summaryrefslogtreecommitdiff
path: root/arch/powerpc
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/Kbuild5
-rw-r--r--arch/powerpc/Kconfig150
-rw-r--r--arch/powerpc/Kconfig.debug25
-rw-r--r--arch/powerpc/Makefile74
-rw-r--r--arch/powerpc/Makefile.postlink8
-rw-r--r--arch/powerpc/boot/.gitignore1
-rw-r--r--arch/powerpc/boot/4xx.c266
-rw-r--r--arch/powerpc/boot/4xx.h4
-rw-r--r--arch/powerpc/boot/Makefile24
-rw-r--r--arch/powerpc/boot/cuboot-acadia.c171
-rw-r--r--arch/powerpc/boot/cuboot-hotfoot.c139
-rw-r--r--arch/powerpc/boot/cuboot-kilauea.c46
-rw-r--r--arch/powerpc/boot/dcr.h11
-rw-r--r--arch/powerpc/boot/decompress.c2
-rw-r--r--arch/powerpc/boot/dts/Makefile3
-rw-r--r--arch/powerpc/boot/dts/acadia.dts224
-rw-r--r--arch/powerpc/boot/dts/akebono.dts6
-rw-r--r--arch/powerpc/boot/dts/fsl/Makefile3
-rw-r--r--arch/powerpc/boot/dts/fsl/b4si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/bsc9131rdb.dts2
-rw-r--r--arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/bsc9132qds.dts2
-rw-r--r--arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/c293pcie.dts2
-rw-r--r--arch/powerpc/boot/dts/fsl/c293si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi14
-rw-r--r--arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts16
-rw-r--r--arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts16
-rw-r--r--arch/powerpc/boot/dts/fsl/p1010rdb.dtsi16
-rw-r--r--arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/p1010si-post.dtsi16
-rw-r--r--arch/powerpc/boot/dts/fsl/p1020si-post.dtsi5
-rw-r--r--arch/powerpc/boot/dts/fsl/p1021si-post.dtsi5
-rw-r--r--arch/powerpc/boot/dts/fsl/p1022si-post.dtsi7
-rw-r--r--arch/powerpc/boot/dts/fsl/p2020si-post.dtsi17
-rw-r--r--arch/powerpc/boot/dts/fsl/pq3-power.dtsi19
-rw-r--r--arch/powerpc/boot/dts/fsl/t1023si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/t1024rdb.dts2
-rw-r--r--arch/powerpc/boot/dts/fsl/t1040rdb.dts2
-rw-r--r--arch/powerpc/boot/dts/fsl/t1040si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/t1042rdb.dts2
-rw-r--r--arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts2
-rw-r--r--arch/powerpc/boot/dts/fsl/t2081si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/fsl/t4240si-post.dtsi2
-rw-r--r--arch/powerpc/boot/dts/haleakala.dts281
-rw-r--r--arch/powerpc/boot/dts/hotfoot.dts296
-rw-r--r--arch/powerpc/boot/dts/kilauea.dts407
-rw-r--r--arch/powerpc/boot/dts/klondike.dts212
-rw-r--r--arch/powerpc/boot/dts/makalu.dts353
-rw-r--r--arch/powerpc/boot/dts/obs600.dts314
-rw-r--r--arch/powerpc/boot/main.c2
-rw-r--r--arch/powerpc/boot/ppcboot-hotfoot.h119
-rw-r--r--arch/powerpc/boot/ppcboot.h2
-rw-r--r--arch/powerpc/boot/ps3.c2
-rw-r--r--arch/powerpc/boot/simple_alloc.c7
-rwxr-xr-xarch/powerpc/boot/wrapper29
-rw-r--r--arch/powerpc/boot/xz_config.h3
-rw-r--r--arch/powerpc/configs/40x/acadia_defconfig61
-rw-r--r--arch/powerpc/configs/40x/kilauea_defconfig69
-rw-r--r--arch/powerpc/configs/40x/klondike_defconfig43
-rw-r--r--arch/powerpc/configs/40x/makalu_defconfig59
-rw-r--r--arch/powerpc/configs/40x/obs600_defconfig69
-rw-r--r--arch/powerpc/configs/40x/walnut_defconfig55
-rw-r--r--arch/powerpc/configs/44x.config2
-rw-r--r--arch/powerpc/configs/85xx-32bit.config1
-rw-r--r--arch/powerpc/configs/85xx-hw.config2
-rw-r--r--arch/powerpc/configs/8xx.config2
-rw-r--r--arch/powerpc/configs/adder875_defconfig2
-rw-r--r--arch/powerpc/configs/cell_defconfig1
-rw-r--r--arch/powerpc/configs/ep88xc_defconfig2
-rw-r--r--arch/powerpc/configs/maple_defconfig111
-rw-r--r--arch/powerpc/configs/mpc866_ads_defconfig2
-rw-r--r--arch/powerpc/configs/mpc885_ads_defconfig2
-rw-r--r--arch/powerpc/configs/pmac32_defconfig1
-rw-r--r--arch/powerpc/configs/powernv_defconfig2
-rw-r--r--arch/powerpc/configs/ppc40x_defconfig74
-rw-r--r--arch/powerpc/configs/ppc64_defconfig6
-rw-r--r--arch/powerpc/configs/ppc6xx_defconfig3
-rw-r--r--arch/powerpc/configs/ps3_defconfig1
-rw-r--r--arch/powerpc/configs/tqm8xx_defconfig2
-rw-r--r--arch/powerpc/crypto/.gitignore2
-rw-r--r--arch/powerpc/crypto/Kconfig59
-rw-r--r--arch/powerpc/crypto/Makefile27
-rw-r--r--arch/powerpc/crypto/aes-gcm-p10-glue.c152
-rw-r--r--arch/powerpc/crypto/aes-gcm-p10.S2421
-rw-r--r--arch/powerpc/crypto/aes.c134
-rw-r--r--arch/powerpc/crypto/aes_cbc.c133
-rw-r--r--arch/powerpc/crypto/aes_ctr.c149
-rw-r--r--arch/powerpc/crypto/aes_xts.c162
-rw-r--r--arch/powerpc/crypto/aesp8-ppc.h30
-rw-r--r--arch/powerpc/crypto/aesp8-ppc.pl3889
-rw-r--r--arch/powerpc/crypto/chacha-p10-glue.c8
-rw-r--r--arch/powerpc/crypto/crc-vpmsum_test.c133
-rw-r--r--arch/powerpc/crypto/crc32c-vpmsum_glue.c173
-rw-r--r--arch/powerpc/crypto/curve25519-ppc64le-core.c300
-rw-r--r--arch/powerpc/crypto/curve25519-ppc64le_asm.S671
-rw-r--r--arch/powerpc/crypto/ghash.c185
-rw-r--r--arch/powerpc/crypto/ghashp8-ppc.pl243
-rw-r--r--arch/powerpc/crypto/poly1305-p10-glue.c2
-rw-r--r--arch/powerpc/crypto/vmx.c77
-rw-r--r--arch/powerpc/include/asm/Kbuild1
-rw-r--r--arch/powerpc/include/asm/asm-compat.h8
-rw-r--r--arch/powerpc/include/asm/atomic.h5
-rw-r--r--arch/powerpc/include/asm/backlight.h5
-rw-r--r--arch/powerpc/include/asm/book3s/32/pgalloc.h2
-rw-r--r--arch/powerpc/include/asm/book3s/32/pgtable.h3
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash-4k.h37
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash.h42
-rw-r--r--arch/powerpc/include/asm/book3s/64/hugetlb.h38
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable-4k.h67
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable-64k.h45
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h104
-rw-r--r--arch/powerpc/include/asm/book3s/64/radix.h2
-rw-r--r--arch/powerpc/include/asm/cacheflush.h2
-rw-r--r--arch/powerpc/include/asm/cpu_has_feature.h5
-rw-r--r--arch/powerpc/include/asm/cputable.h30
-rw-r--r--arch/powerpc/include/asm/cputime.h13
-rw-r--r--arch/powerpc/include/asm/dtl.h4
-rw-r--r--arch/powerpc/include/asm/eeh.h3
-rw-r--r--arch/powerpc/include/asm/elf.h2
-rw-r--r--arch/powerpc/include/asm/fadump-internal.h36
-rw-r--r--arch/powerpc/include/asm/fadump.h11
-rw-r--r--arch/powerpc/include/asm/feature-fixups.h2
-rw-r--r--arch/powerpc/include/asm/fpu.h28
-rw-r--r--arch/powerpc/include/asm/ftrace.h67
-rw-r--r--arch/powerpc/include/asm/guest-state-buffer.h3
-rw-r--r--arch/powerpc/include/asm/hugetlb.h30
-rw-r--r--arch/powerpc/include/asm/hvcall.h11
-rw-r--r--arch/powerpc/include/asm/hw_irq.h8
-rw-r--r--arch/powerpc/include/asm/ibmebus.h2
-rw-r--r--arch/powerpc/include/asm/interrupt.h18
-rw-r--r--arch/powerpc/include/asm/io.h40
-rw-r--r--arch/powerpc/include/asm/iommu.h16
-rw-r--r--arch/powerpc/include/asm/irq.h2
-rw-r--r--arch/powerpc/include/asm/kasan.h2
-rw-r--r--arch/powerpc/include/asm/kexec.h120
-rw-r--r--arch/powerpc/include/asm/kexec_ranges.h20
-rw-r--r--arch/powerpc/include/asm/kfence.h15
-rw-r--r--arch/powerpc/include/asm/kprobes.h2
-rw-r--r--arch/powerpc/include/asm/kup.h2
-rw-r--r--arch/powerpc/include/asm/kvm_book3s.h5
-rw-r--r--arch/powerpc/include/asm/kvm_book3s_64.h11
-rw-r--r--arch/powerpc/include/asm/kvm_host.h9
-rw-r--r--arch/powerpc/include/asm/kvm_ppc.h1
-rw-r--r--arch/powerpc/include/asm/lppaca.h11
-rw-r--r--arch/powerpc/include/asm/machdep.h9
-rw-r--r--arch/powerpc/include/asm/macio.h4
-rw-r--r--arch/powerpc/include/asm/mman.h2
-rw-r--r--arch/powerpc/include/asm/mmu.h26
-rw-r--r--arch/powerpc/include/asm/mmu_context.h12
-rw-r--r--arch/powerpc/include/asm/mmzone.h6
-rw-r--r--arch/powerpc/include/asm/module.h12
-rw-r--r--arch/powerpc/include/asm/mpic.h2
-rw-r--r--arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h38
-rw-r--r--arch/powerpc/include/asm/nohash/32/mmu-40x.h68
-rw-r--r--arch/powerpc/include/asm/nohash/32/mmu-8xx.h12
-rw-r--r--arch/powerpc/include/asm/nohash/32/pgtable.h8
-rw-r--r--arch/powerpc/include/asm/nohash/32/pte-40x.h73
-rw-r--r--arch/powerpc/include/asm/nohash/32/pte-44x.h3
-rw-r--r--arch/powerpc/include/asm/nohash/32/pte-85xx.h3
-rw-r--r--arch/powerpc/include/asm/nohash/32/pte-8xx.h58
-rw-r--r--arch/powerpc/include/asm/nohash/hugetlb-e500.h39
-rw-r--r--arch/powerpc/include/asm/nohash/mmu-e500.h6
-rw-r--r--arch/powerpc/include/asm/nohash/mmu.h5
-rw-r--r--arch/powerpc/include/asm/nohash/pgalloc.h10
-rw-r--r--arch/powerpc/include/asm/nohash/pgtable.h56
-rw-r--r--arch/powerpc/include/asm/nohash/pte-e500.h63
-rw-r--r--arch/powerpc/include/asm/opal-api.h4
-rw-r--r--arch/powerpc/include/asm/paca.h4
-rw-r--r--arch/powerpc/include/asm/page.h42
-rw-r--r--arch/powerpc/include/asm/percpu.h10
-rw-r--r--arch/powerpc/include/asm/perf_event_server.h9
-rw-r--r--arch/powerpc/include/asm/pgtable-be-types.h10
-rw-r--r--arch/powerpc/include/asm/pgtable-types.h21
-rw-r--r--arch/powerpc/include/asm/pgtable.h34
-rw-r--r--arch/powerpc/include/asm/plpar_wrappers.h28
-rw-r--r--arch/powerpc/include/asm/plpks.h5
-rw-r--r--arch/powerpc/include/asm/pmac_feature.h2
-rw-r--r--arch/powerpc/include/asm/ppc-opcode.h20
-rw-r--r--arch/powerpc/include/asm/ppc_asm.h28
-rw-r--r--arch/powerpc/include/asm/processor.h15
-rw-r--r--arch/powerpc/include/asm/ps3.h6
-rw-r--r--arch/powerpc/include/asm/ptrace.h2
-rw-r--r--arch/powerpc/include/asm/reg.h31
-rw-r--r--arch/powerpc/include/asm/reg_booke.h113
-rw-r--r--arch/powerpc/include/asm/reg_fsl_emb.h25
-rw-r--r--arch/powerpc/include/asm/rtas.h1
-rw-r--r--arch/powerpc/include/asm/set_memory.h19
-rw-r--r--arch/powerpc/include/asm/simple_spinlock_types.h2
-rw-r--r--arch/powerpc/include/asm/smp.h1
-rw-r--r--arch/powerpc/include/asm/spinlock_types.h2
-rw-r--r--arch/powerpc/include/asm/spu_priv1.h1
-rw-r--r--arch/powerpc/include/asm/sstep.h5
-rw-r--r--arch/powerpc/include/asm/switch_to.h4
-rw-r--r--arch/powerpc/include/asm/systemcfg.h52
-rw-r--r--arch/powerpc/include/asm/text-patching.h (renamed from arch/powerpc/include/asm/code-patching.h)37
-rw-r--r--arch/powerpc/include/asm/thread_info.h13
-rw-r--r--arch/powerpc/include/asm/time.h9
-rw-r--r--arch/powerpc/include/asm/tlb.h3
-rw-r--r--arch/powerpc/include/asm/topology.h13
-rw-r--r--arch/powerpc/include/asm/trace.h7
-rw-r--r--arch/powerpc/include/asm/uaccess.h22
-rw-r--r--arch/powerpc/include/asm/udbg.h2
-rw-r--r--arch/powerpc/include/asm/uninorth.h2
-rw-r--r--arch/powerpc/include/asm/unistd.h1
-rw-r--r--arch/powerpc/include/asm/vdso.h1
-rw-r--r--arch/powerpc/include/asm/vdso/getrandom.h66
-rw-r--r--arch/powerpc/include/asm/vdso/gettimeofday.h29
-rw-r--r--arch/powerpc/include/asm/vdso/vsyscall.h10
-rw-r--r--arch/powerpc/include/asm/vdso_datapage.h78
-rw-r--r--arch/powerpc/include/asm/vga.h5
-rw-r--r--arch/powerpc/include/asm/video.h (renamed from arch/powerpc/include/asm/fb.h)8
-rw-r--r--arch/powerpc/include/asm/vio.h8
-rw-r--r--arch/powerpc/include/asm/vmalloc.h4
-rw-r--r--arch/powerpc/include/asm/word-at-a-time.h4
-rw-r--r--arch/powerpc/include/uapi/asm/bootx.h2
-rw-r--r--arch/powerpc/include/uapi/asm/kvm.h48
-rw-r--r--arch/powerpc/include/uapi/asm/papr_pdsm.h165
-rw-r--r--arch/powerpc/kernel/Makefile10
-rw-r--r--arch/powerpc/kernel/asm-offsets.c16
-rw-r--r--arch/powerpc/kernel/cacheinfo.c2
-rw-r--r--arch/powerpc/kernel/cpu_setup_6xx.S4
-rw-r--r--arch/powerpc/kernel/cpu_specs.h4
-rw-r--r--arch/powerpc/kernel/cpu_specs_40x.h280
-rw-r--r--arch/powerpc/kernel/cpu_specs_book3s_64.h34
-rw-r--r--arch/powerpc/kernel/crash_dump.c2
-rw-r--r--arch/powerpc/kernel/dexcr.c124
-rw-r--r--arch/powerpc/kernel/dma-iommu.c2
-rw-r--r--arch/powerpc/kernel/dt_cpu_ftrs.c22
-rw-r--r--arch/powerpc/kernel/eeh.c228
-rw-r--r--arch/powerpc/kernel/eeh_driver.c13
-rw-r--r--arch/powerpc/kernel/eeh_pe.c15
-rw-r--r--arch/powerpc/kernel/entry_32.S48
-rw-r--r--arch/powerpc/kernel/epapr_hcalls.S2
-rw-r--r--arch/powerpc/kernel/epapr_paravirt.c2
-rw-r--r--arch/powerpc/kernel/exceptions-64e.S4
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S17
-rw-r--r--arch/powerpc/kernel/fadump.c607
-rw-r--r--arch/powerpc/kernel/head_32.h12
-rw-r--r--arch/powerpc/kernel/head_40x.S721
-rw-r--r--arch/powerpc/kernel/head_64.S5
-rw-r--r--arch/powerpc/kernel/head_85xx.S70
-rw-r--r--arch/powerpc/kernel/head_8xx.S89
-rw-r--r--arch/powerpc/kernel/head_book3s_32.S148
-rw-r--r--arch/powerpc/kernel/head_booke.h3
-rw-r--r--arch/powerpc/kernel/idle.c2
-rw-r--r--arch/powerpc/kernel/interrupt.c10
-rw-r--r--arch/powerpc/kernel/iommu.c180
-rw-r--r--arch/powerpc/kernel/irq.c51
-rw-r--r--arch/powerpc/kernel/isa-bridge.c4
-rw-r--r--arch/powerpc/kernel/jump_label.c2
-rw-r--r--arch/powerpc/kernel/kgdb.c6
-rw-r--r--arch/powerpc/kernel/kprobes-ftrace.c3
-rw-r--r--arch/powerpc/kernel/kprobes.c101
-rw-r--r--arch/powerpc/kernel/misc_32.S66
-rw-r--r--arch/powerpc/kernel/misc_64.S12
-rw-r--r--arch/powerpc/kernel/module.c40
-rw-r--r--arch/powerpc/kernel/module_32.c2
-rw-r--r--arch/powerpc/kernel/module_64.c97
-rw-r--r--arch/powerpc/kernel/nvram_64.c8
-rw-r--r--arch/powerpc/kernel/optprobes.c4
-rw-r--r--arch/powerpc/kernel/pci-common.c2
-rw-r--r--arch/powerpc/kernel/pci-hotplug.c35
-rw-r--r--arch/powerpc/kernel/pci_32.c5
-rw-r--r--arch/powerpc/kernel/proc_powerpc.c37
-rw-r--r--arch/powerpc/kernel/process.c61
-rw-r--r--arch/powerpc/kernel/prom.c74
-rw-r--r--arch/powerpc/kernel/prom_init.c156
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-tm.c2
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-view.c7
-rw-r--r--arch/powerpc/kernel/rethook.c73
-rw-r--r--arch/powerpc/kernel/rtas.c25
-rw-r--r--arch/powerpc/kernel/rtas_flash.c1
-rw-r--r--arch/powerpc/kernel/secure_boot.c13
-rw-r--r--arch/powerpc/kernel/security.c2
-rw-r--r--arch/powerpc/kernel/secvar-sysfs.c2
-rw-r--r--arch/powerpc/kernel/setup-common.c85
-rw-r--r--arch/powerpc/kernel/setup.h2
-rw-r--r--arch/powerpc/kernel/setup_32.c12
-rw-r--r--arch/powerpc/kernel/setup_64.c11
-rw-r--r--arch/powerpc/kernel/smp.c25
-rw-r--r--arch/powerpc/kernel/stacktrace.c6
-rw-r--r--arch/powerpc/kernel/static_call.c4
-rw-r--r--arch/powerpc/kernel/syscall.c4
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl11
-rw-r--r--arch/powerpc/kernel/sysfs.c5
-rw-r--r--arch/powerpc/kernel/time.c29
-rw-r--r--arch/powerpc/kernel/trace/Makefile11
-rw-r--r--arch/powerpc/kernel/trace/ftrace.c312
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64_pg.c87
-rw-r--r--arch/powerpc/kernel/trace/ftrace_entry.S244
-rw-r--r--arch/powerpc/kernel/traps.c8
-rw-r--r--arch/powerpc/kernel/udbg.c6
-rw-r--r--arch/powerpc/kernel/udbg_16550.c46
-rw-r--r--arch/powerpc/kernel/vdso.c71
-rw-r--r--arch/powerpc/kernel/vdso/Makefile75
-rw-r--r--arch/powerpc/kernel/vdso/getrandom.S56
-rw-r--r--arch/powerpc/kernel/vdso/gettimeofday.S22
-rw-r--r--arch/powerpc/kernel/vdso/vdso32.lds.S7
-rw-r--r--arch/powerpc/kernel/vdso/vdso64.lds.S7
-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/vdso32_wrapper.S2
-rw-r--r--arch/powerpc/kernel/vdso64_wrapper.S2
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S5
-rw-r--r--arch/powerpc/kexec/Makefile6
-rw-r--r--arch/powerpc/kexec/core.c54
-rw-r--r--arch/powerpc/kexec/core_32.c1
-rw-r--r--arch/powerpc/kexec/core_64.c123
-rw-r--r--arch/powerpc/kexec/crash.c195
-rw-r--r--arch/powerpc/kexec/elf_64.c19
-rw-r--r--arch/powerpc/kexec/file_load_64.c416
-rw-r--r--arch/powerpc/kexec/ranges.c320
-rw-r--r--arch/powerpc/kexec/relocate_32.S2
-rw-r--r--arch/powerpc/kexec/vmcore_info.c32
-rw-r--r--arch/powerpc/kvm/Kconfig1
-rw-r--r--arch/powerpc/kvm/book3s.c16
-rw-r--r--arch/powerpc/kvm/book3s.h1
-rw-r--r--arch/powerpc/kvm/book3s_32_mmu_host.c7
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_host.c12
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c37
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c47
-rw-r--r--arch/powerpc/kvm/book3s_64_vio.c9
-rw-r--r--arch/powerpc/kvm/book3s_emulate.c4
-rw-r--r--arch/powerpc/kvm/book3s_hv.c252
-rw-r--r--arch/powerpc/kvm/book3s_hv.h3
-rw-r--r--arch/powerpc/kvm/book3s_hv_nested.c22
-rw-r--r--arch/powerpc/kvm/book3s_hv_nestedv2.c33
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_xics.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv_uvmem.c25
-rw-r--r--arch/powerpc/kvm/book3s_mmu_hpte.c8
-rw-r--r--arch/powerpc/kvm/book3s_pr.c22
-rw-r--r--arch/powerpc/kvm/book3s_xive.c2
-rw-r--r--arch/powerpc/kvm/book3s_xive_native.c2
-rw-r--r--arch/powerpc/kvm/e500.h2
-rw-r--r--arch/powerpc/kvm/e500_mmu_host.c214
-rw-r--r--arch/powerpc/kvm/powerpc.c34
-rw-r--r--arch/powerpc/kvm/test-guest-state-buffer.c3
-rw-r--r--arch/powerpc/kvm/trace_hv.h29
-rw-r--r--arch/powerpc/lib/Makefile10
-rw-r--r--arch/powerpc/lib/code-patching.c109
-rw-r--r--arch/powerpc/lib/copypage_power7.S12
-rw-r--r--arch/powerpc/lib/copyuser_power7.S12
-rw-r--r--arch/powerpc/lib/crc-t10dif-glue.c (renamed from arch/powerpc/crypto/crct10dif-vpmsum_glue.c)69
-rw-r--r--arch/powerpc/lib/crc32-glue.c92
-rw-r--r--arch/powerpc/lib/crc32-vpmsum_core.S (renamed from arch/powerpc/crypto/crc32-vpmsum_core.S)0
-rw-r--r--arch/powerpc/lib/crc32c-vpmsum_asm.S (renamed from arch/powerpc/crypto/crc32c-vpmsum_asm.S)0
-rw-r--r--arch/powerpc/lib/crct10dif-vpmsum_asm.S (renamed from arch/powerpc/crypto/crct10dif-vpmsum_asm.S)0
-rw-r--r--arch/powerpc/lib/crtsavres.S2
-rw-r--r--arch/powerpc/lib/feature-fixups.c10
-rw-r--r--arch/powerpc/lib/memcpy_power7.S10
-rw-r--r--arch/powerpc/lib/qspinlock.c10
-rw-r--r--arch/powerpc/lib/sstep.c35
-rw-r--r--arch/powerpc/lib/test-code-patching.c135
-rw-r--r--arch/powerpc/lib/test_emulate_step.c2
-rw-r--r--arch/powerpc/lib/vmx-helper.c2
-rw-r--r--arch/powerpc/mm/Makefile2
-rw-r--r--arch/powerpc/mm/book3s32/mmu.c18
-rw-r--r--arch/powerpc/mm/book3s64/Makefile2
-rw-r--r--arch/powerpc/mm/book3s64/hash_hugepage.c15
-rw-r--r--arch/powerpc/mm/book3s64/hash_utils.c378
-rw-r--r--arch/powerpc/mm/book3s64/hugetlbpage.c10
-rw-r--r--arch/powerpc/mm/book3s64/mmu_context.c2
-rw-r--r--arch/powerpc/mm/book3s64/pgtable.c58
-rw-r--r--arch/powerpc/mm/book3s64/radix_pgtable.c102
-rw-r--r--arch/powerpc/mm/book3s64/slb.c2
-rw-r--r--arch/powerpc/mm/book3s64/slice.c80
-rw-r--r--arch/powerpc/mm/cacheflush.c2
-rw-r--r--arch/powerpc/mm/drmem.c14
-rw-r--r--arch/powerpc/mm/fault.c47
-rw-r--r--arch/powerpc/mm/hugetlbpage.c461
-rw-r--r--arch/powerpc/mm/init-common.c16
-rw-r--r--arch/powerpc/mm/kasan/8xx.c21
-rw-r--r--arch/powerpc/mm/kasan/init_32.c2
-rw-r--r--arch/powerpc/mm/kasan/init_book3e_64.c10
-rw-r--r--arch/powerpc/mm/kasan/init_book3s_64.c4
-rw-r--r--arch/powerpc/mm/mem.c90
-rw-r--r--arch/powerpc/mm/mmu_context.c2
-rw-r--r--arch/powerpc/mm/mmu_decl.h24
-rw-r--r--arch/powerpc/mm/nohash/40x.c161
-rw-r--r--arch/powerpc/mm/nohash/44x.c2
-rw-r--r--arch/powerpc/mm/nohash/8xx.c85
-rw-r--r--arch/powerpc/mm/nohash/Makefile5
-rw-r--r--arch/powerpc/mm/nohash/book3e_pgtable.c6
-rw-r--r--arch/powerpc/mm/nohash/e500.c10
-rw-r--r--arch/powerpc/mm/nohash/kaslr_booke.c6
-rw-r--r--arch/powerpc/mm/nohash/kup.c2
-rw-r--r--arch/powerpc/mm/nohash/mmu_context.c21
-rw-r--r--arch/powerpc/mm/nohash/tlb.c409
-rw-r--r--arch/powerpc/mm/nohash/tlb_64e.c314
-rw-r--r--arch/powerpc/mm/nohash/tlb_low.S27
-rw-r--r--arch/powerpc/mm/nohash/tlb_low_64e.S428
-rw-r--r--arch/powerpc/mm/numa.c46
-rw-r--r--arch/powerpc/mm/pageattr.c28
-rw-r--r--arch/powerpc/mm/pgtable-frag.c10
-rw-r--r--arch/powerpc/mm/pgtable.c113
-rw-r--r--arch/powerpc/mm/pgtable_32.c60
-rw-r--r--arch/powerpc/mm/pgtable_64.c15
-rw-r--r--arch/powerpc/mm/ptdump/Makefile2
-rw-r--r--arch/powerpc/mm/ptdump/hashpagetable.c2
-rw-r--r--arch/powerpc/mm/ptdump/ptdump.c21
-rw-r--r--arch/powerpc/net/bpf_jit.h17
-rw-r--r--arch/powerpc/net/bpf_jit_comp.c863
-rw-r--r--arch/powerpc/net/bpf_jit_comp32.c156
-rw-r--r--arch/powerpc/net/bpf_jit_comp64.c267
-rw-r--r--arch/powerpc/perf/8xx-pmu.c2
-rw-r--r--arch/powerpc/perf/Makefile2
-rw-r--r--arch/powerpc/perf/callchain.c2
-rw-r--r--arch/powerpc/perf/callchain_32.c2
-rw-r--r--arch/powerpc/perf/callchain_64.c2
-rw-r--r--arch/powerpc/perf/core-book3s.c55
-rw-r--r--arch/powerpc/perf/hv-24x7.c10
-rw-r--r--arch/powerpc/perf/hv-gpci.c29
-rw-r--r--arch/powerpc/perf/internal.h1
-rw-r--r--arch/powerpc/perf/power10-pmu.c30
-rw-r--r--arch/powerpc/perf/vpa-pmu.c203
-rw-r--r--arch/powerpc/platforms/40x/Kconfig78
-rw-r--r--arch/powerpc/platforms/40x/Makefile2
-rw-r--r--arch/powerpc/platforms/40x/ppc40x_simple.c77
-rw-r--r--arch/powerpc/platforms/44x/Makefile6
-rw-r--r--arch/powerpc/platforms/44x/cpm.c (renamed from arch/powerpc/platforms/4xx/cpm.c)0
-rw-r--r--arch/powerpc/platforms/44x/gpio.c (renamed from arch/powerpc/platforms/4xx/gpio.c)0
-rw-r--r--arch/powerpc/platforms/44x/hsta_msi.c (renamed from arch/powerpc/platforms/4xx/hsta_msi.c)0
-rw-r--r--arch/powerpc/platforms/44x/machine_check.c15
-rw-r--r--arch/powerpc/platforms/44x/pci.c (renamed from arch/powerpc/platforms/4xx/pci.c)123
-rw-r--r--arch/powerpc/platforms/44x/pci.h (renamed from arch/powerpc/platforms/4xx/pci.h)0
-rw-r--r--arch/powerpc/platforms/44x/ppc476.c2
-rw-r--r--arch/powerpc/platforms/44x/soc.c (renamed from arch/powerpc/platforms/4xx/soc.c)0
-rw-r--r--arch/powerpc/platforms/44x/uic.c (renamed from arch/powerpc/platforms/4xx/uic.c)0
-rw-r--r--arch/powerpc/platforms/44x/warp.c1
-rw-r--r--arch/powerpc/platforms/4xx/Makefile7
-rw-r--r--arch/powerpc/platforms/4xx/machine_check.c23
-rw-r--r--arch/powerpc/platforms/512x/mpc512x_generic.c4
-rw-r--r--arch/powerpc/platforms/512x/mpc512x_lpbfifo.c2
-rw-r--r--arch/powerpc/platforms/512x/mpc512x_shared.c2
-rw-r--r--arch/powerpc/platforms/52xx/efika.c5
-rw-r--r--arch/powerpc/platforms/52xx/lite5200.c10
-rw-r--r--arch/powerpc/platforms/52xx/lite5200_sleep.S6
-rw-r--r--arch/powerpc/platforms/52xx/mpc5200_simple.c10
-rw-r--r--arch/powerpc/platforms/52xx/mpc52xx_common.c2
-rw-r--r--arch/powerpc/platforms/52xx/mpc52xx_gpt.c3
-rw-r--r--arch/powerpc/platforms/82xx/ep8248e.c2
-rw-r--r--arch/powerpc/platforms/82xx/km82xx.c6
-rw-r--r--arch/powerpc/platforms/83xx/mpc830x_rdb.c10
-rw-r--r--arch/powerpc/platforms/83xx/mpc831x_rdb.c10
-rw-r--r--arch/powerpc/platforms/83xx/mpc837x_rdb.c10
-rw-r--r--arch/powerpc/platforms/83xx/suspend-asm.S6
-rw-r--r--arch/powerpc/platforms/83xx/suspend.c3
-rw-r--r--arch/powerpc/platforms/85xx/Kconfig21
-rw-r--r--arch/powerpc/platforms/85xx/bsc913x_qds.c2
-rw-r--r--arch/powerpc/platforms/85xx/bsc913x_rdb.c2
-rw-r--r--arch/powerpc/platforms/85xx/corenet_generic.c2
-rw-r--r--arch/powerpc/platforms/85xx/ge_imp3a.c2
-rw-r--r--arch/powerpc/platforms/85xx/sgy_cts1000.c4
-rw-r--r--arch/powerpc/platforms/85xx/smp.c11
-rw-r--r--arch/powerpc/platforms/85xx/t1042rdb_diu.c1
-rw-r--r--arch/powerpc/platforms/85xx/tqm85xx.c10
-rw-r--r--arch/powerpc/platforms/86xx/mpc86xx_smp.c2
-rw-r--r--arch/powerpc/platforms/8xx/Kconfig7
-rw-r--r--arch/powerpc/platforms/8xx/cpm1.c119
-rw-r--r--arch/powerpc/platforms/Kconfig2
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype39
-rw-r--r--arch/powerpc/platforms/Makefile3
-rw-r--r--arch/powerpc/platforms/amigaone/setup.c8
-rw-r--r--arch/powerpc/platforms/book3s/vas-api.c36
-rw-r--r--arch/powerpc/platforms/cell/axon_msi.c2
-rw-r--r--arch/powerpc/platforms/cell/cbe_powerbutton.c1
-rw-r--r--arch/powerpc/platforms/cell/cbe_thermal.c1
-rw-r--r--arch/powerpc/platforms/cell/cpufreq_spudemand.c1
-rw-r--r--arch/powerpc/platforms/cell/iommu.c66
-rw-r--r--arch/powerpc/platforms/cell/smp.c3
-rw-r--r--arch/powerpc/platforms/cell/spu_syscalls.c68
-rw-r--r--arch/powerpc/platforms/cell/spufs/coredump.c4
-rw-r--r--arch/powerpc/platforms/cell/spufs/file.c37
-rw-r--r--arch/powerpc/platforms/cell/spufs/inode.c1
-rw-r--r--arch/powerpc/platforms/cell/spufs/sched.c2
-rw-r--r--arch/powerpc/platforms/chrp/nvram.c1
-rw-r--r--arch/powerpc/platforms/chrp/pegasos_eth.c7
-rw-r--r--arch/powerpc/platforms/embedded6xx/linkstation.c4
-rw-r--r--arch/powerpc/platforms/embedded6xx/mpc10x.h3
-rw-r--r--arch/powerpc/platforms/embedded6xx/mvme5100.c1
-rw-r--r--arch/powerpc/platforms/maple/Kconfig19
-rw-r--r--arch/powerpc/platforms/maple/maple.h15
-rw-r--r--arch/powerpc/platforms/maple/pci.c672
-rw-r--r--arch/powerpc/platforms/maple/setup.c363
-rw-r--r--arch/powerpc/platforms/maple/time.c170
-rw-r--r--arch/powerpc/platforms/pasemi/gpio_mdio.c4
-rw-r--r--arch/powerpc/platforms/pasemi/pasemi.h1
-rw-r--r--arch/powerpc/platforms/pasemi/pci.c4
-rw-r--r--arch/powerpc/platforms/powermac/Kconfig2
-rw-r--r--arch/powerpc/platforms/powermac/backlight.c40
-rw-r--r--arch/powerpc/platforms/powermac/feature.c2
-rw-r--r--arch/powerpc/platforms/powermac/nvram.c5
-rw-r--r--arch/powerpc/platforms/powermac/pfunc_base.c2
-rw-r--r--arch/powerpc/platforms/powermac/pic.c2
-rw-r--r--arch/powerpc/platforms/powermac/sleep.S2
-rw-r--r--arch/powerpc/platforms/powermac/smp.c4
-rw-r--r--arch/powerpc/platforms/powernv/eeh-powernv.c3
-rw-r--r--arch/powerpc/platforms/powernv/idle.c2
-rw-r--r--arch/powerpc/platforms/powernv/memtrace.c31
-rw-r--r--arch/powerpc/platforms/powernv/opal-core.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal-dump.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal-elog.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal-fadump.c35
-rw-r--r--arch/powerpc/platforms/powernv/opal-irqchip.c1
-rw-r--r--arch/powerpc/platforms/powernv/opal-kmsg.c4
-rw-r--r--arch/powerpc/platforms/powernv/opal-lpc.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal-prd.c5
-rw-r--r--arch/powerpc/platforms/powernv/opal.c15
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda.c6
-rw-r--r--arch/powerpc/platforms/powernv/pci-sriov.c4
-rw-r--r--arch/powerpc/platforms/powernv/pci.h1
-rw-r--r--arch/powerpc/platforms/powernv/smp.c9
-rw-r--r--arch/powerpc/platforms/powernv/vas-window.c2
-rw-r--r--arch/powerpc/platforms/ps3/Kconfig1
-rw-r--r--arch/powerpc/platforms/ps3/device-init.c63
-rw-r--r--arch/powerpc/platforms/ps3/hvcall.S298
-rw-r--r--arch/powerpc/platforms/ps3/interrupt.c2
-rw-r--r--arch/powerpc/platforms/ps3/repository.c2
-rw-r--r--arch/powerpc/platforms/ps3/setup.c5
-rw-r--r--arch/powerpc/platforms/ps3/system-bus.c13
-rw-r--r--arch/powerpc/platforms/pseries/Kconfig14
-rw-r--r--arch/powerpc/platforms/pseries/Makefile1
-rw-r--r--arch/powerpc/platforms/pseries/dlpar.c234
-rw-r--r--arch/powerpc/platforms/pseries/dtl.c9
-rw-r--r--arch/powerpc/platforms/pseries/eeh_pseries.c45
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-cpu.c7
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-memory.c16
-rw-r--r--arch/powerpc/platforms/pseries/ibmebus.c6
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c797
-rw-r--r--arch/powerpc/platforms/pseries/kexec.c8
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c15
-rw-r--r--arch/powerpc/platforms/pseries/lparcfg.c60
-rw-r--r--arch/powerpc/platforms/pseries/mobility.c2
-rw-r--r--arch/powerpc/platforms/pseries/msi.c12
-rw-r--r--arch/powerpc/platforms/pseries/papr-vpd.c5
-rw-r--r--arch/powerpc/platforms/pseries/papr_platform_attributes.c8
-rw-r--r--arch/powerpc/platforms/pseries/papr_scm.c53
-rw-r--r--arch/powerpc/platforms/pseries/pci.c27
-rw-r--r--arch/powerpc/platforms/pseries/pci_dlpar.c14
-rw-r--r--arch/powerpc/platforms/pseries/plpks.c12
-rw-r--r--arch/powerpc/platforms/pseries/pmem.c2
-rw-r--r--arch/powerpc/platforms/pseries/pseries.h1
-rw-r--r--arch/powerpc/platforms/pseries/rtas-fadump.c322
-rw-r--r--arch/powerpc/platforms/pseries/rtas-fadump.h29
-rw-r--r--arch/powerpc/platforms/pseries/setup.c17
-rw-r--r--arch/powerpc/platforms/pseries/smp.c2
-rw-r--r--arch/powerpc/platforms/pseries/svm.c1
-rw-r--r--arch/powerpc/platforms/pseries/vas-sysfs.c4
-rw-r--r--arch/powerpc/platforms/pseries/vas.c24
-rw-r--r--arch/powerpc/platforms/pseries/vio.c77
-rw-r--r--arch/powerpc/purgatory/Makefile3
-rw-r--r--arch/powerpc/sysdev/Kconfig4
-rw-r--r--arch/powerpc/sysdev/Makefile2
-rw-r--r--arch/powerpc/sysdev/dart_iommu.c4
-rw-r--r--arch/powerpc/sysdev/fsl_gtm.c6
-rw-r--r--arch/powerpc/sysdev/fsl_msi.c8
-rw-r--r--arch/powerpc/sysdev/mpic.c2
-rw-r--r--arch/powerpc/sysdev/msi_bitmap.c5
-rw-r--r--arch/powerpc/sysdev/pmi.c4
-rw-r--r--arch/powerpc/sysdev/rtc_cmos_setup.c1
-rw-r--r--arch/powerpc/sysdev/xive/common.c6
-rw-r--r--arch/powerpc/sysdev/xive/native.c6
-rw-r--r--arch/powerpc/sysdev/xive/spapr.c4
-rw-r--r--arch/powerpc/tools/.gitignore (renamed from arch/powerpc/platforms/maple/Makefile)2
-rw-r--r--arch/powerpc/tools/Makefile10
-rwxr-xr-xarch/powerpc/tools/ftrace-gen-ool-stubs.sh52
-rwxr-xr-xarch/powerpc/tools/ftrace_check.sh50
-rw-r--r--arch/powerpc/xmon/Makefile2
-rw-r--r--arch/powerpc/xmon/ppc-dis.c33
-rw-r--r--arch/powerpc/xmon/xmon.c34
575 files changed, 17475 insertions, 14964 deletions
diff --git a/arch/powerpc/Kbuild b/arch/powerpc/Kbuild
index 22cd0d55a892..b010ccb071b6 100644
--- a/arch/powerpc/Kbuild
+++ b/arch/powerpc/Kbuild
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror -Wa,--fatal-warnings
+subdir-asflags-$(CONFIG_PPC_WERROR) := -Wa,--fatal-warnings
obj-y += kernel/
obj-y += mm/
@@ -18,4 +19,4 @@ obj-$(CONFIG_KEXEC_CORE) += kexec/
obj-$(CONFIG_KEXEC_FILE) += purgatory/
# for cleaning
-subdir- += boot
+subdir- += boot tools
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b9fc064d38d2..424f188e62d9 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -127,16 +127,19 @@ config PPC
select ARCH_ENABLE_MEMORY_HOTPLUG
select ARCH_ENABLE_MEMORY_HOTREMOVE
select ARCH_HAS_COPY_MC if PPC64
+ select ARCH_HAS_CRC32 if PPC64 && ALTIVEC
+ select ARCH_HAS_CRC_T10DIF if PPC64 && ALTIVEC
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DEBUG_WX if STRICT_KERNEL_RWX
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_DMA_MAP_DIRECT if PPC_PSERIES
+ select ARCH_HAS_DMA_OPS if PPC64
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_HUGEPD if HUGETLB_PAGE
select ARCH_HAS_KCOV
+ select ARCH_HAS_KERNEL_FPU_SUPPORT if PPC64 && PPC_FPU
select ARCH_HAS_MEMBARRIER_CALLBACKS
select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_MEMREMAP_COMPAT_ALIGN if PPC_64S_HASH_MMU
@@ -144,18 +147,20 @@ config PPC
select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
select ARCH_HAS_PHYS_TO_DMA
select ARCH_HAS_PMEM_API
+ select ARCH_HAS_PREEMPT_LAZY
select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
select ARCH_HAS_SET_MEMORY
- select ARCH_HAS_STRICT_KERNEL_RWX if (PPC_BOOK3S || PPC_8xx || 40x) && !HIBERNATION
+ select ARCH_HAS_STRICT_KERNEL_RWX if (PPC_BOOK3S || PPC_8xx) && !HIBERNATION
select ARCH_HAS_STRICT_KERNEL_RWX if PPC_85xx && !HIBERNATION && !RANDOMIZE_BASE
select ARCH_HAS_STRICT_MODULE_RWX if ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_HAS_SYSCALL_WRAPPER if !SPU_BASE && !COMPAT
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_HAS_UACCESS_FLUSHCACHE
- select ARCH_HAS_UBSAN_SANITIZE_ALL
+ select ARCH_HAS_UBSAN
select ARCH_HAVE_NMI_SAFE_CMPXCHG
+ select ARCH_HAVE_EXTRA_ELF_NOTES if SPU_BASE
select ARCH_KEEP_MEMBLOCK
select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE if PPC_RADIX_MMU
select ARCH_MIGHT_HAVE_PC_PARPORT
@@ -165,7 +170,7 @@ config PPC
select ARCH_SPLIT_ARG64 if PPC32
select ARCH_STACKWALK
select ARCH_SUPPORTS_ATOMIC_RMW
- select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx || 40x
+ select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_CMPXCHG_LOCKREF if PPC64
select ARCH_USE_MEMTEST
@@ -184,7 +189,6 @@ config PPC
select CPUMASK_OFFSTACK if NR_CPUS >= 8192
select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
select DMA_OPS_BYPASS if PPC64
- select DMA_OPS if PPC64
select DYNAMIC_FTRACE if FUNCTION_TRACER
select EDAC_ATOMIC_SCRUB
select EDAC_SUPPORT
@@ -212,7 +216,7 @@ config PPC
select HAVE_ARCH_HUGE_VMAP if PPC_RADIX_MMU || PPC_8xx
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_JUMP_LABEL_RELATIVE
- select HAVE_ARCH_KASAN if PPC32 && PPC_PAGE_SHIFT <= 14
+ select HAVE_ARCH_KASAN if PPC32 && PAGE_SHIFT <= 14
select HAVE_ARCH_KASAN if PPC_RADIX_MMU
select HAVE_ARCH_KASAN if PPC_BOOK3E_64
select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN
@@ -233,16 +237,19 @@ config PPC
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_ARGS if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
+ select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if PPC_FTRACE_OUT_OF_LINE || (PPC32 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
+ select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
select HAVE_DYNAMIC_FTRACE_WITH_REGS if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
select HAVE_EBPF_JIT
select HAVE_EFFICIENT_UNALIGNED_ACCESS
- select HAVE_FAST_GUP
+ select HAVE_GUP_FAST
+ select HAVE_FTRACE_GRAPH_FUNC
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_ARG_ACCESS_API
select HAVE_FUNCTION_DESCRIPTORS if PPC64_ELF_ABI_V1
select HAVE_FUNCTION_ERROR_INJECTION
select HAVE_FUNCTION_GRAPH_TRACER
- select HAVE_FUNCTION_TRACER if PPC64 || (PPC32 && CC_IS_GCC)
+ select HAVE_FUNCTION_TRACER if !COMPILE_TEST && (PPC64 || (PPC32 && CC_IS_GCC))
select HAVE_GCC_PLUGINS if GCC_VERSION >= 50200 # plugin support on gcc <= 5.1 is buggy on PPC
select HAVE_GENERIC_VDSO
select HAVE_HARDLOCKUP_DETECTOR_ARCH if PPC_BOOK3S_64 && SMP
@@ -268,13 +275,16 @@ config PPC
select HAVE_PERF_EVENTS_NMI if PPC64
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
+ select HAVE_RETHOOK if KPROBES
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE
select HAVE_RSEQ
+ select HAVE_SAMPLE_FTRACE_DIRECT if HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ select HAVE_SAMPLE_FTRACE_DIRECT_MULTI if HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
select HAVE_SETUP_PER_CPU_AREA if PPC64
select HAVE_SOFTIRQ_ON_OWN_STACK
- select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
- select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
+ select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,$(m32-flag) -mstack-protector-guard=tls -mstack-protector-guard-reg=r2 -mstack-protector-guard-offset=0)
+ select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,$(m64-flag) -mstack-protector-guard=tls -mstack-protector-guard-reg=r13 -mstack-protector-guard-offset=0)
select HAVE_STATIC_CALL if PPC32
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING
@@ -285,7 +295,7 @@ config PPC
select IOMMU_HELPER if PPC64
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
- select KASAN_VMALLOC if KASAN && MODULES
+ select KASAN_VMALLOC if KASAN && EXECMEM
select LOCK_MM_AND_FIND_VMA
select MMU_GATHER_PAGE_SIZE
select MMU_GATHER_RCU_TABLE_FREE
@@ -310,6 +320,7 @@ config PPC
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
select TRACE_IRQFLAGS_SUPPORT
+ select VDSO_GETRANDOM
#
# Please keep this list sorted alphabetically.
#
@@ -333,7 +344,6 @@ config PANIC_TIMEOUT
config COMPAT
bool "Enable support for 32bit binaries"
depends on PPC64
- depends on !CC_IS_CLANG || CLANG_VERSION >= 120000
default y if !CPU_LITTLE_ENDIAN
select ARCH_WANT_OLD_COMPAT_IPC
select COMPAT_OLD_SIGACTION
@@ -388,7 +398,7 @@ config ARCH_SUSPEND_POSSIBLE
def_bool y
depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \
(PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
- || 44x || 40x
+ || 44x
config ARCH_SUSPEND_NONZERO_CPU
def_bool y
@@ -442,7 +452,7 @@ config ARCH_SUPPORTS_UPROBES
config PPC_ADV_DEBUG_REGS
bool
- depends on 40x || BOOKE
+ depends on BOOKE
default y
config PPC_ADV_DEBUG_IACS
@@ -489,7 +499,7 @@ source "kernel/Kconfig.hz"
config MATH_EMULATION
bool "Math emulation"
- depends on 4xx || PPC_8xx || PPC_MPC832x || BOOKE || PPC_MICROWATT
+ depends on 44x || PPC_8xx || PPC_MPC832x || BOOKE || PPC_MICROWATT
select PPC_FPU_REGS
help
Some PowerPC chips designed for embedded applications do not have
@@ -567,6 +577,22 @@ config ARCH_USING_PATCHABLE_FUNCTION_ENTRY
def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN
def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN
+config PPC_FTRACE_OUT_OF_LINE
+ def_bool PPC64 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+ select ARCH_WANTS_PRE_LINK_VMLINUX
+
+config PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE
+ int "Number of ftrace out-of-line stubs to reserve within .text"
+ depends on PPC_FTRACE_OUT_OF_LINE
+ default 32768
+ help
+ Number of stubs to reserve for use by ftrace. This space is
+ reserved within .text, and is distinct from any additional space
+ added at the end of .text before the final vmlinux link. Set to
+ zero to have stubs only be generated at the end of vmlinux (only
+ if the size of vmlinux is less than 32MB). Set to a higher value
+ if building vmlinux larger than 48MB.
+
config HOTPLUG_CPU
bool "Support for enabling/disabling CPUs"
depends on SMP && (PPC_PSERIES || \
@@ -682,16 +708,22 @@ config RELOCATABLE_TEST
config ARCH_SUPPORTS_CRASH_DUMP
def_bool PPC64 || PPC_BOOK3S_32 || PPC_85xx || (44x && !SMP)
+config ARCH_DEFAULT_CRASH_DUMP
+ bool
+ default y if !PPC_BOOK3S_32
+
config ARCH_SELECTS_CRASH_DUMP
def_bool y
depends on CRASH_DUMP
select RELOCATABLE if PPC64 || 44x || PPC_85xx
+config ARCH_SUPPORTS_CRASH_HOTPLUG
+ def_bool y
+ depends on PPC64
+
config FA_DUMP
bool "Firmware-assisted dump"
- depends on PPC64 && (PPC_RTAS || PPC_POWERNV)
- select CRASH_CORE
- select CRASH_DUMP
+ depends on CRASH_DUMP && PPC64 && (PPC_RTAS || PPC_POWERNV)
help
A robust mechanism to get reliable kernel crash dump with
assistance from firmware. This approach does not use kexec,
@@ -809,19 +841,23 @@ choice
config PPC_4K_PAGES
bool "4k page size"
select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
+ select HAVE_PAGE_SIZE_4KB
config PPC_16K_PAGES
bool "16k page size"
depends on 44x || PPC_8xx
+ select HAVE_PAGE_SIZE_16KB
config PPC_64K_PAGES
bool "64k page size"
depends on 44x || PPC_BOOK3S_64
select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
+ select HAVE_PAGE_SIZE_64KB
config PPC_256K_PAGES
bool "256k page size (Requires non-standard binutils settings)"
depends on 44x && !PPC_47x
+ select HAVE_PAGE_SIZE_256KB
help
Make the page size 256k.
@@ -832,29 +868,6 @@ config PPC_256K_PAGES
endchoice
-config PAGE_SIZE_4KB
- def_bool y
- depends on PPC_4K_PAGES
-
-config PAGE_SIZE_16KB
- def_bool y
- depends on PPC_16K_PAGES
-
-config PAGE_SIZE_64KB
- def_bool y
- depends on PPC_64K_PAGES
-
-config PAGE_SIZE_256KB
- def_bool y
- depends on PPC_256K_PAGES
-
-config PPC_PAGE_SHIFT
- int
- default 18 if PPC_256K_PAGES
- default 16 if PPC_64K_PAGES
- default 14 if PPC_16K_PAGES
- default 12
-
config THREAD_SHIFT
int "Thread shift" if EXPERT
range 13 15
@@ -870,8 +883,8 @@ config DATA_SHIFT_BOOL
bool "Set custom data alignment"
depends on ADVANCED_OPTIONS
depends on STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE
- depends on PPC_BOOK3S_32 || (PPC_8xx && !PIN_TLB_DATA && !STRICT_KERNEL_RWX) || \
- PPC_85xx
+ depends on (PPC_8xx && !PIN_TLB_DATA && (!STRICT_KERNEL_RWX || !PIN_TLB_TEXT)) || \
+ PPC_BOOK3S_32 || PPC_85xx
help
This option allows you to set the kernel data alignment. When
RAM is mapped by blocks, the alignment needs to fit the size and
@@ -887,11 +900,11 @@ config DATA_SHIFT
range 20 24 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_85xx
default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default 18 if (DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32
- default 23 if STRICT_KERNEL_RWX && PPC_8xx
- default 23 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && PIN_TLB_DATA
- default 19 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
+ default 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && \
+ (PIN_TLB_DATA || PIN_TLB_TEXT)
+ default 19 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
default 24 if STRICT_KERNEL_RWX && PPC_85xx
- default PPC_PAGE_SHIFT
+ default PAGE_SHIFT
help
On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO.
Smaller is the alignment, greater is the number of necessary DBATs.
@@ -981,7 +994,8 @@ config CMDLINE
most cases you will need to specify the root device here.
choice
- prompt "Kernel command line type" if CMDLINE != ""
+ prompt "Kernel command line type"
+ depends on CMDLINE != ""
default CMDLINE_FROM_BOOTLOADER
config CMDLINE_FROM_BOOTLOADER
@@ -1042,6 +1056,10 @@ config PPC_MEM_KEYS
If unsure, say y.
+config ARCH_PKEY_BITS
+ int
+ default 5
+
config PPC_SECURE_BOOT
prompt "Enable secure boot support"
bool
@@ -1093,7 +1111,7 @@ config GENERIC_ISA_DMA
config PPC_INDIRECT_PCI
bool
depends on PCI
- default y if 40x || 44x
+ default y if 44x
config SBUS
bool
@@ -1118,15 +1136,12 @@ config FSL_PMC
config PPC4xx_CPM
bool
default y
- depends on SUSPEND && (44x || 40x)
+ depends on SUSPEND && 44x
help
PPC4xx Clock Power Management (CPM) support (suspend/resume).
It also enables support for two different idle states (idle-wait
and idle-doze).
-config 4xx_SOC
- bool
-
config FSL_LBC
bool "Freescale Local Bus support"
help
@@ -1288,10 +1303,37 @@ config TASK_SIZE_BOOL
config TASK_SIZE
hex "Size of user task space" if TASK_SIZE_BOOL
default "0x80000000" if PPC_8xx
- default "0xb0000000" if PPC_BOOK3S_32
+ default "0xb0000000" if PPC_BOOK3S_32 && EXECMEM
default "0xc0000000"
+
+config MODULES_SIZE_BOOL
+ bool "Set custom size for modules/execmem area"
+ depends on EXECMEM && ADVANCED_OPTIONS
+ help
+ This option allows you to set the size of kernel virtual address
+ space dedicated for modules/execmem.
+ For the time being it is only for 8xx and book3s/32. Other
+ platform share it with vmalloc space.
+
+ Say N here unless you know what you are doing.
+
+config MODULES_SIZE
+ int "Size of modules/execmem area (In Mbytes)" if MODULES_SIZE_BOOL
+ range 1 256 if EXECMEM
+ default 64 if EXECMEM && PPC_BOOK3S_32
+ default 32 if EXECMEM && PPC_8xx
+ default 0
+
endmenu
+config PPC64_PROC_SYSTEMCFG
+ def_bool y
+ depends on PPC64 && PROC_FS
+ help
+ This option enables the presence of /proc/ppc64/systemcfg through
+ which the systemcfg page can be accessed.
+ This interface only exists for backwards-compatibility.
+
if PPC64
# This value must have zeroes in the bottom 60 bits otherwise lots will break
config PAGE_OFFSET
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 8c80b154e814..20d05605fa83 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -223,12 +223,6 @@ config PPC_EARLY_DEBUG_RTAS_CONSOLE
help
Select this to enable early debugging via the RTAS console.
-config PPC_EARLY_DEBUG_MAPLE
- bool "Maple real mode"
- depends on PPC_MAPLE
- help
- Select this to enable early debugging for Maple.
-
config PPC_EARLY_DEBUG_PAS_REALMODE
bool "PA Semi real mode"
depends on PPC_PASEMI
@@ -244,14 +238,6 @@ config PPC_EARLY_DEBUG_44x
inbuilt serial port. If you enable this, ensure you set
PPC_EARLY_DEBUG_44x_PHYSLOW below to suit your target board.
-config PPC_EARLY_DEBUG_40x
- bool "Early serial debugging for IBM/AMCC 40x CPUs"
- depends on 40x
- help
- Select this to enable early debugging for IBM 40x chips via the
- inbuilt serial port. This works on chips with a 16550 compatible
- UART.
-
config PPC_EARLY_DEBUG_CPM
bool "Early serial debugging for Freescale CPM-based serial ports"
depends on SERIAL_CPM=y
@@ -356,11 +342,6 @@ config PPC_EARLY_DEBUG_44x_PHYSHIGH
depends on PPC_EARLY_DEBUG_44x
default "0x1"
-config PPC_EARLY_DEBUG_40x_PHYSADDR
- hex "Early debug UART physical address"
- depends on PPC_EARLY_DEBUG_40x
- default "0xef600300"
-
config PPC_EARLY_DEBUG_CPM_ADDR
hex "CPM UART early debug transmit descriptor address"
depends on PPC_EARLY_DEBUG_CPM
@@ -392,12 +373,6 @@ config FAIL_IOMMU
If you are unsure, say N.
-config PPC_FAST_ENDIAN_SWITCH
- bool "Deprecated fast endian-switch syscall"
- depends on DEBUG_KERNEL && PPC_BOOK3S_64
- help
- If you're unsure what this is, say N.
-
config KASAN_SHADOW_OFFSET
hex
depends on KASAN
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 051247027da0..f3804103c56c 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -62,14 +62,14 @@ KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
endif
ifdef CONFIG_CPU_LITTLE_ENDIAN
-KBUILD_CFLAGS += -mlittle-endian
+KBUILD_CPPFLAGS += -mlittle-endian
KBUILD_LDFLAGS += -EL
LDEMULATION := lppc
GNUTARGET := powerpcle
MULTIPLEWORD := -mno-multiple
KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect)
else
-KBUILD_CFLAGS += $(call cc-option,-mbig-endian)
+KBUILD_CPPFLAGS += $(call cc-option,-mbig-endian)
KBUILD_LDFLAGS += -EB
LDEMULATION := ppc
GNUTARGET := powerpc
@@ -95,18 +95,11 @@ aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian
ifeq ($(HAS_BIARCH),y)
-KBUILD_CFLAGS += -m$(BITS)
+KBUILD_CPPFLAGS += -m$(BITS)
KBUILD_AFLAGS += -m$(BITS)
KBUILD_LDFLAGS += -m elf$(BITS)$(LDEMULATION)
endif
-cflags-$(CONFIG_STACKPROTECTOR) += -mstack-protector-guard=tls
-ifdef CONFIG_PPC64
-cflags-$(CONFIG_STACKPROTECTOR) += -mstack-protector-guard-reg=r13
-else
-cflags-$(CONFIG_STACKPROTECTOR) += -mstack-protector-guard-reg=r2
-endif
-
LDFLAGS_vmlinux-y := -Bstatic
LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie
LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) += -z notext
@@ -114,7 +107,6 @@ LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y)
ifdef CONFIG_PPC64
ifndef CONFIG_PPC_KERNEL_PCREL
-ifeq ($(call cc-option-yn,-mcmodel=medium),y)
# -mcmodel=medium breaks modules because it uses 32bit offsets from
# the TOC pointer to create pointers where possible. Pointers into the
# percpu data area are created by this method.
@@ -124,9 +116,6 @@ ifeq ($(call cc-option-yn,-mcmodel=medium),y)
# kernel percpu data space (starting with 0xc...). We need a full
# 64bit relocation for this to work, hence -mcmodel=large.
KBUILD_CFLAGS_MODULE += -mcmodel=large
-else
- export NO_MINIMAL_TOC := -mno-minimal-toc
-endif
endif
endif
@@ -139,24 +128,35 @@ CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1)
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc)
endif
endif
-CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
+CFLAGS-$(CONFIG_PPC64) += -mcmodel=medium
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions)
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mlong-double-128)
# Clang unconditionally reserves r2 on ppc32 and does not support the flag
-# https://bugs.llvm.org/show_bug.cgi?id=39555
+# https://llvm.org/pr39555
CFLAGS-$(CONFIG_PPC32) := $(call cc-option, -ffixed-r2)
# Clang doesn't support -mmultiple / -mno-multiple
-# https://bugs.llvm.org/show_bug.cgi?id=39556
+# https://llvm.org/pr39556
CFLAGS-$(CONFIG_PPC32) += $(call cc-option, $(MULTIPLEWORD))
CFLAGS-$(CONFIG_PPC32) += $(call cc-option,-mno-readonly-in-sdata)
+CC_FLAGS_FPU := $(call cc-option,-mhard-float)
+CC_FLAGS_NO_FPU := $(call cc-option,-msoft-float)
+
ifdef CONFIG_FUNCTION_TRACER
ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
+ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+CC_FLAGS_FTRACE := -fpatchable-function-entry=1
+else
+ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS # PPC32 only
+CC_FLAGS_FTRACE := -fpatchable-function-entry=3,1
+else
CC_FLAGS_FTRACE := -fpatchable-function-entry=2
+endif
+endif
else
CC_FLAGS_FTRACE := -pg
ifdef CONFIG_MPROFILE_KERNEL
@@ -174,9 +174,8 @@ asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
KBUILD_CPPFLAGS += -I $(srctree)/arch/powerpc $(asinstr)
KBUILD_AFLAGS += $(AFLAGS-y)
-KBUILD_CFLAGS += $(call cc-option,-msoft-float)
+KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU)
KBUILD_CFLAGS += $(CFLAGS-y)
-CPP = $(CC) -E $(KBUILD_CFLAGS)
CHECKFLAGS += -m$(BITS) -D__powerpc__ -D__powerpc$(BITS)__
ifdef CONFIG_CPU_BIG_ENDIAN
@@ -219,18 +218,6 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
# often slow when they are implemented at all
KBUILD_CFLAGS += $(call cc-option,-mno-string)
-cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec)
-
-# When using '-many -mpower4' gas will first try and find a matching power4
-# mnemonic and failing that it will allow any valid mnemonic that GAS knows
-# about. GCC will pass -many to GAS when assembling, clang does not.
-# LLVM IAS doesn't understand either flag: https://github.com/ClangBuiltLinux/linux/issues/675
-# but LLVM IAS only supports ISA >= 2.06 for Book3S 64 anyway...
-cpu-as-$(CONFIG_PPC_BOOK3S_64) += $(call as-option,-Wa$(comma)-mpower4) $(call as-option,-Wa$(comma)-many)
-
-KBUILD_AFLAGS += $(cpu-as-y)
-KBUILD_CFLAGS += $(cpu-as-y)
-
KBUILD_AFLAGS += $(aflags-y)
KBUILD_CFLAGS += $(cflags-y)
@@ -314,6 +301,21 @@ ppc32_allmodconfig:
$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/book3s_32.config \
-f $(srctree)/Makefile allmodconfig
+generated_configs += ppc44x_allmodconfig
+ppc44x_allmodconfig:
+ $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/44x.config \
+ -f $(srctree)/Makefile allmodconfig
+
+generated_configs += ppc8xx_allmodconfig
+ppc8xx_allmodconfig:
+ $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/8xx.config \
+ -f $(srctree)/Makefile allmodconfig
+
+generated_configs += ppc85xx_allmodconfig
+ppc85xx_allmodconfig:
+ $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/85xx-32bit.config \
+ -f $(srctree)/Makefile allmodconfig
+
generated_configs += ppc_defconfig
ppc_defconfig:
$(call merge_into_defconfig,book3s_32.config,)
@@ -357,7 +359,7 @@ define archhelp
echo ' install - Install kernel using'
echo ' (your) ~/bin/$(INSTALLKERNEL) or'
echo ' (distribution) /sbin/$(INSTALLKERNEL) or'
- echo ' install to $$(INSTALL_PATH) and run lilo'
+ echo ' install to $$(INSTALL_PATH)'
echo ' *_defconfig - Select default config from arch/powerpc/configs'
echo ''
echo ' Targets with <dt> embed a device tree blob inside the image'
@@ -400,9 +402,13 @@ prepare: stack_protector_prepare
PHONY += stack_protector_prepare
stack_protector_prepare: prepare0
ifdef CONFIG_PPC64
- $(eval KBUILD_CFLAGS += -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "PACA_CANARY") print $$3;}' include/generated/asm-offsets.h))
+ $(eval KBUILD_CFLAGS += -mstack-protector-guard=tls -mstack-protector-guard-reg=r13 \
+ -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "PACA_CANARY") print $$3;}' \
+ $(objtree)/include/generated/asm-offsets.h))
else
- $(eval KBUILD_CFLAGS += -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "TASK_CANARY") print $$3;}' include/generated/asm-offsets.h))
+ $(eval KBUILD_CFLAGS += -mstack-protector-guard=tls -mstack-protector-guard-reg=r2 \
+ -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "TASK_CANARY") print $$3;}' \
+ $(objtree)/include/generated/asm-offsets.h))
endif
endif
diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink
index ae5a4256b03d..bb601be36173 100644
--- a/arch/powerpc/Makefile.postlink
+++ b/arch/powerpc/Makefile.postlink
@@ -24,6 +24,9 @@ else
$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@"
endif
+quiet_cmd_ftrace_check = CHKFTRC $@
+ cmd_ftrace_check = $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/ftrace_check.sh "$(NM)" "$@"
+
# `@true` prevents complaint when there is nothing to be done
vmlinux: FORCE
@@ -34,6 +37,11 @@ endif
ifdef CONFIG_RELOCATABLE
$(call if_changed,relocs_check)
endif
+ifdef CONFIG_FUNCTION_TRACER
+ifndef CONFIG_PPC64_ELF_ABI_V1
+ $(call cmd,ftrace_check)
+endif
+endif
clean:
rm -f .tmp_symbols.txt
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index a4716d138cfc..5a867f23fe7f 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -30,7 +30,6 @@ zImage.coff
zImage.epapr
zImage.holly
zImage.*lds
-zImage.maple
zImage.miboot
zImage.pmac
zImage.pseries
diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c
index 00c4d843a023..682ca3827892 100644
--- a/arch/powerpc/boot/4xx.c
+++ b/arch/powerpc/boot/4xx.c
@@ -253,7 +253,6 @@ void ibm4xx_denali_fixup_memsize(void)
dt_fixup_memory(0, memsize);
}
-#define SPRN_DBCR0_40X 0x3F2
#define SPRN_DBCR0_44X 0x134
#define DBCR0_RST_SYSTEM 0x30000000
@@ -270,18 +269,6 @@ void ibm44x_dbcr_reset(void)
}
-void ibm40x_dbcr_reset(void)
-{
- unsigned long tmp;
-
- asm volatile (
- "mfspr %0,%1\n"
- "oris %0,%0,%2@h\n"
- "mtspr %1,%0"
- : "=&r"(tmp) : "i"(SPRN_DBCR0_40X), "i"(DBCR0_RST_SYSTEM)
- );
-}
-
#define EMAC_RESET 0x20000000
void ibm4xx_quiesce_eth(u32 *emac0, u32 *emac1)
{
@@ -544,256 +531,3 @@ void ibm440spe_fixup_clocks(unsigned int sys_clk,
eplike_fixup_uart_clk(1, "/plb/opb/serial@f0000300", ser_clk, plb_clk);
eplike_fixup_uart_clk(2, "/plb/opb/serial@f0000600", ser_clk, plb_clk);
}
-
-void ibm405gp_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk)
-{
- u32 pllmr = mfdcr(DCRN_CPC0_PLLMR);
- u32 cpc0_cr0 = mfdcr(DCRN_405_CPC0_CR0);
- u32 cpc0_cr1 = mfdcr(DCRN_405_CPC0_CR1);
- u32 psr = mfdcr(DCRN_405_CPC0_PSR);
- u32 cpu, plb, opb, ebc, tb, uart0, uart1, m;
- u32 fwdv, fwdvb, fbdv, cbdv, opdv, epdv, ppdv, udiv;
-
- fwdv = (8 - ((pllmr & 0xe0000000) >> 29));
- fbdv = (pllmr & 0x1e000000) >> 25;
- if (fbdv == 0)
- fbdv = 16;
- cbdv = ((pllmr & 0x00060000) >> 17) + 1; /* CPU:PLB */
- opdv = ((pllmr & 0x00018000) >> 15) + 1; /* PLB:OPB */
- ppdv = ((pllmr & 0x00006000) >> 13) + 1; /* PLB:PCI */
- epdv = ((pllmr & 0x00001800) >> 11) + 2; /* PLB:EBC */
- udiv = ((cpc0_cr0 & 0x3e) >> 1) + 1;
-
- /* check for 405GPr */
- if ((mfpvr() & 0xfffffff0) == (0x50910951 & 0xfffffff0)) {
- fwdvb = 8 - (pllmr & 0x00000007);
- if (!(psr & 0x00001000)) /* PCI async mode enable == 0 */
- if (psr & 0x00000020) /* New mode enable */
- m = fwdvb * 2 * ppdv;
- else
- m = fwdvb * cbdv * ppdv;
- else if (psr & 0x00000020) /* New mode enable */
- if (psr & 0x00000800) /* PerClk synch mode */
- m = fwdvb * 2 * epdv;
- else
- m = fbdv * fwdv;
- else if (epdv == fbdv)
- m = fbdv * cbdv * epdv;
- else
- m = fbdv * fwdvb * cbdv;
-
- cpu = sys_clk * m / fwdv;
- plb = sys_clk * m / (fwdvb * cbdv);
- } else {
- m = fwdv * fbdv * cbdv;
- cpu = sys_clk * m / fwdv;
- plb = cpu / cbdv;
- }
- opb = plb / opdv;
- ebc = plb / epdv;
-
- if (cpc0_cr0 & 0x80)
- /* uart0 uses the external clock */
- uart0 = ser_clk;
- else
- uart0 = cpu / udiv;
-
- if (cpc0_cr0 & 0x40)
- /* uart1 uses the external clock */
- uart1 = ser_clk;
- else
- uart1 = cpu / udiv;
-
- /* setup the timebase clock to tick at the cpu frequency */
- cpc0_cr1 = cpc0_cr1 & ~0x00800000;
- mtdcr(DCRN_405_CPC0_CR1, cpc0_cr1);
- tb = cpu;
-
- dt_fixup_cpu_clocks(cpu, tb, 0);
- dt_fixup_clock("/plb", plb);
- dt_fixup_clock("/plb/opb", opb);
- dt_fixup_clock("/plb/ebc", ebc);
- dt_fixup_clock("/plb/opb/serial@ef600300", uart0);
- dt_fixup_clock("/plb/opb/serial@ef600400", uart1);
-}
-
-
-void ibm405ep_fixup_clocks(unsigned int sys_clk)
-{
- u32 pllmr0 = mfdcr(DCRN_CPC0_PLLMR0);
- u32 pllmr1 = mfdcr(DCRN_CPC0_PLLMR1);
- u32 cpc0_ucr = mfdcr(DCRN_CPC0_UCR);
- u32 cpu, plb, opb, ebc, uart0, uart1;
- u32 fwdva, fwdvb, fbdv, cbdv, opdv, epdv;
- u32 pllmr0_ccdv, tb, m;
-
- fwdva = 8 - ((pllmr1 & 0x00070000) >> 16);
- fwdvb = 8 - ((pllmr1 & 0x00007000) >> 12);
- fbdv = (pllmr1 & 0x00f00000) >> 20;
- if (fbdv == 0)
- fbdv = 16;
-
- cbdv = ((pllmr0 & 0x00030000) >> 16) + 1; /* CPU:PLB */
- epdv = ((pllmr0 & 0x00000300) >> 8) + 2; /* PLB:EBC */
- opdv = ((pllmr0 & 0x00003000) >> 12) + 1; /* PLB:OPB */
-
- m = fbdv * fwdvb;
-
- pllmr0_ccdv = ((pllmr0 & 0x00300000) >> 20) + 1;
- if (pllmr1 & 0x80000000)
- cpu = sys_clk * m / (fwdva * pllmr0_ccdv);
- else
- cpu = sys_clk / pllmr0_ccdv;
-
- plb = cpu / cbdv;
- opb = plb / opdv;
- ebc = plb / epdv;
- tb = cpu;
- uart0 = cpu / (cpc0_ucr & 0x0000007f);
- uart1 = cpu / ((cpc0_ucr & 0x00007f00) >> 8);
-
- dt_fixup_cpu_clocks(cpu, tb, 0);
- dt_fixup_clock("/plb", plb);
- dt_fixup_clock("/plb/opb", opb);
- dt_fixup_clock("/plb/ebc", ebc);
- dt_fixup_clock("/plb/opb/serial@ef600300", uart0);
- dt_fixup_clock("/plb/opb/serial@ef600400", uart1);
-}
-
-static u8 ibm405ex_fwdv_multi_bits[] = {
- /* values for: 1 - 16 */
- 0x01, 0x02, 0x0e, 0x09, 0x04, 0x0b, 0x10, 0x0d, 0x0c, 0x05,
- 0x06, 0x0f, 0x0a, 0x07, 0x08, 0x03
-};
-
-u32 ibm405ex_get_fwdva(unsigned long cpr_fwdv)
-{
- u32 index;
-
- for (index = 0; index < ARRAY_SIZE(ibm405ex_fwdv_multi_bits); index++)
- if (cpr_fwdv == (u32)ibm405ex_fwdv_multi_bits[index])
- return index + 1;
-
- return 0;
-}
-
-static u8 ibm405ex_fbdv_multi_bits[] = {
- /* values for: 1 - 100 */
- 0x00, 0xff, 0x7e, 0xfd, 0x7a, 0xf5, 0x6a, 0xd5, 0x2a, 0xd4,
- 0x29, 0xd3, 0x26, 0xcc, 0x19, 0xb3, 0x67, 0xce, 0x1d, 0xbb,
- 0x77, 0xee, 0x5d, 0xba, 0x74, 0xe9, 0x52, 0xa5, 0x4b, 0x96,
- 0x2c, 0xd8, 0x31, 0xe3, 0x46, 0x8d, 0x1b, 0xb7, 0x6f, 0xde,
- 0x3d, 0xfb, 0x76, 0xed, 0x5a, 0xb5, 0x6b, 0xd6, 0x2d, 0xdb,
- 0x36, 0xec, 0x59, 0xb2, 0x64, 0xc9, 0x12, 0xa4, 0x48, 0x91,
- 0x23, 0xc7, 0x0e, 0x9c, 0x38, 0xf0, 0x61, 0xc2, 0x05, 0x8b,
- 0x17, 0xaf, 0x5f, 0xbe, 0x7c, 0xf9, 0x72, 0xe5, 0x4a, 0x95,
- 0x2b, 0xd7, 0x2e, 0xdc, 0x39, 0xf3, 0x66, 0xcd, 0x1a, 0xb4,
- 0x68, 0xd1, 0x22, 0xc4, 0x09, 0x93, 0x27, 0xcf, 0x1e, 0xbc,
- /* values for: 101 - 200 */
- 0x78, 0xf1, 0x62, 0xc5, 0x0a, 0x94, 0x28, 0xd0, 0x21, 0xc3,
- 0x06, 0x8c, 0x18, 0xb0, 0x60, 0xc1, 0x02, 0x84, 0x08, 0x90,
- 0x20, 0xc0, 0x01, 0x83, 0x07, 0x8f, 0x1f, 0xbf, 0x7f, 0xfe,
- 0x7d, 0xfa, 0x75, 0xea, 0x55, 0xaa, 0x54, 0xa9, 0x53, 0xa6,
- 0x4c, 0x99, 0x33, 0xe7, 0x4e, 0x9d, 0x3b, 0xf7, 0x6e, 0xdd,
- 0x3a, 0xf4, 0x69, 0xd2, 0x25, 0xcb, 0x16, 0xac, 0x58, 0xb1,
- 0x63, 0xc6, 0x0d, 0x9b, 0x37, 0xef, 0x5e, 0xbd, 0x7b, 0xf6,
- 0x6d, 0xda, 0x35, 0xeb, 0x56, 0xad, 0x5b, 0xb6, 0x6c, 0xd9,
- 0x32, 0xe4, 0x49, 0x92, 0x24, 0xc8, 0x11, 0xa3, 0x47, 0x8e,
- 0x1c, 0xb8, 0x70, 0xe1, 0x42, 0x85, 0x0b, 0x97, 0x2f, 0xdf,
- /* values for: 201 - 255 */
- 0x3e, 0xfc, 0x79, 0xf2, 0x65, 0xca, 0x15, 0xab, 0x57, 0xae,
- 0x5c, 0xb9, 0x73, 0xe6, 0x4d, 0x9a, 0x34, 0xe8, 0x51, 0xa2,
- 0x44, 0x89, 0x13, 0xa7, 0x4f, 0x9e, 0x3c, 0xf8, 0x71, 0xe2,
- 0x45, 0x8a, 0x14, 0xa8, 0x50, 0xa1, 0x43, 0x86, 0x0c, 0x98,
- 0x30, 0xe0, 0x41, 0x82, 0x04, 0x88, 0x10, 0xa0, 0x40, 0x81,
- 0x03, 0x87, 0x0f, 0x9f, 0x3f /* END */
-};
-
-u32 ibm405ex_get_fbdv(unsigned long cpr_fbdv)
-{
- u32 index;
-
- for (index = 0; index < ARRAY_SIZE(ibm405ex_fbdv_multi_bits); index++)
- if (cpr_fbdv == (u32)ibm405ex_fbdv_multi_bits[index])
- return index + 1;
-
- return 0;
-}
-
-void ibm405ex_fixup_clocks(unsigned int sys_clk, unsigned int uart_clk)
-{
- /* PLL config */
- u32 pllc = CPR0_READ(DCRN_CPR0_PLLC);
- u32 plld = CPR0_READ(DCRN_CPR0_PLLD);
- u32 cpud = CPR0_READ(DCRN_CPR0_PRIMAD);
- u32 plbd = CPR0_READ(DCRN_CPR0_PRIMBD);
- u32 opbd = CPR0_READ(DCRN_CPR0_OPBD);
- u32 perd = CPR0_READ(DCRN_CPR0_PERD);
-
- /* Dividers */
- u32 fbdv = ibm405ex_get_fbdv(__fix_zero((plld >> 24) & 0xff, 1));
-
- u32 fwdva = ibm405ex_get_fwdva(__fix_zero((plld >> 16) & 0x0f, 1));
-
- u32 cpudv0 = __fix_zero((cpud >> 24) & 7, 8);
-
- /* PLBDV0 is hardwared to 010. */
- u32 plbdv0 = 2;
- u32 plb2xdv0 = __fix_zero((plbd >> 16) & 7, 8);
-
- u32 opbdv0 = __fix_zero((opbd >> 24) & 3, 4);
-
- u32 perdv0 = __fix_zero((perd >> 24) & 3, 4);
-
- /* Resulting clocks */
- u32 cpu, plb, opb, ebc, vco, tb, uart0, uart1;
-
- /* PLL's VCO is the source for primary forward ? */
- if (pllc & 0x40000000) {
- u32 m;
-
- /* Feedback path */
- switch ((pllc >> 24) & 7) {
- case 0:
- /* PLLOUTx */
- m = fbdv;
- break;
- case 1:
- /* CPU */
- m = fbdv * fwdva * cpudv0;
- break;
- case 5:
- /* PERClk */
- m = fbdv * fwdva * plb2xdv0 * plbdv0 * opbdv0 * perdv0;
- break;
- default:
- printf("WARNING ! Invalid PLL feedback source !\n");
- goto bypass;
- }
-
- vco = (unsigned int)(sys_clk * m);
- } else {
-bypass:
- /* Bypass system PLL */
- vco = 0;
- }
-
- /* CPU = VCO / ( FWDVA x CPUDV0) */
- cpu = vco / (fwdva * cpudv0);
- /* PLB = VCO / ( FWDVA x PLB2XDV0 x PLBDV0) */
- plb = vco / (fwdva * plb2xdv0 * plbdv0);
- /* OPB = PLB / OPBDV0 */
- opb = plb / opbdv0;
- /* EBC = OPB / PERDV0 */
- ebc = opb / perdv0;
-
- tb = cpu;
- uart0 = uart1 = uart_clk;
-
- dt_fixup_cpu_clocks(cpu, tb, 0);
- dt_fixup_clock("/plb", plb);
- dt_fixup_clock("/plb/opb", opb);
- dt_fixup_clock("/plb/opb/ebc", ebc);
- dt_fixup_clock("/plb/opb/serial@ef600200", uart0);
- dt_fixup_clock("/plb/opb/serial@ef600300", uart1);
-}
diff --git a/arch/powerpc/boot/4xx.h b/arch/powerpc/boot/4xx.h
index 77f15d124c81..62df496b7ba6 100644
--- a/arch/powerpc/boot/4xx.h
+++ b/arch/powerpc/boot/4xx.h
@@ -12,13 +12,9 @@ void ibm4xx_sdram_fixup_memsize(void);
void ibm440spe_fixup_memsize(void);
void ibm4xx_denali_fixup_memsize(void);
void ibm44x_dbcr_reset(void);
-void ibm40x_dbcr_reset(void);
void ibm4xx_quiesce_eth(u32 *emac0, u32 *emac1);
void ibm4xx_fixup_ebc_ranges(const char *ebc);
-void ibm405gp_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk);
-void ibm405ep_fixup_clocks(unsigned int sys_clk);
-void ibm405ex_fixup_clocks(unsigned int sys_clk, unsigned int uart_clk);
void ibm440gp_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk);
void ibm440ep_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk,
unsigned int tmr_clk);
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 968aee2025b8..1ff6ad4f6cd2 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -54,10 +54,8 @@ endif
$(obj)/4xx.o: BOOTTARGETFLAGS += -mcpu=405
$(obj)/ebony.o: BOOTTARGETFLAGS += -mcpu=440
-$(obj)/cuboot-hotfoot.o: BOOTTARGETFLAGS += -mcpu=405
$(obj)/cuboot-taishan.o: BOOTTARGETFLAGS += -mcpu=440
$(obj)/cuboot-katmai.o: BOOTTARGETFLAGS += -mcpu=440
-$(obj)/cuboot-acadia.o: BOOTTARGETFLAGS += -mcpu=405
$(obj)/treeboot-iss4xx.o: BOOTTARGETFLAGS += -mcpu=405
$(obj)/treeboot-currituck.o: BOOTTARGETFLAGS += -mcpu=405
$(obj)/treeboot-akebono.o: BOOTTARGETFLAGS += -mcpu=405
@@ -108,8 +106,8 @@ DTC_FLAGS ?= -p 1024
# these files into the build dir, fix up any includes and ensure that dependent
# files are copied in the right order.
-# these need to be seperate variables because they are copied out of different
-# directories in the kernel tree. Sure you COULd merge them, but it's a
+# these need to be separate variables because they are copied out of different
+# directories in the kernel tree. Sure you COULD merge them, but it's a
# cure-is-worse-than-disease situation.
zlib-decomp-$(CONFIG_KERNEL_GZIP) := decompress_inflate.c
zlib-$(CONFIG_KERNEL_GZIP) := inffast.c inflate.c inftrees.c
@@ -146,7 +144,6 @@ src-wlib-$(CONFIG_PPC_POWERNV) += opal-calls.S opal.c
ifndef CONFIG_PPC64_BOOT_WRAPPER
src-wlib-y += crtsavres.S
endif
-src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c
src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c
src-wlib-$(CONFIG_PPC_8xx) += mpc8xx.c planetcore.c fsl-soc.c
src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c
@@ -154,9 +151,6 @@ src-wlib-$(CONFIG_EMBEDDED6xx) += ugecon.c fsl-soc.c
src-wlib-$(CONFIG_CPM) += cpm-serial.c
src-plat-y := of.c epapr.c
-src-plat-$(CONFIG_40x) += fixed-head.S cuboot-hotfoot.c \
- cuboot-acadia.c \
- cuboot-kilauea.c simpleboot.c
src-plat-$(CONFIG_44x) += treeboot-ebony.c cuboot-ebony.c treeboot-bamboo.c \
cuboot-bamboo.c cuboot-sam440ep.c \
cuboot-sequoia.c cuboot-rainier.c \
@@ -218,7 +212,7 @@ $(addprefix $(obj)/,$(libfdt) $(libfdtheader)): $(obj)/%: $(srctree)/scripts/dtc
$(obj)/empty.c:
$(Q)touch $@
-$(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(srctree)/$(src)/%.S
+$(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(src)/%.S
$(Q)cp $< $@
clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \
@@ -252,9 +246,9 @@ targets += $(patsubst $(obj)/%,%,$(obj-boot) wrapper.a) zImage.lds
extra-y := $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
$(obj)/zImage.lds $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds
-dtstree := $(srctree)/$(src)/dts
+dtstree := $(src)/dts
-wrapper :=$(srctree)/$(src)/wrapper
+wrapper := $(src)/wrapper
wrapperbits := $(extra-y) $(addprefix $(obj)/,addnote hack-coff mktree) \
$(wrapper) FORCE
@@ -282,7 +276,6 @@ quiet_cmd_wrap = WRAP $@
image-$(CONFIG_PPC_PSERIES) += zImage.pseries
image-$(CONFIG_PPC_POWERNV) += zImage.pseries
-image-$(CONFIG_PPC_MAPLE) += zImage.maple
image-$(CONFIG_PPC_IBM_CELL_BLADE) += zImage.pseries
image-$(CONFIG_PPC_PS3) += dtbImage.ps3
image-$(CONFIG_PPC_CHRP) += zImage.chrp
@@ -300,11 +293,6 @@ image-$(CONFIG_EPAPR_BOOT) += zImage.epapr
# Boards with newish u-boot firmware can use the uImage target above
#
-# Board ports in arch/powerpc/platform/40x/Kconfig
-image-$(CONFIG_HOTFOOT) += cuImage.hotfoot
-image-$(CONFIG_ACADIA) += cuImage.acadia
-image-$(CONFIG_OBS600) += uImage.obs600
-
# Board ports in arch/powerpc/platform/44x/Kconfig
image-$(CONFIG_EBONY) += treeImage.ebony cuImage.ebony
image-$(CONFIG_BAMBOO) += treeImage.bamboo cuImage.bamboo
@@ -455,7 +443,7 @@ $(obj)/zImage.initrd: $(addprefix $(obj)/, $(initrd-y))
clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \
zImage zImage.initrd zImage.chrp zImage.coff zImage.holly \
zImage.miboot zImage.pmac zImage.pseries \
- zImage.maple simpleImage.* otheros.bld
+ simpleImage.* otheros.bld
# clean up files cached by wrapper
clean-kernel-base := vmlinux.strip vmlinux.bin
diff --git a/arch/powerpc/boot/cuboot-acadia.c b/arch/powerpc/boot/cuboot-acadia.c
deleted file mode 100644
index 46e96756cfe1..000000000000
--- a/arch/powerpc/boot/cuboot-acadia.c
+++ /dev/null
@@ -1,171 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Old U-boot compatibility for Acadia
- *
- * Author: Josh Boyer <jwboyer@linux.vnet.ibm.com>
- *
- * Copyright 2008 IBM Corporation
- */
-
-#include "ops.h"
-#include "io.h"
-#include "dcr.h"
-#include "stdio.h"
-#include "4xx.h"
-#include "44x.h"
-#include "cuboot.h"
-
-#define TARGET_4xx
-#include "ppcboot.h"
-
-static bd_t bd;
-
-#define CPR_PERD0_SPIDV_MASK 0x000F0000 /* SPI Clock Divider */
-
-#define PLLC_SRC_MASK 0x20000000 /* PLL feedback source */
-
-#define PLLD_FBDV_MASK 0x1F000000 /* PLL feedback divider value */
-#define PLLD_FWDVA_MASK 0x000F0000 /* PLL forward divider A value */
-#define PLLD_FWDVB_MASK 0x00000700 /* PLL forward divider B value */
-
-#define PRIMAD_CPUDV_MASK 0x0F000000 /* CPU Clock Divisor Mask */
-#define PRIMAD_PLBDV_MASK 0x000F0000 /* PLB Clock Divisor Mask */
-#define PRIMAD_OPBDV_MASK 0x00000F00 /* OPB Clock Divisor Mask */
-#define PRIMAD_EBCDV_MASK 0x0000000F /* EBC Clock Divisor Mask */
-
-#define PERD0_PWMDV_MASK 0xFF000000 /* PWM Divider Mask */
-#define PERD0_SPIDV_MASK 0x000F0000 /* SPI Divider Mask */
-#define PERD0_U0DV_MASK 0x0000FF00 /* UART 0 Divider Mask */
-#define PERD0_U1DV_MASK 0x000000FF /* UART 1 Divider Mask */
-
-static void get_clocks(void)
-{
- unsigned long sysclk, cpr_plld, cpr_pllc, cpr_primad, plloutb, i;
- unsigned long pllFwdDiv, pllFwdDivB, pllFbkDiv, pllPlbDiv, pllExtBusDiv;
- unsigned long pllOpbDiv, freqEBC, freqUART, freqOPB;
- unsigned long div; /* total divisor udiv * bdiv */
- unsigned long umin; /* minimum udiv */
- unsigned short diff; /* smallest diff */
- unsigned long udiv; /* best udiv */
- unsigned short idiff; /* current diff */
- unsigned short ibdiv; /* current bdiv */
- unsigned long est; /* current estimate */
- unsigned long baud;
- void *np;
-
- /* read the sysclk value from the CPLD */
- sysclk = (in_8((unsigned char *)0x80000000) == 0xc) ? 66666666 : 33333000;
-
- /*
- * Read PLL Mode registers
- */
- cpr_plld = CPR0_READ(DCRN_CPR0_PLLD);
- cpr_pllc = CPR0_READ(DCRN_CPR0_PLLC);
-
- /*
- * Determine forward divider A
- */
- pllFwdDiv = ((cpr_plld & PLLD_FWDVA_MASK) >> 16);
-
- /*
- * Determine forward divider B
- */
- pllFwdDivB = ((cpr_plld & PLLD_FWDVB_MASK) >> 8);
- if (pllFwdDivB == 0)
- pllFwdDivB = 8;
-
- /*
- * Determine FBK_DIV.
- */
- pllFbkDiv = ((cpr_plld & PLLD_FBDV_MASK) >> 24);
- if (pllFbkDiv == 0)
- pllFbkDiv = 256;
-
- /*
- * Read CPR_PRIMAD register
- */
- cpr_primad = CPR0_READ(DCRN_CPR0_PRIMAD);
-
- /*
- * Determine PLB_DIV.
- */
- pllPlbDiv = ((cpr_primad & PRIMAD_PLBDV_MASK) >> 16);
- if (pllPlbDiv == 0)
- pllPlbDiv = 16;
-
- /*
- * Determine EXTBUS_DIV.
- */
- pllExtBusDiv = (cpr_primad & PRIMAD_EBCDV_MASK);
- if (pllExtBusDiv == 0)
- pllExtBusDiv = 16;
-
- /*
- * Determine OPB_DIV.
- */
- pllOpbDiv = ((cpr_primad & PRIMAD_OPBDV_MASK) >> 8);
- if (pllOpbDiv == 0)
- pllOpbDiv = 16;
-
- /* There is a bug in U-Boot that prevents us from using
- * bd.bi_opbfreq because U-Boot doesn't populate it for
- * 405EZ. We get to calculate it, yay!
- */
- freqOPB = (sysclk *pllFbkDiv) /pllOpbDiv;
-
- freqEBC = (sysclk * pllFbkDiv) / pllExtBusDiv;
-
- plloutb = ((sysclk * ((cpr_pllc & PLLC_SRC_MASK) ?
- pllFwdDivB : pllFwdDiv) *
- pllFbkDiv) / pllFwdDivB);
-
- np = find_node_by_alias("serial0");
- if (getprop(np, "current-speed", &baud, sizeof(baud)) != sizeof(baud))
- fatal("no current-speed property\n\r");
-
- udiv = 256; /* Assume lowest possible serial clk */
- div = plloutb / (16 * baud); /* total divisor */
- umin = (plloutb / freqOPB) << 1; /* 2 x OPB divisor */
- diff = 256; /* highest possible */
-
- /* i is the test udiv value -- start with the largest
- * possible (256) to minimize serial clock and constrain
- * search to umin.
- */
- for (i = 256; i > umin; i--) {
- ibdiv = div / i;
- est = i * ibdiv;
- idiff = (est > div) ? (est-div) : (div-est);
- if (idiff == 0) {
- udiv = i;
- break; /* can't do better */
- } else if (idiff < diff) {
- udiv = i; /* best so far */
- diff = idiff; /* update lowest diff*/
- }
- }
- freqUART = plloutb / udiv;
-
- dt_fixup_cpu_clocks(bd.bi_procfreq, bd.bi_intfreq, bd.bi_plb_busfreq);
- dt_fixup_clock("/plb/ebc", freqEBC);
- dt_fixup_clock("/plb/opb", freqOPB);
- dt_fixup_clock("/plb/opb/serial@ef600300", freqUART);
- dt_fixup_clock("/plb/opb/serial@ef600400", freqUART);
-}
-
-static void acadia_fixups(void)
-{
- dt_fixup_memory(bd.bi_memstart, bd.bi_memsize);
- get_clocks();
- dt_fixup_mac_address_by_alias("ethernet0", bd.bi_enetaddr);
-}
-
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
- unsigned long r6, unsigned long r7)
-{
- CUBOOT_INIT();
- platform_ops.fixups = acadia_fixups;
- platform_ops.exit = ibm40x_dbcr_reset;
- fdt_init(_dtb_start);
- serial_console_init();
-}
diff --git a/arch/powerpc/boot/cuboot-hotfoot.c b/arch/powerpc/boot/cuboot-hotfoot.c
deleted file mode 100644
index 0e5532f855d6..000000000000
--- a/arch/powerpc/boot/cuboot-hotfoot.c
+++ /dev/null
@@ -1,139 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Old U-boot compatibility for Esteem 195E Hotfoot CPU Board
- *
- * Author: Solomon Peachy <solomon@linux-wlan.com>
- */
-
-#include "ops.h"
-#include "stdio.h"
-#include "reg.h"
-#include "dcr.h"
-#include "4xx.h"
-#include "cuboot.h"
-
-#define TARGET_4xx
-#define TARGET_HOTFOOT
-
-#include "ppcboot-hotfoot.h"
-
-static bd_t bd;
-
-#define NUM_REGS 3
-
-static void hotfoot_fixups(void)
-{
- u32 uart = mfdcr(DCRN_CPC0_UCR) & 0x7f;
-
- dt_fixup_memory(bd.bi_memstart, bd.bi_memsize);
-
- dt_fixup_cpu_clocks(bd.bi_procfreq, bd.bi_procfreq, 0);
- dt_fixup_clock("/plb", bd.bi_plb_busfreq);
- dt_fixup_clock("/plb/opb", bd.bi_opbfreq);
- dt_fixup_clock("/plb/ebc", bd.bi_pci_busfreq);
- dt_fixup_clock("/plb/opb/serial@ef600300", bd.bi_procfreq / uart);
- dt_fixup_clock("/plb/opb/serial@ef600400", bd.bi_procfreq / uart);
-
- dt_fixup_mac_address_by_alias("ethernet0", bd.bi_enetaddr);
- dt_fixup_mac_address_by_alias("ethernet1", bd.bi_enet1addr);
-
- /* Is this a single eth/serial board? */
- if ((bd.bi_enet1addr[0] == 0) &&
- (bd.bi_enet1addr[1] == 0) &&
- (bd.bi_enet1addr[2] == 0) &&
- (bd.bi_enet1addr[3] == 0) &&
- (bd.bi_enet1addr[4] == 0) &&
- (bd.bi_enet1addr[5] == 0)) {
- void *devp;
-
- printf("Trimming devtree for single serial/eth board\n");
-
- devp = finddevice("/plb/opb/serial@ef600300");
- if (!devp)
- fatal("Can't find node for /plb/opb/serial@ef600300");
- del_node(devp);
-
- devp = finddevice("/plb/opb/ethernet@ef600900");
- if (!devp)
- fatal("Can't find node for /plb/opb/ethernet@ef600900");
- del_node(devp);
- }
-
- ibm4xx_quiesce_eth((u32 *)0xef600800, (u32 *)0xef600900);
-
- /* Fix up flash size in fdt for 4M boards. */
- if (bd.bi_flashsize < 0x800000) {
- u32 regs[NUM_REGS];
- void *devp = finddevice("/plb/ebc/nor_flash@0");
- if (!devp)
- fatal("Can't find FDT node for nor_flash!??");
-
- printf("Fixing devtree for 4M Flash\n");
-
- /* First fix up the base address */
- getprop(devp, "reg", regs, sizeof(regs));
- regs[0] = 0;
- regs[1] = 0xffc00000;
- regs[2] = 0x00400000;
- setprop(devp, "reg", regs, sizeof(regs));
-
- /* Then the offsets */
- devp = finddevice("/plb/ebc/nor_flash@0/partition@0");
- if (!devp)
- fatal("Can't find FDT node for partition@0");
- getprop(devp, "reg", regs, 2*sizeof(u32));
- regs[0] -= 0x400000;
- setprop(devp, "reg", regs, 2*sizeof(u32));
-
- devp = finddevice("/plb/ebc/nor_flash@0/partition@1");
- if (!devp)
- fatal("Can't find FDT node for partition@1");
- getprop(devp, "reg", regs, 2*sizeof(u32));
- regs[0] -= 0x400000;
- setprop(devp, "reg", regs, 2*sizeof(u32));
-
- devp = finddevice("/plb/ebc/nor_flash@0/partition@2");
- if (!devp)
- fatal("Can't find FDT node for partition@2");
- getprop(devp, "reg", regs, 2*sizeof(u32));
- regs[0] -= 0x400000;
- setprop(devp, "reg", regs, 2*sizeof(u32));
-
- devp = finddevice("/plb/ebc/nor_flash@0/partition@3");
- if (!devp)
- fatal("Can't find FDT node for partition@3");
- getprop(devp, "reg", regs, 2*sizeof(u32));
- regs[0] -= 0x400000;
- setprop(devp, "reg", regs, 2*sizeof(u32));
-
- devp = finddevice("/plb/ebc/nor_flash@0/partition@4");
- if (!devp)
- fatal("Can't find FDT node for partition@4");
- getprop(devp, "reg", regs, 2*sizeof(u32));
- regs[0] -= 0x400000;
- setprop(devp, "reg", regs, 2*sizeof(u32));
-
- devp = finddevice("/plb/ebc/nor_flash@0/partition@6");
- if (!devp)
- fatal("Can't find FDT node for partition@6");
- getprop(devp, "reg", regs, 2*sizeof(u32));
- regs[0] -= 0x400000;
- setprop(devp, "reg", regs, 2*sizeof(u32));
-
- /* Delete the FeatFS node */
- devp = finddevice("/plb/ebc/nor_flash@0/partition@5");
- if (!devp)
- fatal("Can't find FDT node for partition@5");
- del_node(devp);
- }
-}
-
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
- unsigned long r6, unsigned long r7)
-{
- CUBOOT_INIT();
- platform_ops.fixups = hotfoot_fixups;
- platform_ops.exit = ibm40x_dbcr_reset;
- fdt_init(_dtb_start);
- serial_console_init();
-}
diff --git a/arch/powerpc/boot/cuboot-kilauea.c b/arch/powerpc/boot/cuboot-kilauea.c
deleted file mode 100644
index fda182f518a2..000000000000
--- a/arch/powerpc/boot/cuboot-kilauea.c
+++ /dev/null
@@ -1,46 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Old U-boot compatibility for PPC405EX. This image is already included
- * a dtb.
- *
- * Author: Tiejun Chen <tiejun.chen@windriver.com>
- *
- * Copyright (C) 2009 Wind River Systems, Inc.
- */
-
-#include "ops.h"
-#include "io.h"
-#include "dcr.h"
-#include "stdio.h"
-#include "4xx.h"
-#include "44x.h"
-#include "cuboot.h"
-
-#define TARGET_4xx
-#define TARGET_44x
-#include "ppcboot.h"
-
-#define KILAUEA_SYS_EXT_SERIAL_CLOCK 11059200 /* ext. 11.059MHz clk */
-
-static bd_t bd;
-
-static void kilauea_fixups(void)
-{
- unsigned long sysclk = 33333333;
-
- ibm405ex_fixup_clocks(sysclk, KILAUEA_SYS_EXT_SERIAL_CLOCK);
- dt_fixup_memory(bd.bi_memstart, bd.bi_memsize);
- ibm4xx_fixup_ebc_ranges("/plb/opb/ebc");
- dt_fixup_mac_address_by_alias("ethernet0", bd.bi_enetaddr);
- dt_fixup_mac_address_by_alias("ethernet1", bd.bi_enet1addr);
-}
-
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
- unsigned long r6, unsigned long r7)
-{
- CUBOOT_INIT();
- platform_ops.fixups = kilauea_fixups;
- platform_ops.exit = ibm40x_dbcr_reset;
- fdt_init(_dtb_start);
- serial_console_init();
-}
diff --git a/arch/powerpc/boot/dcr.h b/arch/powerpc/boot/dcr.h
index 334ab8b5a668..91dc3a302cc8 100644
--- a/arch/powerpc/boot/dcr.h
+++ b/arch/powerpc/boot/dcr.h
@@ -153,17 +153,6 @@ static const unsigned long sdram_bxcr[] = { SDRAM0_B0CR, SDRAM0_B1CR,
#define CPR0_SCPID 0x120
#define CPR0_PLLC0 0x40
-/* 405GP Clocking/Power Management/Chip Control regs */
-#define DCRN_CPC0_PLLMR 0xb0
-#define DCRN_405_CPC0_CR0 0xb1
-#define DCRN_405_CPC0_CR1 0xb2
-#define DCRN_405_CPC0_PSR 0xb4
-
-/* 405EP Clocking/Power Management/Chip Control regs */
-#define DCRN_CPC0_PLLMR0 0xf0
-#define DCRN_CPC0_PLLMR1 0xf4
-#define DCRN_CPC0_UCR 0xf5
-
/* 440GX/405EX Clock Control reg */
#define DCRN_CPR0_CLKUPD 0x020
#define DCRN_CPR0_PLLC 0x040
diff --git a/arch/powerpc/boot/decompress.c b/arch/powerpc/boot/decompress.c
index 977eb15a6d17..6835cb53f034 100644
--- a/arch/powerpc/boot/decompress.c
+++ b/arch/powerpc/boot/decompress.c
@@ -101,7 +101,7 @@ static void print_err(char *s)
* @input_size: length of the input buffer
* @outbuf: output buffer
* @output_size: length of the output buffer
- * @skip number of output bytes to ignore
+ * @_skip: number of output bytes to ignore
*
* This function takes compressed data from inbuf, decompresses and write it to
* outbuf. Once output_size bytes are written to the output buffer, or the
diff --git a/arch/powerpc/boot/dts/Makefile b/arch/powerpc/boot/dts/Makefile
index fb335d05aae8..0cd0d8558b47 100644
--- a/arch/powerpc/boot/dts/Makefile
+++ b/arch/powerpc/boot/dts/Makefile
@@ -2,5 +2,4 @@
subdir-y += fsl
-dtstree := $(srctree)/$(src)
-dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/powerpc/boot/dts/acadia.dts b/arch/powerpc/boot/dts/acadia.dts
deleted file mode 100644
index deb52e41ab84..000000000000
--- a/arch/powerpc/boot/dts/acadia.dts
+++ /dev/null
@@ -1,224 +0,0 @@
-/*
- * Device Tree Source for AMCC Acadia (405EZ)
- *
- * Copyright IBM Corp. 2008
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
- #address-cells = <1>;
- #size-cells = <1>;
- model = "amcc,acadia";
- compatible = "amcc,acadia";
- dcr-parent = <&{/cpus/cpu@0}>;
-
- aliases {
- ethernet0 = &EMAC0;
- serial0 = &UART0;
- serial1 = &UART1;
- };
-
- cpus {
- #address-cells = <1>;
- #size-cells = <0>;
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,405EZ";
- reg = <0x0>;
- clock-frequency = <0>; /* Filled in by wrapper */
- timebase-frequency = <0>; /* Filled in by wrapper */
- i-cache-line-size = <32>;
- d-cache-line-size = <32>;
- i-cache-size = <16384>;
- d-cache-size = <16384>;
- dcr-controller;
- dcr-access-method = "native";
- };
- };
-
- memory {
- device_type = "memory";
- reg = <0x0 0x0>; /* Filled in by wrapper */
- };
-
- UIC0: interrupt-controller {
- compatible = "ibm,uic-405ez", "ibm,uic";
- interrupt-controller;
- dcr-reg = <0x0c0 0x009>;
- cell-index = <0>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- };
-
- plb {
- compatible = "ibm,plb-405ez", "ibm,plb3";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges;
- clock-frequency = <0>; /* Filled in by wrapper */
-
- MAL0: mcmal {
- compatible = "ibm,mcmal-405ez", "ibm,mcmal";
- dcr-reg = <0x380 0x62>;
- num-tx-chans = <1>;
- num-rx-chans = <1>;
- interrupt-parent = <&UIC0>;
- /* 405EZ has only 3 interrupts to the UIC, as
- * SERR, TXDE, and RXDE are or'd together into
- * one UIC bit
- */
- interrupts = <
- 0x13 0x4 /* TXEOB */
- 0x15 0x4 /* RXEOB */
- 0x12 0x4 /* SERR, TXDE, RXDE */>;
- };
-
- POB0: opb {
- compatible = "ibm,opb-405ez", "ibm,opb";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges;
- dcr-reg = <0x0a 0x05>;
- clock-frequency = <0>; /* Filled in by wrapper */
-
- UART0: serial@ef600300 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600300 0x8>;
- virtual-reg = <0xef600300>;
- clock-frequency = <0>; /* Filled in by wrapper */
- current-speed = <115200>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x5 0x4>;
- };
-
- UART1: serial@ef600400 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600400 0x8>;
- clock-frequency = <0>; /* Filled in by wrapper */
- current-speed = <115200>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x6 0x4>;
- };
-
- IIC: i2c@ef600500 {
- compatible = "ibm,iic-405ez", "ibm,iic";
- reg = <0xef600500 0x11>;
- interrupt-parent = <&UIC0>;
- interrupts = <0xa 0x4>;
- };
-
- GPIO0: gpio@ef600700 {
- compatible = "ibm,gpio-405ez";
- reg = <0xef600700 0x20>;
- };
-
- GPIO1: gpio@ef600800 {
- compatible = "ibm,gpio-405ez";
- reg = <0xef600800 0x20>;
- };
-
- EMAC0: ethernet@ef600900 {
- device_type = "network";
- compatible = "ibm,emac-405ez", "ibm,emac";
- interrupt-parent = <&UIC0>;
- interrupts = <
- 0x10 0x4 /* Ethernet */
- 0x11 0x4 /* Ethernet Wake up */>;
- local-mac-address = [000000000000]; /* Filled in by wrapper */
- reg = <0xef600900 0x70>;
- mal-device = <&MAL0>;
- mal-tx-channel = <0>;
- mal-rx-channel = <0>;
- cell-index = <0>;
- max-frame-size = <1500>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- phy-mode = "mii";
- phy-map = <0x0>;
- };
-
- CAN0: can@ef601000 {
- compatible = "amcc,can-405ez";
- reg = <0xef601000 0x620>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x7 0x4>;
- };
-
- CAN1: can@ef601800 {
- compatible = "amcc,can-405ez";
- reg = <0xef601800 0x620>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x8 0x4>;
- };
-
- cameleon@ef602000 {
- compatible = "amcc,cameleon-405ez";
- reg = <0xef602000 0x800>;
- interrupt-parent = <&UIC0>;
- interrupts = <0xb 0x4 0xc 0x4>;
- };
-
- ieee1588@ef602800 {
- compatible = "amcc,ieee1588-405ez";
- reg = <0xef602800 0x60>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x4 0x4>;
- /* This thing is a bit weird. It has it's own UIC
- * that it uses to generate snapshot triggers. We
- * don't really support this device yet, and it needs
- * work to figure this out.
