aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/arch/powerpc/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kernel')
-rw-r--r--arch/powerpc/kernel/85xx_entry_mapping.S (renamed from arch/powerpc/kernel/fsl_booke_entry_mapping.S)0
-rw-r--r--arch/powerpc/kernel/Makefile80
-rw-r--r--arch/powerpc/kernel/asm-offsets.c65
-rw-r--r--arch/powerpc/kernel/audit.c3
-rw-r--r--arch/powerpc/kernel/audit_32.h7
-rw-r--r--arch/powerpc/kernel/btext.c364
-rw-r--r--arch/powerpc/kernel/cacheinfo.c2
-rw-r--r--arch/powerpc/kernel/compat_audit.c2
-rw-r--r--arch/powerpc/kernel/cpu_setup_6xx.S50
-rw-r--r--arch/powerpc/kernel/cpu_setup_e500.S (renamed from arch/powerpc/kernel/cpu_setup_fsl_booke.S)14
-rw-r--r--arch/powerpc/kernel/cpu_setup_power.c10
-rw-r--r--arch/powerpc/kernel/cpu_specs.h25
-rw-r--r--arch/powerpc/kernel/cpu_specs_44x.h304
-rw-r--r--arch/powerpc/kernel/cpu_specs_47x.h74
-rw-r--r--arch/powerpc/kernel/cpu_specs_85xx.h57
-rw-r--r--arch/powerpc/kernel/cpu_specs_8xx.h23
-rw-r--r--arch/powerpc/kernel/cpu_specs_book3s_32.h605
-rw-r--r--arch/powerpc/kernel/cpu_specs_book3s_64.h530
-rw-r--r--arch/powerpc/kernel/cpu_specs_e500mc.h76
-rw-r--r--arch/powerpc/kernel/cputable.c1995
-rw-r--r--arch/powerpc/kernel/crash_dump.c14
-rw-r--r--arch/powerpc/kernel/dawr.c1
-rw-r--r--arch/powerpc/kernel/dbell.c2
-rw-r--r--arch/powerpc/kernel/dexcr.c124
-rw-r--r--arch/powerpc/kernel/dma-iommu.c8
-rw-r--r--arch/powerpc/kernel/dma-mask.c1
-rw-r--r--arch/powerpc/kernel/dt_cpu_ftrs.c28
-rw-r--r--arch/powerpc/kernel/eeh.c251
-rw-r--r--arch/powerpc/kernel/eeh_driver.c73
-rw-r--r--arch/powerpc/kernel/eeh_pe.c26
-rw-r--r--arch/powerpc/kernel/entry_32.S199
-rw-r--r--arch/powerpc/kernel/epapr_hcalls.S8
-rw-r--r--arch/powerpc/kernel/epapr_paravirt.c2
-rw-r--r--arch/powerpc/kernel/exceptions-64e.S161
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S467
-rw-r--r--arch/powerpc/kernel/fadump.c630
-rw-r--r--arch/powerpc/kernel/firmware.c2
-rw-r--r--arch/powerpc/kernel/fpu.S15
-rw-r--r--arch/powerpc/kernel/head_32.h16
-rw-r--r--arch/powerpc/kernel/head_40x.S718
-rw-r--r--arch/powerpc/kernel/head_44x.S47
-rw-r--r--arch/powerpc/kernel/head_64.S247
-rw-r--r--arch/powerpc/kernel/head_85xx.S (renamed from arch/powerpc/kernel/head_fsl_booke.S)107
-rw-r--r--arch/powerpc/kernel/head_8xx.S97
-rw-r--r--arch/powerpc/kernel/head_book3s_32.S209
-rw-r--r--arch/powerpc/kernel/head_booke.h16
-rw-r--r--arch/powerpc/kernel/hw_breakpoint.c381
-rw-r--r--arch/powerpc/kernel/hw_breakpoint_constraints.c7
-rw-r--r--arch/powerpc/kernel/idle.c18
-rw-r--r--arch/powerpc/kernel/idle_64e.S (renamed from arch/powerpc/kernel/idle_book3e.S)10
-rw-r--r--arch/powerpc/kernel/idle_85xx.S (renamed from arch/powerpc/kernel/idle_e500.S)0
-rw-r--r--arch/powerpc/kernel/ima_arch.c8
-rw-r--r--arch/powerpc/kernel/interrupt.c223
-rw-r--r--arch/powerpc/kernel/interrupt_64.S251
-rw-r--r--arch/powerpc/kernel/io-workarounds.c197
-rw-r--r--arch/powerpc/kernel/io.c70
-rw-r--r--arch/powerpc/kernel/iommu.c306
-rw-r--r--arch/powerpc/kernel/irq.c561
-rw-r--r--arch/powerpc/kernel/irq_64.c522
-rw-r--r--arch/powerpc/kernel/isa-bridge.c171
-rw-r--r--arch/powerpc/kernel/jump_label.c2
-rw-r--r--arch/powerpc/kernel/kgdb.c25
-rw-r--r--arch/powerpc/kernel/kprobes-ftrace.c3
-rw-r--r--arch/powerpc/kernel/kprobes.c128
-rw-r--r--arch/powerpc/kernel/kvm.c16
-rw-r--r--arch/powerpc/kernel/legacy_serial.c90
-rw-r--r--arch/powerpc/kernel/mce.c12
-rw-r--r--arch/powerpc/kernel/misc.S2
-rw-r--r--arch/powerpc/kernel/misc_32.S70
-rw-r--r--arch/powerpc/kernel/misc_64.S30
-rw-r--r--arch/powerpc/kernel/module.c40
-rw-r--r--arch/powerpc/kernel/module_32.c9
-rw-r--r--arch/powerpc/kernel/module_64.c511
-rw-r--r--arch/powerpc/kernel/nvram_64.c8
-rw-r--r--arch/powerpc/kernel/of_platform.c104
-rw-r--r--arch/powerpc/kernel/optprobes.c6
-rw-r--r--arch/powerpc/kernel/optprobes_head.S6
-rw-r--r--arch/powerpc/kernel/paca.c42
-rw-r--r--arch/powerpc/kernel/pci-common.c80
-rw-r--r--arch/powerpc/kernel/pci-hotplug.c38
-rw-r--r--arch/powerpc/kernel/pci_32.c48
-rw-r--r--arch/powerpc/kernel/pci_64.c6
-rw-r--r--arch/powerpc/kernel/pci_dn.c3
-rw-r--r--arch/powerpc/kernel/pmc.c2
-rw-r--r--arch/powerpc/kernel/ppc32.h60
-rw-r--r--arch/powerpc/kernel/ppc_save_regs.S61
-rw-r--r--arch/powerpc/kernel/proc_powerpc.c38
-rw-r--r--arch/powerpc/kernel/process.c344
-rw-r--r--arch/powerpc/kernel/prom.c160
-rw-r--r--arch/powerpc/kernel/prom_entry_64.S87
-rw-r--r--arch/powerpc/kernel/prom_init.c166
-rw-r--r--arch/powerpc/kernel/prom_init_check.sh33
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-decl.h6
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-tm.c12
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-view.c263
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-vsx.c2
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace.c7
-rw-r--r--arch/powerpc/kernel/reloc_64.S14
-rw-r--r--arch/powerpc/kernel/rethook.c73
-rw-r--r--arch/powerpc/kernel/rtas-proc.c26
-rw-r--r--arch/powerpc/kernel/rtas-rtc.c6
-rw-r--r--arch/powerpc/kernel/rtas.c1618
-rw-r--r--arch/powerpc/kernel/rtas_entry.S4
-rw-r--r--arch/powerpc/kernel/rtas_flash.c92
-rw-r--r--arch/powerpc/kernel/rtas_pci.c16
-rw-r--r--arch/powerpc/kernel/rtasd.c9
-rw-r--r--arch/powerpc/kernel/secure_boot.c13
-rw-r--r--arch/powerpc/kernel/security.c50
-rw-r--r--arch/powerpc/kernel/secvar-ops.c10
-rw-r--r--arch/powerpc/kernel/secvar-sysfs.c196
-rw-r--r--arch/powerpc/kernel/setup-common.c155
-rw-r--r--arch/powerpc/kernel/setup.h4
-rw-r--r--arch/powerpc/kernel/setup_32.c14
-rw-r--r--arch/powerpc/kernel/setup_64.c80
-rw-r--r--arch/powerpc/kernel/signal.c5
-rw-r--r--arch/powerpc/kernel/signal.h10
-rw-r--r--arch/powerpc/kernel/signal_32.c17
-rw-r--r--arch/powerpc/kernel/signal_64.c9
-rw-r--r--arch/powerpc/kernel/smp.c263
-rw-r--r--arch/powerpc/kernel/stacktrace.c43
-rw-r--r--arch/powerpc/kernel/static_call.c60
-rw-r--r--arch/powerpc/kernel/switch.S (renamed from arch/powerpc/kernel/entry_64.S)330
-rw-r--r--arch/powerpc/kernel/swsusp_32.S5
-rw-r--r--arch/powerpc/kernel/swsusp_64.c2
-rw-r--r--arch/powerpc/kernel/swsusp_85xx.S (renamed from arch/powerpc/kernel/swsusp_booke.S)0
-rw-r--r--arch/powerpc/kernel/swsusp_asm64.S16
-rw-r--r--arch/powerpc/kernel/sys_ppc32.c97
-rw-r--r--arch/powerpc/kernel/syscall.c189
-rw-r--r--arch/powerpc/kernel/syscalls.c60
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl60
-rw-r--r--arch/powerpc/kernel/sysfs.c25
-rw-r--r--arch/powerpc/kernel/systbl.c (renamed from arch/powerpc/kernel/systbl.S)32
-rw-r--r--arch/powerpc/kernel/systbl_chk.sh30
-rw-r--r--arch/powerpc/kernel/tau_6xx.c2
-rw-r--r--arch/powerpc/kernel/time.c248
-rw-r--r--arch/powerpc/kernel/tm.S10
-rw-r--r--arch/powerpc/kernel/trace/Makefile18
-rw-r--r--arch/powerpc/kernel/trace/ftrace.c1052
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64_pg.c832
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64_pg_entry.S (renamed from arch/powerpc/kernel/trace/ftrace_64_pg.S)67
-rw-r--r--arch/powerpc/kernel/trace/ftrace_entry.S471
-rw-r--r--arch/powerpc/kernel/trace/ftrace_low.S78
-rw-r--r--arch/powerpc/kernel/trace/ftrace_mprofile.S253
-rw-r--r--arch/powerpc/kernel/traps.c109
-rw-r--r--arch/powerpc/kernel/ucall.S2
-rw-r--r--arch/powerpc/kernel/udbg.c11
-rw-r--r--arch/powerpc/kernel/udbg_16550.c91
-rw-r--r--arch/powerpc/kernel/vdso.c203
-rw-r--r--arch/powerpc/kernel/vdso/Makefile95
-rw-r--r--arch/powerpc/kernel/vdso/cacheflush.S3
-rw-r--r--arch/powerpc/kernel/vdso/datapage.S4
-rw-r--r--arch/powerpc/kernel/vdso/getrandom.S56
-rw-r--r--arch/powerpc/kernel/vdso/gettimeofday.S20
-rw-r--r--arch/powerpc/kernel/vdso/vdso32.lds.S12
-rw-r--r--arch/powerpc/kernel/vdso/vdso64.lds.S12
-rw-r--r--arch/powerpc/kernel/vdso/vgetrandom-chacha.S365
-rw-r--r--arch/powerpc/kernel/vdso/vgetrandom.c14
-rw-r--r--arch/powerpc/kernel/vdso/vgettimeofday.c14
-rw-r--r--arch/powerpc/kernel/vdso32_wrapper.S2
-rw-r--r--arch/powerpc/kernel/vdso64_wrapper.S2
-rw-r--r--arch/powerpc/kernel/vector.S29
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S129
-rw-r--r--arch/powerpc/kernel/watchdog.c40
163 files changed, 11030 insertions, 9847 deletions
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/85xx_entry_mapping.S
index dedc17fac8f8..dedc17fac8f8 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/85xx_entry_mapping.S
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index c8cf924bf9c0..2f0a2e69c607 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -3,9 +3,6 @@
# Makefile for the linux kernel.
#
-ifdef CONFIG_PPC64
-CFLAGS_prom_init.o += $(NO_MINIMAL_TOC)
-endif
ifdef CONFIG_PPC32
CFLAGS_prom_init.o += -fPIC
CFLAGS_btext.o += -fPIC
@@ -54,18 +51,32 @@ CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING
CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
endif
-obj-y := cputable.o syscalls.o \
+KCSAN_SANITIZE_early_32.o := n
+KCSAN_SANITIZE_cputable.o := n
+KCSAN_SANITIZE_btext.o := n
+KCSAN_SANITIZE_paca.o := n
+KCSAN_SANITIZE_setup_64.o := n
+
+#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
+# Remove stack protector to avoid triggering unneeded stack canary
+# checks due to randomize_kstack_offset.
+CFLAGS_REMOVE_syscall.o = -fstack-protector -fstack-protector-strong
+CFLAGS_syscall.o += -fno-stack-protector
+#endif
+
+obj-y := cputable.o syscalls.o switch.o \
irq.o align.o signal_$(BITS).o pmc.o vdso.o \
process.o systbl.o idle.o \
signal.o sysfs.o cacheinfo.o time.o \
prom.o traps.o setup-common.o \
udbg.o misc.o io.o misc_$(BITS).o \
- of_platform.o prom_parse.o firmware.o \
+ prom_parse.o firmware.o \
hw_breakpoint_constraints.o interrupt.o \
- kdebugfs.o stacktrace.o
+ kdebugfs.o stacktrace.o syscall.o
obj-y += ptrace/
-obj-$(CONFIG_PPC64) += setup_64.o \
+obj-$(CONFIG_PPC64) += setup_64.o irq_64.o\
paca.o nvram_64.o note.o
+obj-$(CONFIG_PPC32) += sys_ppc32.o
obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o
obj-$(CONFIG_VDSO32) += vdso32_wrapper.o
obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o
@@ -73,8 +84,9 @@ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_DAWR) += dawr.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
+obj-$(CONFIG_PPC_BOOK3S_64) += dexcr.o
obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
-obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
+obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_64e.o
obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
obj-$(CONFIG_PPC64) += vdso64_wrapper.o
obj-$(CONFIG_ALTIVEC) += vecemu.o
@@ -93,31 +105,28 @@ obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_FA_DUMP) += fadump.o
obj-$(CONFIG_PRESERVE_FA_DUMP) += fadump.o
-ifdef CONFIG_PPC32
-obj-$(CONFIG_E500) += idle_e500.o
-endif
+obj-$(CONFIG_PPC_85xx) += idle_85xx.o
obj-$(CONFIG_PPC_BOOK3S_32) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
obj-$(CONFIG_TAU) += tau_6xx.o
obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o
-ifdef CONFIG_FSL_BOOKE
-obj-$(CONFIG_HIBERNATION) += swsusp_booke.o
+ifdef CONFIG_PPC_85xx
+obj-$(CONFIG_HIBERNATION) += swsusp_85xx.o
else
obj-$(CONFIG_HIBERNATION) += swsusp_$(BITS).o
endif
obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o
obj-$(CONFIG_MODULES) += module.o module_$(BITS).o
obj-$(CONFIG_44x) += cpu_setup_44x.o
-obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o
+obj-$(CONFIG_PPC_E500) += cpu_setup_e500.o
obj-$(CONFIG_PPC_DOORBELL) += dbell.o
obj-$(CONFIG_JUMP_LABEL) += jump_label.o
-extra-$(CONFIG_PPC64) := head_64.o
-extra-$(CONFIG_PPC_BOOK3S_32) := head_book3s_32.o
-extra-$(CONFIG_40x) := head_40x.o
-extra-$(CONFIG_44x) := head_44x.o
-extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o
-extra-$(CONFIG_PPC_8xx) := head_8xx.o
-extra-y += vmlinux.lds
+obj-$(CONFIG_PPC64) += head_64.o
+obj-$(CONFIG_PPC_BOOK3S_32) += head_book3s_32.o
+obj-$(CONFIG_44x) += head_44x.o
+obj-$(CONFIG_PPC_8xx) += head_8xx.o
+obj-$(CONFIG_PPC_85xx) += head_85xx.o
+always-$(KBUILD_BUILTIN) += vmlinux.lds
obj-$(CONFIG_RELOCATABLE) += reloc_$(BITS).o
@@ -130,6 +139,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_OPTPROBES) += optprobes.o optprobes_head.o
obj-$(CONFIG_KPROBES_ON_FTRACE) += kprobes-ftrace.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_RETHOOK) += rethook.o
obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o
obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o
obj-$(CONFIG_ARCH_HAS_DMA_SET_MASK) += dma-mask.o
@@ -142,8 +152,6 @@ obj-$(CONFIG_PCI_MSI) += msi.o
obj-$(CONFIG_AUDIT) += audit.o
obj64-$(CONFIG_AUDIT) += compat_audit.o
-obj-$(CONFIG_PPC_IO_WORKAROUNDS) += io-workarounds.o
-
obj-y += trace/
ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
@@ -152,12 +160,7 @@ endif
obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o
-obj-$(CONFIG_PPC64) += $(obj64-y)
-obj-$(CONFIG_PPC32) += $(obj32-y)
-
-ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE)(CONFIG_PPC_BOOK3S),)
obj-y += ppc_save_regs.o
-endif
obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
@@ -171,16 +174,16 @@ obj-$(CONFIG_PPC_SECVAR_SYSFS) += secvar-sysfs.o
# Disable GCOV, KCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_prom_init.o := n
KCOV_INSTRUMENT_prom_init.o := n
+KCSAN_SANITIZE_prom_init.o := n
UBSAN_SANITIZE_prom_init.o := n
GCOV_PROFILE_kprobes.o := n
KCOV_INSTRUMENT_kprobes.o := n
+KCSAN_SANITIZE_kprobes.o := n
UBSAN_SANITIZE_kprobes.o := n
GCOV_PROFILE_kprobes-ftrace.o := n
KCOV_INSTRUMENT_kprobes-ftrace.o := n
+KCSAN_SANITIZE_kprobes-ftrace.o := n
UBSAN_SANITIZE_kprobes-ftrace.o := n
-GCOV_PROFILE_syscall_64.o := n
-KCOV_INSTRUMENT_syscall_64.o := n
-UBSAN_SANITIZE_syscall_64.o := n
UBSAN_SANITIZE_vdso.o := n
# Necessary for booting with kcov enabled on book3e machines
@@ -191,12 +194,17 @@ KCOV_INSTRUMENT_paca.o := n
CFLAGS_setup_64.o += -fno-stack-protector
CFLAGS_paca.o += -fno-stack-protector
-extra-$(CONFIG_PPC_FPU) += fpu.o
-extra-$(CONFIG_ALTIVEC) += vector.o
-extra-$(CONFIG_PPC64) += entry_64.o
-extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o
+obj-$(CONFIG_PPC_FPU) += fpu.o
+obj-$(CONFIG_ALTIVEC) += vector.o
-extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check
+obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o
+obj64-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_entry_64.o
+ifdef KBUILD_BUILTIN
+always-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check
+endif
+
+obj-$(CONFIG_PPC64) += $(obj64-y)
+obj-$(CONFIG_PPC32) += $(obj32-y)
quiet_cmd_prom_init_check = PROMCHK $@
cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" $(obj)/prom_init.o; touch $@
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index eec536aef83a..b3048f6d3822 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -54,12 +54,12 @@
#endif
#ifdef CONFIG_PPC32
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
#include "head_booke.h"
#endif
#endif
-#if defined(CONFIG_PPC_FSL_BOOK3E)
+#if defined(CONFIG_PPC_E500)
#include "../mm/mmu_decl.h"
#endif
@@ -72,7 +72,7 @@
#endif
#define STACK_PT_REGS_OFFSET(sym, val) \
- DEFINE(sym, STACK_FRAME_OVERHEAD + offsetof(struct pt_regs, val))
+ DEFINE(sym, STACK_INT_FRAME_REGS + offsetof(struct pt_regs, val))
int main(void)
{
@@ -167,9 +167,8 @@ int main(void)
OFFSET(THREAD_CKVRSTATE, thread_struct, ckvr_state.vr);
OFFSET(THREAD_CKVRSAVE, thread_struct, ckvrsave);
OFFSET(THREAD_CKFPSTATE, thread_struct, ckfp_state.fpr);
- /* Local pt_regs on stack for Transactional Memory funcs. */
- DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD +
- sizeof(struct pt_regs) + 16);
+ /* Local pt_regs on stack in int frame form, plus 16 bytes for TM */
+ DEFINE(TM_FRAME_SIZE, STACK_INT_FRAME_SIZE + 16);
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
@@ -186,7 +185,9 @@ int main(void)
offsetof(struct task_struct, thread_info));
OFFSET(PACASAVEDMSR, paca_struct, saved_msr);
OFFSET(PACAR1, paca_struct, saved_r1);
+#ifndef CONFIG_PPC_KERNEL_PCREL
OFFSET(PACATOC, paca_struct, kernel_toc);
+#endif
OFFSET(PACAKBASE, paca_struct, kernelbase);
OFFSET(PACAKMSR, paca_struct, kernel_msr);
#ifdef CONFIG_PPC_BOOK3S_64
@@ -197,7 +198,7 @@ int main(void)
OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened);
OFFSET(PACA_FTRACE_ENABLED, paca_struct, ftrace_enabled);
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
OFFSET(PACAPGD, paca_struct, pgd);
OFFSET(PACA_KERNELPGD, paca_struct, kernel_pgd);
OFFSET(PACA_EXGEN, paca_struct, exgen);
@@ -213,7 +214,7 @@ int main(void)
OFFSET(TCD_ESEL_NEXT, tlb_core_data, esel_next);
OFFSET(TCD_ESEL_MAX, tlb_core_data, esel_max);
OFFSET(TCD_ESEL_FIRST, tlb_core_data, esel_first);
-#endif /* CONFIG_PPC_BOOK3E */
+#endif /* CONFIG_PPC_BOOK3E_64 */
#ifdef CONFIG_PPC_BOOK3S_64
OFFSET(PACA_EXGEN, paca_struct, exgen);
@@ -245,10 +246,8 @@ int main(void)
OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);
OFFSET(PACA_DSCR_DEFAULT, paca_struct, dscr_default);
-#ifdef CONFIG_PPC64
OFFSET(PACA_EXIT_SAVE_R1, paca_struct, exit_save_r1);
-#endif
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save);
#endif
OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso);
@@ -261,7 +260,7 @@ int main(void)
/* Interrupt register frame */
DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
- DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_WITH_PT_REGS);
+ DEFINE(SWITCH_FRAME_SIZE, STACK_SWITCH_FRAME_SIZE);
STACK_PT_REGS_OFFSET(GPR0, gpr[0]);
STACK_PT_REGS_OFFSET(GPR1, gpr[1]);
STACK_PT_REGS_OFFSET(GPR2, gpr[2]);
@@ -335,7 +334,6 @@ int main(void)
#endif /* ! CONFIG_PPC64 */
/* datapage offsets for use by vdso */
- OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
#ifdef CONFIG_PPC64
OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
@@ -379,7 +377,7 @@ int main(void)
OFFSET(VCPU_SPRG2, kvm_vcpu, arch.shregs.sprg2);
OFFSET(VCPU_SPRG3, kvm_vcpu, arch.shregs.sprg3);
#endif
-#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
OFFSET(VCPU_TB_RMENTRY, kvm_vcpu, arch.rm_entry);
OFFSET(VCPU_TB_RMINTR, kvm_vcpu, arch.rm_intr);
OFFSET(VCPU_TB_RMEXIT, kvm_vcpu, arch.rm_exit);
@@ -418,21 +416,18 @@ int main(void)
/* book3s */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- OFFSET(KVM_TLB_SETS, kvm, arch.tlb_sets);
OFFSET(KVM_SDR1, kvm, arch.sdr1);
OFFSET(KVM_HOST_LPID, kvm, arch.host_lpid);
OFFSET(KVM_HOST_LPCR, kvm, arch.host_lpcr);
OFFSET(KVM_HOST_SDR1, kvm, arch.host_sdr1);
OFFSET(KVM_ENABLED_HCALLS, kvm, arch.enabled_hcalls);
OFFSET(KVM_VRMA_SLB_V, kvm, arch.vrma_slb_v);
- OFFSET(KVM_RADIX, kvm, arch.radix);
OFFSET(KVM_SECURE_GUEST, kvm, arch.secure_guest);
OFFSET(VCPU_DSISR, kvm_vcpu, arch.shregs.dsisr);
OFFSET(VCPU_DAR, kvm_vcpu, arch.shregs.dar);
OFFSET(VCPU_VPA, kvm_vcpu, arch.vpa.pinned_addr);
OFFSET(VCPU_VPA_DIRTY, kvm_vcpu, arch.vpa.dirty);
OFFSET(VCPU_HEIR, kvm_vcpu, arch.emul_inst);
- OFFSET(VCPU_NESTED, kvm_vcpu, arch.nested);
OFFSET(VCPU_CPU, kvm_vcpu, cpu);
OFFSET(VCPU_THREAD_CPU, kvm_vcpu, arch.thread_cpu);
#endif
@@ -449,16 +444,12 @@ int main(void)
OFFSET(VCPU_DABRX, kvm_vcpu, arch.dabrx);
OFFSET(VCPU_DAWR0, kvm_vcpu, arch.dawr0);
OFFSET(VCPU_DAWRX0, kvm_vcpu, arch.dawrx0);
- OFFSET(VCPU_DAWR1, kvm_vcpu, arch.dawr1);
- OFFSET(VCPU_DAWRX1, kvm_vcpu, arch.dawrx1);
OFFSET(VCPU_CIABR, kvm_vcpu, arch.ciabr);
OFFSET(VCPU_HFLAGS, kvm_vcpu, arch.hflags);
OFFSET(VCPU_DEC_EXPIRES, kvm_vcpu, arch.dec_expires);
OFFSET(VCPU_PENDING_EXC, kvm_vcpu, arch.pending_exceptions);
OFFSET(VCPU_CEDED, kvm_vcpu, arch.ceded);
OFFSET(VCPU_PRODDED, kvm_vcpu, arch.prodded);
- OFFSET(VCPU_IRQ_PENDING, kvm_vcpu, arch.irq_pending);
- OFFSET(VCPU_DBELL_REQ, kvm_vcpu, arch.doorbell_request);
OFFSET(VCPU_MMCR, kvm_vcpu, arch.mmcr);
OFFSET(VCPU_MMCRA, kvm_vcpu, arch.mmcra);
OFFSET(VCPU_MMCRS, kvm_vcpu, arch.mmcrs);
@@ -486,8 +477,6 @@ int main(void)
OFFSET(VCPU_TCSCR, kvm_vcpu, arch.tcscr);
OFFSET(VCPU_ACOP, kvm_vcpu, arch.acop);
OFFSET(VCPU_WORT, kvm_vcpu, arch.wort);
- OFFSET(VCPU_TID, kvm_vcpu, arch.tid);
- OFFSET(VCPU_PSSCR, kvm_vcpu, arch.psscr);
OFFSET(VCPU_HFSCR, kvm_vcpu, arch.hfscr);
OFFSET(VCORE_ENTRY_EXIT, kvmppc_vcore, entry_exit_map);
OFFSET(VCORE_IN_GUEST, kvmppc_vcore, in_guest);
@@ -582,8 +571,6 @@ int main(void)
HSTATE_FIELD(HSTATE_HWTHREAD_STATE, hwthread_state);
HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
- HSTATE_FIELD(HSTATE_XIVE_TIMA_PHYS, xive_tima_phys);
- HSTATE_FIELD(HSTATE_XIVE_TIMA_VIRT, xive_tima_virt);
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
HSTATE_FIELD(HSTATE_PTID, ptid);
HSTATE_FIELD(HSTATE_FAKE_SUSPEND, fake_suspend);
@@ -594,9 +581,6 @@ int main(void)
HSTATE_FIELD(HSTATE_SDAR, host_mmcr[4]);
HSTATE_FIELD(HSTATE_MMCR2, host_mmcr[5]);
HSTATE_FIELD(HSTATE_SIER, host_mmcr[6]);
- HSTATE_FIELD(HSTATE_MMCR3, host_mmcr[7]);
- HSTATE_FIELD(HSTATE_SIER2, host_mmcr[8]);
- HSTATE_FIELD(HSTATE_SIER3, host_mmcr[9]);
HSTATE_FIELD(HSTATE_PMC1, host_pmc[0]);
HSTATE_FIELD(HSTATE_PMC2, host_pmc[1]);
HSTATE_FIELD(HSTATE_PMC3, host_pmc[2]);
@@ -609,7 +593,6 @@ int main(void)
HSTATE_FIELD(HSTATE_DABR, dabr);
HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
HSTATE_FIELD(HSTATE_SPLIT_MODE, kvm_split_mode);
- DEFINE(IPI_PRIORITY, IPI_PRIORITY);
OFFSET(KVM_SPLIT_RPR, kvm_split_mode, rpr);
OFFSET(KVM_SPLIT_PMMAR, kvm_split_mode, pmmar);
OFFSET(KVM_SPLIT_LDBAR, kvm_split_mode, ldbar);
@@ -651,7 +634,7 @@ int main(void)
DEFINE(PGD_T_LOG2, PGD_T_LOG2);
DEFINE(PTE_T_LOG2, PTE_T_LOG2);
#endif
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
OFFSET(TLBCAM_MAS0, tlbcam, MAS0);
OFFSET(TLBCAM_MAS1, tlbcam, MAS1);
@@ -672,17 +655,6 @@ int main(void)
OFFSET(VCPU_HOST_MAS6, kvm_vcpu, arch.host_mas6);
#endif
-#ifdef CONFIG_KVM_XICS
- DEFINE(VCPU_XIVE_SAVED_STATE, offsetof(struct kvm_vcpu,
- arch.xive_saved_state));
- DEFINE(VCPU_XIVE_CAM_WORD, offsetof(struct kvm_vcpu,
- arch.xive_cam_word));
- DEFINE(VCPU_XIVE_PUSHED, offsetof(struct kvm_vcpu, arch.xive_pushed));
- DEFINE(VCPU_XIVE_ESC_ON, offsetof(struct kvm_vcpu, arch.xive_esc_on));
- DEFINE(VCPU_XIVE_ESC_RADDR, offsetof(struct kvm_vcpu, arch.xive_esc_raddr));
- DEFINE(VCPU_XIVE_ESC_VADDR, offsetof(struct kvm_vcpu, arch.xive_esc_vaddr));
-#endif
-
#ifdef CONFIG_KVM_EXIT_TIMING
OFFSET(VCPU_TIMING_EXIT_TBU, kvm_vcpu, arch.timing_exit.tv32.tbu);
OFFSET(VCPU_TIMING_EXIT_TBL, kvm_vcpu, arch.timing_exit.tv32.tbl);
@@ -700,5 +672,16 @@ int main(void)
DEFINE(BPT_SIZE, BPT_SIZE);
#endif
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ DEFINE(FTRACE_OOL_STUB_SIZE, sizeof(struct ftrace_ool_stub));
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+ OFFSET(FTRACE_OPS_FUNC, ftrace_ops, func);
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ OFFSET(FTRACE_OPS_DIRECT_CALL, ftrace_ops, direct_call);
+#endif
+#endif
+
return 0;
}
diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c
index 1bcfca5fdf67..92298d6a3a37 100644
--- a/arch/powerpc/kernel/audit.c
+++ b/arch/powerpc/kernel/audit.c
@@ -4,6 +4,8 @@
#include <linux/audit.h>
#include <asm/unistd.h>
+#include "audit_32.h"
+
static unsigned dir_class[] = {
#include <asm-generic/audit_dir_write.h>
~0U
@@ -41,7 +43,6 @@ int audit_classify_arch(int arch)
int audit_classify_syscall(int abi, unsigned syscall)
{
#ifdef CONFIG_PPC64
- extern int ppc32_classify_syscall(unsigned);
if (abi == AUDIT_ARCH_PPC)
return ppc32_classify_syscall(syscall);
#endif
diff --git a/arch/powerpc/kernel/audit_32.h b/arch/powerpc/kernel/audit_32.h
new file mode 100644
index 000000000000..c6c79c3041ab
--- /dev/null
+++ b/arch/powerpc/kernel/audit_32.h
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __AUDIT_32_H__
+#define __AUDIT_32_H__
+
+extern int ppc32_classify_syscall(unsigned);
+
+#endif
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 8f69bb07e500..7f63f1cdc6c3 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -8,6 +8,7 @@
#include <linux/string.h>
#include <linux/init.h>
#include <linux/export.h>
+#include <linux/font.h>
#include <linux/memblock.h>
#include <linux/pgtable.h>
#include <linux/of.h>
@@ -41,10 +42,6 @@ static unsigned char *logicalDisplayBase __force_data;
unsigned long disp_BAT[2] __initdata = {0, 0};
-#define cmapsz (16*256)
-
-static unsigned char vga_font[cmapsz];
-
static int boot_text_mapped __force_data;
extern void rmci_on(void);
@@ -73,7 +70,7 @@ static inline void rmci_maybe_off(void)
* the display during identify_machine() and MMU_Init()
*
* The display is mapped to virtual address 0xD0000000, rather
- * than 1:1, because some some CHRP machines put the frame buffer
+ * than 1:1, because some CHRP machines put the frame buffer
* in the region starting at 0xC0000000 (PAGE_OFFSET).
* This mapping is temporary and will disappear as soon as the
* setup done by MMU_Init() is applied.
@@ -235,7 +232,7 @@ int __init btext_find_display(int allow_nonstdout)
return rc;
for_each_node_by_type(np, "display") {
- if (of_get_property(np, "linux,opened", NULL)) {
+ if (of_property_read_bool(np, "linux,opened")) {
printk("trying %pOF ...\n", np);
rc = btext_initialize(np);
printk("result: %d\n", rc);
@@ -407,7 +404,7 @@ static unsigned int expand_bits_16[4] = {
};
-static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
+static void draw_byte_32(const unsigned char *font, unsigned int *base, int rb)
{
int l, bits;
int fg = 0xFFFFFFFFUL;
@@ -428,7 +425,7 @@ static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
}
}
-static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
+static inline void draw_byte_16(const unsigned char *font, unsigned int *base, int rb)
{
int l, bits;
int fg = 0xFFFFFFFFUL;
@@ -446,7 +443,7 @@ static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
}
}
-static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+static inline void draw_byte_8(const unsigned char *font, unsigned int *base, int rb)
{
int l, bits;
int fg = 0x0F0F0F0FUL;
@@ -465,7 +462,8 @@ static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
static noinline void draw_byte(unsigned char c, long locX, long locY)
{
unsigned char *base = calc_base(locX << 3, locY << 4);
- unsigned char *font = &vga_font[((unsigned int)c) * 16];
+ unsigned int font_index = c * 16;
+ const unsigned char *font = font_sun_8x16.data + font_index;
int rb = dispDeviceRowBytes;
rmci_maybe_on();
@@ -583,349 +581,3 @@ void __init udbg_init_btext(void)
*/
udbg_putc = btext_drawchar;
}
-
-static unsigned char vga_font[cmapsz] = {
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x81, 0xa5, 0x81, 0x81, 0xbd,
-0x99, 0x81, 0x81, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xff,
-0xdb, 0xff, 0xff, 0xc3, 0xe7, 0xff, 0xff, 0x7e, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x6c, 0xfe, 0xfe, 0xfe, 0xfe, 0x7c, 0x38, 0x10,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x7c, 0xfe,
-0x7c, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18,
-0x3c, 0x3c, 0xe7, 0xe7, 0xe7, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x18, 0x3c, 0x7e, 0xff, 0xff, 0x7e, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c,
-0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
-0xff, 0xff, 0xe7, 0xc3, 0xc3, 0xe7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x42, 0x42, 0x66, 0x3c, 0x00,
-0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc3, 0x99, 0xbd,
-0xbd, 0x99, 0xc3, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x1e, 0x0e,
-0x1a, 0x32, 0x78, 0xcc, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x3c, 0x66, 0x66, 0x66, 0x66, 0x3c, 0x18, 0x7e, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x33, 0x3f, 0x30, 0x30, 0x30,
-0x30, 0x70, 0xf0, 0xe0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0x63,
-0x7f, 0x63, 0x63, 0x63, 0x63, 0x67, 0xe7, 0xe6, 0xc0, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x18, 0x18, 0xdb, 0x3c, 0xe7, 0x3c, 0xdb, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfe, 0xf8,
-0xf0, 0xe0, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x06, 0x0e,
-0x1e, 0x3e, 0xfe, 0x3e, 0x1e, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66,
-0x66, 0x00, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xdb,
-0xdb, 0xdb, 0x7b, 0x1b, 0x1b, 0x1b, 0x1b, 0x1b, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x7c, 0xc6, 0x60, 0x38, 0x6c, 0xc6, 0xc6, 0x6c, 0x38, 0x0c, 0xc6,
-0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0xfe, 0xfe, 0xfe, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c,
-0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x7e, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x18, 0x0c, 0xfe, 0x0c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x60, 0xfe, 0x60, 0x30, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0xc0,
-0xc0, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x24, 0x66, 0xff, 0x66, 0x24, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x38, 0x7c, 0x7c, 0xfe, 0xfe, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xfe, 0x7c, 0x7c,
-0x38, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x24, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6c,
-0x6c, 0xfe, 0x6c, 0x6c, 0x6c, 0xfe, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00,
-0x18, 0x18, 0x7c, 0xc6, 0xc2, 0xc0, 0x7c, 0x06, 0x06, 0x86, 0xc6, 0x7c,
-0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc2, 0xc6, 0x0c, 0x18,
-0x30, 0x60, 0xc6, 0x86, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c,
-0x6c, 0x38, 0x76, 0xdc, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x30, 0x30, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x30, 0x30, 0x30,
-0x30, 0x30, 0x18, 0x0c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x18,
-0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x3c, 0xff, 0x3c, 0x66, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e,
-0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x02, 0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xce, 0xde, 0xf6, 0xe6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x38, 0x78, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
-0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0x06, 0x06, 0x3c, 0x06, 0x06, 0x06, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x1c, 0x3c, 0x6c, 0xcc, 0xfe,
-0x0c, 0x0c, 0x0c, 0x1e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0,
-0xc0, 0xc0, 0xfc, 0x06, 0x06, 0x06, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x38, 0x60, 0xc0, 0xc0, 0xfc, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0x06, 0x06, 0x0c, 0x18,
-0x30, 0x30, 0x30, 0x30, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
-0xc6, 0xc6, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x06, 0x06, 0x0c, 0x78,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00,
-0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x18, 0x18, 0x00, 0x00, 0x00, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x06,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00,
-0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60,
-0x30, 0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0xc6, 0x0c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xde, 0xde,
-0xde, 0xdc, 0xc0, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38,
-0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x66, 0x66, 0x66, 0x66, 0xfc,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0xc2, 0xc0, 0xc0, 0xc0,
-0xc0, 0xc2, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x6c,
-0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x6c, 0xf8, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, 0x60, 0x62, 0x66, 0xfe,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68,
-0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66,
-0xc2, 0xc0, 0xc0, 0xde, 0xc6, 0xc6, 0x66, 0x3a, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x0c,
-0x0c, 0x0c, 0x0c, 0x0c, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xe6, 0x66, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0x66, 0xe6,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, 0x60, 0x60, 0x60, 0x60, 0x60,
-0x60, 0x62, 0x66, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xe7,
-0xff, 0xff, 0xdb, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, 0xc6,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66,
-0x66, 0x66, 0x7c, 0x60, 0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xd6, 0xde, 0x7c,
-0x0c, 0x0e, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x6c,
-0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
-0xc6, 0x60, 0x38, 0x0c, 0x06, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xff, 0xdb, 0x99, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3,
-0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x66,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x18,
-0x3c, 0x66, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3,
-0xc3, 0x66, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xff, 0xc3, 0x86, 0x0c, 0x18, 0x30, 0x60, 0xc1, 0xc3, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x30, 0x30, 0x30, 0x30, 0x30,
-0x30, 0x30, 0x30, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80,
-0xc0, 0xe0, 0x70, 0x38, 0x1c, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x3c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0x00,
-0x30, 0x30, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x78, 0x0c, 0x7c,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe0, 0x60,
-0x60, 0x78, 0x6c, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc0, 0xc0, 0xc0, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x0c, 0x0c, 0x3c, 0x6c, 0xcc,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xf0,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xcc, 0xcc,
-0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0xcc, 0x78, 0x00, 0x00, 0x00, 0xe0, 0x60,
-0x60, 0x6c, 0x76, 0x66, 0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x06, 0x00, 0x0e, 0x06, 0x06,
-0x06, 0x06, 0x06, 0x06, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0xe0, 0x60,
-0x60, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe6, 0xff, 0xdb,
-0xdb, 0xdb, 0xdb, 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x66, 0x66,
-0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x76, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0x0c, 0x1e, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x76, 0x66, 0x60, 0x60, 0x60, 0xf0,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0x60,
-0x38, 0x0c, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x30,
-0x30, 0xfc, 0x30, 0x30, 0x30, 0x30, 0x36, 0x1c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0xc3,
-0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0x3c, 0x66, 0xc3,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xfe, 0xcc, 0x18, 0x30, 0x60, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x0e, 0x18, 0x18, 0x18, 0x70, 0x18, 0x18, 0x18, 0x18, 0x0e,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x00, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0x18,
-0x18, 0x18, 0x0e, 0x18, 0x18, 0x18, 0x18, 0x70, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6,
-0xc6, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66,
-0xc2, 0xc0, 0xc0, 0xc0, 0xc2, 0x66, 0x3c, 0x0c, 0x06, 0x7c, 0x00, 0x00,
-0x00, 0x00, 0xcc, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x00, 0x7c, 0xc6, 0xfe,
-0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c,
-0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xcc, 0x00, 0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0x78, 0x0c, 0x7c,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38,
-0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x60, 0x60, 0x66, 0x3c, 0x0c, 0x06,
-0x3c, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xfe,
-0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00,
-0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x60, 0x30, 0x18, 0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x00, 0x00, 0x38, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, 0x66,
-0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x60, 0x30, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0xc6,
-0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, 0x00,
-0x38, 0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
-0x18, 0x30, 0x60, 0x00, 0xfe, 0x66, 0x60, 0x7c, 0x60, 0x60, 0x66, 0xfe,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6e, 0x3b, 0x1b,
-0x7e, 0xd8, 0xdc, 0x77, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3e, 0x6c,
-0xcc, 0xcc, 0xfe, 0xcc, 0xcc, 0xcc, 0xcc, 0xce, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x00, 0x7c, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18,
-0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x30, 0x78, 0xcc, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0xcc, 0xcc, 0xcc,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00,
-0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0x78, 0x00,
-0x00, 0xc6, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e,
-0xc3, 0xc0, 0xc0, 0xc0, 0xc3, 0x7e, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xe6, 0xfc,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0xff, 0x18,
-0xff, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66,
-0x7c, 0x62, 0x66, 0x6f, 0x66, 0x66, 0x66, 0xf3, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x0e, 0x1b, 0x18, 0x18, 0x18, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18,
-0xd8, 0x70, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0x78, 0x0c, 0x7c,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30,
-0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x18, 0x30, 0x60, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0xcc, 0xcc, 0xcc,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc,
-0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00,
-0x76, 0xdc, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x6c, 0x6c, 0x3e, 0x00, 0x7e, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c,
-0x38, 0x00, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x30, 0x30, 0x00, 0x30, 0x30, 0x60, 0xc0, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0,
-0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xfe, 0x06, 0x06, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, 0x60, 0xce, 0x9b, 0x06,
-0x0c, 0x1f, 0x00, 0x00, 0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30,
-0x66, 0xce, 0x96, 0x3e, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18,
-0x00, 0x18, 0x18, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x6c, 0xd8, 0x6c, 0x36, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd8, 0x6c, 0x36,
-0x6c, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x11, 0x44, 0x11, 0x44,
-0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44,
-0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa,
-0x55, 0xaa, 0x55, 0xaa, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77,
-0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x18, 0xf8,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36,
-0x36, 0xf6, 0x06, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x06, 0xf6,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0xf6, 0x06, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xfe, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0xf8, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x37,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x37, 0x30, 0x3f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xf7, 0x00, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xff, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x37, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36,
-0x36, 0xf7, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xff, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x3f,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x1f, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0xff, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x1f, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
-0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff,
-0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf0, 0xf0, 0xf0, 0xf0,
-0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0,
-0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
-0x0f, 0x0f, 0x0f, 0x0f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x76, 0xdc, 0xd8, 0xd8, 0xd8, 0xdc, 0x76, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x78, 0xcc, 0xcc, 0xcc, 0xd8, 0xcc, 0xc6, 0xc6, 0xc6, 0xcc,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0xc6, 0xc0, 0xc0, 0xc0,
-0xc0, 0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0xfe, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0xfe, 0xc6, 0x60, 0x30, 0x18, 0x30, 0x60, 0xc6, 0xfe,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xd8, 0xd8,
-0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x66, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xc0, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x18, 0x3c, 0x66, 0x66,
-0x66, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38,
-0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0x6c, 0x38, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x38, 0x6c, 0xc6, 0xc6, 0xc6, 0x6c, 0x6c, 0x6c, 0x6c, 0xee,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x30, 0x18, 0x0c, 0x3e, 0x66,
-0x66, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x7e, 0xdb, 0xdb, 0xdb, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x03, 0x06, 0x7e, 0xdb, 0xdb, 0xf3, 0x7e, 0x60, 0xc0,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x30, 0x60, 0x60, 0x7c, 0x60,
-0x60, 0x60, 0x30, 0x1c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c,
-0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, 0x18,
-0x18, 0x00, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30,
-0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x00, 0x7e,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0e, 0x1b, 0x1b, 0x1b, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x7e, 0x00, 0x18, 0x18, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x00,
-0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c,
-0x38, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0f, 0x0c, 0x0c,
-0x0c, 0x0c, 0x0c, 0xec, 0x6c, 0x6c, 0x3c, 0x1c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xd8, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0xd8, 0x30, 0x60, 0xc8, 0xf8, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00,
-};
-
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index f502337dd37d..0fcc463b02e2 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -735,7 +735,7 @@ static const struct sysfs_ops cache_index_ops = {
.show = cache_index_show,
};
-static struct kobj_type cache_index_type = {
+static const struct kobj_type cache_index_type = {
.release = cache_index_release,
.sysfs_ops = &cache_index_ops,
.default_groups = cache_index_default_groups,
diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c
index d92ffe4e5dc1..57b38c592b9f 100644
--- a/arch/powerpc/kernel/compat_audit.c
+++ b/arch/powerpc/kernel/compat_audit.c
@@ -3,6 +3,8 @@
#include <linux/audit_arch.h>
#include <asm/unistd.h>
+#include "audit_32.h"
+
unsigned ppc32_dir_class[] = {
#include <asm-generic/audit_dir_write.h>
~0U
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f8b5ff64b604..ab3ca74e6730 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -4,6 +4,8 @@
* Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
*/
+#include <linux/linkage.h>
+
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/cputable.h>
@@ -24,6 +26,15 @@ BEGIN_FTR_SECTION
bl __init_fpu_registers
END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
bl setup_common_caches
+
+ /*
+ * This assumes that all cores using __setup_cpu_603 with
+ * MMU_FTR_USE_HIGH_BATS are G2_LE compatible
+ */
+BEGIN_MMU_FTR_SECTION
+ bl setup_g2_le_hid2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
mtlr r5
blr
_GLOBAL(__setup_cpu_604)
@@ -81,7 +92,7 @@ _GLOBAL(__setup_cpu_745x)
blr
/* Enable caches for 603's, 604, 750 & 7400 */
-setup_common_caches:
+SYM_FUNC_START_LOCAL(setup_common_caches)
mfspr r11,SPRN_HID0
andi. r0,r11,HID0_DCE
ori r11,r11,HID0_ICE|HID0_DCE
@@ -95,11 +106,12 @@ setup_common_caches:
sync
isync
blr
+SYM_FUNC_END(setup_common_caches)
/* 604, 604e, 604ev, ...
* Enable superscalar execution & branch history table
*/
-setup_604_hid0:
+SYM_FUNC_START_LOCAL(setup_604_hid0)
mfspr r11,SPRN_HID0
ori r11,r11,HID0_SIED|HID0_BHTE
ori r8,r11,HID0_BTCD
@@ -110,6 +122,17 @@ setup_604_hid0:
sync
isync
blr
+SYM_FUNC_END(setup_604_hid0)
+
+/* Enable high BATs for G2_LE and derivatives like e300cX */
+SYM_FUNC_START_LOCAL(setup_g2_le_hid2)
+ mfspr r11,SPRN_HID2_G2_LE
+ oris r11,r11,HID2_G2_LE_HBE@h
+ mtspr SPRN_HID2_G2_LE,r11
+ sync
+ isync
+ blr
+SYM_FUNC_END(setup_g2_le_hid2)
/* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
* erratas we work around here.
@@ -125,13 +148,14 @@ setup_604_hid0:
* needed once we have applied workaround #5 (though it's
* not set by Apple's firmware at least).
*/
-setup_7400_workarounds:
+SYM_FUNC_START_LOCAL(setup_7400_workarounds)
mfpvr r3
rlwinm r3,r3,0,20,31
cmpwi 0,r3,0x0207
ble 1f
blr
-setup_7410_workarounds:
+SYM_FUNC_END(setup_7400_workarounds)
+SYM_FUNC_START_LOCAL(setup_7410_workarounds)
mfpvr r3
rlwinm r3,r3,0,20,31
cmpwi 0,r3,0x0100
@@ -151,6 +175,7 @@ setup_7410_workarounds:
sync
isync
blr
+SYM_FUNC_END(setup_7410_workarounds)
/* 740/750/7400/7410
* Enable Store Gathering (SGE), Address Broadcast (ABE),
@@ -158,7 +183,7 @@ setup_7410_workarounds:
* Dynamic Power Management (DPM), Speculative (SPD)
* Clear Instruction cache throttling (ICTC)
*/
-setup_750_7400_hid0:
+SYM_FUNC_START_LOCAL(setup_750_7400_hid0)
mfspr r11,SPRN_HID0
ori r11,r11,HID0_SGE | HID0_ABE | HID0_BHTE | HID0_BTIC
oris r11,r11,HID0_DPM@h
@@ -177,12 +202,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_NO_DPM)
sync
isync
blr
+SYM_FUNC_END(setup_750_7400_hid0)
/* 750cx specific
* Looks like we have to disable NAP feature for some PLL settings...
* (waiting for confirmation)
*/
-setup_750cx:
+SYM_FUNC_START_LOCAL(setup_750cx)
mfspr r10, SPRN_HID1
rlwinm r10,r10,4,28,31
cmpwi cr0,r10,7
@@ -196,11 +222,13 @@ setup_750cx:
andc r6,r6,r7
stw r6,CPU_SPEC_FEATURES(r4)
blr
+SYM_FUNC_END(setup_750cx)
/* 750fx specific
*/
-setup_750fx:
+SYM_FUNC_START_LOCAL(setup_750fx)
blr
+SYM_FUNC_END(setup_750fx)
/* MPC 745x
* Enable Store Gathering (SGE), Branch Folding (FOLD)
@@ -212,7 +240,7 @@ setup_750fx:
* Clear Instruction cache throttling (ICTC)
* Enable L2 HW prefetch
*/
-setup_745x_specifics:
+SYM_FUNC_START_LOCAL(setup_745x_specifics)
/* We check for the presence of an L3 cache setup by
* the firmware. If any, we disable NAP capability as
* it's known to be bogus on rev 2.1 and earlier
@@ -270,6 +298,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NO_DPM)
sync
isync
blr
+SYM_FUNC_END(setup_745x_specifics)
/*
* Initialize the FPU registers. This is needed to work around an errata
@@ -372,7 +401,7 @@ _GLOBAL(__save_cpu_setup)
andi. r3,r3,0xff00
cmpwi cr0,r3,0x0200
bne 1f
- mfspr r4,SPRN_HID2
+ mfspr r4,SPRN_HID2_750FX
stw r4,CS_HID2(r5)
1:
mtcr r7
@@ -467,7 +496,7 @@ _GLOBAL(__restore_cpu_setup)
bne 4f
lwz r4,CS_HID2(r5)
rlwinm r4,r4,0,19,17
- mtspr SPRN_HID2,r4
+ mtspr SPRN_HID2_750FX,r4
sync
4:
lwz r4,CS_HID1(r5)
@@ -485,4 +514,3 @@ _GLOBAL(__restore_cpu_setup)
mtcr r7
blr
_ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
-
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_e500.S
index 4bf33f1b4193..077cfccc3461 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_e500.S
@@ -8,11 +8,13 @@
* Benjamin Herrenschmidt <benh@kernel.crashing.org>
*/
+#include <linux/linkage.h>
+
#include <asm/page.h>
#include <asm/processor.h>
#include <asm/cputable.h>
#include <asm/ppc_asm.h>
-#include <asm/nohash/mmu-book3e.h>
+#include <asm/nohash/mmu-e500.h>
#include <asm/asm-offsets.h>
#include <asm/mpc85xx.h>
@@ -108,7 +110,7 @@ _GLOBAL(__setup_cpu_e6500)
#endif /* CONFIG_PPC_E500MC */
#ifdef CONFIG_PPC32
-#ifdef CONFIG_E500
+#ifdef CONFIG_PPC_E500
#ifndef CONFIG_PPC_E500MC
_GLOBAL(__setup_cpu_e500v1)
_GLOBAL(__setup_cpu_e500v2)
@@ -156,7 +158,7 @@ _GLOBAL(__setup_cpu_e5500)
mtlr r5
blr
#endif /* CONFIG_PPC_E500MC */
-#endif /* CONFIG_E500 */
+#endif /* CONFIG_PPC_E500 */
#endif /* CONFIG_PPC32 */
#ifdef CONFIG_PPC_BOOK3E_64
@@ -274,7 +276,7 @@ _GLOBAL(flush_dcache_L1)
blr
-has_L2_cache:
+SYM_FUNC_START_LOCAL(has_L2_cache)
/* skip L2 cache on P2040/P2040E as they have no L2 cache */
mfspr r3, SPRN_SVR
/* shift right by 8 bits and clear E bit of SVR */
@@ -290,9 +292,10 @@ has_L2_cache:
1:
li r3, 0
blr
+SYM_FUNC_END(has_L2_cache)
/* flush backside L2 cache */
-flush_backside_L2_cache:
+SYM_FUNC_START_LOCAL(flush_backside_L2_cache)
mflr r10
bl has_L2_cache
mtlr r10
@@ -313,6 +316,7 @@ flush_backside_L2_cache:
bne 1b
2:
blr
+SYM_FUNC_END(flush_backside_L2_cache)
_GLOBAL(cpu_down_flush_e500v2)
mflr r0
diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c
index 3dc61e203f37..98bd4e6c1770 100644
--- a/arch/powerpc/kernel/cpu_setup_power.c
+++ b/arch/powerpc/kernel/cpu_setup_power.c
@@ -11,7 +11,7 @@
#include <asm/synch.h>
#include <linux/bitops.h>
#include <asm/cputable.h>
-#include <asm/cpu_setup_power.h>
+#include <asm/cpu_setup.h>
/* Disable CPU_FTR_HVMODE and return false if MSR:HV is not set */
static bool init_hvmode_206(struct cpu_spec *t)
@@ -126,6 +126,12 @@ static void init_PMU_ISA31(void)
mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT);
}
+static void init_DEXCR(void)
+{
+ mtspr(SPRN_DEXCR, DEXCR_INIT);
+ mtspr(SPRN_HASHKEYR, 0);
+}
+
/*
* Note that we can be called twice of pseudo-PVRs.
* The parameter offset is not used.
@@ -241,6 +247,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t)
init_FSCR_power10();
init_PMU();
init_PMU_ISA31();
+ init_DEXCR();
if (!init_hvmode_206(t))
return;
@@ -263,6 +270,7 @@ void __restore_cpu_power10(void)
init_FSCR_power10();
init_PMU();
init_PMU_ISA31();
+ init_DEXCR();
msr = mfmsr();
if (!(msr & MSR_HV))
diff --git a/arch/powerpc/kernel/cpu_specs.h b/arch/powerpc/kernel/cpu_specs.h
new file mode 100644
index 000000000000..5ea14605bb41
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifdef CONFIG_PPC_47x
+#include "cpu_specs_47x.h"
+#elif defined(CONFIG_44x)
+#include "cpu_specs_44x.h"
+#endif
+
+#ifdef CONFIG_PPC_8xx
+#include "cpu_specs_8xx.h"
+#endif
+
+#ifdef CONFIG_PPC_E500MC
+#include "cpu_specs_e500mc.h"
+#elif defined(CONFIG_PPC_85xx)
+#include "cpu_specs_85xx.h"
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_32
+#include "cpu_specs_book3s_32.h"
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#include "cpu_specs_book3s_64.h"
+#endif
diff --git a/arch/powerpc/kernel/cpu_specs_44x.h b/arch/powerpc/kernel/cpu_specs_44x.h
new file mode 100644
index 000000000000..69c4cdc0cdee
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_44x.h
@@ -0,0 +1,304 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_BOOKE)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ {
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000850,
+ .cpu_name = "440GR Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000858,
+ .cpu_name = "440EP Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440ep,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ {
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x400008d3,
+ .cpu_name = "440GR Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* Matches both physical and logical PVR for 440EP (logical pvr = pvr | 0x8) */
+ .pvr_mask = 0xf0000ff7,
+ .pvr_value = 0x400008d4,
+ .cpu_name = "440EP Rev. C",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440ep,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x400008db,
+ .cpu_name = "440EP Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440ep,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* 440GRX */
+ .pvr_mask = 0xf0000ffb,
+ .pvr_value = 0x200008D0,
+ .cpu_name = "440GRX",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440grx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* Use logical PVR for 440EPx (logical pvr = pvr | 0x8) */
+ .pvr_mask = 0xf0000ffb,
+ .pvr_value = 0x200008D8,
+ .cpu_name = "440EPX",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440epx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440GP Rev. B */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000440,
+ .cpu_name = "440GP Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440gp",
+ },
+ { /* 440GP Rev. C */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000481,
+ .cpu_name = "440GP Rev. C",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440gp",
+ },
+ { /* 440GX Rev. A */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000850,
+ .cpu_name = "440GX Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440gx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440GX Rev. B */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000851,
+ .cpu_name = "440GX Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440gx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440GX Rev. C */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000892,
+ .cpu_name = "440GX Rev. C",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440gx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440GX Rev. F */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000894,
+ .cpu_name = "440GX Rev. F",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440gx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440SP Rev. A */
+ .pvr_mask = 0xfff00fff,
+ .pvr_value = 0x53200891,
+ .cpu_name = "440SP Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* 440SPe Rev. A */
+ .pvr_mask = 0xfff00fff,
+ .pvr_value = 0x53400890,
+ .cpu_name = "440SPe Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440spe,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440SPe Rev. B */
+ .pvr_mask = 0xfff00fff,
+ .pvr_value = 0x53400891,
+ .cpu_name = "440SPe Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440spe,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460EX */
+ .pvr_mask = 0xffff0006,
+ .pvr_value = 0x13020002,
+ .cpu_name = "460EX",
+ .cpu_features = CPU_FTRS_440x6,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460ex,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460EX Rev B */
+ .pvr_mask = 0xffff0007,
+ .pvr_value = 0x13020004,
+ .cpu_name = "460EX Rev. B",
+ .cpu_features = CPU_FTRS_440x6,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460ex,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460GT */
+ .pvr_mask = 0xffff0006,
+ .pvr_value = 0x13020000,
+ .cpu_name = "460GT",
+ .cpu_features = CPU_FTRS_440x6,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460gt,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460GT Rev B */
+ .pvr_mask = 0xffff0007,
+ .pvr_value = 0x13020005,
+ .cpu_name = "460GT Rev. B",
+ .cpu_features = CPU_FTRS_440x6,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460gt,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460SX */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x13541800,
+ .cpu_name = "460SX",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460sx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 464 in APM821xx */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x12C41C80,
+ .cpu_name = "APM821XX",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE |
+ PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_apm821xx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic 44x PPC)",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_47x.h b/arch/powerpc/kernel/cpu_specs_47x.h
new file mode 100644
index 000000000000..3143cd504a51
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_47x.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_BOOKE)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* 476 DD2 core */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x11a52080,
+ .cpu_name = "476",
+ .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST |
+ MMU_FTR_LOCK_BCAST_INVAL,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ },
+ { /* 476fpe */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x7ff50000,
+ .cpu_name = "476fpe",
+ .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST |
+ MMU_FTR_LOCK_BCAST_INVAL,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ },
+ { /* 476 iss */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00050000,
+ .cpu_name = "476",
+ .cpu_features = CPU_FTRS_47X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST |
+ MMU_FTR_LOCK_BCAST_INVAL,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ },
+ { /* 476 others */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x11a50000,
+ .cpu_name = "476",
+ .cpu_features = CPU_FTRS_47X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST |
+ MMU_FTR_LOCK_BCAST_INVAL,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic 47x PPC)",
+ .cpu_features = CPU_FTRS_47X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_47x,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_85xx.h b/arch/powerpc/kernel/cpu_specs_85xx.h
new file mode 100644
index 000000000000..aaae202c1a89
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_85xx.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_BOOKE)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* e500 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80200000,
+ .cpu_name = "e500",
+ .cpu_features = CPU_FTRS_E500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP |
+ PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_e500v1,
+ .machine_check = machine_check_e500,
+ .platform = "ppc8540",
+ },
+ { /* e500v2 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80210000,
+ .cpu_name = "e500v2",
+ .cpu_features = CPU_FTRS_E500_2,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP |
+ PPC_FEATURE_HAS_EFP_SINGLE_COMP |
+ PPC_FEATURE_HAS_EFP_DOUBLE_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_e500v2,
+ .machine_check = machine_check_e500,
+ .platform = "ppc8548",
+ .cpu_down_flush = cpu_down_flush_e500v2,
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic E500 PPC)",
+ .cpu_features = CPU_FTRS_E500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP |
+ PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+ .mmu_features = MMU_FTR_TYPE_FSL_E,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_e500,
+ .platform = "powerpc",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_8xx.h b/arch/powerpc/kernel/cpu_specs_8xx.h
new file mode 100644
index 000000000000..93ddbc202ba3
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_8xx.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* 8xx */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = PVR_8xx,
+ .cpu_name = "8xx",
+ /*
+ * CPU_FTR_MAYBE_CAN_DOZE is possible,
+ * if the 8xx code is there....
+ */
+ .cpu_features = CPU_FTRS_8XX,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .mmu_features = MMU_FTR_TYPE_8xx,
+ .icache_bsize = 16,
+ .dcache_bsize = 16,
+ .machine_check = machine_check_8xx,
+ .platform = "ppc823",
+ },
+};
diff --git a/arch/powerpc/kernel/cpu_specs_book3s_32.h b/arch/powerpc/kernel/cpu_specs_book3s_32.h
new file mode 100644
index 000000000000..3714634d194a
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_book3s_32.h
@@ -0,0 +1,605 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \
+ PPC_FEATURE_HAS_MMU)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+#ifdef CONFIG_PPC_BOOK3S_603
+ { /* 603 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00030000,
+ .cpu_name = "603",
+ .cpu_features = CPU_FTRS_603,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = 0,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+ { /* 603e */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00060000,
+ .cpu_name = "603e",
+ .cpu_features = CPU_FTRS_603,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = 0,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+ { /* 603ev */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00070000,
+ .cpu_name = "603ev",
+ .cpu_features = CPU_FTRS_603,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = 0,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+ { /* 82xx (8240, 8245, 8260 are all 603e cores) */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00810000,
+ .cpu_name = "82xx",
+ .cpu_features = CPU_FTRS_82XX,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = 0,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+ { /* All G2_LE (603e core, plus some) have the same pvr */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00820000,
+ .cpu_name = "G2_LE",
+ .cpu_features = CPU_FTRS_G2_LE,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+#ifdef CONFIG_PPC_83xx
+ { /* e300c1 (a 603e core, plus some) on 83xx */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00830000,
+ .cpu_name = "e300c1",
+ .cpu_features = CPU_FTRS_E300,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_83xx,
+ .platform = "ppc603",
+ },
+ { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00840000,
+ .cpu_name = "e300c2",
+ .cpu_features = CPU_FTRS_E300C2,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_83xx,
+ .platform = "ppc603",
+ },
+ { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00850000,
+ .cpu_name = "e300c3",
+ .cpu_features = CPU_FTRS_E300,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_83xx,
+ .num_pmcs = 4,
+ .platform = "ppc603",
+ },
+ { /* e300c4 (e300c1, plus one IU) */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00860000,
+ .cpu_name = "e300c4",
+ .cpu_features = CPU_FTRS_E300,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_83xx,
+ .num_pmcs = 4,
+ .platform = "ppc603",
+ },
+#endif
+#endif /* CONFIG_PPC_BOOK3S_603 */
+#ifdef CONFIG_PPC_BOOK3S_604
+ { /* 604 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00040000,
+ .cpu_name = "604",
+ .cpu_features = CPU_FTRS_604,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 2,
+ .cpu_setup = __setup_cpu_604,
+ .machine_check = machine_check_generic,
+ .platform = "ppc604",
+ },
+ { /* 604e */
+ .pvr_mask = 0xfffff000,
+ .pvr_value = 0x00090000,
+ .cpu_name = "604e",
+ .cpu_features = CPU_FTRS_604,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604,
+ .machine_check = machine_check_generic,
+ .platform = "ppc604",
+ },
+ { /* 604r */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00090000,
+ .cpu_name = "604r",
+ .cpu_features = CPU_FTRS_604,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604,
+ .machine_check = machine_check_generic,
+ .platform = "ppc604",
+ },
+ { /* 604ev */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x000a0000,
+ .cpu_name = "604ev",
+ .cpu_features = CPU_FTRS_604,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604,
+ .machine_check = machine_check_generic,
+ .platform = "ppc604",
+ },
+ { /* 740/750 (0x4202, don't support TAU ?) */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x00084202,
+ .cpu_name = "740/750",
+ .cpu_features = CPU_FTRS_740_NOTAU,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CX (80100 and 8010x?) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00080100,
+ .cpu_name = "750CX",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750cx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CX (82201 and 82202) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00082200,
+ .cpu_name = "750CX",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750cx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CXe (82214) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00082210,
+ .cpu_name = "750CXe",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750cx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CXe "Gekko" (83214) */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x00083214,
+ .cpu_name = "750CXe",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750cx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CL (and "Broadway") */
+ .pvr_mask = 0xfffff0e0,
+ .pvr_value = 0x00087000,
+ .cpu_name = "750CL",
+ .cpu_features = CPU_FTRS_750CL,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 745/755 */
+ .pvr_mask = 0xfffff000,
+ .pvr_value = 0x00083000,
+ .cpu_name = "745/755",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750FX rev 1.x */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x70000100,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTRS_750FX1,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750FX rev 2.0 must disable HID0[DPM] */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x70000200,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTRS_750FX2,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750FX (All revs except 2.0) */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x70000000,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTRS_750FX,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750fx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750GX */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x70020000,
+ .cpu_name = "750GX",
+ .cpu_features = CPU_FTRS_750GX,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750fx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 740/750 (L2CR bit need fixup for 740) */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00080000,
+ .cpu_name = "740/750",
+ .cpu_features = CPU_FTRS_740,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 7400 rev 1.1 ? (no TAU) */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x000c1101,
+ .cpu_name = "7400 (1.1)",
+ .cpu_features = CPU_FTRS_7400_NOTAU,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_7400,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7400",
+ },
+ { /* 7400 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x000c0000,
+ .cpu_name = "7400",
+ .cpu_features = CPU_FTRS_7400,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_7400,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7400",
+ },
+ { /* 7410 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x800c0000,
+ .cpu_name = "7410",
+ .cpu_features = CPU_FTRS_7400,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_7410,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7400",
+ },
+ { /* 7450 2.0 - no doze/nap */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80000200,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTRS_7450_20,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7450 2.1 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80000201,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTRS_7450_21,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7450 2.3 and newer */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80000000,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTRS_7450_23,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7455 rev 1.x */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x80010100,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTRS_7455_1,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7455 rev 2.0 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80010200,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTRS_7455_20,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7455 others */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80010000,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTRS_7455,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7447/7457 Rev 1.0 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80020100,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTRS_7447_10,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7447/7457 Rev 1.1 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80020101,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTRS_7447_10,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7447/7457 Rev 1.2 and later */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80020000,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTRS_7447,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7447A */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80030000,
+ .cpu_name = "7447A",
+ .cpu_features = CPU_FTRS_7447A,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7448 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80040000,
+ .cpu_name = "7448",
+ .cpu_features = CPU_FTRS_7448,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* default match, we assume split I/D cache & TB (non-601)... */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic PPC)",
+ .cpu_features = CPU_FTRS_CLASSIC32,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+#endif /* CONFIG_PPC_BOOK3S_604 */
+};
diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h
new file mode 100644
index 000000000000..98d4274a1b6b
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h
@@ -0,0 +1,530 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * Modifications for ppc64:
+ * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ */
+
+/* NOTE:
+ * Unlike ppc32, ppc64 will only call cpu_setup() for the boot CPU, it's
+ * the responsibility of the appropriate CPU save/restore functions to
+ * eventually copy these settings over. Those save/restore aren't yet
+ * part of the cputable though. That has to be fixed for both ppc32
+ * and ppc64
+ */
+#define COMMON_USER_PPC64 (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_64)
+#define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4)
+#define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP)
+#define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP)
+#define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_PSERIES_PERFMON_COMPAT)
+#define COMMON_USER_POWER7 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_PSERIES_PERFMON_COMPAT)
+#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR)
+#define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_PSERIES_PERFMON_COMPAT)
+#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \
+ PPC_FEATURE2_HTM_COMP | \
+ PPC_FEATURE2_HTM_NOSC_COMP | \
+ PPC_FEATURE2_DSCR | \
+ PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+ PPC_FEATURE2_VEC_CRYPTO)
+#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_HAS_ALTIVEC_COMP)
+#define COMMON_USER_POWER9 COMMON_USER_POWER8
+#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \
+ PPC_FEATURE2_ARCH_3_00 | \
+ PPC_FEATURE2_HAS_IEEE128 | \
+ PPC_FEATURE2_DARN | \
+ PPC_FEATURE2_SCV)
+#define COMMON_USER_POWER10 COMMON_USER_POWER9
+#define COMMON_USER2_POWER10 (PPC_FEATURE2_ARCH_3_1 | \
+ PPC_FEATURE2_MMA | \
+ PPC_FEATURE2_ARCH_3_00 | \
+ PPC_FEATURE2_HAS_IEEE128 | \
+ PPC_FEATURE2_DARN | \
+ PPC_FEATURE2_SCV | \
+ PPC_FEATURE2_ARCH_2_07 | \
+ PPC_FEATURE2_DSCR | \
+ PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+ PPC_FEATURE2_VEC_CRYPTO)
+
+#define COMMON_USER_POWER11 COMMON_USER_POWER10
+#define COMMON_USER2_POWER11 COMMON_USER2_POWER10
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* PPC970 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00390000,
+ .cpu_name = "PPC970",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970,
+ .cpu_restore = __restore_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* PPC970FX */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003c0000,
+ .cpu_name = "PPC970FX",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970,
+ .cpu_restore = __restore_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x00440100,
+ .cpu_name = "PPC970MP",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970,
+ .cpu_restore = __restore_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* PPC970MP */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00440000,
+ .cpu_name = "PPC970MP",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970MP,
+ .cpu_restore = __restore_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* PPC970GX */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00450000,
+ .cpu_name = "PPC970GX",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* Power5 GR */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003a0000,
+ .cpu_name = "POWER5 (gr)",
+ .cpu_features = CPU_FTRS_POWER5,
+ .cpu_user_features = COMMON_USER_POWER5,
+ .mmu_features = MMU_FTRS_POWER5,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "power5",
+ },
+ { /* Power5++ */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x003b0300,
+ .cpu_name = "POWER5+ (gs)",
+ .cpu_features = CPU_FTRS_POWER5,
+ .cpu_user_features = COMMON_USER_POWER5_PLUS,
+ .mmu_features = MMU_FTRS_POWER5,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .platform = "power5+",
+ },
+ { /* Power5 GS */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003b0000,
+ .cpu_name = "POWER5+ (gs)",
+ .cpu_features = CPU_FTRS_POWER5,
+ .cpu_user_features = COMMON_USER_POWER5_PLUS,
+ .mmu_features = MMU_FTRS_POWER5,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "power5+",
+ },
+ { /* POWER6 in P5+ mode; 2.04-compliant processor */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000001,
+ .cpu_name = "POWER5+",
+ .cpu_features = CPU_FTRS_POWER5,
+ .cpu_user_features = COMMON_USER_POWER5_PLUS,
+ .mmu_features = MMU_FTRS_POWER5,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .platform = "power5+",
+ },
+ { /* Power6 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003e0000,
+ .cpu_name = "POWER6 (raw)",
+ .cpu_features = CPU_FTRS_POWER6,
+ .cpu_user_features = COMMON_USER_POWER6 | PPC_FEATURE_POWER6_EXT,
+ .mmu_features = MMU_FTRS_POWER6,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "power6x",
+ },
+ { /* 2.05-compliant processor, i.e. Power6 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000002,
+ .cpu_name = "POWER6 (architected)",
+ .cpu_features = CPU_FTRS_POWER6,
+ .cpu_user_features = COMMON_USER_POWER6,
+ .mmu_features = MMU_FTRS_POWER6,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .platform = "power6",
+ },
+ { /* 2.06-compliant processor, i.e. Power7 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000003,
+ .cpu_name = "POWER7 (architected)",
+ .cpu_features = CPU_FTRS_POWER7,
+ .cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
+ .mmu_features = MMU_FTRS_POWER7,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power7,
+ .cpu_restore = __restore_cpu_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
+ .platform = "power7",
+ },
+ { /* 2.07-compliant processor, i.e. Power8 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000004,
+ .cpu_name = "POWER8 (architected)",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* 2.07-compliant processor, HeXin C2000 processor */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00660000,
+ .cpu_name = "HX-C2000",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* 3.00-compliant processor, i.e. Power9 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000005,
+ .cpu_name = "POWER9 (architected)",
+ .cpu_features = CPU_FTRS_POWER9,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .platform = "power9",
+ },
+ { /* 3.1-compliant processor, i.e. Power10 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000006,
+ .cpu_name = "POWER10 (architected)",
+ .cpu_features = CPU_FTRS_POWER10,
+ .cpu_user_features = COMMON_USER_POWER10,
+ .cpu_user_features2 = COMMON_USER2_POWER10,
+ .mmu_features = MMU_FTRS_POWER10,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power10,
+ .cpu_restore = __restore_cpu_power10,
+ .platform = "power10",
+ },
+ { /* 3.1-compliant processor, i.e. Power11 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000007,
+ .cpu_name = "Power11 (architected)",
+ .cpu_features = CPU_FTRS_POWER11,
+ .cpu_user_features = COMMON_USER_POWER11,
+ .cpu_user_features2 = COMMON_USER2_POWER11,
+ .mmu_features = MMU_FTRS_POWER11,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power10,
+ .cpu_restore = __restore_cpu_power10,
+ .platform = "power11",
+ },
+ { /* Power7 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003f0000,
+ .cpu_name = "POWER7 (raw)",
+ .cpu_features = CPU_FTRS_POWER7,
+ .cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
+ .mmu_features = MMU_FTRS_POWER7,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power7,
+ .cpu_restore = __restore_cpu_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
+ .platform = "power7",
+ },
+ { /* Power7+ */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004A0000,
+ .cpu_name = "POWER7+ (raw)",
+ .cpu_features = CPU_FTRS_POWER7,
+ .cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
+ .mmu_features = MMU_FTRS_POWER7,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power7,
+ .cpu_restore = __restore_cpu_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
+ .platform = "power7+",
+ },
+ { /* Power8E */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004b0000,
+ .cpu_name = "POWER8E (raw)",
+ .cpu_features = CPU_FTRS_POWER8E,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* Power8NVL */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004c0000,
+ .cpu_name = "POWER8NVL (raw)",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* Power8 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004d0000,
+ .cpu_name = "POWER8 (raw)",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* Power9 DD2.0 */
+ .pvr_mask = 0xffffefff,
+ .pvr_value = 0x004e0200,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_0,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power9 DD 2.1 */
+ .pvr_mask = 0xffffefff,
+ .pvr_value = 0x004e0201,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_1,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power9 DD2.2 */
+ .pvr_mask = 0xffffefff,
+ .pvr_value = 0x004e0202,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_2,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power9 DD2.3 or later */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004e0000,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_3,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power10 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00800000,
+ .cpu_name = "POWER10 (raw)",
+ .cpu_features = CPU_FTRS_POWER10,
+ .cpu_user_features = COMMON_USER_POWER10,
+ .cpu_user_features2 = COMMON_USER2_POWER10,
+ .mmu_features = MMU_FTRS_POWER10,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power10,
+ .cpu_restore = __restore_cpu_power10,
+ .machine_check_early = __machine_check_early_realmode_p10,
+ .platform = "power10",
+ },
+ { /* Power11 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00820000,
+ .cpu_name = "Power11 (raw)",
+ .cpu_features = CPU_FTRS_POWER11,
+ .cpu_user_features = COMMON_USER_POWER11,
+ .cpu_user_features2 = COMMON_USER2_POWER11,
+ .mmu_features = MMU_FTRS_POWER11,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power10,
+ .cpu_restore = __restore_cpu_power10,
+ .machine_check_early = __machine_check_early_realmode_p10,
+ .platform = "power11",
+ },
+ { /* Cell Broadband Engine */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00700000,
+ .cpu_name = "Cell Broadband Engine",
+ .cpu_features = CPU_FTRS_CELL,
+ .cpu_user_features = COMMON_USER_PPC64 | PPC_FEATURE_CELL |
+ PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_SMT,
+ .mmu_features = MMU_FTRS_CELL,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "ppc-cell-be",
+ },
+ { /* PA Semi PA6T */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00900000,
+ .cpu_name = "PA6T",
+ .cpu_features = CPU_FTRS_PA6T,
+ .cpu_user_features = COMMON_USER_PA6T,
+ .mmu_features = MMU_FTRS_PA6T,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_PA6T,
+ .cpu_setup = __setup_cpu_pa6t,
+ .cpu_restore = __restore_cpu_pa6t,
+ .platform = "pa6t",
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "POWER5 (compatible)",
+ .cpu_features = CPU_FTRS_COMPATIBLE,
+ .cpu_user_features = COMMON_USER_PPC64,
+ .mmu_features = MMU_FTRS_POWER,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "power5",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h
new file mode 100644
index 000000000000..2ae8e9a7b461
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_e500mc.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * Modifications for ppc64:
+ * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ */
+
+#ifdef CONFIG_PPC64
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \
+ PPC_FEATURE_BOOKE)
+#else
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_BOOKE)
+#endif
+
+static struct cpu_spec cpu_specs[] __initdata = {
+#ifdef CONFIG_PPC32
+ { /* e500mc */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80230000,
+ .cpu_name = "e500mc",
+ .cpu_features = CPU_FTRS_E500MC,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_e500mc,
+ .machine_check = machine_check_e500mc,
+ .platform = "ppce500mc",
+ .cpu_down_flush = cpu_down_flush_e500mc,
+ },
+#endif /* CONFIG_PPC32 */
+ { /* e5500 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80240000,
+ .cpu_name = "e5500",
+ .cpu_features = CPU_FTRS_E5500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_e5500,
+#ifndef CONFIG_PPC32
+ .cpu_restore = __restore_cpu_e5500,
+#endif
+ .machine_check = machine_check_e500mc,
+ .platform = "ppce5500",
+ .cpu_down_flush = cpu_down_flush_e5500,
+ },
+ { /* e6500 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80400000,
+ .cpu_name = "e6500",
+ .cpu_features = CPU_FTRS_E6500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU |
+ PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_e6500,
+#ifndef CONFIG_PPC32
+ .cpu_restore = __restore_cpu_e6500,
+#endif
+ .machine_check = machine_check_e500mc,
+ .platform = "ppce6500",
+ .cpu_down_flush = cpu_down_flush_e6500,
+ },
+};
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index a5dbfccd2047..6f6801da9dc1 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -18,1981 +18,17 @@
#include <asm/mce.h>
#include <asm/mmu.h>
#include <asm/setup.h>
+#include <asm/cpu_setup.h>
-static struct cpu_spec the_cpu_spec __read_mostly;
+static struct cpu_spec the_cpu_spec __ro_after_init;
-struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
+struct cpu_spec *cur_cpu_spec __ro_after_init = NULL;
EXPORT_SYMBOL(cur_cpu_spec);
/* The platform string corresponding to the real PVR */
const char *powerpc_base_platform;
-/* NOTE:
- * Unlike ppc32, ppc64 will only call this once for the boot CPU, it's
- * the responsibility of the appropriate CPU save/restore functions to
- * eventually copy these settings over. Those save/restore aren't yet
- * part of the cputable though. That has to be fixed for both ppc32
- * and ppc64
- */
-#ifdef CONFIG_PPC32
-extern void __setup_cpu_e500v1(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_e500v2(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_e500mc(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_440ep(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_440epx(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_440gx(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_440grx(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_440spe(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_440x5(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_460ex(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_460gt(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_460sx(unsigned long offset, struct cpu_spec *spec);
-extern void __setup_cpu_apm821xx(unsigned long offset, struct cpu_spec *spec);
-extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_750cx(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_750fx(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_7400(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_7410(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec);
-#endif /* CONFIG_PPC32 */
-#ifdef CONFIG_PPC64
-#include <asm/cpu_setup_power.h>
-extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec* spec);
-extern void __restore_cpu_pa6t(void);
-extern void __restore_cpu_ppc970(void);
-extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
-#endif /* CONFIG_PPC64 */
-#if defined(CONFIG_E500)
-extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_e6500(unsigned long offset, struct cpu_spec* spec);
-extern void __restore_cpu_e5500(void);
-extern void __restore_cpu_e6500(void);
-#endif /* CONFIG_E500 */
-
-/* This table only contains "desktop" CPUs, it need to be filled with embedded
- * ones as well...
- */
-#define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \
- PPC_FEATURE_HAS_MMU)
-#define COMMON_USER_PPC64 (COMMON_USER | PPC_FEATURE_64)
-#define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4)
-#define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5 |\
- PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP)
-#define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\
- PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP)
-#define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\
- PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
- PPC_FEATURE_TRUE_LE | \
- PPC_FEATURE_PSERIES_PERFMON_COMPAT)
-#define COMMON_USER_POWER7 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\
- PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
- PPC_FEATURE_TRUE_LE | \
- PPC_FEATURE_PSERIES_PERFMON_COMPAT)
-#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR)
-#define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\
- PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
- PPC_FEATURE_TRUE_LE | \
- PPC_FEATURE_PSERIES_PERFMON_COMPAT)
-#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \
- PPC_FEATURE2_HTM_COMP | \
- PPC_FEATURE2_HTM_NOSC_COMP | \
- PPC_FEATURE2_DSCR | \
- PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
- PPC_FEATURE2_VEC_CRYPTO)
-#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
- PPC_FEATURE_TRUE_LE | \
- PPC_FEATURE_HAS_ALTIVEC_COMP)
-#define COMMON_USER_POWER9 COMMON_USER_POWER8
-#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \
- PPC_FEATURE2_ARCH_3_00 | \
- PPC_FEATURE2_HAS_IEEE128 | \
- PPC_FEATURE2_DARN | \
- PPC_FEATURE2_SCV)
-#define COMMON_USER_POWER10 COMMON_USER_POWER9
-#define COMMON_USER2_POWER10 (PPC_FEATURE2_ARCH_3_1 | \
- PPC_FEATURE2_MMA | \
- PPC_FEATURE2_ARCH_3_00 | \
- PPC_FEATURE2_HAS_IEEE128 | \
- PPC_FEATURE2_DARN | \
- PPC_FEATURE2_SCV | \
- PPC_FEATURE2_ARCH_2_07 | \
- PPC_FEATURE2_DSCR | \
- PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
- PPC_FEATURE2_VEC_CRYPTO)
-
-#ifdef CONFIG_PPC_BOOK3E_64
-#define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE)
-#else
-#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
- PPC_FEATURE_BOOKE)
-#endif
-
-static struct cpu_spec __initdata cpu_specs[] = {
-#ifdef CONFIG_PPC_BOOK3S_64
- { /* PPC970 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00390000,
- .cpu_name = "PPC970",
- .cpu_features = CPU_FTRS_PPC970,
- .cpu_user_features = COMMON_USER_POWER4 |
- PPC_FEATURE_HAS_ALTIVEC_COMP,
- .mmu_features = MMU_FTRS_PPC970,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 8,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_ppc970,
- .cpu_restore = __restore_cpu_ppc970,
- .oprofile_cpu_type = "ppc64/970",
- .platform = "ppc970",
- },
- { /* PPC970FX */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x003c0000,
- .cpu_name = "PPC970FX",
- .cpu_features = CPU_FTRS_PPC970,
- .cpu_user_features = COMMON_USER_POWER4 |
- PPC_FEATURE_HAS_ALTIVEC_COMP,
- .mmu_features = MMU_FTRS_PPC970,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 8,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_ppc970,
- .cpu_restore = __restore_cpu_ppc970,
- .oprofile_cpu_type = "ppc64/970",
- .platform = "ppc970",
- },
- { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x00440100,
- .cpu_name = "PPC970MP",
- .cpu_features = CPU_FTRS_PPC970,
- .cpu_user_features = COMMON_USER_POWER4 |
- PPC_FEATURE_HAS_ALTIVEC_COMP,
- .mmu_features = MMU_FTRS_PPC970,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 8,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_ppc970,
- .cpu_restore = __restore_cpu_ppc970,
- .oprofile_cpu_type = "ppc64/970MP",
- .platform = "ppc970",
- },
- { /* PPC970MP */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00440000,
- .cpu_name = "PPC970MP",
- .cpu_features = CPU_FTRS_PPC970,
- .cpu_user_features = COMMON_USER_POWER4 |
- PPC_FEATURE_HAS_ALTIVEC_COMP,
- .mmu_features = MMU_FTRS_PPC970,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 8,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_ppc970MP,
- .cpu_restore = __restore_cpu_ppc970,
- .oprofile_cpu_type = "ppc64/970MP",
- .platform = "ppc970",
- },
- { /* PPC970GX */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00450000,
- .cpu_name = "PPC970GX",
- .cpu_features = CPU_FTRS_PPC970,
- .cpu_user_features = COMMON_USER_POWER4 |
- PPC_FEATURE_HAS_ALTIVEC_COMP,
- .mmu_features = MMU_FTRS_PPC970,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 8,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_ppc970,
- .oprofile_cpu_type = "ppc64/970",
- .platform = "ppc970",
- },
- { /* Power5 GR */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x003a0000,
- .cpu_name = "POWER5 (gr)",
- .cpu_features = CPU_FTRS_POWER5,
- .cpu_user_features = COMMON_USER_POWER5,
- .mmu_features = MMU_FTRS_POWER5,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power5",
- .platform = "power5",
- },
- { /* Power5++ */
- .pvr_mask = 0xffffff00,
- .pvr_value = 0x003b0300,
- .cpu_name = "POWER5+ (gs)",
- .cpu_features = CPU_FTRS_POWER5,
- .cpu_user_features = COMMON_USER_POWER5_PLUS,
- .mmu_features = MMU_FTRS_POWER5,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .oprofile_cpu_type = "ppc64/power5++",
- .platform = "power5+",
- },
- { /* Power5 GS */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x003b0000,
- .cpu_name = "POWER5+ (gs)",
- .cpu_features = CPU_FTRS_POWER5,
- .cpu_user_features = COMMON_USER_POWER5_PLUS,
- .mmu_features = MMU_FTRS_POWER5,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power5+",
- .platform = "power5+",
- },
- { /* POWER6 in P5+ mode; 2.04-compliant processor */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x0f000001,
- .cpu_name = "POWER5+",
- .cpu_features = CPU_FTRS_POWER5,
- .cpu_user_features = COMMON_USER_POWER5_PLUS,
- .mmu_features = MMU_FTRS_POWER5,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .oprofile_cpu_type = "ppc64/ibm-compat-v1",
- .platform = "power5+",
- },
- { /* Power6 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x003e0000,
- .cpu_name = "POWER6 (raw)",
- .cpu_features = CPU_FTRS_POWER6,
- .cpu_user_features = COMMON_USER_POWER6 |
- PPC_FEATURE_POWER6_EXT,
- .mmu_features = MMU_FTRS_POWER6,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power6",
- .platform = "power6x",
- },
- { /* 2.05-compliant processor, i.e. Power6 "architected" mode */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x0f000002,
- .cpu_name = "POWER6 (architected)",
- .cpu_features = CPU_FTRS_POWER6,
- .cpu_user_features = COMMON_USER_POWER6,
- .mmu_features = MMU_FTRS_POWER6,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .oprofile_cpu_type = "ppc64/ibm-compat-v1",
- .platform = "power6",
- },
- { /* 2.06-compliant processor, i.e. Power7 "architected" mode */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x0f000003,
- .cpu_name = "POWER7 (architected)",
- .cpu_features = CPU_FTRS_POWER7,
- .cpu_user_features = COMMON_USER_POWER7,
- .cpu_user_features2 = COMMON_USER2_POWER7,
- .mmu_features = MMU_FTRS_POWER7,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .oprofile_cpu_type = "ppc64/ibm-compat-v1",
- .cpu_setup = __setup_cpu_power7,
- .cpu_restore = __restore_cpu_power7,
- .machine_check_early = __machine_check_early_realmode_p7,
- .platform = "power7",
- },
- { /* 2.07-compliant processor, i.e. Power8 "architected" mode */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x0f000004,
- .cpu_name = "POWER8 (architected)",
- .cpu_features = CPU_FTRS_POWER8,
- .cpu_user_features = COMMON_USER_POWER8,
- .cpu_user_features2 = COMMON_USER2_POWER8,
- .mmu_features = MMU_FTRS_POWER8,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .oprofile_cpu_type = "ppc64/ibm-compat-v1",
- .cpu_setup = __setup_cpu_power8,
- .cpu_restore = __restore_cpu_power8,
- .machine_check_early = __machine_check_early_realmode_p8,
- .platform = "power8",
- },
- { /* 3.00-compliant processor, i.e. Power9 "architected" mode */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x0f000005,
- .cpu_name = "POWER9 (architected)",
- .cpu_features = CPU_FTRS_POWER9,
- .cpu_user_features = COMMON_USER_POWER9,
- .cpu_user_features2 = COMMON_USER2_POWER9,
- .mmu_features = MMU_FTRS_POWER9,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .oprofile_cpu_type = "ppc64/ibm-compat-v1",
- .cpu_setup = __setup_cpu_power9,
- .cpu_restore = __restore_cpu_power9,
- .platform = "power9",
- },
- { /* 3.1-compliant processor, i.e. Power10 "architected" mode */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x0f000006,
- .cpu_name = "POWER10 (architected)",
- .cpu_features = CPU_FTRS_POWER10,
- .cpu_user_features = COMMON_USER_POWER10,
- .cpu_user_features2 = COMMON_USER2_POWER10,
- .mmu_features = MMU_FTRS_POWER10,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .oprofile_cpu_type = "ppc64/ibm-compat-v1",
- .cpu_setup = __setup_cpu_power10,
- .cpu_restore = __restore_cpu_power10,
- .platform = "power10",
- },
- { /* Power7 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x003f0000,
- .cpu_name = "POWER7 (raw)",
- .cpu_features = CPU_FTRS_POWER7,
- .cpu_user_features = COMMON_USER_POWER7,
- .cpu_user_features2 = COMMON_USER2_POWER7,
- .mmu_features = MMU_FTRS_POWER7,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power7",
- .cpu_setup = __setup_cpu_power7,
- .cpu_restore = __restore_cpu_power7,
- .machine_check_early = __machine_check_early_realmode_p7,
- .platform = "power7",
- },
- { /* Power7+ */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x004A0000,
- .cpu_name = "POWER7+ (raw)",
- .cpu_features = CPU_FTRS_POWER7,
- .cpu_user_features = COMMON_USER_POWER7,
- .cpu_user_features2 = COMMON_USER2_POWER7,
- .mmu_features = MMU_FTRS_POWER7,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power7",
- .cpu_setup = __setup_cpu_power7,
- .cpu_restore = __restore_cpu_power7,
- .machine_check_early = __machine_check_early_realmode_p7,
- .platform = "power7+",
- },
- { /* Power8E */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x004b0000,
- .cpu_name = "POWER8E (raw)",
- .cpu_features = CPU_FTRS_POWER8E,
- .cpu_user_features = COMMON_USER_POWER8,
- .cpu_user_features2 = COMMON_USER2_POWER8,
- .mmu_features = MMU_FTRS_POWER8,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power8",
- .cpu_setup = __setup_cpu_power8,
- .cpu_restore = __restore_cpu_power8,
- .machine_check_early = __machine_check_early_realmode_p8,
- .platform = "power8",
- },
- { /* Power8NVL */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x004c0000,
- .cpu_name = "POWER8NVL (raw)",
- .cpu_features = CPU_FTRS_POWER8,
- .cpu_user_features = COMMON_USER_POWER8,
- .cpu_user_features2 = COMMON_USER2_POWER8,
- .mmu_features = MMU_FTRS_POWER8,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power8",
- .cpu_setup = __setup_cpu_power8,
- .cpu_restore = __restore_cpu_power8,
- .machine_check_early = __machine_check_early_realmode_p8,
- .platform = "power8",
- },
- { /* Power8 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x004d0000,
- .cpu_name = "POWER8 (raw)",
- .cpu_features = CPU_FTRS_POWER8,
- .cpu_user_features = COMMON_USER_POWER8,
- .cpu_user_features2 = COMMON_USER2_POWER8,
- .mmu_features = MMU_FTRS_POWER8,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power8",
- .cpu_setup = __setup_cpu_power8,
- .cpu_restore = __restore_cpu_power8,
- .machine_check_early = __machine_check_early_realmode_p8,
- .platform = "power8",
- },
- { /* Power9 DD2.0 */
- .pvr_mask = 0xffffefff,
- .pvr_value = 0x004e0200,
- .cpu_name = "POWER9 (raw)",
- .cpu_features = CPU_FTRS_POWER9_DD2_0,
- .cpu_user_features = COMMON_USER_POWER9,
- .cpu_user_features2 = COMMON_USER2_POWER9,
- .mmu_features = MMU_FTRS_POWER9,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power9",
- .cpu_setup = __setup_cpu_power9,
- .cpu_restore = __restore_cpu_power9,
- .machine_check_early = __machine_check_early_realmode_p9,
- .platform = "power9",
- },
- { /* Power9 DD 2.1 */
- .pvr_mask = 0xffffefff,
- .pvr_value = 0x004e0201,
- .cpu_name = "POWER9 (raw)",
- .cpu_features = CPU_FTRS_POWER9_DD2_1,
- .cpu_user_features = COMMON_USER_POWER9,
- .cpu_user_features2 = COMMON_USER2_POWER9,
- .mmu_features = MMU_FTRS_POWER9,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power9",
- .cpu_setup = __setup_cpu_power9,
- .cpu_restore = __restore_cpu_power9,
- .machine_check_early = __machine_check_early_realmode_p9,
- .platform = "power9",
- },
- { /* Power9 DD2.2 */
- .pvr_mask = 0xffffefff,
- .pvr_value = 0x004e0202,
- .cpu_name = "POWER9 (raw)",
- .cpu_features = CPU_FTRS_POWER9_DD2_2,
- .cpu_user_features = COMMON_USER_POWER9,
- .cpu_user_features2 = COMMON_USER2_POWER9,
- .mmu_features = MMU_FTRS_POWER9,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power9",
- .cpu_setup = __setup_cpu_power9,
- .cpu_restore = __restore_cpu_power9,
- .machine_check_early = __machine_check_early_realmode_p9,
- .platform = "power9",
- },
- { /* Power9 DD2.3 or later */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x004e0000,
- .cpu_name = "POWER9 (raw)",
- .cpu_features = CPU_FTRS_POWER9_DD2_3,
- .cpu_user_features = COMMON_USER_POWER9,
- .cpu_user_features2 = COMMON_USER2_POWER9,
- .mmu_features = MMU_FTRS_POWER9,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power9",
- .cpu_setup = __setup_cpu_power9,
- .cpu_restore = __restore_cpu_power9,
- .machine_check_early = __machine_check_early_realmode_p9,
- .platform = "power9",
- },
- { /* Power10 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00800000,
- .cpu_name = "POWER10 (raw)",
- .cpu_features = CPU_FTRS_POWER10,
- .cpu_user_features = COMMON_USER_POWER10,
- .cpu_user_features2 = COMMON_USER2_POWER10,
- .mmu_features = MMU_FTRS_POWER10,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/power10",
- .cpu_setup = __setup_cpu_power10,
- .cpu_restore = __restore_cpu_power10,
- .machine_check_early = __machine_check_early_realmode_p10,
- .platform = "power10",
- },
- { /* Cell Broadband Engine */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00700000,
- .cpu_name = "Cell Broadband Engine",
- .cpu_features = CPU_FTRS_CELL,
- .cpu_user_features = COMMON_USER_PPC64 |
- PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP |
- PPC_FEATURE_SMT,
- .mmu_features = MMU_FTRS_CELL,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = "ppc64/cell-be",
- .platform = "ppc-cell-be",
- },
- { /* PA Semi PA6T */
- .pvr_mask = 0x7fff0000,
- .pvr_value = 0x00900000,
- .cpu_name = "PA6T",
- .cpu_features = CPU_FTRS_PA6T,
- .cpu_user_features = COMMON_USER_PA6T,
- .mmu_features = MMU_FTRS_PA6T,
- .icache_bsize = 64,
- .dcache_bsize = 64,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_PA6T,
- .cpu_setup = __setup_cpu_pa6t,
- .cpu_restore = __restore_cpu_pa6t,
- .oprofile_cpu_type = "ppc64/pa6t",
- .platform = "pa6t",
- },
- { /* default match */
- .pvr_mask = 0x00000000,
- .pvr_value = 0x00000000,
- .cpu_name = "POWER5 (compatible)",
- .cpu_features = CPU_FTRS_COMPATIBLE,
- .cpu_user_features = COMMON_USER_PPC64,
- .mmu_features = MMU_FTRS_POWER,
- .icache_bsize = 128,
- .dcache_bsize = 128,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_IBM,
- .platform = "power5",
- }
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-#ifdef CONFIG_PPC32
-#ifdef CONFIG_PPC_BOOK3S_32
-#ifdef CONFIG_PPC_BOOK3S_604
- { /* 604 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00040000,
- .cpu_name = "604",
- .cpu_features = CPU_FTRS_604,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 2,
- .cpu_setup = __setup_cpu_604,
- .machine_check = machine_check_generic,
- .platform = "ppc604",
- },
- { /* 604e */
- .pvr_mask = 0xfffff000,
- .pvr_value = 0x00090000,
- .cpu_name = "604e",
- .cpu_features = CPU_FTRS_604,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .cpu_setup = __setup_cpu_604,
- .machine_check = machine_check_generic,
- .platform = "ppc604",
- },
- { /* 604r */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00090000,
- .cpu_name = "604r",
- .cpu_features = CPU_FTRS_604,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .cpu_setup = __setup_cpu_604,
- .machine_check = machine_check_generic,
- .platform = "ppc604",
- },
- { /* 604ev */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x000a0000,
- .cpu_name = "604ev",
- .cpu_features = CPU_FTRS_604,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .cpu_setup = __setup_cpu_604,
- .machine_check = machine_check_generic,
- .platform = "ppc604",
- },
- { /* 740/750 (0x4202, don't support TAU ?) */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x00084202,
- .cpu_name = "740/750",
- .cpu_features = CPU_FTRS_740_NOTAU,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .cpu_setup = __setup_cpu_750,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- },
- { /* 750CX (80100 and 8010x?) */
- .pvr_mask = 0xfffffff0,
- .pvr_value = 0x00080100,
- .cpu_name = "750CX",
- .cpu_features = CPU_FTRS_750,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .cpu_setup = __setup_cpu_750cx,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- },
- { /* 750CX (82201 and 82202) */
- .pvr_mask = 0xfffffff0,
- .pvr_value = 0x00082200,
- .cpu_name = "750CX",
- .cpu_features = CPU_FTRS_750,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750cx,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- },
- { /* 750CXe (82214) */
- .pvr_mask = 0xfffffff0,
- .pvr_value = 0x00082210,
- .cpu_name = "750CXe",
- .cpu_features = CPU_FTRS_750,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750cx,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- },
- { /* 750CXe "Gekko" (83214) */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x00083214,
- .cpu_name = "750CXe",
- .cpu_features = CPU_FTRS_750,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750cx,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- },
- { /* 750CL (and "Broadway") */
- .pvr_mask = 0xfffff0e0,
- .pvr_value = 0x00087000,
- .cpu_name = "750CL",
- .cpu_features = CPU_FTRS_750CL,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- .oprofile_cpu_type = "ppc/750",
- },
- { /* 745/755 */
- .pvr_mask = 0xfffff000,
- .pvr_value = 0x00083000,
- .cpu_name = "745/755",
- .cpu_features = CPU_FTRS_750,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- },
- { /* 750FX rev 1.x */
- .pvr_mask = 0xffffff00,
- .pvr_value = 0x70000100,
- .cpu_name = "750FX",
- .cpu_features = CPU_FTRS_750FX1,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- .oprofile_cpu_type = "ppc/750",
- },
- { /* 750FX rev 2.0 must disable HID0[DPM] */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x70000200,
- .cpu_name = "750FX",
- .cpu_features = CPU_FTRS_750FX2,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- .oprofile_cpu_type = "ppc/750",
- },
- { /* 750FX (All revs except 2.0) */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x70000000,
- .cpu_name = "750FX",
- .cpu_features = CPU_FTRS_750FX,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750fx,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- .oprofile_cpu_type = "ppc/750",
- },
- { /* 750GX */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x70020000,
- .cpu_name = "750GX",
- .cpu_features = CPU_FTRS_750GX,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750fx,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- .oprofile_cpu_type = "ppc/750",
- },
- { /* 740/750 (L2CR bit need fixup for 740) */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00080000,
- .cpu_name = "740/750",
- .cpu_features = CPU_FTRS_740,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_IBM,
- .cpu_setup = __setup_cpu_750,
- .machine_check = machine_check_generic,
- .platform = "ppc750",
- },
- { /* 7400 rev 1.1 ? (no TAU) */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x000c1101,
- .cpu_name = "7400 (1.1)",
- .cpu_features = CPU_FTRS_7400_NOTAU,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_7400,
- .machine_check = machine_check_generic,
- .platform = "ppc7400",
- },
- { /* 7400 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x000c0000,
- .cpu_name = "7400",
- .cpu_features = CPU_FTRS_7400,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_7400,
- .machine_check = machine_check_generic,
- .platform = "ppc7400",
- },
- { /* 7410 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x800c0000,
- .cpu_name = "7410",
- .cpu_features = CPU_FTRS_7400,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_7410,
- .machine_check = machine_check_generic,
- .platform = "ppc7400",
- },
- { /* 7450 2.0 - no doze/nap */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x80000200,
- .cpu_name = "7450",
- .cpu_features = CPU_FTRS_7450_20,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7450 2.1 */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x80000201,
- .cpu_name = "7450",
- .cpu_features = CPU_FTRS_7450_21,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7450 2.3 and newer */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80000000,
- .cpu_name = "7450",
- .cpu_features = CPU_FTRS_7450_23,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7455 rev 1.x */
- .pvr_mask = 0xffffff00,
- .pvr_value = 0x80010100,
- .cpu_name = "7455",
- .cpu_features = CPU_FTRS_7455_1,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7455 rev 2.0 */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x80010200,
- .cpu_name = "7455",
- .cpu_features = CPU_FTRS_7455_20,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7455 others */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80010000,
- .cpu_name = "7455",
- .cpu_features = CPU_FTRS_7455,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7447/7457 Rev 1.0 */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x80020100,
- .cpu_name = "7447/7457",
- .cpu_features = CPU_FTRS_7447_10,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7447/7457 Rev 1.1 */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x80020101,
- .cpu_name = "7447/7457",
- .cpu_features = CPU_FTRS_7447_10,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7447/7457 Rev 1.2 and later */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80020000,
- .cpu_name = "7447/7457",
- .cpu_features = CPU_FTRS_7447,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7447A */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80030000,
- .cpu_name = "7447A",
- .cpu_features = CPU_FTRS_7447A,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
- { /* 7448 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80040000,
- .cpu_name = "7448",
- .cpu_features = CPU_FTRS_7448,
- .cpu_user_features = COMMON_USER |
- PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
- .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 6,
- .pmc_type = PPC_PMC_G4,
- .cpu_setup = __setup_cpu_745x,
- .oprofile_cpu_type = "ppc/7450",
- .machine_check = machine_check_generic,
- .platform = "ppc7450",
- },
-#endif /* CONFIG_PPC_BOOK3S_604 */
-#ifdef CONFIG_PPC_BOOK3S_603
- { /* 603 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00030000,
- .cpu_name = "603",
- .cpu_features = CPU_FTRS_603,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = 0,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_generic,
- .platform = "ppc603",
- },
- { /* 603e */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00060000,
- .cpu_name = "603e",
- .cpu_features = CPU_FTRS_603,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = 0,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_generic,
- .platform = "ppc603",
- },
- { /* 603ev */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00070000,
- .cpu_name = "603ev",
- .cpu_features = CPU_FTRS_603,
- .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
- .mmu_features = 0,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_generic,
- .platform = "ppc603",
- },
- { /* 82xx (8240, 8245, 8260 are all 603e cores) */
- .pvr_mask = 0x7fff0000,
- .pvr_value = 0x00810000,
- .cpu_name = "82xx",
- .cpu_features = CPU_FTRS_82XX,
- .cpu_user_features = COMMON_USER,
- .mmu_features = 0,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_generic,
- .platform = "ppc603",
- },
- { /* All G2_LE (603e core, plus some) have the same pvr */
- .pvr_mask = 0x7fff0000,
- .pvr_value = 0x00820000,
- .cpu_name = "G2_LE",
- .cpu_features = CPU_FTRS_G2_LE,
- .cpu_user_features = COMMON_USER,
- .mmu_features = MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_generic,
- .platform = "ppc603",
- },
-#ifdef CONFIG_PPC_83xx
- { /* e300c1 (a 603e core, plus some) on 83xx */
- .pvr_mask = 0x7fff0000,
- .pvr_value = 0x00830000,
- .cpu_name = "e300c1",
- .cpu_features = CPU_FTRS_E300,
- .cpu_user_features = COMMON_USER,
- .mmu_features = MMU_FTR_USE_HIGH_BATS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_83xx,
- .platform = "ppc603",
- },
- { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */
- .pvr_mask = 0x7fff0000,
- .pvr_value = 0x00840000,
- .cpu_name = "e300c2",
- .cpu_features = CPU_FTRS_E300C2,
- .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
- .mmu_features = MMU_FTR_USE_HIGH_BATS |
- MMU_FTR_NEED_DTLB_SW_LRU,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_83xx,
- .platform = "ppc603",
- },
- { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */
- .pvr_mask = 0x7fff0000,
- .pvr_value = 0x00850000,
- .cpu_name = "e300c3",
- .cpu_features = CPU_FTRS_E300,
- .cpu_user_features = COMMON_USER,
- .mmu_features = MMU_FTR_USE_HIGH_BATS |
- MMU_FTR_NEED_DTLB_SW_LRU,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_83xx,
- .num_pmcs = 4,
- .oprofile_cpu_type = "ppc/e300",
- .platform = "ppc603",
- },
- { /* e300c4 (e300c1, plus one IU) */
- .pvr_mask = 0x7fff0000,
- .pvr_value = 0x00860000,
- .cpu_name = "e300c4",
- .cpu_features = CPU_FTRS_E300,
- .cpu_user_features = COMMON_USER,
- .mmu_features = MMU_FTR_USE_HIGH_BATS |
- MMU_FTR_NEED_DTLB_SW_LRU,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_603,
- .machine_check = machine_check_83xx,
- .num_pmcs = 4,
- .oprofile_cpu_type = "ppc/e300",
- .platform = "ppc603",
- },
-#endif
-#endif /* CONFIG_PPC_BOOK3S_603 */
-#ifdef CONFIG_PPC_BOOK3S_604
- { /* default match, we assume split I/D cache & TB (non-601)... */
- .pvr_mask = 0x00000000,
- .pvr_value = 0x00000000,
- .cpu_name = "(generic PPC)",
- .cpu_features = CPU_FTRS_CLASSIC32,
- .cpu_user_features = COMMON_USER,
- .mmu_features = MMU_FTR_HPTE_TABLE,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_generic,
- .platform = "ppc603",
- },
-#endif /* CONFIG_PPC_BOOK3S_604 */
-#endif /* CONFIG_PPC_BOOK3S_32 */
-#ifdef CONFIG_PPC_8xx
- { /* 8xx */
- .pvr_mask = 0xffff0000,
- .pvr_value = PVR_8xx,
- .cpu_name = "8xx",
- /* CPU_FTR_MAYBE_CAN_DOZE is possible,
- * if the 8xx code is there.... */
- .cpu_features = CPU_FTRS_8XX,
- .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
- .mmu_features = MMU_FTR_TYPE_8xx,
- .icache_bsize = 16,
- .dcache_bsize = 16,
- .machine_check = machine_check_8xx,
- .platform = "ppc823",
- },
-#endif /* CONFIG_PPC_8xx */
-#ifdef CONFIG_40x
- { /* STB 04xxx */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x41810000,
- .cpu_name = "STB04xxx",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* NP405L */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x41610000,
- .cpu_name = "NP405L",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* NP4GS3 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x40B10000,
- .cpu_name = "NP4GS3",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* NP405H */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x41410000,
- .cpu_name = "NP405H",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405GPr */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x50910000,
- .cpu_name = "405GPr",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* STBx25xx */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x51510000,
- .cpu_name = "STBx25xx",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405LP */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x41F10000,
- .cpu_name = "405LP",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EP */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x51210000,
- .cpu_name = "405EP",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EX Rev. A/B with Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x12910007,
- .cpu_name = "405EX Rev. A/B",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EX Rev. C without Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x1291000d,
- .cpu_name = "405EX Rev. C",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EX Rev. C with Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x1291000f,
- .cpu_name = "405EX Rev. C",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EX Rev. D without Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x12910003,
- .cpu_name = "405EX Rev. D",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EX Rev. D with Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x12910005,
- .cpu_name = "405EX Rev. D",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EXr Rev. A/B without Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x12910001,
- .cpu_name = "405EXr Rev. A/B",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EXr Rev. C without Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x12910009,
- .cpu_name = "405EXr Rev. C",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EXr Rev. C with Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x1291000b,
- .cpu_name = "405EXr Rev. C",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EXr Rev. D without Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x12910000,
- .cpu_name = "405EXr Rev. D",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* 405EXr Rev. D with Security */
- .pvr_mask = 0xffff000f,
- .pvr_value = 0x12910002,
- .cpu_name = "405EXr Rev. D",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- {
- /* 405EZ */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x41510000,
- .cpu_name = "405EZ",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* APM8018X */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x7ff11432,
- .cpu_name = "APM8018X",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- },
- { /* default match */
- .pvr_mask = 0x00000000,
- .pvr_value = 0x00000000,
- .cpu_name = "(generic 40x PPC)",
- .cpu_features = CPU_FTRS_40X,
- .cpu_user_features = PPC_FEATURE_32 |
- PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
- .mmu_features = MMU_FTR_TYPE_40x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc405",
- }
-
-#endif /* CONFIG_40x */
-#ifdef CONFIG_44x
-#ifndef CONFIG_PPC_47x
- {
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x40000850,
- .cpu_name = "440GR Rev. A",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc440",
- },
- { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x40000858,
- .cpu_name = "440EP Rev. A",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440ep,
- .machine_check = machine_check_4xx,
- .platform = "ppc440",
- },
- {
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x400008d3,
- .cpu_name = "440GR Rev. B",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc440",
- },
- { /* Matches both physical and logical PVR for 440EP (logical pvr = pvr | 0x8) */
- .pvr_mask = 0xf0000ff7,
- .pvr_value = 0x400008d4,
- .cpu_name = "440EP Rev. C",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440ep,
- .machine_check = machine_check_4xx,
- .platform = "ppc440",
- },
- { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x400008db,
- .cpu_name = "440EP Rev. B",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440ep,
- .machine_check = machine_check_4xx,
- .platform = "ppc440",
- },
- { /* 440GRX */
- .pvr_mask = 0xf0000ffb,
- .pvr_value = 0x200008D0,
- .cpu_name = "440GRX",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440grx,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* Use logical PVR for 440EPx (logical pvr = pvr | 0x8) */
- .pvr_mask = 0xf0000ffb,
- .pvr_value = 0x200008D8,
- .cpu_name = "440EPX",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440epx,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 440GP Rev. B */
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x40000440,
- .cpu_name = "440GP Rev. B",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc440gp",
- },
- { /* 440GP Rev. C */
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x40000481,
- .cpu_name = "440GP Rev. C",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc440gp",
- },
- { /* 440GX Rev. A */
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x50000850,
- .cpu_name = "440GX Rev. A",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440gx,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 440GX Rev. B */
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x50000851,
- .cpu_name = "440GX Rev. B",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440gx,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 440GX Rev. C */
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x50000892,
- .cpu_name = "440GX Rev. C",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440gx,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 440GX Rev. F */
- .pvr_mask = 0xf0000fff,
- .pvr_value = 0x50000894,
- .cpu_name = "440GX Rev. F",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440gx,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 440SP Rev. A */
- .pvr_mask = 0xfff00fff,
- .pvr_value = 0x53200891,
- .cpu_name = "440SP Rev. A",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc440",
- },
- { /* 440SPe Rev. A */
- .pvr_mask = 0xfff00fff,
- .pvr_value = 0x53400890,
- .cpu_name = "440SPe Rev. A",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440spe,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 440SPe Rev. B */
- .pvr_mask = 0xfff00fff,
- .pvr_value = 0x53400891,
- .cpu_name = "440SPe Rev. B",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_440spe,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 460EX */
- .pvr_mask = 0xffff0006,
- .pvr_value = 0x13020002,
- .cpu_name = "460EX",
- .cpu_features = CPU_FTRS_440x6,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_460ex,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 460EX Rev B */
- .pvr_mask = 0xffff0007,
- .pvr_value = 0x13020004,
- .cpu_name = "460EX Rev. B",
- .cpu_features = CPU_FTRS_440x6,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_460ex,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 460GT */
- .pvr_mask = 0xffff0006,
- .pvr_value = 0x13020000,
- .cpu_name = "460GT",
- .cpu_features = CPU_FTRS_440x6,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_460gt,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 460GT Rev B */
- .pvr_mask = 0xffff0007,
- .pvr_value = 0x13020005,
- .cpu_name = "460GT Rev. B",
- .cpu_features = CPU_FTRS_440x6,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_460gt,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 460SX */
- .pvr_mask = 0xffffff00,
- .pvr_value = 0x13541800,
- .cpu_name = "460SX",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_460sx,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* 464 in APM821xx */
- .pvr_mask = 0xfffffff0,
- .pvr_value = 0x12C41C80,
- .cpu_name = "APM821XX",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE |
- PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .cpu_setup = __setup_cpu_apm821xx,
- .machine_check = machine_check_440A,
- .platform = "ppc440",
- },
- { /* default match */
- .pvr_mask = 0x00000000,
- .pvr_value = 0x00000000,
- .cpu_name = "(generic 44x PPC)",
- .cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_44x,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_4xx,
- .platform = "ppc440",
- }
-#else /* CONFIG_PPC_47x */
- { /* 476 DD2 core */
- .pvr_mask = 0xffffffff,
- .pvr_value = 0x11a52080,
- .cpu_name = "476",
- .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2,
- .cpu_user_features = COMMON_USER_BOOKE |
- PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_47x |
- MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL,
- .icache_bsize = 32,
- .dcache_bsize = 128,
- .machine_check = machine_check_47x,
- .platform = "ppc470",
- },
- { /* 476fpe */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x7ff50000,
- .cpu_name = "476fpe",
- .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2,
- .cpu_user_features = COMMON_USER_BOOKE |
- PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_47x |
- MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL,
- .icache_bsize = 32,
- .dcache_bsize = 128,
- .machine_check = machine_check_47x,
- .platform = "ppc470",
- },
- { /* 476 iss */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00050000,
- .cpu_name = "476",
- .cpu_features = CPU_FTRS_47X,
- .cpu_user_features = COMMON_USER_BOOKE |
- PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_47x |
- MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL,
- .icache_bsize = 32,
- .dcache_bsize = 128,
- .machine_check = machine_check_47x,
- .platform = "ppc470",
- },
- { /* 476 others */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x11a50000,
- .cpu_name = "476",
- .cpu_features = CPU_FTRS_47X,
- .cpu_user_features = COMMON_USER_BOOKE |
- PPC_FEATURE_HAS_FPU,
- .mmu_features = MMU_FTR_TYPE_47x |
- MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL,
- .icache_bsize = 32,
- .dcache_bsize = 128,
- .machine_check = machine_check_47x,
- .platform = "ppc470",
- },
- { /* default match */
- .pvr_mask = 0x00000000,
- .pvr_value = 0x00000000,
- .cpu_name = "(generic 47x PPC)",
- .cpu_features = CPU_FTRS_47X,
- .cpu_user_features = COMMON_USER_BOOKE,
- .mmu_features = MMU_FTR_TYPE_47x,
- .icache_bsize = 32,
- .dcache_bsize = 128,
- .machine_check = machine_check_47x,
- .platform = "ppc470",
- }
-#endif /* CONFIG_PPC_47x */
-#endif /* CONFIG_44x */
-#endif /* CONFIG_PPC32 */
-#ifdef CONFIG_E500
-#ifdef CONFIG_PPC32
-#ifndef CONFIG_PPC_E500MC
- { /* e500 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80200000,
- .cpu_name = "e500",
- .cpu_features = CPU_FTRS_E500,
- .cpu_user_features = COMMON_USER_BOOKE |
- PPC_FEATURE_HAS_SPE_COMP |
- PPC_FEATURE_HAS_EFP_SINGLE_COMP,
- .cpu_user_features2 = PPC_FEATURE2_ISEL,
- .mmu_features = MMU_FTR_TYPE_FSL_E,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .oprofile_cpu_type = "ppc/e500",
- .cpu_setup = __setup_cpu_e500v1,
- .machine_check = machine_check_e500,
- .platform = "ppc8540",
- },
- { /* e500v2 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80210000,
- .cpu_name = "e500v2",
- .cpu_features = CPU_FTRS_E500_2,
- .cpu_user_features = COMMON_USER_BOOKE |
- PPC_FEATURE_HAS_SPE_COMP |
- PPC_FEATURE_HAS_EFP_SINGLE_COMP |
- PPC_FEATURE_HAS_EFP_DOUBLE_COMP,
- .cpu_user_features2 = PPC_FEATURE2_ISEL,
- .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .num_pmcs = 4,
- .oprofile_cpu_type = "ppc/e500",
- .cpu_setup = __setup_cpu_e500v2,
- .machine_check = machine_check_e500,
- .platform = "ppc8548",
- .cpu_down_flush = cpu_down_flush_e500v2,
- },
-#else
- { /* e500mc */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80230000,
- .cpu_name = "e500mc",
- .cpu_features = CPU_FTRS_E500MC,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .cpu_user_features2 = PPC_FEATURE2_ISEL,
- .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
- MMU_FTR_USE_TLBILX,
- .icache_bsize = 64,
- .dcache_bsize = 64,
- .num_pmcs = 4,
- .oprofile_cpu_type = "ppc/e500mc",
- .cpu_setup = __setup_cpu_e500mc,
- .machine_check = machine_check_e500mc,
- .platform = "ppce500mc",
- .cpu_down_flush = cpu_down_flush_e500mc,
- },
-#endif /* CONFIG_PPC_E500MC */
-#endif /* CONFIG_PPC32 */
-#ifdef CONFIG_PPC_E500MC
- { /* e5500 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80240000,
- .cpu_name = "e5500",
- .cpu_features = CPU_FTRS_E5500,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
- .cpu_user_features2 = PPC_FEATURE2_ISEL,
- .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
- MMU_FTR_USE_TLBILX,
- .icache_bsize = 64,
- .dcache_bsize = 64,
- .num_pmcs = 4,
- .oprofile_cpu_type = "ppc/e500mc",
- .cpu_setup = __setup_cpu_e5500,
-#ifndef CONFIG_PPC32
- .cpu_restore = __restore_cpu_e5500,
-#endif
- .machine_check = machine_check_e500mc,
- .platform = "ppce5500",
- .cpu_down_flush = cpu_down_flush_e5500,
- },
- { /* e6500 */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x80400000,
- .cpu_name = "e6500",
- .cpu_features = CPU_FTRS_E6500,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU |
- PPC_FEATURE_HAS_ALTIVEC_COMP,
- .cpu_user_features2 = PPC_FEATURE2_ISEL,
- .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
- MMU_FTR_USE_TLBILX,
- .icache_bsize = 64,
- .dcache_bsize = 64,
- .num_pmcs = 6,
- .oprofile_cpu_type = "ppc/e6500",
- .cpu_setup = __setup_cpu_e6500,
-#ifndef CONFIG_PPC32
- .cpu_restore = __restore_cpu_e6500,
-#endif
- .machine_check = machine_check_e500mc,
- .platform = "ppce6500",
- .cpu_down_flush = cpu_down_flush_e6500,
- },
-#endif /* CONFIG_PPC_E500MC */
-#ifdef CONFIG_PPC32
- { /* default match */
- .pvr_mask = 0x00000000,
- .pvr_value = 0x00000000,
- .cpu_name = "(generic E500 PPC)",
- .cpu_features = CPU_FTRS_E500,
- .cpu_user_features = COMMON_USER_BOOKE |
- PPC_FEATURE_HAS_SPE_COMP |
- PPC_FEATURE_HAS_EFP_SINGLE_COMP,
- .mmu_features = MMU_FTR_TYPE_FSL_E,
- .icache_bsize = 32,
- .dcache_bsize = 32,
- .machine_check = machine_check_e500,
- .platform = "powerpc",
- }
-#endif /* CONFIG_PPC32 */
-#endif /* CONFIG_E500 */
-};
+#include "cpu_specs.h"
void __init set_cur_cpu_spec(struct cpu_spec *s)
{
@@ -2033,25 +69,16 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
t->pmc_type = old.pmc_type;
/*
- * If we have passed through this logic once before and
- * have pulled the default case because the real PVR was
- * not found inside cpu_specs[], then we are possibly
- * running in compatibility mode. In that case, let the
- * oprofiler know which set of compatibility counters to
- * pull from by making sure the oprofile_cpu_type string
- * is set to that of compatibility mode. If the
- * oprofile_cpu_type already has a value, then we are
- * possibly overriding a real PVR with a logical one,
- * and, in that case, keep the current value for
- * oprofile_cpu_type. Furthermore, let's ensure that the
+ * Let's ensure that the
* fix for the PMAO bug is enabled on compatibility mode.
