFT + THREAD_SIZE_ORDER)) != 0) {
- /* Need to switch to the async. stack. */
- new -= STACK_FRAME_OVERHEAD;
- ((struct stack_frame *) new)->back_chain = old;
- asm volatile(" la 15,0(%0)\n"
- " brasl 14,__do_softirq\n"
- " la 15,0(%1)\n"
- : : "a" (new), "a" (old)
- : "0", "1", "2", "3", "4", "5", "14",
- "cc", "memory" );
+ CALL_ON_STACK(__do_softirq, new, 0);
} else {
/* We are already on the async stack. */
__do_softirq();
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index 43f8430..ab584e8 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -10,36 +10,29 @@
#include <linux/jump_label.h>
#include <asm/ipl.h>
-#ifdef HAVE_JUMP_LABEL
-
struct insn {
u16 opcode;
s32 offset;
} __packed;
-struct insn_args {
- struct jump_entry *entry;
- enum jump_label_type type;
-};
-
static void jump_label_make_nop(struct jump_entry *entry, struct insn *insn)
{
- /* brcl 0,0 */
+ /* brcl 0,offset */
insn->opcode = 0xc004;
- insn->offset = 0;
+ insn->offset = (jump_entry_target(entry) - jump_entry_code(entry)) >> 1;
}
static void jump_label_make_branch(struct jump_entry *entry, struct insn *insn)
{
/* brcl 15,offset */
insn->opcode = 0xc0f4;
- insn->offset = (entry->target - entry->code) >> 1;
+ insn->offset = (jump_entry_target(entry) - jump_entry_code(entry)) >> 1;
}
static void jump_label_bug(struct jump_entry *entry, struct insn *expected,
struct insn *new)
{
- unsigned char *ipc = (unsigned char *)entry->code;
+ unsigned char *ipc = (unsigned char *)jump_entry_code(entry);
unsigned char *ipe = (unsigned char *)expected;
unsigned char *ipn = (unsigned char *)new;
@@ -59,6 +52,7 @@
enum jump_label_type type,
int init)
{
+ void *code = (void *)jump_entry_code(entry);
struct insn old, new;
if (type == JUMP_LABEL_JMP) {
@@ -69,32 +63,24 @@
jump_label_make_nop(entry, &new);
}
if (init) {
- if (memcmp((void *)entry->code, &orignop, sizeof(orignop)))
+ if (memcmp(code, &orignop, sizeof(orignop)))
jump_label_bug(entry, &orignop, &new);
} else {
- if (memcmp((void *)entry->code, &old, sizeof(old)))
+ if (memcmp(code, &old, sizeof(old)))
jump_label_bug(entry, &old, &new);
}
- s390_kernel_write((void *)entry->code, &new, sizeof(new));
+ s390_kernel_write(code, &new, sizeof(new));
}
-static int __sm_arch_jump_label_transform(void *data)
+static void __jump_label_sync(void *dummy)
{
- struct insn_args *args = data;
-
- __jump_label_transform(args->entry, args->type, 0);
- return 0;
}
void arch_jump_label_transform(struct jump_entry *entry,
enum jump_label_type type)
{
- struct insn_args args;
-
- args.entry = entry;
- args.type = type;
-
- stop_machine_cpuslocked(__sm_arch_jump_label_transform, &args, NULL);
+ __jump_label_transform(entry, type, 0);
+ smp_call_function(__jump_label_sync, NULL, 1);
}
void arch_jump_label_transform_static(struct jump_entry *entry,
@@ -102,5 +88,3 @@
{
__jump_label_transform(entry, type, 1);
}
-
-#endif
diff --git a/arch/s390/kernel/kdebugfs.c b/arch/s390/kernel/kdebugfs.c
index 2c46bd6..33130c7 100644
--- a/arch/s390/kernel/kdebugfs.c
+++ b/arch/s390/kernel/kdebugfs.c
@@ -9,8 +9,6 @@
static int __init arch_kdebugfs_init(void)
{
arch_debugfs_dir = debugfs_create_dir("s390", NULL);
- if (IS_ERR(arch_debugfs_dir))
- arch_debugfs_dir = NULL;
return 0;
}
postcore_initcall(arch_kdebugfs_init);
diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
index 5a286b0..9da6fa3 100644
--- a/arch/s390/kernel/kexec_elf.c
+++ b/arch/s390/kernel/kexec_elf.c
@@ -10,19 +10,26 @@
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
+#include <asm/ipl.h>
#include <asm/setup.h>
-static int kexec_file_add_elf_kernel(struct kimage *image,
- struct s390_load_data *data,
- char *kernel, unsigned long kernel_len)
+static int kexec_file_add_kernel_elf(struct kimage *image,
+ struct s390_load_data *data)
{
struct kexec_buf buf;
const Elf_Ehdr *ehdr;
const Elf_Phdr *phdr;
+ Elf_Addr entry;
+ void *kernel;
int i, ret;
+ kernel = image->kernel_buf;
ehdr = (Elf_Ehdr *)kernel;
buf.image = image;
+ if (image->type == KEXEC_TYPE_CRASH)
+ entry = STARTUP_KDUMP_OFFSET;
+ else
+ entry = ehdr->e_entry;
phdr = (void *)ehdr + ehdr->e_phoff;
for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
@@ -33,30 +40,27 @@
buf.bufsz = phdr->p_filesz;
buf.mem = ALIGN(phdr->p_paddr, phdr->p_align);
- buf.memsz = phdr->p_memsz;
-
- if (phdr->p_paddr == 0) {
- data->kernel_buf = buf.buffer;
- data->memsz += STARTUP_NORMAL_OFFSET;
-
- buf.buffer += STARTUP_NORMAL_OFFSET;
- buf.bufsz -= STARTUP_NORMAL_OFFSET;
-
- buf.mem += STARTUP_NORMAL_OFFSET;
- buf.memsz -= STARTUP_NORMAL_OFFSET;
- }
-
if (image->type == KEXEC_TYPE_CRASH)
buf.mem += crashk_res.start;
+ buf.memsz = phdr->p_memsz;
+ data->memsz = ALIGN(data->memsz, phdr->p_align) + buf.memsz;
+ if (entry - phdr->p_paddr < phdr->p_memsz) {
+ data->kernel_buf = buf.buffer;
+ data->kernel_mem = buf.mem;
+ data->parm = buf.buffer + PARMAREA;
+ }
+
+ ipl_report_add_component(data->report, &buf,
+ IPL_RB_COMPONENT_FLAG_SIGNED |
+ IPL_RB_COMPONENT_FLAG_VERIFIED,
+ IPL_RB_CERT_UNKNOWN);
ret = kexec_add_buffer(&buf);
if (ret)
return ret;
-
- data->memsz += buf.memsz;
}
- return 0;
+ return data->memsz ? 0 : -EINVAL;
}
static void *s390_elf_load(struct kimage *image,
@@ -64,11 +68,10 @@
char *initrd, unsigned long initrd_len,
char *cmdline, unsigned long cmdline_len)
{
- struct s390_load_data data = {0};
const Elf_Ehdr *ehdr;
const Elf_Phdr *phdr;
size_t size;
- int i, ret;
+ int i;
/* image->fobs->probe already checked for valid ELF magic number. */
ehdr = (Elf_Ehdr *)kernel;
@@ -101,24 +104,7 @@
if (size > kernel_len)
return ERR_PTR(-EINVAL);
- ret = kexec_file_add_elf_kernel(image, &data, kernel, kernel_len);
- if (ret)
- return ERR_PTR(ret);
-
- if (!data.memsz)
- return ERR_PTR(-EINVAL);
-
- if (initrd) {
- ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
- if (ret)
- return ERR_PTR(ret);
- }
-
- ret = kexec_file_add_purgatory(image, &data);
- if (ret)
- return ERR_PTR(ret);
-
- return kexec_file_update_kernel(image, &data);
+ return kexec_file_add_components(image, kexec_file_add_kernel_elf);
}
static int s390_elf_probe(const char *buf, unsigned long len)
@@ -144,4 +130,7 @@
const struct kexec_file_ops s390_kexec_elf_ops = {
.probe = s390_elf_probe,
.load = s390_elf_load,
+#ifdef CONFIG_KEXEC_SIG
+ .verify_sig = s390_verify_sig,
+#endif /* CONFIG_KEXEC_SIG */
};
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
index 3800852..af23eff 100644
--- a/arch/s390/kernel/kexec_image.c
+++ b/arch/s390/kernel/kexec_image.c
@@ -10,31 +10,34 @@
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
+#include <asm/ipl.h>
#include <asm/setup.h>
-static int kexec_file_add_image_kernel(struct kimage *image,
- struct s390_load_data *data,
- char *kernel, unsigned long kernel_len)
+static int kexec_file_add_kernel_image(struct kimage *image,
+ struct s390_load_data *data)
{
struct kexec_buf buf;
- int ret;
buf.image = image;
- buf.buffer = kernel + STARTUP_NORMAL_OFFSET;
- buf.bufsz = kernel_len - STARTUP_NORMAL_OFFSET;
+ buf.buffer = image->kernel_buf;
+ buf.bufsz = image->kernel_buf_len;
- buf.mem = STARTUP_NORMAL_OFFSET;
+ buf.mem = 0;
if (image->type == KEXEC_TYPE_CRASH)
buf.mem += crashk_res.start;
buf.memsz = buf.bufsz;
- ret = kexec_add_buffer(&buf);
+ data->kernel_buf = image->kernel_buf;
+ data->kernel_mem = buf.mem;
+ data->parm = image->kernel_buf + PARMAREA;
+ data->memsz += buf.memsz;
- data->kernel_buf = kernel;
- data->memsz += buf.memsz + STARTUP_NORMAL_OFFSET;
-
- return ret;
+ ipl_report_add_component(data->report, &buf,
+ IPL_RB_COMPONENT_FLAG_SIGNED |
+ IPL_RB_COMPONENT_FLAG_VERIFIED,
+ IPL_RB_CERT_UNKNOWN);
+ return kexec_add_buffer(&buf);
}
static void *s390_image_load(struct kimage *image,
@@ -42,24 +45,7 @@
char *initrd, unsigned long initrd_len,
char *cmdline, unsigned long cmdline_len)
{
- struct s390_load_data data = {0};
- int ret;
-
- ret = kexec_file_add_image_kernel(image, &data, kernel, kernel_len);
- if (ret)
- return ERR_PTR(ret);
-
- if (initrd) {
- ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
- if (ret)
- return ERR_PTR(ret);
- }
-
- ret = kexec_file_add_purgatory(image, &data);
- if (ret)
- return ERR_PTR(ret);
-
- return kexec_file_update_kernel(image, &data);
+ return kexec_file_add_components(image, kexec_file_add_kernel_image);
}
static int s390_image_probe(const char *buf, unsigned long len)
@@ -73,4 +59,7 @@
const struct kexec_file_ops s390_kexec_image_ops = {
.probe = s390_image_probe,
.load = s390_image_load,
+#ifdef CONFIG_KEXEC_SIG
+ .verify_sig = s390_verify_sig,
+#endif /* CONFIG_KEXEC_SIG */
};
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 7c0a095..6f13883 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -27,29 +27,30 @@
struct kretprobe_blackpoint kretprobe_blacklist[] = { };
-DEFINE_INSN_CACHE_OPS(dmainsn);
+DEFINE_INSN_CACHE_OPS(s390_insn);
-static void *alloc_dmainsn_page(void)
+static int insn_page_in_use;
+static char insn_page[PAGE_SIZE] __aligned(PAGE_SIZE);
+
+static void *alloc_s390_insn_page(void)
{
- void *page;
-
- page = (void *) __get_free_page(GFP_KERNEL | GFP_DMA);
- if (page)
- set_memory_x((unsigned long) page, 1);
- return page;
+ if (xchg(&insn_page_in_use, 1) == 1)
+ return NULL;
+ set_memory_x((unsigned long) &insn_page, 1);
+ return &insn_page;
}
-static void free_dmainsn_page(void *page)
+static void free_s390_insn_page(void *page)
{
set_memory_nx((unsigned long) page, 1);
- free_page((unsigned long)page);
+ xchg(&insn_page_in_use, 0);
}
-struct kprobe_insn_cache kprobe_dmainsn_slots = {
- .mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex),
- .alloc = alloc_dmainsn_page,
- .free = free_dmainsn_page,
- .pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages),
+struct kprobe_insn_cache kprobe_s390_insn_slots = {
+ .mutex = __MUTEX_INITIALIZER(kprobe_s390_insn_slots.mutex),
+ .alloc = alloc_s390_insn_page,
+ .free = free_s390_insn_page,
+ .pages = LIST_HEAD_INIT(kprobe_s390_insn_slots.pages),
.insn_size = MAX_INSN_SIZE,
};
@@ -102,7 +103,7 @@
*/
p->ainsn.insn = NULL;
if (is_kernel_addr(p->addr))
- p->ainsn.insn = get_dmainsn_slot();
+ p->ainsn.insn = get_s390_insn_slot();
else if (is_module_addr(p->addr))
p->ainsn.insn = get_insn_slot();
return p->ainsn.insn ? 0 : -ENOMEM;
@@ -114,7 +115,7 @@
if (!p->ainsn.insn)
return;
if (is_kernel_addr(p->addr))
- free_dmainsn_slot(p->ainsn.insn, 0);
+ free_s390_insn_slot(p->ainsn.insn, 0);
else
free_insn_slot(p->ainsn.insn, 0);
p->ainsn.insn = NULL;
@@ -572,7 +573,7 @@
* In case the user-specified fault handler returned
* zero, try to fix up.
*/
- entry = search_exception_tables(regs->psw.addr);
+ entry = s390_search_extables(regs->psw.addr);
if (entry) {
regs->psw.addr = extable_fixup(entry);
return 1;
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index b7020e7..444a191 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -27,6 +27,7 @@
#include <asm/cacheflush.h>
#include <asm/os_info.h>
#include <asm/set_memory.h>
+#include <asm/stacktrace.h>
#include <asm/switch_to.h>
#include <asm/nmi.h>
@@ -95,7 +96,7 @@
start_kdump(1);
/* Die if start_kdump returns */
- disabled_wait((unsigned long) __builtin_return_address(0));
+ disabled_wait();
}
/*
@@ -140,7 +141,20 @@
*/
store_status(__do_machine_kdump, image);
}
-#endif
+
+static unsigned long do_start_kdump(unsigned long addr)
+{
+ struct kimage *image = (struct kimage *) addr;
+ int (*start_kdump)(int) = (void *)image->start;
+ int rc;
+
+ __arch_local_irq_stnsm(0xfb); /* disable DAT */
+ rc = start_kdump(0);
+ __arch_local_irq_stosm(0x04); /* enable DAT */
+ return rc;
+}
+
+#endif /* CONFIG_CRASH_DUMP */
/*
* Check if kdump checksums are valid: We call purgatory with parameter "0"
@@ -148,12 +162,9 @@
static bool kdump_csum_valid(struct kimage *image)
{
#ifdef CONFIG_CRASH_DUMP
- int (*start_kdump)(int) = (void *)image->start;
int rc;
- __arch_local_irq_stnsm(0xfb); /* disable DAT */
- rc = start_kdump(0);
- __arch_local_irq_stosm(0x04); /* enable DAT */
+ rc = CALL_ON_STACK(do_start_kdump, S390_lowcore.nodat_stack, 1, image);
return rc == 0;
#else
return false;
@@ -244,6 +255,9 @@
VMCOREINFO_SYMBOL(high_memory);
VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
+ vmcoreinfo_append_str("SDMA=%lx\n", __sdma);
+ vmcoreinfo_append_str("EDMA=%lx\n", __edma);
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
}
void machine_shutdown(void)
@@ -271,7 +285,7 @@
(*data_mover)(&image->head, image->start);
/* Die if kexec returns */
- disabled_wait((unsigned long) __builtin_return_address(0));
+ disabled_wait();
}
/*
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index f413f57..8415ae7 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -8,7 +8,12 @@
*/
#include <linux/elf.h>
+#include <linux/errno.h>
#include <linux/kexec.h>
+#include <linux/module_signature.h>
+#include <linux/verification.h>
+#include <asm/boot_data.h>
+#include <asm/ipl.h>
#include <asm/setup.h>
const struct kexec_file_ops * const kexec_file_loaders[] = {
@@ -17,38 +22,56 @@
NULL,
};
-int *kexec_file_update_kernel(struct kimage *image,
- struct s390_load_data *data)
+#ifdef CONFIG_KEXEC_SIG
+int s390_verify_sig(const char *kernel, unsigned long kernel_len)
{
- unsigned long *loc;
+ const unsigned long marker_len = sizeof(MODULE_SIG_STRING) - 1;
+ struct module_signature *ms;
+ unsigned long sig_len;
- if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE)
- return ERR_PTR(-EINVAL);
+ /* Skip signature verification when not secure IPLed. */
+ if (!ipl_secure_flag)
+ return 0;
- if (image->cmdline_buf_len)
- memcpy(data->kernel_buf + COMMAND_LINE_OFFSET,
- image->cmdline_buf, image->cmdline_buf_len);
+ if (marker_len > kernel_len)
+ return -EKEYREJECTED;
- if (image->type == KEXEC_TYPE_CRASH) {
- loc = (unsigned long *)(data->kernel_buf + OLDMEM_BASE_OFFSET);
- *loc = crashk_res.start;
+ if (memcmp(kernel + kernel_len - marker_len, MODULE_SIG_STRING,
+ marker_len))
+ return -EKEYREJECTED;
+ kernel_len -= marker_len;
- loc = (unsigned long *)(data->kernel_buf + OLDMEM_SIZE_OFFSET);
- *loc = crashk_res.end - crashk_res.start + 1;
+ ms = (void *)kernel + kernel_len - sizeof(*ms);
+ kernel_len -= sizeof(*ms);
+
+ sig_len = be32_to_cpu(ms->sig_len);
+ if (sig_len >= kernel_len)
+ return -EKEYREJECTED;
+ kernel_len -= sig_len;
+
+ if (ms->id_type != PKEY_ID_PKCS7)
+ return -EKEYREJECTED;
+
+ if (ms->algo != 0 ||
+ ms->hash != 0 ||
+ ms->signer_len != 0 ||
+ ms->key_id_len != 0 ||
+ ms->__pad[0] != 0 ||
+ ms->__pad[1] != 0 ||
+ ms->__pad[2] != 0) {
+ return -EBADMSG;
}
- if (image->initrd_buf) {
- loc = (unsigned long *)(data->kernel_buf + INITRD_START_OFFSET);
- *loc = data->initrd_load_addr;
-
- loc = (unsigned long *)(data->kernel_buf + INITRD_SIZE_OFFSET);
- *loc = image->initrd_buf_len;
- }
-
- return NULL;
+ return verify_pkcs7_signature(kernel, kernel_len,
+ kernel + kernel_len, sig_len,
+ VERIFY_USE_PLATFORM_KEYRING,
+ VERIFYING_MODULE_SIGNATURE,
+ NULL, NULL);
}
+#endif /* CONFIG_KEXEC_SIG */
-static int kexec_file_update_purgatory(struct kimage *image)
+static int kexec_file_update_purgatory(struct kimage *image,
+ struct s390_load_data *data)
{
u64 entry, type;
int ret;
@@ -90,7 +113,8 @@
return ret;
}
-int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data)
+static int kexec_file_add_purgatory(struct kimage *image,
+ struct s390_load_data *data)
{
struct kexec_buf buf;
int ret;
@@ -105,21 +129,21 @@
ret = kexec_load_purgatory(image, &buf);
if (ret)
return ret;
+ data->memsz += buf.memsz;
- ret = kexec_file_update_purgatory(image);
- return ret;
+ return kexec_file_update_purgatory(image, data);
}
-int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data,
- char *initrd, unsigned long initrd_len)
+static int kexec_file_add_initrd(struct kimage *image,
+ struct s390_load_data *data)
{
struct kexec_buf buf;
int ret;
buf.image = image;
- buf.buffer = initrd;
- buf.bufsz = initrd_len;
+ buf.buffer = image->initrd_buf;
+ buf.bufsz = image->initrd_buf_len;
data->memsz = ALIGN(data->memsz, PAGE_SIZE);
buf.mem = data->memsz;
@@ -127,21 +151,115 @@
buf.mem += crashk_res.start;
buf.memsz = buf.bufsz;
- data->initrd_load_addr = buf.mem;
+ data->parm->initrd_start = buf.mem;
+ data->parm->initrd_size = buf.memsz;
data->memsz += buf.memsz;
ret = kexec_add_buffer(&buf);
- return ret;
+ if (ret)
+ return ret;
+
+ return ipl_report_add_component(data->report, &buf, 0, 0);
}
-/*
- * The kernel is loaded to a fixed location. Turn off kexec_locate_mem_hole
- * and provide kbuf->mem by hand.
- */
-int arch_kexec_walk_mem(struct kexec_buf *kbuf,
- int (*func)(struct resource *, void *))
+static int kexec_file_add_ipl_report(struct kimage *image,
+ struct s390_load_data *data)
{
- return 1;
+ __u32 *lc_ipl_parmblock_ptr;
+ unsigned int len, ncerts;
+ struct kexec_buf buf;
+ unsigned long addr;
+ void *ptr, *end;
+
+ buf.image = image;
+
+ data->memsz = ALIGN(data->memsz, PAGE_SIZE);
+ buf.mem = data->memsz;
+ if (image->type == KEXEC_TYPE_CRASH)
+ buf.mem += crashk_res.start;
+
+ ptr = (void *)ipl_cert_list_addr;
+ end = ptr + ipl_cert_list_size;
+ ncerts = 0;
+ while (ptr < end) {
+ ncerts++;
+ len = *(unsigned int *)ptr;
+ ptr += sizeof(len);
+ ptr += len;
+ }
+
+ addr = data->memsz + data->report->size;
+ addr += ncerts * sizeof(struct ipl_rb_certificate_entry);
+ ptr = (void *)ipl_cert_list_addr;
+ while (ptr < end) {
+ len = *(unsigned int *)ptr;
+ ptr += sizeof(len);
+ ipl_report_add_certificate(data->report, ptr, addr, len);
+ addr += len;
+ ptr += len;
+ }
+
+ buf.buffer = ipl_report_finish(data->report);
+ buf.bufsz = data->report->size;
+ buf.memsz = buf.bufsz;
+
+ data->memsz += buf.memsz;
+
+ lc_ipl_parmblock_ptr =
+ data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
+ *lc_ipl_parmblock_ptr = (__u32)buf.mem;
+
+ return kexec_add_buffer(&buf);
+}
+
+void *kexec_file_add_components(struct kimage *image,
+ int (*add_kernel)(struct kimage *image,
+ struct s390_load_data *data))
+{
+ struct s390_load_data data = {0};
+ int ret;
+
+ data.report = ipl_report_init(&ipl_block);
+ if (IS_ERR(data.report))
+ return data.report;
+
+ ret = add_kernel(image, &data);
+ if (ret)
+ goto out;
+
+ if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE) {
+ ret = -EINVAL;
+ goto out;
+ }
+ memcpy(data.parm->command_line, image->cmdline_buf,
+ image->cmdline_buf_len);
+
+ if (image->type == KEXEC_TYPE_CRASH) {
+ data.parm->oldmem_base = crashk_res.start;
+ data.parm->oldmem_size = crashk_res.end - crashk_res.start + 1;
+ }
+
+ if (image->initrd_buf) {
+ ret = kexec_file_add_initrd(image, &data);
+ if (ret)
+ goto out;
+ }
+
+ ret = kexec_file_add_purgatory(image, &data);
+ if (ret)
+ goto out;
+
+ if (data.kernel_mem == 0) {
+ unsigned long restart_psw = 0x0008000080000000UL;
+ restart_psw += image->start;
+ memcpy(data.kernel_buf, &restart_psw, sizeof(restart_psw));
+ image->start = 0;
+ }
+
+ ret = kexec_file_add_ipl_report(image, &data);
+out:
+ ipl_report_free(data.report);
+ return ERR_PTR(ret);
}
int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
@@ -150,7 +268,7 @@
const Elf_Shdr *symtab)
{
Elf_Rela *relas;
- int i;
+ int i, r_type;
relas = (void *)pi->ehdr + relsec->sh_offset;
@@ -184,46 +302,8 @@
addr = section->sh_addr + relas[i].r_offset;
- switch (ELF64_R_TYPE(relas[i].r_info)) {
- case R_390_8: /* Direct 8 bit. */
- *(u8 *)loc = val;
- break;
- case R_390_12: /* Direct 12 bit. */
- *(u16 *)loc &= 0xf000;
- *(u16 *)loc |= val & 0xfff;
- break;
- case R_390_16: /* Direct 16 bit. */
- *(u16 *)loc = val;
- break;
- case R_390_20: /* Direct 20 bit. */
- *(u32 *)loc &= 0xf00000ff;
- *(u32 *)loc |= (val & 0xfff) << 16; /* DL */
- *(u32 *)loc |= (val & 0xff000) >> 4; /* DH */
- break;
- case R_390_32: /* Direct 32 bit. */
- *(u32 *)loc = val;
- break;
- case R_390_64: /* Direct 64 bit. */
- *(u64 *)loc = val;
- break;
- case R_390_PC16: /* PC relative 16 bit. */
- *(u16 *)loc = (val - addr);
- break;
- case R_390_PC16DBL: /* PC relative 16 bit shifted by 1. */
- *(u16 *)loc = (val - addr) >> 1;
- break;
- case R_390_PC32DBL: /* PC relative 32 bit shifted by 1. */
- *(u32 *)loc = (val - addr) >> 1;
- break;
- case R_390_PC32: /* PC relative 32 bit. */
- *(u32 *)loc = (val - addr);
- break;
- case R_390_PC64: /* PC relative 64 bit. */
- *(u64 *)loc = (val - addr);
- break;
- default:
- break;
- }
+ r_type = ELF64_R_TYPE(relas[i].r_info);
+ arch_kexec_do_relocs(r_type, loc, val, addr);
}
return 0;
}
@@ -235,10 +315,8 @@
* load memory in head.S will be accessed, e.g. to register the next
* command line. If the next kernel were smaller the current kernel
* will panic at load.
- *
- * 0x11000 = sizeof(head.S)
*/
- if (buf_len < 0x11000)
+ if (buf_len < HEAD_END)
return -ENOEXEC;
return kexec_image_probe_default(image, buf, buf_len);
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
new file mode 100644
index 0000000..d5035de
--- /dev/null
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/elf.h>
+#include <asm/kexec.h>
+
+int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
+ unsigned long addr)
+{
+ switch (r_type) {
+ case R_390_NONE:
+ break;
+ case R_390_8: /* Direct 8 bit. */
+ *(u8 *)loc = val;
+ break;
+ case R_390_12: /* Direct 12 bit. */
+ *(u16 *)loc &= 0xf000;
+ *(u16 *)loc |= val & 0xfff;
+ break;
+ case R_390_16: /* Direct 16 bit. */
+ *(u16 *)loc = val;
+ break;
+ case R_390_20: /* Direct 20 bit. */
+ *(u32 *)loc &= 0xf00000ff;
+ *(u32 *)loc |= (val & 0xfff) << 16; /* DL */
+ *(u32 *)loc |= (val & 0xff000) >> 4; /* DH */
+ break;
+ case R_390_32: /* Direct 32 bit. */
+ *(u32 *)loc = val;
+ break;
+ case R_390_64: /* Direct 64 bit. */
+ case R_390_GLOB_DAT:
+ *(u64 *)loc = val;
+ break;
+ case R_390_PC16: /* PC relative 16 bit. */
+ *(u16 *)loc = (val - addr);
+ break;
+ case R_390_PC16DBL: /* PC relative 16 bit shifted by 1. */
+ *(u16 *)loc = (val - addr) >> 1;
+ break;
+ case R_390_PC32DBL: /* PC relative 32 bit shifted by 1. */
+ *(u32 *)loc = (val - addr) >> 1;
+ break;
+ case R_390_PC32: /* PC relative 32 bit. */
+ *(u32 *)loc = (val - addr);
+ break;
+ case R_390_PC64: /* PC relative 64 bit. */
+ *(u64 *)loc = (val - addr);
+ break;
+ case R_390_RELATIVE:
+ *(unsigned long *) loc = val;
+ break;
+ default:
+ return 1;
+ }
+ return 0;
+}
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index e93fbf0..9e1660a 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -20,6 +20,7 @@
ENTRY(ftrace_stub)
BR_EX %r14
+ENDPROC(ftrace_stub)
#define STACK_FRAME_SIZE (STACK_FRAME_OVERHEAD + __PT_SIZE)
#define STACK_PTREGS (STACK_FRAME_OVERHEAD)
@@ -28,7 +29,7 @@
ENTRY(_mcount)
BR_EX %r14
-
+ENDPROC(_mcount)
EXPORT_SYMBOL(_mcount)
ENTRY(ftrace_caller)
@@ -61,10 +62,11 @@
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
# The j instruction gets runtime patched to a nop instruction.
# See ftrace_enable_ftrace_graph_caller.
-ENTRY(ftrace_graph_caller)
+ .globl ftrace_graph_caller
+ftrace_graph_caller:
j ftrace_graph_caller_end
- lg %r2,(STACK_PTREGS_GPRS+14*8)(%r15)
- lg %r3,(STACK_PTREGS_PSW+8)(%r15)
+ lmg %r2,%r3,(STACK_PTREGS_GPRS+14*8)(%r15)
+ lg %r4,(STACK_PTREGS_PSW+8)(%r15)
brasl %r14,prepare_ftrace_return
stg %r2,(STACK_PTREGS_GPRS+14*8)(%r15)
ftrace_graph_caller_end:
@@ -73,6 +75,7 @@
lg %r1,(STACK_PTREGS_PSW+8)(%r15)
lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
BR_EX %r1
+ENDPROC(ftrace_caller)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -86,5 +89,6 @@
lgr %r14,%r2
lmg %r2,%r5,32(%r15)
BR_EX %r14
+ENDPROC(return_to_handler)
#endif
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index d298d3c..ba8f19b 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -16,6 +16,7 @@
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/kernel.h>
+#include <linux/kasan.h>
#include <linux/moduleloader.h>
#include <linux/bug.h>
#include <asm/alternative.h>
@@ -32,12 +33,18 @@
void *module_alloc(unsigned long size)
{
+ void *p;
+
if (PAGE_ALIGN(size) > MODULES_LEN)
return NULL;
- return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
- GFP_KERNEL, PAGE_KERNEL_EXEC,
- 0, NUMA_NO_NODE,
- __builtin_return_address(0));
+ p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END,
+ GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+ __builtin_return_address(0));
+ if (p && (kasan_module_alloc(p, size) < 0)) {
+ vfree(p);
+ return NULL;
+ }
+ return p;
}
void module_arch_freeing_init(struct module *mod)
@@ -465,11 +472,11 @@
apply_alternatives(aseg, aseg + s->sh_size);
if (IS_ENABLED(CONFIG_EXPOLINE) &&
- (!strncmp(".s390_indirect", secname, 14)))
+ (str_has_prefix(secname, ".s390_indirect")))
nospec_revert(aseg, aseg + s->sh_size);
if (IS_ENABLED(CONFIG_EXPOLINE) &&
- (!strncmp(".s390_return", secname, 12)))
+ (str_has_prefix(secname, ".s390_return")))
nospec_revert(aseg, aseg + s->sh_size);
}
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 8c867b4..0a487fa 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -125,7 +125,7 @@
static notrace void s390_handle_damage(void)
{
smp_emergency_stop();
- disabled_wait((unsigned long) __builtin_return_address(0));
+ disabled_wait();
while (1);
}
NOKPROBE_SYMBOL(s390_handle_damage);
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index bdddaae..29e511f 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/cpu.h>
#include <asm/nospec-branch.h>
static int __init nobp_setup_early(char *str)
@@ -37,7 +38,7 @@
{
if (test_facility(156))
pr_info("Spectre V2 mitigation: etokens\n");
- if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+ if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable)
pr_info("Spectre V2 mitigation: execute trampolines\n");
if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
pr_info("Spectre V2 mitigation: limited branch prediction\n");
@@ -58,15 +59,15 @@
void __init nospec_auto_detect(void)
{
- if (test_facility(156)) {
+ if (test_facility(156) || cpu_mitigations_off()) {
/*
* The machine supports etokens.
* Disable expolines and disable nobp.
*/
- if (IS_ENABLED(CC_USING_EXPOLINE))
+ if (__is_defined(CC_USING_EXPOLINE))
nospec_disable = 1;
__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
- } else if (IS_ENABLED(CC_USING_EXPOLINE)) {
+ } else if (__is_defined(CC_USING_EXPOLINE)) {
/*
* The kernel has been compiled with expolines.
* Keep expolines enabled and disable nobp.
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
index e30e580..48f472b 100644
--- a/arch/s390/kernel/nospec-sysfs.c
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -15,7 +15,7 @@
{
if (test_facility(156))
return sprintf(buf, "Mitigation: etokens\n");
- if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+ if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable)
return sprintf(buf, "Mitigation: execute trampolines\n");
if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
return sprintf(buf, "Mitigation: limited branch prediction\n");
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index d5523ad..48d48b6 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -2,81 +2,19 @@
/*
* Performance event support for s390x - CPU-measurement Counter Facility
*
- * Copyright IBM Corp. 2012, 2017
- * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ * Copyright IBM Corp. 2012, 2019
+ * Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
*/
#define KMSG_COMPONENT "cpum_cf"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/kernel.h>
#include <linux/kernel_stat.h>
-#include <linux/perf_event.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/init.h>
#include <linux/export.h>
-#include <asm/ctl_reg.h>
-#include <asm/irq.h>
-#include <asm/cpu_mf.h>
-
-enum cpumf_ctr_set {
- CPUMF_CTR_SET_BASIC = 0, /* Basic Counter Set */
- CPUMF_CTR_SET_USER = 1, /* Problem-State Counter Set */
- CPUMF_CTR_SET_CRYPTO = 2, /* Crypto-Activity Counter Set */
- CPUMF_CTR_SET_EXT = 3, /* Extended Counter Set */
- CPUMF_CTR_SET_MT_DIAG = 4, /* MT-diagnostic Counter Set */
-
- /* Maximum number of counter sets */
- CPUMF_CTR_SET_MAX,
-};
-
-#define CPUMF_LCCTL_ENABLE_SHIFT 16
-#define CPUMF_LCCTL_ACTCTL_SHIFT 0
-static const u64 cpumf_state_ctl[CPUMF_CTR_SET_MAX] = {
- [CPUMF_CTR_SET_BASIC] = 0x02,
- [CPUMF_CTR_SET_USER] = 0x04,
- [CPUMF_CTR_SET_CRYPTO] = 0x08,
- [CPUMF_CTR_SET_EXT] = 0x01,
- [CPUMF_CTR_SET_MT_DIAG] = 0x20,
-};
-
-static void ctr_set_enable(u64 *state, int ctr_set)
-{
- *state |= cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT;
-}
-static void ctr_set_disable(u64 *state, int ctr_set)
-{
- *state &= ~(cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT);
-}
-static void ctr_set_start(u64 *state, int ctr_set)
-{
- *state |= cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT;
-}
-static void ctr_set_stop(u64 *state, int ctr_set)
-{
- *state &= ~(cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT);
-}
-
-/* Local CPUMF event structure */
-struct cpu_hw_events {
- struct cpumf_ctr_info info;
- atomic_t ctr_set[CPUMF_CTR_SET_MAX];
- u64 state, tx_state;
- unsigned int flags;
- unsigned int txn_flags;
-};
-static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
- .ctr_set = {
- [CPUMF_CTR_SET_BASIC] = ATOMIC_INIT(0),
- [CPUMF_CTR_SET_USER] = ATOMIC_INIT(0),
- [CPUMF_CTR_SET_CRYPTO] = ATOMIC_INIT(0),
- [CPUMF_CTR_SET_EXT] = ATOMIC_INIT(0),
- [CPUMF_CTR_SET_MT_DIAG] = ATOMIC_INIT(0),
- },
- .state = 0,
- .flags = 0,
- .txn_flags = 0,
-};
+#include <asm/cpu_mcf.h>
static enum cpumf_ctr_set get_counter_set(u64 event)
{
@@ -88,7 +26,7 @@
set = CPUMF_CTR_SET_USER;
else if (event < 128)
set = CPUMF_CTR_SET_CRYPTO;
- else if (event < 256)
+ else if (event < 288)
set = CPUMF_CTR_SET_EXT;
else if (event >= 448 && event < 496)
set = CPUMF_CTR_SET_MT_DIAG;
@@ -98,11 +36,11 @@
static int validate_ctr_version(const struct hw_perf_event *hwc)
{
- struct cpu_hw_events *cpuhw;
+ struct cpu_cf_events *cpuhw;
int err = 0;
u16 mtdiag_ctl;
- cpuhw = &get_cpu_var(cpu_hw_events);
+ cpuhw = &get_cpu_var(cpu_cf_events);
/* check required version for counter sets */
switch (hwc->config_base) {
@@ -112,12 +50,19 @@
err = -EOPNOTSUPP;
break;
case CPUMF_CTR_SET_CRYPTO:
+ if ((cpuhw->info.csvn >= 1 && cpuhw->info.csvn <= 5 &&
+ hwc->config > 79) ||
+ (cpuhw->info.csvn >= 6 && hwc->config > 83))
+ err = -EOPNOTSUPP;
+ break;
case CPUMF_CTR_SET_EXT:
if (cpuhw->info.csvn < 1)
err = -EOPNOTSUPP;
if ((cpuhw->info.csvn == 1 && hwc->config > 159) ||
(cpuhw->info.csvn == 2 && hwc->config > 175) ||
- (cpuhw->info.csvn > 2 && hwc->config > 255))
+ (cpuhw->info.csvn >= 3 && cpuhw->info.csvn <= 5
+ && hwc->config > 255) ||
+ (cpuhw->info.csvn >= 6 && hwc->config > 287))
err = -EOPNOTSUPP;
break;
case CPUMF_CTR_SET_MT_DIAG:
@@ -135,7 +80,7 @@
* Thus, the counters can only be used if SMT is on and the
* counter set is enabled and active.
*/
- mtdiag_ctl = cpumf_state_ctl[CPUMF_CTR_SET_MT_DIAG];
+ mtdiag_ctl = cpumf_ctr_ctl[CPUMF_CTR_SET_MT_DIAG];
if (!((cpuhw->info.auth_ctl & mtdiag_ctl) &&
(cpuhw->info.enable_ctl & mtdiag_ctl) &&
(cpuhw->info.act_ctl & mtdiag_ctl)))
@@ -143,28 +88,28 @@
break;
}
- put_cpu_var(cpu_hw_events);
+ put_cpu_var(cpu_cf_events);
return err;
}
static int validate_ctr_auth(const struct hw_perf_event *hwc)
{
- struct cpu_hw_events *cpuhw;
+ struct cpu_cf_events *cpuhw;
u64 ctrs_state;
int err = 0;
- cpuhw = &get_cpu_var(cpu_hw_events);
+ cpuhw = &get_cpu_var(cpu_cf_events);
/* Check authorization for cpu counter sets.
* If the particular CPU counter set is not authorized,
* return with -ENOENT in order to fall back to other
* PMUs that might suffice the event request.
*/
- ctrs_state = cpumf_state_ctl[hwc->config_base];
+ ctrs_state = cpumf_ctr_ctl[hwc->config_base];
if (!(ctrs_state & cpuhw->info.auth_ctl))
err = -ENOENT;
- put_cpu_var(cpu_hw_events);
+ put_cpu_var(cpu_cf_events);
return err;
}
@@ -175,7 +120,7 @@
*/
static void cpumf_pmu_enable(struct pmu *pmu)
{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
int err;
if (cpuhw->flags & PMU_F_ENABLED)
@@ -198,7 +143,7 @@
*/
static void cpumf_pmu_disable(struct pmu *pmu)
{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
int err;
u64 inactive;
@@ -222,86 +167,13 @@
/* Used to avoid races in calling reserve/release_cpumf_hardware */
static DEFINE_MUTEX(pmc_reserve_mutex);
-/* CPU-measurement alerts for the counter facility */
-static void cpumf_measurement_alert(struct ext_code ext_code,
- unsigned int alert, unsigned long unused)
-{
- struct cpu_hw_events *cpuhw;
-
- if (!(alert & CPU_MF_INT_CF_MASK))
- return;
-
- inc_irq_stat(IRQEXT_CMC);
- cpuhw = this_cpu_ptr(&cpu_hw_events);
-
- /* Measurement alerts are shared and might happen when the PMU
- * is not reserved. Ignore these alerts in this case. */
- if (!(cpuhw->flags & PMU_F_RESERVED))
- return;
-
- /* counter authorization change alert */
- if (alert & CPU_MF_INT_CF_CACA)
- qctri(&cpuhw->info);
-
- /* loss of counter data alert */
- if (alert & CPU_MF_INT_CF_LCDA)
- pr_err("CPU[%i] Counter data was lost\n", smp_processor_id());
-
- /* loss of MT counter data alert */
- if (alert & CPU_MF_INT_CF_MTDA)
- pr_warn("CPU[%i] MT counter data was lost\n",
- smp_processor_id());
-}
-
-#define PMC_INIT 0
-#define PMC_RELEASE 1
-static void setup_pmc_cpu(void *flags)
-{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
-
- switch (*((int *) flags)) {
- case PMC_INIT:
- memset(&cpuhw->info, 0, sizeof(cpuhw->info));
- qctri(&cpuhw->info);
- cpuhw->flags |= PMU_F_RESERVED;
- break;
-
- case PMC_RELEASE:
- cpuhw->flags &= ~PMU_F_RESERVED;
- break;
- }
-
- /* Disable CPU counter sets */
- lcctl(0);
-}
-
-/* Initialize the CPU-measurement facility */
-static int reserve_pmc_hardware(void)
-{
- int flags = PMC_INIT;
-
- on_each_cpu(setup_pmc_cpu, &flags, 1);
- irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
-
- return 0;
-}
-
-/* Release the CPU-measurement facility */
-static void release_pmc_hardware(void)
-{
- int flags = PMC_RELEASE;
-
- on_each_cpu(setup_pmc_cpu, &flags, 1);
- irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
-}
-
/* Release the PMU if event is the last perf event */
static void hw_perf_event_destroy(struct perf_event *event)
{
if (!atomic_add_unless(&num_events, -1, 1)) {
mutex_lock(&pmc_reserve_mutex);
if (atomic_dec_return(&num_events) == 0)
- release_pmc_hardware();
+ __kernel_cpumcf_end();
mutex_unlock(&pmc_reserve_mutex);
}
}
@@ -332,7 +204,7 @@
struct perf_event_attr *attr = &event->attr;
struct hw_perf_event *hwc = &event->hw;
enum cpumf_ctr_set set;
- int err;
+ int err = 0;
u64 ev;
switch (attr->type) {
@@ -402,12 +274,14 @@
/* Initialize for using the CPU-measurement counter facility */
if (!atomic_inc_not_zero(&num_events)) {
mutex_lock(&pmc_reserve_mutex);
- if (atomic_read(&num_events) == 0 && reserve_pmc_hardware())
+ if (atomic_read(&num_events) == 0 && __kernel_cpumcf_begin())
err = -EBUSY;
else
atomic_inc(&num_events);
mutex_unlock(&pmc_reserve_mutex);
}
+ if (err)
+ return err;
event->destroy = hw_perf_event_destroy;
/* Finally, validate version and authorization of the counter set */
@@ -488,7 +362,7 @@
static void cpumf_pmu_start(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
struct hw_perf_event *hwc = &event->hw;
if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
@@ -519,7 +393,7 @@
static void cpumf_pmu_stop(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
struct hw_perf_event *hwc = &event->hw;
if (!(hwc->state & PERF_HES_STOPPED)) {
@@ -540,7 +414,7 @@
static int cpumf_pmu_add(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
/* Check authorization for the counter set to which this
* counter belongs.
@@ -564,7 +438,7 @@
static void cpumf_pmu_del(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
cpumf_pmu_stop(event, PERF_EF_UPDATE);
@@ -592,7 +466,7 @@
*/
static void cpumf_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
WARN_ON_ONCE(cpuhw->txn_flags); /* txn already in flight */
@@ -612,7 +486,7 @@
static void cpumf_pmu_cancel_txn(struct pmu *pmu)
{
unsigned int txn_flags;
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
WARN_ON_ONCE(!cpuhw->txn_flags); /* no txn in flight */
@@ -633,7 +507,7 @@
*/
static int cpumf_pmu_commit_txn(struct pmu *pmu)
{
- struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
u64 state;
WARN_ON_ONCE(!cpuhw->txn_flags); /* no txn in flight */
@@ -671,54 +545,17 @@
.cancel_txn = cpumf_pmu_cancel_txn,
};
-static int cpumf_pmf_setup(unsigned int cpu, int flags)
-{
- local_irq_disable();
- setup_pmc_cpu(&flags);
- local_irq_enable();
- return 0;
-}
-
-static int s390_pmu_online_cpu(unsigned int cpu)
-{
- return cpumf_pmf_setup(cpu, PMC_INIT);
-}
-
-static int s390_pmu_offline_cpu(unsigned int cpu)
-{
- return cpumf_pmf_setup(cpu, PMC_RELEASE);
-}
-
static int __init cpumf_pmu_init(void)
{
int rc;
- if (!cpum_cf_avail())
+ if (!kernel_cpumcf_avail())
return -ENODEV;
- /* clear bit 15 of cr0 to unauthorize problem-state to
- * extract measurement counters */
- ctl_clear_bit(0, 48);
-
- /* register handler for measurement-alert interruptions */
- rc = register_external_irq(EXT_IRQ_MEASURE_ALERT,
- cpumf_measurement_alert);
- if (rc) {
- pr_err("Registering for CPU-measurement alerts "
- "failed with rc=%i\n", rc);
- return rc;
- }
-
cpumf_pmu.attr_groups = cpumf_cf_event_group();
rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
- if (rc) {
+ if (rc)
pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
- unregister_external_irq(EXT_IRQ_MEASURE_ALERT,
- cpumf_measurement_alert);
- return rc;
- }
- return cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE,
- "perf/s390/cf:online",
- s390_pmu_online_cpu, s390_pmu_offline_cpu);
+ return rc;
}
-early_initcall(cpumf_pmu_init);
+subsys_initcall(cpumf_pmu_init);
diff --git a/arch/s390/kernel/perf_cpum_cf_common.c b/arch/s390/kernel/perf_cpum_cf_common.c
new file mode 100644
index 0000000..3bced89
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_cf_common.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * CPU-Measurement Counter Facility Support - Common Layer
+ *
+ * Copyright IBM Corp. 2019
+ * Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
+ */
+#define KMSG_COMPONENT "cpum_cf_common"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <asm/ctl_reg.h>
+#include <asm/irq.h>
+#include <asm/cpu_mcf.h>
+
+/* Per-CPU event structure for the counter facility */
+DEFINE_PER_CPU(struct cpu_cf_events, cpu_cf_events) = {
+ .ctr_set = {
+ [CPUMF_CTR_SET_BASIC] = ATOMIC_INIT(0),
+ [CPUMF_CTR_SET_USER] = ATOMIC_INIT(0),
+ [CPUMF_CTR_SET_CRYPTO] = ATOMIC_INIT(0),
+ [CPUMF_CTR_SET_EXT] = ATOMIC_INIT(0),
+ [CPUMF_CTR_SET_MT_DIAG] = ATOMIC_INIT(0),
+ },
+ .alert = ATOMIC64_INIT(0),
+ .state = 0,
+ .flags = 0,
+ .txn_flags = 0,
+};
+/* Indicator whether the CPU-Measurement Counter Facility Support is ready */
+static bool cpum_cf_initalized;
+
+/* CPU-measurement alerts for the counter facility */
+static void cpumf_measurement_alert(struct ext_code ext_code,
+ unsigned int alert, unsigned long unused)
+{
+ struct cpu_cf_events *cpuhw;
+
+ if (!(alert & CPU_MF_INT_CF_MASK))
+ return;
+
+ inc_irq_stat(IRQEXT_CMC);
+ cpuhw = this_cpu_ptr(&cpu_cf_events);
+
+ /* Measurement alerts are shared and might happen when the PMU
+ * is not reserved. Ignore these alerts in this case. */
+ if (!(cpuhw->flags & PMU_F_RESERVED))
+ return;
+
+ /* counter authorization change alert */
+ if (alert & CPU_MF_INT_CF_CACA)
+ qctri(&cpuhw->info);
+
+ /* loss of counter data alert */
+ if (alert & CPU_MF_INT_CF_LCDA)
+ pr_err("CPU[%i] Counter data was lost\n", smp_processor_id());
+
+ /* loss of MT counter data alert */
+ if (alert & CPU_MF_INT_CF_MTDA)
+ pr_warn("CPU[%i] MT counter data was lost\n",
+ smp_processor_id());
+
+ /* store alert for special handling by in-kernel users */
+ atomic64_or(alert, &cpuhw->alert);
+}
+
+#define PMC_INIT 0
+#define PMC_RELEASE 1
+static void cpum_cf_setup_cpu(void *flags)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+
+ switch (*((int *) flags)) {
+ case PMC_INIT:
+ memset(&cpuhw->info, 0, sizeof(cpuhw->info));
+ qctri(&cpuhw->info);
+ cpuhw->flags |= PMU_F_RESERVED;
+ break;
+
+ case PMC_RELEASE:
+ cpuhw->flags &= ~PMU_F_RESERVED;
+ break;
+ }
+
+ /* Disable CPU counter sets */
+ lcctl(0);
+}
+
+bool kernel_cpumcf_avail(void)
+{
+ return cpum_cf_initalized;
+}
+EXPORT_SYMBOL(kernel_cpumcf_avail);
+
+
+/* Reserve/release functions for sharing perf hardware */
+static DEFINE_SPINLOCK(cpumcf_owner_lock);
+static void *cpumcf_owner;
+
+/* Initialize the CPU-measurement counter facility */
+int __kernel_cpumcf_begin(void)
+{
+ int flags = PMC_INIT;
+ int err = 0;
+
+ spin_lock(&cpumcf_owner_lock);
+ if (cpumcf_owner)
+ err = -EBUSY;
+ else
+ cpumcf_owner = __builtin_return_address(0);
+ spin_unlock(&cpumcf_owner_lock);
+ if (err)
+ return err;
+
+ on_each_cpu(cpum_cf_setup_cpu, &flags, 1);
+ irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+
+ return 0;
+}
+EXPORT_SYMBOL(__kernel_cpumcf_begin);
+
+/* Obtain the CPU-measurement alerts for the counter facility */
+unsigned long kernel_cpumcf_alert(int clear)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ unsigned long alert;
+
+ alert = atomic64_read(&cpuhw->alert);
+ if (clear)
+ atomic64_set(&cpuhw->alert, 0);
+
+ return alert;
+}
+EXPORT_SYMBOL(kernel_cpumcf_alert);
+
+/* Release the CPU-measurement counter facility */
+void __kernel_cpumcf_end(void)
+{
+ int flags = PMC_RELEASE;
+
+ on_each_cpu(cpum_cf_setup_cpu, &flags, 1);
+ irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+
+ spin_lock(&cpumcf_owner_lock);
+ cpumcf_owner = NULL;
+ spin_unlock(&cpumcf_owner_lock);
+}
+EXPORT_SYMBOL(__kernel_cpumcf_end);
+
+static int cpum_cf_setup(unsigned int cpu, int flags)
+{
+ local_irq_disable();
+ cpum_cf_setup_cpu(&flags);
+ local_irq_enable();
+ return 0;
+}
+
+static int cpum_cf_online_cpu(unsigned int cpu)
+{
+ return cpum_cf_setup(cpu, PMC_INIT);
+}
+
+static int cpum_cf_offline_cpu(unsigned int cpu)
+{
+ return cpum_cf_setup(cpu, PMC_RELEASE);
+}
+
+static int __init cpum_cf_init(void)
+{
+ int rc;
+
+ if (!cpum_cf_avail())
+ return -ENODEV;
+
+ /* clear bit 15 of cr0 to unauthorize problem-state to
+ * extract measurement counters */
+ ctl_clear_bit(0, 48);
+
+ /* register handler for measurement-alert interruptions */
+ rc = register_external_irq(EXT_IRQ_MEASURE_ALERT,
+ cpumf_measurement_alert);
+ if (rc) {
+ pr_err("Registering for CPU-measurement alerts "
+ "failed with rc=%i\n", rc);
+ return rc;
+ }
+
+ rc = cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE,
+ "perf/s390/cf:online",
+ cpum_cf_online_cpu, cpum_cf_offline_cpu);
+ if (!rc)
+ cpum_cf_initalized = true;
+
+ return rc;
+}
+early_initcall(cpum_cf_init);
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
new file mode 100644
index 0000000..2654e34
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -0,0 +1,705 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Performance event support for s390x - CPU-measurement Counter Sets
+ *
+ * Copyright IBM Corp. 2019
+ * Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
+ * Thomas Richer <tmricht@linux.ibm.com>
+ */
+#define KMSG_COMPONENT "cpum_cf_diag"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/processor.h>
+
+#include <asm/ctl_reg.h>
+#include <asm/irq.h>
+#include <asm/cpu_mcf.h>
+#include <asm/timex.h>
+#include <asm/debug.h>
+
+#define CF_DIAG_CTRSET_DEF 0xfeef /* Counter set header mark */
+
+static unsigned int cf_diag_cpu_speed;
+static debug_info_t *cf_diag_dbg;
+
+struct cf_diag_csd { /* Counter set data per CPU */
+ size_t used; /* Bytes used in data/start */
+ unsigned char start[PAGE_SIZE]; /* Counter set at event start */
+ unsigned char data[PAGE_SIZE]; /* Counter set at event delete */
+};
+static DEFINE_PER_CPU(struct cf_diag_csd, cf_diag_csd);
+
+/* Counter sets are stored as data stream in a page sized memory buffer and
+ * exported to user space via raw data attached to the event sample data.