- */
- dcr-reg = <0xe0 0x9>;
- };
-
- usb@ef603000 {
- compatible = "ohci-be";
- reg = <0xef603000 0x80>;
- interrupt-parent = <&UIC0>;
- interrupts = <0xd 0x4 0xe 0x4>;
- };
-
- dac@ef603300 {
- compatible = "amcc,dac-405ez";
- reg = <0xef603300 0x40>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x18 0x4>;
- };
-
- adc@ef603400 {
- compatible = "amcc,adc-405ez";
- reg = <0xef603400 0x40>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x17 0x4>;
- };
-
- spi@ef603500 {
- compatible = "amcc,spi-405ez";
- reg = <0xef603500 0x100>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x9 0x4>;
- };
- };
-
- EBC0: ebc {
- compatible = "ibm,ebc-405ez", "ibm,ebc";
- dcr-reg = <0x12 0x2>;
- #address-cells = <2>;
- #size-cells = <1>;
- clock-frequency = <0>; /* Filled in by wrapper */
- };
- };
-
- chosen {
- stdout-path = "/plb/opb/serial@ef600300";
- };
-};
diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts
index df18f8dc4642..343326c30380 100644
--- a/arch/powerpc/boot/dts/akebono.dts
+++ b/arch/powerpc/boot/dts/akebono.dts
@@ -126,7 +126,7 @@
interrupts = <93 2>;
};
- EHCI0: ehci@30010000000 {
+ EHCI0: usb@30010000000 {
compatible = "ibm,476gtr-ehci", "generic-ehci";
reg = <0x300 0x10000000 0x0 0x10000>;
interrupt-parent = <&MPIC>;
@@ -140,14 +140,14 @@
interrupt-parent = <&MPIC>;
};
- OHCI0: ohci@30010010000 {
+ OHCI0: usb@30010010000 {
compatible = "ibm,476gtr-ohci", "generic-ohci";
reg = <0x300 0x10010000 0x0 0x10000>;
interrupt-parent = <&MPIC>;
interrupts = <89 1>;
};
- OHCI1: ohci@30010020000 {
+ OHCI1: usb@30010020000 {
compatible = "ibm,476gtr-ohci", "generic-ohci";
reg = <0x300 0x10020000 0x0 0x10000>;
interrupt-parent = <&MPIC>;
diff --git a/arch/powerpc/boot/dts/fsl/Makefile b/arch/powerpc/boot/dts/fsl/Makefile
index 3bae982641e9..d3ecdf14bc42 100644
--- a/arch/powerpc/boot/dts/fsl/Makefile
+++ b/arch/powerpc/boot/dts/fsl/Makefile
@@ -1,4 +1,3 @@
# SPDX-License-Identifier: GPL-2.0
-dtstree := $(srctree)/$(src)
-dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
index 4f044b41a776..fb3200b006ad 100644
--- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
@@ -50,7 +50,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
interrupts = <25 2 0 0>;
};
diff --git a/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts b/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
index 8da984251abc..0ba86a6dce1b 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
@@ -15,7 +15,7 @@
device_type = "memory";
};
- board_ifc: ifc: ifc@ff71e000 {
+ board_ifc: ifc: memory-controller@ff71e000 {
/* NAND Flash on board */
ranges = <0x0 0x0 0x0 0xff800000 0x00004000>;
reg = <0x0 0xff71e000 0x0 0x2000>;
diff --git a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
index 2a677fd323eb..5c53cee8755f 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
@@ -35,7 +35,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
interrupts = <16 2 0 0 20 2 0 0>;
};
diff --git a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
index 7cb2158dfe58..ce642e879a1b 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
+++ b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
@@ -15,7 +15,7 @@
device_type = "memory";
};
- ifc: ifc@ff71e000 {
+ ifc: memory-controller@ff71e000 {
/* NOR, NAND Flash on board */
ranges = <0x0 0x0 0x0 0x88000000 0x08000000
0x1 0x0 0x0 0xff800000 0x00010000>;
diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
index b8e0edd1ac69..4da451e000d9 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
@@ -35,7 +35,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
/* FIXME: Test whether interrupts are split */
interrupts = <16 2 0 0 20 2 0 0>;
};
diff --git a/arch/powerpc/boot/dts/fsl/c293pcie.dts b/arch/powerpc/boot/dts/fsl/c293pcie.dts
index 5e905e0857cf..e2fdac2ed420 100644
--- a/arch/powerpc/boot/dts/fsl/c293pcie.dts
+++ b/arch/powerpc/boot/dts/fsl/c293pcie.dts
@@ -42,7 +42,7 @@
device_type = "memory";
};
- ifc: ifc@fffe1e000 {
+ ifc: memory-controller@fffe1e000 {
reg = <0xf 0xffe1e000 0 0x2000>;
ranges = <0x0 0x0 0xf 0xec000000 0x04000000
0x1 0x0 0xf 0xff800000 0x00010000
diff --git a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi
index f208fb8f64b3..2d443d519274 100644
--- a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi
@@ -35,7 +35,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
interrupts = <19 2 0 0>;
};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
index 41935709ebe8..fba40a1bccc0 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
@@ -199,6 +199,10 @@
/include/ "pq3-dma-0.dtsi"
/include/ "pq3-etsec1-0.dtsi"
+ enet0: ethernet@24000 {
+ fsl,wake-on-filer;
+ fsl,pmc-handle = <&etsec1_clk>;
+ };
/include/ "pq3-etsec1-timer-0.dtsi"
usb@22000 {
@@ -222,9 +226,10 @@
};
/include/ "pq3-etsec1-2.dtsi"
-
- ethernet@26000 {
+ enet2: ethernet@26000 {
cell-index = <1>;
+ fsl,wake-on-filer;
+ fsl,pmc-handle = <&etsec3_clk>;
};
usb@2b000 {
@@ -249,4 +254,9 @@
reg = <0xe0000 0x1000>;
fsl,has-rstcr;
};
+
+/include/ "pq3-power.dtsi"
+ power@e0070 {
+ compatible = "fsl,mpc8536-pmc", "fsl,mpc8548-pmc";
+ };
};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi
index b68eb119faef..ea7416af7ee3 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi
@@ -188,4 +188,6 @@
reg = <0xe0000 0x1000>;
fsl,has-rstcr;
};
+
+/include/ "pq3-power.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
index 579d76cb8e32..dddb7374508d 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
@@ -156,4 +156,6 @@
reg = <0xe0000 0x1000>;
fsl,has-rstcr;
};
+
+/include/ "pq3-power.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi
index 49294cf36b4e..40a6cff77032 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi
@@ -193,4 +193,6 @@
reg = <0xe0000 0x1000>;
fsl,has-rstcr;
};
+
+/include/ "pq3-power.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts b/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
index 3a94acbb3c03..ce3346d77858 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
@@ -29,3 +29,19 @@
};
/include/ "p1010si-post.dtsi"
+
+&pci0 {
+ pcie@0 {
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ /*
+ *irq[4:5] are active-high
+ *irq[6:7] are active-low
+ */
+ 0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0
+ 0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0
+ 0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0
+ 0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0
+ >;
+ };
+};
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts b/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts
index 4cf255fedc96..83590354f9a0 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts
@@ -56,3 +56,19 @@
};
/include/ "p1010si-post.dtsi"
+
+&pci0 {
+ pcie@0 {
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ /*
+ *irq[4:5] are active-high
+ *irq[6:7] are active-low
+ */
+ 0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0
+ 0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0
+ 0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0
+ 0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0
+ >;
+ };
+};
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi
index 2ca9cee2ddeb..ef49a7d6c69d 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi
@@ -215,19 +215,3 @@
phy-connection-type = "sgmii";
};
};
-
-&pci0 {
- pcie@0 {
- interrupt-map = <
- /* IDSEL 0x0 */
- /*
- *irq[4:5] are active-high
- *irq[6:7] are active-low
- */
- 0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0
- 0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0
- 0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0
- 0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0
- >;
- };
-};
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi
index fdc19aab2f70..583a6cd05079 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi
@@ -36,7 +36,7 @@ memory {
device_type = "memory";
};
-board_ifc: ifc: ifc@ffe1e000 {
+board_ifc: ifc: memory-controller@ffe1e000 {
/* NOR, NAND Flashes and CPLD on board */
ranges = <0x0 0x0 0x0 0xee000000 0x02000000
0x1 0x0 0x0 0xff800000 0x00010000
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi
index de2fceed4f79..4d41efe0038f 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi
@@ -36,7 +36,7 @@ memory {
device_type = "memory";
};
-board_ifc: ifc: ifc@fffe1e000 {
+board_ifc: ifc: memory-controller@fffe1e000 {
/* NOR, NAND Flashes and CPLD on board */
ranges = <0x0 0x0 0xf 0xee000000 0x02000000
0x1 0x0 0xf 0xff800000 0x00010000
diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
index ccda0a91abf0..2d2550729dcc 100644
--- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
@@ -35,7 +35,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
interrupts = <16 2 0 0 19 2 0 0>;
};
@@ -183,9 +183,23 @@
/include/ "pq3-etsec2-1.dtsi"
/include/ "pq3-etsec2-2.dtsi"
+ enet0: ethernet@b0000 {
+ fsl,pmc-handle = <&etsec1_clk>;
+ };
+
+ enet1: ethernet@b1000 {
+ fsl,pmc-handle = <&etsec2_clk>;
+ };
+
+ enet2: ethernet@b2000 {
+ fsl,pmc-handle = <&etsec3_clk>;
+ };
+
global-utilities@e0000 {
compatible = "fsl,p1010-guts";
reg = <0xe0000 0x1000>;
fsl,has-rstcr;
};
+
+/include/ "pq3-power.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
index 642dc3a83d0e..cc4c7461003b 100644
--- a/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
@@ -163,14 +163,17 @@
/include/ "pq3-etsec2-0.dtsi"
enet0: enet0_grp2: ethernet@b0000 {
+ fsl,pmc-handle = <&etsec1_clk>;
};
/include/ "pq3-etsec2-1.dtsi"
enet1: enet1_grp2: ethernet@b1000 {
+ fsl,pmc-handle = <&etsec2_clk>;
};
/include/ "pq3-etsec2-2.dtsi"
enet2: enet2_grp2: ethernet@b2000 {
+ fsl,pmc-handle = <&etsec3_clk>;
};
global-utilities@e0000 {
@@ -178,6 +181,8 @@
reg = <0xe0000 0x1000>;
fsl,has-rstcr;
};
+
+/include/ "pq3-power.dtsi"
};
/include/ "pq3-etsec2-grp2-0.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
index 407cb5fd0f5b..378195db9fca 100644
--- a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
@@ -159,14 +159,17 @@
/include/ "pq3-etsec2-0.dtsi"
enet0: enet0_grp2: ethernet@b0000 {
+ fsl,pmc-handle = <&etsec1_clk>;
};
/include/ "pq3-etsec2-1.dtsi"
enet1: enet1_grp2: ethernet@b1000 {
+ fsl,pmc-handle = <&etsec2_clk>;
};
/include/ "pq3-etsec2-2.dtsi"
enet2: enet2_grp2: ethernet@b2000 {
+ fsl,pmc-handle = <&etsec3_clk>;
};
global-utilities@e0000 {
@@ -174,6 +177,8 @@
reg = <0xe0000 0x1000>;
fsl,has-rstcr;
};
+
+/include/ "pq3-power.dtsi"
};
&qe {
diff --git a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
index 093e4e3ed368..6ac21e81344a 100644
--- a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
@@ -225,11 +225,13 @@
/include/ "pq3-etsec2-0.dtsi"
enet0: enet0_grp2: ethernet@b0000 {
fsl,wake-on-filer;
+ fsl,pmc-handle = <&etsec1_clk>;
};
/include/ "pq3-etsec2-1.dtsi"
enet1: enet1_grp2: ethernet@b1000 {
fsl,wake-on-filer;
+ fsl,pmc-handle = <&etsec2_clk>;
};
global-utilities@e0000 {
@@ -238,9 +240,10 @@
fsl,has-rstcr;
};
+/include/ "pq3-power.dtsi"
power@e0070 {
- compatible = "fsl,mpc8536-pmc", "fsl,mpc8548-pmc";
- reg = <0xe0070 0x20>;
+ compatible = "fsl,p1022-pmc", "fsl,mpc8536-pmc",
+ "fsl,mpc8548-pmc";
};
};
diff --git a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
index 81b9ab2119be..d410082d21c0 100644
--- a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
@@ -178,6 +178,10 @@
compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
};
/include/ "pq3-etsec1-0.dtsi"
+ enet0: ethernet@24000 {
+ fsl,pmc-handle = <&etsec1_clk>;
+
+ };
/include/ "pq3-etsec1-timer-0.dtsi"
ptp_clock@24e00 {
@@ -186,7 +190,15 @@
/include/ "pq3-etsec1-1.dtsi"
+ enet1: ethernet@25000 {
+ fsl,pmc-handle = <&etsec2_clk>;
+ };
+
/include/ "pq3-etsec1-2.dtsi"
+ enet2: ethernet@26000 {
+ fsl,pmc-handle = <&etsec3_clk>;
+ };
+
/include/ "pq3-esdhc-0.dtsi"
sdhc@2e000 {
compatible = "fsl,p2020-esdhc", "fsl,esdhc";
@@ -202,8 +214,5 @@
fsl,has-rstcr;
};
- pmc: power@e0070 {
- compatible = "fsl,mpc8548-pmc";
- reg = <0xe0070 0x20>;
- };
+/include/ "pq3-power.dtsi"
};
diff --git a/arch/powerpc/boot/dts/fsl/pq3-power.dtsi b/arch/powerpc/boot/dts/fsl/pq3-power.dtsi
new file mode 100644
index 000000000000..6af12401004d
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/pq3-power.dtsi
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: (GPL-2.0+)
+/*
+ * Copyright 2024 NXP
+ */
+
+power@e0070 {
+ compatible = "fsl,mpc8548-pmc";
+ reg = <0xe0070 0x20>;
+
+ etsec1_clk: soc-clk@24 {
+ fsl,pmcdr-mask = <0x00000080>;
+ };
+ etsec2_clk: soc-clk@25 {
+ fsl,pmcdr-mask = <0x00000040>;
+ };
+ etsec3_clk: soc-clk@26 {
+ fsl,pmcdr-mask = <0x00000020>;
+ };
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
index aa5152ca8120..8ef0c020206b 100644
--- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
@@ -52,7 +52,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
interrupts = <25 2 0 0>;
};
diff --git a/arch/powerpc/boot/dts/fsl/t1024rdb.dts b/arch/powerpc/boot/dts/fsl/t1024rdb.dts
index 270aaf631f2a..7d003e07a9fb 100644
--- a/arch/powerpc/boot/dts/fsl/t1024rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1024rdb.dts
@@ -91,7 +91,7 @@
board-control@2,0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "fsl,t1024-cpld";
+ compatible = "fsl,t1024-cpld", "fsl,deepsleep-cpld";
reg = <3 0 0x300>;
ranges = <0 3 0 0x300>;
bank-width = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
index dd3aab81e9de..4347924e9aa7 100644
--- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
@@ -104,7 +104,7 @@
ifc: localbus@ffe124000 {
cpld@3,0 {
- compatible = "fsl,t1040rdb-cpld";
+ compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld";
};
};
};
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index 776788623204..c9542b73bd7f 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -52,7 +52,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
interrupts = <25 2 0 0>;
};
diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb.dts b/arch/powerpc/boot/dts/fsl/t1042rdb.dts
index 3ebb712224cb..099764322b33 100644
--- a/arch/powerpc/boot/dts/fsl/t1042rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1042rdb.dts
@@ -68,7 +68,7 @@
ifc: localbus@ffe124000 {
cpld@3,0 {
- compatible = "fsl,t1042rdb-cpld";
+ compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld";
};
};
};
diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts b/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts
index 8ec3ff45e6fc..b10cab1a347b 100644
--- a/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts
+++ b/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts
@@ -41,7 +41,7 @@
ifc: localbus@ffe124000 {
cpld@3,0 {
- compatible = "fsl,t1042rdb_pi-cpld";
+ compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld";
};
};
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index 27714dc2f04a..6bb95878d39d 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -50,7 +50,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
interrupts = <25 2 0 0>;
};
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index fcac73486d48..65f3e17c0d41 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -50,7 +50,7 @@
&ifc {
#address-cells = <2>;
#size-cells = <1>;
- compatible = "fsl,ifc", "simple-bus";
+ compatible = "fsl,ifc";
interrupts = <25 2 0 0>;
};
diff --git a/arch/powerpc/boot/dts/haleakala.dts b/arch/powerpc/boot/dts/haleakala.dts
deleted file mode 100644
index f81ce8786d59..000000000000
--- a/arch/powerpc/boot/dts/haleakala.dts
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * Device Tree Source for AMCC Haleakala (405EXr)
- *
- * Copyright 2008 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
- #address-cells = <1>;
- #size-cells = <1>;
- model = "amcc,haleakala";
- compatible = "amcc,haleakala", "amcc,kilauea";
- dcr-parent = <&{/cpus/cpu@0}>;
-
- aliases {
- ethernet0 = &EMAC0;
- serial0 = &UART0;
- serial1 = &UART1;
- };
-
- cpus {
- #address-cells = <1>;
- #size-cells = <0>;
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,405EXr";
- reg = <0x00000000>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- timebase-frequency = <0>; /* Filled in by U-Boot */
- i-cache-line-size = <32>;
- d-cache-line-size = <32>;
- i-cache-size = <16384>; /* 16 kB */
- d-cache-size = <16384>; /* 16 kB */
- dcr-controller;
- dcr-access-method = "native";
- };
- };
-
- memory {
- device_type = "memory";
- reg = <0x00000000 0x00000000>; /* Filled in by U-Boot */
- };
-
- UIC0: interrupt-controller {
- compatible = "ibm,uic-405exr", "ibm,uic";
- interrupt-controller;
- cell-index = <0>;
- dcr-reg = <0x0c0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- };
-
- UIC1: interrupt-controller1 {
- compatible = "ibm,uic-405exr","ibm,uic";
- interrupt-controller;
- cell-index = <1>;
- dcr-reg = <0x0d0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- UIC2: interrupt-controller2 {
- compatible = "ibm,uic-405exr","ibm,uic";
- interrupt-controller;
- cell-index = <2>;
- dcr-reg = <0x0e0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1c 0x4 0x1d 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- plb {
- compatible = "ibm,plb-405exr", "ibm,plb4";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- SDRAM0: memory-controller {
- compatible = "ibm,sdram-405exr", "ibm,sdram-4xx-ddr2";
- dcr-reg = <0x010 0x002>;
- interrupt-parent = <&UIC2>;
- interrupts = <0x5 0x4 /* ECC DED Error */
- 0x6 0x4>; /* ECC SEC Error */
- };
-
- MAL0: mcmal {
- compatible = "ibm,mcmal-405exr", "ibm,mcmal2";
- dcr-reg = <0x180 0x062>;
- num-tx-chans = <2>;
- num-rx-chans = <2>;
- interrupt-parent = <&MAL0>;
- interrupts = <0x0 0x1 0x2 0x3 0x4>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*TXEOB*/ 0x0 &UIC0 0xa 0x4
- /*RXEOB*/ 0x1 &UIC0 0xb 0x4
- /*SERR*/ 0x2 &UIC1 0x0 0x4
- /*TXDE*/ 0x3 &UIC1 0x1 0x4
- /*RXDE*/ 0x4 &UIC1 0x2 0x4>;
- interrupt-map-mask = <0xffffffff>;
- };
-
- POB0: opb {
- compatible = "ibm,opb-405exr", "ibm,opb";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0x80000000 0x80000000 0x10000000
- 0xef600000 0xef600000 0x00a00000
- 0xf0000000 0xf0000000 0x10000000>;
- dcr-reg = <0x0a0 0x005>;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- EBC0: ebc {
- compatible = "ibm,ebc-405exr", "ibm,ebc";
- dcr-reg = <0x012 0x002>;
- #address-cells = <2>;
- #size-cells = <1>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- /* ranges property is supplied by U-Boot */
- interrupts = <0x5 0x1>;
- interrupt-parent = <&UIC1>;
-
- nor_flash@0,0 {
- compatible = "amd,s29gl512n", "cfi-flash";
- bank-width = <2>;
- reg = <0x00000000 0x00000000 0x04000000>;
- #address-cells = <1>;
- #size-cells = <1>;
- partition@0 {
- label = "kernel";
- reg = <0x00000000 0x00200000>;
- };
- partition@200000 {
- label = "root";
- reg = <0x00200000 0x00200000>;
- };
- partition@400000 {
- label = "user";
- reg = <0x00400000 0x03b60000>;
- };
- partition@3f60000 {
- label = "env";
- reg = <0x03f60000 0x00040000>;
- };
- partition@3fa0000 {
- label = "u-boot";
- reg = <0x03fa0000 0x00060000>;
- };
- };
- };
-
- UART0: serial@ef600200 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600200 0x00000008>;
- virtual-reg = <0xef600200>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- current-speed = <0>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1a 0x4>;
- };
-
- UART1: serial@ef600300 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600300 0x00000008>;
- virtual-reg = <0xef600300>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- current-speed = <0>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1 0x4>;
- };
-
- IIC0: i2c@ef600400 {
- compatible = "ibm,iic-405exr", "ibm,iic";
- reg = <0xef600400 0x00000014>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x2 0x4>;
- };
-
- IIC1: i2c@ef600500 {
- compatible = "ibm,iic-405exr", "ibm,iic";
- reg = <0xef600500 0x00000014>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x7 0x4>;
- };
-
-
- RGMII0: emac-rgmii@ef600b00 {
- compatible = "ibm,rgmii-405exr", "ibm,rgmii";
- reg = <0xef600b00 0x00000104>;
- has-mdio;
- };
-
- EMAC0: ethernet@ef600900 {
- linux,network-index = <0x0>;
- device_type = "network";
- compatible = "ibm,emac-405exr", "ibm,emac4sync";
- interrupt-parent = <&EMAC0>;
- interrupts = <0x0 0x1>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x18 0x4
- /*Wake*/ 0x1 &UIC1 0x1d 0x4>;
- reg = <0xef600900 0x000000c4>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <0>;
- mal-rx-channel = <0>;
- cell-index = <0>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- rx-fifo-size-gige = <16384>;
- tx-fifo-size-gige = <16384>;
- phy-mode = "rgmii";
- phy-map = <0x00000000>;
- rgmii-device = <&RGMII0>;
- rgmii-channel = <0>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- };
- };
-
- PCIE0: pcie@a0000000 {
- device_type = "pci";
- #interrupt-cells = <1>;
- #size-cells = <2>;
- #address-cells = <3>;
- compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
- primary;
- port = <0x0>; /* port number */
- reg = <0xa0000000 0x20000000 /* Config space access */
- 0xef000000 0x00001000>; /* Registers */
- dcr-reg = <0x040 0x020>;
- sdr-base = <0x400>;
-
- /* Outbound ranges, one memory and one IO,
- * later cannot be changed
- */
- ranges = <0x02000000 0x00000000 0x80000000 0x90000000 0x00000000 0x08000000
- 0x01000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00010000>;
-
- /* Inbound 2GB range starting at 0 */
- dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
- /* This drives busses 0x00 to 0x3f */
- bus-range = <0x0 0x3f>;
-
- /* Legacy interrupts (note the weird polarity, the bridge seems
- * to invert PCIe legacy interrupts).
- * We are de-swizzling here because the numbers are actually for
- * port of the root complex virtual P2P bridge. But I want
- * to avoid putting a node for it in the tree, so the numbers
- * below are basically de-swizzled numbers.
- * The real slot is on idsel 0, so the swizzling is 1:1
- */
- interrupt-map-mask = <0x0 0x0 0x0 0x7>;
- interrupt-map = <
- 0x0 0x0 0x0 0x1 &UIC2 0x0 0x4 /* swizzled int A */
- 0x0 0x0 0x0 0x2 &UIC2 0x1 0x4 /* swizzled int B */
- 0x0 0x0 0x0 0x3 &UIC2 0x2 0x4 /* swizzled int C */
- 0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
- };
- };
-};
diff --git a/arch/powerpc/boot/dts/hotfoot.dts b/arch/powerpc/boot/dts/hotfoot.dts
deleted file mode 100644
index b93bf2d9dd5b..000000000000
--- a/arch/powerpc/boot/dts/hotfoot.dts
+++ /dev/null
@@ -1,296 +0,0 @@
-/*
- * Device Tree Source for ESTeem 195E Hotfoot
- *
- * Copyright 2009 AbsoluteValue Systems <solomon@linux-wlan.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
- #address-cells = <1>;
- #size-cells = <1>;
- model = "est,hotfoot";
- compatible = "est,hotfoot";
- dcr-parent = <&{/cpus/cpu@0}>;
-
- aliases {
- ethernet0 = &EMAC0;
- ethernet1 = &EMAC1;
- serial0 = &UART0;
- serial1 = &UART1;
- };
-
- cpus {
- #address-cells = <1>;
- #size-cells = <0>;
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,405EP";
- reg = <0x00000000>;
- clock-frequency = <0>; /* Filled in by zImage */
- timebase-frequency = <0>; /* Filled in by zImage */
- i-cache-line-size = <0x20>;
- d-cache-line-size = <0x20>;
- i-cache-size = <0x4000>;
- d-cache-size = <0x4000>;
- dcr-controller;
- dcr-access-method = "native";
- };
- };
-
- memory {
- device_type = "memory";
- reg = <0x00000000 0x00000000>; /* Filled in by zImage */
- };
-
- UIC0: interrupt-controller {
- compatible = "ibm,uic";
- interrupt-controller;
- cell-index = <0>;
- dcr-reg = <0x0c0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- };
-
- plb {
- compatible = "ibm,plb3";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges;
- clock-frequency = <0>; /* Filled in by zImage */
-
- SDRAM0: memory-controller {
- compatible = "ibm,sdram-405ep";
- dcr-reg = <0x010 0x002>;
- };
-
- MAL: mcmal {
- compatible = "ibm,mcmal-405ep", "ibm,mcmal";
- dcr-reg = <0x180 0x062>;
- num-tx-chans = <4>;
- num-rx-chans = <2>;
- interrupt-parent = <&UIC0>;
- interrupts = <
- 0xb 0x4 /* TXEOB */
- 0xc 0x4 /* RXEOB */
- 0xa 0x4 /* SERR */
- 0xd 0x4 /* TXDE */
- 0xe 0x4 /* RXDE */>;
- };
-
- POB0: opb {
- compatible = "ibm,opb-405ep", "ibm,opb";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0xef600000 0xef600000 0x00a00000>;
- dcr-reg = <0x0a0 0x005>;
- clock-frequency = <0>; /* Filled in by zImage */
-
- /* Hotfoot has UART0/UART1 swapped */
-
- UART0: serial@ef600400 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600400 0x00000008>;
- virtual-reg = <0xef600400>;
- clock-frequency = <0>; /* Filled in by zImage */
- current-speed = <0x9600>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1 0x4>;
- };
-
- UART1: serial@ef600300 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600300 0x00000008>;
- virtual-reg = <0xef600300>;
- clock-frequency = <0>; /* Filled in by zImage */
- current-speed = <0x9600>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x0 0x4>;
- };
-
- IIC: i2c@ef600500 {
- #address-cells = <1>;
- #size-cells = <0>;
- compatible = "ibm,iic-405ep", "ibm,iic";
- reg = <0xef600500 0x00000011>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x2 0x4>;
-
- rtc@68 {
- /* Actually a DS1339 */
- compatible = "dallas,ds1307";
- reg = <0x68>;
- };
-
- temp@4a {
- /* Not present on all boards */
- compatible = "national,lm75";
- reg = <0x4a>;
- };
- };
-
- GPIO: gpio@ef600700 {
- #gpio-cells = <2>;
- compatible = "ibm,ppc4xx-gpio";
- reg = <0xef600700 0x00000020>;
- gpio-controller;
- };
-
- gpio-leds {
- compatible = "gpio-leds";
- status {
- label = "Status";
- gpios = <&GPIO 1 0>;
- };
- radiorx {
- label = "Rx";
- gpios = <&GPIO 0xe 0>;
- };
- };
-
- EMAC0: ethernet@ef600800 {
- linux,network-index = <0x0>;
- device_type = "network";
- compatible = "ibm,emac-405ep", "ibm,emac";
- interrupt-parent = <&UIC0>;
- interrupts = <
- 0xf 0x4 /* Ethernet */
- 0x9 0x4 /* Ethernet Wake Up */>;
- local-mac-address = [000000000000]; /* Filled in by zImage */
- reg = <0xef600800 0x00000070>;
- mal-device = <&MAL>;
- mal-tx-channel = <0>;
- mal-rx-channel = <0>;
- cell-index = <0>;
- max-frame-size = <0x5dc>;
- rx-fifo-size = <0x1000>;
- tx-fifo-size = <0x800>;
- phy-mode = "mii";
- phy-map = <0x00000000>;
- };
-
- EMAC1: ethernet@ef600900 {
- linux,network-index = <0x1>;
- device_type = "network";
- compatible = "ibm,emac-405ep", "ibm,emac";
- interrupt-parent = <&UIC0>;
- interrupts = <
- 0x11 0x4 /* Ethernet */
- 0x9 0x4 /* Ethernet Wake Up */>;
- local-mac-address = [000000000000]; /* Filled in by zImage */
- reg = <0xef600900 0x00000070>;
- mal-device = <&MAL>;
- mal-tx-channel = <2>;
- mal-rx-channel = <1>;
- cell-index = <1>;
- max-frame-size = <0x5dc>;
- rx-fifo-size = <0x1000>;
- tx-fifo-size = <0x800>;
- mdio-device = <&EMAC0>;
- phy-mode = "mii";
- phy-map = <0x0000001>;
- };
- };
-
- EBC0: ebc {
- compatible = "ibm,ebc-405ep", "ibm,ebc";
- dcr-reg = <0x012 0x002>;
- #address-cells = <2>;
- #size-cells = <1>;
-
- /* The ranges property is supplied by the bootwrapper
- * and is based on the firmware's configuration of the
- * EBC bridge
- */
- clock-frequency = <0>; /* Filled in by zImage */
-
- nor_flash@0 {
- compatible = "cfi-flash";
- bank-width = <2>;
- reg = <0x0 0xff800000 0x00800000>;
- #address-cells = <1>;
- #size-cells = <1>;
-
- /* This mapping is for the 8M flash
- 4M flash has all ofssets -= 4M,
- and FeatFS partition is not present */
- partition@0 {
- label = "Bootloader";
- reg = <0x7c0000 0x40000>;
- /* read-only; */
- };
- partition@1 {
- label = "Env_and_Config_Primary";
- reg = <0x400000 0x10000>;
- };
- partition@2 {
- label = "Kernel";
- reg = <0x420000 0x100000>;
- };
- partition@3 {
- label = "Filesystem";
- reg = <0x520000 0x2a0000>;
- };
- partition@4 {
- label = "Env_and_Config_Secondary";
- reg = <0x410000 0x10000>;
- };
- partition@5 {
- label = "FeatFS";
- reg = <0x000000 0x400000>;
- };
- partition@6 {
- label = "Bootloader_Env";
- reg = <0x7d0000 0x10000>;
- };
- };
- };
-
- PCI0: pci@ec000000 {
- device_type = "pci";
- #interrupt-cells = <1>;
- #size-cells = <2>;
- #address-cells = <3>;
- compatible = "ibm,plb405ep-pci", "ibm,plb-pci";
- primary;
- reg = <0xeec00000 0x00000008 /* Config space access */
- 0xeed80000 0x00000004 /* IACK */
- 0xeed80000 0x00000004 /* Special cycle */
- 0xef480000 0x00000040>; /* Internal registers */
-
- /* Outbound ranges, one memory and one IO,
- * later cannot be changed. Chip supports a second
- * IO range but we don't use it for now
- */
- ranges = <0x02000000 0x00000000 0x80000000 0x80000000 0x00000000 0x20000000
- 0x01000000 0x00000000 0x00000000 0xe8000000 0x00000000 0x00010000>;
-
- /* Inbound 2GB range starting at 0 */
- dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
- interrupt-parent = <&UIC0>;
- interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
- interrupt-map = <
- /* IDSEL 3 -- slot1 (optional) 27/29 A/B IRQ2/4 */
- 0x1800 0x0 0x0 0x1 &UIC0 0x1b 0x8
- 0x1800 0x0 0x0 0x2 &UIC0 0x1d 0x8
-
- /* IDSEL 4 -- slot0, 26/28 A/B IRQ1/3 */
- 0x2000 0x0 0x0 0x1 &UIC0 0x1a 0x8
- 0x2000 0x0 0x0 0x2 &UIC0 0x1c 0x8
- >;
- };
- };
-
- chosen {
- stdout-path = &UART0;
- };
-};
diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts
deleted file mode 100644
index c07a7525a72c..000000000000
--- a/arch/powerpc/boot/dts/kilauea.dts
+++ /dev/null
@@ -1,407 +0,0 @@
-/*
- * Device Tree Source for AMCC Kilauea (405EX)
- *
- * Copyright 2007-2009 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
- #address-cells = <1>;
- #size-cells = <1>;
- model = "amcc,kilauea";
- compatible = "amcc,kilauea";
- dcr-parent = <&{/cpus/cpu@0}>;
-
- aliases {
- ethernet0 = &EMAC0;
- ethernet1 = &EMAC1;
- serial0 = &UART0;
- serial1 = &UART1;
- };
-
- cpus {
- #address-cells = <1>;
- #size-cells = <0>;
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,405EX";
- reg = <0x00000000>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- timebase-frequency = <0>; /* Filled in by U-Boot */
- i-cache-line-size = <32>;
- d-cache-line-size = <32>;
- i-cache-size = <16384>; /* 16 kB */
- d-cache-size = <16384>; /* 16 kB */
- dcr-controller;
- dcr-access-method = "native";
- };
- };
-
- memory {
- device_type = "memory";
- reg = <0x00000000 0x00000000>; /* Filled in by U-Boot */
- };
-
- UIC0: interrupt-controller {
- compatible = "ibm,uic-405ex", "ibm,uic";
- interrupt-controller;
- cell-index = <0>;
- dcr-reg = <0x0c0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- };
-
- UIC1: interrupt-controller1 {
- compatible = "ibm,uic-405ex","ibm,uic";
- interrupt-controller;
- cell-index = <1>;
- dcr-reg = <0x0d0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- UIC2: interrupt-controller2 {
- compatible = "ibm,uic-405ex","ibm,uic";
- interrupt-controller;
- cell-index = <2>;
- dcr-reg = <0x0e0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1c 0x4 0x1d 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- CPM0: cpm {
- compatible = "ibm,cpm";
- dcr-access-method = "native";
- dcr-reg = <0x0b0 0x003>;
- unused-units = <0x00000000>;
- idle-doze = <0x02000000>;
- standby = <0xe3e74800>;
- };
-
- plb {
- compatible = "ibm,plb-405ex", "ibm,plb4";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- SDRAM0: memory-controller {
- compatible = "ibm,sdram-405ex", "ibm,sdram-4xx-ddr2";
- dcr-reg = <0x010 0x002>;
- interrupt-parent = <&UIC2>;
- interrupts = <0x5 0x4 /* ECC DED Error */
- 0x6 0x4>; /* ECC SEC Error */
- };
-
- CRYPTO: crypto@ef700000 {
- compatible = "amcc,ppc405ex-crypto", "amcc,ppc4xx-crypto";
- reg = <0xef700000 0x80400>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x17 0x2>;
- };
-
- MAL0: mcmal {
- compatible = "ibm,mcmal-405ex", "ibm,mcmal2";
- dcr-reg = <0x180 0x062>;
- num-tx-chans = <2>;
- num-rx-chans = <2>;
- interrupt-parent = <&MAL0>;
- interrupts = <0x0 0x1 0x2 0x3 0x4>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*TXEOB*/ 0x0 &UIC0 0xa 0x4
- /*RXEOB*/ 0x1 &UIC0 0xb 0x4
- /*SERR*/ 0x2 &UIC1 0x0 0x4
- /*TXDE*/ 0x3 &UIC1 0x1 0x4
- /*RXDE*/ 0x4 &UIC1 0x2 0x4>;
- interrupt-map-mask = <0xffffffff>;
- };
-
- POB0: opb {
- compatible = "ibm,opb-405ex", "ibm,opb";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0x80000000 0x80000000 0x10000000
- 0xef600000 0xef600000 0x00a00000
- 0xf0000000 0xf0000000 0x10000000>;
- dcr-reg = <0x0a0 0x005>;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- EBC0: ebc {
- compatible = "ibm,ebc-405ex", "ibm,ebc";
- dcr-reg = <0x012 0x002>;
- #address-cells = <2>;
- #size-cells = <1>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- /* ranges property is supplied by U-Boot */
- interrupts = <0x5 0x1>;
- interrupt-parent = <&UIC1>;
-
- nor_flash@0,0 {
- compatible = "amd,s29gl512n", "cfi-flash";
- bank-width = <2>;
- reg = <0x00000000 0x00000000 0x04000000>;
- #address-cells = <1>;
- #size-cells = <1>;
- partition@0 {
- label = "kernel";
- reg = <0x00000000 0x001e0000>;
- };
- partition@1e0000 {
- label = "dtb";
- reg = <0x001e0000 0x00020000>;
- };
- partition@200000 {
- label = "root";
- reg = <0x00200000 0x00200000>;
- };
- partition@400000 {
- label = "user";
- reg = <0x00400000 0x03b60000>;
- };
- partition@3f60000 {
- label = "env";
- reg = <0x03f60000 0x00040000>;
- };
- partition@3fa0000 {
- label = "u-boot";
- reg = <0x03fa0000 0x00060000>;
- };
- };
-
- ndfc@1,0 {
- compatible = "ibm,ndfc";
- reg = <0x00000001 0x00000000 0x00002000>;
- ccr = <0x00001000>;
- bank-settings = <0x80002222>;
- #address-cells = <1>;
- #size-cells = <1>;
-
- nand {
- #address-cells = <1>;
- #size-cells = <1>;
-
- partition@0 {
- label = "u-boot";
- reg = <0x00000000 0x00100000>;
- };
- partition@100000 {
- label = "user";
- reg = <0x00000000 0x03f00000>;
- };
- };
- };
- };
-
- UART0: serial@ef600200 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600200 0x00000008>;
- virtual-reg = <0xef600200>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- current-speed = <0>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1a 0x4>;
- };
-
- UART1: serial@ef600300 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600300 0x00000008>;
- virtual-reg = <0xef600300>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- current-speed = <0>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1 0x4>;
- };
-
- IIC0: i2c@ef600400 {
- compatible = "ibm,iic-405ex", "ibm,iic";
- reg = <0xef600400 0x00000014>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x2 0x4>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- rtc@68 {
- compatible = "dallas,ds1338";
- reg = <0x68>;
- };
-
- dtt@48 {
- compatible = "dallas,ds1775";
- reg = <0x48>;
- };
- };
-
- IIC1: i2c@ef600500 {
- compatible = "ibm,iic-405ex", "ibm,iic";
- reg = <0xef600500 0x00000014>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x7 0x4>;
- };
-
- RGMII0: emac-rgmii@ef600b00 {
- compatible = "ibm,rgmii-405ex", "ibm,rgmii";
- reg = <0xef600b00 0x00000104>;
- has-mdio;
- };
-
- EMAC0: ethernet@ef600900 {
- linux,network-index = <0x0>;
- device_type = "network";
- compatible = "ibm,emac-405ex", "ibm,emac4sync";
- interrupt-parent = <&EMAC0>;
- interrupts = <0x0 0x1>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x18 0x4
- /*Wake*/ 0x1 &UIC1 0x1d 0x4>;
- reg = <0xef600900 0x000000c4>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <0>;
- mal-rx-channel = <0>;
- cell-index = <0>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- rx-fifo-size-gige = <16384>;
- tx-fifo-size-gige = <16384>;
- phy-mode = "rgmii";
- phy-map = <0x00000000>;
- rgmii-device = <&RGMII0>;
- rgmii-channel = <0>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- };
-
- EMAC1: ethernet@ef600a00 {
- linux,network-index = <0x1>;
- device_type = "network";
- compatible = "ibm,emac-405ex", "ibm,emac4sync";
- interrupt-parent = <&EMAC1>;
- interrupts = <0x0 0x1>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x19 0x4
- /*Wake*/ 0x1 &UIC1 0x1f 0x4>;
- reg = <0xef600a00 0x000000c4>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <1>;
- mal-rx-channel = <1>;
- cell-index = <1>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- rx-fifo-size-gige = <16384>;
- tx-fifo-size-gige = <16384>;
- phy-mode = "rgmii";
- phy-map = <0x00000000>;
- rgmii-device = <&RGMII0>;
- rgmii-channel = <1>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- };
- };
-
- PCIE0: pcie@a0000000 {
- device_type = "pci";
- #interrupt-cells = <1>;
- #size-cells = <2>;
- #address-cells = <3>;
- compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
- primary;
- port = <0x0>; /* port number */
- reg = <0xa0000000 0x20000000 /* Config space access */
- 0xef000000 0x00001000>; /* Registers */
- dcr-reg = <0x040 0x020>;
- sdr-base = <0x400>;
-
- /* Outbound ranges, one memory and one IO,
- * later cannot be changed
- */
- ranges = <0x02000000 0x00000000 0x80000000 0x90000000 0x00000000 0x08000000
- 0x01000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00010000>;
-
- /* Inbound 2GB range starting at 0 */
- dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
- /* This drives busses 0x00 to 0x3f */
- bus-range = <0x0 0x3f>;
-
- /* Legacy interrupts (note the weird polarity, the bridge seems
- * to invert PCIe legacy interrupts).
- * We are de-swizzling here because the numbers are actually for
- * port of the root complex virtual P2P bridge. But I want
- * to avoid putting a node for it in the tree, so the numbers
- * below are basically de-swizzled numbers.
- * The real slot is on idsel 0, so the swizzling is 1:1
- */
- interrupt-map-mask = <0x0 0x0 0x0 0x7>;
- interrupt-map = <
- 0x0 0x0 0x0 0x1 &UIC2 0x0 0x4 /* swizzled int A */
- 0x0 0x0 0x0 0x2 &UIC2 0x1 0x4 /* swizzled int B */
- 0x0 0x0 0x0 0x3 &UIC2 0x2 0x4 /* swizzled int C */
- 0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
- };
-
- PCIE1: pcie@c0000000 {
- device_type = "pci";
- #interrupt-cells = <1>;
- #size-cells = <2>;
- #address-cells = <3>;
- compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
- primary;
- port = <0x1>; /* port number */
- reg = <0xc0000000 0x20000000 /* Config space access */
- 0xef001000 0x00001000>; /* Registers */
- dcr-reg = <0x060 0x020>;
- sdr-base = <0x440>;
-
- /* Outbound ranges, one memory and one IO,
- * later cannot be changed
- */
- ranges = <0x02000000 0x00000000 0x80000000 0x98000000 0x00000000 0x08000000
- 0x01000000 0x00000000 0x00000000 0xe0010000 0x00000000 0x00010000>;
-
- /* Inbound 2GB range starting at 0 */
- dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
- /* This drives busses 0x40 to 0x7f */
- bus-range = <0x40 0x7f>;
-
- /* Legacy interrupts (note the weird polarity, the bridge seems
- * to invert PCIe legacy interrupts).
- * We are de-swizzling here because the numbers are actually for
- * port of the root complex virtual P2P bridge. But I want
- * to avoid putting a node for it in the tree, so the numbers
- * below are basically de-swizzled numbers.
- * The real slot is on idsel 0, so the swizzling is 1:1
- */
- interrupt-map-mask = <0x0 0x0 0x0 0x7>;
- interrupt-map = <
- 0x0 0x0 0x0 0x1 &UIC2 0xb 0x4 /* swizzled int A */
- 0x0 0x0 0x0 0x2 &UIC2 0xc 0x4 /* swizzled int B */
- 0x0 0x0 0x0 0x3 &UIC2 0xd 0x4 /* swizzled int C */
- 0x0 0x0 0x0 0x4 &UIC2 0xe 0x4 /* swizzled int D */>;
- };
- };
-};
diff --git a/arch/powerpc/boot/dts/klondike.dts b/arch/powerpc/boot/dts/klondike.dts
deleted file mode 100644
index 97432177892a..000000000000
--- a/arch/powerpc/boot/dts/klondike.dts
+++ /dev/null
@@ -1,212 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Device Tree for Klondike (APM8018X) board.
- *
- * Copyright (c) 2010, Applied Micro Circuits Corporation
- * Author: Tanmay Inamdar <tinamdar@apm.com>
- */
-
-/dts-v1/;
-
-/ {
- #address-cells = <1>;
- #size-cells = <1>;
- model = "apm,klondike";
- compatible = "apm,klondike";
- dcr-parent = <&{/cpus/cpu@0}>;
-
- aliases {
- ethernet0 = &EMAC0;
- ethernet1 = &EMAC1;
- };
-
- cpus {
- #address-cells = <1>;
- #size-cells = <0>;
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,apm8018x";
- reg = <0x00000000>;
- clock-frequency = <300000000>; /* Filled in by U-Boot */
- timebase-frequency = <300000000>; /* Filled in by U-Boot */
- i-cache-line-size = <32>;
- d-cache-line-size = <32>;
- i-cache-size = <16384>; /* 16 kB */
- d-cache-size = <16384>; /* 16 kB */
- dcr-controller;
- dcr-access-method = "native";
- };
- };
-
- memory {
- device_type = "memory";
- reg = <0x00000000 0x20000000>; /* Filled in by U-Boot */
- };
-
- UIC0: interrupt-controller {
- compatible = "ibm,uic";
- interrupt-controller;
- cell-index = <0>;
- dcr-reg = <0x0c0 0x010>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- };
-
- UIC1: interrupt-controller1 {
- compatible = "ibm,uic";
- interrupt-controller;
- cell-index = <1>;
- dcr-reg = <0x0d0 0x010>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- UIC2: interrupt-controller2 {
- compatible = "ibm,uic";
- interrupt-controller;
- cell-index = <2>;
- dcr-reg = <0x0e0 0x010>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x0a 0x4 0x0b 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- UIC3: interrupt-controller3 {
- compatible = "ibm,uic";
- interrupt-controller;
- cell-index = <3>;
- dcr-reg = <0x0f0 0x010>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x10 0x4 0x11 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- plb {
- compatible = "ibm,plb4";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- SDRAM0: memory-controller {
- compatible = "ibm,sdram-apm8018x";
- dcr-reg = <0x010 0x002>;
- };
-
- MAL0: mcmal {
- compatible = "ibm,mcmal2";
- dcr-reg = <0x180 0x062>;
- num-tx-chans = <2>;
- num-rx-chans = <16>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-parent = <&UIC1>;
- interrupts = </*TXEOB*/ 0x6 0x4
- /*RXEOB*/ 0x7 0x4
- /*SERR*/ 0x1 0x4
- /*TXDE*/ 0x2 0x4
- /*RXDE*/ 0x3 0x4>;
- };
-
- POB0: opb {
- compatible = "ibm,opb";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0x20000000 0x20000000 0x30000000
- 0x50000000 0x50000000 0x10000000
- 0x60000000 0x60000000 0x10000000
- 0xFE000000 0xFE000000 0x00010000>;
- dcr-reg = <0x100 0x020>;
- clock-frequency = <300000000>; /* Filled in by U-Boot */
-
- RGMII0: emac-rgmii@400a2000 {
- compatible = "ibm,rgmii";
- reg = <0x400a2000 0x00000010>;
- has-mdio;
- };
-
- TAH0: emac-tah@400a3000 {
- compatible = "ibm,tah";
- reg = <0x400a3000 0x100>;
- };
-
- TAH1: emac-tah@400a4000 {
- compatible = "ibm,tah";
- reg = <0x400a4000 0x100>;
- };
-
- EMAC0: ethernet@400a0000 {
- compatible = "ibm,emac4", "ibm-emac4sync";
- interrupt-parent = <&EMAC0>;
- interrupts = <0x0>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x13 0x4>;
- reg = <0x400a0000 0x00000100>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <0x0>;
- mal-rx-channel = <0x0>;
- cell-index = <0>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- phy-mode = "rgmii";
- phy-address = <0x2>;
- turbo = "no";
- phy-map = <0x00000000>;
- rgmii-device = <&RGMII0>;
- rgmii-channel = <0>;
- tah-device = <&TAH0>;
- tah-channel = <0>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- };
-
- EMAC1: ethernet@400a1000 {
- compatible = "ibm,emac4", "ibm-emac4sync";
- status = "disabled";
- interrupt-parent = <&EMAC1>;
- interrupts = <0x0>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x14 0x4>;
- reg = <0x400a1000 0x00000100>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <1>;
- mal-rx-channel = <8>;
- cell-index = <1>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- phy-mode = "rgmii";
- phy-address = <0x3>;
- turbo = "no";
- phy-map = <0x00000000>;
- rgmii-device = <&RGMII0>;
- rgmii-channel = <1>;
- tah-device = <&TAH1>;
- tah-channel = <0>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- mdio-device = <&EMAC0>;
- };
- };
- };
-
- chosen {
- stdout-path = "/plb/opb/serial@50001000";
- };
-};
diff --git a/arch/powerpc/boot/dts/makalu.dts b/arch/powerpc/boot/dts/makalu.dts
deleted file mode 100644
index c473cd911bca..000000000000
--- a/arch/powerpc/boot/dts/makalu.dts
+++ /dev/null
@@ -1,353 +0,0 @@
-/*
- * Device Tree Source for AMCC Makalu (405EX)
- *
- * Copyright 2007 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
- #address-cells = <1>;
- #size-cells = <1>;
- model = "amcc,makalu";
- compatible = "amcc,makalu";
- dcr-parent = <&{/cpus/cpu@0}>;
-
- aliases {
- ethernet0 = &EMAC0;
- ethernet1 = &EMAC1;
- serial0 = &UART0;
- serial1 = &UART1;
- };
-
- cpus {
- #address-cells = <1>;
- #size-cells = <0>;
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,405EX";
- reg = <0x00000000>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- timebase-frequency = <0>; /* Filled in by U-Boot */
- i-cache-line-size = <32>;
- d-cache-line-size = <32>;
- i-cache-size = <16384>; /* 16 kB */
- d-cache-size = <16384>; /* 16 kB */
- dcr-controller;
- dcr-access-method = "native";
- };
- };
-
- memory {
- device_type = "memory";
- reg = <0x00000000 0x00000000>; /* Filled in by U-Boot */
- };
-
- UIC0: interrupt-controller {
- compatible = "ibm,uic-405ex", "ibm,uic";
- interrupt-controller;
- cell-index = <0>;
- dcr-reg = <0x0c0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- };
-
- UIC1: interrupt-controller1 {
- compatible = "ibm,uic-405ex","ibm,uic";
- interrupt-controller;
- cell-index = <1>;
- dcr-reg = <0x0d0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- UIC2: interrupt-controller2 {
- compatible = "ibm,uic-405ex","ibm,uic";
- interrupt-controller;
- cell-index = <2>;
- dcr-reg = <0x0e0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1c 0x4 0x1d 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- plb {
- compatible = "ibm,plb-405ex", "ibm,plb4";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- SDRAM0: memory-controller {
- compatible = "ibm,sdram-405ex", "ibm,sdram-4xx-ddr2";
- dcr-reg = <0x010 0x002>;
- interrupt-parent = <&UIC2>;
- interrupts = <0x5 0x4 /* ECC DED Error */
- 0x6 0x4 /* ECC SEC Error */ >;
- };
-
- MAL0: mcmal {
- compatible = "ibm,mcmal-405ex", "ibm,mcmal2";
- dcr-reg = <0x180 0x062>;
- num-tx-chans = <2>;
- num-rx-chans = <2>;
- interrupt-parent = <&MAL0>;
- interrupts = <0x0 0x1 0x2 0x3 0x4>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*TXEOB*/ 0x0 &UIC0 0xa 0x4
- /*RXEOB*/ 0x1 &UIC0 0xb 0x4
- /*SERR*/ 0x2 &UIC1 0x0 0x4
- /*TXDE*/ 0x3 &UIC1 0x1 0x4
- /*RXDE*/ 0x4 &UIC1 0x2 0x4>;
- interrupt-map-mask = <0xffffffff>;
- };
-
- POB0: opb {
- compatible = "ibm,opb-405ex", "ibm,opb";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0x80000000 0x80000000 0x10000000
- 0xef600000 0xef600000 0x00a00000
- 0xf0000000 0xf0000000 0x10000000>;
- dcr-reg = <0x0a0 0x005>;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- EBC0: ebc {
- compatible = "ibm,ebc-405ex", "ibm,ebc";
- dcr-reg = <0x012 0x002>;
- #address-cells = <2>;
- #size-cells = <1>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- /* ranges property is supplied by U-Boot */
- interrupts = <0x5 0x1>;
- interrupt-parent = <&UIC1>;
-
- nor_flash@0,0 {
- compatible = "amd,s29gl512n", "cfi-flash";
- bank-width = <2>;
- reg = <0x00000000 0x00000000 0x04000000>;
- #address-cells = <1>;
- #size-cells = <1>;
- partition@0 {
- label = "kernel";
- reg = <0x00000000 0x00200000>;
- };
- partition@200000 {
- label = "root";
- reg = <0x00200000 0x00200000>;
- };
- partition@400000 {
- label = "user";
- reg = <0x00400000 0x03b60000>;
- };
- partition@3f60000 {
- label = "env";
- reg = <0x03f60000 0x00040000>;
- };
- partition@3fa0000 {
- label = "u-boot";
- reg = <0x03fa0000 0x00060000>;
- };
- };
- };
-
- UART0: serial@ef600200 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600200 0x00000008>;
- virtual-reg = <0xef600200>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- current-speed = <0>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1a 0x4>;
- };
-
- UART1: serial@ef600300 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600300 0x00000008>;
- virtual-reg = <0xef600300>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- current-speed = <0>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1 0x4>;
- };
-
- IIC0: i2c@ef600400 {
- compatible = "ibm,iic-405ex", "ibm,iic";
- reg = <0xef600400 0x00000014>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x2 0x4>;
- };
-
- IIC1: i2c@ef600500 {
- compatible = "ibm,iic-405ex", "ibm,iic";
- reg = <0xef600500 0x00000014>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x7 0x4>;
- };
-
-
- RGMII0: emac-rgmii@ef600b00 {
- compatible = "ibm,rgmii-405ex", "ibm,rgmii";
- reg = <0xef600b00 0x00000104>;
- has-mdio;
- };
-
- EMAC0: ethernet@ef600900 {
- linux,network-index = <0x0>;
- device_type = "network";
- compatible = "ibm,emac-405ex", "ibm,emac4sync";
- interrupt-parent = <&EMAC0>;
- interrupts = <0x0 0x1>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x18 0x4
- /*Wake*/ 0x1 &UIC1 0x1d 0x4>;
- reg = <0xef600900 0x000000c4>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <0>;
- mal-rx-channel = <0>;
- cell-index = <0>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- rx-fifo-size-gige = <16384>;
- tx-fifo-size-gige = <16384>;
- phy-mode = "rgmii";
- phy-map = <0x0000003f>; /* Start at 6 */
- rgmii-device = <&RGMII0>;
- rgmii-channel = <0>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- };
-
- EMAC1: ethernet@ef600a00 {
- linux,network-index = <0x1>;
- device_type = "network";
- compatible = "ibm,emac-405ex", "ibm,emac4sync";
- interrupt-parent = <&EMAC1>;
- interrupts = <0x0 0x1>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x19 0x4
- /*Wake*/ 0x1 &UIC1 0x1f 0x4>;
- reg = <0xef600a00 0x000000c4>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <1>;
- mal-rx-channel = <1>;
- cell-index = <1>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- rx-fifo-size-gige = <16384>;
- tx-fifo-size-gige = <16384>;
- phy-mode = "rgmii";
- phy-map = <0x00000000>;
- rgmii-device = <&RGMII0>;
- rgmii-channel = <1>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- };
- };
-
- PCIE0: pcie@a0000000 {
- device_type = "pci";
- #interrupt-cells = <1>;
- #size-cells = <2>;
- #address-cells = <3>;
- compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
- primary;
- port = <0x0>; /* port number */
- reg = <0xa0000000 0x20000000 /* Config space access */
- 0xef000000 0x00001000>; /* Registers */
- dcr-reg = <0x040 0x020>;
- sdr-base = <0x400>;
-
- /* Outbound ranges, one memory and one IO,
- * later cannot be changed
- */
- ranges = <0x02000000 0x00000000 0x80000000 0x90000000 0x00000000 0x08000000
- 0x01000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00010000>;
-
- /* Inbound 2GB range starting at 0 */
- dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
- /* This drives busses 0x00 to 0x3f */
- bus-range = <0x0 0x3f>;
-
- /* Legacy interrupts (note the weird polarity, the bridge seems
- * to invert PCIe legacy interrupts).
- * We are de-swizzling here because the numbers are actually for
- * port of the root complex virtual P2P bridge. But I want
- * to avoid putting a node for it in the tree, so the numbers
- * below are basically de-swizzled numbers.
- * The real slot is on idsel 0, so the swizzling is 1:1
- */
- interrupt-map-mask = <0x0 0x0 0x0 0x7>;
- interrupt-map = <
- 0x0 0x0 0x0 0x1 &UIC2 0x0 0x4 /* swizzled int A */
- 0x0 0x0 0x0 0x2 &UIC2 0x1 0x4 /* swizzled int B */
- 0x0 0x0 0x0 0x3 &UIC2 0x2 0x4 /* swizzled int C */
- 0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
- };
-
- PCIE1: pcie@c0000000 {
- device_type = "pci";
- #interrupt-cells = <1>;
- #size-cells = <2>;
- #address-cells = <3>;
- compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
- primary;
- port = <0x1>; /* port number */
- reg = <0xc0000000 0x20000000 /* Config space access */
- 0xef001000 0x00001000>; /* Registers */
- dcr-reg = <0x060 0x020>;
- sdr-base = <0x440>;
-
- /* Outbound ranges, one memory and one IO,
- * later cannot be changed
- */
- ranges = <0x02000000 0x00000000 0x80000000 0x98000000 0x00000000 0x08000000
- 0x01000000 0x00000000 0x00000000 0xe0010000 0x00000000 0x00010000>;
-
- /* Inbound 2GB range starting at 0 */
- dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
- /* This drives busses 0x40 to 0x7f */
- bus-range = <0x40 0x7f>;
-
- /* Legacy interrupts (note the weird polarity, the bridge seems
- * to invert PCIe legacy interrupts).
- * We are de-swizzling here because the numbers are actually for
- * port of the root complex virtual P2P bridge. But I want
- * to avoid putting a node for it in the tree, so the numbers
- * below are basically de-swizzled numbers.
- * The real slot is on idsel 0, so the swizzling is 1:1
- */
- interrupt-map-mask = <0x0 0x0 0x0 0x7>;
- interrupt-map = <
- 0x0 0x0 0x0 0x1 &UIC2 0xb 0x4 /* swizzled int A */
- 0x0 0x0 0x0 0x2 &UIC2 0xc 0x4 /* swizzled int B */
- 0x0 0x0 0x0 0x3 &UIC2 0xd 0x4 /* swizzled int C */
- 0x0 0x0 0x0 0x4 &UIC2 0xe 0x4 /* swizzled int D */>;
- };
- };
-};
diff --git a/arch/powerpc/boot/dts/obs600.dts b/arch/powerpc/boot/dts/obs600.dts
deleted file mode 100644
index d10b0411809b..000000000000
--- a/arch/powerpc/boot/dts/obs600.dts
+++ /dev/null
@@ -1,314 +0,0 @@
-/*
- * Device Tree Source for PlatHome OpenBlockS 600 (405EX)
- *
- * Copyright 2011 Ben Herrenschmidt, IBM Corp.
- *
- * Based on Kilauea by:
- *
- * Copyright 2007-2009 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
- #address-cells = <1>;
- #size-cells = <1>;
- model = "PlatHome,OpenBlockS 600";
- compatible = "plathome,obs600";
- dcr-parent = <&{/cpus/cpu@0}>;
-
- aliases {
- ethernet0 = &EMAC0;
- ethernet1 = &EMAC1;
- serial0 = &UART0;
- serial1 = &UART1;
- };
-
- cpus {
- #address-cells = <1>;
- #size-cells = <0>;
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,405EX";
- reg = <0x00000000>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- timebase-frequency = <0>; /* Filled in by U-Boot */
- i-cache-line-size = <32>;
- d-cache-line-size = <32>;
- i-cache-size = <16384>; /* 16 kB */
- d-cache-size = <16384>; /* 16 kB */
- dcr-controller;
- dcr-access-method = "native";
- };
- };
-
- memory {
- device_type = "memory";
- reg = <0x00000000 0x00000000>; /* Filled in by U-Boot */
- };
-
- UIC0: interrupt-controller {
- compatible = "ibm,uic-405ex", "ibm,uic";
- interrupt-controller;
- cell-index = <0>;
- dcr-reg = <0x0c0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- };
-
- UIC1: interrupt-controller1 {
- compatible = "ibm,uic-405ex","ibm,uic";
- interrupt-controller;
- cell-index = <1>;
- dcr-reg = <0x0d0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- UIC2: interrupt-controller2 {
- compatible = "ibm,uic-405ex","ibm,uic";
- interrupt-controller;
- cell-index = <2>;
- dcr-reg = <0x0e0 0x009>;
- #address-cells = <0>;
- #size-cells = <0>;
- #interrupt-cells = <2>;
- interrupts = <0x1c 0x4 0x1d 0x4>; /* cascade */
- interrupt-parent = <&UIC0>;
- };
-
- CPM0: cpm {
- compatible = "ibm,cpm";
- dcr-access-method = "native";
- dcr-reg = <0x0b0 0x003>;
- unused-units = <0x00000000>;
- idle-doze = <0x02000000>;
- standby = <0xe3e74800>;
- };
-
- plb {
- compatible = "ibm,plb-405ex", "ibm,plb4";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- SDRAM0: memory-controller {
- compatible = "ibm,sdram-405ex", "ibm,sdram-4xx-ddr2";
- dcr-reg = <0x010 0x002>;
- interrupt-parent = <&UIC2>;
- interrupts = <0x5 0x4 /* ECC DED Error */
- 0x6 0x4>; /* ECC SEC Error */
- };
-
- CRYPTO: crypto@ef700000 {
- compatible = "amcc,ppc405ex-crypto", "amcc,ppc4xx-crypto";
- reg = <0xef700000 0x80400>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x17 0x2>;
- };
-
- MAL0: mcmal {
- compatible = "ibm,mcmal-405ex", "ibm,mcmal2";
- dcr-reg = <0x180 0x062>;
- num-tx-chans = <2>;
- num-rx-chans = <2>;
- interrupt-parent = <&MAL0>;
- interrupts = <0x0 0x1 0x2 0x3 0x4>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*TXEOB*/ 0x0 &UIC0 0xa 0x4
- /*RXEOB*/ 0x1 &UIC0 0xb 0x4
- /*SERR*/ 0x2 &UIC1 0x0 0x4
- /*TXDE*/ 0x3 &UIC1 0x1 0x4
- /*RXDE*/ 0x4 &UIC1 0x2 0x4>;
- interrupt-map-mask = <0xffffffff>;
- };
-
- POB0: opb {
- compatible = "ibm,opb-405ex", "ibm,opb";
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0x80000000 0x80000000 0x10000000
- 0xef600000 0xef600000 0x00a00000
- 0xf0000000 0xf0000000 0x10000000>;
- dcr-reg = <0x0a0 0x005>;
- clock-frequency = <0>; /* Filled in by U-Boot */
-
- EBC0: ebc {
- compatible = "ibm,ebc-405ex", "ibm,ebc";
- dcr-reg = <0x012 0x002>;
- #address-cells = <2>;
- #size-cells = <1>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- /* ranges property is supplied by U-Boot */
- interrupts = <0x5 0x1>;
- interrupt-parent = <&UIC1>;
-
- nor_flash@0,0 {
- compatible = "amd,s29gl512n", "cfi-flash";
- bank-width = <2>;
- reg = <0x00000000 0x00000000 0x08000000>;
- #address-cells = <1>;
- #size-cells = <1>;
- partition@0 {
- label = "kernel + initrd";
- reg = <0x00000000 0x03de0000>;
- };
- partition@3de0000 {
- label = "user config area";
- reg = <0x03de0000 0x00080000>;
- };
- partition@3e60000 {
- label = "user program area";
- reg = <0x03e60000 0x04000000>;
- };
- partition@7e60000 {
- label = "flat device tree";
- reg = <0x07e60000 0x00080000>;
- };
- partition@7ee0000 {
- label = "test program";
- reg = <0x07ee0000 0x00080000>;
- };
- partition@7f60000 {
- label = "u-boot env";
- reg = <0x07f60000 0x00040000>;
- };
- partition@7fa0000 {
- label = "u-boot";
- reg = <0x07fa0000 0x00060000>;
- };
- };
- };
-
- UART0: serial@ef600200 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600200 0x00000008>;
- virtual-reg = <0xef600200>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- current-speed = <0>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1a 0x4>;
- };
-
- UART1: serial@ef600300 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600300 0x00000008>;
- virtual-reg = <0xef600300>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- current-speed = <0>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x1 0x4>;
- };
-
- IIC0: i2c@ef600400 {
- compatible = "ibm,iic-405ex", "ibm,iic";
- reg = <0xef600400 0x00000014>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x2 0x4>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- rtc@68 {
- compatible = "dallas,ds1340";
- reg = <0x68>;
- };
- };
-
- IIC1: i2c@ef600500 {
- compatible = "ibm,iic-405ex", "ibm,iic";
- reg = <0xef600500 0x00000014>;
- interrupt-parent = <&UIC0>;
- interrupts = <0x7 0x4>;
- };
-
- RGMII0: emac-rgmii@ef600b00 {
- compatible = "ibm,rgmii-405ex", "ibm,rgmii";
- reg = <0xef600b00 0x00000104>;
- has-mdio;
- };
-
- EMAC0: ethernet@ef600900 {
- linux,network-index = <0x0>;
- device_type = "network";
- compatible = "ibm,emac-405ex", "ibm,emac4sync";
- interrupt-parent = <&EMAC0>;
- interrupts = <0x0 0x1>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x18 0x4
- /*Wake*/ 0x1 &UIC1 0x1d 0x4>;
- reg = <0xef600900 0x000000c4>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <0>;
- mal-rx-channel = <0>;
- cell-index = <0>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- rx-fifo-size-gige = <16384>;
- tx-fifo-size-gige = <16384>;
- phy-mode = "rgmii";
- phy-map = <0x00000000>;
- rgmii-device = <&RGMII0>;
- rgmii-channel = <0>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- };
-
- EMAC1: ethernet@ef600a00 {
- linux,network-index = <0x1>;
- device_type = "network";
- compatible = "ibm,emac-405ex", "ibm,emac4sync";
- interrupt-parent = <&EMAC1>;
- interrupts = <0x0 0x1>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = </*Status*/ 0x0 &UIC0 0x19 0x4
- /*Wake*/ 0x1 &UIC1 0x1f 0x4>;
- reg = <0xef600a00 0x000000c4>;
- local-mac-address = [000000000000]; /* Filled in by U-Boot */
- mal-device = <&MAL0>;
- mal-tx-channel = <1>;
- mal-rx-channel = <1>;
- cell-index = <1>;
- max-frame-size = <9000>;
- rx-fifo-size = <4096>;
- tx-fifo-size = <2048>;
- rx-fifo-size-gige = <16384>;
- tx-fifo-size-gige = <16384>;
- phy-mode = "rgmii";
- phy-map = <0x00000000>;
- rgmii-device = <&RGMII0>;
- rgmii-channel = <1>;
- has-inverted-stacr-oc;
- has-new-stacr-staopc;
- };
-
- GPIO: gpio@ef600800 {
- device_type = "gpio";
- compatible = "ibm,gpio-405ex", "ibm,ppc4xx-gpio";
- reg = <0xef600800 0x50>;
- };
- };
- };
- chosen {
- stdout-path = "/plb/opb/serial@ef600200";
- };
-};
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index cae31a6e8f02..2c0e2a1cab01 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -188,7 +188,7 @@ static inline void prep_esm_blob(struct addr_range vmlinux, void *chosen) { }
/* A buffer that may be edited by tools operating on a zImage binary so as to
* edit the command line passed to vmlinux (by setting /chosen/bootargs).
- * The buffer is put in it's own section so that tools may locate it easier.
+ * The buffer is put in its own section so that tools may locate it easier.
*/
static char cmdline[BOOT_COMMAND_LINE_SIZE]
__attribute__((__section__("__builtin_cmdline")));
diff --git a/arch/powerpc/boot/ppcboot-hotfoot.h b/arch/powerpc/boot/ppcboot-hotfoot.h
deleted file mode 100644
index 4728db95f58a..000000000000
--- a/arch/powerpc/boot/ppcboot-hotfoot.h
+++ /dev/null
@@ -1,119 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * This interface is used for compatibility with old U-boots *ONLY*.
- * Please do not imitate or extend this.
- */
-
-/*
- * Unfortunately, the ESTeem Hotfoot board uses a mangled version of
- * ppcboot.h for historical reasons, and in the interest of having a
- * mainline kernel boot on the production board+bootloader, this was the
- * least-offensive solution. Please direct all flames to:
- *
- * Solomon Peachy <solomon@linux-wlan.com>
- *
- * (This header is identical to ppcboot.h except for the
- * TARGET_HOTFOOT bits)
- */
-
-/*
- * (C) Copyright 2000, 2001
- * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
- */
-
-#ifndef __PPCBOOT_H__
-#define __PPCBOOT_H__
-
-/*
- * Board information passed to kernel from PPCBoot
- *
- * include/asm-ppc/ppcboot.h
- */
-
-#include "types.h"
-
-typedef struct bd_info {
- unsigned long bi_memstart; /* start of DRAM memory */
- unsigned long bi_memsize; /* size of DRAM memory in bytes */
- unsigned long bi_flashstart; /* start of FLASH memory */
- unsigned long bi_flashsize; /* size of FLASH memory */
- unsigned long bi_flashoffset; /* reserved area for startup monitor */
- unsigned long bi_sramstart; /* start of SRAM memory */
- unsigned long bi_sramsize; /* size of SRAM memory */
-#if defined(TARGET_8xx) || defined(TARGET_CPM2) || defined(TARGET_85xx) ||\
- defined(TARGET_83xx)
- unsigned long bi_immr_base; /* base of IMMR register */
-#endif
-#if defined(TARGET_PPC_MPC52xx)
- unsigned long bi_mbar_base; /* base of internal registers */
-#endif
- unsigned long bi_bootflags; /* boot / reboot flag (for LynxOS) */
- unsigned long bi_ip_addr; /* IP Address */
- unsigned char bi_enetaddr[6]; /* Ethernet address */
-#if defined(TARGET_HOTFOOT)
- /* second onboard ethernet port */
- unsigned char bi_enet1addr[6];
-#define HAVE_ENET1ADDR
-#endif /* TARGET_HOOTFOOT */
- unsigned short bi_ethspeed; /* Ethernet speed in Mbps */
- unsigned long bi_intfreq; /* Internal Freq, in MHz */
- unsigned long bi_busfreq; /* Bus Freq, in MHz */
-#if defined(TARGET_CPM2)
- unsigned long bi_cpmfreq; /* CPM_CLK Freq, in MHz */
- unsigned long bi_brgfreq; /* BRG_CLK Freq, in MHz */
- unsigned long bi_sccfreq; /* SCC_CLK Freq, in MHz */
- unsigned long bi_vco; /* VCO Out from PLL, in MHz */
-#endif
-#if defined(TARGET_PPC_MPC52xx)
- unsigned long bi_ipbfreq; /* IPB Bus Freq, in MHz */
- unsigned long bi_pcifreq; /* PCI Bus Freq, in MHz */
-#endif
- unsigned long bi_baudrate; /* Console Baudrate */
-#if defined(TARGET_4xx)
- unsigned char bi_s_version[4]; /* Version of this structure */
- unsigned char bi_r_version[32]; /* Version of the ROM (IBM) */
- unsigned int bi_procfreq; /* CPU (Internal) Freq, in Hz */
- unsigned int bi_plb_busfreq; /* PLB Bus speed, in Hz */
- unsigned int bi_pci_busfreq; /* PCI Bus speed, in Hz */
- unsigned char bi_pci_enetaddr[6]; /* PCI Ethernet MAC address */
-#endif
-#if defined(TARGET_HOTFOOT)
- unsigned int bi_pllouta_freq; /* PLL OUTA speed, in Hz */
-#endif
-#if defined(TARGET_HYMOD)
- hymod_conf_t bi_hymod_conf; /* hymod configuration information */
-#endif
-#if defined(TARGET_EVB64260) || defined(TARGET_405EP) || defined(TARGET_44x) || \
- defined(TARGET_85xx) || defined(TARGET_83xx) || defined(TARGET_HAS_ETH1)
- /* second onboard ethernet port */
- unsigned char bi_enet1addr[6];
-#define HAVE_ENET1ADDR
-#endif
-#if defined(TARGET_EVB64260) || defined(TARGET_440GX) || \
- defined(TARGET_85xx) || defined(TARGET_HAS_ETH2)
- /* third onboard ethernet ports */
- unsigned char bi_enet2addr[6];
-#define HAVE_ENET2ADDR
-#endif
-#if defined(TARGET_440GX) || defined(TARGET_HAS_ETH3)
- /* fourth onboard ethernet ports */
- unsigned char bi_enet3addr[6];
-#define HAVE_ENET3ADDR
-#endif
-#if defined(TARGET_HOTFOOT)
- int bi_phynum[2]; /* Determines phy mapping */
- int bi_phymode[2]; /* Determines phy mode */
-#endif
-#if defined(TARGET_4xx)
- unsigned int bi_opbfreq; /* OB clock in Hz */
- int bi_iic_fast[2]; /* Use fast i2c mode */
-#endif
-#if defined(TARGET_440GX)
- int bi_phynum[4]; /* phy mapping */
- int bi_phymode[4]; /* phy mode */
-#endif
-} bd_t;
-
-#define bi_tbfreq bi_intfreq
-
-#endif /* __PPCBOOT_H__ */
diff --git a/arch/powerpc/boot/ppcboot.h b/arch/powerpc/boot/ppcboot.h
index a78b0b257698..90c8f452fe6e 100644
--- a/arch/powerpc/boot/ppcboot.h
+++ b/arch/powerpc/boot/ppcboot.h
@@ -63,7 +63,7 @@ typedef struct bd_info {
#if defined(TARGET_HYMOD)
hymod_conf_t bi_hymod_conf; /* hymod configuration information */
#endif
-#if defined(TARGET_EVB64260) || defined(TARGET_405EP) || defined(TARGET_44x) || \
+#if defined(TARGET_EVB64260) || defined(TARGET_44x) || \
defined(TARGET_85xx) || defined(TARGET_83xx) || defined(TARGET_HAS_ETH1)
/* second onboard ethernet port */
unsigned char bi_enet1addr[6];
diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c
index f157717ae814..89ff46b8b225 100644
--- a/arch/powerpc/boot/ps3.c
+++ b/arch/powerpc/boot/ps3.c
@@ -25,7 +25,7 @@ BSS_STACK(4096);
/* A buffer that may be edited by tools operating on a zImage binary so as to
* edit the command line passed to vmlinux (by setting /chosen/bootargs).
- * The buffer is put in it's own section so that tools may locate it easier.
+ * The buffer is put in its own section so that tools may locate it easier.
*/
static char cmdline[BOOT_COMMAND_LINE_SIZE]
diff --git a/arch/powerpc/boot/simple_alloc.c b/arch/powerpc/boot/simple_alloc.c
index 267d6524caac..d07796fdf91a 100644
--- a/arch/powerpc/boot/simple_alloc.c
+++ b/arch/powerpc/boot/simple_alloc.c
@@ -112,8 +112,11 @@ static void *simple_realloc(void *ptr, unsigned long size)
return ptr;
new = simple_malloc(size);
- memcpy(new, ptr, p->size);
- simple_free(ptr);
+ if (new) {
+ memcpy(new, ptr, p->size);
+ simple_free(ptr);
+ }
+
return new;
}
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 352d7de24018..1db60fe13802 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -271,11 +271,6 @@ pseries)
fi
make_space=n
;;
-maple)
- platformo="$object/of.o $object/epapr.o"
- link_address='0x400000'
- make_space=n
- ;;
pmac|chrp)
platformo="$object/of.o $object/epapr.o"
make_space=n
@@ -337,7 +332,7 @@ ps3)
make_space=n
pie=
;;
-ep88xc|ep405|ep8248e)
+ep88xc|ep8248e)
platformo="$object/fixed-head.o $object/$platform.o"
binary=y
;;
@@ -468,26 +463,6 @@ uboot)
fi
exit 0
;;
-uboot-obs600)
- rm -f "$ofile"
- # obs600 wants a multi image with an initrd, so we need to put a fake
- # one in even when building a "normal" image.
- if [ -n "$initrd" ]; then
- real_rd="$initrd"
- else
- real_rd=`mktemp`
- echo "\0" >>"$real_rd"
- fi
- ${MKIMAGE} -A ppc -O linux -T multi -C gzip -a $membase -e $membase \
- $uboot_version -d "$vmz":"$real_rd":"$dtb" "$ofile"
- if [ -z "$initrd" ]; then
- rm -f "$real_rd"
- fi
- if [ -z "$cacheit" ]; then
- rm -f "$vmz"
- fi
- exit 0
- ;;
esac
addsec() {
@@ -537,7 +512,7 @@ fi
# post-processing needed for some platforms
case "$platform" in
-pseries|chrp|maple)
+pseries|chrp)
$objbin/addnote "$ofile"
;;
coff)
diff --git a/arch/powerpc/boot/xz_config.h b/arch/powerpc/boot/xz_config.h
index ebfadd39e192..9506a96ebbcc 100644
--- a/arch/powerpc/boot/xz_config.h
+++ b/arch/powerpc/boot/xz_config.h
@@ -50,11 +50,8 @@ static inline void put_unaligned_be32(u32 val, void *p)
/* prevent the inclusion of the xz-preboot MM headers */
#define DECOMPR_MM_H
#define memmove memmove
-#define XZ_EXTERN static
/* xz.h needs to be included directly since we need enum xz_mode */
#include "../../../include/linux/xz.h"
-#undef XZ_EXTERN
-
#endif
diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig
deleted file mode 100644
index 25eed86ec528..000000000000
--- a/arch/powerpc/configs/40x/acadia_defconfig
+++ /dev/null
@@ -1,61 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_ACADIA=y
-CONFIG_PCI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-CONFIG_IBM_EMAC_RXB=256
-CONFIG_IBM_EMAC_TXB=256
-CONFIG_IBM_EMAC_DEBUG=y
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig
deleted file mode 100644
index 3549c9e950e8..000000000000
--- a/arch/powerpc/configs/40x/kilauea_defconfig
+++ /dev/null
@@ -1,69 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_KILAUEA=y
-CONFIG_PCI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_RAW_NAND=y
-CONFIG_MTD_NAND_NDFC=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-CONFIG_IBM_EMAC_RXB=256
-CONFIG_IBM_EMAC_TXB=256
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_IBM_IIC=y
-CONFIG_SENSORS_LM75=y
-CONFIG_THERMAL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1307=y
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/40x/klondike_defconfig b/arch/powerpc/configs/40x/klondike_defconfig
deleted file mode 100644
index a974d1e945cc..000000000000
--- a/arch/powerpc/configs/40x/klondike_defconfig
+++ /dev/null
@@ -1,43 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_APM8018X=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_MATH_EMULATION=y
-# CONFIG_SUSPEND is not set
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_SAS_ATTRS=y
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_UNIX98_PTYS is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-# CONFIG_USB_SUPPORT is not set
-# CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-CONFIG_MAGIC_SYSRQ=y
-# CONFIG_SCHED_DEBUG is not set
-# CONFIG_DEBUG_BUGVERBOSE is not set
-# CONFIG_FTRACE is not set
diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig
deleted file mode 100644
index 4563f88acf0c..000000000000
--- a/arch/powerpc/configs/40x/makalu_defconfig
+++ /dev/null
@@ -1,59 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_MAKALU=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-CONFIG_IBM_EMAC_RXB=256
-CONFIG_IBM_EMAC_TXB=256
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/40x/obs600_defconfig b/arch/powerpc/configs/40x/obs600_defconfig
deleted file mode 100644
index 2a2bb3f46847..000000000000
--- a/arch/powerpc/configs/40x/obs600_defconfig
+++ /dev/null
@@ -1,69 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_OBS600=y
-CONFIG_MATH_EMULATION=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_RAW_NAND=y
-CONFIG_MTD_NAND_NDFC=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-CONFIG_IBM_EMAC_RXB=256
-CONFIG_IBM_EMAC_TXB=256
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_IBM_IIC=y
-CONFIG_SENSORS_LM75=y
-CONFIG_THERMAL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1307=y
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig
deleted file mode 100644
index 9eaaf1a1d2c6..000000000000
--- a/arch/powerpc/configs/40x/walnut_defconfig
+++ /dev/null
@@ -1,55 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/44x.config b/arch/powerpc/configs/44x.config
new file mode 100644
index 000000000000..79b7b1962995
--- /dev/null
+++ b/arch/powerpc/configs/44x.config
@@ -0,0 +1,2 @@
+CONFIG_PPC64=n
+CONFIG_44x=y
diff --git a/arch/powerpc/configs/85xx-32bit.config b/arch/powerpc/configs/85xx-32bit.config
index 6b8894d727a2..a85310bcb1fd 100644
--- a/arch/powerpc/configs/85xx-32bit.config
+++ b/arch/powerpc/configs/85xx-32bit.config
@@ -1,3 +1,4 @@
+CONFIG_PPC64=n
CONFIG_HIGHMEM=y
CONFIG_KEXEC=y
CONFIG_PPC_85xx=y
diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
index 524db76f47b7..8aff83217397 100644
--- a/arch/powerpc/configs/85xx-hw.config
+++ b/arch/powerpc/configs/85xx-hw.config
@@ -24,6 +24,7 @@ CONFIG_FS_ENET=y
CONFIG_FSL_CORENET_CF=y
CONFIG_FSL_DMA=y
CONFIG_FSL_HV_MANAGER=y
+CONFIG_FSL_IFC=y
CONFIG_FSL_PQ_MDIO=y
CONFIG_FSL_RIO=y
CONFIG_FSL_XGMAC_MDIO=y
@@ -58,6 +59,7 @@ CONFIG_INPUT_FF_MEMLESS=m
CONFIG_MARVELL_PHY=y
CONFIG_MDIO_BUS_MUX_GPIO=y
CONFIG_MDIO_BUS_MUX_MMIOREG=y
+CONFIG_MEMORY=y
CONFIG_MMC_SDHCI_OF_ESDHC=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_MMC_SDHCI=y
diff --git a/arch/powerpc/configs/8xx.config b/arch/powerpc/configs/8xx.config
new file mode 100644
index 000000000000..7eb3ffbbd667
--- /dev/null
+++ b/arch/powerpc/configs/8xx.config
@@ -0,0 +1,2 @@
+CONFIG_PPC64=n
+CONFIG_PPC_8xx=y
diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig
index 7f35d5bc1229..97f4d4851735 100644
--- a/arch/powerpc/configs/adder875_defconfig
+++ b/arch/powerpc/configs/adder875_defconfig
@@ -4,7 +4,7 @@ CONFIG_SYSVIPC=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_EXPERT=y
# CONFIG_ELF_CORE is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
# CONFIG_FUTEX is not set
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 53f43a34e1a9..b33f0034990c 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -168,7 +168,6 @@ CONFIG_INFINIBAND_MTHCA=m
CONFIG_INFINIBAND_IPOIB=m
CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
CONFIG_EDAC=y
-CONFIG_EDAC_CELL=y
CONFIG_UIO=m
CONFIG_EXT2_FS=y
CONFIG_EXT4_FS=y
diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig
index a98ef6a4abef..50cc59eb36cf 100644
--- a/arch/powerpc/configs/ep88xc_defconfig
+++ b/arch/powerpc/configs/ep88xc_defconfig
@@ -6,7 +6,7 @@ CONFIG_HIGH_RES_TIMERS=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_EXPERT=y
# CONFIG_ELF_CORE is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
# CONFIG_FUTEX is not set
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig
deleted file mode 100644
index c821a97f4a89..000000000000
--- a/arch/powerpc/configs/maple_defconfig
+++ /dev/null
@@ -1,111 +0,0 @@
-CONFIG_PPC64=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=4
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_KPROBES=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-# CONFIG_PPC_POWERNV is not set
-# CONFIG_PPC_PSERIES is not set
-# CONFIG_PPC_PMAC is not set
-CONFIG_PPC_MAPLE=y
-CONFIG_UDBG_RTAS_CONSOLE=y
-CONFIG_GEN_RTC=y
-CONFIG_KEXEC=y
-CONFIG_IRQ_ALL_CPUS=y
-CONFIG_PPC_4K_PAGES=y
-CONFIG_PCI_MSI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_IPV6 is not set
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=8192
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_IPR=y
-CONFIG_ATA=y
-CONFIG_PATA_AMD=y
-CONFIG_ATA_GENERIC=y
-CONFIG_NETDEVICES=y
-CONFIG_AMD8111_ETH=y
-CONFIG_TIGON3=y
-CONFIG_E1000=y
-CONFIG_USB_PEGASUS=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_HVC_RTAS=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_AMD8111=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_HID_GYRATION=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_ROOT_HUB_TT=y
-# CONFIG_USB_EHCI_HCD_PPC_OF is not set
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_UHCI_HCD=y
-CONFIG_USB_SERIAL=y
-CONFIG_USB_SERIAL_GENERIC=y
-CONFIG_USB_SERIAL_CYPRESS_M8=m
-CONFIG_USB_SERIAL_GARMIN=m
-CONFIG_USB_SERIAL_IPW=m
-CONFIG_USB_SERIAL_KEYSPAN=y
-CONFIG_USB_SERIAL_TI=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=y
-CONFIG_FS_DAX=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_HUGETLBFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_DEFAULT="utf-8"
-CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_XMON=y
-CONFIG_XMON_DEFAULT=y
-CONFIG_BOOTX_TEXT=y
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_PCBC=m
-# CONFIG_CRYPTO_HW is not set
-CONFIG_PRINTK_TIME=y
diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig
index 5c56d36cdfc5..6f449411abf7 100644
--- a/arch/powerpc/configs/mpc866_ads_defconfig
+++ b/arch/powerpc/configs/mpc866_ads_defconfig
@@ -6,7 +6,7 @@ CONFIG_HIGH_RES_TIMERS=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_EXPERT=y
# CONFIG_BUG is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
# CONFIG_EPOLL is not set
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig
index 56b876e418e9..77306be62e9e 100644
--- a/arch/powerpc/configs/mpc885_ads_defconfig
+++ b/arch/powerpc/configs/mpc885_ads_defconfig
@@ -7,7 +7,7 @@ CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_EXPERT=y
# CONFIG_ELF_CORE is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
# CONFIG_FUTEX is not set
CONFIG_PERF_EVENTS=y
# CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index 57ded82c2840..e8b3f67bf3f5 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -208,6 +208,7 @@ CONFIG_FB_ATY=y
CONFIG_FB_ATY_CT=y
CONFIG_FB_ATY_GX=y
CONFIG_FB_3DFX=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
# CONFIG_VGA_CONSOLE is not set
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index ee84ade7a033..6b6d7467fecf 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -320,8 +320,6 @@ CONFIG_XMON=y
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_CRC32C_VPMSUM=m
-CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m
CONFIG_CRYPTO_MD5_PPC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_SHA1_PPC=m
diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig
deleted file mode 100644
index 7e48693775f4..000000000000
--- a/arch/powerpc/configs/ppc40x_defconfig
+++ /dev/null
@@ -1,74 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PPC4xx_GPIO=y
-CONFIG_ACADIA=y
-CONFIG_HOTFOOT=y
-CONFIG_KILAUEA=y
-CONFIG_MAKALU=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_UBI=m
-CONFIG_MTD_UBI_GLUEBI=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-# CONFIG_INPUT is not set
-CONFIG_SERIO=m
-# CONFIG_SERIO_I8042 is not set
-# CONFIG_SERIO_SERPORT is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_I2C_IBM_IIC=m
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-CONFIG_FB=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=m
-CONFIG_UBIFS_FS=m
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 544a65fda77b..465eb96c755e 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -44,7 +44,6 @@ CONFIG_PPC_SMLPAR=y
CONFIG_IBMEBUS=y
CONFIG_PAPR_SCM=m
CONFIG_PPC_SVM=y
-CONFIG_PPC_MAPLE=y
CONFIG_PPC_PASEMI=y
CONFIG_PPC_PASEMI_IOMMU=y
CONFIG_PPC_PS3=y
@@ -81,7 +80,6 @@ CONFIG_MODULE_SIG_SHA512=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_BINFMT_MISC=m
CONFIG_ZSWAP=y
-CONFIG_Z3FOLD=y
CONFIG_ZSMALLOC=y
# CONFIG_SLAB_MERGE_DEFAULT is not set
CONFIG_SLAB_FREELIST_RANDOM=y
@@ -93,6 +91,7 @@ CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_MEM_SOFT_DIRTY=y
+CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_ZONE_DEVICE=y
CONFIG_NET=y
CONFIG_PACKET=y
@@ -390,9 +389,6 @@ CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_SHA256=y
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_LZO=m
-CONFIG_CRYPTO_CRC32C_VPMSUM=m
-CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m
-CONFIG_CRYPTO_VPMSUM_TESTER=m
CONFIG_CRYPTO_MD5_PPC=m
CONFIG_CRYPTO_SHA1_PPC=m
CONFIG_CRYPTO_AES_GCM_P10=m
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 66c7b28d7450..ca0c90e95837 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -12,7 +12,6 @@ CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y
CONFIG_CGROUPS=y
CONFIG_CGROUP_SCHED=y
-CONFIG_RT_GROUP_SCHED=y
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_USER_NS=y
@@ -436,7 +435,6 @@ CONFIG_DM9102=m
CONFIG_ULI526X=m
CONFIG_PCMCIA_XIRCOM=m
CONFIG_DL2K=m
-CONFIG_SUNDANCE=m
CONFIG_S2IO=m
CONFIG_FEC_MPC52xx=m
CONFIG_GIANFAR=m
@@ -718,6 +716,7 @@ CONFIG_FB_TRIDENT=m
CONFIG_FB_SM501=m
CONFIG_FB_IBM_GXT4500=y
CONFIG_LCD_PLATFORM=m
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
CONFIG_LOGO=y
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index aa8bb0208bcc..2b175ddf82f0 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -24,7 +24,6 @@ CONFIG_PS3_VRAM=m
CONFIG_PS3_LPM=m
# CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
CONFIG_KEXEC=y
-# CONFIG_PPC64_BIG_ENDIAN_ELF_ABI_V2 is not set
CONFIG_PPC_4K_PAGES=y
CONFIG_SCHED_SMT=y
CONFIG_PM=y
diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig
index 083c2e57520a..383c0966e92f 100644
--- a/arch/powerpc/configs/tqm8xx_defconfig
+++ b/arch/powerpc/configs/tqm8xx_defconfig
@@ -6,7 +6,7 @@ CONFIG_HIGH_RES_TIMERS=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_EXPERT=y
# CONFIG_ELF_CORE is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
# CONFIG_FUTEX is not set
# CONFIG_VM_EVENT_COUNTERS is not set
CONFIG_MODULES=y
diff --git a/arch/powerpc/crypto/.gitignore b/arch/powerpc/crypto/.gitignore
index e1094f08f713..e9fe73aac8b6 100644
--- a/arch/powerpc/crypto/.gitignore
+++ b/arch/powerpc/crypto/.gitignore
@@ -1,3 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
aesp10-ppc.S
+aesp8-ppc.S
ghashp10-ppc.S
+ghashp8-ppc.S
diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig
index 6fc2248ca561..5b315e9756b3 100644
--- a/arch/powerpc/crypto/Kconfig
+++ b/arch/powerpc/crypto/Kconfig
@@ -2,38 +2,16 @@
menu "Accelerated Cryptographic Algorithms for CPU (powerpc)"
-config CRYPTO_CRC32C_VPMSUM
- tristate "CRC32c"
- depends on PPC64 && ALTIVEC
- select CRYPTO_HASH
- select CRC32
+config CRYPTO_CURVE25519_PPC64
+ tristate "Public key crypto: Curve25519 (PowerPC64)"
+ depends on PPC64 && CPU_LITTLE_ENDIAN
+ select CRYPTO_LIB_CURVE25519_GENERIC
+ select CRYPTO_ARCH_HAVE_LIB_CURVE25519
help
- CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720)
-
- Architecture: powerpc64 using
- - AltiVec extensions
-
- Enable on POWER8 and newer processors for improved performance.
-
-config CRYPTO_CRCT10DIF_VPMSUM
- tristate "CRC32T10DIF"
- depends on PPC64 && ALTIVEC && CRC_T10DIF
- select CRYPTO_HASH
- help
- CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF)
-
- Architecture: powerpc64 using
- - AltiVec extensions
+ Curve25519 algorithm
- Enable on POWER8 and newer processors for improved performance.
-
-config CRYPTO_VPMSUM_TESTER
- tristate "CRC32c and CRC32T10DIF hardware acceleration tester"
- depends on CRYPTO_CRCT10DIF_VPMSUM && CRYPTO_CRC32C_VPMSUM
- help
- Stress test for CRC32c and CRCT10DIF algorithms implemented with
- powerpc64 AltiVec extensions (POWER8 vpmsum instructions).
- Unless you are testing these algorithms, you don't need this.
+ Architecture: PowerPC64
+ - Little-endian
config CRYPTO_MD5_PPC
tristate "Digests: MD5"
@@ -101,6 +79,7 @@ config CRYPTO_AES_GCM_P10
select CRYPTO_ALGAPI
select CRYPTO_AEAD
select CRYPTO_SKCIPHER
+ select CRYPTO_SIMD
help
AEAD cipher: AES cipher algorithms (FIPS-197)
GCM (Galois/Counter Mode) authenticated encryption mode (NIST SP800-38D)
@@ -137,4 +116,24 @@ config CRYPTO_POLY1305_P10
- Power10 or later
- Little-endian
+config CRYPTO_DEV_VMX
+ bool "Support for VMX cryptographic acceleration instructions"
+ depends on PPC64 && VSX
+ help
+ Support for VMX cryptographic acceleration instructions.
+
+config CRYPTO_DEV_VMX_ENCRYPT
+ tristate "Encryption acceleration support on P8 CPU"
+ depends on CRYPTO_DEV_VMX
+ select CRYPTO_AES
+ select CRYPTO_CBC
+ select CRYPTO_CTR
+ select CRYPTO_GHASH
+ select CRYPTO_XTS
+ default m
+ help
+ Support for VMX cryptographic acceleration instructions on Power8 CPU.
+ This module supports acceleration for AES and GHASH in hardware. If you
+ choose 'M' here, this module will be called vmx-crypto.