*/
- if (old.oprofile_cpu_type != NULL) {
- t->oprofile_cpu_type = old.oprofile_cpu_type;
- t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG;
- }
+ t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG;
}
+ /* Set kuap ON at startup, will be disabled later if cmdline has 'nosmap' */
+ if (IS_ENABLED(CONFIG_PPC_KUAP) && IS_ENABLED(CONFIG_PPC32))
+ t->mmu_features |= MMU_FTR_KUAP;
+
*PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
/*
@@ -2081,6 +108,8 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
struct cpu_spec *s = cpu_specs;
int i;
+ BUILD_BUG_ON(!ARRAY_SIZE(cpu_specs));
+
s = PTRRELOC(s);
for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) {
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 9a3b85bfc83f..103b6605dd68 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -13,12 +13,13 @@
#include <linux/io.h>
#include <linux/memblock.h>
#include <linux/of.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/kdump.h>
#include <asm/firmware.h>
#include <linux/uio.h>
#include <asm/rtas.h>
#include <asm/inst.h>
+#include <asm/fadump.h>
#ifdef DEBUG
#include <asm/udbg.h>
@@ -92,6 +93,17 @@ ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
return csize;
}
+/*
+ * Return true only when kexec based kernel dump capturing method is used.
+ * This ensures all restritions applied for kdump case are not automatically
+ * applied for fadump case.
+ */
+bool is_kdump_kernel(void)
+{
+ return !is_fadump_active() && elfcorehdr_addr != ELFCORE_ADDR_MAX;
+}
+EXPORT_SYMBOL_GPL(is_kdump_kernel);
+
#ifdef CONFIG_PPC_RTAS
/*
* The crashkernel region will almost always overlap the RTAS region, so
diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c
index 30d4eca88d17..909a05cd2809 100644
--- a/arch/powerpc/kernel/dawr.c
+++ b/arch/powerpc/kernel/dawr.c
@@ -11,6 +11,7 @@
#include <linux/debugfs.h>
#include <asm/machdep.h>
#include <asm/hvcall.h>
+#include <asm/firmware.h>
bool dawr_force_enable;
EXPORT_SYMBOL_GPL(dawr_force_enable);
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index f55c6fb34a3a..5712dd846263 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -27,7 +27,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
ppc_msgsync();
- if (should_hard_irq_enable())
+ if (should_hard_irq_enable(regs))
do_hard_irq_enable();
kvmppc_clear_host_ipi(smp_processor_id());
diff --git a/arch/powerpc/kernel/dexcr.c b/arch/powerpc/kernel/dexcr.c
new file mode 100644
index 000000000000..3a0358e91c60
--- /dev/null
+++ b/arch/powerpc/kernel/dexcr.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/capability.h>
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/prctl.h>
+#include <linux/sched.h>
+
+#include <asm/cpu_has_feature.h>
+#include <asm/cputable.h>
+#include <asm/processor.h>
+#include <asm/reg.h>
+
+static int __init init_task_dexcr(void)
+{
+ if (!early_cpu_has_feature(CPU_FTR_ARCH_31))
+ return 0;
+
+ current->thread.dexcr_onexec = mfspr(SPRN_DEXCR);
+
+ return 0;
+}
+early_initcall(init_task_dexcr)
+
+/* Allow thread local configuration of these by default */
+#define DEXCR_PRCTL_EDITABLE ( \
+ DEXCR_PR_IBRTPD | \
+ DEXCR_PR_SRAPD | \
+ DEXCR_PR_NPHIE)
+
+static int prctl_to_aspect(unsigned long which, unsigned int *aspect)
+{
+ switch (which) {
+ case PR_PPC_DEXCR_SBHE:
+ *aspect = DEXCR_PR_SBHE;
+ break;
+ case PR_PPC_DEXCR_IBRTPD:
+ *aspect = DEXCR_PR_IBRTPD;
+ break;
+ case PR_PPC_DEXCR_SRAPD:
+ *aspect = DEXCR_PR_SRAPD;
+ break;
+ case PR_PPC_DEXCR_NPHIE:
+ *aspect = DEXCR_PR_NPHIE;
+ break;
+ default:
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+int get_dexcr_prctl(struct task_struct *task, unsigned long which)
+{
+ unsigned int aspect;
+ int ret;
+
+ ret = prctl_to_aspect(which, &aspect);
+ if (ret)
+ return ret;
+
+ if (aspect & DEXCR_PRCTL_EDITABLE)
+ ret |= PR_PPC_DEXCR_CTRL_EDITABLE;
+
+ if (aspect & mfspr(SPRN_DEXCR))
+ ret |= PR_PPC_DEXCR_CTRL_SET;
+ else
+ ret |= PR_PPC_DEXCR_CTRL_CLEAR;
+
+ if (aspect & task->thread.dexcr_onexec)
+ ret |= PR_PPC_DEXCR_CTRL_SET_ONEXEC;
+ else
+ ret |= PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC;
+
+ return ret;
+}
+
+int set_dexcr_prctl(struct task_struct *task, unsigned long which, unsigned long ctrl)
+{
+ unsigned long dexcr;
+ unsigned int aspect;
+ int err = 0;
+
+ err = prctl_to_aspect(which, &aspect);
+ if (err)
+ return err;
+
+ if (!(aspect & DEXCR_PRCTL_EDITABLE))
+ return -EPERM;
+
+ if (ctrl & ~PR_PPC_DEXCR_CTRL_MASK)
+ return -EINVAL;
+
+ if (ctrl & PR_PPC_DEXCR_CTRL_SET && ctrl & PR_PPC_DEXCR_CTRL_CLEAR)
+ return -EINVAL;
+
+ if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC && ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC)
+ return -EINVAL;
+
+ /*
+ * We do not want an unprivileged process being able to disable
+ * a setuid process's hash check instructions
+ */
+ if (aspect == DEXCR_PR_NPHIE &&
+ ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC &&
+ !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ dexcr = mfspr(SPRN_DEXCR);
+
+ if (ctrl & PR_PPC_DEXCR_CTRL_SET)
+ dexcr |= aspect;
+ else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR)
+ dexcr &= ~aspect;
+
+ if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC)
+ task->thread.dexcr_onexec |= aspect;
+ else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC)
+ task->thread.dexcr_onexec &= ~aspect;
+
+ mtspr(SPRN_DEXCR, dexcr);
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 038ce8d9061d..4d64a5db50f3 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -136,7 +136,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
struct pci_dev *pdev = to_pci_dev(dev);
struct pci_controller *phb = pci_bus_to_host(pdev->bus);
- if (iommu_fixed_is_weak || !phb->controller_ops.iommu_bypass_supported)
+ if (!phb->controller_ops.iommu_bypass_supported)
return false;
return phb->controller_ops.iommu_bypass_supported(pdev, mask);
}
@@ -144,7 +144,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
/* We support DMA to/from any memory page via the iommu */
int dma_iommu_dma_supported(struct device *dev, u64 mask)
{
- struct iommu_table *tbl = get_iommu_table_base(dev);
+ struct iommu_table *tbl;
if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
/*
@@ -162,6 +162,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
return 1;
}
+ tbl = get_iommu_table_base(dev);
+
if (!tbl) {
dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask);
return 0;
@@ -214,6 +216,6 @@ const struct dma_map_ops dma_iommu_ops = {
.get_required_mask = dma_iommu_get_required_mask,
.mmap = dma_common_mmap,
.get_sgtable = dma_common_get_sgtable,
- .alloc_pages = dma_common_alloc_pages,
+ .alloc_pages_op = dma_common_alloc_pages,
.free_pages = dma_common_free_pages,
};
diff --git a/arch/powerpc/kernel/dma-mask.c b/arch/powerpc/kernel/dma-mask.c
index ffbbbc432612..5b07ca7b73aa 100644
--- a/arch/powerpc/kernel/dma-mask.c
+++ b/arch/powerpc/kernel/dma-mask.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
#include <linux/export.h>
#include <asm/machdep.h>
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 2ad365c21afa..3af6c06af02f 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -102,7 +102,6 @@ static struct cpu_spec __initdata base_cpu_spec = {
.dcache_bsize = 32, /* cache info init. */
.num_pmcs = 0,
.pmc_type = PPC_PMC_DEFAULT,
- .oprofile_cpu_type = NULL,
.cpu_setup = NULL,
.cpu_restore = __restore_cpu_cpufeatures,
.machine_check_early = NULL,
@@ -387,7 +386,6 @@ static int __init feat_enable_pmu_power8(struct dt_cpu_feature *f)
cur_cpu_spec->num_pmcs = 6;
cur_cpu_spec->pmc_type = PPC_PMC_IBM;
- cur_cpu_spec->oprofile_cpu_type = "ppc64/power8";
return 1;
}
@@ -423,7 +421,6 @@ static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f)
cur_cpu_spec->num_pmcs = 6;
cur_cpu_spec->pmc_type = PPC_PMC_IBM;
- cur_cpu_spec->oprofile_cpu_type = "ppc64/power9";
return 1;
}
@@ -449,7 +446,6 @@ static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f)
cur_cpu_spec->num_pmcs = 6;
cur_cpu_spec->pmc_type = PPC_PMC_IBM;
- cur_cpu_spec->oprofile_cpu_type = "ppc64/power10";
return 1;
}
@@ -462,6 +458,14 @@ static int __init feat_enable_mce_power10(struct dt_cpu_feature *f)
return 1;
}
+static int __init feat_enable_mce_power11(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->platform = "power11";
+ cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p10;
+
+ return 1;
+}
+
static int __init feat_enable_tm(struct dt_cpu_feature *f)
{
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -652,8 +656,10 @@ static struct dt_cpu_feature_match __initdata
{"pc-relative-addressing", feat_enable, 0},
{"machine-check-power9", feat_enable_mce_power9, 0},
{"machine-check-power10", feat_enable_mce_power10, 0},
+ {"machine-check-power11", feat_enable_mce_power11, 0},
{"performance-monitor-power9", feat_enable_pmu_power9, 0},
{"performance-monitor-power10", feat_enable_pmu_power10, 0},
+ {"performance-monitor-power11", feat_enable_pmu_power10, 0},
{"event-based-branch-v3", feat_enable, 0},
{"random-number-generator", feat_enable, 0},
{"system-call-vectored", feat_disable, 0},
@@ -861,7 +867,7 @@ bool __init dt_cpu_ftrs_init(void *fdt)
using_dt_cpu_ftrs = false;
/* Setup and verify the FDT, if it fails we just bail */
- if (!early_init_dt_verify(fdt))
+ if (!early_init_dt_verify(fdt, __pa(fdt)))
return false;
if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
@@ -1081,12 +1087,10 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
/* Count and allocate space for cpu features */
of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,
&nr_dt_cpu_features);
- dt_cpu_features = memblock_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE);
- if (!dt_cpu_features)
- panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
- __func__,
- sizeof(struct dt_cpu_feature) * nr_dt_cpu_features,
- PAGE_SIZE);
+ dt_cpu_features =
+ memblock_alloc_or_panic(
+ sizeof(struct dt_cpu_feature) * nr_dt_cpu_features,
+ PAGE_SIZE);
cpufeatures_setup_start(isa);
@@ -1103,7 +1107,7 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
prop = of_get_flat_dt_prop(node, "display-name", NULL);
if (prop && strlen((char *)prop) != 0) {
- strlcpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name));
+ strscpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name));
cur_cpu_spec->cpu_name = dt_cpu_name;
}
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index ab316e155ea9..bb836f02101c 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -506,9 +506,18 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
* We will punt with the following conditions: Failure to get
* PE's state, EEH not support and Permanently unavailable
* state, PE is in good state.
+ *
+ * On the pSeries, after reaching the threshold, get_state might
+ * return EEH_STATE_NOT_SUPPORT. However, it's possible that the
+ * device state remains uncleared if the device is not marked
+ * pci_channel_io_perm_failure. Therefore, consider logging the
+ * event to let device removal happen.
+ *
*/
if ((ret < 0) ||
- (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) {
+ (ret == EEH_STATE_NOT_SUPPORT &&
+ dev->error_state == pci_channel_io_perm_failure) ||
+ eeh_state_active(ret)) {
eeh_stats.false_positives++;
pe->false_positives++;
rc = 0;
@@ -1130,6 +1139,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe)
return ret;
}
+EXPORT_SYMBOL_GPL(eeh_unfreeze_pe);
static struct pci_device_id eeh_reset_ids[] = {
@@ -1199,16 +1209,16 @@ int eeh_dev_open(struct pci_dev *pdev)
struct eeh_dev *edev;
int ret = -ENODEV;
- mutex_lock(&eeh_dev_mutex);
+ guard(mutex)(&eeh_dev_mutex);
/* No PCI device ? */
if (!pdev)
- goto out;
+ return ret;
/* No EEH device or PE ? */
edev = pci_dev_to_eeh_dev(pdev);
if (!edev || !edev->pe)
- goto out;
+ return ret;
/*
* The PE might have been put into frozen state, but we
@@ -1218,16 +1228,12 @@ int eeh_dev_open(struct pci_dev *pdev)
*/
ret = eeh_pe_change_owner(edev->pe);
if (ret)
- goto out;
+ return ret;
/* Increase PE's pass through count */
atomic_inc(&edev->pe->pass_dev_cnt);
- mutex_unlock(&eeh_dev_mutex);
return 0;
-out:
- mutex_unlock(&eeh_dev_mutex);
- return ret;
}
EXPORT_SYMBOL_GPL(eeh_dev_open);
@@ -1243,43 +1249,25 @@ void eeh_dev_release(struct pci_dev *pdev)
{
struct eeh_dev *edev;
- mutex_lock(&eeh_dev_mutex);
+ guard(mutex)(&eeh_dev_mutex);
/* No PCI device ? */
if (!pdev)
- goto out;
+ return;
/* No EEH device ? */
edev = pci_dev_to_eeh_dev(pdev);
if (!edev || !edev->pe || !eeh_pe_passed(edev->pe))
- goto out;
+ return;
/* Decrease PE's pass through count */
WARN_ON(atomic_dec_if_positive(&edev->pe->pass_dev_cnt) < 0);
eeh_pe_change_owner(edev->pe);
-out:
- mutex_unlock(&eeh_dev_mutex);
}
EXPORT_SYMBOL(eeh_dev_release);
#ifdef CONFIG_IOMMU_API
-static int dev_has_iommu_table(struct device *dev, void *data)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct pci_dev **ppdev = data;
-
- if (!dev)
- return 0;
-
- if (device_iommu_mapped(dev)) {
- *ppdev = pdev;
- return 1;
- }
-
- return 0;
-}
-
/**
* eeh_iommu_group_to_pe - Convert IOMMU group to EEH PE
* @group: IOMMU group
@@ -1516,6 +1504,8 @@ int eeh_pe_configure(struct eeh_pe *pe)
/* Invalid PE ? */
if (!pe)
return -ENODEV;
+ else
+ ret = eeh_ops->configure_bridge(pe);
return ret;
}
@@ -1544,10 +1534,6 @@ int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
if (!eeh_ops || !eeh_ops->err_inject)
return -ENOENT;
- /* Check on PCI error type */
- if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
- return -EINVAL;
-
/* Check on PCI error function */
if (func < EEH_ERR_FUNC_MIN || func > EEH_ERR_FUNC_MAX)
return -EINVAL;
@@ -1585,6 +1571,104 @@ static int proc_eeh_show(struct seq_file *m, void *v)
}
#endif /* CONFIG_PROC_FS */
+static int eeh_break_device(struct pci_dev *pdev)
+{
+ struct resource *bar = NULL;
+ void __iomem *mapped;
+ u16 old, bit;
+ int i, pos;
+
+ /* Do we have an MMIO BAR to disable? */
+ for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+ struct resource *r = &pdev->resource[i];
+
+ if (!r->flags || !r->start)
+ continue;
+ if (r->flags & IORESOURCE_IO)
+ continue;
+ if (r->flags & IORESOURCE_UNSET)
+ continue;
+
+ bar = r;
+ break;
+ }
+
+ if (!bar) {
+ pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n");
+ return -ENXIO;
+ }
+
+ pci_err(pdev, "Going to break: %pR\n", bar);
+
+ if (pdev->is_virtfn) {
+#ifndef CONFIG_PCI_IOV
+ return -ENXIO;
+#else
+ /*
+ * VFs don't have a per-function COMMAND register, so the best
+ * we can do is clear the Memory Space Enable bit in the PF's
+ * SRIOV control reg.
+ *
+ * Unfortunately, this requires that we have a PF (i.e doesn't
+ * work for a passed-through VF) and it has the potential side
+ * effect of also causing an EEH on every other VF under the
+ * PF. Oh well.
+ */
+ pdev = pdev->physfn;
+ if (!pdev)
+ return -ENXIO; /* passed through VFs have no PF */
+
+ pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
+ pos += PCI_SRIOV_CTRL;
+ bit = PCI_SRIOV_CTRL_MSE;
+#endif /* !CONFIG_PCI_IOV */
+ } else {
+ bit = PCI_COMMAND_MEMORY;
+ pos = PCI_COMMAND;
+ }
+
+ /*
+ * Process here is:
+ *
+ * 1. Disable Memory space.
+ *
+ * 2. Perform an MMIO to the device. This should result in an error
+ * (CA / UR) being raised by the device which results in an EEH
+ * PE freeze. Using the in_8() accessor skips the eeh detection hook
+ * so the freeze hook so the EEH Detection machinery won't be
+ * triggered here. This is to match the usual behaviour of EEH
+ * where the HW will asynchronously freeze a PE and it's up to
+ * the kernel to notice and deal with it.
+ *
+ * 3. Turn Memory space back on. This is more important for VFs
+ * since recovery will probably fail if we don't. For normal
+ * the COMMAND register is reset as a part of re-initialising
+ * the device.
+ *
+ * Breaking stuff is the point so who cares if it's racy ;)
+ */
+ pci_read_config_word(pdev, pos, &old);
+
+ mapped = ioremap(bar->start, PAGE_SIZE);
+ if (!mapped) {
+ pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar);
+ return -ENXIO;
+ }
+
+ pci_write_config_word(pdev, pos, old & ~bit);
+ in_8(mapped);
+ pci_write_config_word(pdev, pos, old);
+
+ iounmap(mapped);
+
+ return 0;
+}
+
+int eeh_pe_inject_mmio_error(struct pci_dev *pdev)
+{
+ return eeh_break_device(pdev);
+}
+
#ifdef CONFIG_DEBUG_FS
@@ -1689,7 +1773,6 @@ static ssize_t eeh_force_recover_write(struct file *filp,
static const struct file_operations eeh_force_recover_fops = {
.open = simple_open,
- .llseek = no_llseek,
.write = eeh_force_recover_write,
};
@@ -1733,104 +1816,10 @@ static ssize_t eeh_dev_check_write(struct file *filp,
static const struct file_operations eeh_dev_check_fops = {
.open = simple_open,
- .llseek = no_llseek,
.write = eeh_dev_check_write,
.read = eeh_debugfs_dev_usage,
};
-static int eeh_debugfs_break_device(struct pci_dev *pdev)
-{
- struct resource *bar = NULL;
- void __iomem *mapped;
- u16 old, bit;
- int i, pos;
-
- /* Do we have an MMIO BAR to disable? */
- for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
- struct resource *r = &pdev->resource[i];
-
- if (!r->flags || !r->start)
- continue;
- if (r->flags & IORESOURCE_IO)
- continue;
- if (r->flags & IORESOURCE_UNSET)
- continue;
-
- bar = r;
- break;
- }
-
- if (!bar) {
- pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n");
- return -ENXIO;
- }
-
- pci_err(pdev, "Going to break: %pR\n", bar);
-
- if (pdev->is_virtfn) {
-#ifndef CONFIG_PCI_IOV
- return -ENXIO;
-#else
- /*
- * VFs don't have a per-function COMMAND register, so the best
- * we can do is clear the Memory Space Enable bit in the PF's
- * SRIOV control reg.
- *
- * Unfortunately, this requires that we have a PF (i.e doesn't
- * work for a passed-through VF) and it has the potential side
- * effect of also causing an EEH on every other VF under the
- * PF. Oh well.
- */
- pdev = pdev->physfn;
- if (!pdev)
- return -ENXIO; /* passed through VFs have no PF */
-
- pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
- pos += PCI_SRIOV_CTRL;
- bit = PCI_SRIOV_CTRL_MSE;
-#endif /* !CONFIG_PCI_IOV */
- } else {
- bit = PCI_COMMAND_MEMORY;
- pos = PCI_COMMAND;
- }
-
- /*
- * Process here is:
- *
- * 1. Disable Memory space.
- *
- * 2. Perform an MMIO to the device. This should result in an error
- * (CA / UR) being raised by the device which results in an EEH
- * PE freeze. Using the in_8() accessor skips the eeh detection hook
- * so the freeze hook so the EEH Detection machinery won't be
- * triggered here. This is to match the usual behaviour of EEH
- * where the HW will asynchronously freeze a PE and it's up to
- * the kernel to notice and deal with it.
- *
- * 3. Turn Memory space back on. This is more important for VFs
- * since recovery will probably fail if we don't. For normal
- * the COMMAND register is reset as a part of re-initialising
- * the device.
- *
- * Breaking stuff is the point so who cares if it's racy ;)
- */
- pci_read_config_word(pdev, pos, &old);
-
- mapped = ioremap(bar->start, PAGE_SIZE);
- if (!mapped) {
- pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar);
- return -ENXIO;
- }
-
- pci_write_config_word(pdev, pos, old & ~bit);
- in_8(mapped);
- pci_write_config_word(pdev, pos, old);
-
- iounmap(mapped);
-
- return 0;
-}
-
static ssize_t eeh_dev_break_write(struct file *filp,
const char __user *user_buf,
size_t count, loff_t *ppos)
@@ -1842,7 +1831,7 @@ static ssize_t eeh_dev_break_write(struct file *filp,
if (IS_ERR(pdev))
return PTR_ERR(pdev);
- ret = eeh_debugfs_break_device(pdev);
+ ret = eeh_break_device(pdev);
pci_dev_put(pdev);
if (ret < 0)
@@ -1853,7 +1842,6 @@ static ssize_t eeh_dev_break_write(struct file *filp,
static const struct file_operations eeh_dev_break_fops = {
.open = simple_open,
- .llseek = no_llseek,
.write = eeh_dev_break_write,
.read = eeh_debugfs_dev_usage,
};
@@ -1900,7 +1888,6 @@ static ssize_t eeh_dev_can_recover(struct file *filp,
static const struct file_operations eeh_dev_can_recover_fops = {
.open = simple_open,
- .llseek = no_llseek,
.write = eeh_dev_can_recover,
.read = eeh_debugfs_dev_usage,
};
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 260273e56431..48ad0116f359 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -39,7 +39,7 @@ static int eeh_result_priority(enum pci_ers_result result)
case PCI_ERS_RESULT_NEED_RESET:
return 6;
default:
- WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", (int)result);
+ WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", result);
return 0;
}
};
@@ -60,7 +60,7 @@ static const char *pci_ers_result_name(enum pci_ers_result result)
case PCI_ERS_RESULT_NO_AER_DRIVER:
return "no AER driver";
default:
- WARN_ONCE(1, "Unknown result type: %d\n", (int)result);
+ WARN_ONCE(1, "Unknown result type: %d\n", result);
return "unknown";
}
};
@@ -257,13 +257,12 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn,
struct pci_driver *driver;
enum pci_ers_result new_result;
- pci_lock_rescan_remove();
pdev = edev->pdev;
if (pdev)
get_device(&pdev->dev);
- pci_unlock_rescan_remove();
if (!pdev) {
eeh_edev_info(edev, "no device");
+ *result = PCI_ERS_RESULT_DISCONNECT;
return;
}
device_lock(&pdev->dev);
@@ -304,8 +303,9 @@ static void eeh_pe_report(const char *name, struct eeh_pe *root,
struct eeh_dev *edev, *tmp;
pr_info("EEH: Beginning: '%s'\n", name);
- eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp)
- eeh_pe_report_edev(edev, fn, result);
+ eeh_for_each_pe(root, pe)
+ eeh_pe_for_each_dev(pe, edev, tmp)
+ eeh_pe_report_edev(edev, fn, result);
if (result)
pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n",
name, pci_ers_result_name(*result));
@@ -383,6 +383,8 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
if (!edev)
return;
+ pci_lock_rescan_remove();
+
/*
* The content in the config space isn't saved because
* the blocked config space on some adapters. We have
@@ -393,14 +395,19 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
if (list_is_last(&edev->entry, &edev->pe->edevs))
eeh_pe_restore_bars(edev->pe);
+ pci_unlock_rescan_remove();
return;
}
pdev = eeh_dev_to_pci_dev(edev);
- if (!pdev)
+ if (!pdev) {
+ pci_unlock_rescan_remove();
return;
+ }
pci_restore_state(pdev);
+
+ pci_unlock_rescan_remove();
}
/**
@@ -647,9 +654,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) {
eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
} else {
- pci_lock_rescan_remove();
pci_hp_remove_devices(bus);
- pci_unlock_rescan_remove();
}
/*
@@ -665,8 +670,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
if (rc)
return rc;
- pci_lock_rescan_remove();
-
/* Restore PE */
eeh_ops->configure_bridge(pe);
eeh_pe_restore_bars(pe);
@@ -674,7 +677,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
/* Clear frozen state */
rc = eeh_clear_pe_frozen_state(pe, false);
if (rc) {
- pci_unlock_rescan_remove();
return rc;
}
@@ -709,7 +711,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
pe->tstamp = tstamp;
pe->freeze_count = cnt;
- pci_unlock_rescan_remove();
return 0;
}
@@ -750,7 +751,7 @@ static void eeh_pe_cleanup(struct eeh_pe *pe)
* @pdev: pci_dev to check
*
* This function may return a false positive if we can't determine the slot's
- * presence state. This might happen for for PCIe slots if the PE containing
+ * presence state. This might happen for PCIe slots if the PE containing
* the upstream bridge is also frozen, or the bridge is part of the same PE
* as the device.
*
@@ -843,10 +844,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
{LIST_HEAD_INIT(rmv_data.removed_vf_list), 0};
int devices = 0;
+ pci_lock_rescan_remove();
+
bus = eeh_pe_bus_get(pe);
if (!bus) {
pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
__func__, pe->phb->global_number, pe->addr);
+ pci_unlock_rescan_remove();
return;
}
@@ -865,9 +869,18 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
devices++;
if (!devices) {
- pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n",
+ pr_warn("EEH: Frozen PHB#%x-PE#%x is empty!\n",
pe->phb->global_number, pe->addr);
- goto out; /* nothing to recover */
+ /*
+ * The device is removed, tear down its state, on powernv
+ * hotplug driver would take care of it but not on pseries,
+ * permanently disable the card as it is hot removed.
+ *
+ * In the case of powernv, note that the removal of device
+ * is covered by pci rescan lock, so no problem even if hotplug
+ * driver attempts to remove the device.
+ */
+ goto recover_failed;
}
/* Log the event */
@@ -898,7 +911,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
/* FIXME: Use the same format as dump_stack() */
pr_err("EEH: Call Trace:\n");
for (i = 0; i < pe->trace_entries; i++)
- pr_err("EEH: [%pK] %pS\n", ptrs[i], ptrs[i]);
+ pr_err("EEH: [%p] %pS\n", ptrs[i], ptrs[i]);
pe->trace_entries = 0;
}
@@ -1065,10 +1078,10 @@ recover_failed:
eeh_slot_error_detail(pe, EEH_LOG_PERM);
/* Notify all devices that they're about to go down. */
- eeh_set_channel_state(pe, pci_channel_io_perm_failure);
eeh_set_irq_state(pe, false);
eeh_pe_report("error_detected(permanent failure)", pe,
eeh_report_failure, NULL);
+ eeh_set_channel_state(pe, pci_channel_io_perm_failure);
/* Mark the PE to be removed permanently */
eeh_pe_state_mark(pe, EEH_PE_REMOVED);
@@ -1085,10 +1098,15 @@ recover_failed:
eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
- pci_lock_rescan_remove();
- pci_hp_remove_devices(bus);
- pci_unlock_rescan_remove();
+ bus = eeh_pe_bus_get(pe);
+ if (bus)
+ pci_hp_remove_devices(bus);
+ else
+ pr_err("%s: PCI bus for PHB#%x-PE#%x disappeared\n",
+ __func__, pe->phb->global_number, pe->addr);
+
/* The passed PE should no longer be used */
+ pci_unlock_rescan_remove();
return;
}
@@ -1105,6 +1123,8 @@ out:
eeh_clear_slot_attention(edev->pdev);
eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+
+ pci_unlock_rescan_remove();
}
/**
@@ -1123,6 +1143,7 @@ void eeh_handle_special_event(void)
unsigned long flags;
int rc;
+ pci_lock_rescan_remove();
do {
rc = eeh_ops->next_error(&pe);
@@ -1162,10 +1183,12 @@ void eeh_handle_special_event(void)
break;
case EEH_NEXT_ERR_NONE:
+ pci_unlock_rescan_remove();
return;
default:
pr_warn("%s: Invalid value %d from next_error()\n",
__func__, rc);
+ pci_unlock_rescan_remove();
return;
}
@@ -1177,7 +1200,9 @@ void eeh_handle_special_event(void)
if (rc == EEH_NEXT_ERR_FROZEN_PE ||
rc == EEH_NEXT_ERR_FENCED_PHB) {
eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+ pci_unlock_rescan_remove();
eeh_handle_normal_event(pe);
+ pci_lock_rescan_remove();
} else {
eeh_for_each_pe(pe, tmp_pe)
eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
@@ -1185,12 +1210,11 @@ void eeh_handle_special_event(void)
/* Notify all devices to be down */
eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
- eeh_set_channel_state(pe, pci_channel_io_perm_failure);
eeh_pe_report(
"error_detected(permanent failure)", pe,
eeh_report_failure, NULL);
+ eeh_set_channel_state(pe, pci_channel_io_perm_failure);
- pci_lock_rescan_remove();
list_for_each_entry(hose, &hose_list, list_node) {
phb_pe = eeh_phb_pe_get(hose);
if (!phb_pe ||
@@ -1209,7 +1233,6 @@ void eeh_handle_special_event(void)
}
pci_hp_remove_devices(bus);
}
- pci_unlock_rescan_remove();
}
/*
@@ -1219,4 +1242,6 @@ void eeh_handle_special_event(void)
if (rc == EEH_NEXT_ERR_DEAD_IOC)
break;
} while (rc != EEH_NEXT_ERR_NONE);
+
+ pci_unlock_rescan_remove();
}
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index d2873d17d2b1..e740101fadf3 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -24,10 +24,10 @@ static int eeh_pe_aux_size = 0;
static LIST_HEAD(eeh_phb_pe);
/**
- * eeh_set_pe_aux_size - Set PE auxillary data size
- * @size: PE auxillary data size
+ * eeh_set_pe_aux_size - Set PE auxiliary data size
+ * @size: PE auxiliary data size in bytes
*
- * Set PE auxillary data size
+ * Set PE auxiliary data size.
*/
void eeh_set_pe_aux_size(int size)
{
@@ -527,7 +527,7 @@ EXPORT_SYMBOL_GPL(eeh_pe_state_mark);
* eeh_pe_mark_isolated
* @pe: EEH PE
*
- * Record that a PE has been isolated by marking the PE and it's children as
+ * Record that a PE has been isolated by marking the PE and its children as
* EEH_PE_ISOLATED (and EEH_PE_CFG_BLOCKED, if required) and their PCI devices
* as pci_channel_io_frozen.
*/
@@ -671,11 +671,12 @@ static void eeh_bridge_check_link(struct eeh_dev *edev)
eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
/* Check link */
- eeh_ops->read_config(edev, cap + PCI_EXP_LNKCAP, 4, &val);
- if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
- eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val);
- msleep(1000);
- return;
+ if (edev->pdev) {
+ if (!edev->pdev->link_active_reporting) {
+ eeh_edev_dbg(edev, "No link reporting capability\n");
+ msleep(1000);
+ return;
+ }
}
/* Wait the link is up until timeout (5s) */
@@ -850,6 +851,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
{
struct eeh_dev *edev;
struct pci_dev *pdev;
+ struct pci_bus *bus = NULL;
if (pe->type & EEH_PE_PHB)
return pe->phb->bus;
@@ -860,9 +862,11 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
/* Retrieve the parent PCI bus of first (top) PCI device */
edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry);
+ pci_lock_rescan_remove();
pdev = eeh_dev_to_pci_dev(edev);
if (pdev)
- return pdev->bus;
+ bus = pdev->bus;
+ pci_unlock_rescan_remove();
- return NULL;
+ return bus;
}
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 1d599df6f169..f4a8c9877249 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -18,6 +18,8 @@
#include <linux/err.h>
#include <linux/sys.h>
#include <linux/threads.h>
+#include <linux/linkage.h>
+
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
@@ -27,7 +29,6 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/ptrace.h>
-#include <asm/export.h>
#include <asm/feature-fixups.h>
#include <asm/barrier.h>
#include <asm/kup.h>
@@ -49,7 +50,7 @@
*/
.align 12
-#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
+#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_E500)
.globl prepare_transfer_to_handler
prepare_transfer_to_handler:
/* if from kernel, check interrupted DOZE/NAP mode */
@@ -68,23 +69,24 @@ prepare_transfer_to_handler:
lwz r9,_MSR(r11) /* if sleeping, clear MSR.EE */
rlwinm r9,r9,0,~MSR_EE
lwz r12,_LINK(r11) /* and return to address in LR */
- lwz r2, GPR2(r11)
+ REST_GPR(2, r11)
b fast_exception_return
_ASM_NOKPROBE_SYMBOL(prepare_transfer_to_handler)
-#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_E500 */
+#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_PPC_E500 */
#if defined(CONFIG_PPC_KUEP) && defined(CONFIG_PPC_BOOK3S_32)
- .globl __kuep_lock
-__kuep_lock:
+SYM_FUNC_START(__kuep_lock)
lwz r9, THREAD+THSR0(r2)
update_user_segments_by_4 r9, r10, r11, r12
blr
+SYM_FUNC_END(__kuep_lock)
-__kuep_unlock:
+SYM_FUNC_START_LOCAL(__kuep_unlock)
lwz r9, THREAD+THSR0(r2)
rlwinm r9,r9,0,~SR_NX
update_user_segments_by_4 r9, r10, r11, r12
blr
+SYM_FUNC_END(__kuep_unlock)
.macro kuep_lock
bl __kuep_lock
@@ -101,11 +103,12 @@ __kuep_unlock:
.globl transfer_to_syscall
transfer_to_syscall:
+ stw r3, ORIG_GPR3(r1)
stw r11, GPR1(r1)
stw r11, 0(r1)
mflr r12
stw r12, _LINK(r1)
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
#endif
lis r12,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
@@ -113,7 +116,7 @@ transfer_to_syscall:
addi r12,r12,STACK_FRAME_REGS_MARKER@l
stw r9,_MSR(r1)
li r2, INTERRUPT_SYSCALL
- stw r12,8(r1)
+ stw r12,STACK_INT_FRAME_MARKER(r1)
stw r2,_TRAP(r1)
SAVE_GPR(0, r1)
SAVE_GPRS(3, 8, r1)
@@ -121,21 +124,22 @@ transfer_to_syscall:
SAVE_NVGPRS(r1)
kuep_lock
- /* Calling convention has r9 = orig r0, r10 = regs */
- addi r10,r1,STACK_FRAME_OVERHEAD
- mr r9,r0
+ /* Calling convention has r3 = regs, r4 = orig r0 */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ mr r4,r0
bl system_call_exception
ret_from_syscall:
- addi r4,r1,STACK_FRAME_OVERHEAD
+ addi r4,r1,STACK_INT_FRAME_REGS
li r5,0
bl syscall_exit_prepare
#ifdef CONFIG_PPC_47x
lis r4,icache_44x_need_flush@ha
lwz r5,icache_44x_need_flush@l(r4)
cmplwi cr0,r5,0
- bne- 2f
+ bne- .L44x_icache_flush
#endif /* CONFIG_PPC_47x */
+.L44x_icache_flush_return:
kuep_unlock
lwz r4,_LINK(r1)
lwz r5,_CCR(r1)
@@ -143,7 +147,7 @@ ret_from_syscall:
lwz r7,_NIP(r1)
lwz r8,_MSR(r1)
cmpwi r3,0
- lwz r3,GPR3(r1)
+ REST_GPR(3, r1)
syscall_exit_finish:
mtspr SPRN_SRR0,r7
mtspr SPRN_SRR1,r8
@@ -151,12 +155,9 @@ syscall_exit_finish:
bne 3f
mtcr r5
-1: lwz r2,GPR2(r1)
- lwz r1,GPR1(r1)
+1: REST_GPR(2, r1)
+ REST_GPR(1, r1)
rfi
-#ifdef CONFIG_40x
- b . /* Prevent prefetch past rfi */
-#endif
3: mtcr r5
lwz r4,_CTR(r1)
@@ -164,29 +165,27 @@ syscall_exit_finish:
REST_NVGPRS(r1)
mtctr r4
mtxer r5
- lwz r0,GPR0(r1)
- lwz r3,GPR3(r1)
- REST_GPRS(4, 11, r1)
- lwz r12,GPR12(r1)
+ REST_GPR(0, r1)
+ REST_GPRS(3, 12, r1)
b 1b
#ifdef CONFIG_44x
-2: li r7,0
+.L44x_icache_flush:
+ li r7,0
iccci r0,r0
stw r7,icache_44x_need_flush@l(r4)
- b 1b
+ b .L44x_icache_flush_return
#endif /* CONFIG_44x */
.globl ret_from_fork
ret_from_fork:
REST_NVGPRS(r1)
bl schedule_tail
- li r3,0
+ li r3,0 /* fork() return value */
b ret_from_syscall
- .globl ret_from_kernel_thread
-ret_from_kernel_thread:
- REST_NVGPRS(r1)
+ .globl ret_from_kernel_user_thread
+ret_from_kernel_user_thread:
bl schedule_tail
mtctr r14
mr r3,r15
@@ -195,77 +194,34 @@ ret_from_kernel_thread:
li r3,0
b ret_from_syscall
-/*
- * This routine switches between two different tasks. The process
- * state of one is saved on its kernel stack. Then the state
- * of the other is restored from its kernel stack. The memory
- * management hardware is updated to the second process's state.
- * Finally, we can return to the second process.
- * On entry, r3 points to the THREAD for the current task, r4
- * points to the THREAD for the new task.
- *
- * This routine is always called with interrupts disabled.
- *
- * Note: there are two ways to get to the "going out" portion
- * of this code; either by coming in via the entry (_switch)
- * or via "fork" which must set up an environment equivalent
- * to the "_switch" path. If you change this , you'll have to
- * change the fork code also.
- *
- * The code which creates the new task context is in 'copy_thread'
- * in arch/ppc/kernel/process.c
- */
-_GLOBAL(_switch)
- stwu r1,-INT_FRAME_SIZE(r1)
- mflr r0
- stw r0,INT_FRAME_SIZE+4(r1)
- /* r3-r12 are caller saved -- Cort */
- SAVE_NVGPRS(r1)
- stw r0,_NIP(r1) /* Return to switch caller */
- mfcr r10
- stw r10,_CCR(r1)
- stw r1,KSP(r3) /* Set old stack pointer */
-
-#ifdef CONFIG_SMP
- /* We need a sync somewhere here to make sure that if the
- * previous task gets rescheduled on another CPU, it sees all
- * stores it has performed on this one.
+ .globl start_kernel_thread
+start_kernel_thread:
+ bl schedule_tail
+ mtctr r14
+ mr r3,r15
+ PPC440EP_ERR42
+ bctrl
+ /*
+ * This must not return. We actually want to BUG here, not WARN,
+ * because BUG will exit the process which is what the kernel thread
+ * should have done, which may give some hope of continuing.
*/
- sync
-#endif /* CONFIG_SMP */
-
- tophys(r0,r4)
- mtspr SPRN_SPRG_THREAD,r0 /* Update current THREAD phys addr */
- lwz r1,KSP(r4) /* Load new stack pointer */
-
- /* save the old current 'last' for return value */
- mr r3,r2
- addi r2,r4,-THREAD /* Update current */
-
- lwz r0,_CCR(r1)
- mtcrf 0xFF,r0
- /* r3-r12 are destroyed -- Cort */
- REST_NVGPRS(r1)
-
- lwz r4,_NIP(r1) /* Return to _switch caller in new task */
- mtlr r4
- addi r1,r1,INT_FRAME_SIZE
- blr
+100: trap
+ EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0
.globl fast_exception_return
fast_exception_return:
-#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+#ifndef CONFIG_BOOKE
andi. r10,r9,MSR_RI /* check for recoverable interrupt */
beq 3f /* if not, we've got problems */
#endif
-2: REST_GPRS(3, 6, r11)
- lwz r10,_CCR(r11)
- REST_GPRS(1, 2, r11)
+2: lwz r10,_CCR(r11)
+ REST_GPRS(1, 6, r11)
mtcr r10
lwz r10,_LINK(r11)
mtlr r10
- /* Clear the exception_marker on the stack to avoid confusing stacktrace */
+ /* Clear the exception marker on the stack to avoid confusing stacktrace */
li r10, 0
stw r10, 8(r11)
REST_GPR(10, r11)
@@ -276,11 +232,8 @@ fast_exception_return:
mtspr SPRN_SRR0,r12
REST_GPR(9, r11)
REST_GPR(12, r11)
- lwz r11,GPR11(r11)
+ REST_GPR(11, r11)
rfi
-#ifdef CONFIG_40x
- b . /* Prevent prefetch past rfi */
-#endif
_ASM_NOKPROBE_SYMBOL(fast_exception_return)
/* aargh, a nonrecoverable interrupt, panic */
@@ -295,7 +248,7 @@ _ASM_NOKPROBE_SYMBOL(fast_exception_return)
.globl interrupt_return
interrupt_return:
lwz r4,_MSR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
andi. r0,r4,MSR_PR
beq .Lkernel_interrupt_return
bl interrupt_exit_user_prepare
@@ -322,7 +275,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
li r0,0
/*
- * Leaving a stale exception_marker on the stack can confuse
+ * Leaving a stale exception marker on the stack can confuse
* the reliable stack unwinder later on. Clear it.
*/
stw r0,8(r1)
@@ -337,9 +290,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
REST_GPR(0, r1)
REST_GPR(1, r1)
rfi
-#ifdef CONFIG_40x
- b . /* Prevent prefetch past rfi */
-#endif
.Lrestore_nvgprs:
REST_NVGPRS(r1)
@@ -374,7 +324,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
mtspr SPRN_XER,r5
/*
- * Leaving a stale exception_marker on the stack can confuse
+ * Leaving a stale exception marker on the stack can confuse
* the reliable stack unwinder later on. Clear it.
*/
stw r0,8(r1)
@@ -387,9 +337,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
REST_GPR(0, r1)
REST_GPR(1, r1)
rfi
-#ifdef CONFIG_40x
- b . /* Prevent prefetch past rfi */
-#endif
1: /*
* Emulate stack store with update. New r1 value was already calculated
@@ -416,12 +363,9 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
mfspr r9, SPRN_SPRG_SCRATCH0
#endif
rfi
-#ifdef CONFIG_40x
- b . /* Prevent prefetch past rfi */
-#endif
_ASM_NOKPROBE_SYMBOL(interrupt_return)
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_BOOKE
/*
* Returning from a critical interrupt in user mode doesn't need
@@ -436,26 +380,14 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
* time of the critical interrupt.
*
*/
-#ifdef CONFIG_40x
-#define PPC_40x_TURN_OFF_MSR_DR \
- /* avoid any possible TLB misses here by turning off MSR.DR, we \
- * assume the instructions here are mapped by a pinned TLB entry */ \
- li r10,MSR_IR; \
- mtmsr r10; \
- isync; \
- tophys(r1, r1);
-#else
-#define PPC_40x_TURN_OFF_MSR_DR
-#endif
#define RET_FROM_EXC_LEVEL(exc_lvl_srr0, exc_lvl_srr1, exc_lvl_rfi) \
REST_NVGPRS(r1); \
lwz r3,_MSR(r1); \
andi. r3,r3,MSR_PR; \
bne interrupt_return; \
- lwz r0,GPR0(r1); \
- lwz r2,GPR2(r1); \
- REST_GPRS(3, 8, r1); \
+ REST_GPR(0, r1); \
+ REST_GPRS(2, 8, r1); \
lwz r10,_XER(r1); \
lwz r11,_CTR(r1); \
mtspr SPRN_XER,r10; \
@@ -465,7 +397,6 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
mtlr r11; \
lwz r10,_CCR(r1); \
mtcrf 0xff,r10; \
- PPC_40x_TURN_OFF_MSR_DR; \
lwz r9,_DEAR(r1); \
lwz r10,_ESR(r1); \
mtspr SPRN_DEAR,r9; \
@@ -474,11 +405,8 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
lwz r12,_MSR(r1); \
mtspr exc_lvl_srr0,r11; \
mtspr exc_lvl_srr1,r12; \
- lwz r9,GPR9(r1); \
- lwz r12,GPR12(r1); \
- lwz r10,GPR10(r1); \
- lwz r11,GPR11(r1); \
- lwz r1,GPR1(r1); \
+ REST_GPRS(9, 12, r1); \
+ REST_GPR(1, r1); \
exc_lvl_rfi; \
b .; /* prevent prefetch past exc_lvl_rfi */
@@ -488,7 +416,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
mtspr SPRN_##exc_lvl_srr0,r9; \
mtspr SPRN_##exc_lvl_srr1,r10;
-#if defined(CONFIG_PPC_BOOK3E_MMU)
+#if defined(CONFIG_PPC_E500)
#ifdef CONFIG_PHYS_64BIT
#define RESTORE_MAS7 \
lwz r11,MAS7(r1); \
@@ -516,20 +444,6 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
#define RESTORE_MMU_REGS
#endif
-#ifdef CONFIG_40x
- .globl ret_from_crit_exc
-ret_from_crit_exc:
- lis r9,crit_srr0@ha;
- lwz r9,crit_srr0@l(r9);
- lis r10,crit_srr1@ha;
- lwz r10,crit_srr1@l(r10);
- mtspr SPRN_SRR0,r9;
- mtspr SPRN_SRR1,r10;
- RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, PPC_RFCI)
-_ASM_NOKPROBE_SYMBOL(ret_from_crit_exc)
-#endif /* CONFIG_40x */
-
-#ifdef CONFIG_BOOKE
.globl ret_from_crit_exc
ret_from_crit_exc:
RESTORE_xSRR(SRR0,SRR1);
@@ -554,4 +468,3 @@ ret_from_mcheck_exc:
RET_FROM_EXC_LEVEL(SPRN_MCSRR0, SPRN_MCSRR1, PPC_RFMCI)
_ASM_NOKPROBE_SYMBOL(ret_from_mcheck_exc)
#endif /* CONFIG_BOOKE */
-#endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
index 69a912550577..6a414ed5a411 100644
--- a/arch/powerpc/kernel/epapr_hcalls.S
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -3,6 +3,7 @@
* Copyright (C) 2012 Freescale Semiconductor, Inc.
*/
+#include <linux/export.h>
#include <linux/threads.h>
#include <asm/epapr_hcalls.h>
#include <asm/reg.h>
@@ -12,7 +13,6 @@
#include <asm/ppc_asm.h>
#include <asm/asm-compat.h>
#include <asm/asm-offsets.h>
-#include <asm/export.h>
#ifndef CONFIG_PPC64
/* epapr_ev_idle() was derived from e500_idle() */
@@ -21,7 +21,13 @@ _GLOBAL(epapr_ev_idle)
ori r4, r4,_TLF_NAPPING /* so when we take an exception */
PPC_STL r4, TI_LOCAL_FLAGS(r2) /* it will return to our caller */
+#ifdef CONFIG_BOOKE
wrteei 1
+#else
+ mfmsr r4
+ ori r4, r4, MSR_EE
+ mtmsr r4
+#endif
idle_loop:
LOAD_REG_IMMEDIATE(r11, EV_HCALL_TOKEN(EV_IDLE))
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index d4b8aff20815..247ab2acaccc 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -9,7 +9,7 @@
#include <linux/of_fdt.h>
#include <asm/epapr_hcalls.h>
#include <asm/cacheflush.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/machdep.h>
#include <asm/inst.h>
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 67dc4e3179a0..63f6b9f513a4 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -5,6 +5,7 @@
* Copyright (C) 2007 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
*/
+#include <linux/linkage.h>
#include <linux/threads.h>
#include <asm/reg.h>
#include <asm/page.h>
@@ -13,7 +14,6 @@
#include <asm/cputable.h>
#include <asm/setup.h>
#include <asm/thread_info.h>
-#include <asm/reg_a2.h>
#include <asm/exception-64e.h>
#include <asm/bug.h>
#include <asm/irqflags.h>
@@ -66,7 +66,7 @@
#define SPECIAL_EXC_LOAD(reg, name) \
ld reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1)
-special_reg_save:
+SYM_CODE_START_LOCAL(special_reg_save)
/*
* We only need (or have stack space) to save this stuff if
* we interrupted the kernel.
@@ -131,8 +131,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
SPECIAL_EXC_STORE(r10,CSRR1)
blr
+SYM_CODE_END(special_reg_save)
-ret_from_level_except:
+SYM_CODE_START_LOCAL(ret_from_level_except)
ld r3,_MSR(r1)
andi. r3,r3,MSR_PR
beq 1f
@@ -206,6 +207,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
mtxer r11
blr
+SYM_CODE_END(ret_from_level_except)
.macro ret_from_level srr0 srr1 paca_ex scratch
bl ret_from_level_except
@@ -216,17 +218,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
mtlr r10
mtcr r11
- ld r10,GPR10(r1)
- ld r11,GPR11(r1)
- ld r12,GPR12(r1)
+ REST_GPRS(10, 12, r1)
mtspr \scratch,r0
std r10,\paca_ex+EX_R10(r13);
std r11,\paca_ex+EX_R11(r13);
ld r10,_NIP(r1)
ld r11,_MSR(r1)
- ld r0,GPR0(r1)
- ld r1,GPR1(r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
mtspr \srr0,r10
mtspr \srr1,r11
ld r10,\paca_ex+EX_R10(r13)
@@ -234,13 +234,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
mfspr r13,\scratch
.endm
-ret_from_crit_except:
+SYM_CODE_START_LOCAL(ret_from_crit_except)
ret_from_level SPRN_CSRR0 SPRN_CSRR1 PACA_EXCRIT SPRN_SPRG_CRIT_SCRATCH
rfci
+SYM_CODE_END(ret_from_crit_except)
-ret_from_mc_except:
+SYM_CODE_START_LOCAL(ret_from_mc_except)
ret_from_level SPRN_MCSRR0 SPRN_MCSRR1 PACA_EXMC SPRN_SPRG_MC_SCRATCH
rfmci
+SYM_CODE_END(ret_from_mc_except)
/* Exception prolog code for all exceptions */
#define EXCEPTION_PROLOG(n, intnum, type, addition) \
@@ -291,7 +293,6 @@ ret_from_mc_except:
#define SPRN_MC_SRR0 SPRN_MCSRR0
#define SPRN_MC_SRR1 SPRN_MCSRR1
-#ifdef CONFIG_PPC_FSL_BOOK3E
#define GEN_BTB_FLUSH \
START_BTB_FLUSH_SECTION \
beq 1f; \
@@ -307,13 +308,6 @@ ret_from_mc_except:
#define DBG_BTB_FLUSH CRIT_BTB_FLUSH
#define MC_BTB_FLUSH CRIT_BTB_FLUSH
#define GDBELL_BTB_FLUSH GEN_BTB_FLUSH
-#else
-#define GEN_BTB_FLUSH
-#define CRIT_BTB_FLUSH
-#define DBG_BTB_FLUSH
-#define MC_BTB_FLUSH
-#define GDBELL_BTB_FLUSH
-#endif
#define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \
EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n))
@@ -368,29 +362,27 @@ ret_from_mc_except:
std r14,PACA_EXMC+EX_R14(r13); \
std r15,PACA_EXMC+EX_R15(r13)
-
/* Core exception code for all exceptions except TLB misses. */
#define EXCEPTION_COMMON_LVL(n, scratch, excf) \
exc_##n##_common: \
- std r0,GPR0(r1); /* save r0 in stackframe */ \
- std r2,GPR2(r1); /* save r2 in stackframe */ \
- SAVE_GPRS(3, 9, r1); /* save r3 - r9 in stackframe */ \
+ SAVE_GPR(0, r1); /* save r0 in stackframe */ \
+ SAVE_GPRS(2, 9, r1); /* save r2 - r9 in stackframe */ \
std r10,_NIP(r1); /* save SRR0 to stackframe */ \
std r11,_MSR(r1); /* save SRR1 to stackframe */ \
beq 2f; /* if from kernel mode */ \
2: ld r3,excf+EX_R10(r13); /* get back r10 */ \
ld r4,excf+EX_R11(r13); /* get back r11 */ \
mfspr r5,scratch; /* get back r13 */ \
- std r12,GPR12(r1); /* save r12 in stackframe */ \
- ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \
+ SAVE_GPR(12, r1); /* save r12 in stackframe */ \
+ LOAD_PACA_TOC(); /* get kernel TOC into r2 */ \
mflr r6; /* save LR in stackframe */ \
mfctr r7; /* save CTR in stackframe */ \
mfspr r8,SPRN_XER; /* save XER in stackframe */ \
ld r9,excf+EX_R1(r13); /* load orig r1 back from PACA */ \
lwz r10,excf+EX_CR(r13); /* load orig CR back from PACA */ \
lbz r11,PACAIRQSOFTMASK(r13); /* get current IRQ softe */ \
- ld r12,exception_marker@toc(r2); \
- li r0,0; \
+ LOAD_REG_IMMEDIATE(r12, STACK_FRAME_REGS_MARKER); \
+ ZEROIZE_GPR(0); \
std r3,GPR10(r1); /* save r10 to stackframe */ \
std r4,GPR11(r1); /* save r11 to stackframe */ \
std r5,GPR13(r1); /* save it to stackframe */ \
@@ -402,10 +394,11 @@ exc_##n##_common: \
std r10,_CCR(r1); /* store orig CR in stackframe */ \
std r9,GPR1(r1); /* store stack frame back link */ \
std r11,SOFTE(r1); /* and save it to stackframe */ \
- std r12,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ \
+ std r12,STACK_INT_FRAME_MARKER(r1); /* mark the frame */ \
std r3,_TRAP(r1); /* set trap number */ \
std r0,RESULT(r1); /* clear regs->result */ \
- SAVE_NVGPRS(r1);
+ SAVE_NVGPRS(r1); \
+ SANITIZE_NVGPRS(); /* minimise speculation influence */
#define EXCEPTION_COMMON(n) \
EXCEPTION_COMMON_LVL(n, SPRN_SPRG_GEN_SCRATCH, PACA_EXGEN)
@@ -466,16 +459,10 @@ exc_##n##_bad_stack: \
EXCEPTION_COMMON(trapnum) \
ack(r8); \
CHECK_NAPPING(); \
- addi r3,r1,STACK_FRAME_OVERHEAD; \
+ addi r3,r1,STACK_INT_FRAME_REGS; \
bl hdlr; \
b interrupt_return
-/* This value is used to mark exception frames on the stack. */
- .section ".toc","aw"
-exception_marker:
- .tc ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER
-
-
/*
* And here we have the exception vectors !
*/
@@ -498,8 +485,8 @@ interrupt_base_book3e: /* fake trap */
EXCEPTION_STUB(0x160, decrementer) /* 0x0900 */
EXCEPTION_STUB(0x180, fixed_interval) /* 0x0980 */
EXCEPTION_STUB(0x1a0, watchdog) /* 0x09f0 */
- EXCEPTION_STUB(0x1c0, data_tlb_miss)
- EXCEPTION_STUB(0x1e0, instruction_tlb_miss)
+ EXCEPTION_STUB(0x1c0, data_tlb_miss_bolted)
+ EXCEPTION_STUB(0x1e0, instruction_tlb_miss_bolted)
EXCEPTION_STUB(0x200, altivec_unavailable)
EXCEPTION_STUB(0x220, altivec_assist)
EXCEPTION_STUB(0x260, perfmon)
@@ -521,7 +508,7 @@ __end_interrupts:
EXCEPTION_COMMON_CRIT(0x100)
bl special_reg_save
CHECK_NAPPING();
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl unknown_nmi_exception
b ret_from_crit_except
@@ -532,7 +519,7 @@ __end_interrupts:
EXCEPTION_COMMON_MC(0x000)
bl special_reg_save
CHECK_NAPPING();
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl machine_check_exception
b ret_from_mc_except
@@ -587,7 +574,7 @@ __end_interrupts:
std r14,_ESR(r1)
ld r14,PACA_EXGEN+EX_R14(r13)
EXCEPTION_COMMON(0x700)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl program_check_exception
REST_NVGPRS(r1)
b interrupt_return
@@ -603,7 +590,7 @@ __end_interrupts:
beq- 1f
bl load_up_fpu
b fast_interrupt_return
-1: addi r3,r1,STACK_FRAME_OVERHEAD
+1: addi r3,r1,STACK_INT_FRAME_REGS
bl kernel_fp_unavailable_exception
b interrupt_return
@@ -623,7 +610,7 @@ BEGIN_FTR_SECTION
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl altivec_unavailable_exception
b interrupt_return
@@ -633,7 +620,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
BOOKE_INTERRUPT_ALTIVEC_ASSIST,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x220)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
bl altivec_assist_exception
@@ -660,7 +647,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
EXCEPTION_COMMON_CRIT(0x9f0)
bl special_reg_save
CHECK_NAPPING();
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
#ifdef CONFIG_BOOKE_WDT
bl WatchdogException
#else
@@ -681,7 +668,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
NORMAL_EXCEPTION_PROLOG(0xf20, BOOKE_INTERRUPT_AP_UNAVAIL,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0xf20)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl unknown_exception
b interrupt_return
@@ -704,9 +691,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
beq+ 1f
#ifdef CONFIG_RELOCATABLE
- ld r15,PACATOC(r13)
- ld r14,interrupt_base_book3e@got(r15)
- ld r15,__end_interrupts@got(r15)
+ __LOAD_PACA_TOC(r15)
+ LOAD_REG_ADDR_ALTTOC(r14, r15, interrupt_base_book3e)
+ LOAD_REG_ADDR_ALTTOC(r15, r15, __end_interrupts)
cmpld cr0,r10,r14
cmpld cr1,r10,r15
#else
@@ -748,7 +735,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
ld r14,PACA_EXCRIT+EX_R14(r13)
ld r15,PACA_EXCRIT+EX_R15(r13)
EXCEPTION_COMMON_CRIT(0xd00)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl DebugException
REST_NVGPRS(r1)
b interrupt_return
@@ -775,9 +762,9 @@ kernel_dbg_exc:
beq+ 1f
#ifdef CONFIG_RELOCATABLE
- ld r15,PACATOC(r13)
- ld r14,interrupt_base_book3e@got(r15)
- ld r15,__end_interrupts@got(r15)
+ __LOAD_PACA_TOC(r15)
+ LOAD_REG_ADDR_ALTTOC(r14, r15, interrupt_base_book3e)
+ LOAD_REG_ADDR_ALTTOC(r15, r15, __end_interrupts)
cmpld cr0,r10,r14
cmpld cr1,r10,r15
#else
@@ -819,7 +806,7 @@ kernel_dbg_exc:
ld r14,PACA_EXDBG+EX_R14(r13)
ld r15,PACA_EXDBG+EX_R15(r13)
EXCEPTION_COMMON_DBG(0xd08)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl DebugException
REST_NVGPRS(r1)
b interrupt_return
@@ -829,7 +816,14 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x260)
CHECK_NAPPING()
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
+ /*
+ * XXX: Returning from performance_monitor_exception taken as a
+ * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return
+ * and could cause bugs in return or elsewhere. That case should just
+ * restore registers and return. There is a workaround for one known
+ * problem in interrupt_exit_kernel_prepare().
+ */
bl performance_monitor_exception
b interrupt_return
@@ -844,7 +838,7 @@ kernel_dbg_exc:
EXCEPTION_COMMON_CRIT(0x2a0)
bl special_reg_save
CHECK_NAPPING();
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl unknown_nmi_exception
b ret_from_crit_except
@@ -856,7 +850,7 @@ kernel_dbg_exc:
GDBELL_EXCEPTION_PROLOG(0x2c0, BOOKE_INTERRUPT_GUEST_DBELL,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x2c0)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl unknown_exception
b interrupt_return
@@ -867,7 +861,7 @@ kernel_dbg_exc:
EXCEPTION_COMMON_CRIT(0x2e0)
bl special_reg_save
CHECK_NAPPING();
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl unknown_nmi_exception
b ret_from_crit_except
@@ -876,7 +870,7 @@ kernel_dbg_exc:
NORMAL_EXCEPTION_PROLOG(0x310, BOOKE_INTERRUPT_HV_SYSCALL,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x310)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl unknown_exception
b interrupt_return
@@ -885,7 +879,7 @@ kernel_dbg_exc:
NORMAL_EXCEPTION_PROLOG(0x320, BOOKE_INTERRUPT_HV_PRIV,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x320)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl unknown_exception
b interrupt_return
@@ -894,15 +888,15 @@ kernel_dbg_exc:
NORMAL_EXCEPTION_PROLOG(0x340, BOOKE_INTERRUPT_LRAT_ERROR,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x340)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
bl unknown_exception
b interrupt_return
.macro SEARCH_RESTART_TABLE
#ifdef CONFIG_RELOCATABLE
- ld r11,PACATOC(r13)
- ld r14,__start___restart_table@got(r11)
- ld r15,__stop___restart_table@got(r11)
+ __LOAD_PACA_TOC(r11)
+ LOAD_REG_ADDR_ALTTOC(r14, r11, __start___restart_table)
+ LOAD_REG_ADDR_ALTTOC(r15, r11, __stop___restart_table)
#else
LOAD_REG_IMMEDIATE_SYM(r14, r11, __start___restart_table)
LOAD_REG_IMMEDIATE_SYM(r15, r11, __stop___restart_table)
@@ -988,20 +982,22 @@ masked_interrupt_book3e_0x2c0:
* r14 and r15 containing the fault address and error code, with the
* original values stashed away in the PACA
*/
-storage_fault_common:
- addi r3,r1,STACK_FRAME_OVERHEAD
+SYM_CODE_START_LOCAL(storage_fault_common)
+ addi r3,r1,STACK_INT_FRAME_REGS
bl do_page_fault
b interrupt_return
+SYM_CODE_END(storage_fault_common)
/*
* Alignment exception doesn't fit entirely in the 0x100 bytes so it
* continues here.
*/
-alignment_more:
- addi r3,r1,STACK_FRAME_OVERHEAD
+SYM_CODE_START_LOCAL(alignment_more)
+ addi r3,r1,STACK_INT_FRAME_REGS
bl alignment_exception
REST_NVGPRS(r1)
b interrupt_return
+SYM_CODE_END(alignment_more)
/*
* Trampolines used when spotting a bad kernel stack pointer in
@@ -1040,8 +1036,7 @@ BAD_STACK_TRAMPOLINE(0xe00)
BAD_STACK_TRAMPOLINE(0xf00)
BAD_STACK_TRAMPOLINE(0xf20)
- .globl bad_stack_book3e
-bad_stack_book3e:
+_GLOBAL(bad_stack_book3e)
/* XXX: Needs to make SPRN_SPRG_GEN depend on exception type */
mfspr r10,SPRN_SRR0; /* read SRR0 before touching stack */
ld r1,PACAEMERGSP(r13)
@@ -1056,15 +1051,14 @@ bad_stack_book3e:
mfspr r11,SPRN_ESR
std r10,_DEAR(r1)
std r11,_ESR(r1)
- std r0,GPR0(r1); /* save r0 in stackframe */ \
- std r2,GPR2(r1); /* save r2 in stackframe */ \
- SAVE_GPRS(3, 9, r1); /* save r3 - r9 in stackframe */ \
+ SAVE_GPR(0, r1); /* save r0 in stackframe */ \
+ SAVE_GPRS(2, 9, r1); /* save r2 - r9 in stackframe */ \
ld r3,PACA_EXGEN+EX_R10(r13);/* get back r10 */ \
ld r4,PACA_EXGEN+EX_R11(r13);/* get back r11 */ \
mfspr r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 XXX can be wrong */ \
std r3,GPR10(r1); /* save r10 to stackframe */ \
std r4,GPR11(r1); /* save r11 to stackframe */ \
- std r12,GPR12(r1); /* save r12 in stackframe */ \
+ SAVE_GPR(12, r1); /* save r12 in stackframe */ \
std r5,GPR13(r1); /* save it to stackframe */ \
mflr r10
mfctr r11
@@ -1072,15 +1066,15 @@ bad_stack_book3e:
std r10,_LINK(r1)
std r11,_CTR(r1)
std r12,_XER(r1)
- SAVE_GPRS(14, 31, r1)
+ SAVE_NVGPRS(r1)
lhz r12,PACA_TRAP_SAVE(r13)
std r12,_TRAP(r1)
addi r11,r1,INT_FRAME_SIZE
std r11,0(r1)
- li r12,0
+ ZEROIZE_GPR(12)
std r12,0(r11)
- ld r2,PACATOC(r13)
-1: addi r3,r1,STACK_FRAME_OVERHEAD
+ LOAD_PACA_TOC()
+1: addi r3,r1,STACK_INT_FRAME_REGS
bl kernel_bad_stack
b 1b
@@ -1296,8 +1290,7 @@ have_hes:
* ever takes any parameters, the SCOM code must also be updated to
* provide them.
*/
- .globl a2_tlbinit_code_start
-a2_tlbinit_code_start:
+_GLOBAL(a2_tlbinit_code_start)
ori r11,r3,MAS0_WQ_ALLWAYS
oris r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */
@@ -1320,8 +1313,8 @@ a2_tlbinit_after_linear_map:
/* Now we branch the new virtual address mapped by this entry */
#ifdef CONFIG_RELOCATABLE
- ld r5,PACATOC(r13)
- ld r3,1f@got(r5)
+ __LOAD_PACA_TOC(r5)
+ LOAD_REG_ADDR_ALTTOC(r3, r5, 1f)
#else
LOAD_REG_IMMEDIATE_SYM(r3, r5, 1f)
#endif
@@ -1490,8 +1483,7 @@ _GLOBAL(book3e_secondary_thread_init)
mflr r28
b 3b
- .globl init_core_book3e
-init_core_book3e:
+_GLOBAL(init_core_book3e)
/* Establish the interrupt vector base */
tovirt(r2,r2)
LOAD_REG_ADDR(r3, interrupt_base_book3e)
@@ -1499,7 +1491,7 @@ init_core_book3e:
sync
blr
-init_thread_book3e:
+SYM_CODE_START_LOCAL(init_thread_book3e)
lis r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h
mtspr SPRN_EPCR,r3
@@ -1513,6 +1505,7 @@ init_thread_book3e:
mtspr SPRN_TSR,r3
blr
+SYM_CODE_END(init_thread_book3e)
_GLOBAL(__setup_base_ivors)
SET_IVOR(0, 0x020) /* Critical Input */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index b66dd6f775a4..b7229430ca94 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -13,6 +13,7 @@
*
*/
+#include <linux/linkage.h>
#include <asm/hw_irq.h>
#include <asm/exception-64s.h>
#include <asm/ptrace.h>
@@ -111,6 +112,7 @@ name:
#define ISTACK .L_ISTACK_\name\() /* Set regular kernel stack */
#define __ISTACK(name) .L_ISTACK_ ## name
#define IKUAP .L_IKUAP_\name\() /* Do KUAP lock */
+#define IMSR_R12 .L_IMSR_R12_\name\() /* Assumes MSR saved to r12 */
#define INT_DEFINE_BEGIN(n) \
.macro int_define_ ## n name
@@ -176,6 +178,9 @@ do_define_int n
.ifndef IKUAP
IKUAP=1
.endif
+ .ifndef IMSR_R12
+ IMSR_R12=0
+ .endif
.endm
/*
@@ -281,7 +286,7 @@ BEGIN_FTR_SECTION
mfspr r9,SPRN_PPR
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
HMT_MEDIUM
- std r10,IAREA+EX_R10(r13) /* save r10 - r12 */
+ std r10,IAREA+EX_R10(r13) /* save r10 */
.if ICFAR
BEGIN_FTR_SECTION
mfspr r10,SPRN_CFAR
@@ -321,7 +326,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
mfctr r10
std r10,IAREA+EX_CTR(r13)
mfcr r9
- std r11,IAREA+EX_R11(r13)
+ std r11,IAREA+EX_R11(r13) /* save r11 - r12 */
std r12,IAREA+EX_R12(r13)
/*
@@ -502,6 +507,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real, text)
std r10,0(r1) /* make stack chain pointer */
std r0,GPR0(r1) /* save r0 in stackframe */
std r10,GPR1(r1) /* save r1 in stackframe */
+ SANITIZE_GPR(0)
/* Mark our [H]SRRs valid for return */
li r10,1
@@ -544,8 +550,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
std r9,GPR11(r1)
std r10,GPR12(r1)
std r11,GPR13(r1)
+ .if !IMSR_R12
+ SANITIZE_GPRS(9, 12)
+ .else
+ SANITIZE_GPRS(9, 11)
+ .endif
SAVE_NVGPRS(r1)
+ SANITIZE_NVGPRS()
.if IDAR
.if IISIDE
@@ -577,10 +589,10 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
ld r10,IAREA+EX_CTR(r13)
std r10,_CTR(r1)
- std r2,GPR2(r1) /* save r2 in stackframe */
- SAVE_GPRS(3, 8, r1) /* save r3 - r8 in stackframe */
+ SAVE_GPRS(2, 8, r1) /* save r2 - r8 in stackframe */
+ SANITIZE_GPRS(2, 8)
mflr r9 /* Get LR, later save to stack */
- ld r2,PACATOC(r13) /* get kernel TOC into r2 */
+ LOAD_PACA_TOC() /* get kernel TOC into r2 */
std r9,_LINK(r1)
lbz r10,PACAIRQSOFTMASK(r13)
mfspr r11,SPRN_XER /* save XER in stackframe */
@@ -589,9 +601,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
li r9,IVEC
std r9,_TRAP(r1) /* set trap number */
li r10,0
- ld r11,exception_marker@toc(r2)
+ LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER)
std r10,RESULT(r1) /* clear regs->result */
- std r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame */
+ std r11,STACK_INT_FRAME_MARKER(r1) /* mark the frame */
.endm
/*
@@ -610,7 +622,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.macro SEARCH_RESTART_TABLE
#ifdef CONFIG_RELOCATABLE
mr r12,r2
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
LOAD_REG_ADDR(r9, __start___restart_table)
LOAD_REG_ADDR(r10, __stop___restart_table)
mr r2,r12
@@ -640,7 +652,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.macro SEARCH_SOFT_MASK_TABLE
#ifdef CONFIG_RELOCATABLE
mr r12,r2
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
LOAD_REG_ADDR(r9, __start___soft_mask_table)
LOAD_REG_ADDR(r10, __stop___soft_mask_table)
mr r2,r12
@@ -696,6 +708,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
mtlr r9
ld r9,_CCR(r1)
mtcr r9
+ SANITIZE_RESTORE_NVGPRS()
REST_GPRS(2, 13, r1)
REST_GPR(0, r1)
/* restore original r1. */
@@ -703,6 +716,71 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.endm
/*
+ * EARLY_BOOT_FIXUP - Fix real-mode interrupt with wrong endian in early boot.
+ *
+ * There's a short window during boot where although the kernel is running
+ * little endian, any exceptions will cause the CPU to switch back to big
+ * endian. For example a WARN() boils down to a trap instruction, which will
+ * cause a program check, and we end up here but with the CPU in big endian
+ * mode. The first instruction of the program check handler (in GEN_INT_ENTRY
+ * below) is an mtsprg, which when executed in the wrong endian is an lhzu with
+ * a ~3GB displacement from r3. The content of r3 is random, so that is a load
+ * from some random location, and depending on the system can easily lead to a
+ * checkstop, or an infinitely recursive page fault.
+ *
+ * So to handle that case we have a trampoline here that can detect we are in
+ * the wrong endian and flip us back to the correct endian. We can't flip
+ * MSR[LE] using mtmsr, so we have to use rfid. That requires backing up SRR0/1
+ * as well as a GPR. To do that we use SPRG0/2/3, as SPRG1 is already used for
+ * the paca. SPRG3 is user readable, but this trampoline is only active very
+ * early in boot, and SPRG3 will be reinitialised in vdso_getcpu_init() before
+ * userspace starts.
+ */
+.macro EARLY_BOOT_FIXUP
+BEGIN_FTR_SECTION
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+ tdi 0,0,0x48 // Trap never, or in reverse endian: b . + 8
+ b 2f // Skip trampoline if endian is correct
+ .long 0xa643707d // mtsprg 0, r11 Backup r11
+ .long 0xa6027a7d // mfsrr0 r11
+ .long 0xa643727d // mtsprg 2, r11 Backup SRR0 in SPRG2
+ .long 0xa6027b7d // mfsrr1 r11
+ .long 0xa643737d // mtsprg 3, r11 Backup SRR1 in SPRG3
+ .long 0xa600607d // mfmsr r11
+ .long 0x01006b69 // xori r11, r11, 1 Invert MSR[LE]
+ .long 0xa6037b7d // mtsrr1 r11
+ /*
+ * This is 'li r11,1f' where 1f is the absolute address of that
+ * label, byteswapped into the SI field of the instruction.
+ */
+ .long 0x00006039 | \
+ ((ABS_ADDR(1f, real_vectors) & 0x00ff) << 24) | \
+ ((ABS_ADDR(1f, real_vectors) & 0xff00) << 8)
+ .long 0xa6037a7d // mtsrr0 r11
+ .long 0x2400004c // rfid
+1:
+ mfsprg r11, 3
+ mtsrr1 r11 // Restore SRR1
+ mfsprg r11, 2
+ mtsrr0 r11 // Restore SRR0
+ mfsprg r11, 0 // Restore r11
+2:
+#endif
+ /*
+ * program check could hit at any time, and pseries can not block
+ * MSR[ME] in early boot. So check if there is anything useful in r13
+ * yet, and spin forever if not.
+ */
+ mtsprg 0, r11
+ mfcr r11
+ cmpdi r13, 0
+ beq .
+ mtcr r11
+ mfsprg r11, 0
+END_FTR_SECTION(0, 1) // nop out after boot
+.endm
+
+/*
* There are a few constraints to be concerned with.
* - Real mode exceptions code/data must be located at their physical location.
* - Virtual mode exceptions must be mapped at their 0xc000... location.
@@ -815,7 +893,7 @@ __start_interrupts:
*
* Call convention:
*
- * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
+ * syscall register convention is in Documentation/arch/powerpc/syscall64-abi.rst
*/
EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
/* SCV 0 */
@@ -996,8 +1074,8 @@ EXC_COMMON_BEGIN(system_reset_common)
subi r1,r1,INT_FRAME_SIZE
__GEN_COMMON_BODY system_reset
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl system_reset_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(system_reset_exception)
/* Clear MSR_RI before setting SRR0 and SRR1. */
li r9,0
@@ -1079,6 +1157,7 @@ INT_DEFINE_BEGIN(machine_check)
INT_DEFINE_END(machine_check)
EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
+ EARLY_BOOT_FIXUP
GEN_INT_ENTRY machine_check_early, virt=0
EXC_REAL_END(machine_check, 0x200, 0x100)
EXC_VIRT_NONE(0x4200, 0x100)
@@ -1142,8 +1221,11 @@ EXC_COMMON_BEGIN(machine_check_early_common)
BEGIN_FTR_SECTION
bl enable_machine_check
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl machine_check_early
+ addi r3,r1,STACK_INT_FRAME_REGS
+BEGIN_FTR_SECTION
+ bl CFUNC(machine_check_early_boot)
+END_FTR_SECTION(0, 1) // nop out after boot
+ bl CFUNC(machine_check_early)
std r3,RESULT(r1) /* Save result */
ld r12,_MSR(r1)
@@ -1204,7 +1286,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
* Queue up the MCE event so that we can log it later, while
* returning from kernel or opal call.
*/
- bl machine_check_queue_event
+ bl CFUNC(machine_check_queue_event)
MACHINE_CHECK_HANDLER_WINDUP
RFI_TO_KERNEL
@@ -1229,8 +1311,8 @@ EXC_COMMON_BEGIN(machine_check_common)
* save area: PACA_EXMC instead of PACA_EXGEN.
*/
GEN_COMMON machine_check
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl machine_check_exception_async
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(machine_check_exception_async)
b interrupt_return_srr
@@ -1240,7 +1322,7 @@ EXC_COMMON_BEGIN(machine_check_common)
* done. Queue the event then call the idle code to do the wake up.
*/
EXC_COMMON_BEGIN(machine_check_idle_common)
- bl machine_check_queue_event
+ bl CFUNC(machine_check_queue_event)
/*
* GPR-loss wakeups are relatively straightforward, because the
@@ -1279,7 +1361,7 @@ EXC_COMMON_BEGIN(unrecoverable_mce)
BEGIN_FTR_SECTION
li r10,0 /* clear MSR_RI */
mtmsrd r10,1
- bl disable_machine_check
+ bl CFUNC(disable_machine_check)
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
ld r10,PACAKMSR(r13)
li r3,MSR_ME
@@ -1295,15 +1377,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
* This is the NMI version of the handler because we are called from
* the early handler which is a true NMI.
*/
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl machine_check_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(machine_check_exception)
/*
* We will not reach here. Even if we did, there is no way out.
* Call unrecoverable_exception and die.
*/
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl unrecoverable_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(unrecoverable_exception)
b .
@@ -1353,26 +1435,26 @@ EXC_VIRT_END(data_access, 0x4300, 0x80)
EXC_COMMON_BEGIN(data_access_common)
GEN_COMMON data_access
ld r4,_DSISR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
andis. r0,r4,DSISR_DABRMATCH@h
bne- 1f
#ifdef CONFIG_PPC_64S_HASH_MMU
BEGIN_MMU_FTR_SECTION
- bl do_hash_fault
+ bl CFUNC(do_hash_fault)
MMU_FTR_SECTION_ELSE
- bl do_page_fault
+ bl CFUNC(do_page_fault)
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
#else
- bl do_page_fault
+ bl CFUNC(do_page_fault)
#endif
b interrupt_return_srr
-1: bl do_break
+1: bl CFUNC(do_break)
/*
* do_break() may have changed the NV GPRS while handling a breakpoint.
* If so, we need to restore them with their updated values.
*/
- REST_NVGPRS(r1)
+ HANDLER_RESTORE_NVGPRS()
b interrupt_return_srr
@@ -1410,8 +1492,8 @@ EXC_COMMON_BEGIN(data_access_slb_common)
#ifdef CONFIG_PPC_64S_HASH_MMU
BEGIN_MMU_FTR_SECTION
/* HPT case, do SLB fault */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_slb_fault
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_slb_fault)
cmpdi r3,0
bne- 1f
b fast_interrupt_return_srr
@@ -1424,8 +1506,8 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
li r3,-EFAULT
#endif
std r3,RESULT(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_bad_segment_interrupt
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_bad_segment_interrupt)
b interrupt_return_srr
@@ -1456,15 +1538,15 @@ EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80)
EXC_VIRT_END(instruction_access, 0x4400, 0x80)
EXC_COMMON_BEGIN(instruction_access_common)
GEN_COMMON instruction_access
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
#ifdef CONFIG_PPC_64S_HASH_MMU
BEGIN_MMU_FTR_SECTION
- bl do_hash_fault
+ bl CFUNC(do_hash_fault)
MMU_FTR_SECTION_ELSE
- bl do_page_fault
+ bl CFUNC(do_page_fault)
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
#else
- bl do_page_fault
+ bl CFUNC(do_page_fault)
#endif
b interrupt_return_srr
@@ -1498,8 +1580,8 @@ EXC_COMMON_BEGIN(instruction_access_slb_common)
#ifdef CONFIG_PPC_64S_HASH_MMU
BEGIN_MMU_FTR_SECTION
/* HPT case, do SLB fault */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_slb_fault
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_slb_fault)
cmpdi r3,0
bne- 1f
b fast_interrupt_return_srr
@@ -1512,8 +1594,8 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
li r3,-EFAULT
#endif
std r3,RESULT(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_bad_segment_interrupt
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_bad_segment_interrupt)
b interrupt_return_srr
@@ -1566,8 +1648,8 @@ EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
EXC_COMMON_BEGIN(hardware_interrupt_common)
GEN_COMMON hardware_interrupt
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_IRQ
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_IRQ)
BEGIN_FTR_SECTION
b interrupt_return_hsrr
FTR_SECTION_ELSE
@@ -1596,9 +1678,9 @@ EXC_VIRT_BEGIN(alignment, 0x4600, 0x100)
EXC_VIRT_END(alignment, 0x4600, 0x100)
EXC_COMMON_BEGIN(alignment_common)
GEN_COMMON alignment
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl alignment_exception
- REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(alignment_exception)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
b interrupt_return_srr
@@ -1619,51 +1701,7 @@ INT_DEFINE_BEGIN(program_check)
INT_DEFINE_END(program_check)
EXC_REAL_BEGIN(program_check, 0x700, 0x100)
-
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
- /*
- * There's a short window during boot where although the kernel is
- * running little endian, any exceptions will cause the CPU to switch
- * back to big endian. For example a WARN() boils down to a trap
- * instruction, which will cause a program check, and we end up here but
- * with the CPU in big endian mode. The first instruction of the program
- * check handler (in GEN_INT_ENTRY below) is an mtsprg, which when
- * executed in the wrong endian is an lhzu with a ~3GB displacement from
- * r3. The content of r3 is random, so that is a load from some random
- * location, and depending on the system can easily lead to a checkstop,
- * or an infinitely recursive page fault.
- *
- * So to handle that case we have a trampoline here that can detect we
- * are in the wrong endian and flip us back to the correct endian. We
- * can't flip MSR[LE] using mtmsr, so we have to use rfid. That requires
- * backing up SRR0/1 as well as a GPR. To do that we use SPRG0/2/3, as
- * SPRG1 is already used for the paca. SPRG3 is user readable, but this
- * trampoline is only active very early in boot, and SPRG3 will be
- * reinitialised in vdso_getcpu_init() before userspace starts.
- */
-BEGIN_FTR_SECTION
- tdi 0,0,0x48 // Trap never, or in reverse endian: b . + 8
- b 1f // Skip trampoline if endian is correct
- .long 0xa643707d // mtsprg 0, r11 Backup r11
- .long 0xa6027a7d // mfsrr0 r11
- .long 0xa643727d // mtsprg 2, r11 Backup SRR0 in SPRG2
- .long 0xa6027b7d // mfsrr1 r11
- .long 0xa643737d // mtsprg 3, r11 Backup SRR1 in SPRG3
- .long 0xa600607d // mfmsr r11
- .long 0x01006b69 // xori r11, r11, 1 Invert MSR[LE]
- .long 0xa6037b7d // mtsrr1 r11
- .long 0x34076039 // li r11, 0x734
- .long 0xa6037a7d // mtsrr0 r11
- .long 0x2400004c // rfid
- mfsprg r11, 3
- mtsrr1 r11 // Restore SRR1
- mfsprg r11, 2
- mtsrr0 r11 // Restore SRR0
- mfsprg r11, 0 // Restore r11
-1:
-END_FTR_SECTION(0, 1) // nop out after boot
-#endif /* CONFIG_CPU_LITTLE_ENDIAN */
-
+ EARLY_BOOT_FIXUP
GEN_INT_ENTRY program_check, virt=0
EXC_REAL_END(program_check, 0x700, 0x100)
EXC_VIRT_BEGIN(program_check, 0x4700, 0x100)
@@ -1706,9 +1744,9 @@ EXC_COMMON_BEGIN(program_check_common)
__GEN_COMMON_BODY program_check
.Ldo_program_check:
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl program_check_exception
- REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(program_check_exception)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
b interrupt_return_srr
@@ -1726,6 +1764,7 @@ INT_DEFINE_BEGIN(fp_unavailable)
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
+ IMSR_R12=1
INT_DEFINE_END(fp_unavailable)
EXC_REAL_BEGIN(fp_unavailable, 0x800, 0x100)
@@ -1737,8 +1776,8 @@ EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
EXC_COMMON_BEGIN(fp_unavailable_common)
GEN_COMMON fp_unavailable
bne 1f /* if from user, just load it up */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl kernel_fp_unavailable_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(kernel_fp_unavailable_exception)
0: trap
EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
1:
@@ -1751,12 +1790,12 @@ BEGIN_FTR_SECTION
bne- 2f
END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
- bl load_up_fpu
+ bl CFUNC(load_up_fpu)
b fast_interrupt_return_srr
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl fp_unavailable_tm
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(fp_unavailable_tm)
b interrupt_return_srr
#endif
@@ -1799,8 +1838,8 @@ EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80)
EXC_VIRT_END(decrementer, 0x4900, 0x80)
EXC_COMMON_BEGIN(decrementer_common)
GEN_COMMON decrementer
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl timer_interrupt
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(timer_interrupt)
b interrupt_return_srr
@@ -1884,11 +1923,11 @@ EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100)
EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
EXC_COMMON_BEGIN(doorbell_super_common)
GEN_COMMON doorbell_super
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
#ifdef CONFIG_PPC_DOORBELL
- bl doorbell_exception
+ bl CFUNC(doorbell_exception)
#else
- bl unknown_async_exception
+ bl CFUNC(unknown_async_exception)
#endif
b interrupt_return_srr
@@ -1913,8 +1952,8 @@ EXC_VIRT_NONE(0x4b00, 0x100)
* Call convention:
*
* syscall and hypercalls register conventions are documented in
- * Documentation/powerpc/syscall64-abi.rst and
- * Documentation/powerpc/papr_hcalls.rst respectively.
+ * Documentation/arch/powerpc/syscall64-abi.rst and
+ * Documentation/arch/powerpc/papr_hcalls.rst respectively.
*
* The intersection of volatile registers that don't contain possible
* inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry
@@ -1950,13 +1989,6 @@ INT_DEFINE_END(system_call)
INTERRUPT_TO_KERNEL
#endif
-#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
-BEGIN_FTR_SECTION
- cmpdi r0,0x1ebe
- beq- 1f
-END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
-#endif
-
/* We reach here with PACA in r13, r13 in r9. */
mfspr r11,SPRN_SRR0
mfspr r12,SPRN_SRR1
@@ -1976,16 +2008,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
b system_call_common
#endif
.endif
-
-#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
- /* Fast LE/BE switch system call */
-1: mfspr r12,SPRN_SRR1
- xori r12,r12,MSR_LE
- mtspr SPRN_SRR1,r12
- mr r13,r9
- RFI_TO_USER /* return to userspace */
- b . /* prevent speculative execution */
-#endif
.endm
EXC_REAL_BEGIN(system_call, 0xc00, 0x100)
@@ -2051,8 +2073,8 @@ EXC_VIRT_BEGIN(single_step, 0x4d00, 0x100)
EXC_VIRT_END(single_step, 0x4d00, 0x100)
EXC_COMMON_BEGIN(single_step_common)
GEN_COMMON single_step
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl single_step_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(single_step_exception)
b interrupt_return_srr
@@ -2085,11 +2107,11 @@ EXC_VIRT_BEGIN(h_data_storage, 0x4e00, 0x20)
EXC_VIRT_END(h_data_storage, 0x4e00, 0x20)
EXC_COMMON_BEGIN(h_data_storage_common)
GEN_COMMON h_data_storage
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
BEGIN_MMU_FTR_SECTION
- bl do_bad_page_fault_segv
+ bl CFUNC(do_bad_page_fault_segv)
MMU_FTR_SECTION_ELSE
- bl unknown_exception
+ bl CFUNC(unknown_exception)
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
b interrupt_return_hsrr
@@ -2114,8 +2136,8 @@ EXC_VIRT_BEGIN(h_instr_storage, 0x4e20, 0x20)
EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20)
EXC_COMMON_BEGIN(h_instr_storage_common)
GEN_COMMON h_instr_storage
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl unknown_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(unknown_exception)
b interrupt_return_hsrr
@@ -2137,9 +2159,9 @@ EXC_VIRT_BEGIN(emulation_assist, 0x4e40, 0x20)
EXC_VIRT_END(emulation_assist, 0x4e40, 0x20)
EXC_COMMON_BEGIN(emulation_assist_common)
GEN_COMMON emulation_assist
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl emulation_assist_interrupt
- REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(emulation_assist_interrupt)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
b interrupt_return_hsrr
@@ -2197,8 +2219,8 @@ EXC_COMMON_BEGIN(hmi_exception_early_common)
__GEN_COMMON_BODY hmi_exception_early
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl hmi_exception_realmode
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(hmi_exception_realmode)
cmpdi cr0,r3,0
bne 1f
@@ -2215,8 +2237,8 @@ EXC_COMMON_BEGIN(hmi_exception_early_common)
EXC_COMMON_BEGIN(hmi_exception_common)
GEN_COMMON hmi_exception
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl handle_hmi_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(handle_hmi_exception)
b interrupt_return_hsrr
@@ -2249,11 +2271,11 @@ EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20)
EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
EXC_COMMON_BEGIN(h_doorbell_common)
GEN_COMMON h_doorbell
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
#ifdef CONFIG_PPC_DOORBELL
- bl doorbell_exception
+ bl CFUNC(doorbell_exception)
#else
- bl unknown_async_exception
+ bl CFUNC(unknown_async_exception)
#endif
b interrupt_return_hsrr
@@ -2285,8 +2307,8 @@ EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20)
EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
EXC_COMMON_BEGIN(h_virt_irq_common)
GEN_COMMON h_virt_irq
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_IRQ
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_IRQ)
b interrupt_return_hsrr
@@ -2331,10 +2353,22 @@ EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20)
EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
EXC_COMMON_BEGIN(performance_monitor_common)
GEN_COMMON performance_monitor
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl performance_monitor_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ lbz r4,PACAIRQSOFTMASK(r13)
+ cmpdi r4,IRQS_ENABLED
+ bne 1f
+ bl CFUNC(performance_monitor_exception_async)
b interrupt_return_srr
+1:
+ bl CFUNC(performance_monitor_exception_nmi)
+ /* Clear MSR_RI before setting SRR0 and SRR1. */
+ li r9,0
+ mtmsrd r9,1
+ kuap_kernel_restore r9, r10
+
+ EXCEPTION_RESTORE_REGS hsrr=0
+ RFI_TO_KERNEL
/**
* Interrupt 0xf20 - Vector Unavailable Interrupt.
@@ -2347,6 +2381,7 @@ INT_DEFINE_BEGIN(altivec_unavailable)
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
+ IMSR_R12=1
INT_DEFINE_END(altivec_unavailable)
EXC_REAL_BEGIN(altivec_unavailable, 0xf20, 0x20)
@@ -2369,19 +2404,19 @@ BEGIN_FTR_SECTION
bne- 2f
END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
#endif
- bl load_up_altivec
+ bl CFUNC(load_up_altivec)
b fast_interrupt_return_srr
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl altivec_unavailable_tm
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(altivec_unavailable_tm)
b interrupt_return_srr
#endif
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl altivec_unavailable_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(altivec_unavailable_exception)
b interrupt_return_srr
@@ -2396,6 +2431,7 @@ INT_DEFINE_BEGIN(vsx_unavailable)
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
+ IMSR_R12=1
INT_DEFINE_END(vsx_unavailable)
EXC_REAL_BEGIN(vsx_unavailable, 0xf40, 0x20)
@@ -2421,15 +2457,15 @@ BEGIN_FTR_SECTION
b load_up_vsx
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl vsx_unavailable_tm
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(vsx_unavailable_tm)
b interrupt_return_srr
#endif
1:
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl vsx_unavailable_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(vsx_unavailable_exception)
b interrupt_return_srr
@@ -2455,9 +2491,9 @@ EXC_VIRT_BEGIN(facility_unavailable, 0x4f60, 0x20)
EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20)
EXC_COMMON_BEGIN(facility_unavailable_common)
GEN_COMMON facility_unavailable
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl facility_unavailable_exception
- REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(facility_unavailable_exception)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
b interrupt_return_srr
@@ -2483,9 +2519,10 @@ EXC_VIRT_BEGIN(h_facility_unavailable, 0x4f80, 0x20)
EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20)
EXC_COMMON_BEGIN(h_facility_unavailable_common)
GEN_COMMON h_facility_unavailable
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl facility_unavailable_exception
- REST_NVGPRS(r1) /* XXX Shouldn't be necessary in practice */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(facility_unavailable_exception)
+ /* XXX Shouldn't be necessary in practice */
+ HANDLER_RESTORE_NVGPRS()
b interrupt_return_hsrr
@@ -2500,27 +2537,8 @@ EXC_REAL_NONE(0x1000, 0x100)
EXC_VIRT_NONE(0x5000, 0x100)
EXC_REAL_NONE(0x1100, 0x100)
EXC_VIRT_NONE(0x5100, 0x100)
-
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_system_error)
- IVEC=0x1200
- IHSRR=1
-INT_DEFINE_END(cbe_system_error)
-
-EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
- GEN_INT_ENTRY cbe_system_error, virt=0
-EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
-EXC_VIRT_NONE(0x5200, 0x100)
-EXC_COMMON_BEGIN(cbe_system_error_common)
- GEN_COMMON cbe_system_error
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl cbe_system_error_exception
- b interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1200, 0x100)
EXC_VIRT_NONE(0x5200, 0x100)
-#endif
/**
* Interrupt 0x1300 - Instruction Address Breakpoint Interrupt.
@@ -2544,8 +2562,8 @@ EXC_VIRT_BEGIN(instruction_breakpoint, 0x5300, 0x100)
EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100)
EXC_COMMON_BEGIN(instruction_breakpoint_common)
GEN_COMMON instruction_breakpoint
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl instruction_breakpoint_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(instruction_breakpoint_exception)
b interrupt_return_srr
@@ -2666,31 +2684,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
EXC_COMMON_BEGIN(denorm_exception_common)
GEN_COMMON denorm_exception
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl unknown_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(unknown_exception)
b interrupt_return_hsrr
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_maintenance)
- IVEC=0x1600
- IHSRR=1
-INT_DEFINE_END(cbe_maintenance)
-
-EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
- GEN_INT_ENTRY cbe_maintenance, virt=0
-EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
-EXC_VIRT_NONE(0x5600, 0x100)
-EXC_COMMON_BEGIN(cbe_maintenance_common)
- GEN_COMMON cbe_maintenance
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl cbe_maintenance_exception
- b interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1600, 0x100)
EXC_VIRT_NONE(0x5600, 0x100)
-#endif
INT_DEFINE_BEGIN(altivec_assist)
@@ -2708,36 +2708,18 @@ EXC_VIRT_BEGIN(altivec_assist, 0x5700, 0x100)
EXC_VIRT_END(altivec_assist, 0x5700, 0x100)
EXC_COMMON_BEGIN(altivec_assist_common)
GEN_COMMON altivec_assist
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
#ifdef CONFIG_ALTIVEC
- bl altivec_assist_exception
- REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ bl CFUNC(altivec_assist_exception)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
#else
- bl unknown_exception
+ bl CFUNC(unknown_exception)
#endif
b interrupt_return_srr
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_thermal)
- IVEC=0x1800
- IHSRR=1
-INT_DEFINE_END(cbe_thermal)
-
-EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
- GEN_INT_ENTRY cbe_thermal, virt=0
-EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
-EXC_VIRT_NONE(0x5800, 0x100)
-EXC_COMMON_BEGIN(cbe_thermal_common)
- GEN_COMMON cbe_thermal
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl cbe_thermal_exception
- b interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1800, 0x100)
EXC_VIRT_NONE(0x5800, 0x100)
-#endif
#ifdef CONFIG_PPC_WATCHDOG
@@ -2763,8 +2745,8 @@ EXC_COMMON_BEGIN(soft_nmi_common)
subi r1,r1,INT_FRAME_SIZE
__GEN_COMMON_BODY soft_nmi
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl soft_nmi_interrupt
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(soft_nmi_interrupt)
/* Clear MSR_RI before setting SRR0 and SRR1. */
li r9,0
@@ -2779,7 +2761,7 @@ EXC_COMMON_BEGIN(soft_nmi_common)
/*
* An interrupt came in while soft-disabled. We set paca->irq_happened, then:
- * - If it was a decrementer interrupt, we bump the dec to max and and return.
+ * - If it was a decrementer interrupt, we bump the dec to max and return.
* - If it was a doorbell we return immediately since doorbells are edge
* triggered and won't automatically refire.
* - If it was a HMI we return immediately since we handled it in realmode
@@ -2794,6 +2776,20 @@ masked_Hinterrupt:
masked_interrupt:
.endif
stw r9,PACA_EXGEN+EX_CCR(r13)
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+ /*
+ * Ensure there was no previous MUST_HARD_MASK interrupt or
+ * HARD_DIS setting. If this does fire, the interrupt is still
+ * masked and MSR[EE] will be cleared on return, so no need to
+ * panic, but somebody probably enabled MSR[EE] under
+ * PACA_IRQ_HARD_DIS, mtmsr(mfmsr() | MSR_x) being a common
+ * cause.
+ */
+ lbz r9,PACAIRQHAPPENED(r13)
+ andi. r9,r9,(PACA_IRQ_MUST_HARD_MASK|PACA_IRQ_HARD_DIS)
+0: tdnei r9,0
+ EMIT_WARN_ENTRY 0b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+#endif
lbz r9,PACAIRQHAPPENED(r13)
or r9,r9,r10
stb r9,PACAIRQHAPPENED(r13)
@@ -3034,22 +3030,6 @@ EXPORT_SYMBOL(do_uaccess_flush)
MASKED_INTERRUPT
MASKED_INTERRUPT hsrr=1
- /*
- * Relocation-on interrupts: A subset of the interrupts can be delivered
- * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering
- * it. Addresses are the same as the original interrupt addresses, but
- * offset by 0xc000000000004000.
- * It's impossible to receive interrupts below 0x300 via this mechanism.
- * KVM: None of these traps are from the guest ; anything that escalated
- * to HV=1 from HV=0 is delivered via real mode handlers.
- */
-
- /*
- * This uses the standard macro, since the original 0x300 vector
- * only has extra guff for STAB-based processors -- which never
- * come here.
- */
-
USE_FIXED_SECTION(virt_trampolines)
/*
* All code below __end_soft_masked is treated as soft-masked. If
@@ -3075,7 +3055,7 @@ CLOSE_FIXED_SECTION(virt_trampolines);
USE_TEXT_SECTION()
/* MSR[RI] should be clear because this uses SRR[01] */
-enable_machine_check:
+_GLOBAL(enable_machine_check)
mflr r0
bcl 20,31,$+4
0: mflr r3
@@ -3089,7 +3069,7 @@ enable_machine_check:
blr
/* MSR[RI] should be clear because this uses SRR[01] */
-disable_machine_check:
+SYM_FUNC_START_LOCAL(disable_machine_check)
mflr r0
bcl 20,31,$+4
0: mflr r3
@@ -3102,3 +3082,4 @@ disable_machine_check:
RFI_TO_KERNEL
1: mtlr r0
blr
+SYM_FUNC_END(disable_machine_check)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index ea0a073abd96..5782e743fd27 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -33,6 +33,7 @@
#include <asm/fadump-internal.h>
#include <asm/setup.h>
#include <asm/interrupt.h>
+#include <asm/prom.h>
/*
* The CPU who acquired the lock to trigger the fadump crash should
@@ -53,8 +54,6 @@ static struct kobject *fadump_kobj;
static atomic_t cpus_in_fadump;
static DEFINE_MUTEX(fadump_mutex);
-static struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false };
-
#define RESERVED_RNGS_SZ 16384 /* 16K - 128 entries */
#define RESERVED_RNGS_CNT (RESERVED_RNGS_SZ / \
sizeof(struct fadump_memory_range))
@@ -80,26 +79,38 @@ static struct cma *fadump_cma;
* But for some reason even if it fails we still have the memory reservation
* with us and we can still continue doing fadump.
*/
-static int __init fadump_cma_init(void)
+void __init fadump_cma_init(void)
{
- unsigned long long base, size;
+ unsigned long long base, size, end;
int rc;
- if (!fw_dump.fadump_enabled)
- return 0;
-
+ if (!fw_dump.fadump_supported || !fw_dump.fadump_enabled ||
+ fw_dump.dump_active)
+ return;
/*
* Do not use CMA if user has provided fadump=nocma kernel parameter.
- * Return 1 to continue with fadump old behaviour.
*/
- if (fw_dump.nocma)
- return 1;
+ if (fw_dump.nocma || !fw_dump.boot_memory_size)
+ return;
+ /*
+ * [base, end) should be reserved during early init in
+ * fadump_reserve_mem(). No need to check this here as
+ * cma_init_reserved_mem() already checks for overlap.
+ * Here we give the aligned chunk of this reserved memory to CMA.
+ */
base = fw_dump.reserve_dump_area_start;
size = fw_dump.boot_memory_size;
+ end = base + size;
- if (!size)
- return 0;
+ base = ALIGN(base, CMA_MIN_ALIGNMENT_BYTES);
+ end = ALIGN_DOWN(end, CMA_MIN_ALIGNMENT_BYTES);
+ size = end - base;
+
+ if (end <= base) {
+ pr_warn("%s: Too less memory to give to CMA\n", __func__);
+ return;
+ }
rc = cma_init_reserved_mem(base, size, 0, "fadump_cma", &fadump_cma);
if (rc) {
@@ -110,7 +121,7 @@ static int __init fadump_cma_init(void)
* blocked from production system usage. Hence return 1,
* so that we can continue with fadump.
*/
- return 1;
+ return;
}
/*
@@ -122,17 +133,50 @@ static int __init fadump_cma_init(void)
/*
* So we now have successfully initialized cma area for fadump.
*/
- pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx "
+ pr_info("Initialized [0x%llx, %luMB] cma area from [0x%lx, %luMB] "
"bytes of memory reserved for firmware-assisted dump\n",
- cma_get_size(fadump_cma),
- (unsigned long)cma_get_base(fadump_cma) >> 20,
- fw_dump.reserve_dump_area_size);
- return 1;
+ cma_get_base(fadump_cma), cma_get_size(fadump_cma) >> 20,
+ fw_dump.reserve_dump_area_start,
+ fw_dump.boot_memory_size >> 20);
+ return;
}
-#else
-static int __init fadump_cma_init(void) { return 1; }
#endif /* CONFIG_CMA */
+/*
+ * Additional parameters meant for capture kernel are placed in a dedicated area.
+ * If this is capture kernel boot, append these parameters to bootargs.
+ */
+void __init fadump_append_bootargs(void)
+{
+ char *append_args;
+ size_t len;
+
+ if (!fw_dump.dump_active || !fw_dump.param_area_supported || !fw_dump.param_area)
+ return;
+
+ if (fw_dump.param_area < fw_dump.boot_mem_top) {
+ if (memblock_reserve(fw_dump.param_area, COMMAND_LINE_SIZE)) {
+ pr_warn("WARNING: Can't use additional parameters area!\n");
+ fw_dump.param_area = 0;
+ return;
+ }
+ }
+
+ append_args = (char *)fw_dump.param_area;
+ len = strlen(boot_command_line);
+
+ /*
+ * Too late to fail even if cmdline size exceeds. Truncate additional parameters
+ * to cmdline size and proceed anyway.
+ */
+ if (len + strlen(append_args) >= COMMAND_LINE_SIZE - 1)
+ pr_warn("WARNING: Appending parameters exceeds cmdline size. Truncating!\n");
+
+ pr_debug("Cmdline: %s\n", boot_command_line);
+ snprintf(boot_command_line + len, COMMAND_LINE_SIZE - len, " %s", append_args);
+ pr_info("Updated cmdline: %s\n", boot_command_line);
+}
+
/* Scan the Firmware Assisted dump configuration details. */
int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
int depth, void *data)
@@ -223,28 +267,6 @@ static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end)
}
/*
- * Returns true, if there are no holes in boot memory area,
- * false otherwise.
- */
-bool is_fadump_boot_mem_contiguous(void)
-{
- unsigned long d_start, d_end;
- bool ret = false;
- int i;
-
- for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
- d_start = fw_dump.boot_mem_addr[i];
- d_end = d_start + fw_dump.boot_mem_sz[i];
-
- ret = is_fadump_mem_area_contiguous(d_start, d_end);
- if (!ret)
- break;
- }
-
- return ret;
-}
-
-/*
* Returns true, if there are no holes in reserved memory area,
* false otherwise.
*/
@@ -268,10 +290,8 @@ static void __init fadump_show_config(void)
if (!fw_dump.fadump_supported)
return;
- pr_debug("Fadump enabled : %s\n",
- (fw_dump.fadump_enabled ? "yes" : "no"));
- pr_debug("Dump Active : %s\n",
- (fw_dump.dump_active ? "yes" : "no"));
+ pr_debug("Fadump enabled : %s\n", str_yes_no(fw_dump.fadump_enabled));
+ pr_debug("Dump Active : %s\n", str_yes_no(fw_dump.dump_active));
pr_debug("Dump section sizes:\n");
pr_debug(" CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
pr_debug(" HPTE region size : %lx\n", fw_dump.hpte_region_size);
@@ -313,7 +333,7 @@ static __init u64 fadump_calculate_reserve_size(void)
* memory at a predefined offset.
*/
ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
- &size, &base);
+ &size, &base, NULL, NULL, NULL);
if (ret == 0 && size > 0) {
unsigned long max_size;
@@ -373,12 +393,6 @@ static unsigned long __init get_fadump_area_size(void)
size = PAGE_ALIGN(size);
size += fw_dump.boot_memory_size;
size += sizeof(struct fadump_crash_info_header);
- size += sizeof(struct elfhdr); /* ELF core header.*/
- size += sizeof(struct elf_phdr); /* place holder for cpu notes */
- /* Program headers for crash memory regions. */
- size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
-
- size = PAGE_ALIGN(size);
/* This is to hold kernel metadata on platforms that support it */
size += (fw_dump.ops->fadump_get_metadata_size ?
@@ -389,10 +403,11 @@ static unsigned long __init get_fadump_area_size(void)
static int __init add_boot_mem_region(unsigned long rstart,
unsigned long rsize)
{
+ int max_boot_mem_rgns = fw_dump.ops->fadump_max_boot_mem_rgns();
int i = fw_dump.boot_mem_regs_cnt++;
- if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) {
- fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS;
+ if (fw_dump.boot_mem_regs_cnt > max_boot_mem_rgns) {
+ fw_dump.boot_mem_regs_cnt = max_boot_mem_rgns;
return 0;
}
@@ -552,13 +567,6 @@ int __init fadump_reserve_mem(void)
if (!fw_dump.dump_active) {
fw_dump.boot_memory_size =
PAGE_ALIGN(fadump_calculate_reserve_size());
-#ifdef CONFIG_CMA
- if (!fw_dump.nocma) {
- fw_dump.boot_memory_size =
- ALIGN(fw_dump.boot_memory_size,
- CMA_MIN_ALIGNMENT_BYTES);
- }
-#endif
bootmem_min = fw_dump.ops->fadump_get_bootmem_min();
if (fw_dump.boot_memory_size < bootmem_min) {
@@ -573,22 +581,6 @@ int __init fadump_reserve_mem(void)
}
}
- /*
- * Calculate the memory boundary.
- * If memory_limit is less than actual memory boundary then reserve
- * the memory for fadump beyond the memory_limit and adjust the
- * memory_limit accordingly, so that the running kernel can run with
- * specified memory_limit.
- */
- if (memory_limit && memory_limit < memblock_end_of_DRAM()) {
- size = get_fadump_area_size();
- if ((memory_limit + size) < memblock_end_of_DRAM())
- memory_limit += size;
- else
- memory_limit = memblock_end_of_DRAM();
- printk(KERN_INFO "Adjusted memory_limit for firmware-assisted"
- " dump, now %#016llx\n", memory_limit);
- }
if (memory_limit)
mem_boundary = memory_limit;
else
@@ -647,13 +639,12 @@ int __init fadump_reserve_mem(void)
pr_info("Reserved %lldMB of memory at %#016llx (System RAM: %lldMB)\n",
(size >> 20), base, (memblock_phys_mem_size() >> 20));
-
- ret = fadump_cma_init();
}
return ret;
error_out:
fw_dump.fadump_enabled = 0;
+ fw_dump.reserve_dump_area_size = 0;
return 0;
}
@@ -704,7 +695,7 @@ void crash_fadump(struct pt_regs *regs, const char *str)
* old_cpu == -1 means this is the first CPU which has come here,
* go ahead and trigger fadump.
*
- * old_cpu != -1 means some other CPU has already on it's way
+ * old_cpu != -1 means some other CPU has already on its way
* to trigger fadump, just keep looping here.
*/
this_cpu = smp_processor_id();
@@ -759,7 +750,7 @@ u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
* prstatus.pr_pid = ????
*/
elf_core_copy_regs(&prstatus.pr_reg, regs);
- buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+ buf = append_elf_note(buf, NN_PRSTATUS, NT_PRSTATUS,
&prstatus, sizeof(prstatus));
return buf;
}
@@ -930,36 +921,6 @@ static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info,
return 0;
}
-static int fadump_exclude_reserved_area(u64 start, u64 end)
-{
- u64 ra_start, ra_end;
- int ret = 0;
-
- ra_start = fw_dump.reserve_dump_area_start;
- ra_end = ra_start + fw_dump.reserve_dump_area_size;
-
- if ((ra_start < end) && (ra_end > start)) {
- if ((start < ra_start) && (end > ra_end)) {
- ret = fadump_add_mem_range(&crash_mrange_info,
- start, ra_start);
- if (ret)
- return ret;
-
- ret = fadump_add_mem_range(&crash_mrange_info,
- ra_end, end);
- } else if (start < ra_start) {
- ret = fadump_add_mem_range(&crash_mrange_info,
- start, ra_start);
- } else if (ra_end < end) {
- ret = fadump_add_mem_range(&crash_mrange_info,
- ra_end, end);
- }
- } else
- ret = fadump_add_mem_range(&crash_mrange_info, start, end);
-
- return ret;
-}
-
static int fadump_init_elfcore_header(char *bufp)
{
struct elfhdr *elf;
@@ -997,52 +958,6 @@ static int fadump_init_elfcore_header(char *bufp)
}
/*
- * Traverse through memblock structure and setup crash memory ranges. These
- * ranges will be used create PT_LOAD program headers in elfcore header.
- */
-static int fadump_setup_crash_memory_ranges(void)
-{
- u64 i, start, end;
- int ret;
-
- pr_debug("Setup crash memory ranges.\n");
- crash_mrange_info.mem_range_cnt = 0;
-
- /*
- * Boot memory region(s) registered with firmware are moved to
- * different location at the time of crash. Create separate program
- * header(s) for this memory chunk(s) with the correct offset.
- */
- for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
- start = fw_dump.boot_mem_addr[i];
- end = start + fw_dump.boot_mem_sz[i];
- ret = fadump_add_mem_range(&crash_mrange_info, start, end);
- if (ret)
- return ret;
- }
-
- for_each_mem_range(i, &start, &end) {
- /*
- * skip the memory chunk that is already added
- * (0 through boot_memory_top).
- */
- if (start < fw_dump.boot_mem_top) {
- if (end > fw_dump.boot_mem_top)
- start = fw_dump.boot_mem_top;
- else
- continue;
- }
-
- /* add this range excluding the reserved dump area. */
- ret = fadump_exclude_reserved_area(start, end);
- if (ret)
- return ret;
- }
-
- return 0;
-}
-
-/*
* If the given physical address falls within the boot memory region then
* return the relocated address that points to the dump region reserved
* for saving initial boot memory contents.
@@ -1072,36 +987,50 @@ static inline unsigned long fadump_relocate(unsigned long paddr)
return raddr;
}
-static int fadump_create_elfcore_headers(char *bufp)
+static void __init populate_elf_pt_load(struct elf_phdr *phdr, u64 start,
+ u64 size, unsigned long long offset)
{
- unsigned long long raddr, offset;
- struct elf_phdr *phdr;
+ phdr->p_align = 0;
+ phdr->p_memsz = size;
+ phdr->p_filesz = size;
+ phdr->p_paddr = start;
+ phdr->p_offset = offset;
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R|PF_W|PF_X;
+ phdr->p_vaddr = (unsigned long)__va(start);
+}
+
+static void __init fadump_populate_elfcorehdr(struct fadump_crash_info_header *fdh)
+{
+ char *bufp;
struct elfhdr *elf;
- int i, j;
+ struct elf_phdr *phdr;
+ u64 boot_mem_dest_offset;
+ unsigned long long i, ra_start, ra_end, ra_size, mstart, mend;
+ bufp = (char *) fw_dump.elfcorehdr_addr;
fadump_init_elfcore_header(bufp);
elf = (struct elfhdr *)bufp;
bufp += sizeof(struct elfhdr);
/*
- * setup ELF PT_NOTE, place holder for cpu notes info. The notes info
- * will be populated during second kernel boot after crash. Hence
- * this PT_NOTE will always be the first elf note.
+ * Set up ELF PT_NOTE, a placeholder for CPU notes information.
+ * The notes info will be populated later by platform-specific code.
+ * Hence, this PT_NOTE will always be the first ELF note.
*
* NOTE: Any new ELF note addition should be placed after this note.
*/
phdr = (struct elf_phdr *)bufp;
bufp += sizeof(struct elf_phdr);
phdr->p_type = PT_NOTE;
- phdr->p_flags = 0;
- phdr->p_vaddr = 0;
- phdr->p_align = 0;
-
- phdr->p_offset = 0;
- phdr->p_paddr = 0;
- phdr->p_filesz = 0;
- phdr->p_memsz = 0;
-
+ phdr->p_flags = 0;
+ phdr->p_vaddr = 0;
+ phdr->p_align = 0;
+ phdr->p_offset = 0;
+ phdr->p_paddr = 0;
+ phdr->p_filesz = 0;
+ phdr->p_memsz = 0;
+ /* Increment number of program headers. */
(elf->e_phnum)++;
/* setup ELF PT_NOTE for vmcoreinfo */
@@ -1111,55 +1040,66 @@ static int fadump_create_elfcore_headers(char *bufp)
phdr->p_flags = 0;
phdr->p_vaddr = 0;
phdr->p_align = 0;
-
- phdr->p_paddr = fadump_relocate(paddr_vmcoreinfo_note());
- phdr->p_offset = phdr->p_paddr;
- phdr->p_memsz = phdr->p_filesz = VMCOREINFO_NOTE_SIZE;
-
+ phdr->p_paddr = phdr->p_offset = fdh->vmcoreinfo_raddr;
+ phdr->p_memsz = phdr->p_filesz = fdh->vmcoreinfo_size;
/* Increment number of program headers. */
(elf->e_phnum)++;
- /* setup PT_LOAD sections. */
- j = 0;
- offset = 0;
- raddr = fw_dump.boot_mem_addr[0];
- for (i = 0; i < crash_mrange_info.mem_range_cnt; i++) {
- u64 mbase, msize;
-
- mbase = crash_mrange_info.mem_ranges[i].base;
- msize = crash_mrange_info.mem_ranges[i].size;
- if (!msize)
- continue;
-
+ /*
+ * Setup PT_LOAD sections. first include boot memory regions
+ * and then add rest of the memory regions.
+ */
+ boot_mem_dest_offset = fw_dump.boot_mem_dest_addr;
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
phdr = (struct elf_phdr *)bufp;
bufp += sizeof(struct elf_phdr);
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R|PF_W|PF_X;
- phdr->p_offset = mbase;
-
- if (mbase == raddr) {
- /*
- * The entire real memory region will be moved by
- * firmware to the specified destination_address.
- * Hence set the correct offset.
- */
- phdr->p_offset = fw_dump.boot_mem_dest_addr + offset;
- if (j < (fw_dump.boot_mem_regs_cnt - 1)) {
- offset += fw_dump.boot_mem_sz[j];
- raddr = fw_dump.boot_mem_addr[++j];
- }
+ populate_elf_pt_load(phdr, fw_dump.boot_mem_addr[i],
+ fw_dump.boot_mem_sz[i],
+ boot_mem_dest_offset);
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+ boot_mem_dest_offset += fw_dump.boot_mem_sz[i];
+ }
+
+ /* Memory reserved for fadump in first kernel */
+ ra_start = fw_dump.reserve_dump_area_start;
+ ra_size = get_fadump_area_size();
+ ra_end = ra_start + ra_size;
+
+ phdr = (struct elf_phdr *)bufp;
+ for_each_mem_range(i, &mstart, &mend) {
+ /* Boot memory regions already added, skip them now */
+ if (mstart < fw_dump.boot_mem_top) {
+ if (mend > fw_dump.boot_mem_top)
+ mstart = fw_dump.boot_mem_top;
+ else
+ continue;
}
- phdr->p_paddr = mbase;
- phdr->p_vaddr = (unsigned long)__va(mbase);
- phdr->p_filesz = msize;
- phdr->p_memsz = msize;
- phdr->p_align = 0;
+ /* Handle memblock regions overlaps with fadump reserved area */
+ if ((ra_start < mend) && (ra_end > mstart)) {
+ if ((mstart < ra_start) && (mend > ra_end)) {
+ populate_elf_pt_load(phdr, mstart, ra_start - mstart, mstart);
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+ bufp += sizeof(struct elf_phdr);
+ phdr = (struct elf_phdr *)bufp;
+ populate_elf_pt_load(phdr, ra_end, mend - ra_end, ra_end);
+ } else if (mstart < ra_start) {
+ populate_elf_pt_load(phdr, mstart, ra_start - mstart, mstart);
+ } else if (ra_end < mend) {
+ populate_elf_pt_load(phdr, ra_end, mend - ra_end, ra_end);
+ }
+ } else {
+ /* No overlap with fadump reserved memory region */
+ populate_elf_pt_load(phdr, mstart, mend - mstart, mstart);
+ }
/* Increment number of program headers. */
(elf->e_phnum)++;
+ bufp += sizeof(struct elf_phdr);
+ phdr = (struct elf_phdr *) bufp;
}
- return 0;
}
static unsigned long init_fadump_header(unsigned long addr)
@@ -1174,14 +1114,25 @@ static unsigned long init_fadump_header(unsigned long addr)
memset(fdh, 0, sizeof(struct fadump_crash_info_header));
fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
- fdh->elfcorehdr_addr = addr;
+ fdh->version = FADUMP_HEADER_VERSION;
/* We will set the crashing cpu id in crash_fadump() during crash. */
fdh->crashing_cpu = FADUMP_CPU_UNKNOWN;
+
+ /*
+ * The physical address and size of vmcoreinfo are required in the
+ * second kernel to prepare elfcorehdr.