+ * Each counter set starts with an eight byte header consisting of:
+ * - a two byte eye catcher (0xfeef)
+ * - a one byte counter set number
+ * - a two byte counter set size (indicates the number of counters in this set)
+ * - a three byte reserved value (must be zero) to make the header the same
+ * size as a counter value.
+ * All counter values are eight byte in size.
+ *
+ * All counter sets are followed by a 64 byte trailer.
+ * The trailer consists of a:
+ * - flag field indicating valid fields when corresponding bit set
+ * - the counter facility first and second version number
+ * - the CPU speed if nonzero
+ * - the time stamp the counter sets have been collected
+ * - the time of day (TOD) base value
+ * - the machine type.
+ *
+ * The counter sets are saved when the process is prepared to be executed on a
+ * CPU and saved again when the process is going to be removed from a CPU.
+ * The difference of both counter sets are calculated and stored in the event
+ * sample data area.
+ */
+
+struct cf_ctrset_entry { /* CPU-M CF counter set entry (8 byte) */
+ unsigned int def:16; /* 0-15 Data Entry Format */
+ unsigned int set:16; /* 16-31 Counter set identifier */
+ unsigned int ctr:16; /* 32-47 Number of stored counters */
+ unsigned int res1:16; /* 48-63 Reserved */
+};
+
+struct cf_trailer_entry { /* CPU-M CF_DIAG trailer (64 byte) */
+ /* 0 - 7 */
+ union {
+ struct {
+ unsigned int clock_base:1; /* TOD clock base set */
+ unsigned int speed:1; /* CPU speed set */
+ /* Measurement alerts */
+ unsigned int mtda:1; /* Loss of MT ctr. data alert */
+ unsigned int caca:1; /* Counter auth. change alert */
+ unsigned int lcda:1; /* Loss of counter data alert */
+ };
+ unsigned long flags; /* 0-63 All indicators */
+ };
+ /* 8 - 15 */
+ unsigned int cfvn:16; /* 64-79 Ctr First Version */
+ unsigned int csvn:16; /* 80-95 Ctr Second Version */
+ unsigned int cpu_speed:32; /* 96-127 CPU speed */
+ /* 16 - 23 */
+ unsigned long timestamp; /* 128-191 Timestamp (TOD) */
+ /* 24 - 55 */
+ union {
+ struct {
+ unsigned long progusage1;
+ unsigned long progusage2;
+ unsigned long progusage3;
+ unsigned long tod_base;
+ };
+ unsigned long progusage[4];
+ };
+ /* 56 - 63 */
+ unsigned int mach_type:16; /* Machine type */
+ unsigned int res1:16; /* Reserved */
+ unsigned int res2:32; /* Reserved */
+};
+
+/* Create the trailer data at the end of a page. */
+static void cf_diag_trailer(struct cf_trailer_entry *te)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ struct cpuid cpuid;
+
+ te->cfvn = cpuhw->info.cfvn; /* Counter version numbers */
+ te->csvn = cpuhw->info.csvn;
+
+ get_cpu_id(&cpuid); /* Machine type */
+ te->mach_type = cpuid.machine;
+ te->cpu_speed = cf_diag_cpu_speed;
+ if (te->cpu_speed)
+ te->speed = 1;
+ te->clock_base = 1; /* Save clock base */
+ memcpy(&te->tod_base, &tod_clock_base[1], 8);
+ store_tod_clock((__u64 *)&te->timestamp);
+}
+
+/*
+ * Change the CPUMF state to active.
+ * Enable and activate the CPU-counter sets according
+ * to the per-cpu control state.
+ */
+static void cf_diag_enable(struct pmu *pmu)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ int err;
+
+ debug_sprintf_event(cf_diag_dbg, 5,
+ "%s pmu %p cpu %d flags %#x state %#llx\n",
+ __func__, pmu, smp_processor_id(), cpuhw->flags,
+ cpuhw->state);
+ if (cpuhw->flags & PMU_F_ENABLED)
+ return;
+
+ err = lcctl(cpuhw->state);
+ if (err) {
+ pr_err("Enabling the performance measuring unit "
+ "failed with rc=%x\n", err);
+ return;
+ }
+ cpuhw->flags |= PMU_F_ENABLED;
+}
+
+/*
+ * Change the CPUMF state to inactive.
+ * Disable and enable (inactive) the CPU-counter sets according
+ * to the per-cpu control state.
+ */
+static void cf_diag_disable(struct pmu *pmu)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ u64 inactive;
+ int err;
+
+ debug_sprintf_event(cf_diag_dbg, 5,
+ "%s pmu %p cpu %d flags %#x state %#llx\n",
+ __func__, pmu, smp_processor_id(), cpuhw->flags,
+ cpuhw->state);
+ if (!(cpuhw->flags & PMU_F_ENABLED))
+ return;
+
+ inactive = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1);
+ err = lcctl(inactive);
+ if (err) {
+ pr_err("Disabling the performance measuring unit "
+ "failed with rc=%x\n", err);
+ return;
+ }
+ cpuhw->flags &= ~PMU_F_ENABLED;
+}
+
+/* Number of perf events counting hardware events */
+static atomic_t cf_diag_events = ATOMIC_INIT(0);
+
+/* Release the PMU if event is the last perf event */
+static void cf_diag_perf_event_destroy(struct perf_event *event)
+{
+ debug_sprintf_event(cf_diag_dbg, 5,
+ "%s event %p cpu %d cf_diag_events %d\n",
+ __func__, event, event->cpu,
+ atomic_read(&cf_diag_events));
+ if (atomic_dec_return(&cf_diag_events) == 0)
+ __kernel_cpumcf_end();
+}
+
+/* Setup the event. Test for authorized counter sets and only include counter
+ * sets which are authorized at the time of the setup. Including unauthorized
+ * counter sets result in specification exception (and panic).
+ */
+static int __hw_perf_event_init(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ struct cpu_cf_events *cpuhw;
+ enum cpumf_ctr_set i;
+ int err = 0;
+
+ debug_sprintf_event(cf_diag_dbg, 5, "%s event %p cpu %d\n", __func__,
+ event, event->cpu);
+
+ event->hw.config = attr->config;
+ event->hw.config_base = 0;
+
+ /* Add all authorized counter sets to config_base. The
+ * the hardware init function is either called per-cpu or just once
+ * for all CPUS (event->cpu == -1). This depends on the whether
+ * counting is started for all CPUs or on a per workload base where
+ * the perf event moves from one CPU to another CPU.
+ * Checking the authorization on any CPU is fine as the hardware
+ * applies the same authorization settings to all CPUs.
+ */
+ cpuhw = &get_cpu_var(cpu_cf_events);
+ for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i)
+ if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i])
+ event->hw.config_base |= cpumf_ctr_ctl[i];
+ put_cpu_var(cpu_cf_events);
+
+ /* No authorized counter sets, nothing to count/sample */
+ if (!event->hw.config_base) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ /* Set sample_period to indicate sampling */
+ event->hw.sample_period = attr->sample_period;
+ local64_set(&event->hw.period_left, event->hw.sample_period);
+ event->hw.last_period = event->hw.sample_period;
+out:
+ debug_sprintf_event(cf_diag_dbg, 5, "%s err %d config_base %#lx\n",
+ __func__, err, event->hw.config_base);
+ return err;
+}
+
+static int cf_diag_event_init(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ int err = -ENOENT;
+
+ debug_sprintf_event(cf_diag_dbg, 5,
+ "%s event %p cpu %d config %#llx "
+ "sample_type %#llx cf_diag_events %d\n", __func__,
+ event, event->cpu, attr->config, attr->sample_type,
+ atomic_read(&cf_diag_events));
+
+ if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG ||
+ event->attr.type != PERF_TYPE_RAW)
+ goto out;
+
+ /* Raw events are used to access counters directly,
+ * hence do not permit excludes.
+ * This event is usesless without PERF_SAMPLE_RAW to return counter set
+ * values as raw data.
+ */
+ if (attr->exclude_kernel || attr->exclude_user || attr->exclude_hv ||
+ !(attr->sample_type & (PERF_SAMPLE_CPU | PERF_SAMPLE_RAW))) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ /* Initialize for using the CPU-measurement counter facility */
+ if (atomic_inc_return(&cf_diag_events) == 1) {
+ if (__kernel_cpumcf_begin()) {
+ atomic_dec(&cf_diag_events);
+ err = -EBUSY;
+ goto out;
+ }
+ }
+ event->destroy = cf_diag_perf_event_destroy;
+
+ err = __hw_perf_event_init(event);
+ if (unlikely(err))
+ event->destroy(event);
+out:
+ debug_sprintf_event(cf_diag_dbg, 5, "%s err %d\n", __func__, err);
+ return err;
+}
+
+static void cf_diag_read(struct perf_event *event)
+{
+ debug_sprintf_event(cf_diag_dbg, 5, "%s event %p\n", __func__, event);
+}
+
+/* Return the maximum possible counter set size (in number of 8 byte counters)
+ * depending on type and model number.
+ */
+static size_t cf_diag_ctrset_size(enum cpumf_ctr_set ctrset,
+ struct cpumf_ctr_info *info)
+{
+ size_t ctrset_size = 0;
+
+ switch (ctrset) {
+ case CPUMF_CTR_SET_BASIC:
+ if (info->cfvn >= 1)
+ ctrset_size = 6;
+ break;
+ case CPUMF_CTR_SET_USER:
+ if (info->cfvn == 1)
+ ctrset_size = 6;
+ else if (info->cfvn >= 3)
+ ctrset_size = 2;
+ break;
+ case CPUMF_CTR_SET_CRYPTO:
+ if (info->csvn >= 1 && info->csvn <= 5)
+ ctrset_size = 16;
+ else if (info->csvn == 6)
+ ctrset_size = 20;
+ break;
+ case CPUMF_CTR_SET_EXT:
+ if (info->csvn == 1)
+ ctrset_size = 32;
+ else if (info->csvn == 2)
+ ctrset_size = 48;
+ else if (info->csvn >= 3 && info->csvn <= 5)
+ ctrset_size = 128;
+ else if (info->csvn == 6)
+ ctrset_size = 160;
+ break;
+ case CPUMF_CTR_SET_MT_DIAG:
+ if (info->csvn > 3)
+ ctrset_size = 48;
+ break;
+ case CPUMF_CTR_SET_MAX:
+ break;
+ }
+
+ return ctrset_size;
+}
+
+/* Calculate memory needed to store all counter sets together with header and
+ * trailer data. This is independend of the counter set authorization which
+ * can vary depending on the configuration.
+ */
+static size_t cf_diag_ctrset_maxsize(struct cpumf_ctr_info *info)
+{
+ size_t max_size = sizeof(struct cf_trailer_entry);
+ enum cpumf_ctr_set i;
+
+ for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) {
+ size_t size = cf_diag_ctrset_size(i, info);
+
+ if (size)
+ max_size += size * sizeof(u64) +
+ sizeof(struct cf_ctrset_entry);
+ }
+ debug_sprintf_event(cf_diag_dbg, 5, "%s max_size %zu\n", __func__,
+ max_size);
+
+ return max_size;
+}
+
+/* Read a counter set. The counter set number determines which counter set and
+ * the CPUM-CF first and second version number determine the number of
+ * available counters in this counter set.
+ * Each counter set starts with header containing the counter set number and
+ * the number of 8 byte counters.
+ *
+ * The functions returns the number of bytes occupied by this counter set
+ * including the header.
+ * If there is no counter in the counter set, this counter set is useless and
+ * zero is returned on this case.
+ */
+static size_t cf_diag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset,
+ size_t room)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ size_t ctrset_size, need = 0;
+ int rc = 3; /* Assume write failure */
+
+ ctrdata->def = CF_DIAG_CTRSET_DEF;
+ ctrdata->set = ctrset;
+ ctrdata->res1 = 0;
+ ctrset_size = cf_diag_ctrset_size(ctrset, &cpuhw->info);
+
+ if (ctrset_size) { /* Save data */
+ need = ctrset_size * sizeof(u64) + sizeof(*ctrdata);
+ if (need <= room)
+ rc = ctr_stcctm(ctrset, ctrset_size,
+ (u64 *)(ctrdata + 1));
+ if (rc != 3)
+ ctrdata->ctr = ctrset_size;
+ else
+ need = 0;
+ }
+
+ debug_sprintf_event(cf_diag_dbg, 6,
+ "%s ctrset %d ctrset_size %zu cfvn %d csvn %d"
+ " need %zd rc %d\n",
+ __func__, ctrset, ctrset_size, cpuhw->info.cfvn,
+ cpuhw->info.csvn, need, rc);
+ return need;
+}
+
+/* Read out all counter sets and save them in the provided data buffer.
+ * The last 64 byte host an artificial trailer entry.
+ */
+static size_t cf_diag_getctr(void *data, size_t sz, unsigned long auth)
+{
+ struct cf_trailer_entry *trailer;
+ size_t offset = 0, done;
+ int i;
+
+ memset(data, 0, sz);
+ sz -= sizeof(*trailer); /* Always room for trailer */
+ for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) {
+ struct cf_ctrset_entry *ctrdata = data + offset;
+
+ if (!(auth & cpumf_ctr_ctl[i]))
+ continue; /* Counter set not authorized */
+
+ done = cf_diag_getctrset(ctrdata, i, sz - offset);
+ offset += done;
+ debug_sprintf_event(cf_diag_dbg, 6,
+ "%s ctrset %d offset %zu done %zu\n",
+ __func__, i, offset, done);
+ }
+ trailer = data + offset;
+ cf_diag_trailer(trailer);
+ return offset + sizeof(*trailer);
+}
+
+/* Calculate the difference for each counter in a counter set. */
+static void cf_diag_diffctrset(u64 *pstart, u64 *pstop, int counters)
+{
+ for (; --counters >= 0; ++pstart, ++pstop)
+ if (*pstop >= *pstart)
+ *pstop -= *pstart;
+ else
+ *pstop = *pstart - *pstop;
+}
+
+/* Scan the counter sets and calculate the difference of each counter
+ * in each set. The result is the increment of each counter during the
+ * period the counter set has been activated.
+ *
+ * Return true on success.
+ */
+static int cf_diag_diffctr(struct cf_diag_csd *csd, unsigned long auth)
+{
+ struct cf_trailer_entry *trailer_start, *trailer_stop;
+ struct cf_ctrset_entry *ctrstart, *ctrstop;
+ size_t offset = 0;
+
+ auth &= (1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1;
+ do {
+ ctrstart = (struct cf_ctrset_entry *)(csd->start + offset);
+ ctrstop = (struct cf_ctrset_entry *)(csd->data + offset);
+
+ if (memcmp(ctrstop, ctrstart, sizeof(*ctrstop))) {
+ pr_err("cpum_cf_diag counter set compare error "
+ "in set %i\n", ctrstart->set);
+ return 0;
+ }
+ auth &= ~cpumf_ctr_ctl[ctrstart->set];
+ if (ctrstart->def == CF_DIAG_CTRSET_DEF) {
+ cf_diag_diffctrset((u64 *)(ctrstart + 1),
+ (u64 *)(ctrstop + 1), ctrstart->ctr);
+ offset += ctrstart->ctr * sizeof(u64) +
+ sizeof(*ctrstart);
+ }
+ debug_sprintf_event(cf_diag_dbg, 6,
+ "%s set %d ctr %d offset %zu auth %lx\n",
+ __func__, ctrstart->set, ctrstart->ctr,
+ offset, auth);
+ } while (ctrstart->def && auth);
+
+ /* Save time_stamp from start of event in stop's trailer */
+ trailer_start = (struct cf_trailer_entry *)(csd->start + offset);
+ trailer_stop = (struct cf_trailer_entry *)(csd->data + offset);
+ trailer_stop->progusage[0] = trailer_start->timestamp;
+
+ return 1;
+}
+
+/* Create perf event sample with the counter sets as raw data. The sample
+ * is then pushed to the event subsystem and the function checks for
+ * possible event overflows. If an event overflow occurs, the PMU is
+ * stopped.
+ *
+ * Return non-zero if an event overflow occurred.
+ */
+static int cf_diag_push_sample(struct perf_event *event,
+ struct cf_diag_csd *csd)
+{
+ struct perf_sample_data data;
+ struct perf_raw_record raw;
+ struct pt_regs regs;
+ int overflow;
+
+ /* Setup perf sample */
+ perf_sample_data_init(&data, 0, event->hw.last_period);
+ memset(®s, 0, sizeof(regs));
+ memset(&raw, 0, sizeof(raw));
+
+ if (event->attr.sample_type & PERF_SAMPLE_CPU)
+ data.cpu_entry.cpu = event->cpu;
+ if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+ raw.frag.size = csd->used;
+ raw.frag.data = csd->data;
+ raw.size = csd->used;
+ data.raw = &raw;
+ }
+
+ overflow = perf_event_overflow(event, &data, ®s);
+ debug_sprintf_event(cf_diag_dbg, 6,
+ "%s event %p cpu %d sample_type %#llx raw %d "
+ "ov %d\n", __func__, event, event->cpu,
+ event->attr.sample_type, raw.size, overflow);
+ if (overflow)
+ event->pmu->stop(event, 0);
+
+ perf_event_update_userpage(event);
+ return overflow;
+}
+
+static void cf_diag_start(struct perf_event *event, int flags)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ struct cf_diag_csd *csd = this_cpu_ptr(&cf_diag_csd);
+ struct hw_perf_event *hwc = &event->hw;
+
+ debug_sprintf_event(cf_diag_dbg, 5,
+ "%s event %p cpu %d flags %#x hwc-state %#x\n",
+ __func__, event, event->cpu, flags, hwc->state);
+ if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+ return;
+
+ /* (Re-)enable and activate all counter sets */
+ lcctl(0); /* Reset counter sets */
+ hwc->state = 0;
+ ctr_set_multiple_enable(&cpuhw->state, hwc->config_base);
+ lcctl(cpuhw->state); /* Enable counter sets */
+ csd->used = cf_diag_getctr(csd->start, sizeof(csd->start),
+ event->hw.config_base);
+ ctr_set_multiple_start(&cpuhw->state, hwc->config_base);
+ /* Function cf_diag_enable() starts the counter sets. */
+}
+
+static void cf_diag_stop(struct perf_event *event, int flags)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ struct cf_diag_csd *csd = this_cpu_ptr(&cf_diag_csd);
+ struct hw_perf_event *hwc = &event->hw;
+
+ debug_sprintf_event(cf_diag_dbg, 5,
+ "%s event %p cpu %d flags %#x hwc-state %#x\n",
+ __func__, event, event->cpu, flags, hwc->state);
+
+ /* Deactivate all counter sets */
+ ctr_set_multiple_stop(&cpuhw->state, hwc->config_base);
+ local64_inc(&event->count);
+ csd->used = cf_diag_getctr(csd->data, sizeof(csd->data),
+ event->hw.config_base);
+ if (cf_diag_diffctr(csd, event->hw.config_base))
+ cf_diag_push_sample(event, csd);
+ hwc->state |= PERF_HES_STOPPED;
+}
+
+static int cf_diag_add(struct perf_event *event, int flags)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ int err = 0;
+
+ debug_sprintf_event(cf_diag_dbg, 5,
+ "%s event %p cpu %d flags %#x cpuhw %p\n",
+ __func__, event, event->cpu, flags, cpuhw);
+
+ if (cpuhw->flags & PMU_F_IN_USE) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+ cpuhw->flags |= PMU_F_IN_USE;
+ if (flags & PERF_EF_START)
+ cf_diag_start(event, PERF_EF_RELOAD);
+out:
+ debug_sprintf_event(cf_diag_dbg, 5, "%s err %d\n", __func__, err);
+ return err;
+}
+
+static void cf_diag_del(struct perf_event *event, int flags)
+{
+ struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+
+ debug_sprintf_event(cf_diag_dbg, 5,
+ "%s event %p cpu %d flags %#x\n",
+ __func__, event, event->cpu, flags);
+
+ cf_diag_stop(event, PERF_EF_UPDATE);
+ ctr_set_multiple_stop(&cpuhw->state, event->hw.config_base);
+ ctr_set_multiple_disable(&cpuhw->state, event->hw.config_base);
+ cpuhw->flags &= ~PMU_F_IN_USE;
+}
+
+CPUMF_EVENT_ATTR(CF_DIAG, CF_DIAG, PERF_EVENT_CPUM_CF_DIAG);
+
+static struct attribute *cf_diag_events_attr[] = {
+ CPUMF_EVENT_PTR(CF_DIAG, CF_DIAG),
+ NULL,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+
+static struct attribute *cf_diag_format_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group cf_diag_events_group = {
+ .name = "events",
+ .attrs = cf_diag_events_attr,
+};
+static struct attribute_group cf_diag_format_group = {
+ .name = "format",
+ .attrs = cf_diag_format_attr,
+};
+static const struct attribute_group *cf_diag_attr_groups[] = {
+ &cf_diag_events_group,
+ &cf_diag_format_group,
+ NULL,
+};
+
+/* Performance monitoring unit for s390x */
+static struct pmu cf_diag = {
+ .task_ctx_nr = perf_sw_context,
+ .pmu_enable = cf_diag_enable,
+ .pmu_disable = cf_diag_disable,
+ .event_init = cf_diag_event_init,
+ .add = cf_diag_add,
+ .del = cf_diag_del,
+ .start = cf_diag_start,
+ .stop = cf_diag_stop,
+ .read = cf_diag_read,
+
+ .attr_groups = cf_diag_attr_groups
+};
+
+/* Get the CPU speed, try sampling facility first and CPU attributes second. */
+static void cf_diag_get_cpu_speed(void)
+{
+ if (cpum_sf_avail()) { /* Sampling facility first */
+ struct hws_qsi_info_block si;
+
+ memset(&si, 0, sizeof(si));
+ if (!qsi(&si)) {
+ cf_diag_cpu_speed = si.cpu_speed;
+ return;
+ }
+ }
+
+ if (test_facility(34)) { /* CPU speed extract static part */
+ unsigned long mhz = __ecag(ECAG_CPU_ATTRIBUTE, 0);
+
+ if (mhz != -1UL)
+ cf_diag_cpu_speed = mhz & 0xffffffff;
+ }
+}
+
+/* Initialize the counter set PMU to generate complete counter set data as
+ * event raw data. This relies on the CPU Measurement Counter Facility device
+ * already being loaded and initialized.
+ */
+static int __init cf_diag_init(void)
+{
+ struct cpumf_ctr_info info;
+ size_t need;
+ int rc;
+
+ if (!kernel_cpumcf_avail() || !stccm_avail() || qctri(&info))
+ return -ENODEV;
+ cf_diag_get_cpu_speed();
+
+ /* Make sure the counter set data fits into predefined buffer. */
+ need = cf_diag_ctrset_maxsize(&info);
+ if (need > sizeof(((struct cf_diag_csd *)0)->start)) {
+ pr_err("Insufficient memory for PMU(cpum_cf_diag) need=%zu\n",
+ need);
+ return -ENOMEM;
+ }
+
+ /* Setup s390dbf facility */
+ cf_diag_dbg = debug_register(KMSG_COMPONENT, 2, 1, 128);
+ if (!cf_diag_dbg) {
+ pr_err("Registration of s390dbf(cpum_cf_diag) failed\n");
+ return -ENOMEM;
+ }
+ debug_register_view(cf_diag_dbg, &debug_sprintf_view);
+
+ rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW);
+ if (rc) {
+ debug_unregister_view(cf_diag_dbg, &debug_sprintf_view);
+ debug_unregister(cf_diag_dbg);
+ pr_err("Registration of PMU(cpum_cf_diag) failed with rc=%i\n",
+ rc);
+ }
+ return rc;
+}
+arch_initcall(cf_diag_init);
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index d63fb3c..8b33e03 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -6,6 +6,7 @@
#include <linux/slab.h>
#include <linux/perf_event.h>
+#include <asm/cpu_mf.h>
/* BEGIN: CPUM_CF COUNTER DEFINITIONS =================================== */
@@ -30,22 +31,26 @@
CPUMF_EVENT_ATTR(cf_fvn3, PROBLEM_STATE_INSTRUCTIONS, 0x0021);
CPUMF_EVENT_ATTR(cf_fvn3, L1D_DIR_WRITES, 0x0004);
CPUMF_EVENT_ATTR(cf_fvn3, L1D_PENALTY_CYCLES, 0x0005);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_FUNCTIONS, 0x0040);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_CYCLES, 0x0041);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_BLOCKED_FUNCTIONS, 0x0042);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_BLOCKED_CYCLES, 0x0043);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_FUNCTIONS, 0x0044);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_CYCLES, 0x0045);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_BLOCKED_FUNCTIONS, 0x0046);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_BLOCKED_CYCLES, 0x0047);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_FUNCTIONS, 0x0048);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_CYCLES, 0x0049);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_BLOCKED_FUNCTIONS, 0x004a);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_BLOCKED_CYCLES, 0x004b);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_FUNCTIONS, 0x004c);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_CYCLES, 0x004d);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_BLOCKED_FUNCTIONS, 0x004e);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_FUNCTIONS, 0x0040);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_CYCLES, 0x0041);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS, 0x0042);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_BLOCKED_CYCLES, 0x0043);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_FUNCTIONS, 0x0044);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_CYCLES, 0x0045);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS, 0x0046);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_BLOCKED_CYCLES, 0x0047);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_FUNCTIONS, 0x0048);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_CYCLES, 0x0049);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS, 0x004a);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_BLOCKED_CYCLES, 0x004b);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_FUNCTIONS, 0x004c);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_CYCLES, 0x004d);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS, 0x004e);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_FUNCTION_COUNT, 0x0050);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_CYCLES_COUNT, 0x0051);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_BLOCKED_FUNCTION_COUNT, 0x0052);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_BLOCKED_CYCLES_COUNT, 0x0053);
CPUMF_EVENT_ATTR(cf_z10, L1I_L2_SOURCED_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z10, L1D_L2_SOURCED_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z10, L1I_L3_LOCAL_WRITES, 0x0082);
@@ -261,23 +266,47 @@
NULL,
};
-static struct attribute *cpumcf_svn_generic_pmu_event_attr[] __initdata = {
- CPUMF_EVENT_PTR(cf_svn_generic, PRNG_FUNCTIONS),
- CPUMF_EVENT_PTR(cf_svn_generic, PRNG_CYCLES),
- CPUMF_EVENT_PTR(cf_svn_generic, PRNG_BLOCKED_FUNCTIONS),
- CPUMF_EVENT_PTR(cf_svn_generic, PRNG_BLOCKED_CYCLES),
- CPUMF_EVENT_PTR(cf_svn_generic, SHA_FUNCTIONS),
- CPUMF_EVENT_PTR(cf_svn_generic, SHA_CYCLES),
- CPUMF_EVENT_PTR(cf_svn_generic, SHA_BLOCKED_FUNCTIONS),
- CPUMF_EVENT_PTR(cf_svn_generic, SHA_BLOCKED_CYCLES),
- CPUMF_EVENT_PTR(cf_svn_generic, DEA_FUNCTIONS),
- CPUMF_EVENT_PTR(cf_svn_generic, DEA_CYCLES),
- CPUMF_EVENT_PTR(cf_svn_generic, DEA_BLOCKED_FUNCTIONS),
- CPUMF_EVENT_PTR(cf_svn_generic, DEA_BLOCKED_CYCLES),
- CPUMF_EVENT_PTR(cf_svn_generic, AES_FUNCTIONS),
- CPUMF_EVENT_PTR(cf_svn_generic, AES_CYCLES),
- CPUMF_EVENT_PTR(cf_svn_generic, AES_BLOCKED_FUNCTIONS),
- CPUMF_EVENT_PTR(cf_svn_generic, AES_BLOCKED_CYCLES),
+static struct attribute *cpumcf_svn_12345_pmu_event_attr[] __initdata = {
+ CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, SHA_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, SHA_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, DEA_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, DEA_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, AES_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, AES_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_CYCLES),
+ NULL,
+};
+
+static struct attribute *cpumcf_svn_6_pmu_event_attr[] __initdata = {
+ CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, SHA_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, SHA_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, DEA_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, DEA_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, AES_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, AES_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf_svn_6, ECC_FUNCTION_COUNT),
+ CPUMF_EVENT_PTR(cf_svn_6, ECC_CYCLES_COUNT),
+ CPUMF_EVENT_PTR(cf_svn_6, ECC_BLOCKED_FUNCTION_COUNT),
+ CPUMF_EVENT_PTR(cf_svn_6, ECC_BLOCKED_CYCLES_COUNT),
NULL,
};
@@ -561,7 +590,18 @@
default:
cfvn = none;
}
- csvn = cpumcf_svn_generic_pmu_event_attr;
+
+ /* Determine version specific crypto set */
+ switch (ci.csvn) {
+ case 1 ... 5:
+ csvn = cpumcf_svn_12345_pmu_event_attr;
+ break;
+ case 6:
+ csvn = cpumcf_svn_6_pmu_event_attr;
+ break;
+ default:
+ csvn = none;
+ }
/* Determine model-specific counter set(s) */
get_cpu_id(&cpu_id);
@@ -584,6 +624,8 @@
break;
case 0x3906:
case 0x3907:
+ case 0x8561:
+ case 0x8562:
model = cpumcf_z14_pmu_event_attr;
break;
default:
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 5c53e97..3d8b12a 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -514,7 +514,6 @@
sfb_pending_allocs(sfb, hwc));
}
-
/* Number of perf events counting hardware events */
static atomic_t num_events;
/* Used to avoid races in calling reserve/release_cpumf_hardware */
@@ -674,13 +673,89 @@
rcu_read_unlock();
}
+static unsigned long getrate(bool freq, unsigned long sample,
+ struct hws_qsi_info_block *si)
+{
+ unsigned long rate;
+
+ if (freq) {
+ rate = freq_to_sample_rate(si, sample);
+ rate = hw_limit_rate(si, rate);
+ } else {
+ /* The min/max sampling rates specifies the valid range
+ * of sample periods. If the specified sample period is
+ * out of range, limit the period to the range boundary.
+ */
+ rate = hw_limit_rate(si, sample);
+
+ /* The perf core maintains a maximum sample rate that is
+ * configurable through the sysctl interface. Ensure the
+ * sampling rate does not exceed this value. This also helps
+ * to avoid throttling when pushing samples with
+ * perf_event_overflow().
+ */
+ if (sample_rate_to_freq(si, rate) >
+ sysctl_perf_event_sample_rate) {
+ debug_sprintf_event(sfdbg, 1,
+ "Sampling rate exceeds maximum "
+ "perf sample rate\n");
+ rate = 0;
+ }
+ }
+ return rate;
+}
+
+/* The sampling information (si) contains information about the
+ * min/max sampling intervals and the CPU speed. So calculate the
+ * correct sampling interval and avoid the whole period adjust
+ * feedback loop.
+ *
+ * Since the CPU Measurement sampling facility can not handle frequency
+ * calculate the sampling interval when frequency is specified using
+ * this formula:
+ * interval := cpu_speed * 1000000 / sample_freq
+ *
+ * Returns errno on bad input and zero on success with parameter interval
+ * set to the correct sampling rate.
+ *
+ * Note: This function turns off freq bit to avoid calling function
+ * perf_adjust_period(). This causes frequency adjustment in the common
+ * code part which causes tremendous variations in the counter values.
+ */
+static int __hw_perf_event_init_rate(struct perf_event *event,
+ struct hws_qsi_info_block *si)
+{
+ struct perf_event_attr *attr = &event->attr;
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned long rate;
+
+ if (attr->freq) {
+ if (!attr->sample_freq)
+ return -EINVAL;
+ rate = getrate(attr->freq, attr->sample_freq, si);
+ attr->freq = 0; /* Don't call perf_adjust_period() */
+ SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FREQ_MODE;
+ } else {
+ rate = getrate(attr->freq, attr->sample_period, si);
+ if (!rate)
+ return -EINVAL;
+ }
+ attr->sample_period = rate;
+ SAMPL_RATE(hwc) = rate;
+ hw_init_period(hwc, SAMPL_RATE(hwc));
+ debug_sprintf_event(sfdbg, 4, "__hw_perf_event_init_rate:"
+ "cpu:%d period:%llx freq:%d,%#lx\n", event->cpu,
+ event->attr.sample_period, event->attr.freq,
+ SAMPLE_FREQ_MODE(hwc));
+ return 0;
+}
+
static int __hw_perf_event_init(struct perf_event *event)
{
struct cpu_hw_sf *cpuhw;
struct hws_qsi_info_block si;
struct perf_event_attr *attr = &event->attr;
struct hw_perf_event *hwc = &event->hw;
- unsigned long rate;
int cpu, err;
/* Reserve CPU-measurement sampling facility */
@@ -728,6 +803,12 @@
goto out;
}
+ if (si.ribm & CPU_MF_SF_RIBM_NOTAV) {
+ pr_warn("CPU Measurement Facility sampling is temporarily not available\n");
+ err = -EBUSY;
+ goto out;
+ }
+
/* Always enable basic sampling */
SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE;
@@ -746,43 +827,9 @@
if (attr->config1 & PERF_CPUM_SF_FULL_BLOCKS)
SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FULL_BLOCKS;
- /* The sampling information (si) contains information about the
- * min/max sampling intervals and the CPU speed. So calculate the
- * correct sampling interval and avoid the whole period adjust
- * feedback loop.
- */
- rate = 0;
- if (attr->freq) {
- if (!attr->sample_freq) {
- err = -EINVAL;
- goto out;
- }
- rate = freq_to_sample_rate(&si, attr->sample_freq);
- rate = hw_limit_rate(&si, rate);
- attr->freq = 0;
- attr->sample_period = rate;
- } else {
- /* The min/max sampling rates specifies the valid range
- * of sample periods. If the specified sample period is
- * out of range, limit the period to the range boundary.
- */
- rate = hw_limit_rate(&si, hwc->sample_period);
-
- /* The perf core maintains a maximum sample rate that is
- * configurable through the sysctl interface. Ensure the
- * sampling rate does not exceed this value. This also helps
- * to avoid throttling when pushing samples with
- * perf_event_overflow().
- */
- if (sample_rate_to_freq(&si, rate) >
- sysctl_perf_event_sample_rate) {
- err = -EINVAL;
- debug_sprintf_event(sfdbg, 1, "Sampling rate exceeds maximum perf sample rate\n");
- goto out;
- }
- }
- SAMPL_RATE(hwc) = rate;
- hw_init_period(hwc, SAMPL_RATE(hwc));
+ err = __hw_perf_event_init_rate(event, &si);
+ if (err)
+ goto out;
/* Initialize sample data overflow accounting */
hwc->extra_reg.reg = REG_OVERFLOW;
@@ -854,7 +901,7 @@
/* Check online status of the CPU to which the event is pinned */
if (event->cpu >= 0 && !cpu_online(event->cpu))
- return -ENODEV;
+ return -ENODEV;
/* Force reset of idle/hv excludes regardless of what the
* user requested.
@@ -905,6 +952,8 @@
if (sfb_has_pending_allocs(&cpuhw->sfb, hwc))
extend_sampling_buffer(&cpuhw->sfb, hwc);
}
+ /* Rate may be adjusted with ioctl() */
+ cpuhw->lsctl.interval = SAMPL_RATE(&cpuhw->event->hw);
}
/* (Re)enable the PMU and sampling facility */
@@ -923,9 +972,11 @@
lpp(&S390_lowcore.lpp);
debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i "
- "tear=%p dear=%p\n", cpuhw->lsctl.es, cpuhw->lsctl.cs,
- cpuhw->lsctl.ed, cpuhw->lsctl.cd,
- (void *) cpuhw->lsctl.tear, (void *) cpuhw->lsctl.dear);
+ "interval:%lx tear=%p dear=%p\n",
+ cpuhw->lsctl.es, cpuhw->lsctl.cs, cpuhw->lsctl.ed,
+ cpuhw->lsctl.cd, cpuhw->lsctl.interval,
+ (void *) cpuhw->lsctl.tear,
+ (void *) cpuhw->lsctl.dear);
}
static void cpumsf_pmu_disable(struct pmu *pmu)
@@ -1083,7 +1134,8 @@
struct hws_trailer_entry *te)
{
debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown "
- "sampling data entry: te->f=%i basic.def=%04x (%p)\n",
+ "sampling data entry: te->f=%i basic.def=%04x "
+ "(%p)\n",
te->f, sample->def, sample);
}
@@ -1216,7 +1268,7 @@
/* Timestamps are valid for full sample-data-blocks only */
debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
- "overflow=%llu timestamp=0x%llx\n",
+ "overflow=%llu timestamp=%#llx\n",
sdbt, te->overflow,
(te->f) ? trailer_timestamp(te) : 0ULL);
@@ -1600,7 +1652,7 @@
/*
* aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling
- * @cpu: On which to allocate, -1 means current
+ * @event: Event the buffer is setup for, event->cpu == -1 means current
* @pages: Array of pointers to buffer pages passed from perf core
* @nr_pages: Total pages
* @snapshot: Flag for snapshot mode
@@ -1612,8 +1664,8 @@
*
* Return the private AUX buffer structure if success or NULL if fails.
*/
-static void *aux_buffer_setup(int cpu, void **pages, int nr_pages,
- bool snapshot)
+static void *aux_buffer_setup(struct perf_event *event, void **pages,
+ int nr_pages, bool snapshot)
{
struct sf_buffer *sfb;
struct aux_buffer *aux;
@@ -1716,6 +1768,44 @@
/* Nothing to do ... updates are interrupt-driven */
}
+/* Check if the new sampling period/freqeuncy is appropriate.
+ *
+ * Return non-zero on error and zero on passed checks.
+ */
+static int cpumsf_pmu_check_period(struct perf_event *event, u64 value)
+{
+ struct hws_qsi_info_block si;
+ unsigned long rate;
+ bool do_freq;
+
+ memset(&si, 0, sizeof(si));
+ if (event->cpu == -1) {
+ if (qsi(&si))
+ return -ENODEV;
+ } else {
+ /* Event is pinned to a particular CPU, retrieve the per-CPU
+ * sampling structure for accessing the CPU-specific QSI.
+ */
+ struct cpu_hw_sf *cpuhw = &per_cpu(cpu_hw_sf, event->cpu);
+
+ si = cpuhw->qsi;
+ }
+
+ do_freq = !!SAMPLE_FREQ_MODE(&event->hw);
+ rate = getrate(do_freq, value, &si);
+ if (!rate)
+ return -EINVAL;
+
+ event->attr.sample_period = rate;
+ SAMPL_RATE(&event->hw) = rate;
+ hw_init_period(&event->hw, SAMPL_RATE(&event->hw));
+ debug_sprintf_event(sfdbg, 4, "cpumsf_pmu_check_period:"
+ "cpu:%d value:%llx period:%llx freq:%d\n",
+ event->cpu, value,
+ event->attr.sample_period, do_freq);
+ return 0;
+}
+
/* Activate sampling control.
* Next call of pmu_enable() starts sampling.
*/
@@ -1842,10 +1932,30 @@
CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF);
CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
-static struct attribute *cpumsf_pmu_events_attr[] = {
- CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
- NULL,
- NULL,
+/* Attribute list for CPU_SF.
+ *
+ * The availablitiy depends on the CPU_MF sampling facility authorization
+ * for basic + diagnositic samples. This is determined at initialization
+ * time by the sampling facility device driver.
+ * If the authorization for basic samples is turned off, it should be
+ * also turned off for diagnostic sampling.
+ *
+ * During initialization of the device driver, check the authorization
+ * level for diagnostic sampling and installs the attribute
+ * file for diagnostic sampling if necessary.
+ *
+ * For now install a placeholder to reference all possible attributes:
+ * SF_CYCLES_BASIC and SF_CYCLES_BASIC_DIAG.
+ * Add another entry for the final NULL pointer.
+ */
+enum {
+ SF_CYCLES_BASIC_ATTR_IDX = 0,
+ SF_CYCLES_BASIC_DIAG_ATTR_IDX,
+ SF_CYCLES_ATTR_MAX
+};
+
+static struct attribute *cpumsf_pmu_events_attr[SF_CYCLES_ATTR_MAX + 1] = {
+ [SF_CYCLES_BASIC_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC)
};
PMU_FORMAT_ATTR(event, "config:0-63");
@@ -1859,10 +1969,12 @@
.name = "events",
.attrs = cpumsf_pmu_events_attr,
};
+
static struct attribute_group cpumsf_pmu_format_group = {
.name = "format",
.attrs = cpumsf_pmu_format_attr,
};
+
static const struct attribute_group *cpumsf_pmu_attr_groups[] = {
&cpumsf_pmu_events_group,
&cpumsf_pmu_format_group,
@@ -1885,6 +1997,8 @@
.setup_aux = aux_buffer_setup,
.free_aux = aux_buffer_free,
+
+ .check_period = cpumsf_pmu_check_period,
};
static void cpumf_measurement_alert(struct ext_code ext_code,
@@ -1918,7 +2032,8 @@
/* Report measurement alerts only for non-PRA codes */
if (alert != CPU_MF_INT_SF_PRA)
- debug_sprintf_event(sfdbg, 6, "measurement alert: 0x%x\n", alert);
+ debug_sprintf_event(sfdbg, 6, "measurement alert: %#x\n",
+ alert);
/* Sampling authorization change request */
if (alert & CPU_MF_INT_SF_SACA)
@@ -1939,6 +2054,7 @@
sf_disable();
}
}
+
static int cpusf_pmu_setup(unsigned int cpu, int flags)
{
/* Ignore the notification if no events are scheduled on the PMU.
@@ -2040,19 +2156,25 @@
if (si.ad) {
sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
- cpumsf_pmu_events_attr[1] =
+ /* Sampling of diagnostic data authorized,
+ * install event into attribute list of PMU device.
+ */
+ cpumsf_pmu_events_attr[SF_CYCLES_BASIC_DIAG_ATTR_IDX] =
CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG);
}
sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80);
- if (!sfdbg)
+ if (!sfdbg) {
pr_err("Registering for s390dbf failed\n");
+ return -ENOMEM;
+ }
debug_register_view(sfdbg, &debug_sprintf_view);
err = register_external_irq(EXT_IRQ_MEASURE_ALERT,
cpumf_measurement_alert);
if (err) {
pr_cpumsf_err(RS_INIT_FAILURE_ALRT);
+ debug_unregister(sfdbg);
goto out;
}
@@ -2061,6 +2183,7 @@
pr_cpumsf_err(RS_INIT_FAILURE_PERF);
unregister_external_irq(EXT_IRQ_MEASURE_ALERT,
cpumf_measurement_alert);
+ debug_unregister(sfdbg);
goto out;
}
@@ -2069,5 +2192,6 @@
out:
return err;
}
+
arch_initcall(init_cpum_sampling_pmu);
core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 0d770e5..fcb6c2e 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -21,6 +21,7 @@
#include <asm/lowcore.h>
#include <asm/processor.h>
#include <asm/sysinfo.h>
+#include <asm/unwind.h>
const char *perf_pmu_name(void)
{
@@ -219,20 +220,13 @@
}
arch_initcall(service_level_perf_register);
-static int __perf_callchain_kernel(void *data, unsigned long address, int reliable)
-{
- struct perf_callchain_entry_ctx *entry = data;
-
- perf_callchain_store(entry, address);
- return 0;
-}
-
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
- if (user_mode(regs))
- return;
- dump_trace(__perf_callchain_kernel, entry, NULL, regs->gprs[15]);
+ struct unwind_state state;
+
+ unwind_for_each_frame(&state, current, regs, 0)
+ perf_callchain_store(entry, state.ip);
}
/* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S
index 3e62aae..59dee9d 100644
--- a/arch/s390/kernel/pgm_check.S
+++ b/arch/s390/kernel/pgm_check.S
@@ -7,7 +7,7 @@
#include <linux/linkage.h>
-#define PGM_CHECK(handler) .long handler
+#define PGM_CHECK(handler) .quad handler
#define PGM_CHECK_DEFAULT PGM_CHECK(default_trap_handler)
/*
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 6e758bb..b0afec6 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -37,6 +37,7 @@
#include <asm/irq.h>
#include <asm/nmi.h>
#include <asm/smp.h>
+#include <asm/stacktrace.h>
#include <asm/switch_to.h>
#include <asm/runtime_instr.h>
#include "entry.h"
@@ -183,20 +184,30 @@
if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p))
return 0;
+
+ if (!try_get_task_stack(p))
+ return 0;
+
low = task_stack_page(p);
high = (struct stack_frame *) task_pt_regs(p);
sf = (struct stack_frame *) p->thread.ksp;
- if (sf <= low || sf > high)
- return 0;
- for (count = 0; count < 16; count++) {
- sf = (struct stack_frame *) sf->back_chain;
- if (sf <= low || sf > high)
- return 0;
- return_address = sf->gprs[8];
- if (!in_sched_functions(return_address))
- return return_address;
+ if (sf <= low || sf > high) {
+ return_address = 0;
+ goto out;
}
- return 0;
+ for (count = 0; count < 16; count++) {
+ sf = (struct stack_frame *)READ_ONCE_NOCHECK(sf->back_chain);
+ if (sf <= low || sf > high) {
+ return_address = 0;
+ goto out;
+ }
+ return_address = READ_ONCE_NOCHECK(sf->gprs[8]);
+ if (!in_sched_functions(return_address))
+ goto out;
+ }
+out:
+ put_task_stack(p);
+ return return_address;
}
unsigned long arch_align_stack(unsigned long sp)
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 6fe2e18..6ebc211 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -7,6 +7,7 @@
#define KMSG_COMPONENT "cpu"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+#include <linux/stop_machine.h>
#include <linux/cpufeature.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
@@ -31,6 +32,7 @@
};
static DEFINE_PER_CPU(struct cpu_info, cpu_info);
+static DEFINE_PER_CPU(int, cpu_relax_retry);
static bool machine_has_cpu_mhz;
@@ -58,15 +60,20 @@
on_each_cpu(update_cpu_mhz, NULL, 0);
}
-void notrace cpu_relax_yield(void)
+void notrace stop_machine_yield(const struct cpumask *cpumask)
{
- if (!smp_cpu_mtid && MACHINE_HAS_DIAG44) {
- diag_stat_inc(DIAG_STAT_X044);
- asm volatile("diag 0,0,0x44");
+ int cpu, this_cpu;
+
+ this_cpu = smp_processor_id();
+ if (__this_cpu_inc_return(cpu_relax_retry) >= spin_retry) {
+ __this_cpu_write(cpu_relax_retry, 0);
+ cpu = cpumask_next_wrap(this_cpu, cpumask, this_cpu, false);
+ if (cpu >= nr_cpu_ids)
+ return;
+ if (arch_vcpu_is_preempted(cpu))
+ smp_yield_cpu(cpu);
}
- barrier();
}
-EXPORT_SYMBOL(cpu_relax_yield);
/*
* cpu_init - initializes state that is per-CPU.
@@ -109,7 +116,8 @@
{
static const char *hwcap_str[] = {
"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
- "edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe", "gs"
+ "edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe", "gs",
+ "vxe2", "vxp", "sort", "dflt"
};
static const char * const int_hwcap_str[] = {
"sie"
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index cd3df55..ad71132 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -24,7 +24,6 @@
#include <linux/seccomp.h>
#include <linux/compat.h>
#include <trace/syscall.h>
-#include <asm/segment.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 7f14adf..4a22163 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -73,6 +73,7 @@
lgr %r9,%r2
lgr %r2,%r3
BR_EX %r9
+ENDPROC(store_status)
.section .bss
.align 8
diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S
index c97c2d4..fe39667 100644
--- a/arch/s390/kernel/relocate_kernel.S
+++ b/arch/s390/kernel/relocate_kernel.S
@@ -58,11 +58,15 @@
j .base
.done:
sgr %r0,%r0 # clear register r0
+ cghi %r3,0
+ je .diag
la %r4,load_psw-.base(%r13) # load psw-address into the register
o %r3,4(%r4) # or load address into psw
st %r3,4(%r4)
mvc 0(8,%r0),0(%r4) # copy psw to absolute address 0
+ .diag:
diag %r0,%r0,0x308
+ENDPROC(relocate_kernel)
.align 8
load_psw:
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c637c12..3ff291b 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -34,7 +34,6 @@
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/initrd.h>
-#include <linux/bootmem.h>
#include <linux/root_dev.h>
#include <linux/console.h>
#include <linux/kernel_stat.h>
@@ -49,7 +48,9 @@
#include <linux/crash_dump.h>
#include <linux/memory.h>
#include <linux/compat.h>
+#include <linux/start_kernel.h>
+#include <asm/boot_data.h>
#include <asm/ipl.h>
#include <asm/facility.h>
#include <asm/smp.h>
@@ -65,10 +66,13 @@
#include <asm/diag.h>
#include <asm/os_info.h>
#include <asm/sclp.h>
+#include <asm/stacktrace.h>
#include <asm/sysinfo.h>
#include <asm/numa.h>
#include <asm/alternative.h>
#include <asm/nospec-branch.h>
+#include <asm/mem_detect.h>
+#include <asm/uv.h>
#include "entry.h"
/*
@@ -88,9 +92,25 @@
unsigned long int_hwcap = 0;
-int __initdata memory_end_set;
-unsigned long __initdata memory_end;
-unsigned long __initdata max_physmem_end;
+#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
+int __bootdata_preserved(prot_virt_guest);
+#endif
+
+int __bootdata(noexec_disabled);
+int __bootdata(memory_end_set);
+unsigned long __bootdata(memory_end);
+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);
+struct exception_table_entry *__bootdata_preserved(__stop_dma_ex_table);
+unsigned long __bootdata_preserved(__swsusp_reset_dma);
+unsigned long __bootdata_preserved(__stext_dma);
+unsigned long __bootdata_preserved(__etext_dma);
+unsigned long __bootdata_preserved(__sdma);
+unsigned long __bootdata_preserved(__edma);
+unsigned long __bootdata_preserved(__kaslr_offset);
unsigned long VMALLOC_START;
EXPORT_SYMBOL(VMALLOC_START);
@@ -149,15 +169,15 @@
static int __init conmode_setup(char *str)
{
#if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE)
- if (strncmp(str, "hwc", 4) == 0 || strncmp(str, "sclp", 5) == 0)
+ if (!strcmp(str, "hwc") || !strcmp(str, "sclp"))
SET_CONSOLE_SCLP;
#endif
#if defined(CONFIG_TN3215_CONSOLE)
- if (strncmp(str, "3215", 5) == 0)
+ if (!strcmp(str, "3215"))
SET_CONSOLE_3215;
#endif
#if defined(CONFIG_TN3270_CONSOLE)
- if (strncmp(str, "3270", 5) == 0)
+ if (!strcmp(str, "3270"))
SET_CONSOLE_3270;
#endif
set_preferred_console();
@@ -192,7 +212,7 @@
#endif
return;
}
- if (strncmp(ptr + 8, "3270", 4) == 0) {
+ if (str_has_prefix(ptr + 8, "3270")) {
#if defined(CONFIG_TN3270_CONSOLE)
SET_CONSOLE_3270;
#elif defined(CONFIG_TN3215_CONSOLE)
@@ -200,7 +220,7 @@
#elif defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE)
SET_CONSOLE_SCLP;
#endif
- } else if (strncmp(ptr + 8, "3215", 4) == 0) {
+ } else if (str_has_prefix(ptr + 8, "3215")) {
#if defined(CONFIG_TN3215_CONSOLE)
SET_CONSOLE_3215;
#elif defined(CONFIG_TN3270_CONSOLE)
@@ -283,27 +303,81 @@
void (*pm_power_off)(void) = machine_power_off;
EXPORT_SYMBOL_GPL(pm_power_off);
-static int __init early_parse_mem(char *p)
-{
- memory_end = memparse(p, &p);
- memory_end &= PAGE_MASK;
- memory_end_set = 1;
- return 0;
-}
-early_param("mem", early_parse_mem);
-
-static int __init parse_vmalloc(char *arg)
-{
- if (!arg)
- return -EINVAL;
- VMALLOC_END = (memparse(arg, &arg) + PAGE_SIZE - 1) & PAGE_MASK;
- return 0;
-}
-early_param("vmalloc", parse_vmalloc);
-
void *restart_stack __section(.data);
-static void __init setup_lowcore(void)
+unsigned long stack_alloc(void)
+{
+#ifdef CONFIG_VMAP_STACK
+ return (unsigned long)
+ __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
+ VMALLOC_START, VMALLOC_END,
+ THREADINFO_GFP,
+ PAGE_KERNEL, 0, NUMA_NO_NODE,
+ __builtin_return_address(0));
+#else
+ return __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
+#endif
+}
+
+void stack_free(unsigned long stack)
+{
+#ifdef CONFIG_VMAP_STACK
+ vfree((void *) stack);
+#else
+ free_pages(stack, THREAD_SIZE_ORDER);
+#endif
+}
+
+int __init arch_early_irq_init(void)
+{
+ unsigned long stack;
+
+ stack = __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
+ if (!stack)
+ panic("Couldn't allocate async stack");
+ S390_lowcore.async_stack = stack + STACK_INIT_OFFSET;
+ return 0;
+}
+
+static int __init async_stack_realloc(void)
+{
+ unsigned long old, new;
+
+ old = S390_lowcore.async_stack - STACK_INIT_OFFSET;
+ new = stack_alloc();
+ if (!new)
+ panic("Couldn't allocate async stack");
+ S390_lowcore.async_stack = new + STACK_INIT_OFFSET;
+ free_pages(old, THREAD_SIZE_ORDER);
+ return 0;
+}
+early_initcall(async_stack_realloc);
+
+void __init arch_call_rest_init(void)
+{
+ struct stack_frame *frame;
+ unsigned long stack;
+
+ stack = stack_alloc();
+ if (!stack)
+ panic("Couldn't allocate kernel stack");
+ current->stack = (void *) stack;
+#ifdef CONFIG_VMAP_STACK
+ current->stack_vm_area = (void *) stack;
+#endif
+ set_task_stack_end_magic(current);
+ stack += STACK_INIT_OFFSET;
+ S390_lowcore.kernel_stack = stack;
+ frame = (struct stack_frame *) stack;
+ memset(frame, 0, sizeof(*frame));
+ /* Branch to rest_init on the new stack, never returns */
+ asm volatile(
+ " la 15,0(%[_frame])\n"
+ " jg rest_init\n"
+ : : [_frame] "a" (frame));
+}
+
+static void __init setup_lowcore_dat_off(void)
{
struct lowcore *lc;
@@ -311,32 +385,27 @@
* Setup lowcore for boot cpu
*/
BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * PAGE_SIZE);
- lc = memblock_virt_alloc_low(sizeof(*lc), sizeof(*lc));
+ lc = memblock_alloc_low(sizeof(*lc), sizeof(*lc));
+ if (!lc)
+ panic("%s: Failed to allocate %zu bytes align=%zx\n",
+ __func__, sizeof(*lc), sizeof(*lc));
+
lc->restart_psw.mask = PSW_KERNEL_BITS;
lc->restart_psw.addr = (unsigned long) restart_int_handler;
- lc->external_new_psw.mask = PSW_KERNEL_BITS |
- PSW_MASK_DAT | PSW_MASK_MCHECK;
+ lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
lc->external_new_psw.addr = (unsigned long) ext_int_handler;
lc->svc_new_psw.mask = PSW_KERNEL_BITS |
- PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
+ PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
lc->svc_new_psw.addr = (unsigned long) system_call;
- lc->program_new_psw.mask = PSW_KERNEL_BITS |
- PSW_MASK_DAT | PSW_MASK_MCHECK;
+ lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
lc->program_new_psw.addr = (unsigned long) pgm_check_handler;
lc->mcck_new_psw.mask = PSW_KERNEL_BITS;
lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler;
- lc->io_new_psw.mask = PSW_KERNEL_BITS |
- PSW_MASK_DAT | PSW_MASK_MCHECK;
+ lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
lc->io_new_psw.addr = (unsigned long) io_int_handler;
lc->clock_comparator = clock_comparator_max;
- lc->kernel_stack = ((unsigned long) &init_thread_union)
+ lc->nodat_stack = ((unsigned long) &init_thread_union)
+ THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
- lc->async_stack = (unsigned long)
- memblock_virt_alloc(ASYNC_SIZE, ASYNC_SIZE)
- + ASYNC_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
- lc->panic_stack = (unsigned long)
- memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE)
- + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
lc->current_task = (unsigned long)&init_task;
lc->lpp = LPP_MAGIC;
lc->machine_flags = S390_lowcore.machine_flags;
@@ -357,8 +426,15 @@
lc->last_update_timer = S390_lowcore.last_update_timer;
lc->last_update_clock = S390_lowcore.last_update_clock;
- restart_stack = memblock_virt_alloc(ASYNC_SIZE, ASYNC_SIZE);
- restart_stack += ASYNC_SIZE;
+ /*
+ * Allocate the global restart stack which is the same for
+ * all CPUs in cast *one* of them does a PSW restart.