+
endmenu
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index ebdac1b9eb9a..9b38f4a7bc15 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -10,31 +10,44 @@ obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o
obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
-obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
-obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
-obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o
obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o
obj-$(CONFIG_CRYPTO_CHACHA20_P10) += chacha-p10-crypto.o
obj-$(CONFIG_CRYPTO_POLY1305_P10) += poly1305-p10-crypto.o
+obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o
+obj-$(CONFIG_CRYPTO_CURVE25519_PPC64) += curve25519-ppc64le.o
aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
md5-ppc-y := md5-asm.o md5-glue.o
sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
-crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
-crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o
chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o
poly1305-p10-crypto-y := poly1305-p10-glue.o poly1305-p10le_64.o
+vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o
+curve25519-ppc64le-y := curve25519-ppc64le-core.o curve25519-ppc64le_asm.o
+
+ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
+override flavour := linux-ppc64le
+else
+ifdef CONFIG_PPC64_ELF_ABI_V2
+override flavour := linux-ppc64-elfv2
+else
+override flavour := linux-ppc64
+endif
+endif
quiet_cmd_perl = PERL $@
- cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@
+ cmd_perl = $(PERL) $< $(flavour) > $@
-targets += aesp10-ppc.S ghashp10-ppc.S
+targets += aesp10-ppc.S ghashp10-ppc.S aesp8-ppc.S ghashp8-ppc.S
$(obj)/aesp10-ppc.S $(obj)/ghashp10-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
$(call if_changed,perl)
+$(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
+ $(call if_changed,perl)
+
OBJECT_FILES_NON_STANDARD_aesp10-ppc.o := y
OBJECT_FILES_NON_STANDARD_ghashp10-ppc.o := y
+OBJECT_FILES_NON_STANDARD_aesp8-ppc.o := y
diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c
index f62ee54076c0..679f52794baf 100644
--- a/arch/powerpc/crypto/aes-gcm-p10-glue.c
+++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c
@@ -5,9 +5,10 @@
* Copyright 2022- IBM Inc. All rights reserved
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <asm/simd.h>
#include <asm/switch_to.h>
+#include <crypto/gcm.h>
#include <crypto/aes.h>
#include <crypto/algapi.h>
#include <crypto/b128ops.h>
@@ -24,6 +25,7 @@
#define PPC_ALIGN 16
#define GCM_IV_SIZE 12
+#define RFC4106_NONCE_SIZE 4
MODULE_DESCRIPTION("PPC64le AES-GCM with Stitched implementation");
MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com");
@@ -31,7 +33,7 @@ MODULE_LICENSE("GPL v2");
MODULE_ALIAS_CRYPTO("aes");
asmlinkage int aes_p10_set_encrypt_key(const u8 *userKey, const int bits,
- void *key);
+ void *key);
asmlinkage void aes_p10_encrypt(const u8 *in, u8 *out, const void *key);
asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len,
void *rkey, u8 *iv, void *Xi);
@@ -39,7 +41,8 @@ asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len,
void *rkey, u8 *iv, void *Xi);
asmlinkage void gcm_init_htable(unsigned char htable[], unsigned char Xi[]);
asmlinkage void gcm_ghash_p10(unsigned char *Xi, unsigned char *Htable,
- unsigned char *aad, unsigned int alen);
+ unsigned char *aad, unsigned int alen);
+asmlinkage void gcm_update(u8 *iv, void *Xi);
struct aes_key {
u8 key[AES_MAX_KEYLENGTH];
@@ -52,6 +55,7 @@ struct gcm_ctx {
u8 aad_hash[16];
u64 aadLen;
u64 Plen; /* offset 56 - used in aes_p10_gcm_{en/de}crypt */
+ u8 pblock[16];
};
struct Hash_ctx {
u8 H[16]; /* subkey */
@@ -60,17 +64,20 @@ struct Hash_ctx {
struct p10_aes_gcm_ctx {
struct aes_key enc_key;
+ u8 nonce[RFC4106_NONCE_SIZE];
};
static void vsx_begin(void)
{
preempt_disable();
+ pagefault_disable();
enable_kernel_vsx();
}
static void vsx_end(void)
{
disable_kernel_vsx();
+ pagefault_enable();
preempt_enable();
}
@@ -185,7 +192,7 @@ static int set_authsize(struct crypto_aead *tfm, unsigned int authsize)
}
static int p10_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
- unsigned int keylen)
+ unsigned int keylen)
{
struct crypto_tfm *tfm = crypto_aead_tfm(aead);
struct p10_aes_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -198,7 +205,8 @@ static int p10_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
return ret ? -EINVAL : 0;
}
-static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
+static int p10_aes_gcm_crypt(struct aead_request *req, u8 *riv,
+ int assoclen, int enc)
{
struct crypto_tfm *tfm = req->base.tfm;
struct p10_aes_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -206,11 +214,9 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
struct gcm_ctx *gctx = PTR_ALIGN((void *)databuf, PPC_ALIGN);
u8 hashbuf[sizeof(struct Hash_ctx) + PPC_ALIGN];
struct Hash_ctx *hash = PTR_ALIGN((void *)hashbuf, PPC_ALIGN);
- struct scatter_walk assoc_sg_walk;
struct skcipher_walk walk;
u8 *assocmem = NULL;
u8 *assoc;
- unsigned int assoclen = req->assoclen;
unsigned int cryptlen = req->cryptlen;
unsigned char ivbuf[AES_BLOCK_SIZE+PPC_ALIGN];
unsigned char *iv = PTR_ALIGN((void *)ivbuf, PPC_ALIGN);
@@ -218,16 +224,16 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
unsigned long auth_tag_len = crypto_aead_authsize(__crypto_aead_cast(tfm));
u8 otag[16];
int total_processed = 0;
+ int nbytes;
memset(databuf, 0, sizeof(databuf));
memset(hashbuf, 0, sizeof(hashbuf));
memset(ivbuf, 0, sizeof(ivbuf));
- memcpy(iv, req->iv, GCM_IV_SIZE);
+ memcpy(iv, riv, GCM_IV_SIZE);
/* Linearize assoc, if not already linear */
if (req->src->length >= assoclen && req->src->length) {
- scatterwalk_start(&assoc_sg_walk, req->src);
- assoc = scatterwalk_map(&assoc_sg_walk);
+ assoc = sg_virt(req->src); /* ppc64 is !HIGHMEM */
} else {
gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
GFP_KERNEL : GFP_ATOMIC;
@@ -245,10 +251,7 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
gcmp10_init(gctx, iv, (unsigned char *) &ctx->enc_key, hash, assoc, assoclen);
vsx_end();
- if (!assocmem)
- scatterwalk_unmap(assoc);
- else
- kfree(assocmem);
+ kfree(assocmem);
if (enc)
ret = skcipher_walk_aead_encrypt(&walk, req, false);
@@ -257,19 +260,25 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
if (ret)
return ret;
- while (walk.nbytes > 0 && ret == 0) {
+ while ((nbytes = walk.nbytes) > 0 && ret == 0) {
+ u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
+ u8 buf[AES_BLOCK_SIZE];
+
+ if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE))
+ src = dst = memcpy(buf, src, nbytes);
vsx_begin();
if (enc)
- aes_p10_gcm_encrypt(walk.src.virt.addr,
- walk.dst.virt.addr,
- walk.nbytes,
+ aes_p10_gcm_encrypt(src, dst, nbytes,
&ctx->enc_key, gctx->iv, hash->Htable);
else
- aes_p10_gcm_decrypt(walk.src.virt.addr,
- walk.dst.virt.addr,
- walk.nbytes,
+ aes_p10_gcm_decrypt(src, dst, nbytes,
&ctx->enc_key, gctx->iv, hash->Htable);
+
+ if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE))
+ memcpy(walk.dst.virt.addr, buf, nbytes);
+
vsx_end();
total_processed += walk.nbytes;
@@ -281,6 +290,7 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
/* Finalize hash */
vsx_begin();
+ gcm_update(gctx->iv, hash->Htable);
finish_tag(gctx, hash, total_processed);
vsx_end();
@@ -302,17 +312,63 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
return 0;
}
+static int rfc4106_setkey(struct crypto_aead *tfm, const u8 *inkey,
+ unsigned int keylen)
+{
+ struct p10_aes_gcm_ctx *ctx = crypto_aead_ctx(tfm);
+ int err;
+
+ keylen -= RFC4106_NONCE_SIZE;
+ err = p10_aes_gcm_setkey(tfm, inkey, keylen);
+ if (err)
+ return err;
+
+ memcpy(ctx->nonce, inkey + keylen, RFC4106_NONCE_SIZE);
+ return 0;
+}
+
+static int rfc4106_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+ return crypto_rfc4106_check_authsize(authsize);
+}
+
+static int rfc4106_encrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct p10_aes_gcm_ctx *ctx = crypto_aead_ctx(aead);
+ u8 iv[AES_BLOCK_SIZE];
+
+ memcpy(iv, ctx->nonce, RFC4106_NONCE_SIZE);
+ memcpy(iv + RFC4106_NONCE_SIZE, req->iv, GCM_RFC4106_IV_SIZE);
+
+ return crypto_ipsec_check_assoclen(req->assoclen) ?:
+ p10_aes_gcm_crypt(req, iv, req->assoclen - GCM_RFC4106_IV_SIZE, 1);
+}
+
+static int rfc4106_decrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct p10_aes_gcm_ctx *ctx = crypto_aead_ctx(aead);
+ u8 iv[AES_BLOCK_SIZE];
+
+ memcpy(iv, ctx->nonce, RFC4106_NONCE_SIZE);
+ memcpy(iv + RFC4106_NONCE_SIZE, req->iv, GCM_RFC4106_IV_SIZE);
+
+ return crypto_ipsec_check_assoclen(req->assoclen) ?:
+ p10_aes_gcm_crypt(req, iv, req->assoclen - GCM_RFC4106_IV_SIZE, 0);
+}
+
static int p10_aes_gcm_encrypt(struct aead_request *req)
{
- return p10_aes_gcm_crypt(req, 1);
+ return p10_aes_gcm_crypt(req, req->iv, req->assoclen, 1);
}
static int p10_aes_gcm_decrypt(struct aead_request *req)
{
- return p10_aes_gcm_crypt(req, 0);
+ return p10_aes_gcm_crypt(req, req->iv, req->assoclen, 0);
}
-static struct aead_alg gcm_aes_alg = {
+static struct aead_alg gcm_aes_algs[] = {{
.ivsize = GCM_IV_SIZE,
.maxauthsize = 16,
@@ -321,23 +377,57 @@ static struct aead_alg gcm_aes_alg = {
.encrypt = p10_aes_gcm_encrypt,
.decrypt = p10_aes_gcm_decrypt,
- .base.cra_name = "gcm(aes)",
- .base.cra_driver_name = "aes_gcm_p10",
+ .base.cra_name = "__gcm(aes)",
+ .base.cra_driver_name = "__aes_gcm_p10",
.base.cra_priority = 2100,
.base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct p10_aes_gcm_ctx),
+ .base.cra_ctxsize = sizeof(struct p10_aes_gcm_ctx)+
+ 4 * sizeof(u64[2]),
.base.cra_module = THIS_MODULE,
-};
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+}, {
+ .ivsize = GCM_RFC4106_IV_SIZE,
+ .maxauthsize = 16,
+ .setkey = rfc4106_setkey,
+ .setauthsize = rfc4106_setauthsize,
+ .encrypt = rfc4106_encrypt,
+ .decrypt = rfc4106_decrypt,
+
+ .base.cra_name = "__rfc4106(gcm(aes))",
+ .base.cra_driver_name = "__rfc4106_aes_gcm_p10",
+ .base.cra_priority = 2100,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct p10_aes_gcm_ctx) +
+ 4 * sizeof(u64[2]),
+ .base.cra_module = THIS_MODULE,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+}};
+
+static struct simd_aead_alg *p10_simd_aeads[ARRAY_SIZE(gcm_aes_algs)];
static int __init p10_init(void)
{
- return crypto_register_aead(&gcm_aes_alg);
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return 0;
+
+ ret = simd_register_aeads_compat(gcm_aes_algs,
+ ARRAY_SIZE(gcm_aes_algs),
+ p10_simd_aeads);
+ if (ret) {
+ simd_unregister_aeads(gcm_aes_algs, ARRAY_SIZE(gcm_aes_algs),
+ p10_simd_aeads);
+ return ret;
+ }
+ return 0;
}
static void __exit p10_exit(void)
{
- crypto_unregister_aead(&gcm_aes_alg);
+ simd_unregister_aeads(gcm_aes_algs, ARRAY_SIZE(gcm_aes_algs),
+ p10_simd_aeads);
}
-module_cpu_feature_match(PPC_MODULE_FEATURE_P10, p10_init);
+module_init(p10_init);
module_exit(p10_exit);
diff --git a/arch/powerpc/crypto/aes-gcm-p10.S b/arch/powerpc/crypto/aes-gcm-p10.S
index a51f4b265308..89f50eef3512 100644
--- a/arch/powerpc/crypto/aes-gcm-p10.S
+++ b/arch/powerpc/crypto/aes-gcm-p10.S
@@ -1,42 +1,42 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
- #
- # Accelerated AES-GCM stitched implementation for ppc64le.
- #
- # Copyright 2022- IBM Inc. All rights reserved
- #
- #===================================================================================
- # Written by Danny Tsen <dtsen@linux.ibm.com>
- #
- # GHASH is based on the Karatsuba multiplication method.
- #
- # Xi xor X1
- #
- # X1 * H^4 + X2 * H^3 + x3 * H^2 + X4 * H =
- # (X1.h * H4.h + xX.l * H4.l + X1 * H4) +
- # (X2.h * H3.h + X2.l * H3.l + X2 * H3) +
- # (X3.h * H2.h + X3.l * H2.l + X3 * H2) +
- # (X4.h * H.h + X4.l * H.l + X4 * H)
- #
- # Xi = v0
- # H Poly = v2
- # Hash keys = v3 - v14
- # ( H.l, H, H.h)
- # ( H^2.l, H^2, H^2.h)
- # ( H^3.l, H^3, H^3.h)
- # ( H^4.l, H^4, H^4.h)
- #
- # v30 is IV
- # v31 - counter 1
- #
- # AES used,
- # vs0 - vs14 for round keys
- # v15, v16, v17, v18, v19, v20, v21, v22 for 8 blocks (encrypted)
- #
- # This implementation uses stitched AES-GCM approach to improve overall performance.
- # AES is implemented with 8x blocks and GHASH is using 2 4x blocks.
- #
- # ===================================================================================
- #
+#
+# Accelerated AES-GCM stitched implementation for ppc64le.
+#
+# Copyright 2024- IBM Inc.
+#
+#===================================================================================
+# Written by Danny Tsen <dtsen@us.ibm.com>
+#
+# GHASH is based on the Karatsuba multiplication method.
+#
+# Xi xor X1
+#
+# X1 * H^4 + X2 * H^3 + x3 * H^2 + X4 * H =
+# (X1.h * H4.h + xX.l * H4.l + X1 * H4) +
+# (X2.h * H3.h + X2.l * H3.l + X2 * H3) +
+# (X3.h * H2.h + X3.l * H2.l + X3 * H2) +
+# (X4.h * H.h + X4.l * H.l + X4 * H)
+#
+# Xi = v0
+# H Poly = v2
+# Hash keys = v3 - v14
+# ( H.l, H, H.h)
+# ( H^2.l, H^2, H^2.h)
+# ( H^3.l, H^3, H^3.h)
+# ( H^4.l, H^4, H^4.h)
+#
+# v30 is IV
+# v31 - counter 1
+#
+# AES used,
+# vs0 - round key 0
+# v15, v16, v17, v18, v19, v20, v21, v22 for 8 blocks (encrypted)
+#
+# This implementation uses stitched AES-GCM approach to improve overall performance.
+# AES is implemented with 8x blocks and GHASH is using 2 4x blocks.
+#
+# ===================================================================================
+#
#include <asm/ppc_asm.h>
#include <linux/linkage.h>
@@ -44,483 +44,224 @@
.machine "any"
.text
- # 4x loops
- # v15 - v18 - input states
- # vs1 - vs9 - round keys
- #
-.macro Loop_aes_middle4x
- xxlor 19+32, 1, 1
- xxlor 20+32, 2, 2
- xxlor 21+32, 3, 3
- xxlor 22+32, 4, 4
-
- vcipher 15, 15, 19
- vcipher 16, 16, 19
- vcipher 17, 17, 19
- vcipher 18, 18, 19
-
- vcipher 15, 15, 20
- vcipher 16, 16, 20
- vcipher 17, 17, 20
- vcipher 18, 18, 20
-
- vcipher 15, 15, 21
- vcipher 16, 16, 21
- vcipher 17, 17, 21
- vcipher 18, 18, 21
-
- vcipher 15, 15, 22
- vcipher 16, 16, 22
- vcipher 17, 17, 22
- vcipher 18, 18, 22
-
- xxlor 19+32, 5, 5
- xxlor 20+32, 6, 6
- xxlor 21+32, 7, 7
- xxlor 22+32, 8, 8
-
- vcipher 15, 15, 19
- vcipher 16, 16, 19
- vcipher 17, 17, 19
- vcipher 18, 18, 19
-
- vcipher 15, 15, 20
- vcipher 16, 16, 20
- vcipher 17, 17, 20
- vcipher 18, 18, 20
-
- vcipher 15, 15, 21
- vcipher 16, 16, 21
- vcipher 17, 17, 21
- vcipher 18, 18, 21
-
- vcipher 15, 15, 22
- vcipher 16, 16, 22
- vcipher 17, 17, 22
- vcipher 18, 18, 22
-
- xxlor 23+32, 9, 9
- vcipher 15, 15, 23
- vcipher 16, 16, 23
- vcipher 17, 17, 23
- vcipher 18, 18, 23
+.macro SAVE_GPR GPR OFFSET FRAME
+ std \GPR,\OFFSET(\FRAME)
.endm
- # 8x loops
- # v15 - v22 - input states
- # vs1 - vs9 - round keys
- #
-.macro Loop_aes_middle8x
- xxlor 23+32, 1, 1
- xxlor 24+32, 2, 2
- xxlor 25+32, 3, 3
- xxlor 26+32, 4, 4
-
- vcipher 15, 15, 23
- vcipher 16, 16, 23
- vcipher 17, 17, 23
- vcipher 18, 18, 23
- vcipher 19, 19, 23
- vcipher 20, 20, 23
- vcipher 21, 21, 23
- vcipher 22, 22, 23
-
- vcipher 15, 15, 24
- vcipher 16, 16, 24
- vcipher 17, 17, 24
- vcipher 18, 18, 24
- vcipher 19, 19, 24
- vcipher 20, 20, 24
- vcipher 21, 21, 24
- vcipher 22, 22, 24
-
- vcipher 15, 15, 25
- vcipher 16, 16, 25
- vcipher 17, 17, 25
- vcipher 18, 18, 25
- vcipher 19, 19, 25
- vcipher 20, 20, 25
- vcipher 21, 21, 25
- vcipher 22, 22, 25
-
- vcipher 15, 15, 26
- vcipher 16, 16, 26
- vcipher 17, 17, 26
- vcipher 18, 18, 26
- vcipher 19, 19, 26
- vcipher 20, 20, 26
- vcipher 21, 21, 26
- vcipher 22, 22, 26
-
- xxlor 23+32, 5, 5
- xxlor 24+32, 6, 6
- xxlor 25+32, 7, 7
- xxlor 26+32, 8, 8
-
- vcipher 15, 15, 23
- vcipher 16, 16, 23
- vcipher 17, 17, 23
- vcipher 18, 18, 23
- vcipher 19, 19, 23
- vcipher 20, 20, 23
- vcipher 21, 21, 23
- vcipher 22, 22, 23
-
- vcipher 15, 15, 24
- vcipher 16, 16, 24
- vcipher 17, 17, 24
- vcipher 18, 18, 24
- vcipher 19, 19, 24
- vcipher 20, 20, 24
- vcipher 21, 21, 24
- vcipher 22, 22, 24
-
- vcipher 15, 15, 25
- vcipher 16, 16, 25
- vcipher 17, 17, 25
- vcipher 18, 18, 25
- vcipher 19, 19, 25
- vcipher 20, 20, 25
- vcipher 21, 21, 25
- vcipher 22, 22, 25
-
- vcipher 15, 15, 26
- vcipher 16, 16, 26
- vcipher 17, 17, 26
- vcipher 18, 18, 26
- vcipher 19, 19, 26
- vcipher 20, 20, 26
- vcipher 21, 21, 26
- vcipher 22, 22, 26
-
- xxlor 23+32, 9, 9
- vcipher 15, 15, 23
- vcipher 16, 16, 23
- vcipher 17, 17, 23
- vcipher 18, 18, 23
- vcipher 19, 19, 23
- vcipher 20, 20, 23
- vcipher 21, 21, 23
- vcipher 22, 22, 23
+.macro SAVE_VRS VRS OFFSET FRAME
+ stxv \VRS+32, \OFFSET(\FRAME)
.endm
-.macro Loop_aes_middle_1x
- xxlor 19+32, 1, 1
- xxlor 20+32, 2, 2
- xxlor 21+32, 3, 3
- xxlor 22+32, 4, 4
-
- vcipher 15, 15, 19
- vcipher 15, 15, 20
- vcipher 15, 15, 21
- vcipher 15, 15, 22
-
- xxlor 19+32, 5, 5
- xxlor 20+32, 6, 6
- xxlor 21+32, 7, 7
- xxlor 22+32, 8, 8
-
- vcipher 15, 15, 19
- vcipher 15, 15, 20
- vcipher 15, 15, 21
- vcipher 15, 15, 22
-
- xxlor 19+32, 9, 9
- vcipher 15, 15, 19
+.macro RESTORE_GPR GPR OFFSET FRAME
+ ld \GPR,\OFFSET(\FRAME)
.endm
- #
- # Compute 4x hash values based on Karatsuba method.
- #
-.macro ppc_aes_gcm_ghash
- vxor 15, 15, 0
-
- vpmsumd 23, 12, 15 # H4.L * X.L
- vpmsumd 24, 9, 16
- vpmsumd 25, 6, 17
- vpmsumd 26, 3, 18
-
- vxor 23, 23, 24
- vxor 23, 23, 25
- vxor 23, 23, 26 # L
-
- vpmsumd 24, 13, 15 # H4.L * X.H + H4.H * X.L
- vpmsumd 25, 10, 16 # H3.L * X1.H + H3.H * X1.L
- vpmsumd 26, 7, 17
- vpmsumd 27, 4, 18
-
- vxor 24, 24, 25
- vxor 24, 24, 26
- vxor 24, 24, 27 # M
-
- # sum hash and reduction with H Poly
- vpmsumd 28, 23, 2 # reduction
-
- vxor 29, 29, 29
- vsldoi 26, 24, 29, 8 # mL
- vsldoi 29, 29, 24, 8 # mH
- vxor 23, 23, 26 # mL + L
-
- vsldoi 23, 23, 23, 8 # swap
- vxor 23, 23, 28
-
- vpmsumd 24, 14, 15 # H4.H * X.H
- vpmsumd 25, 11, 16
- vpmsumd 26, 8, 17
- vpmsumd 27, 5, 18
-
- vxor 24, 24, 25
- vxor 24, 24, 26
- vxor 24, 24, 27
-
- vxor 24, 24, 29
-
- # sum hash and reduction with H Poly
- vsldoi 27, 23, 23, 8 # swap
- vpmsumd 23, 23, 2
- vxor 27, 27, 24
- vxor 23, 23, 27
-
- xxlor 32, 23+32, 23+32 # update hash
-
+.macro RESTORE_VRS VRS OFFSET FRAME
+ lxv \VRS+32, \OFFSET(\FRAME)
.endm
- #
- # Combine two 4x ghash
- # v15 - v22 - input blocks
- #
-.macro ppc_aes_gcm_ghash2_4x
- # first 4x hash
- vxor 15, 15, 0 # Xi + X
-
- vpmsumd 23, 12, 15 # H4.L * X.L
- vpmsumd 24, 9, 16
- vpmsumd 25, 6, 17
- vpmsumd 26, 3, 18
-
- vxor 23, 23, 24
- vxor 23, 23, 25
- vxor 23, 23, 26 # L
-
- vpmsumd 24, 13, 15 # H4.L * X.H + H4.H * X.L
- vpmsumd 25, 10, 16 # H3.L * X1.H + H3.H * X1.L
- vpmsumd 26, 7, 17
- vpmsumd 27, 4, 18
-
- vxor 24, 24, 25
- vxor 24, 24, 26
-
- # sum hash and reduction with H Poly
- vpmsumd 28, 23, 2 # reduction
-
- vxor 29, 29, 29
-
- vxor 24, 24, 27 # M
- vsldoi 26, 24, 29, 8 # mL
- vsldoi 29, 29, 24, 8 # mH
- vxor 23, 23, 26 # mL + L
-
- vsldoi 23, 23, 23, 8 # swap
- vxor 23, 23, 28
+.macro SAVE_REGS
+ mflr 0
+ std 0, 16(1)
+ stdu 1,-512(1)
+
+ SAVE_GPR 14, 112, 1
+ SAVE_GPR 15, 120, 1
+ SAVE_GPR 16, 128, 1
+ SAVE_GPR 17, 136, 1
+ SAVE_GPR 18, 144, 1
+ SAVE_GPR 19, 152, 1
+ SAVE_GPR 20, 160, 1
+ SAVE_GPR 21, 168, 1
+ SAVE_GPR 22, 176, 1
+ SAVE_GPR 23, 184, 1
+ SAVE_GPR 24, 192, 1
+
+ addi 9, 1, 256
+ SAVE_VRS 20, 0, 9
+ SAVE_VRS 21, 16, 9
+ SAVE_VRS 22, 32, 9
+ SAVE_VRS 23, 48, 9
+ SAVE_VRS 24, 64, 9
+ SAVE_VRS 25, 80, 9
+ SAVE_VRS 26, 96, 9
+ SAVE_VRS 27, 112, 9
+ SAVE_VRS 28, 128, 9
+ SAVE_VRS 29, 144, 9
+ SAVE_VRS 30, 160, 9
+ SAVE_VRS 31, 176, 9
+.endm # SAVE_REGS
- vpmsumd 24, 14, 15 # H4.H * X.H
- vpmsumd 25, 11, 16
- vpmsumd 26, 8, 17
- vpmsumd 27, 5, 18
+.macro RESTORE_REGS
+ addi 9, 1, 256
+ RESTORE_VRS 20, 0, 9
+ RESTORE_VRS 21, 16, 9
+ RESTORE_VRS 22, 32, 9
+ RESTORE_VRS 23, 48, 9
+ RESTORE_VRS 24, 64, 9
+ RESTORE_VRS 25, 80, 9
+ RESTORE_VRS 26, 96, 9
+ RESTORE_VRS 27, 112, 9
+ RESTORE_VRS 28, 128, 9
+ RESTORE_VRS 29, 144, 9
+ RESTORE_VRS 30, 160, 9
+ RESTORE_VRS 31, 176, 9
+
+ RESTORE_GPR 14, 112, 1
+ RESTORE_GPR 15, 120, 1
+ RESTORE_GPR 16, 128, 1
+ RESTORE_GPR 17, 136, 1
+ RESTORE_GPR 18, 144, 1
+ RESTORE_GPR 19, 152, 1
+ RESTORE_GPR 20, 160, 1
+ RESTORE_GPR 21, 168, 1
+ RESTORE_GPR 22, 176, 1
+ RESTORE_GPR 23, 184, 1
+ RESTORE_GPR 24, 192, 1
+
+ addi 1, 1, 512
+ ld 0, 16(1)
+ mtlr 0
+.endm # RESTORE_REGS
+
+# 4x loops
+.macro AES_CIPHER_4x _VCIPHER ST r
+ \_VCIPHER \ST, \ST, \r
+ \_VCIPHER \ST+1, \ST+1, \r
+ \_VCIPHER \ST+2, \ST+2, \r
+ \_VCIPHER \ST+3, \ST+3, \r
+.endm
- vxor 24, 24, 25
- vxor 24, 24, 26
- vxor 24, 24, 27 # H
+# 8x loops
+.macro AES_CIPHER_8x _VCIPHER ST r
+ \_VCIPHER \ST, \ST, \r
+ \_VCIPHER \ST+1, \ST+1, \r
+ \_VCIPHER \ST+2, \ST+2, \r
+ \_VCIPHER \ST+3, \ST+3, \r
+ \_VCIPHER \ST+4, \ST+4, \r
+ \_VCIPHER \ST+5, \ST+5, \r
+ \_VCIPHER \ST+6, \ST+6, \r
+ \_VCIPHER \ST+7, \ST+7, \r
+.endm
- vxor 24, 24, 29 # H + mH
+.macro LOOP_8AES_STATE
+ xxlor 32+23, 1, 1
+ xxlor 32+24, 2, 2
+ xxlor 32+25, 3, 3
+ xxlor 32+26, 4, 4
+ AES_CIPHER_8x vcipher, 15, 23
+ AES_CIPHER_8x vcipher, 15, 24
+ AES_CIPHER_8x vcipher, 15, 25
+ AES_CIPHER_8x vcipher, 15, 26
+ xxlor 32+23, 5, 5
+ xxlor 32+24, 6, 6
+ xxlor 32+25, 7, 7
+ xxlor 32+26, 8, 8
+ AES_CIPHER_8x vcipher, 15, 23
+ AES_CIPHER_8x vcipher, 15, 24
+ AES_CIPHER_8x vcipher, 15, 25
+ AES_CIPHER_8x vcipher, 15, 26
+.endm
- # sum hash and reduction with H Poly
- vsldoi 27, 23, 23, 8 # swap
- vpmsumd 23, 23, 2
- vxor 27, 27, 24
- vxor 27, 23, 27 # 1st Xi
-
- # 2nd 4x hash
- vpmsumd 24, 9, 20
- vpmsumd 25, 6, 21
- vpmsumd 26, 3, 22
- vxor 19, 19, 27 # Xi + X
- vpmsumd 23, 12, 19 # H4.L * X.L
-
- vxor 23, 23, 24
- vxor 23, 23, 25
- vxor 23, 23, 26 # L
-
- vpmsumd 24, 13, 19 # H4.L * X.H + H4.H * X.L
- vpmsumd 25, 10, 20 # H3.L * X1.H + H3.H * X1.L
- vpmsumd 26, 7, 21
- vpmsumd 27, 4, 22
-
- vxor 24, 24, 25
- vxor 24, 24, 26
+#
+# PPC_GHASH4x(H, S1, S2, S3, S4): Compute 4x hash values based on Karatsuba method.
+# H: returning digest
+# S#: states
+#
+# S1 should xor with the previous digest
+#
+# Xi = v0
+# H Poly = v2
+# Hash keys = v3 - v14
+# Scratch: v23 - v29
+#
+.macro PPC_GHASH4x H S1 S2 S3 S4
+
+ vpmsumd 23, 12, \S1 # H4.L * X.L
+ vpmsumd 24, 9, \S2
+ vpmsumd 25, 6, \S3
+ vpmsumd 26, 3, \S4
+
+ vpmsumd 27, 13, \S1 # H4.L * X.H + H4.H * X.L
+ vpmsumd 28, 10, \S2 # H3.L * X1.H + H3.H * X1.L
+
+ vxor 23, 23, 24
+ vxor 23, 23, 25
+ vxor 23, 23, 26 # L
+
+ vxor 24, 27, 28
+ vpmsumd 25, 7, \S3
+ vpmsumd 26, 4, \S4
+
+ vxor 24, 24, 25
+ vxor 24, 24, 26 # M
# sum hash and reduction with H Poly
- vpmsumd 28, 23, 2 # reduction
-
- vxor 29, 29, 29
+ vpmsumd 28, 23, 2 # reduction
- vxor 24, 24, 27 # M
- vsldoi 26, 24, 29, 8 # mL
- vsldoi 29, 29, 24, 8 # mH
- vxor 23, 23, 26 # mL + L
+ vxor 1, 1, 1
+ vsldoi 25, 24, 1, 8 # mL
+ vsldoi 1, 1, 24, 8 # mH
+ vxor 23, 23, 25 # mL + L
- vsldoi 23, 23, 23, 8 # swap
- vxor 23, 23, 28
+ # This performs swap and xor like,
+ # vsldoi 23, 23, 23, 8 # swap
+ # vxor 23, 23, 28
+ xxlor 32+25, 10, 10
+ vpermxor 23, 23, 28, 25
- vpmsumd 24, 14, 19 # H4.H * X.H
- vpmsumd 25, 11, 20
- vpmsumd 26, 8, 21
- vpmsumd 27, 5, 22
+ vpmsumd 26, 14, \S1 # H4.H * X.H
+ vpmsumd 27, 11, \S2
+ vpmsumd 28, 8, \S3
+ vpmsumd 29, 5, \S4
- vxor 24, 24, 25
- vxor 24, 24, 26
- vxor 24, 24, 27 # H
+ vxor 24, 26, 27
+ vxor 24, 24, 28
+ vxor 24, 24, 29
- vxor 24, 24, 29 # H + mH
+ vxor 24, 24, 1
# sum hash and reduction with H Poly
- vsldoi 27, 23, 23, 8 # swap
- vpmsumd 23, 23, 2
- vxor 27, 27, 24
- vxor 23, 23, 27
-
- xxlor 32, 23+32, 23+32 # update hash
-
+ vsldoi 25, 23, 23, 8 # swap
+ vpmsumd 23, 23, 2
+ vxor 27, 25, 24
+ vxor \H, 23, 27
.endm
- #
- # Compute update single hash
- #
-.macro ppc_update_hash_1x
- vxor 28, 28, 0
-
- vxor 19, 19, 19
+#
+# Compute update single ghash
+# scratch: v1, v22..v27
+#
+.macro PPC_GHASH1x H S1
- vpmsumd 22, 3, 28 # L
- vpmsumd 23, 4, 28 # M
- vpmsumd 24, 5, 28 # H
+ vxor 1, 1, 1
- vpmsumd 27, 22, 2 # reduction
+ vpmsumd 22, 3, \S1 # L
+ vpmsumd 23, 4, \S1 # M
+ vpmsumd 24, 5, \S1 # H
- vsldoi 25, 23, 19, 8 # mL
- vsldoi 26, 19, 23, 8 # mH
- vxor 22, 22, 25 # LL + LL
- vxor 24, 24, 26 # HH + HH
+ vpmsumd 27, 22, 2 # reduction
- vsldoi 22, 22, 22, 8 # swap
- vxor 22, 22, 27
+ vsldoi 25, 23, 1, 8 # mL
+ vsldoi 26, 1, 23, 8 # mH
+ vxor 22, 22, 25 # LL + LL
+ vxor 24, 24, 26 # HH + HH
- vsldoi 20, 22, 22, 8 # swap
- vpmsumd 22, 22, 2 # reduction
- vxor 20, 20, 24
- vxor 22, 22, 20
+ xxlor 32+25, 10, 10
+ vpermxor 22, 22, 27, 25
- vmr 0, 22 # update hash
-
-.endm
-
-.macro SAVE_REGS
- stdu 1,-640(1)
- mflr 0
-
- std 14,112(1)
- std 15,120(1)
- std 16,128(1)
- std 17,136(1)
- std 18,144(1)
- std 19,152(1)
- std 20,160(1)
- std 21,168(1)
- li 9, 256
- stvx 20, 9, 1
- addi 9, 9, 16
- stvx 21, 9, 1
- addi 9, 9, 16
- stvx 22, 9, 1
- addi 9, 9, 16
- stvx 23, 9, 1
- addi 9, 9, 16
- stvx 24, 9, 1
- addi 9, 9, 16
- stvx 25, 9, 1
- addi 9, 9, 16
- stvx 26, 9, 1
- addi 9, 9, 16
- stvx 27, 9, 1
- addi 9, 9, 16
- stvx 28, 9, 1
- addi 9, 9, 16
- stvx 29, 9, 1
- addi 9, 9, 16
- stvx 30, 9, 1
- addi 9, 9, 16
- stvx 31, 9, 1
- stxv 14, 464(1)
- stxv 15, 480(1)
- stxv 16, 496(1)
- stxv 17, 512(1)
- stxv 18, 528(1)
- stxv 19, 544(1)
- stxv 20, 560(1)
- stxv 21, 576(1)
- stxv 22, 592(1)
- std 0, 656(1)
-.endm
-
-.macro RESTORE_REGS
- lxv 14, 464(1)
- lxv 15, 480(1)
- lxv 16, 496(1)
- lxv 17, 512(1)
- lxv 18, 528(1)
- lxv 19, 544(1)
- lxv 20, 560(1)
- lxv 21, 576(1)
- lxv 22, 592(1)
- li 9, 256
- lvx 20, 9, 1
- addi 9, 9, 16
- lvx 21, 9, 1
- addi 9, 9, 16
- lvx 22, 9, 1
- addi 9, 9, 16
- lvx 23, 9, 1
- addi 9, 9, 16
- lvx 24, 9, 1
- addi 9, 9, 16
- lvx 25, 9, 1
- addi 9, 9, 16
- lvx 26, 9, 1
- addi 9, 9, 16
- lvx 27, 9, 1
- addi 9, 9, 16
- lvx 28, 9, 1
- addi 9, 9, 16
- lvx 29, 9, 1
- addi 9, 9, 16
- lvx 30, 9, 1
- addi 9, 9, 16
- lvx 31, 9, 1
-
- ld 0, 656(1)
- ld 14,112(1)
- ld 15,120(1)
- ld 16,128(1)
- ld 17,136(1)
- ld 18,144(1)
- ld 19,152(1)
- ld 20,160(1)
- ld 21,168(1)
-
- mtlr 0
- addi 1, 1, 640
+ vsldoi 23, 22, 22, 8 # swap
+ vpmsumd 22, 22, 2 # reduction
+ vxor 23, 23, 24
+ vxor \H, 22, 23
.endm
+#
+# LOAD_HASH_TABLE
+# Xi = v0
+# H Poly = v2
+# Hash keys = v3 - v14
+#
.macro LOAD_HASH_TABLE
# Load Xi
lxvb16x 32, 0, 8 # load Xi
@@ -557,657 +298,434 @@
lxvd2x 14+32, 10, 8 # H^4h
.endm
- #
- # aes_p10_gcm_encrypt (const void *inp, void *out, size_t len,
- # const char *rk, unsigned char iv[16], void *Xip);
- #
- # r3 - inp
- # r4 - out
- # r5 - len
- # r6 - AES round keys
- # r7 - iv and other data
- # r8 - Xi, HPoli, hash keys
- #
- # rounds is at offset 240 in rk
- # Xi is at 0 in gcm_table (Xip).
- #
-_GLOBAL(aes_p10_gcm_encrypt)
-.align 5
-
- SAVE_REGS
-
- LOAD_HASH_TABLE
-
- # initialize ICB: GHASH( IV ), IV - r7
- lxvb16x 30+32, 0, 7 # load IV - v30
-
- mr 12, 5 # length
- li 11, 0 # block index
-
- # counter 1
- vxor 31, 31, 31
- vspltisb 22, 1
- vsldoi 31, 31, 22,1 # counter 1
-
- # load round key to VSR
- lxv 0, 0(6)
- lxv 1, 0x10(6)
- lxv 2, 0x20(6)
- lxv 3, 0x30(6)
- lxv 4, 0x40(6)
- lxv 5, 0x50(6)
- lxv 6, 0x60(6)
- lxv 7, 0x70(6)
- lxv 8, 0x80(6)
- lxv 9, 0x90(6)
- lxv 10, 0xa0(6)
-
- # load rounds - 10 (128), 12 (192), 14 (256)
- lwz 9,240(6)
-
- #
- # vxor state, state, w # addroundkey
- xxlor 32+29, 0, 0
- vxor 15, 30, 29 # IV + round key - add round key 0
-
- cmpdi 9, 10
- beq Loop_aes_gcm_8x
-
- # load 2 more round keys (v11, v12)
- lxv 11, 0xb0(6)
- lxv 12, 0xc0(6)
-
- cmpdi 9, 12
- beq Loop_aes_gcm_8x
-
- # load 2 more round keys (v11, v12, v13, v14)
- lxv 13, 0xd0(6)
- lxv 14, 0xe0(6)
- cmpdi 9, 14
- beq Loop_aes_gcm_8x
-
- b aes_gcm_out
-
-.align 5
-Loop_aes_gcm_8x:
- mr 14, 3
- mr 9, 4
-
- #
- # check partial block
- #
-Continue_partial_check:
- ld 15, 56(7)
- cmpdi 15, 0
- beq Continue
- bgt Final_block
- cmpdi 15, 16
- blt Final_block
-
-Continue:
- # n blcoks
- li 10, 128
- divdu 10, 12, 10 # n 128 bytes-blocks
- cmpdi 10, 0
- beq Loop_last_block
-
- vaddudm 30, 30, 31 # IV + counter
- vxor 16, 30, 29
- vaddudm 30, 30, 31
- vxor 17, 30, 29
- vaddudm 30, 30, 31
- vxor 18, 30, 29
- vaddudm 30, 30, 31
- vxor 19, 30, 29
- vaddudm 30, 30, 31
- vxor 20, 30, 29
- vaddudm 30, 30, 31
- vxor 21, 30, 29
- vaddudm 30, 30, 31
- vxor 22, 30, 29
-
- mtctr 10
-
- li 15, 16
- li 16, 32
- li 17, 48
- li 18, 64
- li 19, 80
- li 20, 96
- li 21, 112
-
- lwz 10, 240(6)
-
-Loop_8x_block:
-
- lxvb16x 15, 0, 14 # load block
- lxvb16x 16, 15, 14 # load block
- lxvb16x 17, 16, 14 # load block
- lxvb16x 18, 17, 14 # load block
- lxvb16x 19, 18, 14 # load block
- lxvb16x 20, 19, 14 # load block
- lxvb16x 21, 20, 14 # load block
- lxvb16x 22, 21, 14 # load block
- addi 14, 14, 128
-
- Loop_aes_middle8x
-
- xxlor 23+32, 10, 10
-
- cmpdi 10, 10
- beq Do_next_ghash
-
- # 192 bits
- xxlor 24+32, 11, 11
-
- vcipher 15, 15, 23
- vcipher 16, 16, 23
- vcipher 17, 17, 23
- vcipher 18, 18, 23
- vcipher 19, 19, 23
- vcipher 20, 20, 23
- vcipher 21, 21, 23
- vcipher 22, 22, 23
-
- vcipher 15, 15, 24
- vcipher 16, 16, 24
- vcipher 17, 17, 24
- vcipher 18, 18, 24
- vcipher 19, 19, 24
- vcipher 20, 20, 24
- vcipher 21, 21, 24
- vcipher 22, 22, 24
-
- xxlor 23+32, 12, 12
-
- cmpdi 10, 12
- beq Do_next_ghash
-
- # 256 bits
- xxlor 24+32, 13, 13
-
- vcipher 15, 15, 23
- vcipher 16, 16, 23
- vcipher 17, 17, 23
- vcipher 18, 18, 23
- vcipher 19, 19, 23
- vcipher 20, 20, 23
- vcipher 21, 21, 23
- vcipher 22, 22, 23
-
- vcipher 15, 15, 24
- vcipher 16, 16, 24
- vcipher 17, 17, 24
- vcipher 18, 18, 24
- vcipher 19, 19, 24
- vcipher 20, 20, 24
- vcipher 21, 21, 24
- vcipher 22, 22, 24
-
- xxlor 23+32, 14, 14
-
- cmpdi 10, 14
- beq Do_next_ghash
- b aes_gcm_out
-
-Do_next_ghash:
-
- #
- # last round
- vcipherlast 15, 15, 23
- vcipherlast 16, 16, 23
-
- xxlxor 47, 47, 15
- stxvb16x 47, 0, 9 # store output
- xxlxor 48, 48, 16
- stxvb16x 48, 15, 9 # store output
-
- vcipherlast 17, 17, 23
- vcipherlast 18, 18, 23
-
- xxlxor 49, 49, 17
- stxvb16x 49, 16, 9 # store output
- xxlxor 50, 50, 18
- stxvb16x 50, 17, 9 # store output
-
- vcipherlast 19, 19, 23
- vcipherlast 20, 20, 23
-
- xxlxor 51, 51, 19
- stxvb16x 51, 18, 9 # store output
- xxlxor 52, 52, 20
- stxvb16x 52, 19, 9 # store output
-
- vcipherlast 21, 21, 23
- vcipherlast 22, 22, 23
-
- xxlxor 53, 53, 21
- stxvb16x 53, 20, 9 # store output
- xxlxor 54, 54, 22
- stxvb16x 54, 21, 9 # store output
-
- addi 9, 9, 128
-
- # ghash here
- ppc_aes_gcm_ghash2_4x
-
- xxlor 27+32, 0, 0
- vaddudm 30, 30, 31 # IV + counter
- vmr 29, 30
- vxor 15, 30, 27 # add round key
- vaddudm 30, 30, 31
- vxor 16, 30, 27
- vaddudm 30, 30, 31
- vxor 17, 30, 27
- vaddudm 30, 30, 31
- vxor 18, 30, 27
- vaddudm 30, 30, 31
- vxor 19, 30, 27
- vaddudm 30, 30, 31
- vxor 20, 30, 27
- vaddudm 30, 30, 31
- vxor 21, 30, 27
- vaddudm 30, 30, 31
- vxor 22, 30, 27
-
- addi 12, 12, -128
- addi 11, 11, 128
-
- bdnz Loop_8x_block
-
- vmr 30, 29
- stxvb16x 30+32, 0, 7 # update IV
-
-Loop_last_block:
- cmpdi 12, 0
- beq aes_gcm_out
-
- # loop last few blocks
+################################################################################
+# Compute AES and ghash one block at a time.
+# r23: AES rounds
+# v30: current IV
+# vs0: roundkey 0
+#
+################################################################################
+SYM_FUNC_START_LOCAL(aes_gcm_crypt_1x)
+
+ cmpdi 5, 16
+ bge __More_1x
+ blr
+__More_1x:
li 10, 16
- divdu 10, 12, 10
-
- mtctr 10
-
- lwz 10, 240(6)
-
- cmpdi 12, 16
- blt Final_block
-
-Next_rem_block:
- lxvb16x 15, 0, 14 # load block
-
- Loop_aes_middle_1x
-
- xxlor 23+32, 10, 10
-
- cmpdi 10, 10
- beq Do_next_1x
-
- # 192 bits
- xxlor 24+32, 11, 11
-
- vcipher 15, 15, 23
- vcipher 15, 15, 24
-
- xxlor 23+32, 12, 12
+ divdu 12, 5, 10
+
+ xxlxor 32+15, 32+30, 0
+
+ # Pre-load 8 AES rounds to scratch vectors.
+ xxlor 32+16, 1, 1
+ xxlor 32+17, 2, 2
+ xxlor 32+18, 3, 3
+ xxlor 32+19, 4, 4
+ xxlor 32+20, 5, 5
+ xxlor 32+21, 6, 6
+ xxlor 32+28, 7, 7
+ xxlor 32+29, 8, 8
+ lwz 23, 240(6) # n rounds
+ addi 22, 23, -9 # remaing AES rounds
- cmpdi 10, 12
- beq Do_next_1x
-
- # 256 bits
- xxlor 24+32, 13, 13
-
- vcipher 15, 15, 23
- vcipher 15, 15, 24
-
- xxlor 23+32, 14, 14
-
- cmpdi 10, 14
- beq Do_next_1x
-
-Do_next_1x:
- vcipherlast 15, 15, 23
-
- xxlxor 47, 47, 15
- stxvb16x 47, 0, 9 # store output
- addi 14, 14, 16
- addi 9, 9, 16
-
- vmr 28, 15
- ppc_update_hash_1x
-
- addi 12, 12, -16
- addi 11, 11, 16
- xxlor 19+32, 0, 0
- vaddudm 30, 30, 31 # IV + counter
- vxor 15, 30, 19 # add round key
-
- bdnz Next_rem_block
-
- li 15, 0
- std 15, 56(7) # clear partial?
- stxvb16x 30+32, 0, 7 # update IV
cmpdi 12, 0
- beq aes_gcm_out
-
-Final_block:
- lwz 10, 240(6)
- Loop_aes_middle_1x
-
- xxlor 23+32, 10, 10
-
- cmpdi 10, 10
- beq Do_final_1x
-
- # 192 bits
- xxlor 24+32, 11, 11
-
- vcipher 15, 15, 23
- vcipher 15, 15, 24
-
- xxlor 23+32, 12, 12
-
- cmpdi 10, 12
- beq Do_final_1x
-
- # 256 bits
- xxlor 24+32, 13, 13
-
- vcipher 15, 15, 23
- vcipher 15, 15, 24
+ bgt __Loop_1x
+ blr
- xxlor 23+32, 14, 14
+__Loop_1x:
+ mtctr 22
+ addi 10, 6, 144
+ vcipher 15, 15, 16
+ vcipher 15, 15, 17
+ vcipher 15, 15, 18
+ vcipher 15, 15, 19
+ vcipher 15, 15, 20
+ vcipher 15, 15, 21
+ vcipher 15, 15, 28
+ vcipher 15, 15, 29
- cmpdi 10, 14
- beq Do_final_1x
+__Loop_aes_1state:
+ lxv 32+1, 0(10)
+ vcipher 15, 15, 1
+ addi 10, 10, 16
+ bdnz __Loop_aes_1state
+ lxv 32+1, 0(10) # last round key
+ lxvb16x 11, 0, 14 # load input block
+ vcipherlast 15, 15, 1
+
+ xxlxor 32+15, 32+15, 11
+ stxvb16x 32+15, 0, 9 # store output
+ addi 14, 14, 16
+ addi 9, 9, 16
-Do_final_1x:
- vcipherlast 15, 15, 23
+ cmpdi 24, 0 # decrypt?
+ bne __Encrypt_1x
+ xxlor 15+32, 11, 11
+__Encrypt_1x:
+ vxor 15, 15, 0
+ PPC_GHASH1x 0, 15
- # check partial block
- li 21, 0 # encrypt
- ld 15, 56(7) # partial?
- cmpdi 15, 0
- beq Normal_block
- bl Do_partial_block
+ addi 5, 5, -16
+ addi 11, 11, 16
+ vadduwm 30, 30, 31 # IV + counter
+ xxlxor 32+15, 32+30, 0
+ addi 12, 12, -1
cmpdi 12, 0
- ble aes_gcm_out
+ bgt __Loop_1x
- b Continue_partial_check
-
-Normal_block:
- lxvb16x 15, 0, 14 # load last block
- xxlxor 47, 47, 15
-
- # create partial block mask
- li 15, 16
- sub 15, 15, 12 # index to the mask
-
- vspltisb 16, -1 # first 16 bytes - 0xffff...ff
- vspltisb 17, 0 # second 16 bytes - 0x0000...00
- li 10, 192
- stvx 16, 10, 1
+ stxvb16x 32+30, 0, 7 # update IV
+ stxvb16x 32+0, 0, 8 # update Xi
+ blr
+SYM_FUNC_END(aes_gcm_crypt_1x)
+
+################################################################################
+# Process a normal partial block when we come here.
+# Compute partial mask, Load and store partial block to stack.
+# Update partial_len and pblock.
+# pblock is (encrypted ^ AES state) for encrypt
+# and (input ^ AES state) for decrypt.
+#
+################################################################################
+SYM_FUNC_START_LOCAL(__Process_partial)
+
+ # create partial mask
+ vspltisb 16, -1
+ li 12, 16
+ sub 12, 12, 5
+ sldi 12, 12, 3
+ mtvsrdd 32+17, 0, 12
+ vslo 16, 16, 17 # partial block mask
+
+ lxvb16x 11, 0, 14 # load partial block
+ xxland 11, 11, 32+16
+
+ # AES crypt partial
+ xxlxor 32+15, 32+30, 0
+ lwz 23, 240(6) # n rounds
+ addi 22, 23, -1 # loop - 1
+ mtctr 22
+ addi 10, 6, 16
+
+__Loop_aes_pstate:
+ lxv 32+1, 0(10)
+ vcipher 15, 15, 1
addi 10, 10, 16
- stvx 17, 10, 1
-
- addi 10, 1, 192
- lxvb16x 16, 15, 10 # load partial block mask
- xxland 47, 47, 16
-
- vmr 28, 15
- ppc_update_hash_1x
+ bdnz __Loop_aes_pstate
+ lxv 32+1, 0(10) # last round key
+ vcipherlast 15, 15, 1
- # * should store only the remaining bytes.
- bl Write_partial_block
-
- stxvb16x 30+32, 0, 7 # update IV
- std 12, 56(7) # update partial?
- li 16, 16
+ xxlxor 32+15, 32+15, 11
+ vand 15, 15, 16
- stxvb16x 32, 0, 8 # write out Xi
- stxvb16x 32, 16, 8 # write out Xi
- b aes_gcm_out
-
- #
- # Compute data mask
- #
-.macro GEN_MASK _mask _start _end
- vspltisb 16, -1 # first 16 bytes - 0xffff...ff
- vspltisb 17, 0 # second 16 bytes - 0x0000...00
- li 10, 192
- stxvb16x 17+32, 10, 1
- add 10, 10, \_start
- stxvb16x 16+32, 10, 1
- add 10, 10, \_end
- stxvb16x 17+32, 10, 1
-
- addi 10, 1, 192
- lxvb16x \_mask, 0, 10 # load partial block mask
-.endm
+ # AES crypt output v15
+ # Write partial
+ li 10, 224
+ stxvb16x 15+32, 10, 1 # write v15 to stack
+ addi 10, 1, 223
+ addi 12, 9, -1
+ mtctr 5 # partial block len
+__Write_partial:
+ lbzu 22, 1(10)
+ stbu 22, 1(12)
+ bdnz __Write_partial
+
+ cmpdi 24, 0 # decrypt?
+ bne __Encrypt_partial
+ xxlor 32+15, 11, 11 # decrypt using the input block
+__Encrypt_partial:
+ #vxor 15, 15, 0 # ^ previous hash
+ #PPC_GHASH1x 0, 15
+
+ add 14, 14, 5
+ add 9, 9, 5
+ std 5, 56(7) # update partial
+ sub 11, 11, 5
+ li 5, 0 # done last byte
- #
- # Handle multiple partial blocks for encrypt and decrypt
- # operations.
- #
-SYM_FUNC_START_LOCAL(Do_partial_block)
- add 17, 15, 5
- cmpdi 17, 16
- bgt Big_block
- GEN_MASK 18, 15, 5
- b _Partial
-SYM_FUNC_END(Do_partial_block)
-Big_block:
+ #
+ # Don't increase IV since this is the last partial.
+ # It should get updated in gcm_update if no more data blocks.
+ #vadduwm 30, 30, 31 # increase IV
+ stxvb16x 32+30, 0, 7 # update IV
+ li 10, 64
+ stxvb16x 32+0, 0, 8 # Update X1
+ stxvb16x 32+15, 10, 7 # Update pblock
+ blr
+SYM_FUNC_END(__Process_partial)
+
+################################################################################
+# Combine partial blocks and ghash when we come here.
+#
+# The partial block has to be shifted to the right location to encrypt/decrypt
+# and compute ghash if combing the previous partial block is needed.
+# - Compute ghash for a full block. Clear Partial_len and pblock. Update IV.
+# Write Xi.
+# - Don't compute ghash if not full block. gcm_update will take care of it
+# is the last block. Update Partial_len and pblock.
+#
+################################################################################
+SYM_FUNC_START_LOCAL(__Combine_partial)
+
+ ld 12, 56(7)
+ mr 21, 5 # these bytes to be processed
+
+ li 17, 0
li 16, 16
- GEN_MASK 18, 15, 16
-
-_Partial:
- lxvb16x 17+32, 0, 14 # load last block
- sldi 16, 15, 3
- mtvsrdd 32+16, 0, 16
- vsro 17, 17, 16
- xxlxor 47, 47, 17+32
- xxland 47, 47, 18
-
- vxor 0, 0, 0 # clear Xi
- vmr 28, 15
-
- cmpdi 21, 0 # encrypt/decrypt ops?
- beq Skip_decrypt
- xxland 32+28, 32+17, 18
-
-Skip_decrypt:
-
- ppc_update_hash_1x
+ sub 22, 16, 12 # bytes to complete a block
+ sub 17, 22, 5 # remaining bytes in a block
+ cmpdi 5, 16
+ ble __Inp_msg_less16
+ li 17, 0
+ mr 21, 22
+ b __Combine_continue
+__Inp_msg_less16:
+ cmpd 22, 5
+ bgt __Combine_continue
+ li 17, 0
+ mr 21, 22 # these bytes to be processed
+
+__Combine_continue:
+ # load msg and shift to the proper location and mask
+ vspltisb 16, -1
+ sldi 15, 12, 3
+ mtvsrdd 32+17, 0, 15
+ vslo 16, 16, 17
+ vsro 16, 16, 17
+ sldi 15, 17, 3
+ mtvsrdd 32+17, 0, 15
+ vsro 16, 16, 17
+ vslo 16, 16, 17 # mask
+
+ lxvb16x 32+19, 0, 14 # load partial block
+ sldi 15, 12, 3
+ mtvsrdd 32+17, 0, 15
+ vsro 19, 19, 17 # 0x00..xxxx??..??
+ sldi 15, 17, 3
+ mtvsrdd 32+17, 0, 15
+ vsro 19, 19, 17 # 0x00..xxxx
+ vslo 19, 19, 17 # shift back to form 0x00..xxxx00..00
+
+ # AES crypt partial
+ xxlxor 32+15, 32+30, 0
+ lwz 23, 240(6) # n rounds
+ addi 22, 23, -1 # loop - 1
+ mtctr 22
+ addi 10, 6, 16
+
+__Loop_aes_cpstate:
+ lxv 32+1, 0(10)
+ vcipher 15, 15, 1
+ addi 10, 10, 16
+ bdnz __Loop_aes_cpstate
+ lxv 32+1, 0(10) # last round key
+ vcipherlast 15, 15, 1
- li 16, 16
- lxvb16x 32+29, 16, 8
- vxor 0, 0, 29
- stxvb16x 32, 0, 8 # save Xi
- stxvb16x 32, 16, 8 # save Xi
-
- # store partial block
- # loop the rest of the stream if any
- sldi 16, 15, 3
- mtvsrdd 32+16, 0, 16
- vslo 15, 15, 16
- #stxvb16x 15+32, 0, 9 # last block
+ vxor 15, 15, 19
+ vand 15, 15, 16
- li 16, 16
- sub 17, 16, 15 # 16 - partial
-
- add 16, 15, 5
- cmpdi 16, 16
- bgt Larger_16
- mr 17, 5
-Larger_16:
-
- # write partial
- li 10, 192
- stxvb16x 15+32, 10, 1 # save current block
-
- addi 10, 9, -1
- addi 16, 1, 191
- mtctr 17 # move partial byte count
-
-Write_last_partial:
- lbzu 18, 1(16)
- stbu 18, 1(10)
- bdnz Write_last_partial
- # Complete loop partial
-
- add 14, 14, 17
- add 9, 9, 17
- sub 12, 12, 17
- add 11, 11, 17
-
- add 15, 15, 5
- cmpdi 15, 16
- blt Save_partial
-
- vaddudm 30, 30, 31
- stxvb16x 30+32, 0, 7 # update IV
- xxlor 32+29, 0, 0
- vxor 15, 30, 29 # IV + round key - add round key 0
- li 15, 0
- std 15, 56(7) # partial done - clear
- b Partial_done
-Save_partial:
- std 15, 56(7) # partial
-
-Partial_done:
+ # AES crypt output v15
+ # Write partial
+ li 10, 224
+ stxvb16x 15+32, 10, 1 # write v15 to stack
+ addi 10, 1, 223
+ add 10, 10, 12 # add offset
+ addi 15, 9, -1
+ mtctr 21 # partial block len
+__Write_combine_partial:
+ lbzu 22, 1(10)
+ stbu 22, 1(15)
+ bdnz __Write_combine_partial
+
+ add 14, 14, 21
+ add 11, 11, 21
+ add 9, 9, 21
+ sub 5, 5, 21
+
+ # Encrypt/Decrypt?
+ cmpdi 24, 0 # decrypt?
+ bne __Encrypt_combine_partial
+ vmr 15, 19 # decrypt using the input block
+
+__Encrypt_combine_partial:
+ #
+ # Update partial flag and combine ghash.
+__Update_partial_ghash:
+ li 10, 64
+ lxvb16x 32+17, 10, 7 # load previous pblock
+ add 12, 12, 21 # combined pprocessed
+ vxor 15, 15, 17 # combined pblock
+
+ cmpdi 12, 16
+ beq __Clear_partial_flag
+ std 12, 56(7) # update partial len
+ stxvb16x 32+15, 10, 7 # Update current pblock
blr
- #
- # Write partial block
- # r9 - output
- # r12 - remaining bytes
- # v15 - partial input data
- #
-SYM_FUNC_START_LOCAL(Write_partial_block)
- li 10, 192
- stxvb16x 15+32, 10, 1 # last block
-
- addi 10, 9, -1
- addi 16, 1, 191
-
- mtctr 12 # remaining bytes
- li 15, 0
-
-Write_last_byte:
- lbzu 14, 1(16)
- stbu 14, 1(10)
- bdnz Write_last_byte
+__Clear_partial_flag:
+ li 12, 0
+ std 12, 56(7)
+ # Update IV and ghash here
+ vadduwm 30, 30, 31 # increase IV
+ stxvb16x 32+30, 0, 7 # update IV
+
+ # v15 either is either (input blockor encrypted)^(AES state)
+ vxor 15, 15, 0
+ PPC_GHASH1x 0, 15
+ stxvb16x 32+0, 10, 7 # update pblock for debug?
+ stxvb16x 32+0, 0, 8 # update Xi
blr
-SYM_FUNC_END(Write_partial_block)
+SYM_FUNC_END(__Combine_partial)
-aes_gcm_out:
- # out = state
- stxvb16x 32, 0, 8 # write out Xi
- add 3, 11, 12 # return count
+################################################################################
+# gcm_update(iv, Xi) - compute last hash
+#
+################################################################################
+SYM_FUNC_START(gcm_update)
- RESTORE_REGS
- blr
+ ld 10, 56(3)
+ cmpdi 10, 0
+ beq __no_update
- #
- # 8x Decrypt
- #
-_GLOBAL(aes_p10_gcm_decrypt)
-.align 5
+ lxvb16x 32, 0, 4 # load Xi
+ # load Hash - h^4, h^3, h^2, h
+ li 10, 32
+ lxvd2x 2+32, 10, 4 # H Poli
+ li 10, 48
+ lxvd2x 3+32, 10, 4 # Hl
+ li 10, 64
+ lxvd2x 4+32, 10, 4 # H
+ li 10, 80
+ lxvd2x 5+32, 10, 4 # Hh
+
+ addis 11, 2, permx@toc@ha
+ addi 11, 11, permx@toc@l
+ lxv 10, 0(11) # vs10: vpermxor vector
+
+ li 9, 64
+ lxvb16x 32+6, 9, 3 # load pblock
+ vxor 6, 6, 0
+
+ vxor 1, 1, 1
+ vpmsumd 12, 3, 6 # L
+ vpmsumd 13, 4, 6 # M
+ vpmsumd 14, 5, 6 # H
+ vpmsumd 17, 12, 2 # reduction
+ vsldoi 15, 13, 1, 8 # mL
+ vsldoi 16, 1, 13, 8 # mH
+ vxor 12, 12, 15 # LL + LL
+ vxor 14, 14, 16 # HH + HH
+ xxlor 32+15, 10, 10
+ vpermxor 12, 12, 17, 15
+ vsldoi 13, 12, 12, 8 # swap
+ vpmsumd 12, 12, 2 # reduction
+ vxor 13, 13, 14
+ vxor 7, 12, 13
+
+ #vxor 0, 0, 0
+ #stxvb16x 32+0, 9, 3
+ li 10, 0
+ std 10, 56(3)
+ stxvb16x 32+7, 0, 4
+
+__no_update:
+ blr
+SYM_FUNC_END(gcm_update)
+
+################################################################################
+# aes_p10_gcm_encrypt (const void *inp, void *out, size_t len,
+# const char *rk, unsigned char iv[16], void *Xip);
+#
+# r3 - inp
+# r4 - out
+# r5 - len
+# r6 - AES round keys
+# r7 - iv and other data
+# r8 - Xi, HPoli, hash keys
+#
+# rounds is at offset 240 in rk
+# Xi is at 0 in gcm_table (Xip).
+#
+################################################################################
+SYM_FUNC_START(aes_p10_gcm_encrypt)
+
+ cmpdi 5, 0
+ ble __Invalid_msg_len
SAVE_REGS
-
LOAD_HASH_TABLE
# initialize ICB: GHASH( IV ), IV - r7
lxvb16x 30+32, 0, 7 # load IV - v30
- mr 12, 5 # length
- li 11, 0 # block index
+ mr 14, 3
+ mr 9, 4
# counter 1
vxor 31, 31, 31
vspltisb 22, 1
vsldoi 31, 31, 22,1 # counter 1
- # load round key to VSR
- lxv 0, 0(6)
- lxv 1, 0x10(6)
- lxv 2, 0x20(6)
- lxv 3, 0x30(6)
- lxv 4, 0x40(6)
- lxv 5, 0x50(6)
- lxv 6, 0x60(6)
- lxv 7, 0x70(6)
- lxv 8, 0x80(6)
- lxv 9, 0x90(6)
- lxv 10, 0xa0(6)
+ addis 11, 2, permx@toc@ha
+ addi 11, 11, permx@toc@l
+ lxv 10, 0(11) # vs10: vpermxor vector
+ li 11, 0
+
+ # load 9 round keys to VSR
+ lxv 0, 0(6) # round key 0
+ lxv 1, 16(6) # round key 1
+ lxv 2, 32(6) # round key 2
+ lxv 3, 48(6) # round key 3
+ lxv 4, 64(6) # round key 4
+ lxv 5, 80(6) # round key 5
+ lxv 6, 96(6) # round key 6
+ lxv 7, 112(6) # round key 7
+ lxv 8, 128(6) # round key 8
# load rounds - 10 (128), 12 (192), 14 (256)
- lwz 9,240(6)
+ lwz 23, 240(6) # n rounds
+ li 24, 1 # encrypt
+__Process_encrypt:
#
- # vxor state, state, w # addroundkey
- xxlor 32+29, 0, 0
- vxor 15, 30, 29 # IV + round key - add round key 0
-
- cmpdi 9, 10
- beq Loop_aes_gcm_8x_dec
-
- # load 2 more round keys (v11, v12)
- lxv 11, 0xb0(6)
- lxv 12, 0xc0(6)
-
- cmpdi 9, 12
- beq Loop_aes_gcm_8x_dec
-
- # load 2 more round keys (v11, v12, v13, v14)
- lxv 13, 0xd0(6)
- lxv 14, 0xe0(6)
- cmpdi 9, 14
- beq Loop_aes_gcm_8x_dec
+ # Process different blocks
+ #
+ ld 12, 56(7)
+ cmpdi 12, 0
+ bgt __Do_combine_enc
+ cmpdi 5, 128
+ blt __Process_more_enc
+
+#
+# Process 8x AES/GCM blocks
+#
+__Process_8x_enc:
+ # 8x blcoks
+ li 10, 128
+ divdu 12, 5, 10 # n 128 bytes-blocks
- b aes_gcm_out
+ addi 12, 12, -1 # loop - 1
-.align 5
-Loop_aes_gcm_8x_dec:
- mr 14, 3
- mr 9, 4
+ vmr 15, 30 # first state: IV
+ vadduwm 16, 15, 31 # state + counter
+ vadduwm 17, 16, 31
+ vadduwm 18, 17, 31
+ vadduwm 19, 18, 31
+ vadduwm 20, 19, 31
+ vadduwm 21, 20, 31
+ vadduwm 22, 21, 31
+ xxlor 9, 32+22, 32+22 # save last state
- #
- # check partial block
- #
-Continue_partial_check_dec:
- ld 15, 56(7)
- cmpdi 15, 0
- beq Continue_dec
- bgt Final_block_dec
- cmpdi 15, 16
- blt Final_block_dec
-
-Continue_dec:
- # n blcoks
- li 10, 128
- divdu 10, 12, 10 # n 128 bytes-blocks
- cmpdi 10, 0
- beq Loop_last_block_dec
-
- vaddudm 30, 30, 31 # IV + counter
- vxor 16, 30, 29
- vaddudm 30, 30, 31
- vxor 17, 30, 29
- vaddudm 30, 30, 31
- vxor 18, 30, 29
- vaddudm 30, 30, 31
- vxor 19, 30, 29
- vaddudm 30, 30, 31
- vxor 20, 30, 29
- vaddudm 30, 30, 31
- vxor 21, 30, 29
- vaddudm 30, 30, 31
- vxor 22, 30, 29
-
- mtctr 10
+ # vxor state, state, w # addroundkey
+ xxlor 32+29, 0, 0
+ vxor 15, 15, 29 # IV + round key - add round key 0
+ vxor 16, 16, 29
+ vxor 17, 17, 29
+ vxor 18, 18, 29
+ vxor 19, 19, 29
+ vxor 20, 20, 29
+ vxor 21, 21, 29
+ vxor 22, 22, 29
li 15, 16
li 16, 32
@@ -1217,305 +735,502 @@ Continue_dec:
li 20, 96
li 21, 112
- lwz 10, 240(6)
-
-Loop_8x_block_dec:
-
- lxvb16x 15, 0, 14 # load block
- lxvb16x 16, 15, 14 # load block
- lxvb16x 17, 16, 14 # load block
- lxvb16x 18, 17, 14 # load block
- lxvb16x 19, 18, 14 # load block
- lxvb16x 20, 19, 14 # load block
- lxvb16x 21, 20, 14 # load block
- lxvb16x 22, 21, 14 # load block
- addi 14, 14, 128
-
- Loop_aes_middle8x
-
- xxlor 23+32, 10, 10
-
- cmpdi 10, 10
- beq Do_next_ghash_dec
-
- # 192 bits
- xxlor 24+32, 11, 11
-
- vcipher 15, 15, 23
- vcipher 16, 16, 23
- vcipher 17, 17, 23
- vcipher 18, 18, 23
- vcipher 19, 19, 23
- vcipher 20, 20, 23
- vcipher 21, 21, 23
- vcipher 22, 22, 23
-
- vcipher 15, 15, 24
- vcipher 16, 16, 24
- vcipher 17, 17, 24
- vcipher 18, 18, 24
- vcipher 19, 19, 24
- vcipher 20, 20, 24
- vcipher 21, 21, 24
- vcipher 22, 22, 24
-
- xxlor 23+32, 12, 12
-
- cmpdi 10, 12
- beq Do_next_ghash_dec
-
- # 256 bits
- xxlor 24+32, 13, 13
-
- vcipher 15, 15, 23
- vcipher 16, 16, 23
- vcipher 17, 17, 23
- vcipher 18, 18, 23
- vcipher 19, 19, 23
- vcipher 20, 20, 23
- vcipher 21, 21, 23
- vcipher 22, 22, 23
-
- vcipher 15, 15, 24
- vcipher 16, 16, 24
- vcipher 17, 17, 24
- vcipher 18, 18, 24
- vcipher 19, 19, 24
- vcipher 20, 20, 24
- vcipher 21, 21, 24
- vcipher 22, 22, 24
-
- xxlor 23+32, 14, 14
-
- cmpdi 10, 14
- beq Do_next_ghash_dec
- b aes_gcm_out
+ #
+ # Pre-compute first 8 AES state and leave 1/3/5 more rounds
+ # for the loop.
+ #
+ addi 22, 23, -9 # process 8 keys
+ mtctr 22 # AES key loop
+ addi 10, 6, 144
-Do_next_ghash_dec:
+ LOOP_8AES_STATE # process 8 AES keys
- #
- # last round
- vcipherlast 15, 15, 23
- vcipherlast 16, 16, 23
-
- xxlxor 47, 47, 15
- stxvb16x 47, 0, 9 # store output
- xxlxor 48, 48, 16
- stxvb16x 48, 15, 9 # store output
-
- vcipherlast 17, 17, 23
- vcipherlast 18, 18, 23
-
- xxlxor 49, 49, 17
- stxvb16x 49, 16, 9 # store output
- xxlxor 50, 50, 18
- stxvb16x 50, 17, 9 # store output
-
- vcipherlast 19, 19, 23
- vcipherlast 20, 20, 23
-
- xxlxor 51, 51, 19
- stxvb16x 51, 18, 9 # store output
- xxlxor 52, 52, 20
- stxvb16x 52, 19, 9 # store output
-
- vcipherlast 21, 21, 23
- vcipherlast 22, 22, 23
-
- xxlxor 53, 53, 21
- stxvb16x 53, 20, 9 # store output
- xxlxor 54, 54, 22
- stxvb16x 54, 21, 9 # store output
-
- addi 9, 9, 128
-
- xxlor 15+32, 15, 15
- xxlor 16+32, 16, 16
- xxlor 17+32, 17, 17
- xxlor 18+32, 18, 18
- xxlor 19+32, 19, 19
- xxlor 20+32, 20, 20
- xxlor 21+32, 21, 21
- xxlor 22+32, 22, 22
+__PreLoop_aes_state:
+ lxv 32+1, 0(10) # round key
+ AES_CIPHER_8x vcipher 15 1
+ addi 10, 10, 16
+ bdnz __PreLoop_aes_state
+ lxv 32+1, 0(10) # last round key (v1)
+
+ cmpdi 12, 0 # Only one loop (8 block)
+ beq __Finish_ghash
+
+#
+# Loop 8x blocks and compute ghash
+#
+__Loop_8x_block_enc:
+ vcipherlast 15, 15, 1
+ vcipherlast 16, 16, 1
+ vcipherlast 17, 17, 1
+ vcipherlast 18, 18, 1
+ vcipherlast 19, 19, 1
+ vcipherlast 20, 20, 1
+ vcipherlast 21, 21, 1
+ vcipherlast 22, 22, 1
+
+ lxvb16x 32+23, 0, 14 # load block
+ lxvb16x 32+24, 15, 14 # load block
+ lxvb16x 32+25, 16, 14 # load block
+ lxvb16x 32+26, 17, 14 # load block
+ lxvb16x 32+27, 18, 14 # load block
+ lxvb16x 32+28, 19, 14 # load block
+ lxvb16x 32+29, 20, 14 # load block
+ lxvb16x 32+30, 21, 14 # load block
+ addi 14, 14, 128
+
+ vxor 15, 15, 23
+ vxor 16, 16, 24
+ vxor 17, 17, 25
+ vxor 18, 18, 26
+ vxor 19, 19, 27
+ vxor 20, 20, 28
+ vxor 21, 21, 29
+ vxor 22, 22, 30
+
+ stxvb16x 47, 0, 9 # store output
+ stxvb16x 48, 15, 9 # store output
+ stxvb16x 49, 16, 9 # store output
+ stxvb16x 50, 17, 9 # store output
+ stxvb16x 51, 18, 9 # store output
+ stxvb16x 52, 19, 9 # store output
+ stxvb16x 53, 20, 9 # store output
+ stxvb16x 54, 21, 9 # store output
+ addi 9, 9, 128
# ghash here
- ppc_aes_gcm_ghash2_4x
-
- xxlor 27+32, 0, 0
- vaddudm 30, 30, 31 # IV + counter
- vmr 29, 30
- vxor 15, 30, 27 # add round key
- vaddudm 30, 30, 31
- vxor 16, 30, 27
- vaddudm 30, 30, 31
- vxor 17, 30, 27
- vaddudm 30, 30, 31
- vxor 18, 30, 27
- vaddudm 30, 30, 31
- vxor 19, 30, 27
- vaddudm 30, 30, 31
- vxor 20, 30, 27
- vaddudm 30, 30, 31
- vxor 21, 30, 27
- vaddudm 30, 30, 31
- vxor 22, 30, 27
-
- addi 12, 12, -128
+ vxor 15, 15, 0
+ PPC_GHASH4x 0, 15, 16, 17, 18
+
+ vxor 19, 19, 0
+ PPC_GHASH4x 0, 19, 20, 21, 22
+
+ xxlor 32+15, 9, 9 # last state
+ vadduwm 15, 15, 31 # state + counter
+ vadduwm 16, 15, 31
+ vadduwm 17, 16, 31
+ vadduwm 18, 17, 31
+ vadduwm 19, 18, 31
+ vadduwm 20, 19, 31
+ vadduwm 21, 20, 31
+ vadduwm 22, 21, 31
+ xxlor 9, 32+22, 32+22 # save last state
+
+ xxlor 32+27, 0, 0 # restore roundkey 0
+ vxor 15, 15, 27 # IV + round key - add round key 0
+ vxor 16, 16, 27
+ vxor 17, 17, 27
+ vxor 18, 18, 27
+ vxor 19, 19, 27
+ vxor 20, 20, 27
+ vxor 21, 21, 27
+ vxor 22, 22, 27
+
+ addi 5, 5, -128
addi 11, 11, 128
- bdnz Loop_8x_block_dec
-
- vmr 30, 29
- stxvb16x 30+32, 0, 7 # update IV
-
-Loop_last_block_dec:
- cmpdi 12, 0
- beq aes_gcm_out
-
- # loop last few blocks
- li 10, 16
- divdu 10, 12, 10
-
- mtctr 10
-
- lwz 10, 240(6)
-
- cmpdi 12, 16
- blt Final_block_dec
-
-Next_rem_block_dec:
- lxvb16x 15, 0, 14 # load block
-
- Loop_aes_middle_1x
-
- xxlor 23+32, 10, 10
+ LOOP_8AES_STATE # process 8 AES keys
+ mtctr 22 # AES key loop
+ addi 10, 6, 144
+__LastLoop_aes_state:
+ lxv 32+1, 0(10) # round key
+ AES_CIPHER_8x vcipher 15 1
+ addi 10, 10, 16
+ bdnz __LastLoop_aes_state
+ lxv 32+1, 0(10) # last round key (v1)
- cmpdi 10, 10
- beq Do_next_1x_dec
+ addi 12, 12, -1
+ cmpdi 12, 0
+ bne __Loop_8x_block_enc
+
+__Finish_ghash:
+ vcipherlast 15, 15, 1
+ vcipherlast 16, 16, 1
+ vcipherlast 17, 17, 1
+ vcipherlast 18, 18, 1
+ vcipherlast 19, 19, 1
+ vcipherlast 20, 20, 1
+ vcipherlast 21, 21, 1
+ vcipherlast 22, 22, 1
+
+ lxvb16x 32+23, 0, 14 # load block
+ lxvb16x 32+24, 15, 14 # load block
+ lxvb16x 32+25, 16, 14 # load block
+ lxvb16x 32+26, 17, 14 # load block
+ lxvb16x 32+27, 18, 14 # load block
+ lxvb16x 32+28, 19, 14 # load block
+ lxvb16x 32+29, 20, 14 # load block
+ lxvb16x 32+30, 21, 14 # load block
+ addi 14, 14, 128
+
+ vxor 15, 15, 23
+ vxor 16, 16, 24
+ vxor 17, 17, 25
+ vxor 18, 18, 26
+ vxor 19, 19, 27
+ vxor 20, 20, 28
+ vxor 21, 21, 29
+ vxor 22, 22, 30
+
+ stxvb16x 47, 0, 9 # store output
+ stxvb16x 48, 15, 9 # store output
+ stxvb16x 49, 16, 9 # store output
+ stxvb16x 50, 17, 9 # store output
+ stxvb16x 51, 18, 9 # store output
+ stxvb16x 52, 19, 9 # store output
+ stxvb16x 53, 20, 9 # store output
+ stxvb16x 54, 21, 9 # store output
+ addi 9, 9, 128
+
+ vxor 15, 15, 0
+ PPC_GHASH4x 0, 15, 16, 17, 18
+
+ vxor 19, 19, 0
+ PPC_GHASH4x 0, 19, 20, 21, 22
+
+ xxlor 30+32, 9, 9 # last ctr
+ vadduwm 30, 30, 31 # increase ctr
+ stxvb16x 32+30, 0, 7 # update IV
+ stxvb16x 32+0, 0, 8 # update Xi
+
+ addi 5, 5, -128
+ addi 11, 11, 128
- # 192 bits
- xxlor 24+32, 11, 11
+ #
+ # Done 8x blocks
+ #
- vcipher 15, 15, 23
- vcipher 15, 15, 24
+ cmpdi 5, 0
+ beq aes_gcm_out
- xxlor 23+32, 12, 12
+__Process_more_enc:
+ li 24, 1 # encrypt
+ bl aes_gcm_crypt_1x
+ cmpdi 5, 0
+ beq aes_gcm_out
- cmpdi 10, 12
- beq Do_next_1x_dec
+ bl __Process_partial
+ cmpdi 5, 0
+ beq aes_gcm_out
+__Do_combine_enc:
+ bl __Combine_partial
+ cmpdi 5, 0
+ bgt __Process_encrypt
+ b aes_gcm_out
- # 256 bits
- xxlor 24+32, 13, 13
+SYM_FUNC_END(aes_p10_gcm_encrypt)
- vcipher 15, 15, 23
- vcipher 15, 15, 24
+################################################################################
+# aes_p10_gcm_decrypt (const void *inp, void *out, size_t len,
+# const char *rk, unsigned char iv[16], void *Xip);
+# 8x Decrypt
+#
+################################################################################
+SYM_FUNC_START(aes_p10_gcm_decrypt)
- xxlor 23+32, 14, 14
+ cmpdi 5, 0
+ ble __Invalid_msg_len
- cmpdi 10, 14
- beq Do_next_1x_dec
+ SAVE_REGS
+ LOAD_HASH_TABLE
-Do_next_1x_dec:
- vcipherlast 15, 15, 23
+ # initialize ICB: GHASH( IV ), IV - r7
+ lxvb16x 30+32, 0, 7 # load IV - v30
- xxlxor 47, 47, 15
- stxvb16x 47, 0, 9 # store output
- addi 14, 14, 16
- addi 9, 9, 16
+ mr 14, 3
+ mr 9, 4
- xxlor 28+32, 15, 15
- #vmr 28, 15
- ppc_update_hash_1x
+ # counter 1
+ vxor 31, 31, 31
+ vspltisb 22, 1
+ vsldoi 31, 31, 22,1 # counter 1
- addi 12, 12, -16
- addi 11, 11, 16
- xxlor 19+32, 0, 0
- vaddudm 30, 30, 31 # IV + counter
- vxor 15, 30, 19 # add round key
+ addis 11, 2, permx@toc@ha
+ addi 11, 11, permx@toc@l
+ lxv 10, 0(11) # vs10: vpermxor vector
+ li 11, 0
+
+ # load 9 round keys to VSR
+ lxv 0, 0(6) # round key 0
+ lxv 1, 16(6) # round key 1
+ lxv 2, 32(6) # round key 2
+ lxv 3, 48(6) # round key 3
+ lxv 4, 64(6) # round key 4
+ lxv 5, 80(6) # round key 5
+ lxv 6, 96(6) # round key 6
+ lxv 7, 112(6) # round key 7
+ lxv 8, 128(6) # round key 8
- bdnz Next_rem_block_dec
+ # load rounds - 10 (128), 12 (192), 14 (256)
+ lwz 23, 240(6) # n rounds
+ li 24, 0 # decrypt
- li 15, 0
- std 15, 56(7) # clear partial?
- stxvb16x 30+32, 0, 7 # update IV
+__Process_decrypt:
+ #
+ # Process different blocks
+ #
+ ld 12, 56(7)
cmpdi 12, 0
- beq aes_gcm_out
-
-Final_block_dec:
- lwz 10, 240(6)
- Loop_aes_middle_1x
-
- xxlor 23+32, 10, 10
-
- cmpdi 10, 10
- beq Do_final_1x_dec
+ bgt __Do_combine_dec
+ cmpdi 5, 128
+ blt __Process_more_dec
+
+#
+# Process 8x AES/GCM blocks
+#
+__Process_8x_dec:
+ # 8x blcoks
+ li 10, 128
+ divdu 12, 5, 10 # n 128 bytes-blocks
- # 192 bits
- xxlor 24+32, 11, 11
+ addi 12, 12, -1 # loop - 1
- vcipher 15, 15, 23
- vcipher 15, 15, 24
+ vmr 15, 30 # first state: IV
+ vadduwm 16, 15, 31 # state + counter
+ vadduwm 17, 16, 31
+ vadduwm 18, 17, 31
+ vadduwm 19, 18, 31
+ vadduwm 20, 19, 31
+ vadduwm 21, 20, 31
+ vadduwm 22, 21, 31
+ xxlor 9, 32+22, 32+22 # save last state
- xxlor 23+32, 12, 12
+ # vxor state, state, w # addroundkey
+ xxlor 32+29, 0, 0
+ vxor 15, 15, 29 # IV + round key - add round key 0
+ vxor 16, 16, 29
+ vxor 17, 17, 29
+ vxor 18, 18, 29
+ vxor 19, 19, 29
+ vxor 20, 20, 29
+ vxor 21, 21, 29
+ vxor 22, 22, 29
- cmpdi 10, 12
- beq Do_final_1x_dec
+ li 15, 16
+ li 16, 32
+ li 17, 48
+ li 18, 64
+ li 19, 80
+ li 20, 96
+ li 21, 112
- # 256 bits
- xxlor 24+32, 13, 13
+ #
+ # Pre-compute first 8 AES state and leave 1/3/5 more rounds
+ # for the loop.
+ #
+ addi 22, 23, -9 # process 8 keys
+ mtctr 22 # AES key loop
+ addi 10, 6, 144
- vcipher 15, 15, 23
- vcipher 15, 15, 24
+ LOOP_8AES_STATE # process 8 AES keys
- xxlor 23+32, 14, 14
+__PreLoop_aes_state_dec:
+ lxv 32+1, 0(10) # round key
+ AES_CIPHER_8x vcipher 15 1
+ addi 10, 10, 16
+ bdnz __PreLoop_aes_state_dec
+ lxv 32+1, 0(10) # last round key (v1)
+
+ cmpdi 12, 0 # Only one loop (8 block)
+ beq __Finish_ghash_dec
+
+#
+# Loop 8x blocks and compute ghash
+#
+__Loop_8x_block_dec:
+ vcipherlast 15, 15, 1
+ vcipherlast 16, 16, 1
+ vcipherlast 17, 17, 1
+ vcipherlast 18, 18, 1
+ vcipherlast 19, 19, 1
+ vcipherlast 20, 20, 1
+ vcipherlast 21, 21, 1
+ vcipherlast 22, 22, 1
+
+ lxvb16x 32+23, 0, 14 # load block
+ lxvb16x 32+24, 15, 14 # load block
+ lxvb16x 32+25, 16, 14 # load block
+ lxvb16x 32+26, 17, 14 # load block
+ lxvb16x 32+27, 18, 14 # load block
+ lxvb16x 32+28, 19, 14 # load block
+ lxvb16x 32+29, 20, 14 # load block
+ lxvb16x 32+30, 21, 14 # load block
+ addi 14, 14, 128
+
+ vxor 15, 15, 23
+ vxor 16, 16, 24
+ vxor 17, 17, 25
+ vxor 18, 18, 26
+ vxor 19, 19, 27
+ vxor 20, 20, 28
+ vxor 21, 21, 29
+ vxor 22, 22, 30
+
+ stxvb16x 47, 0, 9 # store output
+ stxvb16x 48, 15, 9 # store output
+ stxvb16x 49, 16, 9 # store output
+ stxvb16x 50, 17, 9 # store output
+ stxvb16x 51, 18, 9 # store output
+ stxvb16x 52, 19, 9 # store output
+ stxvb16x 53, 20, 9 # store output
+ stxvb16x 54, 21, 9 # store output
+
+ addi 9, 9, 128
+
+ vmr 15, 23
+ vmr 16, 24
+ vmr 17, 25
+ vmr 18, 26
+ vmr 19, 27
+ vmr 20, 28
+ vmr 21, 29
+ vmr 22, 30
- cmpdi 10, 14
- beq Do_final_1x_dec
+ # ghash here
+ vxor 15, 15, 0
+ PPC_GHASH4x 0, 15, 16, 17, 18
+
+ vxor 19, 19, 0
+ PPC_GHASH4x 0, 19, 20, 21, 22
+
+ xxlor 32+15, 9, 9 # last state
+ vadduwm 15, 15, 31 # state + counter
+ vadduwm 16, 15, 31
+ vadduwm 17, 16, 31
+ vadduwm 18, 17, 31
+ vadduwm 19, 18, 31
+ vadduwm 20, 19, 31
+ vadduwm 21, 20, 31
+ vadduwm 22, 21, 31
+ xxlor 9, 32+22, 32+22 # save last state
+
+ xxlor 32+27, 0, 0 # restore roundkey 0
+ vxor 15, 15, 27 # IV + round key - add round key 0
+ vxor 16, 16, 27
+ vxor 17, 17, 27
+ vxor 18, 18, 27
+ vxor 19, 19, 27
+ vxor 20, 20, 27
+ vxor 21, 21, 27
+ vxor 22, 22, 27
+
+ addi 5, 5, -128
+ addi 11, 11, 128
-Do_final_1x_dec:
- vcipherlast 15, 15, 23
+ LOOP_8AES_STATE # process 8 AES keys
+ mtctr 22 # AES key loop
+ addi 10, 6, 144
+__LastLoop_aes_state_dec:
+ lxv 32+1, 0(10) # round key
+ AES_CIPHER_8x vcipher 15 1
+ addi 10, 10, 16
+ bdnz __LastLoop_aes_state_dec
+ lxv 32+1, 0(10) # last round key (v1)
- # check partial block
- li 21, 1 # decrypt
- ld 15, 56(7) # partial?
- cmpdi 15, 0
- beq Normal_block_dec
- bl Do_partial_block
+ addi 12, 12, -1
cmpdi 12, 0
- ble aes_gcm_out
-
- b Continue_partial_check_dec
+ bne __Loop_8x_block_dec
+
+__Finish_ghash_dec:
+ vcipherlast 15, 15, 1
+ vcipherlast 16, 16, 1
+ vcipherlast 17, 17, 1
+ vcipherlast 18, 18, 1
+ vcipherlast 19, 19, 1
+ vcipherlast 20, 20, 1
+ vcipherlast 21, 21, 1
+ vcipherlast 22, 22, 1
+
+ lxvb16x 32+23, 0, 14 # load block
+ lxvb16x 32+24, 15, 14 # load block
+ lxvb16x 32+25, 16, 14 # load block
+ lxvb16x 32+26, 17, 14 # load block
+ lxvb16x 32+27, 18, 14 # load block
+ lxvb16x 32+28, 19, 14 # load block
+ lxvb16x 32+29, 20, 14 # load block
+ lxvb16x 32+30, 21, 14 # load block
+ addi 14, 14, 128
+
+ vxor 15, 15, 23
+ vxor 16, 16, 24
+ vxor 17, 17, 25
+ vxor 18, 18, 26
+ vxor 19, 19, 27
+ vxor 20, 20, 28
+ vxor 21, 21, 29
+ vxor 22, 22, 30
+
+ stxvb16x 47, 0, 9 # store output
+ stxvb16x 48, 15, 9 # store output
+ stxvb16x 49, 16, 9 # store output
+ stxvb16x 50, 17, 9 # store output
+ stxvb16x 51, 18, 9 # store output
+ stxvb16x 52, 19, 9 # store output
+ stxvb16x 53, 20, 9 # store output
+ stxvb16x 54, 21, 9 # store output
+ addi 9, 9, 128
+
+ #vmr 15, 23
+ vxor 15, 23, 0
+ vmr 16, 24
+ vmr 17, 25
+ vmr 18, 26
+ vmr 19, 27
+ vmr 20, 28
+ vmr 21, 29
+ vmr 22, 30
+
+ #vxor 15, 15, 0
+ PPC_GHASH4x 0, 15, 16, 17, 18
+
+ vxor 19, 19, 0
+ PPC_GHASH4x 0, 19, 20, 21, 22
+
+ xxlor 30+32, 9, 9 # last ctr
+ vadduwm 30, 30, 31 # increase ctr
+ stxvb16x 32+30, 0, 7 # update IV
+ stxvb16x 32+0, 0, 8 # update Xi
+
+ addi 5, 5, -128
+ addi 11, 11, 128
-Normal_block_dec:
- lxvb16x 15, 0, 14 # load last block
- xxlxor 47, 47, 15
+ #
+ # Done 8x blocks
+ #
- # create partial block mask
- li 15, 16
- sub 15, 15, 12 # index to the mask
+ cmpdi 5, 0
+ beq aes_gcm_out
- vspltisb 16, -1 # first 16 bytes - 0xffff...ff
- vspltisb 17, 0 # second 16 bytes - 0x0000...00
- li 10, 192
- stvx 16, 10, 1
- addi 10, 10, 16
- stvx 17, 10, 1
+__Process_more_dec:
+ li 24, 0 # decrypt
+ bl aes_gcm_crypt_1x
+ cmpdi 5, 0
+ beq aes_gcm_out
- addi 10, 1, 192
- lxvb16x 16, 15, 10 # load partial block mask
- xxland 47, 47, 16
+ bl __Process_partial
+ cmpdi 5, 0
+ beq aes_gcm_out
+__Do_combine_dec:
+ bl __Combine_partial
+ cmpdi 5, 0
+ bgt __Process_decrypt
+ b aes_gcm_out
+SYM_FUNC_END(aes_p10_gcm_decrypt)
- xxland 32+28, 15, 16
- #vmr 28, 15
- ppc_update_hash_1x
+SYM_FUNC_START_LOCAL(aes_gcm_out)
- # * should store only the remaining bytes.
- bl Write_partial_block
+ mr 3, 11 # return count
- stxvb16x 30+32, 0, 7 # update IV
- std 12, 56(7) # update partial?
- li 16, 16
+ RESTORE_REGS
+ blr
- stxvb16x 32, 0, 8 # write out Xi
- stxvb16x 32, 16, 8 # write out Xi
- b aes_gcm_out
+__Invalid_msg_len:
+ li 3, 0
+ blr
+SYM_FUNC_END(aes_gcm_out)
+
+SYM_DATA_START_LOCAL(PERMX)
+.align 4
+# for vector permute and xor
+permx:
+.long 0x4c5d6e7f, 0x08192a3b, 0xc4d5e6f7, 0x8091a2b3
+SYM_DATA_END(permx)
diff --git a/arch/powerpc/crypto/aes.c b/arch/powerpc/crypto/aes.c
new file mode 100644
index 000000000000..ec06189fbf99
--- /dev/null
+++ b/arch/powerpc/crypto/aes.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AES routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/internal/cipher.h>
+#include <crypto/internal/simd.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_ctx {
+ struct crypto_cipher *fallback;
+ struct aes_key enc_key;
+ struct aes_key dec_key;
+};
+
+static int p8_aes_init(struct crypto_tfm *tfm)
+{
+ const char *alg = crypto_tfm_alg_name(tfm);
+ struct crypto_cipher *fallback;
+ struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ fallback = crypto_alloc_cipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+ if (IS_ERR(fallback)) {
+ printk(KERN_ERR
+ "Failed to allocate transformation for '%s': %ld\n",
+ alg, PTR_ERR(fallback));
+ return PTR_ERR(fallback);
+ }
+
+ crypto_cipher_set_flags(fallback,
+ crypto_cipher_get_flags((struct
+ crypto_cipher *)
+ tfm));
+ ctx->fallback = fallback;
+
+ return 0;
+}
+
+static void p8_aes_exit(struct crypto_tfm *tfm)
+{
+ struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ if (ctx->fallback) {
+ crypto_free_cipher(ctx->fallback);
+ ctx->fallback = NULL;
+ }
+}
+
+static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ int ret;
+ struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+ ret |= aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ ret |= crypto_cipher_setkey(ctx->fallback, key, keylen);
+
+ return ret ? -EINVAL : 0;
+}
+
+static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+ struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ if (!crypto_simd_usable()) {
+ crypto_cipher_encrypt_one(ctx->fallback, dst, src);
+ } else {
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ aes_p8_encrypt(src, dst, &ctx->enc_key);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+ }
+}
+
+static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+ struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ if (!crypto_simd_usable()) {
+ crypto_cipher_decrypt_one(ctx->fallback, dst, src);
+ } else {
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ aes_p8_decrypt(src, dst, &ctx->dec_key);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+ }
+}
+
+struct crypto_alg p8_aes_alg = {
+ .cra_name = "aes",
+ .cra_driver_name = "p8_aes",
+ .cra_module = THIS_MODULE,
+ .cra_priority = 1000,
+ .cra_type = NULL,
+ .cra_flags = CRYPTO_ALG_TYPE_CIPHER | CRYPTO_ALG_NEED_FALLBACK,
+ .cra_alignmask = 0,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct p8_aes_ctx),
+ .cra_init = p8_aes_init,
+ .cra_exit = p8_aes_exit,
+ .cra_cipher = {
+ .cia_min_keysize = AES_MIN_KEY_SIZE,
+ .cia_max_keysize = AES_MAX_KEY_SIZE,
+ .cia_setkey = p8_aes_setkey,
+ .cia_encrypt = p8_aes_encrypt,
+ .cia_decrypt = p8_aes_decrypt,
+ },
+};
diff --git a/arch/powerpc/crypto/aes_cbc.c b/arch/powerpc/crypto/aes_cbc.c
new file mode 100644
index 000000000000..ed0debc7acb5
--- /dev/null
+++ b/arch/powerpc/crypto/aes_cbc.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AES CBC routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_cbc_ctx {
+ struct crypto_skcipher *fallback;
+ struct aes_key enc_key;
+ struct aes_key dec_key;
+};
+
+static int p8_aes_cbc_init(struct crypto_skcipher *tfm)
+{
+ struct p8_aes_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct crypto_skcipher *fallback;
+
+ fallback = crypto_alloc_skcipher("cbc(aes)", 0,
+ CRYPTO_ALG_NEED_FALLBACK |
+ CRYPTO_ALG_ASYNC);
+ if (IS_ERR(fallback)) {
+ pr_err("Failed to allocate cbc(aes) fallback: %ld\n",
+ PTR_ERR(fallback));
+ return PTR_ERR(fallback);
+ }
+
+ crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+ crypto_skcipher_reqsize(fallback));
+ ctx->fallback = fallback;
+ return 0;
+}
+
+static void p8_aes_cbc_exit(struct crypto_skcipher *tfm)
+{
+ struct p8_aes_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ crypto_free_skcipher(ctx->fallback);
+}
+
+static int p8_aes_cbc_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct p8_aes_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int ret;
+
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+ ret |= aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ ret |= crypto_skcipher_setkey(ctx->fallback, key, keylen);
+
+ return ret ? -EINVAL : 0;
+}
+
+static int p8_aes_cbc_crypt(struct skcipher_request *req, int enc)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ const struct p8_aes_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int ret;
+
+ if (!crypto_simd_usable()) {
+ struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+ *subreq = *req;
+ skcipher_request_set_tfm(subreq, ctx->fallback);
+ return enc ? crypto_skcipher_encrypt(subreq) :
+ crypto_skcipher_decrypt(subreq);
+ }
+
+ ret = skcipher_walk_virt(&walk, req, false);
+ while ((nbytes = walk.nbytes) != 0) {
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ aes_p8_cbc_encrypt(walk.src.virt.addr,
+ walk.dst.virt.addr,
+ round_down(nbytes, AES_BLOCK_SIZE),
+ enc ? &ctx->enc_key : &ctx->dec_key,
+ walk.iv, enc);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ ret = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
+ }
+ return ret;
+}
+
+static int p8_aes_cbc_encrypt(struct skcipher_request *req)
+{
+ return p8_aes_cbc_crypt(req, 1);
+}
+
+static int p8_aes_cbc_decrypt(struct skcipher_request *req)
+{
+ return p8_aes_cbc_crypt(req, 0);
+}
+
+struct skcipher_alg p8_aes_cbc_alg = {
+ .base.cra_name = "cbc(aes)",
+ .base.cra_driver_name = "p8_aes_cbc",
+ .base.cra_module = THIS_MODULE,
+ .base.cra_priority = 2000,
+ .base.cra_flags = CRYPTO_ALG_NEED_FALLBACK,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct p8_aes_cbc_ctx),
+ .setkey = p8_aes_cbc_setkey,
+ .encrypt = p8_aes_cbc_encrypt,
+ .decrypt = p8_aes_cbc_decrypt,
+ .init = p8_aes_cbc_init,
+ .exit = p8_aes_cbc_exit,
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+};
diff --git a/arch/powerpc/crypto/aes_ctr.c b/arch/powerpc/crypto/aes_ctr.c
new file mode 100644
index 000000000000..9a3da8cd62f3
--- /dev/null
+++ b/arch/powerpc/crypto/aes_ctr.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AES CTR routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_ctr_ctx {
+ struct crypto_skcipher *fallback;
+ struct aes_key enc_key;
+};
+
+static int p8_aes_ctr_init(struct crypto_skcipher *tfm)
+{
+ struct p8_aes_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct crypto_skcipher *fallback;
+
+ fallback = crypto_alloc_skcipher("ctr(aes)", 0,
+ CRYPTO_ALG_NEED_FALLBACK |
+ CRYPTO_ALG_ASYNC);
+ if (IS_ERR(fallback)) {
+ pr_err("Failed to allocate ctr(aes) fallback: %ld\n",
+ PTR_ERR(fallback));
+ return PTR_ERR(fallback);
+ }
+
+ crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+ crypto_skcipher_reqsize(fallback));
+ ctx->fallback = fallback;
+ return 0;
+}
+
+static void p8_aes_ctr_exit(struct crypto_skcipher *tfm)
+{
+ struct p8_aes_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ crypto_free_skcipher(ctx->fallback);
+}
+
+static int p8_aes_ctr_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct p8_aes_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int ret;
+
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ ret |= crypto_skcipher_setkey(ctx->fallback, key, keylen);
+
+ return ret ? -EINVAL : 0;
+}
+
+static void p8_aes_ctr_final(const struct p8_aes_ctr_ctx *ctx,
+ struct skcipher_walk *walk)
+{
+ u8 *ctrblk = walk->iv;
+ u8 keystream[AES_BLOCK_SIZE];
+ u8 *src = walk->src.virt.addr;
+ u8 *dst = walk->dst.virt.addr;
+ unsigned int nbytes = walk->nbytes;
+
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ crypto_xor_cpy(dst, keystream, src, nbytes);
+ crypto_inc(ctrblk, AES_BLOCK_SIZE);
+}
+
+static int p8_aes_ctr_crypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ const struct p8_aes_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int ret;
+
+ if (!crypto_simd_usable()) {
+ struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+ *subreq = *req;
+ skcipher_request_set_tfm(subreq, ctx->fallback);
+ return crypto_skcipher_encrypt(subreq);
+ }
+
+ ret = skcipher_walk_virt(&walk, req, false);
+ while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ aes_p8_ctr32_encrypt_blocks(walk.src.virt.addr,
+ walk.dst.virt.addr,
+ nbytes / AES_BLOCK_SIZE,
+ &ctx->enc_key, walk.iv);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ do {
+ crypto_inc(walk.iv, AES_BLOCK_SIZE);
+ } while ((nbytes -= AES_BLOCK_SIZE) >= AES_BLOCK_SIZE);
+
+ ret = skcipher_walk_done(&walk, nbytes);
+ }
+ if (nbytes) {
+ p8_aes_ctr_final(ctx, &walk);
+ ret = skcipher_walk_done(&walk, 0);
+ }
+ return ret;
+}
+
+struct skcipher_alg p8_aes_ctr_alg = {
+ .base.cra_name = "ctr(aes)",
+ .base.cra_driver_name = "p8_aes_ctr",
+ .base.cra_module = THIS_MODULE,
+ .base.cra_priority = 2000,
+ .base.cra_flags = CRYPTO_ALG_NEED_FALLBACK,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct p8_aes_ctr_ctx),
+ .setkey = p8_aes_ctr_setkey,
+ .encrypt = p8_aes_ctr_crypt,
+ .decrypt = p8_aes_ctr_crypt,
+ .init = p8_aes_ctr_init,
+ .exit = p8_aes_ctr_exit,
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .chunksize = AES_BLOCK_SIZE,
+};
diff --git a/arch/powerpc/crypto/aes_xts.c b/arch/powerpc/crypto/aes_xts.c
new file mode 100644
index 000000000000..dabbccb41550
--- /dev/null
+++ b/arch/powerpc/crypto/aes_xts.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AES XTS routines supporting VMX In-core instructions on Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Leonidas S. Barbosa <leosilva@linux.vnet.ibm.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/xts.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_xts_ctx {
+ struct crypto_skcipher *fallback;
+ struct aes_key enc_key;
+ struct aes_key dec_key;
+ struct aes_key tweak_key;
+};
+
+static int p8_aes_xts_init(struct crypto_skcipher *tfm)
+{
+ struct p8_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct crypto_skcipher *fallback;
+
+ fallback = crypto_alloc_skcipher("xts(aes)", 0,
+ CRYPTO_ALG_NEED_FALLBACK |
+ CRYPTO_ALG_ASYNC);
+ if (IS_ERR(fallback)) {
+ pr_err("Failed to allocate xts(aes) fallback: %ld\n",
+ PTR_ERR(fallback));
+ return PTR_ERR(fallback);
+ }
+
+ crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+ crypto_skcipher_reqsize(fallback));
+ ctx->fallback = fallback;
+ return 0;
+}
+
+static void p8_aes_xts_exit(struct crypto_skcipher *tfm)
+{
+ struct p8_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ crypto_free_skcipher(ctx->fallback);
+}
+
+static int p8_aes_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct p8_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int ret;
+
+ ret = xts_verify_key(tfm, key, keylen);
+ if (ret)
+ return ret;
+
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ ret = aes_p8_set_encrypt_key(key + keylen/2, (keylen/2) * 8, &ctx->tweak_key);
+ ret |= aes_p8_set_encrypt_key(key, (keylen/2) * 8, &ctx->enc_key);
+ ret |= aes_p8_set_decrypt_key(key, (keylen/2) * 8, &ctx->dec_key);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ ret |= crypto_skcipher_setkey(ctx->fallback, key, keylen);
+
+ return ret ? -EINVAL : 0;
+}
+
+static int p8_aes_xts_crypt(struct skcipher_request *req, int enc)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ const struct p8_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ u8 tweak[AES_BLOCK_SIZE];
+ int ret;
+
+ if (req->cryptlen < AES_BLOCK_SIZE)
+ return -EINVAL;
+
+ if (!crypto_simd_usable() || (req->cryptlen % XTS_BLOCK_SIZE) != 0) {
+ struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+ *subreq = *req;
+ skcipher_request_set_tfm(subreq, ctx->fallback);
+ return enc ? crypto_skcipher_encrypt(subreq) :
+ crypto_skcipher_decrypt(subreq);
+ }
+
+ ret = skcipher_walk_virt(&walk, req, false);
+ if (ret)
+ return ret;
+
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+
+ aes_p8_encrypt(walk.iv, tweak, &ctx->tweak_key);
+
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ while ((nbytes = walk.nbytes) != 0) {
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ if (enc)
+ aes_p8_xts_encrypt(walk.src.virt.addr,
+ walk.dst.virt.addr,
+ round_down(nbytes, AES_BLOCK_SIZE),
+ &ctx->enc_key, NULL, tweak);
+ else
+ aes_p8_xts_decrypt(walk.src.virt.addr,
+ walk.dst.virt.addr,
+ round_down(nbytes, AES_BLOCK_SIZE),
+ &ctx->dec_key, NULL, tweak);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ ret = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
+ }
+ return ret;
+}
+
+static int p8_aes_xts_encrypt(struct skcipher_request *req)
+{
+ return p8_aes_xts_crypt(req, 1);
+}
+
+static int p8_aes_xts_decrypt(struct skcipher_request *req)
+{
+ return p8_aes_xts_crypt(req, 0);
+}
+
+struct skcipher_alg p8_aes_xts_alg = {
+ .base.cra_name = "xts(aes)",
+ .base.cra_driver_name = "p8_aes_xts",
+ .base.cra_module = THIS_MODULE,
+ .base.cra_priority = 2000,
+ .base.cra_flags = CRYPTO_ALG_NEED_FALLBACK,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct p8_aes_xts_ctx),
+ .setkey = p8_aes_xts_setkey,
+ .encrypt = p8_aes_xts_encrypt,
+ .decrypt = p8_aes_xts_decrypt,
+ .init = p8_aes_xts_init,
+ .exit = p8_aes_xts_exit,
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+};
diff --git a/arch/powerpc/crypto/aesp8-ppc.h b/arch/powerpc/crypto/aesp8-ppc.h
new file mode 100644
index 000000000000..5764d4438388
--- /dev/null
+++ b/arch/powerpc/crypto/aesp8-ppc.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/types.h>
+#include <crypto/aes.h>
+
+struct aes_key {
+ u8 key[AES_MAX_KEYLENGTH];
+ int rounds;
+};
+
+extern struct shash_alg p8_ghash_alg;
+extern struct crypto_alg p8_aes_alg;
+extern struct skcipher_alg p8_aes_cbc_alg;
+extern struct skcipher_alg p8_aes_ctr_alg;
+extern struct skcipher_alg p8_aes_xts_alg;
+
+int aes_p8_set_encrypt_key(const u8 *userKey, const int bits,
+ struct aes_key *key);
+int aes_p8_set_decrypt_key(const u8 *userKey, const int bits,
+ struct aes_key *key);
+void aes_p8_encrypt(const u8 *in, u8 *out, const struct aes_key *key);
+void aes_p8_decrypt(const u8 *in, u8 *out, const struct aes_key *key);
+void aes_p8_cbc_encrypt(const u8 *in, u8 *out, size_t len,
+ const struct aes_key *key, u8 *iv, const int enc);
+void aes_p8_ctr32_encrypt_blocks(const u8 *in, u8 *out,
+ size_t len, const struct aes_key *key,
+ const u8 *iv);
+void aes_p8_xts_encrypt(const u8 *in, u8 *out, size_t len,
+ const struct aes_key *key1, const struct aes_key *key2, u8 *iv);
+void aes_p8_xts_decrypt(const u8 *in, u8 *out, size_t len,
+ const struct aes_key *key1, const struct aes_key *key2, u8 *iv);
diff --git a/arch/powerpc/crypto/aesp8-ppc.pl b/arch/powerpc/crypto/aesp8-ppc.pl
new file mode 100644
index 000000000000..f729589d792e
--- /dev/null
+++ b/arch/powerpc/crypto/aesp8-ppc.pl
@@ -0,0 +1,3889 @@
+#! /usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from CRYPTOGAMs[1] and is included here using the option
+# in the license to distribute the code under the GPL. Therefore this program
+# is free software; you can redistribute it and/or modify it under the terms of
+# the GNU General Public License version 2 as published by the Free Software
+# Foundation.