+ */
+ fdh->vmcoreinfo_raddr = fadump_relocate(paddr_vmcoreinfo_note());
+ fdh->vmcoreinfo_size = VMCOREINFO_NOTE_SIZE;
+
+
+ fdh->pt_regs_sz = sizeof(struct pt_regs);
/*
* When LPAR is terminated by PYHP, ensure all possible CPUs'
* register data is processed while exporting the vmcore.
*/
fdh->cpu_mask = *cpu_possible_mask;
+ fdh->cpu_mask_sz = sizeof(struct cpumask);
return addr;
}
@@ -1189,8 +1140,6 @@ static unsigned long init_fadump_header(unsigned long addr)
static int register_fadump(void)
{
unsigned long addr;
- void *vaddr;
- int ret;
/*
* If no memory is reserved then we can not register for firmware-
@@ -1199,18 +1148,10 @@ static int register_fadump(void)
if (!fw_dump.reserve_dump_area_size)
return -ENODEV;
- ret = fadump_setup_crash_memory_ranges();
- if (ret)
- return ret;
-
addr = fw_dump.fadumphdr_addr;
/* Initialize fadump crash info header. */
addr = init_fadump_header(addr);
- vaddr = __va(addr);
-
- pr_debug("Creating ELF core headers at %#016lx\n", addr);
- fadump_create_elfcore_headers(vaddr);
/* register the future kernel dump with firmware. */
pr_debug("Registering for firmware-assisted kernel dump...\n");
@@ -1229,7 +1170,6 @@ void fadump_cleanup(void)
} else if (fw_dump.dump_registered) {
/* Un-register Firmware-assisted dump if it was registered. */
fw_dump.ops->fadump_unregister(&fw_dump);
- fadump_free_mem_ranges(&crash_mrange_info);
}
if (fw_dump.ops->fadump_cleanup)
@@ -1415,17 +1355,31 @@ static void fadump_release_memory(u64 begin, u64 end)
fadump_release_reserved_area(tstart, end);
}
-static void fadump_invalidate_release_mem(void)
+static void fadump_free_elfcorehdr_buf(void)
{
- mutex_lock(&fadump_mutex);
- if (!fw_dump.dump_active) {
- mutex_unlock(&fadump_mutex);
+ if (fw_dump.elfcorehdr_addr == 0 || fw_dump.elfcorehdr_size == 0)
return;
- }
- fadump_cleanup();
- mutex_unlock(&fadump_mutex);
+ /*
+ * Before freeing the memory of `elfcorehdr`, reset the global
+ * `elfcorehdr_addr` to prevent modules like `vmcore` from accessing
+ * invalid memory.
+ */
+ elfcorehdr_addr = ELFCORE_ADDR_ERR;
+ fadump_free_buffer(fw_dump.elfcorehdr_addr, fw_dump.elfcorehdr_size);
+ fw_dump.elfcorehdr_addr = 0;
+ fw_dump.elfcorehdr_size = 0;
+}
+
+static void fadump_invalidate_release_mem(void)
+{
+ scoped_guard(mutex, &fadump_mutex) {
+ if (!fw_dump.dump_active)
+ return;
+ fadump_cleanup();
+ }
+ fadump_free_elfcorehdr_buf();
fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM());
fadump_free_cpu_notes_buf();
@@ -1483,6 +1437,18 @@ static ssize_t enabled_show(struct kobject *kobj,
return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
}
+/*
+ * /sys/kernel/fadump/hotplug_ready sysfs node returns 1, which inidcates
+ * to usersapce that fadump re-registration is not required on memory
+ * hotplug events.
+ */
+static ssize_t hotplug_ready_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", 1);
+}
+
static ssize_t mem_reserved_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
@@ -1497,6 +1463,43 @@ static ssize_t registered_show(struct kobject *kobj,
return sprintf(buf, "%d\n", fw_dump.dump_registered);
}
+static ssize_t bootargs_append_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%s\n", (char *)__va(fw_dump.param_area));
+}
+
+static ssize_t bootargs_append_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ char *params;
+
+ if (!fw_dump.fadump_enabled || fw_dump.dump_active)
+ return -EPERM;
+
+ if (count >= COMMAND_LINE_SIZE)
+ return -EINVAL;
+
+ /*
+ * Fail here instead of handling this scenario with
+ * some silly workaround in capture kernel.
+ */
+ if (saved_command_line_len + count >= COMMAND_LINE_SIZE) {
+ pr_err("Appending parameters exceeds cmdline size!\n");
+ return -ENOSPC;
+ }
+
+ params = __va(fw_dump.param_area);
+ strscpy_pad(params, buf, COMMAND_LINE_SIZE);
+ /* Remove newline character at the end. */
+ if (params[count-1] == '\n')
+ params[count-1] = '\0';
+
+ return count;
+}
+
static ssize_t registered_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
@@ -1555,11 +1558,14 @@ static struct kobj_attribute release_attr = __ATTR_WO(release_mem);
static struct kobj_attribute enable_attr = __ATTR_RO(enabled);
static struct kobj_attribute register_attr = __ATTR_RW(registered);
static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved);
+static struct kobj_attribute hotplug_ready_attr = __ATTR_RO(hotplug_ready);
+static struct kobj_attribute bootargs_append_attr = __ATTR_RW(bootargs_append);
static struct attribute *fadump_attrs[] = {
&enable_attr.attr,
&register_attr.attr,
&mem_reserved_attr.attr,
+ &hotplug_ready_attr.attr,
NULL,
};
@@ -1577,6 +1583,12 @@ static void __init fadump_init_files(void)
return;
}
+ if (fw_dump.param_area) {
+ rc = sysfs_create_file(fadump_kobj, &bootargs_append_attr.attr);
+ if (rc)
+ pr_err("unable to create bootargs_append sysfs file (%d)\n", rc);
+ }
+
debugfs_create_file("fadump_region", 0444, arch_debugfs_dir, NULL,
&fadump_region_fops);
@@ -1631,6 +1643,150 @@ static void __init fadump_init_files(void)
return;
}
+static int __init fadump_setup_elfcorehdr_buf(void)
+{
+ int elf_phdr_cnt;
+ unsigned long elfcorehdr_size;
+
+ /*
+ * Program header for CPU notes comes first, followed by one for
+ * vmcoreinfo, and the remaining program headers correspond to
+ * memory regions.
+ */
+ elf_phdr_cnt = 2 + fw_dump.boot_mem_regs_cnt + memblock_num_regions(memory);
+ elfcorehdr_size = sizeof(struct elfhdr) + (elf_phdr_cnt * sizeof(struct elf_phdr));
+ elfcorehdr_size = PAGE_ALIGN(elfcorehdr_size);
+
+ fw_dump.elfcorehdr_addr = (u64)fadump_alloc_buffer(elfcorehdr_size);
+ if (!fw_dump.elfcorehdr_addr) {
+ pr_err("Failed to allocate %lu bytes for elfcorehdr\n",
+ elfcorehdr_size);
+ return -ENOMEM;
+ }
+ fw_dump.elfcorehdr_size = elfcorehdr_size;
+ return 0;
+}
+
+/*
+ * Check if the fadump header of crashed kernel is compatible with fadump kernel.
+ *
+ * It checks the magic number, endianness, and size of non-primitive type
+ * members of fadump header to ensure safe dump collection.
+ */
+static bool __init is_fadump_header_compatible(struct fadump_crash_info_header *fdh)
+{
+ if (fdh->magic_number == FADUMP_CRASH_INFO_MAGIC_OLD) {
+ pr_err("Old magic number, can't process the dump.\n");
+ return false;
+ }
+
+ if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
+ if (fdh->magic_number == swab64(FADUMP_CRASH_INFO_MAGIC))
+ pr_err("Endianness mismatch between the crashed and fadump kernels.\n");
+ else
+ pr_err("Fadump header is corrupted.\n");
+
+ return false;
+ }
+
+ /*
+ * Dump collection is not safe if the size of non-primitive type members
+ * of the fadump header do not match between crashed and fadump kernel.
+ */
+ if (fdh->pt_regs_sz != sizeof(struct pt_regs) ||
+ fdh->cpu_mask_sz != sizeof(struct cpumask)) {
+ pr_err("Fadump header size mismatch.\n");
+ return false;
+ }
+
+ return true;
+}
+
+static void __init fadump_process(void)
+{
+ struct fadump_crash_info_header *fdh;
+
+ fdh = (struct fadump_crash_info_header *) __va(fw_dump.fadumphdr_addr);
+ if (!fdh) {
+ pr_err("Crash info header is empty.\n");
+ goto err_out;
+ }
+
+ /* Avoid processing the dump if fadump header isn't compatible */
+ if (!is_fadump_header_compatible(fdh))
+ goto err_out;
+
+ /* Allocate buffer for elfcorehdr */
+ if (fadump_setup_elfcorehdr_buf())
+ goto err_out;
+
+ fadump_populate_elfcorehdr(fdh);
+
+ /* Let platform update the CPU notes in elfcorehdr */
+ if (fw_dump.ops->fadump_process(&fw_dump) < 0)
+ goto err_out;
+
+ /*
+ * elfcorehdr is now ready to be exported.
+ *
+ * set elfcorehdr_addr so that vmcore module will export the
+ * elfcorehdr through '/proc/vmcore'.
+ */
+ elfcorehdr_addr = virt_to_phys((void *)fw_dump.elfcorehdr_addr);
+ return;
+
+err_out:
+ fadump_invalidate_release_mem();
+}
+
+/*
+ * Reserve memory to store additional parameters to be passed
+ * for fadump/capture kernel.
+ */
+void __init fadump_setup_param_area(void)
+{
+ phys_addr_t range_start, range_end;
+
+ if (!fw_dump.param_area_supported || fw_dump.dump_active)
+ return;
+
+ /* This memory can't be used by PFW or bootloader as it is shared across kernels */
+ if (early_radix_enabled()) {
+ /*
+ * Anywhere in the upper half should be good enough as all memory
+ * is accessible in real mode.
+ */
+ range_start = memblock_end_of_DRAM() / 2;
+ range_end = memblock_end_of_DRAM();
+ } else {
+ /*
+ * Memory range for passing additional parameters for HASH MMU
+ * must meet the following conditions:
+ * 1. The first memory block size must be higher than the
+ * minimum RMA (MIN_RMA) size. Bootloader can use memory
+ * upto RMA size. So it should be avoided.
+ * 2. The range should be between MIN_RMA and RMA size (ppc64_rma_size)
+ * 3. It must not overlap with the fadump reserved area.
+ */
+ if (ppc64_rma_size < MIN_RMA*1024*1024)
+ return;
+
+ range_start = MIN_RMA * 1024 * 1024;
+ range_end = min(ppc64_rma_size, fw_dump.boot_mem_top);
+ }
+
+ fw_dump.param_area = memblock_phys_alloc_range(COMMAND_LINE_SIZE,
+ COMMAND_LINE_SIZE,
+ range_start,
+ range_end);
+ if (!fw_dump.param_area) {
+ pr_warn("WARNING: Could not setup area to pass additional parameters!\n");
+ return;
+ }
+
+ memset((void *)fw_dump.param_area, 0, COMMAND_LINE_SIZE);
+}
+
/*
* Prepare for firmware-assisted dump.
*/
@@ -1650,12 +1806,7 @@ int __init setup_fadump(void)
* saving it to the disk.
*/
if (fw_dump.dump_active) {
- /*
- * if dump process fails then invalidate the registration
- * and release memory before proceeding for re-registration.
- */
- if (fw_dump.ops->fadump_process(&fw_dump) < 0)
- fadump_invalidate_release_mem();
+ fadump_process();
}
/* Initialize the kernel dump memory structure and register with f/w */
else if (fw_dump.reserve_dump_area_size) {
@@ -1734,8 +1885,3 @@ static void __init fadump_reserve_crash_area(u64 base)
memblock_reserve(mstart, msize);
}
}
-
-unsigned long __init arch_reserved_kernel_pages(void)
-{
- return memblock_reserved_size() / PAGE_SIZE;
-}
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
index 20328f72f9f2..8987eee33dc8 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -23,6 +23,8 @@ EXPORT_SYMBOL_GPL(powerpc_firmware_features);
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST)
DEFINE_STATIC_KEY_FALSE(kvm_guest);
+EXPORT_SYMBOL_GPL(kvm_guest);
+
int __init check_kvm_guest(void)
{
struct device_node *hyper_node;
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index f71f2bbd4de6..2f8f3f93cbb6 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -9,6 +9,7 @@
* Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
*/
+#include <linux/export.h>
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
@@ -18,11 +19,19 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
-#include <asm/export.h>
#include <asm/asm-compat.h>
#include <asm/feature-fixups.h>
#ifdef CONFIG_VSX
+#define __REST_1FPVSR(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ REST_FPR(n,base); \
+ b 3f; \
+2: REST_VSR(n,c,base); \
+3:
+
#define __REST_32FPVSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
@@ -41,9 +50,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
2: SAVE_32VSRS(n,c,base); \
3:
#else
+#define __REST_1FPVSR(n,b,base) REST_FPR(n, base)
#define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
#define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
#endif
+#define REST_1FPVSR(n,c,base) __REST_1FPVSR(n,__REG_##c,__REG_##base)
#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
@@ -67,6 +78,7 @@ _GLOBAL(store_fp_state)
SAVE_32FPVSRS(0, R4, R3)
mffs fr0
stfd fr0,FPSTATE_FPSCR(r3)
+ REST_1FPVSR(0, R4, R3)
blr
EXPORT_SYMBOL(store_fp_state)
@@ -138,4 +150,5 @@ _GLOBAL(save_fpu)
2: SAVE_32FPVSRS(0, R4, R6)
mffs fr0
stfd fr0,FPSTATE_FPSCR(r6)
+ REST_1FPVSR(0, R4, R6)
blr
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index c3286260a7d1..9cba7dbf58dd 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -21,17 +21,9 @@
mtspr SPRN_SPRG_SCRATCH1,r11
mfspr r10, SPRN_SPRG_THREAD
.if \handle_dar_dsisr
-#ifdef CONFIG_40x
- mfspr r11, SPRN_DEAR
-#else
mfspr r11, SPRN_DAR
-#endif
stw r11, DAR(r10)
-#ifdef CONFIG_40x
- mfspr r11, SPRN_ESR
-#else
mfspr r11, SPRN_DSISR
-#endif
stw r11, DSISR(r10)
.endif
mfspr r11, SPRN_SRR0
@@ -96,9 +88,7 @@
.endif
lwz r9, SRR1(r12)
lwz r12, SRR0(r12)
-#ifdef CONFIG_40x
- rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
-#elif defined(CONFIG_PPC_8xx)
+#ifdef CONFIG_PPC_8xx
mtspr SPRN_EID, r2 /* Set MSR_RI */
#else
li r10, MSR_KERNEL /* can take exceptions */
@@ -112,7 +102,7 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt)
stw r0,GPR0(r1)
lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
addi r10,r10,STACK_FRAME_REGS_MARKER@l
- stw r10,8(r1)
+ stw r10,STACK_INT_FRAME_MARKER(r1)
li r10, \trapno
stw r10,_TRAP(r1)
SAVE_GPRS(3, 8, r1)
@@ -127,7 +117,7 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt)
mfspr r10,SPRN_XER
addi r2, r2, -THREAD
stw r10,_XER(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
.endm
.macro prepare_transfer_to_handler
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
deleted file mode 100644
index 088f500896c7..000000000000
--- a/arch/powerpc/kernel/head_40x.S
+++ /dev/null
@@ -1,718 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
- * Initial PowerPC version.
- * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu>
- * Rewritten for PReP
- * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
- * Low-level exception handers, MMU support, and rewrite.
- * Copyright (c) 1997 Dan Malek <dmalek@jlc.net>
- * PowerPC 8xx modifications.
- * Copyright (c) 1998-1999 TiVo, Inc.
- * PowerPC 403GCX modifications.
- * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
- * PowerPC 403GCX/405GP modifications.
- * Copyright 2000 MontaVista Software Inc.
- * PPC405 modifications
- * PowerPC 403GCX/405GP modifications.
- * Author: MontaVista Software, Inc.
- * frank_rowand@mvista.com or source@mvista.com
- * debbie_chu@mvista.com
- *
- * Module name: head_4xx.S
- *
- * Description:
- * Kernel execution entry point code.
- */
-
-#include <linux/init.h>
-#include <linux/pgtable.h>
-#include <linux/sizes.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/mmu.h>
-#include <asm/cputable.h>
-#include <asm/thread_info.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/ptrace.h>
-#include <asm/export.h>
-
-#include "head_32.h"
-
-/* As with the other PowerPC ports, it is expected that when code
- * execution begins here, the following registers contain valid, yet
- * optional, information:
- *
- * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.)
- * r4 - Starting address of the init RAM disk
- * r5 - Ending address of the init RAM disk
- * r6 - Start of kernel command line string (e.g. "mem=96m")
- * r7 - End of kernel command line string
- *
- * This is all going to change RSN when we add bi_recs....... -- Dan
- */
- __HEAD
-_GLOBAL(_stext);
-_GLOBAL(_start);
-
- mr r31,r3 /* save device tree ptr */
-
- /* We have to turn on the MMU right away so we get cache modes
- * set correctly.
- */
- bl initial_mmu
-
-/* We now have the lower 16 Meg mapped into TLB entries, and the caches
- * ready to work.
- */
-turn_on_mmu:
- lis r0,MSR_KERNEL@h
- ori r0,r0,MSR_KERNEL@l
- mtspr SPRN_SRR1,r0
- lis r0,start_here@h
- ori r0,r0,start_here@l
- mtspr SPRN_SRR0,r0
- rfi /* enables MMU */
- b . /* prevent prefetch past rfi */
-
-/*
- * This area is used for temporarily saving registers during the
- * critical exception prolog.
- */
- . = 0xc0
-crit_save:
-_GLOBAL(crit_r10)
- .space 4
-_GLOBAL(crit_r11)
- .space 4
-_GLOBAL(crit_srr0)
- .space 4
-_GLOBAL(crit_srr1)
- .space 4
-_GLOBAL(crit_r1)
- .space 4
-_GLOBAL(crit_dear)
- .space 4
-_GLOBAL(crit_esr)
- .space 4
-
-/*
- * Exception prolog for critical exceptions. This is a little different
- * from the normal exception prolog above since a critical exception
- * can potentially occur at any point during normal exception processing.
- * Thus we cannot use the same SPRG registers as the normal prolog above.
- * Instead we use a couple of words of memory at low physical addresses.
- * This is OK since we don't support SMP on these processors.
- */
-.macro CRITICAL_EXCEPTION_PROLOG trapno name
- stw r10,crit_r10@l(0) /* save two registers to work with */
- stw r11,crit_r11@l(0)
- mfspr r10,SPRN_SRR0
- mfspr r11,SPRN_SRR1
- stw r10,crit_srr0@l(0)
- stw r11,crit_srr1@l(0)
- mfspr r10,SPRN_DEAR
- mfspr r11,SPRN_ESR
- stw r10,crit_dear@l(0)
- stw r11,crit_esr@l(0)
- mfcr r10 /* save CR in r10 for now */
- mfspr r11,SPRN_SRR3 /* check whether user or kernel */
- andi. r11,r11,MSR_PR
- lis r11,(critirq_ctx-PAGE_OFFSET)@ha
- lwz r11,(critirq_ctx-PAGE_OFFSET)@l(r11)
- beq 1f
- /* COMING FROM USER MODE */
- mfspr r11,SPRN_SPRG_THREAD /* if from user, start at top of */
- lwz r11,TASK_STACK-THREAD(r11) /* this thread's kernel stack */
-1: stw r1,crit_r1@l(0)
- addi r1,r11,THREAD_SIZE-INT_FRAME_SIZE /* Alloc an excpt frm */
- LOAD_REG_IMMEDIATE(r11, MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)) /* re-enable MMU */
- mtspr SPRN_SRR1, r11
- lis r11, 1f@h
- ori r11, r11, 1f@l
- mtspr SPRN_SRR0, r11
- rfi
-
- .text
-1:
-\name\()_virt:
- lwz r11,crit_r1@l(0)
- stw r11,GPR1(r1)
- stw r11,0(r1)
- mr r11,r1
- stw r10,_CCR(r11) /* save various registers */
- stw r12,GPR12(r11)
- stw r9,GPR9(r11)
- mflr r10
- stw r10,_LINK(r11)
- lis r9,PAGE_OFFSET@ha
- lwz r10,crit_r10@l(r9)
- lwz r12,crit_r11@l(r9)
- stw r10,GPR10(r11)
- stw r12,GPR11(r11)
- lwz r12,crit_dear@l(r9)
- lwz r9,crit_esr@l(r9)
- stw r12,_DEAR(r11) /* since they may have had stuff */
- stw r9,_ESR(r11) /* exception was taken */
- mfspr r12,SPRN_SRR2
- mfspr r9,SPRN_SRR3
- rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
- COMMON_EXCEPTION_PROLOG_END \trapno + 2
-_ASM_NOKPROBE_SYMBOL(\name\()_virt)
-.endm
-
- /*
- * State at this point:
- * r9 saved in stack frame, now saved SRR3 & ~MSR_WE
- * r10 saved in crit_r10 and in stack frame, trashed
- * r11 saved in crit_r11 and in stack frame,
- * now phys stack/exception frame pointer
- * r12 saved in stack frame, now saved SRR2
- * CR saved in stack frame, CR0.EQ = !SRR3.PR
- * LR, DEAR, ESR in stack frame
- * r1 saved in stack frame, now virt stack/excframe pointer
- * r0, r3-r8 saved in stack frame
- */
-
-/*
- * Exception vectors.
- */
-#define CRITICAL_EXCEPTION(n, label, hdlr) \
- START_EXCEPTION(n, label); \
- CRITICAL_EXCEPTION_PROLOG n label; \
- prepare_transfer_to_handler; \
- bl hdlr; \
- b ret_from_crit_exc
-
-/*
- * 0x0100 - Critical Interrupt Exception
- */
- CRITICAL_EXCEPTION(0x0100, CriticalInterrupt, unknown_exception)
-
-/*
- * 0x0200 - Machine Check Exception
- */
- CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
-
-/*
- * 0x0300 - Data Storage Exception
- * This happens for just a few reasons. U0 set (but we don't do that),
- * or zone protection fault (user violation, write to protected page).
- * The other Data TLB exceptions bail out to this point
- * if they can't resolve the lightweight TLB fault.
- */
- START_EXCEPTION(0x0300, DataStorage)
- EXCEPTION_PROLOG 0x300 DataStorage handle_dar_dsisr=1
- prepare_transfer_to_handler
- bl do_page_fault
- b interrupt_return
-
-/*
- * 0x0400 - Instruction Storage Exception
- * This is caused by a fetch from non-execute or guarded pages.
- */
- START_EXCEPTION(0x0400, InstructionAccess)
- EXCEPTION_PROLOG 0x400 InstructionAccess
- li r5,0
- stw r5, _ESR(r11) /* Zero ESR */
- stw r12, _DEAR(r11) /* SRR0 as DEAR */
- prepare_transfer_to_handler
- bl do_page_fault
- b interrupt_return
-
-/* 0x0500 - External Interrupt Exception */
- EXCEPTION(0x0500, HardwareInterrupt, do_IRQ)
-
-/* 0x0600 - Alignment Exception */
- START_EXCEPTION(0x0600, Alignment)
- EXCEPTION_PROLOG 0x600 Alignment handle_dar_dsisr=1
- prepare_transfer_to_handler
- bl alignment_exception
- REST_NVGPRS(r1)
- b interrupt_return
-
-/* 0x0700 - Program Exception */
- START_EXCEPTION(0x0700, ProgramCheck)
- EXCEPTION_PROLOG 0x700 ProgramCheck handle_dar_dsisr=1
- prepare_transfer_to_handler
- bl program_check_exception
- REST_NVGPRS(r1)
- b interrupt_return
-
- EXCEPTION(0x0800, Trap_08, unknown_exception)
- EXCEPTION(0x0900, Trap_09, unknown_exception)
- EXCEPTION(0x0A00, Trap_0A, unknown_exception)
- EXCEPTION(0x0B00, Trap_0B, unknown_exception)
-
-/* 0x0C00 - System Call Exception */
- START_EXCEPTION(0x0C00, SystemCall)
- SYSCALL_ENTRY 0xc00
-/* Trap_0D is commented out to get more space for system call exception */
-
-/* EXCEPTION(0x0D00, Trap_0D, unknown_exception) */
- EXCEPTION(0x0E00, Trap_0E, unknown_exception)
- EXCEPTION(0x0F00, Trap_0F, unknown_exception)
-
-/* 0x1000 - Programmable Interval Timer (PIT) Exception */
- START_EXCEPTION(0x1000, DecrementerTrap)
- b Decrementer
-
-/* 0x1010 - Fixed Interval Timer (FIT) Exception */
- START_EXCEPTION(0x1010, FITExceptionTrap)
- b FITException
-
-/* 0x1020 - Watchdog Timer (WDT) Exception */
- START_EXCEPTION(0x1020, WDTExceptionTrap)
- b WDTException
-
-/* 0x1100 - Data TLB Miss Exception
- * As the name implies, translation is not in the MMU, so search the
- * page tables and fix it. The only purpose of this function is to
- * load TLB entries from the page table if they exist.
- */
- START_EXCEPTION(0x1100, DTLBMiss)
- mtspr SPRN_SPRG_SCRATCH5, r10 /* Save some working registers */
- mtspr SPRN_SPRG_SCRATCH6, r11
- mtspr SPRN_SPRG_SCRATCH3, r12
- mtspr SPRN_SPRG_SCRATCH4, r9
- mfcr r12
- mfspr r9, SPRN_PID
- rlwimi r12, r9, 0, 0xff
- mfspr r10, SPRN_DEAR /* Get faulting address */
-
- /* If we are faulting a kernel address, we have to use the
- * kernel page tables.
- */
- lis r11, PAGE_OFFSET@h
- cmplw r10, r11
- blt+ 3f
- lis r11, swapper_pg_dir@h
- ori r11, r11, swapper_pg_dir@l
- li r9, 0
- mtspr SPRN_PID, r9 /* TLB will have 0 TID */
- b 4f
-
- /* Get the PGD for the current thread.
- */
-3:
- mfspr r11,SPRN_SPRG_THREAD
- lwz r11,PGDIR(r11)
-#ifdef CONFIG_PPC_KUAP
- rlwinm. r9, r9, 0, 0xff
- beq 5f /* Kuap fault */
-#endif
-4:
- tophys(r11, r11)
- rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
- lwz r11, 0(r11) /* Get L1 entry */
- andi. r9, r11, _PMD_PRESENT /* Check if it points to a PTE page */
- beq 2f /* Bail if no table */
-
- rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
- lwz r11, 0(r11) /* Get Linux PTE */
- li r9, _PAGE_PRESENT | _PAGE_ACCESSED
- andc. r9, r9, r11 /* Check permission */
- bne 5f
-
- rlwinm r9, r11, 1, _PAGE_RW /* dirty => rw */
- and r9, r9, r11 /* hwwrite = dirty & rw */
- rlwimi r11, r9, 0, _PAGE_RW /* replace rw by hwwrite */
-
- /* Create TLB tag. This is the faulting address plus a static
- * set of bits. These are size, valid, E, U0.
- */
- li r9, 0x00c0
- rlwimi r10, r9, 0, 20, 31
-
- b finish_tlb_load
-
-2: /* Check for possible large-page pmd entry */
- rlwinm. r9, r11, 2, 22, 24
- beq 5f
-
- /* Create TLB tag. This is the faulting address, plus a static
- * set of bits (valid, E, U0) plus the size from the PMD.
- */
- ori r9, r9, 0x40
- rlwimi r10, r9, 0, 20, 31
-
- b finish_tlb_load
-
-5:
- /* The bailout. Restore registers to pre-exception conditions
- * and call the heavyweights to help us out.
- */
- mtspr SPRN_PID, r12
- mtcrf 0x80, r12
- mfspr r9, SPRN_SPRG_SCRATCH4
- mfspr r12, SPRN_SPRG_SCRATCH3
- mfspr r11, SPRN_SPRG_SCRATCH6
- mfspr r10, SPRN_SPRG_SCRATCH5
- b DataStorage
-
-/* 0x1200 - Instruction TLB Miss Exception
- * Nearly the same as above, except we get our information from different
- * registers and bailout to a different point.
- */
- START_EXCEPTION(0x1200, ITLBMiss)
- mtspr SPRN_SPRG_SCRATCH5, r10 /* Save some working registers */
- mtspr SPRN_SPRG_SCRATCH6, r11
- mtspr SPRN_SPRG_SCRATCH3, r12
- mtspr SPRN_SPRG_SCRATCH4, r9
- mfcr r12
- mfspr r9, SPRN_PID
- rlwimi r12, r9, 0, 0xff
- mfspr r10, SPRN_SRR0 /* Get faulting address */
-
- /* If we are faulting a kernel address, we have to use the
- * kernel page tables.
- */
- lis r11, PAGE_OFFSET@h
- cmplw r10, r11
- blt+ 3f
- lis r11, swapper_pg_dir@h
- ori r11, r11, swapper_pg_dir@l
- li r9, 0
- mtspr SPRN_PID, r9 /* TLB will have 0 TID */
- b 4f
-
- /* Get the PGD for the current thread.
- */
-3:
- mfspr r11,SPRN_SPRG_THREAD
- lwz r11,PGDIR(r11)
-#ifdef CONFIG_PPC_KUAP
- rlwinm. r9, r9, 0, 0xff
- beq 5f /* Kuap fault */
-#endif
-4:
- tophys(r11, r11)
- rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
- lwz r11, 0(r11) /* Get L1 entry */
- andi. r9, r11, _PMD_PRESENT /* Check if it points to a PTE page */
- beq 2f /* Bail if no table */
-
- rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
- lwz r11, 0(r11) /* Get Linux PTE */
- li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
- andc. r9, r9, r11 /* Check permission */
- bne 5f
-
- rlwinm r9, r11, 1, _PAGE_RW /* dirty => rw */
- and r9, r9, r11 /* hwwrite = dirty & rw */
- rlwimi r11, r9, 0, _PAGE_RW /* replace rw by hwwrite */
-
- /* Create TLB tag. This is the faulting address plus a static
- * set of bits. These are size, valid, E, U0.
- */
- li r9, 0x00c0
- rlwimi r10, r9, 0, 20, 31
-
- b finish_tlb_load
-
-2: /* Check for possible large-page pmd entry */
- rlwinm. r9, r11, 2, 22, 24
- beq 5f
-
- /* Create TLB tag. This is the faulting address, plus a static
- * set of bits (valid, E, U0) plus the size from the PMD.
- */
- ori r9, r9, 0x40
- rlwimi r10, r9, 0, 20, 31
-
- b finish_tlb_load
-
-5:
- /* The bailout. Restore registers to pre-exception conditions
- * and call the heavyweights to help us out.
- */
- mtspr SPRN_PID, r12
- mtcrf 0x80, r12
- mfspr r9, SPRN_SPRG_SCRATCH4
- mfspr r12, SPRN_SPRG_SCRATCH3
- mfspr r11, SPRN_SPRG_SCRATCH6
- mfspr r10, SPRN_SPRG_SCRATCH5
- b InstructionAccess
-
- EXCEPTION(0x1300, Trap_13, unknown_exception)
- EXCEPTION(0x1400, Trap_14, unknown_exception)
- EXCEPTION(0x1500, Trap_15, unknown_exception)
- EXCEPTION(0x1600, Trap_16, unknown_exception)
- EXCEPTION(0x1700, Trap_17, unknown_exception)
- EXCEPTION(0x1800, Trap_18, unknown_exception)
- EXCEPTION(0x1900, Trap_19, unknown_exception)
- EXCEPTION(0x1A00, Trap_1A, unknown_exception)
- EXCEPTION(0x1B00, Trap_1B, unknown_exception)
- EXCEPTION(0x1C00, Trap_1C, unknown_exception)
- EXCEPTION(0x1D00, Trap_1D, unknown_exception)
- EXCEPTION(0x1E00, Trap_1E, unknown_exception)
- EXCEPTION(0x1F00, Trap_1F, unknown_exception)
-
-/* Check for a single step debug exception while in an exception
- * handler before state has been saved. This is to catch the case
- * where an instruction that we are trying to single step causes
- * an exception (eg ITLB/DTLB miss) and thus the first instruction of
- * the exception handler generates a single step debug exception.
- *
- * If we get a debug trap on the first instruction of an exception handler,
- * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is
- * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR).
- * The exception handler was handling a non-critical interrupt, so it will
- * save (and later restore) the MSR via SPRN_SRR1, which will still have
- * the MSR_DE bit set.
- */
- /* 0x2000 - Debug Exception */
- START_EXCEPTION(0x2000, DebugTrap)
- CRITICAL_EXCEPTION_PROLOG 0x2000 DebugTrap
-
- /*
- * If this is a single step or branch-taken exception in an
- * exception entry sequence, it was probably meant to apply to
- * the code where the exception occurred (since exception entry
- * doesn't turn off DE automatically). We simulate the effect
- * of turning off DE on entry to an exception handler by turning
- * off DE in the SRR3 value and clearing the debug status.
- */
- mfspr r10,SPRN_DBSR /* check single-step/branch taken */
- andis. r10,r10,DBSR_IC@h
- beq+ 2f
-
- andi. r10,r9,MSR_IR|MSR_PR /* check supervisor + MMU off */
- beq 1f /* branch and fix it up */
-
- mfspr r10,SPRN_SRR2 /* Faulting instruction address */
- cmplwi r10,0x2100
- bgt+ 2f /* address above exception vectors */
-
- /* here it looks like we got an inappropriate debug exception. */
-1: rlwinm r9,r9,0,~MSR_DE /* clear DE in the SRR3 value */
- lis r10,DBSR_IC@h /* clear the IC event */
- mtspr SPRN_DBSR,r10
- /* restore state and get out */
- lwz r10,_CCR(r11)
- lwz r0,GPR0(r11)
- lwz r1,GPR1(r11)
- mtcrf 0x80,r10
- mtspr SPRN_SRR2,r12
- mtspr SPRN_SRR3,r9
- lwz r9,GPR9(r11)
- lwz r12,GPR12(r11)
- lwz r10,crit_r10@l(0)
- lwz r11,crit_r11@l(0)
- rfci
- b .
-
- /* continue normal handling for a critical exception... */
-2: mfspr r4,SPRN_DBSR
- stw r4,_ESR(r11) /* DebugException takes DBSR in _ESR */
- prepare_transfer_to_handler
- bl DebugException
- b ret_from_crit_exc
-
- /* Programmable Interval Timer (PIT) Exception. (from 0x1000) */
- __HEAD
-Decrementer:
- EXCEPTION_PROLOG 0x1000 Decrementer
- lis r0,TSR_PIS@h
- mtspr SPRN_TSR,r0 /* Clear the PIT exception */
- prepare_transfer_to_handler
- bl timer_interrupt
- b interrupt_return
-
- /* Fixed Interval Timer (FIT) Exception. (from 0x1010) */
- __HEAD
-FITException:
- EXCEPTION_PROLOG 0x1010 FITException
- prepare_transfer_to_handler
- bl unknown_exception
- b interrupt_return
-
- /* Watchdog Timer (WDT) Exception. (from 0x1020) */
- __HEAD
-WDTException:
- CRITICAL_EXCEPTION_PROLOG 0x1020 WDTException
- prepare_transfer_to_handler
- bl WatchdogException
- b ret_from_crit_exc
-
-/* Other PowerPC processors, namely those derived from the 6xx-series
- * have vectors from 0x2100 through 0x2F00 defined, but marked as reserved.
- * However, for the 4xx-series processors these are neither defined nor
- * reserved.
- */
-
- __HEAD
- /* Damn, I came up one instruction too many to fit into the
- * exception space :-). Both the instruction and data TLB
- * miss get to this point to load the TLB.
- * r10 - TLB_TAG value
- * r11 - Linux PTE
- * r9 - available to use
- * PID - loaded with proper value when we get here
- * Upon exit, we reload everything and RFI.
- * Actually, it will fit now, but oh well.....a common place
- * to load the TLB.
- */
-tlb_4xx_index:
- .long 0
-finish_tlb_load:
- /*
- * Clear out the software-only bits in the PTE to generate the
- * TLB_DATA value. These are the bottom 2 bits of the RPM, the
- * top 3 bits of the zone field, and M.
- */
- li r9, 0x0ce2
- andc r11, r11, r9
-
- /* load the next available TLB index. */
- lwz r9, tlb_4xx_index@l(0)
- addi r9, r9, 1
- andi. r9, r9, PPC40X_TLB_SIZE - 1
- stw r9, tlb_4xx_index@l(0)
-
- tlbwe r11, r9, TLB_DATA /* Load TLB LO */
- tlbwe r10, r9, TLB_TAG /* Load TLB HI */
-
- /* Done...restore registers and get out of here.
- */
- mtspr SPRN_PID, r12
- mtcrf 0x80, r12
- mfspr r9, SPRN_SPRG_SCRATCH4
- mfspr r12, SPRN_SPRG_SCRATCH3
- mfspr r11, SPRN_SPRG_SCRATCH6
- mfspr r10, SPRN_SPRG_SCRATCH5
- rfi /* Should sync shadow TLBs */
- b . /* prevent prefetch past rfi */
-
-/* This is where the main kernel code starts.
- */
-start_here:
-
- /* ptr to current */
- lis r2,init_task@h
- ori r2,r2,init_task@l
-
- /* ptr to phys current thread */
- tophys(r4,r2)
- addi r4,r4,THREAD /* init task's THREAD */
- mtspr SPRN_SPRG_THREAD,r4
-
- /* stack */
- lis r1,init_thread_union@ha
- addi r1,r1,init_thread_union@l
- li r0,0
- stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
-
- bl early_init /* We have to do this with MMU on */
-
-/*
- * Decide what sort of machine this is and initialize the MMU.
- */
-#ifdef CONFIG_KASAN
- bl kasan_early_init
-#endif
- li r3,0
- mr r4,r31
- bl machine_init
- bl MMU_init
-
-/* Go back to running unmapped so we can load up new values
- * and change to using our exception vectors.
- * On the 4xx, all we have to do is invalidate the TLB to clear
- * the old 16M byte TLB mappings.
- */
- lis r4,2f@h
- ori r4,r4,2f@l
- tophys(r4,r4)
- lis r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@h
- ori r3,r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@l
- mtspr SPRN_SRR0,r4
- mtspr SPRN_SRR1,r3
- rfi
- b . /* prevent prefetch past rfi */
-
-/* Load up the kernel context */
-2:
- sync /* Flush to memory before changing TLB */
- tlbia
- isync /* Flush shadow TLBs */
-
- /* set up the PTE pointers for the Abatron bdiGDB.
- */
- lis r6, swapper_pg_dir@h
- ori r6, r6, swapper_pg_dir@l
- lis r5, abatron_pteptrs@h
- ori r5, r5, abatron_pteptrs@l
- stw r5, 0xf0(0) /* Must match your Abatron config file */
- tophys(r5,r5)
- stw r6, 0(r5)
-
-/* Now turn on the MMU for real! */
- lis r4,MSR_KERNEL@h
- ori r4,r4,MSR_KERNEL@l
- lis r3,start_kernel@h
- ori r3,r3,start_kernel@l
- mtspr SPRN_SRR0,r3
- mtspr SPRN_SRR1,r4
- rfi /* enable MMU and jump to start_kernel */
- b . /* prevent prefetch past rfi */
-
-/* Set up the initial MMU state so we can do the first level of
- * kernel initialization. This maps the first 32 MBytes of memory 1:1
- * virtual to physical and more importantly sets the cache mode.
- */
-initial_mmu:
- tlbia /* Invalidate all TLB entries */
- isync
-
- /* We should still be executing code at physical address 0x0000xxxx
- * at this point. However, start_here is at virtual address
- * 0xC000xxxx. So, set up a TLB mapping to cover this once
- * translation is enabled.
- */
-
- lis r3,KERNELBASE@h /* Load the kernel virtual address */
- ori r3,r3,KERNELBASE@l
- tophys(r4,r3) /* Load the kernel physical address */
-
- iccci r0,r3 /* Invalidate the i-cache before use */
-
- /* Load the kernel PID.
- */
- li r0,0
- mtspr SPRN_PID,r0
- sync
-
- /* Configure and load one entry into TLB slots 63 */
- clrrwi r4,r4,10 /* Mask off the real page number */
- ori r4,r4,(TLB_WR | TLB_EX) /* Set the write and execute bits */
-
- clrrwi r3,r3,10 /* Mask off the effective page number */
- ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_16M))
-
- li r0,63 /* TLB slot 63 */
-
- tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */
- tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */
-
- li r0,62 /* TLB slot 62 */
- addis r4,r4,SZ_16M@h
- addis r3,r3,SZ_16M@h
- tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */
- tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */
-
- isync
-
- /* Establish the exception vector base
- */
- lis r4,KERNELBASE@h /* EVPR only uses the high 16-bits */
- tophys(r0,r4) /* Use the physical address */
- mtspr SPRN_EVPR,r0
-
- blr
-
-_GLOBAL(abort)
- mfspr r13,SPRN_DBCR0
- oris r13,r13,DBCR0_RST_SYSTEM@h
- mtspr SPRN_DBCR0,r13
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index f15cb9fdb692..25642e802ed3 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -35,7 +35,6 @@
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
#include <asm/synch.h>
-#include <asm/export.h>
#include <asm/code-patching-asm.h>
#include "head_booke.h"
@@ -109,7 +108,7 @@ _GLOBAL(_start);
lis r1,init_thread_union@h
ori r1,r1,init_thread_union@l
li r0,0
- stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
bl early_init
@@ -315,8 +314,8 @@ interrupt_base:
* kernel page tables.
*/
lis r11, PAGE_OFFSET@h
- cmplw r10, r11
- blt+ 3f
+ cmplw cr7, r10, r11
+ blt+ cr7, 3f
lis r11, swapper_pg_dir@h
ori r11, r11, swapper_pg_dir@l
@@ -343,7 +342,7 @@ interrupt_base:
mtspr SPRN_MMUCR,r12
/* Mask of required permission bits. Note that while we
- * do copy ESR:ST to _PAGE_RW position as trying to write
+ * do copy ESR:ST to _PAGE_WRITE position as trying to write
* to an RO page is pretty common, we don't do it with
* _PAGE_DIRTY. We could do it, but it's a fairly rare
* event so I'd rather take the overhead when it happens
@@ -356,7 +355,7 @@ interrupt_base:
* place or can we save a couple of instructions here ?
*/
mfspr r12,SPRN_ESR
- li r13,_PAGE_PRESENT|_PAGE_ACCESSED
+ li r13,_PAGE_PRESENT|_PAGE_ACCESSED|_PAGE_READ
rlwimi r13,r12,10,30,30
/* Load the PTE */
@@ -429,8 +428,8 @@ interrupt_base:
* kernel page tables.
*/
lis r11, PAGE_OFFSET@h
- cmplw r10, r11
- blt+ 3f
+ cmplw cr7, r10, r11
+ blt+ cr7, 3f
lis r11, swapper_pg_dir@h
ori r11, r11, swapper_pg_dir@l
@@ -516,6 +515,7 @@ interrupt_base:
* r11 - PTE high word value
* r12 - PTE low word value
* r13 - TLB index
+ * cr7 - Result of comparison with PAGE_OFFSET
* MMUCR - loaded with proper value when we get here
* Upon exit, we reload everything and RFI.
*/
@@ -534,11 +534,10 @@ finish_tlb_load_44x:
tlbwe r10,r13,PPC44x_TLB_PAGEID /* Write PAGEID */
/* And WS 2 */
- li r10,0xf85 /* Mask to apply from PTE */
- rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */
+ li r10,0xf84 /* Mask to apply from PTE */
+ rlwimi r10,r12,29,30,31 /* DIRTY,READ -> SW,SR position */
and r11,r12,r10 /* Mask PTE bits to keep */
- andi. r10,r12,_PAGE_USER /* User page ? */
- beq 1f /* nope, leave U bits empty */
+ bge cr7,1f /* User page ? no, leave U bits empty */
rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */
rlwinm r11,r11,0,~PPC44x_TLB_SX /* Clear SX if User page */
1: tlbwe r11,r13,PPC44x_TLB_ATTRIB /* Write ATTRIB */
@@ -569,8 +568,8 @@ finish_tlb_load_44x:
* kernel page tables.
*/
lis r11,PAGE_OFFSET@h
- cmplw cr0,r10,r11
- blt+ 3f
+ cmplw cr7,r10,r11
+ blt+ cr7,3f
lis r11,swapper_pg_dir@h
ori r11,r11, swapper_pg_dir@l
li r12,0 /* MMUCR = 0 */
@@ -587,7 +586,7 @@ finish_tlb_load_44x:
4: mtspr SPRN_MMUCR,r12 /* Set MMUCR */
/* Mask of required permission bits. Note that while we
- * do copy ESR:ST to _PAGE_RW position as trying to write
+ * do copy ESR:ST to _PAGE_WRITE position as trying to write
* to an RO page is pretty common, we don't do it with
* _PAGE_DIRTY. We could do it, but it's a fairly rare
* event so I'd rather take the overhead when it happens
@@ -600,7 +599,7 @@ finish_tlb_load_44x:
* place or can we save a couple of instructions here ?
*/
mfspr r12,SPRN_ESR
- li r13,_PAGE_PRESENT|_PAGE_ACCESSED
+ li r13,_PAGE_PRESENT|_PAGE_ACCESSED|_PAGE_READ
rlwimi r13,r12,10,30,30
/* Load the PTE */
@@ -670,8 +669,8 @@ finish_tlb_load_44x:
* kernel page tables.
*/
lis r11,PAGE_OFFSET@h
- cmplw cr0,r10,r11
- blt+ 3f
+ cmplw cr7,r10,r11
+ blt+ cr7,3f
lis r11,swapper_pg_dir@h
ori r11,r11, swapper_pg_dir@l
li r12,0 /* MMUCR = 0 */
@@ -745,6 +744,7 @@ finish_tlb_load_44x:
* r11 - PTE high word value
* r12 - PTE low word value
* r13 - free to use
+ * cr7 - Result of comparison with PAGE_OFFSET
* MMUCR - loaded with proper value when we get here
* Upon exit, we reload everything and RFI.
*/
@@ -754,11 +754,10 @@ finish_tlb_load_47x:
tlbwe r11,r13,1
/* And make up word 2 */
- li r10,0xf85 /* Mask to apply from PTE */
- rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */
+ li r10,0xf84 /* Mask to apply from PTE */
+ rlwimi r10,r12,29,30,31 /* DIRTY,READ -> SW,SR position */
and r11,r12,r10 /* Mask PTE bits to keep */
- andi. r10,r12,_PAGE_USER /* User page ? */
- beq 1f /* nope, leave U bits empty */
+ bge cr7,1f /* User page ? no, leave U bits empty */
rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */
rlwinm r11,r11,0,~PPC47x_TLB2_SX /* Clear SX if User page */
1: tlbwe r11,r13,2
@@ -1012,7 +1011,7 @@ _GLOBAL(start_secondary_47x)
*/
lis r1,temp_boot_stack@h
ori r1,r1,temp_boot_stack@l
- addi r1,r1,1024-STACK_FRAME_OVERHEAD
+ addi r1,r1,1024-STACK_FRAME_MIN_SIZE
li r0,0
stw r0,0(r1)
bl mmu_init_secondary
@@ -1025,7 +1024,7 @@ _GLOBAL(start_secondary_47x)
lwz r1,TASK_STACK(r2)
/* Current stack pointer */
- addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE
li r0,0
stw r0,0(r1)
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index d3eea633d11a..63432a33ec49 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -18,6 +18,7 @@
* variants.
*/
+#include <linux/linkage.h>
#include <linux/threads.h>
#include <linux/init.h>
#include <asm/reg.h>
@@ -39,7 +40,6 @@
#include <asm/hw_irq.h>
#include <asm/cputhreads.h>
#include <asm/ppc-opcode.h>
-#include <asm/export.h>
#include <asm/feature-fixups.h>
#ifdef CONFIG_PPC_BOOK3S
#include <asm/exception-64s.h>
@@ -75,6 +75,13 @@
* 2. The kernel is entered at __start
*/
+/*
+ * boot_from_prom and prom_init run at the physical address. Everything
+ * after prom and kexec entry run at the virtual address (PAGE_OFFSET).
+ * Secondaries run at the virtual address from generic_secondary_common_init
+ * onward.
+ */
+
OPEN_FIXED_SECTION(first_256B, 0x0, 0x100)
USE_FIXED_SECTION(first_256B)
/*
@@ -143,7 +150,7 @@ DEFINE_FIXED_SYMBOL(__run_at_load, first_256B)
.globl __secondary_hold
__secondary_hold:
FIXUP_ENDIAN
-#ifndef CONFIG_PPC_BOOK3E
+#ifndef CONFIG_PPC_BOOK3E_64
mfmsr r24
ori r24,r24,MSR_RI
mtmsrd r24 /* RI on */
@@ -159,17 +166,13 @@ __secondary_hold:
std r24,(ABS_ADDR(__secondary_hold_acknowledge, first_256B))(0)
sync
- li r26,0
-#ifdef CONFIG_PPC_BOOK3E
- tovirt(r26,r26)
-#endif
/* All secondary cpus wait here until told to start. */
-100: ld r12,(ABS_ADDR(__secondary_hold_spinloop, first_256B))(r26)
+100: ld r12,(ABS_ADDR(__secondary_hold_spinloop, first_256B))(0)
cmpdi 0,r12,0
beq 100b
#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
tovirt(r12,r12)
#endif
mtctr r12
@@ -178,7 +181,7 @@ __secondary_hold:
* it may be the case that other platforms have r4 right to
* begin with, this gives us some safety in case it is not
*/
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
mr r4,r25
#else
li r4,0
@@ -192,13 +195,6 @@ __secondary_hold:
#endif
CLOSE_FIXED_SECTION(first_256B)
-/* This value is used to mark exception frames on the stack. */
- .section ".toc","aw"
-/* This value is used to mark exception frames on the stack. */
-exception_marker:
- .tc ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER
- .previous
-
/*
* On server, we include the exception vectors code here as it
* relies on absolute addressing which is only possible within
@@ -214,7 +210,7 @@ USE_TEXT_SECTION()
#include "interrupt_64.S"
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
/*
* The booting_thread_hwid holds the thread id we want to boot in cpu
* hotplug case. It is set by cpu hotplug code, and is invalid by default.
@@ -313,16 +309,14 @@ _GLOBAL(fsl_secondary_thread_init)
/* turn on 64-bit mode */
bl enable_64b_mode
- /* get a valid TOC pointer, wherever we're mapped at */
- bl relative_toc
- tovirt(r2,r2)
-
/* Book3E initialization */
mr r3,r24
bl book3e_secondary_thread_init
+ bl relative_toc
+
b generic_secondary_common_init
-#endif /* CONFIG_PPC_BOOK3E */
+#endif /* CONFIG_PPC_BOOK3E_64 */
/*
* On pSeries and most other platforms, secondary processors spin
@@ -335,22 +329,24 @@ _GLOBAL(fsl_secondary_thread_init)
*/
_GLOBAL(generic_secondary_smp_init)
FIXUP_ENDIAN
+
+ li r13,0
+
+ /* Poison TOC */
+ li r2,-1
+
mr r24,r3
mr r25,r4
/* turn on 64-bit mode */
bl enable_64b_mode
- /* get a valid TOC pointer, wherever we're mapped at */
- bl relative_toc
- tovirt(r2,r2)
-
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
/* Book3E initialization */
mr r3,r24
mr r4,r25
bl book3e_secondary_core_init
-
+ /* Now NIA and r2 are relocated to PAGE_OFFSET if not already */
/*
* After common core init has finished, check if the current thread is the
* one we wanted to boot. If not, start the specified thread and stop the
@@ -378,8 +374,7 @@ _GLOBAL(generic_secondary_smp_init)
beq 20f
/* start the specified thread */
- LOAD_REG_ADDR(r5, fsl_secondary_thread_init)
- ld r4, 0(r5)
+ LOAD_REG_ADDR(r5, DOTSYM(fsl_secondary_thread_init))
bl book3e_start_thread
/* stop the current thread */
@@ -388,6 +383,16 @@ _GLOBAL(generic_secondary_smp_init)
10:
b 10b
20:
+#else
+ /* Now the MMU is off, can branch to our PAGE_OFFSET address */
+ bcl 20,31,$+4
+1: mflr r11
+ addi r11,r11,(2f - 1b)
+ tovirt(r11, r11)
+ mtctr r11
+ bctr
+2:
+ bl relative_toc
#endif
generic_secondary_common_init:
@@ -400,8 +405,12 @@ generic_secondary_common_init:
#else
LOAD_REG_ADDR(r8, paca_ptrs) /* Load paca_ptrs pointe */
ld r8,0(r8) /* Get base vaddr of array */
+#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
+ LOAD_REG_IMMEDIATE(r7, NR_CPUS)
+#else
LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */
lwz r7,0(r7) /* also the max paca allocated */
+#endif
li r5,0 /* logical cpu id */
1:
sldi r9,r5,3 /* get paca_ptrs[] index from cpu id */
@@ -417,7 +426,7 @@ generic_secondary_common_init:
b kexec_wait /* next kernel might do better */
2: SET_PACA(r13)
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
addi r12,r13,PACA_EXTLB /* and TLB exc frame in another */
mtspr SPRN_SPRG_TLB_EXFRAME,r12
#endif
@@ -427,7 +436,7 @@ generic_secondary_common_init:
/* Create a temp kernel stack for use before relocation is on. */
ld r1,PACAEMERGSP(r13)
- subi r1,r1,STACK_FRAME_OVERHEAD
+ subi r1,r1,STACK_FRAME_MIN_SIZE
/* See if we need to call a cpu state restore handler */
LOAD_REG_ADDR(r23, cur_cpu_spec)
@@ -465,7 +474,7 @@ generic_secondary_common_init:
* Assumes we're mapped EA == RA if the MMU is on.
*/
#ifdef CONFIG_PPC_BOOK3S
-__mmu_off:
+SYM_FUNC_START_LOCAL(__mmu_off)
mfmsr r3
andi. r0,r3,MSR_IR|MSR_DR
beqlr
@@ -476,8 +485,34 @@ __mmu_off:
sync
rfid
b . /* prevent speculative execution */
-#endif
+SYM_FUNC_END(__mmu_off)
+SYM_FUNC_START_LOCAL(start_initialization_book3s)
+ mflr r25
+
+ /* Setup some critical 970 SPRs before switching MMU off */
+ mfspr r0,SPRN_PVR
+ srwi r0,r0,16
+ cmpwi r0,0x39 /* 970 */
+ beq 1f
+ cmpwi r0,0x3c /* 970FX */
+ beq 1f
+ cmpwi r0,0x44 /* 970MP */
+ beq 1f
+ cmpwi r0,0x45 /* 970GX */
+ bne 2f
+1: bl __cpu_preinit_ppc970
+2:
+
+ /* Switch off MMU if not already off */
+ bl __mmu_off
+
+ /* Now the MMU is off, can return to our PAGE_OFFSET address */
+ tovirt(r25,r25)
+ mtlr r25
+ blr
+SYM_FUNC_END(start_initialization_book3s)
+#endif
/*
* Here is our main kernel entry point. We support currently 2 kind of entries
@@ -494,14 +529,11 @@ __start_initialization_multiplatform:
/* Make sure we are running in 64 bits mode */
bl enable_64b_mode
- /* Get TOC pointer (current runtime address) */
- bl relative_toc
+ /* Zero r13 (paca) so early program check / mce don't use it */
+ li r13,0
- /* find out where we are now */
- bcl 20,31,$+4
-0: mflr r26 /* r26 = runtime addr here */
- addis r26,r26,(_stext - 0b)@ha
- addi r26,r26,(_stext - 0b)@l /* current runtime base addr */
+ /* Poison TOC */
+ li r2,-1
/*
* Are we booted from a PROM Of-type client-interface ?
@@ -519,32 +551,41 @@ __start_initialization_multiplatform:
mr r29,r9
#endif
-#ifdef CONFIG_PPC_BOOK3E
+ /* Get TOC pointer (current runtime address) */
+ bl relative_toc
+
+ /* These functions return to the virtual (PAGE_OFFSET) address */
+#ifdef CONFIG_PPC_BOOK3E_64
bl start_initialization_book3e
- b __after_prom_start
#else
- /* Setup some critical 970 SPRs before switching MMU off */
- mfspr r0,SPRN_PVR
- srwi r0,r0,16
- cmpwi r0,0x39 /* 970 */
- beq 1f
- cmpwi r0,0x3c /* 970FX */
- beq 1f
- cmpwi r0,0x44 /* 970MP */
- beq 1f
- cmpwi r0,0x45 /* 970GX */
- bne 2f
-1: bl __cpu_preinit_ppc970
-2:
+ bl start_initialization_book3s
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+ /* Get TOC pointer, virtual */
+ bl relative_toc
+
+ /* find out where we are now */
+
+ /* OPAL doesn't pass base address in r4, have to derive it. */
+ bcl 20,31,$+4
+0: mflr r26 /* r26 = runtime addr here */
+ addis r26,r26,(_stext - 0b)@ha
+ addi r26,r26,(_stext - 0b)@l /* current runtime base addr */
- /* Switch off MMU if not already off */
- bl __mmu_off
b __after_prom_start
-#endif /* CONFIG_PPC_BOOK3E */
__REF
__boot_from_prom:
#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
+ /* Get TOC pointer, non-virtual */
+ bl relative_toc
+
+ /* find out where we are now */
+ bcl 20,31,$+4
+0: mflr r26 /* r26 = runtime addr here */
+ addis r26,r26,(_stext - 0b)@ha
+ addi r26,r26,(_stext - 0b)@l /* current runtime base addr */
+
/* Save parameters */
mr r31,r3
mr r30,r4
@@ -574,7 +615,7 @@ __boot_from_prom:
/* Do all of the interaction with OF client interface */
mr r8,r26
- bl prom_init
+ bl CFUNC(prom_init)
#endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */
/* We never return. We also hit that trap if trying to boot
@@ -585,21 +626,14 @@ __boot_from_prom:
__after_prom_start:
#ifdef CONFIG_RELOCATABLE
/* process relocations for the final address of the kernel */
- lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */
- sldi r25,r25,32
-#if defined(CONFIG_PPC_BOOK3E)
- tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */
-#endif
lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26)
-#if defined(CONFIG_PPC_BOOK3E)
- tophys(r26,r26)
-#endif
cmplwi cr0,r7,1 /* flagged to stay where we are ? */
- bne 1f
- add r25,r25,r26
+ mr r25,r26 /* then use current kernel base */
+ beq 1f
+ LOAD_REG_IMMEDIATE(r25, PAGE_OFFSET) /* else use static kernel base */
1: mr r3,r25
bl relocate
-#if defined(CONFIG_PPC_BOOK3E)
+#if defined(CONFIG_PPC_BOOK3E_64)
/* IVPR needs to be set after relocation. */
bl init_core_book3e
#endif
@@ -612,15 +646,10 @@ __after_prom_start:
*
* Note: This process overwrites the OF exception vectors.
*/
- li r3,0 /* target addr */
-#ifdef CONFIG_PPC_BOOK3E
- tovirt(r3,r3) /* on booke, we already run at PAGE_OFFSET */
-#endif
- mr. r4,r26 /* In some cases the loader may */
-#if defined(CONFIG_PPC_BOOK3E)
- tovirt(r4,r4)
-#endif
- beq 9f /* have already put us at zero */
+ LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET)
+ mr r4,r26 /* Load the virtual source address into r4 */
+ cmpld r3,r4 /* Check if source == dest */
+ beq 9f /* If so skip the copy */
li r6,0x100 /* Start offset, the first 0x100 */
/* bytes were copied earlier. */
@@ -630,14 +659,11 @@ __after_prom_start:
* variable __run_at_load, if it is set the kernel is treated as relocatable
* kernel, otherwise it will be moved to PHYSICAL_START
*/
-#if defined(CONFIG_PPC_BOOK3E)
- tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */
-#endif
lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26)
cmplwi cr0,r7,1
bne 3f
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
LOAD_REG_ADDR(r5, __end_interrupts)
LOAD_REG_ADDR(r11, _stext)
sub r5,r5,r11
@@ -751,9 +777,15 @@ _GLOBAL(pmac_secondary_start)
sync
slbia
- /* get TOC pointer (real address) */
+ /* Branch to our PAGE_OFFSET address */
+ bcl 20,31,$+4
+1: mflr r11
+ addi r11,r11,(2f - 1b)
+ tovirt(r11, r11)
+ mtctr r11
+ bctr
+2:
bl relative_toc
- tovirt(r2,r2)
/* Copy some CPU settings from CPU 0 */
bl __restore_cpu_ppc970
@@ -780,7 +812,7 @@ _GLOBAL(pmac_secondary_start)
/* Create a temp kernel stack for use before relocation is on. */
ld r1,PACAEMERGSP(r13)
- subi r1,r1,STACK_FRAME_OVERHEAD
+ subi r1,r1,STACK_FRAME_MIN_SIZE
b __secondary_start
@@ -812,7 +844,7 @@ __secondary_start:
* can turn it on below. This is a call to C, which is OK, we're still
* running on the emergency stack.
*/
- bl early_setup_secondary
+ bl CFUNC(early_setup_secondary)
/*
* The primary has initialized our kernel stack for us in the paca, grab
@@ -848,10 +880,10 @@ __secondary_start:
* before going into C code.
*/
start_secondary_prolog:
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
li r3,0
std r3,0(r1) /* Zero the stack frame pointer */
- bl start_secondary
+ bl CFUNC(start_secondary)
b .
/*
* Reset stack pointer and call start_secondary
@@ -862,25 +894,26 @@ _GLOBAL(start_secondary_resume)
ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */
li r3,0
std r3,0(r1) /* Zero the stack frame pointer */
- bl start_secondary
+ bl CFUNC(start_secondary)
b .
#endif
/*
* This subroutine clobbers r11 and r12
*/
-enable_64b_mode:
+SYM_FUNC_START_LOCAL(enable_64b_mode)
mfmsr r11 /* grab the current MSR */
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */
mtmsr r11
-#else /* CONFIG_PPC_BOOK3E */
+#else /* CONFIG_PPC_BOOK3E_64 */
LOAD_REG_IMMEDIATE(r12, MSR_64BIT)
or r11,r11,r12
mtmsrd r11
isync
#endif
blr
+SYM_FUNC_END(enable_64b_mode)
/*
* This puts the TOC pointer into r2, offset by 0x8000 (as expected
@@ -891,10 +924,15 @@ enable_64b_mode:
* TOC in -mcmodel=medium mode. After we relocate to 0 but before
* the MMU is on we need our TOC to be a virtual address otherwise
* these pointers will be real addresses which may get stored and
- * accessed later with the MMU on. We use tovirt() at the call
- * sites to handle this.
+ * accessed later with the MMU on. We branch to the virtual address
+ * while still in real mode then call relative_toc again to handle
+ * this.
*/
_GLOBAL(relative_toc)
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ tdnei r2,-1
+ blr
+#else
mflr r0
bcl 20,31,$+4
0: mflr r11
@@ -905,15 +943,15 @@ _GLOBAL(relative_toc)
.balign 8
p_toc: .8byte .TOC. - 0b
+#endif
/*
* This is where the main kernel code starts.
*/
__REF
start_here_multiplatform:
- /* set up the TOC */
- bl relative_toc
- tovirt(r2,r2)
+ /* Adjust TOC for moved kernel. Could adjust when moving it instead. */
+ bl relative_toc
/* Clear out the BSS. It may have been done in prom_init,
* already but that's irrelevant since prom_init will soon
@@ -940,7 +978,7 @@ start_here_multiplatform:
std r29,8(r11);
#endif
-#ifndef CONFIG_PPC_BOOK3E
+#ifndef CONFIG_PPC_BOOK3E_64
mfmsr r6
ori r6,r6,MSR_RI
mtmsrd r6 /* RI on */
@@ -958,13 +996,16 @@ start_here_multiplatform:
LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
add r1,r3,r1
li r0,0
- stdu r0,-STACK_FRAME_OVERHEAD(r1)
+ stdu r0,-STACK_FRAME_MIN_SIZE(r1)
/*
* Do very early kernel initializations, including initial hash table
* and SLB setup before we turn on relocation.
*/
+#ifdef CONFIG_KASAN
+ bl CFUNC(kasan_early_init)
+#endif
/* Restore parameters passed from prom_init/kexec */
mr r3,r31
LOAD_REG_ADDR(r12, DOTSYM(early_setup))
@@ -985,7 +1026,7 @@ start_here_common:
std r1,PACAKSAVE(r13)
/* Load the TOC (virtual address) */
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
/* Mark interrupts soft and hard disabled (they might be enabled
* in the PACA when doing hotplug)
@@ -996,7 +1037,7 @@ start_here_common:
stb r0,PACAIRQHAPPENED(r13)
/* Generic kernel entry */
- bl start_kernel
+ bl CFUNC(start_kernel)
/* Not reached */
0: trap
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_85xx.S
index f0db4f52bc00..f9a73fae6464 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_85xx.S
@@ -29,6 +29,8 @@
#include <linux/init.h>
#include <linux/threads.h>
#include <linux/pgtable.h>
+#include <linux/linkage.h>
+
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
@@ -38,7 +40,6 @@
#include <asm/asm-offsets.h>
#include <asm/cache.h>
#include <asm/ptrace.h>
-#include <asm/export.h>
#include <asm/feature-fixups.h>
#include "head_booke.h"
@@ -129,7 +130,7 @@ _GLOBAL(_start);
/*
* For the second relocation, we already set the right tlb entries
- * for the kernel space, so skip the code in fsl_booke_entry_mapping.S
+ * for the kernel space, so skip the code in 85xx_entry_mapping.S
*/
cmpwi r19,1
beq set_ivor
@@ -159,7 +160,7 @@ _GLOBAL(__early_start)
lwz r20,0(r20)
#define ENTRY_MAPPING_BOOT_SETUP
-#include "fsl_booke_entry_mapping.S"
+#include "85xx_entry_mapping.S"
#undef ENTRY_MAPPING_BOOT_SETUP
set_ivor:
@@ -229,7 +230,7 @@ set_ivor:
lis r1,init_thread_union@h
ori r1,r1,init_thread_union@l
li r0,0
- stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
#ifdef CONFIG_SMP
stw r24, TASK_CPU(r2)
@@ -293,9 +294,10 @@ set_ivor:
/* Macros to hide the PTE size differences
*
* FIND_PTE -- walks the page tables given EA & pgdir pointer
- * r10 -- EA of fault
+ * r10 -- free
* r11 -- PGDIR pointer
* r12 -- free
+ * r13 -- EA of fault
* label 2: is the bailout case
*
* if we find the pte (fall through):
@@ -306,34 +308,34 @@ set_ivor:
#ifdef CONFIG_PTE_64BIT
#ifdef CONFIG_HUGETLB_PAGE
#define FIND_PTE \
- rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \
- lwzx r11, r12, r11; /* Get pgd/pmd entry */ \
+ rlwinm r12, r13, 14, 18, 28; /* Compute pgdir/pmd offset */ \
+ add r12, r11, r12; \
+ lwz r11, 4(r12); /* Get pgd/pmd entry */ \
+ rlwinm. r10, r11, 32 - _PAGE_PSIZE_SHIFT, 0x1e; /* get tsize*/ \
+ bne 1000f; /* Huge page (leaf entry) */ \
rlwinm. r12, r11, 0, 0, 20; /* Extract pt base address */ \
- blt 1000f; /* Normal non-huge page */ \
beq 2f; /* Bail if no table */ \
- oris r11, r11, PD_HUGE@h; /* Put back address bit */ \
- andi. r10, r11, HUGEPD_SHIFT_MASK@l; /* extract size field */ \
- xor r12, r10, r11; /* drop size bits from pointer */ \
- b 1001f; \
-1000: rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \
+ rlwimi r12, r13, 23, 20, 28; /* Compute pte address */ \
li r10, 0; /* clear r10 */ \
-1001: lwz r11, 4(r12); /* Get pte entry */
+ lwz r11, 4(r12); /* Get pte entry */ \
+1000:
#else
#define FIND_PTE \
- rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \
- lwzx r11, r12, r11; /* Get pgd/pmd entry */ \
+ rlwinm r12, r13, 14, 18, 28; /* Compute pgdir/pmd offset */ \
+ add r12, r11, r12; \
+ lwz r11, 4(r12); /* Get pgd/pmd entry */ \
rlwinm. r12, r11, 0, 0, 20; /* Extract pt base address */ \
beq 2f; /* Bail if no table */ \
- rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \
+ rlwimi r12, r13, 23, 20, 28; /* Compute pte address */ \
lwz r11, 4(r12); /* Get pte entry */
#endif /* HUGEPAGE */
#else /* !PTE_64BIT */
#define FIND_PTE \
- rlwimi r11, r10, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \
+ rlwimi r11, r13, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \
lwz r11, 0(r11); /* Get L1 entry */ \
rlwinm. r12, r11, 0, 0, 19; /* Extract L2 (pte) base address */ \
beq 2f; /* Bail if no table */ \
- rlwimi r12, r10, 22, 20, 29; /* Compute PTE address */ \
+ rlwimi r12, r13, 22, 20, 29; /* Compute PTE address */ \
lwz r11, 0(r12); /* Get Linux PTE */
#endif
@@ -394,7 +396,7 @@ interrupt_base:
#ifdef CONFIG_PPC_FPU
FP_UNAVAILABLE_EXCEPTION
#else
- EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, unknown_exception)
+ EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, emulation_assist_interrupt)
#endif
/* System Call Interrupt */
@@ -440,13 +442,13 @@ START_BTB_FLUSH_SECTION
BTB_FLUSH(r10)
1:
END_BTB_FLUSH_SECTION
- mfspr r10, SPRN_DEAR /* Get faulting address */
+ mfspr r13, SPRN_DEAR /* Get faulting address */
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
lis r11, PAGE_OFFSET@h
- cmplw 5, r10, r11
+ cmplw 5, r13, r11
blt 5, 3f
lis r11, swapper_pg_dir@h
ori r11, r11, swapper_pg_dir@l
@@ -469,29 +471,14 @@ END_BTB_FLUSH_SECTION
#endif
4:
- /* Mask of required permission bits. Note that while we
- * do copy ESR:ST to _PAGE_RW position as trying to write
- * to an RO page is pretty common, we don't do it with
- * _PAGE_DIRTY. We could do it, but it's a fairly rare
- * event so I'd rather take the overhead when it happens
- * rather than adding an instruction here. We should measure
- * whether the whole thing is worth it in the first place
- * as we could avoid loading SPRN_ESR completely in the first
- * place...
- *
- * TODO: Is it worth doing that mfspr & rlwimi in the first
- * place or can we save a couple of instructions here ?
- */
- mfspr r12,SPRN_ESR
+ FIND_PTE
+
#ifdef CONFIG_PTE_64BIT
- li r13,_PAGE_PRESENT
+ li r13,_PAGE_PRESENT|_PAGE_BAP_SR
oris r13,r13,_PAGE_ACCESSED@h
#else
- li r13,_PAGE_PRESENT|_PAGE_ACCESSED
+ li r13,_PAGE_PRESENT|_PAGE_READ|_PAGE_ACCESSED
#endif
- rlwimi r13,r12,11,29,29
-
- FIND_PTE
andc. r13,r13,r11 /* Check permission */
#ifdef CONFIG_PTE_64BIT
@@ -548,13 +535,13 @@ START_BTB_FLUSH_SECTION
1:
END_BTB_FLUSH_SECTION
- mfspr r10, SPRN_SRR0 /* Get faulting address */
+ mfspr r13, SPRN_SRR0 /* Get faulting address */
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
lis r11, PAGE_OFFSET@h
- cmplw 5, r10, r11
+ cmplw 5, r13, r11
blt 5, 3f
lis r11, swapper_pg_dir@h
ori r11, r11, swapper_pg_dir@l
@@ -563,6 +550,7 @@ END_BTB_FLUSH_SECTION
rlwinm r12,r12,0,16,1
mtspr SPRN_MAS1,r12
+ FIND_PTE
/* Make up the required permissions for kernel code */
#ifdef CONFIG_PTE_64BIT
li r13,_PAGE_PRESENT | _PAGE_BAP_SX
@@ -583,6 +571,7 @@ END_BTB_FLUSH_SECTION
beq 2f /* KUAP fault */
#endif
+ FIND_PTE
/* Make up the required permissions for user code */
#ifdef CONFIG_PTE_64BIT
li r13,_PAGE_PRESENT | _PAGE_BAP_UX
@@ -592,7 +581,6 @@ END_BTB_FLUSH_SECTION
#endif
4:
- FIND_PTE
andc. r13,r13,r11 /* Check permission */
#ifdef CONFIG_PTE_64BIT
@@ -745,17 +733,12 @@ finish_tlb_load:
lwz r15, 0(r14)
100: stw r15, 0(r17)
- /*
- * Calc MAS1_TSIZE from r10 (which has pshift encoded)
- * tlb_enc = (pshift - 10).
- */
- subi r15, r10, 10
mfspr r16, SPRN_MAS1
- rlwimi r16, r15, 7, 20, 24
+ rlwimi r16, r10, MAS1_TSIZE_SHIFT, MAS1_TSIZE_MASK
mtspr SPRN_MAS1, r16
/* copy the pshift for use later */
- mr r14, r10
+ addi r14, r10, _PAGE_PSIZE_SHIFT_OFFSET
/* fall through */
@@ -782,15 +765,15 @@ BEGIN_MMU_FTR_SECTION
mtspr SPRN_MAS7, r10
END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
#else
- li r10, (_PAGE_EXEC | _PAGE_PRESENT)
+ li r10, (_PAGE_EXEC | _PAGE_READ)
mr r13, r11
rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */
and r12, r11, r10
- andi. r10, r11, _PAGE_USER /* Test for _PAGE_USER */
+ mcrf cr0, cr5 /* Test for user page */
slwi r10, r12, 1
or r10, r10, r12
rlwinm r10, r10, 0, ~_PAGE_EXEC /* Clear SX on user pages */
- iseleq r12, r12, r10
+ isellt r12, r10, r12
rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */
mtspr SPRN_MAS3, r13
#endif
@@ -862,7 +845,7 @@ _GLOBAL(load_up_spe)
* SPE unavailable trap from kernel - print a message, but let
* the task use SPE in the kernel until it returns to user mode.
*/
-KernelSPE:
+SYM_FUNC_START_LOCAL(KernelSPE)
lwz r3,_MSR(r1)
oris r3,r3,MSR_SPE@h
stw r3,_MSR(r1) /* enable use of SPE after return */
@@ -879,13 +862,14 @@ KernelSPE:
#endif
.align 4,0
+SYM_FUNC_END(KernelSPE)
#endif /* CONFIG_SPE */
/*
* Translate the effec addr in r3 to phys addr. The phys addr will be put
* into r3(higher 32bit) and r4(lower 32bit)
*/
-get_phys_addr:
+SYM_FUNC_START_LOCAL(get_phys_addr)
mfmsr r8
mfspr r9,SPRN_PID
rlwinm r9,r9,16,0x3fff0000 /* turn PID into MAS6[SPID] */
@@ -907,12 +891,13 @@ get_phys_addr:
mfspr r3,SPRN_MAS7
#endif
blr
+SYM_FUNC_END(get_phys_addr)
/*
* Global functions
*/
-#ifdef CONFIG_E500
+#ifdef CONFIG_PPC_E500
#ifndef CONFIG_PPC_E500MC
/* Adjust or setup IVORs for e500v1/v2 */
_GLOBAL(__setup_e500_ivors)
@@ -955,7 +940,7 @@ _GLOBAL(__setup_ehv_ivors)
sync
blr
#endif /* CONFIG_PPC_E500MC */
-#endif /* CONFIG_E500 */
+#endif /* CONFIG_PPC_E500 */
#ifdef CONFIG_SPE
/*
@@ -972,10 +957,10 @@ _GLOBAL(__giveup_spe)
li r4,THREAD_ACC
evstddx evr6, r4, r3 /* save off accumulator */
beq 1f
- lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ lwz r4,_MSR-STACK_INT_FRAME_REGS(r5)
lis r3,MSR_SPE@h
andc r4,r4,r3 /* disable SPE for previous task */
- stw r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ stw r4,_MSR-STACK_INT_FRAME_REGS(r5)
1:
blr
#endif /* CONFIG_SPE */
@@ -1044,7 +1029,7 @@ __secondary_start:
lwz r1,TASK_STACK(r2)
/* stack */
- addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE
li r0,0
stw r0,0(r1)
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 0b05f2be66b9..56c5ebe21b99 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -18,6 +18,8 @@
#include <linux/magic.h>
#include <linux/pgtable.h>
#include <linux/sizes.h>
+#include <linux/linkage.h>
+
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
@@ -27,7 +29,6 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
-#include <asm/export.h>
#include <asm/code-patching-asm.h>
#include <asm/interrupt.h>
@@ -39,16 +40,6 @@
#include "head_32.h"
-.macro compare_to_kernel_boundary scratch, addr
-#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
-/* By simply checking Address >= 0x80000000, we know if its a kernel address */
- not. \scratch, \addr
-#else
- rlwinm \scratch, \addr, 16, 0xfff8
- cmpli cr0, \scratch, PAGE_OFFSET@h
-#endif
-.endm
-
#define PAGE_SHIFT_512K 19
#define PAGE_SHIFT_8M 23
@@ -198,18 +189,7 @@ instruction_counter:
mfspr r10, SPRN_SRR0 /* Get effective address of fault */
INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11)
mtspr SPRN_MD_EPN, r10
-#ifdef CONFIG_MODULES
- mfcr r11
- compare_to_kernel_boundary r10, r10
-#endif
mfspr r10, SPRN_M_TWB /* Get level 1 table */
-#ifdef CONFIG_MODULES
- blt+ 3f
- rlwinm r10, r10, 0, 20, 31
- oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
-3:
- mtcr r11
-#endif
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
mtspr SPRN_MD_TWC, r11
mfspr r10, SPRN_MD_TWC
@@ -247,19 +227,12 @@ instruction_counter:
START_EXCEPTION(INTERRUPT_DATA_TLB_MISS_8xx, DataStoreTLBMiss)
mtspr SPRN_SPRG_SCRATCH2, r10
mtspr SPRN_M_TW, r11
- mfcr r11
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
mfspr r10, SPRN_MD_EPN
- compare_to_kernel_boundary r10, r10
mfspr r10, SPRN_M_TWB /* Get level 1 table */
- blt+ 3f
- rlwinm r10, r10, 0, 20, 31
- oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
-3:
- mtcr r11
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
mtspr SPRN_MD_TWC, r11
@@ -331,15 +304,19 @@ instruction_counter:
cmpwi cr1, r11, RPN_PATTERN
beq- cr1, FixupDAR /* must be a buggy dcbX, icbi insn. */
DARFixed:/* Return from dcbx instruction bug workaround */
+ mfspr r11, SPRN_DSISR
+ rlwinm r11, r11, 0, DSISR_NOHPTE
+ cmpwi cr1, r11, 0
+ beq+ cr1, .Ldtlbie
+ mfspr r11, SPRN_DAR
+ tlbie r11
+ rlwinm r11, r11, 16, 0xffff
+ cmplwi cr1, r11, TASK_SIZE@h
+ bge- cr1, FixupPGD
+.Ldtlbie:
EXCEPTION_PROLOG_1
/* 0x300 is DataAccess exception, needed by bad_page_fault() */
EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataTLBError handle_dar_dsisr=1
- lwz r4, _DAR(r11)
- lwz r5, _DSISR(r11)
- andis. r10,r5,DSISR_NOHPTE@h
- beq+ .Ldtlbie
- tlbie r4
-.Ldtlbie:
prepare_transfer_to_handler
bl do_page_fault
b interrupt_return
@@ -393,6 +370,30 @@ DARFixed:/* Return from dcbx instruction bug workaround */
__HEAD
. = 0x2000
+FixupPGD:
+ mtspr SPRN_M_TW, r10
+ mfspr r10, SPRN_DAR
+ mtspr SPRN_MD_EPN, r10
+ mfspr r11, SPRN_M_TWB /* Get level 1 table */
+ lwz r10, (swapper_pg_dir - PAGE_OFFSET)@l(r11) /* Get the level 1 entry */
+ cmpwi cr1, r10, 0
+ bne cr1, 1f
+
+ rlwinm r10, r11, 0, 20, 31
+ oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
+ lwz r10, (swapper_pg_dir - PAGE_OFFSET)@l(r10) /* Get the level 1 entry */
+ cmpwi cr1, r10, 0
+ beq cr1, 1f
+ stw r10, (swapper_pg_dir - PAGE_OFFSET)@l(r11) /* Set the level 1 entry */
+ mfspr r10, SPRN_M_TW
+ mtcr r10
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ rfi
+1:
+ mfspr r10, SPRN_M_TW
+ b .Ldtlbie
+
/* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
* by decoding the registers used by the dcbx instruction and adding them.
* DAR is set to the calculated address.
@@ -403,7 +404,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
mfspr r10, SPRN_SRR0
mtspr SPRN_MD_EPN, r10
rlwinm r11, r10, 16, 0xfff8
- cmpli cr1, r11, PAGE_OFFSET@h
+ cmpli cr1, r11, TASK_SIZE@h
mfspr r11, SPRN_M_TWB /* Get level 1 table */
blt+ cr1, 3f
@@ -414,14 +415,13 @@ FixupDAR:/* Entry point for dcbx workaround. */
oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha
3:
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */
+ rlwinm r11, r11, 0, ~_PMD_PAGE_8M
mtspr SPRN_MD_TWC, r11
- mtcrf 0x01, r11
mfspr r11, SPRN_MD_TWC
lwz r11, 0(r11) /* Get the pte */
- bt 28,200f /* bit 28 = Large page (8M) */
/* concat physical page address(r11) and page offset(r10) */
rlwimi r11, r10, 0, 32 - PAGE_SHIFT, 31
-201: lwz r11,0(r11)
+ lwz r11,0(r11)
/* Check if it really is a dcbx instruction. */
/* dcbt and dcbtst does not generate DTLB Misses/Errors,
* no need to include them here */
@@ -440,11 +440,6 @@ FixupDAR:/* Entry point for dcbx workaround. */
141: mfspr r10,SPRN_M_TW
b DARFixed /* Nope, go back to normal TLB processing */
-200:
- /* concat physical page address(r11) and page offset(r10) */
- rlwimi r11, r10, 0, 32 - PAGE_SHIFT_8M, 31
- b 201b
-
144: mfspr r10, SPRN_DSISR
rlwinm r10, r10,0,7,5 /* Clear store bit for buggy dcbst insn */
mtspr SPRN_DSISR, r10
@@ -499,6 +494,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
bctr /* jump into table */
152:
mfdar r11
+ mtdar r10
mtctr r11 /* restore ctr reg from DAR */
mfspr r11, SPRN_SPRG_THREAD
stw r10, DAR(r11)
@@ -537,7 +533,7 @@ start_here:
ori r0, r0, STACK_END_MAGIC@l
stw r0, 0(r1)
li r0,0
- stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
lis r6, swapper_pg_dir@ha
tophys(r6,r6)
@@ -592,6 +588,10 @@ start_here:
lis r0, (MD_TWAM | MD_RSV4I)@h
mtspr SPRN_MD_CTR, r0
#endif
+#ifndef CONFIG_PIN_TLB_TEXT
+ li r0, 0
+ mtspr SPRN_MI_CTR, r0
+#endif
#if !defined(CONFIG_PIN_TLB_DATA) && !defined(CONFIG_PIN_TLB_IMMR)
lis r0, MD_TWAM@h
mtspr SPRN_MD_CTR, r0
@@ -625,7 +625,7 @@ start_here:
* 24 Mbytes of data, and the 512k IMMR space. Anything not covered by
* these mappings is mapped by page tables.
*/
-initial_mmu:
+SYM_FUNC_START_LOCAL(initial_mmu)
li r8, 0
mtspr SPRN_MI_CTR, r8 /* remove PINNED ITLB entries */
lis r10, MD_TWAM@h
@@ -686,7 +686,9 @@ initial_mmu:
#endif
mtspr SPRN_DER, r8
blr
+SYM_FUNC_END(initial_mmu)
+#ifdef CONFIG_PIN_TLB
_GLOBAL(mmu_pin_tlb)
lis r9, (1f - PAGE_OFFSET)@h
ori r9, r9, (1f - PAGE_OFFSET)@l
@@ -708,6 +710,7 @@ _GLOBAL(mmu_pin_tlb)
mtspr SPRN_MD_CTR, r6
tlbia
+#ifdef CONFIG_PIN_TLB_TEXT
LOAD_REG_IMMEDIATE(r5, 28 << 8)
LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
@@ -728,6 +731,7 @@ _GLOBAL(mmu_pin_tlb)
bdnzt lt, 2b
lis r0, MI_RSV4I@h
mtspr SPRN_MI_CTR, r0
+#endif
LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
#ifdef CONFIG_PIN_TLB_DATA
@@ -787,3 +791,4 @@ _GLOBAL(mmu_pin_tlb)
mtspr SPRN_SRR1, r10
mtspr SPRN_SRR0, r11
rfi
+#endif
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 6c739beb938c..cb2bca76be53 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -18,6 +18,8 @@
#include <linux/init.h>
#include <linux/pgtable.h>
+#include <linux/linkage.h>
+
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
@@ -29,7 +31,6 @@
#include <asm/ptrace.h>
#include <asm/bug.h>
#include <asm/kvm_book3s_asm.h>
-#include <asm/export.h>
#include <asm/feature-fixups.h>
#include <asm/interrupt.h>
@@ -410,44 +411,34 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE)
*/
. = INTERRUPT_INST_TLB_MISS_603
InstructionTLBMiss:
-/*
- * r0: scratch
- * r1: linux style pte ( later becomes ppc hardware pte )
- * r2: ptr to linux-style pte
- * r3: scratch
- */
/* Get PTE (linux-style) and check access */
- mfspr r3,SPRN_IMISS
-#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
- lis r1, TASK_SIZE@h /* check if kernel address */
- cmplw 0,r1,r3
-#endif
+ mfspr r0,SPRN_IMISS
mfspr r2, SPRN_SDR1
- li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
- rlwinm r2, r2, 28, 0xfffff000
-#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
- bgt- 112f
- lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
- addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
-#endif
-112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
+ rlwinm r2, r2, 28, 0xfffff000
+ rlwimi r2,r0,12,20,29 /* insert top 10 bits of address */
lwz r2,0(r2) /* get pmd entry */
+#ifdef CONFIG_EXECMEM
+ rlwinm r3, r0, 4, 0xf
+ subi r3, r3, (TASK_SIZE >> 28) & 0xf
+#endif
rlwinm. r2,r2,0,0,19 /* extract address of pte page */
beq- InstructionAddressInvalid /* return if no mapping */
- rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
- lwz r0,0(r2) /* get linux-style pte */
- andc. r1,r1,r0 /* check access & ~permission */
+ rlwimi r2,r0,22,20,29 /* insert next 10 bits of address */
+ lwz r2,0(r2) /* get linux-style pte */
+ andc. r1,r1,r2 /* check access & ~permission */
bne- InstructionAddressInvalid /* return if access not permitted */
/* Convert linux-style PTE to low word of PPC-style PTE */
- rlwimi r0,r0,32-2,31,31 /* _PAGE_USER -> PP lsb */
+#ifdef CONFIG_EXECMEM
+ rlwimi r2, r3, 1, 31, 31 /* userspace ? -> PP lsb */
+#endif
ori r1, r1, 0xe06 /* clear out reserved bits */
- andc r1, r0, r1 /* PP = user? 1 : 0 */
+ andc r1, r2, r1 /* PP = user? 1 : 0 */
BEGIN_FTR_SECTION
rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
mtspr SPRN_RPA,r1
- tlbli r3
+ tlbli r0
mfspr r3,SPRN_SRR1 /* Need to restore CR0 */
mtcrf 0x80,r3
rfi
@@ -476,63 +467,62 @@ InstructionAddressInvalid:
*/
. = INTERRUPT_DATA_LOAD_TLB_MISS_603
DataLoadTLBMiss:
-/*
- * r0: scratch
- * r1: linux style pte ( later becomes ppc hardware pte )
- * r2: ptr to linux-style pte
- * r3: scratch
- */
/* Get PTE (linux-style) and check access */
- mfspr r3,SPRN_DMISS
- lis r1, TASK_SIZE@h /* check if kernel address */
- cmplw 0,r1,r3
+ mfspr r0,SPRN_DMISS
mfspr r2, SPRN_SDR1
- li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
- rlwinm r2, r2, 28, 0xfffff000
- bgt- 112f
- lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
- li r1, _PAGE_PRESENT | _PAGE_ACCESSED
- addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
-112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
- lwz r2,0(r2) /* get pmd entry */
+ rlwinm r1, r2, 28, 0xfffff000
+ rlwimi r1,r0,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r1) /* get pmd entry */
+ rlwinm r3, r0, 4, 0xf
rlwinm. r2,r2,0,0,19 /* extract address of pte page */
- beq- DataAddressInvalid /* return if no mapping */
- rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
- lwz r0,0(r2) /* get linux-style pte */
- andc. r1,r1,r0 /* check access & ~permission */
+ subi r3, r3, (TASK_SIZE >> 28) & 0xf
+ beq- 2f /* bail if no mapping */
+1: rlwimi r2,r0,22,20,29 /* insert next 10 bits of address */
+ lwz r2,0(r2) /* get linux-style pte */
+ li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_READ
+ andc. r1,r1,r2 /* check access & ~permission */
bne- DataAddressInvalid /* return if access not permitted */
/* Convert linux-style PTE to low word of PPC-style PTE */
- rlwinm r1,r0,32-9,30,30 /* _PAGE_RW -> PP msb */
- rlwimi r0,r0,32-1,30,30 /* _PAGE_USER -> PP msb */
- rlwimi r1,r0,32-3,24,24 /* _PAGE_RW -> _PAGE_DIRTY */
- rlwimi r0,r0,32-1,31,31 /* _PAGE_USER -> PP lsb */
+ rlwinm r1,r2,32-9,30,30 /* _PAGE_WRITE -> PP msb */
+ rlwimi r2,r3,2,30,31 /* userspace ? -> PP */
+ rlwimi r1,r2,32-3,24,24 /* _PAGE_WRITE -> _PAGE_DIRTY */
xori r1,r1,_PAGE_DIRTY /* clear dirty when not rw */
ori r1,r1,0xe04 /* clear out reserved bits */
- andc r1,r0,r1 /* PP = user? rw? 1: 3: 0 */
+ andc r1,r2,r1 /* PP = user? rw? 1: 3: 0 */
BEGIN_FTR_SECTION
rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
mtspr SPRN_RPA,r1
BEGIN_MMU_FTR_SECTION
- li r0,1
+ li r3,1
mfspr r1,SPRN_SPRG_603_LRU
- rlwinm r2,r3,20,27,31 /* Get Address bits 15:19 */
- slw r0,r0,r2
- xor r1,r0,r1
- srw r0,r1,r2
+ rlwinm r2,r0,20,27,31 /* Get Address bits 15:19 */
+ slw r3,r3,r2
+ xor r1,r3,r1
+ srw r3,r1,r2
mtspr SPRN_SPRG_603_LRU,r1
mfspr r2,SPRN_SRR1
- rlwimi r2,r0,31-14,14,14
+ rlwimi r2,r3,31-14,14,14
mtspr SPRN_SRR1,r2
mtcrf 0x80,r2
- tlbld r3
+ tlbld r0
rfi
MMU_FTR_SECTION_ELSE
mfspr r2,SPRN_SRR1 /* Need to restore CR0 */
mtcrf 0x80,r2
- tlbld r3
+ tlbld r0
rfi
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
+
+2: lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha
+ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
+ rlwimi r2,r0,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r2) /* get pmd entry */
+ cmpwi cr0,r2,0
+ beq- DataAddressInvalid /* return if no mapping */
+ stw r2,0(r1)
+ rlwinm. r2,r2,0,0,19 /* extract address of pte page */
+ b 1b
DataAddressInvalid:
mfspr r3,SPRN_SRR1
rlwinm r1,r3,9,6,6 /* Get load/store bit */
@@ -556,35 +546,26 @@ DataAddressInvalid:
*/
. = INTERRUPT_DATA_STORE_TLB_MISS_603
DataStoreTLBMiss:
-/*
- * r0: scratch
- * r1: linux style pte ( later becomes ppc hardware pte )
- * r2: ptr to linux-style pte
- * r3: scratch
- */
/* Get PTE (linux-style) and check access */
- mfspr r3,SPRN_DMISS
- lis r1, TASK_SIZE@h /* check if kernel address */
- cmplw 0,r1,r3
+ mfspr r0,SPRN_DMISS
mfspr r2, SPRN_SDR1
- li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
- rlwinm r2, r2, 28, 0xfffff000
- bgt- 112f
- lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
- li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
- addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
-112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
- lwz r2,0(r2) /* get pmd entry */
+ rlwinm r1, r2, 28, 0xfffff000
+ rlwimi r1,r0,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r1) /* get pmd entry */
+ rlwinm r3, r0, 4, 0xf
rlwinm. r2,r2,0,0,19 /* extract address of pte page */
- beq- DataAddressInvalid /* return if no mapping */
- rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
- lwz r0,0(r2) /* get linux-style pte */
- andc. r1,r1,r0 /* check access & ~permission */
+ subi r3, r3, (TASK_SIZE >> 28) & 0xf
+ beq- 2f /* bail if no mapping */
+1:
+ rlwimi r2,r0,22,20,29 /* insert next 10 bits of address */
+ lwz r2,0(r2) /* get linux-style pte */
+ li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
+ andc. r1,r1,r2 /* check access & ~permission */
bne- DataAddressInvalid /* return if access not permitted */
/* Convert linux-style PTE to low word of PPC-style PTE */
- rlwimi r0,r0,32-2,31,31 /* _PAGE_USER -> PP lsb */
+ rlwimi r2,r3,1,31,31 /* userspace ? -> PP lsb */
li r1,0xe06 /* clear out reserved bits & PP msb */
- andc r1,r0,r1 /* PP = user? 1: 0 */
+ andc r1,r2,r1 /* PP = user? 1: 0 */
BEGIN_FTR_SECTION
rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
@@ -592,26 +573,36 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
mfspr r2,SPRN_SRR1 /* Need to restore CR0 */
mtcrf 0x80,r2
BEGIN_MMU_FTR_SECTION
- li r0,1
+ li r3,1
mfspr r1,SPRN_SPRG_603_LRU
- rlwinm r2,r3,20,27,31 /* Get Address bits 15:19 */
- slw r0,r0,r2
- xor r1,r0,r1
- srw r0,r1,r2
+ rlwinm r2,r0,20,27,31 /* Get Address bits 15:19 */
+ slw r3,r3,r2
+ xor r1,r3,r1
+ srw r3,r1,r2
mtspr SPRN_SPRG_603_LRU,r1
mfspr r2,SPRN_SRR1
- rlwimi r2,r0,31-14,14,14
+ rlwimi r2,r3,31-14,14,14
mtspr SPRN_SRR1,r2
mtcrf 0x80,r2
- tlbld r3
+ tlbld r0
rfi
MMU_FTR_SECTION_ELSE
mfspr r2,SPRN_SRR1 /* Need to restore CR0 */
mtcrf 0x80,r2
- tlbld r3
+ tlbld r0
rfi
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
+2: lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha
+ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
+ rlwimi r2,r0,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r2) /* get pmd entry */
+ cmpwi cr0,r2,0
+ beq- DataAddressInvalid /* return if no mapping */
+ stw r2,0(r1)
+ rlwinm r2,r2,0,0,19 /* extract address of pte page */
+ b 1b
+
#ifndef CONFIG_ALTIVEC
#define altivec_assist_exception unknown_exception
#endif
@@ -688,7 +679,8 @@ hash_page_dsi:
mfdar r4
mfsrr0 r5
mfsrr1 r9
- rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */
+ rlwinm r3, r3, 32 - 15, _PAGE_WRITE /* DSISR_STORE -> _PAGE_WRITE */
+ ori r3, r3, _PAGE_PRESENT | _PAGE_READ
bl hash_page
mfspr r10, SPRN_SPRG_THREAD
restore_regs_thread r10
@@ -698,7 +690,7 @@ hash_page_isi:
mr r11, r10
mfspr r10, SPRN_SPRG_THREAD
save_regs_thread r10
- li r3, 0
+ li r3, _PAGE_PRESENT | _PAGE_EXEC
lwz r4, SRR0(r10)
lwz r9, SRR1(r10)
bl hash_page
@@ -840,7 +832,7 @@ __secondary_start:
lwz r1,TASK_STACK(r1)
/* stack */
- addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE
li r0,0
tophys(r3,r1)
stw r0,0(r3)
@@ -877,7 +869,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_HPTE_TABLE)
* Load stuff into the MMU. Intended to be called with
* IR=0 and DR=0.
*/
-early_hash_table:
+SYM_FUNC_START_LOCAL(early_hash_table)
sync /* Force all PTE updates to finish */
isync
tlbia /* Clear all TLB entries */
@@ -888,8 +880,9 @@ early_hash_table:
ori r6, r6, 3 /* 256kB table */
mtspr SPRN_SDR1, r6
blr
+SYM_FUNC_END(early_hash_table)
-load_up_mmu:
+SYM_FUNC_START_LOCAL(load_up_mmu)
sync /* Force all PTE updates to finish */
isync
tlbia /* Clear all TLB entries */
@@ -918,6 +911,7 @@ BEGIN_MMU_FTR_SECTION
LOAD_BAT(7,r3,r4,r5)
END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
blr
+SYM_FUNC_END(load_up_mmu)
_GLOBAL(load_segment_registers)
li r0, NUM_USER_SEGMENTS /* load up user segment register values */
@@ -966,7 +960,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_HPTE_TABLE)
lis r1,init_thread_union@ha
addi r1,r1,init_thread_union@l
li r0,0
- stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
/*
* Do early platform-specific initialization,
* and set up the MMU.
@@ -1028,7 +1022,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_HPTE_TABLE)
* this makes sure it's done.
* -- Cort
*/
-clear_bats:
+SYM_FUNC_START_LOCAL(clear_bats)
li r10,0
mtspr SPRN_DBAT0U,r10
@@ -1072,6 +1066,7 @@ BEGIN_MMU_FTR_SECTION
mtspr SPRN_IBAT7L,r10
END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
blr
+SYM_FUNC_END(clear_bats)
_GLOBAL(update_bats)
lis r4, 1f@h
@@ -1108,15 +1103,16 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
mtspr SPRN_SRR1, r6
rfi
-flush_tlbs:
+SYM_FUNC_START_LOCAL(flush_tlbs)
lis r10, 0x40
1: addic. r10, r10, -0x1000
tlbie r10
bgt 1b
sync
blr
+SYM_FUNC_END(flush_tlbs)
-mmu_off:
+SYM_FUNC_START_LOCAL(mmu_off)
addi r4, r3, __after_mmu_off - _start
mfmsr r3
andi. r0,r3,MSR_DR|MSR_IR /* MMU enabled? */
@@ -1128,9 +1124,10 @@ mmu_off:
mtspr SPRN_SRR1,r3
sync
rfi
+SYM_FUNC_END(mmu_off)
/* We use one BAT to map up to 256M of RAM at _PAGE_OFFSET */
-initial_bats:
+SYM_FUNC_START_LOCAL(initial_bats)
lis r11,PAGE_OFFSET@h
tophys(r8,r11)
#ifdef CONFIG_SMP
@@ -1146,9 +1143,10 @@ initial_bats:
mtspr SPRN_IBAT0U,r11
isync
blr
+SYM_FUNC_END(initial_bats)
#ifdef CONFIG_BOOTX_TEXT
-setup_disp_bat:
+SYM_FUNC_START_LOCAL(setup_disp_bat)
/*
* setup the display bat prepared for us in prom.c
*/
@@ -1164,10 +1162,11 @@ setup_disp_bat:
mtspr SPRN_DBAT3L,r8
mtspr SPRN_DBAT3U,r11
blr
+SYM_FUNC_END(setup_disp_bat)
#endif /* CONFIG_BOOTX_TEXT */
#ifdef CONFIG_PPC_EARLY_DEBUG_CPM
-setup_cpm_bat:
+SYM_FUNC_START_LOCAL(setup_cpm_bat)
lis r8, 0xf000
ori r8, r8, 0x002a
mtspr SPRN_DBAT1L, r8
@@ -1177,10 +1176,11 @@ setup_cpm_bat:
mtspr SPRN_DBAT1U, r11
blr
+SYM_FUNC_END(setup_cpm_bat)
#endif
#ifdef CONFIG_PPC_EARLY_DEBUG_USBGECKO
-setup_usbgecko_bat:
+SYM_FUNC_START_LOCAL(setup_usbgecko_bat)
/* prepare a BAT for early io */
#if defined(CONFIG_GAMECUBE)
lis r8, 0x0c00
@@ -1199,6 +1199,7 @@ setup_usbgecko_bat:
mtspr SPRN_DBAT1L, r8
mtspr SPRN_DBAT1U, r11
blr
+SYM_FUNC_END(setup_usbgecko_bat)
#endif
.data
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index bb6d5d0fc4ac..0b5c1993809e 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -5,6 +5,7 @@
#include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */
#include <asm/kvm_asm.h>
#include <asm/kvm_booke_hv_asm.h>
+#include <asm/thread_info.h> /* for THREAD_SHIFT */
#ifdef __ASSEMBLY__
@@ -34,7 +35,7 @@
*/
#define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4))
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
#define BOOKE_CLEAR_BTB(reg) \
START_BTB_FLUSH_SECTION \
BTB_FLUSH(reg) \
@@ -84,7 +85,7 @@ END_BTB_FLUSH_SECTION
stw r0,GPR0(r1)
lis r10, STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
addi r10, r10, STACK_FRAME_REGS_MARKER@l
- stw r10, 8(r1)
+ stw r10, STACK_INT_FRAME_MARKER(r1)
li r10, \trapno
stw r10,_TRAP(r1)
SAVE_GPRS(3, 8, r1)
@@ -99,11 +100,11 @@ END_BTB_FLUSH_SECTION
mfspr r10,SPRN_XER
addi r2, r2, -THREAD
stw r10,_XER(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
.endm
.macro prepare_transfer_to_handler
-#ifdef CONFIG_E500
+#ifdef CONFIG_PPC_E500
andi. r12,r9,MSR_PR
bne 777f
bl prepare_transfer_to_handler
@@ -144,10 +145,9 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
b transfer_to_syscall /* jump to handler */
.endm
-/* To handle the additional exception priority levels on 40x and Book-E
+/* To handle the additional exception priority levels on Book-E
* processors we allocate a stack per additional priority level.
*
- * On 40x critical is the only additional level
* On 44x/e500 we have critical and machine check
*
* Additionally we reserve a SPRG for each priority level so we can free up a
@@ -242,7 +242,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
.macro SAVE_MMU_REGS
-#ifdef CONFIG_PPC_BOOK3E_MMU
+#ifdef CONFIG_PPC_E500
mfspr r0,SPRN_MAS0
stw r0,MAS0(r1)
mfspr r0,SPRN_MAS1
@@ -257,7 +257,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
mfspr r0,SPRN_MAS7
stw r0,MAS7(r1)
#endif /* CONFIG_PHYS_64BIT */
-#endif /* CONFIG_PPC_BOOK3E_MMU */
+#endif /* CONFIG_PPC_E500 */
#ifdef CONFIG_44x
mfspr r0,SPRN_MMUCR
stw r0,MMUCR(r1)
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 2669f80b3a49..a1318ce18d0e 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -15,6 +15,7 @@
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/smp.h>
+#include <linux/spinlock.h>
#include <linux/debugfs.h>
#include <linux/init.h>
@@ -42,16 +43,6 @@ int hw_breakpoint_slots(int type)
return 0; /* no instruction breakpoints available */
}
-static bool single_step_pending(void)
-{
- int i;
-
- for (i = 0; i < nr_wp_slots(); i++) {
- if (current->thread.last_hit_ubp[i])
- return true;
- }
- return false;
-}
/*
* Install a perf counter breakpoint.
@@ -83,7 +74,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
* Do not install DABR values if the instruction must be single-stepped.
* If so, DABR will be populated in single_step_dabr_instruction().
*/
- if (!single_step_pending())
+ if (!info->perf_single_step)
__set_breakpoint(i, info);
return 0;
@@ -123,249 +114,6 @@ static bool is_ptrace_bp(struct perf_event *bp)
return bp->overflow_handler == ptrace_triggered;
}
-struct breakpoint {
- struct list_head list;
- struct perf_event *bp;
- bool ptrace_bp;
-};
-
-static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]);
-static LIST_HEAD(task_bps);
-
-static struct breakpoint *alloc_breakpoint(struct perf_event *bp)
-{
- struct breakpoint *tmp;
-
- tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
- if (!tmp)
- return ERR_PTR(-ENOMEM);
- tmp->bp = bp;
- tmp->ptrace_bp = is_ptrace_bp(bp);
- return tmp;
-}
-
-static bool bp_addr_range_overlap(struct perf_event *bp1, struct perf_event *bp2)
-{
- __u64 bp1_saddr, bp1_eaddr, bp2_saddr, bp2_eaddr;
-
- bp1_saddr = ALIGN_DOWN(bp1->attr.bp_addr, HW_BREAKPOINT_SIZE);
- bp1_eaddr = ALIGN(bp1->attr.bp_addr + bp1->attr.bp_len, HW_BREAKPOINT_SIZE);
- bp2_saddr = ALIGN_DOWN(bp2->attr.bp_addr, HW_BREAKPOINT_SIZE);
- bp2_eaddr = ALIGN(bp2->attr.bp_addr + bp2->attr.bp_len, HW_BREAKPOINT_SIZE);
-
- return (bp1_saddr < bp2_eaddr && bp1_eaddr > bp2_saddr);
-}
-
-static bool alternate_infra_bp(struct breakpoint *b, struct perf_event *bp)
-{
- return is_ptrace_bp(bp) ? !b->ptrace_bp : b->ptrace_bp;
-}
-
-static bool can_co_exist(struct breakpoint *b, struct perf_event *bp)
-{
- return !(alternate_infra_bp(b, bp) && bp_addr_range_overlap(b->bp, bp));
-}
-
-static int task_bps_add(struct perf_event *bp)
-{
- struct breakpoint *tmp;
-
- tmp = alloc_breakpoint(bp);
- if (IS_ERR(tmp))
- return PTR_ERR(tmp);
-
- list_add(&tmp->list, &task_bps);
- return 0;
-}
-
-static void task_bps_remove(struct perf_event *bp)
-{
- struct list_head *pos, *q;
-
- list_for_each_safe(pos, q, &task_bps) {
- struct breakpoint *tmp = list_entry(pos, struct breakpoint, list);
-
- if (tmp->bp == bp) {
- list_del(&tmp->list);
- kfree(tmp);
- break;
- }
- }
-}
-
-/*
- * If any task has breakpoint from alternate infrastructure,
- * return true. Otherwise return false.
- */
-static bool all_task_bps_check(struct perf_event *bp)
-{
- struct breakpoint *tmp;
-
- list_for_each_entry(tmp, &task_bps, list) {
- if (!can_co_exist(tmp, bp))
- return true;
- }
- return false;
-}
-
-/*
- * If same task has breakpoint from alternate infrastructure,
- * return true. Otherwise return false.
- */
-static bool same_task_bps_check(struct perf_event *bp)
-{
- struct breakpoint *tmp;
-
- list_for_each_entry(tmp, &task_bps, list) {
- if (tmp->bp->hw.target == bp->hw.target &&
- !can_co_exist(tmp, bp))
- return true;
- }
- return false;
-}
-
-static int cpu_bps_add(struct perf_event *bp)
-{
- struct breakpoint **cpu_bp;
- struct breakpoint *tmp;
- int i = 0;
-
- tmp = alloc_breakpoint(bp);
- if (IS_ERR(tmp))
- return PTR_ERR(tmp);
-
- cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
- for (i = 0; i < nr_wp_slots(); i++) {
- if (!cpu_bp[i]) {
- cpu_bp[i] = tmp;
- break;
- }
- }
- return 0;
-}
-
-static void cpu_bps_remove(struct perf_event *bp)
-{
- struct breakpoint **cpu_bp;
- int i = 0;
-
- cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
- for (i = 0; i < nr_wp_slots(); i++) {
- if (!cpu_bp[i])
- continue;
-
- if (cpu_bp[i]->bp == bp) {
- kfree(cpu_bp[i]);
- cpu_bp[i] = NULL;
- break;
- }
- }
-}
-
-static bool cpu_bps_check(int cpu, struct perf_event *bp)
-{
- struct breakpoint **cpu_bp;
- int i;
-
- cpu_bp = per_cpu_ptr(cpu_bps, cpu);
- for (i = 0; i < nr_wp_slots(); i++) {
- if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp))
- return true;
- }
- return false;
-}
-
-static bool all_cpu_bps_check(struct perf_event *bp)
-{
- int cpu;
-
- for_each_online_cpu(cpu) {
- if (cpu_bps_check(cpu, bp))
- return true;
- }
- return false;
-}
-
-/*
- * We don't use any locks to serialize accesses to cpu_bps or task_bps
- * because are already inside nr_bp_mutex.
- */
-int arch_reserve_bp_slot(struct perf_event *bp)
-{
- int ret;
-
- /* ptrace breakpoint */
- if (is_ptrace_bp(bp)) {
- if (all_cpu_bps_check(bp))
- return -ENOSPC;
-
- if (same_task_bps_check(bp))
- return -ENOSPC;
-
- return task_bps_add(bp);
- }
-
- /* perf breakpoint */
- if (is_kernel_addr(bp->attr.bp_addr))
- return 0;
-
- if (bp->hw.target && bp->cpu == -1) {
- if (same_task_bps_check(bp))
- return -ENOSPC;
-
- return task_bps_add(bp);
- } else if (!bp->hw.target && bp->cpu != -1) {
- if (all_task_bps_check(bp))
- return -ENOSPC;
-
- return cpu_bps_add(bp);
- }
-
- if (same_task_bps_check(bp))
- return -ENOSPC;
-
- ret = cpu_bps_add(bp);
- if (ret)
- return ret;
- ret = task_bps_add(bp);
- if (ret)
- cpu_bps_remove(bp);
-
- return ret;
-}
-
-void arch_release_bp_slot(struct perf_event *bp)
-{
- if (!is_kernel_addr(bp->attr.bp_addr)) {
- if (bp->hw.target)
- task_bps_remove(bp);
- if (bp->cpu != -1)
- cpu_bps_remove(bp);
- }
-}
-
-/*
- * Perform cleanup of arch-specific counters during unregistration
- * of the perf-event
- */
-void arch_unregister_hw_breakpoint(struct perf_event *bp)
-{
- /*
- * If the breakpoint is unregistered between a hw_breakpoint_handler()
- * and the single_step_dabr_instruction(), then cleanup the breakpoint
- * restoration variables to prevent dangling pointers.
- * FIXME, this should not be using bp->ctx at all! Sayeth peterz.
- */
- if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L)) {
- int i;
-
- for (i = 0; i < nr_wp_slots(); i++) {
- if (bp->ctx->task->thread.last_hit_ubp[i] == bp)
- bp->ctx->task->thread.last_hit_ubp[i] = NULL;
- }
- }
-}
-
/*
* Check for virtual address in kernel space.
*/
@@ -472,25 +220,36 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
* Restores the breakpoint on the debug registers.
* Invoke this function if it is known that the execution context is
* about to change to cause loss of MSR_SE settings.
+ *
+ * The perf watchpoint will simply re-trigger once the thread is started again,
+ * and the watchpoint handler will set up MSR_SE and perf_single_step as
+ * needed.
*/
void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
{
struct arch_hw_breakpoint *info;
int i;
+ preempt_disable();
+
for (i = 0; i < nr_wp_slots(); i++) {
- if (unlikely(tsk->thread.last_hit_ubp[i]))
+ struct perf_event *bp = __this_cpu_read(bp_per_reg[i]);
+
+ if (unlikely(bp && counter_arch_bp(bp)->perf_single_step))
goto reset;
}
- return;
+ goto out;
reset:
regs_set_return_msr(regs, regs->msr & ~MSR_SE);
for (i = 0; i < nr_wp_slots(); i++) {
info = counter_arch_bp(__this_cpu_read(bp_per_reg[i]));
__set_breakpoint(i, info);
- tsk->thread.last_hit_ubp[i] = NULL;
+ info->perf_single_step = false;
}
+
+out:
+ preempt_enable();
}
static bool is_larx_stcx_instr(int type)
@@ -507,23 +266,22 @@ static bool is_octword_vsx_instr(int type, int size)
* We've failed in reliably handling the hw-breakpoint. Unregister
* it and throw a warning message to let the user know about it.
*/
-static void handler_error(struct perf_event *bp, struct arch_hw_breakpoint *info)
+static void handler_error(struct perf_event *bp)
{
WARN(1, "Unable to handle hardware breakpoint. Breakpoint at 0x%lx will be disabled.",
- info->address);
+ counter_arch_bp(bp)->address);
perf_event_disable_inatomic(bp);
}
-static void larx_stcx_err(struct perf_event *bp, struct arch_hw_breakpoint *info)
+static void larx_stcx_err(struct perf_event *bp)
{
printk_ratelimited("Breakpoint hit on instruction that can't be emulated. Breakpoint at 0x%lx will be disabled.\n",
- info->address);
+ counter_arch_bp(bp)->address);
perf_event_disable_inatomic(bp);
}
static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
- struct arch_hw_breakpoint **info, int *hit,
- ppc_inst_t instr)
+ int *hit, ppc_inst_t instr)
{
int i;
int stepped;
@@ -533,8 +291,9 @@ static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
for (i = 0; i < nr_wp_slots(); i++) {
if (!hit[i])
continue;
- current->thread.last_hit_ubp[i] = bp[i];
- info[i] = NULL;
+
+ counter_arch_bp(bp[i])->perf_single_step = true;
+ bp[i] = NULL;
}
regs_set_return_msr(regs, regs->msr | MSR_SE);
return false;
@@ -545,15 +304,15 @@ static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
for (i = 0; i < nr_wp_slots(); i++) {
if (!hit[i])
continue;
- handler_error(bp[i], info[i]);
- info[i] = NULL;
+ handler_error(bp[i]);
+ bp[i] = NULL;
}
return false;
}
return true;
}
-static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info,
+static void handle_p10dd1_spurious_exception(struct perf_event **bp,
int *hit, unsigned long ea)
{
int i;
@@ -565,10 +324,14 @@ static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info,
* spurious exception.
*/
for (i = 0; i < nr_wp_slots(); i++) {
- if (!info[i])
+ struct arch_hw_breakpoint *info;
+
+ if (!bp[i])
continue;
- hw_end_addr = ALIGN(info[i]->address + info[i]->len, HW_BREAKPOINT_SIZE);
+ info = counter_arch_bp(bp[i]);
+
+ hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE);
/*
* Ending address of DAWR range is less than starting
@@ -598,20 +361,24 @@ static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info,
return;
for (i = 0; i < nr_wp_slots(); i++) {
- if (info[i]) {
+ if (bp[i]) {
hit[i] = 1;
- info[i]->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ counter_arch_bp(bp[i])->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
}
}
}
+/*
+ * Handle a DABR or DAWR exception.
+ *
+ * Called in atomic context.
+ */
int hw_breakpoint_handler(struct die_args *args)
{
bool err = false;
int rc = NOTIFY_STOP;
struct perf_event *bp[HBP_NUM_MAX] = { NULL };
struct pt_regs *regs = args->regs;
- struct arch_hw_breakpoint *info[HBP_NUM_MAX] = { NULL };
int i;
int hit[HBP_NUM_MAX] = {0};
int nr_hit = 0;
@@ -619,7 +386,7 @@ int hw_breakpoint_handler(struct die_args *args)
ppc_inst_t instr = ppc_inst(0);
int type = 0;
int size = 0;
- unsigned long ea;
+ unsigned long ea = 0;
/* Disable breakpoints during exception handling */
hw_breakpoint_disable();
@@ -636,18 +403,20 @@ int hw_breakpoint_handler(struct die_args *args)
wp_get_instr_detail(regs, &instr, &type, &size, &ea);
for (i = 0; i < nr_wp_slots(); i++) {
+ struct arch_hw_breakpoint *info;
+
bp[i] = __this_cpu_read(bp_per_reg[i]);
if (!bp[i])
continue;
- info[i] = counter_arch_bp(bp[i]);
- info[i]->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ info = counter_arch_bp(bp[i]);
+ info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
- if (wp_check_constraints(regs, instr, ea, type, size, info[i])) {
+ if (wp_check_constraints(regs, instr, ea, type, size, info)) {
if (!IS_ENABLED(CONFIG_PPC_8xx) &&
ppc_inst_equal(instr, ppc_inst(0))) {
- handler_error(bp[i], info[i]);
- info[i] = NULL;
+ handler_error(bp[i]);
+ bp[i] = NULL;
err = 1;
continue;
}
@@ -666,7 +435,7 @@ int hw_breakpoint_handler(struct die_args *args)
/* Workaround for Power10 DD1 */
if (!IS_ENABLED(CONFIG_PPC_8xx) && mfspr(SPRN_PVR) == 0x800100 &&
is_octword_vsx_instr(type, size)) {
- handle_p10dd1_spurious_exception(info, hit, ea);
+ handle_p10dd1_spurious_exception(bp, hit, ea);
} else {
rc = NOTIFY_DONE;
goto out;
@@ -681,10 +450,10 @@ int hw_breakpoint_handler(struct die_args *args)
*/
if (ptrace_bp) {
for (i = 0; i < nr_wp_slots(); i++) {
- if (!hit[i])
+ if (!hit[i] || !is_ptrace_bp(bp[i]))
continue;
perf_bp_event(bp[i], regs);
- info[i] = NULL;
+ bp[i] = NULL;
}
rc = NOTIFY_DONE;
goto reset;
@@ -695,13 +464,13 @@ int hw_breakpoint_handler(struct die_args *args)
for (i = 0; i < nr_wp_slots(); i++) {
if (!hit[i])
continue;
- larx_stcx_err(bp[i], info[i]);
- info[i] = NULL;
+ larx_stcx_err(bp[i]);
+ bp[i] = NULL;
}
goto reset;
}
- if (!stepping_handler(regs, bp, info, hit, instr))
+ if (!stepping_handler(regs, bp, hit, instr))
goto reset;
}
@@ -712,15 +481,15 @@ int hw_breakpoint_handler(struct die_args *args)
for (i = 0; i < nr_wp_slots(); i++) {
if (!hit[i])
continue;
- if (!(info[i]->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
+ if (!(counter_arch_bp(bp[i])->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
perf_bp_event(bp[i], regs);
}
reset:
for (i = 0; i < nr_wp_slots(); i++) {
- if (!info[i])
+ if (!bp[i])
continue;
- __set_breakpoint(i, info[i]);
+ __set_breakpoint(i, counter_arch_bp(bp[i]));
}
out:
@@ -731,28 +500,34 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler);
/*
* Handle single-step exceptions following a DABR hit.
+ *
+ * Called in atomic context.
*/
static int single_step_dabr_instruction(struct die_args *args)
{
struct pt_regs *regs = args->regs;
- struct perf_event *bp = NULL;
- struct arch_hw_breakpoint *info;
- int i;
bool found = false;
/*
* Check if we are single-stepping as a result of a
* previous HW Breakpoint exception
*/
- for (i = 0; i < nr_wp_slots(); i++) {
- bp = current->thread.last_hit_ubp[i];
+ for (int i = 0; i < nr_wp_slots(); i++) {
+ struct perf_event *bp;
+ struct arch_hw_breakpoint *info;
+
+ bp = __this_cpu_read(bp_per_reg[i]);
if (!bp)
continue;
- found = true;
info = counter_arch_bp(bp);
+ if (!info->perf_single_step)
+ continue;
+
+ found = true;
+
/*
* We shall invoke the user-defined callback function in the
* single stepping handler to confirm to 'trigger-after-execute'
@@ -760,26 +535,16 @@ static int single_step_dabr_instruction(struct die_args *args)
*/
if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
perf_bp_event(bp, regs);
- current->thread.last_hit_ubp[i] = NULL;
- }
- if (!found)
- return NOTIFY_DONE;
-
- for (i = 0; i < nr_wp_slots(); i++) {
- bp = __this_cpu_read(bp_per_reg[i]);
- if (!bp)
- continue;
-
- info = counter_arch_bp(bp);
- __set_breakpoint(i, info);
+ info->perf_single_step = false;
+ __set_breakpoint(i, counter_arch_bp(bp));
}
/*
* If the process was being single-stepped by ptrace, let the
* other single-step actions occur (e.g. generate SIGTRAP).