+ */
+ restart_stack = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
+ if (!restart_stack)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+ __func__, THREAD_SIZE, THREAD_SIZE);
+ restart_stack += STACK_INIT_OFFSET;
/*
* Set up PSW restart to call ipl.c:do_restart(). Copy the relevant
@@ -377,17 +453,25 @@
mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source);
mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw);
-#ifdef CONFIG_SMP
lc->spinlock_lockval = arch_spin_lockval(0);
lc->spinlock_index = 0;
arch_spin_lock_setup(0);
-#endif
lc->br_r1_trampoline = 0x07f1; /* br %r1 */
set_prefix((u32)(unsigned long) lc);
lowcore_ptr[0] = lc;
}
+static void __init setup_lowcore_dat_on(void)
+{
+ __ctl_clear_bit(0, 28);
+ S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT;
+ S390_lowcore.svc_new_psw.mask |= PSW_MASK_DAT;
+ S390_lowcore.program_new_psw.mask |= PSW_MASK_DAT;
+ S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT;
+ __ctl_set_bit(0, 28);
+}
+
static struct resource code_resource = {
.name = "Kernel code",
.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
@@ -423,7 +507,10 @@
bss_resource.end = (unsigned long) __bss_stop - 1;
for_each_memblock(memory, reg) {
- res = memblock_virt_alloc(sizeof(*res), 8);
+ res = memblock_alloc(sizeof(*res), 8);
+ if (!res)
+ panic("%s: Failed to allocate %zu bytes align=0x%x\n",
+ __func__, sizeof(*res), 8);
res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
res->name = "System RAM";
@@ -437,7 +524,10 @@
std_res->start > res->end)
continue;
if (std_res->end > res->end) {
- sub_res = memblock_virt_alloc(sizeof(*sub_res), 8);
+ sub_res = memblock_alloc(sizeof(*sub_res), 8);
+ if (!sub_res)
+ panic("%s: Failed to allocate %zu bytes align=0x%x\n",
+ __func__, sizeof(*sub_res), 8);
*sub_res = *std_res;
sub_res->end = res->end;
std_res->start = res->end + 1;
@@ -465,21 +555,27 @@
static void __init setup_memory_end(void)
{
- unsigned long vmax, vmalloc_size, tmp;
+ unsigned long vmax, tmp;
- /* Choose kernel address space layout: 2, 3, or 4 levels. */
- vmalloc_size = VMALLOC_END ?: (128UL << 30) - MODULES_LEN;
- tmp = (memory_end ?: max_physmem_end) / 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 */
+ /* Choose kernel address space layout: 3 or 4 levels. */
+ if (IS_ENABLED(CONFIG_KASAN)) {
+ vmax = IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING)
+ ? _REGION1_SIZE
+ : _REGION2_SIZE;
+ } else {
+ tmp = (memory_end ?: max_physmem_end) / 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;
MODULES_VADDR = MODULES_END - MODULES_LEN;
VMALLOC_END = MODULES_VADDR;
- VMALLOC_START = vmax - vmalloc_size;
+ VMALLOC_START = VMALLOC_END - vmalloc_size;
/* Split remaining virtual space between 1:1 mapping & vmemmap array */
tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page));
@@ -491,7 +587,12 @@
vmemmap = (struct page *) tmp;
/* Take care that memory_end is set and <= vmemmap */
- memory_end = min(memory_end ?: max_physmem_end, tmp);
+ memory_end = min(memory_end ?: max_physmem_end, (unsigned long)vmemmap);
+#ifdef CONFIG_KASAN
+ /* fit in kasan shadow memory region between 1:1 and vmemmap */
+ memory_end = min(memory_end, 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);
@@ -532,17 +633,8 @@
*/
static void reserve_memory_end(void)
{
-#ifdef CONFIG_CRASH_DUMP
- if (ipl_info.type == IPL_TYPE_FCP_DUMP &&
- !OLDMEM_BASE && sclp.hsa_size) {
- memory_end = sclp.hsa_size;
- memory_end &= PAGE_MASK;
- memory_end_set = 1;
- }
-#endif
- if (!memory_end_set)
- return;
- memblock_reserve(memory_end, ULONG_MAX);
+ if (memory_end_set)
+ memblock_reserve(memory_end, ULONG_MAX);
}
/*
@@ -650,6 +742,71 @@
}
/*
+ * Reserve the memory area used to pass the certificate lists
+ */
+static void __init reserve_certificate_list(void)
+{
+ if (ipl_cert_list_addr)
+ memblock_reserve(ipl_cert_list_addr, ipl_cert_list_size);
+}
+
+static void __init reserve_mem_detect_info(void)
+{
+ unsigned long start, size;
+
+ get_mem_detect_reserved(&start, &size);
+ if (size)
+ memblock_reserve(start, size);
+}
+
+static void __init free_mem_detect_info(void)
+{
+ unsigned long start, size;
+
+ get_mem_detect_reserved(&start, &size);
+ if (size)
+ memblock_free(start, size);
+}
+
+static void __init memblock_physmem_add(phys_addr_t start, phys_addr_t size)
+{
+ memblock_dbg("memblock_physmem_add: [%#016llx-%#016llx]\n",
+ start, start + size - 1);
+ memblock_add_range(&memblock.memory, start, size, 0, 0);
+ memblock_add_range(&memblock.physmem, start, size, 0, 0);
+}
+
+static const char * __init get_mem_info_source(void)
+{
+ switch (mem_detect.info_source) {
+ case MEM_DETECT_SCLP_STOR_INFO:
+ return "sclp storage info";
+ case MEM_DETECT_DIAG260:
+ return "diag260";
+ case MEM_DETECT_SCLP_READ_INFO:
+ return "sclp read info";
+ case MEM_DETECT_BIN_SEARCH:
+ return "binary search";
+ }
+ return "none";
+}
+
+static void __init memblock_add_mem_detect_info(void)
+{
+ unsigned long start, end;
+ int i;
+
+ memblock_dbg("physmem info source: %s (%hhd)\n",
+ get_mem_info_source(), mem_detect.info_source);
+ /* keep memblock lists close to the kernel */
+ memblock_set_bottom_up(true);
+ for_each_mem_detect_block(i, &start, &end)
+ memblock_physmem_add(start, end - start);
+ memblock_set_bottom_up(false);
+ memblock_dump_all();
+}
+
+/*
* Check for initrd being in usable memory
*/
static void __init check_initrd(void)
@@ -671,18 +828,10 @@
{
unsigned long start_pfn = PFN_UP(__pa(_end));
-#ifdef CONFIG_DMA_API_DEBUG
- /*
- * DMA_API_DEBUG code stumbles over addresses from the
- * range [PARMAREA_END, _stext]. Mark the memory as reserved
- * so it is not used for CONFIG_DMA_API_DEBUG=y.
- */
- memblock_reserve(0, PFN_PHYS(start_pfn));
-#else
- memblock_reserve(0, PARMAREA_END);
+ memblock_reserve(0, HEAD_END);
memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
- (unsigned long)_stext);
-#endif
+ memblock_reserve(__sdma, __edma - __sdma);
}
static void __init setup_memory(void)
@@ -780,7 +929,15 @@
elf_hwcap |= HWCAP_S390_VXRS_EXT;
if (test_facility(135))
elf_hwcap |= HWCAP_S390_VXRS_BCD;
+ if (test_facility(148))
+ elf_hwcap |= HWCAP_S390_VXRS_EXT2;
+ if (test_facility(152))
+ elf_hwcap |= HWCAP_S390_VXRS_PDE;
}
+ if (test_facility(150))
+ elf_hwcap |= HWCAP_S390_SORT;
+ if (test_facility(151))
+ elf_hwcap |= HWCAP_S390_DFLT;
/*
* Guarded storage support HWCAP_S390_GS is bit 12.
@@ -824,6 +981,10 @@
case 0x3907:
strcpy(elf_platform, "z14");
break;
+ case 0x8561:
+ case 0x8562:
+ strcpy(elf_platform, "z15");
+ break;
}
/*
@@ -843,7 +1004,11 @@
{
struct sysinfo_3_2_2 *vmms;
- vmms = (struct sysinfo_3_2_2 *) memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ vmms = (struct sysinfo_3_2_2 *) memblock_phys_alloc(PAGE_SIZE,
+ PAGE_SIZE);
+ if (!vmms)
+ panic("Failed to allocate memory for sysinfo structure\n");
+
if (stsi(vmms, 3, 2, 2) == 0 && vmms->count)
add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count);
memblock_free((unsigned long) vmms, PAGE_SIZE);
@@ -866,6 +1031,57 @@
}
/*
+ * Issue diagnose 318 to set the control program name and
+ * version codes.
+ */
+static void __init setup_control_program_code(void)
+{
+ union diag318_info diag318_info = {
+ .cpnc = CPNC_LINUX,
+ .cpvc_linux = 0,
+ .cpvc_distro = {0},
+ };
+
+ if (!sclp.has_diag318)
+ return;
+
+ diag_stat_inc(DIAG_STAT_X318);
+ asm volatile("diag %0,0,0x318\n" : : "d" (diag318_info.val));
+}
+
+/*
+ * Print the component list from the IPL report
+ */
+static void __init log_component_list(void)
+{
+ struct ipl_rb_component_entry *ptr, *end;
+ char *str;
+
+ if (!early_ipl_comp_list_addr)
+ return;
+ if (ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR)
+ pr_info("Linux is running with Secure-IPL enabled\n");
+ else
+ pr_info("Linux is running with Secure-IPL disabled\n");
+ ptr = (void *) early_ipl_comp_list_addr;
+ end = (void *) ptr + early_ipl_comp_list_size;
+ pr_info("The IPL report contains the following components:\n");
+ while (ptr < end) {
+ if (ptr->flags & IPL_RB_COMPONENT_FLAG_SIGNED) {
+ if (ptr->flags & IPL_RB_COMPONENT_FLAG_VERIFIED)
+ str = "signed, verified";
+ else
+ str = "signed, verification failed";
+ } else {
+ str = "not signed";
+ }
+ pr_info("%016llx - %016llx (%s)\n",
+ ptr->addr, ptr->addr + ptr->len, str);
+ ptr++;
+ }
+}
+
+/*
* Setup function called from init/main.c just after the banner
* was printed.
*/
@@ -882,6 +1098,10 @@
pr_info("Linux is running under KVM in 64-bit mode\n");
else if (MACHINE_IS_LPAR)
pr_info("Linux is running natively in 64-bit mode\n");
+ else
+ pr_info("Linux is running as a guest in 64-bit mode\n");
+
+ log_component_list();
/* Have one command line that is parsed and saved in /proc/cmdline */
/* boot_command_line has been already set up in early.c */
@@ -889,8 +1109,7 @@
ROOT_DEV = Root_RAM0;
- /* Is init_mm really needed? */
- init_mm.start_code = PAGE_OFFSET;
+ init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = (unsigned long) _end;
@@ -907,17 +1126,21 @@
os_info_init();
setup_ipl();
setup_task_size();
+ setup_control_program_code();
/* Do some memory reservations *before* memory is added to memblock */
reserve_memory_end();
reserve_oldmem();
reserve_kernel();
reserve_initrd();
+ reserve_certificate_list();
+ reserve_mem_detect_info();
memblock_allow_resize();
/* Get information about *all* installed memory */
- detect_memory_memblock();
+ memblock_add_mem_detect_info();
+ free_mem_detect_info();
remove_oldmem();
/*
@@ -944,7 +1167,7 @@
#endif
setup_resources();
- setup_lowcore();
+ setup_lowcore_dat_off();
smp_fill_possible_mask();
cpu_detect_mhz_feature();
cpu_init();
@@ -957,6 +1180,12 @@
*/
paging_init();
+ /*
+ * After paging_init created the kernel page table, the new PSWs
+ * in lowcore can now run with DAT enabled.
+ */
+ setup_lowcore_dat_on();
+
/* Setup default console */
conmode_default();
set_preferred_console();
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 22f0824..e6fca54 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -232,7 +232,7 @@
load_sigregs();
return regs->gprs[2];
badframe:
- force_sig(SIGSEGV, current);
+ force_sig(SIGSEGV);
return 0;
}
@@ -256,7 +256,7 @@
load_sigregs();
return regs->gprs[2];
badframe:
- force_sig(SIGSEGV, current);
+ force_sig(SIGSEGV);
return 0;
}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 2f8f7d7..4497465 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -20,7 +20,7 @@
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/workqueue.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/mm.h>
@@ -35,7 +35,6 @@
#include <linux/sched/hotplug.h>
#include <linux/sched/task_stack.h>
#include <linux/crash_dump.h>
-#include <linux/memblock.h>
#include <linux/kprobes.h>
#include <asm/asm-offsets.h>
#include <asm/diag.h>
@@ -54,6 +53,7 @@
#include <asm/sigp.h>
#include <asm/idle.h>
#include <asm/nmi.h>
+#include <asm/stacktrace.h>
#include <asm/topology.h>
#include "entry.h"
@@ -186,36 +186,34 @@
pcpu_sigp_retry(pcpu, order, 0);
}
-#define ASYNC_FRAME_OFFSET (ASYNC_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE)
-#define PANIC_FRAME_OFFSET (PAGE_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE)
-
static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
{
- unsigned long async_stack, panic_stack;
+ unsigned long async_stack, nodat_stack;
struct lowcore *lc;
if (pcpu != &pcpu_devices[0]) {
pcpu->lowcore = (struct lowcore *)
__get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);
- async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
- panic_stack = __get_free_page(GFP_KERNEL);
- if (!pcpu->lowcore || !panic_stack || !async_stack)
+ nodat_stack = __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
+ if (!pcpu->lowcore || !nodat_stack)
goto out;
} else {
- async_stack = pcpu->lowcore->async_stack - ASYNC_FRAME_OFFSET;
- panic_stack = pcpu->lowcore->panic_stack - PANIC_FRAME_OFFSET;
+ nodat_stack = pcpu->lowcore->nodat_stack - STACK_INIT_OFFSET;
}
+ async_stack = stack_alloc();
+ if (!async_stack)
+ goto out;
lc = pcpu->lowcore;
memcpy(lc, &S390_lowcore, 512);
memset((char *) lc + 512, 0, sizeof(*lc) - 512);
- lc->async_stack = async_stack + ASYNC_FRAME_OFFSET;
- lc->panic_stack = panic_stack + PANIC_FRAME_OFFSET;
+ lc->async_stack = async_stack + STACK_INIT_OFFSET;
+ lc->nodat_stack = nodat_stack + STACK_INIT_OFFSET;
lc->cpu_nr = cpu;
lc->spinlock_lockval = arch_spin_lockval(cpu);
lc->spinlock_index = 0;
lc->br_r1_trampoline = 0x07f1; /* br %r1 */
if (nmi_alloc_per_cpu(lc))
- goto out;
+ goto out_async;
if (vdso_alloc_per_cpu(lc))
goto out_mcesa;
lowcore_ptr[cpu] = lc;
@@ -224,32 +222,35 @@
out_mcesa:
nmi_free_per_cpu(lc);
+out_async:
+ stack_free(async_stack);
out:
if (pcpu != &pcpu_devices[0]) {
- free_page(panic_stack);
- free_pages(async_stack, ASYNC_ORDER);
+ free_pages(nodat_stack, THREAD_SIZE_ORDER);
free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
}
return -ENOMEM;
}
-#ifdef CONFIG_HOTPLUG_CPU
-
static void pcpu_free_lowcore(struct pcpu *pcpu)
{
+ unsigned long async_stack, nodat_stack, lowcore;
+
+ nodat_stack = pcpu->lowcore->nodat_stack - STACK_INIT_OFFSET;
+ async_stack = pcpu->lowcore->async_stack - STACK_INIT_OFFSET;
+ lowcore = (unsigned long) pcpu->lowcore;
+
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])
return;
- free_page(pcpu->lowcore->panic_stack-PANIC_FRAME_OFFSET);
- free_pages(pcpu->lowcore->async_stack-ASYNC_FRAME_OFFSET, ASYNC_ORDER);
- free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
+ free_pages(nodat_stack, THREAD_SIZE_ORDER);
+ free_pages(lowcore, LC_ORDER);
}
-#endif /* CONFIG_HOTPLUG_CPU */
-
static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
{
struct lowcore *lc = pcpu->lowcore;
@@ -262,7 +263,8 @@
lc->percpu_offset = __per_cpu_offset[cpu];
lc->kernel_asce = S390_lowcore.kernel_asce;
lc->machine_flags = S390_lowcore.machine_flags;
- lc->user_timer = lc->system_timer = lc->steal_timer = 0;
+ lc->user_timer = lc->system_timer =
+ lc->steal_timer = lc->avg_steal_timer = 0;
__ctl_store(lc->cregs_save_area, 0, 15);
save_access_regs((unsigned int *) lc->access_regs_save_area);
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
@@ -293,7 +295,7 @@
{
struct lowcore *lc = pcpu->lowcore;
- lc->restart_stack = lc->kernel_stack;
+ lc->restart_stack = lc->nodat_stack;
lc->restart_fn = (unsigned long) func;
lc->restart_data = (unsigned long) data;
lc->restart_source = -1UL;
@@ -303,15 +305,21 @@
/*
* Call function via PSW restart on pcpu and stop the current cpu.
*/
-static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *),
- void *data, unsigned long stack)
+static void __pcpu_delegate(void (*func)(void*), void *data)
+{
+ func(data); /* should not return */
+}
+
+static void __no_sanitize_address pcpu_delegate(struct pcpu *pcpu,
+ void (*func)(void *),
+ void *data, unsigned long stack)
{
struct lowcore *lc = lowcore_ptr[pcpu - pcpu_devices];
unsigned long source_cpu = stap();
- __load_psw_mask(PSW_KERNEL_BITS);
+ __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
if (pcpu->address == source_cpu)
- func(data); /* should not return */
+ CALL_ON_STACK(__pcpu_delegate, stack, 2, func, data);
/* Stop target cpu (if func returns this stops the current cpu). */
pcpu_sigp_retry(pcpu, SIGP_STOP, 0);
/* Restart func on the target cpu and stop the current cpu. */
@@ -371,9 +379,13 @@
*/
void smp_call_ipl_cpu(void (*func)(void *), void *data)
{
+ struct lowcore *lc = pcpu_devices->lowcore;
+
+ if (pcpu_devices[0].address == stap())
+ lc = &S390_lowcore;
+
pcpu_delegate(&pcpu_devices[0], func, data,
- pcpu_devices->lowcore->panic_stack -
- PANIC_FRAME_OFFSET + PAGE_SIZE);
+ lc->nodat_stack);
}
int smp_find_processor_id(u16 address)
@@ -402,7 +414,7 @@
diag_stat_inc_norecursion(DIAG_STAT_X09C);
asm volatile("diag %0,0,0x9c"
: : "d" (pcpu_devices[cpu].address));
- } else if (MACHINE_HAS_DIAG44) {
+ } else if (MACHINE_HAS_DIAG44 && !smp_cpu_mtid) {
diag_stat_inc_norecursion(DIAG_STAT_X044);
asm volatile("diag 0,0,0x44");
}
@@ -642,7 +654,11 @@
/* No previous system present, normal boot. */
return;
/* Allocate a page as dumping area for the store status sigps */
- page = memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, 1UL << 31);
+ page = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0, 1UL << 31);
+ if (!page)
+ panic("ERROR: Failed to allocate %lx bytes below %lx\n",
+ PAGE_SIZE, 1UL << 31);
+
/* Set multi-threading state to the previous system. */
pcpu_set_smt(sclp.mtid_prev);
boot_cpu_addr = stap();
@@ -670,7 +686,7 @@
smp_save_cpu_regs(sa, addr, is_boot_cpu, page);
}
memblock_free(page, PAGE_SIZE);
- diag308_reset();
+ diag_dma_ops.diag308_reset();
pcpu_set_smt(0);
}
#endif /* CONFIG_CRASH_DUMP */
@@ -751,7 +767,10 @@
u16 address;
/* Get CPU information */
- info = memblock_virt_alloc(sizeof(*info), 8);
+ info = memblock_alloc(sizeof(*info), 8);
+ if (!info)
+ panic("%s: Failed to allocate %zu bytes align=0x%x\n",
+ __func__, sizeof(*info), 8);
smp_get_core_info(info, 1);
/* Find boot CPU type */
if (sclp.has_core_type) {
@@ -791,37 +810,42 @@
memblock_free_early((unsigned long)info, sizeof(*info));
}
-/*
- * Activate a secondary processor.
- */
-static void smp_start_secondary(void *cpuvoid)
+static void smp_init_secondary(void)
{
int cpu = smp_processor_id();
S390_lowcore.last_update_clock = get_tod_clock();
- S390_lowcore.restart_stack = (unsigned long) restart_stack;
- S390_lowcore.restart_fn = (unsigned long) do_restart;
- S390_lowcore.restart_data = 0;
- S390_lowcore.restart_source = -1UL;
restore_access_regs(S390_lowcore.access_regs_save_area);
- __ctl_load(S390_lowcore.cregs_save_area, 0, 15);
- __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
cpu_init();
preempt_disable();
init_cpu_timer();
vtime_init();
pfault_init();
- notify_cpu_starting(cpu);
+ notify_cpu_starting(smp_processor_id());
if (topology_cpu_dedicated(cpu))
set_cpu_flag(CIF_DEDICATED_CPU);
else
clear_cpu_flag(CIF_DEDICATED_CPU);
- set_cpu_online(cpu, true);
+ set_cpu_online(smp_processor_id(), true);
inc_irq_stat(CPU_RST);
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
+/*
+ * Activate a secondary processor.
+ */
+static void __no_sanitize_address smp_start_secondary(void *cpuvoid)
+{
+ S390_lowcore.restart_stack = (unsigned long) restart_stack;
+ S390_lowcore.restart_fn = (unsigned long) do_restart;
+ S390_lowcore.restart_data = 0;
+ S390_lowcore.restart_source = -1UL;
+ __ctl_load(S390_lowcore.cregs_save_area, 0, 15);
+ __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
+ CALL_ON_STACK(smp_init_secondary, S390_lowcore.kernel_stack, 0);
+}
+
/* Upping and downing of CPUs */
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
@@ -867,8 +891,6 @@
}
early_param("possible_cpus", _setup_possible_cpus);
-#ifdef CONFIG_HOTPLUG_CPU
-
int __cpu_disable(void)
{
unsigned long cregs[16];
@@ -909,8 +931,6 @@
for (;;) ;
}
-#endif /* CONFIG_HOTPLUG_CPU */
-
void __init smp_fill_possible_mask(void)
{
unsigned int possible, sclp_max, cpu;
@@ -968,7 +988,6 @@
return 0;
}
-#ifdef CONFIG_HOTPLUG_CPU
static ssize_t cpu_configure_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -1045,7 +1064,6 @@
return rc ? rc : count;
}
static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
-#endif /* CONFIG_HOTPLUG_CPU */
static ssize_t show_cpu_address(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -1055,9 +1073,7 @@
static DEVICE_ATTR(address, 0444, show_cpu_address, NULL);
static struct attribute *cpu_common_attrs[] = {
-#ifdef CONFIG_HOTPLUG_CPU
&dev_attr_configure.attr,
-#endif
&dev_attr_address.attr,
NULL,
};
@@ -1116,15 +1132,11 @@
out_topology:
sysfs_remove_group(&s->kobj, &cpu_common_attr_group);
out_cpu:
-#ifdef CONFIG_HOTPLUG_CPU
unregister_cpu(c);
-#endif
out:
return rc;
}
-#ifdef CONFIG_HOTPLUG_CPU
-
int __ref smp_rescan_cpus(void)
{
struct sclp_core_info *info;
@@ -1152,21 +1164,22 @@
{
int rc;
+ rc = lock_device_hotplug_sysfs();
+ if (rc)
+ return rc;
rc = smp_rescan_cpus();
+ unlock_device_hotplug();
return rc ? rc : count;
}
static DEVICE_ATTR_WO(rescan);
-#endif /* CONFIG_HOTPLUG_CPU */
static int __init s390_smp_init(void)
{
int cpu, rc = 0;
-#ifdef CONFIG_HOTPLUG_CPU
rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan);
if (rc)
return rc;
-#endif
for_each_present_cpu(cpu) {
rc = smp_add_present_cpu(cpu);
if (rc)
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 460dcfb..f8fc4f8 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -6,70 +6,19 @@
* Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
*/
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
#include <linux/stacktrace.h>
-#include <linux/kallsyms.h>
-#include <linux/export.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
-static int __save_address(void *data, unsigned long address, int nosched)
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+ struct task_struct *task, struct pt_regs *regs)
{
- struct stack_trace *trace = data;
+ struct unwind_state state;
+ unsigned long addr;
- if (nosched && in_sched_functions(address))
- return 0;
- if (trace->skip > 0) {
- trace->skip--;
- return 0;
+ unwind_for_each_frame(&state, task, regs, 0) {
+ addr = unwind_get_return_address(&state);
+ if (!addr || !consume_entry(cookie, addr, false))
+ break;
}
- if (trace->nr_entries < trace->max_entries) {
- trace->entries[trace->nr_entries++] = address;
- return 0;
- }
- return 1;
}
-
-static int save_address(void *data, unsigned long address, int reliable)
-{
- return __save_address(data, address, 0);
-}
-
-static int save_address_nosched(void *data, unsigned long address, int reliable)
-{
- return __save_address(data, address, 1);
-}
-
-void save_stack_trace(struct stack_trace *trace)
-{
- unsigned long sp;
-
- sp = current_stack_pointer();
- dump_trace(save_address, trace, NULL, sp);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
-
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
-{
- unsigned long sp;
-
- sp = tsk->thread.ksp;
- if (tsk == current)
- sp = current_stack_pointer();
- dump_trace(save_address_nosched, trace, tsk, sp);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
-
-void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
-{
- unsigned long sp;
-
- sp = kernel_stack_pointer(regs);
- dump_trace(save_address, trace, NULL, sp);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_regs);
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index c1a080b..a7baf0b 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -29,10 +29,11 @@
.section .text
ENTRY(swsusp_arch_suspend)
- stmg %r6,%r15,__SF_GPRS(%r15)
- lgr %r1,%r15
- aghi %r15,-STACK_FRAME_OVERHEAD
- stg %r1,__SF_BACKCHAIN(%r15)
+ lg %r1,__LC_NODAT_STACK
+ stmg %r6,%r15,__SF_GPRS(%r1)
+ aghi %r1,-STACK_FRAME_OVERHEAD
+ stg %r15,__SF_BACKCHAIN(%r1)
+ lgr %r15,%r1
/* Store FPU registers */
brasl %r14,save_fpu_regs
@@ -107,6 +108,7 @@
lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
lghi %r2,0
BR_EX %r14
+ENDPROC(swsusp_arch_suspend)
/*
* Restore saved memory image to correct place and restore register context.
@@ -123,13 +125,13 @@
lghi %r2,1
brasl %r14,arch_set_page_states
- /* Deactivate DAT */
- stnsm __SF_EMPTY(%r15),0xfb
-
/* Set prefix page to zero */
xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15)
spx __SF_EMPTY(%r15)
+ /* Deactivate DAT */
+ stnsm __SF_EMPTY(%r15),0xfb
+
/* Restore saved image */
larl %r1,restore_pblist
lg %r1,0(%r1)
@@ -153,21 +155,13 @@
ptlb /* flush tlb */
/* Reset System */
- larl %r1,restart_entry
- larl %r2,.Lrestart_diag308_psw
- og %r1,0(%r2)
- stg %r1,0(%r0)
larl %r1,.Lnew_pgm_check_psw
epsw %r2,%r3
stm %r2,%r3,0(%r1)
mvc __LC_PGM_NEW_PSW(16,%r0),0(%r1)
- lghi %r0,0
- diag %r0,%r0,0x308
-restart_entry:
- lhi %r1,1
- sigp %r1,%r0,SIGP_SET_ARCHITECTURE
- sam64
-#ifdef CONFIG_SMP
+ larl %r1,__swsusp_reset_dma
+ lg %r1,0(%r1)
+ BASR_EX %r14,%r1
larl %r1,smp_cpu_mt_shift
icm %r1,15,0(%r1)
jz smt_done
@@ -177,7 +171,6 @@
brc 8,smt_done /* accepted */
brc 2,smt_loop /* busy, try again */
smt_done:
-#endif
larl %r1,.Lnew_pgm_check_psw
lpswe 0(%r1)
pgm_check_entry:
@@ -197,9 +190,7 @@
brc 2,3b /* busy, try again */
/* Suspend CPU not available -> panic */
- larl %r15,init_thread_union
- aghi %r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)
- aghi %r15,-STACK_FRAME_OVERHEAD
+ larl %r15,init_thread_union+THREAD_SIZE-STACK_FRAME_OVERHEAD
larl %r2,.Lpanic_string
brasl %r14,sclp_early_printk_force
larl %r3,.Ldisabled_wait_31
@@ -268,6 +259,7 @@
lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
lghi %r2,0
BR_EX %r14
+ENDPROC(swsusp_arch_resume)
.section .data..nosave,"aw",@progbits
.align 8
@@ -276,8 +268,6 @@
.Lpanic_string:
.asciz "Resume not possible because suspend CPU is no longer available\n"
.align 8
-.Lrestart_diag308_psw:
- .long 0x00080000,0x80000000
.Lrestart_suspend_psw:
.quad 0x0000000180000000,restart_suspend
.Lnew_pgm_check_psw:
diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c
index 31cefe0..202fa73 100644
--- a/arch/s390/kernel/sys_s390.c
+++ b/arch/s390/kernel/sys_s390.c
@@ -58,6 +58,7 @@
return error;
}
+#ifdef CONFIG_SYSVIPC
/*
* sys_ipc() is the de-multiplexer for the SysV IPC calls.
*/
@@ -74,19 +75,28 @@
* Therefore we can call the generic variant by simply passing the
* third parameter also as fifth parameter.
*/
- return sys_ipc(call, first, second, third, ptr, third);
+ return ksys_ipc(call, first, second, third, ptr, third);
}
+#endif /* CONFIG_SYSVIPC */
SYSCALL_DEFINE1(s390_personality, unsigned int, personality)
{
- unsigned int ret;
+ unsigned int ret = current->personality;
if (personality(current->personality) == PER_LINUX32 &&
personality(personality) == PER_LINUX)
personality |= PER_LINUX32;
- ret = sys_personality(personality);
+
+ if (personality != 0xffffffff)
+ set_personality(personality);
+
if (personality(ret) == PER_LINUX32)
ret &= ~PER_LINUX32;
return ret;
}
+
+SYSCALL_DEFINE0(ni_syscall)
+{
+ return -ENOSYS;
+}
diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile
index 4d929ed..b98f250 100644
--- a/arch/s390/kernel/syscalls/Makefile
+++ b/arch/s390/kernel/syscalls/Makefile
@@ -24,17 +24,11 @@
_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \
$(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)')
-define filechk_syshdr
- $(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2" < $<
-endef
+filechk_syshdr = $(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2" < $<
-define filechk_sysnr
- $(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget)) < $<
-endef
+filechk_sysnr = $(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget)) < $<
-define filechk_syscalls
- $(CONFIG_SHELL) '$(systbl)' -S < $<
-endef
+filechk_syscalls = $(CONFIG_SHELL) '$(systbl)' -S < $<
syshdr_abi_unistd_32 := common,32
$(uapi)/unistd_32.h: $(syscall) FORCE
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 022fc09..3054e9c 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -15,86 +15,86 @@
5 common open sys_open compat_sys_open
6 common close sys_close sys_close
7 common restart_syscall sys_restart_syscall sys_restart_syscall
-8 common creat sys_creat compat_sys_creat
-9 common link sys_link compat_sys_link
-10 common unlink sys_unlink compat_sys_unlink
+8 common creat sys_creat sys_creat
+9 common link sys_link sys_link
+10 common unlink sys_unlink sys_unlink
11 common execve sys_execve compat_sys_execve
-12 common chdir sys_chdir compat_sys_chdir
-13 32 time - compat_sys_time
-14 common mknod sys_mknod compat_sys_mknod
-15 common chmod sys_chmod compat_sys_chmod
-16 32 lchown - compat_sys_s390_lchown16
+12 common chdir sys_chdir sys_chdir
+13 32 time - sys_time32
+14 common mknod sys_mknod sys_mknod
+15 common chmod sys_chmod sys_chmod
+16 32 lchown - sys_lchown16
19 common lseek sys_lseek compat_sys_lseek
20 common getpid sys_getpid sys_getpid
21 common mount sys_mount compat_sys_mount
-22 common umount sys_oldumount compat_sys_oldumount
-23 32 setuid - compat_sys_s390_setuid16
-24 32 getuid - compat_sys_s390_getuid16
-25 32 stime - compat_sys_stime
+22 common umount sys_oldumount sys_oldumount
+23 32 setuid - sys_setuid16
+24 32 getuid - sys_getuid16
+25 32 stime - sys_stime32
26 common ptrace sys_ptrace compat_sys_ptrace
27 common alarm sys_alarm sys_alarm
29 common pause sys_pause sys_pause
-30 common utime sys_utime compat_sys_utime
-33 common access sys_access compat_sys_access
+30 common utime sys_utime sys_utime32
+33 common access sys_access sys_access
34 common nice sys_nice sys_nice
36 common sync sys_sync sys_sync
37 common kill sys_kill sys_kill
-38 common rename sys_rename compat_sys_rename
-39 common mkdir sys_mkdir compat_sys_mkdir
-40 common rmdir sys_rmdir compat_sys_rmdir
+38 common rename sys_rename sys_rename
+39 common mkdir sys_mkdir sys_mkdir
+40 common rmdir sys_rmdir sys_rmdir
41 common dup sys_dup sys_dup
-42 common pipe sys_pipe compat_sys_pipe
+42 common pipe sys_pipe sys_pipe
43 common times sys_times compat_sys_times
-45 common brk sys_brk compat_sys_brk
-46 32 setgid - compat_sys_s390_setgid16
-47 32 getgid - compat_sys_s390_getgid16
-48 common signal sys_signal compat_sys_signal
-49 32 geteuid - compat_sys_s390_geteuid16
-50 32 getegid - compat_sys_s390_getegid16
-51 common acct sys_acct compat_sys_acct
-52 common umount2 sys_umount compat_sys_umount
+45 common brk sys_brk sys_brk
+46 32 setgid - sys_setgid16
+47 32 getgid - sys_getgid16
+48 common signal sys_signal sys_signal
+49 32 geteuid - sys_geteuid16
+50 32 getegid - sys_getegid16
+51 common acct sys_acct sys_acct
+52 common umount2 sys_umount sys_umount
54 common ioctl sys_ioctl compat_sys_ioctl
55 common fcntl sys_fcntl compat_sys_fcntl
57 common setpgid sys_setpgid sys_setpgid
60 common umask sys_umask sys_umask
-61 common chroot sys_chroot compat_sys_chroot
+61 common chroot sys_chroot sys_chroot
62 common ustat sys_ustat compat_sys_ustat
63 common dup2 sys_dup2 sys_dup2
64 common getppid sys_getppid sys_getppid
65 common getpgrp sys_getpgrp sys_getpgrp
66 common setsid sys_setsid sys_setsid
67 common sigaction sys_sigaction compat_sys_sigaction
-70 32 setreuid - compat_sys_s390_setreuid16
-71 32 setregid - compat_sys_s390_setregid16
-72 common sigsuspend sys_sigsuspend compat_sys_sigsuspend
+70 32 setreuid - sys_setreuid16
+71 32 setregid - sys_setregid16
+72 common sigsuspend sys_sigsuspend sys_sigsuspend
73 common sigpending sys_sigpending compat_sys_sigpending
-74 common sethostname sys_sethostname compat_sys_sethostname
+74 common sethostname sys_sethostname sys_sethostname
75 common setrlimit sys_setrlimit compat_sys_setrlimit
76 32 getrlimit - compat_sys_old_getrlimit
77 common getrusage sys_getrusage compat_sys_getrusage
78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday
79 common settimeofday sys_settimeofday compat_sys_settimeofday
-80 32 getgroups - compat_sys_s390_getgroups16
-81 32 setgroups - compat_sys_s390_setgroups16
-83 common symlink sys_symlink compat_sys_symlink
-85 common readlink sys_readlink compat_sys_readlink
-86 common uselib sys_uselib compat_sys_uselib
-87 common swapon sys_swapon compat_sys_swapon
-88 common reboot sys_reboot compat_sys_reboot
+80 32 getgroups - sys_getgroups16
+81 32 setgroups - sys_setgroups16
+83 common symlink sys_symlink sys_symlink
+85 common readlink sys_readlink sys_readlink
+86 common uselib sys_uselib sys_uselib
+87 common swapon sys_swapon sys_swapon
+88 common reboot sys_reboot sys_reboot
89 common readdir - compat_sys_old_readdir
90 common mmap sys_old_mmap compat_sys_s390_old_mmap
-91 common munmap sys_munmap compat_sys_munmap
+91 common munmap sys_munmap sys_munmap
92 common truncate sys_truncate compat_sys_truncate
93 common ftruncate sys_ftruncate compat_sys_ftruncate
94 common fchmod sys_fchmod sys_fchmod
-95 32 fchown - compat_sys_s390_fchown16
+95 32 fchown - sys_fchown16
96 common getpriority sys_getpriority sys_getpriority
97 common setpriority sys_setpriority sys_setpriority
99 common statfs sys_statfs compat_sys_statfs
100 common fstatfs sys_fstatfs compat_sys_fstatfs
101 32 ioperm - -
102 common socketcall sys_socketcall compat_sys_socketcall
-103 common syslog sys_syslog compat_sys_syslog
+103 common syslog sys_syslog sys_syslog
104 common setitimer sys_setitimer compat_sys_setitimer
105 common getitimer sys_getitimer compat_sys_getitimer
106 common stat sys_newstat compat_sys_newstat
@@ -104,76 +104,76 @@
111 common vhangup sys_vhangup sys_vhangup
112 common idle - -
114 common wait4 sys_wait4 compat_sys_wait4
-115 common swapoff sys_swapoff compat_sys_swapoff
+115 common swapoff sys_swapoff sys_swapoff
116 common sysinfo sys_sysinfo compat_sys_sysinfo
117 common ipc sys_s390_ipc compat_sys_s390_ipc
118 common fsync sys_fsync sys_fsync
119 common sigreturn sys_sigreturn compat_sys_sigreturn
-120 common clone sys_clone compat_sys_clone
-121 common setdomainname sys_setdomainname compat_sys_setdomainname
-122 common uname sys_newuname compat_sys_newuname
-124 common adjtimex sys_adjtimex compat_sys_adjtimex
-125 common mprotect sys_mprotect compat_sys_mprotect
+120 common clone sys_clone sys_clone
+121 common setdomainname sys_setdomainname sys_setdomainname
+122 common uname sys_newuname sys_newuname
+124 common adjtimex sys_adjtimex sys_adjtimex_time32
+125 common mprotect sys_mprotect sys_mprotect
126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask
127 common create_module - -
-128 common init_module sys_init_module compat_sys_init_module
-129 common delete_module sys_delete_module compat_sys_delete_module
+128 common init_module sys_init_module sys_init_module
+129 common delete_module sys_delete_module sys_delete_module
130 common get_kernel_syms - -
-131 common quotactl sys_quotactl compat_sys_quotactl
+131 common quotactl sys_quotactl sys_quotactl
132 common getpgid sys_getpgid sys_getpgid
133 common fchdir sys_fchdir sys_fchdir
-134 common bdflush sys_bdflush compat_sys_bdflush
-135 common sysfs sys_sysfs compat_sys_sysfs
+134 common bdflush sys_bdflush sys_bdflush
+135 common sysfs sys_sysfs sys_sysfs
136 common personality sys_s390_personality sys_s390_personality
137 common afs_syscall - -
-138 32 setfsuid - compat_sys_s390_setfsuid16
-139 32 setfsgid - compat_sys_s390_setfsgid16
-140 32 _llseek - compat_sys_llseek
+138 32 setfsuid - sys_setfsuid16
+139 32 setfsgid - sys_setfsgid16
+140 32 _llseek - sys_llseek
141 common getdents sys_getdents compat_sys_getdents
142 32 _newselect - compat_sys_select
142 64 select sys_select -
143 common flock sys_flock sys_flock
-144 common msync sys_msync compat_sys_msync
+144 common msync sys_msync sys_msync
145 common readv sys_readv compat_sys_readv
146 common writev sys_writev compat_sys_writev
147 common getsid sys_getsid sys_getsid
148 common fdatasync sys_fdatasync sys_fdatasync
149 common _sysctl sys_sysctl compat_sys_sysctl
-150 common mlock sys_mlock compat_sys_mlock
-151 common munlock sys_munlock compat_sys_munlock
+150 common mlock sys_mlock sys_mlock
+151 common munlock sys_munlock sys_munlock
152 common mlockall sys_mlockall sys_mlockall
153 common munlockall sys_munlockall sys_munlockall
-154 common sched_setparam sys_sched_setparam compat_sys_sched_setparam
-155 common sched_getparam sys_sched_getparam compat_sys_sched_getparam
-156 common sched_setscheduler sys_sched_setscheduler compat_sys_sched_setscheduler
+154 common sched_setparam sys_sched_setparam sys_sched_setparam
+155 common sched_getparam sys_sched_getparam sys_sched_getparam
+156 common sched_setscheduler sys_sched_setscheduler sys_sched_setscheduler
157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler
158 common sched_yield sys_sched_yield sys_sched_yield
159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max
160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min
-161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval
-162 common nanosleep sys_nanosleep compat_sys_nanosleep
-163 common mremap sys_mremap compat_sys_mremap
-164 32 setresuid - compat_sys_s390_setresuid16
-165 32 getresuid - compat_sys_s390_getresuid16
+161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32
+162 common nanosleep sys_nanosleep sys_nanosleep_time32
+163 common mremap sys_mremap sys_mremap
+164 32 setresuid - sys_setresuid16
+165 32 getresuid - sys_getresuid16
167 common query_module - -
-168 common poll sys_poll compat_sys_poll
+168 common poll sys_poll sys_poll
169 common nfsservctl - -
-170 32 setresgid - compat_sys_s390_setresgid16
-171 32 getresgid - compat_sys_s390_getresgid16
-172 common prctl sys_prctl compat_sys_prctl
+170 32 setresgid - sys_setresgid16
+171 32 getresgid - sys_getresgid16
+172 common prctl sys_prctl sys_prctl
173 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn
174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction
175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask
176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending
-177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait
+177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32
178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend
180 common pread64 sys_pread64 compat_sys_s390_pread64
181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64
-182 32 chown - compat_sys_s390_chown16
-183 common getcwd sys_getcwd compat_sys_getcwd
-184 common capget sys_capget compat_sys_capget
-185 common capset sys_capset compat_sys_capset
+182 32 chown - sys_chown16
+183 common getcwd sys_getcwd sys_getcwd
+184 common capget sys_capget sys_capget
+185 common capset sys_capset sys_capset
186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack
187 common sendfile sys_sendfile64 compat_sys_sendfile
188 common getpmsg - -
@@ -187,7 +187,7 @@
195 32 stat64 - compat_sys_s390_stat64
196 32 lstat64 - compat_sys_s390_lstat64
197 32 fstat64 - compat_sys_s390_fstat64
-198 32 lchown32 - compat_sys_lchown
+198 32 lchown32 - sys_lchown
198 64 lchown sys_lchown -
199 32 getuid32 - sys_getuid
199 64 getuid sys_getuid -
@@ -201,21 +201,21 @@
203 64 setreuid sys_setreuid -
204 32 setregid32 - sys_setregid
204 64 setregid sys_setregid -
-205 32 getgroups32 - compat_sys_getgroups
+205 32 getgroups32 - sys_getgroups
205 64 getgroups sys_getgroups -
-206 32 setgroups32 - compat_sys_setgroups
+206 32 setgroups32 - sys_setgroups
206 64 setgroups sys_setgroups -
207 32 fchown32 - sys_fchown
207 64 fchown sys_fchown -
208 32 setresuid32 - sys_setresuid
208 64 setresuid sys_setresuid -
-209 32 getresuid32 - compat_sys_getresuid
+209 32 getresuid32 - sys_getresuid
209 64 getresuid sys_getresuid -
210 32 setresgid32 - sys_setresgid
210 64 setresgid sys_setresgid -
-211 32 getresgid32 - compat_sys_getresgid
+211 32 getresgid32 - sys_getresgid
211 64 getresgid sys_getresgid -
-212 32 chown32 - compat_sys_chown
+212 32 chown32 - sys_chown
212 64 chown sys_chown -
213 32 setuid32 - sys_setuid
213 64 setuid sys_setuid -
@@ -225,169 +225,216 @@
215 64 setfsuid sys_setfsuid -
216 32 setfsgid32 - sys_setfsgid
216 64 setfsgid sys_setfsgid -
-217 common pivot_root sys_pivot_root compat_sys_pivot_root
-218 common mincore sys_mincore compat_sys_mincore
-219 common madvise sys_madvise compat_sys_madvise
-220 common getdents64 sys_getdents64 compat_sys_getdents64
+217 common pivot_root sys_pivot_root sys_pivot_root
+218 common mincore sys_mincore sys_mincore
+219 common madvise sys_madvise sys_madvise
+220 common getdents64 sys_getdents64 sys_getdents64
221 32 fcntl64 - compat_sys_fcntl64
222 common readahead sys_readahead compat_sys_s390_readahead
223 32 sendfile64 - compat_sys_sendfile64
-224 common setxattr sys_setxattr compat_sys_setxattr
-225 common lsetxattr sys_lsetxattr compat_sys_lsetxattr
-226 common fsetxattr sys_fsetxattr compat_sys_fsetxattr
-227 common getxattr sys_getxattr compat_sys_getxattr
-228 common lgetxattr sys_lgetxattr compat_sys_lgetxattr
-229 common fgetxattr sys_fgetxattr compat_sys_fgetxattr
-230 common listxattr sys_listxattr compat_sys_listxattr
-231 common llistxattr sys_llistxattr compat_sys_llistxattr
-232 common flistxattr sys_flistxattr compat_sys_flistxattr
-233 common removexattr sys_removexattr compat_sys_removexattr
-234 common lremovexattr sys_lremovexattr compat_sys_lremovexattr
-235 common fremovexattr sys_fremovexattr compat_sys_fremovexattr
+224 common setxattr sys_setxattr sys_setxattr
+225 common lsetxattr sys_lsetxattr sys_lsetxattr
+226 common fsetxattr sys_fsetxattr sys_fsetxattr
+227 common getxattr sys_getxattr sys_getxattr
+228 common lgetxattr sys_lgetxattr sys_lgetxattr
+229 common fgetxattr sys_fgetxattr sys_fgetxattr
+230 common listxattr sys_listxattr sys_listxattr
+231 common llistxattr sys_llistxattr sys_llistxattr
+232 common flistxattr sys_flistxattr sys_flistxattr
+233 common removexattr sys_removexattr sys_removexattr
+234 common lremovexattr sys_lremovexattr sys_lremovexattr
+235 common fremovexattr sys_fremovexattr sys_fremovexattr
236 common gettid sys_gettid sys_gettid
237 common tkill sys_tkill sys_tkill
-238 common futex sys_futex compat_sys_futex
+238 common futex sys_futex sys_futex_time32
239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity
240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity
241 common tgkill sys_tgkill sys_tgkill
243 common io_setup sys_io_setup compat_sys_io_setup
-244 common io_destroy sys_io_destroy compat_sys_io_destroy
-245 common io_getevents sys_io_getevents compat_sys_io_getevents
+244 common io_destroy sys_io_destroy sys_io_destroy
+245 common io_getevents sys_io_getevents sys_io_getevents_time32
246 common io_submit sys_io_submit compat_sys_io_submit
-247 common io_cancel sys_io_cancel compat_sys_io_cancel
+247 common io_cancel sys_io_cancel sys_io_cancel
248 common exit_group sys_exit_group sys_exit_group
249 common epoll_create sys_epoll_create sys_epoll_create
-250 common epoll_ctl sys_epoll_ctl compat_sys_epoll_ctl
-251 common epoll_wait sys_epoll_wait compat_sys_epoll_wait
-252 common set_tid_address sys_set_tid_address compat_sys_set_tid_address
+250 common epoll_ctl sys_epoll_ctl sys_epoll_ctl
+251 common epoll_wait sys_epoll_wait sys_epoll_wait
+252 common set_tid_address sys_set_tid_address sys_set_tid_address
253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64
254 common timer_create sys_timer_create compat_sys_timer_create
-255 common timer_settime sys_timer_settime compat_sys_timer_settime
-256 common timer_gettime sys_timer_gettime compat_sys_timer_gettime
+255 common timer_settime sys_timer_settime sys_timer_settime32
+256 common timer_gettime sys_timer_gettime sys_timer_gettime32
257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun
258 common timer_delete sys_timer_delete sys_timer_delete
-259 common clock_settime sys_clock_settime compat_sys_clock_settime
-260 common clock_gettime sys_clock_gettime compat_sys_clock_gettime
-261 common clock_getres sys_clock_getres compat_sys_clock_getres
-262 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep
+259 common clock_settime sys_clock_settime sys_clock_settime32
+260 common clock_gettime sys_clock_gettime sys_clock_gettime32
+261 common clock_getres sys_clock_getres sys_clock_getres_time32
+262 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32
264 32 fadvise64_64 - compat_sys_s390_fadvise64_64
265 common statfs64 sys_statfs64 compat_sys_statfs64
266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
-267 common remap_file_pages sys_remap_file_pages compat_sys_remap_file_pages
+267 common remap_file_pages sys_remap_file_pages sys_remap_file_pages
268 common mbind sys_mbind compat_sys_mbind
269 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy
271 common mq_open sys_mq_open compat_sys_mq_open
-272 common mq_unlink sys_mq_unlink compat_sys_mq_unlink
-273 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend
-274 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive
+272 common mq_unlink sys_mq_unlink sys_mq_unlink
+273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32
+274 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32
275 common mq_notify sys_mq_notify compat_sys_mq_notify
276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr
277 common kexec_load sys_kexec_load compat_sys_kexec_load
-278 common add_key sys_add_key compat_sys_add_key
-279 common request_key sys_request_key compat_sys_request_key
+278 common add_key sys_add_key sys_add_key
+279 common request_key sys_request_key sys_request_key
280 common keyctl sys_keyctl compat_sys_keyctl
281 common waitid sys_waitid compat_sys_waitid
282 common ioprio_set sys_ioprio_set sys_ioprio_set
283 common ioprio_get sys_ioprio_get sys_ioprio_get
284 common inotify_init sys_inotify_init sys_inotify_init
-285 common inotify_add_watch sys_inotify_add_watch compat_sys_inotify_add_watch
+285 common inotify_add_watch sys_inotify_add_watch sys_inotify_add_watch
286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch
287 common migrate_pages sys_migrate_pages compat_sys_migrate_pages
288 common openat sys_openat compat_sys_openat
-289 common mkdirat sys_mkdirat compat_sys_mkdirat
-290 common mknodat sys_mknodat compat_sys_mknodat
-291 common fchownat sys_fchownat compat_sys_fchownat
-292 common futimesat sys_futimesat compat_sys_futimesat
+289 common mkdirat sys_mkdirat sys_mkdirat
+290 common mknodat sys_mknodat sys_mknodat
+291 common fchownat sys_fchownat sys_fchownat
+292 common futimesat sys_futimesat sys_futimesat_time32
293 32 fstatat64 - compat_sys_s390_fstatat64
293 64 newfstatat sys_newfstatat -
-294 common unlinkat sys_unlinkat compat_sys_unlinkat
-295 common renameat sys_renameat compat_sys_renameat
-296 common linkat sys_linkat compat_sys_linkat
-297 common symlinkat sys_symlinkat compat_sys_symlinkat