+#
+# [1] https://www.openssl.org/~appro/cryptogams/
+
+# Copyright (c) 2006-2017, CRYPTOGAMS by <appro@openssl.org>
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+# * Redistributions of source code must retain copyright notices,
+# this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above
+# copyright notice, this list of conditions and the following
+# disclaimer in the documentation and/or other materials
+# provided with the distribution.
+#
+# * Neither the name of the CRYPTOGAMS nor the names of its
+# copyright holder and contributors may be used to endorse or
+# promote products derived from this software without specific
+# prior written permission.
+#
+# ALTERNATIVELY, provided that this notice is retained in full, this
+# product may be distributed under the terms of the GNU General Public
+# License (GPL), in which case the provisions of the GPL apply INSTEAD OF
+# those given above.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see https://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# This module implements support for AES instructions as per PowerISA
+# specification version 2.07, first implemented by POWER8 processor.
+# The module is endian-agnostic in sense that it supports both big-
+# and little-endian cases. Data alignment in parallelizable modes is
+# handled with VSX loads and stores, which implies MSR.VSX flag being
+# set. It should also be noted that ISA specification doesn't prohibit
+# alignment exceptions for these instructions on page boundaries.
+# Initially alignment was handled in pure AltiVec/VMX way [when data
+# is aligned programmatically, which in turn guarantees exception-
+# free execution], but it turned to hamper performance when vcipher
+# instructions are interleaved. It's reckoned that eventual
+# misalignment penalties at page boundaries are in average lower
+# than additional overhead in pure AltiVec approach.
+#
+# May 2016
+#
+# Add XTS subroutine, 9x on little- and 12x improvement on big-endian
+# systems were measured.
+#
+######################################################################
+# Current large-block performance in cycles per byte processed with
+# 128-bit key (less is better).
+#
+# CBC en-/decrypt CTR XTS
+# POWER8[le] 3.96/0.72 0.74 1.1
+# POWER8[be] 3.75/0.65 0.66 1.0
+
+$flavour = shift;
+
+if ($flavour =~ /64/) {
+ $SIZE_T =8;
+ $LRSAVE =2*$SIZE_T;
+ $STU ="stdu";
+ $POP ="ld";
+ $PUSH ="std";
+ $UCMP ="cmpld";
+ $SHL ="sldi";
+} elsif ($flavour =~ /32/) {
+ $SIZE_T =4;
+ $LRSAVE =$SIZE_T;
+ $STU ="stwu";
+ $POP ="lwz";
+ $PUSH ="stw";
+ $UCMP ="cmplw";
+ $SHL ="slwi";
+} else { die "nonsense $flavour"; }
+
+$LITTLE_ENDIAN = ($flavour=~/le$/) ? $SIZE_T : 0;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or
+die "can't locate ppc-xlate.pl";
+
+open STDOUT,"| $^X $xlate $flavour ".shift || die "can't call $xlate: $!";
+
+$FRAME=8*$SIZE_T;
+$prefix="aes_p8";
+
+$sp="r1";
+$vrsave="r12";
+
+#########################################################################
+{{{ # Key setup procedures #
+my ($inp,$bits,$out,$ptr,$cnt,$rounds)=map("r$_",(3..8));
+my ($zero,$in0,$in1,$key,$rcon,$mask,$tmp)=map("v$_",(0..6));
+my ($stage,$outperm,$outmask,$outhead,$outtail)=map("v$_",(7..11));
+
+$code.=<<___;
+.machine "any"
+
+.text
+
+.align 7
+rcon:
+.long 0x01000000, 0x01000000, 0x01000000, 0x01000000 ?rev
+.long 0x1b000000, 0x1b000000, 0x1b000000, 0x1b000000 ?rev
+.long 0x0d0e0f0c, 0x0d0e0f0c, 0x0d0e0f0c, 0x0d0e0f0c ?rev
+.long 0,0,0,0 ?asis
+.long 0x0f102132, 0x43546576, 0x8798a9ba, 0xcbdcedfe
+Lconsts:
+ mflr r0
+ bcl 20,31,\$+4
+ mflr $ptr #vvvvv "distance between . and rcon
+ addi $ptr,$ptr,-0x58
+ mtlr r0
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,0,0
+.asciz "AES for PowerISA 2.07, CRYPTOGAMS by <appro\@openssl.org>"
+
+.globl .${prefix}_set_encrypt_key
+Lset_encrypt_key:
+ mflr r11
+ $PUSH r11,$LRSAVE($sp)
+
+ li $ptr,-1
+ ${UCMP}i $inp,0
+ beq- Lenc_key_abort # if ($inp==0) return -1;
+ ${UCMP}i $out,0
+ beq- Lenc_key_abort # if ($out==0) return -1;
+ li $ptr,-2
+ cmpwi $bits,128
+ blt- Lenc_key_abort
+ cmpwi $bits,256
+ bgt- Lenc_key_abort
+ andi. r0,$bits,0x3f
+ bne- Lenc_key_abort
+
+ lis r0,0xfff0
+ mfspr $vrsave,256
+ mtspr 256,r0
+
+ bl Lconsts
+ mtlr r11
+
+ neg r9,$inp
+ lvx $in0,0,$inp
+ addi $inp,$inp,15 # 15 is not typo
+ lvsr $key,0,r9 # borrow $key
+ li r8,0x20
+ cmpwi $bits,192
+ lvx $in1,0,$inp
+ le?vspltisb $mask,0x0f # borrow $mask
+ lvx $rcon,0,$ptr
+ le?vxor $key,$key,$mask # adjust for byte swap
+ lvx $mask,r8,$ptr
+ addi $ptr,$ptr,0x10
+ vperm $in0,$in0,$in1,$key # align [and byte swap in LE]
+ li $cnt,8
+ vxor $zero,$zero,$zero
+ mtctr $cnt
+
+ ?lvsr $outperm,0,$out
+ vspltisb $outmask,-1
+ lvx $outhead,0,$out
+ ?vperm $outmask,$zero,$outmask,$outperm
+
+ blt Loop128
+ addi $inp,$inp,8
+ beq L192
+ addi $inp,$inp,8
+ b L256
+
+.align 4
+Loop128:
+ vperm $key,$in0,$in0,$mask # rotate-n-splat
+ vsldoi $tmp,$zero,$in0,12 # >>32
+ vperm $outtail,$in0,$in0,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ vcipherlast $key,$key,$rcon
+ stvx $stage,0,$out
+ addi $out,$out,16
+
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vadduwm $rcon,$rcon,$rcon
+ vxor $in0,$in0,$key
+ bdnz Loop128
+
+ lvx $rcon,0,$ptr # last two round keys
+
+ vperm $key,$in0,$in0,$mask # rotate-n-splat
+ vsldoi $tmp,$zero,$in0,12 # >>32
+ vperm $outtail,$in0,$in0,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ vcipherlast $key,$key,$rcon
+ stvx $stage,0,$out
+ addi $out,$out,16
+
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vadduwm $rcon,$rcon,$rcon
+ vxor $in0,$in0,$key
+
+ vperm $key,$in0,$in0,$mask # rotate-n-splat
+ vsldoi $tmp,$zero,$in0,12 # >>32
+ vperm $outtail,$in0,$in0,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ vcipherlast $key,$key,$rcon
+ stvx $stage,0,$out
+ addi $out,$out,16
+
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vxor $in0,$in0,$key
+ vperm $outtail,$in0,$in0,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ stvx $stage,0,$out
+
+ addi $inp,$out,15 # 15 is not typo
+ addi $out,$out,0x50
+
+ li $rounds,10
+ b Ldone
+
+.align 4
+L192:
+ lvx $tmp,0,$inp
+ li $cnt,4
+ vperm $outtail,$in0,$in0,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ stvx $stage,0,$out
+ addi $out,$out,16
+ vperm $in1,$in1,$tmp,$key # align [and byte swap in LE]
+ vspltisb $key,8 # borrow $key
+ mtctr $cnt
+ vsububm $mask,$mask,$key # adjust the mask
+
+Loop192:
+ vperm $key,$in1,$in1,$mask # roate-n-splat
+ vsldoi $tmp,$zero,$in0,12 # >>32
+ vcipherlast $key,$key,$rcon
+
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+
+ vsldoi $stage,$zero,$in1,8
+ vspltw $tmp,$in0,3
+ vxor $tmp,$tmp,$in1
+ vsldoi $in1,$zero,$in1,12 # >>32
+ vadduwm $rcon,$rcon,$rcon
+ vxor $in1,$in1,$tmp
+ vxor $in0,$in0,$key
+ vxor $in1,$in1,$key
+ vsldoi $stage,$stage,$in0,8
+
+ vperm $key,$in1,$in1,$mask # rotate-n-splat
+ vsldoi $tmp,$zero,$in0,12 # >>32
+ vperm $outtail,$stage,$stage,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ vcipherlast $key,$key,$rcon
+ stvx $stage,0,$out
+ addi $out,$out,16
+
+ vsldoi $stage,$in0,$in1,8
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vperm $outtail,$stage,$stage,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ stvx $stage,0,$out
+ addi $out,$out,16
+
+ vspltw $tmp,$in0,3
+ vxor $tmp,$tmp,$in1
+ vsldoi $in1,$zero,$in1,12 # >>32
+ vadduwm $rcon,$rcon,$rcon
+ vxor $in1,$in1,$tmp
+ vxor $in0,$in0,$key
+ vxor $in1,$in1,$key
+ vperm $outtail,$in0,$in0,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ stvx $stage,0,$out
+ addi $inp,$out,15 # 15 is not typo
+ addi $out,$out,16
+ bdnz Loop192
+
+ li $rounds,12
+ addi $out,$out,0x20
+ b Ldone
+
+.align 4
+L256:
+ lvx $tmp,0,$inp
+ li $cnt,7
+ li $rounds,14
+ vperm $outtail,$in0,$in0,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ stvx $stage,0,$out
+ addi $out,$out,16
+ vperm $in1,$in1,$tmp,$key # align [and byte swap in LE]
+ mtctr $cnt
+
+Loop256:
+ vperm $key,$in1,$in1,$mask # rotate-n-splat
+ vsldoi $tmp,$zero,$in0,12 # >>32
+ vperm $outtail,$in1,$in1,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ vcipherlast $key,$key,$rcon
+ stvx $stage,0,$out
+ addi $out,$out,16
+
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in0,$in0,$tmp
+ vadduwm $rcon,$rcon,$rcon
+ vxor $in0,$in0,$key
+ vperm $outtail,$in0,$in0,$outperm # rotate
+ vsel $stage,$outhead,$outtail,$outmask
+ vmr $outhead,$outtail
+ stvx $stage,0,$out
+ addi $inp,$out,15 # 15 is not typo
+ addi $out,$out,16
+ bdz Ldone
+
+ vspltw $key,$in0,3 # just splat
+ vsldoi $tmp,$zero,$in1,12 # >>32
+ vsbox $key,$key
+
+ vxor $in1,$in1,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in1,$in1,$tmp
+ vsldoi $tmp,$zero,$tmp,12 # >>32
+ vxor $in1,$in1,$tmp
+
+ vxor $in1,$in1,$key
+ b Loop256
+
+.align 4
+Ldone:
+ lvx $in1,0,$inp # redundant in aligned case
+ vsel $in1,$outhead,$in1,$outmask
+ stvx $in1,0,$inp
+ li $ptr,0
+ mtspr 256,$vrsave
+ stw $rounds,0($out)
+
+Lenc_key_abort:
+ mr r3,$ptr
+ blr
+ .long 0
+ .byte 0,12,0x14,1,0,0,3,0
+ .long 0
+.size .${prefix}_set_encrypt_key,.-.${prefix}_set_encrypt_key
+
+.globl .${prefix}_set_decrypt_key
+ $STU $sp,-$FRAME($sp)
+ mflr r10
+ $PUSH r10,$FRAME+$LRSAVE($sp)
+ bl Lset_encrypt_key
+ mtlr r10
+
+ cmpwi r3,0
+ bne- Ldec_key_abort
+
+ slwi $cnt,$rounds,4
+ subi $inp,$out,240 # first round key
+ srwi $rounds,$rounds,1
+ add $out,$inp,$cnt # last round key
+ mtctr $rounds
+
+Ldeckey:
+ lwz r0, 0($inp)
+ lwz r6, 4($inp)
+ lwz r7, 8($inp)
+ lwz r8, 12($inp)
+ addi $inp,$inp,16
+ lwz r9, 0($out)
+ lwz r10,4($out)
+ lwz r11,8($out)
+ lwz r12,12($out)
+ stw r0, 0($out)
+ stw r6, 4($out)
+ stw r7, 8($out)
+ stw r8, 12($out)
+ subi $out,$out,16
+ stw r9, -16($inp)
+ stw r10,-12($inp)
+ stw r11,-8($inp)
+ stw r12,-4($inp)
+ bdnz Ldeckey
+
+ xor r3,r3,r3 # return value
+Ldec_key_abort:
+ addi $sp,$sp,$FRAME
+ blr
+ .long 0
+ .byte 0,12,4,1,0x80,0,3,0
+ .long 0
+.size .${prefix}_set_decrypt_key,.-.${prefix}_set_decrypt_key
+___
+}}}
+#########################################################################
+{{{ # Single block en- and decrypt procedures #
+sub gen_block () {
+my $dir = shift;
+my $n = $dir eq "de" ? "n" : "";
+my ($inp,$out,$key,$rounds,$idx)=map("r$_",(3..7));
+
+$code.=<<___;
+.globl .${prefix}_${dir}crypt
+ lwz $rounds,240($key)
+ lis r0,0xfc00
+ mfspr $vrsave,256
+ li $idx,15 # 15 is not typo
+ mtspr 256,r0
+
+ lvx v0,0,$inp
+ neg r11,$out
+ lvx v1,$idx,$inp
+ lvsl v2,0,$inp # inpperm
+ le?vspltisb v4,0x0f
+ ?lvsl v3,0,r11 # outperm
+ le?vxor v2,v2,v4
+ li $idx,16
+ vperm v0,v0,v1,v2 # align [and byte swap in LE]
+ lvx v1,0,$key
+ ?lvsl v5,0,$key # keyperm
+ srwi $rounds,$rounds,1
+ lvx v2,$idx,$key
+ addi $idx,$idx,16
+ subi $rounds,$rounds,1
+ ?vperm v1,v1,v2,v5 # align round key
+
+ vxor v0,v0,v1
+ lvx v1,$idx,$key
+ addi $idx,$idx,16
+ mtctr $rounds
+
+Loop_${dir}c:
+ ?vperm v2,v2,v1,v5
+ v${n}cipher v0,v0,v2
+ lvx v2,$idx,$key
+ addi $idx,$idx,16
+ ?vperm v1,v1,v2,v5
+ v${n}cipher v0,v0,v1
+ lvx v1,$idx,$key
+ addi $idx,$idx,16
+ bdnz Loop_${dir}c
+
+ ?vperm v2,v2,v1,v5
+ v${n}cipher v0,v0,v2
+ lvx v2,$idx,$key
+ ?vperm v1,v1,v2,v5
+ v${n}cipherlast v0,v0,v1
+
+ vspltisb v2,-1
+ vxor v1,v1,v1
+ li $idx,15 # 15 is not typo
+ ?vperm v2,v1,v2,v3 # outmask
+ le?vxor v3,v3,v4
+ lvx v1,0,$out # outhead
+ vperm v0,v0,v0,v3 # rotate [and byte swap in LE]
+ vsel v1,v1,v0,v2
+ lvx v4,$idx,$out
+ stvx v1,0,$out
+ vsel v0,v0,v4,v2
+ stvx v0,$idx,$out
+
+ mtspr 256,$vrsave
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,3,0
+ .long 0
+.size .${prefix}_${dir}crypt,.-.${prefix}_${dir}crypt
+___
+}
+&gen_block("en");
+&gen_block("de");
+}}}
+#########################################################################
+{{{ # CBC en- and decrypt procedures #
+my ($inp,$out,$len,$key,$ivp,$enc,$rounds,$idx)=map("r$_",(3..10));
+my ($rndkey0,$rndkey1,$inout,$tmp)= map("v$_",(0..3));
+my ($ivec,$inptail,$inpperm,$outhead,$outperm,$outmask,$keyperm)=
+ map("v$_",(4..10));
+$code.=<<___;
+.globl .${prefix}_cbc_encrypt
+ ${UCMP}i $len,16
+ bltlr-
+
+ cmpwi $enc,0 # test direction
+ lis r0,0xffe0
+ mfspr $vrsave,256
+ mtspr 256,r0
+
+ li $idx,15
+ vxor $rndkey0,$rndkey0,$rndkey0
+ le?vspltisb $tmp,0x0f
+
+ lvx $ivec,0,$ivp # load [unaligned] iv
+ lvsl $inpperm,0,$ivp
+ lvx $inptail,$idx,$ivp
+ le?vxor $inpperm,$inpperm,$tmp
+ vperm $ivec,$ivec,$inptail,$inpperm
+
+ neg r11,$inp
+ ?lvsl $keyperm,0,$key # prepare for unaligned key
+ lwz $rounds,240($key)
+
+ lvsr $inpperm,0,r11 # prepare for unaligned load
+ lvx $inptail,0,$inp
+ addi $inp,$inp,15 # 15 is not typo
+ le?vxor $inpperm,$inpperm,$tmp
+
+ ?lvsr $outperm,0,$out # prepare for unaligned store
+ vspltisb $outmask,-1
+ lvx $outhead,0,$out
+ ?vperm $outmask,$rndkey0,$outmask,$outperm
+ le?vxor $outperm,$outperm,$tmp
+
+ srwi $rounds,$rounds,1
+ li $idx,16
+ subi $rounds,$rounds,1
+ beq Lcbc_dec
+
+Lcbc_enc:
+ vmr $inout,$inptail
+ lvx $inptail,0,$inp
+ addi $inp,$inp,16
+ mtctr $rounds
+ subi $len,$len,16 # len-=16
+
+ lvx $rndkey0,0,$key
+ vperm $inout,$inout,$inptail,$inpperm
+ lvx $rndkey1,$idx,$key
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key
+ addi $idx,$idx,16
+ vxor $inout,$inout,$ivec
+
+Loop_cbc_enc:
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vcipher $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key
+ addi $idx,$idx,16
+ bdnz Loop_cbc_enc
+
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key
+ li $idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vcipherlast $ivec,$inout,$rndkey0
+ ${UCMP}i $len,16
+
+ vperm $tmp,$ivec,$ivec,$outperm
+ vsel $inout,$outhead,$tmp,$outmask
+ vmr $outhead,$tmp
+ stvx $inout,0,$out
+ addi $out,$out,16
+ bge Lcbc_enc
+
+ b Lcbc_done
+
+.align 4
+Lcbc_dec:
+ ${UCMP}i $len,128
+ bge _aesp8_cbc_decrypt8x
+ vmr $tmp,$inptail
+ lvx $inptail,0,$inp
+ addi $inp,$inp,16
+ mtctr $rounds
+ subi $len,$len,16 # len-=16
+
+ lvx $rndkey0,0,$key
+ vperm $tmp,$tmp,$inptail,$inpperm
+ lvx $rndkey1,$idx,$key
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $inout,$tmp,$rndkey0
+ lvx $rndkey0,$idx,$key
+ addi $idx,$idx,16
+
+Loop_cbc_dec:
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vncipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vncipher $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key
+ addi $idx,$idx,16
+ bdnz Loop_cbc_dec
+
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vncipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key
+ li $idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vncipherlast $inout,$inout,$rndkey0
+ ${UCMP}i $len,16
+
+ vxor $inout,$inout,$ivec
+ vmr $ivec,$tmp
+ vperm $tmp,$inout,$inout,$outperm
+ vsel $inout,$outhead,$tmp,$outmask
+ vmr $outhead,$tmp
+ stvx $inout,0,$out
+ addi $out,$out,16
+ bge Lcbc_dec
+
+Lcbc_done:
+ addi $out,$out,-1
+ lvx $inout,0,$out # redundant in aligned case
+ vsel $inout,$outhead,$inout,$outmask
+ stvx $inout,0,$out
+
+ neg $enc,$ivp # write [unaligned] iv
+ li $idx,15 # 15 is not typo
+ vxor $rndkey0,$rndkey0,$rndkey0
+ vspltisb $outmask,-1
+ le?vspltisb $tmp,0x0f
+ ?lvsl $outperm,0,$enc
+ ?vperm $outmask,$rndkey0,$outmask,$outperm
+ le?vxor $outperm,$outperm,$tmp
+ lvx $outhead,0,$ivp
+ vperm $ivec,$ivec,$ivec,$outperm
+ vsel $inout,$outhead,$ivec,$outmask
+ lvx $inptail,$idx,$ivp
+ stvx $inout,0,$ivp
+ vsel $inout,$ivec,$inptail,$outmask
+ stvx $inout,$idx,$ivp
+
+ mtspr 256,$vrsave
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,6,0
+ .long 0
+___
+#########################################################################
+{{ # Optimized CBC decrypt procedure #
+my $key_="r11";
+my ($x00,$x10,$x20,$x30,$x40,$x50,$x60,$x70)=map("r$_",(0,8,26..31));
+my ($in0, $in1, $in2, $in3, $in4, $in5, $in6, $in7 )=map("v$_",(0..3,10..13));
+my ($out0,$out1,$out2,$out3,$out4,$out5,$out6,$out7)=map("v$_",(14..21));
+my $rndkey0="v23"; # v24-v25 rotating buffer for first found keys
+ # v26-v31 last 6 round keys
+my ($tmp,$keyperm)=($in3,$in4); # aliases with "caller", redundant assignment
+
+$code.=<<___;
+.align 5
+_aesp8_cbc_decrypt8x:
+ $STU $sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+ li r10,`$FRAME+8*16+15`
+ li r11,`$FRAME+8*16+31`
+ stvx v20,r10,$sp # ABI says so
+ addi r10,r10,32
+ stvx v21,r11,$sp
+ addi r11,r11,32
+ stvx v22,r10,$sp
+ addi r10,r10,32
+ stvx v23,r11,$sp
+ addi r11,r11,32
+ stvx v24,r10,$sp
+ addi r10,r10,32
+ stvx v25,r11,$sp
+ addi r11,r11,32
+ stvx v26,r10,$sp
+ addi r10,r10,32
+ stvx v27,r11,$sp
+ addi r11,r11,32
+ stvx v28,r10,$sp
+ addi r10,r10,32
+ stvx v29,r11,$sp
+ addi r11,r11,32
+ stvx v30,r10,$sp
+ stvx v31,r11,$sp
+ li r0,-1
+ stw $vrsave,`$FRAME+21*16-4`($sp) # save vrsave
+ li $x10,0x10
+ $PUSH r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+ li $x20,0x20
+ $PUSH r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+ li $x30,0x30
+ $PUSH r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+ li $x40,0x40
+ $PUSH r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+ li $x50,0x50
+ $PUSH r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+ li $x60,0x60
+ $PUSH r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+ li $x70,0x70
+ mtspr 256,r0
+
+ subi $rounds,$rounds,3 # -4 in total
+ subi $len,$len,128 # bias
+
+ lvx $rndkey0,$x00,$key # load key schedule
+ lvx v30,$x10,$key
+ addi $key,$key,0x20
+ lvx v31,$x00,$key
+ ?vperm $rndkey0,$rndkey0,v30,$keyperm
+ addi $key_,$sp,$FRAME+15
+ mtctr $rounds
+
+Load_cbc_dec_key:
+ ?vperm v24,v30,v31,$keyperm
+ lvx v30,$x10,$key
+ addi $key,$key,0x20
+ stvx v24,$x00,$key_ # off-load round[1]
+ ?vperm v25,v31,v30,$keyperm
+ lvx v31,$x00,$key
+ stvx v25,$x10,$key_ # off-load round[2]
+ addi $key_,$key_,0x20
+ bdnz Load_cbc_dec_key
+
+ lvx v26,$x10,$key
+ ?vperm v24,v30,v31,$keyperm
+ lvx v27,$x20,$key
+ stvx v24,$x00,$key_ # off-load round[3]
+ ?vperm v25,v31,v26,$keyperm
+ lvx v28,$x30,$key
+ stvx v25,$x10,$key_ # off-load round[4]
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ ?vperm v26,v26,v27,$keyperm
+ lvx v29,$x40,$key
+ ?vperm v27,v27,v28,$keyperm
+ lvx v30,$x50,$key
+ ?vperm v28,v28,v29,$keyperm
+ lvx v31,$x60,$key
+ ?vperm v29,v29,v30,$keyperm
+ lvx $out0,$x70,$key # borrow $out0
+ ?vperm v30,v30,v31,$keyperm
+ lvx v24,$x00,$key_ # pre-load round[1]
+ ?vperm v31,v31,$out0,$keyperm
+ lvx v25,$x10,$key_ # pre-load round[2]
+
+ #lvx $inptail,0,$inp # "caller" already did this
+ #addi $inp,$inp,15 # 15 is not typo
+ subi $inp,$inp,15 # undo "caller"
+
+ le?li $idx,8
+ lvx_u $in0,$x00,$inp # load first 8 "words"
+ le?lvsl $inpperm,0,$idx
+ le?vspltisb $tmp,0x0f
+ lvx_u $in1,$x10,$inp
+ le?vxor $inpperm,$inpperm,$tmp # transform for lvx_u/stvx_u
+ lvx_u $in2,$x20,$inp
+ le?vperm $in0,$in0,$in0,$inpperm
+ lvx_u $in3,$x30,$inp
+ le?vperm $in1,$in1,$in1,$inpperm
+ lvx_u $in4,$x40,$inp
+ le?vperm $in2,$in2,$in2,$inpperm
+ vxor $out0,$in0,$rndkey0
+ lvx_u $in5,$x50,$inp
+ le?vperm $in3,$in3,$in3,$inpperm
+ vxor $out1,$in1,$rndkey0
+ lvx_u $in6,$x60,$inp
+ le?vperm $in4,$in4,$in4,$inpperm
+ vxor $out2,$in2,$rndkey0
+ lvx_u $in7,$x70,$inp
+ addi $inp,$inp,0x80
+ le?vperm $in5,$in5,$in5,$inpperm
+ vxor $out3,$in3,$rndkey0
+ le?vperm $in6,$in6,$in6,$inpperm
+ vxor $out4,$in4,$rndkey0
+ le?vperm $in7,$in7,$in7,$inpperm
+ vxor $out5,$in5,$rndkey0
+ vxor $out6,$in6,$rndkey0
+ vxor $out7,$in7,$rndkey0
+
+ mtctr $rounds
+ b Loop_cbc_dec8x
+.align 5
+Loop_cbc_dec8x:
+ vncipher $out0,$out0,v24
+ vncipher $out1,$out1,v24
+ vncipher $out2,$out2,v24
+ vncipher $out3,$out3,v24
+ vncipher $out4,$out4,v24
+ vncipher $out5,$out5,v24
+ vncipher $out6,$out6,v24
+ vncipher $out7,$out7,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vncipher $out0,$out0,v25
+ vncipher $out1,$out1,v25
+ vncipher $out2,$out2,v25
+ vncipher $out3,$out3,v25
+ vncipher $out4,$out4,v25
+ vncipher $out5,$out5,v25
+ vncipher $out6,$out6,v25
+ vncipher $out7,$out7,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz Loop_cbc_dec8x
+
+ subic $len,$len,128 # $len-=128
+ vncipher $out0,$out0,v24
+ vncipher $out1,$out1,v24
+ vncipher $out2,$out2,v24
+ vncipher $out3,$out3,v24
+ vncipher $out4,$out4,v24
+ vncipher $out5,$out5,v24
+ vncipher $out6,$out6,v24
+ vncipher $out7,$out7,v24
+
+ subfe. r0,r0,r0 # borrow?-1:0
+ vncipher $out0,$out0,v25
+ vncipher $out1,$out1,v25
+ vncipher $out2,$out2,v25
+ vncipher $out3,$out3,v25
+ vncipher $out4,$out4,v25
+ vncipher $out5,$out5,v25
+ vncipher $out6,$out6,v25
+ vncipher $out7,$out7,v25
+
+ and r0,r0,$len
+ vncipher $out0,$out0,v26
+ vncipher $out1,$out1,v26
+ vncipher $out2,$out2,v26
+ vncipher $out3,$out3,v26
+ vncipher $out4,$out4,v26
+ vncipher $out5,$out5,v26
+ vncipher $out6,$out6,v26
+ vncipher $out7,$out7,v26
+
+ add $inp,$inp,r0 # $inp is adjusted in such
+ # way that at exit from the
+ # loop inX-in7 are loaded
+ # with last "words"
+ vncipher $out0,$out0,v27
+ vncipher $out1,$out1,v27
+ vncipher $out2,$out2,v27
+ vncipher $out3,$out3,v27
+ vncipher $out4,$out4,v27
+ vncipher $out5,$out5,v27
+ vncipher $out6,$out6,v27
+ vncipher $out7,$out7,v27
+
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ vncipher $out0,$out0,v28
+ vncipher $out1,$out1,v28
+ vncipher $out2,$out2,v28
+ vncipher $out3,$out3,v28
+ vncipher $out4,$out4,v28
+ vncipher $out5,$out5,v28
+ vncipher $out6,$out6,v28
+ vncipher $out7,$out7,v28
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+
+ vncipher $out0,$out0,v29
+ vncipher $out1,$out1,v29
+ vncipher $out2,$out2,v29
+ vncipher $out3,$out3,v29
+ vncipher $out4,$out4,v29
+ vncipher $out5,$out5,v29
+ vncipher $out6,$out6,v29
+ vncipher $out7,$out7,v29
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+
+ vncipher $out0,$out0,v30
+ vxor $ivec,$ivec,v31 # xor with last round key
+ vncipher $out1,$out1,v30
+ vxor $in0,$in0,v31
+ vncipher $out2,$out2,v30
+ vxor $in1,$in1,v31
+ vncipher $out3,$out3,v30
+ vxor $in2,$in2,v31
+ vncipher $out4,$out4,v30
+ vxor $in3,$in3,v31
+ vncipher $out5,$out5,v30
+ vxor $in4,$in4,v31
+ vncipher $out6,$out6,v30
+ vxor $in5,$in5,v31
+ vncipher $out7,$out7,v30
+ vxor $in6,$in6,v31
+
+ vncipherlast $out0,$out0,$ivec
+ vncipherlast $out1,$out1,$in0
+ lvx_u $in0,$x00,$inp # load next input block
+ vncipherlast $out2,$out2,$in1
+ lvx_u $in1,$x10,$inp
+ vncipherlast $out3,$out3,$in2
+ le?vperm $in0,$in0,$in0,$inpperm
+ lvx_u $in2,$x20,$inp
+ vncipherlast $out4,$out4,$in3
+ le?vperm $in1,$in1,$in1,$inpperm
+ lvx_u $in3,$x30,$inp
+ vncipherlast $out5,$out5,$in4
+ le?vperm $in2,$in2,$in2,$inpperm
+ lvx_u $in4,$x40,$inp
+ vncipherlast $out6,$out6,$in5
+ le?vperm $in3,$in3,$in3,$inpperm
+ lvx_u $in5,$x50,$inp
+ vncipherlast $out7,$out7,$in6
+ le?vperm $in4,$in4,$in4,$inpperm
+ lvx_u $in6,$x60,$inp
+ vmr $ivec,$in7
+ le?vperm $in5,$in5,$in5,$inpperm
+ lvx_u $in7,$x70,$inp
+ addi $inp,$inp,0x80
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ le?vperm $out1,$out1,$out1,$inpperm
+ stvx_u $out0,$x00,$out
+ le?vperm $in6,$in6,$in6,$inpperm
+ vxor $out0,$in0,$rndkey0
+ le?vperm $out2,$out2,$out2,$inpperm
+ stvx_u $out1,$x10,$out
+ le?vperm $in7,$in7,$in7,$inpperm
+ vxor $out1,$in1,$rndkey0
+ le?vperm $out3,$out3,$out3,$inpperm
+ stvx_u $out2,$x20,$out
+ vxor $out2,$in2,$rndkey0
+ le?vperm $out4,$out4,$out4,$inpperm
+ stvx_u $out3,$x30,$out
+ vxor $out3,$in3,$rndkey0
+ le?vperm $out5,$out5,$out5,$inpperm
+ stvx_u $out4,$x40,$out
+ vxor $out4,$in4,$rndkey0
+ le?vperm $out6,$out6,$out6,$inpperm
+ stvx_u $out5,$x50,$out
+ vxor $out5,$in5,$rndkey0
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out6,$x60,$out
+ vxor $out6,$in6,$rndkey0
+ stvx_u $out7,$x70,$out
+ addi $out,$out,0x80
+ vxor $out7,$in7,$rndkey0
+
+ mtctr $rounds
+ beq Loop_cbc_dec8x # did $len-=128 borrow?
+
+ addic. $len,$len,128
+ beq Lcbc_dec8x_done
+ nop
+ nop
+
+Loop_cbc_dec8x_tail: # up to 7 "words" tail...
+ vncipher $out1,$out1,v24
+ vncipher $out2,$out2,v24
+ vncipher $out3,$out3,v24
+ vncipher $out4,$out4,v24
+ vncipher $out5,$out5,v24
+ vncipher $out6,$out6,v24
+ vncipher $out7,$out7,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vncipher $out1,$out1,v25
+ vncipher $out2,$out2,v25
+ vncipher $out3,$out3,v25
+ vncipher $out4,$out4,v25
+ vncipher $out5,$out5,v25
+ vncipher $out6,$out6,v25
+ vncipher $out7,$out7,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz Loop_cbc_dec8x_tail
+
+ vncipher $out1,$out1,v24
+ vncipher $out2,$out2,v24
+ vncipher $out3,$out3,v24
+ vncipher $out4,$out4,v24
+ vncipher $out5,$out5,v24
+ vncipher $out6,$out6,v24
+ vncipher $out7,$out7,v24
+
+ vncipher $out1,$out1,v25
+ vncipher $out2,$out2,v25
+ vncipher $out3,$out3,v25
+ vncipher $out4,$out4,v25
+ vncipher $out5,$out5,v25
+ vncipher $out6,$out6,v25
+ vncipher $out7,$out7,v25
+
+ vncipher $out1,$out1,v26
+ vncipher $out2,$out2,v26
+ vncipher $out3,$out3,v26
+ vncipher $out4,$out4,v26
+ vncipher $out5,$out5,v26
+ vncipher $out6,$out6,v26
+ vncipher $out7,$out7,v26
+
+ vncipher $out1,$out1,v27
+ vncipher $out2,$out2,v27
+ vncipher $out3,$out3,v27
+ vncipher $out4,$out4,v27
+ vncipher $out5,$out5,v27
+ vncipher $out6,$out6,v27
+ vncipher $out7,$out7,v27
+
+ vncipher $out1,$out1,v28
+ vncipher $out2,$out2,v28
+ vncipher $out3,$out3,v28
+ vncipher $out4,$out4,v28
+ vncipher $out5,$out5,v28
+ vncipher $out6,$out6,v28
+ vncipher $out7,$out7,v28
+
+ vncipher $out1,$out1,v29
+ vncipher $out2,$out2,v29
+ vncipher $out3,$out3,v29
+ vncipher $out4,$out4,v29
+ vncipher $out5,$out5,v29
+ vncipher $out6,$out6,v29
+ vncipher $out7,$out7,v29
+
+ vncipher $out1,$out1,v30
+ vxor $ivec,$ivec,v31 # last round key
+ vncipher $out2,$out2,v30
+ vxor $in1,$in1,v31
+ vncipher $out3,$out3,v30
+ vxor $in2,$in2,v31
+ vncipher $out4,$out4,v30
+ vxor $in3,$in3,v31
+ vncipher $out5,$out5,v30
+ vxor $in4,$in4,v31
+ vncipher $out6,$out6,v30
+ vxor $in5,$in5,v31
+ vncipher $out7,$out7,v30
+ vxor $in6,$in6,v31
+
+ cmplwi $len,32 # switch($len)
+ blt Lcbc_dec8x_one
+ nop
+ beq Lcbc_dec8x_two
+ cmplwi $len,64
+ blt Lcbc_dec8x_three
+ nop
+ beq Lcbc_dec8x_four
+ cmplwi $len,96
+ blt Lcbc_dec8x_five
+ nop
+ beq Lcbc_dec8x_six
+
+Lcbc_dec8x_seven:
+ vncipherlast $out1,$out1,$ivec
+ vncipherlast $out2,$out2,$in1
+ vncipherlast $out3,$out3,$in2
+ vncipherlast $out4,$out4,$in3
+ vncipherlast $out5,$out5,$in4
+ vncipherlast $out6,$out6,$in5
+ vncipherlast $out7,$out7,$in6
+ vmr $ivec,$in7
+
+ le?vperm $out1,$out1,$out1,$inpperm
+ le?vperm $out2,$out2,$out2,$inpperm
+ stvx_u $out1,$x00,$out
+ le?vperm $out3,$out3,$out3,$inpperm
+ stvx_u $out2,$x10,$out
+ le?vperm $out4,$out4,$out4,$inpperm
+ stvx_u $out3,$x20,$out
+ le?vperm $out5,$out5,$out5,$inpperm
+ stvx_u $out4,$x30,$out
+ le?vperm $out6,$out6,$out6,$inpperm
+ stvx_u $out5,$x40,$out
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out6,$x50,$out
+ stvx_u $out7,$x60,$out
+ addi $out,$out,0x70
+ b Lcbc_dec8x_done
+
+.align 5
+Lcbc_dec8x_six:
+ vncipherlast $out2,$out2,$ivec
+ vncipherlast $out3,$out3,$in2
+ vncipherlast $out4,$out4,$in3
+ vncipherlast $out5,$out5,$in4
+ vncipherlast $out6,$out6,$in5
+ vncipherlast $out7,$out7,$in6
+ vmr $ivec,$in7
+
+ le?vperm $out2,$out2,$out2,$inpperm
+ le?vperm $out3,$out3,$out3,$inpperm
+ stvx_u $out2,$x00,$out
+ le?vperm $out4,$out4,$out4,$inpperm
+ stvx_u $out3,$x10,$out
+ le?vperm $out5,$out5,$out5,$inpperm
+ stvx_u $out4,$x20,$out
+ le?vperm $out6,$out6,$out6,$inpperm
+ stvx_u $out5,$x30,$out
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out6,$x40,$out
+ stvx_u $out7,$x50,$out
+ addi $out,$out,0x60
+ b Lcbc_dec8x_done
+
+.align 5
+Lcbc_dec8x_five:
+ vncipherlast $out3,$out3,$ivec
+ vncipherlast $out4,$out4,$in3
+ vncipherlast $out5,$out5,$in4
+ vncipherlast $out6,$out6,$in5
+ vncipherlast $out7,$out7,$in6
+ vmr $ivec,$in7
+
+ le?vperm $out3,$out3,$out3,$inpperm
+ le?vperm $out4,$out4,$out4,$inpperm
+ stvx_u $out3,$x00,$out
+ le?vperm $out5,$out5,$out5,$inpperm
+ stvx_u $out4,$x10,$out
+ le?vperm $out6,$out6,$out6,$inpperm
+ stvx_u $out5,$x20,$out
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out6,$x30,$out
+ stvx_u $out7,$x40,$out
+ addi $out,$out,0x50
+ b Lcbc_dec8x_done
+
+.align 5
+Lcbc_dec8x_four:
+ vncipherlast $out4,$out4,$ivec
+ vncipherlast $out5,$out5,$in4
+ vncipherlast $out6,$out6,$in5
+ vncipherlast $out7,$out7,$in6
+ vmr $ivec,$in7
+
+ le?vperm $out4,$out4,$out4,$inpperm
+ le?vperm $out5,$out5,$out5,$inpperm
+ stvx_u $out4,$x00,$out
+ le?vperm $out6,$out6,$out6,$inpperm
+ stvx_u $out5,$x10,$out
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out6,$x20,$out
+ stvx_u $out7,$x30,$out
+ addi $out,$out,0x40
+ b Lcbc_dec8x_done
+
+.align 5
+Lcbc_dec8x_three:
+ vncipherlast $out5,$out5,$ivec
+ vncipherlast $out6,$out6,$in5
+ vncipherlast $out7,$out7,$in6
+ vmr $ivec,$in7
+
+ le?vperm $out5,$out5,$out5,$inpperm
+ le?vperm $out6,$out6,$out6,$inpperm
+ stvx_u $out5,$x00,$out
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out6,$x10,$out
+ stvx_u $out7,$x20,$out
+ addi $out,$out,0x30
+ b Lcbc_dec8x_done
+
+.align 5
+Lcbc_dec8x_two:
+ vncipherlast $out6,$out6,$ivec
+ vncipherlast $out7,$out7,$in6
+ vmr $ivec,$in7
+
+ le?vperm $out6,$out6,$out6,$inpperm
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out6,$x00,$out
+ stvx_u $out7,$x10,$out
+ addi $out,$out,0x20
+ b Lcbc_dec8x_done
+
+.align 5
+Lcbc_dec8x_one:
+ vncipherlast $out7,$out7,$ivec
+ vmr $ivec,$in7
+
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out7,0,$out
+ addi $out,$out,0x10
+
+Lcbc_dec8x_done:
+ le?vperm $ivec,$ivec,$ivec,$inpperm
+ stvx_u $ivec,0,$ivp # write [unaligned] iv
+
+ li r10,`$FRAME+15`
+ li r11,`$FRAME+31`
+ stvx $inpperm,r10,$sp # wipe copies of round keys
+ addi r10,r10,32
+ stvx $inpperm,r11,$sp
+ addi r11,r11,32
+ stvx $inpperm,r10,$sp
+ addi r10,r10,32
+ stvx $inpperm,r11,$sp
+ addi r11,r11,32
+ stvx $inpperm,r10,$sp
+ addi r10,r10,32
+ stvx $inpperm,r11,$sp
+ addi r11,r11,32
+ stvx $inpperm,r10,$sp
+ addi r10,r10,32
+ stvx $inpperm,r11,$sp
+ addi r11,r11,32
+
+ mtspr 256,$vrsave
+ lvx v20,r10,$sp # ABI says so
+ addi r10,r10,32
+ lvx v21,r11,$sp
+ addi r11,r11,32
+ lvx v22,r10,$sp
+ addi r10,r10,32
+ lvx v23,r11,$sp
+ addi r11,r11,32
+ lvx v24,r10,$sp
+ addi r10,r10,32
+ lvx v25,r11,$sp
+ addi r11,r11,32
+ lvx v26,r10,$sp
+ addi r10,r10,32
+ lvx v27,r11,$sp
+ addi r11,r11,32
+ lvx v28,r10,$sp
+ addi r10,r10,32
+ lvx v29,r11,$sp
+ addi r11,r11,32
+ lvx v30,r10,$sp
+ lvx v31,r11,$sp
+ $POP r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+ $POP r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+ $POP r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+ $POP r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+ $POP r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+ $POP r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+ addi $sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0x80,6,6,0
+ .long 0
+.size .${prefix}_cbc_encrypt,.-.${prefix}_cbc_encrypt
+___
+}} }}}
+
+#########################################################################
+{{{ # CTR procedure[s] #
+
+####################### WARNING: Here be dragons! #######################
+#
+# This code is written as 'ctr32', based on a 32-bit counter used
+# upstream. The kernel does *not* use a 32-bit counter. The kernel uses
+# a 128-bit counter.
+#
+# This leads to subtle changes from the upstream code: the counter
+# is incremented with vaddu_q_m rather than vaddu_w_m. This occurs in
+# both the bulk (8 blocks at a time) path, and in the individual block
+# path. Be aware of this when doing updates.
+#
+# See:
+# 1d4aa0b4c181 ("crypto: vmx - Fixing AES-CTR counter bug")
+# 009b30ac7444 ("crypto: vmx - CTR: always increment IV as quadword")
+# https://github.com/openssl/openssl/pull/8942
+#
+#########################################################################
+my ($inp,$out,$len,$key,$ivp,$x10,$rounds,$idx)=map("r$_",(3..10));
+my ($rndkey0,$rndkey1,$inout,$tmp)= map("v$_",(0..3));
+my ($ivec,$inptail,$inpperm,$outhead,$outperm,$outmask,$keyperm,$one)=
+ map("v$_",(4..11));
+my $dat=$tmp;
+
+$code.=<<___;
+.globl .${prefix}_ctr32_encrypt_blocks
+ ${UCMP}i $len,1
+ bltlr-
+
+ lis r0,0xfff0
+ mfspr $vrsave,256
+ mtspr 256,r0
+
+ li $idx,15
+ vxor $rndkey0,$rndkey0,$rndkey0
+ le?vspltisb $tmp,0x0f
+
+ lvx $ivec,0,$ivp # load [unaligned] iv
+ lvsl $inpperm,0,$ivp
+ lvx $inptail,$idx,$ivp
+ vspltisb $one,1
+ le?vxor $inpperm,$inpperm,$tmp
+ vperm $ivec,$ivec,$inptail,$inpperm
+ vsldoi $one,$rndkey0,$one,1
+
+ neg r11,$inp
+ ?lvsl $keyperm,0,$key # prepare for unaligned key
+ lwz $rounds,240($key)
+
+ lvsr $inpperm,0,r11 # prepare for unaligned load
+ lvx $inptail,0,$inp
+ addi $inp,$inp,15 # 15 is not typo
+ le?vxor $inpperm,$inpperm,$tmp
+
+ srwi $rounds,$rounds,1
+ li $idx,16
+ subi $rounds,$rounds,1
+
+ ${UCMP}i $len,8
+ bge _aesp8_ctr32_encrypt8x
+
+ ?lvsr $outperm,0,$out # prepare for unaligned store
+ vspltisb $outmask,-1
+ lvx $outhead,0,$out
+ ?vperm $outmask,$rndkey0,$outmask,$outperm
+ le?vxor $outperm,$outperm,$tmp
+
+ lvx $rndkey0,0,$key
+ mtctr $rounds
+ lvx $rndkey1,$idx,$key
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $inout,$ivec,$rndkey0
+ lvx $rndkey0,$idx,$key
+ addi $idx,$idx,16
+ b Loop_ctr32_enc
+
+.align 5
+Loop_ctr32_enc:
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vcipher $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key
+ addi $idx,$idx,16
+ bdnz Loop_ctr32_enc
+
+ vadduqm $ivec,$ivec,$one # Kernel change for 128-bit
+ vmr $dat,$inptail
+ lvx $inptail,0,$inp
+ addi $inp,$inp,16
+ subic. $len,$len,1 # blocks--
+
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key
+ vperm $dat,$dat,$inptail,$inpperm
+ li $idx,16
+ ?vperm $rndkey1,$rndkey0,$rndkey1,$keyperm
+ lvx $rndkey0,0,$key
+ vxor $dat,$dat,$rndkey1 # last round key
+ vcipherlast $inout,$inout,$dat
+
+ lvx $rndkey1,$idx,$key
+ addi $idx,$idx,16
+ vperm $inout,$inout,$inout,$outperm
+ vsel $dat,$outhead,$inout,$outmask
+ mtctr $rounds
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vmr $outhead,$inout
+ vxor $inout,$ivec,$rndkey0
+ lvx $rndkey0,$idx,$key
+ addi $idx,$idx,16
+ stvx $dat,0,$out
+ addi $out,$out,16
+ bne Loop_ctr32_enc
+
+ addi $out,$out,-1
+ lvx $inout,0,$out # redundant in aligned case
+ vsel $inout,$outhead,$inout,$outmask
+ stvx $inout,0,$out
+
+ mtspr 256,$vrsave
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,6,0
+ .long 0
+___
+#########################################################################
+{{ # Optimized CTR procedure #
+my $key_="r11";
+my ($x00,$x10,$x20,$x30,$x40,$x50,$x60,$x70)=map("r$_",(0,8,26..31));
+my ($in0, $in1, $in2, $in3, $in4, $in5, $in6, $in7 )=map("v$_",(0..3,10,12..14));
+my ($out0,$out1,$out2,$out3,$out4,$out5,$out6,$out7)=map("v$_",(15..22));
+my $rndkey0="v23"; # v24-v25 rotating buffer for first found keys
+ # v26-v31 last 6 round keys
+my ($tmp,$keyperm)=($in3,$in4); # aliases with "caller", redundant assignment
+my ($two,$three,$four)=($outhead,$outperm,$outmask);
+
+$code.=<<___;
+.align 5
+_aesp8_ctr32_encrypt8x:
+ $STU $sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+ li r10,`$FRAME+8*16+15`
+ li r11,`$FRAME+8*16+31`
+ stvx v20,r10,$sp # ABI says so
+ addi r10,r10,32
+ stvx v21,r11,$sp
+ addi r11,r11,32
+ stvx v22,r10,$sp
+ addi r10,r10,32
+ stvx v23,r11,$sp
+ addi r11,r11,32
+ stvx v24,r10,$sp
+ addi r10,r10,32
+ stvx v25,r11,$sp
+ addi r11,r11,32
+ stvx v26,r10,$sp
+ addi r10,r10,32
+ stvx v27,r11,$sp
+ addi r11,r11,32
+ stvx v28,r10,$sp
+ addi r10,r10,32
+ stvx v29,r11,$sp
+ addi r11,r11,32
+ stvx v30,r10,$sp
+ stvx v31,r11,$sp
+ li r0,-1
+ stw $vrsave,`$FRAME+21*16-4`($sp) # save vrsave
+ li $x10,0x10
+ $PUSH r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+ li $x20,0x20
+ $PUSH r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+ li $x30,0x30
+ $PUSH r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+ li $x40,0x40
+ $PUSH r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+ li $x50,0x50
+ $PUSH r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+ li $x60,0x60
+ $PUSH r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+ li $x70,0x70
+ mtspr 256,r0
+
+ subi $rounds,$rounds,3 # -4 in total
+
+ lvx $rndkey0,$x00,$key # load key schedule
+ lvx v30,$x10,$key
+ addi $key,$key,0x20
+ lvx v31,$x00,$key
+ ?vperm $rndkey0,$rndkey0,v30,$keyperm
+ addi $key_,$sp,$FRAME+15
+ mtctr $rounds
+
+Load_ctr32_enc_key:
+ ?vperm v24,v30,v31,$keyperm
+ lvx v30,$x10,$key
+ addi $key,$key,0x20
+ stvx v24,$x00,$key_ # off-load round[1]
+ ?vperm v25,v31,v30,$keyperm
+ lvx v31,$x00,$key
+ stvx v25,$x10,$key_ # off-load round[2]
+ addi $key_,$key_,0x20
+ bdnz Load_ctr32_enc_key
+
+ lvx v26,$x10,$key
+ ?vperm v24,v30,v31,$keyperm
+ lvx v27,$x20,$key
+ stvx v24,$x00,$key_ # off-load round[3]
+ ?vperm v25,v31,v26,$keyperm
+ lvx v28,$x30,$key
+ stvx v25,$x10,$key_ # off-load round[4]
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ ?vperm v26,v26,v27,$keyperm
+ lvx v29,$x40,$key
+ ?vperm v27,v27,v28,$keyperm
+ lvx v30,$x50,$key
+ ?vperm v28,v28,v29,$keyperm
+ lvx v31,$x60,$key
+ ?vperm v29,v29,v30,$keyperm
+ lvx $out0,$x70,$key # borrow $out0
+ ?vperm v30,v30,v31,$keyperm
+ lvx v24,$x00,$key_ # pre-load round[1]
+ ?vperm v31,v31,$out0,$keyperm
+ lvx v25,$x10,$key_ # pre-load round[2]
+
+ vadduqm $two,$one,$one
+ subi $inp,$inp,15 # undo "caller"
+ $SHL $len,$len,4
+
+ vadduqm $out1,$ivec,$one # counter values ...
+ vadduqm $out2,$ivec,$two # (do all ctr adds as 128-bit)
+ vxor $out0,$ivec,$rndkey0 # ... xored with rndkey[0]
+ le?li $idx,8
+ vadduqm $out3,$out1,$two
+ vxor $out1,$out1,$rndkey0
+ le?lvsl $inpperm,0,$idx
+ vadduqm $out4,$out2,$two
+ vxor $out2,$out2,$rndkey0
+ le?vspltisb $tmp,0x0f
+ vadduqm $out5,$out3,$two
+ vxor $out3,$out3,$rndkey0
+ le?vxor $inpperm,$inpperm,$tmp # transform for lvx_u/stvx_u
+ vadduqm $out6,$out4,$two
+ vxor $out4,$out4,$rndkey0
+ vadduqm $out7,$out5,$two
+ vxor $out5,$out5,$rndkey0
+ vadduqm $ivec,$out6,$two # next counter value
+ vxor $out6,$out6,$rndkey0
+ vxor $out7,$out7,$rndkey0
+
+ mtctr $rounds
+ b Loop_ctr32_enc8x
+.align 5
+Loop_ctr32_enc8x:
+ vcipher $out0,$out0,v24
+ vcipher $out1,$out1,v24
+ vcipher $out2,$out2,v24
+ vcipher $out3,$out3,v24
+ vcipher $out4,$out4,v24
+ vcipher $out5,$out5,v24
+ vcipher $out6,$out6,v24
+ vcipher $out7,$out7,v24
+Loop_ctr32_enc8x_middle:
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vcipher $out0,$out0,v25
+ vcipher $out1,$out1,v25
+ vcipher $out2,$out2,v25
+ vcipher $out3,$out3,v25
+ vcipher $out4,$out4,v25
+ vcipher $out5,$out5,v25
+ vcipher $out6,$out6,v25
+ vcipher $out7,$out7,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz Loop_ctr32_enc8x
+
+ subic r11,$len,256 # $len-256, borrow $key_
+ vcipher $out0,$out0,v24
+ vcipher $out1,$out1,v24
+ vcipher $out2,$out2,v24
+ vcipher $out3,$out3,v24
+ vcipher $out4,$out4,v24
+ vcipher $out5,$out5,v24
+ vcipher $out6,$out6,v24
+ vcipher $out7,$out7,v24
+
+ subfe r0,r0,r0 # borrow?-1:0
+ vcipher $out0,$out0,v25
+ vcipher $out1,$out1,v25
+ vcipher $out2,$out2,v25
+ vcipher $out3,$out3,v25
+ vcipher $out4,$out4,v25
+ vcipher $out5,$out5,v25
+ vcipher $out6,$out6,v25
+ vcipher $out7,$out7,v25
+
+ and r0,r0,r11
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ vcipher $out0,$out0,v26
+ vcipher $out1,$out1,v26
+ vcipher $out2,$out2,v26
+ vcipher $out3,$out3,v26
+ vcipher $out4,$out4,v26
+ vcipher $out5,$out5,v26
+ vcipher $out6,$out6,v26
+ vcipher $out7,$out7,v26
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+
+ subic $len,$len,129 # $len-=129
+ vcipher $out0,$out0,v27
+ addi $len,$len,1 # $len-=128 really
+ vcipher $out1,$out1,v27
+ vcipher $out2,$out2,v27
+ vcipher $out3,$out3,v27
+ vcipher $out4,$out4,v27
+ vcipher $out5,$out5,v27
+ vcipher $out6,$out6,v27
+ vcipher $out7,$out7,v27
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+
+ vcipher $out0,$out0,v28
+ lvx_u $in0,$x00,$inp # load input
+ vcipher $out1,$out1,v28
+ lvx_u $in1,$x10,$inp
+ vcipher $out2,$out2,v28
+ lvx_u $in2,$x20,$inp
+ vcipher $out3,$out3,v28
+ lvx_u $in3,$x30,$inp
+ vcipher $out4,$out4,v28
+ lvx_u $in4,$x40,$inp
+ vcipher $out5,$out5,v28
+ lvx_u $in5,$x50,$inp
+ vcipher $out6,$out6,v28
+ lvx_u $in6,$x60,$inp
+ vcipher $out7,$out7,v28
+ lvx_u $in7,$x70,$inp
+ addi $inp,$inp,0x80
+
+ vcipher $out0,$out0,v29
+ le?vperm $in0,$in0,$in0,$inpperm
+ vcipher $out1,$out1,v29
+ le?vperm $in1,$in1,$in1,$inpperm
+ vcipher $out2,$out2,v29
+ le?vperm $in2,$in2,$in2,$inpperm
+ vcipher $out3,$out3,v29
+ le?vperm $in3,$in3,$in3,$inpperm
+ vcipher $out4,$out4,v29
+ le?vperm $in4,$in4,$in4,$inpperm
+ vcipher $out5,$out5,v29
+ le?vperm $in5,$in5,$in5,$inpperm
+ vcipher $out6,$out6,v29
+ le?vperm $in6,$in6,$in6,$inpperm
+ vcipher $out7,$out7,v29
+ le?vperm $in7,$in7,$in7,$inpperm
+
+ add $inp,$inp,r0 # $inp is adjusted in such
+ # way that at exit from the
+ # loop inX-in7 are loaded
+ # with last "words"
+ subfe. r0,r0,r0 # borrow?-1:0
+ vcipher $out0,$out0,v30
+ vxor $in0,$in0,v31 # xor with last round key
+ vcipher $out1,$out1,v30
+ vxor $in1,$in1,v31
+ vcipher $out2,$out2,v30
+ vxor $in2,$in2,v31
+ vcipher $out3,$out3,v30
+ vxor $in3,$in3,v31
+ vcipher $out4,$out4,v30
+ vxor $in4,$in4,v31
+ vcipher $out5,$out5,v30
+ vxor $in5,$in5,v31
+ vcipher $out6,$out6,v30
+ vxor $in6,$in6,v31
+ vcipher $out7,$out7,v30
+ vxor $in7,$in7,v31
+
+ bne Lctr32_enc8x_break # did $len-129 borrow?
+
+ vcipherlast $in0,$out0,$in0
+ vcipherlast $in1,$out1,$in1
+ vadduqm $out1,$ivec,$one # counter values ...
+ vcipherlast $in2,$out2,$in2
+ vadduqm $out2,$ivec,$two
+ vxor $out0,$ivec,$rndkey0 # ... xored with rndkey[0]
+ vcipherlast $in3,$out3,$in3
+ vadduqm $out3,$out1,$two
+ vxor $out1,$out1,$rndkey0
+ vcipherlast $in4,$out4,$in4
+ vadduqm $out4,$out2,$two
+ vxor $out2,$out2,$rndkey0
+ vcipherlast $in5,$out5,$in5
+ vadduqm $out5,$out3,$two
+ vxor $out3,$out3,$rndkey0
+ vcipherlast $in6,$out6,$in6
+ vadduqm $out6,$out4,$two
+ vxor $out4,$out4,$rndkey0
+ vcipherlast $in7,$out7,$in7
+ vadduqm $out7,$out5,$two
+ vxor $out5,$out5,$rndkey0
+ le?vperm $in0,$in0,$in0,$inpperm
+ vadduqm $ivec,$out6,$two # next counter value
+ vxor $out6,$out6,$rndkey0
+ le?vperm $in1,$in1,$in1,$inpperm
+ vxor $out7,$out7,$rndkey0
+ mtctr $rounds
+
+ vcipher $out0,$out0,v24
+ stvx_u $in0,$x00,$out
+ le?vperm $in2,$in2,$in2,$inpperm
+ vcipher $out1,$out1,v24
+ stvx_u $in1,$x10,$out
+ le?vperm $in3,$in3,$in3,$inpperm
+ vcipher $out2,$out2,v24
+ stvx_u $in2,$x20,$out
+ le?vperm $in4,$in4,$in4,$inpperm
+ vcipher $out3,$out3,v24
+ stvx_u $in3,$x30,$out
+ le?vperm $in5,$in5,$in5,$inpperm
+ vcipher $out4,$out4,v24
+ stvx_u $in4,$x40,$out
+ le?vperm $in6,$in6,$in6,$inpperm
+ vcipher $out5,$out5,v24
+ stvx_u $in5,$x50,$out
+ le?vperm $in7,$in7,$in7,$inpperm
+ vcipher $out6,$out6,v24
+ stvx_u $in6,$x60,$out
+ vcipher $out7,$out7,v24
+ stvx_u $in7,$x70,$out
+ addi $out,$out,0x80
+
+ b Loop_ctr32_enc8x_middle
+
+.align 5
+Lctr32_enc8x_break:
+ cmpwi $len,-0x60
+ blt Lctr32_enc8x_one
+ nop
+ beq Lctr32_enc8x_two
+ cmpwi $len,-0x40
+ blt Lctr32_enc8x_three
+ nop
+ beq Lctr32_enc8x_four
+ cmpwi $len,-0x20
+ blt Lctr32_enc8x_five
+ nop
+ beq Lctr32_enc8x_six
+ cmpwi $len,0x00
+ blt Lctr32_enc8x_seven
+
+Lctr32_enc8x_eight:
+ vcipherlast $out0,$out0,$in0
+ vcipherlast $out1,$out1,$in1
+ vcipherlast $out2,$out2,$in2
+ vcipherlast $out3,$out3,$in3
+ vcipherlast $out4,$out4,$in4
+ vcipherlast $out5,$out5,$in5
+ vcipherlast $out6,$out6,$in6
+ vcipherlast $out7,$out7,$in7
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ le?vperm $out1,$out1,$out1,$inpperm
+ stvx_u $out0,$x00,$out
+ le?vperm $out2,$out2,$out2,$inpperm
+ stvx_u $out1,$x10,$out
+ le?vperm $out3,$out3,$out3,$inpperm
+ stvx_u $out2,$x20,$out
+ le?vperm $out4,$out4,$out4,$inpperm
+ stvx_u $out3,$x30,$out
+ le?vperm $out5,$out5,$out5,$inpperm
+ stvx_u $out4,$x40,$out
+ le?vperm $out6,$out6,$out6,$inpperm
+ stvx_u $out5,$x50,$out
+ le?vperm $out7,$out7,$out7,$inpperm
+ stvx_u $out6,$x60,$out
+ stvx_u $out7,$x70,$out
+ addi $out,$out,0x80
+ b Lctr32_enc8x_done
+
+.align 5
+Lctr32_enc8x_seven:
+ vcipherlast $out0,$out0,$in1
+ vcipherlast $out1,$out1,$in2
+ vcipherlast $out2,$out2,$in3
+ vcipherlast $out3,$out3,$in4
+ vcipherlast $out4,$out4,$in5
+ vcipherlast $out5,$out5,$in6
+ vcipherlast $out6,$out6,$in7
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ le?vperm $out1,$out1,$out1,$inpperm
+ stvx_u $out0,$x00,$out
+ le?vperm $out2,$out2,$out2,$inpperm
+ stvx_u $out1,$x10,$out
+ le?vperm $out3,$out3,$out3,$inpperm
+ stvx_u $out2,$x20,$out
+ le?vperm $out4,$out4,$out4,$inpperm
+ stvx_u $out3,$x30,$out
+ le?vperm $out5,$out5,$out5,$inpperm
+ stvx_u $out4,$x40,$out
+ le?vperm $out6,$out6,$out6,$inpperm
+ stvx_u $out5,$x50,$out
+ stvx_u $out6,$x60,$out
+ addi $out,$out,0x70
+ b Lctr32_enc8x_done
+
+.align 5
+Lctr32_enc8x_six:
+ vcipherlast $out0,$out0,$in2
+ vcipherlast $out1,$out1,$in3
+ vcipherlast $out2,$out2,$in4
+ vcipherlast $out3,$out3,$in5
+ vcipherlast $out4,$out4,$in6
+ vcipherlast $out5,$out5,$in7
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ le?vperm $out1,$out1,$out1,$inpperm
+ stvx_u $out0,$x00,$out
+ le?vperm $out2,$out2,$out2,$inpperm
+ stvx_u $out1,$x10,$out
+ le?vperm $out3,$out3,$out3,$inpperm
+ stvx_u $out2,$x20,$out
+ le?vperm $out4,$out4,$out4,$inpperm
+ stvx_u $out3,$x30,$out
+ le?vperm $out5,$out5,$out5,$inpperm
+ stvx_u $out4,$x40,$out
+ stvx_u $out5,$x50,$out
+ addi $out,$out,0x60
+ b Lctr32_enc8x_done
+
+.align 5
+Lctr32_enc8x_five:
+ vcipherlast $out0,$out0,$in3
+ vcipherlast $out1,$out1,$in4
+ vcipherlast $out2,$out2,$in5
+ vcipherlast $out3,$out3,$in6
+ vcipherlast $out4,$out4,$in7
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ le?vperm $out1,$out1,$out1,$inpperm
+ stvx_u $out0,$x00,$out
+ le?vperm $out2,$out2,$out2,$inpperm
+ stvx_u $out1,$x10,$out
+ le?vperm $out3,$out3,$out3,$inpperm
+ stvx_u $out2,$x20,$out
+ le?vperm $out4,$out4,$out4,$inpperm
+ stvx_u $out3,$x30,$out
+ stvx_u $out4,$x40,$out
+ addi $out,$out,0x50
+ b Lctr32_enc8x_done
+
+.align 5
+Lctr32_enc8x_four:
+ vcipherlast $out0,$out0,$in4
+ vcipherlast $out1,$out1,$in5
+ vcipherlast $out2,$out2,$in6
+ vcipherlast $out3,$out3,$in7
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ le?vperm $out1,$out1,$out1,$inpperm
+ stvx_u $out0,$x00,$out
+ le?vperm $out2,$out2,$out2,$inpperm
+ stvx_u $out1,$x10,$out
+ le?vperm $out3,$out3,$out3,$inpperm
+ stvx_u $out2,$x20,$out
+ stvx_u $out3,$x30,$out
+ addi $out,$out,0x40
+ b Lctr32_enc8x_done
+
+.align 5
+Lctr32_enc8x_three:
+ vcipherlast $out0,$out0,$in5
+ vcipherlast $out1,$out1,$in6
+ vcipherlast $out2,$out2,$in7
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ le?vperm $out1,$out1,$out1,$inpperm
+ stvx_u $out0,$x00,$out
+ le?vperm $out2,$out2,$out2,$inpperm
+ stvx_u $out1,$x10,$out
+ stvx_u $out2,$x20,$out
+ addi $out,$out,0x30
+ b Lctr32_enc8x_done
+
+.align 5
+Lctr32_enc8x_two:
+ vcipherlast $out0,$out0,$in6
+ vcipherlast $out1,$out1,$in7
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ le?vperm $out1,$out1,$out1,$inpperm
+ stvx_u $out0,$x00,$out
+ stvx_u $out1,$x10,$out
+ addi $out,$out,0x20
+ b Lctr32_enc8x_done
+
+.align 5
+Lctr32_enc8x_one:
+ vcipherlast $out0,$out0,$in7
+
+ le?vperm $out0,$out0,$out0,$inpperm
+ stvx_u $out0,0,$out
+ addi $out,$out,0x10
+
+Lctr32_enc8x_done:
+ li r10,`$FRAME+15`
+ li r11,`$FRAME+31`
+ stvx $inpperm,r10,$sp # wipe copies of round keys
+ addi r10,r10,32
+ stvx $inpperm,r11,$sp
+ addi r11,r11,32
+ stvx $inpperm,r10,$sp
+ addi r10,r10,32
+ stvx $inpperm,r11,$sp
+ addi r11,r11,32
+ stvx $inpperm,r10,$sp
+ addi r10,r10,32
+ stvx $inpperm,r11,$sp
+ addi r11,r11,32
+ stvx $inpperm,r10,$sp
+ addi r10,r10,32
+ stvx $inpperm,r11,$sp
+ addi r11,r11,32
+
+ mtspr 256,$vrsave
+ lvx v20,r10,$sp # ABI says so
+ addi r10,r10,32
+ lvx v21,r11,$sp
+ addi r11,r11,32
+ lvx v22,r10,$sp
+ addi r10,r10,32
+ lvx v23,r11,$sp
+ addi r11,r11,32
+ lvx v24,r10,$sp
+ addi r10,r10,32
+ lvx v25,r11,$sp
+ addi r11,r11,32
+ lvx v26,r10,$sp
+ addi r10,r10,32
+ lvx v27,r11,$sp
+ addi r11,r11,32
+ lvx v28,r10,$sp
+ addi r10,r10,32
+ lvx v29,r11,$sp
+ addi r11,r11,32
+ lvx v30,r10,$sp
+ lvx v31,r11,$sp
+ $POP r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+ $POP r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+ $POP r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+ $POP r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+ $POP r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+ $POP r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+ addi $sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0x80,6,6,0
+ .long 0
+.size .${prefix}_ctr32_encrypt_blocks,.-.${prefix}_ctr32_encrypt_blocks
+___
+}} }}}
+
+#########################################################################
+{{{ # XTS procedures #
+# int aes_p8_xts_[en|de]crypt(const char *inp, char *out, size_t len, #
+# const AES_KEY *key1, const AES_KEY *key2, #
+# [const] unsigned char iv[16]); #
+# If $key2 is NULL, then a "tweak chaining" mode is engaged, in which #
+# input tweak value is assumed to be encrypted already, and last tweak #
+# value, one suitable for consecutive call on same chunk of data, is #
+# written back to original buffer. In addition, in "tweak chaining" #
+# mode only complete input blocks are processed. #
+
+my ($inp,$out,$len,$key1,$key2,$ivp,$rounds,$idx) = map("r$_",(3..10));
+my ($rndkey0,$rndkey1,$inout) = map("v$_",(0..2));
+my ($output,$inptail,$inpperm,$leperm,$keyperm) = map("v$_",(3..7));
+my ($tweak,$seven,$eighty7,$tmp,$tweak1) = map("v$_",(8..12));
+my $taillen = $key2;
+
+ ($inp,$idx) = ($idx,$inp); # reassign
+
+$code.=<<___;
+.globl .${prefix}_xts_encrypt
+ mr $inp,r3 # reassign
+ li r3,-1
+ ${UCMP}i $len,16
+ bltlr-
+
+ lis r0,0xfff0
+ mfspr r12,256 # save vrsave
+ li r11,0
+ mtspr 256,r0
+
+ vspltisb $seven,0x07 # 0x070707..07
+ le?lvsl $leperm,r11,r11
+ le?vspltisb $tmp,0x0f
+ le?vxor $leperm,$leperm,$seven
+
+ li $idx,15
+ lvx $tweak,0,$ivp # load [unaligned] iv
+ lvsl $inpperm,0,$ivp
+ lvx $inptail,$idx,$ivp
+ le?vxor $inpperm,$inpperm,$tmp
+ vperm $tweak,$tweak,$inptail,$inpperm
+
+ neg r11,$inp
+ lvsr $inpperm,0,r11 # prepare for unaligned load
+ lvx $inout,0,$inp
+ addi $inp,$inp,15 # 15 is not typo
+ le?vxor $inpperm,$inpperm,$tmp
+
+ ${UCMP}i $key2,0 # key2==NULL?
+ beq Lxts_enc_no_key2
+
+ ?lvsl $keyperm,0,$key2 # prepare for unaligned key
+ lwz $rounds,240($key2)
+ srwi $rounds,$rounds,1
+ subi $rounds,$rounds,1
+ li $idx,16
+
+ lvx $rndkey0,0,$key2
+ lvx $rndkey1,$idx,$key2
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $tweak,$tweak,$rndkey0
+ lvx $rndkey0,$idx,$key2
+ addi $idx,$idx,16
+ mtctr $rounds
+
+Ltweak_xts_enc:
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $tweak,$tweak,$rndkey1
+ lvx $rndkey1,$idx,$key2
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vcipher $tweak,$tweak,$rndkey0
+ lvx $rndkey0,$idx,$key2
+ addi $idx,$idx,16
+ bdnz Ltweak_xts_enc
+
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $tweak,$tweak,$rndkey1
+ lvx $rndkey1,$idx,$key2
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vcipherlast $tweak,$tweak,$rndkey0
+
+ li $ivp,0 # don't chain the tweak
+ b Lxts_enc
+
+Lxts_enc_no_key2:
+ li $idx,-16
+ and $len,$len,$idx # in "tweak chaining"
+ # mode only complete
+ # blocks are processed
+Lxts_enc:
+ lvx $inptail,0,$inp
+ addi $inp,$inp,16
+
+ ?lvsl $keyperm,0,$key1 # prepare for unaligned key
+ lwz $rounds,240($key1)
+ srwi $rounds,$rounds,1
+ subi $rounds,$rounds,1
+ li $idx,16
+
+ vslb $eighty7,$seven,$seven # 0x808080..80
+ vor $eighty7,$eighty7,$seven # 0x878787..87
+ vspltisb $tmp,1 # 0x010101..01
+ vsldoi $eighty7,$eighty7,$tmp,15 # 0x870101..01
+
+ ${UCMP}i $len,96
+ bge _aesp8_xts_encrypt6x
+
+ andi. $taillen,$len,15
+ subic r0,$len,32
+ subi $taillen,$taillen,16
+ subfe r0,r0,r0
+ and r0,r0,$taillen
+ add $inp,$inp,r0
+
+ lvx $rndkey0,0,$key1
+ lvx $rndkey1,$idx,$key1
+ addi $idx,$idx,16
+ vperm $inout,$inout,$inptail,$inpperm
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $inout,$inout,$tweak
+ vxor $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key1
+ addi $idx,$idx,16
+ mtctr $rounds
+ b Loop_xts_enc
+
+.align 5
+Loop_xts_enc:
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key1
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vcipher $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key1
+ addi $idx,$idx,16
+ bdnz Loop_xts_enc
+
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key1
+ li $idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $rndkey0,$rndkey0,$tweak
+ vcipherlast $output,$inout,$rndkey0
+
+ le?vperm $tmp,$output,$output,$leperm
+ be?nop
+ le?stvx_u $tmp,0,$out
+ be?stvx_u $output,0,$out
+ addi $out,$out,16
+
+ subic. $len,$len,16
+ beq Lxts_enc_done
+
+ vmr $inout,$inptail
+ lvx $inptail,0,$inp
+ addi $inp,$inp,16
+ lvx $rndkey0,0,$key1
+ lvx $rndkey1,$idx,$key1
+ addi $idx,$idx,16
+
+ subic r0,$len,32
+ subfe r0,r0,r0
+ and r0,r0,$taillen
+ add $inp,$inp,r0
+
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ vsldoi $tmp,$tmp,$tmp,15
+ vand $tmp,$tmp,$eighty7
+ vxor $tweak,$tweak,$tmp
+
+ vperm $inout,$inout,$inptail,$inpperm
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $inout,$inout,$tweak
+ vxor $output,$output,$rndkey0 # just in case $len<16
+ vxor $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key1
+ addi $idx,$idx,16
+
+ mtctr $rounds
+ ${UCMP}i $len,16
+ bge Loop_xts_enc
+
+ vxor $output,$output,$tweak
+ lvsr $inpperm,0,$len # $inpperm is no longer needed
+ vxor $inptail,$inptail,$inptail # $inptail is no longer needed
+ vspltisb $tmp,-1
+ vperm $inptail,$inptail,$tmp,$inpperm
+ vsel $inout,$inout,$output,$inptail
+
+ subi r11,$out,17
+ subi $out,$out,16
+ mtctr $len
+ li $len,16
+Loop_xts_enc_steal:
+ lbzu r0,1(r11)
+ stb r0,16(r11)
+ bdnz Loop_xts_enc_steal
+
+ mtctr $rounds
+ b Loop_xts_enc # one more time...
+
+Lxts_enc_done:
+ ${UCMP}i $ivp,0
+ beq Lxts_enc_ret
+
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ vsldoi $tmp,$tmp,$tmp,15
+ vand $tmp,$tmp,$eighty7
+ vxor $tweak,$tweak,$tmp
+
+ le?vperm $tweak,$tweak,$tweak,$leperm
+ stvx_u $tweak,0,$ivp
+
+Lxts_enc_ret:
+ mtspr 256,r12 # restore vrsave
+ li r3,0
+ blr
+ .long 0
+ .byte 0,12,0x04,0,0x80,6,6,0
+ .long 0
+.size .${prefix}_xts_encrypt,.-.${prefix}_xts_encrypt
+
+.globl .${prefix}_xts_decrypt
+ mr $inp,r3 # reassign
+ li r3,-1
+ ${UCMP}i $len,16
+ bltlr-
+
+ lis r0,0xfff8
+ mfspr r12,256 # save vrsave
+ li r11,0
+ mtspr 256,r0
+
+ andi. r0,$len,15
+ neg r0,r0
+ andi. r0,r0,16
+ sub $len,$len,r0
+
+ vspltisb $seven,0x07 # 0x070707..07
+ le?lvsl $leperm,r11,r11
+ le?vspltisb $tmp,0x0f
+ le?vxor $leperm,$leperm,$seven
+
+ li $idx,15
+ lvx $tweak,0,$ivp # load [unaligned] iv
+ lvsl $inpperm,0,$ivp
+ lvx $inptail,$idx,$ivp
+ le?vxor $inpperm,$inpperm,$tmp
+ vperm $tweak,$tweak,$inptail,$inpperm
+
+ neg r11,$inp
+ lvsr $inpperm,0,r11 # prepare for unaligned load
+ lvx $inout,0,$inp
+ addi $inp,$inp,15 # 15 is not typo
+ le?vxor $inpperm,$inpperm,$tmp
+
+ ${UCMP}i $key2,0 # key2==NULL?
+ beq Lxts_dec_no_key2
+
+ ?lvsl $keyperm,0,$key2 # prepare for unaligned key
+ lwz $rounds,240($key2)
+ srwi $rounds,$rounds,1
+ subi $rounds,$rounds,1
+ li $idx,16
+
+ lvx $rndkey0,0,$key2
+ lvx $rndkey1,$idx,$key2
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $tweak,$tweak,$rndkey0
+ lvx $rndkey0,$idx,$key2
+ addi $idx,$idx,16
+ mtctr $rounds
+
+Ltweak_xts_dec:
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $tweak,$tweak,$rndkey1
+ lvx $rndkey1,$idx,$key2
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vcipher $tweak,$tweak,$rndkey0
+ lvx $rndkey0,$idx,$key2
+ addi $idx,$idx,16
+ bdnz Ltweak_xts_dec
+
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vcipher $tweak,$tweak,$rndkey1
+ lvx $rndkey1,$idx,$key2
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vcipherlast $tweak,$tweak,$rndkey0
+
+ li $ivp,0 # don't chain the tweak
+ b Lxts_dec
+
+Lxts_dec_no_key2:
+ neg $idx,$len
+ andi. $idx,$idx,15
+ add $len,$len,$idx # in "tweak chaining"
+ # mode only complete
+ # blocks are processed
+Lxts_dec:
+ lvx $inptail,0,$inp
+ addi $inp,$inp,16
+
+ ?lvsl $keyperm,0,$key1 # prepare for unaligned key
+ lwz $rounds,240($key1)
+ srwi $rounds,$rounds,1
+ subi $rounds,$rounds,1
+ li $idx,16
+
+ vslb $eighty7,$seven,$seven # 0x808080..80
+ vor $eighty7,$eighty7,$seven # 0x878787..87
+ vspltisb $tmp,1 # 0x010101..01
+ vsldoi $eighty7,$eighty7,$tmp,15 # 0x870101..01
+
+ ${UCMP}i $len,96
+ bge _aesp8_xts_decrypt6x
+
+ lvx $rndkey0,0,$key1
+ lvx $rndkey1,$idx,$key1
+ addi $idx,$idx,16
+ vperm $inout,$inout,$inptail,$inpperm
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $inout,$inout,$tweak
+ vxor $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key1
+ addi $idx,$idx,16
+ mtctr $rounds
+
+ ${UCMP}i $len,16
+ blt Ltail_xts_dec
+ be?b Loop_xts_dec
+
+.align 5
+Loop_xts_dec:
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vncipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key1
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vncipher $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key1
+ addi $idx,$idx,16
+ bdnz Loop_xts_dec
+
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vncipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key1
+ li $idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $rndkey0,$rndkey0,$tweak
+ vncipherlast $output,$inout,$rndkey0
+
+ le?vperm $tmp,$output,$output,$leperm
+ be?nop
+ le?stvx_u $tmp,0,$out
+ be?stvx_u $output,0,$out
+ addi $out,$out,16
+
+ subic. $len,$len,16
+ beq Lxts_dec_done
+
+ vmr $inout,$inptail
+ lvx $inptail,0,$inp
+ addi $inp,$inp,16
+ lvx $rndkey0,0,$key1
+ lvx $rndkey1,$idx,$key1
+ addi $idx,$idx,16
+
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ vsldoi $tmp,$tmp,$tmp,15
+ vand $tmp,$tmp,$eighty7
+ vxor $tweak,$tweak,$tmp
+
+ vperm $inout,$inout,$inptail,$inpperm
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $inout,$inout,$tweak
+ vxor $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key1
+ addi $idx,$idx,16
+
+ mtctr $rounds
+ ${UCMP}i $len,16
+ bge Loop_xts_dec
+
+Ltail_xts_dec:
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak1,$tweak,$tweak
+ vsldoi $tmp,$tmp,$tmp,15
+ vand $tmp,$tmp,$eighty7
+ vxor $tweak1,$tweak1,$tmp
+
+ subi $inp,$inp,16
+ add $inp,$inp,$len
+
+ vxor $inout,$inout,$tweak # :-(
+ vxor $inout,$inout,$tweak1 # :-)
+
+Loop_xts_dec_short:
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vncipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key1
+ addi $idx,$idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vncipher $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key1
+ addi $idx,$idx,16
+ bdnz Loop_xts_dec_short
+
+ ?vperm $rndkey1,$rndkey1,$rndkey0,$keyperm
+ vncipher $inout,$inout,$rndkey1
+ lvx $rndkey1,$idx,$key1
+ li $idx,16
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+ vxor $rndkey0,$rndkey0,$tweak1
+ vncipherlast $output,$inout,$rndkey0
+
+ le?vperm $tmp,$output,$output,$leperm
+ be?nop
+ le?stvx_u $tmp,0,$out
+ be?stvx_u $output,0,$out
+
+ vmr $inout,$inptail
+ lvx $inptail,0,$inp
+ #addi $inp,$inp,16
+ lvx $rndkey0,0,$key1
+ lvx $rndkey1,$idx,$key1
+ addi $idx,$idx,16
+ vperm $inout,$inout,$inptail,$inpperm
+ ?vperm $rndkey0,$rndkey0,$rndkey1,$keyperm
+
+ lvsr $inpperm,0,$len # $inpperm is no longer needed
+ vxor $inptail,$inptail,$inptail # $inptail is no longer needed
+ vspltisb $tmp,-1
+ vperm $inptail,$inptail,$tmp,$inpperm
+ vsel $inout,$inout,$output,$inptail
+
+ vxor $rndkey0,$rndkey0,$tweak
+ vxor $inout,$inout,$rndkey0
+ lvx $rndkey0,$idx,$key1
+ addi $idx,$idx,16
+
+ subi r11,$out,1
+ mtctr $len
+ li $len,16
+Loop_xts_dec_steal:
+ lbzu r0,1(r11)
+ stb r0,16(r11)
+ bdnz Loop_xts_dec_steal
+
+ mtctr $rounds
+ b Loop_xts_dec # one more time...
+
+Lxts_dec_done:
+ ${UCMP}i $ivp,0
+ beq Lxts_dec_ret
+
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ vsldoi $tmp,$tmp,$tmp,15
+ vand $tmp,$tmp,$eighty7
+ vxor $tweak,$tweak,$tmp
+
+ le?vperm $tweak,$tweak,$tweak,$leperm
+ stvx_u $tweak,0,$ivp
+
+Lxts_dec_ret:
+ mtspr 256,r12 # restore vrsave
+ li r3,0
+ blr
+ .long 0
+ .byte 0,12,0x04,0,0x80,6,6,0
+ .long 0
+.size .${prefix}_xts_decrypt,.-.${prefix}_xts_decrypt
+___
+#########################################################################
+{{ # Optimized XTS procedures #
+my $key_=$key2;
+my ($x00,$x10,$x20,$x30,$x40,$x50,$x60,$x70)=map("r$_",(0,3,26..31));
+ $x00=0 if ($flavour =~ /osx/);
+my ($in0, $in1, $in2, $in3, $in4, $in5 )=map("v$_",(0..5));
+my ($out0, $out1, $out2, $out3, $out4, $out5)=map("v$_",(7,12..16));
+my ($twk0, $twk1, $twk2, $twk3, $twk4, $twk5)=map("v$_",(17..22));
+my $rndkey0="v23"; # v24-v25 rotating buffer for first found keys
+ # v26-v31 last 6 round keys
+my ($keyperm)=($out0); # aliases with "caller", redundant assignment
+my $taillen=$x70;
+
+$code.=<<___;
+.align 5
+_aesp8_xts_encrypt6x:
+ $STU $sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+ mflr r11
+ li r7,`$FRAME+8*16+15`
+ li r3,`$FRAME+8*16+31`
+ $PUSH r11,`$FRAME+21*16+6*$SIZE_T+$LRSAVE`($sp)
+ stvx v20,r7,$sp # ABI says so
+ addi r7,r7,32
+ stvx v21,r3,$sp
+ addi r3,r3,32
+ stvx v22,r7,$sp
+ addi r7,r7,32
+ stvx v23,r3,$sp
+ addi r3,r3,32
+ stvx v24,r7,$sp
+ addi r7,r7,32
+ stvx v25,r3,$sp
+ addi r3,r3,32
+ stvx v26,r7,$sp
+ addi r7,r7,32
+ stvx v27,r3,$sp
+ addi r3,r3,32
+ stvx v28,r7,$sp
+ addi r7,r7,32
+ stvx v29,r3,$sp
+ addi r3,r3,32
+ stvx v30,r7,$sp
+ stvx v31,r3,$sp
+ li r0,-1
+ stw $vrsave,`$FRAME+21*16-4`($sp) # save vrsave
+ li $x10,0x10
+ $PUSH r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+ li $x20,0x20
+ $PUSH r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+ li $x30,0x30
+ $PUSH r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+ li $x40,0x40
+ $PUSH r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+ li $x50,0x50
+ $PUSH r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+ li $x60,0x60
+ $PUSH r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+ li $x70,0x70
+ mtspr 256,r0
+
+ xxlor 2, 32+$eighty7, 32+$eighty7
+ vsldoi $eighty7,$tmp,$eighty7,1 # 0x010101..87
+ xxlor 1, 32+$eighty7, 32+$eighty7
+
+ # Load XOR Lconsts.
+ mr $x70, r6
+ bl Lconsts
+ lxvw4x 0, $x40, r6 # load XOR contents
+ mr r6, $x70
+ li $x70,0x70
+
+ subi $rounds,$rounds,3 # -4 in total
+
+ lvx $rndkey0,$x00,$key1 # load key schedule
+ lvx v30,$x10,$key1
+ addi $key1,$key1,0x20
+ lvx v31,$x00,$key1
+ ?vperm $rndkey0,$rndkey0,v30,$keyperm
+ addi $key_,$sp,$FRAME+15
+ mtctr $rounds
+
+Load_xts_enc_key:
+ ?vperm v24,v30,v31,$keyperm
+ lvx v30,$x10,$key1
+ addi $key1,$key1,0x20
+ stvx v24,$x00,$key_ # off-load round[1]
+ ?vperm v25,v31,v30,$keyperm
+ lvx v31,$x00,$key1
+ stvx v25,$x10,$key_ # off-load round[2]
+ addi $key_,$key_,0x20
+ bdnz Load_xts_enc_key
+
+ lvx v26,$x10,$key1
+ ?vperm v24,v30,v31,$keyperm
+ lvx v27,$x20,$key1
+ stvx v24,$x00,$key_ # off-load round[3]
+ ?vperm v25,v31,v26,$keyperm
+ lvx v28,$x30,$key1
+ stvx v25,$x10,$key_ # off-load round[4]
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ ?vperm v26,v26,v27,$keyperm
+ lvx v29,$x40,$key1
+ ?vperm v27,v27,v28,$keyperm
+ lvx v30,$x50,$key1
+ ?vperm v28,v28,v29,$keyperm
+ lvx v31,$x60,$key1
+ ?vperm v29,v29,v30,$keyperm
+ lvx $twk5,$x70,$key1 # borrow $twk5
+ ?vperm v30,v30,v31,$keyperm
+ lvx v24,$x00,$key_ # pre-load round[1]
+ ?vperm v31,v31,$twk5,$keyperm
+ lvx v25,$x10,$key_ # pre-load round[2]
+
+ # Switch to use the following codes with 0x010101..87 to generate tweak.
+ # eighty7 = 0x010101..87
+ # vsrab tmp, tweak, seven # next tweak value, right shift 7 bits
+ # vand tmp, tmp, eighty7 # last byte with carry
+ # vaddubm tweak, tweak, tweak # left shift 1 bit (x2)
+ # xxlor vsx, 0, 0
+ # vpermxor tweak, tweak, tmp, vsx
+
+ vperm $in0,$inout,$inptail,$inpperm
+ subi $inp,$inp,31 # undo "caller"
+ vxor $twk0,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ vand $tmp,$tmp,$eighty7
+ vxor $out0,$in0,$twk0
+ xxlor 32+$in1, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in1
+
+ lvx_u $in1,$x10,$inp
+ vxor $twk1,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in1,$in1,$in1,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out1,$in1,$twk1
+ xxlor 32+$in2, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in2
+
+ lvx_u $in2,$x20,$inp
+ andi. $taillen,$len,15
+ vxor $twk2,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in2,$in2,$in2,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out2,$in2,$twk2
+ xxlor 32+$in3, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in3
+
+ lvx_u $in3,$x30,$inp
+ sub $len,$len,$taillen
+ vxor $twk3,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in3,$in3,$in3,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out3,$in3,$twk3
+ xxlor 32+$in4, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in4
+
+ lvx_u $in4,$x40,$inp
+ subi $len,$len,0x60
+ vxor $twk4,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in4,$in4,$in4,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out4,$in4,$twk4
+ xxlor 32+$in5, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in5
+
+ lvx_u $in5,$x50,$inp
+ addi $inp,$inp,0x60
+ vxor $twk5,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in5,$in5,$in5,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out5,$in5,$twk5
+ xxlor 32+$in0, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in0
+
+ vxor v31,v31,$rndkey0
+ mtctr $rounds
+ b Loop_xts_enc6x
+
+.align 5
+Loop_xts_enc6x:
+ vcipher $out0,$out0,v24
+ vcipher $out1,$out1,v24
+ vcipher $out2,$out2,v24
+ vcipher $out3,$out3,v24
+ vcipher $out4,$out4,v24
+ vcipher $out5,$out5,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vcipher $out0,$out0,v25
+ vcipher $out1,$out1,v25
+ vcipher $out2,$out2,v25
+ vcipher $out3,$out3,v25
+ vcipher $out4,$out4,v25
+ vcipher $out5,$out5,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz Loop_xts_enc6x
+
+ xxlor 32+$eighty7, 1, 1 # 0x010101..87
+
+ subic $len,$len,96 # $len-=96
+ vxor $in0,$twk0,v31 # xor with last round key
+ vcipher $out0,$out0,v24
+ vcipher $out1,$out1,v24
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk0,$tweak,$rndkey0
+ vaddubm $tweak,$tweak,$tweak
+ vcipher $out2,$out2,v24
+ vcipher $out3,$out3,v24
+ vcipher $out4,$out4,v24
+ vcipher $out5,$out5,v24
+
+ subfe. r0,r0,r0 # borrow?-1:0
+ vand $tmp,$tmp,$eighty7
+ vcipher $out0,$out0,v25
+ vcipher $out1,$out1,v25
+ xxlor 32+$in1, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in1
+ vcipher $out2,$out2,v25
+ vcipher $out3,$out3,v25
+ vxor $in1,$twk1,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk1,$tweak,$rndkey0
+ vcipher $out4,$out4,v25
+ vcipher $out5,$out5,v25
+
+ and r0,r0,$len
+ vaddubm $tweak,$tweak,$tweak
+ vcipher $out0,$out0,v26
+ vcipher $out1,$out1,v26
+ vand $tmp,$tmp,$eighty7
+ vcipher $out2,$out2,v26
+ vcipher $out3,$out3,v26
+ xxlor 32+$in2, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in2
+ vcipher $out4,$out4,v26
+ vcipher $out5,$out5,v26
+
+ add $inp,$inp,r0 # $inp is adjusted in such
+ # way that at exit from the
+ # loop inX-in5 are loaded
+ # with last "words"
+ vxor $in2,$twk2,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk2,$tweak,$rndkey0
+ vaddubm $tweak,$tweak,$tweak
+ vcipher $out0,$out0,v27
+ vcipher $out1,$out1,v27
+ vcipher $out2,$out2,v27
+ vcipher $out3,$out3,v27
+ vand $tmp,$tmp,$eighty7
+ vcipher $out4,$out4,v27
+ vcipher $out5,$out5,v27
+
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ xxlor 32+$in3, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in3
+ vcipher $out0,$out0,v28
+ vcipher $out1,$out1,v28
+ vxor $in3,$twk3,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk3,$tweak,$rndkey0
+ vcipher $out2,$out2,v28
+ vcipher $out3,$out3,v28
+ vaddubm $tweak,$tweak,$tweak
+ vcipher $out4,$out4,v28
+ vcipher $out5,$out5,v28
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+ vand $tmp,$tmp,$eighty7
+
+ vcipher $out0,$out0,v29
+ vcipher $out1,$out1,v29
+ xxlor 32+$in4, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in4
+ vcipher $out2,$out2,v29
+ vcipher $out3,$out3,v29
+ vxor $in4,$twk4,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk4,$tweak,$rndkey0
+ vcipher $out4,$out4,v29
+ vcipher $out5,$out5,v29
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+ vaddubm $tweak,$tweak,$tweak
+
+ vcipher $out0,$out0,v30
+ vcipher $out1,$out1,v30
+ vand $tmp,$tmp,$eighty7
+ vcipher $out2,$out2,v30
+ vcipher $out3,$out3,v30
+ xxlor 32+$in5, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in5
+ vcipher $out4,$out4,v30
+ vcipher $out5,$out5,v30
+ vxor $in5,$twk5,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk5,$tweak,$rndkey0
+
+ vcipherlast $out0,$out0,$in0
+ lvx_u $in0,$x00,$inp # load next input block
+ vaddubm $tweak,$tweak,$tweak
+ vcipherlast $out1,$out1,$in1
+ lvx_u $in1,$x10,$inp
+ vcipherlast $out2,$out2,$in2
+ le?vperm $in0,$in0,$in0,$leperm
+ lvx_u $in2,$x20,$inp
+ vand $tmp,$tmp,$eighty7
+ vcipherlast $out3,$out3,$in3
+ le?vperm $in1,$in1,$in1,$leperm
+ lvx_u $in3,$x30,$inp
+ vcipherlast $out4,$out4,$in4
+ le?vperm $in2,$in2,$in2,$leperm
+ lvx_u $in4,$x40,$inp
+ xxlor 10, 32+$in0, 32+$in0
+ xxlor 32+$in0, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in0
+ xxlor 32+$in0, 10, 10
+ vcipherlast $tmp,$out5,$in5 # last block might be needed
+ # in stealing mode
+ le?vperm $in3,$in3,$in3,$leperm
+ lvx_u $in5,$x50,$inp
+ addi $inp,$inp,0x60
+ le?vperm $in4,$in4,$in4,$leperm
+ le?vperm $in5,$in5,$in5,$leperm
+
+ le?vperm $out0,$out0,$out0,$leperm
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ vxor $out0,$in0,$twk0
+ le?vperm $out2,$out2,$out2,$leperm
+ stvx_u $out1,$x10,$out
+ vxor $out1,$in1,$twk1
+ le?vperm $out3,$out3,$out3,$leperm
+ stvx_u $out2,$x20,$out
+ vxor $out2,$in2,$twk2
+ le?vperm $out4,$out4,$out4,$leperm
+ stvx_u $out3,$x30,$out
+ vxor $out3,$in3,$twk3
+ le?vperm $out5,$tmp,$tmp,$leperm
+ stvx_u $out4,$x40,$out
+ vxor $out4,$in4,$twk4
+ le?stvx_u $out5,$x50,$out
+ be?stvx_u $tmp, $x50,$out
+ vxor $out5,$in5,$twk5
+ addi $out,$out,0x60
+
+ mtctr $rounds
+ beq Loop_xts_enc6x # did $len-=96 borrow?
+
+ xxlor 32+$eighty7, 2, 2 # 0x010101..87
+
+ addic. $len,$len,0x60
+ beq Lxts_enc6x_zero
+ cmpwi $len,0x20
+ blt Lxts_enc6x_one
+ nop
+ beq Lxts_enc6x_two
+ cmpwi $len,0x40
+ blt Lxts_enc6x_three
+ nop
+ beq Lxts_enc6x_four
+
+Lxts_enc6x_five:
+ vxor $out0,$in1,$twk0
+ vxor $out1,$in2,$twk1
+ vxor $out2,$in3,$twk2
+ vxor $out3,$in4,$twk3
+ vxor $out4,$in5,$twk4
+
+ bl _aesp8_xts_enc5x
+
+ le?vperm $out0,$out0,$out0,$leperm
+ vmr $twk0,$twk5 # unused tweak
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ le?vperm $out2,$out2,$out2,$leperm
+ stvx_u $out1,$x10,$out
+ le?vperm $out3,$out3,$out3,$leperm
+ stvx_u $out2,$x20,$out
+ vxor $tmp,$out4,$twk5 # last block prep for stealing
+ le?vperm $out4,$out4,$out4,$leperm
+ stvx_u $out3,$x30,$out
+ stvx_u $out4,$x40,$out
+ addi $out,$out,0x50
+ bne Lxts_enc6x_steal
+ b Lxts_enc6x_done
+
+.align 4
+Lxts_enc6x_four:
+ vxor $out0,$in2,$twk0
+ vxor $out1,$in3,$twk1
+ vxor $out2,$in4,$twk2
+ vxor $out3,$in5,$twk3
+ vxor $out4,$out4,$out4
+
+ bl _aesp8_xts_enc5x
+
+ le?vperm $out0,$out0,$out0,$leperm
+ vmr $twk0,$twk4 # unused tweak
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ le?vperm $out2,$out2,$out2,$leperm
+ stvx_u $out1,$x10,$out
+ vxor $tmp,$out3,$twk4 # last block prep for stealing
+ le?vperm $out3,$out3,$out3,$leperm
+ stvx_u $out2,$x20,$out
+ stvx_u $out3,$x30,$out
+ addi $out,$out,0x40
+ bne Lxts_enc6x_steal
+ b Lxts_enc6x_done
+
+.align 4
+Lxts_enc6x_three:
+ vxor $out0,$in3,$twk0
+ vxor $out1,$in4,$twk1
+ vxor $out2,$in5,$twk2
+ vxor $out3,$out3,$out3
+ vxor $out4,$out4,$out4
+
+ bl _aesp8_xts_enc5x
+
+ le?vperm $out0,$out0,$out0,$leperm
+ vmr $twk0,$twk3 # unused tweak
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ vxor $tmp,$out2,$twk3 # last block prep for stealing
+ le?vperm $out2,$out2,$out2,$leperm
+ stvx_u $out1,$x10,$out
+ stvx_u $out2,$x20,$out
+ addi $out,$out,0x30
+ bne Lxts_enc6x_steal
+ b Lxts_enc6x_done
+
+.align 4
+Lxts_enc6x_two:
+ vxor $out0,$in4,$twk0
+ vxor $out1,$in5,$twk1
+ vxor $out2,$out2,$out2
+ vxor $out3,$out3,$out3
+ vxor $out4,$out4,$out4
+
+ bl _aesp8_xts_enc5x
+
+ le?vperm $out0,$out0,$out0,$leperm
+ vmr $twk0,$twk2 # unused tweak
+ vxor $tmp,$out1,$twk2 # last block prep for stealing
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ stvx_u $out1,$x10,$out
+ addi $out,$out,0x20
+ bne Lxts_enc6x_steal
+ b Lxts_enc6x_done
+
+.align 4
+Lxts_enc6x_one:
+ vxor $out0,$in5,$twk0
+ nop
+Loop_xts_enc1x:
+ vcipher $out0,$out0,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vcipher $out0,$out0,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz Loop_xts_enc1x
+
+ add $inp,$inp,$taillen
+ cmpwi $taillen,0
+ vcipher $out0,$out0,v24
+
+ subi $inp,$inp,16
+ vcipher $out0,$out0,v25
+
+ lvsr $inpperm,0,$taillen
+ vcipher $out0,$out0,v26
+
+ lvx_u $in0,0,$inp
+ vcipher $out0,$out0,v27
+
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ vcipher $out0,$out0,v28
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+
+ vcipher $out0,$out0,v29
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+ vxor $twk0,$twk0,v31
+
+ le?vperm $in0,$in0,$in0,$leperm
+ vcipher $out0,$out0,v30
+
+ vperm $in0,$in0,$in0,$inpperm
+ vcipherlast $out0,$out0,$twk0
+
+ vmr $twk0,$twk1 # unused tweak
+ vxor $tmp,$out0,$twk1 # last block prep for stealing
+ le?vperm $out0,$out0,$out0,$leperm
+ stvx_u $out0,$x00,$out # store output
+ addi $out,$out,0x10
+ bne Lxts_enc6x_steal
+ b Lxts_enc6x_done
+
+.align 4
+Lxts_enc6x_zero:
+ cmpwi $taillen,0
+ beq Lxts_enc6x_done
+
+ add $inp,$inp,$taillen
+ subi $inp,$inp,16
+ lvx_u $in0,0,$inp
+ lvsr $inpperm,0,$taillen # $in5 is no more
+ le?vperm $in0,$in0,$in0,$leperm
+ vperm $in0,$in0,$in0,$inpperm
+ vxor $tmp,$tmp,$twk0
+Lxts_enc6x_steal:
+ vxor $in0,$in0,$twk0
+ vxor $out0,$out0,$out0
+ vspltisb $out1,-1
+ vperm $out0,$out0,$out1,$inpperm
+ vsel $out0,$in0,$tmp,$out0 # $tmp is last block, remember?
+
+ subi r30,$out,17
+ subi $out,$out,16
+ mtctr $taillen
+Loop_xts_enc6x_steal:
+ lbzu r0,1(r30)
+ stb r0,16(r30)
+ bdnz Loop_xts_enc6x_steal
+
+ li $taillen,0
+ mtctr $rounds
+ b Loop_xts_enc1x # one more time...