*/
- if (test_thread_flag(TIF_SINGLESTEP))
+ if (!found || test_thread_flag(TIF_SINGLESTEP))
return NOTIFY_DONE;
return NOTIFY_STOP;
@@ -788,6 +553,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction);
/*
* Handle debug exception notifications.
+ *
+ * Called in atomic context.
*/
int hw_breakpoint_exceptions_notify(
struct notifier_block *unused, unsigned long val, void *data)
diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c
index a74623025f3a..9e51801c4915 100644
--- a/arch/powerpc/kernel/hw_breakpoint_constraints.c
+++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c
@@ -131,8 +131,13 @@ void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr,
int *type, int *size, unsigned long *ea)
{
struct instruction_op op;
+ int err;
- if (__get_user_instr(*instr, (void __user *)regs->nip))
+ pagefault_disable();
+ err = __get_user_instr(*instr, (void __user *)regs->nip);
+ pagefault_enable();
+
+ if (err)
return;
analyse_instr(&op, regs, *instr);
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 77cd4c5a2d63..e527cd3ef128 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -51,10 +51,9 @@ void arch_cpu_idle(void)
* Some power_save functions return with
* interrupts enabled, some don't.
*/
- if (irqs_disabled())
- raw_local_irq_enable();
+ if (!irqs_disabled())
+ raw_local_irq_disable();
} else {
- raw_local_irq_enable();
/*
* Go into low thread priority and possibly
* low power mode.
@@ -98,7 +97,7 @@ void power4_idle(void)
/*
* Register the sysctl to set/clear powersave_nap.
*/
-static struct ctl_table powersave_nap_ctl_table[] = {
+static const struct ctl_table powersave_nap_ctl_table[] = {
{
.procname = "powersave-nap",
.data = &powersave_nap,
@@ -106,21 +105,12 @@ static struct ctl_table powersave_nap_ctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {}
-};
-static struct ctl_table powersave_nap_sysctl_root[] = {
- {
- .procname = "kernel",
- .mode = 0555,
- .child = powersave_nap_ctl_table,
- },
- {}
};
static int __init
register_powersave_nap_sysctl(void)
{
- register_sysctl_table(powersave_nap_sysctl_root);
+ register_sysctl("kernel", powersave_nap_ctl_table);
return 0;
}
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_64e.S
index cc008de58b05..0fc680e03dee 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_64e.S
@@ -2,7 +2,7 @@
/*
* Copyright 2010 IBM Corp, Benjamin Herrenschmidt <benh@kernel.crashing.org>
*
- * Generic idle routine for Book3E processors
+ * Generic idle routine for 64 bits e500 processors
*/
#include <linux/threads.h>
@@ -16,8 +16,6 @@
#include <asm/hw_irq.h>
/* 64-bit version only for now */
-#ifdef CONFIG_PPC64
-
.macro BOOK3E_IDLE name loop
_GLOBAL(\name)
/* Save LR for later */
@@ -77,7 +75,7 @@ _GLOBAL(\name)
.macro BOOK3E_IDLE_LOOP
1:
- PPC_WAIT(0)
+ PPC_WAIT_v203
b 1b
.endm
@@ -98,6 +96,4 @@ epapr_ev_idle_start:
BOOK3E_IDLE epapr_ev_idle EPAPR_EV_IDLE_LOOP
-BOOK3E_IDLE book3e_idle BOOK3E_IDLE_LOOP
-
-#endif /* CONFIG_PPC64 */
+BOOK3E_IDLE e500_idle BOOK3E_IDLE_LOOP
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_85xx.S
index 9e1bc4502c50..9e1bc4502c50 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_85xx.S
diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c
index 957abd592075..b7029beed847 100644
--- a/arch/powerpc/kernel/ima_arch.c
+++ b/arch/powerpc/kernel/ima_arch.c
@@ -23,9 +23,9 @@ bool arch_ima_get_secureboot(void)
* is not enabled.
*/
static const char *const secure_rules[] = {
- "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+ "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig",
#ifndef CONFIG_MODULE_SIG
- "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+ "appraise func=MODULE_CHECK appraise_type=imasig|modsig",
#endif
NULL
};
@@ -49,9 +49,9 @@ static const char *const trusted_rules[] = {
static const char *const secure_and_trusted_rules[] = {
"measure func=KEXEC_KERNEL_CHECK template=ima-modsig",
"measure func=MODULE_CHECK template=ima-modsig",
- "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+ "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig",
#ifndef CONFIG_MODULE_SIG
- "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+ "appraise func=MODULE_CHECK appraise_type=imasig|modsig",
#endif
NULL
};
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 784ea3289c84..e0c681d0b076 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -3,6 +3,7 @@
#include <linux/context_tracking.h>
#include <linux/err.h>
#include <linux/compat.h>
+#include <linux/rseq.h>
#include <linux/sched/debug.h> /* for show_regs */
#include <asm/kup.h>
@@ -24,7 +25,9 @@
unsigned long global_dbcr0[NR_CPUS];
#endif
-typedef long (*syscall_fn)(long, long, long, long, long, long);
+#if defined(CONFIG_PREEMPT_DYNAMIC)
+DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+#endif
#ifdef CONFIG_PPC_BOOK3S_64
DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
@@ -52,16 +55,18 @@ static inline bool exit_must_hard_disable(void)
*/
static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable)
{
+ bool must_hard_disable = (exit_must_hard_disable() || !restartable);
+
/* This must be done with RI=1 because tracing may touch vmaps */
trace_hardirqs_on();
- if (exit_must_hard_disable() || !restartable)
+ if (must_hard_disable)
__hard_EE_RI_disable();
#ifdef CONFIG_PPC64
/* This pattern matches prep_irq_for_idle */
if (unlikely(lazy_irq_pending_nocheck())) {
- if (exit_must_hard_disable() || !restartable) {
+ if (must_hard_disable) {
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
__hard_RI_enable();
}
@@ -73,165 +78,6 @@ static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable)
return true;
}
-/* Has to run notrace because it is entered not completely "reconciled" */
-notrace long system_call_exception(long r3, long r4, long r5,
- long r6, long r7, long r8,
- unsigned long r0, struct pt_regs *regs)
-{
- syscall_fn f;
-
- kuap_lock();
-
- regs->orig_gpr3 = r3;
-
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
-
- trace_hardirqs_off(); /* finish reconciling */
-
- CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
- user_exit_irqoff();
-
- BUG_ON(regs_is_unrecoverable(regs));
- BUG_ON(!(regs->msr & MSR_PR));
- BUG_ON(arch_irq_disabled_regs(regs));
-
-#ifdef CONFIG_PPC_PKEY
- if (mmu_has_feature(MMU_FTR_PKEY)) {
- unsigned long amr, iamr;
- bool flush_needed = false;
- /*
- * When entering from userspace we mostly have the AMR/IAMR
- * different from kernel default values. Hence don't compare.
- */
- amr = mfspr(SPRN_AMR);
- iamr = mfspr(SPRN_IAMR);
- regs->amr = amr;
- regs->iamr = iamr;
- if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) {
- mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
- flush_needed = true;
- }
- if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
- mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
- flush_needed = true;
- }
- if (flush_needed)
- isync();
- } else
-#endif
- kuap_assert_locked();
-
- booke_restore_dbcr0();
-
- account_cpu_user_entry();
-
- account_stolen_time();
-
- /*
- * This is not required for the syscall exit path, but makes the
- * stack frame look nicer. If this was initialised in the first stack
- * frame, or if the unwinder was taught the first stack frame always
- * returns to user with IRQS_ENABLED, this store could be avoided!
- */
- irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
-
- /*
- * If system call is called with TM active, set _TIF_RESTOREALL to
- * prevent RFSCV being used to return to userspace, because POWER9
- * TM implementation has problems with this instruction returning to
- * transactional state. Final register values are not relevant because
- * the transaction will be aborted upon return anyway. Or in the case
- * of unsupported_scv SIGILL fault, the return state does not much
- * matter because it's an edge case.
- */
- if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
- unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
- set_bits(_TIF_RESTOREALL, &current_thread_info()->flags);
-
- /*
- * If the system call was made with a transaction active, doom it and
- * return without performing the system call. Unless it was an
- * unsupported scv vector, in which case it's treated like an illegal
- * instruction.
- */
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
- !trap_is_unsupported_scv(regs)) {
- /* Enable TM in the kernel, and disable EE (for scv) */
- hard_irq_disable();
- mtmsr(mfmsr() | MSR_TM);
-
- /* tabort, this dooms the transaction, nothing else */
- asm volatile(".long 0x7c00071d | ((%0) << 16)"
- :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT));
-
- /*
- * Userspace will never see the return value. Execution will
- * resume after the tbegin. of the aborted transaction with the
- * checkpointed register state. A context switch could occur
- * or signal delivered to the process before resuming the
- * doomed transaction context, but that should all be handled
- * as expected.
- */
- return -ENOSYS;
- }
-#endif // CONFIG_PPC_TRANSACTIONAL_MEM
-
- local_irq_enable();
-
- if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) {
- if (unlikely(trap_is_unsupported_scv(regs))) {
- /* Unsupported scv vector */
- _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
- return regs->gpr[3];
- }
- /*
- * We use the return value of do_syscall_trace_enter() as the
- * syscall number. If the syscall was rejected for any reason
- * do_syscall_trace_enter() returns an invalid syscall number
- * and the test against NR_syscalls will fail and the return
- * value to be used is in regs->gpr[3].
- */
- r0 = do_syscall_trace_enter(regs);
- if (unlikely(r0 >= NR_syscalls))
- return regs->gpr[3];
- r3 = regs->gpr[3];
- r4 = regs->gpr[4];
- r5 = regs->gpr[5];
- r6 = regs->gpr[6];
- r7 = regs->gpr[7];
- r8 = regs->gpr[8];
-
- } else if (unlikely(r0 >= NR_syscalls)) {
- if (unlikely(trap_is_unsupported_scv(regs))) {
- /* Unsupported scv vector */
- _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
- return regs->gpr[3];
- }
- return -ENOSYS;
- }
-
- /* May be faster to do array_index_nospec? */
- barrier_nospec();
-
- if (unlikely(is_compat_task())) {
- f = (void *)compat_sys_call_table[r0];
-
- r3 &= 0x00000000ffffffffULL;
- r4 &= 0x00000000ffffffffULL;
- r5 &= 0x00000000ffffffffULL;
- r6 &= 0x00000000ffffffffULL;
- r7 &= 0x00000000ffffffffULL;
- r8 &= 0x00000000ffffffffULL;
-
- } else {
- f = (void *)sys_call_table[r0];
- }
-
- return f(r3, r4, r5, r6, r7, r8);
-}
-
static notrace void booke_load_dbcr0(void)
{
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -254,7 +100,7 @@ static notrace void booke_load_dbcr0(void)
#endif
}
-static void check_return_regs_valid(struct pt_regs *regs)
+static notrace void check_return_regs_valid(struct pt_regs *regs)
{
#ifdef CONFIG_PPC_BOOK3S_64
unsigned long trap, srr0, srr1;
@@ -284,7 +130,7 @@ static void check_return_regs_valid(struct pt_regs *regs)
case 0x1600:
case 0x1800:
validp = &local_paca->hsrr_valid;
- if (!*validp)
+ if (!READ_ONCE(*validp))
return;
srr0 = mfspr(SPRN_HSRR0);
@@ -294,7 +140,7 @@ static void check_return_regs_valid(struct pt_regs *regs)
break;
default:
validp = &local_paca->srr_valid;
- if (!*validp)
+ if (!READ_ONCE(*validp))
return;
srr0 = mfspr(SPRN_SRR0);
@@ -320,19 +166,17 @@ static void check_return_regs_valid(struct pt_regs *regs)
* such things will get caught most of the time, statistically
* enough to be able to get a warning out.
*/
- barrier();
-
- if (!*validp)
+ if (!READ_ONCE(*validp))
return;
- if (!warned) {
- warned = true;
+ if (!data_race(warned)) {
+ data_race(warned = true);
printk("%sSRR0 was: %lx should be: %lx\n", h, srr0, regs->nip);
printk("%sSRR1 was: %lx should be: %lx\n", h, srr1, regs->msr);
show_regs(regs);
}
- *validp = 0; /* fixup */
+ WRITE_ONCE(*validp, 0); /* fixup */
#endif
}
@@ -345,7 +189,7 @@ again:
ti_flags = read_thread_flags();
while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
local_irq_enable();
- if (ti_flags & _TIF_NEED_RESCHED) {
+ if (ti_flags & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
schedule();
} else {
/*
@@ -426,7 +270,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
unsigned long ret = 0;
bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv;
- CT_WARN_ON(ct_state() == CONTEXT_USER);
+ CT_WARN_ON(ct_state() == CT_STATE_USER);
kuap_assert_locked();
@@ -504,7 +348,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs)
BUG_ON(regs_is_unrecoverable(regs));
BUG_ON(arch_irq_disabled_regs(regs));
- CT_WARN_ON(ct_state() == CONTEXT_USER);
+ CT_WARN_ON(ct_state() == CT_STATE_USER);
/*
* We don't need to restore AMR on the way back to userspace for KUAP.
@@ -527,7 +371,6 @@ void preempt_schedule_irq(void);
notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
{
- unsigned long flags;
unsigned long ret = 0;
unsigned long kuap;
bool stack_store = read_thread_flags() & _TIF_EMULATE_STACK_STORE;
@@ -535,21 +378,29 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
if (regs_is_unrecoverable(regs))
unrecoverable_exception(regs);
/*
- * CT_WARN_ON comes here via program_check_exception,
- * so avoid recursion.
+ * CT_WARN_ON comes here via program_check_exception, so avoid
+ * recursion.
+ *
+ * Skip the assertion on PMIs on 64e to work around a problem caused
+ * by NMI PMIs incorrectly taking this interrupt return path, it's
+ * possible for this to hit after interrupt exit to user switches
+ * context to user. See also the comment in the performance monitor
+ * handler in exceptions-64e.S
*/
- if (TRAP(regs) != INTERRUPT_PROGRAM)
- CT_WARN_ON(ct_state() == CONTEXT_USER);
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
+ TRAP(regs) != INTERRUPT_PROGRAM &&
+ TRAP(regs) != INTERRUPT_PERFMON)
+ CT_WARN_ON(ct_state() == CT_STATE_USER);
kuap = kuap_get_and_assert_locked();
- local_irq_save(flags);
+ local_irq_disable();
if (!arch_irq_disabled_regs(regs)) {
/* Returning to a kernel context with local irqs enabled. */
WARN_ON_ONCE(!(regs->msr & MSR_EE));
again:
- if (IS_ENABLED(CONFIG_PREEMPT)) {
+ if (need_irq_preemption()) {
/* Return to preemptible kernel context */
if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) {
if (preempt_count() == 0)
@@ -592,16 +443,6 @@ again:
if (unlikely(stack_store))
__hard_EE_RI_disable();
- /*
- * Returning to a kernel context with local irqs disabled.
- * Here, if EE was enabled in the interrupted context, enable
- * it on return as well. A problem exists here where a soft
- * masked interrupt may have cleared MSR[EE] and set HARD_DIS
- * here, and it will still exist on return to the caller. This
- * will be resolved by the masked interrupt firing again.
- */
- if (regs->msr & MSR_EE)
- local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
#endif /* CONFIG_PPC64 */
}
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index ce25b28cf418..1ad059a9e2fe 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -13,16 +13,6 @@
#include <asm/ppc_asm.h>
#include <asm/ptrace.h>
- .section ".toc","aw"
-SYS_CALL_TABLE:
- .tc sys_call_table[TC],sys_call_table
-
-#ifdef CONFIG_COMPAT
-COMPAT_SYS_CALL_TABLE:
- .tc compat_sys_call_table[TC],compat_sys_call_table
-#endif
- .previous
-
.align 7
.macro DEBUG_SRR_VALID srr
@@ -62,21 +52,17 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
mr r10,r1
ld r1,PACAKSAVE(r13)
std r10,0(r1)
- std r11,_NIP(r1)
+ std r11,_LINK(r1)
+ std r11,_NIP(r1) /* Saved LR is also the next instruction */
std r12,_MSR(r1)
std r0,GPR0(r1)
std r10,GPR1(r1)
std r2,GPR2(r1)
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
mfcr r12
li r11,0
- /* Can we avoid saving r3-r8 in common case? */
- std r3,GPR3(r1)
- std r4,GPR4(r1)
- std r5,GPR5(r1)
- std r6,GPR6(r1)
- std r7,GPR7(r1)
- std r8,GPR8(r1)
+ /* Save syscall parameters in r3-r8 */
+ SAVE_GPRS(3, 8, r1)
/* Zero r9-r12, this should only be required when restoring all GPRs */
std r11,GPR9(r1)
std r11,GPR10(r1)
@@ -85,15 +71,17 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
std r9,GPR13(r1)
SAVE_NVGPRS(r1)
std r11,_XER(r1)
- std r11,_LINK(r1)
std r11,_CTR(r1)
li r11,\trapnr
std r11,_TRAP(r1)
std r12,_CCR(r1)
- addi r10,r1,STACK_FRAME_OVERHEAD
- ld r11,exception_marker@toc(r2)
- std r11,-16(r10) /* "regshere" marker */
+ std r3,ORIG_GPR3(r1)
+ LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER)
+ std r11,STACK_INT_FRAME_MARKER(r1) /* "regs" marker */
+ /* Calling convention has r3 = regs, r4 = orig r0 */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ mr r4,r0
BEGIN_FTR_SECTION
HMT_MEDIUM
@@ -108,14 +96,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
* but this is the best we can do.
*/
- /* Calling convention has r9 = orig r0, r10 = regs */
- mr r9,r0
- bl system_call_exception
+ /*
+ * Zero user registers to prevent influencing speculative execution
+ * state of kernel code.
+ */
+ SANITIZE_SYSCALL_GPRS()
+ bl CFUNC(system_call_exception)
.Lsyscall_vectored_\name\()_exit:
- addi r4,r1,STACK_FRAME_OVERHEAD
+ addi r4,r1,STACK_INT_FRAME_REGS
li r5,1 /* scv */
- bl syscall_exit_prepare
+ bl CFUNC(syscall_exit_prepare)
std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
.Lsyscall_vectored_\name\()_rst_start:
lbz r11,PACAIRQHAPPENED(r13)
@@ -138,6 +129,7 @@ BEGIN_FTR_SECTION
HMT_MEDIUM_LOW
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+ SANITIZE_RESTORE_NVGPRS()
cmpdi r3,0
bne .Lsyscall_vectored_\name\()_restore_regs
@@ -148,17 +140,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* Could zero these as per ABI, but we may consider a stricter ABI
* which preserves these if libc implementations can benefit, so
* restore them for now until further measurement is done. */
- ld r0,GPR0(r1)
- ld r4,GPR4(r1)
- ld r5,GPR5(r1)
- ld r6,GPR6(r1)
- ld r7,GPR7(r1)
- ld r8,GPR8(r1)
+ REST_GPR(0, r1)
+ REST_GPRS(4, 8, r1)
/* Zero volatile regs that may contain sensitive kernel data */
- li r9,0
- li r10,0
- li r11,0
- li r12,0
+ ZEROIZE_GPRS(9, 12)
mtspr SPRN_XER,r0
/*
@@ -180,8 +165,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
ld r4,_LINK(r1)
ld r5,_XER(r1)
- REST_NVGPRS(r1)
- ld r0,GPR0(r1)
+ HANDLER_RESTORE_NVGPRS()
+ REST_GPR(0, r1)
mtcr r2
mtctr r3
mtlr r4
@@ -195,12 +180,12 @@ syscall_vectored_\name\()_restart:
_ASM_NOKPROBE_SYMBOL(syscall_vectored_\name\()_restart)
GET_PACA(r13)
ld r1,PACA_EXIT_SAVE_R1(r13)
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
ld r3,RESULT(r1)
- addi r4,r1,STACK_FRAME_OVERHEAD
+ addi r4,r1,STACK_INT_FRAME_REGS
li r11,IRQS_ALL_DISABLED
stb r11,PACAIRQSOFTMASK(r13)
- bl syscall_exit_restart
+ bl CFUNC(syscall_exit_restart)
std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
b .Lsyscall_vectored_\name\()_rst_start
1:
@@ -240,21 +225,16 @@ _ASM_NOKPROBE_SYMBOL(system_call_common)
std r0,GPR0(r1)
std r10,GPR1(r1)
std r2,GPR2(r1)
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
START_BTB_FLUSH_SECTION
BTB_FLUSH(r10)
END_BTB_FLUSH_SECTION
#endif
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
mfcr r12
li r11,0
- /* Can we avoid saving r3-r8 in common case? */
- std r3,GPR3(r1)
- std r4,GPR4(r1)
- std r5,GPR5(r1)
- std r6,GPR6(r1)
- std r7,GPR7(r1)
- std r8,GPR8(r1)
+ /* Save syscall parameters in r3-r8 */
+ SAVE_GPRS(3, 8, r1)
/* Zero r9-r12, this should only be required when restoring all GPRs */
std r11,GPR9(r1)
std r11,GPR10(r1)
@@ -275,9 +255,12 @@ END_BTB_FLUSH_SECTION
std r10,_LINK(r1)
std r11,_TRAP(r1)
std r12,_CCR(r1)
- addi r10,r1,STACK_FRAME_OVERHEAD
- ld r11,exception_marker@toc(r2)
- std r11,-16(r10) /* "regshere" marker */
+ std r3,ORIG_GPR3(r1)
+ LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER)
+ std r11,STACK_INT_FRAME_MARKER(r1) /* "regs" marker */
+ /* Calling convention has r3 = regs, r4 = orig r0 */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ mr r4,r0
#ifdef CONFIG_PPC_BOOK3S
li r11,1
@@ -298,14 +281,17 @@ END_BTB_FLUSH_SECTION
wrteei 1
#endif
- /* Calling convention has r9 = orig r0, r10 = regs */
- mr r9,r0
- bl system_call_exception
+ /*
+ * Zero user registers to prevent influencing speculative execution
+ * state of kernel code.
+ */
+ SANITIZE_SYSCALL_GPRS()
+ bl CFUNC(system_call_exception)
.Lsyscall_exit:
- addi r4,r1,STACK_FRAME_OVERHEAD
+ addi r4,r1,STACK_INT_FRAME_REGS
li r5,0 /* !scv */
- bl syscall_exit_prepare
+ bl CFUNC(syscall_exit_prepare)
std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
#ifdef CONFIG_PPC_BOOK3S
.Lsyscall_rst_start:
@@ -340,19 +326,12 @@ BEGIN_FTR_SECTION
stdcx. r0,0,r1 /* to clear the reservation */
END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+ SANITIZE_RESTORE_NVGPRS()
cmpdi r3,0
bne .Lsyscall_restore_regs
/* Zero volatile regs that may contain sensitive kernel data */
- li r0,0
- li r4,0
- li r5,0
- li r6,0
- li r7,0
- li r8,0
- li r9,0
- li r10,0
- li r11,0
- li r12,0
+ ZEROIZE_GPR(0)
+ ZEROIZE_GPRS(4, 12)
mtctr r0
mtspr SPRN_XER,r0
.Lsyscall_restore_regs_cont:
@@ -375,10 +354,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
.Lsyscall_restore_regs:
ld r3,_CTR(r1)
ld r4,_XER(r1)
- REST_NVGPRS(r1)
+ HANDLER_RESTORE_NVGPRS()
mtctr r3
mtspr SPRN_XER,r4
- ld r0,GPR0(r1)
+ REST_GPR(0, r1)
REST_GPRS(4, 12, r1)
b .Lsyscall_restore_regs_cont
.Lsyscall_rst_end:
@@ -388,12 +367,12 @@ syscall_restart:
_ASM_NOKPROBE_SYMBOL(syscall_restart)
GET_PACA(r13)
ld r1,PACA_EXIT_SAVE_R1(r13)
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
ld r3,RESULT(r1)
- addi r4,r1,STACK_FRAME_OVERHEAD
+ addi r4,r1,STACK_INT_FRAME_REGS
li r11,IRQS_ALL_DISABLED
stb r11,PACAIRQSOFTMASK(r13)
- bl syscall_exit_restart
+ bl CFUNC(syscall_exit_restart)
std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
b .Lsyscall_rst_start
1:
@@ -421,8 +400,8 @@ _ASM_NOKPROBE_SYMBOL(fast_interrupt_return_srr)
andi. r0,r5,MSR_RI
li r3,0 /* 0 return value, no EMULATE_STACK_STORE */
bne+ .Lfast_kernel_interrupt_return_srr
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl unrecoverable_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(unrecoverable_exception)
b . /* should not get here */
#else
bne .Lfast_user_interrupt_return_srr
@@ -439,11 +418,13 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\())
beq interrupt_return_\srr\()_kernel
interrupt_return_\srr\()_user: /* make backtraces match the _kernel variant */
_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl interrupt_exit_user_prepare
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(interrupt_exit_user_prepare)
+#ifndef CONFIG_INTERRUPT_SANITIZE_REGISTERS
cmpdi r3,0
bne- .Lrestore_nvgprs_\srr
.Lrestore_nvgprs_\srr\()_cont:
+#endif
std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
#ifdef CONFIG_PPC_BOOK3S
.Linterrupt_return_\srr\()_user_rst_start:
@@ -457,6 +438,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user)
stb r11,PACAIRQHAPPENED(r13) # clear out possible HARD_DIS
.Lfast_user_interrupt_return_\srr\():
+ SANITIZE_RESTORE_NVGPRS()
#ifdef CONFIG_PPC_BOOK3S
.ifc \srr,srr
lbz r4,PACASRR_VALID(r13)
@@ -526,20 +508,22 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
b . /* prevent speculative execution */
.Linterrupt_return_\srr\()_user_rst_end:
+#ifndef CONFIG_INTERRUPT_SANITIZE_REGISTERS
.Lrestore_nvgprs_\srr\():
REST_NVGPRS(r1)
b .Lrestore_nvgprs_\srr\()_cont
+#endif
#ifdef CONFIG_PPC_BOOK3S
interrupt_return_\srr\()_user_restart:
_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user_restart)
GET_PACA(r13)
ld r1,PACA_EXIT_SAVE_R1(r13)
- ld r2,PACATOC(r13)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ LOAD_PACA_TOC()
+ addi r3,r1,STACK_INT_FRAME_REGS
li r11,IRQS_ALL_DISABLED
stb r11,PACAIRQSOFTMASK(r13)
- bl interrupt_exit_user_restart
+ bl CFUNC(interrupt_exit_user_restart)
std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
b .Linterrupt_return_\srr\()_user_rst_start
1:
@@ -551,25 +535,74 @@ RESTART_TABLE(.Linterrupt_return_\srr\()_user_rst_start, .Linterrupt_return_\srr
.balign IFETCH_ALIGN_BYTES
interrupt_return_\srr\()_kernel:
_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl interrupt_exit_kernel_prepare
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(interrupt_exit_kernel_prepare)
std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
.Linterrupt_return_\srr\()_kernel_rst_start:
ld r11,SOFTE(r1)
cmpwi r11,IRQS_ENABLED
stb r11,PACAIRQSOFTMASK(r13)
- bne 1f
+ beq .Linterrupt_return_\srr\()_soft_enabled
+
+ /*
+ * Returning to soft-disabled context.
+ * Check if a MUST_HARD_MASK interrupt has become pending, in which
+ * case we need to disable MSR[EE] in the return context.
+ *
+ * The MSR[EE] check catches among other things the short incoherency
+ * in hard_irq_disable() between clearing MSR[EE] and setting
+ * PACA_IRQ_HARD_DIS.
+ */
+ ld r12,_MSR(r1)
+ andi. r10,r12,MSR_EE
+ beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled
+ lbz r11,PACAIRQHAPPENED(r13)
+ andi. r10,r11,PACA_IRQ_MUST_HARD_MASK
+ bne 1f // HARD_MASK is pending
+ // No HARD_MASK pending, clear possible HARD_DIS set by interrupt
+ andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l
+ stb r11,PACAIRQHAPPENED(r13)
+ b .Lfast_kernel_interrupt_return_\srr\()
+
+
+1: /* Must clear MSR_EE from _MSR */
+#ifdef CONFIG_PPC_BOOK3S
+ li r10,0
+ /* Clear valid before changing _MSR */
+ .ifc \srr,srr
+ stb r10,PACASRR_VALID(r13)
+ .else
+ stb r10,PACAHSRR_VALID(r13)
+ .endif
+#endif
+ xori r12,r12,MSR_EE
+ std r12,_MSR(r1)
+ b .Lfast_kernel_interrupt_return_\srr\()
+
+.Linterrupt_return_\srr\()_soft_enabled:
+ /*
+ * In the soft-enabled case, need to double-check that we have no
+ * pending interrupts that might have come in before we reached the
+ * restart section of code, and restart the exit so those can be
+ * handled.
+ *
+ * If there are none, it is be possible that the interrupt still
+ * has PACA_IRQ_HARD_DIS set, which needs to be cleared for the
+ * interrupted context. This clear will not clobber a new pending
+ * interrupt coming in, because we're in the restart section, so
+ * such would return to the restart location.
+ */
#ifdef CONFIG_PPC_BOOK3S
lbz r11,PACAIRQHAPPENED(r13)
andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l
bne- interrupt_return_\srr\()_kernel_restart
#endif
li r11,0
- stb r11,PACAIRQHAPPENED(r13) # clear out possible HARD_DIS
-1:
+ stb r11,PACAIRQHAPPENED(r13) // clear the possible HARD_DIS
.Lfast_kernel_interrupt_return_\srr\():
+ SANITIZE_RESTORE_NVGPRS()
cmpdi cr1,r3,0
#ifdef CONFIG_PPC_BOOK3S
.ifc \srr,srr
@@ -619,10 +652,10 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
mtspr SPRN_XER,r5
/*
- * Leaving a stale exception_marker on the stack can confuse
+ * Leaving a stale STACK_FRAME_REGS_MARKER on the stack can confuse
* the reliable stack unwinder later on. Clear it.
*/
- std r0,STACK_FRAME_OVERHEAD-16(r1)
+ std r0,STACK_INT_FRAME_MARKER(r1)
REST_GPRS(2, 5, r1)
@@ -668,11 +701,11 @@ interrupt_return_\srr\()_kernel_restart:
_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel_restart)
GET_PACA(r13)
ld r1,PACA_EXIT_SAVE_R1(r13)
- ld r2,PACATOC(r13)
- addi r3,r1,STACK_FRAME_OVERHEAD
+ LOAD_PACA_TOC()
+ addi r3,r1,STACK_INT_FRAME_REGS
li r11,IRQS_ALL_DISABLED
stb r11,PACAIRQSOFTMASK(r13)
- bl interrupt_exit_kernel_restart
+ bl CFUNC(interrupt_exit_kernel_restart)
std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
b .Linterrupt_return_\srr\()_kernel_rst_start
1:
@@ -694,21 +727,20 @@ DEFINE_FIXED_SYMBOL(__end_soft_masked, text)
#ifdef CONFIG_PPC_BOOK3S
_GLOBAL(ret_from_fork_scv)
- bl schedule_tail
- REST_NVGPRS(r1)
+ bl CFUNC(schedule_tail)
+ HANDLER_RESTORE_NVGPRS()
li r3,0 /* fork() return value */
b .Lsyscall_vectored_common_exit
#endif
_GLOBAL(ret_from_fork)
- bl schedule_tail
- REST_NVGPRS(r1)
+ bl CFUNC(schedule_tail)
+ HANDLER_RESTORE_NVGPRS()
li r3,0 /* fork() return value */
b .Lsyscall_exit
-_GLOBAL(ret_from_kernel_thread)
- bl schedule_tail
- REST_NVGPRS(r1)
+_GLOBAL(ret_from_kernel_user_thread)
+ bl CFUNC(schedule_tail)
mtctr r14
mr r3,r15
#ifdef CONFIG_PPC64_ELF_ABI_V2
@@ -716,4 +748,25 @@ _GLOBAL(ret_from_kernel_thread)
#endif
bctrl
li r3,0
+ /*
+ * It does not matter whether this returns via the scv or sc path
+ * because it returns as execve() and therefore has no calling ABI
+ * (i.e., it sets registers according to the exec()ed entry point).
+ */
b .Lsyscall_exit
+
+_GLOBAL(start_kernel_thread)
+ bl CFUNC(schedule_tail)
+ mtctr r14
+ mr r3,r15
+#ifdef CONFIG_PPC64_ELF_ABI_V2
+ mr r12,r14
+#endif
+ bctrl
+ /*
+ * This must not return. We actually want to BUG here, not WARN,
+ * because BUG will exit the process which is what the kernel thread
+ * should have done, which may give some hope of continuing.
+ */
+100: trap
+ EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
deleted file mode 100644
index c877f074d174..000000000000
--- a/arch/powerpc/kernel/io-workarounds.c
+++ /dev/null
@@ -1,197 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Support PCI IO workaround
- *
- * Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>
- * IBM, Corp.
- * (C) Copyright 2007-2008 TOSHIBA CORPORATION
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/sched/mm.h> /* for init_mm */
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/ppc-pci.h>
-#include <asm/io-workarounds.h>
-#include <asm/pte-walk.h>
-
-
-#define IOWA_MAX_BUS 8
-
-static struct iowa_bus iowa_busses[IOWA_MAX_BUS];
-static unsigned int iowa_bus_count;
-
-static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
-{
- int i, j;
- struct resource *res;
- unsigned long vstart, vend;
-
- for (i = 0; i < iowa_bus_count; i++) {
- struct iowa_bus *bus = &iowa_busses[i];
- struct pci_controller *phb = bus->phb;
-
- if (vaddr) {
- vstart = (unsigned long)phb->io_base_virt;
- vend = vstart + phb->pci_io_size - 1;
- if ((vaddr >= vstart) && (vaddr <= vend))
- return bus;
- }
-
- if (paddr)
- for (j = 0; j < 3; j++) {
- res = &phb->mem_resources[j];
- if (paddr >= res->start && paddr <= res->end)
- return bus;
- }
- }
-
- return NULL;
-}
-
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
-{
- struct iowa_bus *bus;
- int token;
-
- token = PCI_GET_ADDR_TOKEN(addr);
-
- if (token && token <= iowa_bus_count)
- bus = &iowa_busses[token - 1];
- else {
- unsigned long vaddr, paddr;
-
- vaddr = (unsigned long)PCI_FIX_ADDR(addr);
- if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
- return NULL;
-
- paddr = ppc_find_vmap_phys(vaddr);
-
- bus = iowa_pci_find(vaddr, paddr);
-
- if (bus == NULL)
- return NULL;
- }
-
- return bus;
-}
-#else /* CONFIG_PPC_INDIRECT_MMIO */
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
-{
- return NULL;
-}
-#endif /* !CONFIG_PPC_INDIRECT_MMIO */
-
-#ifdef CONFIG_PPC_INDIRECT_PIO
-struct iowa_bus *iowa_pio_find_bus(unsigned long port)
-{
- unsigned long vaddr = (unsigned long)pci_io_base + port;
- return iowa_pci_find(vaddr, 0);
-}
-#else
-struct iowa_bus *iowa_pio_find_bus(unsigned long port)
-{
- return NULL;
-}
-#endif
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \
-static ret iowa_##name at \
-{ \
- struct iowa_bus *bus; \
- bus = iowa_##space##_find_bus(aa); \
- if (bus && bus->ops && bus->ops->name) \
- return bus->ops->name al; \
- return __do_##name al; \
-}
-
-#define DEF_PCI_AC_NORET(name, at, al, space, aa) \
-static void iowa_##name at \
-{ \
- struct iowa_bus *bus; \
- bus = iowa_##space##_find_bus(aa); \
- if (bus && bus->ops && bus->ops->name) { \
- bus->ops->name al; \
- return; \
- } \
- __do_##name al; \
-}
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-static const struct ppc_pci_io iowa_pci_io = {
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) .name = iowa_##name,
-#define DEF_PCI_AC_NORET(name, at, al, space, aa) .name = iowa_##name,
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-};
-
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
- pgprot_t prot, void *caller)
-{
- struct iowa_bus *bus;
- void __iomem *res = __ioremap_caller(addr, size, prot, caller);
- int busno;
-
- bus = iowa_pci_find(0, (unsigned long)addr);
- if (bus != NULL) {
- busno = bus - iowa_busses;
- PCI_SET_ADDR_TOKEN(res, busno + 1);
- }
- return res;
-}
-#endif /* !CONFIG_PPC_INDIRECT_MMIO */
-
-bool io_workaround_inited;
-
-/* Enable IO workaround */
-static void io_workaround_init(void)
-{
- if (io_workaround_inited)
- return;
- ppc_pci_io = iowa_pci_io;
- io_workaround_inited = true;
-}
-
-/* Register new bus to support workaround */
-void iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops,
- int (*initfunc)(struct iowa_bus *, void *), void *data)
-{
- struct iowa_bus *bus;
- struct device_node *np = phb->dn;
-
- io_workaround_init();
-
- if (iowa_bus_count >= IOWA_MAX_BUS) {
- pr_err("IOWA:Too many pci bridges, "
- "workarounds disabled for %pOF\n", np);
- return;
- }
-
- bus = &iowa_busses[iowa_bus_count];
- bus->phb = phb;
- bus->ops = ops;
- bus->private = data;
-
- if (initfunc)
- if ((*initfunc)(bus, data))
- return;
-
- iowa_bus_count++;
-
- pr_debug("IOWA:[%d]Add bus, %pOF.\n", iowa_bus_count-1, np);
-}
-
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 2f29b7d432de..bcc201c01514 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -31,13 +31,14 @@ void _insb(const volatile u8 __iomem *port, void *buf, long count)
if (unlikely(count <= 0))
return;
- asm volatile("sync");
+
+ mb();
do {
- tmp = *port;
+ tmp = *(const volatile u8 __force *)port;
eieio();
*tbuf++ = tmp;
} while (--count != 0);
- asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+ data_barrier(tmp);
}
EXPORT_SYMBOL(_insb);
@@ -47,75 +48,80 @@ void _outsb(volatile u8 __iomem *port, const void *buf, long count)
if (unlikely(count <= 0))
return;
- asm volatile("sync");
+
+ mb();
do {
- *port = *tbuf++;
+ *(volatile u8 __force *)port = *tbuf++;
} while (--count != 0);
- asm volatile("sync");
+ mb();
}
EXPORT_SYMBOL(_outsb);
-void _insw_ns(const volatile u16 __iomem *port, void *buf, long count)
+void _insw(const volatile u16 __iomem *port, void *buf, long count)
{
u16 *tbuf = buf;
u16 tmp;
if (unlikely(count <= 0))
return;
- asm volatile("sync");
+
+ mb();
do {
- tmp = *port;
+ tmp = *(const volatile u16 __force *)port;
eieio();
*tbuf++ = tmp;
} while (--count != 0);
- asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+ data_barrier(tmp);
}
-EXPORT_SYMBOL(_insw_ns);
+EXPORT_SYMBOL(_insw);
-void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count)
+void _outsw(volatile u16 __iomem *port, const void *buf, long count)
{
const u16 *tbuf = buf;
if (unlikely(count <= 0))
return;
- asm volatile("sync");
+
+ mb();
do {
- *port = *tbuf++;
+ *(volatile u16 __force *)port = *tbuf++;
} while (--count != 0);
- asm volatile("sync");
+ mb();
}
-EXPORT_SYMBOL(_outsw_ns);
+EXPORT_SYMBOL(_outsw);
-void _insl_ns(const volatile u32 __iomem *port, void *buf, long count)
+void _insl(const volatile u32 __iomem *port, void *buf, long count)
{
u32 *tbuf = buf;
u32 tmp;
if (unlikely(count <= 0))
return;
- asm volatile("sync");
+
+ mb();
do {
- tmp = *port;
+ tmp = *(const volatile u32 __force *)port;
eieio();
*tbuf++ = tmp;
} while (--count != 0);
- asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+ data_barrier(tmp);
}
-EXPORT_SYMBOL(_insl_ns);
+EXPORT_SYMBOL(_insl);
-void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count)
+void _outsl(volatile u32 __iomem *port, const void *buf, long count)
{
const u32 *tbuf = buf;
if (unlikely(count <= 0))
return;
- asm volatile("sync");
+
+ mb();
do {
- *port = *tbuf++;
+ *(volatile u32 __force *)port = *tbuf++;
} while (--count != 0);
- asm volatile("sync");
+ mb();
}
-EXPORT_SYMBOL(_outsl_ns);
+EXPORT_SYMBOL(_outsl);
#define IO_CHECK_ALIGN(v,a) ((((unsigned long)(v)) & ((a) - 1)) == 0)
@@ -127,7 +133,7 @@ _memset_io(volatile void __iomem *addr, int c, unsigned long n)
lc |= lc << 8;
lc |= lc << 16;
- __asm__ __volatile__ ("sync" : : : "memory");
+ mb();
while(n && !IO_CHECK_ALIGN(p, 4)) {
*((volatile u8 *)p) = c;
p++;
@@ -143,7 +149,7 @@ _memset_io(volatile void __iomem *addr, int c, unsigned long n)
p++;
n--;
}
- __asm__ __volatile__ ("sync" : : : "memory");
+ mb();
}
EXPORT_SYMBOL(_memset_io);
@@ -152,7 +158,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src,
{
void *vsrc = (void __force *) src;
- __asm__ __volatile__ ("sync" : : : "memory");
+ mb();
while(n && (!IO_CHECK_ALIGN(vsrc, 4) || !IO_CHECK_ALIGN(dest, 4))) {
*((u8 *)dest) = *((volatile u8 *)vsrc);
eieio();
@@ -174,7 +180,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src,
dest++;
n--;
}
- __asm__ __volatile__ ("sync" : : : "memory");
+ mb();
}
EXPORT_SYMBOL(_memcpy_fromio);
@@ -182,7 +188,7 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
{
void *vdest = (void __force *) dest;
- __asm__ __volatile__ ("sync" : : : "memory");
+ mb();
while(n && (!IO_CHECK_ALIGN(vdest, 4) || !IO_CHECK_ALIGN(src, 4))) {
*((volatile u8 *)vdest) = *((u8 *)src);
src++;
@@ -201,6 +207,6 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
vdest++;
n--;
}
- __asm__ __volatile__ ("sync" : : : "memory");
+ mb();
}
EXPORT_SYMBOL(_memcpy_toio);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 7e56ddb3e0b9..244eb4857e7f 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -16,6 +16,7 @@
#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/string.h>
+#include <linux/string_choices.h>
#include <linux/dma-mapping.h>
#include <linux/bitmap.h>
#include <linux/iommu-helper.h>
@@ -26,6 +27,7 @@
#include <linux/iommu.h>
#include <linux/sched.h>
#include <linux/debugfs.h>
+#include <linux/vmalloc.h>
#include <asm/io.h>
#include <asm/iommu.h>
#include <asm/pci-bridge.h>
@@ -35,6 +37,7 @@
#include <asm/vio.h>
#include <asm/tce.h>
#include <asm/mmu_context.h>
+#include <asm/ppc-pci.h>
#define DBG(...)
@@ -67,11 +70,9 @@ static void iommu_debugfs_add(struct iommu_table *tbl)
static void iommu_debugfs_del(struct iommu_table *tbl)
{
char name[10];
- struct dentry *liobn_entry;
sprintf(name, "%08lx", tbl->it_index);
- liobn_entry = debugfs_lookup(name, iommu_debugfs_dir);
- debugfs_remove(liobn_entry);
+ debugfs_lookup_and_remove(name, iommu_debugfs_dir);
}
#else
static void iommu_debugfs_add(struct iommu_table *tbl){}
@@ -173,17 +174,28 @@ static int fail_iommu_bus_notify(struct notifier_block *nb,
return 0;
}
-static struct notifier_block fail_iommu_bus_notifier = {
+/*
+ * PCI and VIO buses need separate notifier_block structs, since they're linked
+ * list nodes. Sharing a notifier_block would mean that any notifiers later
+ * registered for PCI buses would also get called by VIO buses and vice versa.
+ */
+static struct notifier_block fail_iommu_pci_bus_notifier = {
+ .notifier_call = fail_iommu_bus_notify
+};
+
+#ifdef CONFIG_IBMVIO
+static struct notifier_block fail_iommu_vio_bus_notifier = {
.notifier_call = fail_iommu_bus_notify
};
+#endif
static int __init fail_iommu_setup(void)
{
#ifdef CONFIG_PCI
- bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier);
+ bus_register_notifier(&pci_bus_type, &fail_iommu_pci_bus_notifier);
#endif
#ifdef CONFIG_IBMVIO
- bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier);
+ bus_register_notifier(&vio_bus_type, &fail_iommu_vio_bus_notifier);
#endif
return 0;
@@ -519,7 +531,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
/* Convert entry to a dma_addr_t */
entry += tbl->it_offset;
dma_addr = entry << tbl->it_page_shift;
- dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl));
+ dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl));
DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n",
npages, entry, dma_addr);
@@ -632,7 +644,7 @@ void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
tbl->it_ops->flush(tbl);
}
-static void iommu_table_clear(struct iommu_table *tbl)
+void iommu_table_clear(struct iommu_table *tbl)
{
/*
* In case of firmware assisted dump system goes through clean
@@ -673,10 +685,10 @@ static void iommu_table_clear(struct iommu_table *tbl)
#endif
}
-static void iommu_table_reserve_pages(struct iommu_table *tbl,
+void iommu_table_reserve_pages(struct iommu_table *tbl,
unsigned long res_start, unsigned long res_end)
{
- int i;
+ unsigned long i;
WARN_ON_ONCE(res_end < res_start);
/*
@@ -758,8 +770,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
iommu_table_clear(tbl);
if (!welcomed) {
- printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n",
- novmerge ? "disabled" : "enabled");
+ pr_info("IOMMU table initialized, virtual merging %s\n",
+ str_disabled_enabled(novmerge));
welcomed = 1;
}
@@ -775,6 +787,11 @@ bool iommu_table_in_use(struct iommu_table *tbl)
/* ignore reserved bit0 */
if (tbl->it_offset == 0)
start = 1;
+
+ /* Simple case with no reserved MMIO32 region */
+ if (!tbl->it_reserved_start && !tbl->it_reserved_end)
+ return find_next_bit(tbl->it_map, tbl->it_size, start) != tbl->it_size;
+
end = tbl->it_reserved_start - tbl->it_offset;
if (find_next_bit(tbl->it_map, end, start) != end)
return true;
@@ -901,6 +918,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
unsigned int order;
unsigned int nio_pages, io_order;
struct page *page;
+ int tcesize = (1 << tbl->it_page_shift);
size = PAGE_ALIGN(size);
order = get_order(size);
@@ -927,7 +945,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
memset(ret, 0, size);
/* Set up tces to cover the allocated range */
- nio_pages = size >> tbl->it_page_shift;
+ nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
+
io_order = get_iommu_order(size, tbl);
mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
mask >> tbl->it_page_shift, io_order, 0);
@@ -935,7 +954,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
free_pages((unsigned long)ret, order);
return NULL;
}
- *dma_handle = mapping;
+
+ *dma_handle = mapping | ((u64)ret & (tcesize - 1));
return ret;
}
@@ -946,7 +966,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
unsigned int nio_pages;
size = PAGE_ALIGN(size);
- nio_pages = size >> tbl->it_page_shift;
+ nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
iommu_free(tbl, dma_handle, nio_pages);
size = PAGE_ALIGN(size);
free_pages((unsigned long)vaddr, get_order(size));
@@ -969,6 +989,23 @@ unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir)
EXPORT_SYMBOL_GPL(iommu_direction_to_tce_perm);
#ifdef CONFIG_IOMMU_API
+
+int dev_has_iommu_table(struct device *dev, void *data)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct pci_dev **ppdev = data;
+
+ if (!dev)
+ return 0;
+
+ if (device_iommu_mapped(dev)) {
+ *ppdev = pdev;
+ return 1;
+ }
+
+ return 0;
+}
+
/*
* SPAPR TCE API
*/
@@ -1056,10 +1093,10 @@ int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
}
EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
-extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
- struct iommu_table *tbl,
- unsigned long entry, unsigned long *hpa,
- enum dma_data_direction *direction)
+long iommu_tce_xchg_no_kill(struct mm_struct *mm,
+ struct iommu_table *tbl,
+ unsigned long entry, unsigned long *hpa,
+ enum dma_data_direction *direction)
{
long ret;
unsigned long size = 0;
@@ -1083,59 +1120,6 @@ void iommu_tce_kill(struct iommu_table *tbl,
}
EXPORT_SYMBOL_GPL(iommu_tce_kill);
-int iommu_take_ownership(struct iommu_table *tbl)
-{
- unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
- int ret = 0;
-
- /*
- * VFIO does not control TCE entries allocation and the guest
- * can write new TCEs on top of existing ones so iommu_tce_build()
- * must be able to release old pages. This functionality
- * requires exchange() callback defined so if it is not
- * implemented, we disallow taking ownership over the table.
- */
- if (!tbl->it_ops->xchg_no_kill)
- return -EINVAL;
-
- spin_lock_irqsave(&tbl->large_pool.lock, flags);
- for (i = 0; i < tbl->nr_pools; i++)
- spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
- if (iommu_table_in_use(tbl)) {
- pr_err("iommu_tce: it_map is not empty");
- ret = -EBUSY;
- } else {
- memset(tbl->it_map, 0xff, sz);
- }
-
- for (i = 0; i < tbl->nr_pools; i++)
- spin_unlock(&tbl->pools[i].lock);
- spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_take_ownership);
-
-void iommu_release_ownership(struct iommu_table *tbl)
-{
- unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
-
- spin_lock_irqsave(&tbl->large_pool.lock, flags);
- for (i = 0; i < tbl->nr_pools; i++)
- spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
- memset(tbl->it_map, 0, sz);
-
- iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
- tbl->it_reserved_end);
-
- for (i = 0; i < tbl->nr_pools; i++)
- spin_unlock(&tbl->pools[i].lock);
- spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-}
-EXPORT_SYMBOL_GPL(iommu_release_ownership);
-
int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
{
/*
@@ -1155,25 +1139,179 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
pr_debug("%s: Adding %s to iommu group %d\n",
__func__, dev_name(dev), iommu_group_id(table_group->group));
-
- return iommu_group_add_device(table_group->group, dev);
+ /*
+ * This is still not adding devices via the IOMMU bus notifier because
+ * of pcibios_init() from arch/powerpc/kernel/pci_64.c which calls
+ * pcibios_scan_phb() first (and this guy adds devices and triggers
+ * the notifier) and only then it calls pci_bus_add_devices() which
+ * configures DMA for buses which also creates PEs and IOMMU groups.
+ */
+ return iommu_probe_device(dev);
}
EXPORT_SYMBOL_GPL(iommu_add_device);
-void iommu_del_device(struct device *dev)
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+/*
+ * A simple iommu_ops to allow less cruft in generic VFIO code.
+ */
+static int
+spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
+ struct device *dev)
{
+ struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+ struct iommu_table_group *table_group;
+ struct iommu_group *grp;
+
+ /* At first attach the ownership is already set */
+ if (!domain)
+ return 0;
+
+ grp = iommu_group_get(dev);
+ table_group = iommu_group_get_iommudata(grp);
/*
- * Some devices might not have IOMMU table and group
- * and we needn't detach them from the associated
- * IOMMU groups
+ * The domain being set to PLATFORM from earlier
+ * BLOCKED. The table_group ownership has to be released.
*/
- if (!device_iommu_mapped(dev)) {
- pr_debug("iommu_tce: skipping device %s with no tbl\n",
- dev_name(dev));
- return;
+ table_group->ops->release_ownership(table_group, dev);
+ iommu_group_put(grp);
+
+ return 0;
+}
+
+static const struct iommu_domain_ops spapr_tce_platform_domain_ops = {
+ .attach_dev = spapr_tce_platform_iommu_attach_dev,
+};
+
+static struct iommu_domain spapr_tce_platform_domain = {
+ .type = IOMMU_DOMAIN_PLATFORM,
+ .ops = &spapr_tce_platform_domain_ops,
+};
+
+static int
+spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
+ struct device *dev)
+{
+ struct iommu_group *grp = iommu_group_get(dev);
+ struct iommu_table_group *table_group;
+ int ret = -EINVAL;
+
+ /*
+ * FIXME: SPAPR mixes blocked and platform behaviors, the blocked domain
+ * also sets the dma_api ops
+ */
+ table_group = iommu_group_get_iommudata(grp);
+ ret = table_group->ops->take_ownership(table_group, dev);
+ iommu_group_put(grp);
+
+ return ret;
+}
+
+static const struct iommu_domain_ops spapr_tce_blocked_domain_ops = {
+ .attach_dev = spapr_tce_blocked_iommu_attach_dev,
+};
+
+static struct iommu_domain spapr_tce_blocked_domain = {
+ .type = IOMMU_DOMAIN_BLOCKED,
+ .ops = &spapr_tce_blocked_domain_ops,
+};
+
+static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+ switch (cap) {
+ case IOMMU_CAP_CACHE_COHERENCY:
+ return true;
+ default:
+ break;
}
- iommu_group_remove_device(dev);
+ return false;
}
-EXPORT_SYMBOL_GPL(iommu_del_device);
+
+static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
+{
+ struct pci_dev *pdev;
+ struct pci_controller *hose;
+
+ if (!dev_is_pci(dev))
+ return ERR_PTR(-ENODEV);
+
+ pdev = to_pci_dev(dev);
+ hose = pdev->bus->sysdata;
+
+ return &hose->iommu;
+}
+
+static void spapr_tce_iommu_release_device(struct device *dev)
+{
+}
+
+static struct iommu_group *spapr_tce_iommu_device_group(struct device *dev)
+{
+ struct pci_controller *hose;
+ struct pci_dev *pdev;
+
+ pdev = to_pci_dev(dev);
+ hose = pdev->bus->sysdata;
+
+ if (!hose->controller_ops.device_group)
+ return ERR_PTR(-ENOENT);
+
+ return hose->controller_ops.device_group(hose, pdev);
+}
+
+static const struct iommu_ops spapr_tce_iommu_ops = {
+ .default_domain = &spapr_tce_platform_domain,
+ .blocked_domain = &spapr_tce_blocked_domain,
+ .capable = spapr_tce_iommu_capable,
+ .probe_device = spapr_tce_iommu_probe_device,
+ .release_device = spapr_tce_iommu_release_device,
+ .device_group = spapr_tce_iommu_device_group,
+};
+
+static struct attribute *spapr_tce_iommu_attrs[] = {
+ NULL,
+};
+
+static struct attribute_group spapr_tce_iommu_group = {
+ .name = "spapr-tce-iommu",
+ .attrs = spapr_tce_iommu_attrs,
+};
+
+static const struct attribute_group *spapr_tce_iommu_groups[] = {
+ &spapr_tce_iommu_group,
+ NULL,
+};
+
+void ppc_iommu_register_device(struct pci_controller *phb)
+{
+ iommu_device_sysfs_add(&phb->iommu, phb->parent,
+ spapr_tce_iommu_groups, "iommu-phb%04x",
+ phb->global_number);
+ iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops,
+ phb->parent);
+}
+
+void ppc_iommu_unregister_device(struct pci_controller *phb)
+{
+ iommu_device_unregister(&phb->iommu);
+ iommu_device_sysfs_remove(&phb->iommu);
+}
+
+/*
+ * This registers IOMMU devices of PHBs. This needs to happen
+ * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
+ * before subsys_initcall(iommu_subsys_init).
+ */
+static int __init spapr_tce_setup_phb_iommus_initcall(void)
+{
+ struct pci_controller *hose;
+
+ list_for_each_entry(hose, &hose_list, list_node) {
+ ppc_iommu_register_device(hose);
+ }
+ return 0;
+}
+postcore_initcall_sync(spapr_tce_setup_phb_iommus_initcall);
+#endif
+
#endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index dd09919c3c66..a0e8b998c9b5 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -65,13 +65,8 @@
#include <asm/smp.h>
#include <asm/hw_irq.h>
#include <asm/softirq_stack.h>
+#include <asm/ppc_asm.h>
-#ifdef CONFIG_PPC64
-#include <asm/paca.h>
-#include <asm/firmware.h>
-#include <asm/lv1call.h>
-#include <asm/dbell.h>
-#endif
#define CREATE_TRACE_POINTS
#include <asm/trace.h>
#include <asm/cpu_has_feature.h>
@@ -88,480 +83,75 @@ u32 tau_interrupts(unsigned long cpu);
#endif
#endif /* CONFIG_PPC32 */
-#ifdef CONFIG_PPC64
-
-int distribute_irqs = 1;
-
-static inline notrace unsigned long get_irq_happened(void)
-{
- unsigned long happened;
-
- __asm__ __volatile__("lbz %0,%1(13)"
- : "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened)));
-
- return happened;
-}
-
-void replay_soft_interrupts(void)
-{
- struct pt_regs regs;
-
- /*
- * Be careful here, calling these interrupt handlers can cause
- * softirqs to be raised, which they may run when calling irq_exit,
- * which will cause local_irq_enable() to be run, which can then
- * recurse into this function. Don't keep any state across
- * interrupt handler calls which may change underneath us.
- *
- * We use local_paca rather than get_paca() to avoid all the
- * debug_smp_processor_id() business in this low level function.
- */
-
- ppc_save_regs(&regs);
- regs.softe = IRQS_ENABLED;
- regs.msr |= MSR_EE;
-
-again:
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(mfmsr() & MSR_EE);
-
- /*
- * Force the delivery of pending soft-disabled interrupts on PS3.
- * Any HV call will have this side effect.
- */
- if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
- u64 tmp, tmp2;
- lv1_get_version_info(&tmp, &tmp2);
- }
-
- /*
- * Check if an hypervisor Maintenance interrupt happened.
- * This is a higher priority interrupt than the others, so
- * replay it first.
- */
- if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) {
- local_paca->irq_happened &= ~PACA_IRQ_HMI;
- regs.trap = INTERRUPT_HMI;
- handle_hmi_exception(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- if (local_paca->irq_happened & PACA_IRQ_DEC) {
- local_paca->irq_happened &= ~PACA_IRQ_DEC;
- regs.trap = INTERRUPT_DECREMENTER;
- timer_interrupt(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- if (local_paca->irq_happened & PACA_IRQ_EE) {
- local_paca->irq_happened &= ~PACA_IRQ_EE;
- regs.trap = INTERRUPT_EXTERNAL;
- do_IRQ(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) {
- local_paca->irq_happened &= ~PACA_IRQ_DBELL;
- regs.trap = INTERRUPT_DOORBELL;
- doorbell_exception(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- /* Book3E does not support soft-masking PMI interrupts */
- if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) {
- local_paca->irq_happened &= ~PACA_IRQ_PMI;
- regs.trap = INTERRUPT_PERFMON;
- performance_monitor_exception(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) {
- /*
- * We are responding to the next interrupt, so interrupt-off
- * latencies should be reset here.
- */
- trace_hardirqs_on();
- trace_hardirqs_off();
- goto again;
- }
-}
-
-#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP)
-static inline void replay_soft_interrupts_irqrestore(void)
-{
- unsigned long kuap_state = get_kuap();
-
- /*
- * Check if anything calls local_irq_enable/restore() when KUAP is
- * disabled (user access enabled). We handle that case here by saving
- * and re-locking AMR but we shouldn't get here in the first place,
- * hence the warning.
- */
- kuap_assert_locked();
-
- if (kuap_state != AMR_KUAP_BLOCKED)
- set_kuap(AMR_KUAP_BLOCKED);
-
- replay_soft_interrupts();
-
- if (kuap_state != AMR_KUAP_BLOCKED)
- set_kuap(kuap_state);
-}
-#else
-#define replay_soft_interrupts_irqrestore() replay_soft_interrupts()
-#endif
-
-notrace void arch_local_irq_restore(unsigned long mask)
-{
- unsigned char irq_happened;
-
- /* Write the new soft-enabled value if it is a disable */
- if (mask) {
- irq_soft_mask_set(mask);
- return;
- }
-
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(in_nmi() || in_hardirq());
-
- /*
- * After the stb, interrupts are unmasked and there are no interrupts
- * pending replay. The restart sequence makes this atomic with
- * respect to soft-masked interrupts. If this was just a simple code
- * sequence, a soft-masked interrupt could become pending right after
- * the comparison and before the stb.
- *
- * This allows interrupts to be unmasked without hard disabling, and
- * also without new hard interrupts coming in ahead of pending ones.
- */
- asm_volatile_goto(
-"1: \n"
-" lbz 9,%0(13) \n"
-" cmpwi 9,0 \n"
-" bne %l[happened] \n"
-" stb 9,%1(13) \n"
-"2: \n"
- RESTART_TABLE(1b, 2b, 1b)
- : : "i" (offsetof(struct paca_struct, irq_happened)),
- "i" (offsetof(struct paca_struct, irq_soft_mask))
- : "cr0", "r9"
- : happened);
-
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(!(mfmsr() & MSR_EE));
-
- return;
-
-happened:
- irq_happened = get_irq_happened();
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(!irq_happened);
-
- if (irq_happened == PACA_IRQ_HARD_DIS) {
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(mfmsr() & MSR_EE);
- irq_soft_mask_set(IRQS_ENABLED);
- local_paca->irq_happened = 0;
- __hard_irq_enable();
- return;
- }
-
- /* Have interrupts to replay, need to hard disable first */
- if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
- if (!(mfmsr() & MSR_EE)) {
- /*
- * An interrupt could have come in and cleared
- * MSR[EE] and set IRQ_HARD_DIS, so check
- * IRQ_HARD_DIS again and warn if it is still
- * clear.
- */
- irq_happened = get_irq_happened();
- WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS));
- }
- }
- __hard_irq_disable();
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
- } else {
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
- if (WARN_ON_ONCE(mfmsr() & MSR_EE))
- __hard_irq_disable();
- }
- }
-
- /*
- * Disable preempt here, so that the below preempt_enable will
- * perform resched if required (a replayed interrupt may set
- * need_resched).
- */
- preempt_disable();
- irq_soft_mask_set(IRQS_ALL_DISABLED);
- trace_hardirqs_off();
-
- replay_soft_interrupts_irqrestore();
- local_paca->irq_happened = 0;
-
- trace_hardirqs_on();
- irq_soft_mask_set(IRQS_ENABLED);
- __hard_irq_enable();
- preempt_enable();
-}
-EXPORT_SYMBOL(arch_local_irq_restore);
-
-/*
- * This is a helper to use when about to go into idle low-power
- * when the latter has the side effect of re-enabling interrupts
- * (such as calling H_CEDE under pHyp).
- *
- * You call this function with interrupts soft-disabled (this is
- * already the case when ppc_md.power_save is called). The function
- * will return whether to enter power save or just return.
- *
- * In the former case, it will have notified lockdep of interrupts
- * being re-enabled and generally sanitized the lazy irq state,
- * and in the latter case it will leave with interrupts hard
- * disabled and marked as such, so the local_irq_enable() call
- * in arch_cpu_idle() will properly re-enable everything.
- */
-bool prep_irq_for_idle(void)
-{
- /*
- * First we need to hard disable to ensure no interrupt
- * occurs before we effectively enter the low power state
- */
- __hard_irq_disable();
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
-
- /*
- * If anything happened while we were soft-disabled,
- * we return now and do not enter the low power state.
- */
- if (lazy_irq_pending())
- return false;
-
- /* Tell lockdep we are about to re-enable */
- trace_hardirqs_on();
-
- /*
- * Mark interrupts as soft-enabled and clear the
- * PACA_IRQ_HARD_DIS from the pending mask since we
- * are about to hard enable as well as a side effect
- * of entering the low power state.
- */
- local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
- irq_soft_mask_set(IRQS_ENABLED);
-
- /* Tell the caller to enter the low power state */
- return true;
-}
-
-#ifdef CONFIG_PPC_BOOK3S
-/*
- * This is for idle sequences that return with IRQs off, but the
- * idle state itself wakes on interrupt. Tell the irq tracer that
- * IRQs are enabled for the duration of idle so it does not get long
- * off times. Must be paired with fini_irq_for_idle_irqsoff.
- */
-bool prep_irq_for_idle_irqsoff(void)
-{
- WARN_ON(!irqs_disabled());
-
- /*
- * First we need to hard disable to ensure no interrupt
- * occurs before we effectively enter the low power state
- */
- __hard_irq_disable();
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
-
- /*
- * If anything happened while we were soft-disabled,
- * we return now and do not enter the low power state.
- */
- if (lazy_irq_pending())
- return false;
-
- /* Tell lockdep we are about to re-enable */
- trace_hardirqs_on();
-
- return true;
-}
-
-/*
- * Take the SRR1 wakeup reason, index into this table to find the
- * appropriate irq_happened bit.
- *
- * Sytem reset exceptions taken in idle state also come through here,
- * but they are NMI interrupts so do not need to wait for IRQs to be
- * restored, and should be taken as early as practical. These are marked
- * with 0xff in the table. The Power ISA specifies 0100b as the system
- * reset interrupt reason.
- */
-#define IRQ_SYSTEM_RESET 0xff
-
-static const u8 srr1_to_lazyirq[0x10] = {
- 0, 0, 0,
- PACA_IRQ_DBELL,
- IRQ_SYSTEM_RESET,
- PACA_IRQ_DBELL,
- PACA_IRQ_DEC,
- 0,
- PACA_IRQ_EE,
- PACA_IRQ_EE,
- PACA_IRQ_HMI,
- 0, 0, 0, 0, 0 };
-
-void replay_system_reset(void)
-{
- struct pt_regs regs;
-
- ppc_save_regs(&regs);
- regs.trap = 0x100;
- get_paca()->in_nmi = 1;
- system_reset_exception(&regs);
- get_paca()->in_nmi = 0;
-}
-EXPORT_SYMBOL_GPL(replay_system_reset);
-
-void irq_set_pending_from_srr1(unsigned long srr1)
-{
- unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18;
- u8 reason = srr1_to_lazyirq[idx];
-
- /*
- * Take the system reset now, which is immediately after registers
- * are restored from idle. It's an NMI, so interrupts need not be
- * re-enabled before it is taken.
- */
- if (unlikely(reason == IRQ_SYSTEM_RESET)) {
- replay_system_reset();
- return;
- }
-
- if (reason == PACA_IRQ_DBELL) {
- /*
- * When doorbell triggers a system reset wakeup, the message
- * is not cleared, so if the doorbell interrupt is replayed
- * and the IPI handled, the doorbell interrupt would still
- * fire when EE is enabled.
- *
- * To avoid taking the superfluous doorbell interrupt,
- * execute a msgclr here before the interrupt is replayed.
- */
- ppc_msgclr(PPC_DBELL_MSGTYPE);
- }
-
- /*
- * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
- * so this can be called unconditionally with the SRR1 wake
- * reason as returned by the idle code, which uses 0 to mean no
- * interrupt.
- *
- * If a future CPU was to designate this as an interrupt reason,
- * then a new index for no interrupt must be assigned.
- */
- local_paca->irq_happened |= reason;
-}
-#endif /* CONFIG_PPC_BOOK3S */
-
-/*
- * Force a replay of the external interrupt handler on this CPU.
- */
-void force_external_irq_replay(void)
-{
- /*
- * This must only be called with interrupts soft-disabled,
- * the replay will happen when re-enabling.
- */
- WARN_ON(!arch_irqs_disabled());
-
- /*
- * Interrupts must always be hard disabled before irq_happened is
- * modified (to prevent lost update in case of interrupt between
- * load and store).
- */
- __hard_irq_disable();
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
-
- /* Indicate in the PACA that we have an interrupt to replay */
- local_paca->irq_happened |= PACA_IRQ_EE;
-}
-
-#endif /* CONFIG_PPC64 */
-
int arch_show_interrupts(struct seq_file *p, int prec)
{
int j;
#if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
if (tau_initialized) {
- seq_printf(p, "%*s: ", prec, "TAU");
+ seq_printf(p, "%*s:", prec, "TAU");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", tau_interrupts(j));
+ seq_put_decimal_ull_width(p, " ", tau_interrupts(j), 10);
seq_puts(p, " PowerPC Thermal Assist (cpu temp)\n");
}
#endif /* CONFIG_PPC32 && CONFIG_TAU_INT */
- seq_printf(p, "%*s: ", prec, "LOC");
+ seq_printf(p, "%*s:", prec, "LOC");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).timer_irqs_event, 10);
seq_printf(p, " Local timer interrupts for timer event device\n");
- seq_printf(p, "%*s: ", prec, "BCT");
+ seq_printf(p, "%*s:", prec, "BCT");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).broadcast_irqs_event);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).broadcast_irqs_event, 10);
seq_printf(p, " Broadcast timer interrupts for timer event device\n");
- seq_printf(p, "%*s: ", prec, "LOC");
+ seq_printf(p, "%*s:", prec, "LOC");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).timer_irqs_others, 10);
seq_printf(p, " Local timer interrupts for others\n");
- seq_printf(p, "%*s: ", prec, "SPU");
+ seq_printf(p, "%*s:", prec, "SPU");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).spurious_irqs, 10);
seq_printf(p, " Spurious interrupts\n");
- seq_printf(p, "%*s: ", prec, "PMI");
+ seq_printf(p, "%*s:", prec, "PMI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).pmu_irqs, 10);
seq_printf(p, " Performance monitoring interrupts\n");
- seq_printf(p, "%*s: ", prec, "MCE");
+ seq_printf(p, "%*s:", prec, "MCE");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).mce_exceptions, 10);
seq_printf(p, " Machine check exceptions\n");
#ifdef CONFIG_PPC_BOOK3S_64
if (cpu_has_feature(CPU_FTR_HVMODE)) {
- seq_printf(p, "%*s: ", prec, "HMI");
+ seq_printf(p, "%*s:", prec, "HMI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", paca_ptrs[j]->hmi_irqs);
+ seq_put_decimal_ull_width(p, " ", paca_ptrs[j]->hmi_irqs, 10);
seq_printf(p, " Hypervisor Maintenance Interrupts\n");
}
#endif
- seq_printf(p, "%*s: ", prec, "NMI");
+ seq_printf(p, "%*s:", prec, "NMI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).sreset_irqs);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).sreset_irqs, 10);
seq_printf(p, " System Reset interrupts\n");
#ifdef CONFIG_PPC_WATCHDOG
- seq_printf(p, "%*s: ", prec, "WDG");
+ seq_printf(p, "%*s:", prec, "WDG");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).soft_nmi_irqs);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).soft_nmi_irqs, 10);
seq_printf(p, " Watchdog soft-NMI interrupts\n");
#endif
#ifdef CONFIG_PPC_DOORBELL
if (cpu_has_feature(CPU_FTR_DBELL)) {
- seq_printf(p, "%*s: ", prec, "DBL");
+ seq_printf(p, "%*s:", prec, "DBL");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).doorbell_irqs);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).doorbell_irqs, 10);
seq_printf(p, " Doorbell interrupts\n");
}
#endif
@@ -595,33 +185,36 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
return sum;
}
-static inline void check_stack_overflow(void)
+static inline void check_stack_overflow(unsigned long sp)
{
- long sp;
-
if (!IS_ENABLED(CONFIG_DEBUG_STACKOVERFLOW))
return;
- sp = current_stack_pointer & (THREAD_SIZE - 1);
+ sp &= THREAD_SIZE - 1;
- /* check for stack overflow: is there less than 2KB free? */
- if (unlikely(sp < 2048)) {
+ /* check for stack overflow: is there less than 1/4th free? */
+ if (unlikely(sp < THREAD_SIZE / 4)) {
pr_err("do_IRQ: stack overflow: %ld\n", sp);
dump_stack();
}
}
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
static __always_inline void call_do_softirq(const void *sp)
{
/* Temporarily switch r1 to sp, call __do_softirq() then restore r1. */
asm volatile (
PPC_STLU " %%r1, %[offset](%[sp]) ;"
"mr %%r1, %[sp] ;"
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ "bl %[callee]@notoc ;"
+#else
"bl %[callee] ;"
+#endif
PPC_LL " %%r1, 0(%%r1) ;"
: // Outputs
: // Inputs
- [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD),
+ [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_MIN_SIZE),
[callee] "i" (__do_softirq)
: // Clobbers
"lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
@@ -629,37 +222,18 @@ static __always_inline void call_do_softirq(const void *sp)
"r11", "r12"
);
}
-
-static __always_inline void call_do_irq(struct pt_regs *regs, void *sp)
-{
- register unsigned long r3 asm("r3") = (unsigned long)regs;
-
- /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */
- asm volatile (
- PPC_STLU " %%r1, %[offset](%[sp]) ;"
- "mr %%r1, %[sp] ;"
- "bl %[callee] ;"
- PPC_LL " %%r1, 0(%%r1) ;"
- : // Outputs
- "+r" (r3)
- : // Inputs
- [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD),
- [callee] "i" (__do_irq)
- : // Clobbers
- "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
- "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10",
- "r11", "r12"
- );
-}
+#endif
DEFINE_STATIC_CALL_RET0(ppc_get_irq, *ppc_md.get_irq);
-void __do_irq(struct pt_regs *regs)
+static void __do_irq(struct pt_regs *regs, unsigned long oldsp)
{
unsigned int irq;
trace_irq_entry(regs);
+ check_stack_overflow(oldsp);
+
/*
* Query the platform PIC for the interrupt & ack it.
*
@@ -668,7 +242,7 @@ void __do_irq(struct pt_regs *regs)
irq = static_call(ppc_get_irq)();
/* We can hard enable interrupts now to allow perf interrupts */
- if (should_hard_irq_enable())
+ if (should_hard_irq_enable(regs))
do_hard_irq_enable();
/* And finally process it */
@@ -680,26 +254,47 @@ void __do_irq(struct pt_regs *regs)
trace_irq_exit(regs);
}
+static __always_inline void call_do_irq(struct pt_regs *regs, void *sp)
+{
+ register unsigned long r3 asm("r3") = (unsigned long)regs;
+
+ /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */
+ asm volatile (
+ PPC_STLU " %%r1, %[offset](%[sp]) ;"
+ "mr %%r4, %%r1 ;"
+ "mr %%r1, %[sp] ;"
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ "bl %[callee]@notoc ;"
+#else
+ "bl %[callee] ;"
+#endif
+ PPC_LL " %%r1, 0(%%r1) ;"
+ : // Outputs
+ "+r" (r3)
+ : // Inputs
+ [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_MIN_SIZE),
+ [callee] "i" (__do_irq)
+ : // Clobbers
+ "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
+ "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10",
+ "r11", "r12"
+ );
+}
+
void __do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- void *cursp, *irqsp, *sirqsp;
+ void *cursp, *irqsp;
/* Switch to the irq stack to handle this */
cursp = (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
irqsp = hardirq_ctx[raw_smp_processor_id()];
- sirqsp = softirq_ctx[raw_smp_processor_id()];
-
- check_stack_overflow();
- /* Already there ? */
- if (unlikely(cursp == irqsp || cursp == sirqsp)) {
- __do_irq(regs);
- set_irq_regs(old_regs);
- return;
- }
- /* Switch stack and call */
- call_do_irq(regs, irqsp);
+ /* Already there ? If not switch stack and call */
+ if (unlikely(cursp == irqsp))
+ __do_irq(regs, current_stack_pointer);
+ else
+ call_do_irq(regs, irqsp);
set_irq_regs(old_regs);
}
@@ -738,7 +333,7 @@ void __init init_IRQ(void)
static_call_update(ppc_get_irq, ppc_md.get_irq);
}
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
void *critirq_ctx[NR_CPUS] __read_mostly;
void *dbgirq_ctx[NR_CPUS] __read_mostly;
void *mcheckirq_ctx[NR_CPUS] __read_mostly;
@@ -747,10 +342,12 @@ void *mcheckirq_ctx[NR_CPUS] __read_mostly;
void *softirq_ctx[NR_CPUS] __read_mostly;
void *hardirq_ctx[NR_CPUS] __read_mostly;
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
void do_softirq_own_stack(void)
{
call_do_softirq(softirq_ctx[smp_processor_id()]);
}
+#endif
irq_hw_number_t virq_to_hw(unsigned int virq)
{
@@ -794,13 +391,3 @@ int irq_choose_cpu(const struct cpumask *mask)
return hard_smp_processor_id();
}
#endif
-
-#ifdef CONFIG_PPC64
-static int __init setup_noirqdistrib(char *str)
-{
- distribute_irqs = 0;
- return 1;
-}
-
-__setup("noirqdistrib", setup_noirqdistrib);
-#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c
new file mode 100644
index 000000000000..d5c48d1b0a31
--- /dev/null
+++ b/arch/powerpc/kernel/irq_64.c
@@ -0,0 +1,522 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Derived from arch/i386/kernel/irq.c
+ * Copyright (C) 1992 Linus Torvalds
+ * Adapted from arch/i386 by Gary Thomas
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Updated and modified by Cort Dougan <cort@fsmlabs.com>
+ * Copyright (C) 1996-2001 Cort Dougan
+ * Adapted for Power Macintosh by Paul Mackerras
+ * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ */
+
+#undef DEBUG
+
+#include <linux/export.h>
+#include <linux/threads.h>
+#include <linux/kernel_stat.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/profile.h>
+#include <linux/bitops.h>
+#include <linux/list.h>
+#include <linux/radix-tree.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/debugfs.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/vmalloc.h>
+#include <linux/pgtable.h>
+#include <linux/static_call.h>
+
+#include <linux/uaccess.h>
+#include <asm/interrupt.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/cache.h>
+#include <asm/ptrace.h>
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/smp.h>
+#include <asm/hw_irq.h>
+#include <asm/softirq_stack.h>
+#include <asm/ppc_asm.h>
+
+#include <asm/paca.h>
+#include <asm/firmware.h>
+#include <asm/lv1call.h>
+#include <asm/dbell.h>
+#include <asm/trace.h>
+#include <asm/cpu_has_feature.h>
+
+int distribute_irqs = 1;
+
+static inline void next_interrupt(struct pt_regs *regs)
+{
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ WARN_ON(!(local_paca->irq_happened & PACA_IRQ_HARD_DIS));
+ WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+ }
+
+ /*
+ * We are responding to the next interrupt, so interrupt-off
+ * latencies should be reset here.
+ */
+ lockdep_hardirq_exit();
+ trace_hardirqs_on();
+ trace_hardirqs_off();
+ lockdep_hardirq_enter();
+}
+
+static inline bool irq_happened_test_and_clear(u8 irq)
+{
+ if (local_paca->irq_happened & irq) {
+ local_paca->irq_happened &= ~irq;
+ return true;
+ }
+ return false;
+}
+
+static __no_kcsan void __replay_soft_interrupts(void)
+{
+ struct pt_regs regs;
+
+ /*
+ * We use local_paca rather than get_paca() to avoid all the
+ * debug_smp_processor_id() business in this low level function.
+ */
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ WARN_ON_ONCE(mfmsr() & MSR_EE);
+ WARN_ON(!(local_paca->irq_happened & PACA_IRQ_HARD_DIS));
+ WARN_ON(local_paca->irq_happened & PACA_IRQ_REPLAYING);
+ }
+
+ /*
+ * PACA_IRQ_REPLAYING prevents interrupt handlers from enabling
+ * MSR[EE] to get PMIs, which can result in more IRQs becoming
+ * pending.
+ */
+ local_paca->irq_happened |= PACA_IRQ_REPLAYING;
+
+ ppc_save_regs(&regs);
+ regs.softe = IRQS_ENABLED;
+ regs.msr |= MSR_EE;
+
+ /*
+ * Force the delivery of pending soft-disabled interrupts on PS3.
+ * Any HV call will have this side effect.
+ */
+ if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
+ u64 tmp, tmp2;
+ lv1_get_version_info(&tmp, &tmp2);
+ }
+
+ /*
+ * Check if an hypervisor Maintenance interrupt happened.
+ * This is a higher priority interrupt than the others, so
+ * replay it first.
+ */
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) &&
+ irq_happened_test_and_clear(PACA_IRQ_HMI)) {
+ regs.trap = INTERRUPT_HMI;
+ handle_hmi_exception(&regs);
+ next_interrupt(&regs);
+ }
+
+ if (irq_happened_test_and_clear(PACA_IRQ_DEC)) {
+ regs.trap = INTERRUPT_DECREMENTER;
+ timer_interrupt(&regs);
+ next_interrupt(&regs);
+ }
+
+ if (irq_happened_test_and_clear(PACA_IRQ_EE)) {
+ regs.trap = INTERRUPT_EXTERNAL;
+ do_IRQ(&regs);
+ next_interrupt(&regs);
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_DOORBELL) &&
+ irq_happened_test_and_clear(PACA_IRQ_DBELL)) {
+ regs.trap = INTERRUPT_DOORBELL;
+ doorbell_exception(&regs);
+ next_interrupt(&regs);
+ }
+
+ /* Book3E does not support soft-masking PMI interrupts */
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) &&
+ irq_happened_test_and_clear(PACA_IRQ_PMI)) {
+ regs.trap = INTERRUPT_PERFMON;
+ performance_monitor_exception(&regs);
+ next_interrupt(&regs);
+ }
+
+ local_paca->irq_happened &= ~PACA_IRQ_REPLAYING;
+}
+
+__no_kcsan void replay_soft_interrupts(void)
+{
+ irq_enter(); /* See comment in arch_local_irq_restore */
+ __replay_soft_interrupts();
+ irq_exit();
+}
+
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP)
+static inline __no_kcsan void replay_soft_interrupts_irqrestore(void)
+{
+ unsigned long kuap_state = get_kuap();
+
+ /*
+ * Check if anything calls local_irq_enable/restore() when KUAP is
+ * disabled (user access enabled). We handle that case here by saving
+ * and re-locking AMR but we shouldn't get here in the first place,
+ * hence the warning.
+ */
+ kuap_assert_locked();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(AMR_KUAP_BLOCKED);
+
+ __replay_soft_interrupts();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(kuap_state);
+}
+#else
+#define replay_soft_interrupts_irqrestore() __replay_soft_interrupts()
+#endif
+
+notrace __no_kcsan void arch_local_irq_restore(unsigned long mask)
+{
+ unsigned char irq_happened;
+
+ /* Write the new soft-enabled value if it is a disable */
+ if (mask) {
+ irq_soft_mask_set(mask);
+ return;
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ WARN_ON_ONCE(in_nmi());
+ WARN_ON_ONCE(in_hardirq());
+ WARN_ON_ONCE(local_paca->irq_happened & PACA_IRQ_REPLAYING);
+ }
+
+again:
+ /*
+ * After the stb, interrupts are unmasked and there are no interrupts
+ * pending replay. The restart sequence makes this atomic with
+ * respect to soft-masked interrupts. If this was just a simple code
+ * sequence, a soft-masked interrupt could become pending right after
+ * the comparison and before the stb.
+ *
+ * This allows interrupts to be unmasked without hard disabling, and
+ * also without new hard interrupts coming in ahead of pending ones.
+ */
+ asm goto(
+"1: \n"
+" lbz 9,%0(13) \n"
+" cmpwi 9,0 \n"
+" bne %l[happened] \n"
+" stb 9,%1(13) \n"
+"2: \n"
+ RESTART_TABLE(1b, 2b, 1b)
+ : : "i" (offsetof(struct paca_struct, irq_happened)),
+ "i" (offsetof(struct paca_struct, irq_soft_mask))
+ : "cr0", "r9"
+ : happened);
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(!(mfmsr() & MSR_EE));
+
+ /*
+ * If we came here from the replay below, we might have a preempt
+ * pending (due to preempt_enable_no_resched()). Have to check now.
+ */
+ preempt_check_resched();
+
+ return;
+
+happened:
+ irq_happened = READ_ONCE(local_paca->irq_happened);
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(!irq_happened);
+
+ if (irq_happened == PACA_IRQ_HARD_DIS) {
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(mfmsr() & MSR_EE);
+ irq_soft_mask_set(IRQS_ENABLED);
+ local_paca->irq_happened = 0;
+ __hard_irq_enable();
+ preempt_check_resched();
+ return;
+ }
+
+ /* Have interrupts to replay, need to hard disable first */
+ if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ if (!(mfmsr() & MSR_EE)) {
+ /*
+ * An interrupt could have come in and cleared
+ * MSR[EE] and set IRQ_HARD_DIS, so check
+ * IRQ_HARD_DIS again and warn if it is still
+ * clear.
+ */
+ irq_happened = READ_ONCE(local_paca->irq_happened);
+ WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS));
+ }
+ }
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+ } else {
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ if (WARN_ON_ONCE(mfmsr() & MSR_EE))
+ __hard_irq_disable();
+ }
+ }
+
+ /*
+ * Disable preempt here, so that the below preempt_enable will
+ * perform resched if required (a replayed interrupt may set
+ * need_resched).
+ */
+ preempt_disable();
+ irq_soft_mask_set(IRQS_ALL_DISABLED);
+ trace_hardirqs_off();
+
+ /*
+ * Now enter interrupt context. The interrupt handlers themselves
+ * also call irq_enter/exit (which is okay, they can nest). But call
+ * it here now to hold off softirqs until the below irq_exit(). If
+ * we allowed replayed handlers to run softirqs, that enables irqs,
+ * which must replay interrupts, which recurses in here and makes
+ * things more complicated. The recursion is limited to 2, and it can
+ * be made to work, but it's complicated.
+ *
+ * local_bh_disable can not be used here because interrupts taken in
+ * idle are not in the right context (RCU, tick, etc) to run softirqs
+ * so irq_enter must be called.
+ */
+ irq_enter();
+
+ replay_soft_interrupts_irqrestore();
+
+ irq_exit();
+
+ if (unlikely(local_paca->irq_happened != PACA_IRQ_HARD_DIS)) {
+ /*
+ * The softirq processing in irq_exit() may enable interrupts
+ * temporarily, which can result in MSR[EE] being enabled and
+ * more irqs becoming pending. Go around again if that happens.
+ */
+ trace_hardirqs_on();
+ preempt_enable_no_resched();
+ goto again;
+ }
+
+ trace_hardirqs_on();
+ irq_soft_mask_set(IRQS_ENABLED);
+ local_paca->irq_happened = 0;
+ __hard_irq_enable();
+ preempt_enable();
+}
+EXPORT_SYMBOL(arch_local_irq_restore);
+
+/*
+ * This is a helper to use when about to go into idle low-power
+ * when the latter has the side effect of re-enabling interrupts
+ * (such as calling H_CEDE under pHyp).
+ *
+ * You call this function with interrupts soft-disabled (this is
+ * already the case when ppc_md.power_save is called). The function
+ * will return whether to enter power save or just return.
+ *
+ * In the former case, it will have generally sanitized the lazy irq
+ * state, and in the latter case it will leave with interrupts hard
+ * disabled and marked as such, so the local_irq_enable() call
+ * in arch_cpu_idle() will properly re-enable everything.
+ */
+__cpuidle bool prep_irq_for_idle(void)
+{
+ /*
+ * First we need to hard disable to ensure no interrupt
+ * occurs before we effectively enter the low power state
+ */
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ /*
+ * If anything happened while we were soft-disabled,
+ * we return now and do not enter the low power state.
+ */
+ if (lazy_irq_pending())
+ return false;
+
+ /*
+ * Mark interrupts as soft-enabled and clear the
+ * PACA_IRQ_HARD_DIS from the pending mask since we
+ * are about to hard enable as well as a side effect
+ * of entering the low power state.
+ */
+ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+ irq_soft_mask_set(IRQS_ENABLED);
+
+ /* Tell the caller to enter the low power state */
+ return true;
+}
+
+#ifdef CONFIG_PPC_BOOK3S
+/*
+ * This is for idle sequences that return with IRQs off, but the
+ * idle state itself wakes on interrupt. Tell the irq tracer that
+ * IRQs are enabled for the duration of idle so it does not get long
+ * off times. Must be paired with fini_irq_for_idle_irqsoff.
+ */
+bool prep_irq_for_idle_irqsoff(void)
+{
+ WARN_ON(!irqs_disabled());
+
+ /*
+ * First we need to hard disable to ensure no interrupt
+ * occurs before we effectively enter the low power state
+ */
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ /*
+ * If anything happened while we were soft-disabled,
+ * we return now and do not enter the low power state.
+ */
+ if (lazy_irq_pending())
+ return false;
+
+ /* Tell lockdep we are about to re-enable */
+ trace_hardirqs_on();
+
+ return true;
+}
+
+/*
+ * Take the SRR1 wakeup reason, index into this table to find the
+ * appropriate irq_happened bit.
+ *
+ * Sytem reset exceptions taken in idle state also come through here,
+ * but they are NMI interrupts so do not need to wait for IRQs to be
+ * restored, and should be taken as early as practical. These are marked
+ * with 0xff in the table. The Power ISA specifies 0100b as the system
+ * reset interrupt reason.
+ */
+#define IRQ_SYSTEM_RESET 0xff
+
+static const u8 srr1_to_lazyirq[0x10] = {
+ 0, 0, 0,
+ PACA_IRQ_DBELL,
+ IRQ_SYSTEM_RESET,
+ PACA_IRQ_DBELL,
+ PACA_IRQ_DEC,
+ 0,
+ PACA_IRQ_EE,
+ PACA_IRQ_EE,
+ PACA_IRQ_HMI,
+ 0, 0, 0, 0, 0 };
+
+void replay_system_reset(void)
+{
+ struct pt_regs regs;
+
+ ppc_save_regs(&regs);
+ regs.trap = 0x100;
+ get_paca()->in_nmi = 1;
+ system_reset_exception(&regs);
+ get_paca()->in_nmi = 0;
+}
+EXPORT_SYMBOL_GPL(replay_system_reset);
+
+void irq_set_pending_from_srr1(unsigned long srr1)
+{
+ unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18;
+ u8 reason = srr1_to_lazyirq[idx];
+
+ /*
+ * Take the system reset now, which is immediately after registers
+ * are restored from idle. It's an NMI, so interrupts need not be
+ * re-enabled before it is taken.
+ */
+ if (unlikely(reason == IRQ_SYSTEM_RESET)) {
+ replay_system_reset();
+ return;
+ }
+
+ if (reason == PACA_IRQ_DBELL) {
+ /*
+ * When doorbell triggers a system reset wakeup, the message
+ * is not cleared, so if the doorbell interrupt is replayed
+ * and the IPI handled, the doorbell interrupt would still
+ * fire when EE is enabled.
+ *
+ * To avoid taking the superfluous doorbell interrupt,
+ * execute a msgclr here before the interrupt is replayed.
+ */
+ ppc_msgclr(PPC_DBELL_MSGTYPE);
+ }
+
+ /*
+ * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
+ * so this can be called unconditionally with the SRR1 wake
+ * reason as returned by the idle code, which uses 0 to mean no
+ * interrupt.
+ *
+ * If a future CPU was to designate this as an interrupt reason,
+ * then a new index for no interrupt must be assigned.
+ */
+ local_paca->irq_happened |= reason;
+}
+#endif /* CONFIG_PPC_BOOK3S */
+
+/*
+ * Force a replay of the external interrupt handler on this CPU.
+ */
+void force_external_irq_replay(void)
+{
+ /*
+ * This must only be called with interrupts soft-disabled,
+ * the replay will happen when re-enabling.
+ */
+ WARN_ON(!arch_irqs_disabled());
+
+ /*
+ * Interrupts must always be hard disabled before irq_happened is
+ * modified (to prevent lost update in case of interrupt between
+ * load and store).
+ */
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ /* Indicate in the PACA that we have an interrupt to replay */
+ local_paca->irq_happened |= PACA_IRQ_EE;
+}
+
+static int __init setup_noirqdistrib(char *str)
+{
+ distribute_irqs = 0;
+ return 1;
+}
+
+__setup("noirqdistrib", setup_noirqdistrib);
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index dc746611ebc0..5c064485197a 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -46,8 +46,8 @@ static void remap_isa_base(phys_addr_t pa, unsigned long size)
WARN_ON_ONCE(size & ~PAGE_MASK);
if (slab_is_available()) {
- if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
- pgprot_noncached(PAGE_KERNEL)))
+ if (vmap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
+ pgprot_noncached(PAGE_KERNEL)))
vunmap_range(ISA_IO_BASE, ISA_IO_BASE + size);
} else {
early_ioremap_range(ISA_IO_BASE, pa, size,
@@ -55,80 +55,50 @@ static void remap_isa_base(phys_addr_t pa, unsigned long size)
}
}
-static void pci_process_ISA_OF_ranges(struct device_node *isa_node,
- unsigned long phb_io_base_phys)
+static int process_ISA_OF_ranges(struct device_node *isa_node,
+ unsigned long phb_io_base_phys)
{
- /* We should get some saner parsing here and remove these structs */
- struct pci_address {
- u32 a_hi;
- u32 a_mid;
- u32 a_lo;
- };
-
- struct isa_address {
- u32 a_hi;
- u32 a_lo;
- };
-
- struct isa_range {
- struct isa_address isa_addr;
- struct pci_address pci_addr;
- unsigned int size;
- };
-
- const struct isa_range *range;
- unsigned long pci_addr;
- unsigned int isa_addr;
unsigned int size;
- int rlen = 0;
+ struct of_range_parser parser;
+ struct of_range range;
- range = of_get_property(isa_node, "ranges", &rlen);
- if (range == NULL || (rlen < sizeof(struct isa_range)))
+ if (of_range_parser_init(&parser, isa_node))
goto inval_range;
- /* From "ISA Binding to 1275"
- * The ranges property is laid out as an array of elements,
- * each of which comprises:
- * cells 0 - 1: an ISA address
- * cells 2 - 4: a PCI address
- * (size depending on dev->n_addr_cells)
- * cell 5: the size of the range
- */
- if ((range->isa_addr.a_hi & ISA_SPACE_MASK) != ISA_SPACE_IO) {
- range++;
- rlen -= sizeof(struct isa_range);
- if (rlen < sizeof(struct isa_range))
- goto inval_range;
- }
- if ((range->isa_addr.a_hi & ISA_SPACE_MASK) != ISA_SPACE_IO)
- goto inval_range;
+ for_each_of_range(&parser, &range) {
+ if ((range.flags & ISA_SPACE_MASK) != ISA_SPACE_IO)
+ continue;
- isa_addr = range->isa_addr.a_lo;
- pci_addr = (unsigned long) range->pci_addr.a_mid << 32 |
- range->pci_addr.a_lo;
+ if (range.cpu_addr == OF_BAD_ADDR) {
+ pr_err("ISA: Bad CPU mapping: %s\n", __func__);
+ return -EINVAL;
+ }
- /* Assume these are both zero. Note: We could fix that and
- * do a proper parsing instead ... oh well, that will do for
- * now as nobody uses fancy mappings for ISA bridges
- */
- if ((pci_addr != 0) || (isa_addr != 0)) {
- printk(KERN_ERR "unexpected isa to pci mapping: %s\n",
- __func__);
- return;
- }
+ /* We need page alignment */
+ if ((range.bus_addr & ~PAGE_MASK) || (range.cpu_addr & ~PAGE_MASK)) {
+ pr_warn("ISA: bridge %pOF has non aligned IO range\n", isa_node);
+ return -EINVAL;
+ }
- /* Align size and make sure it's cropped to 64K */
- size = PAGE_ALIGN(range->size);
- if (size > 0x10000)
- size = 0x10000;
+ /* Align size and make sure it's cropped to 64K */
+ size = PAGE_ALIGN(range.size);
+ if (size > 0x10000)
+ size = 0x10000;
- remap_isa_base(phb_io_base_phys, size);
- return;
+ if (!phb_io_base_phys)
+ phb_io_base_phys = range.cpu_addr;
+
+ remap_isa_base(phb_io_base_phys, size);
+ return 0;
+ }
inval_range:
- printk(KERN_ERR "no ISA IO ranges or unexpected isa range, "
- "mapping 64k\n");
- remap_isa_base(phb_io_base_phys, 0x10000);
+ if (phb_io_base_phys) {
+ pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n");
+ remap_isa_base(phb_io_base_phys, 0x10000);
+ return 0;
+ }
+ return -EINVAL;
}
@@ -170,7 +140,7 @@ void __init isa_bridge_find_early(struct pci_controller *hose)
isa_bridge_devnode = np;
/* Now parse the "ranges" property and setup the ISA mapping */
- pci_process_ISA_OF_ranges(np, hose->io_base_phys);
+ process_ISA_OF_ranges(np, hose->io_base_phys);
/* Set the global ISA io base to indicate we have an ISA bridge */
isa_io_base = ISA_IO_BASE;
@@ -186,75 +156,15 @@ void __init isa_bridge_find_early(struct pci_controller *hose)
*/
void __init isa_bridge_init_non_pci(struct device_node *np)
{
- const __be32 *ranges, *pbasep = NULL;
- int rlen, i, rs;
- u32 na, ns, pna;
- u64 cbase, pbase, size = 0;
+ int ret;
/* If we already have an ISA bridge, bail off */
if (isa_bridge_devnode != NULL)
return;
- pna = of_n_addr_cells(np);
- if (of_property_read_u32(np, "#address-cells", &na) ||
- of_property_read_u32(np, "#size-cells", &ns)) {
- pr_warn("ISA: Non-PCI bridge %pOF is missing address format\n",
- np);
- return;
- }
-
- /* Check it's a supported address format */
- if (na != 2 || ns != 1) {
- pr_warn("ISA: Non-PCI bridge %pOF has unsupported address format\n",
- np);
- return;
- }
- rs = na + ns + pna;
-
- /* Grab the ranges property */
- ranges = of_get_property(np, "ranges", &rlen);
- if (ranges == NULL || rlen < rs) {
- pr_warn("ISA: Non-PCI bridge %pOF has absent or invalid ranges\n",
- np);
- return;
- }
-
- /* Parse it. We are only looking for IO space */
- for (i = 0; (i + rs - 1) < rlen; i += rs) {
- if (be32_to_cpup(ranges + i) != 1)
- continue;
- cbase = be32_to_cpup(ranges + i + 1);
- size = of_read_number(ranges + i + na + pna, ns);
- pbasep = ranges + i + na;
- break;
- }
-
- /* Got something ? */
- if (!size || !pbasep) {
- pr_warn("ISA: Non-PCI bridge %pOF has no usable IO range\n",
- np);
+ ret = process_ISA_OF_ranges(np, 0);
+ if (ret)
return;
- }
-
- /* Align size and make sure it's cropped to 64K */
- size = PAGE_ALIGN(size);
- if (size > 0x10000)
- size = 0x10000;
-
- /* Map pbase */
- pbase = of_translate_address(np, pbasep);
- if (pbase == OF_BAD_ADDR) {
- pr_warn("ISA: Non-PCI bridge %pOF failed to translate IO base\n",
- np);
- return;
- }
-
- /* We need page alignment */
- if ((cbase & ~PAGE_MASK) || (pbase & ~PAGE_MASK)) {
- pr_warn("ISA: Non-PCI bridge %pOF has non aligned IO range\n",
- np);
- return;
- }
/* Got it */
isa_bridge_devnode = np;
@@ -263,7 +173,6 @@ void __init isa_bridge_init_non_pci(struct device_node *np)
* and map it
*/
isa_io_base = ISA_IO_BASE;
- remap_isa_base(pbase, size);
pr_debug("ISA: Non-PCI bridge is %pOF\n", np);
}
@@ -282,7 +191,7 @@ static void isa_bridge_find_late(struct pci_dev *pdev,
isa_bridge_pcidev = pdev;
/* Now parse the "ranges" property and setup the ISA mapping */
- pci_process_ISA_OF_ranges(devnode, hose->io_base_phys);
+ process_ISA_OF_ranges(devnode, hose->io_base_phys);
/* Set the global ISA io base to indicate we have an ISA bridge */
isa_io_base = ISA_IO_BASE;
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index 5277cf582c16..2659e1ac8604 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -5,7 +5,7 @@
#include <linux/kernel.h>
#include <linux/jump_label.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/inst.h>
void arch_jump_label_transform(struct jump_entry *entry,
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 9f8d0fa7b718..5081334b7bd2 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* PowerPC backend to the KGDB stub.
*
@@ -8,10 +9,6 @@
* PPC32 support restored by Vitaly Wool <vwool@ru.mvista.com> and
* Sergei Shtylyov <sshtylyov@ru.mvista.com>
* Copyright (C) 2007-2008 Wind River Systems, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program as licensed "as is" without any warranty of any
- * kind, whether express or implied.
*/
#include <linux/kernel.h>
@@ -24,7 +21,7 @@
#include <asm/processor.h>
#include <asm/machdep.h>
#include <asm/debug.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <linux/slab.h>
#include <asm/inst.h>
@@ -48,9 +45,9 @@ static struct hard_trap_info
{ 0x0800, 0x08 /* SIGFPE */ }, /* fp unavailable */
{ 0x0900, 0x0e /* SIGALRM */ }, /* decrementer */
{ 0x0c00, 0x14 /* SIGCHLD */ }, /* system call */
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
{ 0x2002, 0x05 /* SIGTRAP */ }, /* debug */
-#if defined(CONFIG_FSL_BOOKE)
+#if defined(CONFIG_PPC_85xx)
{ 0x2010, 0x08 /* SIGFPE */ }, /* spe unavailable */
{ 0x2020, 0x08 /* SIGFPE */ }, /* spe unavailable */
{ 0x2030, 0x08 /* SIGFPE */ }, /* spe fp data */
@@ -60,14 +57,14 @@ static struct hard_trap_info
{ 0x2900, 0x08 /* SIGFPE */ }, /* apu unavailable */
{ 0x3100, 0x0e /* SIGALRM */ }, /* fixed interval timer */
{ 0x3200, 0x02 /* SIGINT */ }, /* watchdog */
-#else /* ! CONFIG_FSL_BOOKE */
+#else /* ! CONFIG_PPC_85xx */
{ 0x1000, 0x0e /* SIGALRM */ }, /* prog interval timer */
{ 0x1010, 0x0e /* SIGALRM */ }, /* fixed interval timer */
{ 0x1020, 0x02 /* SIGINT */ }, /* watchdog */
{ 0x2010, 0x08 /* SIGFPE */ }, /* fp unavailable */
{ 0x2020, 0x08 /* SIGFPE */ }, /* ap unavailable */
#endif
-#else /* !CONFIG_BOOKE_OR_40x */
+#else /* !CONFIG_BOOKE */
{ 0x0d00, 0x05 /* SIGTRAP */ }, /* single-step */
#if defined(CONFIG_PPC_8xx)
{ 0x1000, 0x04 /* SIGILL */ }, /* software emulation */
@@ -194,7 +191,7 @@ static int kgdb_break_match(struct pt_regs *regs)
void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
{
struct pt_regs *regs = (struct pt_regs *)(p->thread.ksp +
- STACK_FRAME_OVERHEAD);
+ STACK_INT_FRAME_REGS);
unsigned long *ptr = gdb_regs;
int reg;
@@ -211,7 +208,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
for (reg = 14; reg < 32; reg++)
PACK64(ptr, regs->gpr[reg]);
-#ifdef CONFIG_FSL_BOOKE
+#ifdef CONFIG_PPC_85xx
#ifdef CONFIG_SPE
for (reg = 0; reg < 32; reg++)
PACK64(ptr, p->thread.evr[reg]);
@@ -237,7 +234,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
#define GDB_SIZEOF_REG sizeof(unsigned long)
#define GDB_SIZEOF_REG_U32 sizeof(u32)
-#ifdef CONFIG_FSL_BOOKE
+#ifdef CONFIG_PPC_85xx
#define GDB_SIZEOF_FLOAT_REG sizeof(unsigned long)
#else
#define GDB_SIZEOF_FLOAT_REG sizeof(u64)
@@ -332,7 +329,7 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
if (regno >= 32 && regno < 64) {
/* FP registers 32 -> 63 */
-#if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE)
+#if defined(CONFIG_PPC_85xx) && defined(CONFIG_SPE)
if (current)
memcpy(mem, &current->thread.evr[regno-32],
dbg_reg_def[regno].size);
@@ -358,7 +355,7 @@ int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
if (regno >= 32 && regno < 64) {
/* FP registers 32 -> 63 */
-#if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE)
+#if defined(CONFIG_PPC_85xx) && defined(CONFIG_SPE)
memcpy(&current->thread.evr[regno-32], mem,
dbg_reg_def[regno].size);
#else
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 072ebe7f290b..f8208c027148 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
struct pt_regs *regs;
int bit;
+ if (unlikely(kprobe_ftrace_disabled))
+ return;
+
bit = ftrace_test_recursion_trylock(nip, parent_nip);
if (bit < 0)
return;
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 1c97c0f177ae..c0d9f12cb441 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -19,13 +19,13 @@
#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
-#include <linux/moduleloader.h>
-#include <asm/code-patching.h>
+#include <linux/set_memory.h>
+#include <linux/execmem.h>
+#include <asm/text-patching.h>
#include <asm/cacheflush.h>
#include <asm/sstep.h>
#include <asm/sections.h>
#include <asm/inst.h>
-#include <asm/set_memory.h>
#include <linux/uaccess.h>
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
@@ -105,42 +105,25 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
return addr;
}
-static bool arch_kprobe_on_func_entry(unsigned long offset)
+static bool arch_kprobe_on_func_entry(unsigned long addr, unsigned long offset)
{
-#ifdef CONFIG_PPC64_ELF_ABI_V2
-#ifdef CONFIG_KPROBES_ON_FTRACE
- return offset <= 16;
-#else
- return offset <= 8;
-#endif
-#else
+ unsigned long ip = ftrace_location(addr);
+
+ if (ip)
+ return offset <= (ip - addr);
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ return offset <= 8;
return !offset;
-#endif
}
/* XXX try and fold the magic of kprobe_lookup_name() in this */
kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
bool *on_func_entry)
{
- *on_func_entry = arch_kprobe_on_func_entry(offset);
+ *on_func_entry = arch_kprobe_on_func_entry(addr, offset);
return (kprobe_opcode_t *)(addr + offset);
}
-void *alloc_insn_page(void)
-{
- void *page;
-
- page = module_alloc(PAGE_SIZE);
- if (!page)
- return NULL;
-
- if (strict_module_rwx_enabled()) {
- set_memory_ro((unsigned long)page, 1);
- set_memory_x((unsigned long)page, 1);
- }
- return page;
-}
-
int arch_prepare_kprobe(struct kprobe *p)
{
int ret = 0;
@@ -158,10 +141,14 @@ int arch_prepare_kprobe(struct kprobe *p)
printk("Cannot register a kprobe on the second word of prefixed instruction\n");
ret = -EINVAL;
}
- preempt_disable();
prev = get_kprobe(p->addr - 1);
- preempt_enable_no_resched();
- if (prev && ppc_inst_prefixed(ppc_inst_read(prev->ainsn.insn))) {
+
+ /*
+ * When prev is a ftrace-based kprobe, we don't have an insn, and it
+ * doesn't probe for prefixed instruction.
+ */
+ if (prev && !kprobe_ftrace(prev) &&
+ ppc_inst_prefixed(ppc_inst_read(prev->ainsn.insn))) {
printk("Cannot register a kprobe on the second word of prefixed instruction\n");
ret = -EINVAL;
}
@@ -239,16 +226,6 @@ static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs
kcb->kprobe_saved_msr = regs->msr;
}
-void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
-{
- ri->ret_addr = (kprobe_opcode_t *)regs->link;
- ri->fp = NULL;
-
- /* Replace the return addr with trampoline addr */
- regs->link = (unsigned long)__kretprobe_trampoline;
-}
-NOKPROBE_SYMBOL(arch_prepare_kretprobe);
-
static int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
{
int ret;
@@ -269,7 +246,7 @@ static int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
* So, we should never get here... but, its still
* good to catch them, just in case...
*/
- printk("Can't step on instruction %s\n", ppc_inst_as_str(insn));
+ printk("Can't step on instruction %08lx\n", ppc_inst_as_ulong(insn));
BUG();
} else {
/*
@@ -365,7 +342,7 @@ int kprobe_handler(struct pt_regs *regs)
if (ret > 0) {
restore_previous_kprobe(kcb);
- preempt_enable_no_resched();
+ preempt_enable();
return 1;
}
}
@@ -378,7 +355,7 @@ int kprobe_handler(struct pt_regs *regs)
if (p->pre_handler && p->pre_handler(p, regs)) {
/* handler changed execution path, so skip ss setup */
reset_current_kprobe();
- preempt_enable_no_resched();
+ preempt_enable();
return 1;
}
@@ -391,7 +368,7 @@ int kprobe_handler(struct pt_regs *regs)
kcb->kprobe_status = KPROBE_HIT_SSDONE;
reset_current_kprobe();
- preempt_enable_no_resched();
+ preempt_enable();
return 1;
}
}
@@ -400,55 +377,12 @@ int kprobe_handler(struct pt_regs *regs)
return 1;
no_kprobe:
- preempt_enable_no_resched();
+ preempt_enable();
return ret;
}
NOKPROBE_SYMBOL(kprobe_handler);
/*
- * Function return probe trampoline:
- * - init_kprobes() establishes a probepoint here
- * - When the probed function returns, this probe
- * causes the handlers to fire
- */
-asm(".global __kretprobe_trampoline\n"
- ".type __kretprobe_trampoline, @function\n"
- "__kretprobe_trampoline:\n"
- "nop\n"
- "blr\n"
- ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n");
-
-/*
- * Called when the probe at kretprobe trampoline is hit
- */
-static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
-{
- unsigned long orig_ret_address;
-
- orig_ret_address = __kretprobe_trampoline_handler(regs, NULL);
- /*
- * We get here through one of two paths:
- * 1. by taking a trap -> kprobe_handler() -> here
- * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here
- *
- * When going back through (1), we need regs->nip to be setup properly
- * as it is used to determine the return address from the trap.
- * For (2), since nip is not honoured with optprobes, we instead setup
- * the link register properly so that the subsequent 'blr' in
- * __kretprobe_trampoline jumps back to the right instruction.
- *
- * For nip, we should set the address to the previous instruction since
- * we end up emulating it in kprobe_handler(), which increments the nip
- * again.
- */
- regs_set_return_ip(regs, orig_ret_address - 4);
- regs->link = orig_ret_address;
-
- return 0;
-}
-NOKPROBE_SYMBOL(trampoline_probe_handler);
-
-/*
* Called after single-stepping. p->addr is the address of the
* instruction whose first byte has been replaced by the "breakpoint"
* instruction. To avoid the SMP problems that can occur when we
@@ -486,7 +420,7 @@ int kprobe_post_handler(struct pt_regs *regs)
}
reset_current_kprobe();
out:
- preempt_enable_no_resched();
+ preempt_enable();
/*
* if somebody else is singlestepping across a probe point, msr
@@ -525,7 +459,7 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
restore_previous_kprobe(kcb);
else
reset_current_kprobe();
- preempt_enable_no_resched();
+ preempt_enable();
break;
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
@@ -550,19 +484,9 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
}
NOKPROBE_SYMBOL(kprobe_fault_handler);
-static struct kprobe trampoline_p = {
- .addr = (kprobe_opcode_t *) &__kretprobe_trampoline,
- .pre_handler = trampoline_probe_handler
-};
-
-int __init arch_init_kprobes(void)
-{
- return register_kprobe(&trampoline_p);
-}
-
int arch_trampoline_kprobe(struct kprobe *p)
{
- if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline)
+ if (p->addr == (kprobe_opcode_t *)&arch_rethook_trampoline)
return 1;
return 0;
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 6568823cf306..7209d00a9c25 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -455,7 +455,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt);
break;
-#ifdef CONFIG_PPC_BOOK3E_MMU
+#ifdef CONFIG_PPC_E500
case KVM_INST_MFSPR(SPRN_MAS0):
if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
kvm_patch_ins_lwz(inst, magic_var(mas0), inst_rt);
@@ -484,7 +484,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
kvm_patch_ins_lwz(inst, magic_var(mas7_3), inst_rt);
break;
-#endif /* CONFIG_PPC_BOOK3E_MMU */
+#endif /* CONFIG_PPC_E500 */
case KVM_INST_MFSPR(SPRN_SPRG4):
#ifdef CONFIG_BOOKE
@@ -557,7 +557,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
case KVM_INST_MTSPR(SPRN_DSISR):
kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
break;
-#ifdef CONFIG_PPC_BOOK3E_MMU
+#ifdef CONFIG_PPC_E500
case KVM_INST_MTSPR(SPRN_MAS0):
if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
kvm_patch_ins_stw(inst, magic_var(mas0), inst_rt);
@@ -586,7 +586,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
kvm_patch_ins_stw(inst, magic_var(mas7_3), inst_rt);
break;
-#endif /* CONFIG_PPC_BOOK3E_MMU */
+#endif /* CONFIG_PPC_E500 */
case KVM_INST_MTSPR(SPRN_SPRG4):
if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
@@ -632,19 +632,19 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
#endif
}
- switch (inst_no_rt & ~KVM_MASK_RB) {
#ifdef CONFIG_PPC_BOOK3S_32
+ switch (inst_no_rt & ~KVM_MASK_RB) {
case KVM_INST_MTSRIN:
if (features & KVM_MAGIC_FEAT_SR) {
u32 inst_rb = _inst & KVM_MASK_RB;
kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
}
break;
-#endif
}
+#endif
- switch (_inst) {
#ifdef CONFIG_BOOKE
+ switch (_inst) {
case KVM_INST_WRTEEI_0:
kvm_patch_ins_wrteei_0(inst);
break;
@@ -652,8 +652,8 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
case KVM_INST_WRTEEI_1:
kvm_patch_ins_wrtee(inst, 0, 1);
break;
-#endif
}
+#endif
}
extern u32 kvm_template_start[];
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 5c58460b269a..ae1906bfe8a5 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -5,8 +5,8 @@
#include <linux/serial_core.h>
#include <linux/console.h>
#include <linux/pci.h>
+#include <linux/of.h>
#include <linux/of_address.h>
-#include <linux/of_device.h>
#include <linux/of_irq.h>
#include <linux/serial_reg.h>
#include <asm/io.h>
@@ -54,9 +54,10 @@ static int legacy_serial_console = -1;
static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
UPF_SHARE_IRQ | UPF_FIXED_PORT;
-static unsigned int tsi_serial_in(struct uart_port *p, int offset)
+static u32 tsi_serial_in(struct uart_port *p, unsigned int offset)
{
- unsigned int tmp;
+ u32 tmp;
+
offset = offset << p->regshift;
if (offset == UART_IIR) {
tmp = readl(p->membase + (UART_IIR & ~3));
@@ -65,7 +66,7 @@ static unsigned int tsi_serial_in(struct uart_port *p, int offset)
return readb(p->membase + offset);
}
-static void tsi_serial_out(struct uart_port *p, int offset, int value)
+static void tsi_serial_out(struct uart_port *p, unsigned int offset, u32 value)
{
offset = offset << p->regshift;
if (!((offset == UART_IER) && (value & UART_IER_UUE)))
@@ -77,6 +78,8 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
phys_addr_t taddr, unsigned long irq,
upf_t flags, int irq_check_parent)
{
+ struct plat_serial8250_port *legacy_port;
+ struct legacy_serial_info *legacy_info;
const __be32 *clk, *spd, *rs;
u32 clock = BASE_BAUD * 16;
u32 shift = 0;
@@ -110,16 +113,17 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
if (index >= legacy_serial_count)
legacy_serial_count = index + 1;
+ legacy_port = &legacy_serial_ports[index];
+ legacy_info = &legacy_serial_infos[index];
+
/* Check if there is a port who already claimed our slot */
- if (legacy_serial_infos[index].np != NULL) {
+ if (legacy_info->np != NULL) {
/* if we still have some room, move it, else override */
if (legacy_serial_count < MAX_LEGACY_SERIAL_PORTS) {
printk(KERN_DEBUG "Moved legacy port %d -> %d\n",
index, legacy_serial_count);
- legacy_serial_ports[legacy_serial_count] =
- legacy_serial_ports[index];
- legacy_serial_infos[legacy_serial_count] =
- legacy_serial_infos[index];
+ legacy_serial_ports[legacy_serial_count] = *legacy_port;
+ legacy_serial_infos[legacy_serial_count] = *legacy_info;
legacy_serial_count++;
} else {
printk(KERN_DEBUG "Replacing legacy port %d\n", index);
@@ -127,36 +131,32 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
}
/* Now fill the entry */
- memset(&legacy_serial_ports[index], 0,
- sizeof(struct plat_serial8250_port));
+ memset(legacy_port, 0, sizeof(*legacy_port));
if (iotype == UPIO_PORT)
- legacy_serial_ports[index].iobase = base;
+ legacy_port->iobase = base;
else
- legacy_serial_ports[index].mapbase = base;
-
- legacy_serial_ports[index].iotype = iotype;
- legacy_serial_ports[index].uartclk = clock;
- legacy_serial_ports[index].irq = irq;
- legacy_serial_ports[index].flags = flags;
- legacy_serial_ports[index].regshift = shift;
- legacy_serial_infos[index].taddr = taddr;
- legacy_serial_infos[index].np = of_node_get(np);
- legacy_serial_infos[index].clock = clock;
- legacy_serial_infos[index].speed = spd ? be32_to_cpup(spd) : 0;
- legacy_serial_infos[index].irq_check_parent = irq_check_parent;
+ legacy_port->mapbase = base;
+
+ legacy_port->iotype = iotype;
+ legacy_port->uartclk = clock;
+ legacy_port->irq = irq;
+ legacy_port->flags = flags;
+ legacy_port->regshift = shift;
+ legacy_info->taddr = taddr;
+ legacy_info->np = of_node_get(np);
+ legacy_info->clock = clock;
+ legacy_info->speed = spd ? be32_to_cpup(spd) : 0;
+ legacy_info->irq_check_parent = irq_check_parent;
if (iotype == UPIO_TSI) {
- legacy_serial_ports[index].serial_in = tsi_serial_in;
- legacy_serial_ports[index].serial_out = tsi_serial_out;
+ legacy_port->serial_in = tsi_serial_in;
+ legacy_port->serial_out = tsi_serial_out;
}
- printk(KERN_DEBUG "Found legacy serial port %d for %pOF\n",
- index, np);
- printk(KERN_DEBUG " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n",
+ printk(KERN_DEBUG "Found legacy serial port %d for %pOF\n", index, np);
+ printk(KERN_DEBUG " %s=%pa, taddr=%pa, irq=%lx, clk=%d, speed=%d\n",
(iotype == UPIO_PORT) ? "port" : "mem",
- (unsigned long long)base, (unsigned long long)taddr, irq,
- legacy_serial_ports[index].uartclk,
- legacy_serial_infos[index].speed);
+ &base, &taddr, irq, legacy_port->uartclk, legacy_info->speed);
return index;
}
@@ -171,15 +171,15 @@ static int __init add_legacy_soc_port(struct device_node *np,
/* We only support ports that have a clock frequency properly
* encoded in the device-tree.
*/
- if (of_get_property(np, "clock-frequency", NULL) == NULL)
+ if (!of_property_present(np, "clock-frequency"))
return -1;
/* if reg-offset don't try to use it */
- if ((of_get_property(np, "reg-offset", NULL) != NULL))
+ if (of_property_present(np, "reg-offset"))
return -1;
/* if rtas uses this device, don't try to use it as well */
- if (of_get_property(np, "used-by-rtas", NULL) != NULL)
+ if (of_property_read_bool(np, "used-by-rtas"))
return -1;
/* Get the address */
@@ -237,7 +237,7 @@ static int __init add_legacy_isa_port(struct device_node *np,
* Note: Don't even try on P8 lpc, we know it's not directly mapped
*/
if (!of_device_is_compatible(isa_brg, "ibm,power8-lpc") ||
- of_get_property(isa_brg, "ranges", NULL)) {
+ of_property_present(isa_brg, "ranges")) {
taddr = of_translate_address(np, reg);
if (taddr == OF_BAD_ADDR)
taddr = 0;
@@ -268,7 +268,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
* compatible UARTs on PCI need all sort of quirks (port offsets
* etc...) that this code doesn't know about
*/
- if (of_get_property(np, "clock-frequency", NULL) == NULL)
+ if (!of_property_present(np, "clock-frequency"))
return -1;
/* Get the PCI address. Assume BAR 0 */
@@ -471,6 +471,8 @@ void __init find_legacy_serial_ports(void)
}
#endif
+ of_node_put(stdout);
+
DBG("legacy_serial_console = %d\n", legacy_serial_console);
if (legacy_serial_console >= 0)
setup_legacy_serial_console(legacy_serial_console);
@@ -506,12 +508,16 @@ static void __init fixup_port_irq(int index,
port->irq = virq;
-#ifdef CONFIG_SERIAL_8250_FSL
- if (of_device_is_compatible(np, "fsl,ns16550")) {
- port->handle_irq = fsl8250_handle_irq;
- port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE);
+ if (IS_ENABLED(CONFIG_SERIAL_8250) &&
+ of_device_is_compatible(np, "fsl,ns16550")) {
+ if (IS_REACHABLE(CONFIG_SERIAL_8250_FSL)) {
+ port->handle_irq = fsl8250_handle_irq;
+ port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE);
+ } else {
+ pr_warn_once("Not activating Freescale specific workaround for device %pOFP\n",
+ np);
+ }
}
-#endif
}
static void __init fixup_port_pio(int index,
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 18173199b79d..219f28637a3e 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -131,6 +131,13 @@ void save_mce_event(struct pt_regs *regs, long handled,
if (mce->error_type == MCE_ERROR_TYPE_UE)
mce->u.ue_error.ignore_event = mce_err->ignore_event;
+ /*
+ * Raise irq work, So that we don't miss to log the error for
+ * unrecoverable errors.