-298 common readlinkat sys_readlinkat compat_sys_readlinkat
-299 common fchmodat sys_fchmodat compat_sys_fchmodat
-300 common faccessat sys_faccessat compat_sys_faccessat
-301 common pselect6 sys_pselect6 compat_sys_pselect6
-302 common ppoll sys_ppoll compat_sys_ppoll
-303 common unshare sys_unshare compat_sys_unshare
+294 common unlinkat sys_unlinkat sys_unlinkat
+295 common renameat sys_renameat sys_renameat
+296 common linkat sys_linkat sys_linkat
+297 common symlinkat sys_symlinkat sys_symlinkat
+298 common readlinkat sys_readlinkat sys_readlinkat
+299 common fchmodat sys_fchmodat sys_fchmodat
+300 common faccessat sys_faccessat sys_faccessat
+301 common pselect6 sys_pselect6 compat_sys_pselect6_time32
+302 common ppoll sys_ppoll compat_sys_ppoll_time32
+303 common unshare sys_unshare sys_unshare
304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list
305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list
-306 common splice sys_splice compat_sys_splice
+306 common splice sys_splice sys_splice
307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range
-308 common tee sys_tee compat_sys_tee
+308 common tee sys_tee sys_tee
309 common vmsplice sys_vmsplice compat_sys_vmsplice
310 common move_pages sys_move_pages compat_sys_move_pages
-311 common getcpu sys_getcpu compat_sys_getcpu
+311 common getcpu sys_getcpu sys_getcpu
312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait
-313 common utimes sys_utimes compat_sys_utimes
+313 common utimes sys_utimes sys_utimes_time32
314 common fallocate sys_fallocate compat_sys_s390_fallocate
-315 common utimensat sys_utimensat compat_sys_utimensat
+315 common utimensat sys_utimensat sys_utimensat_time32
316 common signalfd sys_signalfd compat_sys_signalfd
317 common timerfd - -
318 common eventfd sys_eventfd sys_eventfd
319 common timerfd_create sys_timerfd_create sys_timerfd_create
-320 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime
-321 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime
+320 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32
+321 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32
322 common signalfd4 sys_signalfd4 compat_sys_signalfd4
323 common eventfd2 sys_eventfd2 sys_eventfd2
324 common inotify_init1 sys_inotify_init1 sys_inotify_init1
-325 common pipe2 sys_pipe2 compat_sys_pipe2
+325 common pipe2 sys_pipe2 sys_pipe2
326 common dup3 sys_dup3 sys_dup3
327 common epoll_create1 sys_epoll_create1 sys_epoll_create1
328 common preadv sys_preadv compat_sys_preadv
329 common pwritev sys_pwritev compat_sys_pwritev
330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
-331 common perf_event_open sys_perf_event_open compat_sys_perf_event_open
+331 common perf_event_open sys_perf_event_open sys_perf_event_open
332 common fanotify_init sys_fanotify_init sys_fanotify_init
333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark
-334 common prlimit64 sys_prlimit64 compat_sys_prlimit64
-335 common name_to_handle_at sys_name_to_handle_at compat_sys_name_to_handle_at
+334 common prlimit64 sys_prlimit64 sys_prlimit64
+335 common name_to_handle_at sys_name_to_handle_at sys_name_to_handle_at
336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at
-337 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime
+337 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32
338 common syncfs sys_syncfs sys_syncfs
339 common setns sys_setns sys_setns
340 common process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv
341 common process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr
-343 common kcmp sys_kcmp compat_sys_kcmp
-344 common finit_module sys_finit_module compat_sys_finit_module
-345 common sched_setattr sys_sched_setattr compat_sys_sched_setattr
-346 common sched_getattr sys_sched_getattr compat_sys_sched_getattr
-347 common renameat2 sys_renameat2 compat_sys_renameat2
-348 common seccomp sys_seccomp compat_sys_seccomp
-349 common getrandom sys_getrandom compat_sys_getrandom
-350 common memfd_create sys_memfd_create compat_sys_memfd_create
-351 common bpf sys_bpf compat_sys_bpf
-352 common s390_pci_mmio_write sys_s390_pci_mmio_write compat_sys_s390_pci_mmio_write
-353 common s390_pci_mmio_read sys_s390_pci_mmio_read compat_sys_s390_pci_mmio_read
+343 common kcmp sys_kcmp sys_kcmp
+344 common finit_module sys_finit_module sys_finit_module
+345 common sched_setattr sys_sched_setattr sys_sched_setattr
+346 common sched_getattr sys_sched_getattr sys_sched_getattr
+347 common renameat2 sys_renameat2 sys_renameat2
+348 common seccomp sys_seccomp sys_seccomp
+349 common getrandom sys_getrandom sys_getrandom
+350 common memfd_create sys_memfd_create sys_memfd_create
+351 common bpf sys_bpf sys_bpf
+352 common s390_pci_mmio_write sys_s390_pci_mmio_write sys_s390_pci_mmio_write
+353 common s390_pci_mmio_read sys_s390_pci_mmio_read sys_s390_pci_mmio_read
354 common execveat sys_execveat compat_sys_execveat
355 common userfaultfd sys_userfaultfd sys_userfaultfd
356 common membarrier sys_membarrier sys_membarrier
-357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg
+357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32
358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg
359 common socket sys_socket sys_socket
-360 common socketpair sys_socketpair compat_sys_socketpair
-361 common bind sys_bind compat_sys_bind
-362 common connect sys_connect compat_sys_connect
+360 common socketpair sys_socketpair sys_socketpair
+361 common bind sys_bind sys_bind
+362 common connect sys_connect sys_connect
363 common listen sys_listen sys_listen
-364 common accept4 sys_accept4 compat_sys_accept4
+364 common accept4 sys_accept4 sys_accept4
365 common getsockopt sys_getsockopt compat_sys_getsockopt
366 common setsockopt sys_setsockopt compat_sys_setsockopt
-367 common getsockname sys_getsockname compat_sys_getsockname
-368 common getpeername sys_getpeername compat_sys_getpeername
-369 common sendto sys_sendto compat_sys_sendto
+367 common getsockname sys_getsockname sys_getsockname
+368 common getpeername sys_getpeername sys_getpeername
+369 common sendto sys_sendto sys_sendto
370 common sendmsg sys_sendmsg compat_sys_sendmsg
371 common recvfrom sys_recvfrom compat_sys_recvfrom
372 common recvmsg sys_recvmsg compat_sys_recvmsg
373 common shutdown sys_shutdown sys_shutdown
-374 common mlock2 sys_mlock2 compat_sys_mlock2
-375 common copy_file_range sys_copy_file_range compat_sys_copy_file_range
+374 common mlock2 sys_mlock2 sys_mlock2
+375 common copy_file_range sys_copy_file_range sys_copy_file_range
376 common preadv2 sys_preadv2 compat_sys_preadv2
377 common pwritev2 sys_pwritev2 compat_sys_pwritev2
-378 common s390_guarded_storage sys_s390_guarded_storage compat_sys_s390_guarded_storage
-379 common statx sys_statx compat_sys_statx
-380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi
-381 common kexec_file_load sys_kexec_file_load compat_sys_kexec_file_load
+378 common s390_guarded_storage sys_s390_guarded_storage sys_s390_guarded_storage
+379 common statx sys_statx sys_statx
+380 common s390_sthyi sys_s390_sthyi sys_s390_sthyi
+381 common kexec_file_load sys_kexec_file_load sys_kexec_file_load
382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents
-383 common rseq sys_rseq compat_sys_rseq
+383 common rseq sys_rseq sys_rseq
+384 common pkey_mprotect sys_pkey_mprotect sys_pkey_mprotect
+385 common pkey_alloc sys_pkey_alloc sys_pkey_alloc
+386 common pkey_free sys_pkey_free sys_pkey_free
+# room for arch specific syscalls
+392 64 semtimedop sys_semtimedop -
+393 common semget sys_semget sys_semget
+394 common semctl sys_semctl compat_sys_semctl
+395 common shmget sys_shmget sys_shmget
+396 common shmctl sys_shmctl compat_sys_shmctl
+397 common shmat sys_shmat compat_sys_shmat
+398 common shmdt sys_shmdt sys_shmdt
+399 common msgget sys_msgget sys_msgget
+400 common msgsnd sys_msgsnd compat_sys_msgsnd
+401 common msgrcv sys_msgrcv compat_sys_msgrcv
+402 common msgctl sys_msgctl compat_sys_msgctl
+403 32 clock_gettime64 - sys_clock_gettime
+404 32 clock_settime64 - sys_clock_settime
+405 32 clock_adjtime64 - sys_clock_adjtime
+406 32 clock_getres_time64 - sys_clock_getres
+407 32 clock_nanosleep_time64 - sys_clock_nanosleep
+408 32 timer_gettime64 - sys_timer_gettime
+409 32 timer_settime64 - sys_timer_settime
+410 32 timerfd_gettime64 - sys_timerfd_gettime
+411 32 timerfd_settime64 - sys_timerfd_settime
+412 32 utimensat_time64 - sys_utimensat
+413 32 pselect6_time64 - compat_sys_pselect6_time64
+414 32 ppoll_time64 - compat_sys_ppoll_time64
+416 32 io_pgetevents_time64 - sys_io_pgetevents
+417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64
+418 32 mq_timedsend_time64 - sys_mq_timedsend
+419 32 mq_timedreceive_time64 - sys_mq_timedreceive
+420 32 semtimedop_time64 - sys_semtimedop
+421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64
+422 32 futex_time64 - sys_futex
+423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register sys_io_uring_register
+428 common open_tree sys_open_tree sys_open_tree
+429 common move_mount sys_move_mount sys_move_mount
+430 common fsopen sys_fsopen sys_fsopen
+431 common fsconfig sys_fsconfig sys_fsconfig
+432 common fsmount sys_fsmount sys_fsmount
+433 common fspick sys_fspick sys_fspick
+434 common pidfd_open sys_pidfd_open sys_pidfd_open
+435 common clone3 sys_clone3 sys_clone3
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 12f80d1..2ac3c9b 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -545,8 +545,6 @@
int lvl, i;
stsi_root = debugfs_create_dir("stsi", arch_debugfs_dir);
- if (IS_ERR_OR_NULL(stsi_root))
- return 0;
lvl = stsi(NULL, 0, 0, 0);
if (lvl > 0)
stsi_0_0_0 = lvl;
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index e8184a1..3627953 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -8,7 +8,7 @@
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/workqueue.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/uaccess.h>
#include <linux/sysctl.h>
#include <linux/cpuset.h>
@@ -311,7 +311,8 @@
on_each_cpu(__arch_update_dedicated_flag, NULL, 0);
for_each_online_cpu(cpu) {
dev = get_cpu_device(cpu);
- kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+ if (dev)
+ kobject_uevent(&dev->kobj, KOBJ_CHANGE);
}
return rc;
}
@@ -519,7 +520,10 @@
nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i];
nr_masks = max(nr_masks, 1);
for (i = 0; i < nr_masks; i++) {
- mask->next = memblock_virt_alloc(sizeof(*mask->next), 8);
+ mask->next = memblock_alloc(sizeof(*mask->next), 8);
+ if (!mask->next)
+ panic("%s: Failed to allocate %zu bytes align=0x%x\n",
+ __func__, sizeof(*mask->next), 8);
mask = mask->next;
}
}
@@ -537,7 +541,10 @@
}
if (!MACHINE_HAS_TOPOLOGY)
goto out;
- tl_info = memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE);
+ tl_info = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ if (!tl_info)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+ __func__, PAGE_SIZE, PAGE_SIZE);
info = tl_info;
store_topology(info);
pr_info("The CPU configuration topology of the machine is: %d %d %d %d %d %d / %d\n",
@@ -581,15 +588,13 @@
{
int enabled = topology_is_enabled();
int new_mode;
- int zero = 0;
- int one = 1;
int rc;
struct ctl_table ctl_entry = {
.procname = ctl->procname,
.data = &enabled,
.maxlen = sizeof(int),
- .extra1 = &zero,
- .extra2 = &one,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
};
rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 8003b38..164c028 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -45,11 +45,11 @@
void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
{
if (user_mode(regs)) {
- force_sig_fault(si_signo, si_code, get_trap_ip(regs), current);
+ force_sig_fault(si_signo, si_code, get_trap_ip(regs));
report_user_fault(regs, si_signo, 0);
} else {
const struct exception_table_entry *fixup;
- fixup = search_exception_tables(regs->psw.addr);
+ fixup = s390_search_extables(regs->psw.addr);
if (fixup)
regs->psw.addr = extable_fixup(fixup);
else {
@@ -79,7 +79,7 @@
if (!current->ptrace)
return;
force_sig_fault(SIGTRAP, TRAP_HWBKPT,
- (void __force __user *) current->thread.per_event.address, current);
+ (void __force __user *) current->thread.per_event.address);
}
NOKPROBE_SYMBOL(do_per_trap);
@@ -165,7 +165,7 @@
return;
if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
if (current->ptrace)
- force_sig_fault(SIGTRAP, TRAP_BRKPT, location, current);
+ force_sig_fault(SIGTRAP, TRAP_BRKPT, location);
else
signal = SIGILL;
#ifdef CONFIG_UPROBES
@@ -229,17 +229,11 @@
void data_exception(struct pt_regs *regs)
{
- int signal = 0;
-
save_fpu_regs();
if (current->thread.fpu.fpc & FPC_DXC_MASK)
- signal = SIGFPE;
- else
- signal = SIGILL;
- if (signal == SIGFPE)
do_fp_trap(regs, current->thread.fpu.fpc);
- else if (signal)
- do_trap(regs, signal, ILL_ILLOPN, "data exception");
+ else
+ do_trap(regs, SIGILL, ILL_ILLOPN, "data exception");
}
void space_switch_exception(struct pt_regs *regs)
@@ -263,5 +257,6 @@
void __init trap_init(void)
{
+ sort_extable(__start_dma_ex_table, __stop_dma_ex_table);
local_mcck_enable();
}
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
new file mode 100644
index 0000000..a8204f9
--- /dev/null
+++ b/arch/s390/kernel/unwind_bc.c
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/interrupt.h>
+#include <asm/sections.h>
+#include <asm/ptrace.h>
+#include <asm/bitops.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+ if (unwind_done(state))
+ return 0;
+ return __kernel_text_address(state->ip) ? state->ip : 0;
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+static bool outside_of_stack(struct unwind_state *state, unsigned long sp)
+{
+ return (sp <= state->sp) ||
+ (sp > state->stack_info.end - sizeof(struct stack_frame));
+}
+
+static bool update_stack_info(struct unwind_state *state, unsigned long sp)
+{
+ struct stack_info *info = &state->stack_info;
+ unsigned long *mask = &state->stack_mask;
+
+ /* New stack pointer leaves the current stack */
+ if (get_stack_info(sp, state->task, info, mask) != 0 ||
+ !on_stack(info, sp, sizeof(struct stack_frame)))
+ /* 'sp' does not point to a valid stack */
+ return false;
+ return true;
+}
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+ struct stack_info *info = &state->stack_info;
+ struct stack_frame *sf;
+ struct pt_regs *regs;
+ unsigned long sp, ip;
+ bool reliable;
+
+ regs = state->regs;
+ if (unlikely(regs)) {
+ if (state->reuse_sp) {
+ sp = state->sp;
+ state->reuse_sp = false;
+ } else {
+ sp = READ_ONCE_NOCHECK(regs->gprs[15]);
+ if (unlikely(outside_of_stack(state, sp))) {
+ if (!update_stack_info(state, sp))
+ goto out_err;
+ }
+ }
+ sf = (struct stack_frame *) sp;
+ ip = READ_ONCE_NOCHECK(sf->gprs[8]);
+ reliable = false;
+ regs = NULL;
+ } else {
+ sf = (struct stack_frame *) state->sp;
+ sp = READ_ONCE_NOCHECK(sf->back_chain);
+ if (likely(sp)) {
+ /* Non-zero back-chain points to the previous frame */
+ if (unlikely(outside_of_stack(state, sp))) {
+ if (!update_stack_info(state, sp))
+ goto out_err;
+ }
+ sf = (struct stack_frame *) sp;
+ ip = READ_ONCE_NOCHECK(sf->gprs[8]);
+ reliable = true;
+ } else {
+ /* No back-chain, look for a pt_regs structure */
+ sp = state->sp + STACK_FRAME_OVERHEAD;
+ if (!on_stack(info, sp, sizeof(struct pt_regs)))
+ goto out_stop;
+ regs = (struct pt_regs *) sp;
+ if (READ_ONCE_NOCHECK(regs->psw.mask) & PSW_MASK_PSTATE)
+ goto out_stop;
+ ip = READ_ONCE_NOCHECK(regs->psw.addr);
+ reliable = true;
+ }
+ }
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ /* Decode any ftrace redirection */
+ if (ip == (unsigned long) return_to_handler)
+ ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ ip, (void *) sp);
+#endif
+
+ /* Update unwind state */
+ state->sp = sp;
+ state->ip = ip;
+ state->regs = regs;
+ state->reliable = reliable;
+ return true;
+
+out_err:
+ state->error = true;
+out_stop:
+ state->stack_info.type = STACK_TYPE_UNKNOWN;
+ return false;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs, unsigned long sp)
+{
+ struct stack_info *info = &state->stack_info;
+ unsigned long *mask = &state->stack_mask;
+ bool reliable, reuse_sp;
+ struct stack_frame *sf;
+ unsigned long ip;
+
+ memset(state, 0, sizeof(*state));
+ state->task = task;
+ state->regs = regs;
+
+ /* Don't even attempt to start from user mode regs: */
+ if (regs && user_mode(regs)) {
+ info->type = STACK_TYPE_UNKNOWN;
+ return;
+ }
+
+ /* Get current stack pointer and initialize stack info */
+ if (get_stack_info(sp, task, info, mask) != 0 ||
+ !on_stack(info, sp, sizeof(struct stack_frame))) {
+ /* Something is wrong with the stack pointer */
+ info->type = STACK_TYPE_UNKNOWN;
+ state->error = true;
+ return;
+ }
+
+ /* Get the instruction pointer from pt_regs or the stack frame */
+ if (regs) {
+ ip = READ_ONCE_NOCHECK(regs->psw.addr);
+ reliable = true;
+ reuse_sp = true;
+ } else {
+ sf = (struct stack_frame *) sp;
+ ip = READ_ONCE_NOCHECK(sf->gprs[8]);
+ reliable = false;
+ reuse_sp = false;
+ }
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ /* Decode any ftrace redirection */
+ if (ip == (unsigned long) return_to_handler)
+ ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ ip, NULL);
+#endif
+
+ /* Update unwind state */
+ state->sp = sp;
+ state->ip = ip;
+ state->reliable = reliable;
+ state->reuse_sp = reuse_sp;
+}
+EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 3031cc6..ed1fc08 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -18,7 +18,7 @@
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/security.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/compat.h>
#include <asm/asm-offsets.h>
#include <asm/pgtable.h>
@@ -29,7 +29,7 @@
#include <asm/vdso.h>
#include <asm/facility.h>
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
extern char vdso32_start, vdso32_end;
static void *vdso32_kbase = &vdso32_start;
static unsigned int vdso32_pages;
@@ -55,8 +55,8 @@
vdso_pagelist = vdso64_pagelist;
vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
- if (is_compat_task()) {
+#ifdef CONFIG_COMPAT_VDSO
+ if (vma->vm_mm->context.compat_mm) {
vdso_pagelist = vdso32_pagelist;
vdso_pages = vdso32_pages;
}
@@ -76,8 +76,8 @@
unsigned long vdso_pages;
vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
- if (is_compat_task())
+#ifdef CONFIG_COMPAT_VDSO
+ if (vma->vm_mm->context.compat_mm)
vdso_pages = vdso32_pages;
#endif
@@ -97,21 +97,13 @@
.mremap = vdso_mremap,
};
-static int __init vdso_setup(char *s)
+static int __init vdso_setup(char *str)
{
- unsigned long val;
- int rc;
+ bool enabled;
- rc = 0;
- if (strncmp(s, "on", 3) == 0)
- vdso_enabled = 1;
- else if (strncmp(s, "off", 4) == 0)
- vdso_enabled = 0;
- else {
- rc = kstrtoul(s, 0, &val);
- vdso_enabled = rc ? 0 : !!val;
- }
- return !rc;
+ if (!kstrtobool(str, &enabled))
+ vdso_enabled = enabled;
+ return 1;
}
__setup("vdso=", vdso_setup);
@@ -216,15 +208,11 @@
if (!vdso_enabled)
return 0;
- /*
- * Only map the vdso for dynamically linked elf binaries.
- */
- if (!uses_interp)
- return 0;
vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
- if (is_compat_task())
+#ifdef CONFIG_COMPAT_VDSO
+ mm->context.compat_mm = is_compat_task();
+ if (mm->context.compat_mm)
vdso_pages = vdso32_pages;
#endif
/*
@@ -279,7 +267,7 @@
int i;
vdso_init_data(vdso_data);
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
/* Calculate the size of the 32 bit vDSO */
vdso32_pages = ((&vdso32_end - &vdso32_start
+ PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
@@ -290,7 +278,6 @@
BUG_ON(vdso32_pagelist == NULL);
for (i = 0; i < vdso32_pages - 1; i++) {
struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
- ClearPageReserved(pg);
get_page(pg);
vdso32_pagelist[i] = pg;
}
@@ -308,7 +295,6 @@
BUG_ON(vdso64_pagelist == NULL);
for (i = 0; i < vdso64_pages - 1; i++) {
struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
- ClearPageReserved(pg);
get_page(pg);
vdso64_pagelist[i] = pg;
}
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index 04dd3e2..aee9ffb 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -19,7 +19,7 @@
KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS))
KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin
KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
- $(call cc-ldoption, -Wl$(comma)--hash-style=both)
+ -Wl,--hash-style=both
$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31)
$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31)
@@ -28,9 +28,10 @@
extra-y += vdso32.lds
CPPFLAGS_vdso32.lds += -P -C -U$(ARCH)
-# Disable gcov profiling and ubsan for VDSO code
+# Disable gcov profiling, ubsan and kasan for VDSO code
GCOV_PROFILE := n
UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
# Force dependency (incbin is bad)
$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
index a9418bf..ada5c11 100644
--- a/arch/s390/kernel/vdso32/clock_gettime.S
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -10,6 +10,7 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/dwarf.h>
+#include <asm/ptrace.h>
.text
.align 4
@@ -18,8 +19,8 @@
__kernel_clock_gettime:
CFI_STARTPROC
ahi %r15,-16
- CFI_DEF_CFA_OFFSET 176
- CFI_VAL_OFFSET 15, -160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
basr %r5,0
0: al %r5,21f-0b(%r5) /* get &_vdso_data */
chi %r2,__CLOCK_REALTIME_COARSE
@@ -72,13 +73,13 @@
st %r1,4(%r3) /* store tp->tv_nsec */
lhi %r2,0
ahi %r15,16
- CFI_DEF_CFA_OFFSET 160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
CFI_RESTORE 15
br %r14
/* CLOCK_MONOTONIC_COARSE */
- CFI_DEF_CFA_OFFSET 176
- CFI_VAL_OFFSET 15, -160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
9: l %r4,__VDSO_UPD_COUNT+4(%r5) /* load update counter */
tml %r4,0x0001 /* pending update ? loop */
jnz 9b
@@ -158,17 +159,17 @@
st %r1,4(%r3) /* store tp->tv_nsec */
lhi %r2,0
ahi %r15,16
- CFI_DEF_CFA_OFFSET 160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
CFI_RESTORE 15
br %r14
/* Fallback to system call */
- CFI_DEF_CFA_OFFSET 176
- CFI_VAL_OFFSET 15, -160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
19: lhi %r1,__NR_clock_gettime
svc 0
ahi %r15,16
- CFI_DEF_CFA_OFFSET 160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
CFI_RESTORE 15
br %r14
CFI_ENDPROC
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
index 3c0db0f..b23063f 100644
--- a/arch/s390/kernel/vdso32/gettimeofday.S
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -10,6 +10,7 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/dwarf.h>
+#include <asm/ptrace.h>
.text
.align 4
@@ -19,7 +20,7 @@
CFI_STARTPROC
ahi %r15,-16
CFI_ADJUST_CFA_OFFSET 16
- CFI_VAL_OFFSET 15, -160
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
basr %r5,0
0: al %r5,13f-0b(%r5) /* get &_vdso_data */
1: ltr %r3,%r3 /* check if tz is NULL */
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index ddebc26..bec19e7 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -19,7 +19,7 @@
KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
- $(call cc-ldoption, -Wl$(comma)--hash-style=both)
+ -Wl,--hash-style=both
$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
@@ -28,9 +28,10 @@
extra-y += vdso64.lds
CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
-# Disable gcov profiling and ubsan for VDSO code
+# Disable gcov profiling, ubsan and kasan for VDSO code
GCOV_PROFILE := n
UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
# Force dependency (incbin is bad)
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
index fac3ab5..9d2ee79 100644
--- a/arch/s390/kernel/vdso64/clock_gettime.S
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -10,6 +10,7 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/dwarf.h>
+#include <asm/ptrace.h>
.text
.align 4
@@ -18,8 +19,8 @@
__kernel_clock_gettime:
CFI_STARTPROC
aghi %r15,-16
- CFI_DEF_CFA_OFFSET 176
- CFI_VAL_OFFSET 15, -160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
larl %r5,_vdso_data
cghi %r2,__CLOCK_REALTIME_COARSE
je 4f
@@ -56,13 +57,13 @@
stg %r1,8(%r3) /* store tp->tv_nsec */
lghi %r2,0
aghi %r15,16
- CFI_DEF_CFA_OFFSET 160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
CFI_RESTORE 15
br %r14
/* CLOCK_MONOTONIC_COARSE */
- CFI_DEF_CFA_OFFSET 176
- CFI_VAL_OFFSET 15, -160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
3: lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */
tmll %r4,0x0001 /* pending update ? loop */
jnz 3b
@@ -115,13 +116,13 @@
stg %r1,8(%r3) /* store tp->tv_nsec */
lghi %r2,0
aghi %r15,16
- CFI_DEF_CFA_OFFSET 160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
CFI_RESTORE 15
br %r14
/* CPUCLOCK_VIRT for this thread */
- CFI_DEF_CFA_OFFSET 176
- CFI_VAL_OFFSET 15, -160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
9: lghi %r4,0
icm %r0,15,__VDSO_ECTG_OK(%r5)
jz 12f
@@ -142,17 +143,17 @@
stg %r4,8(%r3)
lghi %r2,0
aghi %r15,16
- CFI_DEF_CFA_OFFSET 160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
CFI_RESTORE 15
br %r14
/* Fallback to system call */
- CFI_DEF_CFA_OFFSET 176
- CFI_VAL_OFFSET 15, -160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
12: lghi %r1,__NR_clock_gettime
svc 0
aghi %r15,16
- CFI_DEF_CFA_OFFSET 160
+ CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
CFI_RESTORE 15
br %r14
CFI_ENDPROC
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
index 6e1f0b4..aebe10d 100644
--- a/arch/s390/kernel/vdso64/gettimeofday.S
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -10,6 +10,7 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/dwarf.h>
+#include <asm/ptrace.h>
.text
.align 4
@@ -19,7 +20,7 @@
CFI_STARTPROC
aghi %r15,-16
CFI_ADJUST_CFA_OFFSET 16
- CFI_VAL_OFFSET 15, -160
+ CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
larl %r5,_vdso_data
0: ltgr %r3,%r3 /* check if tz is NULL */
je 1f
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index b43f8d3..7e0eb40 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -16,6 +16,7 @@
#define RO_AFTER_INIT_DATA
#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
OUTPUT_ARCH(s390:64-bit)
@@ -31,10 +32,9 @@
SECTIONS
{
. = 0x100000;
- _stext = .; /* Start of text section */
.text : {
- /* Text and read-only data */
- _text = .;
+ _stext = .; /* Start of text section */
+ _text = .; /* Text and read-only data */
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
@@ -46,11 +46,10 @@
*(.text.*_indirect_*)
*(.fixup)
*(.gnu.warning)
+ . = ALIGN(PAGE_SIZE);
+ _etext = .; /* End of text section */
} :text = 0x0700
- . = ALIGN(PAGE_SIZE);
- _etext = .; /* End of text section */
-
NOTES :text :note
.dummy : { *(.dummy) } :data
@@ -64,12 +63,14 @@
__start_ro_after_init = .;
.data..ro_after_init : {
*(.data..ro_after_init)
+ JUMP_TABLE_DATA
}
EXCEPTION_TABLE(16)
. = ALIGN(PAGE_SIZE);
__end_ro_after_init = .;
RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE)
+ BOOT_DATA_PRESERVED
_edata = .; /* End of data section */
@@ -134,11 +135,25 @@
__nospec_return_end = . ;
}
+ BOOT_DATA
+
/* early.c uses stsi, which requires page aligned data. */
. = ALIGN(PAGE_SIZE);
INIT_DATA_SECTION(0x100)
PERCPU_SECTION(0x100)
+
+ .dynsym ALIGN(8) : {
+ __dynsym_start = .;
+ *(.dynsym)
+ __dynsym_end = .;
+ }
+ .rela.dyn ALIGN(8) : {
+ __rela_dyn_start = .;
+ *(.rela*)
+ __rela_dyn_end = .;
+ }
+
. = ALIGN(PAGE_SIZE);
__init_end = .; /* freed after init ends here */
@@ -146,6 +161,25 @@
_end = . ;
+ /*
+ * uncompressed image info used by the decompressor
+ * it should match struct vmlinux_info
+ */
+ .vmlinux.info 0 (INFO) : {
+ QUAD(_stext) /* default_lma */
+ QUAD(startup_continue) /* entry */
+ QUAD(__bss_start - _stext) /* image_size */
+ QUAD(__bss_stop - __bss_start) /* bss_size */
+ QUAD(__boot_data_start) /* bootdata_off */
+ QUAD(__boot_data_end - __boot_data_start) /* bootdata_size */
+ QUAD(__boot_data_preserved_start) /* bootdata_preserved_off */
+ QUAD(__boot_data_preserved_end -
+ __boot_data_preserved_start) /* bootdata_preserved_size */
+ QUAD(__dynsym_start) /* dynsym_start */
+ QUAD(__rela_dyn_start) /* rela_dyn_start */
+ QUAD(__rela_dyn_end) /* rela_dyn_end */
+ } :NONE
+
/* Debugging sections. */
STABS_DEBUG
DWARF_DEBUG
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index f24395a..c475ca4 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -37,7 +37,7 @@
{
u64 timer;
- asm volatile("stpt %0" : "=m" (timer));
+ asm volatile("stpt %0" : "=Q" (timer));
return timer;
}
@@ -48,7 +48,7 @@
asm volatile(
" stpt %0\n" /* Store current cpu timer value */
" spt %1" /* Set new value imm. afterwards */
- : "=m" (timer) : "m" (expires));
+ : "=Q" (timer) : "Q" (expires));
S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer;
S390_lowcore.last_update_timer = expires;
}
@@ -69,7 +69,7 @@
u64 delta, fac, mult, div;
int i;
- stcctm5(smp_cpu_mtid + 1, cycles_new);
+ stcctm(MT_DIAG, smp_cpu_mtid + 1, cycles_new);
cycles_old = this_cpu_ptr(mt_cycles);
fac = 1;
mult = div = 0;
@@ -124,7 +124,7 @@
*/
static int do_account_vtime(struct task_struct *tsk)
{
- u64 timer, clock, user, guest, system, hardirq, softirq, steal;
+ u64 timer, clock, user, guest, system, hardirq, softirq;
timer = S390_lowcore.last_update_timer;
clock = S390_lowcore.last_update_clock;
@@ -135,8 +135,8 @@
#else
" stck %1" /* Store current tod clock value */
#endif
- : "=m" (S390_lowcore.last_update_timer),
- "=m" (S390_lowcore.last_update_clock));
+ : "=Q" (S390_lowcore.last_update_timer),
+ "=Q" (S390_lowcore.last_update_clock));
clock = S390_lowcore.last_update_clock - clock;
timer -= S390_lowcore.last_update_timer;
@@ -182,12 +182,6 @@
if (softirq)
account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ);
- steal = S390_lowcore.steal_timer;
- if ((s64) steal > 0) {
- S390_lowcore.steal_timer = 0;
- account_steal_time(cputime_to_nsecs(steal));
- }
-
return virt_timer_forward(user + guest + system + hardirq + softirq);
}
@@ -213,8 +207,19 @@
*/
void vtime_flush(struct task_struct *tsk)
{
+ u64 steal, avg_steal;
+
if (do_account_vtime(tsk))
virt_timer_expire();
+
+ steal = S390_lowcore.steal_timer;
+ avg_steal = S390_lowcore.avg_steal_timer / 2;
+ if ((s64) steal > 0) {
+ S390_lowcore.steal_timer = 0;
+ account_steal_time(steal);
+ avg_steal += steal;
+ }
+ S390_lowcore.avg_steal_timer = avg_steal;
}
/*
@@ -432,6 +437,6 @@
__this_cpu_write(mt_scaling_jiffies, jiffies);
__this_cpu_write(mt_scaling_mult, 1);
__this_cpu_write(mt_scaling_div, 1);
- stcctm5(smp_cpu_mtid + 1, this_cpu_ptr(mt_cycles));
+ stcctm(MT_DIAG, smp_cpu_mtid + 1, this_cpu_ptr(mt_cycles));
}
}
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index a3dbd45..d3db3d7 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -21,7 +21,6 @@
prompt "Kernel-based Virtual Machine (KVM) support"
depends on HAVE_KVM
select PREEMPT_NOTIFIERS
- select ANON_INODES
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_VCPU_ASYNC_IOCTL
select HAVE_KVM_EVENTFD
@@ -31,6 +30,7 @@
select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_INVALID_WAKEUPS
+ select HAVE_KVM_NO_POLL
select SRCU
select KVM_VFIO
---help---
@@ -57,6 +57,6 @@
# OK, it's a little counter-intuitive to do this, but it puts it neatly under
# the virtualization menu.
-source drivers/vhost/Kconfig
+source "drivers/vhost/Kconfig"
endif # VIRTUALIZATION
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index fcb55b0..d1ccc16 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -7,10 +7,14 @@
* Author(s): Carsten Otte <cotte@de.ibm.com>
*/
+#define KMSG_COMPONENT "kvm-s390"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
#include <linux/interrupt.h>
#include <linux/kvm_host.h>
#include <linux/hrtimer.h>
#include <linux/mmu_context.h>
+#include <linux/nospec.h>
#include <linux/signal.h>
#include <linux/slab.h>
#include <linux/bitmap.h>
@@ -23,6 +27,7 @@
#include <asm/gmap.h>
#include <asm/switch_to.h>
#include <asm/nmi.h>
+#include <asm/airq.h>
#include "kvm-s390.h"
#include "gaccess.h"
#include "trace-s390.h"
@@ -31,6 +36,8 @@
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
+static struct kvm_s390_gib *gib;
+
/* handle external calls via sigp interpretation facility */
static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
{
@@ -217,22 +224,100 @@
*/
#define IPM_BIT_OFFSET (offsetof(struct kvm_s390_gisa, ipm) * BITS_PER_BYTE)
-static inline void kvm_s390_gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+/**
+ * gisa_set_iam - change the GISA interruption alert mask
+ *
+ * @gisa: gisa to operate on
+ * @iam: new IAM value to use
+ *
+ * Change the IAM atomically with the next alert address and the IPM
+ * of the GISA if the GISA is not part of the GIB alert list. All three
+ * fields are located in the first long word of the GISA.
+ *
+ * Returns: 0 on success
+ * -EBUSY in case the gisa is part of the alert list
+ */
+static inline int gisa_set_iam(struct kvm_s390_gisa *gisa, u8 iam)
+{
+ u64 word, _word;
+
+ do {
+ word = READ_ONCE(gisa->u64.word[0]);
+ if ((u64)gisa != word >> 32)
+ return -EBUSY;
+ _word = (word & ~0xffUL) | iam;
+ } while (cmpxchg(&gisa->u64.word[0], word, _word) != word);
+
+ return 0;
+}
+
+/**
+ * gisa_clear_ipm - clear the GISA interruption pending mask
+ *
+ * @gisa: gisa to operate on
+ *
+ * Clear the IPM atomically with the next alert address and the IAM
+ * of the GISA unconditionally. All three fields are located in the
+ * first long word of the GISA.
+ */
+static inline void gisa_clear_ipm(struct kvm_s390_gisa *gisa)
+{
+ u64 word, _word;
+
+ do {
+ word = READ_ONCE(gisa->u64.word[0]);
+ _word = word & ~(0xffUL << 24);
+ } while (cmpxchg(&gisa->u64.word[0], word, _word) != word);
+}
+
+/**
+ * gisa_get_ipm_or_restore_iam - return IPM or restore GISA IAM
+ *
+ * @gi: gisa interrupt struct to work on
+ *
+ * Atomically restores the interruption alert mask if none of the
+ * relevant ISCs are pending and return the IPM.
+ *
+ * Returns: the relevant pending ISCs
+ */
+static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi)
+{
+ u8 pending_mask, alert_mask;
+ u64 word, _word;
+
+ do {
+ word = READ_ONCE(gi->origin->u64.word[0]);
+ alert_mask = READ_ONCE(gi->alert.mask);
+ pending_mask = (u8)(word >> 24) & alert_mask;
+ if (pending_mask)
+ return pending_mask;
+ _word = (word & ~0xffUL) | alert_mask;
+ } while (cmpxchg(&gi->origin->u64.word[0], word, _word) != word);
+
+ return 0;
+}
+
+static inline int gisa_in_alert_list(struct kvm_s390_gisa *gisa)
+{
+ return READ_ONCE(gisa->next_alert) != (u32)(u64)gisa;
+}
+
+static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
{
set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
}
-static inline u8 kvm_s390_gisa_get_ipm(struct kvm_s390_gisa *gisa)
+static inline u8 gisa_get_ipm(struct kvm_s390_gisa *gisa)
{
return READ_ONCE(gisa->ipm);
}
-static inline void kvm_s390_gisa_clear_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+static inline void gisa_clear_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
{
clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
}
-static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+static inline int gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
{
return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
}
@@ -245,8 +330,13 @@
static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
{
- return pending_irqs_no_gisa(vcpu) |
- kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7;
+ struct kvm_s390_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int;
+ unsigned long pending_mask;
+
+ pending_mask = pending_irqs_no_gisa(vcpu);
+ if (gi->origin)
+ pending_mask |= gisa_get_ipm(gi->origin) << IRQ_PEND_IO_ISC_7;
+ return pending_mask;
}
static inline int isc_to_irq_type(unsigned long isc)
@@ -318,13 +408,13 @@
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
- set_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
+ set_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask);
}
static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
- clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
+ clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask);
}
static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
@@ -345,7 +435,7 @@
{
if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_IO_MASK))
return;
- else if (psw_ioint_disabled(vcpu))
+ if (psw_ioint_disabled(vcpu))
kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT);
else
vcpu->arch.sie_block->lctl |= LCTL_CR6;
@@ -353,7 +443,7 @@
static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
{
- if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK))
+ if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_EXT_MASK))
return;
if (psw_extint_disabled(vcpu))
kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
@@ -363,7 +453,7 @@
static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu)
{
- if (!(pending_irqs(vcpu) & IRQ_PEND_MCHK_MASK))
+ if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_MCHK_MASK))
return;
if (psw_mchk_disabled(vcpu))
vcpu->arch.sie_block->ictl |= ICTL_LPSW;
@@ -956,6 +1046,7 @@
{
struct list_head *isc_list;
struct kvm_s390_float_interrupt *fi;
+ struct kvm_s390_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int;
struct kvm_s390_interrupt_info *inti = NULL;
struct kvm_s390_io_info io;
u32 isc;
@@ -998,8 +1089,7 @@
goto out;
}
- if (vcpu->kvm->arch.gisa &&
- kvm_s390_gisa_tac_ipm_gisc(vcpu->kvm->arch.gisa, isc)) {
+ if (gi->origin && gisa_tac_ipm_gisc(gi->origin, isc)) {
/*
* in case an adapter interrupt was not delivered
* in SIE context KVM will handle the delivery
@@ -1089,6 +1179,7 @@
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
+ struct kvm_s390_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int;
u64 sltime;
vcpu->stat.exit_wait_state++;
@@ -1102,6 +1193,11 @@
return -EOPNOTSUPP; /* disabled wait */
}
+ if (gi->origin &&
+ (gisa_get_ipm_or_restore_iam(gi) &
+ vcpu->arch.sie_block->gcr[6] >> 24))
+ return 0;
+
if (!ckc_interrupts_enabled(vcpu) &&
!cpu_timer_interrupts_enabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
@@ -1128,28 +1224,11 @@
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
- /*
- * We cannot move this into the if, as the CPU might be already
- * in kvm_vcpu_block without having the waitqueue set (polling)
- */
vcpu->valid_wakeup = true;
+ kvm_vcpu_wake_up(vcpu);
+
/*
- * This is mostly to document, that the read in swait_active could
- * be moved before other stores, leading to subtle races.
- * All current users do not store or use an atomic like update
- */
- smp_mb__after_atomic();
- if (swait_active(&vcpu->wq)) {
- /*
- * The vcpu gave up the cpu voluntarily, mark it as a good
- * yield-candidate.
- */
- vcpu->preempted = true;
- swake_up_one(&vcpu->wq);
- vcpu->stat.halt_wakeup++;
- }
- /*
- * The VCPU might not be sleeping but is executing the VSIE. Let's
+ * The VCPU might not be sleeping but rather executing VSIE. Let's
* kick it, so it leaves the SIE to process the request.
*/
kvm_s390_vsie_kick(vcpu);
@@ -1533,18 +1612,19 @@
static int get_top_gisa_isc(struct kvm *kvm, u64 isc_mask, u32 schid)
{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
unsigned long active_mask;
int isc;
if (schid)
goto out;
- if (!kvm->arch.gisa)
+ if (!gi->origin)
goto out;
- active_mask = (isc_mask & kvm_s390_gisa_get_ipm(kvm->arch.gisa) << 24) << 32;
+ active_mask = (isc_mask & gisa_get_ipm(gi->origin) << 24) << 32;
while (active_mask) {
isc = __fls(active_mask) ^ (BITS_PER_LONG - 1);
- if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, isc))
+ if (gisa_tac_ipm_gisc(gi->origin, isc))
return isc;
clear_bit_inv(isc, &active_mask);
}
@@ -1567,6 +1647,7 @@
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
u64 isc_mask, u32 schid)
{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_s390_interrupt_info *inti, *tmp_inti;
int isc;
@@ -1584,7 +1665,7 @@
/* both types of interrupts present */
if (int_word_to_isc(inti->io.io_int_word) <= isc) {
/* classical IO int with higher priority */
- kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+ gisa_set_ipm_gisc(gi->origin, isc);
goto out;
}
gisa_out:
@@ -1596,7 +1677,7 @@
kvm_s390_reinject_io_int(kvm, inti);
inti = tmp_inti;
} else
- kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+ gisa_set_ipm_gisc(gi->origin, isc);
out:
return inti;
}
@@ -1685,6 +1766,7 @@
static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_s390_float_interrupt *fi;
struct list_head *list;
int isc;
@@ -1692,9 +1774,9 @@
kvm->stat.inject_io++;
isc = int_word_to_isc(inti->io.io_int_word);
- if (kvm->arch.gisa && inti->type & KVM_S390_INT_IO_AI_MASK) {
+ if (gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) {
VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc);
- kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+ gisa_set_ipm_gisc(gi->origin, isc);
kfree(inti);
return 0;
}
@@ -1726,7 +1808,6 @@
*/
static void __floating_irq_kick(struct kvm *kvm, u64 type)
{
- struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
struct kvm_vcpu *dst_vcpu;
int sigcpu, online_vcpus, nr_tries = 0;
@@ -1735,11 +1816,11 @@
return;
/* find idle VCPUs first, then round robin */
- sigcpu = find_first_bit(fi->idle_mask, online_vcpus);
+ sigcpu = find_first_bit(kvm->arch.idle_mask, online_vcpus);
if (sigcpu == online_vcpus) {
do {
- sigcpu = fi->next_rr_cpu;
- fi->next_rr_cpu = (fi->next_rr_cpu + 1) % online_vcpus;
+ sigcpu = kvm->arch.float_int.next_rr_cpu++;
+ kvm->arch.float_int.next_rr_cpu %= online_vcpus;
/* avoid endless loops if all vcpus are stopped */
if (nr_tries++ >= online_vcpus)
return;
@@ -1753,7 +1834,8 @@
kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT);
break;
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- if (!(type & KVM_S390_INT_IO_AI_MASK && kvm->arch.gisa))
+ if (!(type & KVM_S390_INT_IO_AI_MASK &&
+ kvm->arch.gisa_int.origin))
kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
break;
default:
@@ -1879,6 +1961,16 @@
case KVM_S390_MCHK:
irq->u.mchk.mcic = s390int->parm64;
break;
+ case KVM_S390_INT_PFAULT_INIT:
+ irq->u.ext.ext_params = s390int->parm;
+ irq->u.ext.ext_params2 = s390int->parm64;
+ break;
+ case KVM_S390_RESTART:
+ case KVM_S390_INT_CLOCK_COMP:
+ case KVM_S390_INT_CPU_TIMER:
+ break;
+ default:
+ return -EINVAL;
}
return 0;
}
@@ -2003,6 +2095,7 @@
static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_s390_interrupt_info *inti;
struct kvm_s390_float_interrupt *fi;
struct kvm_s390_irq *buf;
@@ -2026,15 +2119,14 @@
max_irqs = len / sizeof(struct kvm_s390_irq);
- if (kvm->arch.gisa &&
- kvm_s390_gisa_get_ipm(kvm->arch.gisa)) {
+ if (gi->origin && gisa_get_ipm(gi->origin)) {
for (i = 0; i <= MAX_ISC; i++) {
if (n == max_irqs) {
/* signal userspace to try again */
ret = -ENOMEM;
goto out_nolock;
}
- if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, i)) {
+ if (gisa_tac_ipm_gisc(gi->origin, i)) {
irq = (struct kvm_s390_irq *) &buf[n];
irq->type = KVM_S390_INT_IO(1, 0, 0, 0);
irq->u.io.io_int_word = isc_to_int_word(i);
@@ -2209,6 +2301,7 @@
{
if (id >= MAX_S390_IO_ADAPTERS)
return NULL;
+ id = array_index_nospec(id, MAX_S390_IO_ADAPTERS);
return kvm->arch.adapters[id];
}
@@ -2222,8 +2315,13 @@
(void __user *)attr->addr, sizeof(adapter_info)))
return -EFAULT;
- if ((adapter_info.id >= MAX_S390_IO_ADAPTERS) ||
- (dev->kvm->arch.adapters[adapter_info.id] != NULL))
+ if (adapter_info.id >= MAX_S390_IO_ADAPTERS)
+ return -EINVAL;
+
+ adapter_info.id = array_index_nospec(adapter_info.id,
+ MAX_S390_IO_ADAPTERS);
+
+ if (dev->kvm->arch.adapters[adapter_info.id] != NULL)
return -EINVAL;
adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
@@ -2278,7 +2376,7 @@
ret = -EFAULT;
goto out;
}
- ret = get_user_pages_fast(map->addr, 1, 1, &map->page);
+ ret = get_user_pages_fast(map->addr, 1, FOLL_WRITE, &map->page);
if (ret < 0)
goto out;
BUG_ON(ret != 1);
@@ -2831,7 +2929,7 @@
int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
{
int scn;
- unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+ DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
unsigned long pending_irqs;
struct kvm_s390_irq irq;
@@ -2884,27 +2982,278 @@
return n;
}
+static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask)
+{
+ int vcpu_id, online_vcpus = atomic_read(&kvm->online_vcpus);
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ struct kvm_vcpu *vcpu;
+
+ for_each_set_bit(vcpu_id, kvm->arch.idle_mask, online_vcpus) {
+ vcpu = kvm_get_vcpu(kvm, vcpu_id);
+ if (psw_ioint_disabled(vcpu))
+ continue;
+ deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
+ if (deliverable_mask) {
+ /* lately kicked but not yet running */
+ if (test_and_set_bit(vcpu_id, gi->kicked_mask))
+ return;
+ kvm_s390_vcpu_wakeup(vcpu);
+ return;
+ }
+ }
+}
+
+static enum hrtimer_restart gisa_vcpu_kicker(struct hrtimer *timer)
+{
+ struct kvm_s390_gisa_interrupt *gi =
+ container_of(timer, struct kvm_s390_gisa_interrupt, timer);
+ struct kvm *kvm =
+ container_of(gi->origin, struct sie_page2, gisa)->kvm;
+ u8 pending_mask;
+
+ pending_mask = gisa_get_ipm_or_restore_iam(gi);
+ if (pending_mask) {
+ __airqs_kick_single_vcpu(kvm, pending_mask);
+ hrtimer_forward_now(timer, ns_to_ktime(gi->expires));
+ return HRTIMER_RESTART;
+ };
+
+ return HRTIMER_NORESTART;
+}
+
+#define NULL_GISA_ADDR 0x00000000UL
+#define NONE_GISA_ADDR 0x00000001UL
+#define GISA_ADDR_MASK 0xfffff000UL
+
+static void process_gib_alert_list(void)
+{
+ struct kvm_s390_gisa_interrupt *gi;
+ struct kvm_s390_gisa *gisa;
+ struct kvm *kvm;
+ u32 final, origin = 0UL;
+
+ do {
+ /*
+ * If the NONE_GISA_ADDR is still stored in the alert list
+ * origin, we will leave the outer loop. No further GISA has
+ * been added to the alert list by millicode while processing
+ * the current alert list.