+
+.align 4
+Lxts_enc6x_done:
+ ${UCMP}i $ivp,0
+ beq Lxts_enc6x_ret
+
+ vxor $tweak,$twk0,$rndkey0
+ le?vperm $tweak,$tweak,$tweak,$leperm
+ stvx_u $tweak,0,$ivp
+
+Lxts_enc6x_ret:
+ mtlr r11
+ li r10,`$FRAME+15`
+ li r11,`$FRAME+31`
+ stvx $seven,r10,$sp # wipe copies of round keys
+ addi r10,r10,32
+ stvx $seven,r11,$sp
+ addi r11,r11,32
+ stvx $seven,r10,$sp
+ addi r10,r10,32
+ stvx $seven,r11,$sp
+ addi r11,r11,32
+ stvx $seven,r10,$sp
+ addi r10,r10,32
+ stvx $seven,r11,$sp
+ addi r11,r11,32
+ stvx $seven,r10,$sp
+ addi r10,r10,32
+ stvx $seven,r11,$sp
+ addi r11,r11,32
+
+ mtspr 256,$vrsave
+ lvx v20,r10,$sp # ABI says so
+ addi r10,r10,32
+ lvx v21,r11,$sp
+ addi r11,r11,32
+ lvx v22,r10,$sp
+ addi r10,r10,32
+ lvx v23,r11,$sp
+ addi r11,r11,32
+ lvx v24,r10,$sp
+ addi r10,r10,32
+ lvx v25,r11,$sp
+ addi r11,r11,32
+ lvx v26,r10,$sp
+ addi r10,r10,32
+ lvx v27,r11,$sp
+ addi r11,r11,32
+ lvx v28,r10,$sp
+ addi r10,r10,32
+ lvx v29,r11,$sp
+ addi r11,r11,32
+ lvx v30,r10,$sp
+ lvx v31,r11,$sp
+ $POP r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+ $POP r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+ $POP r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+ $POP r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+ $POP r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+ $POP r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+ addi $sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+ blr
+ .long 0
+ .byte 0,12,0x04,1,0x80,6,6,0
+ .long 0
+
+.align 5
+_aesp8_xts_enc5x:
+ vcipher $out0,$out0,v24
+ vcipher $out1,$out1,v24
+ vcipher $out2,$out2,v24
+ vcipher $out3,$out3,v24
+ vcipher $out4,$out4,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vcipher $out0,$out0,v25
+ vcipher $out1,$out1,v25
+ vcipher $out2,$out2,v25
+ vcipher $out3,$out3,v25
+ vcipher $out4,$out4,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz _aesp8_xts_enc5x
+
+ add $inp,$inp,$taillen
+ cmpwi $taillen,0
+ vcipher $out0,$out0,v24
+ vcipher $out1,$out1,v24
+ vcipher $out2,$out2,v24
+ vcipher $out3,$out3,v24
+ vcipher $out4,$out4,v24
+
+ subi $inp,$inp,16
+ vcipher $out0,$out0,v25
+ vcipher $out1,$out1,v25
+ vcipher $out2,$out2,v25
+ vcipher $out3,$out3,v25
+ vcipher $out4,$out4,v25
+ vxor $twk0,$twk0,v31
+
+ vcipher $out0,$out0,v26
+ lvsr $inpperm,r0,$taillen # $in5 is no more
+ vcipher $out1,$out1,v26
+ vcipher $out2,$out2,v26
+ vcipher $out3,$out3,v26
+ vcipher $out4,$out4,v26
+ vxor $in1,$twk1,v31
+
+ vcipher $out0,$out0,v27
+ lvx_u $in0,0,$inp
+ vcipher $out1,$out1,v27
+ vcipher $out2,$out2,v27
+ vcipher $out3,$out3,v27
+ vcipher $out4,$out4,v27
+ vxor $in2,$twk2,v31
+
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ vcipher $out0,$out0,v28
+ vcipher $out1,$out1,v28
+ vcipher $out2,$out2,v28
+ vcipher $out3,$out3,v28
+ vcipher $out4,$out4,v28
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+ vxor $in3,$twk3,v31
+
+ vcipher $out0,$out0,v29
+ le?vperm $in0,$in0,$in0,$leperm
+ vcipher $out1,$out1,v29
+ vcipher $out2,$out2,v29
+ vcipher $out3,$out3,v29
+ vcipher $out4,$out4,v29
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+ vxor $in4,$twk4,v31
+
+ vcipher $out0,$out0,v30
+ vperm $in0,$in0,$in0,$inpperm
+ vcipher $out1,$out1,v30
+ vcipher $out2,$out2,v30
+ vcipher $out3,$out3,v30
+ vcipher $out4,$out4,v30
+
+ vcipherlast $out0,$out0,$twk0
+ vcipherlast $out1,$out1,$in1
+ vcipherlast $out2,$out2,$in2
+ vcipherlast $out3,$out3,$in3
+ vcipherlast $out4,$out4,$in4
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,0,0
+
+.align 5
+_aesp8_xts_decrypt6x:
+ $STU $sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+ mflr r11
+ li r7,`$FRAME+8*16+15`
+ li r3,`$FRAME+8*16+31`
+ $PUSH r11,`$FRAME+21*16+6*$SIZE_T+$LRSAVE`($sp)
+ stvx v20,r7,$sp # ABI says so
+ addi r7,r7,32
+ stvx v21,r3,$sp
+ addi r3,r3,32
+ stvx v22,r7,$sp
+ addi r7,r7,32
+ stvx v23,r3,$sp
+ addi r3,r3,32
+ stvx v24,r7,$sp
+ addi r7,r7,32
+ stvx v25,r3,$sp
+ addi r3,r3,32
+ stvx v26,r7,$sp
+ addi r7,r7,32
+ stvx v27,r3,$sp
+ addi r3,r3,32
+ stvx v28,r7,$sp
+ addi r7,r7,32
+ stvx v29,r3,$sp
+ addi r3,r3,32
+ stvx v30,r7,$sp
+ stvx v31,r3,$sp
+ li r0,-1
+ stw $vrsave,`$FRAME+21*16-4`($sp) # save vrsave
+ li $x10,0x10
+ $PUSH r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+ li $x20,0x20
+ $PUSH r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+ li $x30,0x30
+ $PUSH r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+ li $x40,0x40
+ $PUSH r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+ li $x50,0x50
+ $PUSH r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+ li $x60,0x60
+ $PUSH r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+ li $x70,0x70
+ mtspr 256,r0
+
+ xxlor 2, 32+$eighty7, 32+$eighty7
+ vsldoi $eighty7,$tmp,$eighty7,1 # 0x010101..87
+ xxlor 1, 32+$eighty7, 32+$eighty7
+
+ # Load XOR Lconsts.
+ mr $x70, r6
+ bl Lconsts
+ lxvw4x 0, $x40, r6 # load XOR contents
+ mr r6, $x70
+ li $x70,0x70
+
+ subi $rounds,$rounds,3 # -4 in total
+
+ lvx $rndkey0,$x00,$key1 # load key schedule
+ lvx v30,$x10,$key1
+ addi $key1,$key1,0x20
+ lvx v31,$x00,$key1
+ ?vperm $rndkey0,$rndkey0,v30,$keyperm
+ addi $key_,$sp,$FRAME+15
+ mtctr $rounds
+
+Load_xts_dec_key:
+ ?vperm v24,v30,v31,$keyperm
+ lvx v30,$x10,$key1
+ addi $key1,$key1,0x20
+ stvx v24,$x00,$key_ # off-load round[1]
+ ?vperm v25,v31,v30,$keyperm
+ lvx v31,$x00,$key1
+ stvx v25,$x10,$key_ # off-load round[2]
+ addi $key_,$key_,0x20
+ bdnz Load_xts_dec_key
+
+ lvx v26,$x10,$key1
+ ?vperm v24,v30,v31,$keyperm
+ lvx v27,$x20,$key1
+ stvx v24,$x00,$key_ # off-load round[3]
+ ?vperm v25,v31,v26,$keyperm
+ lvx v28,$x30,$key1
+ stvx v25,$x10,$key_ # off-load round[4]
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ ?vperm v26,v26,v27,$keyperm
+ lvx v29,$x40,$key1
+ ?vperm v27,v27,v28,$keyperm
+ lvx v30,$x50,$key1
+ ?vperm v28,v28,v29,$keyperm
+ lvx v31,$x60,$key1
+ ?vperm v29,v29,v30,$keyperm
+ lvx $twk5,$x70,$key1 # borrow $twk5
+ ?vperm v30,v30,v31,$keyperm
+ lvx v24,$x00,$key_ # pre-load round[1]
+ ?vperm v31,v31,$twk5,$keyperm
+ lvx v25,$x10,$key_ # pre-load round[2]
+
+ vperm $in0,$inout,$inptail,$inpperm
+ subi $inp,$inp,31 # undo "caller"
+ vxor $twk0,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ vand $tmp,$tmp,$eighty7
+ vxor $out0,$in0,$twk0
+ xxlor 32+$in1, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in1
+
+ lvx_u $in1,$x10,$inp
+ vxor $twk1,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in1,$in1,$in1,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out1,$in1,$twk1
+ xxlor 32+$in2, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in2
+
+ lvx_u $in2,$x20,$inp
+ andi. $taillen,$len,15
+ vxor $twk2,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in2,$in2,$in2,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out2,$in2,$twk2
+ xxlor 32+$in3, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in3
+
+ lvx_u $in3,$x30,$inp
+ sub $len,$len,$taillen
+ vxor $twk3,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in3,$in3,$in3,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out3,$in3,$twk3
+ xxlor 32+$in4, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in4
+
+ lvx_u $in4,$x40,$inp
+ subi $len,$len,0x60
+ vxor $twk4,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in4,$in4,$in4,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out4,$in4,$twk4
+ xxlor 32+$in5, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in5
+
+ lvx_u $in5,$x50,$inp
+ addi $inp,$inp,0x60
+ vxor $twk5,$tweak,$rndkey0
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vaddubm $tweak,$tweak,$tweak
+ le?vperm $in5,$in5,$in5,$leperm
+ vand $tmp,$tmp,$eighty7
+ vxor $out5,$in5,$twk5
+ xxlor 32+$in0, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in0
+
+ vxor v31,v31,$rndkey0
+ mtctr $rounds
+ b Loop_xts_dec6x
+
+.align 5
+Loop_xts_dec6x:
+ vncipher $out0,$out0,v24
+ vncipher $out1,$out1,v24
+ vncipher $out2,$out2,v24
+ vncipher $out3,$out3,v24
+ vncipher $out4,$out4,v24
+ vncipher $out5,$out5,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vncipher $out0,$out0,v25
+ vncipher $out1,$out1,v25
+ vncipher $out2,$out2,v25
+ vncipher $out3,$out3,v25
+ vncipher $out4,$out4,v25
+ vncipher $out5,$out5,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz Loop_xts_dec6x
+
+ xxlor 32+$eighty7, 1, 1 # 0x010101..87
+
+ subic $len,$len,96 # $len-=96
+ vxor $in0,$twk0,v31 # xor with last round key
+ vncipher $out0,$out0,v24
+ vncipher $out1,$out1,v24
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk0,$tweak,$rndkey0
+ vaddubm $tweak,$tweak,$tweak
+ vncipher $out2,$out2,v24
+ vncipher $out3,$out3,v24
+ vncipher $out4,$out4,v24
+ vncipher $out5,$out5,v24
+
+ subfe. r0,r0,r0 # borrow?-1:0
+ vand $tmp,$tmp,$eighty7
+ vncipher $out0,$out0,v25
+ vncipher $out1,$out1,v25
+ xxlor 32+$in1, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in1
+ vncipher $out2,$out2,v25
+ vncipher $out3,$out3,v25
+ vxor $in1,$twk1,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk1,$tweak,$rndkey0
+ vncipher $out4,$out4,v25
+ vncipher $out5,$out5,v25
+
+ and r0,r0,$len
+ vaddubm $tweak,$tweak,$tweak
+ vncipher $out0,$out0,v26
+ vncipher $out1,$out1,v26
+ vand $tmp,$tmp,$eighty7
+ vncipher $out2,$out2,v26
+ vncipher $out3,$out3,v26
+ xxlor 32+$in2, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in2
+ vncipher $out4,$out4,v26
+ vncipher $out5,$out5,v26
+
+ add $inp,$inp,r0 # $inp is adjusted in such
+ # way that at exit from the
+ # loop inX-in5 are loaded
+ # with last "words"
+ vxor $in2,$twk2,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk2,$tweak,$rndkey0
+ vaddubm $tweak,$tweak,$tweak
+ vncipher $out0,$out0,v27
+ vncipher $out1,$out1,v27
+ vncipher $out2,$out2,v27
+ vncipher $out3,$out3,v27
+ vand $tmp,$tmp,$eighty7
+ vncipher $out4,$out4,v27
+ vncipher $out5,$out5,v27
+
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ xxlor 32+$in3, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in3
+ vncipher $out0,$out0,v28
+ vncipher $out1,$out1,v28
+ vxor $in3,$twk3,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk3,$tweak,$rndkey0
+ vncipher $out2,$out2,v28
+ vncipher $out3,$out3,v28
+ vaddubm $tweak,$tweak,$tweak
+ vncipher $out4,$out4,v28
+ vncipher $out5,$out5,v28
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+ vand $tmp,$tmp,$eighty7
+
+ vncipher $out0,$out0,v29
+ vncipher $out1,$out1,v29
+ xxlor 32+$in4, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in4
+ vncipher $out2,$out2,v29
+ vncipher $out3,$out3,v29
+ vxor $in4,$twk4,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk4,$tweak,$rndkey0
+ vncipher $out4,$out4,v29
+ vncipher $out5,$out5,v29
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+ vaddubm $tweak,$tweak,$tweak
+
+ vncipher $out0,$out0,v30
+ vncipher $out1,$out1,v30
+ vand $tmp,$tmp,$eighty7
+ vncipher $out2,$out2,v30
+ vncipher $out3,$out3,v30
+ xxlor 32+$in5, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in5
+ vncipher $out4,$out4,v30
+ vncipher $out5,$out5,v30
+ vxor $in5,$twk5,v31
+ vsrab $tmp,$tweak,$seven # next tweak value
+ vxor $twk5,$tweak,$rndkey0
+
+ vncipherlast $out0,$out0,$in0
+ lvx_u $in0,$x00,$inp # load next input block
+ vaddubm $tweak,$tweak,$tweak
+ vncipherlast $out1,$out1,$in1
+ lvx_u $in1,$x10,$inp
+ vncipherlast $out2,$out2,$in2
+ le?vperm $in0,$in0,$in0,$leperm
+ lvx_u $in2,$x20,$inp
+ vand $tmp,$tmp,$eighty7
+ vncipherlast $out3,$out3,$in3
+ le?vperm $in1,$in1,$in1,$leperm
+ lvx_u $in3,$x30,$inp
+ vncipherlast $out4,$out4,$in4
+ le?vperm $in2,$in2,$in2,$leperm
+ lvx_u $in4,$x40,$inp
+ xxlor 10, 32+$in0, 32+$in0
+ xxlor 32+$in0, 0, 0
+ vpermxor $tweak, $tweak, $tmp, $in0
+ xxlor 32+$in0, 10, 10
+ vncipherlast $out5,$out5,$in5
+ le?vperm $in3,$in3,$in3,$leperm
+ lvx_u $in5,$x50,$inp
+ addi $inp,$inp,0x60
+ le?vperm $in4,$in4,$in4,$leperm
+ le?vperm $in5,$in5,$in5,$leperm
+
+ le?vperm $out0,$out0,$out0,$leperm
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ vxor $out0,$in0,$twk0
+ le?vperm $out2,$out2,$out2,$leperm
+ stvx_u $out1,$x10,$out
+ vxor $out1,$in1,$twk1
+ le?vperm $out3,$out3,$out3,$leperm
+ stvx_u $out2,$x20,$out
+ vxor $out2,$in2,$twk2
+ le?vperm $out4,$out4,$out4,$leperm
+ stvx_u $out3,$x30,$out
+ vxor $out3,$in3,$twk3
+ le?vperm $out5,$out5,$out5,$leperm
+ stvx_u $out4,$x40,$out
+ vxor $out4,$in4,$twk4
+ stvx_u $out5,$x50,$out
+ vxor $out5,$in5,$twk5
+ addi $out,$out,0x60
+
+ mtctr $rounds
+ beq Loop_xts_dec6x # did $len-=96 borrow?
+
+ xxlor 32+$eighty7, 2, 2 # 0x010101..87
+
+ addic. $len,$len,0x60
+ beq Lxts_dec6x_zero
+ cmpwi $len,0x20
+ blt Lxts_dec6x_one
+ nop
+ beq Lxts_dec6x_two
+ cmpwi $len,0x40
+ blt Lxts_dec6x_three
+ nop
+ beq Lxts_dec6x_four
+
+Lxts_dec6x_five:
+ vxor $out0,$in1,$twk0
+ vxor $out1,$in2,$twk1
+ vxor $out2,$in3,$twk2
+ vxor $out3,$in4,$twk3
+ vxor $out4,$in5,$twk4
+
+ bl _aesp8_xts_dec5x
+
+ le?vperm $out0,$out0,$out0,$leperm
+ vmr $twk0,$twk5 # unused tweak
+ vxor $twk1,$tweak,$rndkey0
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ vxor $out0,$in0,$twk1
+ le?vperm $out2,$out2,$out2,$leperm
+ stvx_u $out1,$x10,$out
+ le?vperm $out3,$out3,$out3,$leperm
+ stvx_u $out2,$x20,$out
+ le?vperm $out4,$out4,$out4,$leperm
+ stvx_u $out3,$x30,$out
+ stvx_u $out4,$x40,$out
+ addi $out,$out,0x50
+ bne Lxts_dec6x_steal
+ b Lxts_dec6x_done
+
+.align 4
+Lxts_dec6x_four:
+ vxor $out0,$in2,$twk0
+ vxor $out1,$in3,$twk1
+ vxor $out2,$in4,$twk2
+ vxor $out3,$in5,$twk3
+ vxor $out4,$out4,$out4
+
+ bl _aesp8_xts_dec5x
+
+ le?vperm $out0,$out0,$out0,$leperm
+ vmr $twk0,$twk4 # unused tweak
+ vmr $twk1,$twk5
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ vxor $out0,$in0,$twk5
+ le?vperm $out2,$out2,$out2,$leperm
+ stvx_u $out1,$x10,$out
+ le?vperm $out3,$out3,$out3,$leperm
+ stvx_u $out2,$x20,$out
+ stvx_u $out3,$x30,$out
+ addi $out,$out,0x40
+ bne Lxts_dec6x_steal
+ b Lxts_dec6x_done
+
+.align 4
+Lxts_dec6x_three:
+ vxor $out0,$in3,$twk0
+ vxor $out1,$in4,$twk1
+ vxor $out2,$in5,$twk2
+ vxor $out3,$out3,$out3
+ vxor $out4,$out4,$out4
+
+ bl _aesp8_xts_dec5x
+
+ le?vperm $out0,$out0,$out0,$leperm
+ vmr $twk0,$twk3 # unused tweak
+ vmr $twk1,$twk4
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ vxor $out0,$in0,$twk4
+ le?vperm $out2,$out2,$out2,$leperm
+ stvx_u $out1,$x10,$out
+ stvx_u $out2,$x20,$out
+ addi $out,$out,0x30
+ bne Lxts_dec6x_steal
+ b Lxts_dec6x_done
+
+.align 4
+Lxts_dec6x_two:
+ vxor $out0,$in4,$twk0
+ vxor $out1,$in5,$twk1
+ vxor $out2,$out2,$out2
+ vxor $out3,$out3,$out3
+ vxor $out4,$out4,$out4
+
+ bl _aesp8_xts_dec5x
+
+ le?vperm $out0,$out0,$out0,$leperm
+ vmr $twk0,$twk2 # unused tweak
+ vmr $twk1,$twk3
+ le?vperm $out1,$out1,$out1,$leperm
+ stvx_u $out0,$x00,$out # store output
+ vxor $out0,$in0,$twk3
+ stvx_u $out1,$x10,$out
+ addi $out,$out,0x20
+ bne Lxts_dec6x_steal
+ b Lxts_dec6x_done
+
+.align 4
+Lxts_dec6x_one:
+ vxor $out0,$in5,$twk0
+ nop
+Loop_xts_dec1x:
+ vncipher $out0,$out0,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vncipher $out0,$out0,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz Loop_xts_dec1x
+
+ subi r0,$taillen,1
+ vncipher $out0,$out0,v24
+
+ andi. r0,r0,16
+ cmpwi $taillen,0
+ vncipher $out0,$out0,v25
+
+ sub $inp,$inp,r0
+ vncipher $out0,$out0,v26
+
+ lvx_u $in0,0,$inp
+ vncipher $out0,$out0,v27
+
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ vncipher $out0,$out0,v28
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+
+ vncipher $out0,$out0,v29
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+ vxor $twk0,$twk0,v31
+
+ le?vperm $in0,$in0,$in0,$leperm
+ vncipher $out0,$out0,v30
+
+ mtctr $rounds
+ vncipherlast $out0,$out0,$twk0
+
+ vmr $twk0,$twk1 # unused tweak
+ vmr $twk1,$twk2
+ le?vperm $out0,$out0,$out0,$leperm
+ stvx_u $out0,$x00,$out # store output
+ addi $out,$out,0x10
+ vxor $out0,$in0,$twk2
+ bne Lxts_dec6x_steal
+ b Lxts_dec6x_done
+
+.align 4
+Lxts_dec6x_zero:
+ cmpwi $taillen,0
+ beq Lxts_dec6x_done
+
+ lvx_u $in0,0,$inp
+ le?vperm $in0,$in0,$in0,$leperm
+ vxor $out0,$in0,$twk1
+Lxts_dec6x_steal:
+ vncipher $out0,$out0,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vncipher $out0,$out0,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz Lxts_dec6x_steal
+
+ add $inp,$inp,$taillen
+ vncipher $out0,$out0,v24
+
+ cmpwi $taillen,0
+ vncipher $out0,$out0,v25
+
+ lvx_u $in0,0,$inp
+ vncipher $out0,$out0,v26
+
+ lvsr $inpperm,0,$taillen # $in5 is no more
+ vncipher $out0,$out0,v27
+
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ vncipher $out0,$out0,v28
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+
+ vncipher $out0,$out0,v29
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+ vxor $twk1,$twk1,v31
+
+ le?vperm $in0,$in0,$in0,$leperm
+ vncipher $out0,$out0,v30
+
+ vperm $in0,$in0,$in0,$inpperm
+ vncipherlast $tmp,$out0,$twk1
+
+ le?vperm $out0,$tmp,$tmp,$leperm
+ le?stvx_u $out0,0,$out
+ be?stvx_u $tmp,0,$out
+
+ vxor $out0,$out0,$out0
+ vspltisb $out1,-1
+ vperm $out0,$out0,$out1,$inpperm
+ vsel $out0,$in0,$tmp,$out0
+ vxor $out0,$out0,$twk0
+
+ subi r30,$out,1
+ mtctr $taillen
+Loop_xts_dec6x_steal:
+ lbzu r0,1(r30)
+ stb r0,16(r30)
+ bdnz Loop_xts_dec6x_steal
+
+ li $taillen,0
+ mtctr $rounds
+ b Loop_xts_dec1x # one more time...
+
+.align 4
+Lxts_dec6x_done:
+ ${UCMP}i $ivp,0
+ beq Lxts_dec6x_ret
+
+ vxor $tweak,$twk0,$rndkey0
+ le?vperm $tweak,$tweak,$tweak,$leperm
+ stvx_u $tweak,0,$ivp
+
+Lxts_dec6x_ret:
+ mtlr r11
+ li r10,`$FRAME+15`
+ li r11,`$FRAME+31`
+ stvx $seven,r10,$sp # wipe copies of round keys
+ addi r10,r10,32
+ stvx $seven,r11,$sp
+ addi r11,r11,32
+ stvx $seven,r10,$sp
+ addi r10,r10,32
+ stvx $seven,r11,$sp
+ addi r11,r11,32
+ stvx $seven,r10,$sp
+ addi r10,r10,32
+ stvx $seven,r11,$sp
+ addi r11,r11,32
+ stvx $seven,r10,$sp
+ addi r10,r10,32
+ stvx $seven,r11,$sp
+ addi r11,r11,32
+
+ mtspr 256,$vrsave
+ lvx v20,r10,$sp # ABI says so
+ addi r10,r10,32
+ lvx v21,r11,$sp
+ addi r11,r11,32
+ lvx v22,r10,$sp
+ addi r10,r10,32
+ lvx v23,r11,$sp
+ addi r11,r11,32
+ lvx v24,r10,$sp
+ addi r10,r10,32
+ lvx v25,r11,$sp
+ addi r11,r11,32
+ lvx v26,r10,$sp
+ addi r10,r10,32
+ lvx v27,r11,$sp
+ addi r11,r11,32
+ lvx v28,r10,$sp
+ addi r10,r10,32
+ lvx v29,r11,$sp
+ addi r11,r11,32
+ lvx v30,r10,$sp
+ lvx v31,r11,$sp
+ $POP r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+ $POP r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+ $POP r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+ $POP r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+ $POP r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+ $POP r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+ addi $sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+ blr
+ .long 0
+ .byte 0,12,0x04,1,0x80,6,6,0
+ .long 0
+
+.align 5
+_aesp8_xts_dec5x:
+ vncipher $out0,$out0,v24
+ vncipher $out1,$out1,v24
+ vncipher $out2,$out2,v24
+ vncipher $out3,$out3,v24
+ vncipher $out4,$out4,v24
+ lvx v24,$x20,$key_ # round[3]
+ addi $key_,$key_,0x20
+
+ vncipher $out0,$out0,v25
+ vncipher $out1,$out1,v25
+ vncipher $out2,$out2,v25
+ vncipher $out3,$out3,v25
+ vncipher $out4,$out4,v25
+ lvx v25,$x10,$key_ # round[4]
+ bdnz _aesp8_xts_dec5x
+
+ subi r0,$taillen,1
+ vncipher $out0,$out0,v24
+ vncipher $out1,$out1,v24
+ vncipher $out2,$out2,v24
+ vncipher $out3,$out3,v24
+ vncipher $out4,$out4,v24
+
+ andi. r0,r0,16
+ cmpwi $taillen,0
+ vncipher $out0,$out0,v25
+ vncipher $out1,$out1,v25
+ vncipher $out2,$out2,v25
+ vncipher $out3,$out3,v25
+ vncipher $out4,$out4,v25
+ vxor $twk0,$twk0,v31
+
+ sub $inp,$inp,r0
+ vncipher $out0,$out0,v26
+ vncipher $out1,$out1,v26
+ vncipher $out2,$out2,v26
+ vncipher $out3,$out3,v26
+ vncipher $out4,$out4,v26
+ vxor $in1,$twk1,v31
+
+ vncipher $out0,$out0,v27
+ lvx_u $in0,0,$inp
+ vncipher $out1,$out1,v27
+ vncipher $out2,$out2,v27
+ vncipher $out3,$out3,v27
+ vncipher $out4,$out4,v27
+ vxor $in2,$twk2,v31
+
+ addi $key_,$sp,$FRAME+15 # rewind $key_
+ vncipher $out0,$out0,v28
+ vncipher $out1,$out1,v28
+ vncipher $out2,$out2,v28
+ vncipher $out3,$out3,v28
+ vncipher $out4,$out4,v28
+ lvx v24,$x00,$key_ # re-pre-load round[1]
+ vxor $in3,$twk3,v31
+
+ vncipher $out0,$out0,v29
+ le?vperm $in0,$in0,$in0,$leperm
+ vncipher $out1,$out1,v29
+ vncipher $out2,$out2,v29
+ vncipher $out3,$out3,v29
+ vncipher $out4,$out4,v29
+ lvx v25,$x10,$key_ # re-pre-load round[2]
+ vxor $in4,$twk4,v31
+
+ vncipher $out0,$out0,v30
+ vncipher $out1,$out1,v30
+ vncipher $out2,$out2,v30
+ vncipher $out3,$out3,v30
+ vncipher $out4,$out4,v30
+
+ vncipherlast $out0,$out0,$twk0
+ vncipherlast $out1,$out1,$in1
+ vncipherlast $out2,$out2,$in2
+ vncipherlast $out3,$out3,$in3
+ vncipherlast $out4,$out4,$in4
+ mtctr $rounds
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,0,0
+___
+}} }}}
+
+my $consts=1;
+foreach(split("\n",$code)) {
+ s/\`([^\`]*)\`/eval($1)/geo;
+
+ # constants table endian-specific conversion
+ if ($consts && m/\.(long|byte)\s+(.+)\s+(\?[a-z]*)$/o) {
+ my $conv=$3;
+ my @bytes=();
+
+ # convert to endian-agnostic format
+ if ($1 eq "long") {
+ foreach (split(/,\s*/,$2)) {
+ my $l = /^0/?oct:int;
+ push @bytes,($l>>24)&0xff,($l>>16)&0xff,($l>>8)&0xff,$l&0xff;
+ }
+ } else {
+ @bytes = map(/^0/?oct:int,split(/,\s*/,$2));
+ }
+
+ # little-endian conversion
+ if ($flavour =~ /le$/o) {
+ SWITCH: for($conv) {
+ /\?inv/ && do { @bytes=map($_^0xf,@bytes); last; };
+ /\?rev/ && do { @bytes=reverse(@bytes); last; };
+ }
+ }
+
+ #emit
+ print ".byte\t",join(',',map (sprintf("0x%02x",$_),@bytes)),"\n";
+ next;
+ }
+ $consts=0 if (m/Lconsts:/o); # end of table
+
+ # instructions prefixed with '?' are endian-specific and need
+ # to be adjusted accordingly...
+ if ($flavour =~ /le$/o) { # little-endian
+ s/le\?//o or
+ s/be\?/#be#/o or
+ s/\?lvsr/lvsl/o or
+ s/\?lvsl/lvsr/o or
+ s/\?(vperm\s+v[0-9]+,\s*)(v[0-9]+,\s*)(v[0-9]+,\s*)(v[0-9]+)/$1$3$2$4/o or
+ s/\?(vsldoi\s+v[0-9]+,\s*)(v[0-9]+,)\s*(v[0-9]+,\s*)([0-9]+)/$1$3$2 16-$4/o or
+ s/\?(vspltw\s+v[0-9]+,\s*)(v[0-9]+,)\s*([0-9])/$1$2 3-$3/o;
+ } else { # big-endian
+ s/le\?/#le#/o or
+ s/be\?//o or
+ s/\?([a-z]+)/$1/o;
+ }
+
+ print $_,"\n";
+}
+
+close STDOUT;
diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c
index 74fb86b0d209..7c728755852e 100644
--- a/arch/powerpc/crypto/chacha-p10-glue.c
+++ b/arch/powerpc/crypto/chacha-p10-glue.c
@@ -197,6 +197,9 @@ static struct skcipher_alg algs[] = {
static int __init chacha_p10_init(void)
{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return 0;
+
static_branch_enable(&have_p10);
return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
@@ -204,10 +207,13 @@ static int __init chacha_p10_init(void)
static void __exit chacha_p10_exit(void)
{
+ if (!static_branch_likely(&have_p10))
+ return;
+
crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
}
-module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init);
+module_init(chacha_p10_init);
module_exit(chacha_p10_exit);
MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)");
diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
deleted file mode 100644
index c61a874a3a5c..000000000000
--- a/arch/powerpc/crypto/crc-vpmsum_test.c
+++ /dev/null
@@ -1,133 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * CRC vpmsum tester
- * Copyright 2017 Daniel Axtens, IBM Corporation.
- */
-
-#include <linux/crc-t10dif.h>
-#include <linux/crc32.h>
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/random.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/cpufeature.h>
-#include <asm/switch_to.h>
-
-static unsigned long iterations = 10000;
-
-#define MAX_CRC_LENGTH 65535
-
-
-static int __init crc_test_init(void)
-{
- u16 crc16 = 0, verify16 = 0;
- __le32 verify32le = 0;
- unsigned char *data;
- u32 verify32 = 0;
- unsigned long i;
- __le32 crc32;
- int ret;
-
- struct crypto_shash *crct10dif_tfm;
- struct crypto_shash *crc32c_tfm;
-
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- data = kmalloc(MAX_CRC_LENGTH, GFP_KERNEL);
- if (!data)
- return -ENOMEM;
-
- crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
-
- if (IS_ERR(crct10dif_tfm)) {
- pr_err("Error allocating crc-t10dif\n");
- goto free_buf;
- }
-
- crc32c_tfm = crypto_alloc_shash("crc32c", 0, 0);
-
- if (IS_ERR(crc32c_tfm)) {
- pr_err("Error allocating crc32c\n");
- goto free_16;
- }
-
- do {
- SHASH_DESC_ON_STACK(crct10dif_shash, crct10dif_tfm);
- SHASH_DESC_ON_STACK(crc32c_shash, crc32c_tfm);
-
- crct10dif_shash->tfm = crct10dif_tfm;
- ret = crypto_shash_init(crct10dif_shash);
-
- if (ret) {
- pr_err("Error initing crc-t10dif\n");
- goto free_32;
- }
-
-
- crc32c_shash->tfm = crc32c_tfm;
- ret = crypto_shash_init(crc32c_shash);
-
- if (ret) {
- pr_err("Error initing crc32c\n");
- goto free_32;
- }
-
- pr_info("crc-vpmsum_test begins, %lu iterations\n", iterations);
- for (i=0; i<iterations; i++) {
- size_t offset = get_random_u32_below(16);
- size_t len = get_random_u32_below(MAX_CRC_LENGTH);
-
- if (len <= offset)
- continue;
- get_random_bytes(data, len);
- len -= offset;
-
- crypto_shash_update(crct10dif_shash, data+offset, len);
- crypto_shash_final(crct10dif_shash, (u8 *)(&crc16));
- verify16 = crc_t10dif_generic(verify16, data+offset, len);
-
-
- if (crc16 != verify16) {
- pr_err("FAILURE in CRC16: got 0x%04x expected 0x%04x (len %lu)\n",
- crc16, verify16, len);
- break;
- }
-
- crypto_shash_update(crc32c_shash, data+offset, len);
- crypto_shash_final(crc32c_shash, (u8 *)(&crc32));
- verify32 = le32_to_cpu(verify32le);
- verify32le = ~cpu_to_le32(__crc32c_le(~verify32, data+offset, len));
- if (crc32 != verify32le) {
- pr_err("FAILURE in CRC32: got 0x%08x expected 0x%08x (len %lu)\n",
- crc32, verify32, len);
- break;
- }
- cond_resched();
- }
- pr_info("crc-vpmsum_test done, completed %lu iterations\n", i);
- } while (0);
-
-free_32:
- crypto_free_shash(crc32c_tfm);
-
-free_16:
- crypto_free_shash(crct10dif_tfm);
-
-free_buf:
- kfree(data);
-
- return 0;
-}
-
-static void __exit crc_test_exit(void) {}
-
-module_init(crc_test_init);
-module_exit(crc_test_exit);
-module_param(iterations, long, 0400);
-
-MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
-MODULE_DESCRIPTION("Vector polynomial multiply-sum CRC tester");
-MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
deleted file mode 100644
index 63760b7dbb76..000000000000
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ /dev/null
@@ -1,173 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#include <linux/crc32.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/cpufeature.h>
-#include <asm/simd.h>
-#include <asm/switch_to.h>
-
-#define CHKSUM_BLOCK_SIZE 1
-#define CHKSUM_DIGEST_SIZE 4
-
-#define VMX_ALIGN 16
-#define VMX_ALIGN_MASK (VMX_ALIGN-1)
-
-#define VECTOR_BREAKPOINT 512
-
-u32 __crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len);
-
-static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
-{
- unsigned int prealign;
- unsigned int tail;
-
- if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable())
- return __crc32c_le(crc, p, len);
-
- if ((unsigned long)p & VMX_ALIGN_MASK) {
- prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
- crc = __crc32c_le(crc, p, prealign);
- len -= prealign;
- p += prealign;
- }
-
- if (len & ~VMX_ALIGN_MASK) {
- preempt_disable();
- pagefault_disable();
- enable_kernel_altivec();
- crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
- disable_kernel_altivec();
- pagefault_enable();
- preempt_enable();
- }
-
- tail = len & VMX_ALIGN_MASK;
- if (tail) {
- p += len & ~VMX_ALIGN_MASK;
- crc = __crc32c_le(crc, p, tail);
- }
-
- return crc;
-}
-
-static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
-{
- u32 *key = crypto_tfm_ctx(tfm);
-
- *key = ~0;
-
- return 0;
-}
-
-/*
- * Setting the seed allows arbitrary accumulators and flexible XOR policy
- * If your algorithm starts with ~0, then XOR with ~0 before you set
- * the seed.
- */
-static int crc32c_vpmsum_setkey(struct crypto_shash *hash, const u8 *key,
- unsigned int keylen)
-{
- u32 *mctx = crypto_shash_ctx(hash);
-
- if (keylen != sizeof(u32))
- return -EINVAL;
- *mctx = le32_to_cpup((__le32 *)key);
- return 0;
-}
-
-static int crc32c_vpmsum_init(struct shash_desc *desc)
-{
- u32 *mctx = crypto_shash_ctx(desc->tfm);
- u32 *crcp = shash_desc_ctx(desc);
-
- *crcp = *mctx;
-
- return 0;
-}
-
-static int crc32c_vpmsum_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- u32 *crcp = shash_desc_ctx(desc);
-
- *crcp = crc32c_vpmsum(*crcp, data, len);
-
- return 0;
-}
-
-static int __crc32c_vpmsum_finup(u32 *crcp, const u8 *data, unsigned int len,
- u8 *out)
-{
- *(__le32 *)out = ~cpu_to_le32(crc32c_vpmsum(*crcp, data, len));
-
- return 0;
-}
-
-static int crc32c_vpmsum_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return __crc32c_vpmsum_finup(shash_desc_ctx(desc), data, len, out);
-}
-
-static int crc32c_vpmsum_final(struct shash_desc *desc, u8 *out)
-{
- u32 *crcp = shash_desc_ctx(desc);
-
- *(__le32 *)out = ~cpu_to_le32p(crcp);
-
- return 0;
-}
-
-static int crc32c_vpmsum_digest(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return __crc32c_vpmsum_finup(crypto_shash_ctx(desc->tfm), data, len,
- out);
-}
-
-static struct shash_alg alg = {
- .setkey = crc32c_vpmsum_setkey,
- .init = crc32c_vpmsum_init,
- .update = crc32c_vpmsum_update,
- .final = crc32c_vpmsum_final,
- .finup = crc32c_vpmsum_finup,
- .digest = crc32c_vpmsum_digest,
- .descsize = sizeof(u32),
- .digestsize = CHKSUM_DIGEST_SIZE,
- .base = {
- .cra_name = "crc32c",
- .cra_driver_name = "crc32c-vpmsum",
- .cra_priority = 200,
- .cra_flags = CRYPTO_ALG_OPTIONAL_KEY,
- .cra_blocksize = CHKSUM_BLOCK_SIZE,
- .cra_ctxsize = sizeof(u32),
- .cra_module = THIS_MODULE,
- .cra_init = crc32c_vpmsum_cra_init,
- }
-};
-
-static int __init crc32c_vpmsum_mod_init(void)
-{
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- return crypto_register_shash(&alg);
-}
-
-static void __exit crc32c_vpmsum_mod_fini(void)
-{
- crypto_unregister_shash(&alg);
-}
-
-module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init);
-module_exit(crc32c_vpmsum_mod_fini);
-
-MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
-MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("crc32c");
-MODULE_ALIAS_CRYPTO("crc32c-vpmsum");
diff --git a/arch/powerpc/crypto/curve25519-ppc64le-core.c b/arch/powerpc/crypto/curve25519-ppc64le-core.c
new file mode 100644
index 000000000000..f7810be0b292
--- /dev/null
+++ b/arch/powerpc/crypto/curve25519-ppc64le-core.c
@@ -0,0 +1,300 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2024- IBM Corp.
+ *
+ * X25519 scalar multiplication with 51 bits limbs for PPC64le.
+ * Based on RFC7748 and AArch64 optimized implementation for X25519
+ * - Algorithm 1 Scalar multiplication of a variable point
+ */
+
+#include <crypto/curve25519.h>
+#include <crypto/internal/kpp.h>
+
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+
+#include <linux/cpufeature.h>
+#include <linux/processor.h>
+
+typedef uint64_t fe51[5];
+
+asmlinkage void x25519_fe51_mul(fe51 h, const fe51 f, const fe51 g);
+asmlinkage void x25519_fe51_sqr(fe51 h, const fe51 f);
+asmlinkage void x25519_fe51_mul121666(fe51 h, fe51 f);
+asmlinkage void x25519_fe51_sqr_times(fe51 h, const fe51 f, int n);
+asmlinkage void x25519_fe51_frombytes(fe51 h, const uint8_t *s);
+asmlinkage void x25519_fe51_tobytes(uint8_t *s, const fe51 h);
+asmlinkage void x25519_cswap(fe51 p, fe51 q, unsigned int bit);
+
+#define fmul x25519_fe51_mul
+#define fsqr x25519_fe51_sqr
+#define fmul121666 x25519_fe51_mul121666
+#define fe51_tobytes x25519_fe51_tobytes
+
+static void fadd(fe51 h, const fe51 f, const fe51 g)
+{
+ h[0] = f[0] + g[0];
+ h[1] = f[1] + g[1];
+ h[2] = f[2] + g[2];
+ h[3] = f[3] + g[3];
+ h[4] = f[4] + g[4];
+}
+
+/*
+ * Prime = 2 ** 255 - 19, 255 bits
+ * (0x7fffffff ffffffff ffffffff ffffffff ffffffff ffffffff ffffffff ffffffed)
+ *
+ * Prime in 5 51-bit limbs
+ */
+static fe51 prime51 = { 0x7ffffffffffed, 0x7ffffffffffff, 0x7ffffffffffff, 0x7ffffffffffff, 0x7ffffffffffff};
+
+static void fsub(fe51 h, const fe51 f, const fe51 g)
+{
+ h[0] = (f[0] + ((prime51[0] * 2))) - g[0];
+ h[1] = (f[1] + ((prime51[1] * 2))) - g[1];
+ h[2] = (f[2] + ((prime51[2] * 2))) - g[2];
+ h[3] = (f[3] + ((prime51[3] * 2))) - g[3];
+ h[4] = (f[4] + ((prime51[4] * 2))) - g[4];
+}
+
+static void fe51_frombytes(fe51 h, const uint8_t *s)
+{
+ /*
+ * Make sure 64-bit aligned.
+ */
+ unsigned char sbuf[32+8];
+ unsigned char *sb = PTR_ALIGN((void *)sbuf, 8);
+
+ memcpy(sb, s, 32);
+ x25519_fe51_frombytes(h, sb);
+}
+
+static void finv(fe51 o, const fe51 i)
+{
+ fe51 a0, b, c, t00;
+
+ fsqr(a0, i);
+ x25519_fe51_sqr_times(t00, a0, 2);
+
+ fmul(b, t00, i);
+ fmul(a0, b, a0);
+
+ fsqr(t00, a0);
+
+ fmul(b, t00, b);
+ x25519_fe51_sqr_times(t00, b, 5);
+
+ fmul(b, t00, b);
+ x25519_fe51_sqr_times(t00, b, 10);
+
+ fmul(c, t00, b);
+ x25519_fe51_sqr_times(t00, c, 20);
+
+ fmul(t00, t00, c);
+ x25519_fe51_sqr_times(t00, t00, 10);
+
+ fmul(b, t00, b);
+ x25519_fe51_sqr_times(t00, b, 50);
+
+ fmul(c, t00, b);
+ x25519_fe51_sqr_times(t00, c, 100);
+
+ fmul(t00, t00, c);
+ x25519_fe51_sqr_times(t00, t00, 50);
+
+ fmul(t00, t00, b);
+ x25519_fe51_sqr_times(t00, t00, 5);
+
+ fmul(o, t00, a0);
+}
+
+static void curve25519_fe51(uint8_t out[32], const uint8_t scalar[32],
+ const uint8_t point[32])
+{
+ fe51 x1, x2, z2, x3, z3;
+ uint8_t s[32];
+ unsigned int swap = 0;
+ int i;
+
+ memcpy(s, scalar, 32);
+ s[0] &= 0xf8;
+ s[31] &= 0x7f;
+ s[31] |= 0x40;
+ fe51_frombytes(x1, point);
+
+ z2[0] = z2[1] = z2[2] = z2[3] = z2[4] = 0;
+ x3[0] = x1[0];
+ x3[1] = x1[1];
+ x3[2] = x1[2];
+ x3[3] = x1[3];
+ x3[4] = x1[4];
+
+ x2[0] = z3[0] = 1;
+ x2[1] = z3[1] = 0;
+ x2[2] = z3[2] = 0;
+ x2[3] = z3[3] = 0;
+ x2[4] = z3[4] = 0;
+
+ for (i = 254; i >= 0; --i) {
+ unsigned int k_t = 1 & (s[i / 8] >> (i & 7));
+ fe51 a, b, c, d, e;
+ fe51 da, cb, aa, bb;
+ fe51 dacb_p, dacb_m;
+
+ swap ^= k_t;
+ x25519_cswap(x2, x3, swap);
+ x25519_cswap(z2, z3, swap);
+ swap = k_t;
+
+ fsub(b, x2, z2); // B = x_2 - z_2
+ fadd(a, x2, z2); // A = x_2 + z_2
+ fsub(d, x3, z3); // D = x_3 - z_3
+ fadd(c, x3, z3); // C = x_3 + z_3
+
+ fsqr(bb, b); // BB = B^2
+ fsqr(aa, a); // AA = A^2
+ fmul(da, d, a); // DA = D * A
+ fmul(cb, c, b); // CB = C * B
+
+ fsub(e, aa, bb); // E = AA - BB
+ fmul(x2, aa, bb); // x2 = AA * BB
+ fadd(dacb_p, da, cb); // DA + CB
+ fsub(dacb_m, da, cb); // DA - CB
+
+ fmul121666(z3, e); // 121666 * E
+ fsqr(z2, dacb_m); // (DA - CB)^2
+ fsqr(x3, dacb_p); // x3 = (DA + CB)^2
+ fadd(b, bb, z3); // BB + 121666 * E
+ fmul(z3, x1, z2); // z3 = x1 * (DA - CB)^2
+ fmul(z2, e, b); // z2 = e * (BB + (DA + CB)^2)
+ }
+
+ finv(z2, z2);
+ fmul(x2, x2, z2);
+ fe51_tobytes(out, x2);
+}
+
+void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE],
+ const u8 secret[CURVE25519_KEY_SIZE],
+ const u8 basepoint[CURVE25519_KEY_SIZE])
+{
+ curve25519_fe51(mypublic, secret, basepoint);
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE],
+ const u8 secret[CURVE25519_KEY_SIZE])
+{
+ curve25519_fe51(pub, secret, curve25519_base_point);
+}
+EXPORT_SYMBOL(curve25519_base_arch);
+
+static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+ unsigned int len)
+{
+ u8 *secret = kpp_tfm_ctx(tfm);
+
+ if (!len)
+ curve25519_generate_secret(secret);
+ else if (len == CURVE25519_KEY_SIZE &&
+ crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE))
+ memcpy(secret, buf, CURVE25519_KEY_SIZE);
+ else
+ return -EINVAL;
+ return 0;
+}
+
+static int curve25519_generate_public_key(struct kpp_request *req)
+{
+ struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+ const u8 *secret = kpp_tfm_ctx(tfm);
+ u8 buf[CURVE25519_KEY_SIZE];
+ int copied, nbytes;
+
+ if (req->src)
+ return -EINVAL;
+
+ curve25519_base_arch(buf, secret);
+
+ /* might want less than we've got */
+ nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+ copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+ nbytes),
+ buf, nbytes);
+ if (copied != nbytes)
+ return -EINVAL;
+ return 0;
+}
+
+static int curve25519_compute_shared_secret(struct kpp_request *req)
+{
+ struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+ const u8 *secret = kpp_tfm_ctx(tfm);
+ u8 public_key[CURVE25519_KEY_SIZE];
+ u8 buf[CURVE25519_KEY_SIZE];
+ int copied, nbytes;
+
+ if (!req->src)
+ return -EINVAL;
+
+ copied = sg_copy_to_buffer(req->src,
+ sg_nents_for_len(req->src,
+ CURVE25519_KEY_SIZE),
+ public_key, CURVE25519_KEY_SIZE);
+ if (copied != CURVE25519_KEY_SIZE)
+ return -EINVAL;
+
+ curve25519_arch(buf, secret, public_key);
+
+ /* might want less than we've got */
+ nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+ copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+ nbytes),
+ buf, nbytes);
+ if (copied != nbytes)
+ return -EINVAL;
+ return 0;
+}
+
+static unsigned int curve25519_max_size(struct crypto_kpp *tfm)
+{
+ return CURVE25519_KEY_SIZE;
+}
+
+static struct kpp_alg curve25519_alg = {
+ .base.cra_name = "curve25519",
+ .base.cra_driver_name = "curve25519-ppc64le",
+ .base.cra_priority = 200,
+ .base.cra_module = THIS_MODULE,
+ .base.cra_ctxsize = CURVE25519_KEY_SIZE,
+
+ .set_secret = curve25519_set_secret,
+ .generate_public_key = curve25519_generate_public_key,
+ .compute_shared_secret = curve25519_compute_shared_secret,
+ .max_size = curve25519_max_size,
+};
+
+
+static int __init curve25519_mod_init(void)
+{
+ return IS_REACHABLE(CONFIG_CRYPTO_KPP) ?
+ crypto_register_kpp(&curve25519_alg) : 0;
+}
+
+static void __exit curve25519_mod_exit(void)
+{
+ if (IS_REACHABLE(CONFIG_CRYPTO_KPP))
+ crypto_unregister_kpp(&curve25519_alg);
+}
+
+module_init(curve25519_mod_init);
+module_exit(curve25519_mod_exit);
+
+MODULE_ALIAS_CRYPTO("curve25519");
+MODULE_ALIAS_CRYPTO("curve25519-ppc64le");
+MODULE_DESCRIPTION("PPC64le Curve25519 scalar multiplication with 51 bits limbs");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Danny Tsen <dtsen@us.ibm.com>");
diff --git a/arch/powerpc/crypto/curve25519-ppc64le_asm.S b/arch/powerpc/crypto/curve25519-ppc64le_asm.S
new file mode 100644
index 000000000000..06c1febe24b9
--- /dev/null
+++ b/arch/powerpc/crypto/curve25519-ppc64le_asm.S
@@ -0,0 +1,671 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#
+# This code is taken from CRYPTOGAMs[1] and is included here using the option
+# in the license to distribute the code under the GPL. Therefore this program
+# is free software; you can redistribute it and/or modify it under the terms of
+# the GNU General Public License version 2 as published by the Free Software
+# Foundation.
+#
+# [1] https://github.com/dot-asm/cryptogams/
+
+# Copyright (c) 2006-2017, CRYPTOGAMS by <appro@openssl.org>
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+# * Redistributions of source code must retain copyright notices,
+# this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above
+# copyright notice, this list of conditions and the following
+# disclaimer in the documentation and/or other materials
+# provided with the distribution.
+#
+# * Neither the name of the CRYPTOGAMS nor the names of its
+# copyright holder and contributors may be used to endorse or
+# promote products derived from this software without specific
+# prior written permission.
+#
+# ALTERNATIVELY, provided that this notice is retained in full, this
+# product may be distributed under the terms of the GNU General Public
+# License (GPL), in which case the provisions of the GPL apply INSTEAD OF
+# those given above.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see https://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+
+#
+# ====================================================================
+# Written and Modified by Danny Tsen <dtsen@us.ibm.com>
+# - Added x25519_fe51_sqr_times, x25519_fe51_frombytes, x25519_fe51_tobytes
+# and x25519_cswap
+#
+# Copyright 2024- IBM Corp.
+#
+# X25519 lower-level primitives for PPC64.
+#
+
+#include <linux/linkage.h>
+
+.text
+
+.align 5
+SYM_FUNC_START(x25519_fe51_mul)
+
+ stdu 1,-144(1)
+ std 21,56(1)
+ std 22,64(1)
+ std 23,72(1)
+ std 24,80(1)
+ std 25,88(1)
+ std 26,96(1)
+ std 27,104(1)
+ std 28,112(1)
+ std 29,120(1)
+ std 30,128(1)
+ std 31,136(1)
+
+ ld 6,0(5)
+ ld 7,0(4)
+ ld 8,8(4)
+ ld 9,16(4)
+ ld 10,24(4)
+ ld 11,32(4)
+
+ mulld 22,7,6
+ mulhdu 23,7,6
+
+ mulld 24,8,6
+ mulhdu 25,8,6
+
+ mulld 30,11,6
+ mulhdu 31,11,6
+ ld 4,8(5)
+ mulli 11,11,19
+
+ mulld 26,9,6
+ mulhdu 27,9,6
+
+ mulld 28,10,6
+ mulhdu 29,10,6
+ mulld 12,11,4
+ mulhdu 21,11,4
+ addc 22,22,12
+ adde 23,23,21
+
+ mulld 12,7,4
+ mulhdu 21,7,4
+ addc 24,24,12
+ adde 25,25,21
+
+ mulld 12,10,4
+ mulhdu 21,10,4
+ ld 6,16(5)
+ mulli 10,10,19
+ addc 30,30,12
+ adde 31,31,21
+
+ mulld 12,8,4
+ mulhdu 21,8,4
+ addc 26,26,12
+ adde 27,27,21
+
+ mulld 12,9,4
+ mulhdu 21,9,4
+ addc 28,28,12
+ adde 29,29,21
+ mulld 12,10,6
+ mulhdu 21,10,6
+ addc 22,22,12
+ adde 23,23,21
+
+ mulld 12,11,6
+ mulhdu 21,11,6
+ addc 24,24,12
+ adde 25,25,21
+
+ mulld 12,9,6
+ mulhdu 21,9,6
+ ld 4,24(5)
+ mulli 9,9,19
+ addc 30,30,12
+ adde 31,31,21
+
+ mulld 12,7,6
+ mulhdu 21,7,6
+ addc 26,26,12
+ adde 27,27,21
+
+ mulld 12,8,6
+ mulhdu 21,8,6
+ addc 28,28,12
+ adde 29,29,21
+ mulld 12,9,4
+ mulhdu 21,9,4
+ addc 22,22,12
+ adde 23,23,21
+
+ mulld 12,10,4
+ mulhdu 21,10,4
+ addc 24,24,12
+ adde 25,25,21
+
+ mulld 12,8,4
+ mulhdu 21,8,4
+ ld 6,32(5)
+ mulli 8,8,19
+ addc 30,30,12
+ adde 31,31,21
+
+ mulld 12,11,4
+ mulhdu 21,11,4
+ addc 26,26,12
+ adde 27,27,21
+
+ mulld 12,7,4
+ mulhdu 21,7,4
+ addc 28,28,12
+ adde 29,29,21
+ mulld 12,8,6
+ mulhdu 21,8,6
+ addc 22,22,12
+ adde 23,23,21
+
+ mulld 12,9,6
+ mulhdu 21,9,6
+ addc 24,24,12
+ adde 25,25,21
+
+ mulld 12,10,6
+ mulhdu 21,10,6
+ addc 26,26,12
+ adde 27,27,21
+
+ mulld 12,11,6
+ mulhdu 21,11,6
+ addc 28,28,12
+ adde 29,29,21
+
+ mulld 12,7,6
+ mulhdu 21,7,6
+ addc 30,30,12
+ adde 31,31,21
+
+.Lfe51_reduce:
+ li 0,-1
+ srdi 0,0,13
+
+ srdi 12,26,51
+ and 9,26,0
+ insrdi 12,27,51,0
+ srdi 21,22,51
+ and 7,22,0
+ insrdi 21,23,51,0
+ addc 28,28,12
+ addze 29,29
+ addc 24,24,21
+ addze 25,25
+
+ srdi 12,28,51
+ and 10,28,0
+ insrdi 12,29,51,0
+ srdi 21,24,51
+ and 8,24,0
+ insrdi 21,25,51,0
+ addc 30,30,12
+ addze 31,31
+ add 9,9,21
+
+ srdi 12,30,51
+ and 11,30,0
+ insrdi 12,31,51,0
+ mulli 12,12,19
+
+ add 7,7,12
+
+ srdi 21,9,51
+ and 9,9,0
+ add 10,10,21
+
+ srdi 12,7,51
+ and 7,7,0
+ add 8,8,12
+
+ std 9,16(3)
+ std 10,24(3)
+ std 11,32(3)
+ std 7,0(3)
+ std 8,8(3)
+
+ ld 21,56(1)
+ ld 22,64(1)
+ ld 23,72(1)
+ ld 24,80(1)
+ ld 25,88(1)
+ ld 26,96(1)
+ ld 27,104(1)
+ ld 28,112(1)
+ ld 29,120(1)
+ ld 30,128(1)
+ ld 31,136(1)
+ addi 1,1,144
+ blr
+SYM_FUNC_END(x25519_fe51_mul)
+
+.align 5
+SYM_FUNC_START(x25519_fe51_sqr)
+
+ stdu 1,-144(1)
+ std 21,56(1)
+ std 22,64(1)
+ std 23,72(1)
+ std 24,80(1)
+ std 25,88(1)
+ std 26,96(1)
+ std 27,104(1)
+ std 28,112(1)
+ std 29,120(1)
+ std 30,128(1)
+ std 31,136(1)
+
+ ld 7,0(4)
+ ld 8,8(4)
+ ld 9,16(4)
+ ld 10,24(4)
+ ld 11,32(4)
+
+ add 6,7,7
+ mulli 21,11,19
+
+ mulld 22,7,7
+ mulhdu 23,7,7
+ mulld 24,8,6
+ mulhdu 25,8,6
+ mulld 26,9,6
+ mulhdu 27,9,6
+ mulld 28,10,6
+ mulhdu 29,10,6
+ mulld 30,11,6
+ mulhdu 31,11,6
+ add 6,8,8
+ mulld 12,11,21
+ mulhdu 11,11,21
+ addc 28,28,12
+ adde 29,29,11
+
+ mulli 5,10,19
+
+ mulld 12,8,8
+ mulhdu 11,8,8
+ addc 26,26,12
+ adde 27,27,11
+ mulld 12,9,6
+ mulhdu 11,9,6
+ addc 28,28,12
+ adde 29,29,11
+ mulld 12,10,6
+ mulhdu 11,10,6
+ addc 30,30,12
+ adde 31,31,11
+ mulld 12,21,6
+ mulhdu 11,21,6
+ add 6,10,10
+ addc 22,22,12
+ adde 23,23,11
+ mulld 12,10,5
+ mulhdu 10,10,5
+ addc 24,24,12
+ adde 25,25,10
+ mulld 12,6,21
+ mulhdu 10,6,21
+ add 6,9,9
+ addc 26,26,12
+ adde 27,27,10
+
+ mulld 12,9,9
+ mulhdu 10,9,9
+ addc 30,30,12
+ adde 31,31,10
+ mulld 12,5,6
+ mulhdu 10,5,6
+ addc 22,22,12
+ adde 23,23,10
+ mulld 12,21,6
+ mulhdu 10,21,6
+ addc 24,24,12
+ adde 25,25,10
+
+ b .Lfe51_reduce
+SYM_FUNC_END(x25519_fe51_sqr)
+
+.align 5
+SYM_FUNC_START(x25519_fe51_mul121666)
+
+ stdu 1,-144(1)
+ std 21,56(1)
+ std 22,64(1)
+ std 23,72(1)
+ std 24,80(1)
+ std 25,88(1)
+ std 26,96(1)
+ std 27,104(1)
+ std 28,112(1)
+ std 29,120(1)
+ std 30,128(1)
+ std 31,136(1)
+
+ lis 6,1
+ ori 6,6,56130
+ ld 7,0(4)
+ ld 8,8(4)
+ ld 9,16(4)
+ ld 10,24(4)
+ ld 11,32(4)
+
+ mulld 22,7,6
+ mulhdu 23,7,6
+ mulld 24,8,6
+ mulhdu 25,8,6
+ mulld 26,9,6
+ mulhdu 27,9,6
+ mulld 28,10,6
+ mulhdu 29,10,6
+ mulld 30,11,6
+ mulhdu 31,11,6
+
+ b .Lfe51_reduce
+SYM_FUNC_END(x25519_fe51_mul121666)
+
+.align 5
+SYM_FUNC_START(x25519_fe51_sqr_times)
+
+ stdu 1,-144(1)
+ std 21,56(1)
+ std 22,64(1)
+ std 23,72(1)
+ std 24,80(1)
+ std 25,88(1)
+ std 26,96(1)
+ std 27,104(1)
+ std 28,112(1)
+ std 29,120(1)
+ std 30,128(1)
+ std 31,136(1)
+
+ ld 7,0(4)
+ ld 8,8(4)
+ ld 9,16(4)
+ ld 10,24(4)
+ ld 11,32(4)
+
+ mtctr 5
+
+.Lsqr_times_loop:
+ add 6,7,7
+ mulli 21,11,19
+
+ mulld 22,7,7
+ mulhdu 23,7,7
+ mulld 24,8,6
+ mulhdu 25,8,6
+ mulld 26,9,6
+ mulhdu 27,9,6
+ mulld 28,10,6
+ mulhdu 29,10,6
+ mulld 30,11,6
+ mulhdu 31,11,6
+ add 6,8,8
+ mulld 12,11,21
+ mulhdu 11,11,21
+ addc 28,28,12
+ adde 29,29,11
+
+ mulli 5,10,19
+
+ mulld 12,8,8
+ mulhdu 11,8,8
+ addc 26,26,12
+ adde 27,27,11
+ mulld 12,9,6
+ mulhdu 11,9,6
+ addc 28,28,12
+ adde 29,29,11
+ mulld 12,10,6
+ mulhdu 11,10,6
+ addc 30,30,12
+ adde 31,31,11
+ mulld 12,21,6
+ mulhdu 11,21,6
+ add 6,10,10
+ addc 22,22,12
+ adde 23,23,11
+ mulld 12,10,5
+ mulhdu 10,10,5
+ addc 24,24,12
+ adde 25,25,10
+ mulld 12,6,21
+ mulhdu 10,6,21
+ add 6,9,9
+ addc 26,26,12
+ adde 27,27,10
+
+ mulld 12,9,9
+ mulhdu 10,9,9
+ addc 30,30,12
+ adde 31,31,10
+ mulld 12,5,6
+ mulhdu 10,5,6
+ addc 22,22,12
+ adde 23,23,10
+ mulld 12,21,6
+ mulhdu 10,21,6
+ addc 24,24,12
+ adde 25,25,10
+
+ # fe51_reduce
+ li 0,-1
+ srdi 0,0,13
+
+ srdi 12,26,51
+ and 9,26,0
+ insrdi 12,27,51,0
+ srdi 21,22,51
+ and 7,22,0
+ insrdi 21,23,51,0
+ addc 28,28,12
+ addze 29,29
+ addc 24,24,21
+ addze 25,25
+
+ srdi 12,28,51
+ and 10,28,0
+ insrdi 12,29,51,0
+ srdi 21,24,51
+ and 8,24,0
+ insrdi 21,25,51,0
+ addc 30,30,12
+ addze 31,31
+ add 9,9,21
+
+ srdi 12,30,51
+ and 11,30,0
+ insrdi 12,31,51,0
+ mulli 12,12,19
+
+ add 7,7,12
+
+ srdi 21,9,51
+ and 9,9,0
+ add 10,10,21
+
+ srdi 12,7,51
+ and 7,7,0
+ add 8,8,12
+
+ bdnz .Lsqr_times_loop
+
+ std 9,16(3)
+ std 10,24(3)
+ std 11,32(3)
+ std 7,0(3)
+ std 8,8(3)
+
+ ld 21,56(1)
+ ld 22,64(1)
+ ld 23,72(1)
+ ld 24,80(1)
+ ld 25,88(1)
+ ld 26,96(1)
+ ld 27,104(1)
+ ld 28,112(1)
+ ld 29,120(1)
+ ld 30,128(1)
+ ld 31,136(1)
+ addi 1,1,144
+ blr
+SYM_FUNC_END(x25519_fe51_sqr_times)
+
+.align 5
+SYM_FUNC_START(x25519_fe51_frombytes)
+
+ li 12, -1
+ srdi 12, 12, 13 # 0x7ffffffffffff
+
+ ld 5, 0(4)
+ ld 6, 8(4)
+ ld 7, 16(4)
+ ld 8, 24(4)
+
+ srdi 10, 5, 51
+ and 5, 5, 12 # h0
+
+ sldi 11, 6, 13
+ or 11, 10, 11 # h1t
+ srdi 10, 6, 38
+ and 6, 11, 12 # h1
+
+ sldi 11, 7, 26
+ or 10, 10, 11 # h2t
+
+ srdi 11, 7, 25
+ and 7, 10, 12 # h2
+ sldi 10, 8, 39
+ or 11, 11, 10 # h3t
+
+ srdi 9, 8, 12
+ and 8, 11, 12 # h3
+ and 9, 9, 12 # h4
+
+ std 5, 0(3)
+ std 6, 8(3)
+ std 7, 16(3)
+ std 8, 24(3)
+ std 9, 32(3)
+
+ blr
+SYM_FUNC_END(x25519_fe51_frombytes)
+
+.align 5
+SYM_FUNC_START(x25519_fe51_tobytes)
+
+ ld 5, 0(4)
+ ld 6, 8(4)
+ ld 7, 16(4)
+ ld 8, 24(4)
+ ld 9, 32(4)
+
+ li 12, -1
+ srdi 12, 12, 13 # 0x7ffffffffffff
+
+ # Full reducuction
+ addi 10, 5, 19
+ srdi 10, 10, 51
+ add 10, 10, 6
+ srdi 10, 10, 51
+ add 10, 10, 7
+ srdi 10, 10, 51
+ add 10, 10, 8
+ srdi 10, 10, 51
+ add 10, 10, 9
+ srdi 10, 10, 51
+
+ mulli 10, 10, 19
+ add 5, 5, 10
+ srdi 11, 5, 51
+ add 6, 6, 11
+ srdi 11, 6, 51
+ add 7, 7, 11
+ srdi 11, 7, 51
+ add 8, 8, 11
+ srdi 11, 8, 51
+ add 9, 9, 11
+
+ and 5, 5, 12
+ and 6, 6, 12
+ and 7, 7, 12
+ and 8, 8, 12
+ and 9, 9, 12
+
+ sldi 10, 6, 51
+ or 5, 5, 10 # s0
+
+ srdi 11, 6, 13
+ sldi 10, 7, 38
+ or 6, 11, 10 # s1
+
+ srdi 11, 7, 26
+ sldi 10, 8, 25
+ or 7, 11, 10 # s2
+
+ srdi 11, 8, 39
+ sldi 10, 9, 12
+ or 8, 11, 10 # s4
+
+ std 5, 0(3)
+ std 6, 8(3)
+ std 7, 16(3)
+ std 8, 24(3)
+
+ blr
+SYM_FUNC_END(x25519_fe51_tobytes)
+
+.align 5
+SYM_FUNC_START(x25519_cswap)
+
+ li 7, 5
+ neg 6, 5
+ mtctr 7
+
+.Lswap_loop:
+ ld 8, 0(3)
+ ld 9, 0(4)
+ xor 10, 8, 9
+ and 10, 10, 6
+ xor 11, 8, 10
+ xor 12, 9, 10
+ std 11, 0(3)
+ addi 3, 3, 8
+ std 12, 0(4)
+ addi 4, 4, 8
+ bdnz .Lswap_loop
+
+ blr
+SYM_FUNC_END(x25519_cswap)
diff --git a/arch/powerpc/crypto/ghash.c b/arch/powerpc/crypto/ghash.c
new file mode 100644
index 000000000000..77eca20bc7ac
--- /dev/null
+++ b/arch/powerpc/crypto/ghash.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * GHASH routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015, 2019 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ *
+ * Extended by Daniel Axtens <dja@axtens.net> to replace the fallback
+ * mechanism. The new approach is based on arm64 code, which is:
+ * Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/ghash.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/b128ops.h>
+#include "aesp8-ppc.h"
+
+void gcm_init_p8(u128 htable[16], const u64 Xi[2]);
+void gcm_gmult_p8(u64 Xi[2], const u128 htable[16]);
+void gcm_ghash_p8(u64 Xi[2], const u128 htable[16],
+ const u8 *in, size_t len);
+
+struct p8_ghash_ctx {
+ /* key used by vector asm */
+ u128 htable[16];
+ /* key used by software fallback */
+ be128 key;
+};
+
+struct p8_ghash_desc_ctx {
+ u64 shash[2];
+ u8 buffer[GHASH_DIGEST_SIZE];
+ int bytes;
+};
+
+static int p8_ghash_init(struct shash_desc *desc)
+{
+ struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+ dctx->bytes = 0;
+ memset(dctx->shash, 0, GHASH_DIGEST_SIZE);
+ return 0;
+}
+
+static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(tfm));
+
+ if (keylen != GHASH_BLOCK_SIZE)
+ return -EINVAL;
+
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ gcm_init_p8(ctx->htable, (const u64 *) key);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+
+ memcpy(&ctx->key, key, GHASH_BLOCK_SIZE);
+
+ return 0;
+}
+
+static inline void __ghash_block(struct p8_ghash_ctx *ctx,
+ struct p8_ghash_desc_ctx *dctx)
+{
+ if (crypto_simd_usable()) {
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ gcm_ghash_p8(dctx->shash, ctx->htable,
+ dctx->buffer, GHASH_DIGEST_SIZE);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+ } else {
+ crypto_xor((u8 *)dctx->shash, dctx->buffer, GHASH_BLOCK_SIZE);
+ gf128mul_lle((be128 *)dctx->shash, &ctx->key);
+ }
+}
+
+static inline void __ghash_blocks(struct p8_ghash_ctx *ctx,
+ struct p8_ghash_desc_ctx *dctx,
+ const u8 *src, unsigned int srclen)
+{
+ if (crypto_simd_usable()) {
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_vsx();
+ gcm_ghash_p8(dctx->shash, ctx->htable,
+ src, srclen);
+ disable_kernel_vsx();
+ pagefault_enable();
+ preempt_enable();
+ } else {
+ while (srclen >= GHASH_BLOCK_SIZE) {
+ crypto_xor((u8 *)dctx->shash, src, GHASH_BLOCK_SIZE);
+ gf128mul_lle((be128 *)dctx->shash, &ctx->key);
+ srclen -= GHASH_BLOCK_SIZE;
+ src += GHASH_BLOCK_SIZE;
+ }
+ }
+}
+
+static int p8_ghash_update(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen)
+{
+ unsigned int len;
+ struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+ struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+ if (dctx->bytes) {
+ if (dctx->bytes + srclen < GHASH_DIGEST_SIZE) {
+ memcpy(dctx->buffer + dctx->bytes, src,
+ srclen);
+ dctx->bytes += srclen;
+ return 0;
+ }
+ memcpy(dctx->buffer + dctx->bytes, src,
+ GHASH_DIGEST_SIZE - dctx->bytes);
+
+ __ghash_block(ctx, dctx);
+
+ src += GHASH_DIGEST_SIZE - dctx->bytes;
+ srclen -= GHASH_DIGEST_SIZE - dctx->bytes;
+ dctx->bytes = 0;
+ }
+ len = srclen & ~(GHASH_DIGEST_SIZE - 1);
+ if (len) {
+ __ghash_blocks(ctx, dctx, src, len);
+ src += len;
+ srclen -= len;
+ }
+ if (srclen) {
+ memcpy(dctx->buffer, src, srclen);
+ dctx->bytes = srclen;
+ }
+ return 0;
+}
+
+static int p8_ghash_final(struct shash_desc *desc, u8 *out)
+{
+ int i;
+ struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+ struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+ if (dctx->bytes) {
+ for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++)
+ dctx->buffer[i] = 0;
+ __ghash_block(ctx, dctx);
+ dctx->bytes = 0;
+ }
+ memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
+ return 0;
+}
+
+struct shash_alg p8_ghash_alg = {
+ .digestsize = GHASH_DIGEST_SIZE,
+ .init = p8_ghash_init,
+ .update = p8_ghash_update,
+ .final = p8_ghash_final,
+ .setkey = p8_ghash_setkey,
+ .descsize = sizeof(struct p8_ghash_desc_ctx)
+ + sizeof(struct ghash_desc_ctx),
+ .base = {
+ .cra_name = "ghash",
+ .cra_driver_name = "p8_ghash",
+ .cra_priority = 1000,
+ .cra_blocksize = GHASH_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct p8_ghash_ctx),
+ .cra_module = THIS_MODULE,
+ },
+};
diff --git a/arch/powerpc/crypto/ghashp8-ppc.pl b/arch/powerpc/crypto/ghashp8-ppc.pl
new file mode 100644
index 000000000000..041e633c214f
--- /dev/null
+++ b/arch/powerpc/crypto/ghashp8-ppc.pl
@@ -0,0 +1,243 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore this program is free software;
+# you can redistribute it and/or modify it under the terms of the GNU General
+# Public License version 2 as published by the Free Software Foundation.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see https://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# GHASH for PowerISA v2.07.
+#
+# July 2014
+#
+# Accurate performance measurements are problematic, because it's
+# always virtualized setup with possibly throttled processor.
+# Relative comparison is therefore more informative. This initial
+# version is ~2.1x slower than hardware-assisted AES-128-CTR, ~12x
+# faster than "4-bit" integer-only compiler-generated 64-bit code.
+# "Initial version" means that there is room for futher improvement.
+
+$flavour=shift;
+$output =shift;
+
+if ($flavour =~ /64/) {
+ $SIZE_T=8;
+ $LRSAVE=2*$SIZE_T;
+ $STU="stdu";
+ $POP="ld";
+ $PUSH="std";
+} elsif ($flavour =~ /32/) {
+ $SIZE_T=4;
+ $LRSAVE=$SIZE_T;
+ $STU="stwu";
+ $POP="lwz";
+ $PUSH="stw";
+} else { die "nonsense $flavour"; }
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or
+die "can't locate ppc-xlate.pl";
+
+open STDOUT,"| $^X $xlate $flavour $output" || die "can't call $xlate: $!";
+
+my ($Xip,$Htbl,$inp,$len)=map("r$_",(3..6)); # argument block
+
+my ($Xl,$Xm,$Xh,$IN)=map("v$_",(0..3));
+my ($zero,$t0,$t1,$t2,$xC2,$H,$Hh,$Hl,$lemask)=map("v$_",(4..12));
+my $vrsave="r12";
+
+$code=<<___;
+.machine "any"
+
+.text
+
+.globl .gcm_init_p8
+ lis r0,0xfff0
+ li r8,0x10
+ mfspr $vrsave,256
+ li r9,0x20
+ mtspr 256,r0
+ li r10,0x30
+ lvx_u $H,0,r4 # load H
+ le?xor r7,r7,r7
+ le?addi r7,r7,0x8 # need a vperm start with 08
+ le?lvsr 5,0,r7
+ le?vspltisb 6,0x0f
+ le?vxor 5,5,6 # set a b-endian mask
+ le?vperm $H,$H,$H,5
+
+ vspltisb $xC2,-16 # 0xf0
+ vspltisb $t0,1 # one
+ vaddubm $xC2,$xC2,$xC2 # 0xe0
+ vxor $zero,$zero,$zero
+ vor $xC2,$xC2,$t0 # 0xe1
+ vsldoi $xC2,$xC2,$zero,15 # 0xe1...
+ vsldoi $t1,$zero,$t0,1 # ...1
+ vaddubm $xC2,$xC2,$xC2 # 0xc2...
+ vspltisb $t2,7
+ vor $xC2,$xC2,$t1 # 0xc2....01
+ vspltb $t1,$H,0 # most significant byte
+ vsl $H,$H,$t0 # H<<=1
+ vsrab $t1,$t1,$t2 # broadcast carry bit
+ vand $t1,$t1,$xC2
+ vxor $H,$H,$t1 # twisted H
+
+ vsldoi $H,$H,$H,8 # twist even more ...
+ vsldoi $xC2,$zero,$xC2,8 # 0xc2.0
+ vsldoi $Hl,$zero,$H,8 # ... and split
+ vsldoi $Hh,$H,$zero,8
+
+ stvx_u $xC2,0,r3 # save pre-computed table
+ stvx_u $Hl,r8,r3
+ stvx_u $H, r9,r3
+ stvx_u $Hh,r10,r3
+
+ mtspr 256,$vrsave
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,2,0
+ .long 0
+.size .gcm_init_p8,.-.gcm_init_p8
+
+.globl .gcm_gmult_p8
+ lis r0,0xfff8
+ li r8,0x10
+ mfspr $vrsave,256
+ li r9,0x20
+ mtspr 256,r0
+ li r10,0x30
+ lvx_u $IN,0,$Xip # load Xi
+
+ lvx_u $Hl,r8,$Htbl # load pre-computed table
+ le?lvsl $lemask,r0,r0
+ lvx_u $H, r9,$Htbl
+ le?vspltisb $t0,0x07
+ lvx_u $Hh,r10,$Htbl
+ le?vxor $lemask,$lemask,$t0
+ lvx_u $xC2,0,$Htbl
+ le?vperm $IN,$IN,$IN,$lemask
+ vxor $zero,$zero,$zero
+
+ vpmsumd $Xl,$IN,$Hl # H.lo·Xi.lo
+ vpmsumd $Xm,$IN,$H # H.hi·Xi.lo+H.lo·Xi.hi
+ vpmsumd $Xh,$IN,$Hh # H.hi·Xi.hi
+
+ vpmsumd $t2,$Xl,$xC2 # 1st phase
+
+ vsldoi $t0,$Xm,$zero,8
+ vsldoi $t1,$zero,$Xm,8
+ vxor $Xl,$Xl,$t0
+ vxor $Xh,$Xh,$t1
+
+ vsldoi $Xl,$Xl,$Xl,8
+ vxor $Xl,$Xl,$t2
+
+ vsldoi $t1,$Xl,$Xl,8 # 2nd phase
+ vpmsumd $Xl,$Xl,$xC2
+ vxor $t1,$t1,$Xh
+ vxor $Xl,$Xl,$t1
+
+ le?vperm $Xl,$Xl,$Xl,$lemask
+ stvx_u $Xl,0,$Xip # write out Xi
+
+ mtspr 256,$vrsave
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,2,0
+ .long 0
+.size .gcm_gmult_p8,.-.gcm_gmult_p8
+
+.globl .gcm_ghash_p8
+ lis r0,0xfff8
+ li r8,0x10
+ mfspr $vrsave,256
+ li r9,0x20
+ mtspr 256,r0
+ li r10,0x30
+ lvx_u $Xl,0,$Xip # load Xi
+
+ lvx_u $Hl,r8,$Htbl # load pre-computed table
+ le?lvsl $lemask,r0,r0
+ lvx_u $H, r9,$Htbl
+ le?vspltisb $t0,0x07
+ lvx_u $Hh,r10,$Htbl
+ le?vxor $lemask,$lemask,$t0
+ lvx_u $xC2,0,$Htbl
+ le?vperm $Xl,$Xl,$Xl,$lemask
+ vxor $zero,$zero,$zero
+
+ lvx_u $IN,0,$inp
+ addi $inp,$inp,16
+ subi $len,$len,16
+ le?vperm $IN,$IN,$IN,$lemask
+ vxor $IN,$IN,$Xl
+ b Loop
+
+.align 5
+Loop:
+ subic $len,$len,16
+ vpmsumd $Xl,$IN,$Hl # H.lo·Xi.lo
+ subfe. r0,r0,r0 # borrow?-1:0
+ vpmsumd $Xm,$IN,$H # H.hi·Xi.lo+H.lo·Xi.hi
+ and r0,r0,$len
+ vpmsumd $Xh,$IN,$Hh # H.hi·Xi.hi
+ add $inp,$inp,r0
+
+ vpmsumd $t2,$Xl,$xC2 # 1st phase
+
+ vsldoi $t0,$Xm,$zero,8
+ vsldoi $t1,$zero,$Xm,8
+ vxor $Xl,$Xl,$t0
+ vxor $Xh,$Xh,$t1
+
+ vsldoi $Xl,$Xl,$Xl,8
+ vxor $Xl,$Xl,$t2
+ lvx_u $IN,0,$inp
+ addi $inp,$inp,16
+
+ vsldoi $t1,$Xl,$Xl,8 # 2nd phase
+ vpmsumd $Xl,$Xl,$xC2
+ le?vperm $IN,$IN,$IN,$lemask
+ vxor $t1,$t1,$Xh
+ vxor $IN,$IN,$t1
+ vxor $IN,$IN,$Xl
+ beq Loop # did $len-=16 borrow?
+
+ vxor $Xl,$Xl,$t1
+ le?vperm $Xl,$Xl,$Xl,$lemask
+ stvx_u $Xl,0,$Xip # write out Xi
+
+ mtspr 256,$vrsave
+ blr
+ .long 0
+ .byte 0,12,0x14,0,0,0,4,0
+ .long 0
+.size .gcm_ghash_p8,.-.gcm_ghash_p8
+
+.asciz "GHASH for PowerISA 2.07, CRYPTOGAMS by <appro\@openssl.org>"
+.align 2
+___
+
+foreach (split("\n",$code)) {
+ if ($flavour =~ /le$/o) { # little-endian
+ s/le\?//o or
+ s/be\?/#be#/o;
+ } else {
+ s/le\?/#le#/o or
+ s/be\?//o;
+ }
+ print $_,"\n";
+}
+
+close STDOUT; # enforce flush
diff --git a/arch/powerpc/crypto/poly1305-p10-glue.c b/arch/powerpc/crypto/poly1305-p10-glue.c
index 95dd708573ee..369686e9370b 100644
--- a/arch/powerpc/crypto/poly1305-p10-glue.c
+++ b/arch/powerpc/crypto/poly1305-p10-glue.c
@@ -14,7 +14,7 @@
#include <crypto/internal/poly1305.h>
#include <crypto/internal/simd.h>
#include <linux/cpufeature.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <asm/simd.h>
#include <asm/switch_to.h>
diff --git a/arch/powerpc/crypto/vmx.c b/arch/powerpc/crypto/vmx.c
new file mode 100644
index 000000000000..0b725e826388
--- /dev/null
+++ b/arch/powerpc/crypto/vmx.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <asm/cputable.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+
+#include "aesp8-ppc.h"
+
+static int __init p8_init(void)
+{
+ int ret;
+
+ ret = crypto_register_shash(&p8_ghash_alg);
+ if (ret)
+ goto err;
+
+ ret = crypto_register_alg(&p8_aes_alg);
+ if (ret)
+ goto err_unregister_ghash;
+
+ ret = crypto_register_skcipher(&p8_aes_cbc_alg);
+ if (ret)
+ goto err_unregister_aes;
+
+ ret = crypto_register_skcipher(&p8_aes_ctr_alg);
+ if (ret)
+ goto err_unregister_aes_cbc;
+
+ ret = crypto_register_skcipher(&p8_aes_xts_alg);
+ if (ret)
+ goto err_unregister_aes_ctr;
+
+ return 0;
+
+err_unregister_aes_ctr:
+ crypto_unregister_skcipher(&p8_aes_ctr_alg);
+err_unregister_aes_cbc:
+ crypto_unregister_skcipher(&p8_aes_cbc_alg);
+err_unregister_aes:
+ crypto_unregister_alg(&p8_aes_alg);
+err_unregister_ghash:
+ crypto_unregister_shash(&p8_ghash_alg);
+err:
+ return ret;
+}
+
+static void __exit p8_exit(void)
+{
+ crypto_unregister_skcipher(&p8_aes_xts_alg);
+ crypto_unregister_skcipher(&p8_aes_ctr_alg);
+ crypto_unregister_skcipher(&p8_aes_cbc_alg);
+ crypto_unregister_alg(&p8_aes_alg);
+ crypto_unregister_shash(&p8_ghash_alg);
+}
+
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, p8_init);
+module_exit(p8_exit);
+
+MODULE_AUTHOR("Marcelo Cerri<mhcerri@br.ibm.com>");
+MODULE_DESCRIPTION("IBM VMX cryptographic acceleration instructions "
+ "support on Power 8");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0.0");
+MODULE_IMPORT_NS("CRYPTO_INTERNAL");
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 61a8d5555cd7..e5fdc336c9b2 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -6,5 +6,4 @@ generic-y += agp.h
generic-y += kvm_types.h
generic-y += mcs_spinlock.h
generic-y += qrwlock.h
-generic-y += vtime.h
generic-y += early_ioremap.h
diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index 2bc53c646ccd..f48e644900a2 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -26,19 +26,23 @@
#define PPC_MIN_STKFRM 112
#ifdef __BIG_ENDIAN__
-#define LHZX_BE stringify_in_c(lhzx)
#define LWZX_BE stringify_in_c(lwzx)
#define LDX_BE stringify_in_c(ldx)
#define STWX_BE stringify_in_c(stwx)
#define STDX_BE stringify_in_c(stdx)
#else
-#define LHZX_BE stringify_in_c(lhbrx)
#define LWZX_BE stringify_in_c(lwbrx)
#define LDX_BE stringify_in_c(ldbrx)
#define STWX_BE stringify_in_c(stwbrx)
#define STDX_BE stringify_in_c(stdbrx)
#endif
+#ifdef CONFIG_CC_IS_CLANG
+#define DS_FORM_CONSTRAINT "Z<>"
+#else
+#define DS_FORM_CONSTRAINT "YZ<>"
+#endif
+
#else /* 32-bit */
/* operations for longs and pointers */
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 5bf6a4d49268..d1ea554c33ed 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -11,6 +11,7 @@
#include <asm/cmpxchg.h>
#include <asm/barrier.h>
#include <asm/asm-const.h>
+#include <asm/asm-compat.h>
/*
* Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
@@ -197,7 +198,7 @@ static __inline__ s64 arch_atomic64_read(const atomic64_t *v)
if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
__asm__ __volatile__("ld %0,0(%1)" : "=r"(t) : "b"(&v->counter));
else
- __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter));
+ __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : DS_FORM_CONSTRAINT (v->counter));
return t;
}
@@ -208,7 +209,7 @@ static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i)
if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
__asm__ __volatile__("std %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter));
else
- __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i));
+ __asm__ __volatile__("std%U0%X0 %1,%0" : "=" DS_FORM_CONSTRAINT (v->counter) : "r"(i));
}
#define ATOMIC64_OP(op, asm_op) \
diff --git a/arch/powerpc/include/asm/backlight.h b/arch/powerpc/include/asm/backlight.h
index 1b5eab62ed04..061a910d7492 100644
--- a/arch/powerpc/include/asm/backlight.h
+++ b/arch/powerpc/include/asm/backlight.h
@@ -10,15 +10,14 @@
#define __ASM_POWERPC_BACKLIGHT_H
#ifdef __KERNEL__
-#include <linux/fb.h>
#include <linux/mutex.h>
+struct backlight_device;
+
/* For locking instructions, see the implementation file */
extern struct backlight_device *pmac_backlight;
extern struct mutex pmac_backlight_mutex;
-extern int pmac_backlight_curve_lookup(struct fb_info *info, int value);
-
extern int pmac_has_backlight_type(const char *type);
extern void pmac_backlight_key(int direction);
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index dc5c039eb28e..dd4eb3063175 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -47,8 +47,6 @@ static inline void pgtable_free(void *table, unsigned index_size)
}
}
-#define get_hugepd_cache_index(x) (x)
-
static inline void pgtable_free_tlb(struct mmu_gather *tlb,
void *table, int shift)
{
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 52971ee30717..42c3af90d1f0 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -196,7 +196,8 @@ void unmap_kernel_page(unsigned long va);
#endif
#define MODULES_END ALIGN_DOWN(PAGE_OFFSET, SZ_256M)
-#define MODULES_VADDR (MODULES_END - SZ_256M)
+#define MODULES_SIZE (CONFIG_MODULES_SIZE * SZ_1M)
+#define MODULES_VADDR (MODULES_END - MODULES_SIZE)
#ifndef __ASSEMBLY__
#include <linux/sched.h>
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 6472b08fa1b0..aa90a048f319 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -74,20 +74,33 @@
#define remap_4k_pfn(vma, addr, pfn, prot) \
remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int hash__hugepd_ok(hugepd_t hpd)
+/*
+ * With 4K page size the real_pte machinery is all nops.
+ */
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
{
- unsigned long hpdval = hpd_val(hpd);
- /*
- * if it is not a pte and have hugepd shift mask
- * set, then it is a hugepd directory pointer
- */
- if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) &&
- ((hpdval & HUGEPD_SHIFT_MASK) != 0))
- return true;
- return false;
+ return (real_pte_t){pte};
}
-#endif
+
+#define __rpte_to_pte(r) ((r).pte)
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+ return pte_val(__rpte_to_pte(rpte)) >> H_PAGE_F_GIX_SHIFT;
+}
+
+#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \
+ do { \
+ index = 0; \
+ shift = mmu_psize_defs[psize].shift; \
+
+#define pte_iterate_hashed_end() } while(0)
+
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
+#define pte_pagesize_index(mm, addr, pte) MMU_PAGE_4K
/*
* 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 6e70ae511631..0755f2567021 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -4,6 +4,7 @@
#ifdef __KERNEL__
#include <asm/asm-const.h>
+#include <asm/book3s/64/slice.h>
/*
* Common bits between 4K and 64K pages in a linux-style PTE.
@@ -161,14 +162,10 @@ extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long pte, int huge);
unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags);
/* Atomic PTE updates */
-static inline unsigned long hash__pte_update(struct mm_struct *mm,
- unsigned long addr,
- pte_t *ptep, unsigned long clr,
- unsigned long set,
- int huge)
+static inline unsigned long hash__pte_update_one(pte_t *ptep, unsigned long clr,
+ unsigned long set)
{
__be64 old_be, tmp_be;
- unsigned long old;
__asm__ __volatile__(
"1: ldarx %0,0,%3 # pte_update\n\
@@ -182,11 +179,40 @@ static inline unsigned long hash__pte_update(struct mm_struct *mm,
: "r" (ptep), "r" (cpu_to_be64(clr)), "m" (*ptep),
"r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set))
: "cc" );
+
+ return be64_to_cpu(old_be);
+}
+
+static inline unsigned long hash__pte_update(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep, unsigned long clr,
+ unsigned long set,
+ int huge)
+{
+ unsigned long old;
+
+ old = hash__pte_update_one(ptep, clr, set);
+
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && huge) {
+ unsigned int psize = get_slice_psize(mm, addr);
+ int nb, i;
+
+ if (psize == MMU_PAGE_16M)
+ nb = SZ_16M / PMD_SIZE;
+ else if (psize == MMU_PAGE_16G)
+ nb = SZ_16G / PUD_SIZE;
+ else
+ nb = 1;
+
+ WARN_ON_ONCE(nb == 1); /* Should never happen */
+
+ for (i = 1; i < nb; i++)
+ hash__pte_update_one(ptep + i, clr, set);
+ }
/* huge pages use the old page table lock */
if (!huge)
assert_pte_locked(mm, addr);
- old = be64_to_cpu(old_be);
if (old & H_PAGE_HASHPTE)
hpte_need_flush(mm, addr, ptep, old, huge);
@@ -269,8 +295,6 @@ int hash__create_section_mapping(unsigned long start, unsigned long end,
int nid, pgprot_t prot);
int hash__remove_section_mapping(unsigned long start, unsigned long end);
-void hash__kernel_map_pages(struct page *page, int numpages, int enable);
-
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index aa1c67c8bfc8..f0bba9c5f9c3 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -49,9 +49,6 @@ static inline bool gigantic_page_runtime_supported(void)
return true;
}
-/* hugepd entry valid bit */
-#define HUGEPD_VAL_BITS (0x8000000000000000UL)
-
#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
@@ -60,29 +57,7 @@ extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t new_pte);
-/*
- * This should work for other subarchs too. But right now we use the
- * new format only for 64bit book3s
- */
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
- BUG_ON(!hugepd_ok(hpd));
- /*
- * We have only four bits to encode, MMU page size
- */
- BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
- return __va(hpd_val(hpd) & HUGEPD_ADDR_MASK);
-}
-
-static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
-{
- return (hpd_val(hpd) & HUGEPD_SHIFT_MASK) >> 2;
-}
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
- return mmu_psize_to_shift(hugepd_mmu_psize(hpd));
-}
static inline void flush_hugetlb_page(struct vm_area_struct *vma,
unsigned long vmaddr)
{
@@ -90,19 +65,6 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
return radix__flush_hugetlb_page(vma, vmaddr);
}
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
- unsigned int pdshift)
-{
- unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
-
- return hugepd_page(hpd) + idx;
-}
-
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
- *hpdp = __hugepd(__pa(new) | HUGEPD_VAL_BITS | (shift_to_mmu_psize(pshift) << 2));
-}
-
void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
static inline int check_and_get_huge_psize(int shift)
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
deleted file mode 100644
index 48f21820afe2..000000000000
--- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H
-#define _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H
-/*
- * hash 4k can't share hugetlb and also doesn't support THP
- */
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int pmd_huge(pmd_t pmd)
-{
- /*
- * leaf pte for huge page
- */
- if (radix_enabled())
- return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
- return 0;
-}
-
-static inline int pud_huge(pud_t pud)
-{
- /*
- * leaf pte for huge page
- */
- if (radix_enabled())
- return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
- return 0;
-}
-
-/*
- * With radix , we have hugepage ptes in the pud and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled.
- */
-static inline int hugepd_ok(hugepd_t hpd)
-{
- if (radix_enabled())
- return 0;
- return hash__hugepd_ok(hpd);
-}
-#define is_hugepd(hpd) (hugepd_ok(hpd))
-
-/*
- * 16M and 16G huge page directory tables are allocated from slab cache
- *
- */
-#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24)
-#define H_16G_CACHE_INDEX \
- (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34)
-
-static inline int get_hugepd_cache_index(int index)
-{
- switch (index) {
- case H_16M_CACHE_INDEX:
- return HTLB_16M_INDEX;
- case H_16G_CACHE_INDEX:
- return HTLB_16G_INDEX;
- default:
- BUG();
- }
- /* should not reach */
-}
-
-#endif /* CONFIG_HUGETLB_PAGE */
-
-#endif /* __ASSEMBLY__ */
-
-#endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
index 2fce3498b000..4d8d7b4ea16b 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
@@ -4,51 +4,6 @@
#ifndef __ASSEMBLY__
#ifdef CONFIG_HUGETLB_PAGE
-/*
- * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have
- * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD;
- *
- * Defined in such a way that we can optimize away code block at build time
- * if CONFIG_HUGETLB_PAGE=n.
- *
- * returns true for pmd migration entries, THP, devmap, hugetlb
- * But compile time dependent on CONFIG_HUGETLB_PAGE
- */
-static inline int pmd_huge(pmd_t pmd)
-{
- /*
- * leaf pte for huge page
- */
- return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
-}
-
-static inline int pud_huge(pud_t pud)
-{
- /*
- * leaf pte for huge page
- */
- return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
-}
-
-/*
- * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled.
- */
-static inline int hugepd_ok(hugepd_t hpd)
-{
- return 0;
-}
-
-#define is_hugepd(pdep) 0
-
-/*
- * This should never get called
- */
-static inline int get_hugepd_cache_index(int index)
-{
- BUG();
-}
#endif /* CONFIG_HUGETLB_PAGE */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 927d585652bc..6d98e6f08d4d 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -262,6 +262,36 @@ extern unsigned long __kernel_io_end;
extern struct page *vmemmap;
extern unsigned long pci_io_base;
+
+#define pmd_leaf pmd_leaf
+static inline bool pmd_leaf(pmd_t pmd)
+{
+ return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
+}
+
+#define pud_leaf pud_leaf
+static inline bool pud_leaf(pud_t pud)
+{
+ return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
+}
+
+#define pmd_leaf_size pmd_leaf_size
+static inline unsigned long pmd_leaf_size(pmd_t pmd)
+{
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled())
+ return SZ_16M;
+ else
+ return PMD_SIZE;
+}
+
+#define pud_leaf_size pud_leaf_size
+static inline unsigned long pud_leaf_size(pud_t pud)
+{
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled())
+ return SZ_16G;
+ else
+ return PUD_SIZE;
+}
#endif /* __ASSEMBLY__ */
#include <asm/book3s/64/hash.h>
@@ -273,11 +303,9 @@ extern unsigned long pci_io_base;
#define MAX_PHYSMEM_BITS R_MAX_PHYSMEM_BITS
#endif
-
+/* hash 4k can't share hugetlb and also doesn't support THP */
#ifdef CONFIG_PPC_64K_PAGES
#include <asm/book3s/64/pgtable-64k.h>
-#else
-#include <asm/book3s/64/pgtable-4k.h>
#endif
#include <asm/barrier.h>
@@ -302,32 +330,6 @@ extern unsigned long pci_io_base;
#ifndef __ASSEMBLY__
-/*
- * This is the default implementation of various PTE accessors, it's
- * used in all cases except Book3S with 64K pages where we have a
- * concept of sub-pages
- */
-#ifndef __real_pte
-
-#define __real_pte(e, p, o) ((real_pte_t){(e)})
-#define __rpte_to_pte(r) ((r).pte)
-#define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
-
-#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \
- do { \
- index = 0; \
- shift = mmu_psize_defs[psize].shift; \
-
-#define pte_iterate_hashed_end() } while(0)
-
-/*
- * We expect this to be called only for user addresses or kernel virtual
- * addresses other than the linear mapping.
- */
-#define pte_pagesize_index(mm, addr, pte) MMU_PAGE_4K
-
-#endif /* __real_pte */
-
static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long clr,
unsigned long set, int huge)
@@ -1027,16 +1029,6 @@ static inline void vmemmap_remove_mapping(unsigned long start,
}
#endif
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-static inline void __kernel_map_pages(struct page *page, int numpages, int enable)
-{
- if (radix_enabled())
- radix__kernel_map_pages(page, numpages, enable);
- else
- hash__kernel_map_pages(page, numpages, enable);
-}
-#endif
-
static inline pte_t pmd_pte(pmd_t pmd)
{
return __pte_raw(pmd_raw(pmd));
@@ -1106,6 +1098,7 @@ extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
extern pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot);
extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
+extern pud_t pud_modify(pud_t pud, pgprot_t newprot);
extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd);
extern void set_pud_at(struct mm_struct *mm, unsigned long addr,
@@ -1158,20 +1151,6 @@ pud_hugepage_update(struct mm_struct *mm, unsigned long addr, pud_t *pudp,
}
/*
- * returns true for pmd migration entries, THP, devmap, hugetlb
- * But compile time dependent on THP config
- */
-static inline int pmd_large(pmd_t pmd)
-{
- return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
-}
-
-static inline int pud_large(pud_t pud)
-{
- return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
-}
-
-/*
* For radix we should always find H_PAGE_HASHPTE zero. Hence
* the below will work for radix too
*/
@@ -1380,6 +1359,8 @@ static inline pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm,
#define __HAVE_ARCH_PMDP_INVALIDATE
extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp);
+extern pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pudp);
#define pmd_move_must_withdraw pmd_move_must_withdraw
struct spinlock;
@@ -1450,22 +1431,5 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va
return false;
}
-/*
- * Like pmd_huge() and pmd_large(), but works regardless of config options
- */
-#define pmd_is_leaf pmd_is_leaf
-#define pmd_leaf pmd_is_leaf
-static inline bool pmd_is_leaf(pmd_t pmd)
-{
- return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
-}
-
-#define pud_is_leaf pud_is_leaf
-#define pud_leaf pud_is_leaf
-static inline bool pud_is_leaf(pud_t pud)
-{
- return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
-}
-
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 357e23a403d3..8f55ff74bb68 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -362,8 +362,6 @@ int radix__create_section_mapping(unsigned long start, unsigned long end,
int radix__remove_section_mapping(unsigned long start, unsigned long end);
#endif /* CONFIG_MEMORY_HOTPLUG */
-void radix__kernel_map_pages(struct page *page, int numpages, int enable);
-
#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
#define vmemmap_can_optimize vmemmap_can_optimize
bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index ef7d2de33b89..f2656774aaa9 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -121,7 +121,7 @@ static inline void invalidate_dcache_range(unsigned long start,
mb(); /* sync */
}
-#ifdef CONFIG_4xx
+#ifdef CONFIG_44x
static inline void flush_instruction_cache(void)
{
iccci((void *)KERNELBASE);
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index 727d4b321937..bf8a228229fa 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -24,12 +24,11 @@ static __always_inline bool cpu_has_feature(unsigned long feature)
{
int i;
-#ifndef __clang__ /* clang can't cope with this */
BUILD_BUG_ON(!__builtin_constant_p(feature));
-#endif
+ BUILD_BUG_ON(__builtin_popcountl(feature) > 1);
#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
- if (!static_key_initialized) {
+ if (!static_key_feature_checks_initialized) {
printk("Warning! cpu_has_feature() used prior to jump label init!\n");
dump_stack();
return early_cpu_has_feature(feature);
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 8765d5158324..29a529d2ab8b 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -193,6 +193,7 @@ static inline void cpu_feature_keys_init(void) { }
#define CPU_FTR_ARCH_31 LONG_ASM_CONST(0x0004000000000000)
#define CPU_FTR_DAWR1 LONG_ASM_CONST(0x0008000000000000)
#define CPU_FTR_DEXCR_NPHIE LONG_ASM_CONST(0x0010000000000000)
+#define CPU_FTR_P11_PVR LONG_ASM_CONST(0x0020000000000000)
#ifndef __ASSEMBLY__
@@ -353,7 +354,6 @@ static inline void cpu_feature_keys_init(void) { }
CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE | CPU_FTR_NOEXECUTE)
#define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON)
#define CPU_FTRS_8XX (CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_40X (CPU_FTR_NOEXECUTE)
#define CPU_FTRS_44X (CPU_FTR_NOEXECUTE)
#define CPU_FTRS_440x6 (CPU_FTR_NOEXECUTE | \
CPU_FTR_INDEXED_DCR)
@@ -454,6 +454,9 @@ static inline void cpu_feature_keys_init(void) { }
CPU_FTR_ARCH_300 | CPU_FTR_ARCH_31 | \
CPU_FTR_DAWR | CPU_FTR_DAWR1 | \
CPU_FTR_DEXCR_NPHIE)
+
+#define CPU_FTRS_POWER11 (CPU_FTRS_POWER10 | CPU_FTR_P11_PVR)
+
#define CPU_FTRS_CELL (CPU_FTR_LWSYNC | \
CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -473,7 +476,7 @@ static inline void cpu_feature_keys_init(void) { }
(CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \
CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | CPU_FTRS_POWER9 | \
CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \
- CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10)
+ CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10 | CPU_FTRS_POWER11)
#else
#define CPU_FTRS_POSSIBLE \
(CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
@@ -481,7 +484,7 @@ static inline void cpu_feature_keys_init(void) { }
CPU_FTRS_POWER8 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \
CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | CPU_FTRS_POWER9 | \
CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \
- CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10)
+ CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10 | CPU_FTRS_POWER11)
#endif /* CONFIG_CPU_LITTLE_ENDIAN */
#endif
#else
@@ -504,9 +507,6 @@ enum {
#ifdef CONFIG_PPC_8xx
CPU_FTRS_8XX |
#endif
-#ifdef CONFIG_40x
- CPU_FTRS_40X |
-#endif
#ifdef CONFIG_PPC_47x
CPU_FTRS_47X | CPU_FTR_476_DD2 |
#elif defined(CONFIG_44x)
@@ -542,20 +542,21 @@ enum {
#define CPU_FTRS_DT_CPU_BASE (~0ul)
#endif
+/* pseries may disable DBELL with ibm,pi-features */
#ifdef CONFIG_CPU_LITTLE_ENDIAN
#define CPU_FTRS_ALWAYS \
- (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & CPU_FTRS_POWER7 & \
- CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & CPU_FTRS_POWER9 & \
- CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
- CPU_FTRS_POWER10 & CPU_FTRS_DT_CPU_BASE)
+ (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & ~CPU_FTR_DBELL & \
+ CPU_FTRS_POWER7 & CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & \
+ CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
+ CPU_FTRS_POWER10 & CPU_FTRS_POWER11 & CPU_FTRS_DT_CPU_BASE)
#else
#define CPU_FTRS_ALWAYS \
(CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \
CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
- ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & CPU_FTRS_POWER9 & \
- CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
- CPU_FTRS_POWER10 & CPU_FTRS_DT_CPU_BASE)
+ ~CPU_FTR_HVMODE & ~CPU_FTR_DBELL & CPU_FTRS_POSSIBLE & \
+ CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
+ CPU_FTRS_POWER10 & CPU_FTRS_POWER11 & CPU_FTRS_DT_CPU_BASE)
#endif /* CONFIG_CPU_LITTLE_ENDIAN */
#endif
#else
@@ -578,9 +579,6 @@ enum {
#ifdef CONFIG_PPC_8xx
CPU_FTRS_8XX &
#endif
-#ifdef CONFIG_40x
- CPU_FTRS_40X &
-#endif
#ifdef CONFIG_PPC_47x
CPU_FTRS_47X &
#elif defined(CONFIG_44x)
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 4961fb38e438..aff858ca99c0 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -32,23 +32,10 @@
#ifdef CONFIG_PPC64
#define get_accounting(tsk) (&get_paca()->accounting)
#define raw_get_accounting(tsk) (&local_paca->accounting)
-static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
#else
#define get_accounting(tsk) (&task_thread_info(tsk)->accounting)
#define raw_get_accounting(tsk) get_accounting(tsk)
-/*
- * 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.
- */
-static inline void arch_vtime_task_switch(struct task_struct *prev)
-{
- struct cpu_accounting_data *acct = get_accounting(current);
- struct cpu_accounting_data *acct0 = get_accounting(prev);
-
- acct->starttime = acct0->starttime;
-}
#endif
/*
diff --git a/arch/powerpc/include/asm/dtl.h b/arch/powerpc/include/asm/dtl.h
index d6f43d149f8d..a5c21bc623cb 100644
--- a/arch/powerpc/include/asm/dtl.h
+++ b/arch/powerpc/include/asm/dtl.h
@@ -1,8 +1,8 @@
#ifndef _ASM_POWERPC_DTL_H
#define _ASM_POWERPC_DTL_H
+#include <linux/rwsem.h>
#include <asm/lppaca.h>
-#include <linux/spinlock_types.h>
/*
* Layout of entries in the hypervisor's dispatch trace log buffer.
@@ -35,7 +35,7 @@ struct dtl_entry {
#define DTL_LOG_ALL (DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT)
extern struct kmem_cache *dtl_cache;
-extern rwlock_t dtl_access_lock;
+extern struct rw_semaphore dtl_access_lock;
extern void register_dtl_buffer(int cpu);
extern void alloc_dtl_buffers(unsigned long *time_limit);
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 514dd056c2c8..5e34611de9ef 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -82,7 +82,7 @@ struct eeh_pe {
int false_positives; /* Times of reported #ff's */
atomic_t pass_dev_cnt; /* Count of passed through devs */
struct eeh_pe *parent; /* Parent PE */
- void *data; /* PE auxillary data */
+ void *data; /* PE auxiliary data */
struct list_head child_list; /* List of PEs below this PE */
struct list_head child; /* Memb. child_list/eeh_phb_pe */
struct list_head edevs; /* List of eeh_dev in this PE */
@@ -308,6 +308,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed);
int eeh_pe_configure(struct eeh_pe *pe);
int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
unsigned long addr, unsigned long mask);
+int eeh_pe_inject_mmio_error(struct pci_dev *pdev);
/**
* EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 79f1c480b5eb..bb4b94444d3e 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -127,8 +127,6 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
/* Notes used in ET_CORE. Note name is "SPU/<fd>/<filename>". */
#define NT_SPU 1
-#define ARCH_HAVE_EXTRA_ELF_NOTES
-
#endif /* CONFIG_SPU_BASE */
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h
index 27f9e11eda28..e83869a4eb6a 100644
--- a/arch/powerpc/include/asm/fadump-internal.h
+++ b/arch/powerpc/include/asm/fadump-internal.h
@@ -42,13 +42,38 @@ static inline u64 fadump_str_to_u64(const char *str)
#define FADUMP_CPU_UNKNOWN (~((u32)0))
-#define FADUMP_CRASH_INFO_MAGIC fadump_str_to_u64("FADMPINF")
+/*
+ * The introduction of new fields in the fadump crash info header has
+ * led to a change in the magic key from `FADMPINF` to `FADMPSIG` for
+ * identifying a kernel crash from an old kernel.