+ */
+ if (mce->disposition == MCE_DISPOSITION_NOT_RECOVERED)
+ mce_irq_work_queue();
+
if (!addr)
return;
@@ -233,9 +240,6 @@ static void machine_check_ue_event(struct machine_check_event *evt)
}
memcpy(&local_paca->mce_info->mce_ue_event_queue[index],
evt, sizeof(*evt));
-
- /* Queue work to process this event later. */
- mce_irq_work_queue();
}
/*
@@ -756,7 +760,7 @@ void __init mce_init(void)
mce_info = memblock_alloc_try_nid(sizeof(*mce_info),
__alignof__(*mce_info),
MEMBLOCK_LOW_LIMIT,
- limit, cpu_to_node(i));
+ limit, early_cpu_to_node(i));
if (!mce_info)
goto err;
paca_ptrs[i]->mce_info = mce_info;
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index fb7de3543c03..29e1440d14cc 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -10,11 +10,11 @@
*
* setjmp/longjmp code by Paul Mackerras.
*/
+#include <linux/export.h>
#include <asm/ppc_asm.h>
#include <asm/unistd.h>
#include <asm/asm-compat.h>
#include <asm/asm-offsets.h>
-#include <asm/export.h>
.text
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index e5127b19fec2..acb727f54e9d 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -8,6 +8,7 @@
*
*/
+#include <linux/export.h>
#include <linux/sys.h>
#include <asm/unistd.h>
#include <asm/errno.h>
@@ -22,38 +23,11 @@
#include <asm/processor.h>
#include <asm/bug.h>
#include <asm/ptrace.h>
-#include <asm/export.h>
#include <asm/feature-fixups.h>
.text
/*
- * This returns the high 64 bits of the product of two 64-bit numbers.
- */
-_GLOBAL(mulhdu)
- cmpwi r6,0
- cmpwi cr1,r3,0
- mr r10,r4
- mulhwu r4,r4,r5
- beq 1f
- mulhwu r0,r10,r6
- mullw r7,r10,r5
- addc r7,r0,r7
- addze r4,r4
-1: beqlr cr1 /* all done if high part of A is 0 */
- mullw r9,r3,r5
- mulhwu r10,r3,r5
- beq 2f
- mullw r0,r3,r6
- mulhwu r8,r3,r6
- addc r7,r0,r7
- adde r4,r4,r8
- addze r10,r10
-2: addc r4,r4,r9
- addze r3,r10
- blr
-
-/*
* reloc_got2 runs through the .got2 section adding an offset
* to each entry.
*/
@@ -176,46 +150,6 @@ _GLOBAL(low_choose_7447a_dfs)
#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */
-#ifdef CONFIG_40x
-
-/*
- * Do an IO access in real mode
- */
-_GLOBAL(real_readb)
- mfmsr r7
- rlwinm r0,r7,0,~MSR_DR
- sync
- mtmsr r0
- sync
- isync
- lbz r3,0(r3)
- sync
- mtmsr r7
- sync
- isync
- blr
-_ASM_NOKPROBE_SYMBOL(real_readb)
-
- /*
- * Do an IO access in real mode
- */
-_GLOBAL(real_writeb)
- mfmsr r7
- rlwinm r0,r7,0,~MSR_DR
- sync
- mtmsr r0
- sync
- isync
- stb r3,0(r4)
- sync
- mtmsr r7
- sync
- isync
- blr
-_ASM_NOKPROBE_SYMBOL(real_writeb)
-
-#endif /* CONFIG_40x */
-
/*
* Copy a whole page. We use the dcbz instruction on the destination
* to reduce memory traffic (it eliminates the unnecessary reads of
@@ -382,7 +316,7 @@ EXPORT_SYMBOL(__bswapdi2)
_GLOBAL(start_secondary_resume)
/* Reset stack */
rlwinm r1, r1, 0, 0, 31 - THREAD_SHIFT
- addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE
li r3,0
stw r3,0(r1) /* Zero the stack frame pointer */
bl start_secondary
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index fd6d8d3a548e..a997c7f43dc0 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -9,6 +9,8 @@
* PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
*/
+#include <linux/export.h>
+#include <linux/linkage.h>
#include <linux/sys.h>
#include <asm/unistd.h>
#include <asm/errno.h>
@@ -22,7 +24,6 @@
#include <asm/kexec.h>
#include <asm/ptrace.h>
#include <asm/mmu.h>
-#include <asm/export.h>
#include <asm/feature-fixups.h>
.text
@@ -73,7 +74,7 @@ _GLOBAL(rmci_off)
blr
#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
-#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
+#ifdef CONFIG_PPC_PMAC
/*
* Do an IO access in real mode
@@ -136,7 +137,7 @@ _GLOBAL(real_writeb)
sync
isync
blr
-#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */
+#endif // CONFIG_PPC_PMAC
#ifdef CONFIG_PPC_PASEMI
@@ -173,7 +174,7 @@ _GLOBAL(real_205_writeb)
#endif /* CONFIG_PPC_PASEMI */
-#if defined(CONFIG_CPU_FREQ_PMAC64) || defined(CONFIG_CPU_FREQ_MAPLE)
+#ifdef CONFIG_CPU_FREQ_PMAC64
/*
* SCOM access functions for 970 (FX only for now)
*
@@ -191,7 +192,7 @@ _GLOBAL(scom970_read)
xori r0,r0,MSR_EE
mtmsrd r0,1
- /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
+ /* rotate 24 bits SCOM address 8 bits left and mask out its low 8 bits
* (including parity). On current CPUs they must be 0'd,
* and finally or in RW bit
*/
@@ -225,7 +226,7 @@ _GLOBAL(scom970_write)
xori r0,r0,MSR_EE
mtmsrd r0,1
- /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
+ /* rotate 24 bits SCOM address 8 bits left and mask out its low 8 bits
* (including parity). On current CPUs they must be 0'd.
*/
@@ -242,7 +243,7 @@ _GLOBAL(scom970_write)
/* restore interrupts */
mtmsrd r5,1
blr
-#endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */
+#endif // CONFIG_CPU_FREQ_PMAC64
/* kexec_wait(phys_cpu)
*
@@ -286,7 +287,7 @@ kexec_flag:
#ifdef CONFIG_KEXEC_CORE
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
/*
* BOOK3E has no real MMU mode, so we have to setup the initial TLB
* for a core to identity map v:0 to p:0. This current implementation
@@ -353,8 +354,8 @@ _GLOBAL(kexec_smp_wait)
*
* don't overwrite r3 here, it is live for kexec_wait above.
*/
-real_mode: /* assume normal blr return */
-#ifdef CONFIG_PPC_BOOK3E
+SYM_FUNC_START_LOCAL(real_mode) /* assume normal blr return */
+#ifdef CONFIG_PPC_BOOK3E_64
/* Create an identity mapping. */
b kexec_create_tlb
#else
@@ -370,6 +371,7 @@ real_mode: /* assume normal blr return */
mtspr SPRN_SRR0,r11
rfid
#endif
+SYM_FUNC_END(real_mode)
/*
* kexec_sequence(newstack, start, image, control, clear_all(),
@@ -384,7 +386,7 @@ _GLOBAL(kexec_sequence)
std r0,16(r1)
/* switch stacks to newstack -- &kexec_stack.stack */
- stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
+ stdu r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r3)
mr r1,r3
li r0,0
@@ -401,7 +403,7 @@ _GLOBAL(kexec_sequence)
std r26,-48(r1)
std r25,-56(r1)
- stdu r1,-STACK_FRAME_OVERHEAD-64(r1)
+ stdu r1,-STACK_FRAME_MIN_SIZE-64(r1)
/* save args into preserved regs */
mr r31,r3 /* newstack (both) */
@@ -413,7 +415,7 @@ _GLOBAL(kexec_sequence)
lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */
/* disable interrupts, we are overwriting kernel data next */
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
wrteei 0
#else
mfmsr r3
@@ -430,7 +432,7 @@ _GLOBAL(kexec_sequence)
1:
/* copy dest pages, flush whole dest image */
mr r3,r29
- bl kexec_copy_flush /* (image) */
+ bl CFUNC(kexec_copy_flush) /* (image) */
/* turn off mmu now if not done earlier */
cmpdi r26,0
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index f6d6ae0a1692..baeb24c102c8 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -7,7 +7,6 @@
#include <linux/elf.h>
#include <linux/moduleloader.h>
#include <linux/err.h>
-#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/bug.h>
#include <asm/module.h>
@@ -17,8 +16,6 @@
#include <asm/setup.h>
#include <asm/sections.h>
-static LIST_HEAD(module_bug_list);
-
static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
const char *name)
@@ -88,40 +85,3 @@ int module_finalize(const Elf_Ehdr *hdr,
return 0;
}
-
-static __always_inline void *
-__module_alloc(unsigned long size, unsigned long start, unsigned long end, bool nowarn)
-{
- pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
- gfp_t gfp = GFP_KERNEL | (nowarn ? __GFP_NOWARN : 0);
-
- /*
- * Don't do huge page allocations for modules yet until more testing
- * is done. STRICT_MODULE_RWX may require extra work to support this
- * too.
- */
- return __vmalloc_node_range(size, 1, start, end, gfp, prot,
- VM_FLUSH_RESET_PERMS,
- NUMA_NO_NODE, __builtin_return_address(0));
-}
-
-void *module_alloc(unsigned long size)
-{
-#ifdef MODULES_VADDR
- unsigned long limit = (unsigned long)_etext - SZ_32M;
- void *ptr = NULL;
-
- BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
-
- /* First try within 32M limit from _etext to avoid branch trampolines */
- if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit)
- ptr = __module_alloc(size, limit, MODULES_END, true);
-
- if (!ptr)
- ptr = __module_alloc(size, MODULES_VADDR, MODULES_END, false);
-
- return ptr;
-#else
- return __module_alloc(size, VMALLOC_START, VMALLOC_END, false);
-#endif
-}
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index ea6536171778..f930e3395a7f 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -18,7 +18,7 @@
#include <linux/bug.h>
#include <linux/sort.h>
#include <asm/setup.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
/* Count how many different relocations (different symbol, different
addend) */
@@ -163,8 +163,7 @@ static uint32_t do_plt_call(void *location,
pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location);
/* Init, or core PLT? */
- if (location >= mod->core_layout.base
- && location < mod->core_layout.base + mod->core_layout.size)
+ if (within_module_core((unsigned long)location, mod))
entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr;
else
entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr;
@@ -322,14 +321,14 @@ notrace int module_trampoline_target(struct module *mod, unsigned long addr,
int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs)
{
- module->arch.tramp = do_plt_call(module->core_layout.base,
+ module->arch.tramp = do_plt_call(module->mem[MOD_TEXT].base,
(unsigned long)ftrace_caller,
sechdrs, module);
if (!module->arch.tramp)
return -ENOENT;
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
- module->arch.tramp_regs = do_plt_call(module->core_layout.base,
+ module->arch.tramp_regs = do_plt_call(module->mem[MOD_TEXT].base,
(unsigned long)ftrace_regs_caller,
sechdrs, module);
if (!module->arch.tramp_regs)
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 7e45dc98df8a..126bf3b06ab7 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -17,7 +17,7 @@
#include <linux/kernel.h>
#include <asm/module.h>
#include <asm/firmware.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <linux/sort.h>
#include <asm/setup.h>
#include <asm/sections.h>
@@ -31,6 +31,16 @@
this, and makes other things simpler. Anton?
--RR. */
+bool module_elf_check_arch(Elf_Ehdr *hdr)
+{
+ unsigned long abi_level = hdr->e_flags & 0x3;
+
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
+ return abi_level == 2;
+ else
+ return abi_level < 2;
+}
+
#ifdef CONFIG_PPC64_ELF_ABI_V2
static func_desc_t func_desc(unsigned long addr)
@@ -91,32 +101,45 @@ static unsigned long stub_func_addr(func_desc_t func)
/* Like PPC32, we need little trampolines to do > 24-bit jumps (into
the kernel itself). But on PPC64, these need to be used for every
jump, actually, to reset r2 (TOC+0x8000). */
-struct ppc64_stub_entry
-{
- /* 28 byte jump instruction sequence (7 instructions). We only
- * need 6 instructions on ABIv2 but we always allocate 7 so
- * so we don't have to modify the trampoline load instruction. */
+struct ppc64_stub_entry {
+ /*
+ * 28 byte jump instruction sequence (7 instructions) that can
+ * hold ppc64_stub_insns or stub_insns. Must be 8-byte aligned
+ * with PCREL kernels that use prefix instructions in the stub.
+ */
u32 jump[7];
/* Used by ftrace to identify stubs */
u32 magic;
/* Data for the above code */
func_desc_t funcdata;
+} __aligned(8);
+
+struct ppc64_got_entry {
+ u64 addr;
};
/*
* PPC64 uses 24 bit jumps, but we need to jump into other modules or
* the kernel which may be further. So we jump to a stub.
*
- * For ELFv1 we need to use this to set up the new r2 value (aka TOC
- * pointer). For ELFv2 it's the callee's responsibility to set up the
- * new r2, but for both we need to save the old r2.
+ * Target address and TOC are loaded from function descriptor in the
+ * ppc64_stub_entry.
+ *
+ * r12 is used to generate the target address, which is required for the
+ * ELFv2 global entry point calling convention.
*
- * We could simply patch the new r2 value and function pointer into
- * the stub, but it's significantly shorter to put these values at the
- * end of the stub code, and patch the stub address (32-bits relative
- * to the TOC ptr, r2) into the stub.
+ * TOC handling:
+ * - PCREL does not have a TOC.
+ * - ELFv2 non-PCREL just has to save r2, the callee is responsible for
+ * setting its own TOC pointer at the global entry address.
+ * - ELFv1 must load the new TOC pointer from the function descriptor.
*/
static u32 ppc64_stub_insns[] = {
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ /* pld r12,addr */
+ PPC_PREFIX_8LS | __PPC_PRFX_R(1),
+ PPC_INST_PLD | ___PPC_RT(_R12),
+#else
PPC_RAW_ADDIS(_R11, _R2, 0),
PPC_RAW_ADDI(_R11, _R11, 0),
/* Save current r2 value in magic place on the stack. */
@@ -126,13 +149,17 @@ static u32 ppc64_stub_insns[] = {
/* Set up new r2 from function descriptor */
PPC_RAW_LD(_R2, _R11, 40),
#endif
+#endif
PPC_RAW_MTCTR(_R12),
PPC_RAW_BCTR(),
};
-/* Count how many different 24-bit relocations (different symbol,
- different addend) */
-static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num)
+/*
+ * Count how many different r_type relocations (different symbol,
+ * different addend).
+ */
+static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num,
+ unsigned long r_type)
{
unsigned int i, r_info, r_addend, _count_relocs;
@@ -141,8 +168,8 @@ static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num)
r_info = 0;
r_addend = 0;
for (i = 0; i < num; i++)
- /* Only count 24-bit relocs, others don't need stubs */
- if (ELF64_R_TYPE(rela[i].r_info) == R_PPC_REL24 &&
+ /* Only count r_type relocs, others don't need stubs */
+ if (ELF64_R_TYPE(rela[i].r_info) == r_type &&
(r_info != ELF64_R_SYM(rela[i].r_info) ||
r_addend != rela[i].r_addend)) {
_count_relocs++;
@@ -178,7 +205,9 @@ static int relacmp(const void *_x, const void *_y)
/* Get size of potential trampolines required. */
static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
- const Elf64_Shdr *sechdrs)
+ const Elf64_Shdr *sechdrs,
+ char *secstrings,
+ struct module *me)
{
/* One extra reloc so it's always 0-addr terminated */
unsigned long relocs = 1;
@@ -203,23 +232,127 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
relocs += count_relocs((void *)sechdrs[i].sh_addr,
sechdrs[i].sh_size
- / sizeof(Elf64_Rela));
+ / sizeof(Elf64_Rela),
+ R_PPC_REL24);
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ relocs += count_relocs((void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size
+ / sizeof(Elf64_Rela),
+ R_PPC64_REL24_NOTOC);
+#endif
}
}
-#ifdef CONFIG_DYNAMIC_FTRACE
- /* make the trampoline to the ftrace_caller */
- relocs++;
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
- /* an additional one for ftrace_regs_caller */
- relocs++;
-#endif
+ /* stubs for ftrace_caller and ftrace_regs_caller */
+ relocs += IS_ENABLED(CONFIG_DYNAMIC_FTRACE) + IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS);
+
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ /* stubs for the function tracer */
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (!strcmp(secstrings + sechdrs[i].sh_name, "__patchable_function_entries")) {
+ me->arch.ool_stub_count = sechdrs[i].sh_size / sizeof(unsigned long);
+ me->arch.ool_stub_index = 0;
+ relocs += roundup(me->arch.ool_stub_count * sizeof(struct ftrace_ool_stub),
+ sizeof(struct ppc64_stub_entry)) /
+ sizeof(struct ppc64_stub_entry);
+ break;
+ }
+ }
#endif
pr_debug("Looks like a total of %lu stubs, max\n", relocs);
return relocs * sizeof(struct ppc64_stub_entry);
}
+#ifdef CONFIG_PPC_KERNEL_PCREL
+static int count_pcpu_relocs(const Elf64_Shdr *sechdrs,
+ const Elf64_Rela *rela, unsigned int num,
+ unsigned int symindex, unsigned int pcpu)
+{
+ unsigned int i, r_info, r_addend, _count_relocs;
+
+ _count_relocs = 0;
+ r_info = 0;
+ r_addend = 0;
+
+ for (i = 0; i < num; i++) {
+ Elf64_Sym *sym;
+
+ /* This is the symbol it is referring to */
+ sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
+ + ELF64_R_SYM(rela[i].r_info);
+
+ if (sym->st_shndx == pcpu &&
+ (r_info != ELF64_R_SYM(rela[i].r_info) ||
+ r_addend != rela[i].r_addend)) {
+ _count_relocs++;
+ r_info = ELF64_R_SYM(rela[i].r_info);
+ r_addend = rela[i].r_addend;
+ }
+ }
+
+ return _count_relocs;
+}
+
+/* Get size of potential GOT required. */
+static unsigned long get_got_size(const Elf64_Ehdr *hdr,
+ const Elf64_Shdr *sechdrs,
+ struct module *me)
+{
+ /* One extra reloc so it's always 0-addr terminated */
+ unsigned long relocs = 1;
+ unsigned int i, symindex = 0;
+
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (sechdrs[i].sh_type == SHT_SYMTAB) {
+ symindex = i;
+ break;
+ }
+ }
+ WARN_ON_ONCE(!symindex);
+
+ /* Every relocated section... */
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (sechdrs[i].sh_type == SHT_RELA) {
+ pr_debug("Found relocations in section %u\n", i);
+ pr_debug("Ptr: %p. Number: %llu\n", (void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size / sizeof(Elf64_Rela));
+
+ /*
+ * Sort the relocation information based on a symbol and
+ * addend key. This is a stable O(n*log n) complexity
+ * algorithm but it will reduce the complexity of
+ * count_relocs() to linear complexity O(n)
+ */
+ sort((void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size / sizeof(Elf64_Rela),
+ sizeof(Elf64_Rela), relacmp, NULL);
+
+ relocs += count_relocs((void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size
+ / sizeof(Elf64_Rela),
+ R_PPC64_GOT_PCREL34);
+
+ /*
+ * Percpu data access typically gets linked with
+ * REL34 relocations, but the percpu section gets
+ * moved at load time and requires that to be
+ * converted to GOT linkage.
+ */
+ if (IS_ENABLED(CONFIG_SMP) && symindex)
+ relocs += count_pcpu_relocs(sechdrs,
+ (void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size
+ / sizeof(Elf64_Rela),
+ symindex, me->arch.pcpu_section);
+ }
+ }
+
+ pr_debug("Looks like a total of %lu GOT entries, max\n", relocs);
+ return relocs * sizeof(struct ppc64_got_entry);
+}
+#else /* CONFIG_PPC_KERNEL_PCREL */
+
/* Still needed for ELFv2, for .TOC. */
static void dedotify_versions(struct modversion_info *vers,
unsigned long size)
@@ -232,6 +365,24 @@ static void dedotify_versions(struct modversion_info *vers,
}
}
+/* Same as normal versions, remove a leading dot if present. */
+static void dedotify_ext_version_names(char *str_seq, unsigned long size)
+{
+ unsigned long out = 0;
+ unsigned long in;
+ char last = '\0';
+
+ for (in = 0; in < size; in++) {
+ /* Skip one leading dot */
+ if (last == '\0' && str_seq[in] == '.')
+ in++;
+ last = str_seq[in];
+ str_seq[out++] = last;
+ }
+ /* Zero the trailing portion of the names table for robustness */
+ memset(&str_seq[out], 0, size - out);
+}
+
/*
* Undefined symbols which refer to .funcname, hack to funcname. Make .TOC.
* seem to be defined (value set later).
@@ -269,6 +420,7 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs,
}
return NULL;
}
+#endif /* CONFIG_PPC_KERNEL_PCREL */
bool module_init_section(const char *name)
{
@@ -287,20 +439,32 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
for (i = 1; i < hdr->e_shnum; i++) {
if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0)
me->arch.stubs_section = i;
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ else if (strcmp(secstrings + sechdrs[i].sh_name, ".data..percpu") == 0)
+ me->arch.pcpu_section = i;
+ else if (strcmp(secstrings + sechdrs[i].sh_name, ".mygot") == 0) {
+ me->arch.got_section = i;
+ if (sechdrs[i].sh_addralign < 8)
+ sechdrs[i].sh_addralign = 8;
+ }
+#else
else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) {
me->arch.toc_section = i;
if (sechdrs[i].sh_addralign < 8)
sechdrs[i].sh_addralign = 8;
- }
- else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0)
+ } else if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0)
dedotify_versions((void *)hdr + sechdrs[i].sh_offset,
sechdrs[i].sh_size);
+ else if (strcmp(secstrings + sechdrs[i].sh_name, "__version_ext_names") == 0)
+ dedotify_ext_version_names((void *)hdr + sechdrs[i].sh_offset,
+ sechdrs[i].sh_size);
if (sechdrs[i].sh_type == SHT_SYMTAB)
dedotify((void *)hdr + sechdrs[i].sh_offset,
sechdrs[i].sh_size / sizeof(Elf64_Sym),
(void *)hdr
+ sechdrs[sechdrs[i].sh_link].sh_offset);
+#endif
}
if (!me->arch.stubs_section) {
@@ -308,26 +472,47 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
return -ENOEXEC;
}
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ if (!me->arch.got_section) {
+ pr_err("%s: doesn't contain .mygot.\n", me->name);
+ return -ENOEXEC;
+ }
+
+ /* Override the got size */
+ sechdrs[me->arch.got_section].sh_size = get_got_size(hdr, sechdrs, me);
+#else
/* If we don't have a .toc, just use .stubs. We need to set r2
to some reasonable value in case the module calls out to
other functions via a stub, or if a function pointer escapes
the module by some means. */
if (!me->arch.toc_section)
me->arch.toc_section = me->arch.stubs_section;
+#endif
/* Override the stubs size */
- sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs);
+ sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs, secstrings, me);
+
return 0;
}
-#ifdef CONFIG_MPROFILE_KERNEL
+#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
static u32 stub_insns[] = {
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase)),
+ PPC_RAW_NOP(), /* align the prefix insn */
+ /* paddi r12,r12,addr */
+ PPC_PREFIX_MLS | __PPC_PRFX_R(0),
+ PPC_INST_PADDI | ___PPC_RT(_R12) | ___PPC_RA(_R12),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR(),
+#else
PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernel_toc)),
PPC_RAW_ADDIS(_R12, _R12, 0),
PPC_RAW_ADDI(_R12, _R12, 0),
PPC_RAW_MTCTR(_R12),
PPC_RAW_BCTR(),
+#endif
};
/*
@@ -348,18 +533,37 @@ static inline int create_ftrace_stub(struct ppc64_stub_entry *entry,
{
long reladdr;
- memcpy(entry->jump, stub_insns, sizeof(stub_insns));
-
- /* Stub uses address relative to kernel toc (from the paca) */
- reladdr = addr - kernel_toc_addr();
- if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
- pr_err("%s: Address of %ps out of range of kernel_toc.\n",
- me->name, (void *)addr);
+ if ((unsigned long)entry->jump % 8 != 0) {
+ pr_err("%s: Address of stub entry is not 8-byte aligned\n", me->name);
return 0;
}
- entry->jump[1] |= PPC_HA(reladdr);
- entry->jump[2] |= PPC_LO(reladdr);
+ BUILD_BUG_ON(sizeof(stub_insns) > sizeof(entry->jump));
+ memcpy(entry->jump, stub_insns, sizeof(stub_insns));
+
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
+ /* Stub uses address relative to kernel base (from the paca) */
+ reladdr = addr - local_paca->kernelbase;
+ if (reladdr > 0x1FFFFFFFFL || reladdr < -0x200000000L) {
+ pr_err("%s: Address of %ps out of range of 34-bit relative address.\n",
+ me->name, (void *)addr);
+ return 0;
+ }
+
+ entry->jump[2] |= IMM_H18(reladdr);
+ entry->jump[3] |= IMM_L(reladdr);
+ } else {
+ /* Stub uses address relative to kernel toc (from the paca) */
+ reladdr = addr - kernel_toc_addr();
+ if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+ pr_err("%s: Address of %ps out of range of kernel_toc.\n",
+ me->name, (void *)addr);
+ return 0;
+ }
+
+ entry->jump[1] |= PPC_HA(reladdr);
+ entry->jump[2] |= PPC_LO(reladdr);
+ }
/* Even though we don't use funcdata in the stub, it's needed elsewhere. */
entry->funcdata = func_desc(addr);
@@ -405,7 +609,11 @@ static bool is_mprofile_ftrace_call(const char *name)
*/
static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me)
{
+#ifndef CONFIG_PPC_KERNEL_PCREL
return (sechdrs[me->arch.toc_section].sh_addr & ~0xfful) + 0x8000;
+#else
+ return -1;
+#endif
}
/* Patch stub to reference function and correct r2 value. */
@@ -422,38 +630,62 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
if (is_mprofile_ftrace_call(name))
return create_ftrace_stub(entry, addr, me);
+ if ((unsigned long)entry->jump % 8 != 0) {
+ pr_err("%s: Address of stub entry is not 8-byte aligned\n", me->name);
+ return 0;
+ }
+
+ BUILD_BUG_ON(sizeof(ppc64_stub_insns) > sizeof(entry->jump));
for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) {
if (patch_instruction(&entry->jump[i],
ppc_inst(ppc64_stub_insns[i])))
return 0;
}
- /* Stub uses address relative to r2. */
- reladdr = (unsigned long)entry - my_r2(sechdrs, me);
- if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
- pr_err("%s: Address %p of stub out of range of %p.\n",
- me->name, (void *)reladdr, (void *)my_r2);
- return 0;
- }
- pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
+ /* Stub uses address relative to itself! */
+ reladdr = 0 + offsetof(struct ppc64_stub_entry, funcdata);
+ BUILD_BUG_ON(reladdr != 32);
+ if (reladdr > 0x1FFFFFFFFL || reladdr < -0x200000000L) {
+ pr_err("%s: Address of %p out of range of 34-bit relative address.\n",
+ me->name, (void *)reladdr);
+ return 0;
+ }
+ pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
- if (patch_instruction(&entry->jump[0],
- ppc_inst(entry->jump[0] | PPC_HA(reladdr))))
- return 0;
+ /* May not even need this if we're relative to 0 */
+ if (patch_instruction(&entry->jump[0],
+ ppc_inst_prefix(entry->jump[0] | IMM_H18(reladdr),
+ entry->jump[1] | IMM_L(reladdr))))
+ return 0;
- if (patch_instruction(&entry->jump[1],
- ppc_inst(entry->jump[1] | PPC_LO(reladdr))))
- return 0;
+ } else {
+ /* Stub uses address relative to r2. */
+ reladdr = (unsigned long)entry - my_r2(sechdrs, me);
+ if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+ pr_err("%s: Address %p of stub out of range of %p.\n",
+ me->name, (void *)reladdr, (void *)my_r2);
+ return 0;
+ }
+ pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
+
+ if (patch_instruction(&entry->jump[0],
+ ppc_inst(entry->jump[0] | PPC_HA(reladdr))))
+ return 0;
+
+ if (patch_instruction(&entry->jump[1],
+ ppc_inst(entry->jump[1] | PPC_LO(reladdr))))
+ return 0;
+ }
// func_desc_t is 8 bytes if ABIv2, else 16 bytes
desc = func_desc(addr);
for (i = 0; i < sizeof(func_desc_t) / sizeof(u32); i++) {
- if (patch_instruction(((u32 *)&entry->funcdata) + i,
- ppc_inst(((u32 *)(&desc))[i])))
+ if (patch_u32(((u32 *)&entry->funcdata) + i, ((u32 *)&desc)[i]))
return 0;
}
- if (patch_instruction(&entry->magic, ppc_inst(STUB_MAGIC)))
+ if (patch_u32(&entry->magic, STUB_MAGIC))
return 0;
return 1;
@@ -487,14 +719,49 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
return (unsigned long)&stubs[i];
}
+#ifdef CONFIG_PPC_KERNEL_PCREL
+/* Create GOT to load the location described in this ptr */
+static unsigned long got_for_addr(const Elf64_Shdr *sechdrs,
+ unsigned long addr,
+ struct module *me,
+ const char *name)
+{
+ struct ppc64_got_entry *got;
+ unsigned int i, num_got;
+
+ if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ return addr;
+
+ num_got = sechdrs[me->arch.got_section].sh_size / sizeof(*got);
+
+ /* Find this stub, or if that fails, the next avail. entry */
+ got = (void *)sechdrs[me->arch.got_section].sh_addr;
+ for (i = 0; got[i].addr; i++) {
+ if (WARN_ON(i >= num_got))
+ return 0;
+
+ if (got[i].addr == addr)
+ return (unsigned long)&got[i];
+ }
+
+ got[i].addr = addr;
+
+ return (unsigned long)&got[i];
+}
+#endif
+
/* We expect a noop next: if it is, replace it with instruction to
restore r2. */
static int restore_r2(const char *name, u32 *instruction, struct module *me)
{
u32 *prev_insn = instruction - 1;
+ u32 insn_val = *instruction;
+
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ return 0;
if (is_mprofile_ftrace_call(name))
- return 1;
+ return 0;
/*
* Make sure the branch isn't a sibling call. Sibling calls aren't
@@ -502,19 +769,25 @@ static int restore_r2(const char *name, u32 *instruction, struct module *me)
* restore afterwards.
*/
if (!instr_is_relative_link_branch(ppc_inst(*prev_insn)))
- return 1;
+ return 0;
- if (*instruction != PPC_RAW_NOP()) {
- pr_err("%s: Expected nop after call, got %08x at %pS\n",
- me->name, *instruction, instruction);
+ /*
+ * For livepatch, the restore r2 instruction might have already been
+ * written previously, if the referenced symbol is in a previously
+ * unloaded module which is now being loaded again. In that case, skip
+ * the warning and the instruction write.
+ */
+ if (insn_val == PPC_INST_LD_TOC)
return 0;
+
+ if (insn_val != PPC_RAW_NOP()) {
+ pr_err("%s: Expected nop after call, got %08x at %pS\n",
+ me->name, insn_val, instruction);
+ return -ENOEXEC;
}
/* ld r2,R2_STACK_OFFSET(r1) */
- if (patch_instruction(instruction, ppc_inst(PPC_INST_LD_TOC)))
- return 0;
-
- return 1;
+ return patch_instruction(instruction, ppc_inst(PPC_INST_LD_TOC));
}
int apply_relocate_add(Elf64_Shdr *sechdrs,
@@ -532,6 +805,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
pr_debug("Applying ADD relocate section %u to %u\n", relsec,
sechdrs[relsec].sh_info);
+#ifndef CONFIG_PPC_KERNEL_PCREL
/* First time we're called, we can fix up .TOC. */
if (!me->arch.toc_fixed) {
sym = find_dot_toc(sechdrs, strtab, symindex);
@@ -541,7 +815,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
sym->st_value = my_r2(sechdrs, me);
me->arch.toc_fixed = true;
}
-
+#endif
for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
/* This is where to make the change */
location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
@@ -569,6 +843,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
*(unsigned long *)location = value;
break;
+#ifndef CONFIG_PPC_KERNEL_PCREL
case R_PPC64_TOC:
*(unsigned long *)location = my_r2(sechdrs, me);
break;
@@ -628,8 +903,13 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
= (*((uint16_t *) location) & ~0xffff)
| (value & 0xffff);
break;
+#endif
case R_PPC_REL24:
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ /* PCREL still generates REL24 for mcount */
+ case R_PPC64_REL24_NOTOC:
+#endif
/* FIXME: Handle weak symbols here --RR */
if (sym->st_shndx == SHN_UNDEF ||
sym->st_shndx == SHN_LIVEPATCH) {
@@ -638,8 +918,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
strtab + sym->st_name);
if (!value)
return -ENOENT;
- if (!restore_r2(strtab + sym->st_name,
- (u32 *)location + 1, me))
+ if (restore_r2(strtab + sym->st_name,
+ (u32 *)location + 1, me))
return -ENOEXEC;
} else
value += local_entry_offset(sym);
@@ -677,6 +957,47 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
*(u32 *)location = value;
break;
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ case R_PPC64_PCREL34: {
+ unsigned long absvalue = value;
+
+ /* Convert value to relative */
+ value -= (unsigned long)location;
+
+ if (value + 0x200000000 > 0x3ffffffff) {
+ if (sym->st_shndx != me->arch.pcpu_section) {
+ pr_err("%s: REL34 %li out of range!\n",
+ me->name, (long)value);
+ return -ENOEXEC;
+ }
+
+ /*
+ * per-cpu section is special cased because
+ * it is moved during loading, so has to be
+ * converted to use GOT.
+ */
+ value = got_for_addr(sechdrs, absvalue, me,
+ strtab + sym->st_name);
+ if (!value)
+ return -ENOENT;
+ value -= (unsigned long)location;
+
+ /* Turn pla into pld */
+ if (patch_instruction((u32 *)location,
+ ppc_inst_prefix((*(u32 *)location & ~0x02000000),
+ (*((u32 *)location + 1) & ~0xf8000000) | 0xe4000000)))
+ return -EFAULT;
+ }
+
+ if (patch_instruction((u32 *)location,
+ ppc_inst_prefix((*(u32 *)location & ~0x3ffff) | IMM_H18(value),
+ (*((u32 *)location + 1) & ~0xffff) | IMM_L(value))))
+ return -EFAULT;
+
+ break;
+ }
+
+#else
case R_PPC64_TOCSAVE:
/*
* Marker reloc indicates we don't have to save r2.
@@ -684,8 +1005,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
* it.
*/
break;
+#endif
case R_PPC64_ENTRY:
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ break;
+
/*
* Optimize ELFv2 large code model entry point if
* the TOC is within 2GB range of current location.
@@ -728,6 +1053,20 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
| (value & 0xffff);
break;
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ case R_PPC64_GOT_PCREL34:
+ value = got_for_addr(sechdrs, value, me,
+ strtab + sym->st_name);
+ if (!value)
+ return -ENOENT;
+ value -= (unsigned long)location;
+ ((uint32_t *)location)[0] = (((uint32_t *)location)[0] & ~0x3ffff) |
+ ((value >> 16) & 0x3ffff);
+ ((uint32_t *)location)[1] = (((uint32_t *)location)[1] & ~0xffff) |
+ (value & 0xffff);
+ break;
+#endif
+
default:
pr_err("%s: Unknown ADD relocation: %lu\n",
me->name,
@@ -776,6 +1115,37 @@ int module_trampoline_target(struct module *mod, unsigned long addr,
return 0;
}
+static int setup_ftrace_ool_stubs(const Elf64_Shdr *sechdrs, unsigned long addr, struct module *me)
+{
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ unsigned int i, total_stubs, num_stubs;
+ struct ppc64_stub_entry *stub;
+
+ total_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stub);
+ num_stubs = roundup(me->arch.ool_stub_count * sizeof(struct ftrace_ool_stub),
+ sizeof(struct ppc64_stub_entry)) / sizeof(struct ppc64_stub_entry);
+
+ /* Find the next available entry */
+ stub = (void *)sechdrs[me->arch.stubs_section].sh_addr;
+ for (i = 0; stub_func_addr(stub[i].funcdata); i++)
+ if (WARN_ON(i >= total_stubs))
+ return -1;
+
+ if (WARN_ON(i + num_stubs > total_stubs))
+ return -1;
+
+ stub += i;
+ me->arch.ool_stubs = (struct ftrace_ool_stub *)stub;
+
+ /* reserve stubs */
+ for (i = 0; i < num_stubs; i++)
+ if (patch_u32((void *)&stub->funcdata, PPC_RAW_NOP()))
+ return -1;
+#endif
+
+ return 0;
+}
+
int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
{
mod->arch.tramp = stub_for_addr(sechdrs,
@@ -794,6 +1164,9 @@ int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
if (!mod->arch.tramp)
return -ENOENT;
+ if (setup_ftrace_ool_stubs(sechdrs, mod->arch.tramp, mod))
+ return -ENOENT;
+
return 0;
}
#endif
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index e385d3164648..f9c6568a9137 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -73,7 +73,7 @@ static const char *nvram_os_partitions[] = {
};
static void oops_to_nvram(struct kmsg_dumper *dumper,
- enum kmsg_dump_reason reason);
+ struct kmsg_dump_detail *detail);
static struct kmsg_dumper nvram_kmsg_dumper = {
.dump = oops_to_nvram
@@ -643,7 +643,7 @@ void __init nvram_init_oops_partition(int rtas_partition_exists)
* partition. If that's too much, go back and capture uncompressed text.
*/
static void oops_to_nvram(struct kmsg_dumper *dumper,
- enum kmsg_dump_reason reason)
+ struct kmsg_dump_detail *detail)
{
struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
static unsigned int oops_count = 0;
@@ -655,7 +655,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ;
int rc = -1;
- switch (reason) {
+ switch (detail->reason) {
case KMSG_DUMP_SHUTDOWN:
/* These are almost always orderly shutdowns. */
return;
@@ -671,7 +671,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
break;
default:
pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n",
- __func__, (int) reason);
+ __func__, (int) detail->reason);
return;
}
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
deleted file mode 100644
index f89376ff633e..000000000000
--- a/arch/powerpc/kernel/of_platform.c
+++ /dev/null
@@ -1,104 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp.
- * <benh@kernel.crashing.org>
- * and Arnd Bergmann, IBM Corp.
- */
-
-#undef DEBUG
-
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/mod_devicetable.h>
-#include <linux/pci.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
-#include <linux/atomic.h>
-
-#include <asm/errno.h>
-#include <asm/topology.h>
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-#include <asm/eeh.h>
-
-#ifdef CONFIG_PPC_OF_PLATFORM_PCI
-
-/* The probing of PCI controllers from of_platform is currently
- * 64 bits only, mostly due to gratuitous differences between
- * the 32 and 64 bits PCI code on PowerPC and the 32 bits one
- * lacking some bits needed here.
- */
-
-static int of_pci_phb_probe(struct platform_device *dev)
-{
- struct pci_controller *phb;
-
- /* Check if we can do that ... */
- if (ppc_md.pci_setup_phb == NULL)
- return -ENODEV;
-
- pr_info("Setting up PCI bus %pOF\n", dev->dev.of_node);
-
- /* Alloc and setup PHB data structure */
- phb = pcibios_alloc_controller(dev->dev.of_node);
- if (!phb)
- return -ENODEV;
-
- /* Setup parent in sysfs */
- phb->parent = &dev->dev;
-
- /* Setup the PHB using arch provided callback */
- if (ppc_md.pci_setup_phb(phb)) {
- pcibios_free_controller(phb);
- return -ENODEV;
- }
-
- /* Process "ranges" property */
- pci_process_bridge_OF_ranges(phb, dev->dev.of_node, 0);
-
- /* Init pci_dn data structures */
- pci_devs_phb_init_dynamic(phb);
-
- /* Create EEH PE for the PHB */
- eeh_phb_pe_create(phb);
-
- /* Scan the bus */
- pcibios_scan_phb(phb);
- if (phb->bus == NULL)
- return -ENXIO;
-
- /* Claim resources. This might need some rework as well depending
- * whether we are doing probe-only or not, like assigning unassigned
- * resources etc...
- */
- pcibios_claim_one_bus(phb->bus);
-
- /* Add probed PCI devices to the device model */
- pci_bus_add_devices(phb->bus);
-
- return 0;
-}
-
-static const struct of_device_id of_pci_phb_ids[] = {
- { .type = "pci", },
- { .type = "pcix", },
- { .type = "pcie", },
- { .type = "pciex", },
- { .type = "ht", },
- {}
-};
-
-static struct platform_driver of_pci_phb_driver = {
- .probe = of_pci_phb_probe,
- .driver = {
- .name = "of-pci",
- .of_match_table = of_pci_phb_ids,
- },
-};
-
-builtin_platform_driver(of_pci_phb_driver);
-
-#endif /* CONFIG_PPC_OF_PLATFORM_PCI */
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 3b1c2236cbee..2e83702bf9ba 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -13,7 +13,7 @@
#include <asm/kprobes.h>
#include <asm/ptrace.h>
#include <asm/cacheflush.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/sstep.h>
#include <asm/ppc-opcode.h>
#include <asm/inst.h>
@@ -56,7 +56,7 @@ static unsigned long can_optimize(struct kprobe *p)
* has a 'nop' instruction, which can be emulated.
* So further checks can be skipped.
*/
- if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline)
+ if (p->addr == (kprobe_opcode_t *)&arch_rethook_trampoline)
return addr + sizeof(kprobe_opcode_t);
/*
@@ -112,7 +112,7 @@ static void optimized_callback(struct optimized_kprobe *op,
__this_cpu_write(current_kprobe, NULL);
}
- preempt_enable_no_resched();
+ preempt_enable();
}
NOKPROBE_SYMBOL(optimized_callback);
diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S
index 5c7f0b4b784b..35932f45fb4e 100644
--- a/arch/powerpc/kernel/optprobes_head.S
+++ b/arch/powerpc/kernel/optprobes_head.S
@@ -73,7 +73,7 @@ optprobe_template_entry:
* further below.
*/
#ifdef CONFIG_PPC64
- ld r2,PACATOC(r13)
+ LOAD_PACA_TOC()
#endif
.global optprobe_template_op_address
@@ -85,7 +85,7 @@ optprobe_template_op_address:
TEMPLATE_FOR_IMM_LOAD_INSNS
/* 2. pt_regs pointer in r4 */
- addi r4,r1,STACK_FRAME_OVERHEAD
+ addi r4,r1,STACK_INT_FRAME_REGS
.global optprobe_template_call_handler
optprobe_template_call_handler:
@@ -96,7 +96,7 @@ optprobe_template_call_handler:
* Parameters for instruction emulation:
* 1. Pass SP in register r3.
*/
- addi r3,r1,STACK_FRAME_OVERHEAD
+ addi r3,r1,STACK_INT_FRAME_REGS
.global optprobe_template_insn
optprobe_template_insn:
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index ba593fd60124..7502066c3c53 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -16,7 +16,6 @@
#include <asm/kexec.h>
#include <asm/svm.h>
#include <asm/ultravisor.h>
-#include <asm/rtas.h>
#include "setup.h"
@@ -69,7 +68,7 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long limit,
memblock_set_bottom_up(true);
/*
- * See Documentation/powerpc/ultravisor.rst for more details.
+ * See Documentation/arch/powerpc/ultravisor.rst for more details.
*
* UV/HV data sharing is in PAGE_SIZE granularity. In order to
* minimize the number of pages shared, align the allocation to
@@ -170,30 +169,6 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit)
}
#endif /* CONFIG_PPC_64S_HASH_MMU */
-#ifdef CONFIG_PPC_PSERIES
-/**
- * new_rtas_args() - Allocates rtas args
- * @cpu: CPU number
- * @limit: Memory limit for this allocation
- *
- * Allocates a struct rtas_args and return it's pointer,
- * if not in Hypervisor mode
- *
- * Return: Pointer to allocated rtas_args
- * NULL if CPU in Hypervisor Mode
- */
-static struct rtas_args * __init new_rtas_args(int cpu, unsigned long limit)
-{
- limit = min_t(unsigned long, limit, RTAS_INSTANTIATE_MAX);
-
- if (early_cpu_has_feature(CPU_FTR_HVMODE))
- return NULL;
-
- return alloc_paca_data(sizeof(struct rtas_args), L1_CACHE_BYTES,
- limit, cpu);
-}
-#endif /* CONFIG_PPC_PSERIES */
-
/* The Paca is an array with one entry per processor. Each contains an
* lppaca, which contains the information shared between the
* hypervisor and Linux.
@@ -211,12 +186,14 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
#ifdef CONFIG_PPC_PSERIES
new_paca->lppaca_ptr = NULL;
#endif
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
new_paca->kernel_pgd = swapper_pg_dir;
#endif
new_paca->lock_token = 0x8000;
new_paca->paca_index = cpu;
+#ifndef CONFIG_PPC_KERNEL_PCREL
new_paca->kernel_toc = kernel_toc_addr();
+#endif
new_paca->kernelbase = (unsigned long) _stext;
/* Only set MSR:IR/DR when MMU is initialized */
new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR);
@@ -228,14 +205,10 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
new_paca->slb_shadow_ptr = NULL;
#endif
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
/* For now -- if we have threads this will be adjusted later */
new_paca->tcd_ptr = &new_paca->tcd;
#endif
-
-#ifdef CONFIG_PPC_PSERIES
- new_paca->rtas_args_reentrant = NULL;
-#endif
}
/* Put the paca pointer into r13 and SPRG_PACA */
@@ -244,7 +217,7 @@ void setup_paca(struct paca_struct *new_paca)
/* Setup r13 */
local_paca = new_paca;
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
/* On Book3E, initialize the TLB miss exception frames */
mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
#else
@@ -308,9 +281,6 @@ void __init allocate_paca(int cpu)
#ifdef CONFIG_PPC_64S_HASH_MMU
paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
#endif
-#ifdef CONFIG_PPC_PSERIES
- paca->rtas_args_reentrant = new_rtas_args(cpu, limit);
-#endif
paca_struct_size += sizeof(struct paca_struct);
}
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 068410cd54a3..eac84d687b53 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -39,6 +39,7 @@
#include <asm/machdep.h>
#include <asm/ppc-pci.h>
#include <asm/eeh.h>
+#include <asm/setup.h>
#include "../../../drivers/pci/pci.h"
@@ -67,23 +68,35 @@ void __init set_pci_dma_ops(const struct dma_map_ops *dma_ops)
pci_dma_ops = dma_ops;
}
-/*
- * This function should run under locking protection, specifically
- * hose_spinlock.
- */
static int get_phb_number(struct device_node *dn)
{
int ret, phb_id = -1;
- u32 prop_32;
u64 prop;
/*
* Try fixed PHB numbering first, by checking archs and reading
- * the respective device-tree properties. Firstly, try powernv by
- * reading "ibm,opal-phbid", only present in OPAL environment.
+ * the respective device-tree properties. Firstly, try reading
+ * standard "linux,pci-domain", then try reading "ibm,opal-phbid"
+ * (only present in powernv OPAL environment), then try device-tree
+ * alias and as the last try to use lower bits of "reg" property.
*/
- ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
+ ret = of_get_pci_domain_nr(dn);
+ if (ret >= 0) {
+ prop = ret;
+ ret = 0;
+ }
+ if (ret)
+ ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
+
+ if (ret) {
+ ret = of_alias_get_id(dn, "pci");
+ if (ret >= 0) {
+ prop = ret;
+ ret = 0;
+ }
+ }
if (ret) {
+ u32 prop_32;
ret = of_property_read_u32_index(dn, "reg", 1, &prop_32);
prop = prop_32;
}
@@ -91,18 +104,20 @@ static int get_phb_number(struct device_node *dn)
if (!ret)
phb_id = (int)(prop & (MAX_PHBS - 1));
+ spin_lock(&hose_spinlock);
+
/* We need to be sure to not use the same PHB number twice. */
if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap))
- return phb_id;
+ goto out_unlock;
- /*
- * If not pseries nor powernv, or if fixed PHB numbering tried to add
- * the same PHB number twice, then fallback to dynamic PHB numbering.
- */
+ /* If everything fails then fallback to dynamic PHB numbering. */
phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS);
BUG_ON(phb_id >= MAX_PHBS);
set_bit(phb_id, phb_bitmap);
+out_unlock:
+ spin_unlock(&hose_spinlock);
+
return phb_id;
}
@@ -110,14 +125,17 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
{
struct pci_controller *phb;
- phb = zalloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL);
+ phb = kzalloc(sizeof(struct pci_controller), GFP_KERNEL);
if (phb == NULL)
return NULL;
- spin_lock(&hose_spinlock);
+
phb->global_number = get_phb_number(dev);
+
+ spin_lock(&hose_spinlock);
list_add_tail(&phb->list_node, &hose_list);
spin_unlock(&hose_spinlock);
- phb->dn = dev;
+
+ phb->dn = of_node_get(dev);
phb->is_dynamic = slab_is_available();
#ifdef CONFIG_PPC64
if (dev) {
@@ -140,7 +158,7 @@ void pcibios_free_controller(struct pci_controller *phb)
/* Clear bit of phb_bitmap to allow reuse of this PHB number. */
if (phb->global_number < MAX_PHBS)
clear_bit(phb->global_number, phb_bitmap);
-
+ of_node_put(phb->dn);
list_del(&phb->list_node);
spin_unlock(&hose_spinlock);
@@ -499,12 +517,11 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma)
}
/*
- * This one is used by /dev/mem and fbdev who have no clue about the
+ * This one is used by /dev/mem and video who have no clue about the
* PCI device, it tries to find the PCI device first and calls the
* above routine
*/
-pgprot_t pci_phys_mem_access_prot(struct file *file,
- unsigned long pfn,
+pgprot_t pci_phys_mem_access_prot(unsigned long pfn,
unsigned long size,
pgprot_t prot)
{
@@ -862,6 +879,7 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
static void pcibios_fixup_resources(struct pci_dev *dev)
{
struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct resource *res;
int i;
if (!hose) {
@@ -873,9 +891,9 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
if (dev->is_virtfn)
return;
- for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
- struct resource *res = dev->resource + i;
+ pci_dev_for_each_resource(dev, res, i) {
struct pci_bus_region reg;
+
if (!res->flags)
continue;
@@ -1087,7 +1105,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
*/
pci_read_bridge_bases(bus);
- /* Now fixup the bus bus */
+ /* Now fixup the bus */
pcibios_setup_bus_self(bus);
}
EXPORT_SYMBOL(pcibios_fixup_bus);
@@ -1434,11 +1452,10 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
struct pci_bus *child_bus;
list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct resource *r;
int i;
- for (i = 0; i < PCI_NUM_RESOURCES; i++) {
- struct resource *r = &dev->resource[i];
-
+ pci_dev_for_each_resource(dev, r, i) {
if (r->parent || !r->start || !r->flags)
continue;
@@ -1687,19 +1704,20 @@ EXPORT_SYMBOL_GPL(pcibios_scan_phb);
static void fixup_hide_host_resource_fsl(struct pci_dev *dev)
{
- int i, class = dev->class >> 8;
+ int class = dev->class >> 8;
/* When configured as agent, programming interface = 1 */
int prog_if = dev->class & 0xf;
+ struct resource *r;
if ((class == PCI_CLASS_PROCESSOR_POWERPC ||
class == PCI_CLASS_BRIDGE_OTHER) &&
(dev->hdr_type == PCI_HEADER_TYPE_NORMAL) &&
(prog_if == 0) &&
(dev->bus->parent == NULL)) {
- for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
- dev->resource[i].start = 0;
- dev->resource[i].end = 0;
- dev->resource[i].flags = 0;
+ pci_dev_for_each_resource(dev, r) {
+ r->start = 0;
+ r->end = 0;
+ r->flags = 0;
}
}
}
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 0fe251c6ac2c..6f444d0822d8 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -93,6 +93,36 @@ void pci_hp_remove_devices(struct pci_bus *bus)
}
EXPORT_SYMBOL_GPL(pci_hp_remove_devices);
+static void traverse_siblings_and_scan_slot(struct device_node *start, struct pci_bus *bus)
+{
+ struct device_node *dn;
+ int slotno;
+
+ u32 class = 0;
+
+ if (!of_property_read_u32(start->child, "class-code", &class)) {
+ /* Call of pci_scan_slot for non-bridge/EP case */
+ if (!((class >> 8) == PCI_CLASS_BRIDGE_PCI)) {
+ slotno = PCI_SLOT(PCI_DN(start->child)->devfn);
+ pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+ return;
+ }
+ }
+
+ /* Iterate all siblings */
+ for_each_child_of_node(start, dn) {
+ class = 0;
+
+ if (!of_property_read_u32(start->child, "class-code", &class)) {
+ /* Call of pci_scan_slot on each sibling-nodes/bridge-ports */
+ if ((class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+ slotno = PCI_SLOT(PCI_DN(dn)->devfn);
+ pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+ }
+ }
+ }
+}
+
/**
* pci_hp_add_devices - adds new pci devices to bus
* @bus: the indicated PCI bus
@@ -106,11 +136,14 @@ EXPORT_SYMBOL_GPL(pci_hp_remove_devices);
*/
void pci_hp_add_devices(struct pci_bus *bus)
{
- int slotno, mode, max;
+ int mode, max;
struct pci_dev *dev;
struct pci_controller *phb;
struct device_node *dn = pci_bus_to_OF_node(bus);
+ if (!dn)
+ return;
+
phb = pci_bus_to_host(bus);
mode = PCI_PROBE_NORMAL;
@@ -129,8 +162,7 @@ void pci_hp_add_devices(struct pci_bus *bus)
* order for fully rescan all the way down to pick them up.
* They can have been removed during partial hotplug.
*/
- slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
- pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+ traverse_siblings_and_scan_slot(dn, bus);
max = bus->busn_res.start;
/*
* Scan bridges that are already configured. We don't touch
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 5a174936c9a0..f8a3bd8cfae4 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -36,18 +36,13 @@ int pcibios_assign_bus_offset = 1;
EXPORT_SYMBOL(isa_io_base);
EXPORT_SYMBOL(pci_dram_offset);
-void __init pcibios_make_OF_bus_map(void);
-
static void fixup_cpc710_pci64(struct pci_dev* dev);
-static u8* pci_to_OF_bus_map;
/* By default, we don't re-assign bus numbers. We do this only on
* some pmacs
*/
static int pci_assign_all_buses;
-static int pci_bus_count;
-
/* This will remain NULL for now, until isa-bridge.c is made common
* to both 32-bit and 64-bit.
*/
@@ -67,6 +62,11 @@ fixup_cpc710_pci64(struct pci_dev* dev)
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CPC710_PCI64, fixup_cpc710_pci64);
+#ifdef CONFIG_PPC_PCI_OF_BUS_MAP
+
+static u8* pci_to_OF_bus_map;
+static int pci_bus_count;
+
/*
* Functions below are used on OpenFirmware machines.
*/
@@ -108,7 +108,7 @@ make_one_node_map(struct device_node* node, u8 pci_bus)
}
}
-void __init
+static void __init
pcibios_make_OF_bus_map(void)
{
int i;
@@ -152,14 +152,18 @@ pcibios_make_OF_bus_map(void)
}
#endif
}
+#endif // CONFIG_PPC_PCI_OF_BUS_MAP
+#ifdef CONFIG_PPC_PMAC
/*
* Returns the PCI device matching a given OF node
*/
int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn)
{
+#ifdef CONFIG_PPC_PCI_OF_BUS_MAP
struct pci_dev *dev = NULL;
+#endif
const __be32 *reg;
int size;
@@ -174,6 +178,9 @@ int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn)
*bus = (be32_to_cpup(&reg[0]) >> 16) & 0xff;
*devfn = (be32_to_cpup(&reg[0]) >> 8) & 0xff;
+#ifndef CONFIG_PPC_PCI_OF_BUS_MAP
+ return 0;
+#else
/* Ok, here we need some tweak. If we have already renumbered
* all busses, we can't rely on the OF bus number any more.
* the pci_to_OF_bus_map is not enough as several PCI busses
@@ -191,9 +198,12 @@ int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn)
}
return -ENODEV;
+#endif // CONFIG_PPC_PCI_OF_BUS_MAP
}
EXPORT_SYMBOL(pci_device_from_OF_node);
+#endif
+#ifdef CONFIG_PPC_PCI_OF_BUS_MAP
/* We create the "pci-OF-bus-map" property now so it appears in the
* /proc device tree
*/
@@ -203,11 +213,8 @@ pci_create_OF_bus_map(void)
struct property* of_prop;
struct device_node *dn;
- of_prop = memblock_alloc(sizeof(struct property) + 256,
+ of_prop = memblock_alloc_or_panic(sizeof(struct property) + 256,
SMP_CACHE_BYTES);
- if (!of_prop)
- panic("%s: Failed to allocate %zu bytes\n", __func__,
- sizeof(struct property) + 256);
dn = of_find_node_by_path("/");
if (dn) {
memset(of_prop, -1, sizeof(struct property) + 256);
@@ -218,6 +225,7 @@ pci_create_OF_bus_map(void)
of_node_put(dn);
}
}
+#endif // CONFIG_PPC_PCI_OF_BUS_MAP
void pcibios_setup_phb_io_space(struct pci_controller *hose)
{
@@ -233,23 +241,41 @@ void pcibios_setup_phb_io_space(struct pci_controller *hose)
static int __init pcibios_init(void)
{
struct pci_controller *hose, *tmp;
+#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
int next_busno = 0;
+#endif
printk(KERN_INFO "PCI: Probing PCI hardware\n");
+#ifdef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
+ /*
+ * Enable PCI domains in /proc when PCI bus numbers are not unique
+ * across all PCI domains to prevent conflicts. And keep PCI domain 0
+ * backward compatible in /proc for video cards.
+ */
+ pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0);
+#endif
+
if (pci_has_flag(PCI_REASSIGN_ALL_BUS))
pci_assign_all_buses = 1;
/* Scan all of the recorded PCI controllers. */
list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
if (pci_assign_all_buses)
hose->first_busno = next_busno;
+#endif
hose->last_busno = 0xff;
pcibios_scan_phb(hose);
pci_bus_add_devices(hose->bus);
+#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
if (pci_assign_all_buses || next_busno <= hose->last_busno)
next_busno = hose->last_busno + pcibios_assign_bus_offset;
+#endif
}
+
+#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP)
+#ifdef CONFIG_PPC_PCI_OF_BUS_MAP
pci_bus_count = next_busno;
/* OpenFirmware based machines need a map of OF bus
@@ -258,6 +284,8 @@ static int __init pcibios_init(void)
*/
if (pci_assign_all_buses)
pcibios_make_OF_bus_map();
+#endif
+#endif
/* Call common code to handle resource allocation */
pcibios_resource_survey();
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 19b03ddf5631..e27342ef128b 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -73,7 +73,7 @@ static int __init pcibios_init(void)
return 0;
}
-subsys_initcall(pcibios_init);
+subsys_initcall_sync(pcibios_init);
int pcibios_unmap_io_space(struct pci_bus *bus)
{
@@ -132,7 +132,7 @@ void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size)
* address decoding but I'd rather not deal with those outside of the
* reserved 64K legacy region.
*/
- area = __get_vm_area_caller(size, 0, PHB_IO_BASE, PHB_IO_END,
+ area = __get_vm_area_caller(size, VM_IOREMAP, PHB_IO_BASE, PHB_IO_END,
__builtin_return_address(0));
if (!area)
return NULL;
@@ -286,6 +286,7 @@ int pcibus_to_node(struct pci_bus *bus)
EXPORT_SYMBOL(pcibus_to_node);
#endif
+#ifdef CONFIG_PPC_PMAC
int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn)
{
if (!PCI_DN(np))
@@ -294,3 +295,4 @@ int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn)
*devfn = PCI_DN(np)->devfn;
return 0;
}
+#endif
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 938ab8838ab5..38561d6a2079 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -259,7 +259,7 @@ void remove_sriov_vf_pdns(struct pci_dev *pdev)
if (edev) {
/*
* We allocate pci_dn's for the totalvfs count,
- * but only only the vfs that were activated
+ * but only the vfs that were activated
* have a configured PE.
*/
if (edev->pe)
@@ -330,6 +330,7 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
INIT_LIST_HEAD(&pdn->list);
parent = of_get_parent(dn);
pdn->parent = parent ? PCI_DN(parent) : NULL;
+ of_node_put(parent);
if (pdn->parent)
list_add_tail(&pdn->list, &pdn->parent->child_list);
diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
index 15414c8a2837..9fabb4d9235e 100644
--- a/arch/powerpc/kernel/pmc.c
+++ b/arch/powerpc/kernel/pmc.c
@@ -74,7 +74,7 @@ void release_pmc_hardware(void)
}
EXPORT_SYMBOL_GPL(release_pmc_hardware);
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
void power4_enable_pmcs(void)
{
unsigned long hid0;
diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h
deleted file mode 100644
index 2346f8c7ff2e..000000000000
--- a/arch/powerpc/kernel/ppc32.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _PPC64_PPC32_H
-#define _PPC64_PPC32_H
-
-#include <linux/compat.h>
-#include <asm/siginfo.h>
-#include <asm/signal.h>
-
-/*
- * Data types and macros for providing 32b PowerPC support.
- */
-
-/* These are here to support 32-bit syscalls on a 64-bit kernel. */
-
-struct pt_regs32 {
- unsigned int gpr[32];
- unsigned int nip;
- unsigned int msr;
- unsigned int orig_gpr3; /* Used for restarting system calls */
- unsigned int ctr;
- unsigned int link;
- unsigned int xer;
- unsigned int ccr;
- unsigned int mq; /* 601 only (not used at present) */
- unsigned int trap; /* Reason for being here */
- unsigned int dar; /* Fault registers */
- unsigned int dsisr;
- unsigned int result; /* Result of a system call */
-};
-
-struct sigcontext32 {
- unsigned int _unused[4];
- int signal;
- compat_uptr_t handler;
- unsigned int oldmask;
- compat_uptr_t regs; /* 4 byte pointer to the pt_regs32 structure. */
-};
-
-struct mcontext32 {
- elf_gregset_t32 mc_gregs;
- elf_fpregset_t mc_fregs;
- unsigned int mc_pad[2];
- elf_vrregset_t32 mc_vregs __attribute__((__aligned__(16)));
- elf_vsrreghalf_t32 mc_vsregs __attribute__((__aligned__(16)));
-};
-
-struct ucontext32 {
- unsigned int uc_flags;
- unsigned int uc_link;
- compat_stack_t uc_stack;
- int uc_pad[7];
- compat_uptr_t uc_regs; /* points to uc_mcontext field */
- compat_sigset_t uc_sigmask; /* mask last for extensibility */
- /* glibc has 1024-bit signal masks, ours are 64-bit */
- int uc_maskext[30];
- int uc_pad2[3];
- struct mcontext32 uc_mcontext;
-};
-
-#endif /* _PPC64_PPC32_H */
diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S
index 2d4d21bb46a9..a9b9c32d0c1f 100644
--- a/arch/powerpc/kernel/ppc_save_regs.S
+++ b/arch/powerpc/kernel/ppc_save_regs.S
@@ -21,60 +21,33 @@
* different ABIs, though).
*/
_GLOBAL(ppc_save_regs)
- PPC_STL r0,0*SZL(r3)
+ /* This allows stack frame accessor macros and offsets to be used */
+ subi r3,r3,STACK_INT_FRAME_REGS
+ PPC_STL r0,GPR0(r3)
#ifdef CONFIG_PPC32
- stmw r2, 2*SZL(r3)
+ stmw r2,GPR2(r3)
#else
- PPC_STL r2,2*SZL(r3)
- PPC_STL r3,3*SZL(r3)
- PPC_STL r4,4*SZL(r3)
- PPC_STL r5,5*SZL(r3)
- PPC_STL r6,6*SZL(r3)
- PPC_STL r7,7*SZL(r3)
- PPC_STL r8,8*SZL(r3)
- PPC_STL r9,9*SZL(r3)
- PPC_STL r10,10*SZL(r3)
- PPC_STL r11,11*SZL(r3)
- PPC_STL r12,12*SZL(r3)
- PPC_STL r13,13*SZL(r3)
- PPC_STL r14,14*SZL(r3)
- PPC_STL r15,15*SZL(r3)
- PPC_STL r16,16*SZL(r3)
- PPC_STL r17,17*SZL(r3)
- PPC_STL r18,18*SZL(r3)
- PPC_STL r19,19*SZL(r3)
- PPC_STL r20,20*SZL(r3)
- PPC_STL r21,21*SZL(r3)
- PPC_STL r22,22*SZL(r3)
- PPC_STL r23,23*SZL(r3)
- PPC_STL r24,24*SZL(r3)
- PPC_STL r25,25*SZL(r3)
- PPC_STL r26,26*SZL(r3)
- PPC_STL r27,27*SZL(r3)
- PPC_STL r28,28*SZL(r3)
- PPC_STL r29,29*SZL(r3)
- PPC_STL r30,30*SZL(r3)
- PPC_STL r31,31*SZL(r3)
+ SAVE_GPRS(2, 31, r3)
lbz r0,PACAIRQSOFTMASK(r13)
- PPC_STL r0,SOFTE-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,SOFTE(r3)
#endif
- /* go up one stack frame for SP */
- PPC_LL r4,0(r1)
- PPC_STL r4,1*SZL(r3)
+ /* store current SP */
+ PPC_STL r1,GPR1(r3)
/* get caller's LR */
+ PPC_LL r4,0(r1)
PPC_LL r0,LRSAVE(r4)
- PPC_STL r0,_LINK-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,_LINK(r3)
mflr r0
- PPC_STL r0,_NIP-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,_NIP(r3)
mfmsr r0
- PPC_STL r0,_MSR-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,_MSR(r3)
mfctr r0
- PPC_STL r0,_CTR-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,_CTR(r3)
mfxer r0
- PPC_STL r0,_XER-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,_XER(r3)
mfcr r0
- PPC_STL r0,_CCR-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,_CCR(r3)
li r0,0
- PPC_STL r0,_TRAP-STACK_FRAME_OVERHEAD(r3)
- PPC_STL r0,ORIG_GPR3-STACK_FRAME_OVERHEAD(r3)
+ PPC_STL r0,_TRAP(r3)
+ PPC_STL r0,ORIG_GPR3(r3)
blr
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index b109cd7b5d01..d083b4517065 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -4,17 +4,20 @@
*/
#include <linux/init.h>
+#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/kernel.h>
#include <linux/of.h>
+#include <linux/string.h>
#include <asm/machdep.h>
#include <asm/vdso_datapage.h>
#include <asm/rtas.h>
+#include <asm/systemcfg.h>
#include <linux/uaccess.h>
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
static loff_t page_map_seek(struct file *file, loff_t off, int whence)
{
@@ -33,10 +36,9 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma )
if ((vma->vm_end - vma->vm_start) > PAGE_SIZE)
return -EINVAL;
- remap_pfn_range(vma, vma->vm_start,
- __pa(pde_data(file_inode(file))) >> PAGE_SHIFT,
- PAGE_SIZE, vma->vm_page_prot);
- return 0;
+ return remap_pfn_range(vma, vma->vm_start,
+ __pa(pde_data(file_inode(file))) >> PAGE_SHIFT,
+ PAGE_SIZE, vma->vm_page_prot);
}
static const struct proc_ops page_map_proc_ops = {
@@ -45,13 +47,35 @@ static const struct proc_ops page_map_proc_ops = {
.proc_mmap = page_map_mmap,
};
+static union {
+ struct systemcfg data;
+ u8 page[PAGE_SIZE];
+} systemcfg_data_store __page_aligned_data;
+struct systemcfg *systemcfg = &systemcfg_data_store.data;
static int __init proc_ppc64_init(void)
{
struct proc_dir_entry *pde;
+ strscpy(systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
+ systemcfg->version.major = SYSTEMCFG_MAJOR;
+ systemcfg->version.minor = SYSTEMCFG_MINOR;
+ systemcfg->processor = mfspr(SPRN_PVR);
+ /*
+ * Fake the old platform number for pSeries and add
+ * in LPAR bit if necessary
+ */
+ systemcfg->platform = 0x100;
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ systemcfg->platform |= 1;
+ systemcfg->physicalMemorySize = memblock_phys_mem_size();
+ systemcfg->dcache_size = ppc64_caches.l1d.size;
+ systemcfg->dcache_line_size = ppc64_caches.l1d.line_size;
+ systemcfg->icache_size = ppc64_caches.l1i.size;
+ systemcfg->icache_line_size = ppc64_caches.l1i.line_size;
+
pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL,
- &page_map_proc_ops, vdso_data);
+ &page_map_proc_ops, systemcfg);
if (!pde)
return 1;
proc_set_size(pde, PAGE_SIZE);
@@ -60,7 +84,7 @@ static int __init proc_ppc64_init(void)
}
__initcall(proc_ppc64_init);
-#endif /* CONFIG_PPC64 */
+#endif /* CONFIG_PPC64_PROC_SYSTEMCFG */
/*
* Create the ppc64 and ppc64/rtas directories early. This allows us to
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 0fbda89cd1bb..855e09886503 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -54,7 +54,7 @@
#include <asm/firmware.h>
#include <asm/hw_irq.h>
#endif
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/exec.h>
#include <asm/livepatch.h>
#include <asm/cpu_has_feature.h>
@@ -72,8 +72,6 @@
#define TM_DEBUG(x...) do { } while(0)
#endif
-extern unsigned long _get_SP(void);
-
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
* Are we running in "Suspend disabled" mode? If so we have to block any
@@ -127,7 +125,7 @@ unsigned long notrace msr_check_and_set(unsigned long bits)
newmsr |= MSR_VSX;
if (oldmsr != newmsr)
- mtmsr_isync(newmsr);
+ newmsr = mtmsr_isync_irqsafe(newmsr);
return newmsr;
}
@@ -145,7 +143,7 @@ void notrace __msr_check_and_clear(unsigned long bits)
newmsr &= ~MSR_VSX;
if (oldmsr != newmsr)
- mtmsr_isync(newmsr);
+ mtmsr_isync_irqsafe(newmsr);
}
EXPORT_SYMBOL(__msr_check_and_clear);
@@ -862,10 +860,8 @@ static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk)
return 0;
}
-void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk)
+static void set_hw_breakpoint(int nr, struct arch_hw_breakpoint *brk)
{
- memcpy(this_cpu_ptr(&current_brk[nr]), brk, sizeof(*brk));
-
if (dawr_enabled())
// Power8 or later
set_dawr(nr, brk);
@@ -879,6 +875,12 @@ void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk)
WARN_ON_ONCE(1);
}
+void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk)
+{
+ memcpy(this_cpu_ptr(&current_brk[nr]), brk, sizeof(*brk));
+ set_hw_breakpoint(nr, brk);
+}
+
/* Check if we have DAWR or DABR hardware */
bool ppc_breakpoint_available(void)
{
@@ -891,6 +893,34 @@ bool ppc_breakpoint_available(void)
}
EXPORT_SYMBOL_GPL(ppc_breakpoint_available);
+/* Disable the breakpoint in hardware without touching current_brk[] */
+void suspend_breakpoints(void)
+{
+ struct arch_hw_breakpoint brk = {0};
+ int i;
+
+ if (!ppc_breakpoint_available())
+ return;
+
+ for (i = 0; i < nr_wp_slots(); i++)
+ set_hw_breakpoint(i, &brk);
+}
+
+/*
+ * Re-enable breakpoints suspended by suspend_breakpoints() in hardware
+ * from current_brk[]
+ */
+void restore_breakpoints(void)
+{
+ int i;
+
+ if (!ppc_breakpoint_available())
+ return;
+
+ for (i = 0; i < nr_wp_slots(); i++)
+ set_hw_breakpoint(i, this_cpu_ptr(&current_brk[i]));
+}
+
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
static inline bool tm_enabled(struct task_struct *tsk)
@@ -970,7 +1000,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk)
WARN_ON(tm_suspend_disabled);
- TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, "
+ TM_DEBUG("---- tm_reclaim on pid %d (NIP=%lx, "
"ccr=%lx, msr=%lx, trap=%lx)\n",
tsk->pid, thr->regs->nip,
thr->regs->ccr, thr->regs->msr,
@@ -978,7 +1008,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk)
tm_reclaim_thread(thr, TM_CAUSE_RESCHED);
- TM_DEBUG("--- tm_reclaim on pid %d complete\n",
+ TM_DEBUG("---- tm_reclaim on pid %d complete\n",
tsk->pid);
out_and_saveregs:
@@ -1150,6 +1180,12 @@ static inline void save_sprs(struct thread_struct *t)
*/
t->tar = mfspr(SPRN_TAR);
}
+
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE))
+ t->hashkeyr = mfspr(SPRN_HASHKEYR);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ t->dexcr = mfspr(SPRN_DEXCR);
#endif
}
@@ -1163,11 +1199,11 @@ void kvmppc_save_user_regs(void)
usermsr = current->thread.regs->msr;
+ /* Caller has enabled FP/VEC/VSX/TM in MSR */
if (usermsr & MSR_FP)
- save_fpu(current);
-
+ __giveup_fpu(current);
if (usermsr & MSR_VEC)
- save_altivec(current);
+ __giveup_altivec(current);
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (usermsr & MSR_TM) {
@@ -1228,6 +1264,14 @@ static inline void restore_sprs(struct thread_struct *old_thread,
if (cpu_has_feature(CPU_FTR_P9_TIDR) &&
old_thread->tidr != new_thread->tidr)
mtspr(SPRN_TIDR, new_thread->tidr);
+
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) &&
+ old_thread->hashkeyr != new_thread->hashkeyr)
+ mtspr(SPRN_HASHKEYR, new_thread->hashkeyr);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31) &&
+ old_thread->dexcr != new_thread->dexcr)
+ mtspr(SPRN_DEXCR, new_thread->dexcr);
#endif
}
@@ -1359,7 +1403,7 @@ static void show_instructions(struct pt_regs *regs)
unsigned long nip = regs->nip;
unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
- printk("Instruction dump:");
+ printk("Code: ");
/*
* If we were executing with the MMU off for instructions, adjust pc
@@ -1373,11 +1417,7 @@ static void show_instructions(struct pt_regs *regs)
for (i = 0; i < NR_INSN_TO_PRINT; i++) {
int instr;
- if (!(i % 8))
- pr_cont("\n");
-
- if (!__kernel_text_address(pc) ||
- get_kernel_nofault(instr, (const void *)pc)) {
+ if (get_kernel_nofault(instr, (const void *)pc)) {
pr_cont("XXXXXXXX ");
} else {
if (nip == pc)
@@ -1531,7 +1571,7 @@ static void __show_regs(struct pt_regs *regs)
if (trap == INTERRUPT_MACHINE_CHECK ||
trap == INTERRUPT_DATA_STORAGE ||
trap == INTERRUPT_ALIGNMENT) {
- if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+ if (IS_ENABLED(CONFIG_BOOKE))
pr_cont("DEAR: "REG" ESR: "REG" ", regs->dear, regs->esr);
else
pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
@@ -1599,10 +1639,17 @@ void arch_setup_new_exec(void)
current->thread.regs->amr = default_amr;
current->thread.regs->iamr = default_iamr;
#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ current->thread.dexcr = current->thread.dexcr_onexec;
+ mtspr(SPRN_DEXCR, current->thread.dexcr);
+ }
+#endif /* CONFIG_PPC_BOOK3S_64 */
}
#ifdef CONFIG_PPC64
-/**
+/*
* Assign a TIDR (thread ID) for task @t and set it in the thread
* structure. For now, we only support setting TIDR for 'current' task.
*
@@ -1612,7 +1659,7 @@ void arch_setup_new_exec(void)
* cases will happen:
*
* 1. The correct thread is running, the wrong thread is not
- * In this situation, the correct thread is woken and proceeds to pass it's
+ * In this situation, the correct thread is woken and proceeds to pass its
* condition check.
*
* 2. Neither threads are running
@@ -1622,15 +1669,15 @@ void arch_setup_new_exec(void)
* for the wrong thread, or they will execute the condition check immediately.
*
* 3. The wrong thread is running, the correct thread is not
- * The wrong thread will be woken, but will fail it's condition check and
+ * The wrong thread will be woken, but will fail its condition check and
* re-execute wait. The correct thread, when scheduled, will execute either
- * it's condition check (which will pass), or wait, which returns immediately
- * when called the first time after the thread is scheduled, followed by it's
+ * its condition check (which will pass), or wait, which returns immediately
+ * when called the first time after the thread is scheduled, followed by its
* condition check (which will pass).
*
* 4. Both threads are running
- * Both threads will be woken. The wrong thread will fail it's condition check
- * and execute another wait, while the correct thread will pass it's condition
+ * Both threads will be woken. The wrong thread will fail its condition check
+ * and execute another wait, while the correct thread will pass its condition
* check.
*
* @t: the task to set the thread ID for
@@ -1655,11 +1702,6 @@ EXPORT_SYMBOL_GPL(set_thread_tidr);
#endif /* CONFIG_PPC64 */
-void
-release_thread(struct task_struct *t)
-{
-}
-
/*
* this gets called so that we can store coprocessor state into memory and
* copy the current task into the new thread.
@@ -1715,64 +1757,83 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp)
*/
int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
{
- unsigned long clone_flags = args->flags;
- unsigned long usp = args->stack;
- unsigned long tls = args->tls;
- struct pt_regs *childregs, *kregs;
+ struct pt_regs *kregs; /* Switch frame regs */
extern void ret_from_fork(void);
extern void ret_from_fork_scv(void);
- extern void ret_from_kernel_thread(void);
+ extern void ret_from_kernel_user_thread(void);
+ extern void start_kernel_thread(void);
void (*f)(void);
unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
- struct thread_info *ti = task_thread_info(p);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
int i;
#endif
klp_init_thread_info(p);
- /* Copy registers */
- sp -= sizeof(struct pt_regs);
- childregs = (struct pt_regs *) sp;
- if (unlikely(args->fn)) {
+ if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
- memset(childregs, 0, sizeof(struct pt_regs));
- childregs->gpr[1] = sp + sizeof(struct pt_regs);
- /* function */
- if (args->fn)
- childregs->gpr[14] = ppc_function_entry((void *)args->fn);
-#ifdef CONFIG_PPC64
- clear_tsk_thread_flag(p, TIF_32BIT);
- childregs->softe = IRQS_ENABLED;
-#endif
- childregs->gpr[15] = (unsigned long)args->fn_arg;
+
+ /* Create initial minimum stack frame. */
+ sp -= STACK_FRAME_MIN_SIZE;
+ ((unsigned long *)sp)[0] = 0;
+
+ f = start_kernel_thread;
p->thread.regs = NULL; /* no user register state */
- ti->flags |= _TIF_RESTOREALL;
- f = ret_from_kernel_thread;
+ clear_tsk_compat_task(p);
} else {
/* user thread */
- struct pt_regs *regs = current_pt_regs();
- *childregs = *regs;
- if (usp)
- childregs->gpr[1] = usp;
- p->thread.regs = childregs;
- /* 64s sets this in ret_from_fork */
- if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
- childregs->gpr[3] = 0; /* Result from fork() */
- if (clone_flags & CLONE_SETTLS) {
- if (!is_32bit_task())
- childregs->gpr[13] = tls;
+ struct pt_regs *childregs;
+
+ /* Create initial user return stack frame. */
+ sp -= STACK_USER_INT_FRAME_SIZE;
+ *(unsigned long *)(sp + STACK_INT_FRAME_MARKER) = STACK_FRAME_REGS_MARKER;
+
+ childregs = (struct pt_regs *)(sp + STACK_INT_FRAME_REGS);
+
+ if (unlikely(args->fn)) {
+ /*
+ * A user space thread, but it first runs a kernel
+ * thread, and then returns as though it had called
+ * execve rather than fork, so user regs will be
+ * filled in (e.g., by kernel_execve()).
+ */
+ ((unsigned long *)sp)[0] = 0;
+ memset(childregs, 0, sizeof(struct pt_regs));
+#ifdef CONFIG_PPC64
+ childregs->softe = IRQS_ENABLED;
+#endif
+ f = ret_from_kernel_user_thread;
+ } else {
+ struct pt_regs *regs = current_pt_regs();
+ unsigned long clone_flags = args->flags;
+ unsigned long usp = args->stack;
+
+ /* Copy registers */
+ *childregs = *regs;
+ if (usp)
+ childregs->gpr[1] = usp;
+ ((unsigned long *)sp)[0] = childregs->gpr[1];
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+ WARN_ON_ONCE(childregs->softe != IRQS_ENABLED);
+#endif
+ if (clone_flags & CLONE_SETTLS) {
+ unsigned long tls = args->tls;
+
+ if (!is_32bit_task())
+ childregs->gpr[13] = tls;
+ else
+ childregs->gpr[2] = tls;
+ }
+
+ if (trap_is_scv(regs))
+ f = ret_from_fork_scv;
else
- childregs->gpr[2] = tls;
+ f = ret_from_fork;
}
- if (trap_is_scv(regs))
- f = ret_from_fork_scv;
- else
- f = ret_from_fork;
+ childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX);
+ p->thread.regs = childregs;
}
- childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX);
- sp -= STACK_FRAME_OVERHEAD;
/*
* The way this works is that at some point in the future
@@ -1782,11 +1843,22 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
* do some house keeping and then return from the fork or clone
* system call, using the stack frame created above.
*/
- ((unsigned long *)sp)[0] = 0;
- sp -= sizeof(struct pt_regs);
- kregs = (struct pt_regs *) sp;
- sp -= STACK_FRAME_OVERHEAD;
+ ((unsigned long *)sp)[STACK_FRAME_LR_SAVE] = (unsigned long)f;
+ sp -= STACK_SWITCH_FRAME_SIZE;
+ ((unsigned long *)sp)[0] = sp + STACK_SWITCH_FRAME_SIZE;
+ kregs = (struct pt_regs *)(sp + STACK_SWITCH_FRAME_REGS);
+ kregs->nip = ppc_function_entry(f);
+ if (unlikely(args->fn)) {
+ /*
+ * Put kthread fn, arg parameters in non-volatile GPRs in the
+ * switch frame so they are loaded by _switch before it returns
+ * to ret_from_kernel_thread.
+ */
+ kregs->gpr[14] = ppc_function_entry((void *)args->fn);
+ kregs->gpr[15] = (unsigned long)args->fn_arg;
+ }
p->thread.ksp = sp;
+
#ifdef CONFIG_HAVE_HW_BREAKPOINT
for (i = 0; i < nr_wp_slots(); i++)
p->thread.ptrace_bps[i] = NULL;
@@ -1801,7 +1873,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
p->thread.kuap = KUAP_NONE;
#endif
-#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP)
p->thread.pid = MMU_NO_CONTEXT;
#endif
@@ -1812,22 +1884,16 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
p->thread.dscr_inherit = current->thread.dscr_inherit;
p->thread.dscr = mfspr(SPRN_DSCR);
}
- if (cpu_has_feature(CPU_FTR_HAS_PPR))
- childregs->ppr = DEFAULT_PPR;
p->thread.tidr = 0;
#endif
- /*
- * Run with the current AMR value of the kernel
- */
-#ifdef CONFIG_PPC_PKEY
- if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
- kregs->amr = AMR_KUAP_BLOCKED;
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE))
+ p->thread.hashkeyr = current->thread.hashkeyr;
- if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP))
- kregs->iamr = AMR_KUEP_BLOCKED;
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ p->thread.dexcr = mfspr(SPRN_DEXCR);
#endif
- kregs->nip = ppc_function_entry(f);
return 0;
}
@@ -1894,8 +1960,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
* address of _start and the second entry is the TOC
* value we need to use.
*/
- __get_user(entry, (unsigned long __user *)start);
- __get_user(toc, (unsigned long __user *)start+1);
+ get_user(entry, (unsigned long __user *)start);
+ get_user(toc, (unsigned long __user *)start+1);
/* Check whether the e_entry function descriptor entries
* need to be relocated before we can use them.
@@ -1944,6 +2010,12 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
current->thread.tm_tfiar = 0;
current->thread.load_tm = 0;
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+ current->thread.hashkeyr = get_random_long();
+ mtspr(SPRN_HASHKEYR, current->thread.hashkeyr);
+ }
+#endif /* CONFIG_PPC_BOOK3S_64 */
}
EXPORT_SYMBOL(start_thread);
@@ -2089,6 +2161,9 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
unsigned long stack_page;
unsigned long cpu = task_cpu(p);
+ if (!hardirq_ctx[cpu] || !softirq_ctx[cpu])
+ return 0;
+
stack_page = (unsigned long)hardirq_ctx[cpu];
if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
@@ -2100,16 +2175,24 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
return 0;
}
+#ifdef CONFIG_PPC64
static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
unsigned long nbytes)
{
-#ifdef CONFIG_PPC64
unsigned long stack_page;
unsigned long cpu = task_cpu(p);
if (!paca_ptrs)
return 0;
+ if (!paca_ptrs[cpu]->emergency_sp)
+ return 0;
+
+# ifdef CONFIG_PPC_BOOK3S_64
+ if (!paca_ptrs[cpu]->nmi_emergency_sp || !paca_ptrs[cpu]->mc_emergency_sp)
+ return 0;
+#endif
+
stack_page = (unsigned long)paca_ptrs[cpu]->emergency_sp - THREAD_SIZE;
if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
@@ -2123,14 +2206,33 @@ static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
# endif
-#endif
return 0;
}
+#else
+static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
+ unsigned long nbytes)
+{
+ unsigned long stack_page;
+ unsigned long cpu = task_cpu(p);
+ if (!IS_ENABLED(CONFIG_VMAP_STACK))
+ return 0;
-int validate_sp(unsigned long sp, struct task_struct *p,
- unsigned long nbytes)
+ stack_page = (unsigned long)emergency_ctx[cpu] - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ return 0;
+}
+#endif
+
+/*
+ * validate the stack frame of a particular minimum size, used for when we are
+ * looking at a certain object in the stack beyond the minimum.
+ */
+int validate_sp_size(unsigned long sp, struct task_struct *p,
+ unsigned long nbytes)
{
unsigned long stack_page = (unsigned long)task_stack_page(p);
@@ -2146,7 +2248,10 @@ int validate_sp(unsigned long sp, struct task_struct *p,
return valid_emergency_stack(sp, p, nbytes);
}
-EXPORT_SYMBOL(validate_sp);
+int validate_sp(unsigned long sp, struct task_struct *p)
+{
+ return validate_sp_size(sp, p, STACK_FRAME_MIN_SIZE);
+}
static unsigned long ___get_wchan(struct task_struct *p)
{
@@ -2154,13 +2259,12 @@ static unsigned long ___get_wchan(struct task_struct *p)
int count = 0;
sp = p->thread.ksp;
- if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD))
+ if (!validate_sp(sp, p))
return 0;
do {
sp = READ_ONCE_NOCHECK(*(unsigned long *)sp);
- if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD) ||
- task_is_running(p))
+ if (!validate_sp(sp, p) || task_is_running(p))
return 0;
if (count > 0) {
ip = READ_ONCE_NOCHECK(((unsigned long *)sp)[STACK_FRAME_LR_SAVE]);
@@ -2185,6 +2289,22 @@ unsigned long __get_wchan(struct task_struct *p)
return ret;
}
+static bool empty_user_regs(struct pt_regs *regs, struct task_struct *tsk)
+{
+ unsigned long stack_page;
+
+ // A non-empty pt_regs should never have a zero MSR or TRAP value.
+ if (regs->msr || regs->trap)
+ return false;
+
+ // Check it sits at the very base of the stack
+ stack_page = (unsigned long)task_stack_page(tsk);
+ if ((unsigned long)(regs + 1) != stack_page + THREAD_SIZE)
+ return false;
+
+ return true;
+}
+
static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
void __no_sanitize_address show_stack(struct task_struct *tsk,
@@ -2214,7 +2334,7 @@ void __no_sanitize_address show_stack(struct task_struct *tsk,
lr = 0;
printk("%sCall Trace:\n", loglvl);
do {
- if (!validate_sp(sp, tsk, STACK_FRAME_OVERHEAD))
+ if (!validate_sp(sp, tsk))
break;
stack = (unsigned long *) sp;
@@ -2235,19 +2355,27 @@ void __no_sanitize_address show_stack(struct task_struct *tsk,
/*
* See if this is an exception frame.
- * We look for the "regshere" marker in the current frame.
+ * We look for the "regs" marker in the current frame.
+ *
+ * STACK_SWITCH_FRAME_SIZE being the smallest frame that
+ * could hold a pt_regs, if that does not fit then it can't
+ * have regs.
*/
- if (validate_sp(sp, tsk, STACK_FRAME_WITH_PT_REGS)
- && stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
+ if (validate_sp_size(sp, tsk, STACK_SWITCH_FRAME_SIZE)
+ && stack[STACK_INT_FRAME_MARKER_LONGS] == STACK_FRAME_REGS_MARKER) {
struct pt_regs *regs = (struct pt_regs *)
- (sp + STACK_FRAME_OVERHEAD);
+ (sp + STACK_INT_FRAME_REGS);
lr = regs->link;
- printk("%s--- interrupt: %lx at %pS\n",
+ printk("%s---- interrupt: %lx at %pS\n",
loglvl, regs->trap, (void *)regs->nip);
- __show_regs(regs);
- printk("%s--- interrupt: %lx\n",
- loglvl, regs->trap);
+
+ // Detect the case of an empty pt_regs at the very base
+ // of the stack and suppress showing it in full.
+ if (!empty_user_regs(regs, tsk)) {
+ __show_regs(regs);
+ printk("%s---- interrupt: %lx\n", loglvl, regs->trap);
+ }
firstframe = 1;
}
@@ -2308,6 +2436,6 @@ void notrace __ppc64_runlatch_off(void)
unsigned long arch_align_stack(unsigned long sp)
{
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
- sp -= get_random_int() & ~PAGE_MASK;
+ sp -= get_random_u32_below(PAGE_SIZE);
return sp & ~0xf;
}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index feae8509b59c..9ed9dde7d231 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -30,6 +30,7 @@
#include <linux/libfdt.h>
#include <linux/cpu.h>
#include <linux/pgtable.h>
+#include <linux/seq_buf.h>
#include <asm/rtas.h>
#include <asm/page.h>
@@ -44,7 +45,7 @@
#include <asm/iommu.h>
#include <asm/btext.h>
#include <asm/sections.h>
-#include <asm/machdep.h>
+#include <asm/setup.h>
#include <asm/pci-bridge.h>
#include <asm/kexec.h>
#include <asm/opal.h>
@@ -54,6 +55,8 @@
#include <asm/dt_cpu_ftrs.h>
#include <asm/drmem.h>
#include <asm/ultravisor.h>
+#include <asm/prom.h>
+#include <asm/plpks.h>
#include <mm/mmu_decl.h>
@@ -70,6 +73,7 @@ int __initdata iommu_is_off;
int __initdata iommu_force_on;
unsigned long tce_alloc_start, tce_alloc_end;
u64 ppc64_rma_size;
+unsigned int boot_cpu_node_count __ro_after_init;
#endif
static phys_addr_t first_memblock_size;
static int __initdata boot_cpu_count;
@@ -136,7 +140,7 @@ static void __init move_device_tree(void)
}
/*
- * ibm,pa-features is a per-cpu property that contains a string of
+ * ibm,pa/pi-features is a per-cpu property that contains a string of
* attribute descriptors, each of which has a 2 byte header plus up
* to 254 bytes worth of processor attribute bits. First header
* byte specifies the number of bytes following the header.
@@ -147,16 +151,21 @@ static void __init move_device_tree(void)
* pa-features property is missing, or a 1/0 to indicate if the feature
* is supported/not supported. Note that the bit numbers are
* big-endian to match the definition in PAPR.
+ * Note: the 'clear' flag clears the feature if the bit is set in the
+ * ibm,pa/pi-features property, it does not set the feature if the
+ * bit is clear.
*/
-static struct ibm_pa_feature {
+struct ibm_feature {
unsigned long cpu_features; /* CPU_FTR_xxx bit */
unsigned long mmu_features; /* MMU_FTR_xxx bit */
unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */
unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */
- unsigned char pabyte; /* byte number in ibm,pa-features */
+ unsigned char pabyte; /* byte number in ibm,pa/pi-features */
unsigned char pabit; /* bit number (big-endian) */
- unsigned char invert; /* if 1, pa bit set => clear feature */
-} ibm_pa_features[] __initdata = {
+ unsigned char clear; /* if 1, pa bit set => clear feature */
+};
+
+static struct ibm_feature ibm_pa_features[] __initdata = {
{ .pabyte = 0, .pabit = 0, .cpu_user_ftrs = PPC_FEATURE_HAS_MMU },
{ .pabyte = 0, .pabit = 1, .cpu_user_ftrs = PPC_FEATURE_HAS_FPU },
{ .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL },
@@ -176,11 +185,23 @@ static struct ibm_pa_feature {
.cpu_user_ftrs2 = PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_HTM_NOSC_COMP },
{ .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 },
+ { .pabyte = 68, .pabit = 5, .cpu_features = CPU_FTR_DEXCR_NPHIE },
+};
+
+/*
+ * ibm,pi-features property provides the support of processor specific
+ * options not described in ibm,pa-features. Right now use byte 0, bit 3
+ * which indicates the occurrence of DSI interrupt when the paste operation
+ * on the suspended NX window.
+ */
+static struct ibm_feature ibm_pi_features[] __initdata = {
+ { .pabyte = 0, .pabit = 3, .mmu_features = MMU_FTR_NX_DSI },
+ { .pabyte = 0, .pabit = 4, .cpu_features = CPU_FTR_DBELL, .clear = 1 },
};
static void __init scan_features(unsigned long node, const unsigned char *ftrs,
unsigned long tablelen,
- struct ibm_pa_feature *fp,
+ struct ibm_feature *fp,
unsigned long ft_size)
{
unsigned long i, len, bit;
@@ -203,12 +224,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs,
if (fp->pabyte >= ftrs[0])
continue;
bit = (ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
- if (bit ^ fp->invert) {
+ if (bit && !fp->clear) {
cur_cpu_spec->cpu_features |= fp->cpu_features;
cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2;
cur_cpu_spec->mmu_features |= fp->mmu_features;
- } else {
+ } else if (bit == fp->clear) {
cur_cpu_spec->cpu_features &= ~fp->cpu_features;
cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2;
@@ -217,17 +238,18 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs,
}
}
-static void __init check_cpu_pa_features(unsigned long node)
+static void __init check_cpu_features(unsigned long node, char *name,
+ struct ibm_feature *fp,
+ unsigned long size)
{
const unsigned char *pa_ftrs;
int tablelen;
- pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
+ pa_ftrs = of_get_flat_dt_prop(node, name, &tablelen);
if (pa_ftrs == NULL)
return;
- scan_features(node, pa_ftrs, tablelen,
- ibm_pa_features, ARRAY_SIZE(ibm_pa_features));
+ scan_features(node, pa_ftrs, tablelen, fp, size);
}
#ifdef CONFIG_PPC_64S_HASH_MMU
@@ -309,6 +331,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
void *data)
{
const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *cpu_version = NULL;
const __be32 *prop;
const __be32 *intserv;
int i, nthreads;
@@ -320,6 +343,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
if (type == NULL || strcmp(type, "cpu") != 0)
return 0;
+ if (IS_ENABLED(CONFIG_PPC64))
+ boot_cpu_node_count++;
+
/* Get physical cpuid */
intserv = of_get_flat_dt_prop(node, "ibm,ppc-interrupt-server#s", &len);
if (!intserv)
@@ -347,12 +373,30 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
if (found < 0)
return 0;
- DBG("boot cpu: logical %d physical %d\n", found,
- be32_to_cpu(intserv[found_thread]));
boot_cpuid = found;
- // Pass the boot CPU's hard CPU id back to our caller
- *((u32 *)data) = be32_to_cpu(intserv[found_thread]);
+ if (IS_ENABLED(CONFIG_PPC64))
+ boot_cpu_hwid = be32_to_cpu(intserv[found_thread]);
+
+ if (nr_cpu_ids % nthreads != 0) {
+ set_nr_cpu_ids(ALIGN(nr_cpu_ids, nthreads));
+ pr_warn("nr_cpu_ids was not a multiple of threads_per_core, adjusted to %d\n",
+ nr_cpu_ids);
+ }
+
+ if (boot_cpuid >= nr_cpu_ids) {
+ // Remember boot core for smp_setup_cpu_maps()
+ boot_core_hwid = be32_to_cpu(intserv[0]);
+
+ pr_warn("Boot CPU %d (core hwid %d) >= nr_cpu_ids, adjusted boot CPU to %d\n",
+ boot_cpuid, boot_core_hwid, found_thread);
+
+ // Adjust boot CPU to appear on logical core 0
+ boot_cpuid = found_thread;
+ }
+
+ DBG("boot cpu: logical %d physical %d\n", boot_cpuid,
+ be32_to_cpu(intserv[found_thread]));
/*
* PAPR defines "logical" PVR values for cpus that
@@ -375,14 +419,25 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
*/
if (!dt_cpu_ftrs_in_use()) {
prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
- if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
+ if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) {
identify_cpu(0, be32_to_cpup(prop));
+ cpu_version = prop;
+ }
check_cpu_feature_properties(node);
- check_cpu_pa_features(node);
+ check_cpu_features(node, "ibm,pa-features", ibm_pa_features,
+ ARRAY_SIZE(ibm_pa_features));
+ check_cpu_features(node, "ibm,pi-features", ibm_pi_features,
+ ARRAY_SIZE(ibm_pi_features));
}
identical_pvr_fixup(node);
+
+ // We can now add the CPU name & PVR to the hardware description
+ seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR));
+ if (cpu_version)
+ seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(cpu_version));
+
init_mmu_slb_size(node);
#ifdef CONFIG_PPC64
@@ -427,7 +482,7 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node,
tce_alloc_end = *lprop;
#endif
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_RESERVE
lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL);
if (lprop)
crashk_res.start = *lprop;
@@ -695,6 +750,23 @@ static void __init tm_init(void)
static void tm_init(void) { }
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+static int __init
+early_init_dt_scan_model(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ const char *prop;
+
+ if (depth != 0)
+ return 0;
+
+ prop = of_get_flat_dt_prop(node, "model", NULL);
+ if (prop)
+ seq_buf_printf(&ppc_hw_desc, "%s ", prop);
+
+ /* break now */
+ return 1;
+}
+
#ifdef CONFIG_PPC64
static void __init save_fscr_to_task(void)
{
@@ -714,15 +786,16 @@ static inline void save_fscr_to_task(void) {}
void __init early_init_devtree(void *params)
{
- u32 boot_cpu_hwid;
- phys_addr_t limit;
+ phys_addr_t int_vector_size;
DBG(" -> early_init_devtree(%px)\n", params);
/* Too early to BUG_ON(), do it by hand */
- if (!early_init_dt_verify(params))
+ if (!early_init_dt_verify(params, __pa(params)))
panic("BUG: Failed verifying flat device tree, bad version?");
+ of_scan_flat_dt(early_init_dt_scan_model, NULL);
+
#ifdef CONFIG_PPC_RTAS
/* Some machines might need RTAS info for debugging, grab it now. */
of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
@@ -747,10 +820,20 @@ void __init early_init_devtree(void *params)
*/
of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line);
+ /* Append additional parameters passed for fadump capture kernel */
+ fadump_append_bootargs();
+
/* Scan memory nodes and rebuild MEMBLOCKs */
early_init_dt_scan_root();
early_init_dt_scan_memory_ppc();
+ /*
+ * As generic code authors expect to be able to use static keys
+ * in early_param() handlers, we initialize the static keys just
+ * before parsing early params (it's fine to call jump_label_init()
+ * more than once).
+ */
+ jump_label_init();
parse_early_param();
/* make sure we've parsed cmdline for mem= before this */
@@ -759,9 +842,16 @@ void __init early_init_devtree(void *params)
setup_initial_memory_limit(memstart_addr, first_memblock_size);
/* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */
memblock_reserve(PHYSICAL_START, __pa(_end) - PHYSICAL_START);
+#ifdef CONFIG_PPC64
+ /* If relocatable, reserve at least 32k for interrupt vectors etc. */
+ int_vector_size = __end_interrupts - _stext;
+ int_vector_size = max_t(phys_addr_t, SZ_32K, int_vector_size);
+#else
/* If relocatable, reserve first 32k for interrupt vectors etc. */
+ int_vector_size = SZ_32K;
+#endif
if (PHYSICAL_START > MEMORY_START)
- memblock_reserve(MEMORY_START, 0x8000);
+ memblock_reserve(MEMORY_START, int_vector_size);
reserve_kdump_trampoline();
#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
/*
@@ -770,12 +860,15 @@ void __init early_init_devtree(void *params)
*/
if (fadump_reserve_mem() == 0)
#endif
- reserve_crashkernel();
+ arch_reserve_crashkernel();
early_reserve_mem();
- /* Ensure that total memory size is page-aligned. */
- limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
- memblock_enforce_memory_limit(limit);
+ if (memory_limit > memblock_phys_mem_size())
+ memory_limit = 0;
+
+ /* Align down to 16 MB which is large page size with hash page translation */
+ memory_limit = ALIGN_DOWN(memory_limit ?: memblock_phys_mem_size(), SZ_16M);
+ memblock_enforce_memory_limit(memory_limit);
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES)
if (!early_radix_enabled())
@@ -798,7 +891,7 @@ void __init early_init_devtree(void *params)
/* Retrieve CPU related informations from the flat tree
* (altivec support, boot CPU ID, ...)
*/
- of_scan_flat_dt(early_init_dt_scan_cpus, &boot_cpu_hwid);
+ of_scan_flat_dt(early_init_dt_scan_cpus, NULL);
if (boot_cpuid < 0) {
printk("Failed to identify boot CPU !\n");
BUG();
@@ -815,10 +908,8 @@ void __init early_init_devtree(void *params)
mmu_early_init_devtree();
- // NB. paca is not installed until later in early_setup()
- allocate_paca_ptrs();
- allocate_paca(boot_cpuid);
- set_hard_smp_processor_id(boot_cpuid, boot_cpu_hwid);
+ /* Setup param area for passing additional parameters to fadump capture kernel. */
+ fadump_setup_param_area();
#ifdef CONFIG_PPC_POWERNV
/* Scan and build the list of machine check recoverable ranges */
@@ -840,6 +931,9 @@ void __init early_init_devtree(void *params)
powerpc_firmware_features |= FW_FEATURE_PS3_POSSIBLE;
#endif
+ /* If kexec left a PLPKS password in the DT, get it and clear it */
+ plpks_early_init_devtree();
+
tm_init();
DBG(" <- early_init_devtree()\n");
diff --git a/arch/powerpc/kernel/prom_entry_64.S b/arch/powerpc/kernel/prom_entry_64.S
new file mode 100644
index 000000000000..f1b8793d28c6
--- /dev/null
+++ b/arch/powerpc/kernel/prom_entry_64.S
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Adapted for Power Macintosh by Paul Mackerras.
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ * This file contains the 64-bit prom entry code.
+ */
+#include <asm/asm-offsets.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
+#include <asm/ppc_asm.h>
+
+.section ".text","ax",@progbits
+
+_GLOBAL(enter_prom)
+ mflr r0
+ std r0,16(r1)
+ stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space */
+
+ /* Because PROM is running in 32b mode, it clobbers the high order half
+ * of all registers that it saves. We therefore save those registers
+ * PROM might touch to the stack. (r0, r3-r13 are caller saved)
+ */
+ SAVE_GPR(2, r1)
+ SAVE_GPR(13, r1)
+ SAVE_NVGPRS(r1)
+ mfcr r10
+ mfmsr r11
+ std r10,_CCR(r1)
+ std r11,_MSR(r1)
+
+ /* Put PROM address in SRR0 */
+ mtsrr0 r4
+
+ /* Setup our trampoline return addr in LR */
+ bcl 20,31,$+4
+0: mflr r4
+ addi r4,r4,(1f - 0b)
+ mtlr r4
+
+ /* Prepare a 32-bit mode big endian MSR
+ */
+#ifdef CONFIG_PPC_BOOK3E_64
+ rlwinm r11,r11,0,1,31
+ mtsrr1 r11
+ rfi
+#else /* CONFIG_PPC_BOOK3E_64 */
+ LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE)
+ andc r11,r11,r12
+ mtsrr1 r11
+ RFI_TO_KERNEL
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+1: /* Return from OF */
+ FIXUP_ENDIAN
+
+ /* Just make sure that r1 top 32 bits didn't get
+ * corrupt by OF
+ */
+ rldicl r1,r1,0,32
+
+ /* Restore the MSR (back to 64 bits) */
+ ld r0,_MSR(r1)
+ MTMSRD(r0)
+ isync
+
+ /* Restore other registers */
+ REST_GPR(2, r1)
+ REST_GPR(13, r1)
+ REST_NVGPRS(r1)
+ ld r4,_CCR(r1)
+ mtcr r4
+
+ addi r1,r1,SWITCH_FRAME_SIZE
+ ld r0,16(r1)
+ mtlr r0
+ blr
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 13d6cb188835..827c958677f8 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -42,7 +42,7 @@
#include <asm/iommu.h>
#include <asm/btext.h>
#include <asm/sections.h>
-#include <asm/machdep.h>
+#include <asm/setup.h>
#include <asm/asm-prototypes.h>
#include <asm/ultravisor-api.h>
@@ -96,12 +96,6 @@ static int of_workarounds __prombss;
#define OF_WA_CLAIM 1 /* do phys/virt claim separately, then map */
#define OF_WA_LONGTRAIL 2 /* work around longtrail bugs */
-#define PROM_BUG() do { \
- prom_printf("kernel BUG at %s line 0x%x!\n", \
- __FILE__, __LINE__); \
- __builtin_trap(); \
-} while (0)
-
#ifdef DEBUG_PROM
#define prom_debug(x...) prom_printf(x)
#else
@@ -823,8 +817,8 @@ static void __init early_cmdline_parse(void)
opt += 4;
prom_memory_limit = prom_memparse(opt, (const char **)&opt);
#ifdef CONFIG_PPC64
- /* Align to 16 MB == size of ppc64 large page */
- prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
+ /* Align down to 16 MB which is large page size with hash page translation */
+ prom_memory_limit = ALIGN_DOWN(prom_memory_limit, SZ_16M);
#endif
}
@@ -953,7 +947,7 @@ struct option_vector7 {
} __packed;
struct ibm_arch_vec {
- struct { u32 mask, val; } pvrs[14];
+ struct { __be32 mask, val; } pvrs[16];
u8 num_vectors;
@@ -1014,6 +1008,14 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
.val = cpu_to_be32(0x00800000),
},
{
+ .mask = cpu_to_be32(0xffff0000), /* POWER11 */
+ .val = cpu_to_be32(0x00820000),
+ },
+ {
+ .mask = cpu_to_be32(0xffffffff), /* P11 compliant */
+ .val = cpu_to_be32(0x0f000007),
+ },
+ {
.mask = cpu_to_be32(0xffffffff), /* all 3.1-compliant */
.val = cpu_to_be32(0x0f000006),
},
@@ -1059,7 +1061,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
.virt_base = cpu_to_be32(0xffffffff),
.virt_size = cpu_to_be32(0xffffffff),
.load_base = cpu_to_be32(0xffffffff),
- .min_rma = cpu_to_be32(512), /* 512MB min RMA */
+ .min_rma = cpu_to_be32(MIN_RMA),
.min_load = cpu_to_be32(0xffffffff), /* full client load */
.min_rma_percent = 0, /* min RMA percentage of total RAM */
.max_pft_size = 48, /* max log_2(hash table size) */
@@ -2790,91 +2792,6 @@ static void __init flatten_device_tree(void)
dt_struct_start, dt_struct_end);
}
-#ifdef CONFIG_PPC_MAPLE
-/* PIBS Version 1.05.0000 04/26/2005 has an incorrect /ht/isa/ranges property.
- * The values are bad, and it doesn't even have the right number of cells. */
-static void __init fixup_device_tree_maple(void)
-{
- phandle isa;
- u32 rloc = 0x01002000; /* IO space; PCI device = 4 */
- u32 isa_ranges[6];
- char *name;
-
- name = "/ht@0/isa@4";
- isa = call_prom("finddevice", 1, 1, ADDR(name));
- if (!PHANDLE_VALID(isa)) {
- name = "/ht@0/isa@6";
- isa = call_prom("finddevice", 1, 1, ADDR(name));
- rloc = 0x01003000; /* IO space; PCI device = 6 */
- }
- if (!PHANDLE_VALID(isa))
- return;
-
- if (prom_getproplen(isa, "ranges") != 12)
- return;
- if (prom_getprop(isa, "ranges", isa_ranges, sizeof(isa_ranges))
- == PROM_ERROR)
- return;
-
- if (isa_ranges[0] != 0x1 ||
- isa_ranges[1] != 0xf4000000 ||
- isa_ranges[2] != 0x00010000)
- return;
-
- prom_printf("Fixing up bogus ISA range on Maple/Apache...\n");
-
- isa_ranges[0] = 0x1;
- isa_ranges[1] = 0x0;
- isa_ranges[2] = rloc;
- isa_ranges[3] = 0x0;
- isa_ranges[4] = 0x0;
- isa_ranges[5] = 0x00010000;
- prom_setprop(isa, name, "ranges",
- isa_ranges, sizeof(isa_ranges));
-}
-
-#define CPC925_MC_START 0xf8000000
-#define CPC925_MC_LENGTH 0x1000000
-/* The values for memory-controller don't have right number of cells */
-static void __init fixup_device_tree_maple_memory_controller(void)
-{
- phandle mc;
- u32 mc_reg[4];
- char *name = "/hostbridge@f8000000";
- u32 ac, sc;
-
- mc = call_prom("finddevice", 1, 1, ADDR(name));
- if (!PHANDLE_VALID(mc))
- return;
-
- if (prom_getproplen(mc, "reg") != 8)
- return;
-
- prom_getprop(prom.root, "#address-cells", &ac, sizeof(ac));
- prom_getprop(prom.root, "#size-cells", &sc, sizeof(sc));
- if ((ac != 2) || (sc != 2))
- return;
-
- if (prom_getprop(mc, "reg", mc_reg, sizeof(mc_reg)) == PROM_ERROR)
- return;
-
- if (mc_reg[0] != CPC925_MC_START || mc_reg[1] != CPC925_MC_LENGTH)
- return;
-
- prom_printf("Fixing up bogus hostbridge on Maple...\n");
-
- mc_reg[0] = 0x0;
- mc_reg[1] = CPC925_MC_START;
- mc_reg[2] = 0x0;
- mc_reg[3] = CPC925_MC_LENGTH;
- prom_setprop(mc, name, "reg", mc_reg, sizeof(mc_reg));
-}
-#else
-#define fixup_device_tree_maple()
-#define fixup_device_tree_maple_memory_controller()
-#endif
-
-#ifdef CONFIG_PPC_CHRP
/*
* Pegasos and BriQ lacks the "ranges" property in the isa node
* Pegasos needs decimal IRQ 14/15, not hexadecimal
@@ -2925,12 +2842,8 @@ static void __init fixup_device_tree_chrp(void)
}
}
}
-#else
-#define fixup_device_tree_chrp()
-#endif
-#if defined(CONFIG_PPC64) && defined(CONFIG_PPC_PMAC)
-static void __init fixup_device_tree_pmac(void)
+static void __init fixup_device_tree_pmac64(void)
{
phandle u3, i2c, mpic;
u32 u3_rev;
@@ -2969,11 +2882,27 @@ static void __init fixup_device_tree_pmac(void)
prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupt-parent",
&parent, sizeof(parent));
}
-#else
-#define fixup_device_tree_pmac()
-#endif
-#ifdef CONFIG_PPC_EFIKA
+static void __init fixup_device_tree_pmac(void)
+{
+ __be32 val = 1;
+ char type[8];
+ phandle node;
+
+ // Some pmacs are missing #size-cells on escc or i2s nodes
+ for (node = 0; prom_next_node(&node); ) {
+ type[0] = '\0';
+ prom_getprop(node, "device_type", type, sizeof(type));
+ if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s"))
+ continue;
+
+ if (prom_getproplen(node, "#size-cells") != PROM_ERROR)
+ continue;
+
+ prom_setprop(node, NULL, "#size-cells", &val, sizeof(val));
+ }
+}
+
/*
* The MPC5200 FEC driver requires an phy-handle property to tell it how
* to talk to the phy. If the phy-handle property is missing, then this
@@ -3105,11 +3034,7 @@ static void __init fixup_device_tree_efika(void)
/* Make sure ethernet phy-handle property exists */
fixup_device_tree_efika_add_phy();
}
-#else
-#define fixup_device_tree_efika()
-#endif
-#ifdef CONFIG_PPC_PASEMI_NEMO
/*
* CFE supplied on Nemo is broken in several ways, biggest
* problem is that it reassigns ISA interrupts to unused mpic ints.
@@ -3185,18 +3110,23 @@ static void __init fixup_device_tree_pasemi(void)
prom_setprop(iob, name, "device_type", "isa", sizeof("isa"));
}
-#else /* !CONFIG_PPC_PASEMI_NEMO */
-static inline void fixup_device_tree_pasemi(void) { }
-#endif
static void __init fixup_device_tree(void)
{
- fixup_device_tree_maple();
- fixup_device_tree_maple_memory_controller();
- fixup_device_tree_chrp();
- fixup_device_tree_pmac();
- fixup_device_tree_efika();
- fixup_device_tree_pasemi();
+ if (IS_ENABLED(CONFIG_PPC_CHRP))
+ fixup_device_tree_chrp();
+
+ if (IS_ENABLED(CONFIG_PPC_PMAC))
+ fixup_device_tree_pmac();
+
+ if (IS_ENABLED(CONFIG_PPC_PMAC) && IS_ENABLED(CONFIG_PPC64))
+ fixup_device_tree_pmac64();
+
+ if (IS_ENABLED(CONFIG_PPC_EFIKA))
+ fixup_device_tree_efika();
+
+ if (IS_ENABLED(CONFIG_PPC_PASEMI_NEMO))
+ fixup_device_tree_pasemi();
}
static void __init prom_find_boot_cpu(void)
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index dfa5f729f774..3090b97258ae 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -13,8 +13,13 @@
# If you really need to reference something from prom_init.o add
# it to the list below:
-grep "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} >/dev/null
-if [ $? -eq 0 ]
+has_renamed_memintrinsics()
+{
+ grep -q "^CONFIG_KASAN=y$" "${KCONFIG_CONFIG}" && \
+ ! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" "${KCONFIG_CONFIG}"
+}
+
+if has_renamed_memintrinsics
then
MEM_FUNCS="__memcpy __memset"
else
@@ -26,8 +31,7 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold
__secondary_hold_acknowledge __secondary_hold_spinloop __start
logo_linux_clut224 btext_prepare_BAT
reloc_got2 kernstart_addr memstart_addr linux_banner _stext
-__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC.
-relocate"
+btext_setup_display TOC. relocate"
NM="$1"
OBJ="$2"
@@ -38,25 +42,24 @@ check_section()
{
file=$1
section=$2
- size=$(objdump -h -j $section $file 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
+ size=$(objdump -h -j "$section" "$file" 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
size=${size:-0}
- if [ $size -ne 0 ]; then
+ if [ "$size" -ne 0 ]; then
ERROR=1
echo "Error: Section $section not empty in prom_init.c" >&2
fi
}
-for UNDEF in $($NM -u $OBJ | awk '{print $2}')
+for UNDEF in $($NM -u "$OBJ" | awk '{print $2}')
do
# On 64-bit nm gives us the function descriptors, which have
# a leading . on the name, so strip it off here.
UNDEF="${UNDEF#.}"
- if [ $KBUILD_VERBOSE ]; then
- if [ $KBUILD_VERBOSE -ne 0 ]; then
- echo "Checking prom_init.o symbol '$UNDEF'"
- fi
- fi
+ case "$KBUILD_VERBOSE" in
+ *1*)
+ echo "Checking prom_init.o symbol '$UNDEF'" ;;
+ esac
OK=0
for WHITE in $WHITELIST
@@ -84,8 +87,8 @@ do
fi
done
-check_section $OBJ .data
-check_section $OBJ .bss
-check_section $OBJ .init.data
+check_section "$OBJ" .data
+check_section "$OBJ" .bss
+check_section "$OBJ" .init.data
exit $ERROR
diff --git a/arch/powerpc/kernel/ptrace/ptrace-decl.h b/arch/powerpc/kernel/ptrace/ptrace-decl.h
index eafe5f0f6289..4171a5727197 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-decl.h
+++ b/arch/powerpc/kernel/ptrace/ptrace-decl.h
@@ -1,5 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <linux/regset.h>
+
/*
* Set of msr bits that gdb can change on behalf of a process.
*/
@@ -55,6 +57,10 @@ enum powerpc_regset {
REGSET_TAR, /* TAR register */
REGSET_EBB, /* EBB registers */
REGSET_PMR, /* Performance Monitor Registers */
+ REGSET_DEXCR, /* DEXCR registers */
+#ifdef CONFIG_CHECKPOINT_RESTORE
+ REGSET_HASHKEYR, /* HASHKEYR register */
+#endif
#endif
#ifdef CONFIG_PPC_MEM_KEYS
REGSET_PKEY, /* AMR register */
diff --git a/arch/powerpc/kernel/ptrace/ptrace-tm.c b/arch/powerpc/kernel/ptrace/ptrace-tm.c
index 44045363a903..447bff87fd21 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-tm.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-tm.c
@@ -12,7 +12,7 @@ void flush_tmregs_to_thread(struct task_struct *tsk)
{
/*
* If task is not current, it will have been flushed already to
- * it's thread_struct during __switch_to().
+ * its thread_struct during __switch_to().
*
* A reclaim flushes ALL the state or if not in TM save TM SPRs
* in the appropriate thread structures from live.
@@ -170,9 +170,9 @@ int tm_cgpr_set(struct task_struct *target, const struct user_regset *regset,
(PT_MAX_PUT_REG + 1) * sizeof(reg));
if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
- ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
- (PT_MAX_PUT_REG + 1) * sizeof(reg),
- PT_TRAP * sizeof(reg));
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_MAX_PUT_REG + 1) * sizeof(reg),
+ PT_TRAP * sizeof(reg));
if (!ret && count > 0) {
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
@@ -183,8 +183,8 @@ int tm_cgpr_set(struct task_struct *target, const struct user_regset *regset,
}
if (!ret)
- ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
- (PT_TRAP + 1) * sizeof(reg), -1);
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
return ret;
}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index 076d867412c7..0310f9097e39 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -267,9 +267,9 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
(PT_MAX_PUT_REG + 1) * sizeof(reg));
if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
- ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
- (PT_MAX_PUT_REG + 1) * sizeof(reg),
- PT_TRAP * sizeof(reg));
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_MAX_PUT_REG + 1) * sizeof(reg),
+ PT_TRAP * sizeof(reg));
if (!ret && count > 0) {
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
@@ -280,8 +280,8 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
}
if (!ret)
- ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
- (PT_TRAP + 1) * sizeof(reg), -1);
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
return ret;
}
@@ -290,6 +290,9 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
static int ppr_get(struct task_struct *target, const struct user_regset *regset,
struct membuf to)
{
+ if (!target->thread.regs)
+ return -EINVAL;
+
return membuf_write(&to, &target->thread.regs->ppr, sizeof(u64));
}
@@ -297,6 +300,9 @@ static int ppr_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count, const void *kbuf,
const void __user *ubuf)
{
+ if (!target->thread.regs)
+ return -EINVAL;
+
return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&target->thread.regs->ppr, 0, sizeof(u64));
}
@@ -448,7 +454,60 @@ static int pmu_set(struct task_struct *target, const struct user_regset *regset,
5 * sizeof(unsigned long));
return ret;
}
-#endif
+
+static int dexcr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ return regset->n;
+}
+
+static int dexcr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ membuf_store(&to, (u64)lower_32_bits(target->thread.dexcr));
+
+ /*
+ * Technically the HDEXCR is per-cpu, but a hypervisor can't reasonably
+ * change it between CPUs of the same guest.