+ */
+ final = (origin & NONE_GISA_ADDR);
+ /*
+ * Cut off the alert list and store the NONE_GISA_ADDR in the
+ * alert list origin to avoid further GAL interruptions.
+ * A new alert list can be build up by millicode in parallel
+ * for guests not in the yet cut-off alert list. When in the
+ * final loop, store the NULL_GISA_ADDR instead. This will re-
+ * enable GAL interruptions on the host again.
+ */
+ origin = xchg(&gib->alert_list_origin,
+ (!final) ? NONE_GISA_ADDR : NULL_GISA_ADDR);
+ /*
+ * Loop through the just cut-off alert list and start the
+ * gisa timers to kick idle vcpus to consume the pending
+ * interruptions asap.
+ */
+ while (origin & GISA_ADDR_MASK) {
+ gisa = (struct kvm_s390_gisa *)(u64)origin;
+ origin = gisa->next_alert;
+ gisa->next_alert = (u32)(u64)gisa;
+ kvm = container_of(gisa, struct sie_page2, gisa)->kvm;
+ gi = &kvm->arch.gisa_int;
+ if (hrtimer_active(&gi->timer))
+ hrtimer_cancel(&gi->timer);
+ hrtimer_start(&gi->timer, 0, HRTIMER_MODE_REL);
+ }
+ } while (!final);
+
+}
+
void kvm_s390_gisa_clear(struct kvm *kvm)
{
- if (kvm->arch.gisa) {
- memset(kvm->arch.gisa, 0, sizeof(struct kvm_s390_gisa));
- kvm->arch.gisa->next_alert = (u32)(u64)kvm->arch.gisa;
- VM_EVENT(kvm, 3, "gisa 0x%pK cleared", kvm->arch.gisa);
- }
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+
+ if (!gi->origin)
+ return;
+ gisa_clear_ipm(gi->origin);
+ VM_EVENT(kvm, 3, "gisa 0x%pK cleared", gi->origin);
}
void kvm_s390_gisa_init(struct kvm *kvm)
{
- if (css_general_characteristics.aiv) {
- kvm->arch.gisa = &kvm->arch.sie_page2->gisa;
- VM_EVENT(kvm, 3, "gisa 0x%pK initialized", kvm->arch.gisa);
- kvm_s390_gisa_clear(kvm);
- }
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+
+ if (!css_general_characteristics.aiv)
+ return;
+ gi->origin = &kvm->arch.sie_page2->gisa;
+ gi->alert.mask = 0;
+ spin_lock_init(&gi->alert.ref_lock);
+ gi->expires = 50 * 1000; /* 50 usec */
+ hrtimer_init(&gi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ gi->timer.function = gisa_vcpu_kicker;
+ memset(gi->origin, 0, sizeof(struct kvm_s390_gisa));
+ gi->origin->next_alert = (u32)(u64)gi->origin;
+ VM_EVENT(kvm, 3, "gisa 0x%pK initialized", gi->origin);
}
void kvm_s390_gisa_destroy(struct kvm *kvm)
{
- if (!kvm->arch.gisa)
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+
+ if (!gi->origin)
return;
- kvm->arch.gisa = NULL;
+ if (gi->alert.mask)
+ KVM_EVENT(3, "vm 0x%pK has unexpected iam 0x%02x",
+ kvm, gi->alert.mask);
+ while (gisa_in_alert_list(gi->origin))
+ cpu_relax();
+ hrtimer_cancel(&gi->timer);
+ gi->origin = NULL;
+}
+
+/**
+ * kvm_s390_gisc_register - register a guest ISC
+ *
+ * @kvm: the kernel vm to work with
+ * @gisc: the guest interruption sub class to register
+ *
+ * The function extends the vm specific alert mask to use.
+ * The effective IAM mask in the GISA is updated as well
+ * in case the GISA is not part of the GIB alert list.
+ * It will be updated latest when the IAM gets restored
+ * by gisa_get_ipm_or_restore_iam().
+ *
+ * Returns: the nonspecific ISC (NISC) the gib alert mechanism
+ * has registered with the channel subsystem.
+ * -ENODEV in case the vm uses no GISA
+ * -ERANGE in case the guest ISC is invalid
+ */
+int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+
+ if (!gi->origin)
+ return -ENODEV;
+ if (gisc > MAX_ISC)
+ return -ERANGE;
+
+ spin_lock(&gi->alert.ref_lock);
+ gi->alert.ref_count[gisc]++;
+ if (gi->alert.ref_count[gisc] == 1) {
+ gi->alert.mask |= 0x80 >> gisc;
+ gisa_set_iam(gi->origin, gi->alert.mask);
+ }
+ spin_unlock(&gi->alert.ref_lock);
+
+ return gib->nisc;
+}
+EXPORT_SYMBOL_GPL(kvm_s390_gisc_register);
+
+/**
+ * kvm_s390_gisc_unregister - unregister a guest ISC
+ *
+ * @kvm: the kernel vm to work with
+ * @gisc: the guest interruption sub class to register
+ *
+ * The function reduces the vm specific alert mask to use.
+ * The effective IAM mask in the GISA is updated as well
+ * in case the GISA is not part of the GIB alert list.
+ * It will be updated latest when the IAM gets restored
+ * by gisa_get_ipm_or_restore_iam().
+ *
+ * Returns: the nonspecific ISC (NISC) the gib alert mechanism
+ * has registered with the channel subsystem.
+ * -ENODEV in case the vm uses no GISA
+ * -ERANGE in case the guest ISC is invalid
+ * -EINVAL in case the guest ISC is not registered
+ */
+int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ int rc = 0;
+
+ if (!gi->origin)
+ return -ENODEV;
+ if (gisc > MAX_ISC)
+ return -ERANGE;
+
+ spin_lock(&gi->alert.ref_lock);
+ if (gi->alert.ref_count[gisc] == 0) {
+ rc = -EINVAL;
+ goto out;
+ }
+ gi->alert.ref_count[gisc]--;
+ if (gi->alert.ref_count[gisc] == 0) {
+ gi->alert.mask &= ~(0x80 >> gisc);
+ gisa_set_iam(gi->origin, gi->alert.mask);
+ }
+out:
+ spin_unlock(&gi->alert.ref_lock);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister);
+
+static void gib_alert_irq_handler(struct airq_struct *airq, bool floating)
+{
+ inc_irq_stat(IRQIO_GAL);
+ process_gib_alert_list();
+}
+
+static struct airq_struct gib_alert_irq = {
+ .handler = gib_alert_irq_handler,
+ .lsi_ptr = &gib_alert_irq.lsi_mask,
+};
+
+void kvm_s390_gib_destroy(void)
+{
+ if (!gib)
+ return;
+ chsc_sgib(0);
+ unregister_adapter_interrupt(&gib_alert_irq);
+ free_page((unsigned long)gib);
+ gib = NULL;
+}
+
+int kvm_s390_gib_init(u8 nisc)
+{
+ int rc = 0;
+
+ if (!css_general_characteristics.aiv) {
+ KVM_EVENT(3, "%s", "gib not initialized, no AIV facility");
+ goto out;
+ }
+
+ gib = (struct kvm_s390_gib *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+ if (!gib) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ gib_alert_irq.isc = nisc;
+ if (register_adapter_interrupt(&gib_alert_irq)) {
+ pr_err("Registering the GIB alert interruption handler failed\n");
+ rc = -EIO;
+ goto out_free_gib;
+ }
+
+ gib->nisc = nisc;
+ if (chsc_sgib((u32)(u64)gib)) {
+ pr_err("Associating the GIB with the AIV facility failed\n");
+ free_page((unsigned long)gib);
+ gib = NULL;
+ rc = -EIO;
+ goto out_unreg_gal;
+ }
+
+ KVM_EVENT(3, "gib 0x%pK (nisc=%d) initialized", gib, gib->nisc);
+ goto out;
+
+out_unreg_gal:
+ unregister_adapter_interrupt(&gib_alert_irq);
+out_free_gib:
+ free_page((unsigned long)gib);
+ gib = NULL;
+out:
+ return rc;
}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ac5da6b..d047e84 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -11,6 +11,9 @@
* Jason J. Herne <jjherne@us.ibm.com>
*/
+#define KMSG_COMPONENT "kvm-s390"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/fs.h>
@@ -40,13 +43,10 @@
#include <asm/sclp.h>
#include <asm/cpacf.h>
#include <asm/timex.h>
+#include <asm/ap.h>
#include "kvm-s390.h"
#include "gaccess.h"
-#define KMSG_COMPONENT "kvm-s390"
-#undef pr_fmt
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
#define CREATE_TRACE_POINTS
#include "trace.h"
#include "trace-s390.h"
@@ -75,6 +75,7 @@
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
+ { "halt_no_poll_steal", VCPU_STAT(halt_no_poll_steal) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
@@ -177,6 +178,11 @@
module_param(hpage, int, 0444);
MODULE_PARM_DESC(hpage, "1m huge page backing support");
+/* maximum percentage of steal time for polling. >100 is treated like 100 */
+static u8 halt_poll_max_steal = 10;
+module_param(halt_poll_max_steal, byte, 0644);
+MODULE_PARM_DESC(halt_poll_max_steal, "Maximum percentage of steal time to allow polling");
+
/*
* For now we handle at most 16 double words as this is what the s390 base
* kernel handles and stores in the prefix page. If we ever need to go beyond
@@ -221,6 +227,11 @@
return 0;
}
+int kvm_arch_check_processor_compat(void)
+{
+ return 0;
+}
+
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
unsigned long end);
@@ -321,6 +332,22 @@
return cc == 0;
}
+static __always_inline void __insn32_query(unsigned int opcode, u8 *query)
+{
+ register unsigned long r0 asm("0") = 0; /* query function */
+ register unsigned long r1 asm("1") = (unsigned long) query;
+
+ asm volatile(
+ /* Parameter regs are ignored */
+ " .insn rrf,%[opc] << 16,2,4,6,0\n"
+ :
+ : "d" (r0), "a" (r1), [opc] "i" (opcode)
+ : "cc", "memory");
+}
+
+#define INSN_SORTL 0xb938
+#define INSN_DFLTCC 0xb939
+
static void kvm_s390_cpu_feat_init(void)
{
int i;
@@ -368,6 +395,16 @@
__cpacf_query(CPACF_KMA, (cpacf_mask_t *)
kvm_s390_available_subfunc.kma);
+ if (test_facility(155)) /* MSA9 */
+ __cpacf_query(CPACF_KDSA, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kdsa);
+
+ if (test_facility(150)) /* SORTL */
+ __insn32_query(INSN_SORTL, kvm_s390_available_subfunc.sortl);
+
+ if (test_facility(151)) /* DFLTCC */
+ __insn32_query(INSN_DFLTCC, kvm_s390_available_subfunc.dfltcc);
+
if (MACHINE_HAS_ESOP)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
/*
@@ -416,23 +453,42 @@
int kvm_arch_init(void *opaque)
{
+ int rc;
+
kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
if (!kvm_s390_dbf)
return -ENOMEM;
if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) {
- debug_unregister(kvm_s390_dbf);
- return -ENOMEM;
+ rc = -ENOMEM;
+ goto out_debug_unreg;
}
kvm_s390_cpu_feat_init();
/* Register floating interrupt controller interface. */
- return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
+ rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
+ if (rc) {
+ pr_err("A FLIC registration call failed with rc=%d\n", rc);
+ goto out_debug_unreg;
+ }
+
+ rc = kvm_s390_gib_init(GAL_ISC);
+ if (rc)
+ goto out_gib_destroy;
+
+ return 0;
+
+out_gib_destroy:
+ kvm_s390_gib_destroy();
+out_debug_unreg:
+ debug_unregister(kvm_s390_dbf);
+ return rc;
}
void kvm_arch_exit(void)
{
+ kvm_s390_gib_destroy();
debug_unregister(kvm_s390_dbf);
}
@@ -463,7 +519,6 @@
case KVM_CAP_S390_CSS_SUPPORT:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_DEVICE_CTRL:
- case KVM_CAP_ENABLE_CAP_VM:
case KVM_CAP_S390_IRQCHIP:
case KVM_CAP_VM_ATTRIBUTES:
case KVM_CAP_MP_STATE:
@@ -489,15 +544,13 @@
break;
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
+ case KVM_CAP_MAX_VCPU_ID:
r = KVM_S390_BSCA_CPU_SLOTS;
if (!kvm_s390_use_sca_entries())
r = KVM_MAX_VCPUS;
else if (sclp.has_esca && sclp.has_64bscao)
r = KVM_S390_ESCA_CPU_SLOTS;
break;
- case KVM_CAP_NR_MEMSLOTS:
- r = KVM_USER_MEM_SLOTS;
- break;
case KVM_CAP_S390_COW:
r = MACHINE_HAS_ESOP;
break;
@@ -606,7 +659,7 @@
}
}
-static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
+int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
{
int r;
@@ -639,6 +692,14 @@
set_kvm_facility(kvm->arch.model.fac_mask, 135);
set_kvm_facility(kvm->arch.model.fac_list, 135);
}
+ if (test_facility(148)) {
+ set_kvm_facility(kvm->arch.model.fac_mask, 148);
+ set_kvm_facility(kvm->arch.model.fac_list, 148);
+ }
+ if (test_facility(152)) {
+ set_kvm_facility(kvm->arch.model.fac_mask, 152);
+ set_kvm_facility(kvm->arch.model.fac_list, 152);
+ }
r = 0;
} else
r = -EINVAL;
@@ -844,20 +905,24 @@
kvm_s390_vcpu_block_all(kvm);
- kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_for_each_vcpu(i, vcpu, kvm) {
kvm_s390_vcpu_crypto_setup(vcpu);
+ /* recreate the shadow crycb by leaving the VSIE handler */
+ kvm_s390_sync_request(KVM_REQ_VSIE_RESTART, vcpu);
+ }
kvm_s390_vcpu_unblock_all(kvm);
}
static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
{
- if (!test_kvm_facility(kvm, 76))
- return -EINVAL;
-
mutex_lock(&kvm->lock);
switch (attr->attr) {
case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
+ if (!test_kvm_facility(kvm, 76)) {
+ mutex_unlock(&kvm->lock);
+ return -EINVAL;
+ }
get_random_bytes(
kvm->arch.crypto.crycb->aes_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
@@ -865,6 +930,10 @@
VM_EVENT(kvm, 3, "%s", "ENABLE: AES keywrapping support");
break;
case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
+ if (!test_kvm_facility(kvm, 76)) {
+ mutex_unlock(&kvm->lock);
+ return -EINVAL;
+ }
get_random_bytes(
kvm->arch.crypto.crycb->dea_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
@@ -872,17 +941,39 @@
VM_EVENT(kvm, 3, "%s", "ENABLE: DEA keywrapping support");
break;
case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
+ if (!test_kvm_facility(kvm, 76)) {
+ mutex_unlock(&kvm->lock);
+ return -EINVAL;
+ }
kvm->arch.crypto.aes_kw = 0;
memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
VM_EVENT(kvm, 3, "%s", "DISABLE: AES keywrapping support");
break;
case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
+ if (!test_kvm_facility(kvm, 76)) {
+ mutex_unlock(&kvm->lock);
+ return -EINVAL;
+ }
kvm->arch.crypto.dea_kw = 0;
memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
VM_EVENT(kvm, 3, "%s", "DISABLE: DEA keywrapping support");
break;
+ case KVM_S390_VM_CRYPTO_ENABLE_APIE:
+ if (!ap_instructions_available()) {
+ mutex_unlock(&kvm->lock);
+ return -EOPNOTSUPP;
+ }
+ kvm->arch.crypto.apie = 1;
+ break;
+ case KVM_S390_VM_CRYPTO_DISABLE_APIE:
+ if (!ap_instructions_available()) {
+ mutex_unlock(&kvm->lock);
+ return -EOPNOTSUPP;
+ }
+ kvm->arch.crypto.apie = 0;
+ break;
default:
mutex_unlock(&kvm->lock);
return -ENXIO;
@@ -927,6 +1018,8 @@
/* mark all the pages in active slots as dirty */
for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
ms = slots->memslots + slotnr;
+ if (!ms->dirty_bitmap)
+ return -EINVAL;
/*
* The second half of the bitmap is only used on x86,
* and would be wasted otherwise, so we put it to good
@@ -1218,11 +1311,78 @@
static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
struct kvm_device_attr *attr)
{
- /*
- * Once supported by kernel + hw, we have to store the subfunctions
- * in kvm->arch and remember that user space configured them.
- */
- return -ENXIO;
+ mutex_lock(&kvm->lock);
+ if (kvm->created_vcpus) {
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
+ }
+
+ if (copy_from_user(&kvm->arch.model.subfuncs, (void __user *)attr->addr,
+ sizeof(struct kvm_s390_vm_cpu_subfunc))) {
+ mutex_unlock(&kvm->lock);
+ return -EFAULT;
+ }
+ mutex_unlock(&kvm->lock);
+
+ VM_EVENT(kvm, 3, "SET: guest PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.plo)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.plo)[1],
+ ((unsigned long *) &kvm->arch.model.subfuncs.plo)[2],
+ ((unsigned long *) &kvm->arch.model.subfuncs.plo)[3]);
+ VM_EVENT(kvm, 3, "SET: guest PTFF subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.ptff)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.ptff)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KMAC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmac)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmac)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KMC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmc)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmc)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KM subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.km)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.km)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KIMD subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kimd)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kimd)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KLMD subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.klmd)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.klmd)[1]);
+ VM_EVENT(kvm, 3, "SET: guest PCKMO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KMCTR subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KMF subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmf)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmf)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KMO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmo)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmo)[1]);
+ VM_EVENT(kvm, 3, "SET: guest PCC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.pcc)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.pcc)[1]);
+ VM_EVENT(kvm, 3, "SET: guest PPNO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.ppno)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.ppno)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KMA subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kma)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kma)[1]);
+ VM_EVENT(kvm, 3, "SET: guest KDSA subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kdsa)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kdsa)[1]);
+ VM_EVENT(kvm, 3, "SET: guest SORTL subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[1],
+ ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[2],
+ ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[3]);
+ VM_EVENT(kvm, 3, "SET: guest DFLTCC subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[1],
+ ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[2],
+ ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[3]);
+
+ return 0;
}
static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
@@ -1341,12 +1501,69 @@
static int kvm_s390_get_processor_subfunc(struct kvm *kvm,
struct kvm_device_attr *attr)
{
- /*
- * Once we can actually configure subfunctions (kernel + hw support),
- * we have to check if they were already set by user space, if so copy
- * them from kvm->arch.
- */
- return -ENXIO;
+ if (copy_to_user((void __user *)attr->addr, &kvm->arch.model.subfuncs,
+ sizeof(struct kvm_s390_vm_cpu_subfunc)))
+ return -EFAULT;
+
+ VM_EVENT(kvm, 3, "GET: guest PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.plo)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.plo)[1],
+ ((unsigned long *) &kvm->arch.model.subfuncs.plo)[2],
+ ((unsigned long *) &kvm->arch.model.subfuncs.plo)[3]);
+ VM_EVENT(kvm, 3, "GET: guest PTFF subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.ptff)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.ptff)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KMAC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmac)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmac)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KMC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmc)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmc)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KM subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.km)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.km)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KIMD subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kimd)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kimd)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KLMD subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.klmd)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.klmd)[1]);
+ VM_EVENT(kvm, 3, "GET: guest PCKMO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KMCTR subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KMF subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmf)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmf)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KMO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmo)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kmo)[1]);
+ VM_EVENT(kvm, 3, "GET: guest PCC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.pcc)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.pcc)[1]);
+ VM_EVENT(kvm, 3, "GET: guest PPNO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.ppno)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.ppno)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KMA subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kma)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kma)[1]);
+ VM_EVENT(kvm, 3, "GET: guest KDSA subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.kdsa)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.kdsa)[1]);
+ VM_EVENT(kvm, 3, "GET: guest SORTL subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[1],
+ ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[2],
+ ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[3]);
+ VM_EVENT(kvm, 3, "GET: guest DFLTCC subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[0],
+ ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[1],
+ ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[2],
+ ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[3]);
+
+ return 0;
}
static int kvm_s390_get_machine_subfunc(struct kvm *kvm,
@@ -1355,8 +1572,68 @@
if (copy_to_user((void __user *)attr->addr, &kvm_s390_available_subfunc,
sizeof(struct kvm_s390_vm_cpu_subfunc)))
return -EFAULT;
+
+ VM_EVENT(kvm, 3, "GET: host PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.plo)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.plo)[1],
+ ((unsigned long *) &kvm_s390_available_subfunc.plo)[2],
+ ((unsigned long *) &kvm_s390_available_subfunc.plo)[3]);
+ VM_EVENT(kvm, 3, "GET: host PTFF subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.ptff)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.ptff)[1]);
+ VM_EVENT(kvm, 3, "GET: host KMAC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.kmac)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.kmac)[1]);
+ VM_EVENT(kvm, 3, "GET: host KMC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.kmc)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.kmc)[1]);
+ VM_EVENT(kvm, 3, "GET: host KM subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.km)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.km)[1]);
+ VM_EVENT(kvm, 3, "GET: host KIMD subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.kimd)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.kimd)[1]);
+ VM_EVENT(kvm, 3, "GET: host KLMD subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.klmd)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.klmd)[1]);
+ VM_EVENT(kvm, 3, "GET: host PCKMO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.pckmo)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.pckmo)[1]);
+ VM_EVENT(kvm, 3, "GET: host KMCTR subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.kmctr)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.kmctr)[1]);
+ VM_EVENT(kvm, 3, "GET: host KMF subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.kmf)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.kmf)[1]);
+ VM_EVENT(kvm, 3, "GET: host KMO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.kmo)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.kmo)[1]);
+ VM_EVENT(kvm, 3, "GET: host PCC subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.pcc)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.pcc)[1]);
+ VM_EVENT(kvm, 3, "GET: host PPNO subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.ppno)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.ppno)[1]);
+ VM_EVENT(kvm, 3, "GET: host KMA subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.kma)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.kma)[1]);
+ VM_EVENT(kvm, 3, "GET: host KDSA subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.kdsa)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.kdsa)[1]);
+ VM_EVENT(kvm, 3, "GET: host SORTL subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.sortl)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.sortl)[1],
+ ((unsigned long *) &kvm_s390_available_subfunc.sortl)[2],
+ ((unsigned long *) &kvm_s390_available_subfunc.sortl)[3]);
+ VM_EVENT(kvm, 3, "GET: host DFLTCC subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[1],
+ ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[2],
+ ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[3]);
+
return 0;
}
+
static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret = -ENXIO;
@@ -1474,10 +1751,9 @@
case KVM_S390_VM_CPU_PROCESSOR_FEAT:
case KVM_S390_VM_CPU_MACHINE_FEAT:
case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
+ case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
ret = 0;
break;
- /* configuring subfunctions is not supported yet */
- case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
default:
ret = -ENXIO;
break;
@@ -1491,6 +1767,10 @@
case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
ret = 0;
break;
+ case KVM_S390_VM_CRYPTO_ENABLE_APIE:
+ case KVM_S390_VM_CRYPTO_DISABLE_APIE:
+ ret = ap_instructions_available() ? 0 : -ENXIO;
+ break;
default:
ret = -ENXIO;
break;
@@ -1898,14 +2178,6 @@
r = kvm_s390_inject_vm(kvm, &s390int);
break;
}
- case KVM_ENABLE_CAP: {
- struct kvm_enable_cap cap;
- r = -EFAULT;
- if (copy_from_user(&cap, argp, sizeof(cap)))
- break;
- r = kvm_vm_ioctl_enable_cap(kvm, &cap);
- break;
- }
case KVM_CREATE_IRQCHIP: {
struct kvm_irq_routing_entry routing;
@@ -1992,55 +2264,101 @@
return r;
}
-static int kvm_s390_query_ap_config(u8 *config)
-{
- u32 fcn_code = 0x04000000UL;
- u32 cc = 0;
-
- memset(config, 0, 128);
- asm volatile(
- "lgr 0,%1\n"
- "lgr 2,%2\n"
- ".long 0xb2af0000\n" /* PQAP(QCI) */
- "0: ipm %0\n"
- "srl %0,28\n"
- "1:\n"
- EX_TABLE(0b, 1b)
- : "+r" (cc)
- : "r" (fcn_code), "r" (config)
- : "cc", "0", "2", "memory"
- );
-
- return cc;
-}
-
static int kvm_s390_apxa_installed(void)
{
- u8 config[128];
- int cc;
+ struct ap_config_info info;
- if (test_facility(12)) {
- cc = kvm_s390_query_ap_config(config);
-
- if (cc)
- pr_err("PQAP(QCI) failed with cc=%d", cc);
- else
- return config[0] & 0x40;
+ if (ap_instructions_available()) {
+ if (ap_qci(&info) == 0)
+ return info.apxa;
}
return 0;
}
+/*
+ * The format of the crypto control block (CRYCB) is specified in the 3 low
+ * order bits of the CRYCB designation (CRYCBD) field as follows:
+ * Format 0: Neither the message security assist extension 3 (MSAX3) nor the
+ * AP extended addressing (APXA) facility are installed.
+ * Format 1: The APXA facility is not installed but the MSAX3 facility is.
+ * Format 2: Both the APXA and MSAX3 facilities are installed
+ */
static void kvm_s390_set_crycb_format(struct kvm *kvm)
{
kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb;
+ /* Clear the CRYCB format bits - i.e., set format 0 by default */
+ kvm->arch.crypto.crycbd &= ~(CRYCB_FORMAT_MASK);
+
+ /* Check whether MSAX3 is installed */
+ if (!test_kvm_facility(kvm, 76))
+ return;
+
if (kvm_s390_apxa_installed())
kvm->arch.crypto.crycbd |= CRYCB_FORMAT2;
else
kvm->arch.crypto.crycbd |= CRYCB_FORMAT1;
}
+void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm,
+ unsigned long *aqm, unsigned long *adm)
+{
+ struct kvm_s390_crypto_cb *crycb = kvm->arch.crypto.crycb;
+
+ mutex_lock(&kvm->lock);
+ kvm_s390_vcpu_block_all(kvm);
+
+ switch (kvm->arch.crypto.crycbd & CRYCB_FORMAT_MASK) {
+ case CRYCB_FORMAT2: /* APCB1 use 256 bits */
+ memcpy(crycb->apcb1.apm, apm, 32);
+ VM_EVENT(kvm, 3, "SET CRYCB: apm %016lx %016lx %016lx %016lx",
+ apm[0], apm[1], apm[2], apm[3]);
+ memcpy(crycb->apcb1.aqm, aqm, 32);
+ VM_EVENT(kvm, 3, "SET CRYCB: aqm %016lx %016lx %016lx %016lx",
+ aqm[0], aqm[1], aqm[2], aqm[3]);
+ memcpy(crycb->apcb1.adm, adm, 32);
+ VM_EVENT(kvm, 3, "SET CRYCB: adm %016lx %016lx %016lx %016lx",
+ adm[0], adm[1], adm[2], adm[3]);
+ break;
+ case CRYCB_FORMAT1:
+ case CRYCB_FORMAT0: /* Fall through both use APCB0 */
+ memcpy(crycb->apcb0.apm, apm, 8);
+ memcpy(crycb->apcb0.aqm, aqm, 2);
+ memcpy(crycb->apcb0.adm, adm, 2);
+ VM_EVENT(kvm, 3, "SET CRYCB: apm %016lx aqm %04x adm %04x",
+ apm[0], *((unsigned short *)aqm),
+ *((unsigned short *)adm));
+ break;
+ default: /* Can not happen */
+ break;
+ }
+
+ /* recreate the shadow crycb for each vcpu */
+ kvm_s390_sync_request_broadcast(kvm, KVM_REQ_VSIE_RESTART);
+ kvm_s390_vcpu_unblock_all(kvm);
+ mutex_unlock(&kvm->lock);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_crypto_set_masks);
+
+void kvm_arch_crypto_clear_masks(struct kvm *kvm)
+{
+ mutex_lock(&kvm->lock);
+ kvm_s390_vcpu_block_all(kvm);
+
+ memset(&kvm->arch.crypto.crycb->apcb0, 0,
+ sizeof(kvm->arch.crypto.crycb->apcb0));
+ memset(&kvm->arch.crypto.crycb->apcb1, 0,
+ sizeof(kvm->arch.crypto.crycb->apcb1));
+
+ VM_EVENT(kvm, 3, "%s", "CLR CRYCB:");
+ /* recreate the shadow crycb for each vcpu */
+ kvm_s390_sync_request_broadcast(kvm, KVM_REQ_VSIE_RESTART);
+ kvm_s390_vcpu_unblock_all(kvm);
+ mutex_unlock(&kvm->lock);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_crypto_clear_masks);
+
static u64 kvm_s390_get_initial_cpuid(void)
{
struct cpuid cpuid;
@@ -2052,12 +2370,12 @@
static void kvm_s390_crypto_init(struct kvm *kvm)
{
- if (!test_kvm_facility(kvm, 76))
- return;
-
kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
kvm_s390_set_crycb_format(kvm);
+ if (!test_kvm_facility(kvm, 76))
+ return;
+
/* Enable AES/DEA protected key functions by default */
kvm->arch.crypto.aes_kw = 1;
kvm->arch.crypto.dea_kw = 1;
@@ -2107,13 +2425,13 @@
kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags);
if (!kvm->arch.sca)
goto out_err;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
sca_offset += 16;
if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
sca_offset = 0;
kvm->arch.sca = (struct bsca_block *)
((char *) kvm->arch.sca + sca_offset);
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
sprintf(debug_name, "kvm-%u", current->pid);
@@ -2127,6 +2445,7 @@
if (!kvm->arch.sie_page2)
goto out_err;
+ kvm->arch.sie_page2->kvm = kvm;
kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
for (i = 0; i < kvm_s390_fac_size(); i++) {
@@ -2136,6 +2455,7 @@
kvm->arch.model.fac_list[i] = S390_lowcore.stfle_fac_list[i] &
kvm_s390_fac_base[i];
}
+ kvm->arch.model.subfuncs = kvm_s390_available_subfunc;
/* we are always in czam mode - even on pre z14 machines */
set_kvm_facility(kvm->arch.model.fac_mask, 138);
@@ -2148,6 +2468,9 @@
set_kvm_facility(kvm->arch.model.fac_list, 147);
}
+ if (css_general_characteristics.aiv && test_facility(65))
+ set_kvm_facility(kvm->arch.model.fac_mask, 65);
+
kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
kvm->arch.model.ibc = sclp.ibc & 0x0fff;
@@ -2195,16 +2518,6 @@
return rc;
}
-bool kvm_arch_has_vcpu_debugfs(void)
-{
- return false;
-}
-
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
-{
- return 0;
-}
-
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 3, "%s", "free cpu");
@@ -2581,19 +2894,52 @@
vcpu->arch.enabled_gmap = vcpu->arch.gmap;
}
+static bool kvm_has_pckmo_subfunc(struct kvm *kvm, unsigned long nr)
+{
+ if (test_bit_inv(nr, (unsigned long *)&kvm->arch.model.subfuncs.pckmo) &&
+ test_bit_inv(nr, (unsigned long *)&kvm_s390_available_subfunc.pckmo))
+ return true;
+ return false;
+}
+
+static bool kvm_has_pckmo_ecc(struct kvm *kvm)
+{
+ /* At least one ECC subfunction must be present */
+ return kvm_has_pckmo_subfunc(kvm, 32) ||
+ kvm_has_pckmo_subfunc(kvm, 33) ||
+ kvm_has_pckmo_subfunc(kvm, 34) ||
+ kvm_has_pckmo_subfunc(kvm, 40) ||
+ kvm_has_pckmo_subfunc(kvm, 41);
+
+}
+
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
{
- if (!test_kvm_facility(vcpu->kvm, 76))
+ /*
+ * If the AP instructions are not being interpreted and the MSAX3
+ * facility is not configured for the guest, there is nothing to set up.
+ */
+ if (!vcpu->kvm->arch.crypto.apie && !test_kvm_facility(vcpu->kvm, 76))
return;
+ vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA);
+ vcpu->arch.sie_block->eca &= ~ECA_APIE;
+ vcpu->arch.sie_block->ecd &= ~ECD_ECC;
- if (vcpu->kvm->arch.crypto.aes_kw)
+ if (vcpu->kvm->arch.crypto.apie)
+ vcpu->arch.sie_block->eca |= ECA_APIE;
+
+ /* Set up protected key support */
+ if (vcpu->kvm->arch.crypto.aes_kw) {
vcpu->arch.sie_block->ecb3 |= ECB3_AES;
+ /* ecc is also wrapped with AES key */
+ if (kvm_has_pckmo_ecc(vcpu->kvm))
+ vcpu->arch.sie_block->ecd |= ECD_ECC;
+ }
+
if (vcpu->kvm->arch.crypto.dea_kw)
vcpu->arch.sie_block->ecb3 |= ECB3_DEA;
-
- vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
}
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
@@ -2685,6 +3031,8 @@
hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
+ vcpu->arch.sie_block->hpid = HPID_KVM;
+
kvm_s390_vcpu_crypto_setup(vcpu);
return rc;
@@ -2720,7 +3068,7 @@
vcpu->arch.sie_block->icpua = id;
spin_lock_init(&vcpu->arch.local_int.lock);
- vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa;
+ vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa_int.origin;
if (vcpu->arch.sie_block->gd && sclp.has_gisaf)
vcpu->arch.sie_block->gd |= GISA_FORMAT1;
seqcount_init(&vcpu->arch.cputm_seqcount);
@@ -2768,18 +3116,25 @@
exit_sie(vcpu);
}
+bool kvm_s390_vcpu_sie_inhibited(struct kvm_vcpu *vcpu)
+{
+ return atomic_read(&vcpu->arch.sie_block->prog20) &
+ (PROG_BLOCK_SIE | PROG_REQUEST);
+}
+
static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
{
atomic_andnot(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
}
/*
- * Kick a guest cpu out of SIE and wait until SIE is not running.
+ * Kick a guest cpu out of (v)SIE and wait until (v)SIE is not running.
* If the CPU is not running (e.g. waiting as idle) the function will
* return immediately. */
void exit_sie(struct kvm_vcpu *vcpu)
{
kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
+ kvm_s390_vsie_kick(vcpu);
while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
cpu_relax();
}
@@ -2815,6 +3170,17 @@
}
}
+bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
+{
+ /* do not poll with more than halt_poll_max_steal percent of steal time */
+ if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >=
+ halt_poll_max_steal) {
+ vcpu->stat.halt_no_poll_steal++;
+ return true;
+ }
+ return false;
+}
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
/* kvm common code refers to this, but never calls it */
@@ -3196,6 +3562,8 @@
/* nothing to do, just clear the request */
kvm_clear_request(KVM_REQ_UNHALT, vcpu);
+ /* we left the vsie handler, nothing to do, just clear the request */
+ kvm_clear_request(KVM_REQ_VSIE_RESTART, vcpu);
return 0;
}
@@ -3357,6 +3725,8 @@
kvm_s390_patch_guest_per_regs(vcpu);
}
+ clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.gisa_int.kicked_mask);
+
vcpu->arch.sie_block->icptcode = 0;
cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
@@ -3630,6 +4000,10 @@
if (kvm_run->immediate_exit)
return -EINTR;
+ if (kvm_run->kvm_valid_regs & ~KVM_SYNC_S390_VALID_FIELDS ||
+ kvm_run->kvm_dirty_regs & ~KVM_SYNC_S390_VALID_FIELDS)
+ return -EINVAL;
+
vcpu_load(vcpu);
if (guestdbg_exit_pending(vcpu)) {
@@ -3887,7 +4261,7 @@
const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
| KVM_S390_MEMOP_F_CHECK_ONLY;
- if (mop->flags & ~supported_flags)
+ if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size)
return -EINVAL;
if (mop->size > MEM_OP_MAX_SIZE)
@@ -3955,7 +4329,7 @@
}
case KVM_S390_INTERRUPT: {
struct kvm_s390_interrupt s390int;
- struct kvm_s390_irq s390irq;
+ struct kvm_s390_irq s390irq = {};
if (copy_from_user(&s390int, argp, sizeof(s390int)))
return -EFAULT;
@@ -4155,21 +4529,28 @@
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
- int rc;
+ int rc = 0;
- /* If the basics of the memslot do not change, we do not want
- * to update the gmap. Every update causes several unnecessary
- * segment translation exceptions. This is usually handled just
- * fine by the normal fault handler + gmap, but it will also
- * cause faults on the prefix page of running guest CPUs.
- */
- if (old->userspace_addr == mem->userspace_addr &&
- old->base_gfn * PAGE_SIZE == mem->guest_phys_addr &&
- old->npages * PAGE_SIZE == mem->memory_size)
- return;
-
- rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
- mem->guest_phys_addr, mem->memory_size);
+ switch (change) {
+ case KVM_MR_DELETE:
+ rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,
+ old->npages * PAGE_SIZE);
+ break;
+ case KVM_MR_MOVE:
+ rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,
+ old->npages * PAGE_SIZE);
+ if (rc)
+ break;
+ /* FALLTHROUGH */
+ case KVM_MR_CREATE:
+ rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
+ mem->guest_phys_addr, mem->memory_size);
+ break;
+ case KVM_MR_FLAGS_ONLY:
+ break;
+ default:
+ WARN(1, "Unknown KVM MR CHANGE: %d\n", change);
+ }
if (rc)
pr_warn("failed to commit memory region\n");
return;
@@ -4192,12 +4573,12 @@
int i;
if (!sclp.has_sief2) {
- pr_info("SIE not available\n");
+ pr_info("SIE is not available\n");
return -ENODEV;
}
if (nested && hpage) {
- pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently");
+ pr_info("A KVM host that supports nesting cannot back its KVM guests with huge pages\n");
return -EINVAL;
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 981e3ba..6d9448d 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -67,7 +67,7 @@
static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
{
- return test_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
+ return test_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask);
}
static inline int kvm_is_ucontrol(struct kvm *kvm)
@@ -290,6 +290,7 @@
void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu);
+bool kvm_s390_vcpu_sie_inhibited(struct kvm_vcpu *vcpu);
void exit_sie(struct kvm_vcpu *vcpu);
void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu);
int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
@@ -380,6 +381,8 @@
void kvm_s390_gisa_init(struct kvm *kvm);
void kvm_s390_gisa_clear(struct kvm *kvm);
void kvm_s390_gisa_destroy(struct kvm *kvm);
+int kvm_s390_gib_init(u8 nisc);
+void kvm_s390_gib_destroy(void);
/* implemented in guestdbg.c */
void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 8679bd7..ed52ffa 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -27,6 +27,7 @@
#include <asm/io.h>
#include <asm/ptrace.h>
#include <asm/sclp.h>
+#include <asm/ap.h>
#include "gaccess.h"
#include "kvm-s390.h"
#include "trace.h"
@@ -592,6 +593,89 @@
}
}
+/*
+ * handle_pqap: Handling pqap interception
+ * @vcpu: the vcpu having issue the pqap instruction
+ *
+ * We now support PQAP/AQIC instructions and we need to correctly
+ * answer the guest even if no dedicated driver's hook is available.
+ *
+ * The intercepting code calls a dedicated callback for this instruction
+ * if a driver did register one in the CRYPTO satellite of the
+ * SIE block.
+ *
+ * If no callback is available, the queues are not available, return this
+ * response code to the caller and set CC to 3.
+ * Else return the response code returned by the callback.
+ */
+static int handle_pqap(struct kvm_vcpu *vcpu)
+{
+ struct ap_queue_status status = {};
+ unsigned long reg0;
+ int ret;
+ uint8_t fc;
+
+ /* Verify that the AP instruction are available */
+ if (!ap_instructions_available())
+ return -EOPNOTSUPP;
+ /* Verify that the guest is allowed to use AP instructions */
+ if (!(vcpu->arch.sie_block->eca & ECA_APIE))
+ return -EOPNOTSUPP;
+ /*
+ * The only possibly intercepted functions when AP instructions are
+ * available for the guest are AQIC and TAPQ with the t bit set
+ * since we do not set IC.3 (FIII) we currently will only intercept
+ * the AQIC function code.
+ */
+ reg0 = vcpu->run->s.regs.gprs[0];
+ fc = (reg0 >> 24) & 0xff;
+ if (WARN_ON_ONCE(fc != 0x03))
+ return -EOPNOTSUPP;
+
+ /* PQAP instruction is allowed for guest kernel only */
+ if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+ return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+ /* Common PQAP instruction specification exceptions */
+ /* bits 41-47 must all be zeros */
+ if (reg0 & 0x007f0000UL)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ /* APFT not install and T bit set */
+ if (!test_kvm_facility(vcpu->kvm, 15) && (reg0 & 0x00800000UL))
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ /* APXA not installed and APID greater 64 or APQI greater 16 */
+ if (!(vcpu->kvm->arch.crypto.crycbd & 0x02) && (reg0 & 0x0000c0f0UL))
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ /* AQIC function code specific exception */
+ /* facility 65 not present for AQIC function code */
+ if (!test_kvm_facility(vcpu->kvm, 65))
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ /*
+ * Verify that the hook callback is registered, lock the owner
+ * and call the hook.
+ */
+ if (vcpu->kvm->arch.crypto.pqap_hook) {
+ if (!try_module_get(vcpu->kvm->arch.crypto.pqap_hook->owner))
+ return -EOPNOTSUPP;
+ ret = vcpu->kvm->arch.crypto.pqap_hook->hook(vcpu);
+ module_put(vcpu->kvm->arch.crypto.pqap_hook->owner);
+ if (!ret && vcpu->run->s.regs.gprs[1] & 0x00ff0000)
+ kvm_s390_set_psw_cc(vcpu, 3);
+ return ret;
+ }
+ /*
+ * A vfio_driver must register a hook.
+ * No hook means no driver to enable the SIE CRYCB and no queues.
+ * We send this response to the guest.
+ */
+ status.response_code = 0x01;
+ memcpy(&vcpu->run->s.regs.gprs[1], &status, sizeof(status));
+ kvm_s390_set_psw_cc(vcpu, 3);
+ return 0;
+}
+
static int handle_stfl(struct kvm_vcpu *vcpu)
{
int rc;
@@ -878,6 +962,8 @@
return handle_sthyi(vcpu);
case 0x7d:
return handle_stsi(vcpu);
+ case 0xaf:
+ return handle_pqap(vcpu);
case 0xb1:
return handle_stfl(vcpu);
case 0xb2:
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index a2b28cd..076090f 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -135,14 +135,148 @@
atomic_set(&scb_s->cpuflags, newflags);
return 0;
}
+/* Copy to APCB FORMAT1 from APCB FORMAT0 */
+static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s,
+ unsigned long apcb_o, struct kvm_s390_apcb1 *apcb_h)
+{
+ struct kvm_s390_apcb0 tmp;
-/*
+ if (read_guest_real(vcpu, apcb_o, &tmp, sizeof(struct kvm_s390_apcb0)))
+ return -EFAULT;
+
+ apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0];
+ apcb_s->aqm[0] = apcb_h->aqm[0] & tmp.aqm[0] & 0xffff000000000000UL;
+ apcb_s->adm[0] = apcb_h->adm[0] & tmp.adm[0] & 0xffff000000000000UL;
+
+ return 0;
+
+}
+
+/**
+ * setup_apcb00 - Copy to APCB FORMAT0 from APCB FORMAT0
+ * @vcpu: pointer to the virtual CPU
+ * @apcb_s: pointer to start of apcb in the shadow crycb
+ * @apcb_o: pointer to start of original apcb in the guest2
+ * @apcb_h: pointer to start of apcb in the guest1
+ *
+ * Returns 0 and -EFAULT on error reading guest apcb
+ */
+static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
+ unsigned long apcb_o, unsigned long *apcb_h)
+{
+ if (read_guest_real(vcpu, apcb_o, apcb_s,
+ sizeof(struct kvm_s390_apcb0)))
+ return -EFAULT;
+
+ bitmap_and(apcb_s, apcb_s, apcb_h, sizeof(struct kvm_s390_apcb0));
+
+ return 0;
+}
+
+/**
+ * setup_apcb11 - Copy the FORMAT1 APCB from the guest to the shadow CRYCB
+ * @vcpu: pointer to the virtual CPU
+ * @apcb_s: pointer to start of apcb in the shadow crycb
+ * @apcb_o: pointer to start of original guest apcb
+ * @apcb_h: pointer to start of apcb in the host
+ *
+ * Returns 0 and -EFAULT on error reading guest apcb
+ */
+static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
+ unsigned long apcb_o,
+ unsigned long *apcb_h)
+{
+ if (read_guest_real(vcpu, apcb_o, apcb_s,
+ sizeof(struct kvm_s390_apcb1)))
+ return -EFAULT;
+
+ bitmap_and(apcb_s, apcb_s, apcb_h, sizeof(struct kvm_s390_apcb1));
+
+ return 0;
+}
+
+/**
+ * setup_apcb - Create a shadow copy of the apcb.
+ * @vcpu: pointer to the virtual CPU
+ * @crycb_s: pointer to shadow crycb
+ * @crycb_o: pointer to original guest crycb
+ * @crycb_h: pointer to the host crycb
+ * @fmt_o: format of the original guest crycb.
+ * @fmt_h: format of the host crycb.
+ *
+ * Checks the compatibility between the guest and host crycb and calls the
+ * appropriate copy function.
+ *
+ * Return 0 or an error number if the guest and host crycb are incompatible.
+ */
+static int setup_apcb(struct kvm_vcpu *vcpu, struct kvm_s390_crypto_cb *crycb_s,
+ const u32 crycb_o,
+ struct kvm_s390_crypto_cb *crycb_h,
+ int fmt_o, int fmt_h)
+{
+ struct kvm_s390_crypto_cb *crycb;
+
+ crycb = (struct kvm_s390_crypto_cb *) (unsigned long)crycb_o;
+
+ switch (fmt_o) {
+ case CRYCB_FORMAT2:
+ if ((crycb_o & PAGE_MASK) != ((crycb_o + 256) & PAGE_MASK))
+ return -EACCES;
+ if (fmt_h != CRYCB_FORMAT2)
+ return -EINVAL;
+ return setup_apcb11(vcpu, (unsigned long *)&crycb_s->apcb1,
+ (unsigned long) &crycb->apcb1,
+ (unsigned long *)&crycb_h->apcb1);
+ case CRYCB_FORMAT1:
+ switch (fmt_h) {
+ case CRYCB_FORMAT2:
+ return setup_apcb10(vcpu, &crycb_s->apcb1,
+ (unsigned long) &crycb->apcb0,
+ &crycb_h->apcb1);
+ case CRYCB_FORMAT1:
+ return setup_apcb00(vcpu,
+ (unsigned long *) &crycb_s->apcb0,
+ (unsigned long) &crycb->apcb0,
+ (unsigned long *) &crycb_h->apcb0);
+ }
+ break;
+ case CRYCB_FORMAT0:
+ if ((crycb_o & PAGE_MASK) != ((crycb_o + 32) & PAGE_MASK))
+ return -EACCES;
+
+ switch (fmt_h) {
+ case CRYCB_FORMAT2:
+ return setup_apcb10(vcpu, &crycb_s->apcb1,
+ (unsigned long) &crycb->apcb0,
+ &crycb_h->apcb1);
+ case CRYCB_FORMAT1:
+ case CRYCB_FORMAT0:
+ return setup_apcb00(vcpu,
+ (unsigned long *) &crycb_s->apcb0,
+ (unsigned long) &crycb->apcb0,
+ (unsigned long *) &crycb_h->apcb0);
+ }
+ }
+ return -EINVAL;
+}
+
+/**
+ * shadow_crycb - Create a shadow copy of the crycb block
+ * @vcpu: a pointer to the virtual CPU
+ * @vsie_page: a pointer to internal date used for the vSIE
+ *
* Create a shadow copy of the crycb block and setup key wrapping, if
* requested for guest 3 and enabled for guest 2.
*
- * We only accept format-1 (no AP in g2), but convert it into format-2
+ * We accept format-1 or format-2, but we convert format-1 into format-2
+ * in the shadow CRYCB.
+ * Using format-2 enables the firmware to choose the right format when
+ * scheduling the SIE.
* There is nothing to do for format-0.
*
+ * This function centralize the issuing of set_validity_icpt() for all
+ * the subfunctions working on the crycb.
+ *
* Returns: - 0 if shadowed or nothing to do
* - > 0 if control has to be given to guest 2
*/
@@ -154,23 +288,44 @@
const u32 crycb_addr = crycbd_o & 0x7ffffff8U;
unsigned long *b1, *b2;
u8 ecb3_flags;
+ u32 ecd_flags;
+ int apie_h;
+ int apie_s;
+ int key_msk = test_kvm_facility(vcpu->kvm, 76);
+ int fmt_o = crycbd_o & CRYCB_FORMAT_MASK;
+ int fmt_h = vcpu->arch.sie_block->crycbd & CRYCB_FORMAT_MASK;
+ int ret = 0;
scb_s->crycbd = 0;
- if (!(crycbd_o & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
+
+ apie_h = vcpu->arch.sie_block->eca & ECA_APIE;
+ apie_s = apie_h & scb_o->eca;
+ if (!apie_s && (!key_msk || (fmt_o == CRYCB_FORMAT0)))
return 0;
- /* format-1 is supported with message-security-assist extension 3 */
- if (!test_kvm_facility(vcpu->kvm, 76))
- return 0;
+
+ if (!crycb_addr)
+ return set_validity_icpt(scb_s, 0x0039U);
+
+ if (fmt_o == CRYCB_FORMAT1)
+ if ((crycb_addr & PAGE_MASK) !=
+ ((crycb_addr + 128) & PAGE_MASK))
+ return set_validity_icpt(scb_s, 0x003CU);
+
+ if (apie_s) {
+ ret = setup_apcb(vcpu, &vsie_page->crycb, crycb_addr,
+ vcpu->kvm->arch.crypto.crycb,
+ fmt_o, fmt_h);
+ if (ret)
+ goto end;
+ scb_s->eca |= scb_o->eca & ECA_APIE;
+ }
+
/* we may only allow it if enabled for guest 2 */
ecb3_flags = scb_o->ecb3 & vcpu->arch.sie_block->ecb3 &
(ECB3_AES | ECB3_DEA);
- if (!ecb3_flags)
- return 0;
-
- if ((crycb_addr & PAGE_MASK) != ((crycb_addr + 128) & PAGE_MASK))
- return set_validity_icpt(scb_s, 0x003CU);
- else if (!crycb_addr)
- return set_validity_icpt(scb_s, 0x0039U);
+ ecd_flags = scb_o->ecd & vcpu->arch.sie_block->ecd & ECD_ECC;
+ if (!ecb3_flags && !ecd_flags)
+ goto end;
/* copy only the wrapping keys */
if (read_guest_real(vcpu, crycb_addr + 72,
@@ -178,8 +333,7 @@
return set_validity_icpt(scb_s, 0x0035U);
scb_s->ecb3 |= ecb3_flags;
- scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT1 |
- CRYCB_FORMAT2;
+ scb_s->ecd |= ecd_flags;
/* xor both blocks in one run */
b1 = (unsigned long *) vsie_page->crycb.dea_wrapping_key_mask;
@@ -187,6 +341,16 @@
vcpu->kvm->arch.crypto.crycb->dea_wrapping_key_mask;
/* as 56%8 == 0, bitmap_xor won't overwrite any data */
bitmap_xor(b1, b1, b2, BITS_PER_BYTE * 56);
+end:
+ switch (ret) {
+ case -EINVAL:
+ return set_validity_icpt(scb_s, 0x0022U);
+ case -EFAULT:
+ return set_validity_icpt(scb_s, 0x0035U);
+ case -EACCES:
+ return set_validity_icpt(scb_s, 0x003CU);
+ }
+ scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT2;
return 0;
}
@@ -383,6 +547,8 @@
if (test_kvm_facility(vcpu->kvm, 156))
scb_s->ecd |= scb_o->ecd & ECD_ETOKENF;
+ scb_s->hpid = HPID_VSIE;
+
prepare_ibc(vcpu, vsie_page);
rc = shadow_crycb(vcpu, vsie_page);
out:
@@ -830,7 +996,7 @@
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
int guest_bp_isolation;
- int rc;
+ int rc = 0;
handle_last_fault(vcpu, vsie_page);
@@ -858,7 +1024,18 @@
guest_enter_irqoff();
local_irq_enable();
- rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
+ /*
+ * Simulate a SIE entry of the VCPU (see sie64a), so VCPU blocking
+ * and VCPU requests also hinder the vSIE from running and lead
+ * to an immediate exit. kvm_s390_vsie_kick() has to be used to
+ * also kick the vSIE.