+ *
+ * To prevent the need for further changes to the magic number in the
+ * event of future modifications to the fadump crash info header, a
+ * version field has been introduced to track the fadump crash info
+ * header version.
+ *
+ * Consider a few points before adding new members to the fadump crash info
+ * header structure:
+ *
+ * - Append new members; avoid adding them in between.
+ * - Non-primitive members should have a size member as well.
+ * - For every change in the fadump header, increment the
+ * fadump header version. This helps the updated kernel decide how to
+ * handle kernel dumps from older kernels.
+ */
+#define FADUMP_CRASH_INFO_MAGIC_OLD fadump_str_to_u64("FADMPINF")
+#define FADUMP_CRASH_INFO_MAGIC fadump_str_to_u64("FADMPSIG")
+#define FADUMP_HEADER_VERSION 1
/* fadump crash info structure */
struct fadump_crash_info_header {
u64 magic_number;
- u64 elfcorehdr_addr;
+ u32 version;
u32 crashing_cpu;
+ u64 vmcoreinfo_raddr;
+ u64 vmcoreinfo_size;
+ u32 pt_regs_sz;
+ u32 cpu_mask_sz;
struct pt_regs regs;
struct cpumask cpu_mask;
};
@@ -94,9 +119,13 @@ struct fw_dump {
u64 boot_mem_regs_cnt;
unsigned long fadumphdr_addr;
+ u64 elfcorehdr_addr;
+ u64 elfcorehdr_size;
unsigned long cpu_notes_buf_vaddr;
unsigned long cpu_notes_buf_size;
+ unsigned long param_area;
+
/*
* Maximum size supported by firmware to copy from source to
* destination address per entry.
@@ -111,6 +140,7 @@ struct fw_dump {
unsigned long dump_active:1;
unsigned long dump_registered:1;
unsigned long nocma:1;
+ unsigned long param_area_supported:1;
struct fadump_ops *ops;
};
@@ -129,6 +159,7 @@ struct fadump_ops {
struct seq_file *m);
void (*fadump_trigger)(struct fadump_crash_info_header *fdh,
const char *msg);
+ int (*fadump_max_boot_mem_rgns)(void);
};
/* Helper functions */
@@ -136,7 +167,6 @@ s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus);
void fadump_free_cpu_notes_buf(void);
u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
void __init fadump_update_elfcore_header(char *bufp);
-bool is_fadump_boot_mem_contiguous(void);
bool is_fadump_reserved_mem_contiguous(void);
#else /* !CONFIG_PRESERVE_FA_DUMP */
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 526a6a647312..a48f54dde4f6 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -19,12 +19,16 @@ extern int is_fadump_active(void);
extern int should_fadump_crash(void);
extern void crash_fadump(struct pt_regs *, const char *);
extern void fadump_cleanup(void);
+void fadump_setup_param_area(void);
+extern void fadump_append_bootargs(void);
#else /* CONFIG_FA_DUMP */
static inline int is_fadump_active(void) { return 0; }
static inline int should_fadump_crash(void) { return 0; }
static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
static inline void fadump_cleanup(void) { }
+static inline void fadump_setup_param_area(void) { }
+static inline void fadump_append_bootargs(void) { }
#endif /* !CONFIG_FA_DUMP */
#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
@@ -32,4 +36,11 @@ extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
int depth, void *data);
extern int fadump_reserve_mem(void);
#endif
+
+#if defined(CONFIG_FA_DUMP) && defined(CONFIG_CMA)
+void fadump_cma_init(void);
+#else
+static inline void fadump_cma_init(void) { }
+#endif
+
#endif /* _ASM_POWERPC_FADUMP_H */
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 77824bd289a3..17d168dd8b49 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -291,6 +291,8 @@ extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
+extern bool static_key_feature_checks_initialized;
+
void apply_feature_fixups(void);
void update_mmu_feature_fixups(unsigned long mask);
void setup_feature_keys(void);
diff --git a/arch/powerpc/include/asm/fpu.h b/arch/powerpc/include/asm/fpu.h
new file mode 100644
index 000000000000..ca584e4bc40f
--- /dev/null
+++ b/arch/powerpc/include/asm/fpu.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_POWERPC_FPU_H
+#define _ASM_POWERPC_FPU_H
+
+#include <linux/preempt.h>
+
+#include <asm/cpu_has_feature.h>
+#include <asm/switch_to.h>
+
+#define kernel_fpu_available() (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE))
+
+static inline void kernel_fpu_begin(void)
+{
+ preempt_disable();
+ enable_kernel_fp();
+}
+
+static inline void kernel_fpu_end(void)
+{
+ disable_kernel_fp();
+ preempt_enable();
+}
+
+#endif /* ! _ASM_POWERPC_FPU_H */
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 107fc5a48456..82da7c7a1d12 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -8,8 +8,6 @@
#define MCOUNT_ADDR ((unsigned long)(_mcount))
#define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */
-#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
-
/* Ignore unused weak functions which will have larger offsets */
#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
#define FTRACE_MCOUNT_MAX_OFFSET 16
@@ -26,7 +24,10 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
struct module;
struct dyn_ftrace;
struct dyn_arch_ftrace {
- struct module *mod;
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ /* pointer to the associated out-of-line stub */
+ unsigned long ool_stub;
+#endif
};
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
@@ -34,42 +35,34 @@ struct dyn_arch_ftrace {
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
#define ftrace_init_nop ftrace_init_nop
-struct ftrace_regs {
- struct pt_regs regs;
-};
+#include <linux/ftrace_regs.h>
static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs)
{
/* We clear regs.msr in ftrace_call */
- return fregs->regs.msr ? &fregs->regs : NULL;
+ return arch_ftrace_regs(fregs)->regs.msr ? &arch_ftrace_regs(fregs)->regs : NULL;
}
+#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \
+ (_regs)->result = 0; \
+ (_regs)->nip = arch_ftrace_regs(fregs)->regs.nip; \
+ (_regs)->gpr[1] = arch_ftrace_regs(fregs)->regs.gpr[1]; \
+ asm volatile("mfmsr %0" : "=r" ((_regs)->msr)); \
+ } while (0)
+
static __always_inline void
ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
unsigned long ip)
{
- regs_set_return_ip(&fregs->regs, ip);
+ regs_set_return_ip(&arch_ftrace_regs(fregs)->regs, ip);
}
static __always_inline unsigned long
-ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs)
+ftrace_regs_get_return_address(struct ftrace_regs *fregs)
{
- return instruction_pointer(&fregs->regs);
+ return arch_ftrace_regs(fregs)->regs.link;
}
-#define ftrace_regs_get_argument(fregs, n) \
- regs_get_kernel_argument(&(fregs)->regs, n)
-#define ftrace_regs_get_stack_pointer(fregs) \
- kernel_stack_pointer(&(fregs)->regs)
-#define ftrace_regs_return_value(fregs) \
- regs_return_value(&(fregs)->regs)
-#define ftrace_regs_set_return_value(fregs, ret) \
- regs_set_return_value(&(fregs)->regs, ret)
-#define ftrace_override_function_with_return(fregs) \
- override_function_with_return(&(fregs)->regs)
-#define ftrace_regs_query_register_offset(name) \
- regs_query_register_offset(name)
-
struct ftrace_ops;
#define ftrace_graph_func ftrace_graph_func
@@ -133,8 +126,36 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
#ifdef CONFIG_FUNCTION_TRACER
extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+struct ftrace_ool_stub {
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+ struct ftrace_ops *ftrace_op;
+#endif
+ u32 insn[4];
+} __aligned(sizeof(unsigned long));
+extern struct ftrace_ool_stub ftrace_ool_stub_text_end[], ftrace_ool_stub_text[],
+ ftrace_ool_stub_inittext[];
+extern unsigned int ftrace_ool_stub_text_end_count, ftrace_ool_stub_text_count,
+ ftrace_ool_stub_inittext_count;
+#endif
void ftrace_free_init_tramp(void);
unsigned long ftrace_call_adjust(unsigned long addr);
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+/*
+ * When an ftrace registered caller is tracing a function that is also set by a
+ * register_ftrace_direct() call, it needs to be differentiated in the
+ * ftrace_caller trampoline so that the direct call can be invoked after the
+ * other ftrace ops. To do this, place the direct caller in the orig_gpr3 field
+ * of pt_regs. This tells ftrace_caller that there's a direct caller.
+ */
+static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr)
+{
+ struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs;
+
+ regs->orig_gpr3 = addr;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
#else
static inline void ftrace_free_init_tramp(void) { }
static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; }
diff --git a/arch/powerpc/include/asm/guest-state-buffer.h b/arch/powerpc/include/asm/guest-state-buffer.h
index 808149f31576..d107abe1468f 100644
--- a/arch/powerpc/include/asm/guest-state-buffer.h
+++ b/arch/powerpc/include/asm/guest-state-buffer.h
@@ -81,6 +81,7 @@
#define KVMPPC_GSID_HASHKEYR 0x1050
#define KVMPPC_GSID_HASHPKEYR 0x1051
#define KVMPPC_GSID_CTRL 0x1052
+#define KVMPPC_GSID_DPDES 0x1053
#define KVMPPC_GSID_CR 0x2000
#define KVMPPC_GSID_PIDR 0x2001
@@ -110,7 +111,7 @@
#define KVMPPC_GSE_META_COUNT (KVMPPC_GSE_META_END - KVMPPC_GSE_META_START + 1)
#define KVMPPC_GSE_DW_REGS_START KVMPPC_GSID_GPR(0)
-#define KVMPPC_GSE_DW_REGS_END KVMPPC_GSID_CTRL
+#define KVMPPC_GSE_DW_REGS_END KVMPPC_GSID_DPDES
#define KVMPPC_GSE_DW_REGS_COUNT \
(KVMPPC_GSE_DW_REGS_END - KVMPPC_GSE_DW_REGS_START + 1)
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index ea71f7245a63..86326587e58d 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -15,6 +15,15 @@
extern bool hugetlb_disabled;
+static inline bool hugepages_supported(void)
+{
+ if (hugetlb_disabled)
+ return false;
+
+ return HPAGE_SHIFT != 0;
+}
+#define hugepages_supported hugepages_supported
+
void __init hugetlbpage_init_defaultsize(void);
int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
@@ -30,14 +39,14 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
}
#define is_hugepage_only_range is_hugepage_only_range
-#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
-void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
- unsigned long end, unsigned long floor,
- unsigned long ceiling);
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep)
+ unsigned long addr, pte_t *ptep,
+ unsigned long sz)
{
return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
}
@@ -47,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
pte_t pte;
+ unsigned long sz = huge_page_size(hstate_vma(vma));
- pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+ pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
flush_hugetlb_page(vma, addr);
return pte;
}
@@ -67,14 +77,6 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
{
}
-#define hugepd_shift(x) 0
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
- unsigned pdshift)
-{
- return NULL;
-}
-
-
static inline void __init gigantic_hugetlb_cma_reserve(void)
{
}
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index a41e542ba94d..65d1f291393d 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -495,6 +495,7 @@
#define H_GUEST_CAP_COPY_MEM (1UL<<(63-0))
#define H_GUEST_CAP_POWER9 (1UL<<(63-1))
#define H_GUEST_CAP_POWER10 (1UL<<(63-2))
+#define H_GUEST_CAP_POWER11 (1UL<<(63-3))
#define H_GUEST_CAP_BITMAP2 (1UL<<(63-63))
#ifndef __ASSEMBLY__
@@ -524,7 +525,7 @@ long plpar_hcall_norets_notrace(unsigned long opcode, ...);
* Used for all but the craziest of phyp interfaces (see plpar_hcall9)
*/
#define PLPAR_HCALL_BUFSIZE 4
-long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...);
+long plpar_hcall(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...);
/**
* plpar_hcall_raw: - Make a hypervisor call without calculating hcall stats
@@ -538,7 +539,7 @@ long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...);
* plpar_hcall, but plpar_hcall_raw works in real mode and does not
* calculate hypervisor call statistics.
*/
-long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...);
+long plpar_hcall_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...);
/**
* plpar_hcall9: - Make a pseries hypervisor call with up to 9 return arguments
@@ -549,8 +550,8 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...);
* PLPAR_HCALL9_BUFSIZE to size the return argument buffer.
*/
#define PLPAR_HCALL9_BUFSIZE 9
-long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...);
-long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...);
+long plpar_hcall9(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...);
+long plpar_hcall9_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...);
/* pseries hcall tracing */
extern struct static_key hcall_tracepoint_key;
@@ -570,7 +571,7 @@ struct hvcall_mpp_data {
unsigned long backing_mem;
};
-int h_get_mpp(struct hvcall_mpp_data *);
+long h_get_mpp(struct hvcall_mpp_data *mpp_data);
struct hvcall_mpp_x_data {
unsigned long coalesced_bytes;
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 317659fdeacf..569ac1165b06 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -63,7 +63,7 @@
static inline void __hard_irq_enable(void)
{
- if (IS_ENABLED(CONFIG_BOOKE_OR_40x))
+ if (IS_ENABLED(CONFIG_BOOKE))
wrtee(MSR_EE);
else if (IS_ENABLED(CONFIG_PPC_8xx))
wrtspr(SPRN_EIE);
@@ -75,7 +75,7 @@ static inline void __hard_irq_enable(void)
static inline void __hard_irq_disable(void)
{
- if (IS_ENABLED(CONFIG_BOOKE_OR_40x))
+ if (IS_ENABLED(CONFIG_BOOKE))
wrtee(0);
else if (IS_ENABLED(CONFIG_PPC_8xx))
wrtspr(SPRN_EID);
@@ -87,7 +87,7 @@ static inline void __hard_irq_disable(void)
static inline void __hard_EE_RI_disable(void)
{
- if (IS_ENABLED(CONFIG_BOOKE_OR_40x))
+ if (IS_ENABLED(CONFIG_BOOKE))
wrtee(0);
else if (IS_ENABLED(CONFIG_PPC_8xx))
wrtspr(SPRN_NRI);
@@ -99,7 +99,7 @@ static inline void __hard_EE_RI_disable(void)
static inline void __hard_RI_enable(void)
{
- if (IS_ENABLED(CONFIG_BOOKE_OR_40x))
+ if (IS_ENABLED(CONFIG_BOOKE))
return;
if (IS_ENABLED(CONFIG_PPC_8xx))
diff --git a/arch/powerpc/include/asm/ibmebus.h b/arch/powerpc/include/asm/ibmebus.h
index 6f33253a364a..46fe406f461c 100644
--- a/arch/powerpc/include/asm/ibmebus.h
+++ b/arch/powerpc/include/asm/ibmebus.h
@@ -48,7 +48,7 @@
struct platform_driver;
-extern struct bus_type ibmebus_bus_type;
+extern const struct bus_type ibmebus_bus_type;
int ibmebus_register_driver(struct platform_driver *drv);
void ibmebus_unregister_driver(struct platform_driver *drv);
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index a4196ab1d016..23638d4e73ac 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -97,7 +97,7 @@ DECLARE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
static inline bool is_implicit_soft_masked(struct pt_regs *regs)
{
- if (regs->msr & MSR_PR)
+ if (user_mode(regs))
return false;
if (regs->nip >= (unsigned long)__end_soft_masked)
@@ -177,7 +177,7 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs)
if (user_mode(regs)) {
kuap_lock();
- CT_WARN_ON(ct_state() != CONTEXT_USER);
+ CT_WARN_ON(ct_state() != CT_STATE_USER);
user_exit_irqoff();
account_cpu_user_entry();
@@ -189,8 +189,8 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs)
* so avoid recursion.
*/
if (TRAP(regs) != INTERRUPT_PROGRAM)
- CT_WARN_ON(ct_state() != CONTEXT_KERNEL &&
- ct_state() != CONTEXT_IDLE);
+ CT_WARN_ON(ct_state() != CT_STATE_KERNEL &&
+ ct_state() != CT_STATE_IDLE);
INT_SOFT_MASK_BUG_ON(regs, is_implicit_soft_masked(regs));
INT_SOFT_MASK_BUG_ON(regs, arch_irq_disabled_regs(regs) &&
search_kernel_restart_table(regs->nip));
@@ -336,6 +336,14 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
if (IS_ENABLED(CONFIG_KASAN))
return;
+ /*
+ * Likewise, do not use it in real mode if percpu first chunk is not
+ * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there
+ * are chances where percpu allocation can come from vmalloc area.
+ */
+ if (percpu_first_chunk_is_paged)
+ return;
+
/* Otherwise, it should be safe to call it */
nmi_enter();
}
@@ -351,6 +359,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
// no nmi_exit for a pseries hash guest taking a real mode exception
} else if (IS_ENABLED(CONFIG_KASAN)) {
// no nmi_exit for KASAN in real mode
+ } else if (percpu_first_chunk_is_paged) {
+ // no nmi_exit if percpu first chunk is not embedded
} else {
nmi_exit();
}
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 08c550ed49be..fd92ac450169 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -37,7 +37,7 @@ extern struct pci_dev *isa_bridge_pcidev;
* define properly based on the platform
*/
#ifndef CONFIG_PCI
-#define _IO_BASE 0
+#define _IO_BASE POISON_POINTER_DELTA
#define _ISA_MEM_BASE 0
#define PCI_DRAM_OFFSET 0
#elif defined(CONFIG_PPC32)
@@ -585,12 +585,12 @@ __do_out_asm(_rec_outl, "stwbrx")
#define __do_inw(port) _rec_inw(port)
#define __do_inl(port) _rec_inl(port)
#else /* CONFIG_PPC32 */
-#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)_IO_BASE+port);
-#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)_IO_BASE+port);
-#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)_IO_BASE+port);
-#define __do_inb(port) readb((PCI_IO_ADDR)_IO_BASE + port);
-#define __do_inw(port) readw((PCI_IO_ADDR)_IO_BASE + port);
-#define __do_inl(port) readl((PCI_IO_ADDR)_IO_BASE + port);
+#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)(_IO_BASE+port));
+#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)(_IO_BASE+port));
+#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)(_IO_BASE+port));
+#define __do_inb(port) readb((PCI_IO_ADDR)(_IO_BASE + port));
+#define __do_inw(port) readw((PCI_IO_ADDR)(_IO_BASE + port));
+#define __do_inl(port) readl((PCI_IO_ADDR)(_IO_BASE + port));
#endif /* !CONFIG_PPC32 */
#ifdef CONFIG_EEH
@@ -606,12 +606,12 @@ __do_out_asm(_rec_outl, "stwbrx")
#define __do_writesw(a, b, n) _outsw(PCI_FIX_ADDR(a),(b),(n))
#define __do_writesl(a, b, n) _outsl(PCI_FIX_ADDR(a),(b),(n))
-#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
-#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
-#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
-#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
-#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
-#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
+#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n))
+#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n))
+#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n))
+#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n))
+#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n))
+#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n))
#define __do_memset_io(addr, c, n) \
_memset_io(PCI_FIX_ADDR(addr), c, n)
@@ -970,19 +970,7 @@ static inline void * phys_to_virt(unsigned long address)
#define phys_to_virt phys_to_virt
/*
- * Change "struct page" to physical address.
- */
-static inline phys_addr_t page_to_phys(struct page *page)
-{
- unsigned long pfn = page_to_pfn(page);
-
- WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && !pfn_valid(pfn));
-
- return PFN_PHYS(pfn);
-}
-
-/*
- * 32 bits still uses virt_to_bus() for it's implementation of DMA
+ * 32 bits still uses virt_to_bus() for its implementation of DMA
* mappings se we have to keep it defined here. We also have some old
* drivers (shame shame shame) that use bus_to_virt() and haven't been
* fixed yet so I need to define it here.
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 026695943550..04072b5f8962 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -31,6 +31,8 @@
#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info"
#define DMA64_PROPNAME "linux,dma64-ddr-window-info"
+#define MIN_DDW_VPMEM_DMA_WINDOW SZ_2G
+
/* Boot time flags */
extern int iommu_is_off;
extern int iommu_force_on;
@@ -156,6 +158,9 @@ extern int iommu_tce_table_put(struct iommu_table *tbl);
extern struct iommu_table *iommu_init_table(struct iommu_table *tbl,
int nid, unsigned long res_start, unsigned long res_end);
bool iommu_table_in_use(struct iommu_table *tbl);
+extern void iommu_table_reserve_pages(struct iommu_table *tbl,
+ unsigned long res_start, unsigned long res_end);
+extern void iommu_table_clear(struct iommu_table *tbl);
#define IOMMU_TABLE_GROUP_MAX_TABLES 2
@@ -178,9 +183,9 @@ struct iommu_table_group_ops {
long (*unset_window)(struct iommu_table_group *table_group,
int num);
/* Switch ownership from platform code to external user (e.g. VFIO) */
- long (*take_ownership)(struct iommu_table_group *table_group);
+ long (*take_ownership)(struct iommu_table_group *table_group, struct device *dev);
/* Switch ownership from external user (e.g. VFIO) back to core */
- void (*release_ownership)(struct iommu_table_group *table_group);
+ void (*release_ownership)(struct iommu_table_group *table_group, struct device *dev);
};
struct iommu_table_group_link {
@@ -217,8 +222,8 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
enum dma_data_direction *direction);
extern void iommu_tce_kill(struct iommu_table *tbl,
unsigned long entry, unsigned long pages);
+int dev_has_iommu_table(struct device *dev, void *data);
-extern struct iommu_table_group_ops spapr_tce_table_group_ops;
#else
static inline void iommu_register_group(struct iommu_table_group *table_group,
int pci_domain_number,
@@ -231,6 +236,11 @@ static inline int iommu_add_device(struct iommu_table_group *table_group,
{
return 0;
}
+
+static inline int dev_has_iommu_table(struct device *dev, void *data)
+{
+ return 0;
+}
#endif /* !CONFIG_IOMMU_API */
u64 dma_iommu_get_required_mask(struct device *dev);
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index ba1a5974e714..aa3751960ffd 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -33,7 +33,7 @@ extern int distribute_irqs;
struct pt_regs;
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
/*
* Per-cpu stacks for handling critical, debug and machine check
* level interrupts.
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index 365d2720097c..b5bbb94c51f6 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -19,7 +19,7 @@
#define KASAN_SHADOW_SCALE_SHIFT 3
-#if defined(CONFIG_MODULES) && defined(CONFIG_PPC32)
+#if defined(CONFIG_EXECMEM) && defined(CONFIG_PPC32)
#define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M)
#else
#define KASAN_KERN_START PAGE_OFFSET
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index e1b43aa12175..601e569303e1 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -55,59 +55,17 @@
typedef void (*crash_shutdown_t)(void);
#ifdef CONFIG_KEXEC_CORE
-
-/*
- * This function is responsible for capturing register states if coming
- * via panic or invoking dump using sysrq-trigger.
- */
-static inline void crash_setup_regs(struct pt_regs *newregs,
- struct pt_regs *oldregs)
-{
- if (oldregs)
- memcpy(newregs, oldregs, sizeof(*newregs));
- else
- ppc_save_regs(newregs);
-}
+struct kimage;
+struct pt_regs;
extern void kexec_smp_wait(void); /* get and clear naca physid, wait for
master to copy new code to 0 */
-extern int crashing_cpu;
-extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
-extern void crash_ipi_callback(struct pt_regs *);
-extern int crash_wake_offline;
-
-struct kimage;
-struct pt_regs;
extern void default_machine_kexec(struct kimage *image);
-extern void default_machine_crash_shutdown(struct pt_regs *regs);
-extern int crash_shutdown_register(crash_shutdown_t handler);
-extern int crash_shutdown_unregister(crash_shutdown_t handler);
-
-extern void crash_kexec_prepare(void);
-extern void crash_kexec_secondary(struct pt_regs *regs);
-int __init overlaps_crashkernel(unsigned long start, unsigned long size);
-extern void reserve_crashkernel(void);
-extern void machine_kexec_mask_interrupts(void);
-
-static inline bool kdump_in_progress(void)
-{
- return crashing_cpu >= 0;
-}
void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_code_buffer,
unsigned long start_address) __noreturn;
-
void kexec_copy_flush(struct kimage *image);
-#if defined(CONFIG_CRASH_DUMP)
-bool is_kdump_kernel(void);
-#define is_kdump_kernel is_kdump_kernel
-#if defined(CONFIG_PPC_RTAS)
-void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
-#define crash_free_reserved_phys_range crash_free_reserved_phys_range
-#endif /* CONFIG_PPC_RTAS */
-#endif /* CONFIG_CRASH_DUMP */
-
#ifdef CONFIG_KEXEC_FILE
extern const struct kexec_file_ops kexec_elf64_ops;
@@ -144,23 +102,73 @@ int load_crashdump_segments_ppc64(struct kimage *image,
int setup_purgatory_ppc64(struct kimage *image, const void *slave_code,
const void *fdt, unsigned long kernel_load_addr,
unsigned long fdt_load_addr);
-unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image);
-int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
- unsigned long initrd_load_addr,
- unsigned long initrd_len, const char *cmdline);
+unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image, struct crash_mem *rmem);
+int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem *rmem);
#endif /* CONFIG_PPC64 */
#endif /* CONFIG_KEXEC_FILE */
-#else /* !CONFIG_KEXEC_CORE */
-static inline void crash_kexec_secondary(struct pt_regs *regs) { }
+#endif /* CONFIG_KEXEC_CORE */
+
+#ifdef CONFIG_CRASH_RESERVE
+int __init overlaps_crashkernel(unsigned long start, unsigned long size);
+extern void reserve_crashkernel(void);
+#else
+static inline void reserve_crashkernel(void) {}
+static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
+#endif
-static inline int overlaps_crashkernel(unsigned long start, unsigned long size)
+#if defined(CONFIG_CRASH_DUMP)
+/*
+ * This function is responsible for capturing register states if coming
+ * via panic or invoking dump using sysrq-trigger.
+ */
+static inline void crash_setup_regs(struct pt_regs *newregs,
+ struct pt_regs *oldregs)
{
- return 0;
+ if (oldregs)
+ memcpy(newregs, oldregs, sizeof(*newregs));
+ else
+ ppc_save_regs(newregs);
}
-static inline void reserve_crashkernel(void) { ; }
+#ifdef CONFIG_CRASH_HOTPLUG
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg);
+#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags);
+#define arch_crash_hotplug_support arch_crash_hotplug_support
+
+unsigned int arch_crash_get_elfcorehdr_size(void);
+#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size
+#endif /* CONFIG_CRASH_HOTPLUG */
+
+extern int crashing_cpu;
+extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
+extern void crash_ipi_callback(struct pt_regs *regs);
+extern int crash_wake_offline;
+
+extern int crash_shutdown_register(crash_shutdown_t handler);
+extern int crash_shutdown_unregister(crash_shutdown_t handler);
+extern void default_machine_crash_shutdown(struct pt_regs *regs);
+
+extern void crash_kexec_prepare(void);
+extern void crash_kexec_secondary(struct pt_regs *regs);
+
+static inline bool kdump_in_progress(void)
+{
+ return crashing_cpu >= 0;
+}
+
+bool is_kdump_kernel(void);
+#define is_kdump_kernel is_kdump_kernel
+#if defined(CONFIG_PPC_RTAS)
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
+#define crash_free_reserved_phys_range crash_free_reserved_phys_range
+#endif /* CONFIG_PPC_RTAS */
+
+#else /* !CONFIG_CRASH_DUMP */
+static inline void crash_kexec_secondary(struct pt_regs *regs) { }
static inline int crash_shutdown_register(crash_shutdown_t handler)
{
@@ -183,7 +191,11 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
{
}
-#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_CRASH_DUMP */
+
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
+int update_cpus_node(void *fdt);
+#endif
#ifdef CONFIG_PPC_BOOK3S_64
#include <asm/book3s/64/kexec.h>
diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h
index f83866a19e87..14055896cbcb 100644
--- a/arch/powerpc/include/asm/kexec_ranges.h
+++ b/arch/powerpc/include/asm/kexec_ranges.h
@@ -7,19 +7,9 @@
void sort_memory_ranges(struct crash_mem *mrngs, bool merge);
struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges);
int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size);
-int add_tce_mem_ranges(struct crash_mem **mem_ranges);
-int add_initrd_mem_range(struct crash_mem **mem_ranges);
-#ifdef CONFIG_PPC_64S_HASH_MMU
-int add_htab_mem_range(struct crash_mem **mem_ranges);
-#else
-static inline int add_htab_mem_range(struct crash_mem **mem_ranges)
-{
- return 0;
-}
-#endif
-int add_kernel_mem_range(struct crash_mem **mem_ranges);
-int add_rtas_mem_range(struct crash_mem **mem_ranges);
-int add_opal_mem_range(struct crash_mem **mem_ranges);
-int add_reserved_mem_ranges(struct crash_mem **mem_ranges);
-
+int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size);
+int get_exclude_memory_ranges(struct crash_mem **mem_ranges);
+int get_reserved_memory_ranges(struct crash_mem **mem_ranges);
+int get_crash_memory_ranges(struct crash_mem **mem_ranges);
+int get_usable_memory_ranges(struct crash_mem **mem_ranges);
#endif /* _ASM_POWERPC_KEXEC_RANGES_H */
diff --git a/arch/powerpc/include/asm/kfence.h b/arch/powerpc/include/asm/kfence.h
index 424ceef82ae6..1f7cab58ab2c 100644
--- a/arch/powerpc/include/asm/kfence.h
+++ b/arch/powerpc/include/asm/kfence.h
@@ -15,9 +15,22 @@
#define ARCH_FUNC_PREFIX "."
#endif
+extern bool kfence_early_init;
+extern bool kfence_disabled;
+
+static inline void disable_kfence(void)
+{
+ kfence_disabled = true;
+}
+
static inline bool arch_kfence_init_pool(void)
{
- return true;
+ return !kfence_disabled;
+}
+
+static inline bool kfence_early_init_enabled(void)
+{
+ return IS_ENABLED(CONFIG_KFENCE) && kfence_early_init;
}
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 4525a9c68260..dfe2e5ad3b21 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -21,7 +21,7 @@
#include <linux/percpu.h>
#include <linux/module.h>
#include <asm/probes.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#ifdef CONFIG_KPROBES
#define __ARCH_WANT_KPROBES_INSN_SLOT
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index ad7e8c5aec3f..2bb03d941e3e 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -20,7 +20,7 @@ static __always_inline bool kuap_is_disabled(void);
#include <asm/nohash/32/kup-8xx.h>
#endif
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
#include <asm/nohash/kup-booke.h>
#endif
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 3e1e2a698c9e..e1ff291ba891 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -203,7 +203,7 @@ extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested,
extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
unsigned long gpa,
struct kvm_memory_slot *memslot,
- bool writing, bool kvm_ro,
+ bool writing,
pte_t *inserted_pte, unsigned int *levelp);
extern int kvmppc_init_vm_radix(struct kvm *kvm);
extern void kvmppc_free_radix(struct kvm *kvm);
@@ -235,7 +235,7 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
extern int kvmppc_emulate_paired_single(struct kvm_vcpu *vcpu);
extern kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa,
- bool writing, bool *writable);
+ bool writing, bool *writable, struct page **page);
extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
unsigned long *rmap, long pte_index, int realmode);
extern void kvmppc_update_dirty_map(const struct kvm_memory_slot *memslot,
@@ -594,6 +594,7 @@ static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \
KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB)
+KVMPPC_BOOK3S_VCORE_ACCESSOR(dpdes, 64, KVMPPC_GSID_DPDES)
KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32, KVMPPC_GSID_LOGICAL_PVR)
KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64, KVMPPC_GSID_LPCR)
KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index d8729ec81ca0..b936e174eefd 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -684,6 +684,17 @@ int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1);
int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu);
int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa);
+int kvmhv_counters_tracepoint_regfunc(void);
+void kvmhv_counters_tracepoint_unregfunc(void);
+int kvmhv_get_l2_counters_status(void);
+void kvmhv_set_l2_counters_status(int cpu, bool status);
+u64 kvmhv_get_l1_to_l2_cs_time(void);
+u64 kvmhv_get_l2_to_l1_cs_time(void);
+u64 kvmhv_get_l2_runtime_agg(void);
+u64 kvmhv_get_l1_to_l2_cs_time_vcpu(void);
+u64 kvmhv_get_l2_to_l1_cs_time_vcpu(void);
+u64 kvmhv_get_l2_runtime_agg_vcpu(void);
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 8abac532146e..6e1108f8fce6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -599,6 +599,9 @@ struct kvm_vcpu_arch {
ulong dawrx0;
ulong dawr1;
ulong dawrx1;
+ ulong dexcr;
+ ulong hashkeyr;
+ ulong hashpkeyr;
ulong ciabr;
ulong cfar;
ulong ppr;
@@ -868,6 +871,11 @@ struct kvm_vcpu_arch {
struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */
#endif
#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ u64 l1_to_l2_cs;
+ u64 l2_to_l1_cs;
+ u64 l2_runtime_agg;
+#endif
};
#define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
@@ -897,7 +905,6 @@ struct kvm_vcpu_arch {
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 3281215097cc..ca3829d47ab7 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -287,7 +287,6 @@ struct kvmppc_ops {
bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range);
bool (*age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
bool (*test_age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
- bool (*set_spte_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
void (*free_memslot)(struct kvm_memory_slot *slot);
int (*init_vm)(struct kvm *kvm);
void (*destroy_vm)(struct kvm *kvm);
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 61ec2447dabf..f40a646bee3c 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -62,7 +62,8 @@ struct lppaca {
u8 donate_dedicated_cpu; /* Donate dedicated CPU cycles */
u8 fpregs_in_use;
u8 pmcregs_in_use;
- u8 reserved8[28];
+ u8 l2_counters_enable; /* Enable usage of counters for KVM guest */
+ u8 reserved8[27];
__be64 wait_state_cycles; /* Wait cycles for this proc */
u8 reserved9[28];
__be16 slb_count; /* # of SLBs to maintain */
@@ -92,9 +93,13 @@ struct lppaca {
/* cacheline 4-5 */
__be32 page_ins; /* CMO Hint - # page ins by OS */
- u8 reserved12[148];
+ u8 reserved12[28];
+ volatile __be64 l1_to_l2_cs_tb;
+ volatile __be64 l2_to_l1_cs_tb;
+ volatile __be64 l2_runtime_tb;
+ u8 reserved13[96];
volatile __be64 dtl_idx; /* Dispatch Trace Log head index */
- u8 reserved13[96];
+ u8 reserved14[96];
} ____cacheline_aligned;
#define lppaca_of(cpu) (*paca_ptrs[cpu]->lppaca_ptr)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index d31a5ec1550d..3298eec123a3 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -4,24 +4,29 @@
#ifdef __KERNEL__
#include <linux/compiler.h>
-#include <linux/seq_file.h>
#include <linux/init.h>
-#include <linux/dma-mapping.h>
#include <linux/export.h>
+#include <linux/time64.h>
+
+#include <asm/page.h>
struct pt_regs;
struct pci_bus;
+struct device;
struct device_node;
struct iommu_table;
struct rtc_time;
struct file;
+struct pci_dev;
struct pci_controller;
struct kimage;
struct pci_host_bridge;
+struct seq_file;
struct machdep_calls {
const char *name;
const char *compatible;
+ const char * const *compatibles;
#ifdef CONFIG_PPC64
#ifdef CONFIG_PM
void (*iommu_restore)(void);
diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h
index 3a07c62973aa..9203ff6acbf6 100644
--- a/arch/powerpc/include/asm/macio.h
+++ b/arch/powerpc/include/asm/macio.h
@@ -6,7 +6,7 @@
#include <linux/of.h>
#include <linux/platform_device.h>
-extern struct bus_type macio_bus_type;
+extern const struct bus_type macio_bus_type;
/* MacIO device driver is defined later */
struct macio_driver;
@@ -126,7 +126,7 @@ static inline struct pci_dev *macio_get_pci_dev(struct macio_dev *mdev)
struct macio_driver
{
int (*probe)(struct macio_dev* dev, const struct of_device_id *match);
- int (*remove)(struct macio_dev* dev);
+ void (*remove)(struct macio_dev *dev);
int (*suspend)(struct macio_dev* dev, pm_message_t state);
int (*resume)(struct macio_dev* dev);
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 17a77d47ed6d..42a51a993d94 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -6,7 +6,7 @@
#include <uapi/asm/mman.h>
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) && !defined(BUILD_VDSO)
#include <asm/cputable.h>
#include <linux/mm.h>
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index d8b7e246a32f..4182d68d9cd1 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -16,7 +16,6 @@
*/
#define MMU_FTR_HPTE_TABLE ASM_CONST(0x00000001)
#define MMU_FTR_TYPE_8xx ASM_CONST(0x00000002)
-#define MMU_FTR_TYPE_40x ASM_CONST(0x00000004)
#define MMU_FTR_TYPE_44x ASM_CONST(0x00000008)
#define MMU_FTR_TYPE_FSL_E ASM_CONST(0x00000010)
#define MMU_FTR_TYPE_47x ASM_CONST(0x00000020)
@@ -133,6 +132,7 @@
#define MMU_FTRS_POWER8 MMU_FTRS_POWER6
#define MMU_FTRS_POWER9 MMU_FTRS_POWER6
#define MMU_FTRS_POWER10 MMU_FTRS_POWER6
+#define MMU_FTRS_POWER11 MMU_FTRS_POWER6
#define MMU_FTRS_CELL MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
MMU_FTR_CI_LARGE_PAGE
#define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
@@ -152,9 +152,6 @@ enum {
#ifdef CONFIG_PPC_8xx
MMU_FTR_TYPE_8xx |
#endif
-#ifdef CONFIG_40x
- MMU_FTR_TYPE_40x |
-#endif
#ifdef CONFIG_PPC_47x
MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL |
#elif defined(CONFIG_44x)
@@ -201,9 +198,6 @@ enum {
#ifdef CONFIG_PPC_8xx
#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_8xx
#endif
-#ifdef CONFIG_40x
-#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_40x
-#endif
#ifdef CONFIG_PPC_47x
#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_47x
#elif defined(CONFIG_44x)
@@ -245,12 +239,11 @@ static __always_inline bool mmu_has_feature(unsigned long feature)
{
int i;
-#ifndef __clang__ /* clang can't cope with this */
BUILD_BUG_ON(!__builtin_constant_p(feature));
-#endif
+ BUILD_BUG_ON(__builtin_popcountl(feature) > 1);
#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
- if (!static_key_initialized) {
+ if (!static_key_feature_checks_initialized) {
printk("Warning! mmu_has_feature() used prior to jump label init!\n");
dump_stack();
return early_mmu_has_feature(feature);
@@ -330,17 +323,10 @@ static __always_inline bool early_radix_enabled(void)
return early_mmu_has_feature(MMU_FTR_TYPE_RADIX);
}
-#ifdef CONFIG_STRICT_KERNEL_RWX
-static inline bool strict_kernel_rwx_enabled(void)
-{
- return rodata_enabled;
-}
-#else
static inline bool strict_kernel_rwx_enabled(void)
{
- return false;
+ return IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && rodata_enabled;
}
-#endif
static inline bool strict_module_rwx_enabled(void)
{
@@ -412,9 +398,5 @@ extern void *abatron_pteptrs[2];
#include <asm/nohash/mmu.h>
#endif
-#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
-#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
-#endif
-
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_MMU_H_ */
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 37bffa0f7918..a157ab513347 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -116,9 +116,6 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
}
#endif
-extern int use_cop(unsigned long acop, struct mm_struct *mm);
-extern void drop_cop(unsigned long acop, struct mm_struct *mm);
-
#ifdef CONFIG_PPC_BOOK3S_64
static inline void inc_mm_active_cpus(struct mm_struct *mm)
{
@@ -260,15 +257,6 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
extern void arch_exit_mmap(struct mm_struct *mm);
-static inline void arch_unmap(struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- unsigned long vdso_base = (unsigned long)mm->context.vdso;
-
- if (start <= vdso_base && vdso_base < end)
- mm->context.vdso = NULL;
-}
-
#ifdef CONFIG_PPC_MEM_KEYS
bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
bool execute, bool foreign);
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index da827d2d0866..d99863cd6cde 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -20,12 +20,6 @@
#ifdef CONFIG_NUMA
-extern struct pglist_data *node_data[];
-/*
- * Return a pointer to the node data for node n.
- */
-#define NODE_DATA(nid) (node_data[nid])
-
/*
* Following are specific to this numa platform.
*/
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index a8e2e8339fb7..e1ee5026ac4a 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -35,9 +35,11 @@ struct mod_arch_specific {
bool toc_fixed; /* Have we fixed up .TOC.? */
#endif
+#ifdef CONFIG_PPC64_ELF_ABI_V1
/* For module function descriptor dereference */
unsigned long start_opd;
unsigned long end_opd;
+#endif
#else /* powerpc64 */
/* Indices of PLT sections within module. */
unsigned int core_plt_section;
@@ -47,12 +49,12 @@ struct mod_arch_specific {
#ifdef CONFIG_DYNAMIC_FTRACE
unsigned long tramp;
unsigned long tramp_regs;
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+ struct ftrace_ool_stub *ool_stubs;
+ unsigned int ool_stub_count;
+ unsigned int ool_stub_index;
+#endif
#endif
-
- /* List of BUG addresses, source line numbers and filenames */
- struct list_head bug_list;
- struct bug_entry *bug_table;
- unsigned int num_bugs;
};
/*
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index 58353c5bd3fb..0c03a98986cd 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -336,7 +336,7 @@ struct mpic
#endif
};
-extern struct bus_type mpic_subsys;
+extern const struct bus_type mpic_subsys;
/*
* MPIC flags (passed to mpic_alloc)
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index 92df40c6cc6b..014799557f60 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -4,42 +4,12 @@
#define PAGE_SHIFT_8M 23
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
- BUG_ON(!hugepd_ok(hpd));
-
- return (pte_t *)__va(hpd_val(hpd) & ~HUGEPD_SHIFT_MASK);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
- return PAGE_SHIFT_8M;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
- unsigned int pdshift)
-{
- unsigned long idx = (addr & (SZ_4M - 1)) >> PAGE_SHIFT;
-
- return hugepd_page(hpd) + idx;
-}
-
static inline void flush_hugetlb_page(struct vm_area_struct *vma,
unsigned long vmaddr)
{
flush_tlb_page(vma, vmaddr);
}
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
- *hpdp = __hugepd(__pa(new) | _PMD_USER | _PMD_PRESENT | _PMD_PAGE_8M);
-}
-
-static inline void hugepd_populate_kernel(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
- *hpdp = __hugepd(__pa(new) | _PMD_PRESENT | _PMD_PAGE_8M);
-}
-
static inline int check_and_get_huge_psize(int shift)
{
return shift_to_mmu_psize(shift);
@@ -49,6 +19,14 @@ static inline int check_and_get_huge_psize(int shift)
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
pte_t pte, unsigned long sz);
+#define __HAVE_ARCH_HUGE_PTEP_GET
+static inline pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+ if (ptep_is_8m_pmdp(mm, addr, ptep))
+ ptep = pte_offset_kernel((pmd_t *)ptep, ALIGN_DOWN(addr, SZ_8M));
+ return ptep_get(ptep);
+}
+
#define __HAVE_ARCH_HUGE_PTE_CLEAR
static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long sz)
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-40x.h b/arch/powerpc/include/asm/nohash/32/mmu-40x.h
deleted file mode 100644
index 8a8f13a22cf4..000000000000
--- a/arch/powerpc/include/asm/nohash/32/mmu-40x.h
+++ /dev/null
@@ -1,68 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_MMU_40X_H_
-#define _ASM_POWERPC_MMU_40X_H_
-
-/*
- * PPC40x support
- */
-
-#define PPC40X_TLB_SIZE 64
-
-/*
- * TLB entries are defined by a "high" tag portion and a "low" data
- * portion. On all architectures, the data portion is 32-bits.
- *
- * TLB entries are managed entirely under software control by reading,
- * writing, and searchoing using the 4xx-specific tlbre, tlbwr, and tlbsx
- * instructions.
- */
-
-#define TLB_LO 1
-#define TLB_HI 0
-
-#define TLB_DATA TLB_LO
-#define TLB_TAG TLB_HI
-
-/* Tag portion */
-
-#define TLB_EPN_MASK 0xFFFFFC00 /* Effective Page Number */
-#define TLB_PAGESZ_MASK 0x00000380
-#define TLB_PAGESZ(x) (((x) & 0x7) << 7)
-#define PAGESZ_1K 0
-#define PAGESZ_4K 1
-#define PAGESZ_16K 2
-#define PAGESZ_64K 3
-#define PAGESZ_256K 4
-#define PAGESZ_1M 5
-#define PAGESZ_4M 6
-#define PAGESZ_16M 7
-#define TLB_VALID 0x00000040 /* Entry is valid */
-
-/* Data portion */
-
-#define TLB_RPN_MASK 0xFFFFFC00 /* Real Page Number */
-#define TLB_PERM_MASK 0x00000300
-#define TLB_EX 0x00000200 /* Instruction execution allowed */
-#define TLB_WR 0x00000100 /* Writes permitted */
-#define TLB_ZSEL_MASK 0x000000F0
-#define TLB_ZSEL(x) (((x) & 0xF) << 4)
-#define TLB_ATTR_MASK 0x0000000F
-#define TLB_W 0x00000008 /* Caching is write-through */
-#define TLB_I 0x00000004 /* Caching is inhibited */
-#define TLB_M 0x00000002 /* Memory is coherent */
-#define TLB_G 0x00000001 /* Memory is guarded from prefetch */
-
-#ifndef __ASSEMBLY__
-
-typedef struct {
- unsigned int id;
- unsigned int active;
- void __user *vdso;
-} mm_context_t;
-
-#endif /* !__ASSEMBLY__ */
-
-#define mmu_virtual_psize MMU_PAGE_4K
-#define mmu_linear_psize MMU_PAGE_256M
-
-#endif /* _ASM_POWERPC_MMU_40X_H_ */
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index 141d82e249a8..2986f9ba40b8 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -170,8 +170,9 @@
#define mmu_linear_psize MMU_PAGE_8M
-#define MODULES_VADDR (PAGE_OFFSET - SZ_256M)
#define MODULES_END PAGE_OFFSET
+#define MODULES_SIZE (CONFIG_MODULES_SIZE * SZ_1M)
+#define MODULES_VADDR (MODULES_END - MODULES_SIZE)
#ifndef __ASSEMBLY__
@@ -189,19 +190,14 @@ typedef struct {
#define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)
-/* Page size definitions, common between 32 and 64-bit
+/*
+ * Page size definitions for 8xx
*
* shift : is the "PAGE_SHIFT" value for that page size
- * penc : is the pte encoding mask
*
*/
struct mmu_psize_def {
unsigned int shift; /* number of bits */
- unsigned int enc; /* PTE encoding */
- unsigned int ind; /* Corresponding indirect page size shift */
- unsigned int flags;
-#define MMU_PAGE_SIZE_DIRECT 0x1 /* Supported as a direct size */
-#define MMU_PAGE_SIZE_INDIRECT 0x2 /* Supported as an indirect size */
};
extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 9164a9e41b02..b481738c4bb5 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -52,7 +52,7 @@
#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
#define pgd_ERROR(e) \
- pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+ pr_err("%s:%d: bad pgd %08llx.\n", __FILE__, __LINE__, (unsigned long long)pgd_val(e))
/*
* This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
@@ -118,9 +118,7 @@
* (hardware-defined) PowerPC PTE as closely as possible.
*/
-#if defined(CONFIG_40x)
-#include <asm/nohash/32/pte-40x.h>
-#elif defined(CONFIG_44x)
+#if defined(CONFIG_44x)
#include <asm/nohash/32/pte-44x.h>
#elif defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT)
#include <asm/nohash/pte-e500.h>
@@ -172,7 +170,7 @@ static inline void pmd_clear(pmd_t *pmdp)
#define pmd_pfn(pmd) (pmd_val(pmd) >> PAGE_SHIFT)
#else
#define pmd_page_vaddr(pmd) \
- ((const void *)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
+ ((const void *)((unsigned long)pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
#define pmd_pfn(pmd) (__pa(pmd_val(pmd)) >> PAGE_SHIFT)
#endif
diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h
deleted file mode 100644
index d759cfd74754..000000000000
--- a/arch/powerpc/include/asm/nohash/32/pte-40x.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_NOHASH_32_PTE_40x_H
-#define _ASM_POWERPC_NOHASH_32_PTE_40x_H
-#ifdef __KERNEL__
-
-/*
- * At present, all PowerPC 400-class processors share a similar TLB
- * architecture. The instruction and data sides share a unified,
- * 64-entry, fully-associative TLB which is maintained totally under
- * software control. In addition, the instruction side has a
- * hardware-managed, 4-entry, fully-associative TLB which serves as a
- * first level to the shared TLB. These two TLBs are known as the UTLB
- * and ITLB, respectively (see "mmu.h" for definitions).
- *
- * There are several potential gotchas here. The 40x hardware TLBLO
- * field looks like this:
- *
- * 0 1 2 3 4 ... 18 19 20 21 22 23 24 25 26 27 28 29 30 31
- * RPN..................... 0 0 EX WR ZSEL....... W I M G
- *
- * Where possible we make the Linux PTE bits match up with this
- *
- * - bits 20 and 21 must be cleared, because we use 4k pages (40x can
- * support down to 1k pages), this is done in the TLBMiss exception
- * handler.
- * - We use only zones 0 (for kernel pages) and 1 (for user pages)
- * of the 16 available. Bit 24-26 of the TLB are cleared in the TLB
- * miss handler. Bit 27 is PAGE_USER, thus selecting the correct
- * zone.
- * - PRESENT *must* be in the bottom two bits because swap PTEs
- * use the top 30 bits. Because 40x doesn't support SMP anyway, M is
- * irrelevant so we borrow it for PAGE_PRESENT. Bit 30
- * is cleared in the TLB miss handler before the TLB entry is loaded.
- * - All other bits of the PTE are loaded into TLBLO without
- * modification, leaving us only the bits 20, 21, 24, 25, 26, 30 for
- * software PTE bits. We actually use bits 21, 24, 25, and
- * 30 respectively for the software bits: ACCESSED, DIRTY, RW, and
- * PRESENT.
- */
-
-#define _PAGE_GUARDED 0x001 /* G: page is guarded from prefetch */
-#define _PAGE_PRESENT 0x002 /* software: PTE contains a translation */
-#define _PAGE_NO_CACHE 0x004 /* I: caching is inhibited */
-#define _PAGE_WRITETHRU 0x008 /* W: caching is write-through */
-#define _PAGE_READ 0x010 /* software: read permission */
-#define _PAGE_SPECIAL 0x020 /* software: Special page */
-#define _PAGE_DIRTY 0x080 /* software: dirty page */
-#define _PAGE_WRITE 0x100 /* hardware: WR, anded with dirty in exception */
-#define _PAGE_EXEC 0x200 /* hardware: EX permission */
-#define _PAGE_ACCESSED 0x400 /* software: R: page referenced */
-
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE 0
-
-/* cache related flags non existing on 40x */
-#define _PAGE_COHERENT 0
-
-#define _PMD_PRESENT 0x400 /* PMD points to page of PTEs */
-#define _PMD_PRESENT_MASK _PMD_PRESENT
-#define _PMD_BAD 0x802
-#define _PMD_SIZE_4M 0x0c0
-#define _PMD_SIZE_16M 0x0e0
-#define _PMD_USER 0
-
-#define _PTE_NONE_MASK 0
-
-#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED)
-#define _PAGE_BASE (_PAGE_BASE_NC)
-
-#include <asm/pgtable-masks.h>
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_NOHASH_32_PTE_40x_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h
index 851813725237..da0469928273 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-44x.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h
@@ -75,9 +75,6 @@
#define _PAGE_NO_CACHE 0x00000400 /* H: I bit */
#define _PAGE_WRITETHRU 0x00000800 /* H: W bit */
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE 0
-
/* TODO: Add large page lowmem mapping support */
#define _PMD_PRESENT 0
#define _PMD_PRESENT_MASK (PAGE_MASK)
diff --git a/arch/powerpc/include/asm/nohash/32/pte-85xx.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h
index 653a342d3b25..14d64b4f3f14 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-85xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-85xx.h
@@ -31,9 +31,6 @@
#define _PAGE_WRITETHRU 0x00400 /* H: W bit */
#define _PAGE_SPECIAL 0x00800 /* S: Special page */
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE 0
-
#define _PMD_PRESENT 0
#define _PMD_PRESENT_MASK (PAGE_MASK)
#define _PMD_BAD (~PAGE_MASK)
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 137dc3c84e45..54ebb91dbdcf 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -74,12 +74,11 @@
#define _PTE_NONE_MASK 0
#ifdef CONFIG_PPC_16K_PAGES
-#define _PAGE_PSIZE _PAGE_SPS
+#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_SPS)
#else
-#define _PAGE_PSIZE 0
+#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED)
#endif
-#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
#define _PAGE_BASE (_PAGE_BASE_NC)
#include <asm/pgtable-masks.h>
@@ -120,7 +119,7 @@ static inline pte_t pte_mkhuge(pte_t pte)
#define pte_mkhuge pte_mkhuge
-static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
unsigned long clr, unsigned long set, int huge);
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
@@ -142,19 +141,12 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, pte_t *pt
}
#define __ptep_set_access_flags __ptep_set_access_flags
-static inline unsigned long pgd_leaf_size(pgd_t pgd)
-{
- if (pgd_val(pgd) & _PMD_PAGE_8M)
- return SZ_8M;
- return SZ_4M;
-}
-
-#define pgd_leaf_size pgd_leaf_size
-
-static inline unsigned long pte_leaf_size(pte_t pte)
+static inline unsigned long __pte_leaf_size(pmd_t pmd, pte_t pte)
{
pte_basic_t val = pte_val(pte);
+ if (pmd_val(pmd) & _PMD_PAGE_8M)
+ return SZ_8M;
if (val & _PAGE_HUGE)
return SZ_512K;
if (val & _PAGE_SPS)
@@ -162,31 +154,38 @@ static inline unsigned long pte_leaf_size(pte_t pte)
return SZ_4K;
}
-#define pte_leaf_size pte_leaf_size
+#define __pte_leaf_size __pte_leaf_size
/*
* On the 8xx, the page tables are a bit special. For 16k pages, we have
* 4 identical entries. For 512k pages, we have 128 entries as if it was
* 4k pages, but they are flagged as 512k pages for the hardware.
- * For other page sizes, we have a single entry in the table.
+ * For 8M pages, we have 1024 entries as if it was 4M pages (PMD_SIZE)
+ * but they are flagged as 8M pages for the hardware.
+ * For 4k pages, we have a single entry in the table.
*/
static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr);
-static int hugepd_ok(hugepd_t hpd);
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address);
+
+static inline bool ptep_is_8m_pmdp(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+ return (pmd_t *)ptep == pmd_off(mm, ALIGN_DOWN(addr, SZ_8M));
+}
static inline int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge)
{
if (!huge)
return PAGE_SIZE / SZ_4K;
- else if (hugepd_ok(*((hugepd_t *)pmd)))
- return 1;
+ else if ((pmd_val(*pmd) & _PMD_PAGE_MASK) == _PMD_PAGE_8M)
+ return SZ_4M / SZ_4K;
else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE))
return SZ_16K / SZ_4K;
else
return SZ_512K / SZ_4K;
}
-static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
- unsigned long clr, unsigned long set, int huge)
+static inline pte_basic_t __pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+ unsigned long clr, unsigned long set, int huge)
{
pte_basic_t *entry = (pte_basic_t *)p;
pte_basic_t old = pte_val(*p);
@@ -198,7 +197,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
for (i = 0; i < num; i += PAGE_SIZE / SZ_4K, new += PAGE_SIZE) {
*entry++ = new;
- if (IS_ENABLED(CONFIG_PPC_16K_PAGES) && num != 1) {
+ if (IS_ENABLED(CONFIG_PPC_16K_PAGES)) {
*entry++ = new;
*entry++ = new;
*entry++ = new;
@@ -208,6 +207,21 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
return old;
}
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ unsigned long clr, unsigned long set, int huge)
+{
+ pte_basic_t old;
+
+ if (huge && ptep_is_8m_pmdp(mm, addr, ptep)) {
+ pmd_t *pmdp = (pmd_t *)ptep;
+
+ old = __pte_update(mm, addr, pte_offset_kernel(pmdp, 0), clr, set, huge);
+ __pte_update(mm, addr, pte_offset_kernel(pmdp + 1, 0), clr, set, huge);
+ } else {
+ old = __pte_update(mm, addr, ptep, clr, set, huge);
+ }
+ return old;
+}
#define pte_update pte_update
#ifdef CONFIG_PPC_16K_PAGES
diff --git a/arch/powerpc/include/asm/nohash/hugetlb-e500.h b/arch/powerpc/include/asm/nohash/hugetlb-e500.h
index 8f04ad20e040..cab0e1f1eea0 100644
--- a/arch/powerpc/include/asm/nohash/hugetlb-e500.h
+++ b/arch/powerpc/include/asm/nohash/hugetlb-e500.h
@@ -2,38 +2,8 @@
#ifndef _ASM_POWERPC_NOHASH_HUGETLB_E500_H
#define _ASM_POWERPC_NOHASH_HUGETLB_E500_H
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
- if (WARN_ON(!hugepd_ok(hpd)))
- return NULL;
-
- return (pte_t *)((hpd_val(hpd) & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
- return hpd_val(hpd) & HUGEPD_SHIFT_MASK;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
- unsigned int pdshift)
-{
- /*
- * On FSL BookE, we have multiple higher-level table entries that
- * point to the same hugepte. Just use the first one since they're all
- * identical. So for that case, idx=0.
- */
- return hugepd_page(hpd);
-}
-
void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
- /* We use the old format for PPC_E500 */
- *hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift);
-}
-
static inline int check_and_get_huge_psize(int shift)
{
if (shift & 1) /* Not a power of 4 */
@@ -42,4 +12,13 @@ static inline int check_and_get_huge_psize(int shift)
return shift_to_mmu_psize(shift);
}
+static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
+{
+ unsigned int tsize = shift - _PAGE_PSIZE_SHIFT_OFFSET;
+ pte_basic_t val = (tsize << _PAGE_PSIZE_SHIFT) & _PAGE_PSIZE_MSK;
+
+ return __pte((pte_val(entry) & ~(pte_basic_t)_PAGE_PSIZE_MSK) | val);
+}
+#define arch_make_huge_pte arch_make_huge_pte
+
#endif /* _ASM_POWERPC_NOHASH_HUGETLB_E500_H */
diff --git a/arch/powerpc/include/asm/nohash/mmu-e500.h b/arch/powerpc/include/asm/nohash/mmu-e500.h
index 6ddced0415cb..b281d9eeaf1e 100644
--- a/arch/powerpc/include/asm/nohash/mmu-e500.h
+++ b/arch/powerpc/include/asm/nohash/mmu-e500.h
@@ -244,14 +244,11 @@ typedef struct {
/* Page size definitions, common between 32 and 64-bit
*
* shift : is the "PAGE_SHIFT" value for that page size
- * penc : is the pte encoding mask
*
*/
struct mmu_psize_def
{
unsigned int shift; /* number of bits */
- unsigned int enc; /* PTE encoding */
- unsigned int ind; /* Corresponding indirect page size shift */
unsigned int flags;
#define MMU_PAGE_SIZE_DIRECT 0x1 /* Supported as a direct size */
#define MMU_PAGE_SIZE_INDIRECT 0x2 /* Supported as an indirect size */
@@ -303,8 +300,7 @@ extern unsigned long linear_map_top;
extern int book3e_htw_mode;
#define PPC_HTW_NONE 0
-#define PPC_HTW_IBM 1
-#define PPC_HTW_E6500 2
+#define PPC_HTW_E6500 1
/*
* 64-bit booke platforms don't load the tlb in the tlb miss handler code.
diff --git a/arch/powerpc/include/asm/nohash/mmu.h b/arch/powerpc/include/asm/nohash/mmu.h
index e264be219fdb..4cc795044103 100644
--- a/arch/powerpc/include/asm/nohash/mmu.h
+++ b/arch/powerpc/include/asm/nohash/mmu.h
@@ -2,10 +2,7 @@
#ifndef _ASM_POWERPC_NOHASH_MMU_H_
#define _ASM_POWERPC_NOHASH_MMU_H_
-#if defined(CONFIG_40x)
-/* 40x-style software loaded TLB */
-#include <asm/nohash/32/mmu-40x.h>
-#elif defined(CONFIG_44x)
+#if defined(CONFIG_44x)
/* 44x-style software loaded TLB */
#include <asm/nohash/32/mmu-44x.h>
#elif defined(CONFIG_PPC_E500)
diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h
index 4b62376318e1..bb5f3e8ea912 100644
--- a/arch/powerpc/include/asm/nohash/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/pgalloc.h
@@ -19,8 +19,14 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
- return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+ pgd_t *pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
pgtable_gfp_flags(mm, GFP_KERNEL));
+
+#if defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_BOOK3S_603)
+ memcpy(pgd + USER_PTRS_PER_PGD, swapper_pg_dir + USER_PTRS_PER_PGD,
+ (MAX_PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+#endif
+ return pgd;
}
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -44,8 +50,6 @@ static inline void pgtable_free(void *table, int shift)
}
}
-#define get_hugepd_cache_index(x) (x)
-
static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
{
unsigned long pgf = (unsigned long)table;
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 427db14292c9..8d1f0b7062eb 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -31,6 +31,13 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
extern int icache_44x_need_flush;
+#ifndef pte_huge_size
+static inline unsigned long pte_huge_size(pte_t pte)
+{
+ return PAGE_SIZE;
+}
+#endif
+
/*
* PTE updates. This function is called whenever an existing
* valid PTE is updated. This does -not- include set_pte_at()
@@ -52,11 +59,34 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
{
pte_basic_t old = pte_val(*p);
pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
+ unsigned long sz;
+ unsigned long pdsize;
+ int i;
if (new == old)
return old;
- *p = __pte(new);
+ if (huge)
+ sz = pte_huge_size(__pte(old));
+ else
+ sz = PAGE_SIZE;
+
+ if (sz < PMD_SIZE)
+ pdsize = PAGE_SIZE;
+ else if (sz < PUD_SIZE)
+ pdsize = PMD_SIZE;
+ else if (sz < P4D_SIZE)
+ pdsize = PUD_SIZE;
+ else if (sz < PGDIR_SIZE)
+ pdsize = P4D_SIZE;
+ else
+ pdsize = PGDIR_SIZE;
+
+ for (i = 0; i < sz / pdsize; i++, p++) {
+ *p = __pte(new);
+ if (new)
+ new += (unsigned long long)(pdsize / PAGE_SIZE) << PTE_RPN_SHIFT;
+ }
if (IS_ENABLED(CONFIG_44x) && !is_kernel_addr(addr) && (old & _PAGE_EXEC))
icache_44x_need_flush = 1;
@@ -340,30 +370,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
#define pgprot_writecombine pgprot_noncached_wc
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int hugepd_ok(hugepd_t hpd)
-{
-#ifdef CONFIG_PPC_8xx
- return ((hpd_val(hpd) & _PMD_PAGE_MASK) == _PMD_PAGE_8M);
-#else
- /* We clear the top bit to indicate hugepd */
- return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
-#endif
-}
-
-static inline int pmd_huge(pmd_t pmd)
-{
- return 0;
-}
-
-static inline int pud_huge(pud_t pud)
-{
- return 0;
-}
-
-#define is_hugepd(hpd) (hugepd_ok(hpd))
-#endif
-
int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
void unmap_kernel_page(unsigned long va);
diff --git a/arch/powerpc/include/asm/nohash/pte-e500.h b/arch/powerpc/include/asm/nohash/pte-e500.h
index f516f0b5b7a8..cb78392494da 100644
--- a/arch/powerpc/include/asm/nohash/pte-e500.h
+++ b/arch/powerpc/include/asm/nohash/pte-e500.h
@@ -19,20 +19,7 @@
#define _PAGE_BAP_SX 0x000040
#define _PAGE_BAP_UX 0x000080
#define _PAGE_PSIZE_MSK 0x000f00
-#define _PAGE_PSIZE_4K 0x000200
-#define _PAGE_PSIZE_8K 0x000300
-#define _PAGE_PSIZE_16K 0x000400
-#define _PAGE_PSIZE_32K 0x000500
-#define _PAGE_PSIZE_64K 0x000600
-#define _PAGE_PSIZE_128K 0x000700
-#define _PAGE_PSIZE_256K 0x000800
-#define _PAGE_PSIZE_512K 0x000900
-#define _PAGE_PSIZE_1M 0x000a00
-#define _PAGE_PSIZE_2M 0x000b00
-#define _PAGE_PSIZE_4M 0x000c00
-#define _PAGE_PSIZE_8M 0x000d00
-#define _PAGE_PSIZE_16M 0x000e00
-#define _PAGE_PSIZE_32M 0x000f00
+#define _PAGE_TSIZE_4K 0x000100
#define _PAGE_DIRTY 0x001000 /* C: page changed */
#define _PAGE_SW0 0x002000
#define _PAGE_U3 0x004000
@@ -46,6 +33,9 @@
#define _PAGE_NO_CACHE 0x400000 /* I: cache inhibit */
#define _PAGE_WRITETHRU 0x800000 /* W: cache write-through */
+#define _PAGE_PSIZE_SHIFT 7
+#define _PAGE_PSIZE_SHIFT_OFFSET 10
+
/* "Higher level" linux bit combinations */
#define _PAGE_EXEC (_PAGE_BAP_SX | _PAGE_BAP_UX) /* .. and was cache cleaned */
#define _PAGE_READ (_PAGE_BAP_SR | _PAGE_BAP_UR) /* User read permission */
@@ -65,8 +55,6 @@
#define _PAGE_SPECIAL _PAGE_SW0
-/* Base page size */
-#define _PAGE_PSIZE _PAGE_PSIZE_4K
#define PTE_RPN_SHIFT (24)
#define PTE_WIMGE_SHIFT (19)
@@ -89,7 +77,7 @@
* pages. We always set _PAGE_COHERENT when SMP is enabled or
* the processor might need it for DMA coherency.
*/
-#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
+#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_TSIZE_4K)
#if defined(CONFIG_SMP)
#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT)
#else
@@ -105,6 +93,47 @@ static inline pte_t pte_mkexec(pte_t pte)
}
#define pte_mkexec pte_mkexec
+static inline unsigned long pte_huge_size(pte_t pte)
+{
+ pte_basic_t val = pte_val(pte);
+
+ return 1UL << (((val & _PAGE_PSIZE_MSK) >> _PAGE_PSIZE_SHIFT) + _PAGE_PSIZE_SHIFT_OFFSET);
+}
+#define pte_huge_size pte_huge_size
+
+static inline int pmd_leaf(pmd_t pmd)
+{
+ if (IS_ENABLED(CONFIG_PPC64))
+ return (long)pmd_val(pmd) > 0;
+ else
+ return pmd_val(pmd) & _PAGE_PSIZE_MSK;
+}
+#define pmd_leaf pmd_leaf
+
+static inline unsigned long pmd_leaf_size(pmd_t pmd)
+{
+ return pte_huge_size(__pte(pmd_val(pmd)));
+}
+#define pmd_leaf_size pmd_leaf_size
+
+#ifdef CONFIG_PPC64
+static inline int pud_leaf(pud_t pud)
+{
+ if (IS_ENABLED(CONFIG_PPC64))
+ return (long)pud_val(pud) > 0;
+ else
+ return pud_val(pud) & _PAGE_PSIZE_MSK;
+}
+#define pud_leaf pud_leaf
+
+static inline unsigned long pud_leaf_size(pud_t pud)
+{
+ return pte_huge_size(__pte(pud_val(pud)));
+}
+#define pud_leaf_size pud_leaf_size
+
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index a2bc4b95e703..8c9d4b26bf57 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -1027,10 +1027,10 @@ struct opal_i2c_request {
* The host will pass on OPAL, a buffer of length OPAL_SYSEPOW_MAX
* with individual elements being 16 bits wide to fetch the system
* wide EPOW status. Each element in the buffer will contain the
- * EPOW status in it's bit representation for a particular EPOW sub
+ * EPOW status in its bit representation for a particular EPOW sub
* class as defined here. So multiple detailed EPOW status bits
* specific for any sub class can be represented in a single buffer
- * element as it's bit representation.
+ * element as its bit representation.
*/
/* System EPOW type */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index e667d455ecb4..1d58da946739 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -163,9 +163,7 @@ struct paca_struct {
u64 kstack; /* Saved Kernel stack addr */
u64 saved_r1; /* r1 save for RTAS calls or PM or EE=0 */
u64 saved_msr; /* MSR saved here by enter_rtas */
-#ifdef CONFIG_PPC64
u64 exit_save_r1; /* Syscall/interrupt R1 save */
-#endif
#ifdef CONFIG_PPC_BOOK3E_64
u16 trap_save; /* Used when bad stack is encountered */
#endif
@@ -214,8 +212,6 @@ struct paca_struct {
/* Non-maskable exceptions that are not performance critical */
u64 exnmi[EX_SIZE]; /* used for system reset (nmi) */
u64 exmc[EX_SIZE]; /* used for machine checks */
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
/* Exclusive stacks for system reset and machine check exception. */
void *nmi_emergency_sp;
void *mc_emergency_sp;
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index e5fcc79b5bfb..af9a2628d1df 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -21,8 +21,7 @@
* page size. When using 64K pages however, whether we are really supporting
* 64K pages in HW or not is irrelevant to those definitions.
*/
-#define PAGE_SHIFT CONFIG_PPC_PAGE_SHIFT
-#define PAGE_SIZE (ASM_CONST(1) << PAGE_SHIFT)
+#include <vdso/page.h>
#ifndef __ASSEMBLY__
#ifndef CONFIG_HUGETLB_PAGE
@@ -42,13 +41,6 @@ extern unsigned int hpage_shift;
#endif
/*
- * Subtle: (1 << PAGE_SHIFT) is an int, not an unsigned long. So if we
- * assign PAGE_MASK to a larger type it gets extended the way we want
- * (i.e. with 1s in the high bits)
- */
-#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1))
-
-/*
* KERNELBASE is the virtual address of the start of the kernel, it's often
* the same as PAGE_OFFSET, but _might not be_.
*
@@ -269,38 +261,6 @@ static inline const void *pfn_to_kaddr(unsigned long pfn)
#define is_kernel_addr(x) ((x) >= TASK_SIZE)
#endif
-#ifndef CONFIG_PPC_BOOK3S_64
-/*
- * Use the top bit of the higher-level page table entries to indicate whether
- * the entries we point to contain hugepages. This works because we know that
- * the page tables live in kernel space. If we ever decide to support having
- * page tables at arbitrary addresses, this breaks and will have to change.
- */
-#ifdef CONFIG_PPC64
-#define PD_HUGE 0x8000000000000000UL
-#else
-#define PD_HUGE 0x80000000
-#endif
-
-#else /* CONFIG_PPC_BOOK3S_64 */
-/*
- * Book3S 64 stores real addresses in the hugepd entries to
- * avoid overlaps with _PAGE_PRESENT and _PAGE_PTE.
- */
-#define HUGEPD_ADDR_MASK (0x0ffffffffffffffful & ~HUGEPD_SHIFT_MASK)
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-/*
- * Some number of bits at the level of the page table that points to
- * a hugepte are used to encode the size. This masks those bits.
- * On 8xx, HW assistance requires 4k alignment for the hugepte.
- */
-#ifdef CONFIG_PPC_8xx
-#define HUGEPD_SHIFT_MASK 0xfff
-#else
-#define HUGEPD_SHIFT_MASK 0x3f
-#endif
-
#ifndef __ASSEMBLY__
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h
index 8e5b7d0b851c..ecf5ac70cfae 100644
--- a/arch/powerpc/include/asm/percpu.h
+++ b/arch/powerpc/include/asm/percpu.h
@@ -15,6 +15,16 @@
#endif /* CONFIG_SMP */
#endif /* __powerpc64__ */
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP)
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
+
+#define percpu_first_chunk_is_paged \
+ (static_key_enabled(&__percpu_first_chunk_is_paged.key))
+#else
+#define percpu_first_chunk_is_paged false
+#endif
+
#include <asm-generic/percpu.h>
#include <asm/paca.h>
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index e2221d29fdf9..af0f46e2373b 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -89,7 +89,8 @@ struct power_pmu {
#define PPMU_NO_SIAR 0x00000100 /* Do not use SIAR */
#define PPMU_ARCH_31 0x00000200 /* Has MMCR3, SIER2 and SIER3 */
#define PPMU_P10_DD1 0x00000400 /* Is power10 DD1 processor version */
-#define PPMU_HAS_ATTR_CONFIG1 0x00000800 /* Using config1 attribute */
+#define PPMU_P10 0x00000800 /* For power10 pmu */
+#define PPMU_HAS_ATTR_CONFIG1 0x00001000 /* Using config1 attribute */
/*
* Values for flags to get_alternatives()
@@ -101,8 +102,8 @@ struct power_pmu {
int __init register_power_pmu(struct power_pmu *pmu);
struct pt_regs;
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_arch_misc_flags(struct pt_regs *regs);
+extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
extern unsigned long int read_bhrb(int n);
/*
@@ -110,7 +111,7 @@ extern unsigned long int read_bhrb(int n);
* if we have hardware PMU support.
*/
#ifdef CONFIG_PPC_PERF_CTRS
-#define perf_misc_flags(regs) perf_misc_flags(regs)
+#define perf_arch_misc_flags(regs) perf_arch_misc_flags(regs)
#endif
/*
diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h
index 82633200b500..6bd8f89b25dc 100644
--- a/arch/powerpc/include/asm/pgtable-be-types.h
+++ b/arch/powerpc/include/asm/pgtable-be-types.h
@@ -101,14 +101,4 @@ static inline bool pmd_xchg(pmd_t *pmdp, pmd_t old, pmd_t new)
return pmd_raw(old) == prev;
}
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-typedef struct { __be64 pdbe; } hugepd_t;
-#define __hugepd(x) ((hugepd_t) { cpu_to_be64(x) })
-
-static inline unsigned long hpd_val(hugepd_t x)
-{
- return be64_to_cpu(x.pdbe);
-}
-#endif
-
#endif /* _ASM_POWERPC_PGTABLE_BE_TYPES_H */
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index 082c85cc09b1..f3086e39e7d2 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -49,12 +49,22 @@ static inline unsigned long pud_val(pud_t x)
#endif /* CONFIG_PPC64 */
/* PGD level */
+#if defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT)
+typedef struct { unsigned long long pgd; } pgd_t;
+
+static inline unsigned long long pgd_val(pgd_t x)
+{
+ return x.pgd;
+}
+#else
typedef struct { unsigned long pgd; } pgd_t;
-#define __pgd(x) ((pgd_t) { (x) })
+
static inline unsigned long pgd_val(pgd_t x)
{
return x.pgd;
}
+#endif
+#define __pgd(x) ((pgd_t) { (x) })
/* Page protection bits */
typedef struct { unsigned long pgprot; } pgprot_t;
@@ -83,13 +93,4 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new)
}
#endif
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-typedef struct { unsigned long pd; } hugepd_t;
-#define __hugepd(x) ((hugepd_t) { (x) })
-static inline unsigned long hpd_val(hugepd_t x)
-{
- return x.pd;
-}
-#endif
-
#endif /* _ASM_POWERPC_PGTABLE_TYPES_H */
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 9224f23065ff..2f72ad885332 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -41,6 +41,8 @@ struct mm_struct;
#ifndef __ASSEMBLY__
+#define PFN_PTE_SHIFT PTE_RPN_SHIFT
+
void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
pte_t pte, unsigned int nr);
#define set_ptes set_ptes
@@ -63,6 +65,7 @@ static inline unsigned long pte_pfn(pte_t pte)
/*
* Select all bits except the pfn
*/
+#define pte_pgprot pte_pgprot
static inline pgprot_t pte_pgprot(pte_t pte)
{
unsigned long pte_flags;
@@ -99,15 +102,14 @@ void poking_init(void);
extern unsigned long ioremap_bot;
extern const pgprot_t protection_map[16];
-#ifndef CONFIG_TRANSPARENT_HUGEPAGE
-#define pmd_large(pmd) 0
-#endif
-
/* can we use this in kvm */
unsigned long vmalloc_to_phys(void *vmalloc_addr);
void pgtable_cache_add(unsigned int shift);
+#ifdef CONFIG_PPC32
+void __init *early_alloc_pgtable(unsigned long size);
+#endif
pte_t *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va);
#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32)
@@ -180,30 +182,6 @@ static inline void pte_frag_set(mm_context_t *ctx, void *p)
}
#endif
-#ifndef pmd_is_leaf
-#define pmd_is_leaf pmd_is_leaf
-static inline bool pmd_is_leaf(pmd_t pmd)
-{
- return false;
-}
-#endif
-
-#ifndef pud_is_leaf
-#define pud_is_leaf pud_is_leaf
-static inline bool pud_is_leaf(pud_t pud)
-{
- return false;
-}
-#endif
-
-#ifndef p4d_is_leaf
-#define p4d_is_leaf p4d_is_leaf
-static inline bool p4d_is_leaf(p4d_t p4d)
-{
- return false;
-}
-#endif
-
#define pmd_pgtable pmd_pgtable
static inline pgtable_t pmd_pgtable(pmd_t pmd)
{
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index b3ee44a40c2f..71648c126970 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -18,16 +18,6 @@ static inline long poll_pending(void)
return plpar_hcall_norets(H_POLL_PENDING);
}
-static inline u8 get_cede_latency_hint(void)
-{
- return get_lppaca()->cede_latency_hint;
-}
-
-static inline void set_cede_latency_hint(u8 latency_hint)
-{
- get_lppaca()->cede_latency_hint = latency_hint;
-}
-
static inline long cede_processor(void)
{
/*
@@ -37,24 +27,6 @@ static inline long cede_processor(void)
return plpar_hcall_norets_notrace(H_CEDE);
}
-static inline long extended_cede_processor(unsigned long latency_hint)
-{
- long rc;
- u8 old_latency_hint = get_cede_latency_hint();
-
- set_cede_latency_hint(latency_hint);
-
- rc = cede_processor();
-
- /* Ensure that H_CEDE returns with IRQs on */
- if (WARN_ON(IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && !(mfmsr() & MSR_EE)))
- __hard_irq_enable();
-
- set_cede_latency_hint(old_latency_hint);
-
- return rc;
-}
-
static inline long vpa_call(unsigned long flags, unsigned long cpu,
unsigned long vpa)
{
diff --git a/arch/powerpc/include/asm/plpks.h b/arch/powerpc/include/asm/plpks.h
index 23b77027c916..7a84069759b0 100644
--- a/arch/powerpc/include/asm/plpks.h
+++ b/arch/powerpc/include/asm/plpks.h
@@ -44,9 +44,8 @@
#define PLPKS_MAX_DATA_SIZE 4000
// Timeouts for PLPKS operations
-#define PLPKS_MAX_TIMEOUT 5000 // msec
-#define PLPKS_FLUSH_SLEEP 10 // msec
-#define PLPKS_FLUSH_SLEEP_RANGE 400
+#define PLPKS_MAX_TIMEOUT (5 * USEC_PER_SEC)
+#define PLPKS_FLUSH_SLEEP 10000 // usec
struct plpks_var {
char *component;
diff --git a/arch/powerpc/include/asm/pmac_feature.h b/arch/powerpc/include/asm/pmac_feature.h
index 2495866f2e97..420e2878ae67 100644
--- a/arch/powerpc/include/asm/pmac_feature.h
+++ b/arch/powerpc/include/asm/pmac_feature.h
@@ -192,7 +192,7 @@ static inline long pmac_call_feature(int selector, struct device_node* node,
/* PMAC_FTR_BMAC_ENABLE (struct device_node* node, 0, int value)
* enable/disable the bmac (ethernet) cell of a mac-io ASIC, also drive
- * it's reset line
+ * its reset line
*/
#define PMAC_FTR_BMAC_ENABLE PMAC_FTR_DEF(6)
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 005601243dda..4312bcb913a4 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -471,6 +471,7 @@
#define PPC_RAW_VCMPEQUB_RC(vrt, vra, vrb) \
(0x10000006 | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | __PPC_RC21)
#define PPC_RAW_LD(r, base, i) (0xe8000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_DS(i))
+#define PPC_RAW_LWA(r, base, i) (0xe8000002 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_DS(i))
#define PPC_RAW_LWZ(r, base, i) (0x80000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
#define PPC_RAW_LWZX(t, a, b) (0x7c00002e | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
#define PPC_RAW_STD(r, base, i) (0xf8000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_DS(i))
@@ -510,6 +511,7 @@
#define PPC_RAW_STB(r, base, i) (0x98000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i))
#define PPC_RAW_LBZ(r, base, i) (0x88000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
#define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
+#define PPC_RAW_LHA(r, base, i) (0xa8000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
#define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
#define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
#define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
@@ -532,7 +534,9 @@
#define PPC_RAW_MULW(d, a, b) (0x7c0001d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
#define PPC_RAW_MULHWU(d, a, b) (0x7c000016 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
#define PPC_RAW_MULI(d, a, i) (0x1c000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i))
+#define PPC_RAW_DIVW(d, a, b) (0x7c0003d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
#define PPC_RAW_DIVWU(d, a, b) (0x7c000396 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_DIVD(d, a, b) (0x7c0003d2 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
#define PPC_RAW_DIVDU(d, a, b) (0x7c000392 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
#define PPC_RAW_DIVDE(t, a, b) (0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
#define PPC_RAW_DIVDE_DOT(t, a, b) (0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1)
@@ -550,6 +554,8 @@
#define PPC_RAW_XOR(d, a, b) (0x7c000278 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b))
#define PPC_RAW_XORI(d, a, i) (0x68000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i))
#define PPC_RAW_XORIS(d, a, i) (0x6c000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i))
+#define PPC_RAW_EXTSB(d, a) (0x7c000774 | ___PPC_RA(d) | ___PPC_RS(a))
+#define PPC_RAW_EXTSH(d, a) (0x7c000734 | ___PPC_RA(d) | ___PPC_RS(a))
#define PPC_RAW_EXTSW(d, a) (0x7c0007b4 | ___PPC_RA(d) | ___PPC_RS(a))
#define PPC_RAW_SLW(d, a, s) (0x7c000030 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s))
#define PPC_RAW_SLD(d, a, s) (0x7c000036 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s))
@@ -581,12 +587,26 @@
#define PPC_RAW_MTSPR(spr, d) (0x7c0003a6 | ___PPC_RS(d) | __PPC_SPR(spr))
#define PPC_RAW_EIEIO() (0x7c0006ac)
+/* bcl 20,31,$+4 */
+#define PPC_RAW_BCL4() (0x429f0005)
#define PPC_RAW_BRANCH(offset) (0x48000000 | PPC_LI(offset))
#define PPC_RAW_BL(offset) (0x48000001 | PPC_LI(offset))
#define PPC_RAW_TW(t0, a, b) (0x7c000008 | ___PPC_RS(t0) | ___PPC_RA(a) | ___PPC_RB(b))
#define PPC_RAW_TRAP() PPC_RAW_TW(31, 0, 0)
#define PPC_RAW_SETB(t, bfa) (0x7c000100 | ___PPC_RT(t) | ___PPC_RA((bfa) << 2))
+#ifdef CONFIG_PPC32
+#define PPC_RAW_STL PPC_RAW_STW
+#define PPC_RAW_STLU PPC_RAW_STWU
+#define PPC_RAW_LL PPC_RAW_LWZ
+#define PPC_RAW_CMPLI PPC_RAW_CMPWI
+#else
+#define PPC_RAW_STL PPC_RAW_STD
+#define PPC_RAW_STLU PPC_RAW_STDU
+#define PPC_RAW_LL PPC_RAW_LD
+#define PPC_RAW_CMPLI PPC_RAW_CMPDI
+#endif
+
/* Deal with instructions that older assemblers aren't aware of */
#define PPC_BCCTR_FLUSH stringify_in_c(.long PPC_INST_BCCTR_FLUSH)
#define PPC_CP_ABORT stringify_in_c(.long PPC_RAW_CP_ABORT)
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index e7792aa13510..02897f4b0dbf 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -201,11 +201,13 @@
#ifdef CONFIG_PPC64_ELF_ABI_V2
#define STK_GOT 24
-#define __STK_PARAM(i) (32 + ((i)-3)*8)
+#define STK_PARAM_AREA 32
#else
#define STK_GOT 40
-#define __STK_PARAM(i) (48 + ((i)-3)*8)
+#define STK_PARAM_AREA 48
#endif
+
+#define __STK_PARAM(i) (STK_PARAM_AREA + ((i)-3)*8)
#define STK_PARAM(i) __STK_PARAM(__REG_##i)
#ifdef CONFIG_PPC64_ELF_ABI_V2
@@ -480,7 +482,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96)
* and they must be used.
*/
-#if !defined(CONFIG_4xx) && !defined(CONFIG_PPC_8xx)
+#if !defined(CONFIG_44x) && !defined(CONFIG_PPC_8xx)
#define tlbia \
li r4,1024; \
mtctr r4; \
@@ -506,7 +508,25 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96)
*/
#define DCBT_BOOK3S_STOP_ALL_STREAM_IDS(scratch) \
lis scratch,0x60000000@h; \
- dcbt 0,scratch,0b01010
+ .machine push; \
+ .machine power4; \
+ dcbt 0,scratch,0b01010; \
+ .machine pop;
+
+#define DCBT_SETUP_STREAMS(from, from_parms, to, to_parms, scratch) \
+ lis scratch,0x8000; /* GO=1 */ \
+ clrldi scratch,scratch,32; \
+ .machine push; \
+ .machine power4; \
+ /* setup read stream 0 */ \
+ dcbt 0,from,0b01000; /* addr from */ \
+ dcbt 0,from_parms,0b01010; /* length and depth from */ \
+ /* setup write stream 1 */ \
+ dcbtst 0,to,0b01000; /* addr to */ \
+ dcbtst 0,to_parms,0b01010; /* length and depth to */ \
+ eieio; \
+ dcbt 0,scratch,0b01010; /* all streams GO */ \
+ .machine pop;
/*
* toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index b2c51d337e60..6b94de17201c 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -159,7 +159,7 @@ struct thread_struct {
unsigned long sr0;
#endif
#endif /* CONFIG_PPC32 */
-#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP)
unsigned long pid; /* value written in PID reg. at interrupt exit */
#endif
/* Debug Registers */
@@ -260,7 +260,8 @@ struct thread_struct {
unsigned long sier2;
unsigned long sier3;
unsigned long hashkeyr;
-
+ unsigned long dexcr;
+ unsigned long dexcr_onexec; /* Reset value to load on exec */
#endif
};
@@ -333,6 +334,16 @@ extern int set_endian(struct task_struct *tsk, unsigned int val);
extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr);
extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
+#ifdef CONFIG_PPC_BOOK3S_64
+
+#define PPC_GET_DEXCR_ASPECT(tsk, asp) get_dexcr_prctl((tsk), (asp))
+#define PPC_SET_DEXCR_ASPECT(tsk, asp, val) set_dexcr_prctl((tsk), (asp), (val))
+
+int get_dexcr_prctl(struct task_struct *tsk, unsigned long asp);
+int set_dexcr_prctl(struct task_struct *tsk, unsigned long asp, unsigned long val);
+
+#endif
+
extern void load_fp_state(struct thread_fp_state *fp);
extern void store_fp_state(struct thread_fp_state *fp);
extern void load_vr_state(struct thread_vr_state *vr);
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index d13d8fdc3411..987e23a2bd28 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -390,11 +390,7 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev);
int ps3_system_bus_driver_register(struct ps3_system_bus_driver *drv);
void ps3_system_bus_driver_unregister(struct ps3_system_bus_driver *drv);
-static inline struct ps3_system_bus_driver *ps3_drv_to_system_bus_drv(
- struct device_driver *_drv)
-{
- return container_of(_drv, struct ps3_system_bus_driver, core);
-}
+#define ps3_drv_to_system_bus_drv(_drv) container_of_const(_drv, struct ps3_system_bus_driver, core)
static inline struct ps3_system_bus_device *ps3_dev_to_system_bus_dev(
const struct device *_dev)
{
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index ea8f91fbc62f..7b9350756875 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -310,7 +310,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
static inline bool cpu_has_msr_ri(void)
{
- return !IS_ENABLED(CONFIG_BOOKE_OR_40x);
+ return !IS_ENABLED(CONFIG_BOOKE);
}
static inline bool regs_is_unrecoverable(struct pt_regs *regs)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index bb47af9054a9..0228c90bbcc7 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -18,7 +18,7 @@
#include <asm/feature-fixups.h>
/* Pickup Book E specific registers. */
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
#include <asm/reg_booke.h>
#endif
@@ -233,14 +233,10 @@
/* Special Purpose Registers (SPRNs)*/
-#ifdef CONFIG_40x
-#define SPRN_PID 0x3B1 /* Process ID */
-#else
#define SPRN_PID 0x030 /* Process ID */
#ifdef CONFIG_BOOKE
#define SPRN_PID0 SPRN_PID/* Process ID Register 0 */
#endif
-#endif
#define SPRN_CTR 0x009 /* Count Register */
#define SPRN_DSCR 0x11
@@ -527,7 +523,7 @@
#define SPRN_TSCR 0x399 /* Thread Switch Control Register */
#define SPRN_DEC 0x016 /* Decrement Register */
-#define SPRN_PIT 0x3DB /* Programmable Interval Timer (40x/BOOKE) */
+#define SPRN_PIT 0x3DB /* Programmable Interval Timer (BOOKE) */
#define SPRN_DER 0x095 /* Debug Enable Register */
#define DER_RSTE 0x40000000 /* Reset Interrupt */
@@ -615,7 +611,7 @@
#define HID1_ABE (1<<10) /* 7450 Address Broadcast Enable */
#define HID1_PS (1<<16) /* 750FX PLL selection */
#endif
-#define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */
+#define SPRN_HID2_750FX 0x3F8 /* IBM 750FX HID2 Register */
#define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */
#define SPRN_HID2_G2_LE 0x3F3 /* G2_LE HID2 Register */
#define HID2_G2_LE_HBE (1<<18) /* High BAT Enable (G2_LE) */
@@ -1116,15 +1112,6 @@
* - SPRG2 indicator that we are in RTAS
* - SPRG4 (603 only) pseudo TLB LRU data
*
- * 32-bit 40x:
- * - SPRG0 scratch for exception vectors
- * - SPRG1 scratch for exception vectors
- * - SPRG2 scratch for exception vectors
- * - SPRG4 scratch for exception vectors (not 403)
- * - SPRG5 scratch for exception vectors (not 403)
- * - SPRG6 scratch for exception vectors (not 403)
- * - SPRG7 scratch for exception vectors (not 403)
- *
* 32-bit 440 and FSL BookE:
* - SPRG0 scratch for exception vectors
* - SPRG1 scratch for exception vectors (*)
@@ -1216,16 +1203,6 @@
#define SPRN_SPRG_603_LRU SPRN_SPRG4
#endif
-#ifdef CONFIG_40x
-#define SPRN_SPRG_SCRATCH0 SPRN_SPRG0
-#define SPRN_SPRG_SCRATCH1 SPRN_SPRG1
-#define SPRN_SPRG_SCRATCH2 SPRN_SPRG2
-#define SPRN_SPRG_SCRATCH3 SPRN_SPRG4
-#define SPRN_SPRG_SCRATCH4 SPRN_SPRG5
-#define SPRN_SPRG_SCRATCH5 SPRN_SPRG6
-#define SPRN_SPRG_SCRATCH6 SPRN_SPRG7
-#endif
-
#ifdef CONFIG_BOOKE
#define SPRN_SPRG_RSCRATCH0 SPRN_SPRG0
#define SPRN_SPRG_WSCRATCH0 SPRN_SPRG0
@@ -1366,6 +1343,7 @@
#define PVR_HX_C2000 0x0066
#define PVR_POWER9 0x004E
#define PVR_POWER10 0x0080
+#define PVR_POWER11 0x0082
#define PVR_BE 0x0070
#define PVR_PA6T 0x0090
@@ -1377,6 +1355,7 @@
#define PVR_ARCH_207 0x0f000004
#define PVR_ARCH_300 0x0f000005
#define PVR_ARCH_31 0x0f000006
+#define PVR_ARCH_31_P11 0x0f000007
/* Macros for setting and retrieving special purpose registers */
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index af56980b6cdb..656bfaf91526 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -1,10 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Contains register definitions common to the Book E PowerPC
- * specification. Notice that while the IBM-40x series of CPUs
- * are not true Book E PowerPCs, they borrowed a number of features
- * before Book E was finalized, and are included here as well. Unfortunately,
- * they sometimes used different locations than true Book E CPUs did.
+ * specification.
*
* Copyright 2009-2010 Freescale Semiconductor, Inc.
*/
@@ -42,9 +39,6 @@
#define MSR_KERNEL (MSR_ | MSR_64BIT)
#define MSR_USER32 (MSR_ | MSR_PR | MSR_EE)
#define MSR_USER64 (MSR_USER32 | MSR_64BIT)
-#elif defined (CONFIG_40x)
-#define MSR_KERNEL (MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
-#define MSR_USER (MSR_KERNEL|MSR_PR|MSR_EE)
#else
#define MSR_KERNEL (MSR_ME|MSR_RI|MSR_CE)
#define MSR_USER (MSR_KERNEL|MSR_PR|MSR_EE)
@@ -157,7 +151,6 @@
#define SPRN_TLB3CFG 0x2B3 /* TLB 3 Config Register */
#define SPRN_EPR 0x2BE /* External Proxy Register */
#define SPRN_CCR1 0x378 /* Core Configuration Register 1 */
-#define SPRN_ZPR 0x3B0 /* Zone Protection Register (40x) */
#define SPRN_MAS7 0x3B0 /* MMU Assist Register 7 */
#define SPRN_MMUCR 0x3B2 /* MMU Control Register */
#define SPRN_CCR0 0x3B3 /* Core Configuration Register 0 */
@@ -166,7 +159,6 @@
#define SPRN_SGR 0x3B9 /* Storage Guarded Register */
#define SPRN_DCWR 0x3BA /* Data Cache Write-thru Register */
#define SPRN_SLER 0x3BB /* Little-endian real mode */
-#define SPRN_SU0R 0x3BC /* "User 0" real mode (40x) */
#define SPRN_DCMP 0x3D1 /* Data TLB Compare Register */
#define SPRN_ICDBDR 0x3D3 /* Instruction Cache Debug Data Register */
#define SPRN_EVPR 0x3D6 /* Exception Vector Prefix Register */
@@ -183,10 +175,8 @@
#define SPRN_SVR 0x3FF /* System Version Register */
/*
- * SPRs which have conflicting definitions on true Book E versus classic,
- * or IBM 40x.
+ * SPRs which have conflicting definitions on true Book E versus classic.
*/
-#ifdef CONFIG_BOOKE
#define SPRN_CSRR0 0x03A /* Critical Save and Restore Register 0 */
#define SPRN_CSRR1 0x03B /* Critical Save and Restore Register 1 */
#define SPRN_DEAR 0x03D /* Data Error Address Register */
@@ -201,22 +191,6 @@
#define SPRN_DAC2 0x13D /* Data Address Compare 2 */
#define SPRN_TSR 0x150 /* Timer Status Register */
#define SPRN_TCR 0x154 /* Timer Control Register */
-#endif /* Book E */
-#ifdef CONFIG_40x
-#define SPRN_DBCR1 0x3BD /* Debug Control Register 1 */
-#define SPRN_ESR 0x3D4 /* Exception Syndrome Register */
-#define SPRN_DEAR 0x3D5 /* Data Error Address Register */
-#define SPRN_TSR 0x3D8 /* Timer Status Register */
-#define SPRN_TCR 0x3DA /* Timer Control Register */
-#define SPRN_SRR2 0x3DE /* Save/Restore Register 2 */
-#define SPRN_SRR3 0x3DF /* Save/Restore Register 3 */
-#define SPRN_DBSR 0x3F0 /* Debug Status Register */
-#define SPRN_DBCR0 0x3F2 /* Debug Control Register 0 */
-#define SPRN_DAC1 0x3F6 /* Data Address Compare 1 */
-#define SPRN_DAC2 0x3F7 /* Data Address Compare 2 */
-#define SPRN_CSRR0 SPRN_SRR2 /* Critical Save and Restore Register 0 */
-#define SPRN_CSRR1 SPRN_SRR3 /* Critical Save and Restore Register 1 */
-#endif
#define SPRN_HACOP 0x15F /* Hypervisor Available Coprocessor Register */
/* Bit definitions for CCR1. */
@@ -296,10 +270,6 @@
#endif
/* Bit definitions for the DBSR. */
-/*
- * DBSR bits which have conflicting definitions on true Book E versus IBM 40x.
- */
-#ifdef CONFIG_BOOKE
#define DBSR_IDE 0x80000000 /* Imprecise Debug Event */
#define DBSR_MRR 0x30000000 /* Most Recent Reset */
#define DBSR_IC 0x08000000 /* Instruction Completion */
@@ -319,21 +289,6 @@
#define DBSR_CRET 0x00000020 /* Critical Return Debug Event */
#define DBSR_IAC12ATS 0x00000002 /* Instr Address Compare 1/2 Toggle */
#define DBSR_IAC34ATS 0x00000001 /* Instr Address Compare 3/4 Toggle */
-#endif
-#ifdef CONFIG_40x
-#define DBSR_IC 0x80000000 /* Instruction Completion */
-#define DBSR_BT 0x40000000 /* Branch taken */
-#define DBSR_IRPT 0x20000000 /* Exception Debug Event */
-#define DBSR_TIE 0x10000000 /* Trap Instruction debug Event */
-#define DBSR_IAC1 0x04000000 /* Instruction Address Compare 1 Event */
-#define DBSR_IAC2 0x02000000 /* Instruction Address Compare 2 Event */
-#define DBSR_IAC3 0x00080000 /* Instruction Address Compare 3 Event */
-#define DBSR_IAC4 0x00040000 /* Instruction Address Compare 4 Event */
-#define DBSR_DAC1R 0x01000000 /* Data Address Compare 1 Read Event */
-#define DBSR_DAC1W 0x00800000 /* Data Address Compare 1 Write Event */
-#define DBSR_DAC2R 0x00400000 /* Data Address Compare 2 Read Event */
-#define DBSR_DAC2W 0x00200000 /* Data Address Compare 2 Write Event */
-#endif
/* Bit definitions related to the ESR. */
#define ESR_MCI 0x80000000 /* Machine Check - Instruction */
@@ -355,69 +310,6 @@
#define ESR_SPV 0x00000080 /* Signal Processing operation */
/* Bit definitions related to the DBCR0. */
-#if defined(CONFIG_40x)
-#define DBCR0_EDM 0x80000000 /* External Debug Mode */
-#define DBCR0_IDM 0x40000000 /* Internal Debug Mode */
-#define DBCR0_RST 0x30000000 /* all the bits in the RST field */
-#define DBCR0_RST_SYSTEM 0x30000000 /* System Reset */
-#define DBCR0_RST_CHIP 0x20000000 /* Chip Reset */
-#define DBCR0_RST_CORE 0x10000000 /* Core Reset */
-#define DBCR0_RST_NONE 0x00000000 /* No Reset */
-#define DBCR0_IC 0x08000000 /* Instruction Completion */
-#define DBCR0_ICMP DBCR0_IC
-#define DBCR0_BT 0x04000000 /* Branch Taken */
-#define DBCR0_BRT DBCR0_BT
-#define DBCR0_EDE 0x02000000 /* Exception Debug Event */
-#define DBCR0_IRPT DBCR0_EDE
-#define DBCR0_TDE 0x01000000 /* TRAP Debug Event */
-#define DBCR0_IA1 0x00800000 /* Instr Addr compare 1 enable */
-#define DBCR0_IAC1 DBCR0_IA1
-#define DBCR0_IA2 0x00400000 /* Instr Addr compare 2 enable */
-#define DBCR0_IAC2 DBCR0_IA2
-#define DBCR0_IA12 0x00200000 /* Instr Addr 1-2 range enable */
-#define DBCR0_IA12X 0x00100000 /* Instr Addr 1-2 range eXclusive */
-#define DBCR0_IA3 0x00080000 /* Instr Addr compare 3 enable */
-#define DBCR0_IAC3 DBCR0_IA3
-#define DBCR0_IA4 0x00040000 /* Instr Addr compare 4 enable */
-#define DBCR0_IAC4 DBCR0_IA4
-#define DBCR0_IA34 0x00020000 /* Instr Addr 3-4 range Enable */
-#define DBCR0_IA34X 0x00010000 /* Instr Addr 3-4 range eXclusive */
-#define DBCR0_IA12T 0x00008000 /* Instr Addr 1-2 range Toggle */
-#define DBCR0_IA34T 0x00004000 /* Instr Addr 3-4 range Toggle */
-#define DBCR0_FT 0x00000001 /* Freeze Timers on debug event */
-
-#define dbcr_iac_range(task) ((task)->thread.debug.dbcr0)
-#define DBCR_IAC12I DBCR0_IA12 /* Range Inclusive */
-#define DBCR_IAC12X (DBCR0_IA12 | DBCR0_IA12X) /* Range Exclusive */
-#define DBCR_IAC12MODE (DBCR0_IA12 | DBCR0_IA12X) /* IAC 1-2 Mode Bits */
-#define DBCR_IAC34I DBCR0_IA34 /* Range Inclusive */
-#define DBCR_IAC34X (DBCR0_IA34 | DBCR0_IA34X) /* Range Exclusive */
-#define DBCR_IAC34MODE (DBCR0_IA34 | DBCR0_IA34X) /* IAC 3-4 Mode Bits */
-
-/* Bit definitions related to the DBCR1. */
-#define DBCR1_DAC1R 0x80000000 /* DAC1 Read Debug Event */
-#define DBCR1_DAC2R 0x40000000 /* DAC2 Read Debug Event */
-#define DBCR1_DAC1W 0x20000000 /* DAC1 Write Debug Event */
-#define DBCR1_DAC2W 0x10000000 /* DAC2 Write Debug Event */
-
-#define dbcr_dac(task) ((task)->thread.debug.dbcr1)
-#define DBCR_DAC1R DBCR1_DAC1R
-#define DBCR_DAC1W DBCR1_DAC1W
-#define DBCR_DAC2R DBCR1_DAC2R
-#define DBCR_DAC2W DBCR1_DAC2W
-
-/*
- * Are there any active Debug Events represented in the
- * Debug Control Registers?