+ */
+ return membuf_store(&to, (u64)lower_32_bits(mfspr(SPRN_HDEXCR_RO)));
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int hashkeyr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ return regset->n;
+}
+
+static int hashkeyr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ return membuf_store(&to, target->thread.hashkeyr);
+}
+
+static int hashkeyr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.hashkeyr,
+ 0, sizeof(unsigned long));
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_PPC_MEM_KEYS
static int pkey_active(struct task_struct *target, const struct user_regset *regset)
@@ -509,110 +568,122 @@ static int pkey_set(struct task_struct *target, const struct user_regset *regset
static const struct user_regset native_regsets[] = {
[REGSET_GPR] = {
- .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+ USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG,
.size = sizeof(long), .align = sizeof(long),
.regset_get = gpr_get, .set = gpr_set
},
[REGSET_FPR] = {
- .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+ USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG,
.size = sizeof(double), .align = sizeof(double),
.regset_get = fpr_get, .set = fpr_set
},
#ifdef CONFIG_ALTIVEC
[REGSET_VMX] = {
- .core_note_type = NT_PPC_VMX, .n = 34,
+ USER_REGSET_NOTE_TYPE(PPC_VMX), .n = 34,
.size = sizeof(vector128), .align = sizeof(vector128),
.active = vr_active, .regset_get = vr_get, .set = vr_set
},
#endif
#ifdef CONFIG_VSX
[REGSET_VSX] = {
- .core_note_type = NT_PPC_VSX, .n = 32,
+ USER_REGSET_NOTE_TYPE(PPC_VSX), .n = 32,
.size = sizeof(double), .align = sizeof(double),
.active = vsr_active, .regset_get = vsr_get, .set = vsr_set
},
#endif
#ifdef CONFIG_SPE
[REGSET_SPE] = {
- .core_note_type = NT_PPC_SPE, .n = 35,
+ USER_REGSET_NOTE_TYPE(PPC_SPE), .n = 35,
.size = sizeof(u32), .align = sizeof(u32),
.active = evr_active, .regset_get = evr_get, .set = evr_set
},
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
[REGSET_TM_CGPR] = {
- .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CGPR), .n = ELF_NGREG,
.size = sizeof(long), .align = sizeof(long),
.active = tm_cgpr_active, .regset_get = tm_cgpr_get, .set = tm_cgpr_set
},
[REGSET_TM_CFPR] = {
- .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CFPR), .n = ELF_NFPREG,
.size = sizeof(double), .align = sizeof(double),
.active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set
},
[REGSET_TM_CVMX] = {
- .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CVMX), .n = ELF_NVMX,
.size = sizeof(vector128), .align = sizeof(vector128),
.active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set
},
[REGSET_TM_CVSX] = {
- .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CVSX), .n = ELF_NVSX,
.size = sizeof(double), .align = sizeof(double),
.active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set
},
[REGSET_TM_SPR] = {
- .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+ USER_REGSET_NOTE_TYPE(PPC_TM_SPR), .n = ELF_NTMSPRREG,
.size = sizeof(u64), .align = sizeof(u64),
.active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set
},
[REGSET_TM_CTAR] = {
- .core_note_type = NT_PPC_TM_CTAR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CTAR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set
},
[REGSET_TM_CPPR] = {
- .core_note_type = NT_PPC_TM_CPPR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CPPR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set
},
[REGSET_TM_CDSCR] = {
- .core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CDSCR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set
},
#endif
#ifdef CONFIG_PPC64
[REGSET_PPR] = {
- .core_note_type = NT_PPC_PPR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_PPR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.regset_get = ppr_get, .set = ppr_set
},
[REGSET_DSCR] = {
- .core_note_type = NT_PPC_DSCR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_DSCR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.regset_get = dscr_get, .set = dscr_set
},
#endif
#ifdef CONFIG_PPC_BOOK3S_64
[REGSET_TAR] = {
- .core_note_type = NT_PPC_TAR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_TAR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.regset_get = tar_get, .set = tar_set
},
[REGSET_EBB] = {
- .core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+ USER_REGSET_NOTE_TYPE(PPC_EBB), .n = ELF_NEBB,
.size = sizeof(u64), .align = sizeof(u64),
.active = ebb_active, .regset_get = ebb_get, .set = ebb_set
},
[REGSET_PMR] = {
- .core_note_type = NT_PPC_PMU, .n = ELF_NPMU,
+ USER_REGSET_NOTE_TYPE(PPC_PMU), .n = ELF_NPMU,
.size = sizeof(u64), .align = sizeof(u64),
.active = pmu_active, .regset_get = pmu_get, .set = pmu_set
},
+ [REGSET_DEXCR] = {
+ USER_REGSET_NOTE_TYPE(PPC_DEXCR), .n = ELF_NDEXCR,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = dexcr_active, .regset_get = dexcr_get
+ },
+#ifdef CONFIG_CHECKPOINT_RESTORE
+ [REGSET_HASHKEYR] = {
+ USER_REGSET_NOTE_TYPE(PPC_HASHKEYR), .n = ELF_NHASHKEYR,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = hashkeyr_active, .regset_get = hashkeyr_get, .set = hashkeyr_set
+ },
+#endif
#endif
#ifdef CONFIG_PPC_MEM_KEYS
[REGSET_PKEY] = {
- .core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY,
+ USER_REGSET_NOTE_TYPE(PPC_PKEY), .n = ELF_NPKEY,
.size = sizeof(u64), .align = sizeof(u64),
.active = pkey_active, .regset_get = pkey_get, .set = pkey_set
},
@@ -640,80 +711,110 @@ int gpr32_get_common(struct task_struct *target,
return membuf_zero(&to, (ELF_NGREG - PT_REGS_COUNT) * sizeof(u32));
}
-int gpr32_set_common(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf,
- unsigned long *regs)
+static int gpr32_set_common_kernel(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, unsigned long *regs)
{
const compat_ulong_t *k = kbuf;
+
+ pos /= sizeof(compat_ulong_t);
+ count /= sizeof(compat_ulong_t);
+
+ for (; count > 0 && pos < PT_MSR; --count)
+ regs[pos++] = *k++;
+
+ if (count > 0 && pos == PT_MSR) {
+ set_user_msr(target, *k++);
+ ++pos;
+ --count;
+ }
+
+ for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
+ regs[pos++] = *k++;
+ for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+ ++k;
+
+ if (count > 0 && pos == PT_TRAP) {
+ set_user_trap(target, *k++);
+ ++pos;
+ --count;
+ }
+
+ kbuf = k;
+ pos *= sizeof(compat_ulong_t);
+ count *= sizeof(compat_ulong_t);
+ user_regset_copyin_ignore(&pos, &count, &kbuf, NULL,
+ (PT_TRAP + 1) * sizeof(compat_ulong_t), -1);
+ return 0;
+}
+
+static int gpr32_set_common_user(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void __user *ubuf, unsigned long *regs)
+{
const compat_ulong_t __user *u = ubuf;
+ const void *kbuf = NULL;
compat_ulong_t reg;
- if (!kbuf && !user_read_access_begin(u, count))
+ if (!user_read_access_begin(u, count))
return -EFAULT;
pos /= sizeof(reg);
count /= sizeof(reg);
- if (kbuf)
- for (; count > 0 && pos < PT_MSR; --count)
- regs[pos++] = *k++;
- else
- for (; count > 0 && pos < PT_MSR; --count) {
- unsafe_get_user(reg, u++, Efault);
- regs[pos++] = reg;
- }
-
+ for (; count > 0 && pos < PT_MSR; --count) {
+ unsafe_get_user(reg, u++, Efault);
+ regs[pos++] = reg;
+ }
if (count > 0 && pos == PT_MSR) {
- if (kbuf)
- reg = *k++;
- else
- unsafe_get_user(reg, u++, Efault);
+ unsafe_get_user(reg, u++, Efault);
set_user_msr(target, reg);
++pos;
--count;
}
- if (kbuf) {
- for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
- regs[pos++] = *k++;
- for (; count > 0 && pos < PT_TRAP; --count, ++pos)
- ++k;
- } else {
- for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
- unsafe_get_user(reg, u++, Efault);
- regs[pos++] = reg;
- }
- for (; count > 0 && pos < PT_TRAP; --count, ++pos)
- unsafe_get_user(reg, u++, Efault);
+ for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
+ unsafe_get_user(reg, u++, Efault);
+ regs[pos++] = reg;
}
+ for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+ unsafe_get_user(reg, u++, Efault);
if (count > 0 && pos == PT_TRAP) {
- if (kbuf)
- reg = *k++;
- else
- unsafe_get_user(reg, u++, Efault);
+ unsafe_get_user(reg, u++, Efault);
set_user_trap(target, reg);
++pos;
--count;
}
- if (!kbuf)
- user_read_access_end();
+ user_read_access_end();
- kbuf = k;
ubuf = u;
pos *= sizeof(reg);
count *= sizeof(reg);
- return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
- (PT_TRAP + 1) * sizeof(reg), -1);
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
+ return 0;
Efault:
user_read_access_end();
return -EFAULT;
}
+int gpr32_set_common(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf,
+ unsigned long *regs)
+{
+ if (kbuf)
+ return gpr32_set_common_kernel(target, regset, pos, count, kbuf, regs);
+ else
+ return gpr32_set_common_user(target, regset, pos, count, ubuf, regs);
+}
+
static int gpr32_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
@@ -742,92 +843,92 @@ static int gpr32_set(struct task_struct *target,
*/
static const struct user_regset compat_regsets[] = {
[REGSET_GPR] = {
- .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+ USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG,
.size = sizeof(compat_long_t), .align = sizeof(compat_long_t),
.regset_get = gpr32_get, .set = gpr32_set
},
[REGSET_FPR] = {
- .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+ USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG,
.size = sizeof(double), .align = sizeof(double),
.regset_get = fpr_get, .set = fpr_set
},
#ifdef CONFIG_ALTIVEC
[REGSET_VMX] = {
- .core_note_type = NT_PPC_VMX, .n = 34,
+ USER_REGSET_NOTE_TYPE(PPC_VMX), .n = 34,
.size = sizeof(vector128), .align = sizeof(vector128),
.active = vr_active, .regset_get = vr_get, .set = vr_set
},
#endif
#ifdef CONFIG_SPE
[REGSET_SPE] = {
- .core_note_type = NT_PPC_SPE, .n = 35,
+ USER_REGSET_NOTE_TYPE(PPC_SPE), .n = 35,
.size = sizeof(u32), .align = sizeof(u32),
.active = evr_active, .regset_get = evr_get, .set = evr_set
},
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
[REGSET_TM_CGPR] = {
- .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CGPR), .n = ELF_NGREG,
.size = sizeof(long), .align = sizeof(long),
.active = tm_cgpr_active,
.regset_get = tm_cgpr32_get, .set = tm_cgpr32_set
},
[REGSET_TM_CFPR] = {
- .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CFPR), .n = ELF_NFPREG,
.size = sizeof(double), .align = sizeof(double),
.active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set
},
[REGSET_TM_CVMX] = {
- .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CVMX), .n = ELF_NVMX,
.size = sizeof(vector128), .align = sizeof(vector128),
.active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set
},
[REGSET_TM_CVSX] = {
- .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CVSX), .n = ELF_NVSX,
.size = sizeof(double), .align = sizeof(double),
.active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set
},
[REGSET_TM_SPR] = {
- .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+ USER_REGSET_NOTE_TYPE(PPC_TM_SPR), .n = ELF_NTMSPRREG,
.size = sizeof(u64), .align = sizeof(u64),
.active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set
},
[REGSET_TM_CTAR] = {
- .core_note_type = NT_PPC_TM_CTAR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CTAR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set
},
[REGSET_TM_CPPR] = {
- .core_note_type = NT_PPC_TM_CPPR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CPPR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set
},
[REGSET_TM_CDSCR] = {
- .core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_TM_CDSCR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set
},
#endif
#ifdef CONFIG_PPC64
[REGSET_PPR] = {
- .core_note_type = NT_PPC_PPR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_PPR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.regset_get = ppr_get, .set = ppr_set
},
[REGSET_DSCR] = {
- .core_note_type = NT_PPC_DSCR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_DSCR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.regset_get = dscr_get, .set = dscr_set
},
#endif
#ifdef CONFIG_PPC_BOOK3S_64
[REGSET_TAR] = {
- .core_note_type = NT_PPC_TAR, .n = 1,
+ USER_REGSET_NOTE_TYPE(PPC_TAR), .n = 1,
.size = sizeof(u64), .align = sizeof(u64),
.regset_get = tar_get, .set = tar_set
},
[REGSET_EBB] = {
- .core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+ USER_REGSET_NOTE_TYPE(PPC_EBB), .n = ELF_NEBB,
.size = sizeof(u64), .align = sizeof(u64),
.active = ebb_active, .regset_get = ebb_get, .set = ebb_set
},
diff --git a/arch/powerpc/kernel/ptrace/ptrace-vsx.c b/arch/powerpc/kernel/ptrace/ptrace-vsx.c
index 1da4303128ef..7df08004c47d 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-vsx.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-vsx.c
@@ -71,7 +71,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset,
}
/*
- * Currently to set and and get all the vsx state, you need to call
+ * Currently to set and get all the vsx state, you need to call
* the fp and VMX calls as well. This only get/sets the lower 32
* 128bit VSX registers.
*/
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 5d7a72b41ae7..c6997df63287 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -9,10 +10,6 @@
*
* Modified by Cort Dougan (cort@hq.fsmlabs.com)
* and Paul Mackerras (paulus@samba.org).
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License. See the file README.legal in the main directory of
- * this archive for more details.
*/
#include <linux/regset.h>
@@ -218,7 +215,7 @@ static int do_seccomp(struct pt_regs *regs)
* have already loaded -ENOSYS into r3, or seccomp has put
* something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
*/
- if (__secure_computing(NULL))
+ if (__secure_computing())
return -1;
/*
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index 232e4549defe..efd52f2e7033 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -27,8 +27,8 @@ _GLOBAL(relocate)
add r9,r9,r12 /* r9 has runtime addr of .rela.dyn section */
ld r10,(p_st - 0b)(r12)
add r10,r10,r12 /* r10 has runtime addr of _stext */
- ld r13,(p_sym - 0b)(r12)
- add r13,r13,r12 /* r13 has runtime addr of .dynsym */
+ ld r4,(p_sym - 0b)(r12)
+ add r4,r4,r12 /* r4 has runtime addr of .dynsym */
/*
* Scan the dynamic section for the RELA, RELASZ and RELAENT entries.
@@ -84,16 +84,16 @@ _GLOBAL(relocate)
ld r0,16(r9) /* reloc->r_addend */
b .Lstore
.Luaddr64:
- srdi r14,r0,32 /* ELF64_R_SYM(reloc->r_info) */
+ srdi r5,r0,32 /* ELF64_R_SYM(reloc->r_info) */
clrldi r0,r0,32
cmpdi r0,R_PPC64_UADDR64
bne .Lnext
ld r6,0(r9)
ld r0,16(r9)
- mulli r14,r14,24 /* 24 == sizeof(elf64_sym) */
- add r14,r14,r13 /* elf64_sym[ELF64_R_SYM] */
- ld r14,8(r14)
- add r0,r0,r14
+ mulli r5,r5,24 /* 24 == sizeof(elf64_sym) */
+ add r5,r5,r4 /* elf64_sym[ELF64_R_SYM] */
+ ld r5,8(r5)
+ add r0,r0,r5
.Lstore:
add r0,r0,r3
stdx r0,r7,r6
diff --git a/arch/powerpc/kernel/rethook.c b/arch/powerpc/kernel/rethook.c
new file mode 100644
index 000000000000..5f5f47ae82cf
--- /dev/null
+++ b/arch/powerpc/kernel/rethook.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PowerPC implementation of rethook. This depends on kprobes.
+ */
+
+#include <linux/kprobes.h>
+#include <linux/rethook.h>
+
+/*
+ * Function return trampoline:
+ * - init_kprobes() establishes a probepoint here
+ * - When the probed function returns, this probe
+ * causes the handlers to fire
+ */
+asm(".global arch_rethook_trampoline\n"
+ ".type arch_rethook_trampoline, @function\n"
+ "arch_rethook_trampoline:\n"
+ "nop\n"
+ "blr\n"
+ ".size arch_rethook_trampoline, .-arch_rethook_trampoline\n");
+
+/*
+ * Called when the probe at kretprobe trampoline is hit
+ */
+static int trampoline_rethook_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ return !rethook_trampoline_handler(regs, regs->gpr[1]);
+}
+NOKPROBE_SYMBOL(trampoline_rethook_handler);
+
+void arch_rethook_prepare(struct rethook_node *rh, struct pt_regs *regs, bool mcount)
+{
+ rh->ret_addr = regs->link;
+ rh->frame = regs->gpr[1];
+
+ /* Replace the return addr with trampoline addr */
+ regs->link = (unsigned long)arch_rethook_trampoline;
+}
+NOKPROBE_SYMBOL(arch_rethook_prepare);
+
+/* This is called from rethook_trampoline_handler(). */
+void arch_rethook_fixup_return(struct pt_regs *regs, unsigned long orig_ret_address)
+{
+ /*
+ * We get here through one of two paths:
+ * 1. by taking a trap -> kprobe_handler() -> here
+ * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here
+ *
+ * When going back through (1), we need regs->nip to be setup properly
+ * as it is used to determine the return address from the trap.
+ * For (2), since nip is not honoured with optprobes, we instead setup
+ * the link register properly so that the subsequent 'blr' in
+ * arch_rethook_trampoline jumps back to the right instruction.
+ *
+ * For nip, we should set the address to the previous instruction since
+ * we end up emulating it in kprobe_handler(), which increments the nip
+ * again.
+ */
+ regs_set_return_ip(regs, orig_ret_address - 4);
+ regs->link = orig_ret_address;
+}
+NOKPROBE_SYMBOL(arch_rethook_fixup_return);
+
+static struct kprobe trampoline_p = {
+ .addr = (kprobe_opcode_t *) &arch_rethook_trampoline,
+ .pre_handler = trampoline_rethook_handler
+};
+
+/* rethook initializer */
+int __init arch_init_kprobes(void)
+{
+ return register_kprobe(&trampoline_p);
+}
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 081b2b741a8c..f38df72e64b8 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -287,9 +287,9 @@ static ssize_t ppc_rtas_poweron_write(struct file *file,
rtc_time64_to_tm(nowtime, &tm);
- error = rtas_call(rtas_token("set-time-for-power-on"), 7, 1, NULL,
- tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
- tm.tm_hour, tm.tm_min, tm.tm_sec, 0 /* nano */);
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_TIME_FOR_POWER_ON), 7, 1, NULL,
+ tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+ tm.tm_hour, tm.tm_min, tm.tm_sec, 0 /* nano */);
if (error)
printk(KERN_WARNING "error: setting poweron time returned: %s\n",
ppc_rtas_process_error(error));
@@ -350,9 +350,9 @@ static ssize_t ppc_rtas_clock_write(struct file *file,
return error;
rtc_time64_to_tm(nowtime, &tm);
- error = rtas_call(rtas_token("set-time-of-day"), 7, 1, NULL,
- tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
- tm.tm_hour, tm.tm_min, tm.tm_sec, 0);
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_TIME_OF_DAY), 7, 1, NULL,
+ tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+ tm.tm_hour, tm.tm_min, tm.tm_sec, 0);
if (error)
printk(KERN_WARNING "error: setting the clock returned: %s\n",
ppc_rtas_process_error(error));
@@ -362,7 +362,7 @@ static ssize_t ppc_rtas_clock_write(struct file *file,
static int ppc_rtas_clock_show(struct seq_file *m, void *v)
{
int ret[8];
- int error = rtas_call(rtas_token("get-time-of-day"), 0, 8, ret);
+ int error = rtas_call(rtas_function_token(RTAS_FN_GET_TIME_OF_DAY), 0, 8, ret);
if (error) {
printk(KERN_WARNING "error: reading the clock returned: %s\n",
@@ -385,7 +385,7 @@ static int ppc_rtas_sensors_show(struct seq_file *m, void *v)
{
int i,j;
int state, error;
- int get_sensor_state = rtas_token("get-sensor-state");
+ int get_sensor_state = rtas_function_token(RTAS_FN_GET_SENSOR_STATE);
seq_printf(m, "RTAS (RunTime Abstraction Services) Sensor Information\n");
seq_printf(m, "Sensor\t\tValue\t\tCondition\tLocation\n");
@@ -708,8 +708,8 @@ static ssize_t ppc_rtas_tone_freq_write(struct file *file,
return error;
rtas_tone_frequency = freq; /* save it for later */
- error = rtas_call(rtas_token("set-indicator"), 3, 1, NULL,
- TONE_FREQUENCY, 0, freq);
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_INDICATOR), 3, 1, NULL,
+ TONE_FREQUENCY, 0, freq);
if (error)
printk(KERN_WARNING "error: setting tone frequency returned: %s\n",
ppc_rtas_process_error(error));
@@ -736,8 +736,8 @@ static ssize_t ppc_rtas_tone_volume_write(struct file *file,
volume = 100;
rtas_tone_volume = volume; /* save it for later */
- error = rtas_call(rtas_token("set-indicator"), 3, 1, NULL,
- TONE_VOLUME, 0, volume);
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_INDICATOR), 3, 1, NULL,
+ TONE_VOLUME, 0, volume);
if (error)
printk(KERN_WARNING "error: setting tone volume returned: %s\n",
ppc_rtas_process_error(error));
@@ -752,6 +752,8 @@ static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v)
/**
* ppc_rtas_rmo_buf_show() - Describe RTAS-addressable region for user space.
+ * @m: seq_file output target.
+ * @v: Unused.
*
* Base + size description of a range of RTAS-addressable memory set
* aside for user space to use as work area(s) for certain RTAS
diff --git a/arch/powerpc/kernel/rtas-rtc.c b/arch/powerpc/kernel/rtas-rtc.c
index 5a31d1829bca..6996214532bd 100644
--- a/arch/powerpc/kernel/rtas-rtc.c
+++ b/arch/powerpc/kernel/rtas-rtc.c
@@ -21,7 +21,7 @@ time64_t __init rtas_get_boot_time(void)
max_wait_tb = get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
do {
- error = rtas_call(rtas_token("get-time-of-day"), 0, 8, ret);
+ error = rtas_call(rtas_function_token(RTAS_FN_GET_TIME_OF_DAY), 0, 8, ret);
wait_time = rtas_busy_delay_time(error);
if (wait_time) {
@@ -53,7 +53,7 @@ void rtas_get_rtc_time(struct rtc_time *rtc_tm)
max_wait_tb = get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
do {
- error = rtas_call(rtas_token("get-time-of-day"), 0, 8, ret);
+ error = rtas_call(rtas_function_token(RTAS_FN_GET_TIME_OF_DAY), 0, 8, ret);
wait_time = rtas_busy_delay_time(error);
if (wait_time) {
@@ -90,7 +90,7 @@ int rtas_set_rtc_time(struct rtc_time *tm)
max_wait_tb = get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
do {
- error = rtas_call(rtas_token("set-time-of-day"), 7, 1, NULL,
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_TIME_OF_DAY), 7, 1, NULL,
tm->tm_year + 1900, tm->tm_mon + 1,
tm->tm_mday, tm->tm_hour, tm->tm_min,
tm->tm_sec, 0);
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 693133972294..e61245c4468e 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -7,77 +7,741 @@
* Copyright (C) 2001 IBM.
*/
-#include <linux/stdarg.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/spinlock.h>
-#include <linux/export.h>
-#include <linux/init.h>
+#define pr_fmt(fmt) "rtas: " fmt
+
+#include <linux/bsearch.h>
#include <linux/capability.h>
#include <linux/delay.h>
-#include <linux/cpu.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <linux/completion.h>
-#include <linux/cpumask.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/lockdep.h>
#include <linux/memblock.h>
-#include <linux/slab.h>
-#include <linux/reboot.h>
-#include <linux/syscalls.h>
+#include <linux/mutex.h>
+#include <linux/nospec.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stdarg.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/xarray.h>
+#include <asm/delay.h>
+#include <asm/firmware.h>
#include <asm/interrupt.h>
-#include <asm/rtas.h>
-#include <asm/hvcall.h>
#include <asm/machdep.h>
-#include <asm/firmware.h>
+#include <asm/mmu.h>
#include <asm/page.h>
-#include <asm/param.h>
-#include <asm/delay.h>
-#include <linux/uaccess.h>
-#include <asm/udbg.h>
-#include <asm/syscalls.h>
-#include <asm/smp.h>
-#include <linux/atomic.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
#include <asm/time.h>
-#include <asm/mmu.h>
-#include <asm/topology.h>
-#include <asm/paca.h>
+#include <asm/trace.h>
+#include <asm/udbg.h>
+
+struct rtas_filter {
+ /* Indexes into the args buffer, -1 if not used */
+ const int buf_idx1;
+ const int size_idx1;
+ const int buf_idx2;
+ const int size_idx2;
+ /*
+ * Assumed buffer size per the spec if the function does not
+ * have a size parameter, e.g. ibm,errinjct. 0 if unused.
+ */
+ const int fixed_size;
+};
+
+/**
+ * struct rtas_function - Descriptor for RTAS functions.
+ *
+ * @token: Value of @name if it exists under the /rtas node.
+ * @name: Function name.
+ * @filter: If non-NULL, invoking this function via the rtas syscall is
+ * generally allowed, and @filter describes constraints on the
+ * arguments. See also @banned_for_syscall_on_le.
+ * @banned_for_syscall_on_le: Set when call via sys_rtas is generally allowed
+ * but specifically restricted on ppc64le. Such
+ * functions are believed to have no users on
+ * ppc64le, and we want to keep it that way. It does
+ * not make sense for this to be set when @filter
+ * is NULL.
+ * @lock: Pointer to an optional dedicated per-function mutex. This
+ * should be set for functions that require multiple calls in
+ * sequence to complete a single operation, and such sequences
+ * will disrupt each other if allowed to interleave. Users of
+ * this function are required to hold the associated lock for
+ * the duration of the call sequence. Add an explanatory
+ * comment to the function table entry if setting this member.
+ */
+struct rtas_function {
+ s32 token;
+ const bool banned_for_syscall_on_le:1;
+ const char * const name;
+ const struct rtas_filter *filter;
+ struct mutex *lock;
+};
+
+/*
+ * Per-function locks for sequence-based RTAS functions.
+ */
+static DEFINE_MUTEX(rtas_ibm_activate_firmware_lock);
+static DEFINE_MUTEX(rtas_ibm_lpar_perftools_lock);
+DEFINE_MUTEX(rtas_ibm_physical_attestation_lock);
+DEFINE_MUTEX(rtas_ibm_get_vpd_lock);
+DEFINE_MUTEX(rtas_ibm_get_indices_lock);
+DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock);
+DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock);
+
+static struct rtas_function rtas_function_table[] __ro_after_init = {
+ [RTAS_FNIDX__CHECK_EXCEPTION] = {
+ .name = "check-exception",
+ },
+ [RTAS_FNIDX__DISPLAY_CHARACTER] = {
+ .name = "display-character",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__EVENT_SCAN] = {
+ .name = "event-scan",
+ },
+ [RTAS_FNIDX__FREEZE_TIME_BASE] = {
+ .name = "freeze-time-base",
+ },
+ [RTAS_FNIDX__GET_POWER_LEVEL] = {
+ .name = "get-power-level",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__GET_SENSOR_STATE] = {
+ .name = "get-sensor-state",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__GET_TERM_CHAR] = {
+ .name = "get-term-char",
+ },
+ [RTAS_FNIDX__GET_TIME_OF_DAY] = {
+ .name = "get-time-of-day",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_ACTIVATE_FIRMWARE] = {
+ .name = "ibm,activate-firmware",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ /*
+ * PAPR+ as of v2.13 doesn't explicitly impose any
+ * restriction, but this typically requires multiple
+ * calls before success, and there's no reason to
+ * allow sequences to interleave.
+ */
+ .lock = &rtas_ibm_activate_firmware_lock,
+ },
+ [RTAS_FNIDX__IBM_CBE_START_PTCAL] = {
+ .name = "ibm,cbe-start-ptcal",
+ },
+ [RTAS_FNIDX__IBM_CBE_STOP_PTCAL] = {
+ .name = "ibm,cbe-stop-ptcal",
+ },
+ [RTAS_FNIDX__IBM_CHANGE_MSI] = {
+ .name = "ibm,change-msi",
+ },
+ [RTAS_FNIDX__IBM_CLOSE_ERRINJCT] = {
+ .name = "ibm,close-errinjct",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_CONFIGURE_BRIDGE] = {
+ .name = "ibm,configure-bridge",
+ },
+ [RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR] = {
+ .name = "ibm,configure-connector",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = 1, .size_idx2 = -1,
+ .fixed_size = 4096,
+ },
+ },
+ [RTAS_FNIDX__IBM_CONFIGURE_KERNEL_DUMP] = {
+ .name = "ibm,configure-kernel-dump",
+ },
+ [RTAS_FNIDX__IBM_CONFIGURE_PE] = {
+ .name = "ibm,configure-pe",
+ },
+ [RTAS_FNIDX__IBM_CREATE_PE_DMA_WINDOW] = {
+ .name = "ibm,create-pe-dma-window",
+ },
+ [RTAS_FNIDX__IBM_DISPLAY_MESSAGE] = {
+ .name = "ibm,display-message",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_ERRINJCT] = {
+ .name = "ibm,errinjct",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 2, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ .fixed_size = 1024,
+ },
+ },
+ [RTAS_FNIDX__IBM_EXTI2C] = {
+ .name = "ibm,exti2c",
+ },
+ [RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO] = {
+ .name = "ibm,get-config-addr-info",
+ },
+ [RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO2] = {
+ .name = "ibm,get-config-addr-info2",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_GET_DYNAMIC_SENSOR_STATE] = {
+ .name = "ibm,get-dynamic-sensor-state",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ /*
+ * PAPR+ v2.13 R1–7.3.19–3 is explicit that the OS
+ * must not call ibm,get-dynamic-sensor-state with
+ * different inputs until a non-retry status has been
+ * returned.
+ */
+ .lock = &rtas_ibm_get_dynamic_sensor_state_lock,
+ },
+ [RTAS_FNIDX__IBM_GET_INDICES] = {
+ .name = "ibm,get-indices",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 2, .size_idx1 = 3,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ /*
+ * PAPR+ v2.13 R1–7.3.17–2 says that the OS must not
+ * interleave ibm,get-indices call sequences with
+ * different inputs.
+ */
+ .lock = &rtas_ibm_get_indices_lock,
+ },
+ [RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY] = {
+ .name = "ibm,get-rio-topology",
+ },
+ [RTAS_FNIDX__IBM_GET_SYSTEM_PARAMETER] = {
+ .name = "ibm,get-system-parameter",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 1, .size_idx1 = 2,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_GET_VPD] = {
+ .name = "ibm,get-vpd",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = 1, .size_idx2 = 2,
+ },
+ /*
+ * PAPR+ v2.13 R1–7.3.20–4 indicates that sequences
+ * should not be allowed to interleave.
+ */
+ .lock = &rtas_ibm_get_vpd_lock,
+ },
+ [RTAS_FNIDX__IBM_GET_XIVE] = {
+ .name = "ibm,get-xive",
+ },
+ [RTAS_FNIDX__IBM_INT_OFF] = {
+ .name = "ibm,int-off",
+ },
+ [RTAS_FNIDX__IBM_INT_ON] = {
+ .name = "ibm,int-on",
+ },
+ [RTAS_FNIDX__IBM_IO_QUIESCE_ACK] = {
+ .name = "ibm,io-quiesce-ack",
+ },
+ [RTAS_FNIDX__IBM_LPAR_PERFTOOLS] = {
+ .name = "ibm,lpar-perftools",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 2, .size_idx1 = 3,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ /*
+ * PAPR+ v2.13 R1–7.3.26–6 says the OS should allow
+ * only one call sequence in progress at a time.
+ */
+ .lock = &rtas_ibm_lpar_perftools_lock,
+ },
+ [RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE] = {
+ .name = "ibm,manage-flash-image",
+ },
+ [RTAS_FNIDX__IBM_MANAGE_STORAGE_PRESERVATION] = {
+ .name = "ibm,manage-storage-preservation",
+ },
+ [RTAS_FNIDX__IBM_NMI_INTERLOCK] = {
+ .name = "ibm,nmi-interlock",
+ },
+ [RTAS_FNIDX__IBM_NMI_REGISTER] = {
+ .name = "ibm,nmi-register",
+ },
+ [RTAS_FNIDX__IBM_OPEN_ERRINJCT] = {
+ .name = "ibm,open-errinjct",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_OPEN_SRIOV_ALLOW_UNFREEZE] = {
+ .name = "ibm,open-sriov-allow-unfreeze",
+ },
+ [RTAS_FNIDX__IBM_OPEN_SRIOV_MAP_PE_NUMBER] = {
+ .name = "ibm,open-sriov-map-pe-number",
+ },
+ [RTAS_FNIDX__IBM_OS_TERM] = {
+ .name = "ibm,os-term",
+ },
+ [RTAS_FNIDX__IBM_PARTNER_CONTROL] = {
+ .name = "ibm,partner-control",
+ },
+ [RTAS_FNIDX__IBM_PHYSICAL_ATTESTATION] = {
+ .name = "ibm,physical-attestation",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = 1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ /*
+ * This follows a sequence-based pattern similar to
+ * ibm,get-vpd et al. Since PAPR+ restricts
+ * interleaving call sequences for other functions of
+ * this style, assume the restriction applies here,
+ * even though it's not explicit in the spec.
+ */
+ .lock = &rtas_ibm_physical_attestation_lock,
+ },
+ [RTAS_FNIDX__IBM_PLATFORM_DUMP] = {
+ .name = "ibm,platform-dump",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 4, .size_idx1 = 5,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ /*
+ * PAPR+ v2.13 7.3.3.4.1 indicates that concurrent
+ * sequences of ibm,platform-dump are allowed if they
+ * are operating on different dump tags. So leave the
+ * lock pointer unset for now. This may need
+ * reconsideration if kernel-internal users appear.
+ */
+ },
+ [RTAS_FNIDX__IBM_POWER_OFF_UPS] = {
+ .name = "ibm,power-off-ups",
+ },
+ [RTAS_FNIDX__IBM_QUERY_INTERRUPT_SOURCE_NUMBER] = {
+ .name = "ibm,query-interrupt-source-number",
+ },
+ [RTAS_FNIDX__IBM_QUERY_PE_DMA_WINDOW] = {
+ .name = "ibm,query-pe-dma-window",
+ },
+ [RTAS_FNIDX__IBM_READ_PCI_CONFIG] = {
+ .name = "ibm,read-pci-config",
+ },
+ [RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE] = {
+ .name = "ibm,read-slot-reset-state",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2] = {
+ .name = "ibm,read-slot-reset-state2",
+ },
+ [RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = {
+ .name = "ibm,remove-pe-dma-window",
+ },
+ [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = {
+ /*
+ * Note: PAPR+ v2.13 7.3.31.4.1 spells this as
+ * "ibm,reset-pe-dma-windows" (plural), but RTAS
+ * implementations use the singular form in practice.
+ */
+ .name = "ibm,reset-pe-dma-window",
+ },
+ [RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = {
+ .name = "ibm,scan-log-dump",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = 1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR] = {
+ .name = "ibm,set-dynamic-indicator",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 2, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ /*
+ * PAPR+ v2.13 R1–7.3.18–3 says the OS must not call
+ * this function with different inputs until a
+ * non-retry status has been returned.
+ */
+ .lock = &rtas_ibm_set_dynamic_indicator_lock,
+ },
+ [RTAS_FNIDX__IBM_SET_EEH_OPTION] = {
+ .name = "ibm,set-eeh-option",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_SET_SLOT_RESET] = {
+ .name = "ibm,set-slot-reset",
+ },
+ [RTAS_FNIDX__IBM_SET_SYSTEM_PARAMETER] = {
+ .name = "ibm,set-system-parameter",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_SET_XIVE] = {
+ .name = "ibm,set-xive",
+ },
+ [RTAS_FNIDX__IBM_SLOT_ERROR_DETAIL] = {
+ .name = "ibm,slot-error-detail",
+ },
+ [RTAS_FNIDX__IBM_SUSPEND_ME] = {
+ .name = "ibm,suspend-me",
+ .banned_for_syscall_on_le = true,
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_TUNE_DMA_PARMS] = {
+ .name = "ibm,tune-dma-parms",
+ },
+ [RTAS_FNIDX__IBM_UPDATE_FLASH_64_AND_REBOOT] = {
+ .name = "ibm,update-flash-64-and-reboot",
+ },
+ [RTAS_FNIDX__IBM_UPDATE_NODES] = {
+ .name = "ibm,update-nodes",
+ .banned_for_syscall_on_le = true,
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ .fixed_size = 4096,
+ },
+ },
+ [RTAS_FNIDX__IBM_UPDATE_PROPERTIES] = {
+ .name = "ibm,update-properties",
+ .banned_for_syscall_on_le = true,
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ .fixed_size = 4096,
+ },
+ },
+ [RTAS_FNIDX__IBM_VALIDATE_FLASH_IMAGE] = {
+ .name = "ibm,validate-flash-image",
+ },
+ [RTAS_FNIDX__IBM_WRITE_PCI_CONFIG] = {
+ .name = "ibm,write-pci-config",
+ },
+ [RTAS_FNIDX__NVRAM_FETCH] = {
+ .name = "nvram-fetch",
+ },
+ [RTAS_FNIDX__NVRAM_STORE] = {
+ .name = "nvram-store",
+ },
+ [RTAS_FNIDX__POWER_OFF] = {
+ .name = "power-off",
+ },
+ [RTAS_FNIDX__PUT_TERM_CHAR] = {
+ .name = "put-term-char",
+ },
+ [RTAS_FNIDX__QUERY_CPU_STOPPED_STATE] = {
+ .name = "query-cpu-stopped-state",
+ },
+ [RTAS_FNIDX__READ_PCI_CONFIG] = {
+ .name = "read-pci-config",
+ },
+ [RTAS_FNIDX__RTAS_LAST_ERROR] = {
+ .name = "rtas-last-error",
+ },
+ [RTAS_FNIDX__SET_INDICATOR] = {
+ .name = "set-indicator",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__SET_POWER_LEVEL] = {
+ .name = "set-power-level",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__SET_TIME_FOR_POWER_ON] = {
+ .name = "set-time-for-power-on",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__SET_TIME_OF_DAY] = {
+ .name = "set-time-of-day",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__START_CPU] = {
+ .name = "start-cpu",
+ },
+ [RTAS_FNIDX__STOP_SELF] = {
+ .name = "stop-self",
+ },
+ [RTAS_FNIDX__SYSTEM_REBOOT] = {
+ .name = "system-reboot",
+ },
+ [RTAS_FNIDX__THAW_TIME_BASE] = {
+ .name = "thaw-time-base",
+ },
+ [RTAS_FNIDX__WRITE_PCI_CONFIG] = {
+ .name = "write-pci-config",
+ },
+};
+
+#define for_each_rtas_function(funcp) \
+ for (funcp = &rtas_function_table[0]; \
+ funcp < &rtas_function_table[ARRAY_SIZE(rtas_function_table)]; \
+ ++funcp)
+
+/*
+ * Nearly all RTAS calls need to be serialized. All uses of the
+ * default rtas_args block must hold rtas_lock.
+ *
+ * Exceptions to the RTAS serialization requirement (e.g. stop-self)
+ * must use a separate rtas_args structure.
+ */
+static DEFINE_RAW_SPINLOCK(rtas_lock);
+static struct rtas_args rtas_args;
+
+/**
+ * rtas_function_token() - RTAS function token lookup.
+ * @handle: Function handle, e.g. RTAS_FN_EVENT_SCAN.
+ *
+ * Context: Any context.
+ * Return: the token value for the function if implemented by this platform,
+ * otherwise RTAS_UNKNOWN_SERVICE.
+ */
+s32 rtas_function_token(const rtas_fn_handle_t handle)
+{
+ const size_t index = handle.index;
+ const bool out_of_bounds = index >= ARRAY_SIZE(rtas_function_table);
+
+ if (WARN_ONCE(out_of_bounds, "invalid function index %zu", index))
+ return RTAS_UNKNOWN_SERVICE;
+ /*
+ * Various drivers attempt token lookups on non-RTAS
+ * platforms.
+ */
+ if (!rtas.dev)
+ return RTAS_UNKNOWN_SERVICE;
+
+ return rtas_function_table[index].token;
+}
+EXPORT_SYMBOL_GPL(rtas_function_token);
+
+static int rtas_function_cmp(const void *a, const void *b)
+{
+ const struct rtas_function *f1 = a;
+ const struct rtas_function *f2 = b;
+
+ return strcmp(f1->name, f2->name);
+}
+
+/*
+ * Boot-time initialization of the function table needs the lookup to
+ * return a non-const-qualified object. Use rtas_name_to_function()
+ * in all other contexts.
+ */
+static struct rtas_function *__rtas_name_to_function(const char *name)
+{
+ const struct rtas_function key = {
+ .name = name,
+ };
+ struct rtas_function *found;
+
+ found = bsearch(&key, rtas_function_table, ARRAY_SIZE(rtas_function_table),
+ sizeof(rtas_function_table[0]), rtas_function_cmp);
+
+ return found;
+}
+
+static const struct rtas_function *rtas_name_to_function(const char *name)
+{
+ return __rtas_name_to_function(name);
+}
+
+static DEFINE_XARRAY(rtas_token_to_function_xarray);
+
+static int __init rtas_token_to_function_xarray_init(void)
+{
+ const struct rtas_function *func;
+ int err = 0;
+
+ for_each_rtas_function(func) {
+ const s32 token = func->token;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ continue;
+
+ err = xa_err(xa_store(&rtas_token_to_function_xarray,
+ token, (void *)func, GFP_KERNEL));
+ if (err)
+ break;
+ }
+
+ return err;
+}
+arch_initcall(rtas_token_to_function_xarray_init);
+
+/*
+ * For use by sys_rtas(), where the token value is provided by user
+ * space and we don't want to warn on failed lookups.
+ */
+static const struct rtas_function *rtas_token_to_function_untrusted(s32 token)
+{
+ return xa_load(&rtas_token_to_function_xarray, token);
+}
+
+/*
+ * Reverse lookup for deriving the function descriptor from a
+ * known-good token value in contexts where the former is not already
+ * available. @token must be valid, e.g. derived from the result of a
+ * prior lookup against the function table.
+ */
+static const struct rtas_function *rtas_token_to_function(s32 token)
+{
+ const struct rtas_function *func;
+
+ if (WARN_ONCE(token < 0, "invalid token %d", token))
+ return NULL;
+
+ func = rtas_token_to_function_untrusted(token);
+ if (func)
+ return func;
+ /*
+ * Fall back to linear scan in case the reverse mapping hasn't
+ * been initialized yet.
+ */
+ if (xa_empty(&rtas_token_to_function_xarray)) {
+ for_each_rtas_function(func) {
+ if (func->token == token)
+ return func;
+ }
+ }
+
+ WARN_ONCE(true, "unexpected failed lookup for token %d", token);
+ return NULL;
+}
/* This is here deliberately so it's only used in this file */
void enter_rtas(unsigned long);
-static inline void do_enter_rtas(unsigned long args)
+static void __do_enter_rtas(struct rtas_args *args)
{
- unsigned long msr;
+ enter_rtas(__pa(args));
+ srr_regs_clobbered(); /* rtas uses SRRs, invalidate */
+}
+
+static void __do_enter_rtas_trace(struct rtas_args *args)
+{
+ const struct rtas_function *func = rtas_token_to_function(be32_to_cpu(args->token));
/*
+ * If there is a per-function lock, it must be held by the
+ * caller.
+ */
+ if (func->lock)
+ lockdep_assert_held(func->lock);
+
+ if (args == &rtas_args)
+ lockdep_assert_held(&rtas_lock);
+
+ trace_rtas_input(args, func->name);
+ trace_rtas_ll_entry(args);
+
+ __do_enter_rtas(args);
+
+ trace_rtas_ll_exit(args);
+ trace_rtas_output(args, func->name);
+}
+
+static void do_enter_rtas(struct rtas_args *args)
+{
+ const unsigned long msr = mfmsr();
+ /*
+ * Situations where we want to skip any active tracepoints for
+ * safety reasons:
+ *
+ * 1. The last code executed on an offline CPU as it stops,
+ * i.e. we're about to call stop-self. The tracepoints'
+ * function name lookup uses xarray, which uses RCU, which
+ * isn't valid to call on an offline CPU. Any events
+ * emitted on an offline CPU will be discarded anyway.
+ *
+ * 2. In real mode, as when invoking ibm,nmi-interlock from
+ * the pseries MCE handler. We cannot count on trace
+ * buffers or the entries in rtas_token_to_function_xarray
+ * to be contained in the RMO.
+ */
+ const unsigned long mask = MSR_IR | MSR_DR;
+ const bool can_trace = likely(cpu_online(raw_smp_processor_id()) &&
+ (msr & mask) == mask);
+ /*
* Make sure MSR[RI] is currently enabled as it will be forced later
* in enter_rtas.
*/
- msr = mfmsr();
BUG_ON(!(msr & MSR_RI));
BUG_ON(!irqs_disabled());
hard_irq_disable(); /* Ensure MSR[EE] is disabled on PPC64 */
- enter_rtas(args);
-
- srr_regs_clobbered(); /* rtas uses SRRs, invalidate */
+ if (can_trace)
+ __do_enter_rtas_trace(args);
+ else
+ __do_enter_rtas(args);
}
-struct rtas_t rtas = {
- .lock = __ARCH_SPIN_LOCK_UNLOCKED
-};
-EXPORT_SYMBOL(rtas);
+struct rtas_t rtas;
DEFINE_SPINLOCK(rtas_data_buf_lock);
-EXPORT_SYMBOL(rtas_data_buf_lock);
+EXPORT_SYMBOL_GPL(rtas_data_buf_lock);
-char rtas_data_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned;
-EXPORT_SYMBOL(rtas_data_buf);
+char rtas_data_buf[RTAS_DATA_BUF_SIZE] __aligned(SZ_4K);
+EXPORT_SYMBOL_GPL(rtas_data_buf);
unsigned long rtas_rmo_buf;
@@ -86,29 +750,7 @@ unsigned long rtas_rmo_buf;
* This is done like this so rtas_flash can be a module.
*/
void (*rtas_flash_term_hook)(int);
-EXPORT_SYMBOL(rtas_flash_term_hook);
-
-/* RTAS use home made raw locking instead of spin_lock_irqsave
- * because those can be called from within really nasty contexts
- * such as having the timebase stopped which would lockup with
- * normal locks and spinlock debugging enabled
- */
-static unsigned long lock_rtas(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- preempt_disable();
- arch_spin_lock(&rtas.lock);
- return flags;
-}
-
-static void unlock_rtas(unsigned long flags)
-{
- arch_spin_unlock(&rtas.lock);
- local_irq_restore(flags);
- preempt_enable();
-}
+EXPORT_SYMBOL_GPL(rtas_flash_term_hook);
/*
* call_rtas_display_status and call_rtas_display_status_delay
@@ -117,14 +759,14 @@ static void unlock_rtas(unsigned long flags)
*/
static void call_rtas_display_status(unsigned char c)
{
- unsigned long s;
+ unsigned long flags;
if (!rtas.base)
return;
- s = lock_rtas();
- rtas_call_unlocked(&rtas.args, 10, 1, 1, NULL, c);
- unlock_rtas(s);
+ raw_spin_lock_irqsave(&rtas_lock, flags);
+ rtas_call_unlocked(&rtas_args, 10, 1, 1, NULL, c);
+ raw_spin_unlock_irqrestore(&rtas_lock, flags);
}
static void call_rtas_display_status_delay(char c)
@@ -132,7 +774,7 @@ static void call_rtas_display_status_delay(char c)
static int pending_newline = 0; /* did last write end with unprinted newline? */
static int width = 16;
- if (c == '\n') {
+ if (c == '\n') {
while (width-- > 0)
call_rtas_display_status(' ');
width = 16;
@@ -142,7 +784,7 @@ static void call_rtas_display_status_delay(char c)
if (pending_newline) {
call_rtas_display_status('\r');
call_rtas_display_status('\n');
- }
+ }
pending_newline = 0;
if (width--) {
call_rtas_display_status(c);
@@ -156,66 +798,6 @@ void __init udbg_init_rtas_panel(void)
udbg_putc = call_rtas_display_status_delay;
}
-#ifdef CONFIG_UDBG_RTAS_CONSOLE
-
-/* If you think you're dying before early_init_dt_scan_rtas() does its
- * work, you can hard code the token values for your firmware here and
- * hardcode rtas.base/entry etc.
- */
-static unsigned int rtas_putchar_token = RTAS_UNKNOWN_SERVICE;
-static unsigned int rtas_getchar_token = RTAS_UNKNOWN_SERVICE;
-
-static void udbg_rtascon_putc(char c)
-{
- int tries;
-
- if (!rtas.base)
- return;
-
- /* Add CRs before LFs */
- if (c == '\n')
- udbg_rtascon_putc('\r');
-
- /* if there is more than one character to be displayed, wait a bit */
- for (tries = 0; tries < 16; tries++) {
- if (rtas_call(rtas_putchar_token, 1, 1, NULL, c) == 0)
- break;
- udelay(1000);
- }
-}
-
-static int udbg_rtascon_getc_poll(void)
-{
- int c;
-
- if (!rtas.base)
- return -1;
-
- if (rtas_call(rtas_getchar_token, 0, 2, &c))
- return -1;
-
- return c;
-}
-
-static int udbg_rtascon_getc(void)
-{
- int c;
-
- while ((c = udbg_rtascon_getc_poll()) == -1)
- ;
-
- return c;
-}
-
-
-void __init udbg_init_rtas_console(void)
-{
- udbg_putc = udbg_rtascon_putc;
- udbg_getc = udbg_rtascon_getc;
- udbg_getc_poll = udbg_rtascon_getc_poll;
-}
-#endif /* CONFIG_UDBG_RTAS_CONSOLE */
-
void rtas_progress(char *s, unsigned short hex)
{
struct device_node *root;
@@ -248,8 +830,8 @@ void rtas_progress(char *s, unsigned short hex)
"ibm,display-truncation-length", NULL);
of_node_put(root);
}
- display_character = rtas_token("display-character");
- set_indicator = rtas_token("set-indicator");
+ display_character = rtas_function_token(RTAS_FN_DISPLAY_CHARACTER);
+ set_indicator = rtas_function_token(RTAS_FN_SET_INDICATOR);
}
if (display_character == RTAS_UNKNOWN_SERVICE) {
@@ -282,7 +864,7 @@ void rtas_progress(char *s, unsigned short hex)
else
rtas_call(display_character, 1, 1, NULL, '\r');
}
-
+
if (row_width)
width = row_width[current_line];
else
@@ -302,9 +884,9 @@ void rtas_progress(char *s, unsigned short hex)
spin_unlock(&progress_lock);
return;
}
-
+
/* RTAS wants CR-LF, not just LF */
-
+
if (*os == '\n') {
rtas_call(display_character, 1, 1, NULL, '\r');
rtas_call(display_character, 1, 1, NULL, '\n');
@@ -314,7 +896,7 @@ void rtas_progress(char *s, unsigned short hex)
*/
rtas_call(display_character, 1, 1, NULL, *os);
}
-
+
if (row_width)
width = row_width[current_line];
else
@@ -323,36 +905,49 @@ void rtas_progress(char *s, unsigned short hex)
width--;
rtas_call(display_character, 1, 1, NULL, *os);
}
-
+
os++;
-
+
/* if we overwrite the screen length */
if (width <= 0)
while ((*os != 0) && (*os != '\n') && (*os != '\r'))
os++;
}
-
+
spin_unlock(&progress_lock);
}
-EXPORT_SYMBOL(rtas_progress); /* needed by rtas_flash module */
+EXPORT_SYMBOL_GPL(rtas_progress); /* needed by rtas_flash module */
int rtas_token(const char *service)
{
+ const struct rtas_function *func;
const __be32 *tokp;
+
if (rtas.dev == NULL)
return RTAS_UNKNOWN_SERVICE;
+
+ func = rtas_name_to_function(service);
+ if (func)
+ return func->token;
+ /*
+ * The caller is looking up a name that is not known to be an
+ * RTAS function. Either it's a function that needs to be
+ * added to the table, or they're misusing rtas_token() to
+ * access non-function properties of the /rtas node. Warn and
+ * fall back to the legacy behavior.
+ */
+ WARN_ONCE(1, "unknown function `%s`, should it be added to rtas_function_table?\n",
+ service);
+
tokp = of_get_property(rtas.dev, service, NULL);
return tokp ? be32_to_cpu(*tokp) : RTAS_UNKNOWN_SERVICE;
}
-EXPORT_SYMBOL(rtas_token);
-
-int rtas_service_present(const char *service)
-{
- return rtas_token(service) != RTAS_UNKNOWN_SERVICE;
-}
-EXPORT_SYMBOL(rtas_service_present);
+EXPORT_SYMBOL_GPL(rtas_token);
#ifdef CONFIG_RTAS_ERROR_LOGGING
+
+static u32 rtas_error_log_max __ro_after_init = RTAS_ERROR_LOG_MAX;
+
/*
* Return the firmware-specified size of the error log buffer
* for all rtas calls that require an error buffer argument.
@@ -360,56 +955,66 @@ EXPORT_SYMBOL(rtas_service_present);
*/
int rtas_get_error_log_max(void)
{
- static int rtas_error_log_max;
- if (rtas_error_log_max)
- return rtas_error_log_max;
-
- rtas_error_log_max = rtas_token ("rtas-error-log-max");
- if ((rtas_error_log_max == RTAS_UNKNOWN_SERVICE) ||
- (rtas_error_log_max > RTAS_ERROR_LOG_MAX)) {
- printk (KERN_WARNING "RTAS: bad log buffer size %d\n",
- rtas_error_log_max);
- rtas_error_log_max = RTAS_ERROR_LOG_MAX;
- }
return rtas_error_log_max;
}
-EXPORT_SYMBOL(rtas_get_error_log_max);
+
+static void __init init_error_log_max(void)
+{
+ static const char propname[] __initconst = "rtas-error-log-max";
+ u32 max;
+
+ if (of_property_read_u32(rtas.dev, propname, &max)) {
+ pr_warn("%s not found, using default of %u\n",
+ propname, RTAS_ERROR_LOG_MAX);
+ max = RTAS_ERROR_LOG_MAX;
+ }
+
+ if (max > RTAS_ERROR_LOG_MAX) {
+ pr_warn("%s = %u, clamping max error log size to %u\n",
+ propname, max, RTAS_ERROR_LOG_MAX);
+ max = RTAS_ERROR_LOG_MAX;
+ }
+
+ rtas_error_log_max = max;
+}
static char rtas_err_buf[RTAS_ERROR_LOG_MAX];
-static int rtas_last_error_token;
/** Return a copy of the detailed error text associated with the
* most recent failed call to rtas. Because the error text
* might go stale if there are any other intervening rtas calls,
* this routine must be called atomically with whatever produced
- * the error (i.e. with rtas.lock still held from the previous call).
+ * the error (i.e. with rtas_lock still held from the previous call).
*/
static char *__fetch_rtas_last_error(char *altbuf)
{
+ const s32 token = rtas_function_token(RTAS_FN_RTAS_LAST_ERROR);
struct rtas_args err_args, save_args;
u32 bufsz;
char *buf = NULL;
- if (rtas_last_error_token == -1)
+ lockdep_assert_held(&rtas_lock);
+
+ if (token == -1)
return NULL;
bufsz = rtas_get_error_log_max();
- err_args.token = cpu_to_be32(rtas_last_error_token);
+ err_args.token = cpu_to_be32(token);
err_args.nargs = cpu_to_be32(2);
err_args.nret = cpu_to_be32(1);
err_args.args[0] = cpu_to_be32(__pa(rtas_err_buf));
err_args.args[1] = cpu_to_be32(bufsz);
err_args.args[2] = 0;
- save_args = rtas.args;
- rtas.args = err_args;
+ save_args = rtas_args;
+ rtas_args = err_args;
- do_enter_rtas(__pa(&rtas.args));
+ do_enter_rtas(&rtas_args);
- err_args = rtas.args;
- rtas.args = save_args;
+ err_args = rtas_args;
+ rtas_args = save_args;
/* Log the error in the unlikely case that there was one. */
if (unlikely(err_args.args[2] == 0)) {
@@ -421,7 +1026,7 @@ static char *__fetch_rtas_last_error(char *altbuf)
buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC);
}
if (buf)
- memcpy(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX);
+ memmove(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX);
}
return buf;
@@ -432,6 +1037,7 @@ static char *__fetch_rtas_last_error(char *altbuf)
#else /* CONFIG_RTAS_ERROR_LOGGING */
#define __fetch_rtas_last_error(x) NULL
#define get_errorlog_buffer() NULL
+static void __init init_error_log_max(void) {}
#endif
@@ -452,9 +1058,26 @@ va_rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret,
for (i = 0; i < nret; ++i)
args->rets[i] = 0;
- do_enter_rtas(__pa(args));
+ do_enter_rtas(args);
}
+/**
+ * rtas_call_unlocked() - Invoke an RTAS firmware function without synchronization.
+ * @args: RTAS parameter block to be used for the call, must obey RTAS addressing
+ * constraints.
+ * @token: Identifies the function being invoked.
+ * @nargs: Number of input parameters. Does not include token.
+ * @nret: Number of output parameters, including the call status.
+ * @....: List of @nargs input parameters.
+ *
+ * Invokes the RTAS function indicated by @token, which the caller
+ * should obtain via rtas_function_token().
+ *
+ * This function is similar to rtas_call(), but must be used with a
+ * limited set of RTAS calls specifically exempted from the general
+ * requirement that only one RTAS call may be in progress at any
+ * time. Examples include stop-self and ibm,nmi-interlock.
+ */
void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...)
{
va_list list;
@@ -464,43 +1087,120 @@ void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret,
va_end(list);
}
+static bool token_is_restricted_errinjct(s32 token)
+{
+ return token == rtas_function_token(RTAS_FN_IBM_OPEN_ERRINJCT) ||
+ token == rtas_function_token(RTAS_FN_IBM_ERRINJCT);
+}
+
+/**
+ * rtas_call() - Invoke an RTAS firmware function.
+ * @token: Identifies the function being invoked.
+ * @nargs: Number of input parameters. Does not include token.
+ * @nret: Number of output parameters, including the call status.
+ * @outputs: Array of @nret output words.
+ * @....: List of @nargs input parameters.
+ *
+ * Invokes the RTAS function indicated by @token, which the caller
+ * should obtain via rtas_function_token().
+ *
+ * The @nargs and @nret arguments must match the number of input and
+ * output parameters specified for the RTAS function.
+ *
+ * rtas_call() returns RTAS status codes, not conventional Linux errno
+ * values. Callers must translate any failure to an appropriate errno
+ * in syscall context. Most callers of RTAS functions that can return
+ * -2 or 990x should use rtas_busy_delay() to correctly handle those
+ * statuses before calling again.
+ *
+ * The return value descriptions are adapted from 7.2.8 [RTAS] Return
+ * Codes of the PAPR and CHRP specifications.
+ *
+ * Context: Process context preferably, interrupt context if
+ * necessary. Acquires an internal spinlock and may perform
+ * GFP_ATOMIC slab allocation in error path. Unsafe for NMI
+ * context.
+ * Return:
+ * * 0 - RTAS function call succeeded.
+ * * -1 - RTAS function encountered a hardware or
+ * platform error, or the token is invalid,
+ * or the function is restricted by kernel policy.
+ * * -2 - Specs say "A necessary hardware device was busy,
+ * and the requested function could not be
+ * performed. The operation should be retried at
+ * a later time." This is misleading, at least with
+ * respect to current RTAS implementations. What it
+ * usually means in practice is that the function
+ * could not be completed while meeting RTAS's
+ * deadline for returning control to the OS (250us
+ * for PAPR/PowerVM, typically), but the call may be
+ * immediately reattempted to resume work on it.
+ * * -3 - Parameter error.
+ * * -7 - Unexpected state change.
+ * * 9000...9899 - Vendor-specific success codes.
+ * * 9900...9905 - Advisory extended delay. Caller should try
+ * again after ~10^x ms has elapsed, where x is
+ * the last digit of the status [0-5]. Again going
+ * beyond the PAPR text, 990x on PowerVM indicates
+ * contention for RTAS-internal resources. Other
+ * RTAS call sequences in progress should be
+ * allowed to complete before reattempting the
+ * call.
+ * * -9000 - Multi-level isolation error.
+ * * -9999...-9004 - Vendor-specific error codes.
+ * * Additional negative values - Function-specific error.
+ * * Additional positive values - Function-specific success.
+ */
int rtas_call(int token, int nargs, int nret, int *outputs, ...)
{
+ struct pin_cookie cookie;
va_list list;
int i;
- unsigned long s;
- struct rtas_args *rtas_args;
+ unsigned long flags;
+ struct rtas_args *args;
char *buff_copy = NULL;
int ret;
if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
return -1;
+ if (token_is_restricted_errinjct(token)) {
+ /*
+ * It would be nicer to not discard the error value
+ * from security_locked_down(), but callers expect an
+ * RTAS status, not an errno.
+ */
+ if (security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION))
+ return -1;
+ }
+
if ((mfmsr() & (MSR_IR|MSR_DR)) != (MSR_IR|MSR_DR)) {
WARN_ON_ONCE(1);
return -1;
}
- s = lock_rtas();
+ raw_spin_lock_irqsave(&rtas_lock, flags);
+ cookie = lockdep_pin_lock(&rtas_lock);
/* We use the global rtas args buffer */
- rtas_args = &rtas.args;
+ args = &rtas_args;
va_start(list, outputs);
- va_rtas_call_unlocked(rtas_args, token, nargs, nret, list);
+ va_rtas_call_unlocked(args, token, nargs, nret, list);
va_end(list);
/* A -1 return code indicates that the last command couldn't
be completed due to a hardware error. */
- if (be32_to_cpu(rtas_args->rets[0]) == -1)
+ if (be32_to_cpu(args->rets[0]) == -1)
buff_copy = __fetch_rtas_last_error(NULL);
if (nret > 1 && outputs != NULL)
for (i = 0; i < nret-1; ++i)
- outputs[i] = be32_to_cpu(rtas_args->rets[i+1]);
- ret = (nret > 0)? be32_to_cpu(rtas_args->rets[0]): 0;
+ outputs[i] = be32_to_cpu(args->rets[i + 1]);
+ ret = (nret > 0) ? be32_to_cpu(args->rets[0]) : 0;
- unlock_rtas(s);
+ lockdep_unpin_lock(&rtas_lock, cookie);
+ raw_spin_unlock_irqrestore(&rtas_lock, flags);
if (buff_copy) {
log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
@@ -509,7 +1209,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
}
return ret;
}
-EXPORT_SYMBOL(rtas_call);
+EXPORT_SYMBOL_GPL(rtas_call);
/**
* rtas_busy_delay_time() - From an RTAS status value, calculate the
@@ -547,7 +1247,47 @@ unsigned int rtas_busy_delay_time(int status)
return ms;
}
-EXPORT_SYMBOL(rtas_busy_delay_time);
+
+/*
+ * Early boot fallback for rtas_busy_delay().
+ */
+static bool __init rtas_busy_delay_early(int status)
+{
+ static size_t successive_ext_delays __initdata;
+ bool retry;
+
+ switch (status) {
+ case RTAS_EXTENDED_DELAY_MIN...RTAS_EXTENDED_DELAY_MAX:
+ /*
+ * In the unlikely case that we receive an extended
+ * delay status in early boot, the OS is probably not
+ * the cause, and there's nothing we can do to clear
+ * the condition. Best we can do is delay for a bit
+ * and hope it's transient. Lie to the caller if it
+ * seems like we're stuck in a retry loop.
+ */
+ mdelay(1);
+ retry = true;
+ successive_ext_delays += 1;
+ if (successive_ext_delays > 1000) {
+ pr_err("too many extended delays, giving up\n");
+ dump_stack();
+ retry = false;
+ successive_ext_delays = 0;
+ }
+ break;
+ case RTAS_BUSY:
+ retry = true;
+ successive_ext_delays = 0;
+ break;
+ default:
+ retry = false;
+ successive_ext_delays = 0;
+ break;
+ }
+
+ return retry;
+}
/**
* rtas_busy_delay() - helper for RTAS busy and extended delay statuses
@@ -567,11 +1307,17 @@ EXPORT_SYMBOL(rtas_busy_delay_time);
* * false - @status is not @RTAS_BUSY nor an extended delay hint. The
* caller is responsible for handling @status.
*/
-bool rtas_busy_delay(int status)
+bool __ref rtas_busy_delay(int status)
{
unsigned int ms;
bool ret;
+ /*
+ * Can't do timed sleeps before timekeeping is up.
+ */
+ if (system_state < SYSTEM_SCHEDULING)
+ return rtas_busy_delay_early(status);
+
switch (status) {
case RTAS_EXTENDED_DELAY_MIN...RTAS_EXTENDED_DELAY_MAX:
ret = true;
@@ -584,21 +1330,14 @@ bool rtas_busy_delay(int status)
*/
ms = clamp(ms, 1U, 1000U);
/*
- * The delay hint is an order-of-magnitude suggestion, not
- * a minimum. It is fine, possibly even advantageous, for
- * us to pause for less time than hinted. For small values,
- * use usleep_range() to ensure we don't sleep much longer
- * than actually needed.
- *
- * See Documentation/timers/timers-howto.rst for
- * explanation of the threshold used here. In effect we use
- * usleep_range() for 9900 and 9901, msleep() for
- * 9902-9905.
+ * The delay hint is an order-of-magnitude suggestion, not a
+ * minimum. It is fine, possibly even advantageous, for us to
+ * pause for less time than hinted. To make sure pause time will
+ * not be way longer than requested independent of HZ
+ * configuration, use fsleep(). See fsleep() for details of
+ * used sleeping functions.
*/
- if (ms <= 20)
- usleep_range(ms * 100, ms * 1000);
- else
- msleep(ms);
+ fsleep(ms * 1000);
break;
case RTAS_BUSY:
ret = true;
@@ -621,40 +1360,40 @@ bool rtas_busy_delay(int status)
return ret;
}
-EXPORT_SYMBOL(rtas_busy_delay);
+EXPORT_SYMBOL_GPL(rtas_busy_delay);
-static int rtas_error_rc(int rtas_rc)
+int rtas_error_rc(int rtas_rc)
{
int rc;
switch (rtas_rc) {
- case -1: /* Hardware Error */
- rc = -EIO;
- break;
- case -3: /* Bad indicator/domain/etc */
- rc = -EINVAL;
- break;
- case -9000: /* Isolation error */
- rc = -EFAULT;
- break;
- case -9001: /* Outstanding TCE/PTE */
- rc = -EEXIST;
- break;
- case -9002: /* No usable slot */
- rc = -ENODEV;
- break;
- default:
- printk(KERN_ERR "%s: unexpected RTAS error %d\n",
- __func__, rtas_rc);
- rc = -ERANGE;
- break;
+ case RTAS_HARDWARE_ERROR: /* Hardware Error */
+ rc = -EIO;
+ break;
+ case RTAS_INVALID_PARAMETER: /* Bad indicator/domain/etc */
+ rc = -EINVAL;
+ break;
+ case -9000: /* Isolation error */
+ rc = -EFAULT;
+ break;
+ case -9001: /* Outstanding TCE/PTE */
+ rc = -EEXIST;
+ break;
+ case -9002: /* No usable slot */
+ rc = -ENODEV;
+ break;
+ default:
+ pr_err("%s: unexpected error %d\n", __func__, rtas_rc);
+ rc = -ERANGE;
+ break;
}
return rc;
}
+EXPORT_SYMBOL_GPL(rtas_error_rc);
int rtas_get_power_level(int powerdomain, int *level)
{
- int token = rtas_token("get-power-level");
+ int token = rtas_function_token(RTAS_FN_GET_POWER_LEVEL);
int rc;
if (token == RTAS_UNKNOWN_SERVICE)
@@ -667,11 +1406,11 @@ int rtas_get_power_level(int powerdomain, int *level)
return rtas_error_rc(rc);
return rc;
}
-EXPORT_SYMBOL(rtas_get_power_level);
+EXPORT_SYMBOL_GPL(rtas_get_power_level);
int rtas_set_power_level(int powerdomain, int level, int *setlevel)
{
- int token = rtas_token("set-power-level");
+ int token = rtas_function_token(RTAS_FN_SET_POWER_LEVEL);
int rc;
if (token == RTAS_UNKNOWN_SERVICE)
@@ -685,11 +1424,11 @@ int rtas_set_power_level(int powerdomain, int level, int *setlevel)
return rtas_error_rc(rc);
return rc;
}
-EXPORT_SYMBOL(rtas_set_power_level);
+EXPORT_SYMBOL_GPL(rtas_set_power_level);
int rtas_get_sensor(int sensor, int index, int *state)
{
- int token = rtas_token("get-sensor-state");
+ int token = rtas_function_token(RTAS_FN_GET_SENSOR_STATE);
int rc;
if (token == RTAS_UNKNOWN_SERVICE)
@@ -703,11 +1442,11 @@ int rtas_get_sensor(int sensor, int index, int *state)
return rtas_error_rc(rc);
return rc;
}
-EXPORT_SYMBOL(rtas_get_sensor);
+EXPORT_SYMBOL_GPL(rtas_get_sensor);
int rtas_get_sensor_fast(int sensor, int index, int *state)
{
- int token = rtas_token("get-sensor-state");
+ int token = rtas_function_token(RTAS_FN_GET_SENSOR_STATE);
int rc;
if (token == RTAS_UNKNOWN_SERVICE)
@@ -746,11 +1485,10 @@ bool rtas_indicator_present(int token, int *maxindex)
return false;
}
-EXPORT_SYMBOL(rtas_indicator_present);
int rtas_set_indicator(int indicator, int index, int new_value)
{
- int token = rtas_token("set-indicator");
+ int token = rtas_function_token(RTAS_FN_SET_INDICATOR);
int rc;
if (token == RTAS_UNKNOWN_SERVICE)
@@ -764,15 +1502,15 @@ int rtas_set_indicator(int indicator, int index, int new_value)
return rtas_error_rc(rc);
return rc;
}
-EXPORT_SYMBOL(rtas_set_indicator);
+EXPORT_SYMBOL_GPL(rtas_set_indicator);
/*
* Ignoring RTAS extended delay
*/
int rtas_set_indicator_fast(int indicator, int index, int new_value)
{
+ int token = rtas_function_token(RTAS_FN_SET_INDICATOR);
int rc;
- int token = rtas_token("set-indicator");
if (token == RTAS_UNKNOWN_SERVICE)
return -ENOENT;
@@ -814,10 +1552,11 @@ int rtas_set_indicator_fast(int indicator, int index, int new_value)
*/
int rtas_ibm_suspend_me(int *fw_status)
{
+ int token = rtas_function_token(RTAS_FN_IBM_SUSPEND_ME);
int fwrc;
int ret;
- fwrc = rtas_call(rtas_token("ibm,suspend-me"), 0, 1, NULL);
+ fwrc = rtas_call(token, 0, 1, NULL);
switch (fwrc) {
case 0:
@@ -849,8 +1588,8 @@ void __noreturn rtas_restart(char *cmd)
{
if (rtas_flash_term_hook)
rtas_flash_term_hook(SYS_RESTART);
- printk("RTAS system-reboot returned %d\n",
- rtas_call(rtas_token("system-reboot"), 0, 1, NULL));
+ pr_emerg("system-reboot returned %d\n",
+ rtas_call(rtas_function_token(RTAS_FN_SYSTEM_REBOOT), 0, 1, NULL));
for (;;);
}
@@ -859,8 +1598,8 @@ void rtas_power_off(void)
if (rtas_flash_term_hook)
rtas_flash_term_hook(SYS_POWER_OFF);
/* allow power on only with power button press */
- printk("RTAS power-off returned %d\n",
- rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1));
+ pr_emerg("power-off returned %d\n",
+ rtas_call(rtas_function_token(RTAS_FN_POWER_OFF), 2, 1, NULL, -1, -1));
for (;;);
}
@@ -869,16 +1608,19 @@ void __noreturn rtas_halt(void)
if (rtas_flash_term_hook)
rtas_flash_term_hook(SYS_HALT);
/* allow power on only with power button press */
- printk("RTAS power-off returned %d\n",
- rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1));
+ pr_emerg("power-off returned %d\n",
+ rtas_call(rtas_function_token(RTAS_FN_POWER_OFF), 2, 1, NULL, -1, -1));
for (;;);
}
/* Must be in the RMO region, so we place it here */
static char rtas_os_term_buf[2048];
+static bool ibm_extended_os_term;
void rtas_os_term(char *str)
{
+ s32 token = rtas_function_token(RTAS_FN_IBM_OS_TERM);
+ static struct rtas_args args;
int status;
/*
@@ -887,19 +1629,24 @@ void rtas_os_term(char *str)
* this property may terminate the partition which we want to avoid
* since it interferes with panic_timeout.
*/
- if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term") ||
- RTAS_UNKNOWN_SERVICE == rtas_token("ibm,extended-os-term"))
+
+ if (token == RTAS_UNKNOWN_SERVICE || !ibm_extended_os_term)
return;
snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
+ /*
+ * Keep calling as long as RTAS returns a "try again" status,
+ * but don't use rtas_busy_delay(), which potentially
+ * schedules.
+ */
do {
- status = rtas_call(rtas_token("ibm,os-term"), 1, 1, NULL,
- __pa(rtas_os_term_buf));
- } while (rtas_busy_delay(status));
+ rtas_call_unlocked(&args, token, 1, 1, NULL, __pa(rtas_os_term_buf));
+ status = be32_to_cpu(args.rets[0]);
+ } while (rtas_busy_delay_time(status));
if (status != 0)
- printk(KERN_EMERG "ibm,os-term call failed %d\n", status);
+ pr_emerg("ibm,os-term call failed %d\n", status);
}
/**
@@ -915,76 +1662,26 @@ void rtas_os_term(char *str)
*/
void rtas_activate_firmware(void)
{
- int token;
+ int token = rtas_function_token(RTAS_FN_IBM_ACTIVATE_FIRMWARE);
int fwrc;
- token = rtas_token("ibm,activate-firmware");
if (token == RTAS_UNKNOWN_SERVICE) {
pr_notice("ibm,activate-firmware method unavailable\n");
return;
}
+ mutex_lock(&rtas_ibm_activate_firmware_lock);
+
do {
fwrc = rtas_call(token, 0, 1, NULL);
} while (rtas_busy_delay(fwrc));
+ mutex_unlock(&rtas_ibm_activate_firmware_lock);
+
if (fwrc)
pr_err("ibm,activate-firmware failed (%i)\n", fwrc);
}
-#ifdef CONFIG_PPC_PSERIES
-/**
- * rtas_call_reentrant() - Used for reentrant rtas calls
- * @token: Token for desired reentrant RTAS call
- * @nargs: Number of Input Parameters
- * @nret: Number of Output Parameters
- * @outputs: Array of outputs
- * @...: Inputs for desired RTAS call
- *
- * According to LoPAR documentation, only "ibm,int-on", "ibm,int-off",
- * "ibm,get-xive" and "ibm,set-xive" are currently reentrant.
- * Reentrant calls need their own rtas_args buffer, so not using rtas.args, but
- * PACA one instead.
- *
- * Return: -1 on error,
- * First output value of RTAS call if (nret > 0),
- * 0 otherwise,
- */
-int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...)
-{
- va_list list;
- struct rtas_args *args;
- unsigned long flags;
- int i, ret = 0;
-
- if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
- return -1;
-
- local_irq_save(flags);
- preempt_disable();
-
- /* We use the per-cpu (PACA) rtas args buffer */
- args = local_paca->rtas_args_reentrant;
-
- va_start(list, outputs);
- va_rtas_call_unlocked(args, token, nargs, nret, list);
- va_end(list);
-
- if (nret > 1 && outputs)
- for (i = 0; i < nret - 1; ++i)
- outputs[i] = be32_to_cpu(args->rets[i + 1]);
-
- if (nret > 0)
- ret = be32_to_cpu(args->rets[0]);
-
- local_irq_restore(flags);
- preempt_enable();
-
- return ret;
-}
-
-#endif /* CONFIG_PPC_PSERIES */
-
/**
* get_pseries_errorlog() - Find a specific pseries error log in an RTAS
* extended event log.
@@ -1023,8 +1720,6 @@ noinstr struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log
return NULL;
}
-#ifdef CONFIG_PPC_RTAS_FILTER
-
/*
* The sys_rtas syscall, as originally designed, allows root to pass
* arbitrary physical addresses to RTAS calls. A number of RTAS calls
@@ -1038,56 +1733,12 @@ noinstr struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log
*
* Accordingly, we filter RTAS requests to check that the call is
* permitted, and that provided pointers fall within the RMO buffer.
- * The rtas_filters list contains an entry for each permitted call,
- * with the indexes of the parameters which are expected to contain
- * addresses and sizes of buffers allocated inside the RMO buffer.
+ * If a function is allowed to be invoked via the syscall, then its
+ * entry in the rtas_functions table points to a rtas_filter that
+ * describes its constraints, with the indexes of the parameters which
+ * are expected to contain addresses and sizes of buffers allocated
+ * inside the RMO buffer.
*/
-struct rtas_filter {
- const char *name;
- int token;
- /* Indexes into the args buffer, -1 if not used */
- int buf_idx1;
- int size_idx1;
- int buf_idx2;
- int size_idx2;
-
- int fixed_size;
-};
-
-static struct rtas_filter rtas_filters[] __ro_after_init = {
- { "ibm,activate-firmware", -1, -1, -1, -1, -1 },
- { "ibm,configure-connector", -1, 0, -1, 1, -1, 4096 }, /* Special cased */
- { "display-character", -1, -1, -1, -1, -1 },
- { "ibm,display-message", -1, 0, -1, -1, -1 },
- { "ibm,errinjct", -1, 2, -1, -1, -1, 1024 },
- { "ibm,close-errinjct", -1, -1, -1, -1, -1 },
- { "ibm,open-errinjct", -1, -1, -1, -1, -1 },
- { "ibm,get-config-addr-info2", -1, -1, -1, -1, -1 },
- { "ibm,get-dynamic-sensor-state", -1, 1, -1, -1, -1 },
- { "ibm,get-indices", -1, 2, 3, -1, -1 },
- { "get-power-level", -1, -1, -1, -1, -1 },
- { "get-sensor-state", -1, -1, -1, -1, -1 },
- { "ibm,get-system-parameter", -1, 1, 2, -1, -1 },
- { "get-time-of-day", -1, -1, -1, -1, -1 },
- { "ibm,get-vpd", -1, 0, -1, 1, 2 },
- { "ibm,lpar-perftools", -1, 2, 3, -1, -1 },
- { "ibm,platform-dump", -1, 4, 5, -1, -1 }, /* Special cased */
- { "ibm,read-slot-reset-state", -1, -1, -1, -1, -1 },
- { "ibm,scan-log-dump", -1, 0, 1, -1, -1 },
- { "ibm,set-dynamic-indicator", -1, 2, -1, -1, -1 },
- { "ibm,set-eeh-option", -1, -1, -1, -1, -1 },
- { "set-indicator", -1, -1, -1, -1, -1 },
- { "set-power-level", -1, -1, -1, -1, -1 },
- { "set-time-for-power-on", -1, -1, -1, -1, -1 },
- { "ibm,set-system-parameter", -1, 1, -1, -1, -1 },
- { "set-time-of-day", -1, -1, -1, -1, -1 },
-#ifdef CONFIG_CPU_BIG_ENDIAN
- { "ibm,suspend-me", -1, -1, -1, -1, -1 },
- { "ibm,update-nodes", -1, 0, -1, -1, -1, 4096 },
- { "ibm,update-properties", -1, 0, -1, -1, -1, 4096 },
-#endif
- { "ibm,physical-attestation", -1, 0, 1, -1, -1 },
-};
static bool in_rmo_buf(u32 base, u32 end)
{
@@ -1098,98 +1749,84 @@ static bool in_rmo_buf(u32 base, u32 end)
end < (rtas_rmo_buf + RTAS_USER_REGION_SIZE);
}
-static bool block_rtas_call(int token, int nargs,
+static bool block_rtas_call(const struct rtas_function *func, int nargs,
struct rtas_args *args)
{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) {
- struct rtas_filter *f = &rtas_filters[i];
- u32 base, size, end;
-
- if (token != f->token)
- continue;
+ const struct rtas_filter *f;
+ const bool is_platform_dump =
+ func == &rtas_function_table[RTAS_FNIDX__IBM_PLATFORM_DUMP];
+ const bool is_config_conn =
+ func == &rtas_function_table[RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR];
+ u32 base, size, end;
- if (f->buf_idx1 != -1) {
- base = be32_to_cpu(args->args[f->buf_idx1]);
- if (f->size_idx1 != -1)
- size = be32_to_cpu(args->args[f->size_idx1]);
- else if (f->fixed_size)
- size = f->fixed_size;
- else
- size = 1;
-
- end = base + size - 1;
+ /*
+ * Only functions with filters attached are allowed.
+ */
+ f = func->filter;
+ if (!f)
+ goto err;
+ /*
+ * And some functions aren't allowed on LE.
+ */
+ if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) && func->banned_for_syscall_on_le)
+ goto err;
+
+ if (f->buf_idx1 != -1) {
+ base = be32_to_cpu(args->args[f->buf_idx1]);
+ if (f->size_idx1 != -1)
+ size = be32_to_cpu(args->args[f->size_idx1]);
+ else if (f->fixed_size)
+ size = f->fixed_size;
+ else
+ size = 1;
- /*
- * Special case for ibm,platform-dump - NULL buffer
- * address is used to indicate end of dump processing
- */
- if (!strcmp(f->name, "ibm,platform-dump") &&
- base == 0)
- return false;
+ end = base + size - 1;
- if (!in_rmo_buf(base, end))
- goto err;
- }
+ /*
+ * Special case for ibm,platform-dump - NULL buffer
+ * address is used to indicate end of dump processing
+ */
+ if (is_platform_dump && base == 0)
+ return false;
- if (f->buf_idx2 != -1) {
- base = be32_to_cpu(args->args[f->buf_idx2]);
- if (f->size_idx2 != -1)
- size = be32_to_cpu(args->args[f->size_idx2]);
- else if (f->fixed_size)
- size = f->fixed_size;
- else
- size = 1;
- end = base + size - 1;
+ if (!in_rmo_buf(base, end))
+ goto err;
+ }
- /*
- * Special case for ibm,configure-connector where the
- * address can be 0
- */
- if (!strcmp(f->name, "ibm,configure-connector") &&
- base == 0)
- return false;
+ if (f->buf_idx2 != -1) {
+ base = be32_to_cpu(args->args[f->buf_idx2]);
+ if (f->size_idx2 != -1)
+ size = be32_to_cpu(args->args[f->size_idx2]);
+ else if (f->fixed_size)
+ size = f->fixed_size;
+ else
+ size = 1;
+ end = base + size - 1;
- if (!in_rmo_buf(base, end))
- goto err;
- }
+ /*
+ * Special case for ibm,configure-connector where the
+ * address can be 0
+ */
+ if (is_config_conn && base == 0)
+ return false;
- return false;
+ if (!in_rmo_buf(base, end))
+ goto err;
}
+ return false;
err:
pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n");
- pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n",
- token, nargs, current->comm);
+ pr_err_ratelimited("sys_rtas: %s nargs=%d (called by %s)\n",
+ func->name, nargs, current->comm);
return true;
}
-static void __init rtas_syscall_filter_init(void)
-{
- unsigned int i;
-
- for (i = 0; i < ARRAY_SIZE(rtas_filters); i++)
- rtas_filters[i].token = rtas_token(rtas_filters[i].name);
-}
-
-#else
-
-static bool block_rtas_call(int token, int nargs,
- struct rtas_args *args)
-{
- return false;
-}
-
-static void __init rtas_syscall_filter_init(void)
-{
-}
-
-#endif /* CONFIG_PPC_RTAS_FILTER */
-
/* We assume to be passed big endian arguments */
SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
{
+ const struct rtas_function *func;
+ struct pin_cookie cookie;
struct rtas_args args;
unsigned long flags;
char *buff_copy, *errbuf = NULL;
@@ -1213,22 +1850,38 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
|| nargs + nret > ARRAY_SIZE(args.args))
return -EINVAL;
+ nargs = array_index_nospec(nargs, ARRAY_SIZE(args.args));
+ nret = array_index_nospec(nret, ARRAY_SIZE(args.args) - nargs);
+
/* Copy in args. */
if (copy_from_user(args.args, uargs->args,
nargs * sizeof(rtas_arg_t)) != 0)
return -EFAULT;
- if (token == RTAS_UNKNOWN_SERVICE)
+ /*
+ * If this token doesn't correspond to a function the kernel
+ * understands, you're not allowed to call it.
+ */
+ func = rtas_token_to_function_untrusted(token);
+ if (!func)
return -EINVAL;
args.rets = &args.args[nargs];
memset(args.rets, 0, nret * sizeof(rtas_arg_t));
- if (block_rtas_call(token, nargs, &args))
+ if (block_rtas_call(func, nargs, &args))
return -EINVAL;
+ if (token_is_restricted_errinjct(token)) {
+ int err;
+
+ err = security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION);
+ if (err)
+ return err;
+ }
+
/* Need to handle ibm,suspend_me call specially */
- if (token == rtas_token("ibm,suspend-me")) {
+ if (token == rtas_function_token(RTAS_FN_IBM_SUSPEND_ME)) {
/*
* rtas_ibm_suspend_me assumes the streamid handle is in cpu
@@ -1249,18 +1902,32 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
buff_copy = get_errorlog_buffer();
- flags = lock_rtas();
+ /*
+ * If this function has a mutex assigned to it, we must
+ * acquire it to avoid interleaving with any kernel-based uses
+ * of the same function. Kernel-based sequences acquire the
+ * appropriate mutex explicitly.
+ */
+ if (func->lock)
+ mutex_lock(func->lock);
+
+ raw_spin_lock_irqsave(&rtas_lock, flags);
+ cookie = lockdep_pin_lock(&rtas_lock);
- rtas.args = args;
- do_enter_rtas(__pa(&rtas.args));
- args = rtas.args;
+ rtas_args = args;
+ do_enter_rtas(&rtas_args);
+ args = rtas_args;
/* A -1 return code indicates that the last command couldn't
be completed due to a hardware error. */
if (be32_to_cpu(args.rets[0]) == -1)
errbuf = __fetch_rtas_last_error(buff_copy);
- unlock_rtas(flags);
+ lockdep_unpin_lock(&rtas_lock, cookie);
+ raw_spin_unlock_irqrestore(&rtas_lock, flags);
+
+ if (func->lock)
+ mutex_unlock(func->lock);
if (buff_copy) {
if (errbuf)
@@ -1278,6 +1945,54 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
return 0;
}
+static void __init rtas_function_table_init(void)
+{
+ struct property *prop;
+
+ for (size_t i = 0; i < ARRAY_SIZE(rtas_function_table); ++i) {
+ struct rtas_function *curr = &rtas_function_table[i];
+ struct rtas_function *prior;
+ int cmp;
+
+ curr->token = RTAS_UNKNOWN_SERVICE;
+
+ if (i == 0)
+ continue;
+ /*
+ * Ensure table is sorted correctly for binary search
+ * on function names.
+ */
+ prior = &rtas_function_table[i - 1];
+
+ cmp = strcmp(prior->name, curr->name);
+ if (cmp < 0)
+ continue;
+
+ if (cmp == 0) {
+ pr_err("'%s' has duplicate function table entries\n",
+ curr->name);
+ } else {
+ pr_err("function table unsorted: '%s' wrongly precedes '%s'\n",
+ prior->name, curr->name);
+ }
+ }
+
+ for_each_property_of_node(rtas.dev, prop) {
+ struct rtas_function *func;
+
+ if (prop->length != sizeof(u32))
+ continue;
+
+ func = __rtas_name_to_function(prop->name);
+ if (!func)
+ continue;
+
+ func->token = be32_to_cpup((__be32 *)prop->value);
+
+ pr_debug("function %s has token %u\n", func->name, func->token);
+ }
+}
+
/*
* Call early during boot, before mem init, to retrieve the RTAS
* information from the device-tree and allocate the RMO buffer for userland
@@ -1309,6 +2024,17 @@ void __init rtas_initialize(void)
no_entry = of_property_read_u32(rtas.dev, "linux,rtas-entry", &entry);
rtas.entry = no_entry ? rtas.base : entry;
+ init_error_log_max();
+
+ /* Must be called before any function token lookups */
+ rtas_function_table_init();
+
+ /*
+ * Discover this now to avoid a device tree lookup in the
+ * panic path.
+ */
+ ibm_extended_os_term = of_property_read_bool(rtas.dev, "ibm,extended-os-term");
+
/* If RTAS was found, allocate the RMO buffer for it and look for
* the stop-self token if any
*/
@@ -1322,11 +2048,7 @@ void __init rtas_initialize(void)
panic("ERROR: RTAS: Failed to allocate %lx bytes below %pa\n",
PAGE_SIZE, &rtas_region);
-#ifdef CONFIG_RTAS_ERROR_LOGGING
- rtas_last_error_token = rtas_token("rtas-last-error");
-#endif
-
- rtas_syscall_filter_init();
+ rtas_work_area_reserve_arena(rtas_region);
}
int __init early_init_dt_scan_rtas(unsigned long node,
@@ -1353,42 +2075,26 @@ int __init early_init_dt_scan_rtas(unsigned long node,
rtas.size = *sizep;
}
-#ifdef CONFIG_UDBG_RTAS_CONSOLE
- basep = of_get_flat_dt_prop(node, "put-term-char", NULL);
- if (basep)
- rtas_putchar_token = *basep;
-
- basep = of_get_flat_dt_prop(node, "get-term-char", NULL);
- if (basep)
- rtas_getchar_token = *basep;
-
- if (rtas_putchar_token != RTAS_UNKNOWN_SERVICE &&
- rtas_getchar_token != RTAS_UNKNOWN_SERVICE)
- udbg_init_rtas_console();
-
-#endif
-
/* break now */
return 1;
}
-static arch_spinlock_t timebase_lock;
+static DEFINE_RAW_SPINLOCK(timebase_lock);
static u64 timebase = 0;
void rtas_give_timebase(void)
{
unsigned long flags;
- local_irq_save(flags);
+ raw_spin_lock_irqsave(&timebase_lock, flags);
hard_irq_disable();
- arch_spin_lock(&timebase_lock);
- rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
+ rtas_call(rtas_function_token(RTAS_FN_FREEZE_TIME_BASE), 0, 1, NULL);
timebase = get_tb();
- arch_spin_unlock(&timebase_lock);
+ raw_spin_unlock(&timebase_lock);
while (timebase)
barrier();
- rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
+ rtas_call(rtas_function_token(RTAS_FN_THAW_TIME_BASE), 0, 1, NULL);
local_irq_restore(flags);
}
@@ -1396,8 +2102,8 @@ void rtas_take_timebase(void)
{
while (!timebase)
barrier();
- arch_spin_lock(&timebase_lock);
+ raw_spin_lock(&timebase_lock);
set_tb(timebase >> 32, timebase & 0xffffffff);
timebase = 0;
- arch_spin_unlock(&timebase_lock);
+ raw_spin_unlock(&timebase_lock);
}
diff --git a/arch/powerpc/kernel/rtas_entry.S b/arch/powerpc/kernel/rtas_entry.S
index 9a434d42e660..6ce95ddadbcd 100644
--- a/arch/powerpc/kernel/rtas_entry.S
+++ b/arch/powerpc/kernel/rtas_entry.S
@@ -109,8 +109,12 @@ __enter_rtas:
* its critical regions (as specified in PAPR+ section 7.2.1). MSR[S]
* is not impacted by RFI_TO_KERNEL (only urfid can unset it). So if
* MSR[S] is set, it will remain when entering RTAS.
+ * If we're in HV mode, RTAS must also run in HV mode, so extract MSR_HV
+ * from the saved MSR value and insert into the value RTAS will use.
*/
+ extrdi r0, r6, 1, 63 - MSR_HV_LG
LOAD_REG_IMMEDIATE(r6, MSR_ME | MSR_RI)
+ insrdi r6, r0, 1, 63 - MSR_HV_LG
li r0,0
mtmsrd r0,1 /* disable RI before using SRR0/1 */
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index bc817a5619d6..583dc16e9d3c 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -312,13 +312,13 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
{
struct rtas_update_flash_t *const uf = &rtas_update_flash_data;
char *p;
- int next_free, rc;
+ int next_free;
struct flash_block_list *fl;
- mutex_lock(&rtas_update_flash_mutex);
+ guard(mutex)(&rtas_update_flash_mutex);
if (uf->status == FLASH_AUTH || count == 0)
- goto out; /* discard data */
+ return count; /* discard data */
/* In the case that the image is not ready for flashing, the memory
* allocated for the block list will be freed upon the release of the
@@ -327,7 +327,7 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
if (uf->flist == NULL) {
uf->flist = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
if (!uf->flist)
- goto nomem;
+ return -ENOMEM;
}
fl = uf->flist;
@@ -338,7 +338,7 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
/* Need to allocate another block_list */
fl->next = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
if (!fl->next)
- goto nomem;
+ return -ENOMEM;
fl = fl->next;
next_free = 0;
}
@@ -347,25 +347,17 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
count = RTAS_BLK_SIZE;
p = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
if (!p)
- goto nomem;
+ return -ENOMEM;
if(copy_from_user(p, buffer, count)) {
kmem_cache_free(flash_block_cache, p);
- rc = -EFAULT;
- goto error;
+ return -EFAULT;
}
fl->blocks[next_free].data = p;
fl->blocks[next_free].length = count;
fl->num_blocks++;
-out:
- mutex_unlock(&rtas_update_flash_mutex);
- return count;
-nomem:
- rc = -ENOMEM;
-error:
- mutex_unlock(&rtas_update_flash_mutex);
- return rc;
+ return count;
}
/*
@@ -376,7 +368,7 @@ static void manage_flash(struct rtas_manage_flash_t *args_buf, unsigned int op)
s32 rc;
do {
- rc = rtas_call(rtas_token("ibm,manage-flash-image"), 1, 1,
+ rc = rtas_call(rtas_function_token(RTAS_FN_IBM_MANAGE_FLASH_IMAGE), 1, 1,
NULL, op);
} while (rtas_busy_delay(rc));
@@ -405,19 +397,18 @@ static ssize_t manage_flash_write(struct file *file, const char __user *buf,
static const char reject_str[] = "0";
static const char commit_str[] = "1";
char stkbuf[10];
- int op, rc;
+ int op;
- mutex_lock(&rtas_manage_flash_mutex);
+ guard(mutex)(&rtas_manage_flash_mutex);
if ((args_buf->status == MANAGE_AUTH) || (count == 0))
- goto out;
+ return count;
op = -1;
if (buf) {
if (count > 9) count = 9;
- rc = -EFAULT;
if (copy_from_user (stkbuf, buf, count))
- goto error;
+ return -EFAULT;
if (strncmp(stkbuf, reject_str, strlen(reject_str)) == 0)
op = RTAS_REJECT_TMP_IMG;
else if (strncmp(stkbuf, commit_str, strlen(commit_str)) == 0)
@@ -425,18 +416,11 @@ static ssize_t manage_flash_write(struct file *file, const char __user *buf,
}
if (op == -1) { /* buf is empty, or contains invalid string */
- rc = -EINVAL;
- goto error;
+ return -EINVAL;
}
manage_flash(args_buf, op);
-out:
- mutex_unlock(&rtas_manage_flash_mutex);
return count;
-
-error:
- mutex_unlock(&rtas_manage_flash_mutex);
- return rc;
}
/*
@@ -444,7 +428,7 @@ error:
*/
static void validate_flash(struct rtas_validate_flash_t *args_buf)
{
- int token = rtas_token("ibm,validate-flash-image");
+ int token = rtas_function_token(RTAS_FN_IBM_VALIDATE_FLASH_IMAGE);
int update_results;
s32 rc;
@@ -499,16 +483,14 @@ static ssize_t validate_flash_write(struct file *file, const char __user *buf,
{
struct rtas_validate_flash_t *const args_buf =
&rtas_validate_flash_data;
- int rc;
- mutex_lock(&rtas_validate_flash_mutex);
+ guard(mutex)(&rtas_validate_flash_mutex);
/* We are only interested in the first 4K of the
* candidate image */
if ((*off >= VALIDATE_BUF_SIZE) ||
(args_buf->status == VALIDATE_AUTH)) {
*off += count;
- mutex_unlock(&rtas_validate_flash_mutex);
return count;
}
@@ -519,20 +501,14 @@ static ssize_t validate_flash_write(struct file *file, const char __user *buf,
args_buf->status = VALIDATE_INCOMPLETE;
}
- if (!access_ok(buf, count)) {
- rc = -EFAULT;
- goto done;
- }
- if (copy_from_user(args_buf->buf + *off, buf, count)) {
- rc = -EFAULT;
- goto done;
- }
+ if (!access_ok(buf, count))
+ return -EFAULT;
+
+ if (copy_from_user(args_buf->buf + *off, buf, count))
+ return -EFAULT;
*off += count;
- rc = count;
-done:
- mutex_unlock(&rtas_validate_flash_mutex);
- return rc;
+ return count;
}
static int validate_flash_release(struct inode *inode, struct file *file)
@@ -570,7 +546,7 @@ static void rtas_flash_firmware(int reboot_type)
return;
}
- update_token = rtas_token("ibm,update-flash-64-and-reboot");
+ update_token = rtas_function_token(RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT);
if (update_token == RTAS_UNKNOWN_SERVICE) {
printk(KERN_ALERT "FLASH: ibm,update-flash-64-and-reboot "
"is not available -- not a service partition?\n");
@@ -653,7 +629,7 @@ static void rtas_flash_firmware(int reboot_type)
*/
struct rtas_flash_file {
const char *filename;
- const char *rtas_call_name;
+ const rtas_fn_handle_t handle;
int *status;
const struct proc_ops ops;
};
@@ -661,7 +637,7 @@ struct rtas_flash_file {
static const struct rtas_flash_file rtas_flash_files[] = {
{
.filename = "powerpc/rtas/" FIRMWARE_FLASH_NAME,
- .rtas_call_name = "ibm,update-flash-64-and-reboot",
+ .handle = RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT,
.status = &rtas_update_flash_data.status,
.ops.proc_read = rtas_flash_read_msg,
.ops.proc_write = rtas_flash_write,
@@ -670,7 +646,7 @@ static const struct rtas_flash_file rtas_flash_files[] = {
},
{
.filename = "powerpc/rtas/" FIRMWARE_UPDATE_NAME,
- .rtas_call_name = "ibm,update-flash-64-and-reboot",
+ .handle = RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT,
.status = &rtas_update_flash_data.status,
.ops.proc_read = rtas_flash_read_num,
.ops.proc_write = rtas_flash_write,
@@ -679,7 +655,7 @@ static const struct rtas_flash_file rtas_flash_files[] = {
},
{
.filename = "powerpc/rtas/" VALIDATE_FLASH_NAME,
- .rtas_call_name = "ibm,validate-flash-image",
+ .handle = RTAS_FN_IBM_VALIDATE_FLASH_IMAGE,
.status = &rtas_validate_flash_data.status,
.ops.proc_read = validate_flash_read,
.ops.proc_write = validate_flash_write,
@@ -688,7 +664,7 @@ static const struct rtas_flash_file rtas_flash_files[] = {
},
{
.filename = "powerpc/rtas/" MANAGE_FLASH_NAME,
- .rtas_call_name = "ibm,manage-flash-image",
+ .handle = RTAS_FN_IBM_MANAGE_FLASH_IMAGE,
.status = &rtas_manage_flash_data.status,
.ops.proc_read = manage_flash_read,
.ops.proc_write = manage_flash_write,
@@ -700,8 +676,7 @@ static int __init rtas_flash_init(void)
{
int i;
- if (rtas_token("ibm,update-flash-64-and-reboot") ==
- RTAS_UNKNOWN_SERVICE) {
+ if (rtas_function_token(RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT) == RTAS_UNKNOWN_SERVICE) {
pr_info("rtas_flash: no firmware flash support\n");
return -EINVAL;
}
@@ -710,9 +685,9 @@ static int __init rtas_flash_init(void)
if (!rtas_validate_flash_data.buf)
return -ENOMEM;
- flash_block_cache = kmem_cache_create("rtas_flash_cache",
- RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0,
- NULL);
+ flash_block_cache = kmem_cache_create_usercopy("rtas_flash_cache",
+ RTAS_BLK_SIZE, RTAS_BLK_SIZE,
+ 0, 0, RTAS_BLK_SIZE, NULL);
if (!flash_block_cache) {
printk(KERN_ERR "%s: failed to create block cache\n",
__func__);
@@ -730,7 +705,7 @@ static int __init rtas_flash_init(void)
* This code assumes that the status int is the first member of the
* struct
*/
- token = rtas_token(f->rtas_call_name);
+ token = rtas_function_token(f->handle);
if (token == RTAS_UNKNOWN_SERVICE)
*f->status = FLASH_AUTH;
else
@@ -774,4 +749,5 @@ static void __exit rtas_flash_cleanup(void)
module_init(rtas_flash_init);
module_exit(rtas_flash_cleanup);
+MODULE_DESCRIPTION("PPC procfs firmware flash interface");
MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 5a2f5ea3b054..fccf96e897f6 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -43,7 +43,7 @@ static inline int config_access_valid(struct pci_dn *dn, int where)
return 0;
}
-int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
{
int returnval = -1;
unsigned long buid, addr;
@@ -87,7 +87,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
pdn = pci_get_pdn_by_devfn(bus, devfn);
/* Validity of pdn is checked in here */
- ret = rtas_read_config(pdn, where, size, val);
+ ret = rtas_pci_dn_read_config(pdn, where, size, val);
if (*val == EEH_IO_ERROR_VALUE(size) &&
eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
return PCIBIOS_DEVICE_NOT_FOUND;
@@ -95,7 +95,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
return ret;
}
-int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
+int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val)
{
unsigned long buid, addr;
int ret;
@@ -134,7 +134,7 @@ static int rtas_pci_write_config(struct pci_bus *bus,
pdn = pci_get_pdn_by_devfn(bus, devfn);
/* Validity of pdn is checked in here. */
- return rtas_write_config(pdn, where, size, val);
+ return rtas_pci_dn_write_config(pdn, where, size, val);
}
static struct pci_ops rtas_pci_ops = {
@@ -191,10 +191,10 @@ static void python_countermeasures(struct device_node *dev)
void __init init_pci_config_tokens(void)
{
- read_pci_config = rtas_token("read-pci-config");
- write_pci_config = rtas_token("write-pci-config");
- ibm_read_pci_config = rtas_token("ibm,read-pci-config");
- ibm_write_pci_config = rtas_token("ibm,write-pci-config");
+ read_pci_config = rtas_function_token(RTAS_FN_READ_PCI_CONFIG);
+ write_pci_config = rtas_function_token(RTAS_FN_WRITE_PCI_CONFIG);
+ ibm_read_pci_config = rtas_function_token(RTAS_FN_IBM_READ_PCI_CONFIG);
+ ibm_write_pci_config = rtas_function_token(RTAS_FN_IBM_WRITE_PCI_CONFIG);
}
unsigned long get_phb_buid(struct device_node *phb)
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 5270b450bbde..9bba469239fc 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -9,6 +9,7 @@
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
+#include <linux/of.h>
#include <linux/poll.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
@@ -499,18 +500,20 @@ EXPORT_SYMBOL_GPL(rtas_cancel_event_scan);
static int __init rtas_event_scan_init(void)
{
+ int err;
+
if (!machine_is(pseries) && !machine_is(chrp))
return 0;
/* No RTAS */
- event_scan = rtas_token("event-scan");
+ event_scan = rtas_function_token(RTAS_FN_EVENT_SCAN);
if (event_scan == RTAS_UNKNOWN_SERVICE) {
printk(KERN_INFO "rtasd: No event-scan on system\n");
return -ENODEV;
}
- rtas_event_scan_rate = rtas_token("rtas-event-scan-rate");
- if (rtas_event_scan_rate == RTAS_UNKNOWN_SERVICE) {
+ err = of_property_read_u32(rtas.dev, "rtas-event-scan-rate", &rtas_event_scan_rate);
+ if (err) {
printk(KERN_ERR "rtasd: no rtas-event-scan-rate on system\n");
return -ENODEV;
}
diff --git a/arch/powerpc/kernel/secure_boot.c b/arch/powerpc/kernel/secure_boot.c
index f9af305d9579..3a28795b4ed8 100644
--- a/arch/powerpc/kernel/secure_boot.c
+++ b/arch/powerpc/kernel/secure_boot.c
@@ -5,6 +5,7 @@
*/
#include <linux/types.h>
#include <linux/of.h>
+#include <linux/string_choices.h>
#include <asm/secure_boot.h>
static struct device_node *get_ppc_fw_sb_node(void)
@@ -32,11 +33,13 @@ bool is_ppc_secureboot_enabled(void)
if (enabled)
goto out;
- if (!of_property_read_u32(of_root, "ibm,secure-boot", &secureboot))
+ node = of_find_node_by_path("/");
+ if (!of_property_read_u32(node, "ibm,secure-boot", &secureboot))
enabled = (secureboot > 1);
+ of_node_put(node);
out:
- pr_info("Secure boot mode %s\n", enabled ? "enabled" : "disabled");
+ pr_info("Secure boot mode %s\n", str_enabled_disabled(enabled));
return enabled;
}
@@ -54,11 +57,13 @@ bool is_ppc_trustedboot_enabled(void)
if (enabled)
goto out;
- if (!of_property_read_u32(of_root, "ibm,trusted-boot", &trustedboot))
+ node = of_find_node_by_path("/");
+ if (!of_property_read_u32(node, "ibm,trusted-boot", &trustedboot))
enabled = (trustedboot > 0);
+ of_node_put(node);
out:
- pr_info("Trusted boot mode %s\n", enabled ? "enabled" : "disabled");
+ pr_info("Trusted boot mode %s\n", str_enabled_disabled(enabled));
return enabled;
}
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index d96fd14bd7c9..fbb7ebd8aa08 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -14,8 +14,9 @@
#include <linux/debugfs.h>
#include <asm/asm-prototypes.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/security_features.h>
+#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/inst.h>
@@ -34,7 +35,7 @@ static enum branch_cache_flush_type link_stack_flush_type = BRANCH_CACHE_FLUSH_N
bool barrier_nospec_enabled;
static bool no_nospec;
static bool btb_flush_enabled;
-#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64)
+#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64)
static bool no_spectrev2;
#endif
@@ -121,7 +122,7 @@ static __init int security_feature_debugfs_init(void)
device_initcall(security_feature_debugfs_init);
#endif /* CONFIG_DEBUG_FS */
-#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64)
+#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64)
static int __init handle_nospectre_v2(char *p)
{
no_spectrev2 = true;
@@ -129,9 +130,9 @@ static int __init handle_nospectre_v2(char *p)
return 0;
}
early_param("nospectre_v2", handle_nospectre_v2);
-#endif /* CONFIG_PPC_FSL_BOOK3E || CONFIG_PPC_BOOK3S_64 */
+#endif /* CONFIG_PPC_E500 || CONFIG_PPC_BOOK3S_64 */
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
void __init setup_spectre_v2(void)
{
if (no_spectrev2 || cpu_mitigations_off())
@@ -139,7 +140,7 @@ void __init setup_spectre_v2(void)
else
btb_flush_enabled = true;
}
-#endif /* CONFIG_PPC_FSL_BOOK3E */
+#endif /* CONFIG_PPC_E500 */
#ifdef CONFIG_PPC_BOOK3S_64
ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
@@ -363,26 +364,27 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *
static int ssb_prctl_get(struct task_struct *task)
{
+ /*
+ * The STF_BARRIER feature is on by default, so if it's off that means
+ * firmware has explicitly said the CPU is not vulnerable via either
+ * the hypercall or device tree.
+ */
+ if (!security_ftr_enabled(SEC_FTR_STF_BARRIER))
+ return PR_SPEC_NOT_AFFECTED;
+
+ /*
+ * If the system's CPU has no known barrier (see setup_stf_barrier())
+ * then assume that the CPU is not vulnerable.
+ */
if (stf_enabled_flush_types == STF_BARRIER_NONE)
- /*
- * We don't have an explicit signal from firmware that we're
- * vulnerable or not, we only have certain CPU revisions that
- * are known to be vulnerable.
- *
- * We assume that if we're on another CPU, where the barrier is
- * NONE, then we are not vulnerable.
- */
return PR_SPEC_NOT_AFFECTED;
- else
- /*
- * If we do have a barrier type then we are vulnerable. The
- * barrier is not a global or per-process mitigation, so the
- * only value we can report here is PR_SPEC_ENABLE, which
- * appears as "vulnerable" in /proc.
- */
- return PR_SPEC_ENABLE;
-
- return -EINVAL;
+
+ /*
+ * Otherwise the CPU is vulnerable. The barrier is not a global or
+ * per-process mitigation, so the only value that can be reported here
+ * is PR_SPEC_ENABLE, which appears as "vulnerable" in /proc.
+ */
+ return PR_SPEC_ENABLE;
}
int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
diff --git a/arch/powerpc/kernel/secvar-ops.c b/arch/powerpc/kernel/secvar-ops.c
index 6a29777d6a2d..19172a2804f0 100644
--- a/arch/powerpc/kernel/secvar-ops.c
+++ b/arch/powerpc/kernel/secvar-ops.c
@@ -8,10 +8,16 @@
#include <linux/cache.h>
#include <asm/secvar.h>
+#include <asm/bug.h>
-const struct secvar_operations *secvar_ops __ro_after_init;
+const struct secvar_operations *secvar_ops __ro_after_init = NULL;
-void set_secvar_ops(const struct secvar_operations *ops)
+int set_secvar_ops(const struct secvar_operations *ops)
{
+ if (WARN_ON_ONCE(secvar_ops))
+ return -EBUSY;
+
secvar_ops = ops;
+
+ return 0;
}
diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c
index 1ee4640a2641..ec900bce0257 100644
--- a/arch/powerpc/kernel/secvar-sysfs.c
+++ b/arch/powerpc/kernel/secvar-sysfs.c
@@ -21,56 +21,48 @@ static struct kset *secvar_kset;
static ssize_t format_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
- ssize_t rc = 0;
- struct device_node *node;
- const char *format;
-
- node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend");
- if (!of_device_is_available(node)) {
- rc = -ENODEV;
- goto out;
- }
-
- rc = of_property_read_string(node, "format", &format);
- if (rc)
- goto out;
-
- rc = sprintf(buf, "%s\n", format);
+ char tmp[32];
+ ssize_t len = secvar_ops->format(tmp, sizeof(tmp));
-out:
- of_node_put(node);
+ if (len > 0)
+ return sysfs_emit(buf, "%s\n", tmp);
+ else if (len < 0)
+ pr_err("Error %zd reading format string\n", len);
+ else
+ pr_err("Got empty format string from backend\n");
- return rc;
+ return -EIO;
}
static ssize_t size_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
- uint64_t dsize;
+ u64 dsize;
int rc;
rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, NULL, &dsize);
if (rc) {
- pr_err("Error retrieving %s variable size %d\n", kobj->name,
- rc);
+ if (rc != -ENOENT)
+ pr_err("Error retrieving %s variable size %d\n", kobj->name, rc);
return rc;
}
- return sprintf(buf, "%llu\n", dsize);
+ return sysfs_emit(buf, "%llu\n", dsize);
}
static ssize_t data_read(struct file *filep, struct kobject *kobj,
- struct bin_attribute *attr, char *buf, loff_t off,
+ const struct bin_attribute *attr, char *buf, loff_t off,
size_t count)
{
- uint64_t dsize;
char *data;
+ u64 dsize;
int rc;
rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, NULL, &dsize);
if (rc) {
- pr_err("Error getting %s variable size %d\n", kobj->name, rc);
+ if (rc != -ENOENT)
+ pr_err("Error getting %s variable size %d\n", kobj->name, rc);
return rc;
}
pr_debug("dsize is %llu\n", dsize);
@@ -93,7 +85,7 @@ data_fail:
}
static ssize_t update_write(struct file *filep, struct kobject *kobj,
- struct bin_attribute *attr, char *buf, loff_t off,
+ const struct bin_attribute *attr, char *buf, loff_t off,
size_t count)
{
int rc;
@@ -112,11 +104,11 @@ static struct kobj_attribute format_attr = __ATTR_RO(format);
static struct kobj_attribute size_attr = __ATTR_RO(size);
-static struct bin_attribute data_attr = __BIN_ATTR_RO(data, 0);
+static struct bin_attribute data_attr __ro_after_init = __BIN_ATTR_RO(data, 0);
-static struct bin_attribute update_attr = __BIN_ATTR_WO(update, 0);
+static struct bin_attribute update_attr __ro_after_init = __BIN_ATTR_WO(update, 0);
-static struct bin_attribute *secvar_bin_attrs[] = {
+static const struct bin_attribute *const secvar_bin_attrs[] = {
&data_attr,
&update_attr,
NULL,
@@ -133,44 +125,68 @@ static const struct attribute_group secvar_attr_group = {
};
__ATTRIBUTE_GROUPS(secvar_attr);
-static struct kobj_type secvar_ktype = {
+static const struct kobj_type secvar_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.default_groups = secvar_attr_groups,
};
-static int update_kobj_size(void)
+static __init int update_kobj_size(void)
{
- struct device_node *node;
u64 varsize;
- int rc = 0;
-
- node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend");
- if (!of_device_is_available(node)) {
- rc = -ENODEV;
- goto out;
- }
+ int rc = secvar_ops->max_size(&varsize);
- rc = of_property_read_u64(node, "max-var-size", &varsize);
if (rc)
- goto out;
+ return rc;
data_attr.size = varsize;
update_attr.size = varsize;
-out:
- of_node_put(node);
+ return 0;
+}
- return rc;
+static __init int secvar_sysfs_config(struct kobject *kobj)
+{
+ struct attribute_group config_group = {
+ .name = "config",
+ .attrs = (struct attribute **)secvar_ops->config_attrs,
+ };
+
+ if (secvar_ops->config_attrs)
+ return sysfs_create_group(kobj, &config_group);
+
+ return 0;
}
-static int secvar_sysfs_load(void)
+static __init int add_var(const char *name)
{
- char *name;
- uint64_t namesize = 0;
struct kobject *kobj;
int rc;
+ kobj = kzalloc(sizeof(*kobj), GFP_KERNEL);
+ if (!kobj)
+ return -ENOMEM;
+
+ kobject_init(kobj, &secvar_ktype);
+
+ rc = kobject_add(kobj, &secvar_kset->kobj, "%s", name);
+ if (rc) {
+ pr_warn("kobject_add error %d for attribute: %s\n", rc,
+ name);
+ kobject_put(kobj);
+ return rc;
+ }
+
+ kobject_uevent(kobj, KOBJ_ADD);
+ return 0;
+}
+
+static __init int secvar_sysfs_load(void)
+{
+ u64 namesize = 0;
+ char *name;
+ int rc;
+
name = kzalloc(NAME_MAX_SIZE, GFP_KERNEL);
if (!name)
return -ENOMEM;
@@ -179,73 +195,99 @@ static int secvar_sysfs_load(void)
rc = secvar_ops->get_next(name, &namesize, NAME_MAX_SIZE);
if (rc) {
if (rc != -ENOENT)
- pr_err("error getting secvar from firmware %d\n",
- rc);
- break;
- }
+ pr_err("error getting secvar from firmware %d\n", rc);
+ else
+ rc = 0;
- kobj = kzalloc(sizeof(*kobj), GFP_KERNEL);
- if (!kobj) {
- rc = -ENOMEM;
break;
}
- kobject_init(kobj, &secvar_ktype);
-
- rc = kobject_add(kobj, &secvar_kset->kobj, "%s", name);
- if (rc) {
- pr_warn("kobject_add error %d for attribute: %s\n", rc,
- name);
- kobject_put(kobj);
- kobj = NULL;
- }
-
- if (kobj)
- kobject_uevent(kobj, KOBJ_ADD);
-
+ rc = add_var(name);
} while (!rc);
kfree(name);
return rc;
}
-static int secvar_sysfs_init(void)
+static __init int secvar_sysfs_load_static(void)
+{
+ const char * const *name_ptr = secvar_ops->var_names;
+ int rc;
+
+ while (*name_ptr) {
+ rc = add_var(*name_ptr);
+ if (rc)
+ return rc;
+ name_ptr++;
+ }
+
+ return 0;
+}
+
+static __init int secvar_sysfs_init(void)
{
+ u64 max_size;
int rc;
if (!secvar_ops) {
- pr_warn("secvar: failed to retrieve secvar operations.\n");
+ pr_warn("Failed to retrieve secvar operations\n");
return -ENODEV;
}
secvar_kobj = kobject_create_and_add("secvar", firmware_kobj);
if (!secvar_kobj) {
- pr_err("secvar: Failed to create firmware kobj\n");
+ pr_err("Failed to create firmware kobj\n");
return -ENOMEM;
}
rc = sysfs_create_file(secvar_kobj, &format_attr.attr);
if (rc) {
- kobject_put(secvar_kobj);
- return -ENOMEM;
+ pr_err("Failed to create format object\n");
+ rc = -ENOMEM;
+ goto err;
}
secvar_kset = kset_create_and_add("vars", NULL, secvar_kobj);
if (!secvar_kset) {
- pr_err("secvar: sysfs kobject registration failed.\n");
- kobject_put(secvar_kobj);
- return -ENOMEM;
+ pr_err("sysfs kobject registration failed\n");
+ rc = -ENOMEM;
+ goto err;
}
rc = update_kobj_size();
if (rc) {
pr_err("Cannot read the size of the attribute\n");
- return rc;
+ goto err;
+ }
+
+ rc = secvar_sysfs_config(secvar_kobj);
+ if (rc) {
+ pr_err("Failed to create config directory\n");
+ goto err;
}
- secvar_sysfs_load();
+ if (secvar_ops->get_next)
+ rc = secvar_sysfs_load();
+ else
+ rc = secvar_sysfs_load_static();
+
+ if (rc) {
+ pr_err("Failed to create variable attributes\n");
+ goto err;
+ }
+
+ // Due to sysfs limitations, we will only ever get a write buffer of
+ // up to 1 page in size. Print a warning if this is potentially going
+ // to cause problems, so that the user is aware.