+ */
+ vcpu->arch.sie_block->prog0c |= PROG_IN_SIE;
+ barrier();
+ if (!kvm_s390_vcpu_sie_inhibited(vcpu))
+ rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
+ barrier();
+ vcpu->arch.sie_block->prog0c &= ~PROG_IN_SIE;
local_irq_disable();
guest_exit_irqoff();
@@ -1005,7 +1182,8 @@
if (rc == -EAGAIN)
rc = 0;
if (rc || scb_s->icptcode || signal_pending(current) ||
- kvm_s390_vcpu_has_irq(vcpu, 0))
+ kvm_s390_vcpu_has_irq(vcpu, 0) ||
+ kvm_s390_vcpu_sie_inhibited(vcpu))
break;
}
@@ -1122,7 +1300,8 @@
if (unlikely(scb_addr & 0x1ffUL))
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0))
+ if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0) ||
+ kvm_s390_vcpu_sie_inhibited(vcpu))
return 0;
vsie_page = get_vsie_page(vcpu->kvm, scb_addr);
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 57ab401..d7c218e 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -3,11 +3,11 @@
# Makefile for s390-specific library files..
#
-lib-y += delay.o string.o uaccess.o find.o
+lib-y += delay.o string.o uaccess.o find.o spinlock.o
obj-y += mem.o xor.o
-lib-$(CONFIG_SMP) += spinlock.o
lib-$(CONFIG_KPROBES) += probes.o
lib-$(CONFIG_UPROBES) += probes.o
-chkbss := mem.o
-include $(srctree)/arch/s390/scripts/Makefile.chkbss
+# Instrumenting memory accesses to __user data (in different address space)
+# produce false positives
+KASAN_SANITIZE_uaccess.o := n
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 40c4d59..dc0874f 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -14,7 +14,8 @@
/*
* void *memmove(void *dest, const void *src, size_t n)
*/
-ENTRY(memmove)
+WEAK(memmove)
+ENTRY(__memmove)
ltgr %r4,%r4
lgr %r1,%r2
jz .Lmemmove_exit
@@ -47,6 +48,7 @@
BR_EX %r14
.Lmemmove_mvc:
mvc 0(1,%r1),0(%r3)
+ENDPROC(__memmove)
EXPORT_SYMBOL(memmove)
/*
@@ -64,7 +66,8 @@
* return __builtin_memset(s, c, n);
* }
*/
-ENTRY(memset)
+WEAK(memset)
+ENTRY(__memset)
ltgr %r4,%r4
jz .Lmemset_exit
ltgr %r3,%r3
@@ -108,6 +111,7 @@
xc 0(1,%r1),0(%r1)
.Lmemset_mvc:
mvc 1(1,%r1),0(%r1)
+ENDPROC(__memset)
EXPORT_SYMBOL(memset)
/*
@@ -115,7 +119,8 @@
*
* void *memcpy(void *dest, const void *src, size_t n)
*/
-ENTRY(memcpy)
+WEAK(memcpy)
+ENTRY(__memcpy)
ltgr %r4,%r4
jz .Lmemcpy_exit
aghi %r4,-1
@@ -136,6 +141,7 @@
j .Lmemcpy_remainder
.Lmemcpy_mvc:
mvc 0(1,%r1),0(%r3)
+ENDPROC(__memcpy)
EXPORT_SYMBOL(memcpy)
/*
@@ -172,6 +178,7 @@
BR_EX %r14
.L__memset_mvc\bits:
mvc \bytes(1,%r1),0(%r1)
+ENDPROC(__memset\bits)
.endm
__MEMSET 16,2,sth
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index a10e11f..0e30e6e 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -43,11 +43,13 @@
*
* returns the length of @s
*/
+#ifdef __HAVE_ARCH_STRLEN
size_t strlen(const char *s)
{
return __strend(s) - s;
}
EXPORT_SYMBOL(strlen);
+#endif
/**
* strnlen - Find the length of a length-limited string
@@ -56,11 +58,13 @@
*
* returns the minimum of the length of @s and @n
*/
+#ifdef __HAVE_ARCH_STRNLEN
size_t strnlen(const char *s, size_t n)
{
return __strnend(s, n) - s;
}
EXPORT_SYMBOL(strnlen);
+#endif
/**
* strcpy - Copy a %NUL terminated string
@@ -69,6 +73,7 @@
*
* returns a pointer to @dest
*/
+#ifdef __HAVE_ARCH_STRCPY
char *strcpy(char *dest, const char *src)
{
register int r0 asm("0") = 0;
@@ -81,6 +86,7 @@
return ret;
}
EXPORT_SYMBOL(strcpy);
+#endif
/**
* strlcpy - Copy a %NUL terminated string into a sized buffer
@@ -93,6 +99,7 @@
* of course, the buffer size is zero). It does not pad
* out the result like strncpy() does.
*/
+#ifdef __HAVE_ARCH_STRLCPY
size_t strlcpy(char *dest, const char *src, size_t size)
{
size_t ret = __strend(src) - src;
@@ -105,6 +112,7 @@
return ret;
}
EXPORT_SYMBOL(strlcpy);
+#endif
/**
* strncpy - Copy a length-limited, %NUL-terminated string
@@ -115,6 +123,7 @@
* The result is not %NUL-terminated if the source exceeds
* @n bytes.
*/
+#ifdef __HAVE_ARCH_STRNCPY
char *strncpy(char *dest, const char *src, size_t n)
{
size_t len = __strnend(src, n) - src;
@@ -123,6 +132,7 @@
return dest;
}
EXPORT_SYMBOL(strncpy);
+#endif
/**
* strcat - Append one %NUL-terminated string to another
@@ -131,6 +141,7 @@
*
* returns a pointer to @dest
*/
+#ifdef __HAVE_ARCH_STRCAT
char *strcat(char *dest, const char *src)
{
register int r0 asm("0") = 0;
@@ -146,6 +157,7 @@
return ret;
}
EXPORT_SYMBOL(strcat);
+#endif
/**
* strlcat - Append a length-limited, %NUL-terminated string to another
@@ -153,6 +165,7 @@
* @src: The string to append to it
* @n: The size of the destination buffer.
*/
+#ifdef __HAVE_ARCH_STRLCAT
size_t strlcat(char *dest, const char *src, size_t n)
{
size_t dsize = __strend(dest) - dest;
@@ -170,6 +183,7 @@
return res;
}
EXPORT_SYMBOL(strlcat);
+#endif
/**
* strncat - Append a length-limited, %NUL-terminated string to another
@@ -182,6 +196,7 @@
* Note that in contrast to strncpy, strncat ensures the result is
* terminated.
*/
+#ifdef __HAVE_ARCH_STRNCAT
char *strncat(char *dest, const char *src, size_t n)
{
size_t len = __strnend(src, n) - src;
@@ -192,6 +207,7 @@
return dest;
}
EXPORT_SYMBOL(strncat);
+#endif
/**
* strcmp - Compare two strings
@@ -202,6 +218,7 @@
* < 0 if @s1 is less than @s2
* > 0 if @s1 is greater than @s2
*/
+#ifdef __HAVE_ARCH_STRCMP
int strcmp(const char *s1, const char *s2)
{
register int r0 asm("0") = 0;
@@ -219,12 +236,14 @@
return ret;
}
EXPORT_SYMBOL(strcmp);
+#endif
/**
* strrchr - Find the last occurrence of a character in a string
* @s: The string to be searched
* @c: The character to search for
*/
+#ifdef __HAVE_ARCH_STRRCHR
char *strrchr(const char *s, int c)
{
size_t len = __strend(s) - s;
@@ -237,6 +256,7 @@
return NULL;
}
EXPORT_SYMBOL(strrchr);
+#endif
static inline int clcle(const char *s1, unsigned long l1,
const char *s2, unsigned long l2)
@@ -261,6 +281,7 @@
* @s1: The string to be searched
* @s2: The string to search for
*/
+#ifdef __HAVE_ARCH_STRSTR
char *strstr(const char *s1, const char *s2)
{
int l1, l2;
@@ -280,6 +301,7 @@
return NULL;
}
EXPORT_SYMBOL(strstr);
+#endif
/**
* memchr - Find a character in an area of memory.
@@ -290,6 +312,7 @@
* returns the address of the first occurrence of @c, or %NULL
* if @c is not found
*/
+#ifdef __HAVE_ARCH_MEMCHR
void *memchr(const void *s, int c, size_t n)
{
register int r0 asm("0") = (char) c;
@@ -304,6 +327,7 @@
return (void *) ret;
}
EXPORT_SYMBOL(memchr);
+#endif
/**
* memcmp - Compare two areas of memory
@@ -311,6 +335,7 @@
* @s2: Another area of memory
* @count: The size of the area.
*/
+#ifdef __HAVE_ARCH_MEMCMP
int memcmp(const void *s1, const void *s2, size_t n)
{
int ret;
@@ -321,6 +346,7 @@
return ret;
}
EXPORT_SYMBOL(memcmp);
+#endif
/**
* memscan - Find a character in an area of memory.
@@ -331,6 +357,7 @@
* returns the address of the first occurrence of @c, or 1 byte past
* the area if @c is not found
*/
+#ifdef __HAVE_ARCH_MEMSCAN
void *memscan(void *s, int c, size_t n)
{
register int r0 asm("0") = (char) c;
@@ -342,3 +369,4 @@
return (void *) ret;
}
EXPORT_SYMBOL(memscan);
+#endif
diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
index 9658059..29d9470 100644
--- a/arch/s390/lib/xor.c
+++ b/arch/s390/lib/xor.c
@@ -9,6 +9,7 @@
#include <linux/types.h>
#include <linux/export.h>
#include <linux/raid/xor.h>
+#include <asm/xor.h>
static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index 33fe418..3175413 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -4,10 +4,12 @@
#
obj-y := init.o fault.o extmem.o mmap.o vmem.o maccess.o
-obj-y += page-states.o gup.o pageattr.o mem_detect.o
-obj-y += pgtable.o pgalloc.o
+obj-y += page-states.o pageattr.o pgtable.o pgalloc.o
obj-$(CONFIG_CMM) += cmm.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_S390_PTDUMP) += dump_pagetables.o
obj-$(CONFIG_PGSTE) += gmap.o
+
+KASAN_SANITIZE_kasan_init.o := n
+obj-$(CONFIG_KASAN) += kasan_init.o
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 510a182..a51c892 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -298,16 +298,16 @@
}
if (write) {
- len = *lenp;
- if (copy_from_user(buf, buffer,
- len > sizeof(buf) ? sizeof(buf) : len))
+ len = min(*lenp, sizeof(buf));
+ if (copy_from_user(buf, buffer, len))
return -EFAULT;
- buf[sizeof(buf) - 1] = '\0';
+ buf[len - 1] = '\0';
cmm_skip_blanks(buf, &p);
nr = simple_strtoul(p, &p, 0);
cmm_skip_blanks(p, &p);
seconds = simple_strtoul(p, &p, 0);
cmm_set_timeout(nr, seconds);
+ *ppos += *lenp;
} else {
len = sprintf(buf, "%ld %ld\n",
cmm_timeout_pages, cmm_timeout_seconds);
@@ -315,9 +315,9 @@
len = *lenp;
if (copy_to_user(buffer, buf, len))
return -EFAULT;
+ *lenp = len;
+ *ppos += len;
}
- *lenp = len;
- *ppos += len;
return 0;
}
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 7cdea2e..5d67b81 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -3,6 +3,8 @@
#include <linux/debugfs.h>
#include <linux/sched.h>
#include <linux/mm.h>
+#include <linux/kasan.h>
+#include <asm/kasan.h>
#include <asm/sections.h>
#include <asm/pgtable.h>
@@ -17,18 +19,26 @@
IDENTITY_NR = 0,
KERNEL_START_NR,
KERNEL_END_NR,
+#ifdef CONFIG_KASAN
+ KASAN_SHADOW_START_NR,
+ KASAN_SHADOW_END_NR,
+#endif
VMEMMAP_NR,
VMALLOC_NR,
MODULES_NR,
};
static struct addr_marker address_markers[] = {
- [IDENTITY_NR] = {0, "Identity Mapping"},
- [KERNEL_START_NR] = {(unsigned long)_stext, "Kernel Image Start"},
- [KERNEL_END_NR] = {(unsigned long)_end, "Kernel Image End"},
- [VMEMMAP_NR] = {0, "vmemmap Area"},
- [VMALLOC_NR] = {0, "vmalloc Area"},
- [MODULES_NR] = {0, "Modules Area"},
+ [IDENTITY_NR] = {0, "Identity Mapping"},
+ [KERNEL_START_NR] = {(unsigned long)_stext, "Kernel Image Start"},
+ [KERNEL_END_NR] = {(unsigned long)_end, "Kernel Image End"},
+#ifdef CONFIG_KASAN
+ [KASAN_SHADOW_START_NR] = {KASAN_SHADOW_START, "Kasan Shadow Start"},
+ [KASAN_SHADOW_END_NR] = {KASAN_SHADOW_END, "Kasan Shadow End"},
+#endif
+ [VMEMMAP_NR] = {0, "vmemmap Area"},
+ [VMALLOC_NR] = {0, "vmalloc Area"},
+ [MODULES_NR] = {0, "Modules Area"},
{ -1, NULL }
};
@@ -80,7 +90,7 @@
} else if (prot != cur || level != st->level ||
st->current_address >= st->marker[1].start_address) {
/* Print the actual finished series */
- seq_printf(m, "0x%0*lx-0x%0*lx",
+ seq_printf(m, "0x%0*lx-0x%0*lx ",
width, st->start_address,
width, st->current_address);
delta = (st->current_address - st->start_address) >> 10;
@@ -90,7 +100,7 @@
}
seq_printf(m, "%9lu%c ", delta, *unit);
print_prot(m, st->current_prot, st->level);
- if (st->current_address >= st->marker[1].start_address) {
+ while (st->current_address >= st->marker[1].start_address) {
st->marker++;
seq_printf(m, "---[ %s ]---\n", st->marker->name);
}
@@ -100,6 +110,18 @@
}
}
+#ifdef CONFIG_KASAN
+static void note_kasan_early_shadow_page(struct seq_file *m,
+ struct pg_state *st)
+{
+ unsigned int prot;
+
+ prot = pte_val(*kasan_early_shadow_pte) &
+ (_PAGE_PROTECT | _PAGE_INVALID | _PAGE_NOEXEC);
+ note_page(m, st, prot, 4);
+}
+#endif
+
/*
* The actual page table walker functions. In order to keep the
* implementation of print_prot() short, we only check and pass
@@ -132,9 +154,16 @@
pmd_t *pmd;
int i;
- for (i = 0; i < PTRS_PER_PMD && addr < max_addr; i++) {
+#ifdef CONFIG_KASAN
+ if ((pud_val(*pud) & PAGE_MASK) == __pa(kasan_early_shadow_pmd)) {
+ note_kasan_early_shadow_page(m, st);
+ return;
+ }
+#endif
+
+ pmd = pmd_offset(pud, addr);
+ for (i = 0; i < PTRS_PER_PMD && addr < max_addr; i++, pmd++) {
st->current_address = addr;
- pmd = pmd_offset(pud, addr);
if (!pmd_none(*pmd)) {
if (pmd_large(*pmd)) {
prot = pmd_val(*pmd) &
@@ -156,9 +185,16 @@
pud_t *pud;
int i;
- for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++) {
+#ifdef CONFIG_KASAN
+ if ((p4d_val(*p4d) & PAGE_MASK) == __pa(kasan_early_shadow_pud)) {
+ note_kasan_early_shadow_page(m, st);
+ return;
+ }
+#endif
+
+ pud = pud_offset(p4d, addr);
+ for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++, pud++) {
st->current_address = addr;
- pud = pud_offset(p4d, addr);
if (!pud_none(*pud))
if (pud_large(*pud)) {
prot = pud_val(*pud) &
@@ -179,9 +215,16 @@
p4d_t *p4d;
int i;
- for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++) {
+#ifdef CONFIG_KASAN
+ if ((pgd_val(*pgd) & PAGE_MASK) == __pa(kasan_early_shadow_p4d)) {
+ note_kasan_early_shadow_page(m, st);
+ return;
+ }
+#endif
+
+ p4d = p4d_offset(pgd, addr);
+ for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++, p4d++) {
st->current_address = addr;
- p4d = p4d_offset(pgd, addr);
if (!p4d_none(*p4d))
walk_pud_level(m, st, p4d, addr);
else
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 84111a4..fd0dae9 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -16,9 +16,10 @@
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/export.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/ctype.h>
#include <linux/ioport.h>
+#include <linux/refcount.h>
#include <asm/diag.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -28,12 +29,7 @@
#include <asm/cpcmd.h>
#include <asm/setup.h>
-#define DCSS_LOADSHR 0x00
-#define DCSS_LOADNSR 0x04
#define DCSS_PURGESEG 0x08
-#define DCSS_FINDSEG 0x0c
-#define DCSS_LOADNOLY 0x10
-#define DCSS_SEGEXT 0x18
#define DCSS_LOADSHRX 0x20
#define DCSS_LOADNSRX 0x24
#define DCSS_FINDSEGX 0x2c
@@ -53,20 +49,6 @@
struct qrange range[6];
};
-struct qrange_old {
- unsigned int start; /* last byte type */
- unsigned int end; /* last byte reserved */
-};
-
-/* output area format for the Diag x'64' old subcode x'18' */
-struct qout64_old {
- int segstart;
- int segend;
- int segcnt;
- int segrcnt;
- struct qrange_old range[6];
-};
-
struct qin64 {
char qopcode;
char rsrv1[3];
@@ -83,7 +65,7 @@
char res_name[16];
unsigned long start_addr;
unsigned long end;
- atomic_t ref_count;
+ refcount_t ref_count;
int do_nonshared;
unsigned int vm_segtype;
struct qrange range[6];
@@ -95,52 +77,10 @@
static LIST_HEAD(dcss_list);
static char *segtype_string[] = { "SW", "EW", "SR", "ER", "SN", "EN", "SC",
"EW/EN-MIXED" };
-static int loadshr_scode, loadnsr_scode;
-static int segext_scode, purgeseg_scode;
-static int scode_set;
-
-/* set correct Diag x'64' subcodes. */
-static int
-dcss_set_subcodes(void)
-{
- char *name = kmalloc(8, GFP_KERNEL | GFP_DMA);
- unsigned long rx, ry;
- int rc;
-
- if (name == NULL)
- return -ENOMEM;
-
- rx = (unsigned long) name;
- ry = DCSS_FINDSEGX;
-
- strcpy(name, "dummy");
- diag_stat_inc(DIAG_STAT_X064);
- asm volatile(
- " diag %0,%1,0x64\n"
- "0: ipm %2\n"
- " srl %2,28\n"
- " j 2f\n"
- "1: la %2,3\n"
- "2:\n"
- EX_TABLE(0b, 1b)
- : "+d" (rx), "+d" (ry), "=d" (rc) : : "cc", "memory");
-
- kfree(name);
- /* Diag x'64' new subcodes are supported, set to new subcodes */
- if (rc != 3) {
- loadshr_scode = DCSS_LOADSHRX;
- loadnsr_scode = DCSS_LOADNSRX;
- purgeseg_scode = DCSS_PURGESEG;
- segext_scode = DCSS_SEGEXTX;
- return 0;
- }
- /* Diag x'64' new subcodes are not supported, set to old subcodes */
- loadshr_scode = DCSS_LOADNOLY;
- loadnsr_scode = DCSS_LOADNSR;
- purgeseg_scode = DCSS_PURGESEG;
- segext_scode = DCSS_SEGEXT;
- return 0;
-}
+static int loadshr_scode = DCSS_LOADSHRX;
+static int loadnsr_scode = DCSS_LOADNSRX;
+static int purgeseg_scode = DCSS_PURGESEG;
+static int segext_scode = DCSS_SEGEXTX;
/*
* Create the 8 bytes, ebcdic VM segment name from
@@ -196,32 +136,15 @@
unsigned long rx, ry;
int rc;
- if (scode_set == 0) {
- rc = dcss_set_subcodes();
- if (rc < 0)
- return rc;
- scode_set = 1;
- }
rx = (unsigned long) parameter;
ry = (unsigned long) *func;
- /* 64-bit Diag x'64' new subcode, keep in 64-bit addressing mode */
diag_stat_inc(DIAG_STAT_X064);
- if (*func > DCSS_SEGEXT)
- asm volatile(
- " diag %0,%1,0x64\n"
- " ipm %2\n"
- " srl %2,28\n"
- : "+d" (rx), "+d" (ry), "=d" (rc) : : "cc");
- /* 31-bit Diag x'64' old subcode, switch to 31-bit addressing mode */
- else
- asm volatile(
- " sam31\n"
- " diag %0,%1,0x64\n"
- " sam64\n"
- " ipm %2\n"
- " srl %2,28\n"
- : "+d" (rx), "+d" (ry), "=d" (rc) : : "cc");
+ asm volatile(
+ " diag %0,%1,0x64\n"
+ " ipm %2\n"
+ " srl %2,28\n"
+ : "+d" (rx), "+d" (ry), "=d" (rc) : : "cc");
*ret1 = rx;
*ret2 = ry;
return rc;
@@ -271,31 +194,6 @@
goto out_free;
}
- /* Only old format of output area of Diagnose x'64' is supported,
- copy data for the new format. */
- if (segext_scode == DCSS_SEGEXT) {
- struct qout64_old *qout_old;
- qout_old = kzalloc(sizeof(*qout_old), GFP_KERNEL | GFP_DMA);
- if (qout_old == NULL) {
- rc = -ENOMEM;
- goto out_free;
- }
- memcpy(qout_old, qout, sizeof(struct qout64_old));
- qout->segstart = (unsigned long) qout_old->segstart;
- qout->segend = (unsigned long) qout_old->segend;
- qout->segcnt = qout_old->segcnt;
- qout->segrcnt = qout_old->segrcnt;
-
- if (qout->segcnt > 6)
- qout->segrcnt = 6;
- for (i = 0; i < qout->segrcnt; i++) {
- qout->range[i].start =
- (unsigned long) qout_old->range[i].start;
- qout->range[i].end =
- (unsigned long) qout_old->range[i].end;
- }
- kfree(qout_old);
- }
if (qout->segcnt > 6) {
rc = -EOPNOTSUPP;
goto out_free;
@@ -410,11 +308,9 @@
if (rc < 0)
goto out_free;
- if (loadshr_scode == DCSS_LOADSHRX) {
- if (segment_overlaps_others(seg)) {
- rc = -EBUSY;
- goto out_free;
- }
+ if (segment_overlaps_others(seg)) {
+ rc = -EBUSY;
+ goto out_free;
}
rc = vmem_add_mapping(seg->start_addr, seg->end - seg->start_addr + 1);
@@ -467,16 +363,16 @@
seg->start_addr = start_addr;
seg->end = end_addr;
seg->do_nonshared = do_nonshared;
- atomic_set(&seg->ref_count, 1);
+ refcount_set(&seg->ref_count, 1);
list_add(&seg->list, &dcss_list);
*addr = seg->start_addr;
*end = seg->end;
if (do_nonshared)
- pr_info("DCSS %s of range %p to %p and type %s loaded as "
+ pr_info("DCSS %s of range %px to %px and type %s loaded as "
"exclusive-writable\n", name, (void*) seg->start_addr,
(void*) seg->end, segtype_string[seg->vm_segtype]);
else {
- pr_info("DCSS %s of range %p to %p and type %s loaded in "
+ pr_info("DCSS %s of range %px to %px and type %s loaded in "
"shared access mode\n", name, (void*) seg->start_addr,
(void*) seg->end, segtype_string[seg->vm_segtype]);
}
@@ -527,7 +423,7 @@
rc = __segment_load (name, do_nonshared, addr, end);
else {
if (do_nonshared == seg->do_nonshared) {
- atomic_inc(&seg->ref_count);
+ refcount_inc(&seg->ref_count);
*addr = seg->start_addr;
*end = seg->end;
rc = seg->vm_segtype;
@@ -573,7 +469,7 @@
rc = 0;
goto out_unlock;
}
- if (atomic_read (&seg->ref_count) != 1) {
+ if (refcount_read(&seg->ref_count) != 1) {
pr_warn("DCSS %s is in use and cannot be reloaded\n", name);
rc = -EAGAIN;
goto out_unlock;
@@ -649,7 +545,7 @@
pr_err("Unloading unknown DCSS %s failed\n", name);
goto out_unlock;
}
- if (atomic_dec_return(&seg->ref_count) != 0)
+ if (!refcount_dec_and_test(&seg->ref_count))
goto out_unlock;
release_resource(seg->res);
kfree(seg->res);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 72af23b..7b0bb47 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -67,49 +67,10 @@
}
early_initcall(fault_init);
-static inline int notify_page_fault(struct pt_regs *regs)
-{
- int ret = 0;
-
- /* kprobe_running() needs smp_processor_id() */
- if (kprobes_built_in() && !user_mode(regs)) {
- preempt_disable();
- if (kprobe_running() && kprobe_fault_handler(regs, 14))
- ret = 1;
- preempt_enable();
- }
- return ret;
-}
-
-
-/*
- * Unlock any spinlocks which will prevent us from getting the
- * message out.
- */
-void bust_spinlocks(int yes)
-{
- if (yes) {
- oops_in_progress = 1;
- } else {
- int loglevel_save = console_loglevel;
- console_unblank();
- oops_in_progress = 0;
- /*
- * OK, the message is on the console. Now we call printk()
- * without oops_in_progress set so that printk will give klogd
- * a poke. Hold onto your hats...
- */
- console_loglevel = 15;
- printk(" ");
- console_loglevel = loglevel_save;
- }
-}
-
/*
* Find out which address space caused the exception.
- * Access register mode is impossible, ignore space == 3.
*/
-static inline enum fault_type get_fault_type(struct pt_regs *regs)
+static enum fault_type get_fault_type(struct pt_regs *regs)
{
unsigned long trans_exc_code;
@@ -132,6 +93,10 @@
}
return VDSO_FAULT;
}
+ if (trans_exc_code == 1) {
+ /* access register mode, not used in the kernel */
+ return USER_FAULT;
+ }
/* home space exception -> access via kernel ASCE */
return KERNEL_FAULT;
}
@@ -235,6 +200,8 @@
asce = S390_lowcore.kernel_asce;
pr_cont("kernel ");
break;
+ default:
+ unreachable();
}
pr_cont("ASCE.\n");
dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK);
@@ -267,8 +234,19 @@
{
report_user_fault(regs, SIGSEGV, 1);
force_sig_fault(SIGSEGV, si_code,
- (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK),
- current);
+ (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK));
+}
+
+const struct exception_table_entry *s390_search_extables(unsigned long addr)
+{
+ const struct exception_table_entry *fixup;
+
+ fixup = search_extable(__start_dma_ex_table,
+ __stop_dma_ex_table - __start_dma_ex_table,
+ addr);
+ if (!fixup)
+ fixup = search_exception_tables(addr);
+ return fixup;
}
static noinline void do_no_context(struct pt_regs *regs)
@@ -276,7 +254,7 @@
const struct exception_table_entry *fixup;
/* Are we prepared to handle this kernel fault? */
- fixup = search_exception_tables(regs->psw.addr);
+ fixup = s390_search_extables(regs->psw.addr);
if (fixup) {
regs->psw.addr = extable_fixup(fixup);
return;
@@ -317,8 +295,7 @@
* or user mode.
*/
force_sig_fault(SIGBUS, BUS_ADRERR,
- (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK),
- current);
+ (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK));
}
static noinline int signal_return(struct pt_regs *regs)
@@ -350,6 +327,7 @@
case VM_FAULT_BADACCESS:
if (access == VM_EXEC && signal_return(regs) == 0)
break;
+ /* fallthrough */
case VM_FAULT_BADMAP:
/* Bad memory access. Check if it is kernel or user space. */
if (user_mode(regs)) {
@@ -359,7 +337,9 @@
do_sigsegv(regs, si_code);
break;
}
+ /* fallthrough */
case VM_FAULT_BADCONTEXT:
+ /* fallthrough */
case VM_FAULT_PFAULT:
do_no_context(regs);
break;
@@ -421,7 +401,7 @@
*/
clear_pt_regs_flag(regs, PIF_PER_TRAP);
- if (notify_page_fault(regs))
+ if (kprobe_page_fault(regs, 14))
return 0;
mm = tsk->mm;
@@ -636,17 +616,19 @@
u64 reserved;
} __attribute__ ((packed, aligned(8)));
+static struct pfault_refbk pfault_init_refbk = {
+ .refdiagc = 0x258,
+ .reffcode = 0,
+ .refdwlen = 5,
+ .refversn = 2,
+ .refgaddr = __LC_LPP,
+ .refselmk = 1ULL << 48,
+ .refcmpmk = 1ULL << 48,
+ .reserved = __PF_RES_FIELD
+};
+
int pfault_init(void)
{
- struct pfault_refbk refbk = {
- .refdiagc = 0x258,
- .reffcode = 0,
- .refdwlen = 5,
- .refversn = 2,
- .refgaddr = __LC_LPP,
- .refselmk = 1ULL << 48,
- .refcmpmk = 1ULL << 48,
- .reserved = __PF_RES_FIELD };
int rc;
if (pfault_disable)
@@ -658,18 +640,20 @@
"1: la %0,8\n"
"2:\n"
EX_TABLE(0b,1b)
- : "=d" (rc) : "a" (&refbk), "m" (refbk) : "cc");
+ : "=d" (rc)
+ : "a" (&pfault_init_refbk), "m" (pfault_init_refbk) : "cc");
return rc;
}
+static struct pfault_refbk pfault_fini_refbk = {
+ .refdiagc = 0x258,
+ .reffcode = 1,
+ .refdwlen = 5,
+ .refversn = 2,
+};
+
void pfault_fini(void)
{
- struct pfault_refbk refbk = {
- .refdiagc = 0x258,
- .reffcode = 1,
- .refdwlen = 5,
- .refversn = 2,
- };
if (pfault_disable)
return;
@@ -678,7 +662,7 @@
" diag %0,0,0x258\n"
"0: nopr %%r7\n"
EX_TABLE(0b,0b)
- : : "a" (&refbk), "m" (refbk) : "cc");
+ : : "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk) : "cc");
}
static DEFINE_SPINLOCK(pfault_lock);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 911c7de..edcdca9 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -9,7 +9,7 @@
*/
#include <linux/kernel.h>
-#include <linux/mm.h>
+#include <linux/pagewalk.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/spinlock.h>
@@ -67,7 +67,7 @@
INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC);
spin_lock_init(&gmap->guest_table_lock);
spin_lock_init(&gmap->shadow_lock);
- atomic_set(&gmap->ref_count, 1);
+ refcount_set(&gmap->ref_count, 1);
page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
if (!page)
goto out_free;
@@ -214,7 +214,7 @@
*/
struct gmap *gmap_get(struct gmap *gmap)
{
- atomic_inc(&gmap->ref_count);
+ refcount_inc(&gmap->ref_count);
return gmap;
}
EXPORT_SYMBOL_GPL(gmap_get);
@@ -227,7 +227,7 @@
*/
void gmap_put(struct gmap *gmap)
{
- if (atomic_dec_return(&gmap->ref_count) == 0)
+ if (refcount_dec_and_test(&gmap->ref_count))
gmap_free(gmap);
}
EXPORT_SYMBOL_GPL(gmap_put);
@@ -907,10 +907,16 @@
pmd_t *pmdp;
BUG_ON(gmap_is_shadow(gmap));
- spin_lock(&gmap->guest_table_lock);
pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1);
+ if (!pmdp)
+ return NULL;
- if (!pmdp || pmd_none(*pmdp)) {
+ /* without huge pages, there is no need to take the table lock */
+ if (!gmap->mm->context.allow_gmap_hpage_1m)
+ return pmd_none(*pmdp) ? NULL : pmdp;
+
+ spin_lock(&gmap->guest_table_lock);
+ if (pmd_none(*pmdp)) {
spin_unlock(&gmap->guest_table_lock);
return NULL;
}
@@ -1588,7 +1594,7 @@
continue;
if (!sg->initialized)
return ERR_PTR(-EAGAIN);
- atomic_inc(&sg->ref_count);
+ refcount_inc(&sg->ref_count);
return sg;
}
return NULL;
@@ -1676,7 +1682,7 @@
}
}
}
- atomic_set(&new->ref_count, 2);
+ refcount_set(&new->ref_count, 2);
list_add(&new->list, &parent->children);
if (asce & _ASCE_REAL_SPACE) {
/* nothing to protect, return right away */
@@ -2418,8 +2424,8 @@
* This function is assumed to be called with the guest_table_lock
* held.
*/
-bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
- unsigned long gaddr)
+static bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
+ unsigned long gaddr)
{
if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
return false;
@@ -2515,13 +2521,9 @@
return 0;
}
-static inline void zap_zero_pages(struct mm_struct *mm)
-{
- struct mm_walk walk = { .pmd_entry = __zap_zero_pages };
-
- walk.mm = mm;
- walk_page_range(0, TASK_SIZE, &walk);
-}
+static const struct mm_walk_ops zap_zero_walk_ops = {
+ .pmd_entry = __zap_zero_pages,
+};
/*
* switch on pgstes for its userspace process (for kvm)
@@ -2540,7 +2542,7 @@
mm->context.has_pgste = 1;
/* split thp mappings and disable thp for future mappings */
thp_split_mm(mm);
- zap_zero_pages(mm);
+ walk_page_range(mm, 0, TASK_SIZE, &zap_zero_walk_ops, NULL);
up_write(&mm->mmap_sem);
return 0;
}
@@ -2583,12 +2585,13 @@
return 0;
}
+static const struct mm_walk_ops enable_skey_walk_ops = {
+ .hugetlb_entry = __s390_enable_skey_hugetlb,
+ .pte_entry = __s390_enable_skey_pte,
+};
+
int s390_enable_skey(void)
{
- struct mm_walk walk = {
- .hugetlb_entry = __s390_enable_skey_hugetlb,
- .pte_entry = __s390_enable_skey_pte,
- };
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
int rc = 0;
@@ -2608,8 +2611,7 @@
}
mm->def_flags &= ~VM_MERGEABLE;
- walk.mm = mm;
- walk_page_range(0, TASK_SIZE, &walk);
+ walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL);
out_up:
up_write(&mm->mmap_sem);
@@ -2627,13 +2629,14 @@
return 0;
}
+static const struct mm_walk_ops reset_cmma_walk_ops = {
+ .pte_entry = __s390_reset_cmma,
+};
+
void s390_reset_cmma(struct mm_struct *mm)
{
- struct mm_walk walk = { .pte_entry = __s390_reset_cmma };
-
down_write(&mm->mmap_sem);
- walk.mm = mm;
- walk_page_range(0, TASK_SIZE, &walk);
+ walk_page_range(mm, 0, TASK_SIZE, &reset_cmma_walk_ops, NULL);
up_write(&mm->mmap_sem);
}
EXPORT_SYMBOL_GPL(s390_reset_cmma);
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
deleted file mode 100644
index 2809d11..0000000
--- a/arch/s390/mm/gup.c
+++ /dev/null
@@ -1,300 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Lockless get_user_pages_fast for s390
- *
- * Copyright IBM Corp. 2010
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/hugetlb.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- struct page *head, *page;
- unsigned long mask;
- pte_t *ptep, pte;
-
- mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
-
- ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
- do {
- pte = *ptep;
- barrier();
- /* Similar to the PMD case, NUMA hinting must take slow path */
- if (pte_protnone(pte))
- return 0;
- if ((pte_val(pte) & mask) != 0)
- return 0;
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
- page = pte_page(pte);
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
- return 0;
- if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- put_page(head);
- return 0;
- }
- VM_BUG_ON_PAGE(compound_head(page) != head, page);
- pages[*nr] = page;
- (*nr)++;
-
- } while (ptep++, addr += PAGE_SIZE, addr != end);
-
- return 1;
-}
-
-static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- struct page *head, *page;
- unsigned long mask;
- int refs;
-
- mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
- if ((pmd_val(pmd) & mask) != 0)
- return 0;
- VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
-
- refs = 0;
- head = pmd_page(pmd);
- page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- if (!page_cache_add_speculative(head, refs)) {
- *nr -= refs;
- return 0;
- }
-
- if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
- return 0;
- }
-
- return 1;
-}
-
-
-static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pmd_t *pmdp, pmd;
-
- pmdp = (pmd_t *) pudp;
- if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
- pmdp = (pmd_t *) pud_deref(pud);
- pmdp += pmd_index(addr);
- do {
- pmd = *pmdp;
- barrier();
- next = pmd_addr_end(addr, end);
- if (pmd_none(pmd))
- return 0;
- if (unlikely(pmd_large(pmd))) {
- /*
- * NUMA hinting faults need to be handled in the GUP
- * slowpath for accounting purposes and so that they
- * can be serialised against THP migration.
- */
- if (pmd_protnone(pmd))
- return 0;
- if (!gup_huge_pmd(pmdp, pmd, addr, next,
- write, pages, nr))
- return 0;
- } else if (!gup_pte_range(pmdp, pmd, addr, next,
- write, pages, nr))
- return 0;
- } while (pmdp++, addr = next, addr != end);
-
- return 1;
-}
-
-static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- struct page *head, *page;
- unsigned long mask;
- int refs;
-
- mask = (write ? _REGION_ENTRY_PROTECT : 0) | _REGION_ENTRY_INVALID;
- if ((pud_val(pud) & mask) != 0)
- return 0;
- VM_BUG_ON(!pfn_valid(pud_pfn(pud)));
-
- refs = 0;
- head = pud_page(pud);
- page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
- do {
- VM_BUG_ON_PAGE(compound_head(page) != head, page);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- if (!page_cache_add_speculative(head, refs)) {
- *nr -= refs;
- return 0;
- }
-
- if (unlikely(pud_val(pud) != pud_val(*pudp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
- return 0;
- }
-
- return 1;
-}
-
-static inline int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pud_t *pudp, pud;
-
- pudp = (pud_t *) p4dp;
- if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
- pudp = (pud_t *) p4d_deref(p4d);
- pudp += pud_index(addr);
- do {
- pud = *pudp;
- barrier();
- next = pud_addr_end(addr, end);
- if (pud_none(pud))
- return 0;
- if (unlikely(pud_large(pud))) {
- if (!gup_huge_pud(pudp, pud, addr, next, write, pages,
- nr))
- return 0;
- } else if (!gup_pmd_range(pudp, pud, addr, next, write, pages,
- nr))
- return 0;
- } while (pudp++, addr = next, addr != end);
-
- return 1;
-}
-
-static inline int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- unsigned long next;
- p4d_t *p4dp, p4d;
-
- p4dp = (p4d_t *) pgdp;
- if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
- p4dp = (p4d_t *) pgd_deref(pgd);
- p4dp += p4d_index(addr);
- do {
- p4d = *p4dp;
- barrier();
- next = p4d_addr_end(addr, end);
- if (p4d_none(p4d))
- return 0;
- if (!gup_pud_range(p4dp, p4d, addr, next, write, pages, nr))
- return 0;
- } while (p4dp++, addr = next, addr != end);
-
- return 1;
-}
-
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next, flags;
- pgd_t *pgdp, pgd;
- int nr = 0;
-
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
- if ((end <= start) || (end > mm->context.asce_limit))
- return 0;
- /*
- * local_irq_save() doesn't prevent pagetable teardown, but does
- * prevent the pagetables from being freed on s390.
- *
- * So long as we atomically load page table pointers versus teardown,
- * we can follow the address down to the the page and take a ref on it.
- */
- local_irq_save(flags);
- pgdp = pgd_offset(mm, addr);
- do {
- pgd = *pgdp;
- barrier();
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- break;
- if (!gup_p4d_range(pgdp, pgd, addr, next, write, pages, &nr))
- break;
- } while (pgdp++, addr = next, addr != end);
- local_irq_restore(flags);
-
- return nr;
-}
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
-{
- int nr, ret;
-
- might_sleep();
- start &= PAGE_MASK;
- nr = __get_user_pages_fast(start, nr_pages, write, pages);
- if (nr == nr_pages)
- return nr;
-
- /* Try to get the remaining pages with get_user_pages */
- start += nr << PAGE_SHIFT;
- pages += nr;
- ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
- write ? FOLL_WRITE : 0);
- /* Have to be a bit careful with return values */
- if (nr > 0)
- ret = (ret < 0) ? nr : ret + nr;
- return ret;
-}
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 3fa3e53..a124f19 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -18,10 +18,11 @@
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
+#include <linux/swiotlb.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/pagemap.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/memory.h>
#include <linux/pfn.h>
#include <linux/poison.h>
@@ -29,7 +30,7 @@
#include <linux/export.h>
#include <linux/cma.h>
#include <linux/gfp.h>
-#include <linux/memblock.h>
+#include <linux/dma-direct.h>
#include <asm/processor.h>
#include <linux/uaccess.h>
#include <asm/pgtable.h>
@@ -42,6 +43,9 @@
#include <asm/ctl_reg.h>
#include <asm/sclp.h>
#include <asm/set_memory.h>
+#include <asm/kasan.h>
+#include <asm/dma-mapping.h>
+#include <asm/uv.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(.bss..swapper_pg_dir);
@@ -49,6 +53,8 @@
EXPORT_SYMBOL(empty_zero_page);
EXPORT_SYMBOL(zero_page_mask);
+bool initmem_freed;
+
static void __init setup_zero_pages(void)
{
unsigned int order;
@@ -59,7 +65,7 @@
order = 7;
/* Limit number of empty zero pages for small memory sizes */
- while (order > 2 && (totalram_pages >> 10) < (1UL << order))
+ while (order > 2 && (totalram_pages() >> 10) < (1UL << order))
order--;
empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
@@ -98,8 +104,9 @@
S390_lowcore.user_asce = S390_lowcore.kernel_asce;
crst_table_init((unsigned long *) init_mm.pgd, pgd_type);
vmem_map_init();
+ kasan_copy_shadow(init_mm.pgd);
- /* enable virtual mapping in kernel mode */
+ /* 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.kernel_asce, 13, 13);
@@ -107,6 +114,7 @@
psw_bits(psw).dat = 1;
psw_bits(psw).as = PSW_BITS_AS_HOME;
__load_psw_mask(psw.mask);
+ kasan_free_early_identity();
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
@@ -124,6 +132,47 @@
pr_info("Write protected read-only-after-init data: %luk\n", size >> 10);
}
+int set_memory_encrypted(unsigned long addr, int numpages)
+{
+ int i;
+
+ /* make specified pages unshared, (swiotlb, dma_free) */
+ for (i = 0; i < numpages; ++i) {
+ uv_remove_shared(addr);
+ addr += PAGE_SIZE;
+ }
+ return 0;
+}
+
+int set_memory_decrypted(unsigned long addr, int numpages)
+{
+ int i;
+ /* make specified pages shared (swiotlb, dma_alloca) */
+ for (i = 0; i < numpages; ++i) {
+ uv_set_shared(addr);
+ addr += PAGE_SIZE;
+ }
+ return 0;
+}
+
+/* are we a protected virtualization guest? */
+bool force_dma_unencrypted(struct device *dev)
+{
+ return is_prot_virt_guest();
+}
+
+/* protected virtualization */
+static void pv_init(void)
+{
+ if (!is_prot_virt_guest())
+ return;
+
+ /* make sure bounce buffers are shared */
+ swiotlb_init(1);
+ swiotlb_update_mem_attributes();
+ swiotlb_force = SWIOTLB_FORCE;
+}
+
void __init mem_init(void)
{
cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
@@ -132,11 +181,13 @@
set_max_mapnr(max_low_pfn);
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+ pv_init();
+
/* Setup guest page hinting */
cmma_init();
/* this will put all low memory onto the freelists */
- free_all_bootmem();
+ memblock_free_all();
setup_zero_pages(); /* Setup zeroed pages. */
cmma_init_nodat();
@@ -146,20 +197,13 @@
void free_initmem(void)
{
+ initmem_freed = true;
__set_memory((unsigned long)_sinittext,
(unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
SET_MEMORY_RW | SET_MEMORY_NX);
free_initmem_default(POISON_FREE_INITMEM);
}
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
- free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
- "initrd");
-}
-#endif
-
unsigned long memory_block_size_bytes(void)
{
/*
@@ -222,32 +266,35 @@
#endif /* CONFIG_CMA */
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
- bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+ struct mhp_restrictions *restrictions)
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long size_pages = PFN_DOWN(size);
int rc;
+ if (WARN_ON_ONCE(restrictions->altmap))
+ return -EINVAL;
+
rc = vmem_add_mapping(start, size);
if (rc)
return rc;
- rc = __add_pages(nid, start_pfn, size_pages, altmap, want_memblock);
+ rc = __add_pages(nid, start_pfn, size_pages, restrictions);
if (rc)
vmem_remove_mapping(start, size);
return rc;
}
-#ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(int nid, u64 start, u64 size,
+ struct vmem_altmap *altmap)
{
- /*
- * There is no hardware or firmware interface which could trigger a
- * hot memory remove on s390. So there is nothing that needs to be
- * implemented.
- */
- return -EBUSY;
+ unsigned long start_pfn = start >> PAGE_SHIFT;
+ unsigned long nr_pages = size >> PAGE_SHIFT;
+ struct zone *zone;
+
+ zone = page_zone(pfn_to_page(start_pfn));
+ __remove_pages(zone, start_pfn, nr_pages, altmap);
+ vmem_remove_mapping(start, size);
}
-#endif
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c
new file mode 100644
index 0000000..460f255
--- /dev/null
+++ b/arch/s390/mm/kasan_init.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kasan.h>
+#include <linux/sched/task.h>
+#include <linux/memblock.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/kasan.h>
+#include <asm/mem_detect.h>
+#include <asm/processor.h>
+#include <asm/sclp.h>
+#include <asm/facility.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+
+static unsigned long segment_pos __initdata;
+static unsigned long segment_low __initdata;
+static unsigned long pgalloc_pos __initdata;
+static unsigned long pgalloc_low __initdata;
+static unsigned long pgalloc_freeable __initdata;
+static bool has_edat __initdata;
+static bool has_nx __initdata;
+
+#define __sha(x) ((unsigned long)kasan_mem_to_shadow((void *)x))
+
+static pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+
+static void __init kasan_early_panic(const char *reason)
+{
+ sclp_early_printk("The Linux kernel failed to boot with the KernelAddressSanitizer:\n");
+ sclp_early_printk(reason);
+ disabled_wait();
+}
+
+static void * __init kasan_early_alloc_segment(void)
+{
+ segment_pos -= _SEGMENT_SIZE;
+
+ if (segment_pos < segment_low)
+ kasan_early_panic("out of memory during initialisation\n");
+
+ return (void *)segment_pos;
+}
+
+static void * __init kasan_early_alloc_pages(unsigned int order)
+{
+ pgalloc_pos -= (PAGE_SIZE << order);
+
+ if (pgalloc_pos < pgalloc_low)
+ kasan_early_panic("out of memory during initialisation\n");
+
+ return (void *)pgalloc_pos;
+}
+
+static void * __init kasan_early_crst_alloc(unsigned long val)
+{
+ unsigned long *table;
+
+ table = kasan_early_alloc_pages(CRST_ALLOC_ORDER);
+ if (table)
+ crst_table_init(table, val);
+ return table;
+}
+
+static pte_t * __init kasan_early_pte_alloc(void)
+{
+ static void *pte_leftover;
+ pte_t *pte;
+
+ BUILD_BUG_ON(_PAGE_TABLE_SIZE * 2 != PAGE_SIZE);
+
+ if (!pte_leftover) {
+ pte_leftover = kasan_early_alloc_pages(0);
+ pte = pte_leftover + _PAGE_TABLE_SIZE;
+ } else {
+ pte = pte_leftover;
+ pte_leftover = NULL;
+ }
+ memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE);
+ return pte;
+}
+
+enum populate_mode {
+ POPULATE_ONE2ONE,
+ POPULATE_MAP,
+ POPULATE_ZERO_SHADOW
+};
+static void __init kasan_early_vmemmap_populate(unsigned long address,
+ unsigned long end,
+ enum populate_mode mode)
+{
+ unsigned long pgt_prot_zero, pgt_prot, sgt_prot;
+ pgd_t *pg_dir;
+ p4d_t *p4_dir;
+ pud_t *pu_dir;
+ pmd_t *pm_dir;
+ pte_t *pt_dir;
+
+ pgt_prot_zero = pgprot_val(PAGE_KERNEL_RO);
+ if (!has_nx)
+ pgt_prot_zero &= ~_PAGE_NOEXEC;
+ pgt_prot = pgprot_val(PAGE_KERNEL_EXEC);
+ sgt_prot = pgprot_val(SEGMENT_KERNEL_EXEC);
+
+ while (address < end) {
+ pg_dir = pgd_offset_k(address);
+ if (pgd_none(*pg_dir)) {
+ if (mode == POPULATE_ZERO_SHADOW &&
+ IS_ALIGNED(address, PGDIR_SIZE) &&
+ end - address >= PGDIR_SIZE) {
+ pgd_populate(&init_mm, pg_dir,
+ kasan_early_shadow_p4d);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ continue;
+ }
+ p4_dir = kasan_early_crst_alloc(_REGION2_ENTRY_EMPTY);
+ pgd_populate(&init_mm, pg_dir, p4_dir);
+ }
+
+ p4_dir = p4d_offset(pg_dir, address);
+ if (p4d_none(*p4_dir)) {
+ if (mode == POPULATE_ZERO_SHADOW &&
+ IS_ALIGNED(address, P4D_SIZE) &&
+ end - address >= P4D_SIZE) {
+ p4d_populate(&init_mm, p4_dir,
+ kasan_early_shadow_pud);
+ address = (address + P4D_SIZE) & P4D_MASK;
+ continue;
+ }
+ pu_dir = kasan_early_crst_alloc(_REGION3_ENTRY_EMPTY);
+ p4d_populate(&init_mm, p4_dir, pu_dir);
+ }
+
+ pu_dir = pud_offset(p4_dir, address);
+ if (pud_none(*pu_dir)) {
+ if (mode == POPULATE_ZERO_SHADOW &&
+ IS_ALIGNED(address, PUD_SIZE) &&
+ end - address >= PUD_SIZE) {
+ pud_populate(&init_mm, pu_dir,
+ kasan_early_shadow_pmd);
+ address = (address + PUD_SIZE) & PUD_MASK;
+ continue;
+ }
+ pm_dir = kasan_early_crst_alloc(_SEGMENT_ENTRY_EMPTY);
+ pud_populate(&init_mm, pu_dir, pm_dir);
+ }
+
+ pm_dir = pmd_offset(pu_dir, address);
+ if (pmd_none(*pm_dir)) {
+ if (mode == POPULATE_ZERO_SHADOW &&
+ IS_ALIGNED(address, PMD_SIZE) &&
+ end - address >= PMD_SIZE) {
+ pmd_populate(&init_mm, pm_dir,
+ kasan_early_shadow_pte);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ continue;
+ }
+ /* the first megabyte of 1:1 is mapped with 4k pages */
+ if (has_edat && address && end - address >= PMD_SIZE &&
+ mode != POPULATE_ZERO_SHADOW) {
+ void *page;
+
+ if (mode == POPULATE_ONE2ONE) {
+ page = (void *)address;
+ } else {
+ page = kasan_early_alloc_segment();
+ memset(page, 0, _SEGMENT_SIZE);
+ }
+ pmd_val(*pm_dir) = __pa(page) | sgt_prot;
+ address = (address + PMD_SIZE) & PMD_MASK;
+ continue;
+ }
+
+ pt_dir = kasan_early_pte_alloc();
+ pmd_populate(&init_mm, pm_dir, pt_dir);
+ } else if (pmd_large(*pm_dir)) {
+ address = (address + PMD_SIZE) & PMD_MASK;
+ continue;
+ }
+
+ pt_dir = pte_offset_kernel(pm_dir, address);
+ if (pte_none(*pt_dir)) {
+ void *page;
+
+ switch (mode) {
+ case POPULATE_ONE2ONE:
+ page = (void *)address;
+ pte_val(*pt_dir) = __pa(page) | pgt_prot;
+ break;
+ case POPULATE_MAP:
+ page = kasan_early_alloc_pages(0);
+ memset(page, 0, PAGE_SIZE);
+ pte_val(*pt_dir) = __pa(page) | pgt_prot;
+ break;
+ case POPULATE_ZERO_SHADOW:
+ page = kasan_early_shadow_page;
+ pte_val(*pt_dir) = __pa(page) | pgt_prot_zero;
+ break;
+ }
+ }
+ address += PAGE_SIZE;
+ }
+}
+
+static void __init kasan_set_pgd(pgd_t *pgd, unsigned long asce_type)
+{
+ unsigned long asce_bits;
+
+ asce_bits = asce_type | _ASCE_TABLE_LENGTH;
+ S390_lowcore.kernel_asce = (__pa(pgd) & PAGE_MASK) | asce_bits;
+ S390_lowcore.user_asce = S390_lowcore.kernel_asce;
+
+ __ctl_load(S390_lowcore.kernel_asce, 1, 1);
+ __ctl_load(S390_lowcore.kernel_asce, 7, 7);
+ __ctl_load(S390_lowcore.kernel_asce, 13, 13);
+}
+
+static void __init kasan_enable_dat(void)
+{
+ psw_t psw;
+
+ psw.mask = __extract_psw();
+ psw_bits(psw).dat = 1;
+ psw_bits(psw).as = PSW_BITS_AS_HOME;
+ __load_psw_mask(psw.mask);
+}
+
+static void __init kasan_early_detect_facilities(void)
+{
+ if (test_facility(8)) {
+ has_edat = true;
+ __ctl_set_bit(0, 23);
+ }
+ if (!noexec_disabled && test_facility(130)) {
+ has_nx = true;
+ __ctl_set_bit(0, 20);
+ }
+}
+
+void __init kasan_early_init(void)
+{
+ unsigned long untracked_mem_end;
+ unsigned long shadow_alloc_size;
+ unsigned long initrd_end;
+ unsigned long asce_type;
+ unsigned long memsize;
+ unsigned long vmax;
+ unsigned long pgt_prot = pgprot_val(PAGE_KERNEL_RO);
+ pte_t pte_z;
+ pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY);
+ pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY);
+ p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY);
+
+ kasan_early_detect_facilities();
+ if (!has_nx)
+ pgt_prot &= ~_PAGE_NOEXEC;
+ pte_z = __pte(__pa(kasan_early_shadow_page) | pgt_prot);
+
+ 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 = vmax = _REGION1_SIZE;
+ 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 = vmax = _REGION2_SIZE;
+ asce_type = _ASCE_TYPE_REGION3;
+ }
+
+ /* init kasan zero shadow */
+ crst_table_init((unsigned long *)kasan_early_shadow_p4d,
+ p4d_val(p4d_z));
+ crst_table_init((unsigned long *)kasan_early_shadow_pud,
+ pud_val(pud_z));
+ crst_table_init((unsigned long *)kasan_early_shadow_pmd,
+ pmd_val(pmd_z));
+ memset64((u64 *)kasan_early_shadow_pte, pte_val(pte_z), PTRS_PER_PTE);
+
+ shadow_alloc_size = memsize >> KASAN_SHADOW_SCALE_SHIFT;
+ pgalloc_low = round_up((unsigned long)_end, _SEGMENT_SIZE);
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD)) {
+ initrd_end =
+ round_up(INITRD_START + INITRD_SIZE, _SEGMENT_SIZE);
+ pgalloc_low = max(pgalloc_low, initrd_end);
+ }
+
+ if (pgalloc_low + shadow_alloc_size > memsize)
+ kasan_early_panic("out of memory during initialisation\n");
+
+ if (has_edat) {
+ segment_pos = round_down(memsize, _SEGMENT_SIZE);
+ segment_low = segment_pos - shadow_alloc_size;
+ pgalloc_pos = segment_low;
+ } else {
+ pgalloc_pos = memsize;
+ }
+ init_mm.pgd = early_pg_dir;
+ /*
+ * Current memory layout:
+ * +- 0 -------------+ +- shadow start -+
+ * | 1:1 ram mapping | /| 1/8 ram |
+ * +- end of ram ----+ / +----------------+
+ * | ... gap ... |/ | kasan |
+ * +- shadow start --+ | zero |
+ * | 1/8 addr space | | page |
+ * +- shadow end -+ | mapping |
+ * | ... gap ... |\ | (untracked) |
+ * +- modules vaddr -+ \ +----------------+
+ * | 2Gb | \| unmapped | allocated per module
+ * +-----------------+ +- shadow end ---+
+ */
+ /* populate kasan shadow (for identity mapping and zero page mapping) */
+ kasan_early_vmemmap_populate(__sha(0), __sha(memsize), POPULATE_MAP);
+ if (IS_ENABLED(CONFIG_MODULES))
+ untracked_mem_end = vmax - MODULES_LEN;
+ kasan_early_vmemmap_populate(__sha(max_physmem_end),
+ __sha(untracked_mem_end),
+ 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_enable_dat();
+ /* enable kasan */
+ init_task.kasan_depth = 0;
+ memblock_reserve(pgalloc_pos, memsize - pgalloc_pos);
+ sclp_early_printk("KernelAddressSanitizer initialized\n");
+}
+
+void __init kasan_copy_shadow(pgd_t *pg_dir)
+{
+ /*
+ * At this point we are still running on early pages setup early_pg_dir,
+ * while swapper_pg_dir has just been initialized with identity mapping.