- */
-#define DBCR0_ACTIVE_EVENTS (DBCR0_ICMP | DBCR0_IAC1 | DBCR0_IAC2 | \
- DBCR0_IAC3 | DBCR0_IAC4)
-#define DBCR1_ACTIVE_EVENTS (DBCR1_DAC1R | DBCR1_DAC2R | \
- DBCR1_DAC1W | DBCR1_DAC2W)
-#define DBCR_ACTIVE_EVENTS(dbcr0, dbcr1) (((dbcr0) & DBCR0_ACTIVE_EVENTS) || \
- ((dbcr1) & DBCR1_ACTIVE_EVENTS))
-
-#elif defined(CONFIG_BOOKE)
#define DBCR0_EDM 0x80000000 /* External Debug Mode */
#define DBCR0_IDM 0x40000000 /* Internal Debug Mode */
#define DBCR0_RST 0x30000000 /* all the bits in the RST field */
@@ -518,7 +410,6 @@
#define DBCR_ACTIVE_EVENTS(dbcr0, dbcr1) (((dbcr0) & DBCR0_ACTIVE_EVENTS) || \
((dbcr1) & DBCR1_ACTIVE_EVENTS))
-#endif /* #elif defined(CONFIG_BOOKE) */
/* Bit definitions related to the TCR. */
#define TCR_WP(x) (((x)&0x3)<<30) /* WDT Period */
diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h
index a21f529c43d9..9893d2001b68 100644
--- a/arch/powerpc/include/asm/reg_fsl_emb.h
+++ b/arch/powerpc/include/asm/reg_fsl_emb.h
@@ -11,10 +11,27 @@
#ifndef __ASSEMBLY__
/* Performance Monitor Registers */
-#define mfpmr(rn) ({unsigned int rval; \
- asm volatile("mfpmr %0," __stringify(rn) \
- : "=r" (rval)); rval;})
-#define mtpmr(rn, v) asm volatile("mtpmr " __stringify(rn) ",%0" : : "r" (v))
+static __always_inline unsigned int mfpmr(unsigned int rn)
+{
+ unsigned int rval;
+
+ asm (".machine push; "
+ ".machine e300; "
+ "mfpmr %[rval], %[rn];"
+ ".machine pop;"
+ : [rval] "=r" (rval) : [rn] "i" (rn));
+
+ return rval;
+}
+
+static __always_inline void mtpmr(unsigned int rn, unsigned int val)
+{
+ asm (".machine push; "
+ ".machine e300; "
+ "mtpmr %[rn], %[val];"
+ ".machine pop;"
+ : [val] "=r" (val) : [rn] "i" (rn));
+}
#endif /* __ASSEMBLY__ */
/* Freescale Book E Performance Monitor APU Registers */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 065ffd1b2f8a..04406162fc5a 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -397,6 +397,7 @@ inline uint16_t pseries_errorlog_length(struct pseries_errorlog *sect)
#define PSERIES_HP_ELOG_RESOURCE_SLOT 3
#define PSERIES_HP_ELOG_RESOURCE_PHB 4
#define PSERIES_HP_ELOG_RESOURCE_PMEM 6
+#define PSERIES_HP_ELOG_RESOURCE_DT 7
#define PSERIES_HP_ELOG_ACTION_ADD 1
#define PSERIES_HP_ELOG_ACTION_REMOVE 2
diff --git a/arch/powerpc/include/asm/set_memory.h b/arch/powerpc/include/asm/set_memory.h
index 7ebc807aa8cc..9c8d5747755d 100644
--- a/arch/powerpc/include/asm/set_memory.h
+++ b/arch/powerpc/include/asm/set_memory.h
@@ -8,37 +8,44 @@
#define SET_MEMORY_X 3
#define SET_MEMORY_NP 4 /* Set memory non present */
#define SET_MEMORY_P 5 /* Set memory present */
+#define SET_MEMORY_ROX 6
int change_memory_attr(unsigned long addr, int numpages, long action);
-static inline int set_memory_ro(unsigned long addr, int numpages)
+static inline int __must_check set_memory_ro(unsigned long addr, int numpages)
{
return change_memory_attr(addr, numpages, SET_MEMORY_RO);
}
-static inline int set_memory_rw(unsigned long addr, int numpages)
+static inline int __must_check set_memory_rw(unsigned long addr, int numpages)
{
return change_memory_attr(addr, numpages, SET_MEMORY_RW);
}
-static inline int set_memory_nx(unsigned long addr, int numpages)
+static inline int __must_check set_memory_nx(unsigned long addr, int numpages)
{
return change_memory_attr(addr, numpages, SET_MEMORY_NX);
}
-static inline int set_memory_x(unsigned long addr, int numpages)
+static inline int __must_check set_memory_x(unsigned long addr, int numpages)
{
return change_memory_attr(addr, numpages, SET_MEMORY_X);
}
-static inline int set_memory_np(unsigned long addr, int numpages)
+static inline int __must_check set_memory_np(unsigned long addr, int numpages)
{
return change_memory_attr(addr, numpages, SET_MEMORY_NP);
}
-static inline int set_memory_p(unsigned long addr, int numpages)
+static inline int __must_check set_memory_p(unsigned long addr, int numpages)
{
return change_memory_attr(addr, numpages, SET_MEMORY_P);
}
+static inline int __must_check set_memory_rox(unsigned long addr, int numpages)
+{
+ return change_memory_attr(addr, numpages, SET_MEMORY_ROX);
+}
+#define set_memory_rox set_memory_rox
+
#endif
diff --git a/arch/powerpc/include/asm/simple_spinlock_types.h b/arch/powerpc/include/asm/simple_spinlock_types.h
index 08243338069d..391fc19f7272 100644
--- a/arch/powerpc/include/asm/simple_spinlock_types.h
+++ b/arch/powerpc/include/asm/simple_spinlock_types.h
@@ -3,7 +3,7 @@
#define _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H
#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
#endif
typedef struct {
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index aaaa576d0e15..b77927ccb0ab 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -27,6 +27,7 @@
extern int boot_cpuid;
extern int boot_cpu_hwid; /* PPC64 only */
+extern int boot_core_hwid;
extern int spinning_secondaries;
extern u32 *cpu_to_phys_id;
extern bool coregroup_enabled;
diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h
index 40b01446cf75..569765fa16bc 100644
--- a/arch/powerpc/include/asm/spinlock_types.h
+++ b/arch/powerpc/include/asm/spinlock_types.h
@@ -3,7 +3,7 @@
#define _ASM_POWERPC_SPINLOCK_TYPES_H
#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
#endif
#ifdef CONFIG_PPC_QUEUED_SPINLOCKS
diff --git a/arch/powerpc/include/asm/spu_priv1.h b/arch/powerpc/include/asm/spu_priv1.h
index 2167d756e6d5..6fee411d973d 100644
--- a/arch/powerpc/include/asm/spu_priv1.h
+++ b/arch/powerpc/include/asm/spu_priv1.h
@@ -216,7 +216,6 @@ spu_disable_spu (struct spu_context *ctx)
*/
extern const struct spu_priv1_ops spu_priv1_mmio_ops;
-extern const struct spu_priv1_ops spu_priv1_beat_ops;
extern const struct spu_management_ops spu_management_of_ops;
diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index 50950deedb87..e3d0e714ff28 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -173,9 +173,4 @@ int emulate_step(struct pt_regs *regs, ppc_inst_t instr);
*/
extern int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op);
-extern void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
- const void *mem, bool cross_endian);
-extern void emulate_vsx_store(struct instruction_op *op,
- const union vsx_reg *reg, void *mem,
- bool cross_endian);
extern int emulate_dcbz(unsigned long ea, struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index aee25e3ebf96..fc933807ddc8 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -48,6 +48,10 @@ static inline void disable_kernel_fp(void)
#else
static inline void save_fpu(struct task_struct *t) { }
static inline void flush_fp_to_thread(struct task_struct *t) { }
+static inline void enable_kernel_fp(void)
+{
+ BUILD_BUG();
+}
#endif
#ifdef CONFIG_ALTIVEC
diff --git a/arch/powerpc/include/asm/systemcfg.h b/arch/powerpc/include/asm/systemcfg.h
new file mode 100644
index 000000000000..2f9b1d6a5c98
--- /dev/null
+++ b/arch/powerpc/include/asm/systemcfg.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _SYSTEMCFG_H
+#define _SYSTEMCFG_H
+
+/*
+ * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM
+ * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>,
+ * IBM Corp.
+ */
+
+#ifdef CONFIG_PPC64
+
+/*
+ * If the major version changes we are incompatible.
+ * Minor version changes are a hint.
+ */
+#define SYSTEMCFG_MAJOR 1
+#define SYSTEMCFG_MINOR 1
+
+#include <linux/types.h>
+
+struct systemcfg {
+ __u8 eye_catcher[16]; /* Eyecatcher: SYSTEMCFG:PPC64 0x00 */
+ struct { /* Systemcfg version numbers */
+ __u32 major; /* Major number 0x10 */
+ __u32 minor; /* Minor number 0x14 */
+ } version;
+
+ /* Note about the platform flags: it now only contains the lpar
+ * bit. The actual platform number is dead and buried
+ */
+ __u32 platform; /* Platform flags 0x18 */
+ __u32 processor; /* Processor type 0x1C */
+ __u64 processorCount; /* # of physical processors 0x20 */
+ __u64 physicalMemorySize; /* Size of real memory(B) 0x28 */
+ __u64 tb_orig_stamp; /* (NU) Timebase at boot 0x30 */
+ __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
+ __u64 tb_to_xs; /* (NU) Inverse of TB to 2^20 0x40 */
+ __u64 stamp_xsec; /* (NU) 0x48 */
+ __u64 tb_update_count; /* (NU) Timebase atomicity ctr 0x50 */
+ __u32 tz_minuteswest; /* (NU) Min. west of Greenwich 0x58 */
+ __u32 tz_dsttime; /* (NU) Type of dst correction 0x5C */
+ __u32 dcache_size; /* L1 d-cache size 0x60 */
+ __u32 dcache_line_size; /* L1 d-cache line size 0x64 */
+ __u32 icache_size; /* L1 i-cache size 0x68 */
+ __u32 icache_line_size; /* L1 i-cache line size 0x6C */
+};
+
+extern struct systemcfg *systemcfg;
+
+#endif /* CONFIG_PPC64 */
+#endif /* _SYSTEMCFG_H */
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/text-patching.h
index 0e29ccf903d0..e7f14720f630 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/text-patching.h
@@ -76,6 +76,43 @@ int patch_instruction(u32 *addr, ppc_inst_t instr);
int raw_patch_instruction(u32 *addr, ppc_inst_t instr);
int patch_instructions(u32 *addr, u32 *code, size_t len, bool repeat_instr);
+/*
+ * The data patching functions patch_uint() and patch_ulong(), etc., must be
+ * called on aligned addresses.
+ *
+ * The instruction patching functions patch_instruction() and similar must be
+ * called on addresses satisfying instruction alignment requirements.
+ */
+
+#ifdef CONFIG_PPC64
+
+int patch_uint(void *addr, unsigned int val);
+int patch_ulong(void *addr, unsigned long val);
+
+#define patch_u64 patch_ulong
+
+#else
+
+static inline int patch_uint(void *addr, unsigned int val)
+{
+ if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned int)))
+ return -EINVAL;
+
+ return patch_instruction(addr, ppc_inst(val));
+}
+
+static inline int patch_ulong(void *addr, unsigned long val)
+{
+ if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned long)))
+ return -EINVAL;
+
+ return patch_instruction(addr, ppc_inst(val));
+}
+
+#endif
+
+#define patch_u32 patch_uint
+
static inline unsigned long patch_site_addr(s32 *site)
{
return (unsigned long)site + *site;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 15c5691dd218..2785c7462ebf 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -103,6 +103,7 @@ void arch_setup_new_exec(void);
#define TIF_PATCH_PENDING 6 /* pending live patching update */
#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
#define TIF_SINGLESTEP 8 /* singlestepping active */
+#define TIF_NEED_RESCHED_LAZY 9 /* Scheduler driven lazy preemption */
#define TIF_SECCOMP 10 /* secure computing */
#define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */
#define TIF_NOERROR 12 /* Force successful syscall return */
@@ -122,6 +123,7 @@ void arch_setup_new_exec(void);
#define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)
#define _TIF_SIGPENDING (1<<TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY)
#define _TIF_NOTIFY_SIGNAL (1<<TIF_NOTIFY_SIGNAL)
#define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG)
#define _TIF_32BIT (1<<TIF_32BIT)
@@ -142,9 +144,10 @@ void arch_setup_new_exec(void);
_TIF_SYSCALL_EMU)
#define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
- _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \
- _TIF_NOTIFY_SIGNAL)
+ _TIF_NEED_RESCHED_LAZY | _TIF_NOTIFY_RESUME | \
+ _TIF_UPROBE | _TIF_RESTORE_TM | \
+ _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL)
+
#define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR)
/* Bits in local_flags */
@@ -226,6 +229,10 @@ static inline int arch_within_stack_frames(const void * const stack,
return BAD_STACK;
}
+#ifdef CONFIG_PPC32
+extern void *emergency_ctx[];
+#endif
+
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 9f50766c4623..9bdd8080299b 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -58,9 +58,6 @@ static inline u64 get_vtb(void)
*/
static inline u64 get_dec(void)
{
- if (IS_ENABLED(CONFIG_40x))
- return mfspr(SPRN_PIT);
-
return mfspr(SPRN_DEC);
}
@@ -71,9 +68,7 @@ static inline u64 get_dec(void)
*/
static inline void set_dec(u64 val)
{
- if (IS_ENABLED(CONFIG_40x))
- mtspr(SPRN_PIT, (u32)val);
- else if (IS_ENABLED(CONFIG_BOOKE))
+ if (IS_ENABLED(CONFIG_BOOKE))
mtspr(SPRN_DEC, val);
else
mtspr(SPRN_DEC, val - 1);
@@ -91,7 +86,7 @@ static inline unsigned long tb_ticks_since(unsigned long tstamp)
#define mulhdu(x,y) \
({unsigned long z; asm ("mulhdu %0,%1,%2" : "=r" (z) : "r" (x), "r" (y)); z;})
#else
-extern u64 mulhdu(u64, u64);
+#define mulhdu(x, y) mul_u64_u64_shr(x, y, 64)
#endif
extern void div128_by_32(u64 dividend_high, u64 dividend_low,
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index b3de6102a907..2058e8d3e013 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -19,6 +19,8 @@
#include <linux/pagemap.h>
+static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
+ unsigned long address);
#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry
#define tlb_flush tlb_flush
@@ -35,6 +37,7 @@ extern void tlb_flush(struct mmu_gather *tlb);
*/
#define tlb_needs_table_invalidate() radix_enabled()
+#define __HAVE_ARCH_TLB_REMOVE_TABLE
/* Get the generic bits... */
#include <asm-generic/tlb.h>
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index f4e6f2dd04b7..16bacfe8c7a2 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -145,6 +145,7 @@ static inline int cpu_to_coregroup_id(int cpu)
#ifdef CONFIG_HOTPLUG_SMT
#include <linux/cpu_smt.h>
+#include <linux/cpumask.h>
#include <asm/cputhreads.h>
static inline bool topology_is_primary_thread(unsigned int cpu)
@@ -156,6 +157,18 @@ static inline bool topology_smt_thread_allowed(unsigned int cpu)
{
return cpu_thread_in_core(cpu) < cpu_smt_num_threads;
}
+
+#define topology_is_core_online topology_is_core_online
+static inline bool topology_is_core_online(unsigned int cpu)
+{
+ int i, first_cpu = cpu_first_thread_sibling(cpu);
+
+ for (i = first_cpu; i < first_cpu + threads_per_core; ++i) {
+ if (cpu_online(i))
+ return true;
+ }
+ return false;
+}
#endif
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index 82cc2c6704e6..a7b69b25296b 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -137,7 +137,7 @@ TRACE_EVENT(rtas_input,
TP_fast_assign(
__entry->nargs = be32_to_cpu(rtas_args->nargs);
- __assign_str(name, name);
+ __assign_str(name);
be32_to_cpu_array(__get_dynamic_array(inputs), rtas_args->args, __entry->nargs);
),
@@ -162,7 +162,7 @@ TRACE_EVENT(rtas_output,
TP_fast_assign(
__entry->nr_other = be32_to_cpu(rtas_args->nret) - 1;
__entry->status = be32_to_cpu(rtas_args->rets[0]);
- __assign_str(name, name);
+ __assign_str(name);
be32_to_cpu_array(__get_dynamic_array(other_outputs),
&rtas_args->rets[1], __entry->nr_other);
),
@@ -267,6 +267,7 @@ TRACE_EVENT_FN(opal_exit,
);
#endif
+#ifdef CONFIG_PPC_64S_HASH_MMU
TRACE_EVENT(hash_fault,
TP_PROTO(unsigned long addr, unsigned long access, unsigned long trap),
@@ -286,7 +287,7 @@ TRACE_EVENT(hash_fault,
TP_printk("hash fault with addr 0x%lx and access = 0x%lx trap = 0x%lx",
__entry->addr, __entry->access, __entry->trap)
);
-
+#endif
TRACE_EVENT(tlbie,
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index de10437fd206..4f5a46a77fa2 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -6,6 +6,7 @@
#include <asm/page.h>
#include <asm/extable.h>
#include <asm/kup.h>
+#include <asm/asm-compat.h>
#ifdef __powerpc64__
/* We use TASK_SIZE_USER64 as TASK_SIZE is not constant */
@@ -93,8 +94,18 @@ __pu_failed: \
#endif
#ifdef __powerpc64__
+#ifdef CONFIG_PPC_KERNEL_PREFIXED
#define __put_user_asm2_goto(x, ptr, label) \
__put_user_asm_goto(x, ptr, label, "std")
+#else
+#define __put_user_asm2_goto(x, addr, label) \
+ asm goto ("1: std%U1%X1 %0,%1 # put_user\n" \
+ EX_TABLE(1b, %l2) \
+ : \
+ : "r" (x), DS_FORM_CONSTRAINT (*addr) \
+ : \
+ : label)
+#endif // CONFIG_PPC_KERNEL_PREFIXED
#else /* __powerpc64__ */
#define __put_user_asm2_goto(x, addr, label) \
asm goto( \
@@ -165,8 +176,19 @@ do { \
#endif
#ifdef __powerpc64__
+#ifdef CONFIG_PPC_KERNEL_PREFIXED
#define __get_user_asm2_goto(x, addr, label) \
__get_user_asm_goto(x, addr, label, "ld")
+#else
+#define __get_user_asm2_goto(x, addr, label) \
+ asm_goto_output( \
+ "1: ld%U1%X1 %0, %1 # get_user\n" \
+ EX_TABLE(1b, %l2) \
+ : "=r" (x) \
+ : DS_FORM_CONSTRAINT (*addr) \
+ : \
+ : label)
+#endif // CONFIG_PPC_KERNEL_PREFIXED
#else /* __powerpc64__ */
#define __get_user_asm2_goto(x, addr, label) \
asm_goto_output( \
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index b1f094728b35..a8681b12864f 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -38,13 +38,11 @@ void __init udbg_early_init(void);
void __init udbg_init_debug_lpar(void);
void __init udbg_init_debug_lpar_hvsi(void);
void __init udbg_init_pmac_realmode(void);
-void __init udbg_init_maple_realmode(void);
void __init udbg_init_pas_realmode(void);
void __init udbg_init_rtas_panel(void);
void __init udbg_init_rtas_console(void);
void __init udbg_init_btext(void);
void __init udbg_init_44x_as1(void);
-void __init udbg_init_40x_realmode(void);
void __init udbg_init_cpm(void);
void __init udbg_init_usbgecko(void);
void __init udbg_init_memcons(void);
diff --git a/arch/powerpc/include/asm/uninorth.h b/arch/powerpc/include/asm/uninorth.h
index e278299b9b37..6949b5daa37d 100644
--- a/arch/powerpc/include/asm/uninorth.h
+++ b/arch/powerpc/include/asm/uninorth.h
@@ -144,7 +144,7 @@
#define UNI_N_HWINIT_STATE_SLEEPING 0x01
#define UNI_N_HWINIT_STATE_RUNNING 0x02
/* This last bit appear to be used by the bootROM to know the second
- * CPU has started and will enter it's sleep loop with IP=0
+ * CPU has started and will enter its sleep loop with IP=0
*/
#define UNI_N_HWINIT_STATE_CPU1_FLAG 0x10000000
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 659a996c75aa..027ef94a12fb 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -51,7 +51,6 @@
#define __ARCH_WANT_SYS_FORK
#define __ARCH_WANT_SYS_VFORK
#define __ARCH_WANT_SYS_CLONE
-#define __ARCH_WANT_SYS_CLONE3
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 7650b6ce14c8..8d972bc98b55 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -25,6 +25,7 @@ int vdso_getcpu_init(void);
#ifdef __VDSO64__
#define V_FUNCTION_BEGIN(name) \
.globl name; \
+ .type name,@function; \
name: \
#define V_FUNCTION_END(name) \
diff --git a/arch/powerpc/include/asm/vdso/getrandom.h b/arch/powerpc/include/asm/vdso/getrandom.h
new file mode 100644
index 000000000000..80ce0709725e
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/getrandom.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+#ifndef _ASM_POWERPC_VDSO_GETRANDOM_H
+#define _ASM_POWERPC_VDSO_GETRANDOM_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/vdso_datapage.h>
+
+static __always_inline int do_syscall_3(const unsigned long _r0, const unsigned long _r3,
+ const unsigned long _r4, const unsigned long _r5)
+{
+ register long r0 asm("r0") = _r0;
+ register unsigned long r3 asm("r3") = _r3;
+ register unsigned long r4 asm("r4") = _r4;
+ register unsigned long r5 asm("r5") = _r5;
+ register int ret asm ("r3");
+
+ asm volatile(
+ " sc\n"
+ " bns+ 1f\n"
+ " neg %0, %0\n"
+ "1:\n"
+ : "=r" (ret), "+r" (r4), "+r" (r5), "+r" (r0)
+ : "r" (r3)
+ : "memory", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "cr0", "ctr");
+
+ return ret;
+}
+
+/**
+ * getrandom_syscall - Invoke the getrandom() syscall.
+ * @buffer: Destination buffer to fill with random bytes.
+ * @len: Size of @buffer in bytes.
+ * @flags: Zero or more GRND_* flags.
+ * Returns: The number of bytes written to @buffer, or a negative value indicating an error.
+ */
+static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsigned int flags)
+{
+ return do_syscall_3(__NR_getrandom, (unsigned long)buffer,
+ (unsigned long)len, (unsigned long)flags);
+}
+
+static __always_inline struct vdso_rng_data *__arch_get_vdso_rng_data(void)
+{
+ struct vdso_arch_data *data;
+
+ asm (
+ " bcl 20, 31, .+4 ;"
+ "0: mflr %0 ;"
+ " addis %0, %0, (_vdso_datapage - 0b)@ha ;"
+ " addi %0, %0, (_vdso_datapage - 0b)@l ;"
+ : "=r" (data) : : "lr"
+ );
+
+ return &data->rng_data;
+}
+
+ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state,
+ size_t opaque_len);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_VDSO_GETRANDOM_H */
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index f0a4cf01e85c..c6390890a60c 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -4,7 +4,6 @@
#ifndef __ASSEMBLY__
-#include <asm/page.h>
#include <asm/vdso/timebase.h>
#include <asm/barrier.h>
#include <asm/unistd.h>
@@ -14,6 +13,17 @@
#define VDSO_HAS_TIME 1
+/*
+ * powerpc specific delta calculation.
+ *
+ * This variant removes the masking of the subtraction because the
+ * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX
+ * which would result in a pointless operation. The compiler cannot
+ * optimize it away as the mask comes from the vdso data and is not compile
+ * time constant.
+ */
+#define VDSO_DELTA_NOMASK 1
+
static __always_inline int do_syscall_2(const unsigned long _r0, const unsigned long _r3,
const unsigned long _r4)
{
@@ -95,7 +105,7 @@ const struct vdso_data *__arch_get_vdso_data(void);
static __always_inline
const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
{
- return (void *)vd + PAGE_SIZE;
+ return (void *)vd + (1U << CONFIG_PAGE_SHIFT);
}
#endif
@@ -105,21 +115,6 @@ static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
}
#define vdso_clocksource_ok vdso_clocksource_ok
-/*
- * powerpc specific delta calculation.
- *
- * This variant removes the masking of the subtraction because the
- * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX
- * which would result in a pointless operation. The compiler cannot
- * optimize it away as the mask comes from the vdso data and is not compile
- * time constant.
- */
-static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
-{
- return (cycles - last) * mult;
-}
-#define vdso_calc_delta vdso_calc_delta
-
#ifndef __powerpc64__
static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift)
{
diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h
index 48cf23f1e273..48560a119559 100644
--- a/arch/powerpc/include/asm/vdso/vsyscall.h
+++ b/arch/powerpc/include/asm/vdso/vsyscall.h
@@ -4,12 +4,8 @@
#ifndef __ASSEMBLY__
-#include <linux/timekeeper_internal.h>
#include <asm/vdso_datapage.h>
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
static __always_inline
struct vdso_data *__arch_get_k_vdso_data(void)
{
@@ -17,6 +13,12 @@ struct vdso_data *__arch_get_k_vdso_data(void)
}
#define __arch_get_k_vdso_data __arch_get_k_vdso_data
+static __always_inline
+struct vdso_rng_data *__arch_get_k_vdso_rng_data(void)
+{
+ return &vdso_data->rng_data;
+}
+
/* The asm-generic header needs to be included after the definitions above */
#include <asm-generic/vdso/vsyscall.h>
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index a585c8e538ff..a202f5b63479 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -9,29 +9,6 @@
* IBM Corp.
*/
-
-/*
- * Note about this structure:
- *
- * This structure was historically called systemcfg and exposed to
- * userland via /proc/ppc64/systemcfg. Unfortunately, this became an
- * ABI issue as some proprietary software started relying on being able
- * to mmap() it, thus we have to keep the base layout at least for a
- * few kernel versions.
- *
- * However, since ppc32 doesn't suffer from this backward handicap,
- * a simpler version of the data structure is used there with only the
- * fields actually used by the vDSO.
- *
- */
-
-/*
- * If the major version changes we are incompatible.
- * Minor version changes are a hint.
- */
-#define SYSTEMCFG_MAJOR 1
-#define SYSTEMCFG_MINOR 1
-
#ifndef __ASSEMBLY__
#include <linux/unistd.h>
@@ -40,41 +17,10 @@
#define SYSCALL_MAP_SIZE ((NR_syscalls + 31) / 32)
-/*
- * So here is the ppc64 backward compatible version
- */
-
#ifdef CONFIG_PPC64
struct vdso_arch_data {
- __u8 eye_catcher[16]; /* Eyecatcher: SYSTEMCFG:PPC64 0x00 */
- struct { /* Systemcfg version numbers */
- __u32 major; /* Major number 0x10 */
- __u32 minor; /* Minor number 0x14 */
- } version;
-
- /* Note about the platform flags: it now only contains the lpar
- * bit. The actual platform number is dead and buried
- */
- __u32 platform; /* Platform flags 0x18 */
- __u32 processor; /* Processor type 0x1C */
- __u64 processorCount; /* # of physical processors 0x20 */
- __u64 physicalMemorySize; /* Size of real memory(B) 0x28 */
- __u64 tb_orig_stamp; /* (NU) Timebase at boot 0x30 */
- __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
- __u64 tb_to_xs; /* (NU) Inverse of TB to 2^20 0x40 */
- __u64 stamp_xsec; /* (NU) 0x48 */
- __u64 tb_update_count; /* (NU) Timebase atomicity ctr 0x50 */
- __u32 tz_minuteswest; /* (NU) Min. west of Greenwich 0x58 */
- __u32 tz_dsttime; /* (NU) Type of dst correction 0x5C */
- __u32 dcache_size; /* L1 d-cache size 0x60 */
- __u32 dcache_line_size; /* L1 d-cache line size 0x64 */
- __u32 icache_size; /* L1 i-cache size 0x68 */
- __u32 icache_line_size; /* L1 i-cache line size 0x6C */
-
- /* those additional ones don't have to be located anywhere
- * special as they were not part of the original systemcfg
- */
+ __u64 tb_ticks_per_sec; /* Timebase tics / sec */
__u32 dcache_block_size; /* L1 d-cache block size */
__u32 icache_block_size; /* L1 i-cache block size */
__u32 dcache_log_block_size; /* L1 d-cache log block size */
@@ -82,19 +28,20 @@ struct vdso_arch_data {
__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
__u32 compat_syscall_map[SYSCALL_MAP_SIZE]; /* Map of compat syscalls */
- struct vdso_data data[CS_BASES];
+ struct vdso_rng_data rng_data;
+
+ struct vdso_data data[CS_BASES] __aligned(1 << CONFIG_PAGE_SHIFT);
};
#else /* CONFIG_PPC64 */
-/*
- * And here is the simpler 32 bits version
- */
struct vdso_arch_data {
- __u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
+ __u64 tb_ticks_per_sec; /* Timebase tics / sec */
__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
__u32 compat_syscall_map[0]; /* No compat syscalls on PPC32 */
- struct vdso_data data[CS_BASES];
+ struct vdso_rng_data rng_data;
+
+ struct vdso_data data[CS_BASES] __aligned(1 << CONFIG_PAGE_SHIFT);
};
#endif /* CONFIG_PPC64 */
@@ -103,14 +50,17 @@ extern struct vdso_arch_data *vdso_data;
#else /* __ASSEMBLY__ */
-.macro get_datapage ptr
+.macro get_datapage ptr offset=0
bcl 20, 31, .+4
999:
mflr \ptr
- addis \ptr, \ptr, (_vdso_datapage - 999b)@ha
- addi \ptr, \ptr, (_vdso_datapage - 999b)@l
+ addis \ptr, \ptr, (_vdso_datapage - 999b + \offset)@ha
+ addi \ptr, \ptr, (_vdso_datapage - 999b + \offset)@l
.endm
+#include <asm/asm-offsets.h>
+#include <asm/page.h>
+
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/vga.h b/arch/powerpc/include/asm/vga.h
index fcf721682a71..f2dc40e1c52a 100644
--- a/arch/powerpc/include/asm/vga.h
+++ b/arch/powerpc/include/asm/vga.h
@@ -40,11 +40,6 @@ static inline void scr_memsetw(u16 *s, u16 v, unsigned int n)
memset16(s, cpu_to_le16(v), n / 2);
}
-#define VT_BUF_HAVE_MEMCPYW
-#define VT_BUF_HAVE_MEMMOVEW
-#define scr_memcpyw memcpy
-#define scr_memmovew memmove
-
#endif /* !CONFIG_VGA_CONSOLE && !CONFIG_MDA_CONSOLE */
#ifdef __powerpc64__
diff --git a/arch/powerpc/include/asm/fb.h b/arch/powerpc/include/asm/video.h
index c0c5d1df7ad1..e1770114ffc3 100644
--- a/arch/powerpc/include/asm/fb.h
+++ b/arch/powerpc/include/asm/video.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
+#ifndef _ASM_VIDEO_H_
+#define _ASM_VIDEO_H_
#include <asm/page.h>
@@ -12,6 +12,6 @@ static inline pgprot_t pgprot_framebuffer(pgprot_t prot,
}
#define pgprot_framebuffer pgprot_framebuffer
-#include <asm-generic/fb.h>
+#include <asm-generic/video.h>
-#endif /* _ASM_FB_H_ */
+#endif /* _ASM_VIDEO_H_ */
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index cc9b787627ad..7c444150c5ad 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -39,7 +39,7 @@
*/
#define VIO_CMO_MIN_ENT 1562624
-extern struct bus_type vio_bus_type;
+extern const struct bus_type vio_bus_type;
struct iommu_table;
@@ -156,11 +156,7 @@ static inline int vio_enable_interrupts(struct vio_dev *dev)
}
#endif
-static inline struct vio_driver *to_vio_driver(struct device_driver *drv)
-{
- return container_of(drv, struct vio_driver, driver);
-}
-
+#define to_vio_driver(__drv) container_of_const(__drv, struct vio_driver, driver)
#define to_vio_dev(__dev) container_of_const(__dev, struct vio_dev, dev)
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h
index 4c69ece52a31..59ed89890c90 100644
--- a/arch/powerpc/include/asm/vmalloc.h
+++ b/arch/powerpc/include/asm/vmalloc.h
@@ -7,14 +7,14 @@
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
#define arch_vmap_pud_supported arch_vmap_pud_supported
-static inline bool arch_vmap_pud_supported(pgprot_t prot)
+static __always_inline bool arch_vmap_pud_supported(pgprot_t prot)
{
/* HPT does not cope with large pages in the vmalloc area */
return radix_enabled();
}
#define arch_vmap_pmd_supported arch_vmap_pmd_supported
-static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+static __always_inline bool arch_vmap_pmd_supported(pgprot_t prot)
{
return radix_enabled();
}
diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h
index 30a12d208687..54653a863414 100644
--- a/arch/powerpc/include/asm/word-at-a-time.h
+++ b/arch/powerpc/include/asm/word-at-a-time.h
@@ -4,8 +4,8 @@
/*
* Word-at-a-time interfaces for PowerPC.
*/
-
-#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/wordpart.h>
#include <asm/asm-compat.h>
#include <asm/extable.h>
diff --git a/arch/powerpc/include/uapi/asm/bootx.h b/arch/powerpc/include/uapi/asm/bootx.h
index 6728c7e24e58..1b8c121071d9 100644
--- a/arch/powerpc/include/uapi/asm/bootx.h
+++ b/arch/powerpc/include/uapi/asm/bootx.h
@@ -108,7 +108,7 @@ typedef struct boot_infos
/* ALL BELOW NEW (vers. 4) */
/* This defines the physical memory. Valid with BOOT_ARCH_NUBUS flag
- (non-PCI) only. On PCI, memory is contiguous and it's size is in the
+ (non-PCI) only. On PCI, memory is contiguous and its size is in the
device-tree. */
boot_info_map_entry_t
physMemoryMap[MAX_MEM_MAP_SIZE]; /* Where the phys memory is */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 9f18fa090f1f..eaeda001784e 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -28,7 +28,6 @@
#define __KVM_HAVE_PPC_SMT
#define __KVM_HAVE_IRQCHIP
#define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_GUEST_DEBUG
/* Not always available, but if it is, this is the correct offset. */
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -646,6 +645,9 @@ struct kvm_ppc_cpu_char {
#define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
#define KVM_REG_PPC_DAWR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4)
#define KVM_REG_PPC_DAWRX1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5)
+#define KVM_REG_PPC_DEXCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc6)
+#define KVM_REG_PPC_HASHKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc7)
+#define KVM_REG_PPC_HASHPKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc8)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
@@ -733,4 +735,48 @@ struct kvm_ppc_xive_eq {
#define KVM_XIVE_TIMA_PAGE_OFFSET 0
#define KVM_XIVE_ESB_PAGE_OFFSET 4
+/* for KVM_PPC_GET_PVINFO */
+
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
+
+struct kvm_ppc_pvinfo {
+ /* out */
+ __u32 flags;
+ __u32 hcall[4];
+ __u8 pad[108];
+};
+
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ 8
+
+struct kvm_ppc_one_page_size {
+ __u32 page_shift; /* Page shift (or 0) */
+ __u32 pte_enc; /* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+ __u32 page_shift; /* Base page shift of segment (or 0) */
+ __u32 slb_enc; /* SLB encoding for BookS */
+ struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
+#define KVM_PPC_1T_SEGMENTS 0x00000002
+#define KVM_PPC_NO_HASH 0x00000004
+
+struct kvm_ppc_smmu_info {
+ __u64 flags;
+ __u32 slb_size;
+ __u16 data_keys; /* # storage keys supported for data */
+ __u16 instr_keys; /* # storage keys supported for instructions */
+ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
+struct kvm_ppc_resize_hpt {
+ __u64 flags;
+ __u32 shift;
+ __u32 pad;
+};
+
#endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h
deleted file mode 100644
index 17439925045c..000000000000
--- a/arch/powerpc/include/uapi/asm/papr_pdsm.h
+++ /dev/null
@@ -1,165 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * PAPR nvDimm Specific Methods (PDSM) and structs for libndctl
- *
- * (C) Copyright IBM 2020
- *
- * Author: Vaibhav Jain <vaibhav at linux.ibm.com>
- */
-
-#ifndef _UAPI_ASM_POWERPC_PAPR_PDSM_H_
-#define _UAPI_ASM_POWERPC_PAPR_PDSM_H_
-
-#include <linux/types.h>
-#include <linux/ndctl.h>
-
-/*
- * PDSM Envelope:
- *
- * The ioctl ND_CMD_CALL exchange data between user-space and kernel via
- * envelope which consists of 2 headers sections and payload sections as
- * illustrated below:
- * +-----------------+---------------+---------------------------+
- * | 64-Bytes | 8-Bytes | Max 184-Bytes |
- * +-----------------+---------------+---------------------------+
- * | ND-HEADER | PDSM-HEADER | PDSM-PAYLOAD |
- * +-----------------+---------------+---------------------------+
- * | nd_family | | |
- * | nd_size_out | cmd_status | |
- * | nd_size_in | reserved | nd_pdsm_payload |
- * | nd_command | payload --> | |
- * | nd_fw_size | | |
- * | nd_payload ---> | | |
- * +---------------+-----------------+---------------------------+
- *
- * ND Header:
- * This is the generic libnvdimm header described as 'struct nd_cmd_pkg'
- * which is interpreted by libnvdimm before passed on to papr_scm. Important
- * member fields used are:
- * 'nd_family' : (In) NVDIMM_FAMILY_PAPR_SCM
- * 'nd_size_in' : (In) PDSM-HEADER + PDSM-IN-PAYLOAD (usually 0)
- * 'nd_size_out' : (In) PDSM-HEADER + PDSM-RETURN-PAYLOAD
- * 'nd_command' : (In) One of PAPR_PDSM_XXX
- * 'nd_fw_size' : (Out) PDSM-HEADER + size of actual payload returned
- *
- * PDSM Header:
- * This is papr-scm specific header that precedes the payload. This is defined
- * as nd_cmd_pdsm_pkg. Following fields aare available in this header:
- *
- * 'cmd_status' : (Out) Errors if any encountered while servicing PDSM.
- * 'reserved' : Not used, reserved for future and should be set to 0.
- * 'payload' : A union of all the possible payload structs
- *
- * PDSM Payload:
- *
- * The layout of the PDSM Payload is defined by various structs shared between
- * papr_scm and libndctl so that contents of payload can be interpreted. As such
- * its defined as a union of all possible payload structs as
- * 'union nd_pdsm_payload'. Based on the value of 'nd_cmd_pkg.nd_command'
- * appropriate member of the union is accessed.
- */
-
-/* Max payload size that we can handle */
-#define ND_PDSM_PAYLOAD_MAX_SIZE 184
-
-/* Max payload size that we can handle */
-#define ND_PDSM_HDR_SIZE \
- (sizeof(struct nd_pkg_pdsm) - ND_PDSM_PAYLOAD_MAX_SIZE)
-
-/* Various nvdimm health indicators */
-#define PAPR_PDSM_DIMM_HEALTHY 0
-#define PAPR_PDSM_DIMM_UNHEALTHY 1
-#define PAPR_PDSM_DIMM_CRITICAL 2
-#define PAPR_PDSM_DIMM_FATAL 3
-
-/* struct nd_papr_pdsm_health.extension_flags field flags */
-
-/* Indicate that the 'dimm_fuel_gauge' field is valid */
-#define PDSM_DIMM_HEALTH_RUN_GAUGE_VALID 1
-
-/* Indicate that the 'dimm_dsc' field is valid */
-#define PDSM_DIMM_DSC_VALID 2
-
-/*
- * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH
- * Various flags indicate the health status of the dimm.
- *
- * extension_flags : Any extension fields present in the struct.
- * dimm_unarmed : Dimm not armed. So contents wont persist.
- * dimm_bad_shutdown : Previous shutdown did not persist contents.
- * dimm_bad_restore : Contents from previous shutdown werent restored.
- * dimm_scrubbed : Contents of the dimm have been scrubbed.
- * dimm_locked : Contents of the dimm cant be modified until CEC reboot
- * dimm_encrypted : Contents of dimm are encrypted.
- * dimm_health : Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX
- * dimm_fuel_gauge : Life remaining of DIMM as a percentage from 0-100
- */
-struct nd_papr_pdsm_health {
- union {
- struct {
- __u32 extension_flags;
- __u8 dimm_unarmed;
- __u8 dimm_bad_shutdown;
- __u8 dimm_bad_restore;
- __u8 dimm_scrubbed;
- __u8 dimm_locked;
- __u8 dimm_encrypted;
- __u16 dimm_health;
-
- /* Extension flag PDSM_DIMM_HEALTH_RUN_GAUGE_VALID */
- __u16 dimm_fuel_gauge;
-
- /* Extension flag PDSM_DIMM_DSC_VALID */
- __u64 dimm_dsc;
- };
- __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
- };
-};
-
-/* Flags for injecting specific smart errors */
-#define PDSM_SMART_INJECT_HEALTH_FATAL (1 << 0)
-#define PDSM_SMART_INJECT_BAD_SHUTDOWN (1 << 1)
-
-struct nd_papr_pdsm_smart_inject {
- union {
- struct {
- /* One or more of PDSM_SMART_INJECT_ */
- __u32 flags;
- __u8 fatal_enable;
- __u8 unsafe_shutdown_enable;
- };
- __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
- };
-};
-
-/*
- * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel
- * via 'nd_cmd_pkg.nd_command' member of the ioctl struct
- */
-enum papr_pdsm {
- PAPR_PDSM_MIN = 0x0,
- PAPR_PDSM_HEALTH,
- PAPR_PDSM_SMART_INJECT,
- PAPR_PDSM_MAX,
-};
-
-/* Maximal union that can hold all possible payload types */
-union nd_pdsm_payload {
- struct nd_papr_pdsm_health health;
- struct nd_papr_pdsm_smart_inject smart_inject;
- __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
-} __packed;
-
-/*
- * PDSM-header + payload expected with ND_CMD_CALL ioctl from libnvdimm
- * Valid member of union 'payload' is identified via 'nd_cmd_pkg.nd_command'
- * that should always precede this struct when sent to papr_scm via CMD_CALL
- * interface.
- */
-struct nd_pkg_pdsm {
- __s32 cmd_status; /* Out: Sub-cmd status returned back */
- __u16 reserved[2]; /* Ignored and to be set as '0' */
- union nd_pdsm_payload payload;
-} __packed;
-
-#endif /* _UAPI_ASM_POWERPC_PAPR_PDSM_H_ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 2919433be355..f43c1198768c 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 += $(NO_MINIMAL_TOC)
-endif
ifdef CONFIG_PPC32
CFLAGS_prom_init.o += -fPIC
CFLAGS_btext.o += -fPIC
@@ -55,7 +52,6 @@ CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
endif
KCSAN_SANITIZE_early_32.o := n
-KCSAN_SANITIZE_early_64.o := n
KCSAN_SANITIZE_cputable.o := n
KCSAN_SANITIZE_btext.o := n
KCSAN_SANITIZE_paca.o := n
@@ -88,6 +84,7 @@ obj-$(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_64e.o
obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
@@ -126,7 +123,6 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o
obj-$(CONFIG_PPC64) += head_64.o
obj-$(CONFIG_PPC_BOOK3S_32) += head_book3s_32.o
-obj-$(CONFIG_40x) += head_40x.o
obj-$(CONFIG_44x) += head_44x.o
obj-$(CONFIG_PPC_8xx) += head_8xx.o
obj-$(CONFIG_PPC_85xx) += head_85xx.o
@@ -143,6 +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
@@ -191,9 +188,6 @@ 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
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 9f14d95b8b32..7a390bd4f4af 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -54,7 +54,7 @@
#endif
#ifdef CONFIG_PPC32
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
#include "head_booke.h"
#endif
#endif
@@ -246,9 +246,7 @@ 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_64
OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save);
#endif
@@ -596,7 +594,6 @@ 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);
@@ -676,5 +673,16 @@ 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/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/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index bfd3f442e5eb..ab3ca74e6730 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -401,7 +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
@@ -496,7 +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)
diff --git a/arch/powerpc/kernel/cpu_specs.h b/arch/powerpc/kernel/cpu_specs.h
index 85ded3f77204..5ea14605bb41 100644
--- a/arch/powerpc/kernel/cpu_specs.h
+++ b/arch/powerpc/kernel/cpu_specs.h
@@ -1,9 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifdef CONFIG_40x
-#include "cpu_specs_40x.h"
-#endif
-
#ifdef CONFIG_PPC_47x
#include "cpu_specs_47x.h"
#elif defined(CONFIG_44x)
diff --git a/arch/powerpc/kernel/cpu_specs_40x.h b/arch/powerpc/kernel/cpu_specs_40x.h
deleted file mode 100644
index a1362a75b8c8..000000000000
--- a/arch/powerpc/kernel/cpu_specs_40x.h
+++ /dev/null
@@ -1,280 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
- */
-
-static struct cpu_spec cpu_specs[] __initdata = {
- { /* 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",
- }
-};
diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h
index 3ff9757df4c0..98d4274a1b6b 100644
--- a/arch/powerpc/kernel/cpu_specs_book3s_64.h
+++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h
@@ -60,6 +60,9 @@
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,
@@ -281,6 +284,20 @@ static struct cpu_spec cpu_specs[] __initdata = {
.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,
@@ -451,6 +468,23 @@ static struct cpu_spec cpu_specs[] __initdata = {
.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,
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 2086fa6cdc25..103b6605dd68 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -13,7 +13,7 @@
#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>
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 8920862ffd79..f0ae39e77e37 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -216,6 +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/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index c3fb9fdf5bd7..3af6c06af02f 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -458,6 +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
@@ -648,8 +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},
@@ -857,7 +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))
@@ -1077,12 +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);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index ab316e155ea9..83fe99861eb1 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;
@@ -1264,22 +1273,6 @@ 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
@@ -1544,10 +1537,6 @@ 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 +1574,104 @@ 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 +1776,6 @@ 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 +1819,10 @@ 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 +1834,7 @@ 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 +1845,6 @@ 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 +1891,6 @@ 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 48773d2d9be3..7efe04c68f0f 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -865,9 +865,18 @@ 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 */
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index e0ce81279624..d283d281d28e 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.
*/
@@ -849,6 +849,7 @@ 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;
@@ -859,9 +860,11 @@ 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 7eda33a24bb4..f4a8c9877249 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -108,7 +108,7 @@ transfer_to_syscall:
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 */
@@ -158,9 +158,6 @@ syscall_exit_finish:
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)
@@ -214,7 +211,7 @@ start_kernel_thread:
.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
@@ -237,9 +234,6 @@ fast_exception_return:
REST_GPR(12, 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 */
@@ -296,9 +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)
@@ -346,9 +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
@@ -375,12 +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
@@ -395,17 +380,6 @@ _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); \
@@ -423,7 +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; \
@@ -471,20 +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);
@@ -509,4 +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 1a9b5ae8ccb2..6a414ed5a411 100644
--- a/arch/powerpc/kernel/epapr_hcalls.S
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -21,7 +21,7 @@ _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_OR_40x
+#ifdef CONFIG_BOOKE
wrteei 1
#else
mfmsr r4
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 dcf0591ad3c2..63f6b9f513a4 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -485,8 +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)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index eaf2f167c342..195b075d116c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1989,13 +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
@@ -2015,16 +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)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index d14eda1e8589..4b371c738213 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -53,8 +53,6 @@ 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 +78,38 @@ 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 +120,7 @@ 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 +132,50 @@ 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 +266,6 @@ 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.
*/
@@ -373,12 +394,6 @@ 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 +404,11 @@ 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 +568,6 @@ 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 +582,6 @@ 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
@@ -647,8 +640,6 @@ 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;
@@ -705,7 +696,7 @@ 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();
@@ -931,36 +922,6 @@ 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;
@@ -998,52 +959,6 @@ 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.
@@ -1073,36 +988,50 @@ 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 */
@@ -1112,55 +1041,66 @@ 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)
@@ -1175,14 +1115,25 @@ 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;
}
@@ -1190,8 +1141,6 @@ 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-
@@ -1200,18 +1149,10 @@ 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");
@@ -1230,7 +1171,6 @@ 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)
@@ -1416,6 +1356,22 @@ static void fadump_release_memory(u64 begin, u64 end)
fadump_release_reserved_area(tstart, end);
}
+static void fadump_free_elfcorehdr_buf(void)
+{
+ if (fw_dump.elfcorehdr_addr == 0 || fw_dump.elfcorehdr_size == 0)
+ return;
+
+ /*
+ * 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)
{
mutex_lock(&fadump_mutex);
@@ -1427,6 +1383,7 @@ static void fadump_invalidate_release_mem(void)
fadump_cleanup();
mutex_unlock(&fadump_mutex);
+ fadump_free_elfcorehdr_buf();
fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM());
fadump_free_cpu_notes_buf();
@@ -1484,6 +1441,18 @@ 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)
@@ -1498,6 +1467,43 @@ 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)
@@ -1556,11 +1562,14 @@ 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,
};
@@ -1578,6 +1587,12 @@ 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);
@@ -1632,6 +1647,150 @@ 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 {
+ /*
+ * Passing additional parameters is supported for hash MMU only
+ * if the first memory block size is 768MB or higher.
+ */
+ if (ppc64_rma_size < 0x30000000)
+ return;
+
+ /*
+ * 640 MB to 768 MB is not used by PFW/bootloader. So, try reserving
+ * memory for passing additional parameters in this range to avoid
+ * being stomped on by PFW/bootloader.
+ */
+ range_start = 0x2A000000;
+ range_end = range_start + 0x4000000;
+ }
+
+ 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.
*/
@@ -1651,12 +1810,7 @@ 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) {
@@ -1735,8 +1889,3 @@ 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/head_32.h b/arch/powerpc/kernel/head_32.h
index f8e2911478a7..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 */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
deleted file mode 100644
index 9fc90410b385..000000000000
--- a/arch/powerpc/kernel/head_40x.S
+++ /dev/null
@@ -1,721 +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 <linux/linkage.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 "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 | _PAGE_READ
- andc. r9, r9, r11 /* Check permission */
- bne 5f
-
- rlwinm r9, r11, 1, _PAGE_WRITE /* dirty => w */
- and r9, r9, r11 /* hwwrite = dirty & w */
- rlwimi r11, r9, 0, _PAGE_WRITE /* replace w 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_WRITE /* dirty => w */
- and r9, r9, r11 /* hwwrite = dirty & w */
- rlwimi r11, r9, 0, _PAGE_WRITE /* replace w 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
- * 4 bits of the zone field, and M.
- */
- li r9, 0x0cf2
- andc r11, r11, r9
- rlwimi r11, r10, 8, 24, 27 /* Copy 4 upper address bit into zone */
-
- /* 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_MIN_SIZE(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.
- */
-SYM_FUNC_START_LOCAL(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
-SYM_FUNC_END(initial_mmu)
-
-_GLOBAL(abort)
- mfspr r13,SPRN_DBCR0
- oris r13,r13,DBCR0_RST_SYSTEM@h
- mtspr SPRN_DBCR0,r13
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 4690c219bfa4..63432a33ec49 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -647,8 +647,9 @@ __after_prom_start:
* Note: This process overwrites the OF exception vectors.
*/
LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET)
- mr. r4,r26 /* In some cases the loader may */
- beq 9f /* have already put us at zero */
+ 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. */
diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S
index 39724ff5ae1f..f9a73fae6464 100644
--- a/arch/powerpc/kernel/head_85xx.S
+++ b/arch/powerpc/kernel/head_85xx.S
@@ -294,9 +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):
@@ -307,34 +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
@@ -441,13 +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
@@ -470,29 +471,14 @@ END_BTB_FLUSH_SECTION
#endif
4:
- /* Mask of required permission bits. Note that while we
- * 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
- * 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|_PAGE_BAP_SR
oris r13,r13,_PAGE_ACCESSED@h
#else
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
@@ -549,13 +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
@@ -564,6 +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
@@ -584,6 +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
@@ -593,7 +581,6 @@ END_BTB_FLUSH_SECTION
#endif
4:
- FIND_PTE
andc. r13,r13,r11 /* Check permission */
#ifdef CONFIG_PTE_64BIT
@@ -746,17 +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 */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 647b0b445e89..56c5ebe21b99 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -40,16 +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
@@ -199,18 +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
@@ -248,19 +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
@@ -332,15 +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
@@ -394,6 +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.
@@ -404,7 +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
@@ -415,14 +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 */
@@ -441,11 +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
@@ -500,6 +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)
@@ -593,6 +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
@@ -689,6 +688,7 @@ SYM_FUNC_START_LOCAL(initial_mmu)
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
@@ -710,6 +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)
@@ -730,6 +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
@@ -789,3 +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 c1d89764dd22..cb2bca76be53 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -411,39 +411,26 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE)
*/
. = INTERRUPT_INST_TLB_MISS_603
InstructionTLBMiss:
-/*
- * r0: userspace flag (later scratch)
- * r1: linux style pte ( later becomes ppc hardware pte )
- * r2: ptr to linux-style pte
- * r3: fault address
- */
/* Get PTE (linux-style) and check access */
- mfspr r3,SPRN_IMISS
-#ifdef CONFIG_MODULES
- 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
rlwinm r2, r2, 28, 0xfffff000
-#ifdef CONFIG_MODULES
- li r0, 3
- bgt- 112f
- lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
- li r0, 0
- 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 */
+ 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 */
+ 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 */
-#ifdef CONFIG_MODULES
- rlwimi r2, r0, 0, 31, 31 /* userspace ? -> 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, r2, r1 /* PP = user? 1 : 0 */
@@ -451,7 +438,7 @@ 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
@@ -480,35 +467,24 @@ InstructionAddressInvalid:
*/
. = INTERRUPT_DATA_LOAD_TLB_MISS_603
DataLoadTLBMiss:
-/*
- * r0: userspace flag (later scratch)
- * r1: linux style pte ( later becomes ppc hardware pte )
- * r2: ptr to linux-style pte
- * r3: fault address
- */
/* 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_READ
- rlwinm r2, r2, 28, 0xfffff000
- li r0, 3
- bgt- 112f
- lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
- li r0, 0
- 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 */
+ 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,r2,32-9,30,30 /* _PAGE_WRITE -> PP msb */
- rlwimi r2,r0,0,30,31 /* userspace ? -> PP */
+ 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 */
@@ -518,25 +494,35 @@ BEGIN_FTR_SECTION
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 */
@@ -560,34 +546,24 @@ DataAddressInvalid:
*/
. = INTERRUPT_DATA_STORE_TLB_MISS_603
DataStoreTLBMiss:
-/*
- * r0: userspace flag (later scratch)
- * r1: linux style pte ( later becomes ppc hardware pte )
- * r2: ptr to linux-style pte
- * r3: fault address
- */
/* 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
- rlwinm r2, r2, 28, 0xfffff000
- li r0, 3
- bgt- 112f
- lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
- li r0, 0
- 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 */
+ 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 r2,r0,0,31,31 /* userspace ? -> PP lsb */
+ rlwimi r2,r3,1,31,31 /* userspace ? -> PP lsb */
li r1,0xe06 /* clear out reserved bits & PP msb */
andc r1,r2,r1 /* PP = user? 1: 0 */
BEGIN_FTR_SECTION
@@ -597,26 +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
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index b6b5b01a173c..0b5c1993809e 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -145,10 +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
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 30b56c67fa61..e527cd3ef128 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -97,7 +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,
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index eca293794a1e..8f4acc55407b 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -185,7 +185,7 @@ 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 {
/*
@@ -266,7 +266,7 @@ 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();
@@ -344,7 +344,7 @@ 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.
@@ -386,7 +386,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
TRAP(regs) != INTERRUPT_PROGRAM &&
TRAP(regs) != INTERRUPT_PERFMON)
- CT_WARN_ON(ct_state() == CONTEXT_USER);
+ CT_WARN_ON(ct_state() == CT_STATE_USER);
kuap = kuap_get_and_assert_locked();
@@ -396,7 +396,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_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 (IS_ENABLED(CONFIG_PREEMPTION)) {
/* Return to preemptible kernel context */
if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) {
if (preempt_count() == 0)
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 1185efebf032..0ebae6e4c19d 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -26,6 +26,7 @@
#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>
@@ -642,7 +643,7 @@ 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
@@ -683,10 +684,10 @@ 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);
/*
@@ -987,6 +988,23 @@ 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
*/
@@ -1101,59 +1119,6 @@ void iommu_tce_kill(struct iommu_table *tbl,
}
EXPORT_SYMBOL_GPL(iommu_tce_kill);
-#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
-static 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;
-}
-
-static 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);
-}
-#endif
-
int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
{
/*
@@ -1186,98 +1151,6 @@ EXPORT_SYMBOL_GPL(iommu_add_device);
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
/*
- * A simple iommu_table_group_ops which only allows reusing the existing
- * iommu_table. This handles VFIO for POWER7 or the nested KVM.
- * The ops does not allow creating windows and only allows reusing the existing
- * one if it matches table_group->tce32_start/tce32_size/page_shift.
- */
-static unsigned long spapr_tce_get_table_size(__u32 page_shift,
- __u64 window_size, __u32 levels)
-{
- unsigned long size;
-
- if (levels > 1)
- return ~0U;
- size = window_size >> (page_shift - 3);
- return size;
-}
-
-static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
- __u32 page_shift, __u64 window_size, __u32 levels,
- struct iommu_table **ptbl)
-{
- struct iommu_table *tbl = table_group->tables[0];
-
- if (num > 0)
- return -EPERM;
-
- if (tbl->it_page_shift != page_shift ||
- tbl->it_size != (window_size >> page_shift) ||
- tbl->it_indirect_levels != levels - 1)
- return -EINVAL;
-
- *ptbl = iommu_tce_table_get(tbl);
- return 0;
-}
-
-static long spapr_tce_set_window(struct iommu_table_group *table_group,
- int num, struct iommu_table *tbl)
-{
- return tbl == table_group->tables[num] ? 0 : -EPERM;
-}
-
-static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
-{
- return 0;
-}
-
-static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
-{
- int i, j, rc = 0;
-
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- struct iommu_table *tbl = table_group->tables[i];
-
- if (!tbl || !tbl->it_map)
- continue;
-
- rc = iommu_take_ownership(tbl);
- if (!rc)
- continue;
-
- for (j = 0; j < i; ++j)
- iommu_release_ownership(table_group->tables[j]);
- return rc;
- }
- return 0;
-}
-
-static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
-{
- int i;
-
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- struct iommu_table *tbl = table_group->tables[i];
-
- if (!tbl)
- continue;
-
- iommu_table_clear(tbl);
- if (tbl->it_map)
- iommu_release_ownership(tbl);
- }
-}
-
-struct iommu_table_group_ops spapr_tce_table_group_ops = {
- .get_table_size = spapr_tce_get_table_size,
- .create_table = spapr_tce_create_table,
- .set_window = spapr_tce_set_window,
- .unset_window = spapr_tce_unset_window,
- .take_ownership = spapr_tce_take_ownership,
- .release_ownership = spapr_tce_release_ownership,
-};
-
-/*
* A simple iommu_ops to allow less cruft in generic VFIO code.
*/
static int
@@ -1285,21 +1158,20 @@ 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_group *grp = iommu_group_get(dev);
struct iommu_table_group *table_group;
+ struct iommu_group *grp;
/* At first attach the ownership is already set */
- if (!domain) {
- iommu_group_put(grp);
+ if (!domain)
return 0;
- }
+ grp = iommu_group_get(dev);
table_group = iommu_group_get_iommudata(grp);
/*
* The domain being set to PLATFORM from earlier
* BLOCKED. The table_group ownership has to be released.
*/
- table_group->ops->release_ownership(table_group);
+ table_group->ops->release_ownership(table_group, dev);
iommu_group_put(grp);
return 0;
@@ -1327,7 +1199,7 @@ spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
* also sets the dma_api ops
*/
table_group = iommu_group_get_iommudata(grp);
- ret = table_group->ops->take_ownership(table_group);
+ ret = table_group->ops->take_ownership(table_group, dev);
iommu_group_put(grp);
return ret;
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 6f7d4edaa0bc..a0e8b998c9b5 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -89,69 +89,69 @@ int arch_show_interrupts(struct seq_file *p, int prec)
#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
@@ -284,15 +284,14 @@ static __always_inline void call_do_irq(struct pt_regs *regs, void *sp)
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()];
/* Already there ? If not switch stack and call */
- if (unlikely(cursp == irqsp || cursp == sirqsp))
+ if (unlikely(cursp == irqsp))
__do_irq(regs, current_stack_pointer);
else
call_do_irq(regs, irqsp);
@@ -334,7 +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;
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 48e0eaf1ad61..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,
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 ebe4d1645ca1..5081334b7bd2 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -21,7 +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>
@@ -45,7 +45,7 @@ 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_PPC_85xx)
{ 0x2010, 0x08 /* SIGFPE */ }, /* spe unavailable */
@@ -64,7 +64,7 @@ static struct hard_trap_info
{ 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 */
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 b20ee72e873a..c0d9f12cb441 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -19,9 +19,9 @@
#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
-#include <linux/moduleloader.h>
#include <linux/set_memory.h>
-#include <asm/code-patching.h>
+#include <linux/execmem.h>
+#include <asm/text-patching.h>
#include <asm/cacheflush.h>
#include <asm/sstep.h>
#include <asm/sections.h>
@@ -105,41 +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_rox((unsigned long)page, 1);
-
- return page;
-}
-
int arch_prepare_kprobe(struct kprobe *p)
{
int ret = 0;
@@ -242,16 +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;
@@ -409,49 +383,6 @@ no_kprobe:
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
@@ -553,19 +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/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 2eabb15687a6..acb727f54e9d 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -28,32 +28,6 @@
.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
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 1a8cdafd68e8..a997c7f43dc0 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -74,7 +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
@@ -137,7 +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
@@ -174,7 +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)
*
@@ -192,7 +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
*/
@@ -226,7 +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.
*/
@@ -243,7 +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)
*
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 816a63fd71fb..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) */
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 7112adc597a8..34a5aec4908f 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>
@@ -205,7 +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;
@@ -241,13 +243,25 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
}
}
-#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;
+ }
+ }
+ if (i == hdr->e_shnum) {
+ pr_err("%s: doesn't contain __patchable_function_entries.\n", me->name);
+ return -ENOEXEC;
+ }
#endif
pr_debug("Looks like a total of %lu stubs, max\n", relocs);
@@ -355,6 +369,24 @@ 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).
@@ -424,10 +456,12 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
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,
@@ -460,7 +494,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
#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;
}
@@ -651,12 +685,11 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
// 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;
@@ -1086,6 +1119,37 @@ 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,
@@ -1104,6 +1168,9 @@ 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/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 004fae2044a3..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);
/*
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index d95a48eff412..eac84d687b53 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -517,7 +517,7 @@ 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
*/
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 0fe251c6ac2c..9ea74973d78d 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
@@ -106,7 +136,7 @@ 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);
@@ -129,8 +159,7 @@ 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 ce0c8623e563..f8a3bd8cfae4 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -213,11 +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);
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index b109cd7b5d01..3816a2bf2b84 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -4,6 +4,7 @@
*/
#include <linux/init.h>
+#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/kernel.h>
@@ -12,9 +13,10 @@
#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 +35,9 @@ 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 +46,35 @@ 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;
+ strcpy((char *)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 +83,7 @@ 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 9452a54d356c..ef91f71e07c4 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
@@ -1185,6 +1183,9 @@ static inline void save_sprs(struct thread_struct *t)
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
}
@@ -1267,6 +1268,10 @@ static inline void restore_sprs(struct thread_struct *old_thread,
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
}
@@ -1566,7 +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);
@@ -1634,6 +1639,13 @@ 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
@@ -1647,7 +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
@@ -1657,15 +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
@@ -1861,7 +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
@@ -1878,6 +1890,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
#ifdef CONFIG_PPC_BOOK3S_64
if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE))
p->thread.hashkeyr = current->thread.hashkeyr;
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ p->thread.dexcr = mfspr(SPRN_DEXCR);
#endif
return 0;
}
@@ -1945,8 +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.
@@ -2160,10 +2175,10 @@ 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);
@@ -2191,10 +2206,26 @@ 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;
+
+ 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
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 0b5878c3125b..e0059842a1c6 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -151,6 +151,9 @@ 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.
*/
struct ibm_feature {
unsigned long cpu_features; /* CPU_FTR_xxx bit */
@@ -159,7 +162,7 @@ struct ibm_feature {
unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */
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 */
+ unsigned char clear; /* if 1, pa bit set => clear feature */
};
static struct ibm_feature ibm_pa_features[] __initdata = {
@@ -193,6 +196,7 @@ static struct ibm_feature ibm_pa_features[] __initdata = {
*/
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,
@@ -220,12 +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;
@@ -327,6 +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;
@@ -368,13 +373,31 @@ 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;
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
* meet various levels of the architecture:
@@ -398,7 +421,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) {
identify_cpu(0, be32_to_cpup(prop));
- seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop));
+ cpu_version = prop;
}
check_cpu_feature_properties(node);
@@ -409,6 +432,12 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
}
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
@@ -453,7 +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;
@@ -757,12 +786,12 @@ static inline void save_fscr_to_task(void) {}
void __init early_init_devtree(void *params)
{
- 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);
@@ -791,6 +820,9 @@ 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();
@@ -810,9 +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)
/*
@@ -824,9 +863,12 @@ void __init early_init_devtree(void *params)
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())
@@ -846,9 +888,6 @@ void __init early_init_devtree(void *params)
dt_cpu_ftrs_scan();
- // 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));
-
/* Retrieve CPU related informations from the flat tree
* (altivec support, boot CPU ID, ...)
*/
@@ -869,6 +908,9 @@ void __init early_init_devtree(void *params)
mmu_early_init_devtree();
+ /* 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 */
of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL);
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index e67effdba85c..57082fac4668 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -817,8 +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
}
@@ -947,7 +947,7 @@ struct option_vector7 {
} __packed;
struct ibm_arch_vec {
- struct { __be32 mask, val; } pvrs[14];
+ struct { __be32 mask, val; } pvrs[16];
u8 num_vectors;
@@ -1008,6 +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),
},
@@ -2784,91 +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
@@ -2919,12 +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;
@@ -2963,11 +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 nodes
+ for (node = 0; prom_next_node(&node); ) {
+ type[0] = '\0';
+ prom_getprop(node, "device_type", type, sizeof(type));
+ if (prom_strcmp(type, "escc"))
+ 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
@@ -3099,11 +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.
@@ -3179,18 +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/ptrace/ptrace-tm.c b/arch/powerpc/kernel/ptrace/ptrace-tm.c
index 210ea834e603..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.
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index 584cf5c3df50..c1819e0a6684 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -469,12 +469,7 @@ static int dexcr_get(struct task_struct *target, const struct user_regset *regse
if (!cpu_has_feature(CPU_FTR_ARCH_31))
return -ENODEV;
- /*
- * The DEXCR is currently static across all CPUs, so we don't
- * store the target's value anywhere, but the static value
- * will also be correct.
- */
- membuf_store(&to, (u64)lower_32_bits(DEXCR_INIT));
+ membuf_store(&to, (u64)lower_32_bits(target->thread.dexcr));
/*
* Technically the HDEXCR is per-cpu, but a hypervisor can't reasonably
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.c b/arch/powerpc/kernel/rtas.c
index 8064d9c3de86..d31c9799cab2 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -19,6 +19,7 @@
#include <linux/lockdep.h>
#include <linux/memblock.h>
#include <linux/mutex.h>
+#include <linux/nospec.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/reboot.h>
@@ -1389,21 +1390,14 @@ bool __ref 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;
@@ -1916,6 +1910,9 @@ 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)
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 359577ec1680..5407024881e5 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -773,4 +773,5 @@ 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/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 4856e1a5161c..fbb7ebd8aa08 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -14,7 +14,7 @@
#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>
diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c
index eb3c053f323f..fbeb1cbac01b 100644
--- a/arch/powerpc/kernel/secvar-sysfs.c
+++ b/arch/powerpc/kernel/secvar-sysfs.c
@@ -125,7 +125,7 @@ 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,
};
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 9b142b9d5187..a08b0ede4e64 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -67,6 +67,7 @@
#include <asm/cpu_has_feature.h>
#include <asm/kasan.h>
#include <asm/mce.h>
+#include <asm/systemcfg.h>
#include "setup.h"
@@ -85,6 +86,7 @@ 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;
@@ -109,7 +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
@@ -404,13 +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
@@ -437,16 +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);
@@ -468,27 +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 */
@@ -536,7 +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/
@@ -616,6 +640,8 @@ static __init void probe_machine(void)
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 && !ppc_md.probe())
continue;
@@ -805,8 +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();
}
@@ -933,6 +959,7 @@ void __init setup_arch(char **cmdline_p)
mem_topology_setup();
/* Set max_mapnr before paging_init() */
set_max_mapnr(max_pfn);
+ high_memory = (void *)__va(max_low_pfn * PAGE_SIZE);
/*
* Release secondary cpus out of their spinloops at 0x60 now that
@@ -970,9 +997,11 @@ 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 7912bb50a7cb..385a00a2e2ca 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -29,7 +29,7 @@ void setup_tlb_core_data(void);
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 b761cc1a403c..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;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2f19d5e94485..e67f3048611f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -60,7 +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>
@@ -696,11 +696,7 @@ __init u64 ppc64_bolted_size(void)
{
#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())
@@ -834,6 +830,7 @@ 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)
{
@@ -876,6 +873,7 @@ 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];
@@ -922,6 +920,7 @@ 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/smp.c b/arch/powerpc/kernel/smp.c
index 693334c20d07..5ac7084eebc0 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -61,6 +61,7 @@
#include <asm/ftrace.h>
#include <asm/kup.h>
#include <asm/fadump.h>
+#include <asm/systemcfg.h>
#include <trace/events/ipi.h>
@@ -588,7 +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;
@@ -631,7 +632,7 @@ void crash_smp_send_stop(void)
stopped = true;
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
if (kexec_crash_image) {
crash_kexec_prepare();
return;
@@ -984,7 +985,7 @@ static bool shared_caches __ro_after_init;
/* 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");
@@ -1010,9 +1011,9 @@ static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
static int powerpc_shared_cache_flags(void)
{
if (static_branch_unlikely(&splpar_asym_pack))
- return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING;
+ return SD_SHARE_LLC | SD_ASYM_PACKING;
- return SD_SHARE_PKG_RESOURCES;
+ return SD_SHARE_LLC;
}
static int powerpc_shared_proc_flags(void)
@@ -1166,7 +1167,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
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
@@ -1186,8 +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();
@@ -1567,7 +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));
@@ -1642,10 +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]);
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index e6a958a5da27..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>
@@ -133,12 +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
diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c
index 863a7aa24650..7cfd0710e757 100644
--- a/arch/powerpc/kernel/static_call.c
+++ b/arch/powerpc/kernel/static_call.c
@@ -2,7 +2,7 @@
#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)
{
@@ -17,7 +17,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
mutex_lock(&text_mutex);
if (func && !is_short) {
- err = patch_instruction(tramp + PPC_SCT_DATA, ppc_inst(target));
+ err = patch_ulong(tramp + PPC_SCT_DATA, target);
if (err)
goto out;
}
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index 77fedb190c93..be159ad4b77b 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -27,11 +27,11 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
trace_hardirqs_off(); /* finish reconciling */
- CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
+ CT_WARN_ON(ct_state() == CT_STATE_KERNEL);
user_exit_irqoff();
BUG_ON(regs_is_unrecoverable(regs));
- BUG_ON(!(regs->msr & MSR_PR));
+ BUG_ON(!user_mode(regs));
BUG_ON(arch_irq_disabled_regs(regs));
#ifdef CONFIG_PPC_PKEY
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 17173b82ca21..d8b4ab78bef0 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -230,8 +230,10 @@
178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend
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
@@ -246,6 +248,7 @@
190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
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_ppc_truncate64 compat_sys_ppc_truncate64
194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64
@@ -293,6 +296,7 @@
232 nospu set_tid_address sys_set_tid_address
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_ni_syscall
236 common epoll_create sys_epoll_create
@@ -502,7 +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
@@ -548,3 +552,8 @@
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
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 0f39a6b84132..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)
{
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index df20cf201f74..0727332ad86f 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 = {
@@ -354,6 +354,28 @@ void vtime_flush(struct task_struct *tsk)
acct->hardirq_time = 0;
acct->softirq_time = 0;
}
+
+/*
+ * 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 __no_kcsan __delay(unsigned long loops)
@@ -673,7 +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 */
@@ -929,6 +951,9 @@ void __init time_init(void)
}
vdso_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();
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
index 125f4ca588b9..d6c3885453bd 100644
--- a/arch/powerpc/kernel/trace/Makefile
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -9,12 +9,15 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_ftrace_64_pg.o = $(CC_FLAGS_FTRACE)
endif
-obj32-$(CONFIG_FUNCTION_TRACER) += ftrace.o ftrace_entry.o
-ifdef CONFIG_MPROFILE_KERNEL
-obj64-$(CONFIG_FUNCTION_TRACER) += ftrace.o ftrace_entry.o
+ifdef CONFIG_FUNCTION_TRACER
+obj32-y += ftrace.o ftrace_entry.o
+ifeq ($(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 ftrace_64_pg_entry.o
+obj64-y += ftrace.o ftrace_entry.o
+endif
endif
+
obj-$(CONFIG_TRACING) += trace_clock.o
obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index d8d6b4fd9a14..2f776f137a89 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -23,7 +23,7 @@
#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>
@@ -37,8 +37,12 @@ unsigned long ftrace_call_adjust(unsigned long addr)
if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
return 0;
- if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
+ 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;
+ }
return addr;
}
@@ -82,7 +86,7 @@ static inline int ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_
{
int ret = ftrace_validate_inst(ip, old);
- if (!ret)
+ if (!ret && !ppc_inst_equal(old, new))
ret = patch_instruction((u32 *)ip, new);
return ret;
@@ -106,28 +110,68 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
return 0;
}
+#ifdef CONFIG_MODULES
+static unsigned long ftrace_lookup_module_stub(unsigned long ip, unsigned long addr)
+{
+ struct module *mod = NULL;
+
+ preempt_disable();
+ mod = __module_text_address(ip);
+ preempt_enable();
+
+ if (!mod)
+ pr_err("No module loaded at addr=%lx\n", ip);
+
+ return (addr == (unsigned long)ftrace_caller ? mod->arch.tramp : mod->arch.tramp_regs);
+}
+#else
+static unsigned long ftrace_lookup_module_stub(unsigned long ip, unsigned long addr)
+{
+ return 0;
+}
+#endif
+
+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
+}
+
static int ftrace_get_call_inst(struct dyn_ftrace *rec, unsigned long addr, ppc_inst_t *call_inst)
{
- unsigned long ip = rec->ip;
+ unsigned long ip;
unsigned long stub;
- if (is_offset_in_branch_range(addr - ip)) {
+ 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;
+ }
+
+ if (is_offset_in_branch_range(addr - ip))
/* Within range */
stub = addr;
-#ifdef CONFIG_MODULES
- } else if (rec->arch.mod) {
- /* Module code would be going to one of the module stubs */
- stub = (addr == (unsigned long)ftrace_caller ? rec->arch.mod->arch.tramp :
- rec->arch.mod->arch.tramp_regs);
-#endif
- } else if (core_kernel_text(ip)) {
+ else if (core_kernel_text(ip))
/* We would be branching to one of our ftrace stubs */
stub = find_ftrace_tramp(ip);
- if (!stub) {
- pr_err("0x%lx: No ftrace stubs reachable\n", ip);
- return -EINVAL;
- }
- } else {
+ else
+ stub = ftrace_lookup_module_stub(ip, addr);
+
+ if (!stub) {
+ pr_err("0x%lx (0x%lx): No ftrace stubs reachable\n", ip, rec->ip);
return -EINVAL;
}
@@ -135,6 +179,145 @@ static int ftrace_get_call_inst(struct dyn_ftrace *rec, unsigned long addr, ppc_
return 0;
}
+static int ftrace_init_ool_stub(struct module *mod, struct dyn_ftrace *rec)
+{
+#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 */
+ }
+ };
+
+ WARN_ON(rec->arch.ool_stub);
+
+ 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;
+ }
+
+ ool_stub += (*ool_stub_index)++;
+
+ if (WARN_ON(*ool_stub_index > ool_stub_count))
+ 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;
+ }
+
+ rec->arch.ool_stub = (unsigned long)&ool_stub->insn[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
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+static const struct ftrace_ops *powerpc_rec_get_ops(struct dyn_ftrace *rec)
+{
+ const struct ftrace_ops *ops = NULL;
+
+ if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
+ ops = ftrace_find_unique_ops(rec);
+ WARN_ON_ONCE(!ops);
+ }
+
+ if (!ops)
+ ops = &ftrace_list_ops;
+
+ return ops;
+}
+
+static int ftrace_rec_set_ops(struct dyn_ftrace *rec, const struct ftrace_ops *ops)
+{
+ 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 patch_ulong((void *)(rec->ip - MCOUNT_INSN_SIZE - sizeof(unsigned long)),
+ (unsigned long)ops);
+}
+
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec)
+{
+ return ftrace_rec_set_ops(rec, &ftrace_nop_ops);
+}
+
+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_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)
{
@@ -147,18 +330,33 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
ppc_inst_t old, new;
- int ret;
+ unsigned long ip = rec->ip;
+ int ret = 0;
/* This can only ever be called during module load */
- if (WARN_ON(!IS_ENABLED(CONFIG_MODULES) || core_kernel_text(rec->ip)))
+ if (WARN_ON(!IS_ENABLED(CONFIG_MODULES) || core_kernel_text(ip)))
return -EINVAL;
old = ppc_inst(PPC_RAW_NOP());
- ret = ftrace_get_call_inst(rec, addr, &new);
+ 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);
+ }
+
+ ret |= ftrace_get_call_inst(rec, addr, &new);
+
+ if (!ret)
+ ret = ftrace_modify_code(ip, old, new);
+
+ ret = ftrace_rec_update_ops(rec);
if (ret)
return ret;
- return ftrace_modify_code(rec->ip, old, new);
+ 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_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
@@ -191,6 +389,13 @@ void ftrace_replace_code(int enable)
new_addr = ftrace_get_addr_new(rec);
update = ftrace_update_record(rec, enable);
+ 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;
+ }
+
switch (update) {
case FTRACE_UPDATE_IGNORE:
default:
@@ -198,16 +403,19 @@ void ftrace_replace_code(int enable)
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;
@@ -215,6 +423,24 @@ void ftrace_replace_code(int enable)
if (!ret)
ret = ftrace_modify_code(ip, old, new);
+
+ 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 (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 (ret)
+ goto out;
+ }
+
if (ret)
goto out;
}
@@ -234,20 +460,27 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
/* Verify instructions surrounding the ftrace location */
if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
/* Expect nops */
- ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_NOP()));
+ 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)
- ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STW(_R0, _R1, 4)));
+ 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)));
- ret |= ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STD(_R0, _R1, 16)));
+ 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;
@@ -256,13 +489,9 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
if (ret)
return ret;
- if (!core_kernel_text(ip)) {
- if (!mod) {
- pr_err("0x%lx: No module provided for non-kernel address\n", ip);
- return -EFAULT;
- }
- rec->arch.mod = mod;
- }
+ /* 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());
@@ -302,6 +531,13 @@ 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_create_branch_inst(ip, ppc_function_entry(func), 1);
ret = ftrace_modify_code(ip, old, new);
@@ -421,8 +657,7 @@ int __init ftrace_dyn_arch_init(void)
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
- unsigned long sp = fregs->regs.gpr[1];
- int bit;
+ unsigned long sp = arch_ftrace_regs(fregs)->regs.gpr[1];
if (unlikely(ftrace_graph_is_dead()))
goto out;
@@ -430,15 +665,10 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
if (unlikely(atomic_read(&current->tracing_graph_pause)))
goto out;
- bit = ftrace_test_recursion_trylock(ip, parent_ip);
- if (bit < 0)
- goto out;
-
- if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp))
+ if (!function_graph_enter_regs(parent_ip, ip, 0, (unsigned long *)sp, fregs))
parent_ip = ppc_function_entry(return_to_handler);
- ftrace_test_recursion_unlock(bit);
out:
- fregs->regs.link = parent_ip;
+ arch_ftrace_regs(fregs)->regs.link = parent_ip;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 12fab1803bcf..ac35015f04c6 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -23,7 +23,7 @@
#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>
@@ -116,6 +116,20 @@ static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
}
#ifdef CONFIG_MODULES
+static struct module *ftrace_lookup_module(struct dyn_ftrace *rec)
+{
+ struct module *mod;
+
+ preempt_disable();
+ mod = __module_text_address(rec->ip);
+ preempt_enable();
+
+ 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)
@@ -124,6 +138,12 @@ __ftrace_make_nop(struct module *mod,
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");
@@ -366,27 +386,6 @@ int ftrace_make_nop(struct module *mod,
return -EINVAL;
}
- /*
- * 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;
-
return __ftrace_make_nop(mod, rec, addr);
}
@@ -411,7 +410,10 @@ __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 = rec->arch.mod;
+ struct module *mod = ftrace_lookup_module(rec);
+
+ if (!mod)
+ return -EINVAL;
/* read where this goes */
if (copy_inst_from_kernel_nofault(op, ip))
@@ -533,16 +535,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
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);
}
@@ -555,7 +547,10 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
ppc_inst_t op;
unsigned long ip = rec->ip;
unsigned long entry, ptr, tramp;
- struct module *mod = rec->arch.mod;
+ 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) {
@@ -668,14 +663,6 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
return -EINVAL;
}
- /*
- * Out of range jumps are called from modules.
- */
- if (!rec->arch.mod) {
- pr_err("No module loaded\n");
- return -EINVAL;
- }
-
return __ftrace_modify_call(rec, old_addr, addr);
}
#endif
@@ -800,10 +787,10 @@ int ftrace_disable_ftrace_graph_caller(void)
* 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)
+__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp,
+ struct ftrace_regs *fregs)
{
unsigned long return_hooker;
- int bit;
if (unlikely(ftrace_graph_is_dead()))
goto out;
@@ -811,16 +798,11 @@ __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;
-
return_hooker = ppc_function_entry(return_to_handler);
- if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
+ if (!function_graph_enter_regs(parent, ip, 0, (unsigned long *)sp, fregs))
parent = return_hooker;
- ftrace_test_recursion_unlock(bit);
out:
return parent;
}
@@ -829,13 +811,14 @@ out:
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]);
+ 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);
+ return __prepare_ftrace_return(parent, ip, sp, NULL);
}
#endif
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index 76dbe9fd2c0f..2c1b24100eca 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -39,13 +39,37 @@
/* 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
- /* Save the original return address in A's stack frame */
- std r0, LRSAVE+SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE(r1)
/* Ok to continue? */
lbz r3, PACA_FTRACE_ENABLED(r13)
cmpdi r3, 0
@@ -54,9 +78,9 @@
.if \allregs == 1
SAVE_GPR(2, r1)
- SAVE_GPRS(11, 31, r1)
+ SAVE_GPRS(13, 31, r1)
.else
-#ifdef CONFIG_LIVEPATCH_64
+#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
SAVE_GPR(14, r1)
#endif
.endif
@@ -67,80 +91,143 @@
.if \allregs == 1
/* Load special regs for save below */
+ mfcr r7
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)
- /* Also save it in B's stackframe header for proper unwind */
- PPC_STL r7, LRSAVE+SWITCH_FRAME_SIZE(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)
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
-
-#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 r7, _CCR(r1)
PPC_STL r9, _CTR(r1)
PPC_STL r10, _XER(r1)
- PPC_STL r11, _CCR(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
- /* Load ctr with the possibly modified NIP */
- PPC_LL r3, _NIP(r1)
+#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
+ .if \allregs == 0
+ REST_GPR(15, r1)
+ .endif
+1: mtlr r3
+#endif
+
/* Restore gprs */
.if \allregs == 1
REST_GPRS(2, 31, r1)
.else
REST_GPRS(3, 10, r1)
-#ifdef CONFIG_LIVEPATCH_64
+#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
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)
@@ -153,23 +240,46 @@
/* Based on the cmpd above, if the NIP was altered handle livepatch */
bne- livepatch_handler
#endif
- bctr /* jump after _mcount site */
+
+ /* 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
-_GLOBAL(ftrace_regs_caller)
- ftrace_regs_entry 1
- /* ftrace_call(r3, r4, r5, r6) */
+.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_call(r3, r4, r5, r6) */
-.globl ftrace_call
-ftrace_call:
- bl ftrace_stub
+ ftrace_regs_func 0
ftrace_regs_exit 0
_GLOBAL(ftrace_stub)
@@ -177,6 +287,11 @@ _GLOBAL(ftrace_stub)
#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)
@@ -184,6 +299,22 @@ ftrace_no_trace:
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
/*
@@ -194,11 +325,17 @@ ftrace_no_trace:
* 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
+ * 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)
@@ -208,18 +345,23 @@ livepatch_handler:
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 */
+ /* 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
/*
@@ -308,6 +450,14 @@ _GLOBAL(return_to_handler)
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:
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 11e062b47d3f..edf5cabe5dfd 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -121,7 +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);
@@ -404,7 +404,7 @@ 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;
/*
@@ -1510,7 +1510,7 @@ 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) {
regs_add_return_ip(regs, 4);
return;
@@ -2244,7 +2244,7 @@ void __noreturn unrecoverable_exception(struct pt_regs *regs)
;
}
-#if defined(CONFIG_BOOKE_WDT) || defined(CONFIG_40x)
+#ifdef CONFIG_BOOKE_WDT
DEFINE_INTERRUPT_HANDLER_NMI(WatchdogException)
{
printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 92b3fc258d11..0a72a537f879 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -39,9 +39,6 @@ void __init udbg_early_init(void)
#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 +46,6 @@ 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)
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index a0467e528b70..dfe8ed2192e8 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -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)
@@ -274,29 +251,6 @@ void __init udbg_init_44x_as1(void)
#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
-#ifdef CONFIG_PPC_EARLY_DEBUG_40x
-
-static u8 udbg_uart_in_40x(unsigned int reg)
-{
- return real_readb((void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
- + reg);
-}
-
-static void udbg_uart_out_40x(unsigned int reg, u8 val)
-{
- real_writeb(val, (void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
- + reg);
-}
-
-void __init udbg_init_40x_realmode(void)
-{
- udbg_uart_in = udbg_uart_in_40x;
- udbg_uart_out = udbg_uart_out_40x;
- udbg_use_uart();
-}
-
-#endif /* CONFIG_PPC_EARLY_DEBUG_40x */
-
#ifdef CONFIG_PPC_EARLY_DEBUG_16550
static void __iomem *udbg_uart_early_addr;
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 7a2ff9010f17..43379365ce1b 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -16,7 +16,6 @@
#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 <vdso/datapage.h>
@@ -48,12 +47,13 @@ long sys_ni_syscall(void);
*/
static union {
struct vdso_arch_data data;
- u8 page[PAGE_SIZE];
+ u8 page[2 * 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_BASE_PAGE_OFFSET,
+ VVAR_TIME_PAGE_OFFSET,
VVAR_TIMENS_PAGE_OFFSET,
VVAR_NR_PAGES,
};
@@ -81,6 +81,21 @@ 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 void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struct *vma)
+{
+ struct mm_struct *mm = vma->vm_mm;
+
+ /*
+ * 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 vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf);
@@ -92,17 +107,19 @@ static struct vm_special_mapping vvar_spec __ro_after_init = {
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;
+ return vvar_page;
}
/*
@@ -136,11 +153,14 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
unsigned long pfn;
switch (vmf->pgoff) {
- case VVAR_DATA_PAGE_OFFSET:
+ case VVAR_BASE_PAGE_OFFSET:
+ pfn = virt_to_pfn(vdso_data);
+ break;
+ case VVAR_TIME_PAGE_OFFSET:
if (timens_page)
pfn = page_to_pfn(timens_page);
else
- pfn = virt_to_pfn(vdso_data);
+ pfn = virt_to_pfn(vdso_data->data);
break;
#ifdef CONFIG_TIME_NS
case VVAR_TIMENS_PAGE_OFFSET:
@@ -153,7 +173,7 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
*/
if (!timens_page)
return VM_FAULT_SIGBUS;
- pfn = virt_to_pfn(vdso_data);
+ pfn = virt_to_pfn(vdso_data->data);
break;
#endif /* CONFIG_TIME_NS */
default:
@@ -197,13 +217,6 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
/* 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);
@@ -223,10 +236,15 @@ 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);
+ }
+
+ // Now that the mappings are in place, set the mm VDSO pointer
+ mm->context.vdso = (void __user *)vdso_base + vvar_size;
- return PTR_ERR_OR_ZERO(vma);
+ return 0;
}
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
@@ -240,8 +258,6 @@ 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;
@@ -336,25 +352,6 @@ 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;
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 1b93655c2857..0e3ed6fb199f 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -8,30 +8,21 @@ include $(srctree)/lib/vdso/Makefile
obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o
obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o
+obj-vdso32 += getrandom-32.o vgetrandom-chacha-32.o
+obj-vdso64 += getrandom-64.o vgetrandom-chacha-64.o
+
ifneq ($(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
- # 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.
- ifdef CONFIG_CC_IS_CLANG
- CFLAGS_REMOVE_vgettimeofday-32.o += -fno-stack-clash-protection
- endif
- 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
@@ -42,26 +33,36 @@ 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
-KCSAN_SANITIZE := n
-
-ccflags-y := -fno-common -fno-builtin
+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_CFLAGS))
+ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
CC32FLAGS := -m32
+CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
+ifdef CONFIG_CC_IS_CLANG
+# This flag is supported by clang for 64-bit but not 32-bit so it will cause
+# an unused command line flag warning for this file.
+CC32FLAGSREMOVE += -fno-stack-clash-protection
+# -mstack-protector-guard values from the 64-bit build are not valid for the
+# 32-bit one. clang validates the values passed to these arguments during
+# parsing, even when -fno-stack-protector is passed afterwards.
+CC32FLAGSREMOVE += -mstack-protector-guard%
+endif
LD32FLAGS := -Wl,-soname=linux-vdso32.so.1
AS32FLAGS := -D__VDSO32__
@@ -74,26 +75,32 @@ targets += vdso64.lds
CPPFLAGS_vdso64.lds += -P -C
# link rule for the .so file, .lds has to be first
-$(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 > $@
@@ -108,11 +115,9 @@ quiet_cmd_vdso32ld_and_check = VDSO32L $@
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) $(ldflags-y) $(LD64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
quiet_cmd_vdso64as = VDSO64A $@
cmd_vdso64as = $(VDSOCC) $(a_flags) $(AS64FLAGS) -c -o $@ $<
-
-OBJECT_FILES_NON_STANDARD := y
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 48fc6658053a..5333848322ca 100644
--- a/arch/powerpc/kernel/vdso/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso/gettimeofday.S
@@ -32,17 +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_DATA_OFFSET
.else
- addi r4, r5, VDSO_DATA_OFFSET
+ get_datapage r4 VDSO_DATA_OFFSET
.endif
-#ifdef __powerpc64__
bl CFUNC(DOTSYM(\funct))
-#else
- bl \funct
-#endif
PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
#ifdef __powerpc64__
PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1)
@@ -118,16 +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 426e1ccc6971..1a1b0b6d681a 100644
--- a/arch/powerpc/kernel/vdso/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso32.lds.S
@@ -16,7 +16,7 @@ OUTPUT_ARCH(powerpc:common)
SECTIONS
{
- PROVIDE(_vdso_datapage = . - 2 * PAGE_SIZE);
+ PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE);
. = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
@@ -74,6 +74,8 @@ SECTIONS
.got : { *(.got) } :text
.plt : { *(.plt) }
+ .rela.dyn : { *(.rela .rela*) }
+
_end = .;
__end = .;
PROVIDE(end = .);
@@ -87,7 +89,7 @@ SECTIONS
*(.branch_lt)
*(.data .data.* .gnu.linkonce.d.* .sdata*)
*(.bss .sbss .dynbss .dynsbss)
- *(.got1 .glink .iplt .rela*)
+ *(.got1 .glink .iplt)
}
}
@@ -128,6 +130,7 @@ 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 bda6c8cdd459..e21b5506cad6 100644
--- a/arch/powerpc/kernel/vdso/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso64.lds.S
@@ -16,7 +16,7 @@ OUTPUT_ARCH(powerpc:common64)
SECTIONS
{
- PROVIDE(_vdso_datapage = . - 2 * PAGE_SIZE);
+ PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE);
. = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
@@ -69,7 +69,7 @@ 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) }
@@ -86,7 +86,7 @@ SECTIONS
*(.data .data.* .gnu.linkonce.d.* .sdata*)
*(.bss .sbss .dynbss .dynsbss)
*(.opd)
- *(.glink .iplt .plt .rela*)
+ *(.glink .iplt .plt)
}
}
@@ -123,6 +123,7 @@ 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/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/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index f420df7888a7..b4c9decc7a75 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -123,8 +123,6 @@ SECTIONS
*/
*(.sfpr);
*(.text.asan.* .text.tsan.*)
- MEM_KEEP(init.text)
- MEM_KEEP(exit.text)
} :text
. = ALIGN(PAGE_SIZE);
@@ -267,14 +265,13 @@ SECTIONS
.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 = .;
- *(.tramp.ftrace.init);
} :text
/* .exit.text is discarded at runtime, not link time,
diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile
index 0c2abe7f9908..470eb0453e17 100644
--- a/arch/powerpc/kexec/Makefile
+++ b/arch/powerpc/kexec/Makefile
@@ -3,11 +3,13 @@
# Makefile for the linux kernel.
#
-obj-y += core.o crash.o core_$(BITS).o
+obj-y += core.o core_$(BITS).o ranges.o
obj-$(CONFIG_PPC32) += relocate_32.o
-obj-$(CONFIG_KEXEC_FILE) += file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o
+obj-$(CONFIG_KEXEC_FILE) += file_load.o file_load_$(BITS).o elf_$(BITS).o
+obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o
+obj-$(CONFIG_CRASH_DUMP) += crash.o
# Disable GCOV, KCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_core_$(BITS).o := n
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 27fa9098a5b7..58a930a47422 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -22,65 +22,17 @@
#include <asm/setup.h>
#include <asm/firmware.h>
-void machine_kexec_mask_interrupts(void) {
- unsigned int i;
- struct irq_desc *desc;
-
- for_each_irq_desc(i, desc) {
- struct irq_chip *chip;
-
- chip = irq_desc_get_chip(desc);
- if (!chip)
- continue;
-
- if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
- chip->irq_eoi(&desc->irq_data);
-
- if (chip->irq_mask)
- chip->irq_mask(&desc->irq_data);
-
- if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
- chip->irq_disable(&desc->irq_data);
- }
-}
-
+#ifdef CONFIG_CRASH_DUMP
void machine_crash_shutdown(struct pt_regs *regs)
{
default_machine_crash_shutdown(regs);
}
+#endif
void machine_kexec_cleanup(struct kimage *image)
{
}
-void arch_crash_save_vmcoreinfo(void)
-{
-
-#ifdef CONFIG_NUMA
- VMCOREINFO_SYMBOL(node_data);
- VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
-#endif
-#ifndef CONFIG_NUMA
- VMCOREINFO_SYMBOL(contig_page_data);
-#endif
-#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP)
- VMCOREINFO_SYMBOL(vmemmap_list);
- VMCOREINFO_SYMBOL(mmu_vmemmap_psize);
- VMCOREINFO_SYMBOL(mmu_psize_defs);
- VMCOREINFO_STRUCT_SIZE(vmemmap_backing);
- VMCOREINFO_OFFSET(vmemmap_backing, list);
- VMCOREINFO_OFFSET(vmemmap_backing, phys);
- VMCOREINFO_OFFSET(vmemmap_backing, virt_addr);
- VMCOREINFO_STRUCT_SIZE(mmu_psize_def);
- VMCOREINFO_OFFSET(mmu_psize_def, shift);
-#endif
- VMCOREINFO_SYMBOL(cur_cpu_spec);
- VMCOREINFO_OFFSET(cpu_spec, cpu_features);
- VMCOREINFO_OFFSET(cpu_spec, mmu_features);
- vmcoreinfo_append_str("NUMBER(RADIX_MMU)=%d\n", early_radix_enabled());
- vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
-}
-
/*
* Do not allocate memory (or fail in any way) in machine_kexec().
* We are past the point of no return, committed to rebooting now.
@@ -105,6 +57,7 @@ void machine_kexec(struct kimage *image)
for(;;);
}
+#ifdef CONFIG_CRASH_RESERVE
void __init reserve_crashkernel(void)
{
unsigned long long crash_size, crash_base, total_mem_sz;
@@ -279,3 +232,4 @@ static int __init kexec_setup(void)
return 0;
}
late_initcall(kexec_setup);
+#endif /* CONFIG_CRASH_RESERVE */
diff --git a/arch/powerpc/kexec/core_32.c b/arch/powerpc/kexec/core_32.c
index c95f96850c9e..deb28eb44f30 100644
--- a/arch/powerpc/kexec/core_32.c
+++ b/arch/powerpc/kexec/core_32.c
@@ -7,6 +7,7 @@
* Copyright (C) 2005 IBM Corporation.
*/
+#include <linux/irq.h>
#include <linux/kexec.h>
#include <linux/mm.h>
#include <linux/string.h>
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 762e4d09aacf..222aa326dace 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -17,6 +17,7 @@
#include <linux/cpu.h>
#include <linux/hardirq.h>
#include <linux/of.h>
+#include <linux/libfdt.h>
#include <asm/page.h>
#include <asm/current.h>
@@ -26,10 +27,12 @@
#include <asm/paca.h>
#include <asm/mmu.h>
#include <asm/sections.h> /* _end */
+#include <asm/setup.h>
#include <asm/smp.h>
#include <asm/hw_breakpoint.h>
#include <asm/svm.h>
#include <asm/ultravisor.h>
+#include <asm/crashdump-ppc64.h>
int machine_kexec_prepare(struct kimage *image)
{
@@ -315,6 +318,16 @@ void default_machine_kexec(struct kimage *image)
if (!kdump_in_progress())
kexec_prepare_cpus();
+#ifdef CONFIG_PPC_PSERIES
+ /*
+ * This must be done after other CPUs have shut down, otherwise they
+ * could execute the 'scv' instruction, which is not supported with
+ * reloc disabled (see configure_exceptions()).
+ */
+ if (firmware_has_feature(FW_FEATURE_SET_MODE))
+ pseries_disable_reloc_on_exc();
+#endif
+
printk("kexec: Starting switchover sequence.\n");
/* switch to a staticly allocated stack. Based on irq stack code.
@@ -419,3 +432,113 @@ static int __init export_htab_values(void)
}
late_initcall(export_htab_values);
#endif /* CONFIG_PPC_64S_HASH_MMU */
+
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
+/**
+ * add_node_props - Reads node properties from device node structure and add
+ * them to fdt.
+ * @fdt: Flattened device tree of the kernel
+ * @node_offset: offset of the node to add a property at
+ * @dn: device node pointer
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
+{
+ int ret = 0;
+ struct property *pp;
+
+ if (!dn)
+ return -EINVAL;
+
+ for_each_property_of_node(dn, pp) {
+ ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
+ if (ret < 0) {
+ pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
+ return ret;
+ }
+ }
+ return ret;
+}
+
+/**
+ * update_cpus_node - Update cpus node of flattened device tree using of_root
+ * device node.
+ * @fdt: Flattened device tree of the kernel.
+ *
+ * Returns 0 on success, negative errno on error.
+ *
+ * Note: expecting no subnodes under /cpus/<node> with device_type == "cpu".
+ * If this changes, update this function to include them.
+ */
+int update_cpus_node(void *fdt)
+{
+ int prev_node_offset;
+ const char *device_type;
+ const struct fdt_property *prop;
+ struct device_node *cpus_node, *dn;
+ int cpus_offset, cpus_subnode_offset, ret = 0;
+
+ cpus_offset = fdt_path_offset(fdt, "/cpus");
+ if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
+ pr_err("Malformed device tree: error reading /cpus node: %s\n",
+ fdt_strerror(cpus_offset));
+ return cpus_offset;
+ }
+
+ prev_node_offset = cpus_offset;
+ /* Delete sub-nodes of /cpus node with device_type == "cpu" */
+ for (cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset); cpus_subnode_offset >= 0;) {
+ /* Ignore nodes that do not have a device_type property or device_type != "cpu" */
+ prop = fdt_get_property(fdt, cpus_subnode_offset, "device_type", NULL);
+ if (!prop || strcmp(prop->data, "cpu")) {
+ prev_node_offset = cpus_subnode_offset;
+ goto next_node;
+ }
+
+ ret = fdt_del_node(fdt, cpus_subnode_offset);
+ if (ret < 0) {
+ pr_err("Failed to delete a cpus sub-node: %s\n", fdt_strerror(ret));
+ return ret;
+ }
+next_node:
+ if (prev_node_offset == cpus_offset)
+ cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset);
+ else
+ cpus_subnode_offset = fdt_next_subnode(fdt, prev_node_offset);
+ }
+
+ cpus_node = of_find_node_by_path("/cpus");
+ /* Fail here to avoid kexec/kdump kernel boot hung */
+ if (!cpus_node) {
+ pr_err("No /cpus node found\n");
+ return -EINVAL;
+ }
+
+ /* Add all /cpus sub-nodes of device_type == "cpu" to FDT */
+ for_each_child_of_node(cpus_node, dn) {
+ /* Ignore device nodes that do not have a device_type property
+ * or device_type != "cpu".
+ */
+ device_type = of_get_property(dn, "device_type", NULL);
+ if (!device_type || strcmp(device_type, "cpu"))
+ continue;
+
+ cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
+ if (cpus_subnode_offset < 0) {
+ pr_err("Unable to add %s subnode: %s\n", dn->full_name,
+ fdt_strerror(cpus_subnode_offset));
+ ret = cpus_subnode_offset;
+ goto out;
+ }
+
+ ret = add_node_props(fdt, cpus_subnode_offset, dn);
+ if (ret < 0)
+ goto out;
+ }
+out:
+ of_node_put(cpus_node);
+ of_node_put(dn);
+ return ret;
+}
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c
index ef5c2d25ec39..9ac3266e4965 100644
--- a/arch/powerpc/kexec/crash.c
+++ b/arch/powerpc/kexec/crash.c
@@ -16,6 +16,8 @@
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/types.h>
+#include <linux/libfdt.h>
+#include <linux/memory.h>
#include <asm/processor.h>
#include <asm/machdep.h>
@@ -24,6 +26,7 @@
#include <asm/setjmp.h>
#include <asm/debug.h>
#include <asm/interrupt.h>
+#include <asm/kexec_ranges.h>
/*
* The primary CPU waits a while for all secondary CPUs to enter. This is to
@@ -392,3 +395,195 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
if (ppc_md.kexec_cpu_down)
ppc_md.kexec_cpu_down(1, 0);
}
+
+#ifdef CONFIG_CRASH_HOTPLUG
+#undef pr_fmt
+#define pr_fmt(fmt) "crash hp: " fmt
+
+/*
+ * Advertise preferred elfcorehdr size to userspace via
+ * /sys/kernel/crash_elfcorehdr_size sysfs interface.
+ */
+unsigned int arch_crash_get_elfcorehdr_size(void)
+{
+ unsigned long phdr_cnt;
+
+ /* A program header for possible CPUs + vmcoreinfo */
+ phdr_cnt = num_possible_cpus() + 1;
+ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+ phdr_cnt += CONFIG_CRASH_MAX_MEMORY_RANGES;
+
+ return sizeof(struct elfhdr) + (phdr_cnt * sizeof(Elf64_Phdr));
+}
+
+/**
+ * update_crash_elfcorehdr() - Recreate the elfcorehdr and replace it with old
+ * elfcorehdr in the kexec segment array.
+ * @image: the active struct kimage
+ * @mn: struct memory_notify data handler
+ */
+static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify *mn)
+{
+ int ret;
+ struct crash_mem *cmem = NULL;
+ struct kexec_segment *ksegment;
+ void *ptr, *mem, *elfbuf = NULL;
+ unsigned long elfsz, memsz, base_addr, size;
+
+ ksegment = &image->segment[image->elfcorehdr_index];
+ mem = (void *) ksegment->mem;
+ memsz = ksegment->memsz;
+
+ ret = get_crash_memory_ranges(&cmem);
+ if (ret) {
+ pr_err("Failed to get crash mem range\n");
+ return;
+ }
+
+ /*
+ * The hot unplugged memory is part of crash memory ranges,
+ * remove it here.
+ */
+ if (image->hp_action == KEXEC_CRASH_HP_REMOVE_MEMORY) {
+ base_addr = PFN_PHYS(mn->start_pfn);
+ size = mn->nr_pages * PAGE_SIZE;
+ ret = remove_mem_range(&cmem, base_addr, size);
+ if (ret) {
+ pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n");
+ goto out;
+ }
+ }
+
+ ret = crash_prepare_elf64_headers(cmem, false, &elfbuf, &elfsz);
+ if (ret) {
+ pr_err("Failed to prepare elf header\n");
+ goto out;
+ }
+
+ /*
+ * It is unlikely that kernel hit this because elfcorehdr kexec
+ * segment (memsz) is built with addition space to accommodate growing
+ * number of crash memory ranges while loading the kdump kernel. It is
+ * Just to avoid any unforeseen case.
+ */
+ if (elfsz > memsz) {
+ pr_err("Updated crash elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz);
+ goto out;
+ }
+
+ ptr = __va(mem);
+ if (ptr) {
+ /* Temporarily invalidate the crash image while it is replaced */
+ xchg(&kexec_crash_image, NULL);
+
+ /* Replace the old elfcorehdr with newly prepared elfcorehdr */
+ memcpy((void *)ptr, elfbuf, elfsz);
+
+ /* The crash image is now valid once again */
+ xchg(&kexec_crash_image, image);
+ }
+out:
+ kvfree(cmem);
+ kvfree(elfbuf);
+}
+
+/**
+ * get_fdt_index - Loop through the kexec segment array and find
+ * the index of the FDT segment.
+ * @image: a pointer to kexec_crash_image
+ *
+ * Returns the index of FDT segment in the kexec segment array
+ * if found; otherwise -1.
+ */
+static int get_fdt_index(struct kimage *image)
+{
+ void *ptr;
+ unsigned long mem;
+ int i, fdt_index = -1;
+
+ /* Find the FDT segment index in kexec segment array. */
+ for (i = 0; i < image->nr_segments; i++) {
+ mem = image->segment[i].mem;
+ ptr = __va(mem);
+
+ if (ptr && fdt_magic(ptr) == FDT_MAGIC) {
+ fdt_index = i;
+ break;
+ }
+ }
+
+ return fdt_index;
+}
+
+/**
+ * update_crash_fdt - updates the cpus node of the crash FDT.