+ secvar_ops->max_size(&max_size);
+ if (max_size > PAGE_SIZE)
+ pr_warn_ratelimited("PAGE_SIZE (%lu) is smaller than maximum object size (%llu), writes are limited to PAGE_SIZE\n",
+ PAGE_SIZE, max_size);
return 0;
+err:
+ kobject_put(secvar_kobj);
+ return rc;
}
late_initcall(secvar_sysfs_init);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 1a02629ec70b..68d47c53876c 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -18,20 +18,21 @@
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/platform_device.h>
+#include <linux/printk.h>
#include <linux/seq_file.h>
#include <linux/ioport.h>
#include <linux/console.h>
-#include <linux/screen_info.h>
#include <linux/root_dev.h>
#include <linux/cpu.h>
#include <linux/unistd.h>
+#include <linux/seq_buf.h>
#include <linux/serial.h>
#include <linux/serial_8250.h>
#include <linux/percpu.h>
#include <linux/memblock.h>
-#include <linux/of_irq.h>
+#include <linux/of.h>
#include <linux/of_fdt.h>
-#include <linux/of_platform.h>
+#include <linux/of_irq.h>
#include <linux/hugetlb.h>
#include <linux/pgtable.h>
#include <asm/io.h>
@@ -57,6 +58,7 @@
#include <asm/xmon.h>
#include <asm/cputhreads.h>
#include <mm/mmu_decl.h>
+#include <asm/archrandom.h>
#include <asm/fadump.h>
#include <asm/udbg.h>
#include <asm/hugetlb.h>
@@ -65,6 +67,7 @@
#include <asm/cpu_has_feature.h>
#include <asm/kasan.h>
#include <asm/mce.h>
+#include <asm/systemcfg.h>
#include "setup.h"
@@ -83,6 +86,11 @@ EXPORT_SYMBOL(machine_id);
int boot_cpuid = -1;
EXPORT_SYMBOL_GPL(boot_cpuid);
+int __initdata boot_core_hwid = -1;
+
+#ifdef CONFIG_PPC64
+int boot_cpu_hwid = -1;
+#endif
/*
* These are used in binfmt_elf.c to put aux entries on the stack
@@ -91,21 +99,6 @@ EXPORT_SYMBOL_GPL(boot_cpuid);
int dcache_bsize;
int icache_bsize;
-/*
- * This still seems to be needed... -- paulus
- */
-struct screen_info screen_info = {
- .orig_x = 0,
- .orig_y = 25,
- .orig_video_cols = 80,
- .orig_video_lines = 25,
- .orig_video_isVGA = 1,
- .orig_video_points = 16
-};
-#if defined(CONFIG_FB_VGA16_MODULE)
-EXPORT_SYMBOL(screen_info);
-#endif
-
/* Variables required to store legacy IO irq routing */
int of_i8042_kbd_irq;
EXPORT_SYMBOL_GPL(of_i8042_kbd_irq);
@@ -118,7 +111,7 @@ int ppc_do_canonicalize_irqs;
EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
#endif
-#ifdef CONFIG_CRASH_CORE
+#ifdef CONFIG_CRASH_DUMP
/* This keeps a track of which one is the crashing cpu. */
int crashing_cpu = -1;
#endif
@@ -171,6 +164,14 @@ EXPORT_SYMBOL_GPL(machine_power_off);
void (*pm_power_off)(void);
EXPORT_SYMBOL_GPL(pm_power_off);
+size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
+{
+ if (max_longs && ppc_md.get_random_seed && ppc_md.get_random_seed(v))
+ return 1;
+ return 0;
+}
+EXPORT_SYMBOL(arch_get_random_seed_longs);
+
void machine_halt(void)
{
machine_shutdown();
@@ -405,13 +406,32 @@ static void __init cpu_init_thread_core_maps(int tpc)
cpumask_set_cpu(i, &threads_core_mask);
printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n",
- tpc, tpc > 1 ? "s" : "");
+ tpc, str_plural(tpc));
printk(KERN_DEBUG " (thread shift is %d)\n", threads_shift);
}
u32 *cpu_to_phys_id = NULL;
+static int assign_threads(unsigned int cpu, unsigned int nthreads, bool present,
+ const __be32 *hw_ids)
+{
+ for (int i = 0; i < nthreads && cpu < nr_cpu_ids; i++) {
+ __be32 hwid;
+
+ hwid = be32_to_cpu(hw_ids[i]);
+
+ DBG(" thread %d -> cpu %d (hard id %d)\n", i, cpu, hwid);
+
+ set_cpu_present(cpu, present);
+ set_cpu_possible(cpu, true);
+ cpu_to_phys_id[cpu] = hwid;
+ cpu++;
+ }
+
+ return cpu;
+}
+
/**
* setup_cpu_maps - initialize the following cpu maps:
* cpu_possible_mask
@@ -438,16 +458,13 @@ void __init smp_setup_cpu_maps(void)
DBG("smp_setup_cpu_maps()\n");
- cpu_to_phys_id = memblock_alloc(nr_cpu_ids * sizeof(u32),
+ cpu_to_phys_id = memblock_alloc_or_panic(nr_cpu_ids * sizeof(u32),
__alignof__(u32));
- if (!cpu_to_phys_id)
- panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
- __func__, nr_cpu_ids * sizeof(u32), __alignof__(u32));
for_each_node_by_type(dn, "cpu") {
const __be32 *intserv;
__be32 cpu_be;
- int j, len;
+ int len;
DBG(" * %pOF...\n", dn);
@@ -469,27 +486,31 @@ void __init smp_setup_cpu_maps(void)
nthreads = len / sizeof(int);
- for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
- bool avail;
-
- DBG(" thread %d -> cpu %d (hard id %d)\n",
- j, cpu, be32_to_cpu(intserv[j]));
+ bool avail = of_device_is_available(dn);
+ if (!avail)
+ avail = !of_property_match_string(dn,
+ "enable-method", "spin-table");
- avail = of_device_is_available(dn);
- if (!avail)
- avail = !of_property_match_string(dn,
- "enable-method", "spin-table");
-
- set_cpu_present(cpu, avail);
- set_cpu_possible(cpu, true);
- cpu_to_phys_id[cpu] = be32_to_cpu(intserv[j]);
- cpu++;
- }
+ if (boot_core_hwid >= 0) {
+ if (cpu == 0) {
+ pr_info("Skipping CPU node %pOF to allow for boot core.\n", dn);
+ cpu = nthreads;
+ continue;
+ }
- if (cpu >= nr_cpu_ids) {
+ if (be32_to_cpu(intserv[0]) == boot_core_hwid) {
+ pr_info("Renumbered boot core %pOF to logical 0\n", dn);
+ assign_threads(0, nthreads, avail, intserv);
+ of_node_put(dn);
+ break;
+ }
+ } else if (cpu >= nr_cpu_ids) {
of_node_put(dn);
break;
}
+
+ if (cpu < nr_cpu_ids)
+ cpu = assign_threads(cpu, nthreads, avail, intserv);
}
/* If no SMT supported, nthreads is forced to 1 */
@@ -537,7 +558,9 @@ void __init smp_setup_cpu_maps(void)
out:
of_node_put(dn);
}
- vdso_data->processorCount = num_present_cpus();
+#endif
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+ systemcfg->processorCount = num_present_cpus();
#endif /* CONFIG_PPC64 */
/* Initialize CPU <=> thread mapping/
@@ -580,6 +603,14 @@ static __init int add_pcspkr(void)
device_initcall(add_pcspkr);
#endif /* CONFIG_PCSPKR_PLATFORM */
+static char ppc_hw_desc_buf[128] __initdata;
+
+struct seq_buf ppc_hw_desc __initdata = {
+ .buffer = ppc_hw_desc_buf,
+ .size = sizeof(ppc_hw_desc_buf),
+ .len = 0,
+};
+
static __init void probe_machine(void)
{
extern struct machdep_calls __machine_desc_start;
@@ -606,13 +637,16 @@ static __init void probe_machine(void)
for (machine_id = &__machine_desc_start;
machine_id < &__machine_desc_end;
machine_id++) {
- DBG(" %s ...", machine_id->name);
+ DBG(" %s ...\n", machine_id->name);
+ if (machine_id->compatible && !of_machine_is_compatible(machine_id->compatible))
+ continue;
+ if (machine_id->compatibles && !of_machine_compatible_match(machine_id->compatibles))
+ continue;
memcpy(&ppc_md, machine_id, sizeof(struct machdep_calls));
- if (ppc_md.probe()) {
- DBG(" match !\n");
- break;
- }
- DBG("\n");
+ if (ppc_md.probe && !ppc_md.probe())
+ continue;
+ DBG(" %s match !\n", machine_id->name);
+ break;
}
/* What can we do if we didn't find ? */
if (machine_id >= &__machine_desc_end) {
@@ -620,7 +654,13 @@ static __init void probe_machine(void)
for (;;);
}
- printk(KERN_INFO "Using %s machine description\n", ppc_md.name);
+ // Append the machine name to other info we've gathered
+ seq_buf_puts(&ppc_hw_desc, ppc_md.name);
+
+ // Set the generic hardware description shown in oopses
+ dump_stack_set_arch_desc(ppc_hw_desc.buffer);
+
+ pr_info("Hardware name: %s\n", ppc_hw_desc.buffer);
}
/* Match a class of boards, not a specific device configuration. */
@@ -791,8 +831,8 @@ static int __init check_cache_coherency(void)
if (devtree_coherency != KERNEL_COHERENCY) {
printk(KERN_ERR
"kernel coherency:%s != device tree_coherency:%s\n",
- KERNEL_COHERENCY ? "on" : "off",
- devtree_coherency ? "on" : "off");
+ str_on_off(KERNEL_COHERENCY),
+ str_on_off(devtree_coherency));
BUG();
}
@@ -917,6 +957,7 @@ void __init setup_arch(char **cmdline_p)
/* Parse memory topology */
mem_topology_setup();
+ high_memory = (void *)__va(max_low_pfn * PAGE_SIZE);
/*
* Release secondary cpus out of their spinloops at 0x60 now that
@@ -938,8 +979,12 @@ void __init setup_arch(char **cmdline_p)
klp_init_thread_info(&init_task);
setup_initial_init_mm(_stext, _etext, _edata, _end);
-
+ /* sched_init() does the mmgrab(&init_mm) for the primary CPU */
+ VM_WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(&init_mm)));
+ cpumask_set_cpu(smp_processor_id(), mm_cpumask(&init_mm));
+ inc_mm_active_cpus(&init_mm);
mm_iommu_init(&init_mm);
+
irqstack_early_init();
exc_lvl_early_init();
emergency_stack_init();
@@ -950,9 +995,11 @@ void __init setup_arch(char **cmdline_p)
initmem_init();
/*
- * Reserve large chunks of memory for use by CMA for KVM and hugetlb. These must
- * be called after initmem_init(), so that pageblock_order is initialised.
+ * Reserve large chunks of memory for use by CMA for fadump, KVM and
+ * hugetlb. These must be called after initmem_init(), so that
+ * pageblock_order is initialised.
*/
+ fadump_cma_init();
kvm_cma_reserve();
gigantic_hugetlb_cma_reserve();
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index 93f22da12abe..385a00a2e2ca 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -23,13 +23,13 @@ void check_smt_enabled(void);
static inline void check_smt_enabled(void) { }
#endif
-#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP)
+#if defined(CONFIG_PPC_BOOK3E_64) && defined(CONFIG_SMP)
void setup_tlb_core_data(void);
#else
static inline void setup_tlb_core_data(void) { }
#endif
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
void exc_lvl_early_init(void);
#else
static inline void exc_lvl_early_init(void) { }
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 813261789303..5a1bf501fbe1 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -40,7 +40,7 @@
#include <asm/time.h>
#include <asm/serial.h>
#include <asm/udbg.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/cpu_has_feature.h>
#include <asm/asm-prototypes.h>
#include <asm/kdump.h>
@@ -140,13 +140,7 @@ arch_initcall(ppc_init);
static void *__init alloc_stack(void)
{
- void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN);
-
- if (!ptr)
- panic("cannot allocate %d bytes for stack at %pS\n",
- THREAD_SIZE, (void *)_RET_IP_);
-
- return ptr;
+ return memblock_alloc_or_panic(THREAD_SIZE, THREAD_ALIGN);
}
void __init irqstack_early_init(void)
@@ -176,7 +170,7 @@ void __init emergency_stack_init(void)
}
#endif
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
void __init exc_lvl_early_init(void)
{
unsigned int i, hw_cpu;
@@ -207,7 +201,7 @@ void __init setup_power_save(void)
ppc_md.power_save = ppc6xx_idle;
#endif
-#ifdef CONFIG_E500
+#ifdef CONFIG_PPC_E500
if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
cpu_has_feature(CPU_FTR_CAN_NAP))
ppc_md.power_save = e500_idle;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 5761f08dae95..8fd7cbf3bd04 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -34,6 +34,7 @@
#include <linux/of.h>
#include <linux/of_fdt.h>
+#include <asm/asm-prototypes.h>
#include <asm/kvm_guest.h>
#include <asm/io.h>
#include <asm/kdump.h>
@@ -59,7 +60,7 @@
#include <asm/xmon.h>
#include <asm/udbg.h>
#include <asm/kexec.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/ftrace.h>
#include <asm/opal.h>
#include <asm/cputhreads.h>
@@ -86,7 +87,7 @@ struct ppc64_caches ppc64_caches = {
};
EXPORT_SYMBOL_GPL(ppc64_caches);
-#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP)
+#if defined(CONFIG_PPC_BOOK3E_64) && defined(CONFIG_SMP)
void __init setup_tlb_core_data(void)
{
int cpu;
@@ -113,7 +114,6 @@ void __init setup_tlb_core_data(void)
* Should we panic instead?
*/
WARN_ONCE(smt_enabled_at_boot >= 2 &&
- !mmu_has_feature(MMU_FTR_USE_TLBRSRV) &&
book3e_htw_mode != PPC_HTW_E6500,
"%s: unsupported MMU configuration\n", __func__);
}
@@ -141,10 +141,7 @@ void __init check_smt_enabled(void)
smt_enabled_at_boot = 0;
else {
int smt;
- int rc;
-
- rc = kstrtoint(smt_enabled_cmdline, 10, &smt);
- if (!rc)
+ if (!kstrtoint(smt_enabled_cmdline, 10, &smt))
smt_enabled_at_boot =
min(threads_per_core, smt);
}
@@ -177,14 +174,26 @@ early_param("smt-enabled", early_smt_enabled);
#endif /* CONFIG_SMP */
/** Fix up paca fields required for the boot cpu */
-static void __init fixup_boot_paca(void)
+static void __init fixup_boot_paca(struct paca_struct *boot_paca)
{
/* The boot cpu is started */
- get_paca()->cpu_start = 1;
+ boot_paca->cpu_start = 1;
+#ifdef CONFIG_PPC_BOOK3S_64
+ /*
+ * Give the early boot machine check stack somewhere to use, use
+ * half of the init stack. This is a bit hacky but there should not be
+ * deep stack usage in early init so shouldn't overflow it or overwrite
+ * things.
+ */
+ boot_paca->mc_emergency_sp = (void *)&init_thread_union +
+ (THREAD_SIZE/2);
+#endif
/* Allow percpu accesses to work until we setup percpu data */
- get_paca()->data_offset = 0;
- /* Mark interrupts disabled in PACA */
- irq_soft_mask_set(IRQS_DISABLED);
+ boot_paca->data_offset = 0;
+ /* Mark interrupts soft and hard disabled in PACA */
+ boot_paca->irq_soft_mask = IRQS_DISABLED;
+ boot_paca->irq_happened = PACA_IRQ_HARD_DIS;
+ WARN_ON(mfmsr() & MSR_EE);
}
static void __init configure_exceptions(void)
@@ -351,11 +360,15 @@ void __init early_setup(unsigned long dt_ptr)
* what CPU we are on.
*/
initialise_paca(&boot_paca, 0);
- setup_paca(&boot_paca);
- fixup_boot_paca();
+ fixup_boot_paca(&boot_paca);
+ WARN_ON(local_paca);
+ setup_paca(&boot_paca); /* install the paca into registers */
/* -------- printk is now safe to use ------- */
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && (mfmsr() & MSR_HV))
+ enable_machine_check();
+
/* Try new device tree based feature discovery ... */
if (!dt_cpu_ftrs_init(__va(dt_ptr)))
/* Otherwise use the old style CPU table */
@@ -369,17 +382,21 @@ void __init early_setup(unsigned long dt_ptr)
/*
* Do early initialization using the flattened device
* tree, such as retrieving the physical memory map or
- * calculating/retrieving the hash table size.
+ * calculating/retrieving the hash table size, discover
+ * boot_cpuid and boot_cpu_hwid.
*/
early_init_devtree(__va(dt_ptr));
- /* Now we know the logical id of our boot cpu, setup the paca. */
- if (boot_cpuid != 0) {
- /* Poison paca_ptrs[0] again if it's not the boot cpu */
- memset(&paca_ptrs[0], 0x88, sizeof(paca_ptrs[0]));
- }
- setup_paca(paca_ptrs[boot_cpuid]);
- fixup_boot_paca();
+ allocate_paca_ptrs();
+ allocate_paca(boot_cpuid);
+ set_hard_smp_processor_id(boot_cpuid, boot_cpu_hwid);
+ fixup_boot_paca(paca_ptrs[boot_cpuid]);
+ setup_paca(paca_ptrs[boot_cpuid]); /* install the paca into registers */
+ // smp_processor_id() now reports boot_cpuid
+
+#ifdef CONFIG_SMP
+ task_thread_info(current)->cpu = boot_cpuid; // fix task_cpu(current)
+#endif
/*
* Configure exception handlers. This include setting up trampolines
@@ -460,7 +477,7 @@ void early_setup_secondary(void)
#endif /* CONFIG_SMP */
-void panic_smp_self_stop(void)
+void __noreturn panic_smp_self_stop(void)
{
hard_irq_disable();
spin_begin();
@@ -674,13 +691,9 @@ void __init initialize_cache_info(void)
*/
__init u64 ppc64_bolted_size(void)
{
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
/* Freescale BookE bolts the entire linear mapping */
- /* XXX: BookE ppc64_rma_limit setup seems to disagree? */
- if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E))
- return linear_map_top;
- /* Other BookE, we assume the first GB is bolted */
- return 1ul << 30;
+ return linear_map_top;
#else
/* BookS radix, does not take faults on linear mapping */
if (early_radix_enabled())
@@ -724,7 +737,7 @@ void __init irqstack_early_init(void)
}
}
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
void __init exc_lvl_early_init(void)
{
unsigned int i;
@@ -814,6 +827,7 @@ static __init int pcpu_cpu_to_node(int cpu)
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
+DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
void __init setup_per_cpu_areas(void)
{
@@ -826,7 +840,7 @@ void __init setup_per_cpu_areas(void)
/*
* BookE and BookS radix are historical values and should be revisited.
*/
- if (IS_ENABLED(CONFIG_PPC_BOOK3E)) {
+ if (IS_ENABLED(CONFIG_PPC_BOOK3E_64)) {
atom_size = SZ_1M;
} else if (radix_enabled()) {
atom_size = PAGE_SIZE;
@@ -856,6 +870,7 @@ void __init setup_per_cpu_areas(void)
if (rc < 0)
panic("cannot initialize percpu area (err=%d)", rc);
+ static_key_enable(&__percpu_first_chunk_is_paged.key);
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
for_each_possible_cpu(cpu) {
__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
@@ -874,7 +889,7 @@ unsigned long memory_block_size_bytes(void)
}
#endif
-#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
+#ifdef CONFIG_PPC_INDIRECT_PIO
struct ppc_pci_io ppc_pci_io;
EXPORT_SYMBOL(ppc_pci_io);
#endif
@@ -902,6 +917,7 @@ static int __init disable_hardlockup_detector(void)
hardlockup_detector_disable();
#else
if (firmware_has_feature(FW_FEATURE_LPAR)) {
+ check_kvm_guest();
if (is_kvm_guest())
hardlockup_detector_disable();
}
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 68a91e553e14..aa17e62f3754 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Common signal handling code for both 32 and 64 bits
*
* Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation
* Extracted from signal_32.c and signal_64.c
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License. See the file README.legal in the main directory of
- * this archive for more details.
*/
#include <linux/resume_user_mode.h>
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index 618aeccdf691..58ecea1cdc27 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -1,10 +1,7 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ *
* Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation
* Extracted from signal_32.c and signal_64.c
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License. See the file README.legal in the main directory of
- * this archive for more details.
*/
#ifndef _POWERPC_ARCH_SIGNAL_H
@@ -196,9 +193,6 @@ extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
#else /* CONFIG_PPC64 */
-extern long sys_rt_sigreturn(void);
-extern long sys_sigreturn(void);
-
static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
struct task_struct *tsk)
{
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 157a7403e3eb..7a718ed32b27 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -43,7 +43,7 @@
#include <asm/tm.h>
#include <asm/asm-prototypes.h>
#ifdef CONFIG_PPC64
-#include "ppc32.h"
+#include <asm/syscalls_32.h>
#include <asm/unistd.h>
#else
#include <asm/ucontext.h>
@@ -264,8 +264,9 @@ static void prepare_save_user_regs(int ctx_has_vsx_region)
#endif
}
-static int __unsafe_save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
- struct mcontext __user *tm_frame, int ctx_has_vsx_region)
+static __always_inline int
+__unsafe_save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
+ struct mcontext __user *tm_frame, int ctx_has_vsx_region)
{
unsigned long msr = regs->msr;
@@ -364,8 +365,9 @@ static void prepare_save_tm_user_regs(void)
current->thread.ckvrsave = mfspr(SPRN_VRSAVE);
}
-static int save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
- struct mcontext __user *tm_frame, unsigned long msr)
+static __always_inline int
+save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
+ struct mcontext __user *tm_frame, unsigned long msr)
{
/* Save both sets of general registers */
unsafe_save_general_regs(&current->thread.ckpt_regs, frame, failed);
@@ -444,8 +446,9 @@ failed:
#else
static void prepare_save_tm_user_regs(void) { }
-static int save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
- struct mcontext __user *tm_frame, unsigned long msr)
+static __always_inline int
+save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
+ struct mcontext __user *tm_frame, unsigned long msr)
{
return 0;
}
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 472596a109e2..86bb5bb4c143 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -377,9 +377,12 @@ static long notrace __unsafe_restore_sigcontext(struct task_struct *tsk, sigset_
unsafe_get_user(set->sig[0], &sc->oldmask, efault_out);
/*
- * Force reload of FP/VEC.
- * This has to be done before copying stuff into tsk->thread.fpr/vr
- * for the reasons explained in the previous comment.
+ * Force reload of FP/VEC/VSX so userspace sees any changes.
+ * Clear these bits from the user process' MSR before copying into the
+ * thread struct. If we are rescheduled or preempted and another task
+ * uses FP/VEC/VSX, and this process has the MSR bits set, then the
+ * context switch code will save the current CPU state into the
+ * thread_struct - possibly overwriting the data we are updating here.
*/
regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX));
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index bcefab484ea6..f59e4b9cc207 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -35,6 +35,7 @@
#include <linux/stackprotector.h>
#include <linux/pgtable.h>
#include <linux/clockchips.h>
+#include <linux/kexec.h>
#include <asm/ptrace.h>
#include <linux/atomic.h>
@@ -46,6 +47,7 @@
#include <asm/smp.h>
#include <asm/time.h>
#include <asm/machdep.h>
+#include <asm/mmu_context.h>
#include <asm/cputhreads.h>
#include <asm/cputable.h>
#include <asm/mpic.h>
@@ -55,11 +57,13 @@
#endif
#include <asm/vdso.h>
#include <asm/debug.h>
-#include <asm/kexec.h>
#include <asm/cpu_has_feature.h>
#include <asm/ftrace.h>
#include <asm/kup.h>
#include <asm/fadump.h>
+#include <asm/systemcfg.h>
+
+#include <trace/events/ipi.h>
#ifdef DEBUG
#include <asm/udbg.h>
@@ -74,10 +78,10 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
#endif
struct task_struct *secondary_current;
-bool has_big_cores;
-bool coregroup_enabled;
-bool thread_group_shares_l2;
-bool thread_group_shares_l3;
+bool has_big_cores __ro_after_init;
+bool coregroup_enabled __ro_after_init;
+bool thread_group_shares_l2 __ro_after_init;
+bool thread_group_shares_l3 __ro_after_init;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
@@ -90,15 +94,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
EXPORT_SYMBOL_GPL(has_big_cores);
-enum {
-#ifdef CONFIG_SCHED_SMT
- smt_idx,
-#endif
- cache_idx,
- mc_idx,
- die_idx,
-};
-
#define MAX_THREAD_LIST_SIZE 8
#define THREAD_GROUP_SHARE_L1 1
#define THREAD_GROUP_SHARE_L2_L3 2
@@ -289,7 +284,7 @@ void smp_muxed_ipi_set_message(int cpu, int msg)
* Order previous accesses before accesses in the IPI handler.
*/
smp_mb();
- message[msg] = 1;
+ WRITE_ONCE(message[msg], 1);
}
void smp_muxed_ipi_message_pass(int cpu, int msg)
@@ -348,7 +343,7 @@ irqreturn_t smp_ipi_demux_relaxed(void)
if (all & IPI_MESSAGE(PPC_MSG_NMI_IPI))
nmi_ipi_action(0, NULL);
#endif
- } while (info->messages);
+ } while (READ_ONCE(info->messages));
return IRQ_HANDLED;
}
@@ -364,12 +359,12 @@ static inline void do_message_pass(int cpu, int msg)
#endif
}
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
{
if (likely(smp_ops))
do_message_pass(cpu, PPC_MSG_RESCHEDULE);
}
-EXPORT_SYMBOL_GPL(smp_send_reschedule);
+EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);
void arch_send_call_function_single_ipi(int cpu)
{
@@ -415,9 +410,9 @@ noinstr static void nmi_ipi_lock_start(unsigned long *flags)
{
raw_local_irq_save(*flags);
hard_irq_disable();
- while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
+ while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
raw_local_irq_restore(*flags);
- spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0);
+ spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0);
raw_local_irq_save(*flags);
hard_irq_disable();
}
@@ -425,15 +420,15 @@ noinstr static void nmi_ipi_lock_start(unsigned long *flags)
noinstr static void nmi_ipi_lock(void)
{
- while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
- spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0);
+ while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
+ spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0);
}
noinstr static void nmi_ipi_unlock(void)
{
smp_mb();
- WARN_ON(arch_atomic_read(&__nmi_ipi_lock) != 1);
- arch_atomic_set(&__nmi_ipi_lock, 0);
+ WARN_ON(raw_atomic_read(&__nmi_ipi_lock) != 1);
+ raw_atomic_set(&__nmi_ipi_lock, 0);
}
noinstr static void nmi_ipi_unlock_end(unsigned long *flags)
@@ -594,7 +589,7 @@ void smp_send_debugger_break(void)
}
#endif
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
{
int cpu;
@@ -619,20 +614,6 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
}
#endif
-#ifdef CONFIG_NMI_IPI
-static void crash_stop_this_cpu(struct pt_regs *regs)
-#else
-static void crash_stop_this_cpu(void *dummy)
-#endif
-{
- /*
- * Just busy wait here and avoid marking CPU as offline to ensure
- * register data is captured appropriately.
- */
- while (1)
- cpu_relax();
-}
-
void crash_smp_send_stop(void)
{
static bool stopped = false;
@@ -651,11 +632,14 @@ void crash_smp_send_stop(void)
stopped = true;
-#ifdef CONFIG_NMI_IPI
- smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_stop_this_cpu, 1000000);
-#else
- smp_call_function(crash_stop_this_cpu, NULL, 0);
-#endif /* CONFIG_NMI_IPI */
+#ifdef CONFIG_CRASH_DUMP
+ if (kexec_crash_image) {
+ crash_kexec_prepare();
+ return;
+ }
+#endif
+
+ smp_send_stop();
}
#ifdef CONFIG_NMI_IPI
@@ -719,7 +703,7 @@ static struct task_struct *current_set[NR_CPUS];
static void smp_store_cpu_info(int id)
{
per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
per_cpu(next_tlbcam_idx, id)
= (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1;
#endif
@@ -995,13 +979,13 @@ static int __init init_thread_group_cache_map(int cpu, int cache_property)
return 0;
}
-static bool shared_caches;
+static bool shared_caches __ro_after_init;
#ifdef CONFIG_SCHED_SMT
/* cpumask of CPUs with asymmetric SMT dependency */
static int powerpc_smt_flags(void)
{
- int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+ int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_LLC;
if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
@@ -1012,6 +996,13 @@ static int powerpc_smt_flags(void)
#endif
/*
+ * On shared processor LPARs scheduled on a big core (which has two or more
+ * independent thread groups per core), prefer lower numbered CPUs, so
+ * that workload consolidates to lesser number of cores.
+ */
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
+
+/*
* P9 has a slightly odd architecture where pairs of cores share an L2 cache.
* This topology makes it *much* cheaper to migrate tasks between adjacent cores
* since the migrated task remains cache hot. We want to take advantage of this
@@ -1019,7 +1010,18 @@ static int powerpc_smt_flags(void)
*/
static int powerpc_shared_cache_flags(void)
{
- return SD_SHARE_PKG_RESOURCES;
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return SD_SHARE_LLC | SD_ASYM_PACKING;
+
+ return SD_SHARE_LLC;
+}
+
+static int powerpc_shared_proc_flags(void)
+{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return SD_ASYM_PACKING;
+
+ return 0;
}
/*
@@ -1045,6 +1047,10 @@ static struct cpumask *cpu_coregroup_mask(int cpu)
static bool has_coregroup_support(void)
{
+ /* Coregroup identification not available on shared systems */
+ if (is_shared_processor())
+ return 0;
+
return coregroup_enabled;
}
@@ -1053,16 +1059,6 @@ static const struct cpumask *cpu_mc_mask(int cpu)
return cpu_coregroup_mask(cpu);
}
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
- { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
- { cpu_mc_mask, SD_INIT_NAME(MC) },
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
- { NULL, },
-};
-
static int __init init_big_cores(void)
{
int cpu;
@@ -1096,7 +1092,7 @@ static int __init init_big_cores(void)
void __init smp_prepare_cpus(unsigned int max_cpus)
{
- unsigned int cpu;
+ unsigned int cpu, num_threads;
DBG("smp_prepare_cpus\n");
@@ -1163,9 +1159,15 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
if (smp_ops && smp_ops->probe)
smp_ops->probe();
+
+ // Initalise the generic SMT topology support
+ num_threads = 1;
+ if (smt_enabled_at_boot)
+ num_threads = smt_enabled_at_boot;
+ cpu_smt_set_num_threads(num_threads, threads_per_core);
}
-void smp_prepare_boot_cpu(void)
+void __init smp_prepare_boot_cpu(void)
{
BUG_ON(smp_processor_id() != boot_cpuid);
#ifdef CONFIG_PPC64
@@ -1185,8 +1187,8 @@ int generic_cpu_disable(void)
return -EBUSY;
set_cpu_online(cpu, false);
-#ifdef CONFIG_PPC64
- vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+ systemcfg->processorCount--;
#endif
/* Update affinity of all IRQs previously aimed at this CPU */
irq_migrate_all_off_this_cpu();
@@ -1260,7 +1262,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
#ifdef CONFIG_PPC64
paca_ptrs[cpu]->__current = idle;
paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
- THREAD_SIZE - STACK_FRAME_OVERHEAD;
+ THREAD_SIZE - STACK_FRAME_MIN_SIZE;
#endif
task_thread_info(idle)->cpu = cpu;
secondary_current = current_set[cpu] = idle;
@@ -1268,7 +1270,12 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
- int rc, c;
+ const unsigned long boot_spin_ms = 5 * MSEC_PER_SEC;
+ const bool booting = system_state < SYSTEM_RUNNING;
+ const unsigned long hp_spin_ms = 1;
+ unsigned long deadline;
+ int rc;
+ const unsigned long spin_wait_ms = booting ? boot_spin_ms : hp_spin_ms;
/*
* Don't allow secondary threads to come online if inhibited
@@ -1313,22 +1320,23 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
}
/*
- * wait to see if the cpu made a callin (is actually up).
- * use this value that I found through experimentation.
- * -- Cort
+ * At boot time, simply spin on the callin word until the
+ * deadline passes.
+ *
+ * At run time, spin for an optimistic amount of time to avoid
+ * sleeping in the common case.
*/
- if (system_state < SYSTEM_RUNNING)
- for (c = 50000; c && !cpu_callin_map[cpu]; c--)
- udelay(100);
-#ifdef CONFIG_HOTPLUG_CPU
- else
- /*
- * CPUs can take much longer to come up in the
- * hotplug case. Wait five seconds.
- */
- for (c = 5000; c && !cpu_callin_map[cpu]; c--)
- msleep(1);
-#endif
+ deadline = jiffies + msecs_to_jiffies(spin_wait_ms);
+ spin_until_cond(cpu_callin_map[cpu] || time_is_before_jiffies(deadline));
+
+ if (!cpu_callin_map[cpu] && system_state >= SYSTEM_RUNNING) {
+ const unsigned long sleep_interval_us = 10 * USEC_PER_MSEC;
+ const unsigned long sleep_wait_ms = 100 * MSEC_PER_SEC;
+
+ deadline = jiffies + msecs_to_jiffies(sleep_wait_ms);
+ while (!cpu_callin_map[cpu] && time_is_after_jiffies(deadline))
+ fsleep(sleep_interval_us);
+ }
if (!cpu_callin_map[cpu]) {
printk(KERN_ERR "Processor %u is stuck.\n", cpu);
@@ -1560,7 +1568,7 @@ static void add_cpu_to_masks(int cpu)
/*
* This CPU will not be in the online mask yet so we need to manually
- * add it to it's own thread sibling mask.
+ * add it to its own thread sibling mask.
*/
map_cpu_to_node(cpu, cpu_to_node(cpu));
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
@@ -1591,7 +1599,7 @@ static void add_cpu_to_masks(int cpu)
/* Skip all CPUs already part of current CPU core mask */
cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
- /* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+ /* If chip_id is -1; limit the cpu_core_mask to within PKG */
if (chip_id == -1)
cpumask_and(mask, mask, cpu_cpu_mask(cpu));
@@ -1608,6 +1616,7 @@ static void add_cpu_to_masks(int cpu)
}
/* Activate a secondary processor. */
+__no_stack_protector
void start_secondary(void *unused)
{
unsigned int cpu = raw_smp_processor_id();
@@ -1616,12 +1625,15 @@ void start_secondary(void *unused)
if (IS_ENABLED(CONFIG_PPC32))
setup_kup();
- mmgrab(&init_mm);
+ mmgrab_lazy_tlb(&init_mm);
current->active_mm = &init_mm;
+ VM_WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(&init_mm)));
+ cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
+ inc_mm_active_cpus(&init_mm);
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
@@ -1631,10 +1643,12 @@ void start_secondary(void *unused)
secondary_cpu_time_init();
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
if (system_state == SYSTEM_RUNNING)
- vdso_data->processorCount++;
+ systemcfg->processorCount++;
+#endif
+#ifdef CONFIG_PPC64
vdso_getcpu_init();
#endif
set_numa_node(numa_cpu_lookup_table[cpu]);
@@ -1674,50 +1688,40 @@ void start_secondary(void *unused)
BUG();
}
-#ifdef CONFIG_PROFILING
-int setup_profiling_timer(unsigned int multiplier)
-{
- return 0;
-}
-#endif
+static struct sched_domain_topology_level powerpc_topology[6];
-static void __init fixup_topology(void)
+static void __init build_sched_topology(void)
{
- int i;
+ int i = 0;
+
+ if (is_shared_processor() && has_big_cores)
+ static_branch_enable(&splpar_asym_pack);
#ifdef CONFIG_SCHED_SMT
if (has_big_cores) {
pr_info("Big cores detected but using small core scheduling\n");
- powerpc_topology[smt_idx].mask = smallcore_smt_mask;
+ powerpc_topology[i++] =
+ SDTL_INIT(smallcore_smt_mask, powerpc_smt_flags, SMT);
+ } else {
+ powerpc_topology[i++] = SDTL_INIT(cpu_smt_mask, powerpc_smt_flags, SMT);
}
#endif
+ if (shared_caches) {
+ powerpc_topology[i++] =
+ SDTL_INIT(shared_cache_mask, powerpc_shared_cache_flags, CACHE);
+ }
- if (!has_coregroup_support())
- powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
-
- /*
- * Try to consolidate topology levels here instead of
- * allowing scheduler to degenerate.
- * - Dont consolidate if masks are different.
- * - Dont consolidate if sd_flags exists and are different.
- */
- for (i = 1; i <= die_idx; i++) {
- if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
- continue;
+ if (has_coregroup_support()) {
+ powerpc_topology[i++] =
+ SDTL_INIT(cpu_mc_mask, powerpc_shared_proc_flags, MC);
+ }
- if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
- powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
- continue;
+ powerpc_topology[i++] = SDTL_INIT(cpu_cpu_mask, powerpc_shared_proc_flags, PKG);
- if (!powerpc_topology[i - 1].sd_flags)
- powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+ /* There must be one trailing NULL entry left. */
+ BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);
- powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
- powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
-#ifdef CONFIG_SCHED_DEBUG
- powerpc_topology[i].name = powerpc_topology[i + 1].name;
-#endif
- }
+ set_sched_topology(powerpc_topology);
}
void __init smp_cpus_done(unsigned int max_cpus)
@@ -1732,9 +1736,20 @@ void __init smp_cpus_done(unsigned int max_cpus)
smp_ops->bringup_done();
dump_numa_cpu_topology();
+ build_sched_topology();
+}
- fixup_topology();
- set_sched_topology(powerpc_topology);
+/*
+ * For asym packing, by default lower numbered CPU has higher priority.
+ * On shared processors, pack to lower numbered core. However avoid moving
+ * between thread_groups within the same core.
+ */
+int arch_asym_cpu_priority(int cpu)
+{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return -cpu / threads_per_core;
+
+ return -cpu;
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -1760,11 +1775,19 @@ int __cpu_disable(void)
void __cpu_die(unsigned int cpu)
{
+ /*
+ * This could perhaps be a generic call in idlea_task_dead(), but
+ * that requires testing from all archs, so first put it here to
+ */
+ VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(&init_mm)));
+ dec_mm_active_cpus(&init_mm);
+ cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
+
if (smp_ops->cpu_die)
smp_ops->cpu_die(cpu);
}
-void arch_cpu_idle_dead(void)
+void __noreturn arch_cpu_idle_dead(void)
{
/*
* Disable on the down path. This will be re-enabled by
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index a2443d61728e..90882b5175cd 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -21,6 +21,7 @@
#include <asm/processor.h>
#include <linux/ftrace.h>
#include <asm/kprobes.h>
+#include <linux/rethook.h>
#include <asm/paca.h>
@@ -43,7 +44,7 @@ void __no_sanitize_address arch_stack_walk(stack_trace_consume_fn consume_entry,
unsigned long *stack = (unsigned long *) sp;
unsigned long newsp, ip;
- if (!validate_sp(sp, task, STACK_FRAME_OVERHEAD))
+ if (!validate_sp(sp, task))
return;
newsp = stack[0];
@@ -73,29 +74,12 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum
bool firstframe;
stack_end = stack_page + THREAD_SIZE;
- if (!is_idle_task(task)) {
- /*
- * For user tasks, this is the SP value loaded on
- * kernel entry, see "PACAKSAVE(r13)" in _switch() and
- * system_call_common()/EXCEPTION_PROLOG_COMMON().
- *
- * Likewise for non-swapper kernel threads,
- * this also happens to be the top of the stack
- * as setup by copy_thread().
- *
- * Note that stack backlinks are not properly setup by
- * copy_thread() and thus, a forked task() will have
- * an unreliable stack trace until it's been
- * _switch()'ed to for the first time.
- */
- stack_end -= STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
- } else {
- /*
- * idle tasks have a custom stack layout,
- * c.f. cpu_idle_thread_init().
- */
- stack_end -= STACK_FRAME_OVERHEAD;
- }
+
+ // See copy_thread() for details.
+ if (task->flags & PF_KTHREAD)
+ stack_end -= STACK_FRAME_MIN_SIZE;
+ else
+ stack_end -= STACK_USER_INT_FRAME_SIZE;
if (task == current)
sp = current_stack_frame();
@@ -136,7 +120,7 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum
/* Mark stacktraces with exception frames as unreliable. */
if (sp <= stack_end - STACK_INT_FRAME_SIZE &&
- stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
+ stack[STACK_INT_FRAME_MARKER_LONGS] == STACK_FRAME_REGS_MARKER) {
return -EINVAL;
}
@@ -150,12 +134,13 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum
* arch-dependent code, they are generic.
*/
ip = ftrace_graph_ret_addr(task, &graph_idx, ip, stack);
-#ifdef CONFIG_KPROBES
+
/*
* Mark stacktraces with kretprobed functions on them
* as unreliable.
*/
- if (ip == (unsigned long)__kretprobe_trampoline)
+#ifdef CONFIG_RETHOOK
+ if (ip == (unsigned long)arch_rethook_trampoline)
return -EINVAL;
#endif
@@ -221,8 +206,8 @@ static void raise_backtrace_ipi(cpumask_t *mask)
}
}
-void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu)
{
- nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi);
+ nmi_trigger_cpumask_backtrace(mask, exclude_cpu, raise_backtrace_ipi);
}
#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */
diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c
index 863a7aa24650..ec3101f95e53 100644
--- a/arch/powerpc/kernel/static_call.c
+++ b/arch/powerpc/kernel/static_call.c
@@ -2,32 +2,60 @@
#include <linux/memory.h>
#include <linux/static_call.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
{
int err;
bool is_ret0 = (func == __static_call_return0);
- unsigned long target = (unsigned long)(is_ret0 ? tramp + PPC_SCT_RET0 : func);
- bool is_short = is_offset_in_branch_range((long)target - (long)tramp);
-
- if (!tramp)
- return;
+ unsigned long _tramp = (unsigned long)tramp;
+ unsigned long _func = (unsigned long)func;
+ unsigned long _ret0 = _tramp + PPC_SCT_RET0;
+ bool is_short = is_offset_in_branch_range((long)func - (long)(site ? : tramp));
mutex_lock(&text_mutex);
- if (func && !is_short) {
- err = patch_instruction(tramp + PPC_SCT_DATA, ppc_inst(target));
- if (err)
- goto out;
+ if (site && tail) {
+ if (!func)
+ err = patch_instruction(site, ppc_inst(PPC_RAW_BLR()));
+ else if (is_ret0)
+ err = patch_branch(site, _ret0, 0);
+ else if (is_short)
+ err = patch_branch(site, _func, 0);
+ else if (tramp)
+ err = patch_branch(site, _tramp, 0);
+ else
+ err = 0;
+ } else if (site) {
+ if (!func)
+ err = patch_instruction(site, ppc_inst(PPC_RAW_NOP()));
+ else if (is_ret0)
+ err = patch_instruction(site, ppc_inst(PPC_RAW_LI(_R3, 0)));
+ else if (is_short)
+ err = patch_branch(site, _func, BRANCH_SET_LINK);
+ else if (tramp)
+ err = patch_branch(site, _tramp, BRANCH_SET_LINK);
+ else
+ err = 0;
+ } else if (tramp) {
+ if (func && !is_short) {
+ err = patch_ulong(tramp + PPC_SCT_DATA, _func);
+ if (err)
+ goto out;
+ }
+
+ if (!func)
+ err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR()));
+ else if (is_ret0)
+ err = patch_branch(tramp, _ret0, 0);
+ else if (is_short)
+ err = patch_branch(tramp, _func, 0);
+ else
+ err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP()));
+ } else {
+ err = 0;
}
- if (!func)
- err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR()));
- else if (is_short)
- err = patch_branch(tramp, target, 0);
- else
- err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP()));
out:
mutex_unlock(&text_mutex);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/switch.S
index 01ace4c56104..59e3ee99db0e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/switch.S
@@ -1,55 +1,21 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * PowerPC version
- * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
- * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
- * Adapted for Power Macintosh by Paul Mackerras.
- * Low-level exception handlers and MMU support
- * rewritten by Paul Mackerras.
- * Copyright (C) 1996 Paul Mackerras.
- * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
- *
- * This file contains the system call entry code, context switch
- * code, and exception/interrupt return code for PowerPC.
- */
-
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <asm/cache.h>
-#include <asm/unistd.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/mmu.h>
-#include <asm/thread_info.h>
+#include <linux/objtool.h>
+#include <asm/asm-offsets.h>
#include <asm/code-patching-asm.h>
+#include <asm/mmu.h>
#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/cputable.h>
-#include <asm/firmware.h>
-#include <asm/bug.h>
-#include <asm/ptrace.h>
-#include <asm/irqflags.h>
-#include <asm/hw_irq.h>
-#include <asm/context_tracking.h>
-#include <asm/ppc-opcode.h>
-#include <asm/barrier.h>
-#include <asm/export.h>
-#include <asm/asm-compat.h>
-#ifdef CONFIG_PPC_BOOK3S
-#include <asm/exception-64s.h>
-#else
-#include <asm/exception-64e.h>
-#endif
-#include <asm/feature-fixups.h>
#include <asm/kup.h>
+#include <asm/thread_info.h>
-/*
- * System calls.
- */
- .section ".text"
+.section ".text","ax",@progbits
#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * Cancel all explict user streams as they will have no use after context
+ * switch and will stop the HW from creating streams itself
+ */
+#define STOP_STREAMS \
+ DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6)
#define FLUSH_COUNT_CACHE \
1: nop; \
@@ -103,87 +69,13 @@ flush_branch_caches:
.endr
blr
-#else
-#define FLUSH_COUNT_CACHE
-#endif /* CONFIG_PPC_BOOK3S_64 */
+#ifdef CONFIG_PPC_64S_HASH_MMU
+.balign 32
/*
- * This routine switches between two different tasks. The process
- * state of one is saved on its kernel stack. Then the state
- * of the other is restored from its kernel stack. The memory
- * management hardware is updated to the second process's state.
- * Finally, we can return to the second process, via interrupt_return.
- * On entry, r3 points to the THREAD for the current task, r4
- * points to the THREAD for the new task.
- *
- * Note: there are two ways to get to the "going out" portion
- * of this code; either by coming in via the entry (_switch)
- * or via "fork" which must set up an environment equivalent
- * to the "_switch" path. If you change this you'll have to change
- * the fork code also.
- *
- * The code which creates the new task context is in 'copy_thread'
- * in arch/powerpc/kernel/process.c
+ * New stack pointer in r8, old stack pointer in r1, must not clobber r3
*/
- .align 7
-_GLOBAL(_switch)
- mflr r0
- std r0,16(r1)
- stdu r1,-SWITCH_FRAME_SIZE(r1)
- /* r3-r13 are caller saved -- Cort */
- SAVE_NVGPRS(r1)
- std r0,_NIP(r1) /* Return to switch caller */
- mfcr r23
- std r23,_CCR(r1)
- std r1,KSP(r3) /* Set old stack pointer */
-
- kuap_check_amr r9, r10
-
- FLUSH_COUNT_CACHE /* Clobbers r9, ctr */
-
- /*
- * On SMP kernels, care must be taken because a task may be
- * scheduled off CPUx and on to CPUy. Memory ordering must be
- * considered.
- *
- * Cacheable stores on CPUx will be visible when the task is
- * scheduled on CPUy by virtue of the core scheduler barriers
- * (see "Notes on Program-Order guarantees on SMP systems." in
- * kernel/sched/core.c).
- *
- * Uncacheable stores in the case of involuntary preemption must
- * be taken care of. The smp_mb__after_spinlock() in __schedule()
- * is implemented as hwsync on powerpc, which orders MMIO too. So
- * long as there is an hwsync in the context switch path, it will
- * be executed on the source CPU after the task has performed
- * all MMIO ops on that CPU, and on the destination CPU before the
- * task performs any MMIO ops there.
- */
-
- /*
- * The kernel context switch path must contain a spin_lock,
- * which contains larx/stcx, which will clear any reservation
- * of the task being switched.
- */
-#ifdef CONFIG_PPC_BOOK3S
-/* Cancel all explict user streams as they will have no use after context
- * switch and will stop the HW from creating streams itself
- */
- DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6)
-#endif
-
- addi r6,r4,-THREAD /* Convert THREAD to 'current' */
- std r6,PACACURRENT(r13) /* Set new 'current' */
-#if defined(CONFIG_STACKPROTECTOR)
- ld r6, TASK_CANARY(r6)
- std r6, PACA_CANARY(r13)
-#endif
-
- ld r8,KSP(r4) /* new stack pointer */
-#ifdef CONFIG_PPC_64S_HASH_MMU
-BEGIN_MMU_FTR_SECTION
- b 2f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
+pin_stack_slb:
BEGIN_FTR_SECTION
clrrdi r6,r8,28 /* get its ESID */
clrrdi r9,r1,28 /* get current sp ESID */
@@ -231,15 +123,57 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
slbmte r7,r0
isync
-2:
+2: blr
+ .size pin_stack_slb,.-pin_stack_slb
#endif /* CONFIG_PPC_64S_HASH_MMU */
- clrrdi r7, r8, THREAD_SHIFT /* base of new stack */
- /* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
- because we don't need to leave the 288-byte ABI gap at the
- top of the kernel stack. */
+#else
+#define STOP_STREAMS
+#define FLUSH_COUNT_CACHE
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+/*
+ * do_switch_32/64 have the same calling convention as _switch, i.e., r3,r4
+ * are prev and next thread_struct *, and returns prev task_struct * in r3.
+
+ * This switches the stack, current, and does other task switch housekeeping.
+ */
+.macro do_switch_32
+ tophys(r0,r4)
+ mtspr SPRN_SPRG_THREAD,r0 /* Update current THREAD phys addr */
+ lwz r1,KSP(r4) /* Load new stack pointer */
+
+ /* save the old current 'last' for return value */
+ mr r3,r2
+ addi r2,r4,-THREAD /* Update current */
+.endm
+
+.macro do_switch_64
+ ld r8,KSP(r4) /* Load new stack pointer */
+
+ kuap_check_amr r9, r10
+
+ FLUSH_COUNT_CACHE /* Clobbers r9, ctr */
+
+ STOP_STREAMS /* Clobbers r6 */
+
+ addi r3,r3,-THREAD /* old thread -> task_struct for return value */
+ addi r6,r4,-THREAD /* new thread -> task_struct */
+ std r6,PACACURRENT(r13) /* Set new task_struct to 'current' */
+#if defined(CONFIG_STACKPROTECTOR)
+ ld r6, TASK_CANARY(r6)
+ std r6, PACA_CANARY(r13)
+#endif
+ /* Set new PACAKSAVE */
+ clrrdi r7,r8,THREAD_SHIFT /* base of new stack */
addi r7,r7,THREAD_SIZE-SWITCH_FRAME_SIZE
+ std r7,PACAKSAVE(r13)
+#ifdef CONFIG_PPC_64S_HASH_MMU
+BEGIN_MMU_FTR_SECTION
+ bl pin_stack_slb
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
+#endif
/*
* PMU interrupts in radix may come in here. They will use r1, not
* PACAKSAVE, so this stack switch will not cause a problem. They
@@ -249,81 +183,75 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
* active on the new CPU, will order those stores.
*/
mr r1,r8 /* start using new stack pointer */
- std r7,PACAKSAVE(r13)
+.endm
+
+/*
+ * This routine switches between two different tasks. The process
+ * state of one is saved on its kernel stack. Then the state
+ * of the other is restored from its kernel stack. The memory
+ * management hardware is updated to the second process's state.
+ * Finally, we can return to the second process.
+ * On entry, r3 points to the THREAD for the current task, r4
+ * points to the THREAD for the new task.
+ *
+ * This routine is always called with interrupts disabled.
+ *
+ * Note: there are two ways to get to the "going out" portion
+ * of this code; either by coming in via the entry (_switch)
+ * or via "fork" which must set up an environment equivalent
+ * to the "_switch" path. If you change this , you'll have to
+ * change the fork code also.
+ *
+ * The code which creates the new task context is in 'copy_thread'
+ * in arch/ppc/kernel/process.c
+ *
+ * Note: this uses SWITCH_FRAME_SIZE rather than USER_INT_FRAME_SIZE
+ * because we don't need to leave the redzone ABI gap at the top of
+ * the kernel stack.
+ */
+_GLOBAL(_switch)
+ PPC_CREATE_STACK_FRAME(SWITCH_FRAME_SIZE)
+ PPC_STL r1,KSP(r3) /* Set old stack pointer */
+ SAVE_NVGPRS(r1) /* volatiles are caller-saved -- Cort */
+ PPC_STL r0,_NIP(r1) /* Return to switch caller */
+ mfcr r0
+ stw r0,_CCR(r1)
- ld r6,_CCR(r1)
- mtcrf 0xFF,r6
+ /*
+ * On SMP kernels, care must be taken because a task may be
+ * scheduled off CPUx and on to CPUy. Memory ordering must be
+ * considered.
+ *
+ * Cacheable stores on CPUx will be visible when the task is
+ * scheduled on CPUy by virtue of the core scheduler barriers
+ * (see "Notes on Program-Order guarantees on SMP systems." in
+ * kernel/sched/core.c).
+ *
+ * Uncacheable stores in the case of involuntary preemption must
+ * be taken care of. The smp_mb__after_spinlock() in __schedule()
+ * is implemented as hwsync on powerpc, which orders MMIO too. So
+ * long as there is an hwsync in the context switch path, it will
+ * be executed on the source CPU after the task has performed
+ * all MMIO ops on that CPU, and on the destination CPU before the
+ * task performs any MMIO ops there.
+ */
+
+ /*
+ * The kernel context switch path must contain a spin_lock,
+ * which contains larx/stcx, which will clear any reservation
+ * of the task being switched.
+ */
- /* r3-r13 are destroyed -- Cort */
- REST_NVGPRS(r1)
+#ifdef CONFIG_PPC32
+ do_switch_32
+#else
+ do_switch_64
+#endif
- /* convert old thread to its task_struct for return value */
- addi r3,r3,-THREAD
- ld r7,_NIP(r1) /* Return to _switch caller in new task */
- mtlr r7
+ lwz r0,_CCR(r1)
+ mtcrf 0xFF,r0
+ REST_NVGPRS(r1) /* volatiles are destroyed -- Cort */
+ PPC_LL r0,_NIP(r1) /* Return to _switch caller in new task */
+ mtlr r0
addi r1,r1,SWITCH_FRAME_SIZE
blr
-
-_GLOBAL(enter_prom)
- mflr r0
- std r0,16(r1)
- stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space */
-
- /* Because PROM is running in 32b mode, it clobbers the high order half
- * of all registers that it saves. We therefore save those registers
- * PROM might touch to the stack. (r0, r3-r13 are caller saved)
- */
- SAVE_GPR(2, r1)
- SAVE_GPR(13, r1)
- SAVE_NVGPRS(r1)
- mfcr r10
- mfmsr r11
- std r10,_CCR(r1)
- std r11,_MSR(r1)
-
- /* Put PROM address in SRR0 */
- mtsrr0 r4
-
- /* Setup our trampoline return addr in LR */
- bcl 20,31,$+4
-0: mflr r4
- addi r4,r4,(1f - 0b)
- mtlr r4
-
- /* Prepare a 32-bit mode big endian MSR
- */
-#ifdef CONFIG_PPC_BOOK3E
- rlwinm r11,r11,0,1,31
- mtsrr1 r11
- rfi
-#else /* CONFIG_PPC_BOOK3E */
- LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE)
- andc r11,r11,r12
- mtsrr1 r11
- RFI_TO_KERNEL
-#endif /* CONFIG_PPC_BOOK3E */
-
-1: /* Return from OF */
- FIXUP_ENDIAN
-
- /* Just make sure that r1 top 32 bits didn't get
- * corrupt by OF
- */
- rldicl r1,r1,0,32
-
- /* Restore the MSR (back to 64 bits) */
- ld r0,_MSR(r1)
- MTMSRD(r0)
- isync
-
- /* Restore other registers */
- REST_GPR(2, r1)
- REST_GPR(13, r1)
- REST_NVGPRS(r1)
- ld r4,_CCR(r1)
- mtcr r4
-
- addi r1,r1,SWITCH_FRAME_SIZE
- ld r0,16(r1)
- mtlr r0
- blr
diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S
index e0cbd63007f2..ffb79326483c 100644
--- a/arch/powerpc/kernel/swsusp_32.S
+++ b/arch/powerpc/kernel/swsusp_32.S
@@ -1,5 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/threads.h>
+#include <linux/linkage.h>
+
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/cputable.h>
@@ -400,7 +402,7 @@ _ASM_NOKPROBE_SYMBOL(swsusp_arch_resume)
/* FIXME:This construct is actually not useful since we don't shut
* down the instruction MMU, we could just flip back MSR-DR on.
*/
-turn_on_mmu:
+SYM_FUNC_START_LOCAL(turn_on_mmu)
mflr r4
mtsrr0 r4
mtsrr1 r3
@@ -408,4 +410,5 @@ turn_on_mmu:
isync
rfi
_ASM_NOKPROBE_SYMBOL(turn_on_mmu)
+SYM_FUNC_END(turn_on_mmu)
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 16ee3baaf09a..50fa8fc9ef95 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -11,6 +11,8 @@
#include <linux/interrupt.h>
#include <linux/nmi.h>
+void do_after_copyback(void);
+
void do_after_copyback(void)
{
iommu_restore();
diff --git a/arch/powerpc/kernel/swsusp_booke.S b/arch/powerpc/kernel/swsusp_85xx.S
index 88cfdbd530f1..88cfdbd530f1 100644
--- a/arch/powerpc/kernel/swsusp_booke.S
+++ b/arch/powerpc/kernel/swsusp_85xx.S
diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S
index 9f1903c7f540..f645652c2654 100644
--- a/arch/powerpc/kernel/swsusp_asm64.S
+++ b/arch/powerpc/kernel/swsusp_asm64.S
@@ -76,16 +76,10 @@
swsusp_save_area:
.space SL_SIZE
- .section ".toc","aw"
-swsusp_save_area_ptr:
- .tc swsusp_save_area[TC],swsusp_save_area
-restore_pblist_ptr:
- .tc restore_pblist[TC],restore_pblist
-
.section .text
.align 5
_GLOBAL(swsusp_arch_suspend)
- ld r11,swsusp_save_area_ptr@toc(r2)
+ LOAD_REG_ADDR(r11, swsusp_save_area)
SAVE_SPECIAL(LR)
SAVE_REGISTER(r1)
SAVE_SPECIAL(CR)
@@ -131,7 +125,7 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR)
bl swsusp_save
/* restore LR */
- ld r11,swsusp_save_area_ptr@toc(r2)
+ LOAD_REG_ADDR(r11, swsusp_save_area)
RESTORE_SPECIAL(LR)
addi r1,r1,128
@@ -145,7 +139,7 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
sync
- ld r12,restore_pblist_ptr@toc(r2)
+ LOAD_REG_ADDR(r11, restore_pblist)
ld r12,0(r12)
cmpdi r12,0
@@ -187,7 +181,7 @@ nothing_to_copy:
tlbia
#endif
- ld r11,swsusp_save_area_ptr@toc(r2)
+ LOAD_REG_ADDR(r11, swsusp_save_area)
RESTORE_SPECIAL(CR)
@@ -265,7 +259,7 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR)
bl do_after_copyback
addi r1,r1,128
- ld r11,swsusp_save_area_ptr@toc(r2)
+ LOAD_REG_ADDR(r11, swsusp_save_area)
RESTORE_SPECIAL(LR)
li r3, 0
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 16ff0399a257..d451a8229223 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -1,13 +1,23 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
- * sys_ppc32.c: Conversion between 32bit and 64bit native syscalls.
+ * sys_ppc32.c: 32-bit system calls with complex calling conventions.
*
* Copyright (C) 2001 IBM
* Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
* Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
*
- * These routines maintain argument size conversion between 32bit and 64bit
- * environment.
+ * 32-bit system calls with 64-bit arguments pass those in register pairs.
+ * This must be specially dealt with on 64-bit kernels. The compat_arg_u64_dual
+ * in generic compat syscalls is not always usable because the register
+ * pairing is constrained depending on preceding arguments.
+ *
+ * An analogous problem exists on 32-bit kernels with ARCH_HAS_SYSCALL_WRAPPER,
+ * the defined system call functions take the pt_regs as an argument, and there
+ * is a mapping macro which maps registers to arguments
+ * (SC_POWERPC_REGS_TO_ARGS) which also does not deal with these 64-bit
+ * arguments.
+ *
+ * This file contains these system calls.
*/
#include <linux/kernel.h>
@@ -25,7 +35,6 @@
#include <linux/poll.h>
#include <linux/personality.h>
#include <linux/stat.h>
-#include <linux/mman.h>
#include <linux/in.h>
#include <linux/syscalls.h>
#include <linux/unistd.h>
@@ -48,75 +57,79 @@
#include <asm/syscalls.h>
#include <asm/switch_to.h>
-unsigned long compat_sys_mmap2(unsigned long addr, size_t len,
- unsigned long prot, unsigned long flags,
- unsigned long fd, unsigned long pgoff)
-{
- /* This should remain 12 even if PAGE_SIZE changes */
- return sys_mmap(addr, len, prot, flags, fd, pgoff << 12);
-}
-
-/*
- * long long munging:
- * The 32 bit ABI passes long longs in an odd even register pair.
- * High and low parts are swapped depending on endian mode,
- * so define a macro (similar to mips linux32) to handle that.
- */
-#ifdef __LITTLE_ENDIAN__
-#define merge_64(low, high) ((u64)high << 32) | low
+#ifdef CONFIG_PPC32
+#define PPC32_SYSCALL_DEFINE4 SYSCALL_DEFINE4
+#define PPC32_SYSCALL_DEFINE5 SYSCALL_DEFINE5
+#define PPC32_SYSCALL_DEFINE6 SYSCALL_DEFINE6
#else
-#define merge_64(high, low) ((u64)high << 32) | low
+#define PPC32_SYSCALL_DEFINE4 COMPAT_SYSCALL_DEFINE4
+#define PPC32_SYSCALL_DEFINE5 COMPAT_SYSCALL_DEFINE5
+#define PPC32_SYSCALL_DEFINE6 COMPAT_SYSCALL_DEFINE6
#endif
-compat_ssize_t compat_sys_pread64(unsigned int fd, char __user *ubuf, compat_size_t count,
- u32 reg6, u32 pos1, u32 pos2)
+PPC32_SYSCALL_DEFINE6(ppc_pread64,
+ unsigned int, fd,
+ char __user *, ubuf, compat_size_t, count,
+ u32, reg6, u32, pos1, u32, pos2)
{
return ksys_pread64(fd, ubuf, count, merge_64(pos1, pos2));
}
-compat_ssize_t compat_sys_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count,
- u32 reg6, u32 pos1, u32 pos2)
+PPC32_SYSCALL_DEFINE6(ppc_pwrite64,
+ unsigned int, fd,
+ const char __user *, ubuf, compat_size_t, count,
+ u32, reg6, u32, pos1, u32, pos2)
{
return ksys_pwrite64(fd, ubuf, count, merge_64(pos1, pos2));
}
-compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offset1, u32 offset2, u32 count)
+PPC32_SYSCALL_DEFINE5(ppc_readahead,
+ int, fd, u32, r4,
+ u32, offset1, u32, offset2, u32, count)
{
return ksys_readahead(fd, merge_64(offset1, offset2), count);
}
-asmlinkage int compat_sys_truncate64(const char __user * path, u32 reg4,
- unsigned long len1, unsigned long len2)
+PPC32_SYSCALL_DEFINE4(ppc_truncate64,
+ const char __user *, path, u32, reg4,
+ unsigned long, len1, unsigned long, len2)
{
return ksys_truncate(path, merge_64(len1, len2));
}
-asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offset1, u32 offset2,
- u32 len1, u32 len2)
-{
- return ksys_fallocate(fd, mode, ((loff_t)offset1 << 32) | offset2,
- merge_64(len1, len2));
-}
-
-asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long len1,
- unsigned long len2)
+PPC32_SYSCALL_DEFINE4(ppc_ftruncate64,
+ unsigned int, fd, u32, reg4,
+ unsigned long, len1, unsigned long, len2)
{
return ksys_ftruncate(fd, merge_64(len1, len2));
}
-long ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2,
- size_t len, int advice)
+PPC32_SYSCALL_DEFINE6(ppc32_fadvise64,
+ int, fd, u32, unused, u32, offset1, u32, offset2,
+ size_t, len, int, advice)
{
return ksys_fadvise64_64(fd, merge_64(offset1, offset2), len,
advice);
}
-asmlinkage long compat_sys_sync_file_range2(int fd, unsigned int flags,
- unsigned offset1, unsigned offset2,
- unsigned nbytes1, unsigned nbytes2)
+PPC32_SYSCALL_DEFINE6(ppc_sync_file_range2,
+ int, fd, unsigned int, flags,
+ unsigned int, offset1, unsigned int, offset2,
+ unsigned int, nbytes1, unsigned int, nbytes2)
{
loff_t offset = merge_64(offset1, offset2);
loff_t nbytes = merge_64(nbytes1, nbytes2);
return ksys_sync_file_range(fd, offset, nbytes, flags);
}
+
+#ifdef CONFIG_PPC32
+SYSCALL_DEFINE6(ppc_fallocate,
+ int, fd, int, mode,
+ u32, offset1, u32, offset2, u32, len1, u32, len2)
+{
+ return ksys_fallocate(fd, mode,
+ merge_64(offset1, offset2),
+ merge_64(len1, len2));
+}
+#endif
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
new file mode 100644
index 000000000000..be159ad4b77b
--- /dev/null
+++ b/arch/powerpc/kernel/syscall.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/compat.h>
+#include <linux/context_tracking.h>
+#include <linux/randomize_kstack.h>
+
+#include <asm/interrupt.h>
+#include <asm/kup.h>
+#include <asm/syscall.h>
+#include <asm/time.h>
+#include <asm/tm.h>
+#include <asm/unistd.h>
+
+
+/* Has to run notrace because it is entered not completely "reconciled" */
+notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
+{
+ long ret;
+ syscall_fn f;
+
+ kuap_lock();
+
+ add_random_kstack_offset();
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+
+ trace_hardirqs_off(); /* finish reconciling */
+
+ CT_WARN_ON(ct_state() == CT_STATE_KERNEL);
+ user_exit_irqoff();
+
+ BUG_ON(regs_is_unrecoverable(regs));
+ BUG_ON(!user_mode(regs));
+ BUG_ON(arch_irq_disabled_regs(regs));
+
+#ifdef CONFIG_PPC_PKEY
+ if (mmu_has_feature(MMU_FTR_PKEY)) {
+ unsigned long amr, iamr;
+ bool flush_needed = false;
+ /*
+ * When entering from userspace we mostly have the AMR/IAMR
+ * different from kernel default values. Hence don't compare.
+ */
+ amr = mfspr(SPRN_AMR);
+ iamr = mfspr(SPRN_IAMR);
+ regs->amr = amr;
+ regs->iamr = iamr;
+ if (mmu_has_feature(MMU_FTR_KUAP)) {
+ mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
+ flush_needed = true;
+ }
+ if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
+ mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
+ flush_needed = true;
+ }
+ if (flush_needed)
+ isync();
+ } else
+#endif
+ kuap_assert_locked();
+
+ booke_restore_dbcr0();
+
+ account_cpu_user_entry();
+
+ account_stolen_time();
+
+ /*
+ * This is not required for the syscall exit path, but makes the
+ * stack frame look nicer. If this was initialised in the first stack
+ * frame, or if the unwinder was taught the first stack frame always
+ * returns to user with IRQS_ENABLED, this store could be avoided!
+ */
+ irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
+
+ /*
+ * If system call is called with TM active, set _TIF_RESTOREALL to
+ * prevent RFSCV being used to return to userspace, because POWER9
+ * TM implementation has problems with this instruction returning to
+ * transactional state. Final register values are not relevant because
+ * the transaction will be aborted upon return anyway. Or in the case
+ * of unsupported_scv SIGILL fault, the return state does not much
+ * matter because it's an edge case.
+ */
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+ unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
+ set_bits(_TIF_RESTOREALL, &current_thread_info()->flags);
+
+ /*
+ * If the system call was made with a transaction active, doom it and
+ * return without performing the system call. Unless it was an
+ * unsupported scv vector, in which case it's treated like an illegal
+ * instruction.
+ */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
+ !trap_is_unsupported_scv(regs)) {
+ /* Enable TM in the kernel, and disable EE (for scv) */
+ hard_irq_disable();
+ mtmsr(mfmsr() | MSR_TM);
+
+ /* tabort, this dooms the transaction, nothing else */
+ asm volatile(".long 0x7c00071d | ((%0) << 16)"
+ :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT));
+
+ /*
+ * Userspace will never see the return value. Execution will
+ * resume after the tbegin. of the aborted transaction with the
+ * checkpointed register state. A context switch could occur
+ * or signal delivered to the process before resuming the
+ * doomed transaction context, but that should all be handled
+ * as expected.
+ */
+ return -ENOSYS;
+ }
+#endif // CONFIG_PPC_TRANSACTIONAL_MEM
+
+ local_irq_enable();
+
+ if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) {
+ if (unlikely(trap_is_unsupported_scv(regs))) {
+ /* Unsupported scv vector */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return regs->gpr[3];
+ }
+ /*
+ * We use the return value of do_syscall_trace_enter() as the
+ * syscall number. If the syscall was rejected for any reason
+ * do_syscall_trace_enter() returns an invalid syscall number
+ * and the test against NR_syscalls will fail and the return
+ * value to be used is in regs->gpr[3].
+ */
+ r0 = do_syscall_trace_enter(regs);
+ if (unlikely(r0 >= NR_syscalls))
+ return regs->gpr[3];
+
+ } else if (unlikely(r0 >= NR_syscalls)) {
+ if (unlikely(trap_is_unsupported_scv(regs))) {
+ /* Unsupported scv vector */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return regs->gpr[3];
+ }
+ return -ENOSYS;
+ }
+
+ /* May be faster to do array_index_nospec? */
+ barrier_nospec();
+
+#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
+ // No COMPAT if we have SYSCALL_WRAPPER, see Kconfig
+ f = (void *)sys_call_table[r0];
+ ret = f(regs);
+#else
+ if (unlikely(is_compat_task())) {
+ unsigned long r3, r4, r5, r6, r7, r8;
+
+ f = (void *)compat_sys_call_table[r0];
+
+ r3 = regs->gpr[3] & 0x00000000ffffffffULL;
+ r4 = regs->gpr[4] & 0x00000000ffffffffULL;
+ r5 = regs->gpr[5] & 0x00000000ffffffffULL;
+ r6 = regs->gpr[6] & 0x00000000ffffffffULL;
+ r7 = regs->gpr[7] & 0x00000000ffffffffULL;
+ r8 = regs->gpr[8] & 0x00000000ffffffffULL;
+
+ ret = f(r3, r4, r5, r6, r7, r8);
+ } else {
+ f = (void *)sys_call_table[r0];
+
+ ret = f(regs->gpr[3], regs->gpr[4], regs->gpr[5],
+ regs->gpr[6], regs->gpr[7], regs->gpr[8]);
+ }
+#endif
+
+ /*
+ * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+ * so the maximum stack offset is 1k bytes (10 bits).
+ *
+ * The actual entropy will be further reduced by the compiler when
+ * applying stack alignment constraints: the powerpc architecture
+ * may have two kinds of stack alignment (16-bytes and 8-bytes).
+ *
+ * So the resulting 6 or 7 bits of entropy is seen in SP[9:4] or SP[9:3].
+ */
+ choose_random_kstack_offset(mftb());
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index fc999140bc27..68ebb23a5af4 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -36,9 +36,9 @@
#include <asm/time.h>
#include <asm/unistd.h>
-static inline long do_mmap2(unsigned long addr, size_t len,
- unsigned long prot, unsigned long flags,
- unsigned long fd, unsigned long off, int shift)
+static long do_mmap2(unsigned long addr, size_t len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long off, int shift)
{
if (!arch_validate_prot(prot, addr))
return -EINVAL;
@@ -56,6 +56,16 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len,
return do_mmap2(addr, len, prot, flags, fd, pgoff, PAGE_SHIFT-12);
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE6(mmap2,
+ unsigned long, addr, size_t, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, unsigned long, off_4k)
+{
+ return do_mmap2(addr, len, prot, flags, fd, off_4k, PAGE_SHIFT-12);
+}
+#endif
+
SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len,
unsigned long, prot, unsigned long, flags,
unsigned long, fd, off_t, offset)
@@ -63,43 +73,39 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len,
return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT);
}
-#ifdef CONFIG_PPC32
-/*
- * Due to some executables calling the wrong select we sometimes
- * get wrong args. This determines how the args are being passed
- * (a single ptr to them all args passed) then calls
- * sys_select() with the appropriate args. -- Cort
- */
-int
-ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp)
-{
- if ((unsigned long)n >= 4096)
- return sys_old_select((void __user *)n);
-
- return sys_select(n, inp, outp, exp, tvp);
-}
-#endif
-
#ifdef CONFIG_PPC64
-long ppc64_personality(unsigned long personality)
+static long do_ppc64_personality(unsigned long personality)
{
long ret;
if (personality(current->personality) == PER_LINUX32
&& personality(personality) == PER_LINUX)
personality = (personality & ~PER_MASK) | PER_LINUX32;
- ret = sys_personality(personality);
+ ret = ksys_personality(personality);
if (personality(ret) == PER_LINUX32)
ret = (ret & ~PER_MASK) | PER_LINUX;
return ret;
}
-#endif
-long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
- u32 len_high, u32 len_low)
+SYSCALL_DEFINE1(ppc64_personality, unsigned long, personality)
+{
+ return do_ppc64_personality(personality);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE1(ppc64_personality, unsigned long, personality)
+{
+ return do_ppc64_personality(personality);
+}
+#endif /* CONFIG_COMPAT */
+#endif /* CONFIG_PPC64 */
+
+SYSCALL_DEFINE6(ppc_fadvise64_64,
+ int, fd, int, advice, u32, offset_high, u32, offset_low,
+ u32, len_high, u32, len_low)
{
- return ksys_fadvise64_64(fd, (u64)offset_high << 32 | offset_low,
- (u64)len_high << 32 | len_low, advice);
+ return ksys_fadvise64_64(fd, merge_64(offset_high, offset_low),
+ merge_64(len_high, len_low), advice);
}
SYSCALL_DEFINE0(switch_endian)
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 2600b4237292..b453e80dfc00 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -110,7 +110,7 @@
79 common settimeofday sys_settimeofday compat_sys_settimeofday
80 common getgroups sys_getgroups
81 common setgroups sys_setgroups
-82 32 select ppc_select sys_ni_syscall
+82 32 select sys_old_select compat_sys_old_select
82 64 select sys_ni_syscall
82 spu select sys_ni_syscall
83 common symlink sys_symlink
@@ -178,9 +178,9 @@
133 common fchdir sys_fchdir
134 common bdflush sys_ni_syscall
135 common sysfs sys_sysfs
-136 32 personality sys_personality ppc64_personality
-136 64 personality ppc64_personality
-136 spu personality ppc64_personality
+136 32 personality sys_personality compat_sys_ppc64_personality
+136 64 personality sys_ppc64_personality
+136 spu personality sys_ppc64_personality
137 common afs_syscall sys_ni_syscall
138 common setfsuid sys_setfsuid
139 common setfsgid sys_setfsgid
@@ -228,8 +228,12 @@
176 64 rt_sigtimedwait sys_rt_sigtimedwait
177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend
-179 common pread64 sys_pread64 compat_sys_pread64
-180 common pwrite64 sys_pwrite64 compat_sys_pwrite64
+179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64
+179 64 pread64 sys_pread64
+179 spu pread64 sys_pread64
+180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64
+180 64 pwrite64 sys_pwrite64
+180 spu pwrite64 sys_pwrite64
181 common chown sys_chown
182 common getcwd sys_getcwd
183 common capget sys_capget
@@ -242,10 +246,12 @@
188 common putpmsg sys_ni_syscall
189 nospu vfork sys_vfork
190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
-191 common readahead sys_readahead compat_sys_readahead
+191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead
+191 64 readahead sys_readahead
+191 spu readahead sys_readahead
192 32 mmap2 sys_mmap2 compat_sys_mmap2
-193 32 truncate64 sys_truncate64 compat_sys_truncate64
-194 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64
+193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64
+194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64
195 32 stat64 sys_stat64
196 32 lstat64 sys_lstat64
197 32 fstat64 sys_fstat64
@@ -288,9 +294,11 @@
230 common io_submit sys_io_submit compat_sys_io_submit
231 common io_cancel sys_io_cancel
232 nospu set_tid_address sys_set_tid_address
-233 common fadvise64 sys_fadvise64 ppc32_fadvise64
+233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64
+233 64 fadvise64 sys_fadvise64
+233 spu fadvise64 sys_fadvise64
234 nospu exit_group sys_exit_group
-235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie
+235 nospu lookup_dcookie sys_ni_syscall
236 common epoll_create sys_epoll_create
237 common epoll_ctl sys_epoll_ctl
238 common epoll_wait sys_epoll_wait
@@ -323,7 +331,7 @@
251 spu utimes sys_utimes
252 common statfs64 sys_statfs64 compat_sys_statfs64
253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
-254 32 fadvise64_64 ppc_fadvise64_64
+254 32 fadvise64_64 sys_ppc_fadvise64_64
254 spu fadvise64_64 sys_ni_syscall
255 common rtas sys_rtas
256 32 sys_debug_setcontext sys_debug_setcontext sys_ni_syscall
@@ -390,8 +398,11 @@
305 common signalfd sys_signalfd compat_sys_signalfd
306 common timerfd_create sys_timerfd_create
307 common eventfd sys_eventfd
-308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2
-309 nospu fallocate sys_fallocate compat_sys_fallocate
+308 32 sync_file_range2 sys_ppc_sync_file_range2 compat_sys_ppc_sync_file_range2
+308 64 sync_file_range2 sys_sync_file_range2
+308 spu sync_file_range2 sys_sync_file_range2
+309 32 fallocate sys_ppc_fallocate compat_sys_fallocate
+309 64 fallocate sys_fallocate
310 nospu subpage_prot sys_subpage_prot
311 32 timerfd_settime sys_timerfd_settime32
311 64 timerfd_settime sys_timerfd_settime
@@ -495,7 +506,7 @@
412 32 utimensat_time64 sys_utimensat sys_utimensat
413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64
414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64
-416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents
+416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64
417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64
418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend
419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive
@@ -530,3 +541,22 @@
448 common process_mrelease sys_process_mrelease
449 common futex_waitv sys_futex_waitv
450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node
+451 common cachestat sys_cachestat
+452 common fchmodat2 sys_fchmodat2
+453 common map_shadow_stack sys_ni_syscall
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
+457 common statmount sys_statmount
+458 common listmount sys_listmount
+459 common lsm_get_self_attr sys_lsm_get_self_attr
+460 common lsm_set_self_attr sys_lsm_set_self_attr
+461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
+463 common setxattrat sys_setxattrat
+464 common getxattrat sys_getxattrat
+465 common listxattrat sys_listxattrat
+466 common removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr
+468 common file_getattr sys_file_getattr
+469 common file_setattr sys_file_setattr
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 3a10cda9c05e..6b3dd6decdf9 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -17,6 +17,7 @@
#include <asm/hvcall.h>
#include <asm/machdep.h>
#include <asm/smp.h>
+#include <asm/time.h>
#include <asm/pmc.h>
#include <asm/firmware.h>
#include <asm/idle.h>
@@ -139,7 +140,7 @@ static unsigned long dscr_default;
* @val: Returned cpu specific DSCR default value
*
* This function returns the per cpu DSCR default value
- * for any cpu which is contained in it's PACA structure.
+ * for any cpu which is contained in its PACA structure.
*/
static void read_dscr(void *val)
{
@@ -152,7 +153,7 @@ static void read_dscr(void *val)
* @val: New cpu specific DSCR default value to update
*
* This function updates the per cpu DSCR default value
- * for any cpu which is contained in it's PACA structure.
+ * for any cpu which is contained in its PACA structure.
*/
static void write_dscr(void *val)
{
@@ -217,18 +218,23 @@ static DEVICE_ATTR(dscr_default, 0600,
static void __init sysfs_create_dscr_default(void)
{
if (cpu_has_feature(CPU_FTR_DSCR)) {
+ struct device *dev_root;
int cpu;
dscr_default = spr_default_dscr;
for_each_possible_cpu(cpu)
paca_ptrs[cpu]->dscr_default = dscr_default;
- device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
+ dev_root = bus_get_dev_root(&cpu_subsys);
+ if (dev_root) {
+ device_create_file(dev_root, &dev_attr_dscr_default);
+ put_device(dev_root);
+ }
}
}
#endif /* CONFIG_PPC64 */
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
#define MAX_BIT 63
static u64 pw20_wt;
@@ -746,7 +752,12 @@ static DEVICE_ATTR(svm, 0444, show_svm, NULL);
static void __init create_svm_file(void)
{
- device_create_file(cpu_subsys.dev_root, &dev_attr_svm);
+ struct device *dev_root = bus_get_dev_root(&cpu_subsys);
+
+ if (dev_root) {
+ device_create_file(dev_root, &dev_attr_svm);
+ put_device(dev_root);
+ }
}
#else
static void __init create_svm_file(void)
@@ -907,7 +918,7 @@ static int register_cpu_online(unsigned int cpu)
device_create_file(s, &dev_attr_tscr);
#endif /* CONFIG_PPC64 */
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) {
device_create_file(s, &dev_attr_pw20_state);
device_create_file(s, &dev_attr_pw20_wait_time);
@@ -1003,7 +1014,7 @@ static int unregister_cpu_online(unsigned int cpu)
device_remove_file(s, &dev_attr_tscr);
#endif /* CONFIG_PPC64 */
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) {
device_remove_file(s, &dev_attr_pw20_state);
device_remove_file(s, &dev_attr_pw20_wait_time);
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.c
index cb3358886203..4305f2a2162f 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.c
@@ -10,31 +10,37 @@
* PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
*/
-#include <asm/ppc_asm.h>
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include <asm/unistd.h>
+#include <asm/syscalls.h>
-.section .rodata,"a"
+#undef __SYSCALL_WITH_COMPAT
+#define __SYSCALL_WITH_COMPAT(nr, entry, compat) __SYSCALL(nr, entry)
-#ifdef CONFIG_PPC64
- .p2align 3
-#define __SYSCALL(nr, entry) .8byte entry
+#undef __SYSCALL
+#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
+#define __SYSCALL(nr, entry) [nr] = entry,
#else
-#define __SYSCALL(nr, entry) .long entry
+/*
+ * Coerce syscall handlers with arbitrary parameters to common type
+ * requires cast to void* to avoid -Wcast-function-type.
+ */
+#define __SYSCALL(nr, entry) [nr] = (void *) entry,
#endif
-#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native)
-.globl sys_call_table
-sys_call_table:
+const syscall_fn sys_call_table[] = {
#ifdef CONFIG_PPC64
#include <asm/syscall_table_64.h>
#else
#include <asm/syscall_table_32.h>
#endif
+};
#ifdef CONFIG_COMPAT
#undef __SYSCALL_WITH_COMPAT
#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat)
-.globl compat_sys_call_table
-compat_sys_call_table:
-#define compat_sys_sigsuspend sys_sigsuspend
+const syscall_fn compat_sys_call_table[] = {
#include <asm/syscall_table_32.h>
-#endif
+};
+#endif /* CONFIG_COMPAT */
diff --git a/arch/powerpc/kernel/systbl_chk.sh b/arch/powerpc/kernel/systbl_chk.sh
deleted file mode 100644
index c7ac3ed657c4..000000000000
--- a/arch/powerpc/kernel/systbl_chk.sh
+++ /dev/null
@@ -1,30 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0-or-later
-#
-# Just process the CPP output from systbl_chk.c and complain
-# if anything is out of order.
-#
-# Copyright © 2008 IBM Corporation
-#
-
-awk 'BEGIN { num = -1; } # Ignore the beginning of the file
- /^#/ { next; }
- /^[ \t]*$/ { next; }
- /^START_TABLE/ { num = 0; next; }
- /^END_TABLE/ {
- if (num != $2) {
- printf "Error: NR_syscalls (%s) is not one more than the last syscall (%s)\n",
- $2, num - 1;
- exit(1);
- }
- num = -1; # Ignore the rest of the file
- }
- {
- if (num == -1) next;
- if (($1 != -1) && ($1 != num)) {
- printf "Error: Syscall %s out of order (expected %s)\n",
- $1, num;
- exit(1);
- };
- num++;
- }' "$1"
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 828d0f4106d2..cba6dd15de3b 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -200,7 +200,7 @@ static int __init TAU_init(void)
tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) &&
!strcmp(cur_cpu_spec->platform, "ppc750");
- tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1);
+ tau_workq = alloc_ordered_workqueue("tau", 0);
if (!tau_workq)
return -ENOMEM;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 587adcc12860..8224381c1dba 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -71,11 +71,11 @@
#include <asm/vdso_datapage.h>
#include <asm/firmware.h>
#include <asm/mce.h>
+#include <asm/systemcfg.h>
/* powerpc clocksource/clockevent code */
#include <linux/clockchips.h>
-#include <linux/timekeeper_internal.h>
static u64 timebase_read(struct clocksource *);
static struct clocksource clocksource_timebase = {
@@ -130,7 +130,7 @@ unsigned long tb_ticks_per_jiffy;
unsigned long tb_ticks_per_usec = 100; /* sane default */
EXPORT_SYMBOL(tb_ticks_per_usec);
unsigned long tb_ticks_per_sec;
-EXPORT_SYMBOL(tb_ticks_per_sec); /* for cputime_t conversions */
+EXPORT_SYMBOL(tb_ticks_per_sec); /* for cputime conversions */
DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL_GPL(rtc_lock);
@@ -151,21 +151,6 @@ bool tb_invalid;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
/*
- * Factor for converting from cputime_t (timebase ticks) to
- * microseconds. This is stored as 0.64 fixed-point binary fraction.
- */
-u64 __cputime_usec_factor;
-EXPORT_SYMBOL(__cputime_usec_factor);
-
-static void calc_cputime_factors(void)
-{
- struct div_result res;
-
- div128_by_32(1000000, 0, tb_ticks_per_sec, &res);
- __cputime_usec_factor = res.result_low;
-}
-
-/*
* Read the SPURR on systems that have it, otherwise the PURR,
* or if that doesn't exist return the timebase value passed in.
*/
@@ -178,92 +163,6 @@ static inline unsigned long read_spurr(unsigned long tb)
return tb;
}
-#ifdef CONFIG_PPC_SPLPAR
-
-#include <asm/dtl.h>
-
-void (*dtl_consumer)(struct dtl_entry *, u64);
-
-/*
- * Scan the dispatch trace log and count up the stolen time.
- * Should be called with interrupts disabled.
- */
-static u64 scan_dispatch_log(u64 stop_tb)
-{
- u64 i = local_paca->dtl_ridx;
- struct dtl_entry *dtl = local_paca->dtl_curr;
- struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
- struct lppaca *vpa = local_paca->lppaca_ptr;
- u64 tb_delta;
- u64 stolen = 0;
- u64 dtb;
-
- if (!dtl)
- return 0;
-
- if (i == be64_to_cpu(vpa->dtl_idx))
- return 0;
- while (i < be64_to_cpu(vpa->dtl_idx)) {
- dtb = be64_to_cpu(dtl->timebase);
- tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +
- be32_to_cpu(dtl->ready_to_enqueue_time);
- barrier();
- if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
- /* buffer has overflowed */
- i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
- dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
- continue;
- }
- if (dtb > stop_tb)
- break;
- if (dtl_consumer)
- dtl_consumer(dtl, i);
- stolen += tb_delta;
- ++i;
- ++dtl;
- if (dtl == dtl_end)
- dtl = local_paca->dispatch_log;
- }
- local_paca->dtl_ridx = i;
- local_paca->dtl_curr = dtl;
- return stolen;
-}
-
-/*
- * Accumulate stolen time by scanning the dispatch trace log.
- * Called on entry from user mode.
- */
-void notrace accumulate_stolen_time(void)
-{
- u64 sst, ust;
- struct cpu_accounting_data *acct = &local_paca->accounting;
-
- sst = scan_dispatch_log(acct->starttime_user);
- ust = scan_dispatch_log(acct->starttime);
- acct->stime -= sst;
- acct->utime -= ust;
- acct->steal_time += ust + sst;
-}
-
-static inline u64 calculate_stolen_time(u64 stop_tb)
-{
- if (!firmware_has_feature(FW_FEATURE_SPLPAR))
- return 0;
-
- if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
- return scan_dispatch_log(stop_tb);
-
- return 0;
-}
-
-#else /* CONFIG_PPC_SPLPAR */
-static inline u64 calculate_stolen_time(u64 stop_tb)
-{
- return 0;
-}
-
-#endif /* CONFIG_PPC_SPLPAR */
-
/*
* Account time for a transition between system, hard irq
* or soft irq state.
@@ -322,7 +221,11 @@ static unsigned long vtime_delta(struct cpu_accounting_data *acct,
*stime_scaled = vtime_delta_scaled(acct, now, stime);
- *steal_time = calculate_stolen_time(now);
+ if (IS_ENABLED(CONFIG_PPC_SPLPAR) &&
+ firmware_has_feature(FW_FEATURE_SPLPAR))
+ *steal_time = pseries_calculate_stolen_time(now);
+ else
+ *steal_time = 0;
return stime;
}
@@ -452,11 +355,30 @@ void vtime_flush(struct task_struct *tsk)
acct->softirq_time = 0;
}
-#else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-#define calc_cputime_factors()
-#endif
+/*
+ * Called from the context switch with interrupts disabled, to charge all
+ * accumulated times to the current process, and to prepare accounting on
+ * the next process.
+ */
+void vtime_task_switch(struct task_struct *prev)
+{
+ if (is_idle_task(prev))
+ vtime_account_idle(prev);
+ else
+ vtime_account_kernel(prev);
+
+ vtime_flush(prev);
+
+ if (!IS_ENABLED(CONFIG_PPC64)) {
+ struct cpu_accounting_data *acct = get_accounting(current);
+ struct cpu_accounting_data *acct0 = get_accounting(prev);
+
+ acct->starttime = acct0->starttime;
+ }
+}
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-void __delay(unsigned long loops)
+void __no_kcsan __delay(unsigned long loops)
{
unsigned long start;
@@ -477,7 +399,7 @@ void __delay(unsigned long loops)
}
EXPORT_SYMBOL(__delay);
-void udelay(unsigned long usecs)
+void __no_kcsan udelay(unsigned long usecs)
{
__delay(tb_ticks_per_usec * usecs);
}
@@ -614,22 +536,23 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
return;
}
- /*
- * Ensure a positive value is written to the decrementer, or
- * else some CPUs will continue to take decrementer exceptions.
- * When the PPC_WATCHDOG (decrementer based) is configured,
- * keep this at most 31 bits, which is about 4 seconds on most
- * systems, which gives the watchdog a chance of catching timer
- * interrupt hard lockups.
- */
- if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
- set_dec(0x7fffffff);
- else
- set_dec(decrementer_max);
-
/* Conditionally hard-enable interrupts. */
- if (should_hard_irq_enable())
+ if (should_hard_irq_enable(regs)) {
+ /*
+ * Ensure a positive value is written to the decrementer, or
+ * else some CPUs will continue to take decrementer exceptions.
+ * When the PPC_WATCHDOG (decrementer based) is configured,
+ * keep this at most 31 bits, which is about 4 seconds on most
+ * systems, which gives the watchdog a chance of catching timer
+ * interrupt hard lockups.
+ */
+ if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
+ set_dec(0x7fffffff);
+ else
+ set_dec(decrementer_max);
+
do_hard_irq_enable();
+ }
#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
if (atomic_read(&ppc_n_lost_interrupts) != 0)
@@ -772,7 +695,7 @@ static int __init get_freq(char *name, int cells, unsigned long *val)
static void start_cpu_decrementer(void)
{
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
unsigned int tcr;
/* Clear any pending timer interrupts */
@@ -978,6 +901,38 @@ void secondary_cpu_time_init(void)
register_decrementer_clockevent(smp_processor_id());
}
+/*
+ * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
+ * result.
+ */
+static __init void div128_by_32(u64 dividend_high, u64 dividend_low,
+ unsigned int divisor, struct div_result *dr)
+{
+ unsigned long a, b, c, d;
+ unsigned long w, x, y, z;
+ u64 ra, rb, rc;
+
+ a = dividend_high >> 32;
+ b = dividend_high & 0xffffffff;
+ c = dividend_low >> 32;
+ d = dividend_low & 0xffffffff;
+
+ w = a / divisor;
+ ra = ((u64)(a - (w * divisor)) << 32) + b;
+
+ rb = ((u64)do_div(ra, divisor) << 32) + c;
+ x = ra;
+
+ rc = ((u64)do_div(rb, divisor) << 32) + d;
+ y = rb;
+
+ do_div(rc, divisor);
+ z = rc;
+
+ dr->result_high = ((u64)w << 32) + x;
+ dr->result_low = ((u64)y << 32) + z;
+}
+
/* This function is only called on the boot processor */
void __init time_init(void)
{
@@ -986,7 +941,11 @@ void __init time_init(void)
unsigned shift;
/* Normal PowerPC with timebase register */
- ppc_md.calibrate_decr();
+ if (ppc_md.calibrate_decr)
+ ppc_md.calibrate_decr();
+ else
+ generic_calibrate_decr();
+
printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n",
ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n",
@@ -995,7 +954,6 @@ void __init time_init(void)
tb_ticks_per_jiffy = ppc_tb_freq / HZ;
tb_ticks_per_sec = ppc_tb_freq;
tb_ticks_per_usec = ppc_tb_freq / 1000000;
- calc_cputime_factors();
/*
* Compute scale factor for sched_clock.
@@ -1024,7 +982,10 @@ void __init time_init(void)
sys_tz.tz_dsttime = 0;
}
- vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+ vdso_k_arch_data->tb_ticks_per_sec = tb_ticks_per_sec;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+ systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
+#endif
/* initialise and enable the large decrementer (if we have one) */
set_decrementer_max();
@@ -1045,39 +1006,6 @@ void __init time_init(void)
enable_sched_clock_irqtime();
}
-/*
- * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
- * result.
- */
-void div128_by_32(u64 dividend_high, u64 dividend_low,
- unsigned divisor, struct div_result *dr)
-{
- unsigned long a, b, c, d;
- unsigned long w, x, y, z;
- u64 ra, rb, rc;
-
- a = dividend_high >> 32;
- b = dividend_high & 0xffffffff;
- c = dividend_low >> 32;
- d = dividend_low & 0xffffffff;
-
- w = a / divisor;
- ra = ((u64)(a - (w * divisor)) << 32) + b;
-
- rb = ((u64) do_div(ra, divisor) << 32) + c;
- x = ra;
-
- rc = ((u64) do_div(rb, divisor) << 32) + d;
- y = rb;
-
- do_div(rc, divisor);
- z = rc;
-
- dr->result_high = ((u64)w << 32) + x;
- dr->result_low = ((u64)y << 32) + z;
-
-}
-
/* We don't need to calibrate delay, we use the CPU timebase for that */
void calibrate_delay(void)
{
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 5a0f023a26e9..a9cd6507163a 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -6,13 +6,13 @@
* Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation.
*/
+#include <linux/export.h>
#include <asm/asm-offsets.h>
#include <asm/ppc_asm.h>
#include <asm/ppc-opcode.h>
#include <asm/ptrace.h>
#include <asm/reg.h>
#include <asm/bug.h>
-#include <asm/export.h>
#include <asm/feature-fixups.h>
#ifdef CONFIG_VSX
@@ -117,7 +117,7 @@ _GLOBAL(tm_reclaim)
std r2, STK_GOT(r1)
stdu r1, -TM_FRAME_SIZE(r1)
- /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */
+ /* We've a struct pt_regs at [r1+STACK_INT_FRAME_REGS]. */
std r3, STK_PARAM(R3)(r1)
SAVE_NVGPRS(r1)
@@ -222,7 +222,7 @@ _GLOBAL(tm_reclaim)
* Make r7 look like an exception frame so that we can use the neat
* GPRx(n) macros. r7 is NOT a pt_regs ptr!
*/
- subi r7, r7, STACK_FRAME_OVERHEAD
+ subi r7, r7, STACK_INT_FRAME_REGS
/* Sync the userland GPRs 2-12, 14-31 to thread->regs: */
SAVE_GPR(0, r7) /* user r0 */
@@ -359,7 +359,7 @@ _GLOBAL(__tm_recheckpoint)
stdu r1, -TM_FRAME_SIZE(r1)
/*
- * We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD].
+ * We've a struct pt_regs at [r1+STACK_INT_FRAME_REGS].
* This is used for backing up the NVGPRs:
*/
SAVE_NVGPRS(r1)
@@ -379,7 +379,7 @@ _GLOBAL(__tm_recheckpoint)
* Make r7 look like an exception frame so that we can use the neat
* GPRx(n) macros. r7 is now NOT a pt_regs ptr!
*/
- subi r7, r7, STACK_FRAME_OVERHEAD
+ subi r7, r7, STACK_INT_FRAME_REGS
/* We need to setup MSR for FP/VMX/VSX register save instructions. */
mfmsr r6
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
index af8527538fe4..d6c3885453bd 100644
--- a/arch/powerpc/kernel/trace/Makefile
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -6,15 +6,18 @@
ifdef CONFIG_FUNCTION_TRACER
# do not trace tracer code
CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace_64_pg.o = $(CC_FLAGS_FTRACE)
endif
-obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o
-ifdef CONFIG_MPROFILE_KERNEL
-obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o
+ifdef CONFIG_FUNCTION_TRACER
+obj32-y += ftrace.o ftrace_entry.o
+ifeq ($(CONFIG_MPROFILE_KERNEL)$(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY),)
+obj64-y += ftrace_64_pg.o ftrace_64_pg_entry.o
else
-obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o
+obj64-y += ftrace.o ftrace_entry.o
+endif
endif
-obj-$(CONFIG_FUNCTION_TRACER) += ftrace_low.o ftrace.o
+
obj-$(CONFIG_TRACING) += trace_clock.o
obj-$(CONFIG_PPC64) += $(obj64-y)
@@ -23,4 +26,9 @@ obj-$(CONFIG_PPC32) += $(obj32-y)
# Disable GCOV, KCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_ftrace.o := n
KCOV_INSTRUMENT_ftrace.o := n
+KCSAN_SANITIZE_ftrace.o := n
UBSAN_SANITIZE_ftrace.o := n
+GCOV_PROFILE_ftrace_64_pg.o := n
+KCOV_INSTRUMENT_ftrace_64_pg.o := n
+KCSAN_SANITIZE_ftrace_64_pg.o := n
+UBSAN_SANITIZE_ftrace_64_pg.o := n
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 2a893e06e4f1..6dca92d5a6e8 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -23,205 +23,85 @@
#include <linux/list.h>
#include <asm/cacheflush.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/ftrace.h>
#include <asm/syscall.h>
#include <asm/inst.h>
+#include <asm/sections.h>
-/*
- * We generally only have a single long_branch tramp and at most 2 or 3 plt
- * tramps generated. But, we don't use the plt tramps currently. We also allot
- * 2 tramps after .text and .init.text. So, we only end up with around 3 usable
- * tramps in total. Set aside 8 just to be sure.
- */
-#define NUM_FTRACE_TRAMPS 8
+#define NUM_FTRACE_TRAMPS 2
static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
-static ppc_inst_t
-ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
+unsigned long ftrace_call_adjust(unsigned long addr)
{
- ppc_inst_t op;
+ if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
+ return 0;
- addr = ppc_function_entry((void *)addr);
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) &&
+ !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+ addr += MCOUNT_INSN_SIZE;
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+ addr += MCOUNT_INSN_SIZE;
+ }
- /* if (link) set op to 'bl' else 'b' */
+ return addr;
+}
+
+static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
+{
+ ppc_inst_t op;
+
+ WARN_ON(!is_offset_in_branch_range(addr - ip));
create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
return op;
}
-static inline int
-ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+static inline int ftrace_read_inst(unsigned long ip, ppc_inst_t *op)
{
- ppc_inst_t replaced;
-
- /*
- * Note:
- * We are paranoid about modifying text, as if a bug was to happen, it
- * could cause us to read or write to someplace that could cause harm.
- * Carefully read and modify the code with probe_kernel_*(), and make
- * sure what we read is what we expected it to be before modifying it.
- */
-
- /* read the text we want to modify */
- if (copy_inst_from_kernel_nofault(&replaced, (void *)ip))
+ if (copy_inst_from_kernel_nofault(op, (void *)ip)) {
+ pr_err("0x%lx: fetching instruction failed\n", ip);
return -EFAULT;
-
- /* Make sure it is what we expect it to be */
- if (!ppc_inst_equal(replaced, old)) {
- pr_err("%p: replaced (%s) != old (%s)",
- (void *)ip, ppc_inst_as_str(replaced), ppc_inst_as_str(old));
- return -EINVAL;
}
- /* replace the text with the new text */
- return patch_instruction((u32 *)ip, new);
+ return 0;
}
-/*
- * Helper functions that are the same for both PPC64 and PPC32.
- */
-static int test_24bit_addr(unsigned long ip, unsigned long addr)
+static inline int ftrace_validate_inst(unsigned long ip, ppc_inst_t inst)
{
- addr = ppc_function_entry((void *)addr);
-
- return is_offset_in_branch_range(addr - ip);
-}
+ ppc_inst_t op;
+ int ret;
-static int is_bl_op(ppc_inst_t op)
-{
- return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
-}
+ ret = ftrace_read_inst(ip, &op);
+ if (!ret && !ppc_inst_equal(op, inst)) {
+ pr_err("0x%lx: expected (%08lx) != found (%08lx)\n",
+ ip, ppc_inst_as_ulong(inst), ppc_inst_as_ulong(op));
+ ret = -EINVAL;
+ }
-static int is_b_op(ppc_inst_t op)
-{
- return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0);
+ return ret;
}
-static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
+static inline int ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
{
- int offset;
+ int ret = ftrace_validate_inst(ip, old);
- offset = PPC_LI(ppc_inst_val(op));
- /* make it signed */
- if (offset & 0x02000000)
- offset |= 0xfe000000;
+ if (!ret && !ppc_inst_equal(old, new))
+ ret = patch_instruction((u32 *)ip, new);
- return ip + (long)offset;
+ return ret;
}
-#ifdef CONFIG_MODULES
-static int
-__ftrace_make_nop(struct module *mod,
- struct dyn_ftrace *rec, unsigned long addr)
-{
- unsigned long entry, ptr, tramp;
- unsigned long ip = rec->ip;
- ppc_inst_t op, pop;
-
- /* read where this goes */
- if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
- pr_err("Fetching opcode failed.\n");
- return -EFAULT;
- }
-
- /* Make sure that that this is still a 24bit jump */
- if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
- return -EINVAL;
- }
-
- /* lets find where the pointer goes */
- tramp = find_bl_target(ip, op);
-
- pr_devel("ip:%lx jumps to %lx", ip, tramp);
-
- if (module_trampoline_target(mod, tramp, &ptr)) {
- pr_err("Failed to get trampoline target\n");
- return -EFAULT;
- }
-
- pr_devel("trampoline target %lx", ptr);
-
- entry = ppc_global_function_entry((void *)addr);
- /* This should match what was called */
- if (ptr != entry) {
- pr_err("addr %lx does not match expected %lx\n", ptr, entry);
- return -EINVAL;
- }
-
- if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
- if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) {
- pr_err("Fetching instruction at %lx failed.\n", ip - 4);
- return -EFAULT;
- }
-
- /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
- if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) &&
- !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
- pr_err("Unexpected instruction %s around bl _mcount\n",
- ppc_inst_as_str(op));
- return -EINVAL;
- }
- } else if (IS_ENABLED(CONFIG_PPC64)) {
- /*
- * Check what is in the next instruction. We can see ld r2,40(r1), but
- * on first pass after boot we will see mflr r0.
- */
- if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) {
- pr_err("Fetching op failed.\n");
- return -EFAULT;
- }
-
- if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) {
- pr_err("Expected %08lx found %s\n", PPC_INST_LD_TOC, ppc_inst_as_str(op));
- return -EINVAL;
- }
- }
-
- /*
- * When using -mprofile-kernel or PPC32 there is no load to jump over.
- *
- * Otherwise our original call site looks like:
- *
- * bl <tramp>
- * ld r2,XX(r1)
- *
- * Milton Miller pointed out that we can not simply nop the branch.
- * If a task was preempted when calling a trace function, the nops
- * will remove the way to restore the TOC in r2 and the r2 TOC will
- * get corrupted.
- *
- * Use a b +8 to jump over the load.
- */
- if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32))
- pop = ppc_inst(PPC_RAW_NOP());
- else
- pop = ppc_inst(PPC_RAW_BRANCH(8)); /* b +8 */
-
- if (patch_instruction((u32 *)ip, pop)) {
- pr_err("Patching NOP failed.\n");
- return -EPERM;
- }
-
- return 0;
-}
-#else
-static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+static int is_bl_op(ppc_inst_t op)
{
- return 0;
+ return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
}
-#endif /* CONFIG_MODULES */
static unsigned long find_ftrace_tramp(unsigned long ip)
{
int i;
- /*
- * We have the compiler generated long_branch tramps at the end
- * and we prefer those
- */
- for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--)
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
if (!ftrace_tramps[i])
continue;
else if (is_offset_in_branch_range(ftrace_tramps[i] - ip))
@@ -230,448 +110,418 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
return 0;
}
-static int add_ftrace_tramp(unsigned long tramp)
+#ifdef CONFIG_MODULES
+static unsigned long ftrace_lookup_module_stub(unsigned long ip, unsigned long addr)
{
- int i;
+ struct module *mod = NULL;
- for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
- if (!ftrace_tramps[i]) {
- ftrace_tramps[i] = tramp;
- return 0;
- }
+ scoped_guard(rcu)
+ mod = __module_text_address(ip);
+ if (!mod)
+ pr_err("No module loaded at addr=%lx\n", ip);
- return -1;
+ return (addr == (unsigned long)ftrace_caller ? mod->arch.tramp : mod->arch.tramp_regs);
}
-
-/*
- * If this is a compiler generated long_branch trampoline (essentially, a
- * trampoline that has a branch to _mcount()), we re-write the branch to
- * instead go to ftrace_[regs_]caller() and note down the location of this
- * trampoline.
- */
-static int setup_mcount_compiler_tramp(unsigned long tramp)
+#else
+static unsigned long ftrace_lookup_module_stub(unsigned long ip, unsigned long addr)
{
- int i;
- ppc_inst_t op;
- unsigned long ptr;
-
- /* Is this a known long jump tramp? */
- for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
- if (ftrace_tramps[i] == tramp)
- return 0;
-
- /* New trampoline -- read where this goes */
- if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) {
- pr_debug("Fetching opcode failed.\n");
- return -1;
- }
+ return 0;
+}
+#endif
- /* Is this a 24 bit branch? */
- if (!is_b_op(op)) {
- pr_debug("Trampoline is not a long branch tramp.\n");
- return -1;
- }
+static unsigned long ftrace_get_ool_stub(struct dyn_ftrace *rec)
+{
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ return rec->arch.ool_stub;
+#else
+ BUILD_BUG();
+#endif
+}
- /* lets find where the pointer goes */
- ptr = find_bl_target(tramp, op);
+static int ftrace_get_call_inst(struct dyn_ftrace *rec, unsigned long addr, ppc_inst_t *call_inst)
+{
+ unsigned long ip;
+ unsigned long stub;
- if (ptr != ppc_global_function_entry((void *)_mcount)) {
- pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr);
- return -1;
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+ ip = ftrace_get_ool_stub(rec) + MCOUNT_INSN_SIZE; /* second instruction in stub */
+ else
+ ip = rec->ip;
+
+ if (!is_offset_in_branch_range(addr - ip) && addr != FTRACE_ADDR &&
+ addr != FTRACE_REGS_ADDR) {
+ /* This can only happen with ftrace direct */
+ if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS)) {
+ pr_err("0x%lx (0x%lx): Unexpected target address 0x%lx\n",
+ ip, rec->ip, addr);
+ return -EINVAL;
+ }
+ addr = FTRACE_ADDR;
}
- /* Let's re-write the tramp to go to ftrace_[regs_]caller */
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
- ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
+ if (is_offset_in_branch_range(addr - ip))
+ /* Within range */
+ stub = addr;
+ else if (core_kernel_text(ip))
+ /* We would be branching to one of our ftrace stubs */
+ stub = find_ftrace_tramp(ip);
else
- ptr = ppc_global_function_entry((void *)ftrace_caller);
-
- if (patch_branch((u32 *)tramp, ptr, 0)) {
- pr_debug("REL24 out of range!\n");
- return -1;
- }
+ stub = ftrace_lookup_module_stub(ip, addr);
- if (add_ftrace_tramp(tramp)) {
- pr_debug("No tramp locations left\n");
- return -1;
+ if (!stub) {
+ pr_err("0x%lx (0x%lx): No ftrace stubs reachable\n", ip, rec->ip);
+ return -EINVAL;
}
+ *call_inst = ftrace_create_branch_inst(ip, stub, 1);
return 0;
}
-static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
+static int ftrace_init_ool_stub(struct module *mod, struct dyn_ftrace *rec)
{
- unsigned long tramp, ip = rec->ip;
- ppc_inst_t op;
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ static int ool_stub_text_index, ool_stub_text_end_index, ool_stub_inittext_index;
+ int ret = 0, ool_stub_count, *ool_stub_index;
+ ppc_inst_t inst;
+ /*
+ * See ftrace_entry.S if changing the below instruction sequence, as we rely on
+ * decoding the last branch instruction here to recover the correct function ip.
+ */
+ struct ftrace_ool_stub *ool_stub, ool_stub_template = {
+ .insn = {
+ PPC_RAW_MFLR(_R0),
+ PPC_RAW_NOP(), /* bl ftrace_caller */
+ PPC_RAW_MTLR(_R0),
+ PPC_RAW_NOP() /* b rec->ip + 4 */
+ }
+ };
- /* Read where this goes */
- if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
- pr_err("Fetching opcode failed.\n");
- return -EFAULT;
- }
+ WARN_ON(rec->arch.ool_stub);
- /* Make sure that that this is still a 24bit jump */
- if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
+ if (is_kernel_inittext(rec->ip)) {
+ ool_stub = ftrace_ool_stub_inittext;
+ ool_stub_index = &ool_stub_inittext_index;
+ ool_stub_count = ftrace_ool_stub_inittext_count;
+ } else if (is_kernel_text(rec->ip)) {
+ /*
+ * ftrace records are sorted, so we first use up the stub area within .text
+ * (ftrace_ool_stub_text) before using the area at the end of .text
+ * (ftrace_ool_stub_text_end), unless the stub is out of range of the record.
+ */
+ if (ool_stub_text_index >= ftrace_ool_stub_text_count ||
+ !is_offset_in_branch_range((long)rec->ip -
+ (long)&ftrace_ool_stub_text[ool_stub_text_index])) {
+ ool_stub = ftrace_ool_stub_text_end;
+ ool_stub_index = &ool_stub_text_end_index;
+ ool_stub_count = ftrace_ool_stub_text_end_count;
+ } else {
+ ool_stub = ftrace_ool_stub_text;
+ ool_stub_index = &ool_stub_text_index;
+ ool_stub_count = ftrace_ool_stub_text_count;
+ }
+#ifdef CONFIG_MODULES
+ } else if (mod) {
+ ool_stub = mod->arch.ool_stubs;
+ ool_stub_index = &mod->arch.ool_stub_index;
+ ool_stub_count = mod->arch.ool_stub_count;
+#endif
+ } else {
return -EINVAL;
}
- /* Let's find where the pointer goes */
- tramp = find_bl_target(ip, op);
+ ool_stub += (*ool_stub_index)++;
- pr_devel("ip:%lx jumps to %lx", ip, tramp);
+ if (WARN_ON(*ool_stub_index > ool_stub_count))
+ return -EINVAL;
- if (setup_mcount_compiler_tramp(tramp)) {
- /* Are other trampolines reachable? */
- if (!find_ftrace_tramp(ip)) {
- pr_err("No ftrace trampolines reachable from %ps\n",
- (void *)ip);
- return -EINVAL;
- }
+ if (!is_offset_in_branch_range((long)rec->ip - (long)&ool_stub->insn[0]) ||
+ !is_offset_in_branch_range((long)(rec->ip + MCOUNT_INSN_SIZE) -
+ (long)&ool_stub->insn[3])) {
+ pr_err("%s: ftrace ool stub out of range (%p -> %p).\n",
+ __func__, (void *)rec->ip, (void *)&ool_stub->insn[0]);
+ return -EINVAL;
}
- if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) {
- pr_err("Patching NOP failed.\n");
- return -EPERM;
- }
+ rec->arch.ool_stub = (unsigned long)&ool_stub->insn[0];
- return 0;
+ /* bl ftrace_caller */
+ if (!mod)
+ ret = ftrace_get_call_inst(rec, (unsigned long)ftrace_caller, &inst);
+#ifdef CONFIG_MODULES
+ else
+ /*
+ * We can't use ftrace_get_call_inst() since that uses
+ * __module_text_address(rec->ip) to look up the module.
+ * But, since the module is not fully formed at this stage,
+ * the lookup fails. We know the target though, so generate
+ * the branch inst directly.
+ */
+ inst = ftrace_create_branch_inst(ftrace_get_ool_stub(rec) + MCOUNT_INSN_SIZE,
+ mod->arch.tramp, 1);
+#endif
+ ool_stub_template.insn[1] = ppc_inst_val(inst);
+
+ /* b rec->ip + 4 */
+ if (!ret && create_branch(&inst, &ool_stub->insn[3], rec->ip + MCOUNT_INSN_SIZE, 0))
+ return -EINVAL;
+ ool_stub_template.insn[3] = ppc_inst_val(inst);
+
+ if (!ret)
+ ret = patch_instructions((u32 *)ool_stub, (u32 *)&ool_stub_template,
+ sizeof(ool_stub_template), false);
+
+ return ret;
+#else /* !CONFIG_PPC_FTRACE_OUT_OF_LINE */
+ BUILD_BUG();
+#endif
}
-int ftrace_make_nop(struct module *mod,
- struct dyn_ftrace *rec, unsigned long addr)
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+static const struct ftrace_ops *powerpc_rec_get_ops(struct dyn_ftrace *rec)
{
- unsigned long ip = rec->ip;
- ppc_inst_t old, new;
+ const struct ftrace_ops *ops = NULL;
- /*
- * If the calling address is more that 24 bits away,
- * then we had to use a trampoline to make the call.
- * Otherwise just update the call site.
- */
- if (test_24bit_addr(ip, addr)) {
- /* within range */
- old = ftrace_call_replace(ip, addr, 1);
- new = ppc_inst(PPC_RAW_NOP());
- return ftrace_modify_code(ip, old, new);
- } else if (core_kernel_text(ip)) {
- return __ftrace_make_nop_kernel(rec, addr);
- } else if (!IS_ENABLED(CONFIG_MODULES)) {
- return -EINVAL;
+ if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
+ ops = ftrace_find_unique_ops(rec);
+ WARN_ON_ONCE(!ops);
}
- /*
- * Out of range jumps are called from modules.
- * We should either already have a pointer to the module
- * or it has been passed in.
- */
- if (!rec->arch.mod) {
- if (!mod) {
- pr_err("No module loaded addr=%lx\n", addr);
- return -EFAULT;
- }
- rec->arch.mod = mod;
- } else if (mod) {
- if (mod != rec->arch.mod) {
- pr_err("Record mod %p not equal to passed in mod %p\n",
- rec->arch.mod, mod);
- return -EINVAL;
- }
- /* nothing to do if mod == rec->arch.mod */
- } else
- mod = rec->arch.mod;
+ if (!ops)
+ ops = &ftrace_list_ops;
- return __ftrace_make_nop(mod, rec, addr);
+ return ops;
}
-#ifdef CONFIG_MODULES
-/*
- * Examine the existing instructions for __ftrace_make_call.
- * They should effectively be a NOP, and follow formal constraints,
- * depending on the ABI. Return false if they don't.
- */
-static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
+static int ftrace_rec_set_ops(struct dyn_ftrace *rec, const struct ftrace_ops *ops)
{
- if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1))
- return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) &&
- ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC));
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+ return patch_ulong((void *)(ftrace_get_ool_stub(rec) - sizeof(unsigned long)),
+ (unsigned long)ops);
else
- return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP()));
+ return patch_ulong((void *)(rec->ip - MCOUNT_INSN_SIZE - sizeof(unsigned long)),
+ (unsigned long)ops);
}
-static int
-__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec)
{
- ppc_inst_t op[2];
- void *ip = (void *)rec->ip;
- unsigned long entry, ptr, tramp;
- struct module *mod = rec->arch.mod;
-
- /* read where this goes */
- if (copy_inst_from_kernel_nofault(op, ip))
- return -EFAULT;
-
- if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1) &&
- copy_inst_from_kernel_nofault(op + 1, ip + 4))
- return -EFAULT;
-
- if (!expected_nop_sequence(ip, op[0], op[1])) {
- pr_err("Unexpected call sequence at %p: %s %s\n",
- ip, ppc_inst_as_str(op[0]), ppc_inst_as_str(op[1]));
- return -EINVAL;
- }
-
- /* If we never set up ftrace trampoline(s), then bail */
- if (!mod->arch.tramp ||
- (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) {
- pr_err("No ftrace trampoline\n");
- return -EINVAL;
- }
-
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS)
- tramp = mod->arch.tramp_regs;
- else
- tramp = mod->arch.tramp;
-
- if (module_trampoline_target(mod, tramp, &ptr)) {
- pr_err("Failed to get trampoline target\n");
- return -EFAULT;
- }
-
- pr_devel("trampoline target %lx", ptr);
-
- entry = ppc_global_function_entry((void *)addr);
- /* This should match what was called */
- if (ptr != entry) {
- pr_err("addr %lx does not match expected %lx\n", ptr, entry);
- return -EINVAL;
- }
-
- if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
+ return ftrace_rec_set_ops(rec, &ftrace_nop_ops);
+}
- return 0;
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec)
+{
+ return ftrace_rec_set_ops(rec, powerpc_rec_get_ops(rec));
}
#else
-static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; }
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; }
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
{
- return 0;
+ /* This should never be called since we override ftrace_replace_code() */
+ WARN_ON(1);
+ return -EINVAL;
}
-#endif /* CONFIG_MODULES */
+#endif
-static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
- ppc_inst_t op;
- void *ip = (void *)rec->ip;
- unsigned long tramp, entry, ptr;
-
- /* Make sure we're being asked to patch branch to a known ftrace addr */
- entry = ppc_global_function_entry((void *)ftrace_caller);
- ptr = ppc_global_function_entry((void *)addr);
-
- if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
- entry = ppc_global_function_entry((void *)ftrace_regs_caller);
+ ppc_inst_t old, new;
+ unsigned long ip = rec->ip;
+ int ret = 0;
- if (ptr != entry) {
- pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
+ /* This can only ever be called during module load */
+ if (WARN_ON(!IS_ENABLED(CONFIG_MODULES) || core_kernel_text(ip)))
return -EINVAL;
- }
- /* Make sure we have a nop */
- if (copy_inst_from_kernel_nofault(&op, ip)) {
- pr_err("Unable to read ftrace location %p\n", ip);
- return -EFAULT;
+ old = ppc_inst(PPC_RAW_NOP());
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+ ip = ftrace_get_ool_stub(rec) + MCOUNT_INSN_SIZE; /* second instruction in stub */
+ ret = ftrace_get_call_inst(rec, (unsigned long)ftrace_caller, &old);
}
- if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) {
- pr_err("Unexpected call sequence at %p: %s\n", ip, ppc_inst_as_str(op));
- return -EINVAL;
- }
+ ret |= ftrace_get_call_inst(rec, addr, &new);
- tramp = find_ftrace_tramp((unsigned long)ip);
- if (!tramp) {
- pr_err("No ftrace trampolines reachable from %ps\n", ip);
- return -EINVAL;
- }
+ if (!ret)
+ ret = ftrace_modify_code(ip, old, new);
- if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
- pr_err("Error patching branch to ftrace tramp!\n");
- return -EINVAL;
- }
+ ret = ftrace_rec_update_ops(rec);
+ if (ret)
+ return ret;
- return 0;
+ if (!ret && IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+ ret = ftrace_modify_code(rec->ip, ppc_inst(PPC_RAW_NOP()),
+ ppc_inst(PPC_RAW_BRANCH((long)ftrace_get_ool_stub(rec) - (long)rec->ip)));
+
+ return ret;
}
-int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
{
- unsigned long ip = rec->ip;
- ppc_inst_t old, new;
-
/*
- * If the calling address is more that 24 bits away,
- * then we had to use a trampoline to make the call.
- * Otherwise just update the call site.
+ * This should never be called since we override ftrace_replace_code(),
+ * as well as ftrace_init_nop()
*/
- if (test_24bit_addr(ip, addr)) {
- /* within range */
- old = ppc_inst(PPC_RAW_NOP());
- new = ftrace_call_replace(ip, addr, 1);
- return ftrace_modify_code(ip, old, new);
- } else if (core_kernel_text(ip)) {
- return __ftrace_make_call_kernel(rec, addr);
- } else if (!IS_ENABLED(CONFIG_MODULES)) {
- /* We should not get here without modules */
- return -EINVAL;
- }
-
- /*
- * Out of range jumps are called from modules.
- * Being that we are converting from nop, it had better
- * already have a module defined.