+ * Carry over shadow memory region from early_pg_dir to swapper_pg_dir.
+ */
+
+ pgd_t *pg_dir_src;
+ 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);
+ 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));
+}
+
+void __init kasan_free_early_identity(void)
+{
+ memblock_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos);
+}
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 7be0647..1864a8b 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -16,6 +16,7 @@
#include <linux/cpu.h>
#include <asm/ctl_reg.h>
#include <asm/io.h>
+#include <asm/stacktrace.h>
static notrace long s390_kernel_write_odd(void *dst, const void *src, size_t size)
{
@@ -51,21 +52,22 @@
* Therefore we have a read-modify-write sequence: the function reads eight
* bytes from destination at an eight byte boundary, modifies the bytes
* requested and writes the result back in a loop.
- *
- * Note: this means that this function may not be called concurrently on
- * several cpus with overlapping words, since this may potentially
- * cause data corruption.
*/
+static DEFINE_SPINLOCK(s390_kernel_write_lock);
+
void notrace s390_kernel_write(void *dst, const void *src, size_t size)
{
+ unsigned long flags;
long copied;
+ spin_lock_irqsave(&s390_kernel_write_lock, flags);
while (size) {
copied = s390_kernel_write_odd(dst, src, size);
dst += copied;
src += copied;
size -= copied;
}
+ spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
}
static int __memcpy_real(void *dest, void *src, size_t count)
@@ -89,10 +91,8 @@
return rc;
}
-/*
- * Copy memory in real mode (kernel to kernel)
- */
-int memcpy_real(void *dest, void *src, size_t count)
+static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
+ unsigned long count)
{
int irqs_disabled, rc;
unsigned long flags;
@@ -103,7 +103,7 @@
irqs_disabled = arch_irqs_disabled_flags(flags);
if (!irqs_disabled)
trace_hardirqs_off();
- rc = __memcpy_real(dest, src, count);
+ rc = __memcpy_real((void *) dest, (void *) src, (size_t) count);
if (!irqs_disabled)
trace_hardirqs_on();
__arch_local_irq_ssm(flags);
@@ -111,6 +111,23 @@
}
/*
+ * Copy memory in real mode (kernel to kernel)
+ */
+int memcpy_real(void *dest, void *src, size_t count)
+{
+ if (S390_lowcore.nodat_stack != 0)
+ return CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack,
+ 3, dest, src, count);
+ /*
+ * This is a really early memcpy_real call, the stacks are
+ * not set up yet. Just call _memcpy_real on the early boot
+ * stack
+ */
+ return _memcpy_real((unsigned long) dest,(unsigned long) src,
+ (unsigned long) count);
+}
+
+/*
* Copy memory in absolute mode (kernel to kernel)
*/
void memcpy_absolute(void *dest, void *src, size_t count)
diff --git a/arch/s390/mm/mem_detect.c b/arch/s390/mm/mem_detect.c
deleted file mode 100644
index 21f6c82..0000000
--- a/arch/s390/mm/mem_detect.c
+++ /dev/null
@@ -1,62 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright IBM Corp. 2008, 2009
- *
- * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
- */
-
-#include <linux/kernel.h>
-#include <linux/memblock.h>
-#include <linux/init.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include <asm/ipl.h>
-#include <asm/sclp.h>
-#include <asm/setup.h>
-
-#define CHUNK_READ_WRITE 0
-#define CHUNK_READ_ONLY 1
-
-static inline void memblock_physmem_add(phys_addr_t start, phys_addr_t size)
-{
- memblock_dbg("memblock_physmem_add: [%#016llx-%#016llx]\n",
- start, start + size - 1);
- memblock_add_range(&memblock.memory, start, size, 0, 0);
- memblock_add_range(&memblock.physmem, start, size, 0, 0);
-}
-
-void __init detect_memory_memblock(void)
-{
- unsigned long memsize, rnmax, rzm, addr, size;
- int type;
-
- rzm = sclp.rzm;
- rnmax = sclp.rnmax;
- memsize = rzm * rnmax;
- if (!rzm)
- rzm = 1UL << 17;
- max_physmem_end = memsize;
- addr = 0;
- /* keep memblock lists close to the kernel */
- memblock_set_bottom_up(true);
- do {
- size = 0;
- /* assume lowcore is writable */
- type = addr ? tprot(addr) : CHUNK_READ_WRITE;
- do {
- size += rzm;
- if (max_physmem_end && addr + size >= max_physmem_end)
- break;
- } while (type == tprot(addr + size));
- if (type == CHUNK_READ_WRITE || type == CHUNK_READ_ONLY) {
- if (max_physmem_end && (addr + size > max_physmem_end))
- size = max_physmem_end - addr;
- memblock_physmem_add(addr, size);
- }
- addr += size;
- } while (addr < max_physmem_end);
- memblock_set_bottom_up(false);
- if (!max_physmem_end)
- max_physmem_end = memblock_end_of_DRAM();
- memblock_dump_all();
-}
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 0a7627c..cbc718b 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -24,19 +24,9 @@
{
if (!(current->flags & PF_RANDOMIZE))
return 0;
- if (current->personality & ADDR_NO_RANDOMIZE)
- return 0;
return STACK_RND_MASK << PAGE_SHIFT;
}
-/*
- * Top of mmap area (just below the process stack).
- *
- * Leave at least a ~32 MB hole.
- */
-#define MIN_GAP (32*1024*1024)
-#define MAX_GAP (STACK_TOP/6*5)
-
static inline int mmap_is_legacy(struct rlimit *rlim_stack)
{
if (current->personality & ADDR_COMPAT_LAYOUT)
@@ -60,13 +50,26 @@
struct rlimit *rlim_stack)
{
unsigned long gap = rlim_stack->rlim_cur;
+ unsigned long pad = stack_maxrandom_size() + stack_guard_gap;
+ unsigned long gap_min, gap_max;
- if (gap < MIN_GAP)
- gap = MIN_GAP;
- else if (gap > MAX_GAP)
- gap = MAX_GAP;
- gap &= PAGE_MASK;
- return STACK_TOP - stack_maxrandom_size() - rnd - gap;
+ /* Values close to RLIM_INFINITY can overflow. */
+ if (gap + pad > gap)
+ gap += pad;
+
+ /*
+ * Top of mmap area (just below the process stack).
+ * Leave at least a ~32 MB hole.
+ */
+ gap_min = 32 * 1024 * 1024UL;
+ gap_max = (STACK_TOP / 6) * 5;
+
+ if (gap < gap_min)
+ gap = gap_min;
+ else if (gap > gap_max)
+ gap = gap_max;
+
+ return PAGE_ALIGN(STACK_TOP - gap - rnd);
}
unsigned long
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index dc3cede..fc14189 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -21,17 +21,11 @@
static int __init cmma(char *str)
{
- char *parm;
+ bool enabled;
- parm = strstrip(str);
- if (strcmp(parm, "yes") == 0 || strcmp(parm, "on") == 0) {
- cmma_flag = 1;
- return 1;
- }
- cmma_flag = 0;
- if (strcmp(parm, "no") == 0 || strcmp(parm, "off") == 0)
- return 1;
- return 0;
+ if (!kstrtobool(str, &enabled))
+ cmma_flag = enabled;
+ return 1;
}
__setup("cmma=", cmma);
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 814f265..3dd253f 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -17,8 +17,6 @@
#ifdef CONFIG_PGSTE
-static int page_table_allocate_pgste_min = 0;
-static int page_table_allocate_pgste_max = 1;
int page_table_allocate_pgste = 0;
EXPORT_SYMBOL(page_table_allocate_pgste);
@@ -29,8 +27,8 @@
.maxlen = sizeof(int),
.mode = S_IRUGO | S_IWUSR,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &page_table_allocate_pgste_min,
- .extra2 = &page_table_allocate_pgste_max,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
},
{ }
};
@@ -131,6 +129,7 @@
}
pgd = mm->pgd;
+ mm_dec_nr_pmds(mm);
mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
mm->context.asce_limit = _REGION3_SIZE;
mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
@@ -211,7 +210,7 @@
page = alloc_page(GFP_KERNEL);
if (!page)
return NULL;
- if (!pgtable_page_ctor(page)) {
+ if (!pgtable_pte_page_ctor(page)) {
__free_page(page);
return NULL;
}
@@ -257,7 +256,7 @@
atomic_xor_bits(&page->_refcount, 3U << 24);
}
- pgtable_page_dtor(page);
+ pgtable_pte_page_dtor(page);
__free_page(page);
}
@@ -289,7 +288,7 @@
tlb_remove_table(tlb, table);
}
-static void __tlb_remove_table(void *_table)
+void __tlb_remove_table(void *_table)
{
unsigned int mask = (unsigned long) _table & 3;
void *table = (void *)((unsigned long) _table ^ mask);
@@ -309,73 +308,12 @@
case 3: /* 4K page table with pgstes */
if (mask & 3)
atomic_xor_bits(&page->_refcount, 3 << 24);
- pgtable_page_dtor(page);
+ pgtable_pte_page_dtor(page);
__free_page(page);
break;
}
}
-static void tlb_remove_table_smp_sync(void *arg)
-{
- /* Simply deliver the interrupt */
-}
-
-static void tlb_remove_table_one(void *table)
-{
- /*
- * This isn't an RCU grace period and hence the page-tables cannot be
- * assumed to be actually RCU-freed.
- *
- * It is however sufficient for software page-table walkers that rely
- * on IRQ disabling. See the comment near struct mmu_table_batch.
- */
- smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
- __tlb_remove_table(table);
-}
-
-static void tlb_remove_table_rcu(struct rcu_head *head)
-{
- struct mmu_table_batch *batch;
- int i;
-
- batch = container_of(head, struct mmu_table_batch, rcu);
-
- for (i = 0; i < batch->nr; i++)
- __tlb_remove_table(batch->tables[i]);
-
- free_page((unsigned long)batch);
-}
-
-void tlb_table_flush(struct mmu_gather *tlb)
-{
- struct mmu_table_batch **batch = &tlb->batch;
-
- if (*batch) {
- call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
- *batch = NULL;
- }
-}
-
-void tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
- struct mmu_table_batch **batch = &tlb->batch;
-
- tlb->mm->context.flush_mm = 1;
- if (*batch == NULL) {
- *batch = (struct mmu_table_batch *)
- __get_free_page(GFP_NOWAIT | __GFP_NOWARN);
- if (*batch == NULL) {
- __tlb_flush_mm_lazy(tlb->mm);
- tlb_remove_table_one(table);
- return;
- }
- (*batch)->nr = 0;
- }
- (*batch)->tables[(*batch)->nr++] = table;
- if ((*batch)->nr == MAX_TABLE_BATCH)
- tlb_flush_mmu(tlb);
-}
-
/*
* Base infrastructure required to generate basic asces, region, segment,
* and page tables that do not make use of enhanced features like EDAT1.
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index f2cc7da..9ebd012 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -301,12 +301,13 @@
}
EXPORT_SYMBOL(ptep_xchg_lazy);
-pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep)
{
pgste_t pgste;
pte_t old;
int nodat;
+ struct mm_struct *mm = vma->vm_mm;
preempt_disable();
pgste = ptep_xchg_start(mm, addr, ptep);
@@ -318,12 +319,12 @@
}
return old;
}
-EXPORT_SYMBOL(ptep_modify_prot_start);
-void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte)
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+ pte_t *ptep, pte_t old_pte, pte_t pte)
{
pgste_t pgste;
+ struct mm_struct *mm = vma->vm_mm;
if (!MACHINE_HAS_NX)
pte_val(pte) &= ~_PAGE_NOEXEC;
@@ -337,7 +338,6 @@
}
preempt_enable();
}
-EXPORT_SYMBOL(ptep_modify_prot_commit);
static inline void pmdp_idte_local(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
@@ -410,6 +410,7 @@
return old;
}
+#ifdef CONFIG_PGSTE
static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
@@ -427,6 +428,7 @@
pmd = pmd_alloc(mm, pud, addr);
return pmd;
}
+#endif
pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t new)
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index db55561..b403fa1 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -4,14 +4,13 @@
* Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
*/
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/pfn.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
-#include <linux/memblock.h>
#include <asm/cacheflush.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
@@ -36,7 +35,7 @@
if (slab_is_available())
return (void *)__get_free_pages(GFP_KERNEL, order);
- return (void *) memblock_alloc(size, size);
+ return (void *) memblock_phys_alloc(size, size);
}
void *vmem_crst_alloc(unsigned long val)
@@ -57,7 +56,7 @@
if (slab_is_available())
pte = (pte_t *) page_table_alloc(&init_mm);
else
- pte = (pte_t *) memblock_alloc(size, size);
+ pte = (pte_t *) memblock_phys_alloc(size, size);
if (!pte)
return NULL;
memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE);
@@ -414,6 +413,8 @@
__set_memory((unsigned long)_sinittext,
(unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
SET_MEMORY_RO | SET_MEMORY_X);
+ __set_memory(__stext_dma, (__etext_dma - __stext_dma) >> PAGE_SHIFT,
+ SET_MEMORY_RO | SET_MEMORY_X);
pr_info("Write protected kernel read-only data: %luk\n",
(unsigned long)(__end_rodata - _stext) >> 10);
}
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index d7052cb..ce88211 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -299,9 +299,11 @@
#define EMIT_ZERO(b1) \
({ \
- /* llgfr %dst,%dst (zero extend to 64 bit) */ \
- EMIT4(0xb9160000, b1, b1); \
- REG_SET_SEEN(b1); \
+ if (!fp->aux->verifier_zext) { \
+ /* llgfr %dst,%dst (zero extend to 64 bit) */ \
+ EMIT4(0xb9160000, b1, b1); \
+ REG_SET_SEEN(b1); \
+ } \
})
/*
@@ -455,7 +457,7 @@
EMIT4(0xb9040000, REG_2, BPF_REG_0);
/* Restore registers */
save_restore_regs(jit, REGS_RESTORE, stack_depth);
- if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+ if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) {
jit->r14_thunk_ip = jit->prg;
/* Generate __s390_indirect_jump_r14 thunk */
if (test_facility(35)) {
@@ -473,7 +475,7 @@
/* br %r14 */
_EMIT2(0x07fe);
- if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable &&
+ if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable &&
(jit->seen & SEEN_FUNC)) {
jit->r1_thunk_ip = jit->prg;
/* Generate __s390_indirect_jump_r1 thunk */
@@ -500,7 +502,8 @@
* NOTE: Use noinline because for gcov (-fprofile-arcs) gcc allocates a lot of
* stack space for the large switch statement.
*/
-static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
+static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
+ int i, bool extra_pass)
{
struct bpf_insn *insn = &fp->insnsi[i];
int jmp_off, last, insn_count = 1;
@@ -520,6 +523,8 @@
case BPF_ALU | BPF_MOV | BPF_X: /* dst = (u32) src */
/* llgfr %dst,%src */
EMIT4(0xb9160000, dst_reg, src_reg);
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
/* lgr %dst,%src */
@@ -528,6 +533,8 @@
case BPF_ALU | BPF_MOV | BPF_K: /* dst = (u32) imm */
/* llilf %dst,imm */
EMIT6_IMM(0xc00f0000, dst_reg, imm);
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = imm */
/* lgfi %dst,imm */
@@ -639,6 +646,8 @@
EMIT4(0xb9970000, REG_W0, src_reg);
/* llgfr %dst,%rc */
EMIT4(0xb9160000, dst_reg, rc_reg);
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
}
case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */
@@ -676,6 +685,8 @@
EMIT_CONST_U32(imm));
/* llgfr %dst,%rc */
EMIT4(0xb9160000, dst_reg, rc_reg);
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
}
case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */
@@ -821,10 +832,22 @@
/*
* BPF_ARSH
*/
+ case BPF_ALU | BPF_ARSH | BPF_X: /* ((s32) dst) >>= src */
+ /* sra %dst,%dst,0(%src) */
+ EMIT4_DISP(0x8a000000, dst_reg, src_reg, 0);
+ EMIT_ZERO(dst_reg);
+ break;
case BPF_ALU64 | BPF_ARSH | BPF_X: /* ((s64) dst) >>= src */
/* srag %dst,%dst,0(%src) */
EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, src_reg, 0);
break;
+ case BPF_ALU | BPF_ARSH | BPF_K: /* ((s32) dst >> imm */
+ if (imm == 0)
+ break;
+ /* sra %dst,imm(%r0) */
+ EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm);
+ EMIT_ZERO(dst_reg);
+ break;
case BPF_ALU64 | BPF_ARSH | BPF_K: /* ((s64) dst) >>= imm */
if (imm == 0)
break;
@@ -841,7 +864,7 @@
break;
case BPF_ALU64 | BPF_NEG: /* dst = -dst */
/* lcgr %dst,%dst */
- EMIT4(0xb9130000, dst_reg, dst_reg);
+ EMIT4(0xb9030000, dst_reg, dst_reg);
break;
/*
* BPF_FROM_BE/LE
@@ -852,10 +875,13 @@
case 16: /* dst = (u16) cpu_to_be16(dst) */
/* llghr %dst,%dst */
EMIT4(0xb9850000, dst_reg, dst_reg);
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
case 32: /* dst = (u32) cpu_to_be32(dst) */
- /* llgfr %dst,%dst */
- EMIT4(0xb9160000, dst_reg, dst_reg);
+ if (!fp->aux->verifier_zext)
+ /* llgfr %dst,%dst */
+ EMIT4(0xb9160000, dst_reg, dst_reg);
break;
case 64: /* dst = (u64) cpu_to_be64(dst) */
break;
@@ -870,12 +896,15 @@
EMIT4_DISP(0x88000000, dst_reg, REG_0, 16);
/* llghr %dst,%dst */
EMIT4(0xb9850000, dst_reg, dst_reg);
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
case 32: /* dst = (u32) cpu_to_le32(dst) */
/* lrvr %dst,%dst */
EMIT4(0xb91f0000, dst_reg, dst_reg);
- /* llgfr %dst,%dst */
- EMIT4(0xb9160000, dst_reg, dst_reg);
+ if (!fp->aux->verifier_zext)
+ /* llgfr %dst,%dst */
+ EMIT4(0xb9160000, dst_reg, dst_reg);
break;
case 64: /* dst = (u64) cpu_to_le64(dst) */
/* lrvgr %dst,%dst */
@@ -956,16 +985,22 @@
/* llgc %dst,0(off,%src) */
EMIT6_DISP_LH(0xe3000000, 0x0090, dst_reg, src_reg, REG_0, off);
jit->seen |= SEEN_MEM;
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */
/* llgh %dst,0(off,%src) */
EMIT6_DISP_LH(0xe3000000, 0x0091, dst_reg, src_reg, REG_0, off);
jit->seen |= SEEN_MEM;
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */
/* llgf %dst,off(%src) */
jit->seen |= SEEN_MEM;
EMIT6_DISP_LH(0xe3000000, 0x0016, dst_reg, src_reg, REG_0, off);
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
break;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */
/* lg %dst,0(off,%src) */
@@ -977,17 +1012,21 @@
*/
case BPF_JMP | BPF_CALL:
{
- /*
- * b0 = (__bpf_call_base + imm)(b1, b2, b3, b4, b5)
- */
- const u64 func = (u64)__bpf_call_base + imm;
+ u64 func;
+ bool func_addr_fixed;
+ int ret;
+
+ ret = bpf_jit_get_func_addr(fp, insn, extra_pass,
+ &func, &func_addr_fixed);
+ if (ret < 0)
+ return -1;
REG_SET_SEEN(BPF_REG_5);
jit->seen |= SEEN_FUNC;
/* lg %w1,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
EMIT_CONST_U64(func));
- if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+ if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) {
/* brasl %r14,__s390_indirect_jump_r1 */
EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
} else {
@@ -1015,8 +1054,8 @@
/* llgf %w1,map.max_entries(%b2) */
EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2,
offsetof(struct bpf_array, map.max_entries));
- /* clgrj %b3,%w1,0xa,label0: if %b3 >= %w1 goto out */
- EMIT6_PCREL_LABEL(0xec000000, 0x0065, BPF_REG_3,
+ /* clrj %b3,%w1,0xa,label0: if (u32)%b3 >= (u32)%w1 goto out */
+ EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3,
REG_W1, 0, 0xa);
/*
@@ -1042,8 +1081,10 @@
* goto out;
*/
- /* sllg %r1,%b3,3: %r1 = index * 8 */
- EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3);
+ /* llgfr %r1,%b3: %r1 = (u32) index */
+ EMIT4(0xb9160000, REG_1, BPF_REG_3);
+ /* sllg %r1,%r1,3: %r1 *= 8 */
+ EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, REG_1, REG_0, 3);
/* lg %r1,prog(%b2,%r1) */
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2,
REG_1, offsetof(struct bpf_array, ptrs));
@@ -1098,103 +1139,145 @@
mask = 0xf000; /* j */
goto branch_oc;
case BPF_JMP | BPF_JSGT | BPF_K: /* ((s64) dst > (s64) imm) */
+ case BPF_JMP32 | BPF_JSGT | BPF_K: /* ((s32) dst > (s32) imm) */
mask = 0x2000; /* jh */
goto branch_ks;
case BPF_JMP | BPF_JSLT | BPF_K: /* ((s64) dst < (s64) imm) */
+ case BPF_JMP32 | BPF_JSLT | BPF_K: /* ((s32) dst < (s32) imm) */
mask = 0x4000; /* jl */
goto branch_ks;
case BPF_JMP | BPF_JSGE | BPF_K: /* ((s64) dst >= (s64) imm) */
+ case BPF_JMP32 | BPF_JSGE | BPF_K: /* ((s32) dst >= (s32) imm) */
mask = 0xa000; /* jhe */
goto branch_ks;
case BPF_JMP | BPF_JSLE | BPF_K: /* ((s64) dst <= (s64) imm) */
+ case BPF_JMP32 | BPF_JSLE | BPF_K: /* ((s32) dst <= (s32) imm) */
mask = 0xc000; /* jle */
goto branch_ks;
case BPF_JMP | BPF_JGT | BPF_K: /* (dst_reg > imm) */
+ case BPF_JMP32 | BPF_JGT | BPF_K: /* ((u32) dst_reg > (u32) imm) */
mask = 0x2000; /* jh */
goto branch_ku;
case BPF_JMP | BPF_JLT | BPF_K: /* (dst_reg < imm) */
+ case BPF_JMP32 | BPF_JLT | BPF_K: /* ((u32) dst_reg < (u32) imm) */
mask = 0x4000; /* jl */
goto branch_ku;
case BPF_JMP | BPF_JGE | BPF_K: /* (dst_reg >= imm) */
+ case BPF_JMP32 | BPF_JGE | BPF_K: /* ((u32) dst_reg >= (u32) imm) */
mask = 0xa000; /* jhe */
goto branch_ku;
case BPF_JMP | BPF_JLE | BPF_K: /* (dst_reg <= imm) */
+ case BPF_JMP32 | BPF_JLE | BPF_K: /* ((u32) dst_reg <= (u32) imm) */
mask = 0xc000; /* jle */
goto branch_ku;
case BPF_JMP | BPF_JNE | BPF_K: /* (dst_reg != imm) */
+ case BPF_JMP32 | BPF_JNE | BPF_K: /* ((u32) dst_reg != (u32) imm) */
mask = 0x7000; /* jne */
goto branch_ku;
case BPF_JMP | BPF_JEQ | BPF_K: /* (dst_reg == imm) */
+ case BPF_JMP32 | BPF_JEQ | BPF_K: /* ((u32) dst_reg == (u32) imm) */
mask = 0x8000; /* je */
goto branch_ku;
case BPF_JMP | BPF_JSET | BPF_K: /* (dst_reg & imm) */
+ case BPF_JMP32 | BPF_JSET | BPF_K: /* ((u32) dst_reg & (u32) imm) */
mask = 0x7000; /* jnz */
- /* lgfi %w1,imm (load sign extend imm) */
- EMIT6_IMM(0xc0010000, REG_W1, imm);
- /* ngr %w1,%dst */
- EMIT4(0xb9800000, REG_W1, dst_reg);
+ if (BPF_CLASS(insn->code) == BPF_JMP32) {
+ /* llilf %w1,imm (load zero extend imm) */
+ EMIT6_IMM(0xc00f0000, REG_W1, imm);
+ /* nr %w1,%dst */
+ EMIT2(0x1400, REG_W1, dst_reg);
+ } else {
+ /* lgfi %w1,imm (load sign extend imm) */
+ EMIT6_IMM(0xc0010000, REG_W1, imm);
+ /* ngr %w1,%dst */
+ EMIT4(0xb9800000, REG_W1, dst_reg);
+ }
goto branch_oc;
case BPF_JMP | BPF_JSGT | BPF_X: /* ((s64) dst > (s64) src) */
+ case BPF_JMP32 | BPF_JSGT | BPF_X: /* ((s32) dst > (s32) src) */
mask = 0x2000; /* jh */
goto branch_xs;
case BPF_JMP | BPF_JSLT | BPF_X: /* ((s64) dst < (s64) src) */
+ case BPF_JMP32 | BPF_JSLT | BPF_X: /* ((s32) dst < (s32) src) */
mask = 0x4000; /* jl */
goto branch_xs;
case BPF_JMP | BPF_JSGE | BPF_X: /* ((s64) dst >= (s64) src) */
+ case BPF_JMP32 | BPF_JSGE | BPF_X: /* ((s32) dst >= (s32) src) */
mask = 0xa000; /* jhe */
goto branch_xs;
case BPF_JMP | BPF_JSLE | BPF_X: /* ((s64) dst <= (s64) src) */
+ case BPF_JMP32 | BPF_JSLE | BPF_X: /* ((s32) dst <= (s32) src) */
mask = 0xc000; /* jle */
goto branch_xs;
case BPF_JMP | BPF_JGT | BPF_X: /* (dst > src) */
+ case BPF_JMP32 | BPF_JGT | BPF_X: /* ((u32) dst > (u32) src) */
mask = 0x2000; /* jh */
goto branch_xu;
case BPF_JMP | BPF_JLT | BPF_X: /* (dst < src) */
+ case BPF_JMP32 | BPF_JLT | BPF_X: /* ((u32) dst < (u32) src) */
mask = 0x4000; /* jl */
goto branch_xu;
case BPF_JMP | BPF_JGE | BPF_X: /* (dst >= src) */
+ case BPF_JMP32 | BPF_JGE | BPF_X: /* ((u32) dst >= (u32) src) */
mask = 0xa000; /* jhe */
goto branch_xu;
case BPF_JMP | BPF_JLE | BPF_X: /* (dst <= src) */
+ case BPF_JMP32 | BPF_JLE | BPF_X: /* ((u32) dst <= (u32) src) */
mask = 0xc000; /* jle */
goto branch_xu;
case BPF_JMP | BPF_JNE | BPF_X: /* (dst != src) */
+ case BPF_JMP32 | BPF_JNE | BPF_X: /* ((u32) dst != (u32) src) */
mask = 0x7000; /* jne */
goto branch_xu;
case BPF_JMP | BPF_JEQ | BPF_X: /* (dst == src) */
+ case BPF_JMP32 | BPF_JEQ | BPF_X: /* ((u32) dst == (u32) src) */
mask = 0x8000; /* je */
goto branch_xu;
case BPF_JMP | BPF_JSET | BPF_X: /* (dst & src) */
+ case BPF_JMP32 | BPF_JSET | BPF_X: /* ((u32) dst & (u32) src) */
+ {
+ bool is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
+
mask = 0x7000; /* jnz */
- /* ngrk %w1,%dst,%src */
- EMIT4_RRF(0xb9e40000, REG_W1, dst_reg, src_reg);
+ /* nrk or ngrk %w1,%dst,%src */
+ EMIT4_RRF((is_jmp32 ? 0xb9f40000 : 0xb9e40000),
+ REG_W1, dst_reg, src_reg);
goto branch_oc;
branch_ks:
+ is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
/* lgfi %w1,imm (load sign extend imm) */
EMIT6_IMM(0xc0010000, REG_W1, imm);
- /* cgrj %dst,%w1,mask,off */
- EMIT6_PCREL(0xec000000, 0x0064, dst_reg, REG_W1, i, off, mask);
+ /* crj or cgrj %dst,%w1,mask,off */
+ EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064),
+ dst_reg, REG_W1, i, off, mask);
break;
branch_ku:
+ is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
/* lgfi %w1,imm (load sign extend imm) */
EMIT6_IMM(0xc0010000, REG_W1, imm);
- /* clgrj %dst,%w1,mask,off */
- EMIT6_PCREL(0xec000000, 0x0065, dst_reg, REG_W1, i, off, mask);
+ /* clrj or clgrj %dst,%w1,mask,off */
+ EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065),
+ dst_reg, REG_W1, i, off, mask);
break;
branch_xs:
- /* cgrj %dst,%src,mask,off */
- EMIT6_PCREL(0xec000000, 0x0064, dst_reg, src_reg, i, off, mask);
+ is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
+ /* crj or cgrj %dst,%src,mask,off */
+ EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064),
+ dst_reg, src_reg, i, off, mask);
break;
branch_xu:
- /* clgrj %dst,%src,mask,off */
- EMIT6_PCREL(0xec000000, 0x0065, dst_reg, src_reg, i, off, mask);
+ is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
+ /* clrj or clgrj %dst,%src,mask,off */
+ EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065),
+ dst_reg, src_reg, i, off, mask);
break;
branch_oc:
/* brc mask,jmp_off (branch instruction needs 4 bytes) */
jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4);
EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off);
break;
+ }
default: /* too complex, give up */
pr_err("Unknown opcode %02x\n", insn->code);
return -1;
@@ -1205,7 +1288,8 @@
/*
* Compile eBPF program into s390x code
*/
-static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
+static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp,
+ bool extra_pass)
{
int i, insn_count;
@@ -1214,7 +1298,7 @@
bpf_jit_prologue(jit, fp->aux->stack_depth);
for (i = 0; i < fp->len; i += insn_count) {
- insn_count = bpf_jit_insn(jit, fp, i);
+ insn_count = bpf_jit_insn(jit, fp, i, extra_pass);
if (insn_count < 0)
return -1;
/* Next instruction address */
@@ -1228,6 +1312,17 @@
return 0;
}
+bool bpf_jit_needs_zext(void)
+{
+ return true;
+}
+
+struct s390_jit_data {
+ struct bpf_binary_header *header;
+ struct bpf_jit ctx;
+ int pass;
+};
+
/*
* Compile eBPF program "fp"
*/
@@ -1235,7 +1330,9 @@
{
struct bpf_prog *tmp, *orig_fp = fp;
struct bpf_binary_header *header;
+ struct s390_jit_data *jit_data;
bool tmp_blinded = false;
+ bool extra_pass = false;
struct bpf_jit jit;
int pass;
@@ -1254,6 +1351,23 @@
fp = tmp;
}
+ jit_data = fp->aux->jit_data;
+ if (!jit_data) {
+ jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+ if (!jit_data) {
+ fp = orig_fp;
+ goto out;
+ }
+ fp->aux->jit_data = jit_data;
+ }
+ if (jit_data->ctx.addrs) {
+ jit = jit_data->ctx;
+ header = jit_data->header;
+ extra_pass = true;
+ pass = jit_data->pass + 1;
+ goto skip_init_ctx;
+ }
+
memset(&jit, 0, sizeof(jit));
jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
if (jit.addrs == NULL) {
@@ -1266,7 +1380,7 @@
* - 3: Calculate program size and addrs arrray
*/
for (pass = 1; pass <= 3; pass++) {
- if (bpf_jit_prog(&jit, fp)) {
+ if (bpf_jit_prog(&jit, fp, extra_pass)) {
fp = orig_fp;
goto free_addrs;
}
@@ -1278,12 +1392,14 @@
fp = orig_fp;
goto free_addrs;
}
+
header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 2, jit_fill_hole);
if (!header) {
fp = orig_fp;
goto free_addrs;
}
- if (bpf_jit_prog(&jit, fp)) {
+skip_init_ctx:
+ if (bpf_jit_prog(&jit, fp, extra_pass)) {
bpf_jit_binary_free(header);
fp = orig_fp;
goto free_addrs;
@@ -1292,12 +1408,24 @@
bpf_jit_dump(fp->len, jit.size, pass, jit.prg_buf);
print_fn_code(jit.prg_buf, jit.size_prg);
}
- bpf_jit_binary_lock_ro(header);
+ if (!fp->is_func || extra_pass) {
+ bpf_jit_binary_lock_ro(header);
+ } else {
+ jit_data->header = header;
+ jit_data->ctx = jit;
+ jit_data->pass = pass;
+ }
fp->bpf_func = (void *) jit.prg_buf;
fp->jited = 1;
fp->jited_len = jit.size;
+
+ if (!fp->is_func || extra_pass) {
+ bpf_prog_fill_jited_linfo(fp, jit.addrs + 1);
free_addrs:
- kfree(jit.addrs);
+ kfree(jit.addrs);
+ kfree(jit_data);
+ fp->aux->jit_data = NULL;
+ }
out:
if (tmp_blinded)
bpf_jit_prog_release_other(fp, fp == orig_fp ?
diff --git a/arch/s390/net/pnet.c b/arch/s390/net/pnet.c
index e22f1b1..79211be 100644
--- a/arch/s390/net/pnet.c
+++ b/arch/s390/net/pnet.c
@@ -12,6 +12,15 @@
#include <asm/ccwgroup.h>
#include <asm/ccwdev.h>
#include <asm/pnet.h>
+#include <asm/ebcdic.h>
+
+#define PNETIDS_LEN 64 /* Total utility string length in bytes
+ * to cover up to 4 PNETIDs of 16 bytes
+ * for up to 4 device ports
+ */
+#define MAX_PNETID_LEN 16 /* Max.length of a single port PNETID */
+#define MAX_PNETID_PORTS (PNETIDS_LEN / MAX_PNETID_LEN)
+ /* Max. # of ports with a PNETID */
/*
* Get the PNETIDs from a device.
@@ -40,6 +49,7 @@
if (!util_str)
return -ENOMEM;
memcpy(pnetids, util_str, PNETIDS_LEN);
+ EBCASC(pnetids, PNETIDS_LEN);
kfree(util_str);
return 0;
}
@@ -47,6 +57,7 @@
struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
memcpy(pnetids, zdev->util_str, sizeof(zdev->util_str));
+ EBCASC(pnetids, sizeof(zdev->util_str));
return 0;
}
return -EOPNOTSUPP;
diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c
index 83b222c..72d742b 100644
--- a/arch/s390/numa/mode_emu.c
+++ b/arch/s390/numa/mode_emu.c
@@ -22,7 +22,6 @@
#include <linux/kernel.h>
#include <linux/cpumask.h>
#include <linux/memblock.h>
-#include <linux/bootmem.h>
#include <linux/node.h>
#include <linux/memory.h>
#include <linux/slab.h>
@@ -313,7 +312,10 @@
{
int i;
- emu_cores = memblock_virt_alloc(sizeof(*emu_cores), 8);
+ emu_cores = memblock_alloc(sizeof(*emu_cores), 8);
+ if (!emu_cores)
+ panic("%s: Failed to allocate %zu bytes align=0x%x\n",
+ __func__, sizeof(*emu_cores), 8);
for (i = 0; i < ARRAY_SIZE(emu_cores->to_node_id); i++)
emu_cores->to_node_id[i] = NODE_ID_FREE;
}
@@ -556,9 +558,7 @@
{
int count;
- if (kstrtoint(p, 0, &count) != 0 || count <= 0)
- return 0;
- if (count <= 0)
+ if (!p || kstrtoint(p, 0, &count) != 0 || count <= 0)
return 0;
emu_nodes = min(count, MAX_NUMNODES);
return 0;
@@ -570,7 +570,8 @@
*/
static int __init early_parse_emu_size(char *p)
{
- emu_size = memparse(p, NULL);
+ if (p)
+ emu_size = memparse(p, NULL);
return 0;
}
early_param("emu_size", early_parse_emu_size);
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index 6c151b4..d2910fa 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -13,7 +13,6 @@
#include <linux/kernel.h>
#include <linux/mmzone.h>
#include <linux/cpumask.h>
-#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/slab.h>
#include <linux/node.h>
@@ -59,18 +58,6 @@
int numa_debug_enabled;
/*
- * alloc_node_data() - Allocate node data
- */
-static __init pg_data_t *alloc_node_data(void)
-{
- pg_data_t *res;
-
- res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 8);
- memset(res, 0, sizeof(pg_data_t));
- return res;
-}
-
-/*
* numa_setup_memory() - Assign bootmem to nodes
*
* The memory is first added to memblock without any respect to nodes.
@@ -105,8 +92,12 @@
} while (cur_base < end_of_dram);
/* Allocate and fill out node_data */
- for (nid = 0; nid < MAX_NUMNODES; nid++)
- NODE_DATA(nid) = alloc_node_data();
+ for (nid = 0; nid < MAX_NUMNODES; nid++) {
+ NODE_DATA(nid) = memblock_alloc(sizeof(pg_data_t), 8);
+ if (!NODE_DATA(nid))
+ panic("%s: Failed to allocate %zu bytes align=0x%x\n",
+ __func__, sizeof(pg_data_t), 8);
+ }
for_each_online_node(nid) {
unsigned long start_pfn, end_pfn;
@@ -167,6 +158,8 @@
static int __init parse_numa(char *parm)
{
+ if (!parm)
+ return 1;
if (strcmp(parm, numa_mode_plain.name) == 0)
mode = &numa_mode_plain;
#ifdef CONFIG_NUMA_EMU
diff --git a/arch/s390/numa/toptree.c b/arch/s390/numa/toptree.c
index 21d1e8a..71a608c 100644
--- a/arch/s390/numa/toptree.c
+++ b/arch/s390/numa/toptree.c
@@ -8,7 +8,7 @@
*/
#include <linux/kernel.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/cpumask.h>
#include <linux/list.h>
#include <linux/list_sort.h>
@@ -34,7 +34,7 @@
if (slab_is_available())
res = kzalloc(sizeof(*res), GFP_KERNEL);
else
- res = memblock_virt_alloc(sizeof(*res), 8);
+ res = memblock_alloc(sizeof(*res), 8);
if (!res)
return res;
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 43d9525..7441857 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -13,23 +13,17 @@
#include <linux/oprofile.h>
#include <linux/init.h>
#include <asm/processor.h>
-
-static int __s390_backtrace(void *data, unsigned long address, int reliable)
-{
- unsigned int *depth = data;
-
- if (*depth == 0)
- return 1;
- (*depth)--;
- oprofile_add_trace(address);
- return 0;
-}
+#include <asm/unwind.h>
static void s390_backtrace(struct pt_regs *regs, unsigned int depth)
{
- if (user_mode(regs))
- return;
- dump_trace(__s390_backtrace, &depth, NULL, regs->gprs[15]);
+ struct unwind_state state;
+
+ unwind_for_each_frame(&state, current, regs, 0) {
+ if (depth-- == 0)
+ break;
+ oprofile_add_trace(state.ip);
+ }
}
int __init oprofile_arch_init(struct oprofile_operations *ops)
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 22d0871..748626a 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -3,5 +3,5 @@
# Makefile for the s390 PCI subsystem.
#
-obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_sysfs.o \
+obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \
pci_event.o pci_debug.o pci_insn.o pci_mmio.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 9f6f392..c7fea9b 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -24,11 +24,9 @@
#include <linux/err.h>
#include <linux/export.h>
#include <linux/delay.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
#include <linux/seq_file.h>
+#include <linux/jump_label.h>
#include <linux/pci.h>
-#include <linux/msi.h>
#include <asm/isc.h>
#include <asm/airq.h>
@@ -37,30 +35,13 @@
#include <asm/pci_clp.h>
#include <asm/pci_dma.h>
-#define DEBUG /* enable pr_debug */
-
-#define SIC_IRQ_MODE_ALL 0
-#define SIC_IRQ_MODE_SINGLE 1
-
-#define ZPCI_NR_DMA_SPACES 1
-#define ZPCI_NR_DEVICES CONFIG_PCI_NR_FUNCTIONS
-
/* list of all detected zpci devices */
static LIST_HEAD(zpci_list);
static DEFINE_SPINLOCK(zpci_list_lock);
-static struct irq_chip zpci_irq_chip = {
- .name = "zPCI",
- .irq_unmask = pci_msi_unmask_irq,
- .irq_mask = pci_msi_mask_irq,
-};
-
static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
static DEFINE_SPINLOCK(zpci_domain_lock);
-static struct airq_iv *zpci_aisb_iv;
-static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES];
-
#define ZPCI_IOMAP_ENTRIES \
min(((unsigned long) ZPCI_NR_DEVICES * PCI_BAR_COUNT / 2), \
ZPCI_IOMAP_MAX_ENTRIES)
@@ -70,6 +51,8 @@
struct zpci_iomap_entry *zpci_iomap_start;
EXPORT_SYMBOL_GPL(zpci_iomap_start);
+DEFINE_STATIC_KEY_FALSE(have_mio);
+
static struct kmem_cache *zdev_fmb_cache;
struct zpci_dev *get_zdev_by_fid(u32 fid)
@@ -123,39 +106,6 @@
}
EXPORT_SYMBOL_GPL(pci_proc_domain);
-/* Modify PCI: Register adapter interruptions */
-static int zpci_set_airq(struct zpci_dev *zdev)
-{
- u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
- struct zpci_fib fib = {0};
- u8 status;
-
- fib.isc = PCI_ISC;
- fib.sum = 1; /* enable summary notifications */
- fib.noi = airq_iv_end(zdev->aibv);
- fib.aibv = (unsigned long) zdev->aibv->vector;
- fib.aibvo = 0; /* each zdev has its own interrupt vector */
- fib.aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8;
- fib.aisbo = zdev->aisb & 63;
-
- return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
-}
-
-/* Modify PCI: Unregister adapter interruptions */
-static int zpci_clear_airq(struct zpci_dev *zdev)
-{
- u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
- struct zpci_fib fib = {0};
- u8 cc, status;
-
- cc = zpci_mod_fc(req, &fib, &status);
- if (cc == 3 || (cc == 1 && status == 24))
- /* Function already gone or IRQs already deregistered. */
- cc = 0;
-
- return cc ? -EIO : 0;
-}
-
/* Modify PCI: Register I/O address translation parameters */
int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
u64 base, u64 limit, u64 iota)
@@ -241,7 +191,7 @@
u64 data;
int rc;
- rc = zpci_load(&data, req, offset);
+ rc = __zpci_load(&data, req, offset);
if (!rc) {
data = le64_to_cpu((__force __le64) data);
data >>= (8 - len) * 8;
@@ -259,7 +209,7 @@
data <<= (8 - len) * 8;
data = (__force u64) cpu_to_le64(data);
- rc = zpci_store(data, req, offset);
+ rc = __zpci_store(data, req, offset);
return rc;
}
@@ -276,18 +226,48 @@
zpci_memcpy_toio(to, from, count);
}
+void __iomem *ioremap(unsigned long ioaddr, unsigned long size)
+{
+ struct vm_struct *area;
+ unsigned long offset;
+
+ if (!size)
+ return NULL;
+
+ if (!static_branch_unlikely(&have_mio))
+ return (void __iomem *) ioaddr;
+
+ offset = ioaddr & ~PAGE_MASK;
+ ioaddr &= PAGE_MASK;
+ size = PAGE_ALIGN(size + offset);
+ area = get_vm_area(size, VM_IOREMAP);
+ if (!area)
+ return NULL;
+
+ if (ioremap_page_range((unsigned long) area->addr,
+ (unsigned long) area->addr + size,
+ ioaddr, PAGE_KERNEL)) {
+ vunmap(area->addr);
+ return NULL;
+ }
+ return (void __iomem *) ((unsigned long) area->addr + offset);
+}
+EXPORT_SYMBOL(ioremap);
+
+void iounmap(volatile void __iomem *addr)
+{
+ if (static_branch_likely(&have_mio))
+ vunmap((__force void *) ((unsigned long) addr & PAGE_MASK));
+}
+EXPORT_SYMBOL(iounmap);
+
/* Create a virtual mapping cookie for a PCI BAR */
-void __iomem *pci_iomap_range(struct pci_dev *pdev,
- int bar,
- unsigned long offset,
- unsigned long max)
+static void __iomem *pci_iomap_range_fh(struct pci_dev *pdev, int bar,
+ unsigned long offset, unsigned long max)
{
struct zpci_dev *zdev = to_zpci(pdev);
int idx;
- if (!pci_resource_len(pdev, bar))
- return NULL;
-
idx = zdev->bars[bar].map_idx;
spin_lock(&zpci_iomap_lock);
/* Detect overrun */
@@ -298,6 +278,30 @@
return (void __iomem *) ZPCI_ADDR(idx) + offset;
}
+
+static void __iomem *pci_iomap_range_mio(struct pci_dev *pdev, int bar,
+ unsigned long offset,
+ unsigned long max)
+{
+ unsigned long barsize = pci_resource_len(pdev, bar);
+ struct zpci_dev *zdev = to_zpci(pdev);
+ void __iomem *iova;
+
+ iova = ioremap((unsigned long) zdev->bars[bar].mio_wt, barsize);
+ return iova ? iova + offset : iova;
+}
+
+void __iomem *pci_iomap_range(struct pci_dev *pdev, int bar,
+ unsigned long offset, unsigned long max)
+{
+ if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT)
+ return NULL;
+
+ if (static_branch_likely(&have_mio))
+ return pci_iomap_range_mio(pdev, bar, offset, max);
+ else
+ return pci_iomap_range_fh(pdev, bar, offset, max);
+}
EXPORT_SYMBOL(pci_iomap_range);
void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
@@ -306,7 +310,37 @@
}
EXPORT_SYMBOL(pci_iomap);
-void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+static void __iomem *pci_iomap_wc_range_mio(struct pci_dev *pdev, int bar,
+ unsigned long offset, unsigned long max)
+{
+ unsigned long barsize = pci_resource_len(pdev, bar);
+ struct zpci_dev *zdev = to_zpci(pdev);
+ void __iomem *iova;
+
+ iova = ioremap((unsigned long) zdev->bars[bar].mio_wb, barsize);
+ return iova ? iova + offset : iova;
+}
+
+void __iomem *pci_iomap_wc_range(struct pci_dev *pdev, int bar,
+ unsigned long offset, unsigned long max)
+{
+ if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT)
+ return NULL;
+
+ if (static_branch_likely(&have_mio))
+ return pci_iomap_wc_range_mio(pdev, bar, offset, max);
+ else
+ return pci_iomap_range_fh(pdev, bar, offset, max);
+}
+EXPORT_SYMBOL(pci_iomap_wc_range);
+
+void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+ return pci_iomap_wc_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL(pci_iomap_wc);
+
+static void pci_iounmap_fh(struct pci_dev *pdev, void __iomem *addr)
{
unsigned int idx = ZPCI_IDX(addr);
@@ -319,6 +353,19 @@
}
spin_unlock(&zpci_iomap_lock);
}
+
+static void pci_iounmap_mio(struct pci_dev *pdev, void __iomem *addr)
+{
+ iounmap(addr);
+}
+
+void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+{
+ if (static_branch_likely(&have_mio))
+ pci_iounmap_mio(pdev, addr);
+ else
+ pci_iounmap_fh(pdev, addr);
+}
EXPORT_SYMBOL(pci_iounmap);
static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
@@ -354,138 +401,18 @@
.write = pci_write,
};
-static void zpci_irq_handler(struct airq_struct *airq)
-{
- unsigned long si, ai;
- struct airq_iv *aibv;
- int irqs_on = 0;
-
- inc_irq_stat(IRQIO_PCI);
- for (si = 0;;) {
- /* Scan adapter summary indicator bit vector */
- si = airq_iv_scan(zpci_aisb_iv, si, airq_iv_end(zpci_aisb_iv));
- if (si == -1UL) {
- if (irqs_on++)
- /* End of second scan with interrupts on. */
- break;
- /* First scan complete, reenable interrupts. */
- if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC))
- break;
- si = 0;
- continue;
- }
-
- /* Scan the adapter interrupt vector for this device. */
- aibv = zpci_aibv[si];
- for (ai = 0;;) {
- ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
- if (ai == -1UL)
- break;
- inc_irq_stat(IRQIO_MSI);
- airq_iv_lock(aibv, ai);
- generic_handle_irq(airq_iv_get_data(aibv, ai));
- airq_iv_unlock(aibv, ai);
- }
- }
-}
-
-int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
-{
- struct zpci_dev *zdev = to_zpci(pdev);
- unsigned int hwirq, msi_vecs;
- unsigned long aisb;
- struct msi_desc *msi;
- struct msi_msg msg;
- int rc, irq;
-
- zdev->aisb = -1UL;
- if (type == PCI_CAP_ID_MSI && nvec > 1)
- return 1;
- msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
-
- /* Allocate adapter summary indicator bit */
- aisb = airq_iv_alloc_bit(zpci_aisb_iv);
- if (aisb == -1UL)
- return -EIO;
- zdev->aisb = aisb;
-
- /* Create adapter interrupt vector */
- zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
- if (!zdev->aibv)
- return -ENOMEM;
-
- /* Wire up shortcut pointer */
- zpci_aibv[aisb] = zdev->aibv;
-
- /* Request MSI interrupts */
- hwirq = 0;
- for_each_pci_msi_entry(msi, pdev) {
- if (hwirq >= msi_vecs)
- break;
- irq = irq_alloc_desc(0); /* Alloc irq on node 0 */
- if (irq < 0)
- return -ENOMEM;
- rc = irq_set_msi_desc(irq, msi);
- if (rc)
- return rc;
- irq_set_chip_and_handler(irq, &zpci_irq_chip,
- handle_simple_irq);
- msg.data = hwirq;
- msg.address_lo = zdev->msi_addr & 0xffffffff;
- msg.address_hi = zdev->msi_addr >> 32;
- pci_write_msi_msg(irq, &msg);
- airq_iv_set_data(zdev->aibv, hwirq, irq);
- hwirq++;
- }
-
- /* Enable adapter interrupts */
- rc = zpci_set_airq(zdev);
- if (rc)
- return rc;
-
- return (msi_vecs == nvec) ? 0 : msi_vecs;
-}
-
-void arch_teardown_msi_irqs(struct pci_dev *pdev)
-{
- struct zpci_dev *zdev = to_zpci(pdev);
- struct msi_desc *msi;
- int rc;
-
- /* Disable adapter interrupts */
- rc = zpci_clear_airq(zdev);
- if (rc)
- return;
-
- /* Release MSI interrupts */
- for_each_pci_msi_entry(msi, pdev) {
- if (!msi->irq)
- continue;
- if (msi->msi_attrib.is_msix)
- __pci_msix_desc_mask_irq(msi, 1);
- else
- __pci_msi_desc_mask_irq(msi, 1, 1);
- irq_set_msi_desc(msi->irq, NULL);
- irq_free_desc(msi->irq);
- msi->msg.address_lo = 0;
- msi->msg.address_hi = 0;
- msi->msg.data = 0;
- msi->irq = 0;
- }
-
- if (zdev->aisb != -1UL) {
- zpci_aibv[zdev->aisb] = NULL;
- airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
- zdev->aisb = -1UL;
- }
- if (zdev->aibv) {
- airq_iv_release(zdev->aibv);
- zdev->aibv = NULL;
- }
-}
+#ifdef CONFIG_PCI_IOV
+static struct resource iov_res = {
+ .name = "PCI IOV res",
+ .start = 0,
+ .end = -1,
+ .flags = IORESOURCE_MEM,
+};
+#endif
static void zpci_map_resources(struct pci_dev *pdev)
{
+ struct zpci_dev *zdev = to_zpci(pdev);
resource_size_t len;
int i;
@@ -493,61 +420,46 @@
len = pci_resource_len(pdev, i);
if (!len)
continue;
- pdev->resource[i].start =
- (resource_size_t __force) pci_iomap(pdev, i, 0);
+
+ if (zpci_use_mio(zdev))
+ pdev->resource[i].start =
+ (resource_size_t __force) zdev->bars[i].mio_wb;
+ else
+ pdev->resource[i].start = (resource_size_t __force)
+ pci_iomap_range_fh(pdev, i, 0, 0);
pdev->resource[i].end = pdev->resource[i].start + len - 1;
}
+
+#ifdef CONFIG_PCI_IOV
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+ int bar = i + PCI_IOV_RESOURCES;
+
+ len = pci_resource_len(pdev, bar);
+ if (!len)
+ continue;
+ pdev->resource[bar].parent = &iov_res;
+ }
+#endif
}
static void zpci_unmap_resources(struct pci_dev *pdev)
{
+ struct zpci_dev *zdev = to_zpci(pdev);
resource_size_t len;
int i;
+ if (zpci_use_mio(zdev))
+ return;
+
for (i = 0; i < PCI_BAR_COUNT; i++) {
len = pci_resource_len(pdev, i);
if (!len)
continue;
- pci_iounmap(pdev, (void __iomem __force *)
- pdev->resource[i].start);
+ pci_iounmap_fh(pdev, (void __iomem __force *)
+ pdev->resource[i].start);
}
}
-static struct airq_struct zpci_airq = {
- .handler = zpci_irq_handler,
- .isc = PCI_ISC,
-};
-
-static int __init zpci_irq_init(void)
-{
- int rc;
-
- rc = register_adapter_interrupt(&zpci_airq);
- if (rc)
- goto out;
- /* Set summary to 1 to be called every time for the ISC. */
- *zpci_airq.lsi_ptr = 1;
-
- rc = -ENOMEM;
- zpci_aisb_iv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
- if (!zpci_aisb_iv)
- goto out_airq;
-
- zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
- return 0;
-
-out_airq:
- unregister_adapter_interrupt(&zpci_airq);
-out:
- return rc;
-}
-
-static void zpci_irq_exit(void)
-{
- airq_iv_release(zpci_aisb_iv);
- unregister_adapter_interrupt(&zpci_airq);
-}
-
static int zpci_alloc_iomap(struct zpci_dev *zdev)
{
unsigned long entry;
@@ -617,7 +529,10 @@
if (zdev->bars[i].val & 4)
flags |= IORESOURCE_MEM_64;
- addr = ZPCI_ADDR(entry);
+ if (zpci_use_mio(zdev))
+ addr = (unsigned long) zdev->bars[i].mio_wb;
+ else
+ addr = ZPCI_ADDR(entry);
size = 1UL << zdev->bars[i].size;
res = __alloc_res(zdev, addr, size, flags);
@@ -651,6 +566,9 @@
struct resource *res;
int i;
+ if (pdev->is_physfn)
+ pdev->no_vf_scan = 1;
+
pdev->dev.groups = zpci_attr_groups;
pdev->dev.dma_ops = &s390_pci_dma_ops;
zpci_map_resources(pdev);
@@ -935,7 +853,9 @@
kmem_cache_destroy(zdev_fmb_cache);
}
-static unsigned int s390_pci_probe = 1;
+static unsigned int s390_pci_probe __initdata = 1;
+static unsigned int s390_pci_no_mio __initdata;
+unsigned int s390_pci_force_floating __initdata;
static unsigned int s390_pci_initialized;
char * __init pcibios_setup(char *str)
@@ -944,6 +864,14 @@
s390_pci_probe = 0;
return NULL;
}
+ if (!strcmp(str, "nomio")) {
+ s390_pci_no_mio = 1;
+ return NULL;
+ }
+ if (!strcmp(str, "force_floating")) {
+ s390_pci_force_floating = 1;
+ return NULL;
+ }
return str;
}
@@ -962,6 +890,11 @@
if (!test_facility(69) || !test_facility(71))
return 0;
+ if (test_facility(153) && !s390_pci_no_mio) {
+ static_branch_enable(&have_mio);
+ ctl_set_bit(2, 5);
+ }
+
rc = zpci_debug_init();
if (rc)
goto out;
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 19b2d2a..e585a62 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -66,7 +66,7 @@
/*
* Call Logical Processor with c=0, the give constant lps and an lpcb request.
*/
-static inline int clp_req(void *data, unsigned int lps)
+static __always_inline int clp_req(void *data, unsigned int lps)
{
struct { u8 _[CLP_BLK_SIZE]; } *req = data;
u64 ignored;
@@ -163,7 +163,14 @@
memcpy(zdev->util_str, response->util_str,
sizeof(zdev->util_str));
}
+ zdev->mio_capable = response->mio_addr_avail;
+ for (i = 0; i < PCI_BAR_COUNT; i++) {
+ if (!(response->mio.valid & (1 << (PCI_BAR_COUNT - i - 1))))
+ continue;
+ zdev->bars[i].mio_wb = (void __iomem *) response->mio.addr[i].wb;
+ zdev->bars[i].mio_wt = (void __iomem *) response->mio.addr[i].wt;
+ }
return 0;
}
@@ -279,11 +286,18 @@
int rc;
rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
- if (!rc)
- /* Success -> store enabled handle in zdev */
- zdev->fh = fh;
+ zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+ if (rc)
+ goto out;
- zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
+ zdev->fh = fh;
+ if (zpci_use_mio(zdev)) {
+ rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_MIO);
+ zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+ if (rc)
+ clp_disable_fh(zdev);
+ }
+out:
return rc;
}
@@ -296,11 +310,10 @@
return 0;
rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN);
+ zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
if (!rc)
- /* Success -> store disabled handle in zdev */
zdev->fh = fh;
- zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
return rc;
}
@@ -436,7 +449,7 @@
struct clp_state_data sd = {fid, ZPCI_FN_STATE_RESERVED};
int rc;
- rrb = clp_alloc_block(GFP_KERNEL);
+ rrb = clp_alloc_block(GFP_ATOMIC);
if (!rrb)
return -ENOMEM;
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 04388a2..3408c0d 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -74,7 +74,7 @@
int i;
for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++)
- seq_printf(m, "%26s:\t%lu\n", pci_sw_names[i],
+ seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i],
atomic64_read(counter));
}
@@ -172,21 +172,14 @@
void zpci_debug_init_device(struct zpci_dev *zdev, const char *name)
{
zdev->debugfs_dev = debugfs_create_dir(name, debugfs_root);
- if (IS_ERR(zdev->debugfs_dev))
- zdev->debugfs_dev = NULL;
- zdev->debugfs_perf = debugfs_create_file("statistics",
- S_IFREG | S_IRUGO | S_IWUSR,
- zdev->debugfs_dev, zdev,
- &debugfs_pci_perf_fops);
- if (IS_ERR(zdev->debugfs_perf))
- zdev->debugfs_perf = NULL;
+ debugfs_create_file("statistics", S_IFREG | S_IRUGO | S_IWUSR,
+ zdev->debugfs_dev, zdev, &debugfs_pci_perf_fops);
}
void zpci_debug_exit_device(struct zpci_dev *zdev)
{
- debugfs_remove(zdev->debugfs_perf);
- debugfs_remove(zdev->debugfs_dev);
+ debugfs_remove_recursive(zdev->debugfs_dev);
}
int __init zpci_debug_init(void)
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index d387a0f..64b1399 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -15,8 +15,6 @@
#include <linux/pci.h>
#include <asm/pci_dma.h>
-#define S390_MAPPING_ERROR (~(dma_addr_t) 0x0)
-
static struct kmem_cache *dma_region_table_cache;
static struct kmem_cache *dma_page_table_cache;
static int s390_iommu_strict;
@@ -301,7 +299,7 @@
out_error:
spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
- return S390_MAPPING_ERROR;
+ return DMA_MAPPING_ERROR;
}
static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size)
@@ -349,7 +347,7 @@
/* This rounds up number of pages based on size and offset */
nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
dma_addr = dma_alloc_address(dev, nr_pages);
- if (dma_addr == S390_MAPPING_ERROR) {
+ if (dma_addr == DMA_MAPPING_ERROR) {
ret = -ENOSPC;
goto out_err;
}
@@ -372,7 +370,7 @@
out_err:
zpci_err("map error:\n");
zpci_err_dma(ret, pa);
- return S390_MAPPING_ERROR;
+ return DMA_MAPPING_ERROR;
}
static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
@@ -406,7 +404,7 @@
dma_addr_t map;
size = PAGE_ALIGN(size);
- page = alloc_pages(flag, get_order(size));
+ page = alloc_pages(flag | __GFP_ZERO, get_order(size));
if (!page)
return NULL;
@@ -449,7 +447,7 @@
int ret;
dma_addr_base = dma_alloc_address(dev, nr_pages);
- if (dma_addr_base == S390_MAPPING_ERROR)
+ if (dma_addr_base == DMA_MAPPING_ERROR)
return -ENOMEM;
dma_addr = dma_addr_base;
@@ -496,7 +494,7 @@
for (i = 1; i < nr_elements; i++) {
s = sg_next(s);
- s->dma_address = S390_MAPPING_ERROR;
+ s->dma_address = DMA_MAPPING_ERROR;
s->dma_length = 0;
if (s->offset || (size & ~PAGE_MASK) ||
@@ -546,11 +544,6 @@
}
}
-static int s390_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
- return dma_addr == S390_MAPPING_ERROR;
-}
-
int zpci_dma_init_device(struct zpci_dev *zdev)
{
int rc;
@@ -675,16 +668,17 @@
.unmap_sg = s390_dma_unmap_sg,
.map_page = s390_dma_map_pages,
.unmap_page = s390_dma_unmap_pages,
- .mapping_error = s390_mapping_error,
+ .mmap = dma_common_mmap,
+ .get_sgtable = dma_common_get_sgtable,
/* dma_supported is unconditionally true without a callback */
};
EXPORT_SYMBOL_GPL(s390_pci_dma_ops);
static int __init s390_iommu_setup(char *str)
{
- if (!strncmp(str, "strict", 6))
+ if (!strcmp(str, "strict"))
s390_iommu_strict = 1;
- return 0;
+ return 1;
}
__setup("s390_iommu=", s390_iommu_setup);
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index f069929..02f9505 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -8,9 +8,11 @@
#include <linux/export.h>
#include <linux/errno.h>
#include <linux/delay.h>
+#include <linux/jump_label.h>
#include <asm/facility.h>
#include <asm/pci_insn.h>
#include <asm/pci_debug.h>
+#include <asm/pci_io.h>
#include <asm/processor.h>
#define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */
@@ -96,13 +98,15 @@
}
/* Set Interruption Controls */
-int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc)
+int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
{
if (!test_facility(72))
return -EIO;
- asm volatile (
- " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
- : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused));
+
+ asm volatile(
+ ".insn rsy,0xeb00000000d1,%[ctl],%[isc],%[iib]\n"
+ : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [iib] "Q" (*iib));
+
return 0;
}
@@ -140,7 +144,7 @@
return cc;
}
-int zpci_load(u64 *data, u64 req, u64 offset)
+int __zpci_load(u64 *data, u64 req, u64 offset)
{
u8 status;
int cc;
@@ -156,6 +160,52 @@
return (cc > 0) ? -EIO : cc;
}
+EXPORT_SYMBOL_GPL(__zpci_load);
+
+static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr,
+ unsigned long len)
+{
+ struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
+ u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+
+ return __zpci_load(data, req, ZPCI_OFFSET(addr));
+}
+
+static inline int __pcilg_mio(u64 *data, u64 ioaddr, u64 len, u8 *status)
+{
+ register u64 addr asm("2") = ioaddr;
+ register u64 r3 asm("3") = len;
+ int cc = -ENXIO;
+ u64 __data;
+
+ asm volatile (
+ " .insn rre,0xb9d60000,%[data],%[ioaddr]\n"
+ "0: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ "1:\n"
+ EX_TABLE(0b, 1b)
+ : [cc] "+d" (cc), [data] "=d" (__data), "+d" (r3)
+ : [ioaddr] "d" (addr)
+ : "cc");
+ *status = r3 >> 24 & 0xff;
+ *data = __data;
+ return cc;
+}
+
+int zpci_load(u64 *data, const volatile void __iomem *addr, unsigned long len)
+{
+ u8 status;
+ int cc;
+
+ if (!static_branch_unlikely(&have_mio))
+ return zpci_load_fh(data, addr, len);
+
+ cc = __pcilg_mio(data, (__force u64) addr, len, &status);
+ if (cc)
+ zpci_err_insn(cc, status, 0, (__force u64) addr);
+
+ return (cc > 0) ? -EIO : cc;
+}
EXPORT_SYMBOL_GPL(zpci_load);
/* PCI Store */
@@ -178,7 +228,7 @@
return cc;
}
-int zpci_store(u64 data, u64 req, u64 offset)
+int __zpci_store(u64 data, u64 req, u64 offset)
{
u8 status;
int cc;
@@ -194,6 +244,50 @@
return (cc > 0) ? -EIO : cc;
}
+EXPORT_SYMBOL_GPL(__zpci_store);
+
+static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data,
+ unsigned long len)
+{
+ struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
+ u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+
+ return __zpci_store(data, req, ZPCI_OFFSET(addr));
+}
+
+static inline int __pcistg_mio(u64 data, u64 ioaddr, u64 len, u8 *status)
+{
+ register u64 addr asm("2") = ioaddr;
+ register u64 r3 asm("3") = len;
+ int cc = -ENXIO;
+
+ asm volatile (
+ " .insn rre,0xb9d40000,%[data],%[ioaddr]\n"
+ "0: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ "1:\n"
+ EX_TABLE(0b, 1b)
+ : [cc] "+d" (cc), "+d" (r3)
+ : [data] "d" (data), [ioaddr] "d" (addr)
+ : "cc");
+ *status = r3 >> 24 & 0xff;
+ return cc;
+}
+
+int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len)
+{
+ u8 status;
+ int cc;
+
+ if (!static_branch_unlikely(&have_mio))
+ return zpci_store_fh(addr, data, len);
+
+ cc = __pcistg_mio(data, (__force u64) addr, len, &status);
+ if (cc)
+ zpci_err_insn(cc, status, 0, (__force u64) addr);
+
+ return (cc > 0) ? -EIO : cc;
+}
EXPORT_SYMBOL_GPL(zpci_store);
/* PCI Store Block */
@@ -214,7 +308,7 @@
return cc;
}
-int zpci_store_block(const u64 *data, u64 req, u64 offset)
+int __zpci_store_block(const u64 *data, u64 req, u64 offset)
{
u8 status;
int cc;
@@ -230,4 +324,63 @@
return (cc > 0) ? -EIO : cc;
}
-EXPORT_SYMBOL_GPL(zpci_store_block);
+EXPORT_SYMBOL_GPL(__zpci_store_block);
+
+static inline int zpci_write_block_fh(volatile void __iomem *dst,
+ const void *src, unsigned long len)
+{
+ struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(dst)];
+ u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+ u64 offset = ZPCI_OFFSET(dst);
+
+ return __zpci_store_block(src, req, offset);
+}
+
+static inline int __pcistb_mio(const u64 *data, u64 ioaddr, u64 len, u8 *status)
+{
+ int cc = -ENXIO;
+
+ asm volatile (
+ " .insn rsy,0xeb00000000d4,%[len],%[ioaddr],%[data]\n"
+ "0: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ "1:\n"
+ EX_TABLE(0b, 1b)
+ : [cc] "+d" (cc), [len] "+d" (len)
+ : [ioaddr] "d" (ioaddr), [data] "Q" (*data)
+ : "cc");
+ *status = len >> 24 & 0xff;
+ return cc;
+}
+
+int zpci_write_block(volatile void __iomem *dst,
+ const void *src, unsigned long len)
+{
+ u8 status;
+ int cc;
+
+ if (!static_branch_unlikely(&have_mio))
+ return zpci_write_block_fh(dst, src, len);
+
+ cc = __pcistb_mio(src, (__force u64) dst, len, &status);
+ if (cc)
+ zpci_err_insn(cc, status, 0, (__force u64) dst);
+
+ return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(zpci_write_block);
+
+static inline void __pciwb_mio(void)
+{
+ unsigned long unused = 0;
+
+ asm volatile (".insn rre,0xb9d50000,%[op],%[op]\n"
+ : [op] "+d" (unused));
+}
+
+void zpci_barrier(void)
+{
+ if (static_branch_likely(&have_mio))
+ __pciwb_mio();
+}
+EXPORT_SYMBOL_GPL(zpci_barrier);
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
new file mode 100644
index 0000000..fbe97ab
--- /dev/null
+++ b/arch/s390/pci/pci_irq.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/kernel_stat.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/smp.h>
+
+#include <asm/isc.h>
+#include <asm/airq.h>
+
+static enum {FLOATING, DIRECTED} irq_delivery;
+
+#define SIC_IRQ_MODE_ALL 0
+#define SIC_IRQ_MODE_SINGLE 1
+#define SIC_IRQ_MODE_DIRECT 4
+#define SIC_IRQ_MODE_D_ALL 16
+#define SIC_IRQ_MODE_D_SINGLE 17
+#define SIC_IRQ_MODE_SET_CPU 18
+
+/*
+ * summary bit vector
+ * FLOATING - summary bit per function
+ * DIRECTED - summary bit per cpu (only used in fallback path)
+ */
+static struct airq_iv *zpci_sbv;
+
+/*
+ * interrupt bit vectors
+ * FLOATING - interrupt bit vector per function
+ * DIRECTED - interrupt bit vector per cpu
+ */
+static struct airq_iv **zpci_ibv;
+
+/* Modify PCI: Register adapter interruptions */
+static int zpci_set_airq(struct zpci_dev *zdev)
+{
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
+ struct zpci_fib fib = {0};
+ u8 status;
+
+ fib.fmt0.isc = PCI_ISC;
+ fib.fmt0.sum = 1; /* enable summary notifications */
+ fib.fmt0.noi = airq_iv_end(zdev->aibv);
+ fib.fmt0.aibv = (unsigned long) zdev->aibv->vector;
+ fib.fmt0.aibvo = 0; /* each zdev has its own interrupt vector */
+ fib.fmt0.aisb = (unsigned long) zpci_sbv->vector + (zdev->aisb/64)*8;
+ fib.fmt0.aisbo = zdev->aisb & 63;
+
+ return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
+}
+
+/* Modify PCI: Unregister adapter interruptions */
+static int zpci_clear_airq(struct zpci_dev *zdev)
+{
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
+ struct zpci_fib fib = {0};
+ u8 cc, status;
+
+ cc = zpci_mod_fc(req, &fib, &status);
+ if (cc == 3 || (cc == 1 && status == 24))
+ /* Function already gone or IRQs already deregistered. */
+ cc = 0;
+
+ return cc ? -EIO : 0;
+}
+
+/* Modify PCI: Register CPU directed interruptions */
+static int zpci_set_directed_irq(struct zpci_dev *zdev)
+{
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT_D);
+ struct zpci_fib fib = {0};
+ u8 status;
+
+ fib.fmt = 1;
+ fib.fmt1.noi = zdev->msi_nr_irqs;
+ fib.fmt1.dibvo = zdev->msi_first_bit;
+
+ return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
+}
+
+/* Modify PCI: Unregister CPU directed interruptions */
+static int zpci_clear_directed_irq(struct zpci_dev *zdev)
+{
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT_D);
+ struct zpci_fib fib = {0};
+ u8 cc, status;
+
+ fib.fmt = 1;
+ cc = zpci_mod_fc(req, &fib, &status);
+ if (cc == 3 || (cc == 1 && status == 24))
+ /* Function already gone or IRQs already deregistered. */
+ cc = 0;
+
+ return cc ? -EIO : 0;
+}
+
+static int zpci_set_irq_affinity(struct irq_data *data, const struct cpumask *dest,
+ bool force)
+{
+ struct msi_desc *entry = irq_get_msi_desc(data->irq);
+ struct msi_msg msg = entry->msg;
+
+ msg.address_lo &= 0xff0000ff;
+ msg.address_lo |= (cpumask_first(dest) << 8);
+ pci_write_msi_msg(data->irq, &msg);
+
+ return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip zpci_irq_chip = {
+ .name = "PCI-MSI",
+ .irq_unmask = pci_msi_unmask_irq,
+ .irq_mask = pci_msi_mask_irq,
+ .irq_set_affinity = zpci_set_irq_affinity,
+};
+
+static void zpci_handle_cpu_local_irq(bool rescan)
+{
+ struct airq_iv *dibv = zpci_ibv[smp_processor_id()];
+ unsigned long bit;
+ int irqs_on = 0;
+
+ for (bit = 0;;) {
+ /* Scan the directed IRQ bit vector */
+ bit = airq_iv_scan(dibv, bit, airq_iv_end(dibv));
+ if (bit == -1UL) {
+ if (!rescan || irqs_on++)
+ /* End of second scan with interrupts on. */
+ break;
+ /* First scan complete, reenable interrupts. */
+ if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC))
+ break;
+ bit = 0;
+ continue;
+ }
+ inc_irq_stat(IRQIO_MSI);
+ generic_handle_irq(airq_iv_get_data(dibv, bit));
+ }
+}
+
+struct cpu_irq_data {
+ call_single_data_t csd;
+ atomic_t scheduled;
+};
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_irq_data, irq_data);
+
+static void zpci_handle_remote_irq(void *data)
+{
+ atomic_t *scheduled = data;
+
+ do {
+ zpci_handle_cpu_local_irq(false);
+ } while (atomic_dec_return(scheduled));
+}
+
+static void zpci_handle_fallback_irq(void)
+{
+ struct cpu_irq_data *cpu_data;
+ unsigned long cpu;
+ int irqs_on = 0;
+
+ for (cpu = 0;;) {
+ cpu = airq_iv_scan(zpci_sbv, cpu, airq_iv_end(zpci_sbv));
+ if (cpu == -1UL) {
+ if (irqs_on++)
+ /* End of second scan with interrupts on. */
+ break;
+ /* First scan complete, reenable interrupts. */
+ if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
+ break;
+ cpu = 0;
+ continue;
+ }
+ cpu_data = &per_cpu(irq_data, cpu);
+ if (atomic_inc_return(&cpu_data->scheduled) > 1)
+ continue;
+
+ cpu_data->csd.func = zpci_handle_remote_irq;
+ cpu_data->csd.info = &cpu_data->scheduled;
+ cpu_data->csd.flags = 0;
+ smp_call_function_single_async(cpu, &cpu_data->csd);
+ }
+}
+
+static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating)
+{
+ if (floating) {
+ inc_irq_stat(IRQIO_PCF);
+ zpci_handle_fallback_irq();
+ } else {
+ inc_irq_stat(IRQIO_PCD);
+ zpci_handle_cpu_local_irq(true);
+ }
+}
+
+static void zpci_floating_irq_handler(struct airq_struct *airq, bool floating)
+{
+ unsigned long si, ai;
+ struct airq_iv *aibv;
+ int irqs_on = 0;
+
+ inc_irq_stat(IRQIO_PCF);
+ for (si = 0;;) {
+ /* Scan adapter summary indicator bit vector */
+ si = airq_iv_scan(zpci_sbv, si, airq_iv_end(zpci_sbv));
+ if (si == -1UL) {
+ if (irqs_on++)
+ /* End of second scan with interrupts on. */
+ break;
+ /* First scan complete, reenable interrupts. */
+ if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
+ break;
+ si = 0;
+ continue;
+ }
+
+ /* Scan the adapter interrupt vector for this device. */
+ aibv = zpci_ibv[si];
+ for (ai = 0;;) {
+ ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
+ if (ai == -1UL)
+ break;
+ inc_irq_stat(IRQIO_MSI);
+ airq_iv_lock(aibv, ai);
+ generic_handle_irq(airq_iv_get_data(aibv, ai));
+ airq_iv_unlock(aibv, ai);
+ }
+ }
+}
+
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+ struct zpci_dev *zdev = to_zpci(pdev);
+ unsigned int hwirq, msi_vecs, cpu;
+ unsigned long bit;
+ struct msi_desc *msi;
+ struct msi_msg msg;
+ int rc, irq;
+
+ zdev->aisb = -1UL;
+ zdev->msi_first_bit = -1U;
+ if (type == PCI_CAP_ID_MSI && nvec > 1)
+ return 1;
+ msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
+
+ if (irq_delivery == DIRECTED) {
+ /* Allocate cpu vector bits */
+ bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
+ if (bit == -1UL)
+ return -EIO;
+ } else {
+ /* Allocate adapter summary indicator bit */
+ bit = airq_iv_alloc_bit(zpci_sbv);
+ if (bit == -1UL)
+ return -EIO;
+ zdev->aisb = bit;
+
+ /* Create adapter interrupt vector */
+ zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
+ if (!zdev->aibv)
+ return -ENOMEM;
+
+ /* Wire up shortcut pointer */
+ zpci_ibv[bit] = zdev->aibv;
+ /* Each function has its own interrupt vector */
+ bit = 0;
+ }
+
+ /* Request MSI interrupts */
+ hwirq = bit;
+ for_each_pci_msi_entry(msi, pdev) {
+ rc = -EIO;
+ if (hwirq - bit >= msi_vecs)
+ break;
+ irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, msi->affinity);
+ if (irq < 0)
+ return -ENOMEM;
+ rc = irq_set_msi_desc(irq, msi);
+ if (rc)
+ return rc;
+ irq_set_chip_and_handler(irq, &zpci_irq_chip,
+ handle_percpu_irq);
+ msg.data = hwirq - bit;
+ if (irq_delivery == DIRECTED) {
+ msg.address_lo = zdev->msi_addr & 0xff0000ff;
+ msg.address_lo |= msi->affinity ?
+ (cpumask_first(&msi->affinity->mask) << 8) : 0;
+ for_each_possible_cpu(cpu) {
+ airq_iv_set_data(zpci_ibv[cpu], hwirq, irq);
+ }
+ } else {
+ msg.address_lo = zdev->msi_addr & 0xffffffff;
+ airq_iv_set_data(zdev->aibv, hwirq, irq);
+ }
+ msg.address_hi = zdev->msi_addr >> 32;
+ pci_write_msi_msg(irq, &msg);
+ hwirq++;
+ }
+
+ zdev->msi_first_bit = bit;
+ zdev->msi_nr_irqs = msi_vecs;
+
+ if (irq_delivery == DIRECTED)
+ rc = zpci_set_directed_irq(zdev);
+ else
+ rc = zpci_set_airq(zdev);
+ if (rc)
+ return rc;
+
+ return (msi_vecs == nvec) ? 0 : msi_vecs;
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *pdev)
+{
+ struct zpci_dev *zdev = to_zpci(pdev);
+ struct msi_desc *msi;
+ int rc;
+
+ /* Disable interrupts */
+ if (irq_delivery == DIRECTED)
+ rc = zpci_clear_directed_irq(zdev);
+ else
+ rc = zpci_clear_airq(zdev);
+ if (rc)
+ return;
+
+ /* Release MSI interrupts */
+ for_each_pci_msi_entry(msi, pdev) {
+ if (!msi->irq)
+ continue;
+ if (msi->msi_attrib.is_msix)
+ __pci_msix_desc_mask_irq(msi, 1);
+ else
+ __pci_msi_desc_mask_irq(msi, 1, 1);
+ irq_set_msi_desc(msi->irq, NULL);
+ irq_free_desc(msi->irq);
+ msi->msg.address_lo = 0;
+ msi->msg.address_hi = 0;
+ msi->msg.data = 0;
+ msi->irq = 0;
+ }
+
+ if (zdev->aisb != -1UL) {
+ zpci_ibv[zdev->aisb] = NULL;
+ airq_iv_free_bit(zpci_sbv, zdev->aisb);
+ zdev->aisb = -1UL;
+ }
+ if (zdev->aibv) {
+ airq_iv_release(zdev->aibv);
+ zdev->aibv = NULL;
+ }
+
+ if ((irq_delivery == DIRECTED) && zdev->msi_first_bit != -1U)
+ airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs);
+}
+
+static struct airq_struct zpci_airq = {
+ .handler = zpci_floating_irq_handler,
+ .isc = PCI_ISC,
+};
+
+static void __init cpu_enable_directed_irq(void *unused)
+{
+ union zpci_sic_iib iib = {{0}};
+
+ iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector;
+
+ __zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
+ zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC);
+}
+
+static int __init zpci_directed_irq_init(void)
+{
+ union zpci_sic_iib iib = {{0}};
+ unsigned int cpu;
+
+ zpci_sbv = airq_iv_create(num_possible_cpus(), 0);
+ if (!zpci_sbv)
+ return -ENOMEM;
+
+ iib.diib.isc = PCI_ISC;
+ iib.diib.nr_cpus = num_possible_cpus();
+ iib.diib.disb_addr = (u64) zpci_sbv->vector;
+ __zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib);
+
+ zpci_ibv = kcalloc(num_possible_cpus(), sizeof(*zpci_ibv),
+ GFP_KERNEL);
+ if (!zpci_ibv)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ /*
+ * Per CPU IRQ vectors look the same but bit-allocation
+ * is only done on the first vector.
+ */
+ zpci_ibv[cpu] = airq_iv_create(cache_line_size() * BITS_PER_BYTE,
+ AIRQ_IV_DATA |
+ AIRQ_IV_CACHELINE |
+ (!cpu ? AIRQ_IV_ALLOC : 0));
+ if (!zpci_ibv[cpu])
+ return -ENOMEM;
+ }
+ on_each_cpu(cpu_enable_directed_irq, NULL, 1);
+
+ zpci_irq_chip.irq_set_affinity = zpci_set_irq_affinity;
+
+ return 0;
+}
+
+static int __init zpci_floating_irq_init(void)
+{
+ zpci_ibv = kcalloc(ZPCI_NR_DEVICES, sizeof(*zpci_ibv), GFP_KERNEL);
+ if (!zpci_ibv)
+ return -ENOMEM;
+
+ zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
+ if (!zpci_sbv)
+ goto out_free;
+
+ return 0;
+
+out_free:
+ kfree(zpci_ibv);
+ return -ENOMEM;
+}
+
+int __init zpci_irq_init(void)
+{
+ int rc;
+
+ irq_delivery = sclp.has_dirq ? DIRECTED : FLOATING;
+ if (s390_pci_force_floating)
+ irq_delivery = FLOATING;
+
+ if (irq_delivery == DIRECTED)
+ zpci_airq.handler = zpci_directed_irq_handler;
+
+ rc = register_adapter_interrupt(&zpci_airq);
+ if (rc)
+ goto out;
+ /* Set summary to 1 to be called every time for the ISC. */
+ *zpci_airq.lsi_ptr = 1;
+
+ switch (irq_delivery) {
+ case FLOATING:
+ rc = zpci_floating_irq_init();
+ break;
+ case DIRECTED:
+ rc = zpci_directed_irq_init();
+ break;
+ }
+
+ if (rc)
+ goto out_airq;
+
+ /*
+ * Enable floating IRQs (with suppression after one IRQ). When using
+ * directed IRQs this enables the fallback path.
+ */
+ zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC);
+
+ return 0;
+out_airq:
+ unregister_adapter_interrupt(&zpci_airq);
+out:
+ return rc;
+}
+
+void __init zpci_irq_exit(void)
+{
+ unsigned int cpu;
+
+ if (irq_delivery == DIRECTED) {
+ for_each_possible_cpu(cpu) {
+ airq_iv_release(zpci_ibv[cpu]);
+ }
+ }
+ kfree(zpci_ibv);
+ if (zpci_sbv)
+ airq_iv_release(zpci_sbv);
+ unregister_adapter_interrupt(&zpci_airq);
+}
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index 430c14b..a433ba0 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -37,6 +37,15 @@
zpci_attr(segment2, "0x%02x\n", pfip[2]);
zpci_attr(segment3, "0x%02x\n", pfip[3]);
+static ssize_t mio_enabled_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
+
+ return sprintf(buf, zpci_use_mio(zdev) ? "1\n" : "0\n");
+}
+static DEVICE_ATTR_RO(mio_enabled);
+
static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
@@ -115,6 +124,7 @@
&dev_attr_vfn.attr,
&dev_attr_uid.attr,
&dev_attr_recover.attr,
+ &dev_attr_mio_enabled.attr,
NULL,
};
static struct attribute_group zpci_attr_group = {
diff --git a/arch/s390/purgatory/.gitignore b/arch/s390/purgatory/.gitignore
index e9e66f1..04a0343 100644
--- a/arch/s390/purgatory/.gitignore
+++ b/arch/s390/purgatory/.gitignore
@@ -1,2 +1,3 @@
-kexec-purgatory.c
+purgatory
+purgatory.lds
purgatory.ro
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index ce6a3f7..bc0d7a0 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -4,34 +4,40 @@
purgatory-y := head.o purgatory.o string.o sha256.o mem.o
-targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
+targets += $(purgatory-y) purgatory.lds purgatory purgatory.ro
PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
-$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
+$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
$(call if_changed_rule,cc_o_c)
+CFLAGS_sha256.o := -D__DISABLE_EXPORTS
+
$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
$(call if_changed_rule,as_o_S)
$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
$(call if_changed_rule,cc_o_c)
-LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
-LDFLAGS_purgatory.ro += -z nodefaultlib
KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common
+KBUILD_CFLAGS += $(CLANG_FLAGS)
KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
-$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
+LDFLAGS_purgatory := -r --no-undefined -nostdlib -z nodefaultlib -T
+$(obj)/purgatory: $(obj)/purgatory.lds $(PURGATORY_OBJS) FORCE
$(call if_changed,ld)
-quiet_cmd_bin2c = BIN2C $@
- cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@
+OBJCOPYFLAGS_purgatory.ro := -O elf64-s390
+OBJCOPYFLAGS_purgatory.ro += --remove-section='*debug*'
+OBJCOPYFLAGS_purgatory.ro += --remove-section='.comment'
+OBJCOPYFLAGS_purgatory.ro += --remove-section='.note.*'
+$(obj)/purgatory.ro: $(obj)/purgatory FORCE
+ $(call if_changed,objcopy)
-$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
- $(call if_changed,bin2c)
+$(obj)/kexec-purgatory.o: $(obj)/kexec-purgatory.S $(obj)/purgatory.ro FORCE
+ $(call if_changed_rule,as_o_S)
obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += kexec-purgatory.o
diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S
index 2e3707b..5a10ce3 100644
--- a/arch/s390/purgatory/head.S
+++ b/arch/s390/purgatory/head.S
@@ -11,6 +11,7 @@
#include <asm/asm-offsets.h>
#include <asm/page.h>
#include <asm/sigp.h>
+#include <asm/ptrace.h>
/* The purgatory is the code running between two kernels. It's main purpose
* is to verify that the next kernel was not corrupted after load and to
@@ -88,8 +89,7 @@
.base_crash:
/* Setup stack */
- larl %r15,purgatory_end
- aghi %r15,-160
+ larl %r15,purgatory_end-STACK_FRAME_OVERHEAD
/* If the next kernel is KEXEC_TYPE_CRASH the purgatory is called
* directly with a flag passed in %r2 whether the purgatory shall do
diff --git a/arch/s390/purgatory/kexec-purgatory.S b/arch/s390/purgatory/kexec-purgatory.S
new file mode 100644
index 0000000..8293753
--- /dev/null
+++ b/arch/s390/purgatory/kexec-purgatory.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+ .section .rodata, "a"
+
+ .align 8
+kexec_purgatory:
+ .globl kexec_purgatory
+ .incbin "arch/s390/purgatory/purgatory.ro"
+.Lkexec_purgatroy_end:
+
+ .align 8
+kexec_purgatory_size:
+ .globl kexec_purgatory_size
+ .quad .Lkexec_purgatroy_end - kexec_purgatory
diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c
index 3528e6d..0a423bc 100644
--- a/arch/s390/purgatory/purgatory.c
+++ b/arch/s390/purgatory/purgatory.c
@@ -8,8 +8,8 @@
*/
#include <linux/kexec.h>
-#include <linux/sha256.h>
#include <linux/string.h>
+#include <crypto/sha.h>
#include <asm/purgatory.h>
int verify_sha256_digest(void)
diff --git a/arch/s390/purgatory/purgatory.lds.S b/arch/s390/purgatory/purgatory.lds.S
new file mode 100644
index 0000000..482eb4f
--- /dev/null
+++ b/arch/s390/purgatory/purgatory.lds.S
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm-generic/vmlinux.lds.h>
+
+OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
+OUTPUT_ARCH(s390:64-bit)
+
+ENTRY(purgatory_start)
+
+SECTIONS
+{
+ . = 0;
+ .head.text : {
+ _head = . ;
+ HEAD_TEXT
+ _ehead = . ;
+ }
+ .text : {
+ _text = .; /* Text */
+ *(.text)
+ *(.text.*)
+ _etext = . ;
+ }
+ .rodata : {
+ _rodata = . ;
+ *(.rodata) /* read-only data */
+ *(.rodata.*)
+ _erodata = . ;
+ }
+ .data : {
+ _data = . ;
+ *(.data)
+ *(.data.*)
+ _edata = . ;
+ }
+
+ . = ALIGN(256);
+ .bss : {
+ _bss = . ;
+ *(.bss)
+ *(.bss.*)
+ *(COMMON)
+ . = ALIGN(8); /* For convenience during zeroing */
+ _ebss = .;
+ }
+ _end = .;
+
+ /* Sections to be discarded */
+ /DISCARD/ : {
+ *(.eh_frame)
+ *(*__ksymtab*)
+ *(___kcrctab*)
+ }
+}
diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
index 9bba2c1..f4f4c2c 100644
--- a/arch/s390/scripts/Makefile.chkbss
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -1,23 +1,20 @@
# SPDX-License-Identifier: GPL-2.0
+chkbss-target ?= built-in.a
+$(obj)/$(chkbss-target): chkbss
+
+chkbss-files := $(addsuffix .chkbss, $(chkbss))
+clean-files += $(chkbss-files)
+
+PHONY += chkbss
+chkbss: $(addprefix $(obj)/, $(chkbss-files))
+
quiet_cmd_chkbss = CHKBSS $<
-define cmd_chkbss
- rm -f $@; \
- if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
+ cmd_chkbss = \
+ if ! $(OBJSIZE) --common $< | $(AWK) 'END { if ($$3) exit 1 }'; then \
echo "error: $< .bss section is not empty" >&2; exit 1; \
fi; \
touch $@;
-endef
-chkbss-target ?= $(obj)/built-in.a
-ifneq (,$(findstring /,$(chkbss)))
-chkbss-files := $(patsubst %, %.chkbss, $(chkbss))
-else
-chkbss-files := $(patsubst %, $(obj)/%.chkbss, $(chkbss))
-endif
-
-$(chkbss-target): $(chkbss-files)
-targets += $(notdir $(chkbss-files))
-
-%.o.chkbss: %.o
+$(obj)/%.o.chkbss: $(obj)/%.o
$(call cmd,chkbss)
diff --git a/arch/s390/tools/Makefile b/arch/s390/tools/Makefile
index 48cdac1..b5e35e8 100644
--- a/arch/s390/tools/Makefile
+++ b/arch/s390/tools/Makefile
@@ -6,7 +6,6 @@
kapi := arch/$(ARCH)/include/generated/asm
kapi-hdrs-y := $(kapi)/facility-defs.h $(kapi)/dis-defs.h
-targets += $(addprefix ../../../,$(kapi-hdrs-y))
PHONY += kapi
kapi: $(kapi-hdrs-y)
@@ -14,19 +13,12 @@
hostprogs-y += gen_facilities
hostprogs-y += gen_opcode_table
-HOSTCFLAGS_gen_facilities.o += -Wall $(LINUXINCLUDE)
-HOSTCFLAGS_gen_opcode_table.o += -Wall $(LINUXINCLUDE)
+HOSTCFLAGS_gen_facilities.o += $(LINUXINCLUDE)
-# Ensure output directory exists
-_dummy := $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)')
+filechk_facility-defs.h = $(obj)/gen_facilities
-define filechk_facility-defs.h
- $(obj)/gen_facilities
-endef
-
-define filechk_dis-defs.h
- ( $(obj)/gen_opcode_table < $(srctree)/arch/$(ARCH)/tools/opcodes.txt )
-endef
+filechk_dis-defs.h = \
+ $(obj)/gen_opcode_table < $(srctree)/arch/$(ARCH)/tools/opcodes.txt
$(kapi)/facility-defs.h: $(obj)/gen_facilities FORCE
$(call filechk,facility-defs.h)
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index 0c85aed..61ce5b5 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -58,6 +58,9 @@
#ifdef CONFIG_HAVE_MARCH_Z14_FEATURES
58, /* miscellaneous-instruction-extension 2 */
#endif
+#ifdef CONFIG_HAVE_MARCH_Z15_FEATURES
+ 61, /* miscellaneous-instruction-extension 3 */
+#endif
-1 /* END */
}
},
@@ -93,6 +96,9 @@
131, /* enhanced-SOP 2 and side-effect */
139, /* multiple epoch facility */
146, /* msa extension 8 */
+ 150, /* enhanced sort */
+ 151, /* deflate conversion */
+ 155, /* msa extension 9 */
-1 /* END */
}
},
@@ -106,6 +112,8 @@
.name = "FACILITIES_KVM_CPUMODEL",
.bits = (int[]){
+ 12, /* AP Query Configuration Information */
+ 15, /* AP Facilities Test */
156, /* etoken facility */
-1 /* END */
}
diff --git a/arch/s390/tools/opcodes.txt b/arch/s390/tools/opcodes.txt
index 1cbed82..46d8ed9 100644
--- a/arch/s390/tools/opcodes.txt
+++ b/arch/s390/tools/opcodes.txt
@@ -1,3 +1,5 @@
+0000 illegal E
+0002 brkpt E
0101 pr E
0102 upt E
0104 ptff E
@@ -257,6 +259,7 @@
b25a bsa RRE_RR
b25d clst RRE_RR
b25e srst RRE_RR
+b25f chsc RRE_R0
b263 cmpsc RRE_RR
b274 siga S_RD
b276 xsch S_00
@@ -277,6 +280,9 @@
b2a5 tre RRE_RR
b2a6 cu21 RRF_U0RR
b2a7 cu12 RRF_U0RR
+b2ad nqap RRE_RR
+b2ae dqap RRE_RR
+b2af pqap RRE_RR
b2b0 stfle S_RD
b2b1 stfl S_RD
b2b2 lpswe S_RD
@@ -290,6 +296,7 @@
b2e8 ppa RRF_U0RR
b2ec etnd RRE_R0
b2ed ecpga RRE_RR
+b2f0 iucv RRE_RR
b2f8 tend S_00
b2fa niai IE_UU
b2fc tabort S_RD
@@ -513,6 +520,9 @@
b92f kmc RRE_RR
b930 cgfr RRE_RR
b931 clgfr RRE_RR
+b938 sortl RRE_RR
+b939 dfltcc RRF_R0RR2
+b93a kdsa RRE_RR
b93c ppno RRE_RR
b93e kimd RRE_RR
b93f klmd RRE_RR
@@ -531,8 +541,16 @@
b95b cxlftr RRF_UUFR
b960 cgrt RRF_U0RR
b961 clgrt RRF_U0RR
+b964 nngrk RRF_R0RR2
+b965 ocgrk RRF_R0RR2
+b966 nogrk RRF_R0RR2
+b967 nxgrk RRF_R0RR2
b972 crt RRF_U0RR
b973 clrt RRF_U0RR
+b974 nnrk RRF_R0RR2
+b975 ocrk RRF_R0RR2
+b976 nork RRF_R0RR2
+b977 nxrk RRF_R0RR2
b980 ngr RRE_RR
b981 ogr RRE_RR
b982 xgr RRE_RR
@@ -559,12 +577,16 @@
b999 slbr RRE_RR
b99a epair RRE_R0
b99b esair RRE_R0
+b99c eqbs RRF_U0RR
b99d esea RRE_R0
b99e pti RRE_RR
b99f ssair RRE_R0
+b9a0 clp RRF_U0RR
b9a1 tpei RRE_RR
b9a2 ptf RRE_R0
+b9a4 uvc RRF_URR
b9aa lptea RRF_RURR2
+b9ab essa RRF_U0RR
b9ac irbm RRE_RR
b9ae rrbm RRE_RR
b9af pfmf RRE_RR
@@ -575,6 +597,7 @@
b9bd trtre RRF_U0RR
b9be srstu RRE_RR
b9bf trte RRF_U0RR
+b9c0 selhhhr RRF_RURR
b9c8 ahhhr RRF_R0RR2
b9c9 shhhr RRF_R0RR2
b9ca alhhhr RRF_R0RR2
@@ -584,6 +607,9 @@
b9d0 pcistg RRE_RR
b9d2 pcilg RRE_RR
b9d3 rpcit RRE_RR
+b9d4 pcistgi RRE_RR
+b9d5 pciwb RRE_00
+b9d6 pcilgi RRE_RR
b9d8 ahhlr RRF_R0RR2
b9d9 shhlr RRF_R0RR2
b9da alhhlr RRF_R0RR2
@@ -591,9 +617,11 @@
b9dd chlr RRE_RR
b9df clhlr RRE_RR
b9e0 locfhr RRF_U0RR
-b9e1 popcnt RRE_RR
+b9e1 popcnt RRF_U0RR
b9e2 locgr RRF_U0RR
+b9e3 selgr RRF_RURR
b9e4 ngrk RRF_R0RR2
+b9e5 ncgrk RRF_R0RR2
b9e6 ogrk RRF_R0RR2
b9e7 xgrk RRF_R0RR2
b9e8 agrk RRF_R0RR2
@@ -602,8 +630,10 @@
b9eb slgrk RRF_R0RR2
b9ec mgrk RRF_R0RR2
b9ed msgrkc RRF_R0RR2
+b9f0 selr RRF_RURR
b9f2 locr RRF_U0RR
b9f4 nrk RRF_R0RR2
+b9f5 ncrk RRF_R0RR2
b9f6 ork RRF_R0RR2
b9f7 xrk RRF_R0RR2
b9f8 ark RRF_R0RR2
@@ -812,6 +842,7 @@
e500 lasp SSE_RDRD
e501 tprot SSE_RDRD
e502 strag SSE_RDRD
+e50a mvcrl SSE_RDRD
e50e mvcsk SSE_RDRD
e50f mvcdk SSE_RDRD
e544 mvhhi SIL_RDI
@@ -825,6 +856,18 @@
e55d clfhsi SIL_RDU
e560 tbegin SIL_RDU
e561 tbeginc SIL_RDU
+e601 vlebrh VRX_VRRDU
+e602 vlebrg VRX_VRRDU
+e603 vlebrf VRX_VRRDU
+e604 vllebrz VRX_VRRDU
+e605 vlbrrep VRX_VRRDU
+e606 vlbr VRX_VRRDU
+e607 vler VRX_VRRDU
+e609 vstebrh VRX_VRRDU
+e60a vstebrg VRX_VRRDU
+e60b vstebrf VRX_VRRDU
+e60e vstbr VRX_VRRDU
+e60f vster VRX_VRRDU
e634 vpkz VSI_URDV
e635 vlrl VSI_URDV
e637 vlrlr VRS_RRDV
@@ -832,8 +875,8 @@
e63d vstrl VSI_URDV
e63f vstrlr VRS_RRDV
e649 vlip VRI_V0UU2
-e650 vcvb VRR_RV0U
-e652 vcvbg VRR_RV0U
+e650 vcvb VRR_RV0UU
+e652 vcvbg VRR_RV0UU
e658 vcvd VRI_VR0UU
e659 vsrp VRI_VVUUU2
e65a vcvdg VRI_VR0UU
@@ -853,13 +896,13 @@
e703 vlef VRX_VRRDU
e704 vllez VRX_VRRDU
e705 vlrep VRX_VRRDU
-e706 vl VRX_VRRD
+e706 vl VRX_VRRDU
e707 vlbb VRX_VRRDU
e708 vsteb VRX_VRRDU
e709 vsteh VRX_VRRDU
e70a vsteg VRX_VRRDU
e70b vstef VRX_VRRDU
-e70e vst VRX_VRRD
+e70e vst VRX_VRRDU
e712 vgeg VRV_VVXRDU
e713 vgef VRV_VVXRDU
e71a vsceg VRV_VVXRDU
@@ -869,11 +912,11 @@
e727 lcbb RXE_RRRDU
e730 vesl VRS_VVRDU
e733 verll VRS_VVRDU
-e736 vlm VRS_VVRD
+e736 vlm VRS_VVRDU
e737 vll VRS_VRRD
e738 vesrl VRS_VVRDU
e73a vesra VRS_VVRDU
-e73e vstm VRS_VVRD
+e73e vstm VRS_VVRDU
e73f vstl VRS_VRRD
e740 vleib VRI_V0IU
e741 vleih VRI_V0IU
@@ -922,7 +965,10 @@
e782 vfae VRR_VVV0U0U
e784 vpdi VRR_VVV0U
e785 vbperm VRR_VVV
+e786 vsld VRI_VVV0U
+e787 vsrd VRI_VVV0U
e78a vstrc VRR_VVVUU0V
+e78b vstrs VRR_VVVUU0V
e78c vperm VRR_VVV0V
e78d vsel VRR_VVV0V
e78e vfms VRR_VVVU0UV
@@ -1039,6 +1085,7 @@
eb7e algsi SIY_IRD
eb80 icmh RSY_RURD
eb81 icmy RSY_RURD
+eb8a sqbs RSY_RDRU
eb8e mvclu RSY_RRRD
eb8f clclu RSY_RRRD
eb90 stmy RSY_RRRD
@@ -1049,6 +1096,7 @@
ebc0 tp RSL_R0RD
ebd0 pcistb RSY_RRRD
ebd1 sic RSY_RRRD
+ebd4 pcistbi RSY_RRRD
ebdc srak RSY_RRRD
ebdd slak RSY_RRRD
ebde srlk RSY_RRRD