- */
- if (!rec->arch.mod) {
- pr_err("No module loaded\n");
- return -EINVAL;
- }
-
- return __ftrace_make_call(rec, addr);
+ WARN_ON(1);
+ return -EINVAL;
}
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-#ifdef CONFIG_MODULES
-static int
-__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
- unsigned long addr)
+void ftrace_replace_code(int enable)
{
- ppc_inst_t op;
- unsigned long ip = rec->ip;
- unsigned long entry, ptr, tramp;
- struct module *mod = rec->arch.mod;
-
- /* If we never set up ftrace trampolines, then bail */
- if (!mod->arch.tramp || !mod->arch.tramp_regs) {
- pr_err("No ftrace trampoline\n");
- return -EINVAL;
- }
+ ppc_inst_t old, new, call_inst, new_call_inst;
+ ppc_inst_t nop_inst = ppc_inst(PPC_RAW_NOP());
+ unsigned long ip, new_addr, addr;
+ struct ftrace_rec_iter *iter;
+ struct dyn_ftrace *rec;
+ int ret = 0, update;
- /* read where this goes */
- if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
- pr_err("Fetching opcode failed.\n");
- return -EFAULT;
- }
-
- /* Make sure that that this is still a 24bit jump */
- if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
- return -EINVAL;
- }
+ for_ftrace_rec_iter(iter) {
+ rec = ftrace_rec_iter_record(iter);
+ ip = rec->ip;
- /* lets find where the pointer goes */
- tramp = find_bl_target(ip, op);
- entry = ppc_global_function_entry((void *)old_addr);
+ if (rec->flags & FTRACE_FL_DISABLED && !(rec->flags & FTRACE_FL_ENABLED))
+ continue;
- pr_devel("ip:%lx jumps to %lx", ip, tramp);
+ addr = ftrace_get_addr_curr(rec);
+ new_addr = ftrace_get_addr_new(rec);
+ update = ftrace_update_record(rec, enable);
- if (tramp != entry) {
- /* old_addr is not within range, so we must have used a trampoline */
- if (module_trampoline_target(mod, tramp, &ptr)) {
- pr_err("Failed to get trampoline target\n");
- return -EFAULT;
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) && update != FTRACE_UPDATE_IGNORE) {
+ ip = ftrace_get_ool_stub(rec) + MCOUNT_INSN_SIZE;
+ ret = ftrace_get_call_inst(rec, (unsigned long)ftrace_caller, &nop_inst);
+ if (ret)
+ goto out;
}
- pr_devel("trampoline target %lx", ptr);
-
- /* This should match what was called */
- if (ptr != entry) {
- pr_err("addr %lx does not match expected %lx\n", ptr, entry);
- return -EINVAL;
+ switch (update) {
+ case FTRACE_UPDATE_IGNORE:
+ default:
+ continue;
+ case FTRACE_UPDATE_MODIFY_CALL:
+ ret = ftrace_get_call_inst(rec, new_addr, &new_call_inst);
+ ret |= ftrace_get_call_inst(rec, addr, &call_inst);
+ ret |= ftrace_rec_update_ops(rec);
+ old = call_inst;
+ new = new_call_inst;
+ break;
+ case FTRACE_UPDATE_MAKE_NOP:
+ ret = ftrace_get_call_inst(rec, addr, &call_inst);
+ ret |= ftrace_rec_set_nop_ops(rec);
+ old = call_inst;
+ new = nop_inst;
+ break;
+ case FTRACE_UPDATE_MAKE_CALL:
+ ret = ftrace_get_call_inst(rec, new_addr, &call_inst);
+ ret |= ftrace_rec_update_ops(rec);
+ old = nop_inst;
+ new = call_inst;
+ break;
}
- }
- /* The new target may be within range */
- if (test_24bit_addr(ip, addr)) {
- /* within range */
- if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
+ if (!ret)
+ ret = ftrace_modify_code(ip, old, new);
- return 0;
- }
+ if (!ret && IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) &&
+ (update == FTRACE_UPDATE_MAKE_NOP || update == FTRACE_UPDATE_MAKE_CALL)) {
+ /* Update the actual ftrace location */
+ call_inst = ppc_inst(PPC_RAW_BRANCH((long)ftrace_get_ool_stub(rec) -
+ (long)rec->ip));
+ nop_inst = ppc_inst(PPC_RAW_NOP());
+ ip = rec->ip;
- if (rec->flags & FTRACE_FL_REGS)
- tramp = mod->arch.tramp_regs;
- else
- tramp = mod->arch.tramp;
+ if (update == FTRACE_UPDATE_MAKE_NOP)
+ ret = ftrace_modify_code(ip, call_inst, nop_inst);
+ else
+ ret = ftrace_modify_code(ip, nop_inst, call_inst);
- if (module_trampoline_target(mod, tramp, &ptr)) {
- pr_err("Failed to get trampoline target\n");
- return -EFAULT;
- }
-
- pr_devel("trampoline target %lx", ptr);
+ if (ret)
+ goto out;
+ }
- entry = ppc_global_function_entry((void *)addr);
- /* This should match what was called */
- if (ptr != entry) {
- pr_err("addr %lx does not match expected %lx\n", ptr, entry);
- return -EINVAL;
+ if (ret)
+ goto out;
}
- if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
-
- return 0;
-}
-#else
-static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
-{
- return 0;
+out:
+ if (ret)
+ ftrace_bug(ret, rec);
+ return;
}
-#endif
-int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
- unsigned long addr)
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
{
- unsigned long ip = rec->ip;
+ unsigned long addr, ip = rec->ip;
ppc_inst_t old, new;
-
- /*
- * If the calling address is more that 24 bits away,
- * then we had to use a trampoline to make the call.
- * Otherwise just update the call site.
- */
- if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) {
- /* within range */
- old = ftrace_call_replace(ip, old_addr, 1);
- new = ftrace_call_replace(ip, addr, 1);
- return ftrace_modify_code(ip, old, new);
- } else if (core_kernel_text(ip)) {
- /*
- * We always patch out of range locations to go to the regs
- * variant, so there is nothing to do here
- */
- return 0;
- } else if (!IS_ENABLED(CONFIG_MODULES)) {
- /* We should not get here without modules */
+ int ret = 0;
+
+ /* Verify instructions surrounding the ftrace location */
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+ /* Expect nops */
+ if (!IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+ ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_NOP()));
+ if (!ret)
+ ret = ftrace_validate_inst(ip, ppc_inst(PPC_RAW_NOP()));
+ } else if (IS_ENABLED(CONFIG_PPC32)) {
+ /* Expected sequence: 'mflr r0', 'stw r0,4(r1)', 'bl _mcount' */
+ ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
+ if (ret)
+ return ret;
+ ret = ftrace_modify_code(ip - 4, ppc_inst(PPC_RAW_STW(_R0, _R1, 4)),
+ ppc_inst(PPC_RAW_NOP()));
+ } else if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
+ /* Expected sequence: 'mflr r0', ['std r0,16(r1)'], 'bl _mcount' */
+ ret = ftrace_read_inst(ip - 4, &old);
+ if (!ret && !ppc_inst_equal(old, ppc_inst(PPC_RAW_MFLR(_R0)))) {
+ /* Gcc v5.x emit the additional 'std' instruction, gcc v6.x don't */
+ ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
+ if (ret)
+ return ret;
+ ret = ftrace_modify_code(ip - 4, ppc_inst(PPC_RAW_STD(_R0, _R1, 16)),
+ ppc_inst(PPC_RAW_NOP()));
+ }
+ } else {
return -EINVAL;
}
- /*
- * Out of range jumps are called from modules.
- */
- if (!rec->arch.mod) {
- pr_err("No module loaded\n");
+ if (ret)
+ return ret;
+
+ /* Set up out-of-line stub */
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+ return ftrace_init_ool_stub(mod, rec);
+
+ /* Nop-out the ftrace location */
+ new = ppc_inst(PPC_RAW_NOP());
+ addr = MCOUNT_ADDR;
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+ /* we instead patch-in the 'mflr r0' */
+ old = ppc_inst(PPC_RAW_NOP());
+ new = ppc_inst(PPC_RAW_MFLR(_R0));
+ ret = ftrace_modify_code(ip - 4, old, new);
+ } else if (is_offset_in_branch_range(addr - ip)) {
+ /* Within range */
+ old = ftrace_create_branch_inst(ip, addr, 1);
+ ret = ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip) || (IS_ENABLED(CONFIG_MODULES) && mod)) {
+ /*
+ * We would be branching to a linker-generated stub, or to the module _mcount
+ * stub. Let's just confirm we have a 'bl' here.
+ */
+ ret = ftrace_read_inst(ip, &old);
+ if (ret)
+ return ret;
+ if (!is_bl_op(old)) {
+ pr_err("0x%lx: expected (bl) != found (%08lx)\n", ip, ppc_inst_as_ulong(old));
+ return -EINVAL;
+ }
+ ret = patch_instruction((u32 *)ip, new);
+ } else {
return -EINVAL;
}
- return __ftrace_modify_call(rec, old_addr, addr);
+ return ret;
}
-#endif
int ftrace_update_ftrace_func(ftrace_func_t func)
{
@@ -679,15 +529,22 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
ppc_inst_t old, new;
int ret;
+ /*
+ * When using CALL_OPS, the function to call is associated with the
+ * call site, and we don't have a global function pointer to update.
+ */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+ return 0;
+
old = ppc_inst_read((u32 *)&ftrace_call);
- new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
ret = ftrace_modify_code(ip, old, new);
/* Also update the regs callback function */
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) {
ip = (unsigned long)(&ftrace_regs_call);
old = ppc_inst_read((u32 *)&ftrace_regs_call);
- new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
ret = ftrace_modify_code(ip, old, new);
}
@@ -703,11 +560,6 @@ void arch_ftrace_update_code(int command)
ftrace_modify_all_code(command);
}
-#ifdef CONFIG_PPC64
-#define PACATOC offsetof(struct paca_struct, kernel_toc)
-
-extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
-
void ftrace_free_init_tramp(void)
{
int i;
@@ -719,84 +571,91 @@ void ftrace_free_init_tramp(void)
}
}
-int __init ftrace_dyn_arch_init(void)
+static void __init add_ftrace_tramp(unsigned long tramp)
{
int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_tramps[i]) {
+ ftrace_tramps[i] = tramp;
+ return;
+ }
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
+ unsigned long addr = FTRACE_REGS_ADDR;
+ long reladdr;
+ int i;
u32 stub_insns[] = {
- PPC_RAW_LD(_R12, _R13, PACATOC),
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ /* pla r12,addr */
+ PPC_PREFIX_MLS | __PPC_PRFX_R(1),
+ PPC_INST_PADDI | ___PPC_RT(_R12),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
+#elif defined(CONFIG_PPC64)
+ PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernel_toc)),
PPC_RAW_ADDIS(_R12, _R12, 0),
PPC_RAW_ADDI(_R12, _R12, 0),
PPC_RAW_MTCTR(_R12),
PPC_RAW_BCTR()
+#else
+ PPC_RAW_LIS(_R12, 0),
+ PPC_RAW_ADDI(_R12, _R12, 0),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
+#endif
};
- unsigned long addr;
- long reladdr;
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
- addr = ppc_global_function_entry((void *)ftrace_regs_caller);
- else
- addr = ppc_global_function_entry((void *)ftrace_caller);
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
+ for (i = 0; i < 2; i++) {
+ reladdr = addr - (unsigned long)tramp[i];
- reladdr = addr - kernel_toc_addr();
+ if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) {
+ pr_err("Address of %ps out of range of pcrel address.\n",
+ (void *)addr);
+ return -1;
+ }
- if (reladdr >= SZ_2G || reladdr < -(long)SZ_2G) {
- pr_err("Address of %ps out of range of kernel_toc.\n",
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][0] |= IMM_H18(reladdr);
+ tramp[i][1] |= IMM_L(reladdr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
+ } else if (IS_ENABLED(CONFIG_PPC64)) {
+ reladdr = addr - kernel_toc_addr();
+
+ if (reladdr >= (long)SZ_2G || reladdr < -(long long)SZ_2G) {
+ pr_err("Address of %ps out of range of kernel_toc.\n",
(void *)addr);
- return -1;
- }
+ return -1;
+ }
- for (i = 0; i < 2; i++) {
- memcpy(tramp[i], stub_insns, sizeof(stub_insns));
- tramp[i][1] |= PPC_HA(reladdr);
- tramp[i][2] |= PPC_LO(reladdr);
- add_ftrace_tramp((unsigned long)tramp[i]);
+ for (i = 0; i < 2; i++) {
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][1] |= PPC_HA(reladdr);
+ tramp[i][2] |= PPC_LO(reladdr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
+ } else {
+ for (i = 0; i < 2; i++) {
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][0] |= PPC_HA(addr);
+ tramp[i][1] |= PPC_LO(addr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
}
return 0;
}
-#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-extern void ftrace_graph_call(void);
-extern void ftrace_graph_stub(void);
-
-static int ftrace_modify_ftrace_graph_caller(bool enable)
-{
- unsigned long ip = (unsigned long)(&ftrace_graph_call);
- unsigned long addr = (unsigned long)(&ftrace_graph_caller);
- unsigned long stub = (unsigned long)(&ftrace_graph_stub);
- ppc_inst_t old, new;
-
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
- return 0;
-
- old = ftrace_call_replace(ip, enable ? stub : addr, 0);
- new = ftrace_call_replace(ip, enable ? addr : stub, 0);
-
- return ftrace_modify_code(ip, old, new);
-}
-
-int ftrace_enable_ftrace_graph_caller(void)
-{
- return ftrace_modify_ftrace_graph_caller(true);
-}
-
-int ftrace_disable_ftrace_graph_caller(void)
-{
- return ftrace_modify_ftrace_graph_caller(false);
-}
-
-/*
- * Hook the return address and push it in the stack of return addrs
- * in current thread info. Return the address we want to divert to.
- */
-static unsigned long
-__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp)
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
{
- unsigned long return_hooker;
- int bit;
+ unsigned long sp = arch_ftrace_regs(fregs)->regs.gpr[1];
if (unlikely(ftrace_graph_is_dead()))
goto out;
@@ -804,41 +663,10 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp
if (unlikely(atomic_read(&current->tracing_graph_pause)))
goto out;
- bit = ftrace_test_recursion_trylock(ip, parent);
- if (bit < 0)
- goto out;
+ if (!function_graph_enter_regs(parent_ip, ip, 0, (unsigned long *)sp, fregs))
+ parent_ip = ppc_function_entry(return_to_handler);
- return_hooker = ppc_function_entry(return_to_handler);
-
- if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
- parent = return_hooker;
-
- ftrace_test_recursion_unlock(bit);
out:
- return parent;
+ arch_ftrace_regs(fregs)->regs.link = parent_ip;
}
-
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
-void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op, struct ftrace_regs *fregs)
-{
- fregs->regs.link = __prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]);
-}
-#else
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
- unsigned long sp)
-{
- return __prepare_ftrace_return(parent, ip, sp);
-}
-#endif
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_PPC64_ELF_ABI_V1
-char *arch_ftrace_match_adjust(char *str, const char *search)
-{
- if (str[0] == '.' && search[0] != '.')
- return str + 1;
- else
- return str;
-}
-#endif /* CONFIG_PPC64_ELF_ABI_V1 */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
new file mode 100644
index 000000000000..5c6e545d1708
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -0,0 +1,832 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box.
+ *
+ * Added function graph tracer code, taken from x86 that was written
+ * by Frederic Weisbecker, and ported to PPC by Steven Rostedt.
+ *
+ */
+
+#define pr_fmt(fmt) "ftrace-powerpc: " fmt
+
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/cacheflush.h>
+#include <asm/text-patching.h>
+#include <asm/ftrace.h>
+#include <asm/syscall.h>
+#include <asm/inst.h>
+
+/*
+ * We generally only have a single long_branch tramp and at most 2 or 3 plt
+ * tramps generated. But, we don't use the plt tramps currently. We also allot
+ * 2 tramps after .text and .init.text. So, we only end up with around 3 usable
+ * tramps in total. Set aside 8 just to be sure.
+ */
+#define NUM_FTRACE_TRAMPS 8
+static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
+
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+ return addr;
+}
+
+static ppc_inst_t
+ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
+{
+ ppc_inst_t op;
+
+ addr = ppc_function_entry((void *)addr);
+
+ /* if (link) set op to 'bl' else 'b' */
+ create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
+
+ return op;
+}
+
+static inline int
+ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+{
+ ppc_inst_t replaced;
+
+ /*
+ * Note:
+ * We are paranoid about modifying text, as if a bug was to happen, it
+ * could cause us to read or write to someplace that could cause harm.
+ * Carefully read and modify the code with probe_kernel_*(), and make
+ * sure what we read is what we expected it to be before modifying it.
+ */
+
+ /* read the text we want to modify */
+ if (copy_inst_from_kernel_nofault(&replaced, (void *)ip))
+ return -EFAULT;
+
+ /* Make sure it is what we expect it to be */
+ if (!ppc_inst_equal(replaced, old)) {
+ pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip,
+ ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old));
+ return -EINVAL;
+ }
+
+ /* replace the text with the new text */
+ return patch_instruction((u32 *)ip, new);
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+ addr = ppc_function_entry((void *)addr);
+
+ return is_offset_in_branch_range(addr - ip);
+}
+
+static int is_bl_op(ppc_inst_t op)
+{
+ return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
+}
+
+static int is_b_op(ppc_inst_t op)
+{
+ return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0);
+}
+
+static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
+{
+ int offset;
+
+ offset = PPC_LI(ppc_inst_val(op));
+ /* make it signed */
+ if (offset & 0x02000000)
+ offset |= 0xfe000000;
+
+ return ip + (long)offset;
+}
+
+#ifdef CONFIG_MODULES
+static struct module *ftrace_lookup_module(struct dyn_ftrace *rec)
+{
+ struct module *mod;
+
+ scoped_guard(rcu)
+ mod = __module_text_address(rec->ip);
+ if (!mod)
+ pr_err("No module loaded at addr=%lx\n", rec->ip);
+
+ return mod;
+}
+
+static int
+__ftrace_make_nop(struct module *mod,
+ struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long entry, ptr, tramp;
+ unsigned long ip = rec->ip;
+ ppc_inst_t op, pop;
+
+ if (!mod) {
+ mod = ftrace_lookup_module(rec);
+ if (!mod)
+ return -EINVAL;
+ }
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* lets find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
+ if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) {
+ pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+ return -EFAULT;
+ }
+
+ /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
+ if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) &&
+ !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
+ pr_err("Unexpected instruction %08lx around bl _mcount\n",
+ ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+ } else if (IS_ENABLED(CONFIG_PPC64)) {
+ /*
+ * Check what is in the next instruction. We can see ld r2,40(r1), but
+ * on first pass after boot we will see mflr r0.
+ */
+ if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) {
+ pr_err("Fetching op failed.\n");
+ return -EFAULT;
+ }
+
+ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) {
+ pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC,
+ ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+ }
+
+ /*
+ * When using -mprofile-kernel or PPC32 there is no load to jump over.
+ *
+ * Otherwise our original call site looks like:
+ *
+ * bl <tramp>
+ * ld r2,XX(r1)
+ *
+ * Milton Miller pointed out that we can not simply nop the branch.
+ * If a task was preempted when calling a trace function, the nops
+ * will remove the way to restore the TOC in r2 and the r2 TOC will
+ * get corrupted.
+ *
+ * Use a b +8 to jump over the load.
+ */
+ if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32))
+ pop = ppc_inst(PPC_RAW_NOP());
+ else
+ pop = ppc_inst(PPC_RAW_BRANCH(8)); /* b +8 */
+
+ if (patch_instruction((u32 *)ip, pop)) {
+ pr_err("Patching NOP failed.\n");
+ return -EPERM;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static unsigned long find_ftrace_tramp(unsigned long ip)
+{
+ int i;
+
+ /*
+ * We have the compiler generated long_branch tramps at the end
+ * and we prefer those
+ */
+ for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--)
+ if (!ftrace_tramps[i])
+ continue;
+ else if (is_offset_in_branch_range(ftrace_tramps[i] - ip))
+ return ftrace_tramps[i];
+
+ return 0;
+}
+
+static int add_ftrace_tramp(unsigned long tramp)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_tramps[i]) {
+ ftrace_tramps[i] = tramp;
+ return 0;
+ }
+
+ return -1;
+}
+
+/*
+ * If this is a compiler generated long_branch trampoline (essentially, a
+ * trampoline that has a branch to _mcount()), we re-write the branch to
+ * instead go to ftrace_[regs_]caller() and note down the location of this
+ * trampoline.
+ */
+static int setup_mcount_compiler_tramp(unsigned long tramp)
+{
+ int i;
+ ppc_inst_t op;
+ unsigned long ptr;
+
+ /* Is this a known long jump tramp? */
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (ftrace_tramps[i] == tramp)
+ return 0;
+
+ /* New trampoline -- read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) {
+ pr_debug("Fetching opcode failed.\n");
+ return -1;
+ }
+
+ /* Is this a 24 bit branch? */
+ if (!is_b_op(op)) {
+ pr_debug("Trampoline is not a long branch tramp.\n");
+ return -1;
+ }
+
+ /* lets find where the pointer goes */
+ ptr = find_bl_target(tramp, op);
+
+ if (ptr != ppc_global_function_entry((void *)_mcount)) {
+ pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr);
+ return -1;
+ }
+
+ /* Let's re-write the tramp to go to ftrace_[regs_]caller */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
+ else
+ ptr = ppc_global_function_entry((void *)ftrace_caller);
+
+ if (patch_branch((u32 *)tramp, ptr, 0)) {
+ pr_debug("REL24 out of range!\n");
+ return -1;
+ }
+
+ if (add_ftrace_tramp(tramp)) {
+ pr_debug("No tramp locations left\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long tramp, ip = rec->ip;
+ ppc_inst_t op;
+
+ /* Read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* Let's find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (setup_mcount_compiler_tramp(tramp)) {
+ /* Are other trampolines reachable? */
+ if (!find_ftrace_tramp(ip)) {
+ pr_err("No ftrace trampolines reachable from %ps\n",
+ (void *)ip);
+ return -EINVAL;
+ }
+ }
+
+ if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) {
+ pr_err("Patching NOP failed.\n");
+ return -EPERM;
+ }
+
+ return 0;
+}
+
+int ftrace_make_nop(struct module *mod,
+ struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ old = ftrace_call_replace(ip, addr, 1);
+ new = ppc_inst(PPC_RAW_NOP());
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ return __ftrace_make_nop_kernel(rec, addr);
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ return -EINVAL;
+ }
+
+ return __ftrace_make_nop(mod, rec, addr);
+}
+
+#ifdef CONFIG_MODULES
+/*
+ * Examine the existing instructions for __ftrace_make_call.
+ * They should effectively be a NOP, and follow formal constraints,
+ * depending on the ABI. Return false if they don't.
+ */
+static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
+{
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP()));
+ else
+ return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) &&
+ ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC));
+}
+
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ ppc_inst_t op[2];
+ void *ip = (void *)rec->ip;
+ unsigned long entry, ptr, tramp;
+ struct module *mod = ftrace_lookup_module(rec);
+
+ if (!mod)
+ return -EINVAL;
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(op, ip))
+ return -EFAULT;
+
+ if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
+ copy_inst_from_kernel_nofault(op + 1, ip + 4))
+ return -EFAULT;
+
+ if (!expected_nop_sequence(ip, op[0], op[1])) {
+ pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip,
+ ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1]));
+ return -EINVAL;
+ }
+
+ /* If we never set up ftrace trampoline(s), then bail */
+ if (!mod->arch.tramp ||
+ (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) {
+ pr_err("No ftrace trampoline\n");
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS)
+ tramp = mod->arch.tramp_regs;
+ else
+ tramp = mod->arch.tramp;
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+ ppc_inst_t op;
+ void *ip = (void *)rec->ip;
+ unsigned long tramp, entry, ptr;
+
+ /* Make sure we're being asked to patch branch to a known ftrace addr */
+ entry = ppc_global_function_entry((void *)ftrace_caller);
+ ptr = ppc_global_function_entry((void *)addr);
+
+ if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ entry = ppc_global_function_entry((void *)ftrace_regs_caller);
+
+ if (ptr != entry) {
+ pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
+ return -EINVAL;
+ }
+
+ /* Make sure we have a nop */
+ if (copy_inst_from_kernel_nofault(&op, ip)) {
+ pr_err("Unable to read ftrace location %p\n", ip);
+ return -EFAULT;
+ }
+
+ if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) {
+ pr_err("Unexpected call sequence at %p: %08lx\n",
+ ip, ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ tramp = find_ftrace_tramp((unsigned long)ip);
+ if (!tramp) {
+ pr_err("No ftrace trampolines reachable from %ps\n", ip);
+ return -EINVAL;
+ }
+
+ if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("Error patching branch to ftrace tramp!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ old = ppc_inst(PPC_RAW_NOP());
+ new = ftrace_call_replace(ip, addr, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ return __ftrace_make_call_kernel(rec, addr);
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ /* We should not get here without modules */
+ return -EINVAL;
+ }
+
+ return __ftrace_make_call(rec, addr);
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_MODULES
+static int
+__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ ppc_inst_t op;
+ unsigned long ip = rec->ip;
+ unsigned long entry, ptr, tramp;
+ struct module *mod = ftrace_lookup_module(rec);
+
+ if (!mod)
+ return -EINVAL;
+
+ /* If we never set up ftrace trampolines, then bail */
+ if (!mod->arch.tramp || !mod->arch.tramp_regs) {
+ pr_err("No ftrace trampoline\n");
+ return -EINVAL;
+ }
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* lets find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+ entry = ppc_global_function_entry((void *)old_addr);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (tramp != entry) {
+ /* old_addr is not within range, so we must have used a trampoline */
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+ }
+
+ /* The new target may be within range */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+ }
+
+ if (rec->flags & FTRACE_FL_REGS)
+ tramp = mod->arch.tramp_regs;
+ else
+ tramp = mod->arch.tramp;
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
+{
+ return 0;
+}
+#endif
+
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) {
+ /* within range */
+ old = ftrace_call_replace(ip, old_addr, 1);
+ new = ftrace_call_replace(ip, addr, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ /*
+ * We always patch out of range locations to go to the regs
+ * variant, so there is nothing to do here
+ */
+ return 0;
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ /* We should not get here without modules */
+ return -EINVAL;
+ }
+
+ return __ftrace_modify_call(rec, old_addr, addr);
+}
+#endif
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+ unsigned long ip = (unsigned long)(&ftrace_call);
+ ppc_inst_t old, new;
+ int ret;
+
+ old = ppc_inst_read((u32 *)&ftrace_call);
+ new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ ret = ftrace_modify_code(ip, old, new);
+
+ /* Also update the regs callback function */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) {
+ ip = (unsigned long)(&ftrace_regs_call);
+ old = ppc_inst_read((u32 *)&ftrace_regs_call);
+ new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ ret = ftrace_modify_code(ip, old, new);
+ }
+
+ return ret;
+}
+
+/*
+ * Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
+void arch_ftrace_update_code(int command)
+{
+ ftrace_modify_all_code(command);
+}
+
+#ifdef CONFIG_PPC64
+#define PACATOC offsetof(struct paca_struct, kernel_toc)
+
+extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+
+void ftrace_free_init_tramp(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS && ftrace_tramps[i]; i++)
+ if (ftrace_tramps[i] == (unsigned long)ftrace_tramp_init) {
+ ftrace_tramps[i] = 0;
+ return;
+ }
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+ int i;
+ unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
+ u32 stub_insns[] = {
+ PPC_RAW_LD(_R12, _R13, PACATOC),
+ PPC_RAW_ADDIS(_R12, _R12, 0),
+ PPC_RAW_ADDI(_R12, _R12, 0),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
+ };
+ unsigned long addr;
+ long reladdr;
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ addr = ppc_global_function_entry((void *)ftrace_regs_caller);
+ else
+ addr = ppc_global_function_entry((void *)ftrace_caller);
+
+ reladdr = addr - kernel_toc_addr();
+
+ if (reladdr >= SZ_2G || reladdr < -(long)SZ_2G) {
+ pr_err("Address of %ps out of range of kernel_toc.\n",
+ (void *)addr);
+ return -1;
+ }
+
+ for (i = 0; i < 2; i++) {
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][1] |= PPC_HA(reladdr);
+ tramp[i][2] |= PPC_LO(reladdr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
+
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+extern void ftrace_graph_call(void);
+extern void ftrace_graph_stub(void);
+
+static int ftrace_modify_ftrace_graph_caller(bool enable)
+{
+ unsigned long ip = (unsigned long)(&ftrace_graph_call);
+ unsigned long addr = (unsigned long)(&ftrace_graph_caller);
+ unsigned long stub = (unsigned long)(&ftrace_graph_stub);
+ ppc_inst_t old, new;
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
+ return 0;
+
+ old = ftrace_call_replace(ip, enable ? stub : addr, 0);
+ new = ftrace_call_replace(ip, enable ? addr : stub, 0);
+
+ return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+ return ftrace_modify_ftrace_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+ return ftrace_modify_ftrace_graph_caller(false);
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info. Return the address we want to divert to.
+ */
+static unsigned long
+__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp,
+ struct ftrace_regs *fregs)
+{
+ unsigned long return_hooker;
+
+ if (unlikely(ftrace_graph_is_dead()))
+ goto out;
+
+ if (unlikely(atomic_read(&current->tracing_graph_pause)))
+ goto out;
+
+ return_hooker = ppc_function_entry(return_to_handler);
+
+ if (!function_graph_enter_regs(parent, ip, 0, (unsigned long *)sp, fregs))
+ parent = return_hooker;
+
+out:
+ return parent;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+ arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip,
+ arch_ftrace_regs(fregs)->regs.gpr[1], fregs);
+}
+#else
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
+ unsigned long sp)
+{
+ return __prepare_ftrace_return(parent, ip, sp, NULL);
+}
+#endif
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+char *arch_ftrace_match_adjust(char *str, const char *search)
+{
+ if (str[0] == '.' && search[0] != '.')
+ return str + 1;
+ else
+ return str;
+}
+#endif /* CONFIG_PPC64_ELF_ABI_V1 */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
index 6708e24db0ab..a8a7f28404c8 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
@@ -3,12 +3,12 @@
* Split from ftrace_64.S
*/
+#include <linux/export.h>
#include <linux/magic.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ftrace.h>
#include <asm/ppc-opcode.h>
-#include <asm/export.h>
_GLOBAL_TOC(ftrace_caller)
lbz r3, PACA_FTRACE_ENABLED(r13)
@@ -65,3 +65,68 @@ _GLOBAL(ftrace_graph_caller)
addi r1, r1, 112
blr
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+.pushsection ".tramp.ftrace.text","aw",@progbits;
+.globl ftrace_tramp_text
+ftrace_tramp_text:
+ .space 32
+.popsection
+
+.pushsection ".tramp.ftrace.init","aw",@progbits;
+.globl ftrace_tramp_init
+ftrace_tramp_init:
+ .space 32
+.popsection
+
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
+ mflr r12
+ mtctr r12
+ mtlr r0
+ bctr
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(return_to_handler)
+ /* need to save return values */
+#ifdef CONFIG_PPC64
+ std r4, -32(r1)
+ std r3, -24(r1)
+ /* save TOC */
+ std r2, -16(r1)
+ std r31, -8(r1)
+ mr r31, r1
+ stdu r1, -112(r1)
+
+ /*
+ * We might be called from a module.
+ * Switch to our TOC to run inside the core kernel.
+ */
+ LOAD_PACA_TOC()
+#else
+ stwu r1, -16(r1)
+ stw r3, 8(r1)
+ stw r4, 12(r1)
+#endif
+
+ bl ftrace_return_to_handler
+ nop
+
+ /* return value has real return address */
+ mtlr r3
+
+#ifdef CONFIG_PPC64
+ ld r1, 0(r1)
+ ld r4, -32(r1)
+ ld r3, -24(r1)
+ ld r2, -16(r1)
+ ld r31, -8(r1)
+#else
+ lwz r3, 8(r1)
+ lwz r4, 12(r1)
+ addi r1, r1, 16
+#endif
+
+ /* Jump back to real return address */
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
new file mode 100644
index 000000000000..3565c67fc638
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -0,0 +1,471 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Split from ftrace_64.S
+ */
+
+#include <linux/export.h>
+#include <linux/magic.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ppc-opcode.h>
+#include <asm/thread_info.h>
+#include <asm/bug.h>
+#include <asm/ptrace.h>
+
+/*
+ *
+ * ftrace_caller()/ftrace_regs_caller() is the function that replaces _mcount()
+ * when ftrace is active.
+ *
+ * We arrive here after a function A calls function B, and we are the trace
+ * function for B. When we enter r1 points to A's stack frame, B has not yet
+ * had a chance to allocate one yet.
+ *
+ * Additionally r2 may point either to the TOC for A, or B, depending on
+ * whether B did a TOC setup sequence before calling us.
+ *
+ * On entry the LR points back to the _mcount() call site, and r0 holds the
+ * saved LR as it was on entry to B, ie. the original return address at the
+ * call site in A.
+ *
+ * Our job is to save the register state into a struct pt_regs (on the stack)
+ * and then arrange for the ftrace function to be called.
+ */
+.macro ftrace_regs_entry allregs
+ /* Create a minimal stack frame for representing B */
+ PPC_STLU r1, -STACK_FRAME_MIN_SIZE(r1)
+
+ /* Create our stack frame + pt_regs */
+ PPC_STLU r1,-SWITCH_FRAME_SIZE(r1)
+
+ .if \allregs == 1
+ SAVE_GPRS(11, 12, r1)
+ .endif
+
+ /* Get the _mcount() call site out of LR */
+ mflr r11
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ /* Load the ftrace_op */
+ PPC_LL r12, -(MCOUNT_INSN_SIZE*2 + SZL)(r11)
+
+ /* Load direct_call from the ftrace_op */
+ PPC_LL r12, FTRACE_OPS_DIRECT_CALL(r12)
+ PPC_LCMPI r12, 0
+ .if \allregs == 1
+ bne .Lftrace_direct_call_regs
+ .else
+ bne .Lftrace_direct_call
+ .endif
+#endif
+
+ /* Save the previous LR in pt_regs->link */
+ PPC_STL r0, _LINK(r1)
+ /* Also save it in A's stack frame */
+ PPC_STL r0, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE+LRSAVE(r1)
+
+ /* Save all gprs to pt_regs */
+ SAVE_GPR(0, r1)
+ SAVE_GPRS(3, 10, r1)
+
+#ifdef CONFIG_PPC64
+ /* Ok to continue? */
+ lbz r3, PACA_FTRACE_ENABLED(r13)
+ cmpdi r3, 0
+ beq ftrace_no_trace
+#endif
+
+ .if \allregs == 1
+ SAVE_GPR(2, r1)
+ SAVE_GPRS(13, 31, r1)
+ .else
+#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
+ SAVE_GPR(14, r1)
+#endif
+ .endif
+
+ /* Save previous stack pointer (r1) */
+ addi r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+ PPC_STL r8, GPR1(r1)
+
+ .if \allregs == 1
+ /* Load special regs for save below */
+ mfcr r7
+ mfmsr r8
+ mfctr r9
+ mfxer r10
+ .else
+ /* Clear MSR to flag as ftrace_caller versus frace_regs_caller */
+ li r8, 0
+ .endif
+
+#ifdef CONFIG_PPC64
+ /* Save callee's TOC in the ABI compliant location */
+ std r2, STK_GOT(r1)
+ LOAD_PACA_TOC() /* get kernel TOC in r2 */
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+ /* r11 points to the instruction following the call to ftrace */
+ PPC_LL r5, -(MCOUNT_INSN_SIZE*2 + SZL)(r11)
+ PPC_LL r12, FTRACE_OPS_FUNC(r5)
+ mtctr r12
+#else /* !CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS */
+#ifdef CONFIG_PPC64
+ LOAD_REG_ADDR(r3, function_trace_op)
+ ld r5,0(r3)
+#else
+ lis r3,function_trace_op@ha
+ lwz r5,function_trace_op@l(r3)
+#endif
+#endif
+
+ /* Save special regs */
+ PPC_STL r8, _MSR(r1)
+ .if \allregs == 1
+ PPC_STL r7, _CCR(r1)
+ PPC_STL r9, _CTR(r1)
+ PPC_STL r10, _XER(r1)
+ .endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ /* Clear orig_gpr3 to later detect ftrace_direct call */
+ li r7, 0
+ PPC_STL r7, ORIG_GPR3(r1)
+#endif
+
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ /* Save our real return address in nvr for return */
+ .if \allregs == 0
+ SAVE_GPR(15, r1)
+ .endif
+ mr r15, r11
+ /*
+ * We want the ftrace location in the function, but our lr (in r11)
+ * points at the 'mtlr r0' instruction in the out of line stub. To
+ * recover the ftrace location, we read the branch instruction in the
+ * stub, and adjust our lr by the branch offset.
+ *
+ * See ftrace_init_ool_stub() for the profile sequence.
+ */
+ lwz r8, MCOUNT_INSN_SIZE(r11)
+ slwi r8, r8, 6
+ srawi r8, r8, 6
+ add r3, r11, r8
+ /*
+ * Override our nip to point past the branch in the original function.
+ * This allows reliable stack trace and the ftrace stack tracer to work as-is.
+ */
+ addi r11, r3, MCOUNT_INSN_SIZE
+#else
+ /* Calculate ip from nip-4 into r3 for call below */
+ subi r3, r11, MCOUNT_INSN_SIZE
+#endif
+
+ /* Save NIP as pt_regs->nip */
+ PPC_STL r11, _NIP(r1)
+ /* Also save it in B's stackframe header for proper unwind */
+ PPC_STL r11, LRSAVE+SWITCH_FRAME_SIZE(r1)
+#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
+ mr r14, r11 /* remember old NIP */
+#endif
+
+ /* Put the original return address in r4 as parent_ip */
+ mr r4, r0
+
+ /* Load &pt_regs in r6 for call below */
+ addi r6, r1, STACK_INT_FRAME_REGS
+.endm
+
+.macro ftrace_regs_exit allregs
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ /* Check orig_gpr3 to detect ftrace_direct call */
+ PPC_LL r3, ORIG_GPR3(r1)
+ PPC_LCMPI cr1, r3, 0
+ mtctr r3
+#endif
+
+ /* Restore possibly modified LR */
+ PPC_LL r0, _LINK(r1)
+
+#ifndef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ /* Load ctr with the possibly modified NIP */
+ PPC_LL r3, _NIP(r1)
+#ifdef CONFIG_LIVEPATCH_64
+ cmpd r14, r3 /* has NIP been altered? */
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ beq cr1,2f
+ mtlr r3
+ b 3f
+#endif
+2: mtctr r3
+ mtlr r0
+3:
+
+#else /* !CONFIG_PPC_FTRACE_OUT_OF_LINE */
+ /* Load LR with the possibly modified NIP */
+ PPC_LL r3, _NIP(r1)
+ cmpd r14, r3 /* has NIP been altered? */
+ bne- 1f
+
+ mr r3, r15
+1: mtlr r3
+ .if \allregs == 0
+ REST_GPR(15, r1)
+ .endif
+#endif
+
+ /* Restore gprs */
+ .if \allregs == 1
+ REST_GPRS(2, 31, r1)
+ .else
+ REST_GPRS(3, 10, r1)
+#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
+ REST_GPR(14, r1)
+#endif
+ .endif
+
+#ifdef CONFIG_PPC64
+ /* Restore callee's TOC */
+ ld r2, STK_GOT(r1)
+#endif
+
+ /* Pop our stack frame */
+ addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+
+#ifdef CONFIG_LIVEPATCH_64
+ /* Based on the cmpd above, if the NIP was altered handle livepatch */
+ bne- livepatch_handler
+#endif
+
+ /* jump after _mcount site */
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ bnectr cr1
+#endif
+ /*
+ * Return with blr to keep the link stack balanced. The function profiling sequence
+ * uses 'mtlr r0' to restore LR.
+ */
+ blr
+#else
+ bctr
+#endif
+.endm
+
+.macro ftrace_regs_func allregs
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+ bctrl
+#else
+ .if \allregs == 1
+.globl ftrace_regs_call
+ftrace_regs_call:
+ .else
+.globl ftrace_call
+ftrace_call:
+ .endif
+ /* ftrace_call(r3, r4, r5, r6) */
+ bl ftrace_stub
+#endif
+.endm
+
+_GLOBAL(ftrace_regs_caller)
+ ftrace_regs_entry 1
+ ftrace_regs_func 1
+ ftrace_regs_exit 1
+
+_GLOBAL(ftrace_caller)
+ ftrace_regs_entry 0
+ ftrace_regs_func 0
+ ftrace_regs_exit 0
+
+_GLOBAL(ftrace_stub)
+ blr
+
+#ifdef CONFIG_PPC64
+ftrace_no_trace:
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ REST_GPR(3, r1)
+ addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+ blr
+#else
+ mflr r3
+ mtctr r3
+ REST_GPR(3, r1)
+ addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+ mtlr r0
+ bctr
+#endif
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+.Lftrace_direct_call_regs:
+ mtctr r12
+ REST_GPRS(11, 12, r1)
+ addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+ bctr
+.Lftrace_direct_call:
+ mtctr r12
+ addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+ bctr
+SYM_FUNC_START(ftrace_stub_direct_tramp)
+ blr
+SYM_FUNC_END(ftrace_stub_direct_tramp)
+#endif
+
+#ifdef CONFIG_LIVEPATCH_64
+ /*
+ * This function runs in the mcount context, between two functions. As
+ * such it can only clobber registers which are volatile and used in
+ * function linkage.
+ *
+ * We get here when a function A, calls another function B, but B has
+ * been live patched with a new function C.
+ *
+ * On entry, we have no stack frame and can not allocate one.
+ *
+ * With PPC_FTRACE_OUT_OF_LINE=n, on entry:
+ * - LR points back to the original caller (in A)
+ * - CTR holds the new NIP in C
+ * - r0, r11 & r12 are free
+ *
+ * With PPC_FTRACE_OUT_OF_LINE=y, on entry:
+ * - r0 points back to the original caller (in A)
+ * - LR holds the new NIP in C
+ * - r11 & r12 are free
+ */
+livepatch_handler:
+ ld r12, PACA_THREAD_INFO(r13)
+
+ /* Allocate 3 x 8 bytes */
+ ld r11, TI_livepatch_sp(r12)
+ addi r11, r11, 24
+ std r11, TI_livepatch_sp(r12)
+
+ /* Store stack end marker */
+ lis r12, STACK_END_MAGIC@h
+ ori r12, r12, STACK_END_MAGIC@l
+ std r12, -8(r11)
+
+ /* Save toc & real LR on livepatch stack */
+ std r2, -24(r11)
+#ifndef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ mflr r12
+ std r12, -16(r11)
+ mfctr r12
+#else
+ std r0, -16(r11)
+ mflr r12
+ /* Put ctr in r12 for global entry and branch there */
+ mtctr r12
+#endif
+ bctrl
+
+ /*
+ * Now we are returning from the patched function to the original
+ * caller A. We are free to use r11, r12 and we can use r2 until we
+ * restore it.
+ */
+
+ ld r12, PACA_THREAD_INFO(r13)
+
+ ld r11, TI_livepatch_sp(r12)
+
+ /* Check stack marker hasn't been trashed */
+ lis r2, STACK_END_MAGIC@h
+ ori r2, r2, STACK_END_MAGIC@l
+ ld r12, -8(r11)
+1: tdne r12, r2
+ EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
+
+ /* Restore LR & toc from livepatch stack */
+ ld r12, -16(r11)
+ mtlr r12
+ ld r2, -24(r11)
+
+ /* Pop livepatch stack frame */
+ ld r12, PACA_THREAD_INFO(r13)
+ subi r11, r11, 24
+ std r11, TI_livepatch_sp(r12)
+
+ /* Return to original caller of live patched function */
+ blr
+#endif /* CONFIG_LIVEPATCH */
+
+#ifndef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
+ mflr r12
+ mtctr r12
+ mtlr r0
+ bctr
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(return_to_handler)
+ /* need to save return values */
+#ifdef CONFIG_PPC64
+ std r4, -32(r1)
+ std r3, -24(r1)
+ /* save TOC */
+ std r2, -16(r1)
+ std r31, -8(r1)
+ mr r31, r1
+ stdu r1, -112(r1)
+
+ /*
+ * We might be called from a module.
+ * Switch to our TOC to run inside the core kernel.
+ */
+ LOAD_PACA_TOC()
+#else
+ stwu r1, -16(r1)
+ stw r3, 8(r1)
+ stw r4, 12(r1)
+#endif
+
+ bl ftrace_return_to_handler
+ nop
+
+ /* return value has real return address */
+ mtlr r3
+
+#ifdef CONFIG_PPC64
+ ld r1, 0(r1)
+ ld r4, -32(r1)
+ ld r3, -24(r1)
+ ld r2, -16(r1)
+ ld r31, -8(r1)
+#else
+ lwz r3, 8(r1)
+ lwz r4, 12(r1)
+ addi r1, r1, 16
+#endif
+
+ /* Jump back to real return address */
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+SYM_DATA(ftrace_ool_stub_text_count, .long CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE)
+
+SYM_START(ftrace_ool_stub_text, SYM_L_GLOBAL, .balign SZL)
+ .space CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE * FTRACE_OOL_STUB_SIZE
+SYM_CODE_END(ftrace_ool_stub_text)
+#endif
+
+.pushsection ".tramp.ftrace.text","aw",@progbits;
+.globl ftrace_tramp_text
+ftrace_tramp_text:
+ .space 32
+.popsection
+
+.pushsection ".tramp.ftrace.init","aw",@progbits;
+.globl ftrace_tramp_init
+ftrace_tramp_init:
+ .space 32
+.popsection
diff --git a/arch/powerpc/kernel/trace/ftrace_low.S b/arch/powerpc/kernel/trace/ftrace_low.S
deleted file mode 100644
index 0bddf1fa6636..000000000000
--- a/arch/powerpc/kernel/trace/ftrace_low.S
+++ /dev/null
@@ -1,78 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Split from entry_64.S
- */
-
-#include <linux/magic.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/ftrace.h>
-#include <asm/ppc-opcode.h>
-#include <asm/export.h>
-
-#ifdef CONFIG_PPC64
-.pushsection ".tramp.ftrace.text","aw",@progbits;
-.globl ftrace_tramp_text
-ftrace_tramp_text:
- .space 64
-.popsection
-
-.pushsection ".tramp.ftrace.init","aw",@progbits;
-.globl ftrace_tramp_init
-ftrace_tramp_init:
- .space 64
-.popsection
-#endif
-
-_GLOBAL(mcount)
-_GLOBAL(_mcount)
-EXPORT_SYMBOL(_mcount)
- mflr r12
- mtctr r12
- mtlr r0
- bctr
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-_GLOBAL(return_to_handler)
- /* need to save return values */
-#ifdef CONFIG_PPC64
- std r4, -32(r1)
- std r3, -24(r1)
- /* save TOC */
- std r2, -16(r1)
- std r31, -8(r1)
- mr r31, r1
- stdu r1, -112(r1)
-
- /*
- * We might be called from a module.
- * Switch to our TOC to run inside the core kernel.
- */
- ld r2, PACATOC(r13)
-#else
- stwu r1, -16(r1)
- stw r3, 8(r1)
- stw r4, 12(r1)
-#endif
-
- bl ftrace_return_to_handler
- nop
-
- /* return value has real return address */
- mtlr r3
-
-#ifdef CONFIG_PPC64
- ld r1, 0(r1)
- ld r4, -32(r1)
- ld r3, -24(r1)
- ld r2, -16(r1)
- ld r31, -8(r1)
-#else
- lwz r3, 8(r1)
- lwz r4, 12(r1)
- addi r1, r1, 16
-#endif
-
- /* Jump back to real return address */
- blr
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S
deleted file mode 100644
index 4fa23e260cab..000000000000
--- a/arch/powerpc/kernel/trace/ftrace_mprofile.S
+++ /dev/null
@@ -1,253 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Split from ftrace_64.S
- */
-
-#include <linux/magic.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/ftrace.h>
-#include <asm/ppc-opcode.h>
-#include <asm/export.h>
-#include <asm/thread_info.h>
-#include <asm/bug.h>
-#include <asm/ptrace.h>
-
-/*
- *
- * ftrace_caller()/ftrace_regs_caller() is the function that replaces _mcount()
- * when ftrace is active.
- *
- * We arrive here after a function A calls function B, and we are the trace
- * function for B. When we enter r1 points to A's stack frame, B has not yet
- * had a chance to allocate one yet.
- *
- * Additionally r2 may point either to the TOC for A, or B, depending on
- * whether B did a TOC setup sequence before calling us.
- *
- * On entry the LR points back to the _mcount() call site, and r0 holds the
- * saved LR as it was on entry to B, ie. the original return address at the
- * call site in A.
- *
- * Our job is to save the register state into a struct pt_regs (on the stack)
- * and then arrange for the ftrace function to be called.
- */
-.macro ftrace_regs_entry allregs
- /* Create our stack frame + pt_regs */
- PPC_STLU r1,-SWITCH_FRAME_SIZE(r1)
-
- /* Save all gprs to pt_regs */
- SAVE_GPR(0, r1)
- SAVE_GPRS(3, 10, r1)
-
-#ifdef CONFIG_PPC64
- /* Save the original return address in A's stack frame */
- std r0, LRSAVE+SWITCH_FRAME_SIZE(r1)
- /* Ok to continue? */
- lbz r3, PACA_FTRACE_ENABLED(r13)
- cmpdi r3, 0
- beq ftrace_no_trace
-#endif
-
- .if \allregs == 1
- SAVE_GPR(2, r1)
- SAVE_GPRS(11, 31, r1)
- .else
-#ifdef CONFIG_LIVEPATCH_64
- SAVE_GPR(14, r1)
-#endif
- .endif
-
- /* Save previous stack pointer (r1) */
- addi r8, r1, SWITCH_FRAME_SIZE
- PPC_STL r8, GPR1(r1)
-
- .if \allregs == 1
- /* Load special regs for save below */
- mfmsr r8
- mfctr r9
- mfxer r10
- mfcr r11
- .else
- /* Clear MSR to flag as ftrace_caller versus frace_regs_caller */
- li r8, 0
- .endif
-
- /* Get the _mcount() call site out of LR */
- mflr r7
- /* Save it as pt_regs->nip */
- PPC_STL r7, _NIP(r1)
- /* Save the read LR in pt_regs->link */
- PPC_STL r0, _LINK(r1)
-
-#ifdef CONFIG_PPC64
- /* Save callee's TOC in the ABI compliant location */
- std r2, STK_GOT(r1)
- ld r2,PACATOC(r13) /* get kernel TOC in r2 */
-
- addis r3,r2,function_trace_op@toc@ha
- addi r3,r3,function_trace_op@toc@l
- ld r5,0(r3)
-#else
- lis r3,function_trace_op@ha
- lwz r5,function_trace_op@l(r3)
-#endif
-
-#ifdef CONFIG_LIVEPATCH_64
- mr r14, r7 /* remember old NIP */
-#endif
-
- /* Calculate ip from nip-4 into r3 for call below */
- subi r3, r7, MCOUNT_INSN_SIZE
-
- /* Put the original return address in r4 as parent_ip */
- mr r4, r0
-
- /* Save special regs */
- PPC_STL r8, _MSR(r1)
- .if \allregs == 1
- PPC_STL r9, _CTR(r1)
- PPC_STL r10, _XER(r1)
- PPC_STL r11, _CCR(r1)
- .endif
-
- /* Load &pt_regs in r6 for call below */
- addi r6, r1, STACK_FRAME_OVERHEAD
-.endm
-
-.macro ftrace_regs_exit allregs
- /* Load ctr with the possibly modified NIP */
- PPC_LL r3, _NIP(r1)
- mtctr r3
-
-#ifdef CONFIG_LIVEPATCH_64
- cmpd r14, r3 /* has NIP been altered? */
-#endif
-
- /* Restore gprs */
- .if \allregs == 1
- REST_GPRS(2, 31, r1)
- .else
- REST_GPRS(3, 10, r1)
-#ifdef CONFIG_LIVEPATCH_64
- REST_GPR(14, r1)
-#endif
- .endif
-
- /* Restore possibly modified LR */
- PPC_LL r0, _LINK(r1)
- mtlr r0
-
-#ifdef CONFIG_PPC64
- /* Restore callee's TOC */
- ld r2, STK_GOT(r1)
-#endif
-
- /* Pop our stack frame */
- addi r1, r1, SWITCH_FRAME_SIZE
-
-#ifdef CONFIG_LIVEPATCH_64
- /* Based on the cmpd above, if the NIP was altered handle livepatch */
- bne- livepatch_handler
-#endif
- bctr /* jump after _mcount site */
-.endm
-
-_GLOBAL(ftrace_regs_caller)
- ftrace_regs_entry 1
- /* ftrace_call(r3, r4, r5, r6) */
-.globl ftrace_regs_call
-ftrace_regs_call:
- bl ftrace_stub
- nop
- ftrace_regs_exit 1
-
-_GLOBAL(ftrace_caller)
- ftrace_regs_entry 0
- /* ftrace_call(r3, r4, r5, r6) */
-.globl ftrace_call
-ftrace_call:
- bl ftrace_stub
- nop
- ftrace_regs_exit 0
-
-_GLOBAL(ftrace_stub)
- blr
-
-#ifdef CONFIG_PPC64
-ftrace_no_trace:
- mflr r3
- mtctr r3
- REST_GPR(3, r1)
- addi r1, r1, SWITCH_FRAME_SIZE
- mtlr r0
- bctr
-#endif
-
-#ifdef CONFIG_LIVEPATCH_64
- /*
- * This function runs in the mcount context, between two functions. As
- * such it can only clobber registers which are volatile and used in
- * function linkage.
- *
- * We get here when a function A, calls another function B, but B has
- * been live patched with a new function C.
- *
- * On entry:
- * - we have no stack frame and can not allocate one
- * - LR points back to the original caller (in A)
- * - CTR holds the new NIP in C
- * - r0, r11 & r12 are free
- */
-livepatch_handler:
- ld r12, PACA_THREAD_INFO(r13)
-
- /* Allocate 3 x 8 bytes */
- ld r11, TI_livepatch_sp(r12)
- addi r11, r11, 24
- std r11, TI_livepatch_sp(r12)
-
- /* Save toc & real LR on livepatch stack */
- std r2, -24(r11)
- mflr r12
- std r12, -16(r11)
-
- /* Store stack end marker */
- lis r12, STACK_END_MAGIC@h
- ori r12, r12, STACK_END_MAGIC@l
- std r12, -8(r11)
-
- /* Put ctr in r12 for global entry and branch there */
- mfctr r12
- bctrl
-
- /*
- * Now we are returning from the patched function to the original
- * caller A. We are free to use r11, r12 and we can use r2 until we
- * restore it.
- */
-
- ld r12, PACA_THREAD_INFO(r13)
-
- ld r11, TI_livepatch_sp(r12)
-
- /* Check stack marker hasn't been trashed */
- lis r2, STACK_END_MAGIC@h
- ori r2, r2, STACK_END_MAGIC@l
- ld r12, -8(r11)
-1: tdne r12, r2
- EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
-
- /* Restore LR & toc from livepatch stack */
- ld r12, -16(r11)
- mtlr r12
- ld r2, -24(r11)
-
- /* Pop livepatch stack frame */
- ld r12, PACA_THREAD_INFO(r13)
- subi r11, r11, 24
- std r11, TI_livepatch_sp(r12)
-
- /* Return to original caller of live patched function */
- blr
-#endif /* CONFIG_LIVEPATCH */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3aaa50e5c72f..cb8e9357383e 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -68,6 +68,7 @@
#include <asm/stacktrace.h>
#include <asm/nmi.h>
#include <asm/disassemble.h>
+#include <asm/udbg.h>
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -120,7 +121,7 @@ static void pmac_backlight_unblank(void)
props = &pmac_backlight->props;
props->brightness = props->max_brightness;
- props->power = FB_BLANK_UNBLANK;
+ props->power = BACKLIGHT_POWER_ON;
backlight_update_status(pmac_backlight);
}
mutex_unlock(&pmac_backlight_mutex);
@@ -156,7 +157,7 @@ static int die_owner = -1;
static unsigned int die_nest_count;
static int die_counter;
-extern void panic_flush_kmsg_start(void)
+void panic_flush_kmsg_start(void)
{
/*
* These are mostly taken from kernel/panic.c, but tries to do
@@ -169,7 +170,7 @@ extern void panic_flush_kmsg_start(void)
bust_spinlocks(1);
}
-extern void panic_flush_kmsg_end(void)
+void panic_flush_kmsg_end(void)
{
kmsg_dump(KMSG_DUMP_PANIC);
bust_spinlocks(0);
@@ -262,10 +263,9 @@ static int __die(const char *str, struct pt_regs *regs, long err)
{
printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
- printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n",
+ printk("%s PAGE_SIZE=%luK%s %s%s%s%s %s\n",
IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
PAGE_SIZE / 1024, get_mmu_str(),
- IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
@@ -403,7 +403,7 @@ noinstr void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
return;
if (!(regs->msr & MSR_HV))
return;
- if (regs->msr & MSR_PR)
+ if (user_mode(regs))
return;
/*
@@ -600,7 +600,7 @@ static inline int check_io_access(struct pt_regs *regs)
#define inst_length(reason) (((reason) & REASON_PREFIXED) ? 8 : 4)
-#if defined(CONFIG_E500)
+#if defined(CONFIG_PPC_E500)
int machine_check_e500mc(struct pt_regs *regs)
{
unsigned long mcsr = mfspr(SPRN_MCSR);
@@ -850,6 +850,19 @@ bail:
}
#ifdef CONFIG_PPC_BOOK3S_64
+DEFINE_INTERRUPT_HANDLER_RAW(machine_check_early_boot)
+{
+ udbg_printf("Machine check (early boot)\n");
+ udbg_printf("SRR0=0x%016lx SRR1=0x%016lx\n", regs->nip, regs->msr);
+ udbg_printf(" DAR=0x%016lx DSISR=0x%08lx\n", regs->dar, regs->dsisr);
+ udbg_printf(" LR=0x%016lx R1=0x%08lx\n", regs->link, regs->gpr[1]);
+ udbg_printf("------\n");
+ die("Machine check (early boot)", regs, SIGBUS);
+ for (;;)
+ ;
+ return 0;
+}
+
DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async)
{
__machine_check_exception(regs);
@@ -1144,12 +1157,13 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
* pretend we got a single-step exception. This was pointed out
* by Kumar Gala. -- paulus
*/
-static void emulate_single_step(struct pt_regs *regs)
+void emulate_single_step(struct pt_regs *regs)
{
if (single_stepping(regs))
__single_step_exception(regs);
}
+#ifdef CONFIG_PPC_FPU_REGS
static inline int __parse_fpscr(unsigned long fpscr)
{
int ret = FPE_FLTUNK;
@@ -1176,6 +1190,7 @@ static inline int __parse_fpscr(unsigned long fpscr)
return ret;
}
+#endif
static void parse_fpe(struct pt_regs *regs)
{
@@ -1423,10 +1438,12 @@ static int emulate_instruction(struct pt_regs *regs)
return -EINVAL;
}
+#ifdef CONFIG_GENERIC_BUG
int is_valid_bugaddr(unsigned long addr)
{
return is_kernel_addr(addr);
}
+#endif
#ifdef CONFIG_MATH_EMULATION
static int emulate_math(struct pt_regs *regs)
@@ -1492,18 +1509,17 @@ static void do_program_check(struct pt_regs *regs)
if (!is_kernel_addr(bugaddr) && !(regs->msr & MSR_IR))
bugaddr += PAGE_OFFSET;
- if (!(regs->msr & MSR_PR) && /* not user-mode */
+ if (!user_mode(regs) &&
report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
- const struct exception_table_entry *entry;
+ regs_add_return_ip(regs, 4);
+ return;
+ }
- entry = search_exception_tables(bugaddr);
- if (entry) {
- regs_set_return_ip(regs, extable_fixup(entry) + regs->nip - bugaddr);
- return;
- }
+ /* User mode considers other cases after enabling IRQs */
+ if (!user_mode(regs)) {
+ _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+ return;
}
- _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
- return;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (reason & REASON_TM) {
@@ -1536,16 +1552,44 @@ static void do_program_check(struct pt_regs *regs)
/*
* If we took the program check in the kernel skip down to sending a
- * SIGILL. The subsequent cases all relate to emulating instructions
- * which we should only do for userspace. We also do not want to enable
- * interrupts for kernel faults because that might lead to further
- * faults, and loose the context of the original exception.
+ * SIGILL. The subsequent cases all relate to user space, such as
+ * emulating instructions which we should only do for user space. We
+ * also do not want to enable interrupts for kernel faults because that
+ * might lead to further faults, and loose the context of the original
+ * exception.
*/
if (!user_mode(regs))
goto sigill;
interrupt_cond_local_irq_enable(regs);
+ /*
+ * (reason & REASON_TRAP) is mostly handled before enabling IRQs,
+ * except get_user_instr() can sleep so we cannot reliably inspect the
+ * current instruction in that context. Now that we know we are
+ * handling a user space trap and can sleep, we can check if the trap
+ * was a hashchk failure.
+ */
+ if (reason & REASON_TRAP) {
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+ ppc_inst_t insn;
+
+ if (get_user_instr(insn, (void __user *)regs->nip)) {
+ _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+ return;
+ }
+
+ if (ppc_inst_primary_opcode(insn) == 31 &&
+ get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
+ _exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
+ return;
+ }
+ }
+
+ _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+ return;
+ }
+
/* (reason & REASON_ILLEGAL) would be the obvious thing here,
* but there seems to be a hardware bug on the 405GP (RevD)
* that means ESR is sometimes set incorrectly - either to
@@ -1676,7 +1720,7 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
}
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
static void tm_unavailable(struct pt_regs *regs)
{
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -2085,7 +2129,7 @@ DEFINE_INTERRUPT_HANDLER(altivec_assist_exception)
}
#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_FSL_BOOKE
+#ifdef CONFIG_PPC_85xx
DEFINE_INTERRUPT_HANDLER(CacheLockingException)
{
unsigned long error_code = regs->dsisr;
@@ -2098,12 +2142,11 @@ DEFINE_INTERRUPT_HANDLER(CacheLockingException)
_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
return;
}
-#endif /* CONFIG_FSL_BOOKE */
+#endif /* CONFIG_PPC_85xx */
#ifdef CONFIG_SPE
DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException)
{
- extern int do_spe_mathemu(struct pt_regs *regs);
unsigned long spefscr;
int fpexc_mode;
int code = FPE_FLTUNK;
@@ -2153,7 +2196,6 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException)
DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
{
- extern int speround_handler(struct pt_regs *regs);
int err;
interrupt_cond_local_irq_enable(regs);
@@ -2201,22 +2243,11 @@ void __noreturn unrecoverable_exception(struct pt_regs *regs)
;
}
-#if defined(CONFIG_BOOKE_WDT) || defined(CONFIG_40x)
-/*
- * Default handler for a Watchdog exception,
- * spins until a reboot occurs
- */
-void __attribute__ ((weak)) WatchdogHandler(struct pt_regs *regs)
-{
- /* Generic WatchdogHandler, implement your own */
- mtspr(SPRN_TCR, mfspr(SPRN_TCR)&(~TCR_WIE));
- return;
-}
-
+#ifdef CONFIG_BOOKE_WDT
DEFINE_INTERRUPT_HANDLER_NMI(WatchdogException)
{
printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
- WatchdogHandler(regs);
+ mtspr(SPRN_TCR, mfspr(SPRN_TCR) & ~TCR_WIE);
return 0;
}
#endif
diff --git a/arch/powerpc/kernel/ucall.S b/arch/powerpc/kernel/ucall.S
index 07296bc39166..80a1f9a4300a 100644
--- a/arch/powerpc/kernel/ucall.S
+++ b/arch/powerpc/kernel/ucall.S
@@ -5,8 +5,8 @@
* Copyright 2019, IBM Corporation.
*
*/
+#include <linux/export.h>
#include <asm/ppc_asm.h>
-#include <asm/export.h>
_GLOBAL(ucall_norets)
EXPORT_SYMBOL_GPL(ucall_norets)
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index b1544b2f6321..862b22b2b616 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -36,12 +36,6 @@ void __init udbg_early_init(void)
#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_PANEL)
/* RTAS panel debug */
udbg_init_rtas_panel();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_CONSOLE)
- /* RTAS console debug */
- udbg_init_rtas_console();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE)
- /* Maple real mode debug */
- udbg_init_maple_realmode();
#elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
udbg_init_pas_realmode();
#elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX)
@@ -49,9 +43,6 @@ void __init udbg_early_init(void)
#elif defined(CONFIG_PPC_EARLY_DEBUG_44x)
/* PPC44x debug */
udbg_init_44x_as1();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_40x)
- /* PPC40x debug */
- udbg_init_40x_realmode();
#elif defined(CONFIG_PPC_EARLY_DEBUG_CPM)
udbg_init_cpm();
#elif defined(CONFIG_PPC_EARLY_DEBUG_USBGECKO)
@@ -67,6 +58,8 @@ void __init udbg_early_init(void)
udbg_init_debug_opal_raw();
#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_HVSI)
udbg_init_debug_opal_hvsi();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_16550)
+ udbg_init_debug_16550();
#endif
#ifdef CONFIG_PPC_EARLY_DEBUG
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index d3942de254c6..dfe8ed2192e8 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -7,7 +7,7 @@
#include <linux/types.h>
#include <asm/udbg.h>
#include <asm/io.h>
-#include <asm/reg_a2.h>
+#include <asm/early_ioremap.h>
extern u8 real_readb(volatile u8 __iomem *addr);
extern void real_writeb(u8 data, volatile u8 __iomem *addr);
@@ -205,29 +205,6 @@ void __init udbg_uart_init_mmio(void __iomem *addr, unsigned int stride)
udbg_use_uart();
}
-#ifdef CONFIG_PPC_MAPLE
-
-#define UDBG_UART_MAPLE_ADDR ((void __iomem *)0xf40003f8)
-
-static u8 udbg_uart_in_maple(unsigned int reg)
-{
- return real_readb(UDBG_UART_MAPLE_ADDR + reg);
-}
-
-static void udbg_uart_out_maple(unsigned int reg, u8 val)
-{
- real_writeb(val, UDBG_UART_MAPLE_ADDR + reg);
-}
-
-void __init udbg_init_maple_realmode(void)
-{
- udbg_uart_in = udbg_uart_in_maple;
- udbg_uart_out = udbg_uart_out_maple;
- udbg_use_uart();
-}
-
-#endif /* CONFIG_PPC_MAPLE */
-
#ifdef CONFIG_PPC_PASEMI
#define UDBG_UART_PAS_ADDR ((void __iomem *)0xfcff03f8UL)
@@ -274,64 +251,34 @@ void __init udbg_init_44x_as1(void)
#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
-#ifdef CONFIG_PPC_EARLY_DEBUG_40x
+#ifdef CONFIG_PPC_EARLY_DEBUG_16550
-static u8 udbg_uart_in_40x(unsigned int reg)
-{
- return real_readb((void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
- + reg);
-}
+static void __iomem *udbg_uart_early_addr;
-static void udbg_uart_out_40x(unsigned int reg, u8 val)
+void __init udbg_init_debug_16550(void)
{
- real_writeb(val, (void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
- + reg);
+ udbg_uart_early_addr = early_ioremap(CONFIG_PPC_EARLY_DEBUG_16550_PHYSADDR, 0x1000);
+ udbg_uart_init_mmio(udbg_uart_early_addr, CONFIG_PPC_EARLY_DEBUG_16550_STRIDE);
}
-void __init udbg_init_40x_realmode(void)
+static int __init udbg_init_debug_16550_ioremap(void)
{
- udbg_uart_in = udbg_uart_in_40x;
- udbg_uart_out = udbg_uart_out_40x;
- udbg_use_uart();
-}
-
-#endif /* CONFIG_PPC_EARLY_DEBUG_40x */
+ void __iomem *addr;
-#ifdef CONFIG_PPC_EARLY_DEBUG_MICROWATT
+ if (!udbg_uart_early_addr)
+ return 0;
-#define UDBG_UART_MW_ADDR ((void __iomem *)0xc0002000)
+ addr = ioremap(CONFIG_PPC_EARLY_DEBUG_16550_PHYSADDR, 0x1000);
+ if (WARN_ON(!addr))
+ return -ENOMEM;
-static u8 udbg_uart_in_isa300_rm(unsigned int reg)
-{
- uint64_t msr = mfmsr();
- uint8_t c;
-
- mtmsr(msr & ~(MSR_EE|MSR_DR));
- isync();
- eieio();
- c = __raw_rm_readb(UDBG_UART_MW_ADDR + (reg << 2));
- mtmsr(msr);
- isync();
- return c;
-}
+ udbg_uart_init_mmio(addr, CONFIG_PPC_EARLY_DEBUG_16550_STRIDE);
+ early_iounmap(udbg_uart_early_addr, 0x1000);
+ udbg_uart_early_addr = NULL;
-static void udbg_uart_out_isa300_rm(unsigned int reg, u8 val)
-{
- uint64_t msr = mfmsr();
-
- mtmsr(msr & ~(MSR_EE|MSR_DR));
- isync();
- eieio();
- __raw_rm_writeb(val, UDBG_UART_MW_ADDR + (reg << 2));
- mtmsr(msr);
- isync();
+ return 0;
}
-void __init udbg_init_debug_microwatt(void)
-{
- udbg_uart_in = udbg_uart_in_isa300_rm;
- udbg_uart_out = udbg_uart_out_isa300_rm;
- udbg_use_uart();
-}
+early_initcall(udbg_init_debug_16550_ioremap);
-#endif /* CONFIG_PPC_EARLY_DEBUG_MICROWATT */
+#endif /* CONFIG_PPC_EARLY_DEBUG_16550 */
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 0da287544054..219d67bcf747 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -16,9 +16,8 @@
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/security.h>
-#include <linux/memblock.h>
#include <linux/syscalls.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
#include <vdso/datapage.h>
#include <asm/syscall.h>
@@ -33,28 +32,15 @@
#include <asm/vdso_datapage.h>
#include <asm/setup.h>
+static_assert(__VDSO_PAGES == VDSO_NR_PAGES);
+
/* The alignment of the vDSO */
#define VDSO_ALIGNMENT (1 << 16)
extern char vdso32_start, vdso32_end;
extern char vdso64_start, vdso64_end;
-/*
- * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
- * Once the early boot kernel code no longer needs to muck around
- * with it, it will become dynamically allocated
- */
-static union {
- struct vdso_arch_data data;
- u8 page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_arch_data *vdso_data = &vdso_data_store.data;
-
-enum vvar_pages {
- VVAR_DATA_PAGE_OFFSET,
- VVAR_TIMENS_PAGE_OFFSET,
- VVAR_NR_PAGES,
-};
+long sys_ni_syscall(void);
static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
unsigned long text_size)
@@ -79,112 +65,33 @@ static int vdso64_mremap(const struct vm_special_mapping *sm, struct vm_area_str
return vdso_mremap(sm, new_vma, &vdso64_end - &vdso64_start);
}
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
- struct vm_area_struct *vma, struct vm_fault *vmf);
+static void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struct *vma)
+{
+ struct mm_struct *mm = vma->vm_mm;
-static struct vm_special_mapping vvar_spec __ro_after_init = {
- .name = "[vvar]",
- .fault = vvar_fault,
-};
+ /*
+ * close() is called for munmap() but also for mremap(). In the mremap()
+ * case the vdso pointer has already been updated by the mremap() hook
+ * above, so it must not be set to NULL here.
+ */
+ if (vma->vm_start != (unsigned long)mm->context.vdso)
+ return;
+
+ mm->context.vdso = NULL;
+}
static struct vm_special_mapping vdso32_spec __ro_after_init = {
.name = "[vdso]",
.mremap = vdso32_mremap,
+ .close = vdso_close,
};
static struct vm_special_mapping vdso64_spec __ro_after_init = {
.name = "[vdso]",
.mremap = vdso64_mremap,
+ .close = vdso_close,
};
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
- return ((struct vdso_arch_data *)vvar_page)->data;
-}
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a task
- * changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
- struct mm_struct *mm = task->mm;
- struct vm_area_struct *vma;
-
- mmap_read_lock(mm);
-
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- unsigned long size = vma->vm_end - vma->vm_start;
-
- if (vma_is_special_mapping(vma, &vvar_spec))
- zap_page_range(vma, vma->vm_start, size);
- }
-
- mmap_read_unlock(mm);
- return 0;
-}
-
-static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
-{
- if (likely(vma->vm_mm == current->mm))
- return current->nsproxy->time_ns->vvar_page;
-
- /*
- * VM_PFNMAP | VM_IO protect .fault() handler from being called
- * through interfaces like /proc/$pid/mem or
- * process_vm_{readv,writev}() as long as there's no .access()
- * in special_mapping_vmops.
- * For more details check_vma_flags() and __access_remote_vm()
- */
- WARN(1, "vvar_page accessed remotely");
-
- return NULL;
-}
-#else
-static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
-{
- return NULL;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
- struct vm_area_struct *vma, struct vm_fault *vmf)
-{
- struct page *timens_page = find_timens_vvar_page(vma);
- unsigned long pfn;
-
- switch (vmf->pgoff) {
- case VVAR_DATA_PAGE_OFFSET:
- if (timens_page)
- pfn = page_to_pfn(timens_page);
- else
- pfn = virt_to_pfn(vdso_data);
- break;
-#ifdef CONFIG_TIME_NS
- case VVAR_TIMENS_PAGE_OFFSET:
- /*
- * If a task belongs to a time namespace then a namespace
- * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
- * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
- * offset.
- * See also the comment near timens_setup_vdso_data().
- */
- if (!timens_page)
- return VM_FAULT_SIGBUS;
- pfn = virt_to_pfn(vdso_data);
- break;
-#endif /* CONFIG_TIME_NS */
- default:
- return VM_FAULT_SIGBUS;
- }
-
- return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
/*
* This is called from binfmt_elf, we create the special vma for the
* vDSO and insert it into the mm struct tree
@@ -193,51 +100,33 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
{
unsigned long vdso_size, vdso_base, mappings_size;
struct vm_special_mapping *vdso_spec;
- unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
+ unsigned long vvar_size = VDSO_NR_PAGES * PAGE_SIZE;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
if (is_32bit_task()) {
vdso_spec = &vdso32_spec;
vdso_size = &vdso32_end - &vdso32_start;
- vdso_base = VDSO32_MBASE;
} else {
vdso_spec = &vdso64_spec;
vdso_size = &vdso64_end - &vdso64_start;
- /*
- * On 64bit we don't have a preferred map address. This
- * allows get_unmapped_area to find an area near other mmaps
- * and most likely share a SLB entry.
- */
- vdso_base = 0;
}
mappings_size = vdso_size + vvar_size;
mappings_size += (VDSO_ALIGNMENT - 1) & PAGE_MASK;
/*
- * pick a base address for the vDSO in process space. We try to put it
- * at vdso_base which is the "natural" base for it, but we might fail
- * and end up putting it elsewhere.
+ * Pick a base address for the vDSO in process space.
* Add enough to the size so that the result can be aligned.
*/
- vdso_base = get_unmapped_area(NULL, vdso_base, mappings_size, 0, 0);
+ vdso_base = get_unmapped_area(NULL, 0, mappings_size, 0, 0);
if (IS_ERR_VALUE(vdso_base))
return vdso_base;
/* Add required alignment. */
vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
- /*
- * Put vDSO base into mm struct. We need to do this before calling
- * install_special_mapping or the perf counter mmap tracking code
- * will fail to recognise it as a vDSO.
- */
- mm->context.vdso = (void __user *)vdso_base + vvar_size;
-
- vma = _install_special_mapping(mm, vdso_base, vvar_size,
- VM_READ | VM_MAYREAD | VM_IO |
- VM_DONTDUMP | VM_PFNMAP, &vvar_spec);
+ vma = vdso_install_vvar_mapping(mm, vdso_base);
if (IS_ERR(vma))
return PTR_ERR(vma);
@@ -254,10 +143,15 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
vma = _install_special_mapping(mm, vdso_base + vvar_size, vdso_size,
VM_READ | VM_EXEC | VM_MAYREAD |
VM_MAYWRITE | VM_MAYEXEC, vdso_spec);
- if (IS_ERR(vma))
+ if (IS_ERR(vma)) {
do_munmap(mm, vdso_base, vvar_size, NULL);
+ return PTR_ERR(vma);
+ }
- return PTR_ERR_OR_ZERO(vma);
+ // Now that the mappings are in place, set the mm VDSO pointer
+ mm->context.vdso = (void __user *)vdso_base + vvar_size;
+
+ return 0;
}
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
@@ -271,8 +165,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
return -EINTR;
rc = __arch_setup_additional_pages(bprm, uses_interp);
- if (rc)
- mm->context.vdso = NULL;
mmap_write_unlock(mm);
return rc;
@@ -313,11 +205,11 @@ static void __init vdso_setup_syscall_map(void)
unsigned int i;
for (i = 0; i < NR_syscalls; i++) {
- if (sys_call_table[i] != (unsigned long)&sys_ni_syscall)
- vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+ if (sys_call_table[i] != (void *)&sys_ni_syscall)
+ vdso_k_arch_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
if (IS_ENABLED(CONFIG_COMPAT) &&
- compat_sys_call_table[i] != (unsigned long)&sys_ni_syscall)
- vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+ compat_sys_call_table[i] != (void *)&sys_ni_syscall)
+ vdso_k_arch_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
}
}
@@ -367,29 +259,10 @@ static struct page ** __init vdso_setup_pages(void *start, void *end)
static int __init vdso_init(void)
{
#ifdef CONFIG_PPC64
- /*
- * Fill up the "systemcfg" stuff for backward compatibility
- */
- strcpy((char *)vdso_data->eye_catcher, "SYSTEMCFG:PPC64");
- vdso_data->version.major = SYSTEMCFG_MAJOR;
- vdso_data->version.minor = SYSTEMCFG_MINOR;
- vdso_data->processor = mfspr(SPRN_PVR);
- /*
- * Fake the old platform number for pSeries and add
- * in LPAR bit if necessary
- */
- vdso_data->platform = 0x100;
- if (firmware_has_feature(FW_FEATURE_LPAR))
- vdso_data->platform |= 1;
- vdso_data->physicalMemorySize = memblock_phys_mem_size();
- vdso_data->dcache_size = ppc64_caches.l1d.size;
- vdso_data->dcache_line_size = ppc64_caches.l1d.line_size;
- vdso_data->icache_size = ppc64_caches.l1i.size;
- vdso_data->icache_line_size = ppc64_caches.l1i.line_size;
- vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
- vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
- vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
- vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
+ vdso_k_arch_data->dcache_block_size = ppc64_caches.l1d.block_size;
+ vdso_k_arch_data->icache_block_size = ppc64_caches.l1i.block_size;
+ vdso_k_arch_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
+ vdso_k_arch_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
#endif /* CONFIG_PPC64 */
vdso_setup_syscall_map();
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 096b0bf1335f..8834dfe9d727 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -2,31 +2,27 @@
# List of files in the vdso, has to be asm only for now
-ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24
-include $(srctree)/lib/vdso/Makefile
+# Include the generic Makefile to check the built vdso.
+include $(srctree)/lib/vdso/Makefile.include
obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o
obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o
+obj-vdso32 += getrandom-32.o vgetrandom-chacha-32.o
+obj-vdso64 += getrandom-64.o vgetrandom-chacha-64.o
+
ifneq ($(c-gettimeofday-y),)
CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y)
- CFLAGS_vgettimeofday-32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
- CFLAGS_vgettimeofday-32.o += $(call cc-option, -fno-stack-protector)
- CFLAGS_vgettimeofday-32.o += -DDISABLE_BRANCH_PROFILING
- CFLAGS_vgettimeofday-32.o += -ffreestanding -fasynchronous-unwind-tables
- CFLAGS_REMOVE_vgettimeofday-32.o = $(CC_FLAGS_FTRACE)
- CFLAGS_REMOVE_vgettimeofday-32.o += -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
- CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y)
- CFLAGS_vgettimeofday-64.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
- CFLAGS_vgettimeofday-64.o += $(call cc-option, -fno-stack-protector)
- CFLAGS_vgettimeofday-64.o += -DDISABLE_BRANCH_PROFILING
- CFLAGS_vgettimeofday-64.o += -ffreestanding -fasynchronous-unwind-tables
- CFLAGS_REMOVE_vgettimeofday-64.o = $(CC_FLAGS_FTRACE)
# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is
# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code
# generation is minimal, it will just use r29 instead.
- CFLAGS_vgettimeofday-64.o += $(call cc-option, -ffixed-r30)
+ CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y) $(call cc-option, -ffixed-r30)
+endif
+
+ifneq ($(c-getrandom-y),)
+ CFLAGS_vgetrandom-32.o += -include $(c-getrandom-y)
+ CFLAGS_vgetrandom-64.o += -include $(c-getrandom-y)
endif
# Build rules
@@ -37,51 +33,74 @@ else
VDSOCC := $(CC)
endif
-targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o
+targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o vgetrandom-32.o
+targets += crtsavres-32.o
obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
-targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o
+targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o vgetrandom-64.o
obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
-GCOV_PROFILE := n
-KCOV_INSTRUMENT := n
-UBSAN_SANITIZE := n
-KASAN_SANITIZE := n
-
-ccflags-y := -shared -fno-common -fno-builtin -nostdlib -Wl,--hash-style=both
-ccflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld)
-
-CC32FLAGS := -Wl,-soname=linux-vdso32.so.1 -m32
-AS32FLAGS := -D__VDSO32__ -s
+ccflags-y := -fno-common -fno-builtin -DBUILD_VDSO
+ccflags-y += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ccflags-y += $(call cc-option, -fno-stack-protector)
+ccflags-y += -DDISABLE_BRANCH_PROFILING
+ccflags-y += -ffreestanding -fasynchronous-unwind-tables
+ccflags-remove-y := $(CC_FLAGS_FTRACE)
+ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack $(CLANG_FLAGS)
+ldflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld)
+ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL)
+
+# Filter flags that clang will warn are unused for linking
+ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
+
+CC32FLAGS := -m32
+CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc -mpcrel
+ifdef CONFIG_CC_IS_CLANG
+# This flag is supported by clang for 64-bit but not 32-bit so it will cause
+# an unused command line flag warning for this file.
+CC32FLAGSREMOVE += -fno-stack-clash-protection
+# -mstack-protector-guard values from the 64-bit build are not valid for the
+# 32-bit one. clang validates the values passed to these arguments during
+# parsing, even when -fno-stack-protector is passed afterwards.
+CC32FLAGSREMOVE += -mstack-protector-guard%
+endif
+LD32FLAGS := -Wl,-soname=linux-vdso32.so.1
+AS32FLAGS := -D__VDSO32__
-CC64FLAGS := -Wl,-soname=linux-vdso64.so.1
-AS64FLAGS := -D__VDSO64__ -s
+LD64FLAGS := -Wl,-soname=linux-vdso64.so.1
+AS64FLAGS := -D__VDSO64__
targets += vdso32.lds
CPPFLAGS_vdso32.lds += -P -C -Upowerpc
targets += vdso64.lds
-CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+CPPFLAGS_vdso64.lds += -P -C
# link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE
+$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o $(obj)/vgetrandom-32.o $(obj)/crtsavres-32.o FORCE
$(call if_changed,vdso32ld_and_check)
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE
+$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o $(obj)/vgetrandom-64.o FORCE
$(call if_changed,vdso64ld_and_check)
# assembly rules for the .S files
$(obj-vdso32): %-32.o: %.S FORCE
$(call if_changed_dep,vdso32as)
+$(obj)/crtsavres-32.o: %-32.o: $(srctree)/arch/powerpc/lib/crtsavres.S FORCE
+ $(call if_changed_dep,vdso32as)
$(obj)/vgettimeofday-32.o: %-32.o: %.c FORCE
$(call if_changed_dep,vdso32cc)
+$(obj)/vgetrandom-32.o: %-32.o: %.c FORCE
+ $(call if_changed_dep,vdso32cc)
$(obj-vdso64): %-64.o: %.S FORCE
$(call if_changed_dep,vdso64as)
$(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE
$(call if_changed_dep,cc_o_c)
+$(obj)/vgetrandom-64.o: %-64.o: %.c FORCE
+ $(call if_changed_dep,cc_o_c)
# Generate VDSO offsets using helper script
-gen-vdso32sym := $(srctree)/$(src)/gen_vdso32_offsets.sh
+gen-vdso32sym := $(src)/gen_vdso32_offsets.sh
quiet_cmd_vdso32sym = VDSO32SYM $@
cmd_vdso32sym = $(NM) $< | $(gen-vdso32sym) | LC_ALL=C sort > $@
-gen-vdso64sym := $(srctree)/$(src)/gen_vdso64_offsets.sh
+gen-vdso64sym := $(src)/gen_vdso64_offsets.sh
quiet_cmd_vdso64sym = VDSO64SYM $@
cmd_vdso64sym = $(NM) $< | $(gen-vdso64sym) | LC_ALL=C sort > $@
@@ -92,13 +111,13 @@ include/generated/vdso64-offsets.h: $(obj)/vdso64.so.dbg FORCE
# actual build commands
quiet_cmd_vdso32ld_and_check = VDSO32L $@
- cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check)
+ cmd_vdso32ld_and_check = $(VDSOCC) $(ldflags-y) $(CC32FLAGS) $(LD32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
quiet_cmd_vdso32as = VDSO32A $@
cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) $(AS32FLAGS) -c -o $@ $<
quiet_cmd_vdso32cc = VDSO32C $@
- cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $<
+ cmd_vdso32cc = $(VDSOCC) $(filter-out $(CC32FLAGSREMOVE), $(c_flags)) $(CC32FLAGS) -c -o $@ $<
quiet_cmd_vdso64ld_and_check = VDSO64L $@
- cmd_vdso64ld_and_check = $(VDSOCC) $(c_flags) $(CC64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check)
+ cmd_vdso64ld_and_check = $(VDSOCC) $(ldflags-y) $(LD64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
quiet_cmd_vdso64as = VDSO64A $@
- cmd_vdso64as = $(VDSOCC) $(a_flags) $(CC64FLAGS) $(AS64FLAGS) -c -o $@ $<
+ cmd_vdso64as = $(VDSOCC) $(a_flags) $(AS64FLAGS) -c -o $@ $<
diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S
index d4e43ab2d5df..488d3ade11e6 100644
--- a/arch/powerpc/kernel/vdso/cacheflush.S
+++ b/arch/powerpc/kernel/vdso/cacheflush.S
@@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
#ifdef CONFIG_PPC64
mflr r12
.cfi_register lr,r12
- get_datapage r10
+ get_datapage r10 vdso_u_arch_data
mtlr r12
.cfi_restore lr
#endif
@@ -91,6 +91,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
3:
crclr cr0*4+so
sync
+ icbi 0,r1
isync
li r3,0
blr
diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S
index db8e167f0166..d23b2e8e2a34 100644
--- a/arch/powerpc/kernel/vdso/datapage.S
+++ b/arch/powerpc/kernel/vdso/datapage.S
@@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
mflr r12
.cfi_register lr,r12
mr. r4,r3
- get_datapage r3
+ get_datapage r3 vdso_u_arch_data
mtlr r12
#ifdef __powerpc64__
addi r3,r3,CFG_SYSCALL_MAP64
@@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- get_datapage r3
+ get_datapage r3 vdso_u_arch_data
#ifndef __powerpc64__
lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
#endif
diff --git a/arch/powerpc/kernel/vdso/getrandom.S b/arch/powerpc/kernel/vdso/getrandom.S
new file mode 100644
index 000000000000..a80d9fb436f7
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/getrandom.S
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Userland implementation of getrandom() for processes
+ * for use in the vDSO
+ *
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+/*
+ * The macro sets two stack frames, one for the caller and one for the callee
+ * because there are no requirement for the caller to set a stack frame when
+ * calling VDSO so it may have omitted to set one, especially on PPC64
+ */
+
+.macro cvdso_call funct
+ .cfi_startproc
+ PPC_STLU r1, -PPC_MIN_STKFRM(r1)
+ .cfi_adjust_cfa_offset PPC_MIN_STKFRM
+ mflr r0
+ PPC_STLU r1, -PPC_MIN_STKFRM(r1)
+ .cfi_adjust_cfa_offset PPC_MIN_STKFRM
+ PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+ .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF
+#ifdef __powerpc64__
+ PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+ .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
+#endif
+ bl CFUNC(DOTSYM(\funct))
+ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+#ifdef __powerpc64__
+ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+ .cfi_restore r2
+#endif
+ cmpwi r3, 0
+ mtlr r0
+ addi r1, r1, 2 * PPC_MIN_STKFRM
+ .cfi_restore lr
+ .cfi_def_cfa_offset 0
+ crclr so
+ bgelr+
+ crset so
+ neg r3, r3
+ blr
+ .cfi_endproc
+.endm
+
+ .text
+V_FUNCTION_BEGIN(__kernel_getrandom)
+ cvdso_call __c_kernel_getrandom
+V_FUNCTION_END(__kernel_getrandom)
diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S
index 0c4ecc8fec5a..79c967212444 100644
--- a/arch/powerpc/kernel/vdso/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso/gettimeofday.S
@@ -32,13 +32,12 @@
PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1)
.cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
#endif
- get_datapage r5
.ifeq \call_time
- addi r5, r5, VDSO_DATA_OFFSET
+ get_datapage r5 vdso_u_time_data
.else
- addi r4, r5, VDSO_DATA_OFFSET
+ get_datapage r4 vdso_u_time_data
.endif
- bl DOTSYM(\funct)
+ bl CFUNC(DOTSYM(\funct))
PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
#ifdef __powerpc64__
PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1)
@@ -114,16 +113,3 @@ V_FUNCTION_END(__kernel_clock_getres)
V_FUNCTION_BEGIN(__kernel_time)
cvdso_call __c_kernel_time call_time=1
V_FUNCTION_END(__kernel_time)
-
-/* Routines for restoring integer registers, called by the compiler. */
-/* Called with r11 pointing to the stack header word of the caller of the */
-/* function, just beyond the end of the integer restore area. */
-#ifndef __powerpc64__
-_GLOBAL(_restgpr_31_x)
-_GLOBAL(_rest32gpr_31_x)
- lwz r0,4(r11)
- lwz r31,-4(r11)
- mtlr r0
- mr r1,r11
- blr
-#endif
diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S
index e0d19d74455f..72a1012b8a20 100644
--- a/arch/powerpc/kernel/vdso/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso32.lds.S
@@ -6,6 +6,7 @@
#include <asm/vdso.h>
#include <asm/page.h>
#include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
#ifdef __LITTLE_ENDIAN__
OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common)
SECTIONS
{
- PROVIDE(_vdso_datapage = . - 2 * PAGE_SIZE);
+ VDSO_VVAR_SYMS
+
. = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
@@ -74,19 +76,22 @@ SECTIONS
.got : { *(.got) } :text
.plt : { *(.plt) }
+ .rela.dyn : { *(.rela .rela*) }
+
_end = .;
__end = .;
PROVIDE(end = .);
- STABS_DEBUG
DWARF_DEBUG
ELF_DETAILS
/DISCARD/ : {
*(.note.GNU-stack)
+ *(*.EMB.apuinfo)
+ *(.branch_lt)
*(.data .data.* .gnu.linkonce.d.* .sdata*)
*(.bss .sbss .dynbss .dynsbss)
- *(.got1)
+ *(.got1 .glink .iplt)
}
}
@@ -127,6 +132,7 @@ VERSION
#if defined(CONFIG_PPC64) || !defined(CONFIG_SMP)
__kernel_getcpu;
#endif
+ __kernel_getrandom;
local: *;
};
diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S
index 1a4a7bc4c815..32102a05eaa7 100644
--- a/arch/powerpc/kernel/vdso/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso64.lds.S
@@ -6,6 +6,7 @@
#include <asm/vdso.h>
#include <asm/page.h>
#include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
#ifdef __LITTLE_ENDIAN__
OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common64)
SECTIONS
{
- PROVIDE(_vdso_datapage = . - 2 * PAGE_SIZE);
+ VDSO_VVAR_SYMS
+
. = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
@@ -32,7 +34,7 @@ SECTIONS
. = ALIGN(16);
.text : {
*(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*)
- *(.sfpr .glink)
+ *(.sfpr)
} :text
PROVIDE(__etext = .);
PROVIDE(_etext = .);
@@ -69,23 +71,24 @@ SECTIONS
.eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
.eh_frame : { KEEP (*(.eh_frame)) } :text
.gcc_except_table : { *(.gcc_except_table) }
- .rela.dyn ALIGN(8) : { *(.rela.dyn) }
+ .rela.dyn ALIGN(8) : { *(.rela .rela*) }
.got ALIGN(8) : { *(.got .toc) }
_end = .;
PROVIDE(end = .);
- STABS_DEBUG
DWARF_DEBUG
ELF_DETAILS
/DISCARD/ : {
*(.note.GNU-stack)
+ *(*.EMB.apuinfo)
*(.branch_lt)
*(.data .data.* .gnu.linkonce.d.* .sdata*)
*(.bss .sbss .dynbss .dynsbss)
*(.opd)
+ *(.glink .iplt .plt)
}
}
@@ -122,6 +125,7 @@ VERSION
__kernel_sigtramp_rt64;
__kernel_getcpu;
__kernel_time;
+ __kernel_getrandom;
local: *;
};
diff --git a/arch/powerpc/kernel/vdso/vgetrandom-chacha.S b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S
new file mode 100644
index 000000000000..7f9061a9e8b4
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S
@@ -0,0 +1,365 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/ppc_asm.h>
+
+#define dst_bytes r3
+#define key r4
+#define counter r5
+#define nblocks r6
+
+#define idx_r0 r0
+#define val4 r4
+
+#define const0 0x61707865
+#define const1 0x3320646e
+#define const2 0x79622d32
+#define const3 0x6b206574
+
+#define key0 r5
+#define key1 r6
+#define key2 r7
+#define key3 r8
+#define key4 r9
+#define key5 r10
+#define key6 r11
+#define key7 r12
+
+#define counter0 r14
+#define counter1 r15
+
+#define state0 r16
+#define state1 r17
+#define state2 r18
+#define state3 r19
+#define state4 r20
+#define state5 r21
+#define state6 r22
+#define state7 r23
+#define state8 r24
+#define state9 r25
+#define state10 r26
+#define state11 r27
+#define state12 r28
+#define state13 r29
+#define state14 r30
+#define state15 r31
+
+.macro quarterround4 a1 b1 c1 d1 a2 b2 c2 d2 a3 b3 c3 d3 a4 b4 c4 d4
+ add \a1, \a1, \b1
+ add \a2, \a2, \b2
+ add \a3, \a3, \b3
+ add \a4, \a4, \b4
+ xor \d1, \d1, \a1
+ xor \d2, \d2, \a2
+ xor \d3, \d3, \a3
+ xor \d4, \d4, \a4
+ rotlwi \d1, \d1, 16
+ rotlwi \d2, \d2, 16
+ rotlwi \d3, \d3, 16
+ rotlwi \d4, \d4, 16
+ add \c1, \c1, \d1
+ add \c2, \c2, \d2
+ add \c3, \c3, \d3
+ add \c4, \c4, \d4
+ xor \b1, \b1, \c1
+ xor \b2, \b2, \c2
+ xor \b3, \b3, \c3
+ xor \b4, \b4, \c4
+ rotlwi \b1, \b1, 12
+ rotlwi \b2, \b2, 12
+ rotlwi \b3, \b3, 12
+ rotlwi \b4, \b4, 12
+ add \a1, \a1, \b1
+ add \a2, \a2, \b2
+ add \a3, \a3, \b3
+ add \a4, \a4, \b4
+ xor \d1, \d1, \a1
+ xor \d2, \d2, \a2
+ xor \d3, \d3, \a3
+ xor \d4, \d4, \a4
+ rotlwi \d1, \d1, 8
+ rotlwi \d2, \d2, 8
+ rotlwi \d3, \d3, 8
+ rotlwi \d4, \d4, 8
+ add \c1, \c1, \d1
+ add \c2, \c2, \d2
+ add \c3, \c3, \d3
+ add \c4, \c4, \d4
+ xor \b1, \b1, \c1
+ xor \b2, \b2, \c2
+ xor \b3, \b3, \c3
+ xor \b4, \b4, \c4
+ rotlwi \b1, \b1, 7
+ rotlwi \b2, \b2, 7
+ rotlwi \b3, \b3, 7
+ rotlwi \b4, \b4, 7
+.endm
+
+#define QUARTERROUND4(a1,b1,c1,d1,a2,b2,c2,d2,a3,b3,c3,d3,a4,b4,c4,d4) \
+ quarterround4 state##a1 state##b1 state##c1 state##d1 \
+ state##a2 state##b2 state##c2 state##d2 \
+ state##a3 state##b3 state##c3 state##d3 \
+ state##a4 state##b4 state##c4 state##d4
+
+/*
+ * Very basic 32 bits implementation of ChaCha20. Produces a given positive number
+ * of blocks of output with a nonce of 0, taking an input key and 8-byte
+ * counter. Importantly does not spill to the stack. Its arguments are:
+ *
+ * r3: output bytes
+ * r4: 32-byte key input
+ * r5: 8-byte counter input/output (saved on stack)
+ * r6: number of 64-byte blocks to write to output
+ *
+ * r0: counter of blocks (initialised with r6)
+ * r4: Value '4' after key has been read.
+ * r5-r12: key
+ * r14-r15: counter
+ * r16-r31: state
+ */
+SYM_FUNC_START(__arch_chacha20_blocks_nostack)
+#ifdef __powerpc64__
+ std counter, -216(r1)
+
+ std r14, -144(r1)
+ std r15, -136(r1)
+ std r16, -128(r1)
+ std r17, -120(r1)
+ std r18, -112(r1)
+ std r19, -104(r1)
+ std r20, -96(r1)
+ std r21, -88(r1)
+ std r22, -80(r1)
+ std r23, -72(r1)
+ std r24, -64(r1)
+ std r25, -56(r1)
+ std r26, -48(r1)
+ std r27, -40(r1)
+ std r28, -32(r1)
+ std r29, -24(r1)
+ std r30, -16(r1)
+ std r31, -8(r1)
+#else
+ stwu r1, -96(r1)
+ stw counter, 20(r1)
+#ifdef __BIG_ENDIAN__
+ stmw r14, 24(r1)
+#else
+ stw r14, 24(r1)
+ stw r15, 28(r1)
+ stw r16, 32(r1)
+ stw r17, 36(r1)
+ stw r18, 40(r1)
+ stw r19, 44(r1)
+ stw r20, 48(r1)
+ stw r21, 52(r1)
+ stw r22, 56(r1)
+ stw r23, 60(r1)
+ stw r24, 64(r1)
+ stw r25, 68(r1)
+ stw r26, 72(r1)
+ stw r27, 76(r1)
+ stw r28, 80(r1)
+ stw r29, 84(r1)
+ stw r30, 88(r1)
+ stw r31, 92(r1)
+#endif
+#endif /* __powerpc64__ */
+
+ lwz counter0, 0(counter)
+ lwz counter1, 4(counter)
+#ifdef __powerpc64__
+ rldimi counter0, counter1, 32, 0
+#endif
+ mr idx_r0, nblocks
+ subi dst_bytes, dst_bytes, 4
+
+ lwz key0, 0(key)
+ lwz key1, 4(key)
+ lwz key2, 8(key)
+ lwz key3, 12(key)
+ lwz key4, 16(key)
+ lwz key5, 20(key)
+ lwz key6, 24(key)
+ lwz key7, 28(key)
+
+ li val4, 4
+.Lblock:
+ li r31, 10
+
+ lis state0, const0@ha
+ lis state1, const1@ha
+ lis state2, const2@ha
+ lis state3, const3@ha
+ addi state0, state0, const0@l
+ addi state1, state1, const1@l
+ addi state2, state2, const2@l
+ addi state3, state3, const3@l
+
+ mtctr r31
+
+ mr state4, key0
+ mr state5, key1
+ mr state6, key2
+ mr state7, key3
+ mr state8, key4
+ mr state9, key5
+ mr state10, key6
+ mr state11, key7
+
+ mr state12, counter0
+ mr state13, counter1
+
+ li state14, 0
+ li state15, 0
+
+.Lpermute:
+ QUARTERROUND4( 0, 4, 8,12, 1, 5, 9,13, 2, 6,10,14, 3, 7,11,15)
+ QUARTERROUND4( 0, 5,10,15, 1, 6,11,12, 2, 7, 8,13, 3, 4, 9,14)
+
+ bdnz .Lpermute
+
+ addis state0, state0, const0@ha
+ addis state1, state1, const1@ha
+ addis state2, state2, const2@ha
+ addis state3, state3, const3@ha
+ addi state0, state0, const0@l
+ addi state1, state1, const1@l
+ addi state2, state2, const2@l
+ addi state3, state3, const3@l
+
+ add state4, state4, key0
+ add state5, state5, key1
+ add state6, state6, key2
+ add state7, state7, key3
+ add state8, state8, key4
+ add state9, state9, key5
+ add state10, state10, key6
+ add state11, state11, key7
+
+ add state12, state12, counter0
+ add state13, state13, counter1
+
+#ifdef __BIG_ENDIAN__
+ stwbrx state0, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state1, 0, dst_bytes
+ stwbrx state2, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state3, 0, dst_bytes
+ stwbrx state4, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state5, 0, dst_bytes
+ stwbrx state6, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state7, 0, dst_bytes
+ stwbrx state8, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state9, 0, dst_bytes
+ stwbrx state10, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state11, 0, dst_bytes
+ stwbrx state12, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state13, 0, dst_bytes
+ stwbrx state14, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state15, 0, dst_bytes
+#else
+ stw state0, 4(dst_bytes)
+ stw state1, 8(dst_bytes)
+ stw state2, 12(dst_bytes)
+ stw state3, 16(dst_bytes)
+ stw state4, 20(dst_bytes)
+ stw state5, 24(dst_bytes)
+ stw state6, 28(dst_bytes)
+ stw state7, 32(dst_bytes)
+ stw state8, 36(dst_bytes)
+ stw state9, 40(dst_bytes)
+ stw state10, 44(dst_bytes)
+ stw state11, 48(dst_bytes)
+ stw state12, 52(dst_bytes)
+ stw state13, 56(dst_bytes)
+ stw state14, 60(dst_bytes)
+ stwu state15, 64(dst_bytes)
+#endif
+
+ subic. idx_r0, idx_r0, 1 /* subi. can't use r0 as source */
+
+#ifdef __powerpc64__
+ addi counter0, counter0, 1
+ srdi counter1, counter0, 32
+#else
+ addic counter0, counter0, 1
+ addze counter1, counter1
+#endif
+
+ bne .Lblock
+
+#ifdef __powerpc64__
+ ld counter, -216(r1)
+#else
+ lwz counter, 20(r1)
+#endif
+ stw counter0, 0(counter)
+ stw counter1, 4(counter)
+
+ li r6, 0
+ li r7, 0
+ li r8, 0
+ li r9, 0
+ li r10, 0
+ li r11, 0
+ li r12, 0
+
+#ifdef __powerpc64__
+ ld r14, -144(r1)
+ ld r15, -136(r1)
+ ld r16, -128(r1)
+ ld r17, -120(r1)
+ ld r18, -112(r1)
+ ld r19, -104(r1)
+ ld r20, -96(r1)
+ ld r21, -88(r1)
+ ld r22, -80(r1)
+ ld r23, -72(r1)
+ ld r24, -64(r1)
+ ld r25, -56(r1)
+ ld r26, -48(r1)
+ ld r27, -40(r1)
+ ld r28, -32(r1)
+ ld r29, -24(r1)
+ ld r30, -16(r1)
+ ld r31, -8(r1)
+#else
+#ifdef __BIG_ENDIAN__
+ lmw r14, 24(r1)
+#else
+ lwz r14, 24(r1)
+ lwz r15, 28(r1)
+ lwz r16, 32(r1)
+ lwz r17, 36(r1)
+ lwz r18, 40(r1)
+ lwz r19, 44(r1)
+ lwz r20, 48(r1)
+ lwz r21, 52(r1)
+ lwz r22, 56(r1)
+ lwz r23, 60(r1)
+ lwz r24, 64(r1)
+ lwz r25, 68(r1)
+ lwz r26, 72(r1)
+ lwz r27, 76(r1)
+ lwz r28, 80(r1)
+ lwz r29, 84(r1)
+ lwz r30, 88(r1)
+ lwz r31, 92(r1)
+#endif
+ addi r1, r1, 96
+#endif /* __powerpc64__ */
+ blr
+SYM_FUNC_END(__arch_chacha20_blocks_nostack)
diff --git a/arch/powerpc/kernel/vdso/vgetrandom.c b/arch/powerpc/kernel/vdso/vgetrandom.c
new file mode 100644
index 000000000000..cc79b960a541
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/vgetrandom.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Powerpc userspace implementation of getrandom()
+ *
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state,
+ size_t opaque_len)
+{
+ return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len);
+}
diff --git a/arch/powerpc/kernel/vdso/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c
index 55a287c9a736..6f5167d81af5 100644
--- a/arch/powerpc/kernel/vdso/vgettimeofday.c
+++ b/arch/powerpc/kernel/vdso/vgettimeofday.c
@@ -7,43 +7,43 @@
#ifdef __powerpc64__
int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
- const struct vdso_data *vd)
+ const struct vdso_time_data *vd)
{
return __cvdso_clock_gettime_data(vd, clock, ts);
}
int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
- const struct vdso_data *vd)
+ const struct vdso_time_data *vd)
{
return __cvdso_clock_getres_data(vd, clock_id, res);
}
#else
int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
- const struct vdso_data *vd)
+ const struct vdso_time_data *vd)
{
return __cvdso_clock_gettime32_data(vd, clock, ts);
}
int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
- const struct vdso_data *vd)
+ const struct vdso_time_data *vd)
{
return __cvdso_clock_gettime_data(vd, clock, ts);
}
int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
- const struct vdso_data *vd)
+ const struct vdso_time_data *vd)
{
return __cvdso_clock_getres_time32_data(vd, clock_id, res);
}
#endif
int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
- const struct vdso_data *vd)
+ const struct vdso_time_data *vd)
{
return __cvdso_gettimeofday_data(vd, tv, tz);
}
-__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_time_data *vd)
{
return __cvdso_time_data(vd, time);
}
diff --git a/arch/powerpc/kernel/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32_wrapper.S
index 10f92f265d51..20bca3548b44 100644
--- a/arch/powerpc/kernel/vdso32_wrapper.S
+++ b/arch/powerpc/kernel/vdso32_wrapper.S
@@ -2,7 +2,7 @@
#include <linux/linkage.h>
#include <asm/page.h>
- __PAGE_ALIGNED_DATA
+ .section ".data..ro_after_init", "aw"
.globl vdso32_start, vdso32_end
.balign PAGE_SIZE
diff --git a/arch/powerpc/kernel/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64_wrapper.S
index 839d1a61411d..1912936fa227 100644
--- a/arch/powerpc/kernel/vdso64_wrapper.S
+++ b/arch/powerpc/kernel/vdso64_wrapper.S
@@ -2,7 +2,7 @@
#include <linux/linkage.h>
#include <asm/page.h>
- __PAGE_ALIGNED_DATA
+ .section ".data..ro_after_init", "aw"
.globl vdso64_start, vdso64_end
.balign PAGE_SIZE
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 5cc24d8cce94..80b3f6e476b6 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -1,4 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
+#include <linux/linkage.h>
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/reg.h>
@@ -7,7 +9,6 @@
#include <asm/thread_info.h>
#include <asm/page.h>
#include <asm/ptrace.h>
-#include <asm/export.h>
#include <asm/asm-compat.h>
/*
@@ -32,6 +33,7 @@ _GLOBAL(store_vr_state)
mfvscr v0
li r4, VRSTATE_VSCR
stvx v0, r4, r3
+ lvx v0, 0, r3
blr
EXPORT_SYMBOL(store_vr_state)
@@ -108,6 +110,7 @@ _GLOBAL(save_altivec)
mfvscr v0
li r4,VRSTATE_VSCR
stvx v0,r4,r7
+ lvx v0,0,r7
blr
#ifdef CONFIG_VSX
@@ -155,8 +158,8 @@ _GLOBAL(load_up_vsx)
* usage of floating-point registers. These routines must be called
* with preempt disabled.
*/
-#ifdef CONFIG_PPC32
.data
+#ifdef CONFIG_PPC32
fpzero:
.long 0
fpone:
@@ -169,24 +172,29 @@ fphalf:
lfs fr,name@l(r11)
#else
- .section ".toc","aw"
fpzero:
- .tc FD_0_0[TC],0
+ .quad 0
fpone:
- .tc FD_3ff00000_0[TC],0x3ff0000000000000 /* 1.0 */
+ .quad 0x3ff0000000000000 /* 1.0 */
fphalf:
- .tc FD_3fe00000_0[TC],0x3fe0000000000000 /* 0.5 */
+ .quad 0x3fe0000000000000 /* 0.5 */
-#define LDCONST(fr, name) \
- lfd fr,name@toc(r2)
+#ifdef CONFIG_PPC_KERNEL_PCREL
+#define LDCONST(fr, name) \
+ pla r11,name@pcrel; \
+ lfd fr,0(r11)
+#else
+#define LDCONST(fr, name) \
+ addis r11,r2,name@toc@ha; \
+ lfd fr,name@toc@l(r11)
+#endif
#endif
-
.text
/*
* Internal routine to enable floating point and set FPSCR to 0.
* Don't call it from C; it doesn't use the normal calling convention.
*/
-fpenable:
+SYM_FUNC_START_LOCAL(fpenable)
#ifdef CONFIG_PPC32
stwu r1,-64(r1)
#else
@@ -203,6 +211,7 @@ fpenable:
mffs fr31
MTFSF_L(fr1)
blr
+SYM_FUNC_END(fpenable)
fpdisable:
mtlr r12
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index fe22d940412f..de6ee7d35cff 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -1,13 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifdef CONFIG_PPC64
-#define PROVIDE32(x) PROVIDE(__unused__##x)
-#else
-#define PROVIDE32(x) PROVIDE(x)
-#endif
-
#define BSS_FIRST_SECTIONS *(.bss.prominit)
#define EMITS_PT_NOTE
#define RO_EXCEPTION_TABLE_ALIGN 0
+#define RUNTIME_DISCARD_EXIT
#define SOFT_MASK_TABLE(align) \
. = ALIGN(align); \
@@ -32,6 +27,10 @@
#define STRICT_ALIGN_SIZE (1 << CONFIG_DATA_SHIFT)
+#if STRICT_ALIGN_SIZE < PAGE_SIZE
+#error "CONFIG_DATA_SHIFT must be >= PAGE_SHIFT"
+#endif
+
ENTRY(_stext)
PHDRS {
@@ -67,7 +66,7 @@ SECTIONS
.head.text : AT(ADDR(.head.text) - LOAD_OFFSET) {
#ifdef CONFIG_PPC64
KEEP(*(.head.text.first_256B));
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3E_64
#else
KEEP(*(.head.text.real_vectors));
*(.head.text.real_trampolines);
@@ -102,12 +101,9 @@ SECTIONS
#endif
/* careful! __ftr_alt_* sections need to be close to .text */
*(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text);
-#ifdef CONFIG_PPC64
*(.tramp.ftrace.text);
-#endif
NOINSTR_TEXT
SCHED_TEXT
- CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
@@ -120,34 +116,72 @@ SECTIONS
* included with the main text sections, so put it by itself.
*/
*(.sfpr);
- MEM_KEEP(init.text)
- MEM_KEEP(exit.text)
+ *(.text.asan.* .text.tsan.*)
+ } :text
+
+ . = ALIGN(PAGE_SIZE);
+ _etext = .;
+
+ /* Read-only data */
+ RO_DATA(PAGE_SIZE)
+
+#ifdef CONFIG_PPC32
+ .sdata2 : AT(ADDR(.sdata2) - LOAD_OFFSET) {
+ *(.sdata2)
+ }
+#endif
+
+ .data.rel.ro : AT(ADDR(.data.rel.ro) - LOAD_OFFSET) {
+ *(.data.rel.ro .data.rel.ro.*)
+ }
+
+ .branch_lt : AT(ADDR(.branch_lt) - LOAD_OFFSET) {
+ *(.branch_lt)
+ }
#ifdef CONFIG_PPC32
+ .got1 : AT(ADDR(.got1) - LOAD_OFFSET) {
*(.got1)
+ }
+ .got2 : AT(ADDR(.got2) - LOAD_OFFSET) {
__got2_start = .;
*(.got2)
__got2_end = .;
-#endif /* CONFIG_PPC32 */
-
- } :text
+ }
+ .got : AT(ADDR(.got) - LOAD_OFFSET) {
+ *(.got)
+ *(.got.plt)
+ }
+ .plt : AT(ADDR(.plt) - LOAD_OFFSET) {
+ /* XXX: is .plt (and .got.plt) required? */
+ *(.plt)
+ }
- . = ALIGN(PAGE_SIZE);
- _etext = .;
- PROVIDE32 (etext = .);
+#else /* CONFIG_PPC32 */
+#ifndef CONFIG_PPC_KERNEL_PCREL
+ .toc1 : AT(ADDR(.toc1) - LOAD_OFFSET) {
+ *(.toc1)
+ }
+#endif
- /* Read-only data */
- RO_DATA(PAGE_SIZE)
+ .got : AT(ADDR(.got) - LOAD_OFFSET) ALIGN(256) {
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ *(.got)
+#else
+ *(.got .toc)
+#endif
+ }
-#ifdef CONFIG_PPC64
SOFT_MASK_TABLE(8)
RESTART_TABLE(8)
+#ifdef CONFIG_PPC64_ELF_ABI_V1
.opd : AT(ADDR(.opd) - LOAD_OFFSET) {
__start_opd = .;
KEEP(*(.opd))
__end_opd = .;
}
+#endif
. = ALIGN(8);
__stf_entry_barrier_fixup : AT(ADDR(__stf_entry_barrier_fixup) - LOAD_OFFSET) {
@@ -190,7 +224,7 @@ SECTIONS
*(__rfi_flush_fixup)
__stop___rfi_flush_fixup = .;
}
-#endif /* CONFIG_PPC64 */
+#endif /* CONFIG_PPC32 */
#ifdef CONFIG_PPC_BARRIER_NOSPEC
. = ALIGN(8);
@@ -201,7 +235,7 @@ SECTIONS
}
#endif /* CONFIG_PPC_BARRIER_NOSPEC */
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_E500
. = ALIGN(8);
__spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) {
__start__btb_flush_fixup = .;
@@ -210,32 +244,36 @@ SECTIONS
}
#endif
+ /*
+ * Various code relies on __init_begin being at the strict RWX boundary.
+ */
+ . = ALIGN(STRICT_ALIGN_SIZE);
+ __srwx_boundary = .;
+ __end_rodata = .;
+ __init_begin = .;
+
/*
* Init sections discarded at runtime
*/
- . = ALIGN(STRICT_ALIGN_SIZE);
- __init_begin = .;
- . = ALIGN(PAGE_SIZE);
.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
_sinittext = .;
INIT_TEXT
-
+ *(.tramp.ftrace.init);
/*
*.init.text might be RO so we must ensure this section ends on
* a page boundary.
*/
. = ALIGN(PAGE_SIZE);
_einittext = .;
-#ifdef CONFIG_PPC64
- *(.tramp.ftrace.init);
-#endif
} :text
/* .exit.text is discarded at runtime, not link time,
* to deal with references from __bug_table
*/
.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+ __exittext_begin = .;
EXIT_TEXT
+ __exittext_end = .;
}
. = ALIGN(PAGE_SIZE);
@@ -317,34 +355,13 @@ SECTIONS
. = ALIGN(PAGE_SIZE);
_sdata = .;
-#ifdef CONFIG_PPC32
.data : AT(ADDR(.data) - LOAD_OFFSET) {
DATA_DATA
*(.data.rel*)
+#ifdef CONFIG_PPC32
*(SDATA_MAIN)
- *(.sdata2)
- *(.got.plt) *(.got)
- *(.plt)
- *(.branch_lt)
- }
-#else
- .data : AT(ADDR(.data) - LOAD_OFFSET) {
- DATA_DATA
- *(.data.rel*)
- *(.toc1)
- *(.branch_lt)
- }
-
- .got : AT(ADDR(.got) - LOAD_OFFSET) ALIGN(256) {
- *(.got)
-#ifndef CONFIG_RELOCATABLE
- __prom_init_toc_start = .;
- arch/powerpc/kernel/prom_init.o*(.toc)
- __prom_init_toc_end = .;
#endif
- *(.toc)
}
-#endif
/* The initial task and kernel stack */
INIT_TASK_DATA_SECTION(THREAD_ALIGN)
@@ -370,7 +387,6 @@ SECTIONS
. = ALIGN(PAGE_SIZE);
_edata = .;
- PROVIDE32 (edata = .);
/*
* And finally the bss
@@ -380,18 +396,19 @@ SECTIONS
. = ALIGN(PAGE_SIZE);
_end = . ;
- PROVIDE32 (end = .);
- STABS_DEBUG
DWARF_DEBUG
ELF_DETAILS
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
- *(.glink .iplt .plt .rela* .comment)
+ *(.glink .iplt .plt)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+ *(.rela*)
+#endif
}
}
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 7d28b9553654..2429cb1c7baa 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -91,6 +91,10 @@ static cpumask_t wd_smp_cpus_pending;
static cpumask_t wd_smp_cpus_stuck;
static u64 wd_smp_last_reset_tb;
+#ifdef CONFIG_PPC_PSERIES
+static u64 wd_timeout_pct;
+#endif
+
/*
* Try to take the exclusive watchdog action / NMI IPI / printing lock.
* wd_smp_lock must be held. If this fails, we should return and wait
@@ -241,7 +245,7 @@ static void watchdog_smp_panic(int cpu)
__cpumask_clear_cpu(c, &wd_smp_cpus_ipi);
}
} else {
- trigger_allbutself_cpu_backtrace();
+ trigger_allbutcpu_cpu_backtrace(cpu);
cpumask_clear(&wd_smp_cpus_ipi);
}
@@ -353,7 +357,7 @@ static void watchdog_timer_interrupt(int cpu)
if (__wd_nmi_output && xchg(&__wd_nmi_output, 0)) {
/*
* Something has called printk from NMI context. It might be
- * stuck, so this this triggers a flush that will get that
+ * stuck, so this triggers a flush that will get that
* printk output to the console.
*
* See wd_lockup_ipi.
@@ -412,7 +416,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi
if (sysctl_hardlockup_all_cpu_backtrace)
- trigger_allbutself_cpu_backtrace();
+ trigger_allbutcpu_cpu_backtrace(cpu);
if (hardlockup_panic)
nmi_panic(regs, "Hard LOCKUP");
@@ -434,7 +438,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
{
int cpu = smp_processor_id();
- if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+ if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
return HRTIMER_NORESTART;
if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
@@ -475,7 +479,7 @@ static void start_watchdog(void *arg)
return;
}
- if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+ if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
return;
if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
@@ -491,8 +495,7 @@ static void start_watchdog(void *arg)
*this_cpu_ptr(&wd_timer_tb) = get_tb();
- hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hrtimer->function = watchdog_timer_fn;
+ hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms),
HRTIMER_MODE_REL_PINNED);
}
@@ -527,7 +530,13 @@ static int stop_watchdog_on_cpu(unsigned int cpu)
static void watchdog_calc_timeouts(void)
{
- wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq;
+ u64 threshold = watchdog_thresh;
+
+#ifdef CONFIG_PPC_PSERIES
+ threshold += (READ_ONCE(wd_timeout_pct) * threshold) / 100;
+#endif
+
+ wd_panic_timeout_tb = threshold * ppc_tb_freq;
/* Have the SMP detector trigger a bit later */
wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2;
@@ -536,7 +545,7 @@ static void watchdog_calc_timeouts(void)
wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5;
}
-void watchdog_nmi_stop(void)
+void watchdog_hardlockup_stop(void)
{
int cpu;
@@ -544,7 +553,7 @@ void watchdog_nmi_stop(void)
stop_watchdog_on_cpu(cpu);
}
-void watchdog_nmi_start(void)
+void watchdog_hardlockup_start(void)
{
int cpu;
@@ -556,7 +565,7 @@ void watchdog_nmi_start(void)
/*
* Invoked from core watchdog init.
*/
-int __init watchdog_nmi_probe(void)
+int __init watchdog_hardlockup_probe(void)
{
int err;
@@ -570,3 +579,12 @@ int __init watchdog_nmi_probe(void)
}
return 0;
}
+
+#ifdef CONFIG_PPC_PSERIES
+void watchdog_hardlockup_set_timeout_pct(u64 pct)
+{
+ pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct);
+ WRITE_ONCE(wd_timeout_pct, pct);
+ lockup_detector_reconfigure();
+}
+#endif