+ *
+ * @image: a pointer to kexec_crash_image
+ */
+static void update_crash_fdt(struct kimage *image)
+{
+ void *fdt;
+ int fdt_index;
+
+ fdt_index = get_fdt_index(image);
+ if (fdt_index < 0) {
+ pr_err("Unable to locate FDT segment.\n");
+ return;
+ }
+
+ fdt = __va((void *)image->segment[fdt_index].mem);
+
+ /* Temporarily invalidate the crash image while it is replaced */
+ xchg(&kexec_crash_image, NULL);
+
+ /* update FDT to reflect changes in CPU resources */
+ if (update_cpus_node(fdt))
+ pr_err("Failed to update crash FDT");
+
+ /* The crash image is now valid once again */
+ xchg(&kexec_crash_image, image);
+}
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
+{
+#ifdef CONFIG_KEXEC_FILE
+ if (image->file_mode)
+ return 1;
+#endif
+ return kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT;
+}
+
+/**
+ * arch_crash_handle_hotplug_event - Handle crash CPU/Memory hotplug events to update the
+ * necessary kexec segments based on the hotplug event.
+ * @image: a pointer to kexec_crash_image
+ * @arg: struct memory_notify handler for memory hotplug case and NULL for CPU hotplug case.
+ *
+ * Update the kdump image based on the type of hotplug event, represented by image->hp_action.
+ * CPU add: Update the FDT segment to include the newly added CPU.
+ * CPU remove: No action is needed, with the assumption that it's okay to have offline CPUs
+ * part of the FDT.
+ * Memory add/remove: No action is taken as this is not yet supported.
+ */
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
+{
+ struct memory_notify *mn;
+
+ switch (image->hp_action) {
+ case KEXEC_CRASH_HP_REMOVE_CPU:
+ return;
+
+ case KEXEC_CRASH_HP_ADD_CPU:
+ update_crash_fdt(image);
+ break;
+
+ case KEXEC_CRASH_HP_REMOVE_MEMORY:
+ case KEXEC_CRASH_HP_ADD_MEMORY:
+ mn = (struct memory_notify *)arg;
+ update_crash_elfcorehdr(image, mn);
+ return;
+ default:
+ pr_warn_once("Unknown hotplug action\n");
+ }
+}
+#endif /* CONFIG_CRASH_HOTPLUG */
diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c
index 904016cf89ea..5d6d616404cf 100644
--- a/arch/powerpc/kexec/elf_64.c
+++ b/arch/powerpc/kexec/elf_64.c
@@ -23,6 +23,7 @@
#include <linux/of_fdt.h>
#include <linux/slab.h>
#include <linux/types.h>
+#include <asm/kexec_ranges.h>
static void *elf64_load(struct kimage *image, char *kernel_buf,
unsigned long kernel_len, char *initrd,
@@ -36,6 +37,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
const void *slave_code;
struct elfhdr ehdr;
char *modified_cmdline = NULL;
+ struct crash_mem *rmem = NULL;
struct kexec_elf_info elf_info;
struct kexec_buf kbuf = { .image = image, .buf_min = 0,
.buf_max = ppc64_rma_size };
@@ -47,7 +49,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
if (ret)
return ERR_PTR(ret);
- if (image->type == KEXEC_TYPE_CRASH) {
+ if (IS_ENABLED(CONFIG_CRASH_DUMP) && image->type == KEXEC_TYPE_CRASH) {
/* min & max buffer values for kdump case */
kbuf.buf_min = pbuf.buf_min = crashk_res.start;
kbuf.buf_max = pbuf.buf_max =
@@ -70,7 +72,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
kexec_dprintk("Loaded purgatory at 0x%lx\n", pbuf.mem);
/* Load additional segments needed for panic kernel */
- if (image->type == KEXEC_TYPE_CRASH) {
+ if (IS_ENABLED(CONFIG_CRASH_DUMP) && image->type == KEXEC_TYPE_CRASH) {
ret = load_crashdump_segments_ppc64(image, &kbuf);
if (ret) {
pr_err("Failed to load kdump kernel segments\n");
@@ -102,21 +104,25 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_load_addr);
}
+ ret = get_reserved_memory_ranges(&rmem);
+ if (ret)
+ goto out;
+
fdt = of_kexec_alloc_and_setup_fdt(image, initrd_load_addr,
initrd_len, cmdline,
- kexec_extra_fdt_size_ppc64(image));
+ kexec_extra_fdt_size_ppc64(image, rmem));
if (!fdt) {
pr_err("Error setting up the new device tree.\n");
ret = -EINVAL;
goto out;
}
- ret = setup_new_fdt_ppc64(image, fdt, initrd_load_addr,
- initrd_len, cmdline);
+ ret = setup_new_fdt_ppc64(image, fdt, rmem);
if (ret)
goto out_free_fdt;
- fdt_pack(fdt);
+ if (!IS_ENABLED(CONFIG_CRASH_HOTPLUG) || image->type != KEXEC_TYPE_CRASH)
+ fdt_pack(fdt);
kbuf.buffer = fdt;
kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt);
@@ -145,6 +151,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
out_free_fdt:
kvfree(fdt);
out:
+ kfree(rmem);
kfree(modified_cmdline);
kexec_free_elf_info(&elf_info);
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index 5b4c5cb23354..dc65c1391157 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -18,6 +18,7 @@
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
#include <linux/of.h>
+#include <linux/of_address.h>
#include <linux/memblock.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
@@ -30,6 +31,7 @@
#include <asm/iommu.h>
#include <asm/prom.h>
#include <asm/plpks.h>
+#include <asm/cputhreads.h>
struct umem_info {
__be64 *buf; /* data buffer for usable-memory property */
@@ -48,196 +50,6 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
};
/**
- * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
- * regions like opal/rtas, tce-table, initrd,
- * kernel, htab which should be avoided while
- * setting up kexec load segments.
- * @mem_ranges: Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
-{
- int ret;
-
- ret = add_tce_mem_ranges(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_initrd_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_htab_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_kernel_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_rtas_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_opal_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_reserved_mem_ranges(mem_ranges);
- if (ret)
- goto out;
-
- /* exclude memory ranges should be sorted for easy lookup */
- sort_memory_ranges(*mem_ranges, true);
-out:
- if (ret)
- pr_err("Failed to setup exclude memory ranges\n");
- return ret;
-}
-
-/**
- * get_usable_memory_ranges - Get usable memory ranges. This list includes
- * regions like crashkernel, opal/rtas & tce-table,
- * that kdump kernel could use.
- * @mem_ranges: Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_usable_memory_ranges(struct crash_mem **mem_ranges)
-{
- int ret;
-
- /*
- * Early boot failure observed on guests when low memory (first memory
- * block?) is not added to usable memory. So, add [0, crashk_res.end]
- * instead of [crashk_res.start, crashk_res.end] to workaround it.
- * Also, crashed kernel's memory must be added to reserve map to
- * avoid kdump kernel from using it.
- */
- ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1);
- if (ret)
- goto out;
-
- ret = add_rtas_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_opal_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_tce_mem_ranges(mem_ranges);
-out:
- if (ret)
- pr_err("Failed to setup usable memory ranges\n");
- return ret;
-}
-
-/**
- * get_crash_memory_ranges - Get crash memory ranges. This list includes
- * first/crashing kernel's memory regions that
- * would be exported via an elfcore.
- * @mem_ranges: Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_crash_memory_ranges(struct crash_mem **mem_ranges)
-{
- phys_addr_t base, end;
- struct crash_mem *tmem;
- u64 i;
- int ret;
-
- for_each_mem_range(i, &base, &end) {
- u64 size = end - base;
-
- /* Skip backup memory region, which needs a separate entry */
- if (base == BACKUP_SRC_START) {
- if (size > BACKUP_SRC_SIZE) {
- base = BACKUP_SRC_END + 1;
- size -= BACKUP_SRC_SIZE;
- } else
- continue;
- }
-
- ret = add_mem_range(mem_ranges, base, size);
- if (ret)
- goto out;
-
- /* Try merging adjacent ranges before reallocation attempt */
- if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges)
- sort_memory_ranges(*mem_ranges, true);
- }
-
- /* Reallocate memory ranges if there is no space to split ranges */
- tmem = *mem_ranges;
- if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
- tmem = realloc_mem_ranges(mem_ranges);
- if (!tmem)
- goto out;
- }
-
- /* Exclude crashkernel region */
- ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
- if (ret)
- goto out;
-
- /*
- * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
- * regions are exported to save their context at the time of
- * crash, they should actually be backed up just like the
- * first 64K bytes of memory.
- */
- ret = add_rtas_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_opal_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- /* create a separate program header for the backup region */
- ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE);
- if (ret)
- goto out;
-
- sort_memory_ranges(*mem_ranges, false);
-out:
- if (ret)
- pr_err("Failed to setup crash memory ranges\n");
- return ret;
-}
-
-/**
- * get_reserved_memory_ranges - Get reserve memory ranges. This list includes
- * memory regions that should be added to the
- * memory reserve map to ensure the region is
- * protected from any mischief.
- * @mem_ranges: Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_reserved_memory_ranges(struct crash_mem **mem_ranges)
-{
- int ret;
-
- ret = add_rtas_mem_range(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_tce_mem_ranges(mem_ranges);
- if (ret)
- goto out;
-
- ret = add_reserved_mem_ranges(mem_ranges);
-out:
- if (ret)
- pr_err("Failed to setup reserved memory ranges\n");
- return ret;
-}
-
-/**
* __locate_mem_hole_top_down - Looks top down for a large enough memory hole
* in the memory regions between buf_min & buf_max
* for the buffer. If found, sets kbuf->mem.
@@ -434,6 +246,7 @@ static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
return ret;
}
+#ifdef CONFIG_CRASH_DUMP
/**
* check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries
* @um_info: Usable memory buffer and ranges info.
@@ -564,11 +377,10 @@ static int kdump_setup_usable_lmb(struct drmem_lmb *lmb, const __be32 **usm,
static int add_usable_mem_property(void *fdt, struct device_node *dn,
struct umem_info *um_info)
{
- int n_mem_addr_cells, n_mem_size_cells, node;
+ int node;
char path[NODE_PATH_LEN];
- int i, len, ranges, ret;
- const __be32 *prop;
- u64 base, end;
+ int i, ret;
+ u64 base, size;
of_node_get(dn);
@@ -587,41 +399,30 @@ static int add_usable_mem_property(void *fdt, struct device_node *dn,
goto out;
}
- /* Get the address & size cells */
- n_mem_addr_cells = of_n_addr_cells(dn);
- n_mem_size_cells = of_n_size_cells(dn);
- kexec_dprintk("address cells: %d, size cells: %d\n", n_mem_addr_cells,
- n_mem_size_cells);
-
um_info->idx = 0;
if (!check_realloc_usable_mem(um_info, 2)) {
ret = -ENOMEM;
goto out;
}
- prop = of_get_property(dn, "reg", &len);
- if (!prop || len <= 0) {
- ret = 0;
- goto out;
- }
-
/*
* "reg" property represents sequence of (addr,size) tuples
* each representing a memory range.
*/
- ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells);
-
- for (i = 0; i < ranges; i++) {
- base = of_read_number(prop, n_mem_addr_cells);
- prop += n_mem_addr_cells;
- end = base + of_read_number(prop, n_mem_size_cells) - 1;
- prop += n_mem_size_cells;
+ for (i = 0; ; i++) {
+ ret = of_property_read_reg(dn, i, &base, &size);
+ if (ret)
+ break;
- ret = add_usable_mem(um_info, base, end);
+ ret = add_usable_mem(um_info, base, base + size - 1);
if (ret)
goto out;
}
+ // No reg or empty reg? Skip this node.
+ if (i == 0)
+ goto out;
+
/*
* No kdump kernel usable memory found in this memory node.
* Write (0,0) tuple in linux,usable-memory property for
@@ -783,6 +584,23 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr)
}
}
+static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem)
+{
+#if defined(CONFIG_CRASH_HOTPLUG) && defined(CONFIG_MEMORY_HOTPLUG)
+ unsigned int extra_sz = 0;
+
+ if (CONFIG_CRASH_MAX_MEMORY_RANGES > (unsigned int)PN_XNUM)
+ pr_warn("Number of Phdrs %u exceeds max\n", CONFIG_CRASH_MAX_MEMORY_RANGES);
+ else if (cmem->nr_ranges >= CONFIG_CRASH_MAX_MEMORY_RANGES)
+ pr_warn("Configured crash mem ranges may not be enough\n");
+ else
+ extra_sz = (CONFIG_CRASH_MAX_MEMORY_RANGES - cmem->nr_ranges) * sizeof(Elf64_Phdr);
+
+ return extra_sz;
+#endif
+ return 0;
+}
+
/**
* load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr
* segment needed to load kdump kernel.
@@ -814,7 +632,8 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
kbuf->buffer = headers;
kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
- kbuf->bufsz = kbuf->memsz = headers_sz;
+ kbuf->bufsz = headers_sz;
+ kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem);
kbuf->top_down = false;
ret = kexec_add_buffer(kbuf);
@@ -863,6 +682,7 @@ int load_crashdump_segments_ppc64(struct kimage *image,
return 0;
}
+#endif
/**
* setup_purgatory_ppc64 - initialize PPC64 specific purgatory's global
@@ -916,13 +736,18 @@ int setup_purgatory_ppc64(struct kimage *image, const void *slave_code,
if (dn) {
u64 val;
- of_property_read_u64(dn, "opal-base-address", &val);
+ ret = of_property_read_u64(dn, "opal-base-address", &val);
+ if (ret)
+ goto out;
+
ret = kexec_purgatory_get_set_symbol(image, "opal_base", &val,
sizeof(val), false);
if (ret)
goto out;
- of_property_read_u64(dn, "opal-entry-address", &val);
+ ret = of_property_read_u64(dn, "opal-entry-address", &val);
+ if (ret)
+ goto out;
ret = kexec_purgatory_get_set_symbol(image, "opal_entry", &val,
sizeof(val), false);
}
@@ -972,26 +797,16 @@ static unsigned int cpu_node_size(void)
return size;
}
-/**
- * kexec_extra_fdt_size_ppc64 - Return the estimated additional size needed to
- * setup FDT for kexec/kdump kernel.
- * @image: kexec image being loaded.
- *
- * Returns the estimated extra size needed for kexec/kdump kernel FDT.
- */
-unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
+static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image, unsigned int cpu_nodes)
{
- unsigned int cpu_nodes, extra_size = 0;
- struct device_node *dn;
+ unsigned int extra_size = 0;
u64 usm_entries;
+#ifdef CONFIG_CRASH_HOTPLUG
+ unsigned int possible_cpu_nodes;
+#endif
- // Budget some space for the password blob. There's already extra space
- // for the key name
- if (plpks_is_available())
- extra_size += (unsigned int)plpks_get_passwordlen();
-
- if (image->type != KEXEC_TYPE_CRASH)
- return extra_size;
+ if (!IS_ENABLED(CONFIG_CRASH_DUMP) || image->type != KEXEC_TYPE_CRASH)
+ return 0;
/*
* For kdump kernel, account for linux,usable-memory and
@@ -1004,106 +819,53 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
extra_size += (unsigned int)(usm_entries * sizeof(u64));
}
+#ifdef CONFIG_CRASH_HOTPLUG
/*
- * Get the number of CPU nodes in the current DT. This allows to
- * reserve places for CPU nodes added since the boot time.
+ * Make sure enough space is reserved to accommodate possible CPU nodes
+ * in the crash FDT. This allows packing possible CPU nodes which are
+ * not yet present in the system without regenerating the entire FDT.
*/
- cpu_nodes = 0;
- for_each_node_by_type(dn, "cpu") {
- cpu_nodes++;
+ if (image->type == KEXEC_TYPE_CRASH) {
+ possible_cpu_nodes = num_possible_cpus() / threads_per_core;
+ if (possible_cpu_nodes > cpu_nodes)
+ extra_size += (possible_cpu_nodes - cpu_nodes) * cpu_node_size();
}
-
- if (cpu_nodes > boot_cpu_node_count)
- extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size();
+#endif
return extra_size;
}
/**
- * add_node_props - Reads node properties from device node structure and add
- * them to fdt.
- * @fdt: Flattened device tree of the kernel
- * @node_offset: offset of the node to add a property at
- * @dn: device node pointer
- *
- * Returns 0 on success, negative errno on error.
- */
-static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
-{
- int ret = 0;
- struct property *pp;
-
- if (!dn)
- return -EINVAL;
-
- for_each_property_of_node(dn, pp) {
- ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
- if (ret < 0) {
- pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
- return ret;
- }
- }
- return ret;
-}
-
-/**
- * update_cpus_node - Update cpus node of flattened device tree using of_root
- * device node.
- * @fdt: Flattened device tree of the kernel.
+ * kexec_extra_fdt_size_ppc64 - Return the estimated additional size needed to
+ * setup FDT for kexec/kdump kernel.
+ * @image: kexec image being loaded.
*
- * Returns 0 on success, negative errno on error.
+ * Returns the estimated extra size needed for kexec/kdump kernel FDT.
*/
-static int update_cpus_node(void *fdt)
+unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image, struct crash_mem *rmem)
{
- struct device_node *cpus_node, *dn;
- int cpus_offset, cpus_subnode_offset, ret = 0;
-
- cpus_offset = fdt_path_offset(fdt, "/cpus");
- if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
- pr_err("Malformed device tree: error reading /cpus node: %s\n",
- fdt_strerror(cpus_offset));
- return cpus_offset;
- }
+ struct device_node *dn;
+ unsigned int cpu_nodes = 0, extra_size = 0;
- if (cpus_offset > 0) {
- ret = fdt_del_node(fdt, cpus_offset);
- if (ret < 0) {
- pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret));
- return -EINVAL;
- }
- }
+ // Budget some space for the password blob. There's already extra space
+ // for the key name
+ if (plpks_is_available())
+ extra_size += (unsigned int)plpks_get_passwordlen();
- /* Add cpus node to fdt */
- cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus");
- if (cpus_offset < 0) {
- pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset));
- return -EINVAL;
+ /* Get the number of CPU nodes in the current device tree */
+ for_each_node_by_type(dn, "cpu") {
+ cpu_nodes++;
}
- /* Add cpus node properties */
- cpus_node = of_find_node_by_path("/cpus");
- ret = add_node_props(fdt, cpus_offset, cpus_node);
- of_node_put(cpus_node);
- if (ret < 0)
- return ret;
+ /* Consider extra space for CPU nodes added since the boot time */
+ if (cpu_nodes > boot_cpu_node_count)
+ extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size();
- /* Loop through all subnodes of cpus and add them to fdt */
- for_each_node_by_type(dn, "cpu") {
- cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
- if (cpus_subnode_offset < 0) {
- pr_err("Unable to add %s subnode: %s\n", dn->full_name,
- fdt_strerror(cpus_subnode_offset));
- ret = cpus_subnode_offset;
- goto out;
- }
+ /* Consider extra space for reserved memory ranges if any */
+ if (rmem->nr_ranges > 0)
+ extra_size += sizeof(struct fdt_reserve_entry) * rmem->nr_ranges;
- ret = add_node_props(fdt, cpus_subnode_offset, dn);
- if (ret < 0)
- goto out;
- }
-out:
- of_node_put(dn);
- return ret;
+ return extra_size + kdump_extra_fdt_size_ppc64(image, cpu_nodes);
}
static int copy_property(void *fdt, int node_offset, const struct device_node *dn,
@@ -1157,20 +919,16 @@ static int update_pci_dma_nodes(void *fdt, const char *dmapropname)
* being loaded.
* @image: kexec image being loaded.
* @fdt: Flattened device tree for the next kernel.
- * @initrd_load_addr: Address where the next initrd will be loaded.
- * @initrd_len: Size of the next initrd, or 0 if there will be none.
- * @cmdline: Command line for the next kernel, or NULL if there will
- * be none.
+ * @rmem: Reserved memory ranges.
*
* Returns 0 on success, negative errno on error.
*/
-int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
- unsigned long initrd_load_addr,
- unsigned long initrd_len, const char *cmdline)
+int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem *rmem)
{
- struct crash_mem *umem = NULL, *rmem = NULL;
+ struct crash_mem *umem = NULL;
int i, nr_ranges, ret;
+#ifdef CONFIG_CRASH_DUMP
/*
* Restrict memory usage for kdump kernel by setting up
* usable memory ranges and memory reserve map.
@@ -1207,6 +965,7 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
goto out;
}
}
+#endif
/* Update cpus nodes information to account hotplug CPUs. */
ret = update_cpus_node(fdt);
@@ -1222,10 +981,6 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
goto out;
/* Update memory reserve map */
- ret = get_reserved_memory_ranges(&rmem);
- if (ret)
- goto out;
-
nr_ranges = rmem ? rmem->nr_ranges : 0;
for (i = 0; i < nr_ranges; i++) {
u64 base, size;
@@ -1245,7 +1000,6 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
ret = plpks_populate_fdt(fdt);
out:
- kfree(rmem);
kfree(umem);
return ret;
}
@@ -1278,7 +1032,7 @@ int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
buf_min = kbuf->buf_min;
buf_max = kbuf->buf_max;
/* Segments for kdump kernel should be within crashkernel region */
- if (kbuf->image->type == KEXEC_TYPE_CRASH) {
+ if (IS_ENABLED(CONFIG_CRASH_DUMP) && kbuf->image->type == KEXEC_TYPE_CRASH) {
buf_min = (buf_min < crashk_res.start ?
crashk_res.start : buf_min);
buf_max = (buf_max > crashk_res.end ?
diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c
index fb3e12f15214..3702b0bdab14 100644
--- a/arch/powerpc/kexec/ranges.c
+++ b/arch/powerpc/kexec/ranges.c
@@ -20,9 +20,13 @@
#include <linux/kexec.h>
#include <linux/of.h>
#include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/crash_core.h>
#include <asm/sections.h>
#include <asm/kexec_ranges.h>
+#include <asm/crashdump-ppc64.h>
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
/**
* get_max_nr_ranges - Get the max no. of ranges crash_mem structure
* could hold, given the size allocated for it.
@@ -234,13 +238,16 @@ int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
return __add_mem_range(mem_ranges, base, size);
}
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
+
+#ifdef CONFIG_KEXEC_FILE
/**
* add_tce_mem_ranges - Adds tce-table range to the given memory ranges list.
* @mem_ranges: Range list to add the memory range(s) to.
*
* Returns 0 on success, negative errno on error.
*/
-int add_tce_mem_ranges(struct crash_mem **mem_ranges)
+static int add_tce_mem_ranges(struct crash_mem **mem_ranges)
{
struct device_node *dn = NULL;
int ret = 0;
@@ -279,7 +286,7 @@ int add_tce_mem_ranges(struct crash_mem **mem_ranges)
*
* Returns 0 on success, negative errno on error.
*/
-int add_initrd_mem_range(struct crash_mem **mem_ranges)
+static int add_initrd_mem_range(struct crash_mem **mem_ranges)
{
u64 base, end;
int ret;
@@ -296,7 +303,6 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges)
return ret;
}
-#ifdef CONFIG_PPC_64S_HASH_MMU
/**
* add_htab_mem_range - Adds htab range to the given memory ranges list,
* if it exists
@@ -304,14 +310,18 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges)
*
* Returns 0 on success, negative errno on error.
*/
-int add_htab_mem_range(struct crash_mem **mem_ranges)
+static int add_htab_mem_range(struct crash_mem **mem_ranges)
{
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
if (!htab_address)
return 0;
return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes);
-}
+#else
+ return 0;
#endif
+}
/**
* add_kernel_mem_range - Adds kernel text region to the given
@@ -320,18 +330,20 @@ int add_htab_mem_range(struct crash_mem **mem_ranges)
*
* Returns 0 on success, negative errno on error.
*/
-int add_kernel_mem_range(struct crash_mem **mem_ranges)
+static int add_kernel_mem_range(struct crash_mem **mem_ranges)
{
return add_mem_range(mem_ranges, 0, __pa(_end));
}
+#endif /* CONFIG_KEXEC_FILE */
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
/**
* add_rtas_mem_range - Adds RTAS region to the given memory ranges list.
* @mem_ranges: Range list to add the memory range to.
*
* Returns 0 on success, negative errno on error.
*/
-int add_rtas_mem_range(struct crash_mem **mem_ranges)
+static int add_rtas_mem_range(struct crash_mem **mem_ranges)
{
struct device_node *dn;
u32 base, size;
@@ -356,7 +368,7 @@ int add_rtas_mem_range(struct crash_mem **mem_ranges)
*
* Returns 0 on success, negative errno on error.
*/
-int add_opal_mem_range(struct crash_mem **mem_ranges)
+static int add_opal_mem_range(struct crash_mem **mem_ranges)
{
struct device_node *dn;
u64 base, size;
@@ -374,7 +386,9 @@ int add_opal_mem_range(struct crash_mem **mem_ranges)
of_node_put(dn);
return ret;
}
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
+#ifdef CONFIG_KEXEC_FILE
/**
* add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w
* to the given memory ranges list.
@@ -382,17 +396,19 @@ int add_opal_mem_range(struct crash_mem **mem_ranges)
*
* Returns 0 on success, negative errno on error.
*/
-int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
+static int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
{
int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0;
+ struct device_node *root = of_find_node_by_path("/");
const __be32 *prop;
- prop = of_get_property(of_root, "reserved-ranges", &len);
+ prop = of_get_property(root, "reserved-ranges", &len);
+ n_mem_addr_cells = of_n_addr_cells(root);
+ n_mem_size_cells = of_n_size_cells(root);
+ of_node_put(root);
if (!prop)
return 0;
- n_mem_addr_cells = of_n_addr_cells(of_root);
- n_mem_size_cells = of_n_size_cells(of_root);
cells = n_mem_addr_cells + n_mem_size_cells;
/* Each reserved range is an (address,size) pair */
@@ -410,3 +426,283 @@ int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
return ret;
}
+
+/**
+ * get_reserved_memory_ranges - Get reserve memory ranges. This list includes
+ * memory regions that should be added to the
+ * memory reserve map to ensure the region is
+ * protected from any mischief.
+ * @mem_ranges: Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_reserved_memory_ranges(struct crash_mem **mem_ranges)
+{
+ int ret;
+
+ ret = add_rtas_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_tce_mem_ranges(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_reserved_mem_ranges(mem_ranges);
+out:
+ if (ret)
+ pr_err("Failed to setup reserved memory ranges\n");
+ return ret;
+}
+
+/**
+ * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
+ * regions like opal/rtas, tce-table, initrd,
+ * kernel, htab which should be avoided while
+ * setting up kexec load segments.
+ * @mem_ranges: Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
+{
+ int ret;
+
+ ret = add_tce_mem_ranges(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_initrd_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_htab_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_kernel_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_rtas_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_opal_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_reserved_mem_ranges(mem_ranges);
+ if (ret)
+ goto out;
+
+ /* exclude memory ranges should be sorted for easy lookup */
+ sort_memory_ranges(*mem_ranges, true);
+out:
+ if (ret)
+ pr_err("Failed to setup exclude memory ranges\n");
+ return ret;
+}
+
+#ifdef CONFIG_CRASH_DUMP
+/**
+ * get_usable_memory_ranges - Get usable memory ranges. This list includes
+ * regions like crashkernel, opal/rtas & tce-table,
+ * that kdump kernel could use.
+ * @mem_ranges: Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_usable_memory_ranges(struct crash_mem **mem_ranges)
+{
+ int ret;
+
+ /*
+ * Early boot failure observed on guests when low memory (first memory
+ * block?) is not added to usable memory. So, add [0, crashk_res.end]
+ * instead of [crashk_res.start, crashk_res.end] to workaround it.
+ * Also, crashed kernel's memory must be added to reserve map to
+ * avoid kdump kernel from using it.
+ */
+ ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1);
+ if (ret)
+ goto out;
+
+ ret = add_rtas_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_opal_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_tce_mem_ranges(mem_ranges);
+out:
+ if (ret)
+ pr_err("Failed to setup usable memory ranges\n");
+ return ret;
+}
+#endif /* CONFIG_CRASH_DUMP */
+#endif /* CONFIG_KEXEC_FILE */
+
+#ifdef CONFIG_CRASH_DUMP
+/**
+ * get_crash_memory_ranges - Get crash memory ranges. This list includes
+ * first/crashing kernel's memory regions that
+ * would be exported via an elfcore.
+ * @mem_ranges: Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_crash_memory_ranges(struct crash_mem **mem_ranges)
+{
+ phys_addr_t base, end;
+ struct crash_mem *tmem;
+ u64 i;
+ int ret;
+
+ for_each_mem_range(i, &base, &end) {
+ u64 size = end - base;
+
+ /* Skip backup memory region, which needs a separate entry */
+ if (base == BACKUP_SRC_START) {
+ if (size > BACKUP_SRC_SIZE) {
+ base = BACKUP_SRC_END + 1;
+ size -= BACKUP_SRC_SIZE;
+ } else
+ continue;
+ }
+
+ ret = add_mem_range(mem_ranges, base, size);
+ if (ret)
+ goto out;
+
+ /* Try merging adjacent ranges before reallocation attempt */
+ if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges)
+ sort_memory_ranges(*mem_ranges, true);
+ }
+
+ /* Reallocate memory ranges if there is no space to split ranges */
+ tmem = *mem_ranges;
+ if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
+ tmem = realloc_mem_ranges(mem_ranges);
+ if (!tmem)
+ goto out;
+ }
+
+ /* Exclude crashkernel region */
+ ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
+ if (ret)
+ goto out;
+
+ /*
+ * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
+ * regions are exported to save their context at the time of
+ * crash, they should actually be backed up just like the
+ * first 64K bytes of memory.
+ */
+ ret = add_rtas_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ ret = add_opal_mem_range(mem_ranges);
+ if (ret)
+ goto out;
+
+ /* create a separate program header for the backup region */
+ ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE);
+ if (ret)
+ goto out;
+
+ sort_memory_ranges(*mem_ranges, false);
+out:
+ if (ret)
+ pr_err("Failed to setup crash memory ranges\n");
+ return ret;
+}
+
+/**
+ * remove_mem_range - Removes the given memory range from the range list.
+ * @mem_ranges: Range list to remove the memory range to.
+ * @base: Base address of the range to remove.
+ * @size: Size of the memory range to remove.
+ *
+ * (Re)allocates memory, if needed.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
+{
+ u64 end;
+ int ret = 0;
+ unsigned int i;
+ u64 mstart, mend;
+ struct crash_mem *mem_rngs = *mem_ranges;
+
+ if (!size)
+ return 0;
+
+ /*
+ * Memory range are stored as start and end address, use
+ * the same format to do remove operation.
+ */
+ end = base + size - 1;
+
+ for (i = 0; i < mem_rngs->nr_ranges; i++) {
+ mstart = mem_rngs->ranges[i].start;
+ mend = mem_rngs->ranges[i].end;
+
+ /*
+ * Memory range to remove is not part of this range entry
+ * in the memory range list
+ */
+ if (!(base >= mstart && end <= mend))
+ continue;
+
+ /*
+ * Memory range to remove is equivalent to this entry in the
+ * memory range list. Remove the range entry from the list.
+ */
+ if (base == mstart && end == mend) {
+ for (; i < mem_rngs->nr_ranges - 1; i++) {
+ mem_rngs->ranges[i].start = mem_rngs->ranges[i+1].start;
+ mem_rngs->ranges[i].end = mem_rngs->ranges[i+1].end;
+ }
+ mem_rngs->nr_ranges--;
+ goto out;
+ }
+ /*
+ * Start address of the memory range to remove and the
+ * current memory range entry in the list is same. Just
+ * move the start address of the current memory range
+ * entry in the list to end + 1.
+ */
+ else if (base == mstart) {
+ mem_rngs->ranges[i].start = end + 1;
+ goto out;
+ }
+ /*
+ * End address of the memory range to remove and the
+ * current memory range entry in the list is same.
+ * Just move the end address of the current memory
+ * range entry in the list to base - 1.
+ */
+ else if (end == mend) {
+ mem_rngs->ranges[i].end = base - 1;
+ goto out;
+ }
+ /*
+ * Memory range to remove is not at the edge of current
+ * memory range entry. Split the current memory entry into
+ * two half.
+ */
+ else {
+ mem_rngs->ranges[i].end = base - 1;
+ size = mem_rngs->ranges[i].end - end;
+ ret = add_mem_range(mem_ranges, end + 1, size);
+ }
+ }
+out:
+ return ret;
+}
+#endif /* CONFIG_CRASH_DUMP */
diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S
index d9f0dd9b34ff..104c9911f406 100644
--- a/arch/powerpc/kexec/relocate_32.S
+++ b/arch/powerpc/kexec/relocate_32.S
@@ -8,6 +8,7 @@
* Author: Suzuki Poulose <suzuki@in.ibm.com>
*/
+#include <linux/objtool.h>
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
@@ -349,6 +350,7 @@ write_utlb:
cmpwi r10, PPC47x_TLB0_4K
bne 0f
li r10, 0x1000 /* r10 = 4k */
+ ANNOTATE_INTRA_FUNCTION_CALL
bl 1f
0:
diff --git a/arch/powerpc/kexec/vmcore_info.c b/arch/powerpc/kexec/vmcore_info.c
new file mode 100644
index 000000000000..2b65d2adca5e
--- /dev/null
+++ b/arch/powerpc/kexec/vmcore_info.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/vmcore_info.h>
+#include <asm/pgalloc.h>
+
+void arch_crash_save_vmcoreinfo(void)
+{
+
+#ifdef CONFIG_NUMA
+ VMCOREINFO_SYMBOL(node_data);
+ VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
+#endif
+#ifndef CONFIG_NUMA
+ VMCOREINFO_SYMBOL(contig_page_data);
+#endif
+#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP)
+ VMCOREINFO_SYMBOL(vmemmap_list);
+ VMCOREINFO_SYMBOL(mmu_vmemmap_psize);
+ VMCOREINFO_SYMBOL(mmu_psize_defs);
+ VMCOREINFO_STRUCT_SIZE(vmemmap_backing);
+ VMCOREINFO_OFFSET(vmemmap_backing, list);
+ VMCOREINFO_OFFSET(vmemmap_backing, phys);
+ VMCOREINFO_OFFSET(vmemmap_backing, virt_addr);
+ VMCOREINFO_STRUCT_SIZE(mmu_psize_def);
+ VMCOREINFO_OFFSET(mmu_psize_def, shift);
+#endif
+ VMCOREINFO_SYMBOL(cur_cpu_spec);
+ VMCOREINFO_OFFSET(cpu_spec, cpu_features);
+ VMCOREINFO_OFFSET(cpu_spec, mmu_features);
+ vmcoreinfo_append_str("NUMBER(RADIX_MMU)=%d\n", early_radix_enabled());
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+}
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 074263429faf..dbfdc126bf14 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -22,7 +22,6 @@ config KVM
select KVM_COMMON
select HAVE_KVM_VCPU_ASYNC_IOCTL
select KVM_VFIO
- select IRQ_BYPASS_MANAGER
select HAVE_KVM_IRQ_BYPASS
config KVM_BOOK3S_HANDLER
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 8acec144120e..d79c5d1098c0 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -360,10 +360,6 @@ static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
break;
}
-#if 0
- printk(KERN_INFO "Deliver interrupt 0x%x? %x\n", vec, deliver);
-#endif
-
if (deliver)
kvmppc_inject_interrupt(vcpu, vec, 0);
@@ -426,7 +422,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter);
kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing,
- bool *writable)
+ bool *writable, struct page **page)
{
ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM;
gfn_t gfn = gpa >> PAGE_SHIFT;
@@ -441,13 +437,14 @@ kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing,
kvm_pfn_t pfn;
pfn = (kvm_pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT;
- get_page(pfn_to_page(pfn));
+ *page = pfn_to_page(pfn);
+ get_page(*page);
if (writable)
*writable = true;
return pfn;
}
- return gfn_to_pfn_prot(vcpu->kvm, gfn, writing, writable);
+ return kvm_faultin_pfn(vcpu, gfn, writing, writable, page);
}
EXPORT_SYMBOL_GPL(kvmppc_gpa_to_pfn);
@@ -899,11 +896,6 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
return kvm->arch.kvm_ops->test_age_gfn(kvm, range);
}
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
- return kvm->arch.kvm_ops->set_spte_gfn(kvm, range);
-}
-
int kvmppc_core_init_vm(struct kvm *kvm)
{
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 58391b4b32ed..4aa2ab89afbc 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -12,7 +12,6 @@ extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
extern bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range);
extern bool kvm_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
extern bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
-extern bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
extern int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu);
extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 4b3a8d80cfa3..5b7212edbb13 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -130,6 +130,7 @@ extern char etext[];
int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
bool iswrite)
{
+ struct page *page;
kvm_pfn_t hpaddr;
u64 vpn;
u64 vsid;
@@ -145,7 +146,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
bool writable;
/* Get host physical address for gpa */
- hpaddr = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable);
+ hpaddr = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable, &page);
if (is_error_noslot_pfn(hpaddr)) {
printk(KERN_INFO "Couldn't get guest page for gpa %lx!\n",
orig_pte->raddr);
@@ -232,7 +233,7 @@ next_pteg:
pte = kvmppc_mmu_hpte_cache_next(vcpu);
if (!pte) {
- kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
+ kvm_release_page_unused(page);
r = -EAGAIN;
goto out;
}
@@ -250,7 +251,7 @@ next_pteg:
kvmppc_mmu_hpte_cache_map(vcpu, pte);
- kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
+ kvm_release_page_clean(page);
out:
return r;
}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index bc6a381b5346..be20aee6fd7d 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -88,13 +88,14 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
struct hpte_cache *cpte;
unsigned long gfn = orig_pte->raddr >> PAGE_SHIFT;
unsigned long pfn;
+ struct page *page;
/* used to check for invalidations in progress */
mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
/* Get host physical address for gpa */
- pfn = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable);
+ pfn = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable, &page);
if (is_error_noslot_pfn(pfn)) {
printk(KERN_INFO "Couldn't get guest page for gpa %lx!\n",
orig_pte->raddr);
@@ -121,13 +122,10 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M);
- kvm_set_pfn_accessed(pfn);
if (!orig_pte->may_write || !writable)
rflags |= PP_RXRX;
- else {
+ else
mark_page_dirty(vcpu->kvm, gfn);
- kvm_set_pfn_dirty(pfn);
- }
if (!orig_pte->may_execute)
rflags |= HPTE_R_N;
@@ -202,8 +200,10 @@ map_again:
}
out_unlock:
+ /* FIXME: Don't unconditionally pass unused=false. */
+ kvm_release_faultin_page(kvm, page, false,
+ orig_pte->may_write && writable);
spin_unlock(&kvm->mmu_lock);
- kvm_release_pfn_clean(pfn);
if (cpte)
kvmppc_mmu_hpte_cache_free(cpte);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 2b1f0cdd8c18..f305395cf26e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -603,27 +603,10 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
write_ok = writing;
hva = gfn_to_hva_memslot(memslot, gfn);
- /*
- * Do a fast check first, since __gfn_to_pfn_memslot doesn't
- * do it with !atomic && !async, which is how we call it.
- * We always ask for write permission since the common case
- * is that the page is writable.
- */
- if (get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
- write_ok = true;
- } else {
- /* Call KVM generic code to do the slow-path check */
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
- writing, &write_ok, NULL);
- if (is_error_noslot_pfn(pfn))
- return -EFAULT;
- page = NULL;
- if (pfn_valid(pfn)) {
- page = pfn_to_page(pfn);
- if (PageReserved(page))
- page = NULL;
- }
- }
+ pfn = __kvm_faultin_pfn(memslot, gfn, writing ? FOLL_WRITE : 0,
+ &write_ok, &page);
+ if (is_error_noslot_pfn(pfn))
+ return -EFAULT;
/*
* Read the PTE from the process' radix tree and use that
@@ -1010,18 +993,6 @@ bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
return kvm_test_age_rmapp(kvm, range->slot, range->start);
}
-bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
-{
- WARN_ON(range->start + 1 != range->end);
-
- if (kvm_is_radix(kvm))
- kvm_unmap_radix(kvm, range->slot, range->start);
- else
- kvm_unmap_rmapp(kvm, range->slot, range->start);
-
- return false;
-}
-
static int vcpus_running(struct kvm *kvm)
{
return atomic_read(&kvm->arch.vcpus_running) != 0;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 4a1abb9f7c05..b3e6e73d6a08 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -503,7 +503,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
for (im = 0; im < PTRS_PER_PMD; ++im, ++p) {
if (!pmd_present(*p))
continue;
- if (pmd_is_leaf(*p)) {
+ if (pmd_leaf(*p)) {
if (full) {
pmd_clear(p);
} else {
@@ -532,7 +532,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) {
if (!pud_present(*p))
continue;
- if (pud_is_leaf(*p)) {
+ if (pud_leaf(*p)) {
pud_clear(p);
} else {
pmd_t *pmd;
@@ -635,12 +635,12 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
new_pud = pud_alloc_one(kvm->mm, gpa);
pmd = NULL;
- if (pud && pud_present(*pud) && !pud_is_leaf(*pud))
+ if (pud && pud_present(*pud) && !pud_leaf(*pud))
pmd = pmd_offset(pud, gpa);
else if (level <= 1)
new_pmd = kvmppc_pmd_alloc();
- if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd)))
+ if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_leaf(*pmd)))
new_ptep = kvmppc_pte_alloc();
/* Check if we might have been invalidated; let the guest retry if so */
@@ -658,7 +658,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
new_pud = NULL;
}
pud = pud_offset(p4d, gpa);
- if (pud_is_leaf(*pud)) {
+ if (pud_leaf(*pud)) {
unsigned long hgpa = gpa & PUD_MASK;
/* Check if we raced and someone else has set the same thing */
@@ -709,7 +709,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
new_pmd = NULL;
}
pmd = pmd_offset(pud, gpa);
- if (pmd_is_leaf(*pmd)) {
+ if (pmd_leaf(*pmd)) {
unsigned long lgpa = gpa & PMD_MASK;
/* Check if we raced and someone else has set the same thing */
@@ -821,7 +821,7 @@ bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing,
int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
unsigned long gpa,
struct kvm_memory_slot *memslot,
- bool writing, bool kvm_ro,
+ bool writing,
pte_t *inserted_pte, unsigned int *levelp)
{
struct kvm *kvm = vcpu->kvm;
@@ -829,40 +829,21 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
unsigned long mmu_seq;
unsigned long hva, gfn = gpa >> PAGE_SHIFT;
bool upgrade_write = false;
- bool *upgrade_p = &upgrade_write;
pte_t pte, *ptep;
unsigned int shift, level;
int ret;
bool large_enable;
+ kvm_pfn_t pfn;
/* used to check for invalidations in progress */
mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
- /*
- * Do a fast check first, since __gfn_to_pfn_memslot doesn't
- * do it with !atomic && !async, which is how we call it.
- * We always ask for write permission since the common case
- * is that the page is writable.
- */
hva = gfn_to_hva_memslot(memslot, gfn);
- if (!kvm_ro && get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
- upgrade_write = true;
- } else {
- unsigned long pfn;
-
- /* Call KVM generic code to do the slow-path check */
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
- writing, upgrade_p, NULL);
- if (is_error_noslot_pfn(pfn))
- return -EFAULT;
- page = NULL;
- if (pfn_valid(pfn)) {
- page = pfn_to_page(pfn);
- if (PageReserved(page))
- page = NULL;
- }
- }
+ pfn = __kvm_faultin_pfn(memslot, gfn, writing ? FOLL_WRITE : 0,
+ &upgrade_write, &page);
+ if (is_error_noslot_pfn(pfn))
+ return -EFAULT;
/*
* Read the PTE from the process' radix tree and use that
@@ -950,7 +931,6 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
struct kvm_memory_slot *memslot;
long ret;
bool writing = !!(dsisr & DSISR_ISSTORE);
- bool kvm_ro = false;
/* Check for unusual errors */
if (dsisr & DSISR_UNSUPP_MMU) {
@@ -1003,7 +983,6 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
ea, DSISR_ISSTORE | DSISR_PROTFAULT);
return RESUME_GUEST;
}
- kvm_ro = true;
}
/* Failed to set the reference/change bits */
@@ -1021,7 +1000,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
/* Try to insert a pte */
ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot, writing,
- kvm_ro, NULL, NULL);
+ NULL, NULL);
if (ret == 0 || ret == -EAGAIN)
ret = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index b569ebaa590e..742aa58a7c7e 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -115,23 +115,20 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
struct iommu_table_group *table_group;
long i;
struct kvmppc_spapr_tce_iommu_table *stit;
- struct fd f;
+ CLASS(fd, f)(tablefd);
- f = fdget(tablefd);
- if (!f.file)
+ if (fd_empty(f))
return -EBADF;
rcu_read_lock();
list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
- if (stt == f.file->private_data) {
+ if (stt == fd_file(f)->private_data) {
found = true;
break;
}
}
rcu_read_unlock();
- fdput(f);
-
if (!found)
return -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 5bbfb2eed127..de126d153328 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -714,7 +714,7 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
case SPRN_HID1:
to_book3s(vcpu)->hid[1] = spr_val;
break;
- case SPRN_HID2:
+ case SPRN_HID2_750FX:
to_book3s(vcpu)->hid[2] = spr_val;
break;
case SPRN_HID2_GEKKO:
@@ -900,7 +900,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
case SPRN_HID1:
*spr_val = to_book3s(vcpu)->hid[1];
break;
- case SPRN_HID2:
+ case SPRN_HID2_750FX:
case SPRN_HID2_GEKKO:
*spr_val = to_book3s(vcpu)->hid[2];
break;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0b921704da45..86bff159c51e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -400,7 +400,10 @@ static inline unsigned long map_pcr_to_cap(unsigned long pcr)
cap = H_GUEST_CAP_POWER9;
break;
case PCR_ARCH_31:
- cap = H_GUEST_CAP_POWER10;
+ if (cpu_has_feature(CPU_FTR_P11_PVR))
+ cap = H_GUEST_CAP_POWER11;
+ else
+ cap = H_GUEST_CAP_POWER10;
break;
default:
break;
@@ -415,7 +418,7 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
struct kvmppc_vcore *vc = vcpu->arch.vcore;
/* We can (emulate) our own architecture version and anything older */
- if (cpu_has_feature(CPU_FTR_ARCH_31))
+ if (cpu_has_feature(CPU_FTR_P11_PVR) || cpu_has_feature(CPU_FTR_ARCH_31))
host_pcr_bit = PCR_ARCH_31;
else if (cpu_has_feature(CPU_FTR_ARCH_300))
host_pcr_bit = PCR_ARCH_300;
@@ -444,6 +447,7 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
guest_pcr_bit = PCR_ARCH_300;
break;
case PVR_ARCH_31:
+ case PVR_ARCH_31_P11:
guest_pcr_bit = PCR_ARCH_31;
break;
default:
@@ -1921,14 +1925,22 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
r = EMULATE_FAIL;
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
- if (cause == FSCR_MSGP_LG)
+ switch (cause) {
+ case FSCR_MSGP_LG:
r = kvmppc_emulate_doorbell_instr(vcpu);
- if (cause == FSCR_PM_LG)
+ break;
+ case FSCR_PM_LG:
r = kvmppc_pmu_unavailable(vcpu);
- if (cause == FSCR_EBB_LG)
+ break;
+ case FSCR_EBB_LG:
r = kvmppc_ebb_unavailable(vcpu);
- if (cause == FSCR_TM_LG)
+ break;
+ case FSCR_TM_LG:
r = kvmppc_tm_unavailable(vcpu);
+ break;
+ default:
+ break;
+ }
}
if (r == EMULATE_FAIL) {
kvmppc_core_queue_program(vcpu, SRR1_PROGILL |
@@ -2051,36 +2063,9 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
fallthrough; /* go to facility unavailable handler */
#endif
- case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: {
- u64 cause = vcpu->arch.hfscr >> 56;
-
- /*
- * Only pass HFU interrupts to the L1 if the facility is
- * permitted but disabled by the L1's HFSCR, otherwise
- * the interrupt does not make sense to the L1 so turn
- * it into a HEAI.
- */
- if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) ||
- (vcpu->arch.nested_hfscr & (1UL << cause))) {
- ppc_inst_t pinst;
- vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
-
- /*
- * If the fetch failed, return to guest and
- * try executing it again.
- */
- r = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst);
- vcpu->arch.emul_inst = ppc_inst_val(pinst);
- if (r != EMULATE_DONE)
- r = RESUME_GUEST;
- else
- r = RESUME_HOST;
- } else {
- r = RESUME_HOST;
- }
-
+ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+ r = RESUME_HOST;
break;
- }
case BOOK3S_INTERRUPT_HV_RM_HARD:
vcpu->arch.trap = 0;
@@ -2304,7 +2289,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
*val = get_reg_val(id, kvmppc_get_siar_hv(vcpu));
break;
case KVM_REG_PPC_SDAR:
- *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu));
+ *val = get_reg_val(id, kvmppc_get_sdar_hv(vcpu));
break;
case KVM_REG_PPC_SIER:
*val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 0));
@@ -2348,6 +2333,15 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_DAWRX1:
*val = get_reg_val(id, kvmppc_get_dawrx1_hv(vcpu));
break;
+ case KVM_REG_PPC_DEXCR:
+ *val = get_reg_val(id, kvmppc_get_dexcr_hv(vcpu));
+ break;
+ case KVM_REG_PPC_HASHKEYR:
+ *val = get_reg_val(id, kvmppc_get_hashkeyr_hv(vcpu));
+ break;
+ case KVM_REG_PPC_HASHPKEYR:
+ *val = get_reg_val(id, kvmppc_get_hashpkeyr_hv(vcpu));
+ break;
case KVM_REG_PPC_CIABR:
*val = get_reg_val(id, kvmppc_get_ciabr_hv(vcpu));
break;
@@ -2539,7 +2533,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
vcpu->arch.mmcrs = set_reg_val(id, *val);
break;
case KVM_REG_PPC_MMCR3:
- *val = get_reg_val(id, vcpu->arch.mmcr[3]);
+ kvmppc_set_mmcr_hv(vcpu, 3, set_reg_val(id, *val));
break;
case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
i = id - KVM_REG_PPC_PMC1;
@@ -2591,6 +2585,15 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_DAWRX1:
kvmppc_set_dawrx1_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP);
break;
+ case KVM_REG_PPC_DEXCR:
+ kvmppc_set_dexcr_hv(vcpu, set_reg_val(id, *val));
+ break;
+ case KVM_REG_PPC_HASHKEYR:
+ kvmppc_set_hashkeyr_hv(vcpu, set_reg_val(id, *val));
+ break;
+ case KVM_REG_PPC_HASHPKEYR:
+ kvmppc_set_hashpkeyr_hv(vcpu, set_reg_val(id, *val));
+ break;
case KVM_REG_PPC_CIABR:
kvmppc_set_ciabr_hv(vcpu, set_reg_val(id, *val));
/* Don't allow setting breakpoints in hypervisor code */
@@ -4030,7 +4033,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
/* Return to whole-core mode if we split the core earlier */
if (cmd_bit) {
unsigned long hid0 = mfspr(SPRN_HID0);
- unsigned long loops = 0;
hid0 &= ~HID0_POWER8_DYNLPARDIS;
stat_bit = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE;
@@ -4042,7 +4044,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
if (!(hid0 & stat_bit))
break;
cpu_relax();
- ++loops;
}
split_info.do_nap = 0;
}
@@ -4107,6 +4108,144 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu)
}
}
+/* Helper functions for reading L2's stats from L1's VPA */
+#ifdef CONFIG_PPC_PSERIES
+static DEFINE_PER_CPU(u64, l1_to_l2_cs);
+static DEFINE_PER_CPU(u64, l2_to_l1_cs);
+static DEFINE_PER_CPU(u64, l2_runtime_agg);
+
+int kvmhv_get_l2_counters_status(void)
+{
+ return firmware_has_feature(FW_FEATURE_LPAR) &&
+ get_lppaca()->l2_counters_enable;
+}
+
+void kvmhv_set_l2_counters_status(int cpu, bool status)
+{
+ if (!firmware_has_feature(FW_FEATURE_LPAR))
+ return;
+ if (status)
+ lppaca_of(cpu).l2_counters_enable = 1;
+ else
+ lppaca_of(cpu).l2_counters_enable = 0;
+}
+EXPORT_SYMBOL(kvmhv_set_l2_counters_status);
+
+int kvmhv_counters_tracepoint_regfunc(void)
+{
+ int cpu;
+
+ for_each_present_cpu(cpu) {
+ kvmhv_set_l2_counters_status(cpu, true);
+ }
+ return 0;
+}
+
+void kvmhv_counters_tracepoint_unregfunc(void)
+{
+ int cpu;
+
+ for_each_present_cpu(cpu) {
+ kvmhv_set_l2_counters_status(cpu, false);
+ }
+}
+
+static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu)
+{
+ struct lppaca *lp = get_lppaca();
+ u64 l1_to_l2_ns, l2_to_l1_ns, l2_runtime_ns;
+ u64 *l1_to_l2_cs_ptr = this_cpu_ptr(&l1_to_l2_cs);
+ u64 *l2_to_l1_cs_ptr = this_cpu_ptr(&l2_to_l1_cs);
+ u64 *l2_runtime_agg_ptr = this_cpu_ptr(&l2_runtime_agg);
+
+ l1_to_l2_ns = tb_to_ns(be64_to_cpu(lp->l1_to_l2_cs_tb));
+ l2_to_l1_ns = tb_to_ns(be64_to_cpu(lp->l2_to_l1_cs_tb));
+ l2_runtime_ns = tb_to_ns(be64_to_cpu(lp->l2_runtime_tb));
+ trace_kvmppc_vcpu_stats(vcpu, l1_to_l2_ns - *l1_to_l2_cs_ptr,
+ l2_to_l1_ns - *l2_to_l1_cs_ptr,
+ l2_runtime_ns - *l2_runtime_agg_ptr);
+ *l1_to_l2_cs_ptr = l1_to_l2_ns;
+ *l2_to_l1_cs_ptr = l2_to_l1_ns;
+ *l2_runtime_agg_ptr = l2_runtime_ns;
+ vcpu->arch.l1_to_l2_cs = l1_to_l2_ns;
+ vcpu->arch.l2_to_l1_cs = l2_to_l1_ns;
+ vcpu->arch.l2_runtime_agg = l2_runtime_ns;
+}
+
+u64 kvmhv_get_l1_to_l2_cs_time(void)
+{
+ return tb_to_ns(be64_to_cpu(get_lppaca()->l1_to_l2_cs_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l1_to_l2_cs_time);
+
+u64 kvmhv_get_l2_to_l1_cs_time(void)
+{
+ return tb_to_ns(be64_to_cpu(get_lppaca()->l2_to_l1_cs_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l2_to_l1_cs_time);
+
+u64 kvmhv_get_l2_runtime_agg(void)
+{
+ return tb_to_ns(be64_to_cpu(get_lppaca()->l2_runtime_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l2_runtime_agg);
+
+u64 kvmhv_get_l1_to_l2_cs_time_vcpu(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vcpu_arch *arch;
+
+ vcpu = local_paca->kvm_hstate.kvm_vcpu;
+ if (vcpu) {
+ arch = &vcpu->arch;
+ return arch->l1_to_l2_cs;
+ } else {
+ return 0;
+ }
+}
+EXPORT_SYMBOL(kvmhv_get_l1_to_l2_cs_time_vcpu);
+
+u64 kvmhv_get_l2_to_l1_cs_time_vcpu(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vcpu_arch *arch;
+
+ vcpu = local_paca->kvm_hstate.kvm_vcpu;
+ if (vcpu) {
+ arch = &vcpu->arch;
+ return arch->l2_to_l1_cs;
+ } else {
+ return 0;
+ }
+}
+EXPORT_SYMBOL(kvmhv_get_l2_to_l1_cs_time_vcpu);
+
+u64 kvmhv_get_l2_runtime_agg_vcpu(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vcpu_arch *arch;
+
+ vcpu = local_paca->kvm_hstate.kvm_vcpu;
+ if (vcpu) {
+ arch = &vcpu->arch;
+ return arch->l2_runtime_agg;
+ } else {
+ return 0;
+ }
+}
+EXPORT_SYMBOL(kvmhv_get_l2_runtime_agg_vcpu);
+
+#else
+int kvmhv_get_l2_counters_status(void)
+{
+ return 0;
+}
+
+static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu)
+{
+}
+#endif
+
static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
unsigned long lpcr, u64 *tb)
{
@@ -4115,6 +4254,11 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
int trap;
long rc;
+ if (vcpu->arch.doorbell_request) {
+ vcpu->arch.doorbell_request = 0;
+ kvmppc_set_dpdes(vcpu, 1);
+ }
+
io = &vcpu->arch.nestedv2_io;
msr = mfmsr();
@@ -4155,6 +4299,10 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
timer_rearm_host_dec(*tb);
+ /* Record context switch and guest_run_time data */
+ if (kvmhv_get_l2_counters_status())
+ do_trace_nested_cs_time(vcpu);
+
return trap;
}
@@ -4205,6 +4353,15 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
hvregs.hdec_expiry = time_limit;
/*
+ * hvregs has the doorbell status, so zero it here which
+ * enables us to receive doorbells when H_ENTER_NESTED is
+ * in progress for this vCPU
+ */
+
+ if (vcpu->arch.doorbell_request)
+ vcpu->arch.doorbell_request = 0;
+
+ /*
* When setting DEC, we must always deal with irq_work_raise
* via NMI vs setting DEC. The problem occurs right as we
* switch into guest mode if a NMI hits and sets pending work
@@ -4793,9 +4950,20 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
BOOK3S_INTERRUPT_EXTERNAL, 0);
else
lpcr |= LPCR_MER;
+ } else {
+ /*
+ * L1's copy of L2's LPCR (vcpu->arch.vcore->lpcr) can get its MER bit
+ * unexpectedly set - for e.g. during NMI handling when all register
+ * states are synchronized from L0 to L1. L1 needs to inform L0 about
+ * MER=1 only when there are pending external interrupts.
+ * In the above if check, MER bit is set if there are pending
+ * external interrupts. Hence, explicitly mask off MER bit
+ * here as otherwise it may generate spurious interrupts in L2 KVM
+ * causing an endless loop, which results in L2 guest getting hung.
+ */
+ lpcr &= ~LPCR_MER;
}
} else if (vcpu->arch.pending_exceptions ||
- vcpu->arch.doorbell_request ||
xive_interrupt_pending(vcpu)) {
vcpu->arch.ret = RESUME_HOST;
goto out;
@@ -4856,7 +5024,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
* entering a nested guest in which case the decrementer is now owned
* by L2 and the L1 decrementer is provided in hdec_expires
*/
- if (!kvmhv_is_nestedv2() && kvmppc_core_pending_dec(vcpu) &&
+ if (kvmppc_core_pending_dec(vcpu) &&
((tb < kvmppc_dec_expires_host_tb(vcpu)) ||
(trap == BOOK3S_INTERRUPT_SYSCALL &&
kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED)))
@@ -6363,7 +6531,6 @@ static struct kvmppc_ops kvm_ops_hv = {
.unmap_gfn_range = kvm_unmap_gfn_range_hv,
.age_gfn = kvm_age_gfn_hv,
.test_age_gfn = kvm_test_age_gfn_hv,
- .set_spte_gfn = kvm_set_spte_gfn_hv,
.free_memslot = kvmppc_core_free_memslot_hv,
.init_vm = kvmppc_core_init_vm_hv,
.destroy_vm = kvmppc_core_destroy_vm_hv,
@@ -6519,6 +6686,7 @@ static void kvmppc_book3s_exit_hv(void)
module_init(kvmppc_book3s_init_hv);
module_exit(kvmppc_book3s_exit_hv);
+MODULE_DESCRIPTION("KVM on Book3S (POWER8 and later) in hypervisor mode");
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");
diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h
index 47b2c815641e..a404c9b221c1 100644
--- a/arch/powerpc/kvm/book3s_hv.h
+++ b/arch/powerpc/kvm/book3s_hv.h
@@ -116,6 +116,9 @@ KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr0, 64, KVMPPC_GSID_DAWR0)
KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr1, 64, KVMPPC_GSID_DAWR1)
KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx0, 64, KVMPPC_GSID_DAWRX0)
KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx1, 64, KVMPPC_GSID_DAWRX1)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dexcr, 64, KVMPPC_GSID_DEXCR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(hashkeyr, 64, KVMPPC_GSID_HASHKEYR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(hashpkeyr, 64, KVMPPC_GSID_HASHPKEYR)
KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ciabr, 64, KVMPPC_GSID_CIABR)
KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(wort, 64, KVMPPC_GSID_WORT)
KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ppr, 64, KVMPPC_GSID_PPR)
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 5c375ec1a3c6..5f8c2321cfb5 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -32,7 +32,7 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
struct kvmppc_vcore *vc = vcpu->arch.vcore;
hr->pcr = vc->pcr | PCR_MASK;
- hr->dpdes = vc->dpdes;
+ hr->dpdes = vcpu->arch.doorbell_request;
hr->hfscr = vcpu->arch.hfscr;
hr->tb_offset = vc->tb_offset;
hr->dawr0 = vcpu->arch.dawr0;
@@ -55,7 +55,7 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
hr->dawrx1 = vcpu->arch.dawrx1;
}
-/* Use noinline_for_stack due to https://bugs.llvm.org/show_bug.cgi?id=49610 */
+/* Use noinline_for_stack due to https://llvm.org/pr49610 */
static noinline_for_stack void byteswap_pt_regs(struct pt_regs *regs)
{
unsigned long *addr = (unsigned long *) regs;
@@ -105,7 +105,7 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu,
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
- hr->dpdes = vc->dpdes;
+ hr->dpdes = vcpu->arch.doorbell_request;
hr->purr = vcpu->arch.purr;
hr->spurr = vcpu->arch.spurr;
hr->ic = vcpu->arch.ic;
@@ -143,7 +143,7 @@ static void restore_hv_regs(struct kvm_vcpu *vcpu, const struct hv_guest_state *
struct kvmppc_vcore *vc = vcpu->arch.vcore;
vc->pcr = hr->pcr | PCR_MASK;
- vc->dpdes = hr->dpdes;
+ vcpu->arch.doorbell_request = hr->dpdes;
vcpu->arch.hfscr = hr->hfscr;
vcpu->arch.dawr0 = hr->dawr0;
vcpu->arch.dawrx0 = hr->dawrx0;
@@ -170,7 +170,13 @@ void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
- vc->dpdes = hr->dpdes;
+ /*
+ * This L2 vCPU might have received a doorbell while H_ENTER_NESTED was being handled.
+ * Make sure we preserve the doorbell if it was either:
+ * a) Sent after H_ENTER_NESTED was called on this vCPU (arch.doorbell_request would be 1)
+ * b) Doorbell was not handled and L2 exited for some other reason (hr->dpdes would be 1)
+ */
+ vcpu->arch.doorbell_request = vcpu->arch.doorbell_request | hr->dpdes;
vcpu->arch.hfscr = hr->hfscr;
vcpu->arch.purr = hr->purr;
vcpu->arch.spurr = hr->spurr;
@@ -445,6 +451,8 @@ long kvmhv_nested_init(void)
if (rc == H_SUCCESS) {
unsigned long capabilities = 0;
+ if (cpu_has_feature(CPU_FTR_P11_PVR))
+ capabilities |= H_GUEST_CAP_POWER11;
if (cpu_has_feature(CPU_FTR_ARCH_31))
capabilities |= H_GUEST_CAP_POWER10;
if (cpu_has_feature(CPU_FTR_ARCH_300))
@@ -1527,7 +1535,6 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
unsigned long n_gpa, gpa, gfn, perm = 0UL;
unsigned int shift, l1_shift, level;
bool writing = !!(dsisr & DSISR_ISSTORE);
- bool kvm_ro = false;
long int ret;
if (!gp->l1_gr_to_hr) {
@@ -1607,7 +1614,6 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
ea, DSISR_ISSTORE | DSISR_PROTFAULT);
return RESUME_GUEST;
}
- kvm_ro = true;
}
/* 2. Find the host pte for this L1 guest real address */
@@ -1629,7 +1635,7 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
if (!pte_present(pte) || (writing && !(pte_val(pte) & _PAGE_WRITE))) {
/* No suitable pte found -> try to insert a mapping */
ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot,
- writing, kvm_ro, &pte, &level);
+ writing, &pte, &level);
if (ret == -EAGAIN)
return RESUME_GUEST;
else if (ret)
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index 8e6f5355f08b..e5c7ce1fb761 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -71,8 +71,8 @@ gs_msg_ops_kvmhv_nestedv2_config_fill_info(struct kvmppc_gs_buff *gsb,
}
if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_OUTPUT)) {
- kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_OUTPUT,
- cfg->vcpu_run_output_cfg);
+ rc = kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_OUTPUT,
+ cfg->vcpu_run_output_cfg);
if (rc < 0)
return rc;
}
@@ -193,6 +193,15 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
case KVMPPC_GSID_DAWRX1:
rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.dawrx1);
break;
+ case KVMPPC_GSID_DEXCR:
+ rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.dexcr);
+ break;
+ case KVMPPC_GSID_HASHKEYR:
+ rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.hashkeyr);
+ break;
+ case KVMPPC_GSID_HASHPKEYR:
+ rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.hashpkeyr);
+ break;
case KVMPPC_GSID_CIABR:
rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ciabr);
break;
@@ -311,6 +320,10 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
rc = kvmppc_gse_put_u64(gsb, iden,
vcpu->arch.vcore->vtb);
break;
+ case KVMPPC_GSID_DPDES:
+ rc = kvmppc_gse_put_u64(gsb, iden,
+ vcpu->arch.vcore->dpdes);
+ break;
case KVMPPC_GSID_LPCR:
rc = kvmppc_gse_put_u64(gsb, iden,
vcpu->arch.vcore->lpcr);
@@ -357,7 +370,9 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
* default to L1's PVR.
*/
if (!vcpu->arch.vcore->arch_compat) {
- if (cpu_has_feature(CPU_FTR_ARCH_31))
+ if (cpu_has_feature(CPU_FTR_P11_PVR))
+ arch_compat = PVR_ARCH_31_P11;
+ else if (cpu_has_feature(CPU_FTR_ARCH_31))
arch_compat = PVR_ARCH_31;
else if (cpu_has_feature(CPU_FTR_ARCH_300))
arch_compat = PVR_ARCH_300;
@@ -441,6 +456,15 @@ static int gs_msg_ops_vcpu_refresh_info(struct kvmppc_gs_msg *gsm,
case KVMPPC_GSID_DAWRX1:
vcpu->arch.dawrx1 = kvmppc_gse_get_u32(gse);
break;
+ case KVMPPC_GSID_DEXCR:
+ vcpu->arch.dexcr = kvmppc_gse_get_u64(gse);
+ break;
+ case KVMPPC_GSID_HASHKEYR:
+ vcpu->arch.hashkeyr = kvmppc_gse_get_u64(gse);
+ break;
+ case KVMPPC_GSID_HASHPKEYR:
+ vcpu->arch.hashpkeyr = kvmppc_gse_get_u64(gse);
+ break;
case KVMPPC_GSID_CIABR:
vcpu->arch.ciabr = kvmppc_gse_get_u64(gse);
break;
@@ -543,6 +567,9 @@ static int gs_msg_ops_vcpu_refresh_info(struct kvmppc_gs_msg *gsm,
case KVMPPC_GSID_VTB:
vcpu->arch.vcore->vtb = kvmppc_gse_get_u64(gse);
break;
+ case KVMPPC_GSID_DPDES:
+ vcpu->arch.vcore->dpdes = kvmppc_gse_get_u64(gse);
+ break;
case KVMPPC_GSID_LPCR:
vcpu->arch.vcore->lpcr = kvmppc_gse_get_u64(gse);
break;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index e42984878503..f2636414d82a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -837,7 +837,7 @@ static inline void this_cpu_inc_rm(unsigned int __percpu *addr)
*/
static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc)
{
- this_cpu_inc_rm(desc->kstat_irqs);
+ this_cpu_inc_rm(&desc->kstat_irqs->cnt);
__this_cpu_inc(kstat.irqs_sum);
}
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 92f33115144b..3a6592a31a10 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -879,9 +879,8 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
{
int ret = H_PARAMETER;
- struct page *uvmem_page;
+ struct page *page, *uvmem_page;
struct kvmppc_uvmem_page_pvt *pvt;
- unsigned long pfn;
unsigned long gfn = gpa >> page_shift;
int srcu_idx;
unsigned long uvmem_pfn;
@@ -901,8 +900,8 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
retry:
mutex_unlock(&kvm->arch.uvmem_lock);
- pfn = gfn_to_pfn(kvm, gfn);
- if (is_error_noslot_pfn(pfn))
+ page = gfn_to_page(kvm, gfn);
+ if (!page)
goto out;
mutex_lock(&kvm->arch.uvmem_lock);
@@ -911,16 +910,16 @@ retry:
pvt = uvmem_page->zone_device_data;
pvt->skip_page_out = true;
pvt->remove_gfn = false; /* it continues to be a valid GFN */
- kvm_release_pfn_clean(pfn);
+ kvm_release_page_unused(page);
goto retry;
}
- if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
+ if (!uv_page_in(kvm->arch.lpid, page_to_pfn(page) << page_shift, gpa, 0,
page_shift)) {
kvmppc_gfn_shared(gfn, kvm);
ret = H_SUCCESS;
}
- kvm_release_pfn_clean(pfn);
+ kvm_release_page_clean(page);
mutex_unlock(&kvm->arch.uvmem_lock);
out:
srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -1083,21 +1082,21 @@ out:
int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
{
- unsigned long pfn;
+ struct page *page;
int ret = U_SUCCESS;
- pfn = gfn_to_pfn(kvm, gfn);
- if (is_error_noslot_pfn(pfn))
+ page = gfn_to_page(kvm, gfn);
+ if (!page)
return -EFAULT;
mutex_lock(&kvm->arch.uvmem_lock);
if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL))
goto out;
- ret = uv_page_in(kvm->arch.lpid, pfn << PAGE_SHIFT, gfn << PAGE_SHIFT,
- 0, PAGE_SHIFT);
+ ret = uv_page_in(kvm->arch.lpid, page_to_pfn(page) << PAGE_SHIFT,
+ gfn << PAGE_SHIFT, 0, PAGE_SHIFT);
out:
- kvm_release_pfn_clean(pfn);
+ kvm_release_page_clean(page);
mutex_unlock(&kvm->arch.uvmem_lock);
return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT;
}
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index ce79ac33e8d3..d904e13e069b 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -92,12 +92,6 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
spin_unlock(&vcpu3s->mmu_lock);
}
-static void free_pte_rcu(struct rcu_head *head)
-{
- struct hpte_cache *pte = container_of(head, struct hpte_cache, rcu_head);
- kmem_cache_free(hpte_cache, pte);
-}
-
static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
{
struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
@@ -126,7 +120,7 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
spin_unlock(&vcpu3s->mmu_lock);
- call_rcu(&pte->rcu_head, free_pte_rcu);
+ kfree_rcu(pte, rcu_head);
}
static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 5b92619a05fd..83bcdc80ce51 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -461,12 +461,6 @@ static bool kvm_test_age_gfn_pr(struct kvm *kvm, struct kvm_gfn_range *range)
return false;
}
-static bool kvm_set_spte_gfn_pr(struct kvm *kvm, struct kvm_gfn_range *range)
-{
- /* The page will get remapped properly on its next fault */
- return do_kvm_unmap_gfn(kvm, range);
-}
-
/*****************************************/
static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
@@ -645,29 +639,27 @@ static void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
*/
static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
{
- struct page *hpage;
+ struct kvm_host_map map;
u64 hpage_offset;
u32 *page;
- int i;
+ int i, r;
- hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
- if (is_error_page(hpage))
+ r = kvm_vcpu_map(vcpu, pte->raddr >> PAGE_SHIFT, &map);
+ if (r)
return;
hpage_offset = pte->raddr & ~PAGE_MASK;
hpage_offset &= ~0xFFFULL;
hpage_offset /= 4;
- get_page(hpage);
- page = kmap_atomic(hpage);
+ page = map.hva;
/* patch dcbz into reserved instruction, so we trap */
for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++)
if ((be32_to_cpu(page[i]) & 0xff0007ff) == INS_DCBZ)
page[i] &= cpu_to_be32(0xfffffff7);
- kunmap_atomic(page);
- put_page(hpage);
+ kvm_vcpu_unmap(vcpu, &map);
}
static bool kvmppc_visible_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
@@ -2071,7 +2063,6 @@ static struct kvmppc_ops kvm_ops_pr = {
.unmap_gfn_range = kvm_unmap_gfn_range_pr,
.age_gfn = kvm_age_gfn_pr,
.test_age_gfn = kvm_test_age_gfn_pr,
- .set_spte_gfn = kvm_set_spte_gfn_pr,
.free_memslot = kvmppc_core_free_memslot_pr,
.init_vm = kvmppc_core_init_vm_pr,
.destroy_vm = kvmppc_core_destroy_vm_pr,
@@ -2118,6 +2109,7 @@ void kvmppc_book3s_exit_pr(void)
module_init(kvmppc_book3s_init_pr);
module_exit(kvmppc_book3s_exit_pr);
+MODULE_DESCRIPTION("KVM on Book3S without using hypervisor mode");
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 29a382249770..1362c672387e 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -531,7 +531,7 @@ static int xive_vm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
xc->cppr = xive_prio_from_guest(new_cppr);
/*
- * IPIs are synthetized from MFRR and thus don't need
+ * IPIs are synthesized from MFRR and thus don't need
* any special EOI handling. The underlying interrupt
* used to signal MFRR changes is EOId when fetched from
* the queue.
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 6e2ebbd8aaac..d9bf1bc3ff61 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -654,7 +654,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
}
page = gfn_to_page(kvm, gfn);
- if (is_error_page(page)) {
+ if (!page) {
srcu_read_unlock(&kvm->srcu, srcu_idx);
pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
return -EINVAL;
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 6d0d329cbb35..f9acf866c709 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -34,6 +34,8 @@ enum vcpu_ftr {
#define E500_TLB_BITMAP (1 << 30)
/* TLB1 entry is mapped by host TLB0 */
#define E500_TLB_TLB0 (1 << 29)
+/* entry is writable on the host */
+#define E500_TLB_WRITABLE (1 << 28)
/* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */
#define E500_TLB_MAS2_ATTR (0x7f)
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index ccb8f16ffe41..06caf8bbbe2b 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -45,11 +45,14 @@ static inline unsigned int tlb1_max_shadow_size(void)
return host_tlb_params[1].entries - tlbcam_index - 1;
}
-static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
+static inline u32 e500_shadow_mas3_attrib(u32 mas3, bool writable, int usermode)
{
/* Mask off reserved bits. */
mas3 &= MAS3_ATTRIB_MASK;
+ if (!writable)
+ mas3 &= ~(MAS3_UW|MAS3_SW);
+
#ifndef CONFIG_KVM_BOOKE_HV
if (!usermode) {
/* Guest is in supervisor mode,
@@ -244,19 +247,16 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
struct kvm_book3e_206_tlb_entry *gtlbe,
- kvm_pfn_t pfn, unsigned int wimg)
+ kvm_pfn_t pfn, unsigned int wimg,
+ bool writable)
{
ref->pfn = pfn;
ref->flags = E500_TLB_VALID;
+ if (writable)
+ ref->flags |= E500_TLB_WRITABLE;
/* Use guest supplied MAS2_G and MAS2_E */
ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg;
-
- /* Mark the page accessed */
- kvm_set_pfn_accessed(pfn);
-
- if (tlbe_is_writable(gtlbe))
- kvm_set_pfn_dirty(pfn);
}
static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
@@ -309,6 +309,7 @@ static void kvmppc_e500_setup_stlbe(
{
kvm_pfn_t pfn = ref->pfn;
u32 pr = vcpu->arch.shared->msr & MSR_PR;
+ bool writable = !!(ref->flags & E500_TLB_WRITABLE);
BUG_ON(!(ref->flags & E500_TLB_VALID));
@@ -316,7 +317,7 @@ static void kvmppc_e500_setup_stlbe(
stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR);
stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
- e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
+ e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr);
}
static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -325,18 +326,19 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
struct tlbe_ref *ref)
{
struct kvm_memory_slot *slot;
- unsigned long pfn = 0; /* silence GCC warning */
+ unsigned int psize;
+ unsigned long pfn;
+ struct page *page = NULL;
unsigned long hva;
- int pfnmap = 0;
int tsize = BOOK3E_PAGESZ_4K;
int ret = 0;
unsigned long mmu_seq;
struct kvm *kvm = vcpu_e500->vcpu.kvm;
- unsigned long tsize_pages = 0;
pte_t *ptep;
unsigned int wimg = 0;
pgd_t *pgdir;
unsigned long flags;
+ bool writable = false;
/* used to check for invalidations in progress */
mmu_seq = kvm->mmu_invalidate_seq;
@@ -353,110 +355,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn);
hva = gfn_to_hva_memslot(slot, gfn);
- if (tlbsel == 1) {
- struct vm_area_struct *vma;
- mmap_read_lock(kvm->mm);
-
- vma = find_vma(kvm->mm, hva);
- if (vma && hva >= vma->vm_start &&
- (vma->vm_flags & VM_PFNMAP)) {
- /*
- * This VMA is a physically contiguous region (e.g.
- * /dev/mem) that bypasses normal Linux page
- * management. Find the overlap between the
- * vma and the memslot.
- */
-
- unsigned long start, end;
- unsigned long slot_start, slot_end;
-
- pfnmap = 1;
-
- start = vma->vm_pgoff;
- end = start +
- vma_pages(vma);
-
- pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT);
-
- slot_start = pfn - (gfn - slot->base_gfn);
- slot_end = slot_start + slot->npages;
-
- if (start < slot_start)
- start = slot_start;
- if (end > slot_end)
- end = slot_end;
-
- tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
- MAS1_TSIZE_SHIFT;
-
- /*
- * e500 doesn't implement the lowest tsize bit,
- * or 1K pages.
- */
- tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
-
- /*
- * Now find the largest tsize (up to what the guest
- * requested) that will cover gfn, stay within the
- * range, and for which gfn and pfn are mutually
- * aligned.
- */
-
- for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
- unsigned long gfn_start, gfn_end;
- tsize_pages = 1UL << (tsize - 2);
-
- gfn_start = gfn & ~(tsize_pages - 1);
- gfn_end = gfn_start + tsize_pages;
-
- if (gfn_start + pfn - gfn < start)
- continue;
- if (gfn_end + pfn - gfn > end)
- continue;
- if ((gfn & (tsize_pages - 1)) !=
- (pfn & (tsize_pages - 1)))
- continue;
-
- gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
- pfn &= ~(tsize_pages - 1);
- break;
- }
- } else if (vma && hva >= vma->vm_start &&
- is_vm_hugetlb_page(vma)) {
- unsigned long psize = vma_kernel_pagesize(vma);
-
- tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
- MAS1_TSIZE_SHIFT;
-
- /*
- * Take the largest page size that satisfies both host
- * and guest mapping
- */
- tsize = min(__ilog2(psize) - 10, tsize);
-
- /*
- * e500 doesn't implement the lowest tsize bit,
- * or 1K pages.
- */
- tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
- }
-
- mmap_read_unlock(kvm->mm);
- }
-
- if (likely(!pfnmap)) {
- tsize_pages = 1UL << (tsize + 10 - PAGE_SHIFT);
- pfn = gfn_to_pfn_memslot(slot, gfn);
- if (is_error_noslot_pfn(pfn)) {
- if (printk_ratelimit())
- pr_err("%s: real page not found for gfn %lx\n",
- __func__, (long)gfn);
- return -EINVAL;
- }
-
- /* Align guest and physical address to page map boundaries */
- pfn &= ~(tsize_pages - 1);
- gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
+ pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &page);
+ if (is_error_noslot_pfn(pfn)) {
+ if (printk_ratelimit())
+ pr_err("%s: real page not found for gfn %lx\n",
+ __func__, (long)gfn);
+ return -EINVAL;
}
spin_lock(&kvm->mmu_lock);
@@ -474,14 +378,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
* can't run hence pfn won't change.
*/
local_irq_save(flags);
- ptep = find_linux_pte(pgdir, hva, NULL, NULL);
+ ptep = find_linux_pte(pgdir, hva, NULL, &psize);
if (ptep) {
pte_t pte = READ_ONCE(*ptep);
if (pte_present(pte)) {
wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) &
MAS2_WIMGE_MASK;
- local_irq_restore(flags);
} else {
local_irq_restore(flags);
pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n",
@@ -490,20 +393,79 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
goto out;
}
}
- kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);
+ local_irq_restore(flags);
+
+ if (psize && tlbsel == 1) {
+ unsigned long psize_pages, tsize_pages;
+ unsigned long start, end;
+ unsigned long slot_start, slot_end;
+
+ psize_pages = 1UL << (psize - PAGE_SHIFT);
+ start = pfn & ~(psize_pages - 1);
+ end = start + psize_pages;
+
+ slot_start = pfn - (gfn - slot->base_gfn);
+ slot_end = slot_start + slot->npages;
+
+ if (start < slot_start)
+ start = slot_start;
+ if (end > slot_end)
+ end = slot_end;
+
+ tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
+ MAS1_TSIZE_SHIFT;
+
+ /*
+ * Any page size that doesn't satisfy the host mapping
+ * will fail the start and end tests.
+ */
+ tsize = min(psize - PAGE_SHIFT + BOOK3E_PAGESZ_4K, tsize);
+
+ /*
+ * e500 doesn't implement the lowest tsize bit,
+ * or 1K pages.
+ */
+ tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
+
+ /*
+ * Now find the largest tsize (up to what the guest
+ * requested) that will cover gfn, stay within the
+ * range, and for which gfn and pfn are mutually
+ * aligned.
+ */
+
+ for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
+ unsigned long gfn_start, gfn_end;
+ tsize_pages = 1UL << (tsize - 2);
+
+ gfn_start = gfn & ~(tsize_pages - 1);
+ gfn_end = gfn_start + tsize_pages;
+
+ if (gfn_start + pfn - gfn < start)
+ continue;
+ if (gfn_end + pfn - gfn > end)
+ continue;
+ if ((gfn & (tsize_pages - 1)) !=
+ (pfn & (tsize_pages - 1)))
+ continue;
+
+ gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
+ pfn &= ~(tsize_pages - 1);
+ break;
+ }
+ }
+ kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable);
kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
ref, gvaddr, stlbe);
+ writable = tlbe_is_writable(stlbe);
/* Clear i-cache for new pages */
kvmppc_mmu_flush_icache(pfn);
out:
+ kvm_release_faultin_page(kvm, page, !!ret, writable);
spin_unlock(&kvm->mmu_lock);
-
- /* Drop refcount on page, so that mmu notifiers can clear it */
- kvm_release_pfn_clean(pfn);
-
return ret;
}
@@ -747,12 +709,6 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
return false;
}
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
- /* The page will get remapped properly on its next fault */
- return kvm_e500_mmu_unmap_gfn(kvm, range);
-}
-
/*****************************************/
int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 23407fbd73c9..ce1d91eed231 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -612,9 +612,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = 8 | 4 | 2 | 1;
}
break;
- case KVM_CAP_PPC_RMA:
- r = 0;
- break;
case KVM_CAP_PPC_HWRNG:
r = kvmppc_hwrng_present();
break;
@@ -1852,7 +1849,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
kvm_sigset_activate(vcpu);
- if (run->immediate_exit)
+ if (!vcpu->wants_to_run)
r = -EINTR;
else
r = kvmppc_vcpu_run(vcpu);
@@ -1933,54 +1930,48 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
#endif
#ifdef CONFIG_KVM_MPIC
case KVM_CAP_IRQ_MPIC: {
- struct fd f;
+ CLASS(fd, f)(cap->args[0]);
struct kvm_device *dev;
r = -EBADF;
- f = fdget(cap->args[0]);
- if (!f.file)
+ if (fd_empty(f))
break;
r = -EPERM;
- dev = kvm_device_from_filp(f.file);
+ dev = kvm_device_from_filp(fd_file(f));
if (dev)
r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]);
- fdput(f);
break;
}
#endif
#ifdef CONFIG_KVM_XICS
case KVM_CAP_IRQ_XICS: {
- struct fd f;
+ CLASS(fd, f)(cap->args[0]);
struct kvm_device *dev;
r = -EBADF;
- f = fdget(cap->args[0]);
- if (!f.file)
+ if (fd_empty(f))
break;
r = -EPERM;
- dev = kvm_device_from_filp(f.file);
+ dev = kvm_device_from_filp(fd_file(f));
if (dev) {
if (xics_on_xive())
r = kvmppc_xive_connect_vcpu(dev, vcpu, cap->args[1]);
else
r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
}
-
- fdput(f);
break;
}
#endif /* CONFIG_KVM_XICS */
#ifdef CONFIG_KVM_XIVE
case KVM_CAP_PPC_IRQ_XIVE: {
- struct fd f;
+ CLASS(fd, f)(cap->args[0]);
struct kvm_device *dev;
r = -EBADF;
- f = fdget(cap->args[0]);
- if (!f.file)
+ if (fd_empty(f))
break;
r = -ENXIO;
@@ -1988,12 +1979,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
break;
r = -EPERM;
- dev = kvm_device_from_filp(f.file);
+ dev = kvm_device_from_filp(fd_file(f));
if (dev)
r = kvmppc_xive_native_connect_vcpu(dev, vcpu,
cap->args[1]);
-
- fdput(f);
break;
}
#endif /* CONFIG_KVM_XIVE */
@@ -2538,9 +2527,8 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_
vcpu->kvm->arch.kvm_ops->create_vcpu_debugfs(vcpu, debugfs_dentry);
}
-int kvm_arch_create_vm_debugfs(struct kvm *kvm)
+void kvm_arch_create_vm_debugfs(struct kvm *kvm)
{
if (kvm->arch.kvm_ops->create_vm_debugfs)
kvm->arch.kvm_ops->create_vm_debugfs(kvm);
- return 0;
}
diff --git a/arch/powerpc/kvm/test-guest-state-buffer.c b/arch/powerpc/kvm/test-guest-state-buffer.c
index 4720b8dc8837..bfd225329a18 100644
--- a/arch/powerpc/kvm/test-guest-state-buffer.c
+++ b/arch/powerpc/kvm/test-guest-state-buffer.c
@@ -151,7 +151,7 @@ static void test_gs_bitmap(struct kunit *test)
i++;
}
- for (u16 iden = KVMPPC_GSID_GPR(0); iden <= KVMPPC_GSID_CTRL; iden++) {
+ for (u16 iden = KVMPPC_GSID_GPR(0); iden <= KVMPPC_GSE_DW_REGS_END; iden++) {
kvmppc_gsbm_set(&gsbm, iden);
kvmppc_gsbm_set(&gsbm1, iden);
KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
@@ -325,4 +325,5 @@ static struct kunit_suite guest_state_buffer_test_suite = {
kunit_test_suites(&guest_state_buffer_test_suite);
+MODULE_DESCRIPTION("KUnit tests for Guest State Buffer APIs");
MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h
index 8d57c8428531..35fccaa575cc 100644
--- a/arch/powerpc/kvm/trace_hv.h
+++ b/arch/powerpc/kvm/trace_hv.h
@@ -512,6 +512,35 @@ TRACE_EVENT(kvmppc_run_vcpu_exit,
__entry->vcpu_id, __entry->exit, __entry->ret)
);
+#ifdef CONFIG_PPC_PSERIES
+
+TRACE_EVENT_FN_COND(kvmppc_vcpu_stats,
+ TP_PROTO(struct kvm_vcpu *vcpu, u64 l1_to_l2_cs, u64 l2_to_l1_cs, u64 l2_runtime),
+
+ TP_ARGS(vcpu, l1_to_l2_cs, l2_to_l1_cs, l2_runtime),
+
+ TP_CONDITION(l1_to_l2_cs || l2_to_l1_cs || l2_runtime),
+
+ TP_STRUCT__entry(
+ __field(int, vcpu_id)
+ __field(u64, l1_to_l2_cs)
+ __field(u64, l2_to_l1_cs)
+ __field(u64, l2_runtime)
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu->vcpu_id;
+ __entry->l1_to_l2_cs = l1_to_l2_cs;
+ __entry->l2_to_l1_cs = l2_to_l1_cs;
+ __entry->l2_runtime = l2_runtime;
+ ),
+
+ TP_printk("VCPU %d: l1_to_l2_cs_time=%llu ns l2_to_l1_cs_time=%llu ns l2_runtime=%llu ns",
+ __entry->vcpu_id, __entry->l1_to_l2_cs,
+ __entry->l2_to_l1_cs, __entry->l2_runtime),
+ kvmhv_counters_tracepoint_regfunc, kvmhv_counters_tracepoint_unregfunc
+);
+#endif
#endif /* _TRACE_KVM_HV_H */
/* This part must be outside protection */
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 6eac63e79a89..dd8a4b52a0cc 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -3,8 +3,6 @@
# Makefile for ppc-specific library files..
#
-ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-
CFLAGS_code-patching.o += -fno-stack-protector
CFLAGS_feature-fixups.o += -fno-stack-protector
@@ -76,8 +74,14 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o
obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o
-CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec)
+CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec)
# Enable <altivec.h>
CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include)
+obj-$(CONFIG_CRC32_ARCH) += crc32-powerpc.o
+crc32-powerpc-y := crc32-glue.o crc32c-vpmsum_asm.o
+
+obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-powerpc.o
+crc-t10dif-powerpc-y := crc-t10dif-glue.o crct10dif-vpmsum_asm.o
+
obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index c6ab46156cda..f84e0337cc02 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -17,18 +17,17 @@
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/inst.h>
-static int __patch_instruction(u32 *exec_addr, ppc_inst_t instr, u32 *patch_addr)
+static int __patch_mem(void *exec_addr, unsigned long val, void *patch_addr, bool is_dword)
{
- if (!ppc_inst_prefixed(instr)) {
- u32 val = ppc_inst_val(instr);
+ if (!IS_ENABLED(CONFIG_PPC64) || likely(!is_dword)) {
+ /* For big endian correctness: plain address would use the wrong half */
+ u32 val32 = val;
- __put_kernel_nofault(patch_addr, &val, u32, failed);
+ __put_kernel_nofault(patch_addr, &val32, u32, failed);
} else {
- u64 val = ppc_inst_as_ulong(instr);
-
__put_kernel_nofault(patch_addr, &val, u64, failed);
}
@@ -44,7 +43,10 @@ failed:
int raw_patch_instruction(u32 *addr, ppc_inst_t instr)
{
- return __patch_instruction(addr, instr, addr);
+ if (ppc_inst_prefixed(instr))
+ return __patch_mem(addr, ppc_inst_as_ulong(instr), addr, true);
+ else
+ return __patch_mem(addr, ppc_inst_val(instr), addr, false);
}
struct patch_context {
@@ -106,7 +108,7 @@ static int text_area_cpu_up(unsigned int cpu)
unsigned long addr;
int err;
- area = get_vm_area(PAGE_SIZE, VM_ALLOC);
+ area = get_vm_area(PAGE_SIZE, 0);
if (!area) {
WARN_ONCE(1, "Failed to create text area for cpu %d\n",
cpu);
@@ -225,7 +227,7 @@ void __init poking_init(void)
static unsigned long get_patch_pfn(void *addr)
{
- if (IS_ENABLED(CONFIG_MODULES) && is_vmalloc_or_module_addr(addr))
+ if (IS_ENABLED(CONFIG_EXECMEM) && is_vmalloc_or_module_addr(addr))
return vmalloc_to_pfn(addr);
else
return __pa_symbol(addr) >> PAGE_SHIFT;
@@ -276,7 +278,7 @@ static void unmap_patch_area(unsigned long addr)
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
}
-static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
+static int __do_patch_mem_mm(void *addr, unsigned long val, bool is_dword)
{
int err;
u32 *patch_addr;
@@ -305,7 +307,7 @@ static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
orig_mm = start_using_temp_mm(patching_mm);
- err = __patch_instruction(addr, instr, patch_addr);
+ err = __patch_mem(addr, val, patch_addr, is_dword);
/* context synchronisation performed by __patch_instruction (isync or exception) */
stop_using_temp_mm(patching_mm, orig_mm);
@@ -322,7 +324,7 @@ static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
return err;
}
-static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
+static int __do_patch_mem(void *addr, unsigned long val, bool is_dword)
{
int err;
u32 *patch_addr;
@@ -339,7 +341,7 @@ static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
if (radix_enabled())
asm volatile("ptesync": : :"memory");
- err = __patch_instruction(addr, instr, patch_addr);
+ err = __patch_mem(addr, val, patch_addr, is_dword);
pte_clear(&init_mm, text_poke_addr, pte);
flush_tlb_kernel_range(text_poke_addr, text_poke_addr + PAGE_SIZE);
@@ -347,7 +349,7 @@ static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
return err;
}
-int patch_instruction(u32 *addr, ppc_inst_t instr)
+static int patch_mem(void *addr, unsigned long val, bool is_dword)
{
int err;
unsigned long flags;
@@ -359,22 +361,83 @@ int patch_instruction(u32 *addr, ppc_inst_t instr)
*/
if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) ||
!static_branch_likely(&poking_init_done))
- return raw_patch_instruction(addr, instr);
+ return __patch_mem(addr, val, addr, is_dword);
local_irq_save(flags);
if (mm_patch_enabled())
- err = __do_patch_instruction_mm(addr, instr);
+ err = __do_patch_mem_mm(addr, val, is_dword);
else
- err = __do_patch_instruction(addr, instr);
+ err = __do_patch_mem(addr, val, is_dword);
local_irq_restore(flags);
return err;
}
+
+#ifdef CONFIG_PPC64
+
+int patch_instruction(u32 *addr, ppc_inst_t instr)
+{
+ if (ppc_inst_prefixed(instr))
+ return patch_mem(addr, ppc_inst_as_ulong(instr), true);
+ else
+ return patch_mem(addr, ppc_inst_val(instr), false);
+}
NOKPROBE_SYMBOL(patch_instruction);
+int patch_uint(void *addr, unsigned int val)
+{
+ if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned int)))
+ return -EINVAL;
+
+ return patch_mem(addr, val, false);
+}
+NOKPROBE_SYMBOL(patch_uint);
+
+int patch_ulong(void *addr, unsigned long val)
+{
+ if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned long)))
+ return -EINVAL;
+
+ return patch_mem(addr, val, true);
+}
+NOKPROBE_SYMBOL(patch_ulong);
+
+#else
+
+int patch_instruction(u32 *addr, ppc_inst_t instr)
+{
+ return patch_mem(addr, ppc_inst_val(instr), false);
+}
+NOKPROBE_SYMBOL(patch_instruction)
+
+#endif
+
+static int patch_memset64(u64 *addr, u64 val, size_t count)
+{
+ for (u64 *end = addr + count; addr < end; addr++)
+ __put_kernel_nofault(addr, &val, u64, failed);
+
+ return 0;
+
+failed:
+ return -EPERM;
+}
+
+static int patch_memset32(u32 *addr, u32 val, size_t count)
+{
+ for (u32 *end = addr + count; addr < end; addr++)
+ __put_kernel_nofault(addr, &val, u32, failed);
+
+ return 0;
+
+failed:
+ return -EPERM;
+}
+
static int __patch_instructions(u32 *patch_addr, u32 *code, size_t len, bool repeat_instr)
{
unsigned long start = (unsigned long)patch_addr;
+ int err;
/* Repeat instruction */
if (repeat_instr) {
@@ -383,19 +446,19 @@ static int __patch_instructions(u32 *patch_addr, u32 *code, size_t len, bool rep
if (ppc_inst_prefixed(instr)) {
u64 val = ppc_inst_as_ulong(instr);
- memset64((u64 *)patch_addr, val, len / 8);
+ err = patch_memset64((u64 *)patch_addr, val, len / 8);
} else {
u32 val = ppc_inst_val(instr);
- memset32(patch_addr, val, len / 4);
+ err = patch_memset32(patch_addr, val, len / 4);
}
} else {
- memcpy(patch_addr, code, len);
+ err = copy_to_kernel_nofault(patch_addr, code, len);
}
smp_wmb(); /* smp write barrier */
flush_icache_range(start, start + len);
- return 0;
+ return err;
}
/*
@@ -430,7 +493,9 @@ static int __do_patch_instructions_mm(u32 *addr, u32 *code, size_t len, bool rep
orig_mm = start_using_temp_mm(patching_mm);
+ kasan_disable_current();
err = __patch_instructions(patch_addr, code, len, repeat_instr);
+ kasan_enable_current();
/* context synchronisation performed by __patch_instructions */
stop_using_temp_mm(patching_mm, orig_mm);
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index a783973f1215..07e7cec4d135 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -27,17 +27,7 @@ _GLOBAL(copypage_power7)
#endif
ori r10,r7,1 /* stream=1 */
- lis r8,0x8000 /* GO=1 */
- clrldi r8,r8,32
-
- /* setup read stream 0 */
- dcbt 0,r4,0b01000 /* addr from */
- dcbt 0,r7,0b01010 /* length and depth from */
- /* setup write stream 1 */
- dcbtst 0,r9,0b01000 /* addr to */
- dcbtst 0,r10,0b01010 /* length and depth to */
- eieio
- dcbt 0,r8,0b01010 /* all streams GO */
+ DCBT_SETUP_STREAMS(r4, r7, r9, r10, r8)
#ifdef CONFIG_ALTIVEC
mflr r0
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index ac41053c3a5a..8474c682a178 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -298,17 +298,7 @@ err1; stb r0,0(r3)
or r7,r7,r0
ori r10,r7,1 /* stream=1 */
- lis r8,0x8000 /* GO=1 */
- clrldi r8,r8,32
-
- /* setup read stream 0 */
- dcbt 0,r6,0b01000 /* addr from */
- dcbt 0,r7,0b01010 /* length and depth from */
- /* setup write stream 1 */
- dcbtst 0,r9,0b01000 /* addr to */
- dcbtst 0,r10,0b01010 /* length and depth to */
- eieio
- dcbt 0,r8,0b01010 /* all streams GO */
+ DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8)
beq cr1,.Lunwind_stack_nonvmx_copy
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/lib/crc-t10dif-glue.c
index 1dc8b6915178..730850dbc51d 100644
--- a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
+++ b/arch/powerpc/lib/crc-t10dif-glue.c
@@ -7,7 +7,6 @@
*/
#include <linux/crc-t10dif.h>
-#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <linux/init.h>
#include <linux/module.h>
@@ -22,15 +21,18 @@
#define VECTOR_BREAKPOINT 64
+static DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
+
u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len);
-static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len)
+u16 crc_t10dif_arch(u16 crci, const u8 *p, size_t len)
{
unsigned int prealign;
unsigned int tail;
u32 crc = crci;
- if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable())
+ if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) ||
+ !static_branch_likely(&have_vec_crypto) || !crypto_simd_usable())
return crc_t10dif_generic(crc, p, len);
if ((unsigned long)p & VMX_ALIGN_MASK) {
@@ -60,67 +62,28 @@ static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len)
return crc & 0xffff;
}
+EXPORT_SYMBOL(crc_t10dif_arch);
-static int crct10dif_vpmsum_init(struct shash_desc *desc)
-{
- u16 *crc = shash_desc_ctx(desc);
-
- *crc = 0;
- return 0;
-}
-
-static int crct10dif_vpmsum_update(struct shash_desc *desc, const u8 *data,
- unsigned int length)
-{
- u16 *crc = shash_desc_ctx(desc);
-
- *crc = crct10dif_vpmsum(*crc, data, length);
-
- return 0;
-}
-
-
-static int crct10dif_vpmsum_final(struct shash_desc *desc, u8 *out)
+static int __init crc_t10dif_powerpc_init(void)
{
- u16 *crcp = shash_desc_ctx(desc);
-
- *(u16 *)out = *crcp;
+ if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+ (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
+ static_branch_enable(&have_vec_crypto);
return 0;
}
+arch_initcall(crc_t10dif_powerpc_init);
-static struct shash_alg alg = {
- .init = crct10dif_vpmsum_init,
- .update = crct10dif_vpmsum_update,
- .final = crct10dif_vpmsum_final,
- .descsize = CRC_T10DIF_DIGEST_SIZE,
- .digestsize = CRC_T10DIF_DIGEST_SIZE,
- .base = {
- .cra_name = "crct10dif",
- .cra_driver_name = "crct10dif-vpmsum",
- .cra_priority = 200,
- .cra_blocksize = CRC_T10DIF_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-static int __init crct10dif_vpmsum_mod_init(void)
+static void __exit crc_t10dif_powerpc_exit(void)
{
- if (!cpu_has_feature(CPU_FTR_ARCH_207S))
- return -ENODEV;
-
- return crypto_register_shash(&alg);
}
+module_exit(crc_t10dif_powerpc_exit);
-static void __exit crct10dif_vpmsum_mod_fini(void)
+bool crc_t10dif_is_optimized(void)
{
- crypto_unregister_shash(&alg);
+ return static_key_enabled(&have_vec_crypto);
}
-
-module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crct10dif_vpmsum_mod_init);
-module_exit(crct10dif_vpmsum_mod_fini);
+EXPORT_SYMBOL(crc_t10dif_is_optimized);
MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions");
MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("crct10dif");
-MODULE_ALIAS_CRYPTO("crct10dif-vpmsum");
diff --git a/arch/powerpc/lib/crc32-glue.c b/arch/powerpc/lib/crc32-glue.c
new file mode 100644
index 000000000000..79cc954f499f
--- /dev/null
+++ b/arch/powerpc/lib/crc32-glue.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/crc32.h>
+#include <crypto/internal/simd.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+#define VMX_ALIGN 16
+#define VMX_ALIGN_MASK (VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT 512
+
+static DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
+
+u32 __crc32c_vpmsum(u32 crc, const u8 *p, size_t len);
+
+u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
+{
+ return crc32_le_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_le_arch);
+
+u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+{
+ unsigned int prealign;
+ unsigned int tail;
+
+ if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) ||
+ !static_branch_likely(&have_vec_crypto) || !crypto_simd_usable())
+ return crc32c_le_base(crc, p, len);
+
+ if ((unsigned long)p & VMX_ALIGN_MASK) {
+ prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+ crc = crc32c_le_base(crc, p, prealign);
+ len -= prealign;
+ p += prealign;
+ }
+
+ if (len & ~VMX_ALIGN_MASK) {
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_altivec();
+ crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+ disable_kernel_altivec();
+ pagefault_enable();
+ preempt_enable();
+ }
+
+ tail = len & VMX_ALIGN_MASK;
+ if (tail) {
+ p += len & ~VMX_ALIGN_MASK;
+ crc = crc32c_le_base(crc, p, tail);
+ }
+
+ return crc;
+}
+EXPORT_SYMBOL(crc32c_le_arch);
+
+u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
+{
+ return crc32_be_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_be_arch);
+
+static int __init crc32_powerpc_init(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+ (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
+ static_branch_enable(&have_vec_crypto);
+ return 0;
+}
+arch_initcall(crc32_powerpc_init);
+
+static void __exit crc32_powerpc_exit(void)
+{
+}
+module_exit(crc32_powerpc_exit);
+
+u32 crc32_optimizations(void)
+{
+ if (static_key_enabled(&have_vec_crypto))
+ return CRC32C_OPTIMIZATION;
+ return 0;
+}
+EXPORT_SYMBOL(crc32_optimizations);
+
+MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
+MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/lib/crc32-vpmsum_core.S
index b0f87f595b26..b0f87f595b26 100644
--- a/arch/powerpc/crypto/crc32-vpmsum_core.S
+++ b/arch/powerpc/lib/crc32-vpmsum_core.S
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/lib/crc32c-vpmsum_asm.S
index bf442004ea1f..bf442004ea1f 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_asm.S
+++ b/arch/powerpc/lib/crc32c-vpmsum_asm.S
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S b/arch/powerpc/lib/crct10dif-vpmsum_asm.S
index f0b93a0fe168..f0b93a0fe168 100644
--- a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
+++ b/arch/powerpc/lib/crct10dif-vpmsum_asm.S
diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
index 7e5e1c28e56a..8967903c15e9 100644
--- a/arch/powerpc/lib/crtsavres.S
+++ b/arch/powerpc/lib/crtsavres.S
@@ -46,7 +46,7 @@
.section ".text"
-#ifndef CONFIG_PPC64
+#ifndef __powerpc64__
/* Routines for saving integer registers, called by the compiler. */
/* Called with r11 pointing to the stack header word of the caller of the */
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 4f82581ca203..587c8cf1230f 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -16,7 +16,7 @@
#include <linux/sched/mm.h>
#include <linux/stop_machine.h>
#include <asm/cputable.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/interrupt.h>
#include <asm/page.h>
#include <asm/sections.h>
@@ -25,6 +25,13 @@
#include <asm/firmware.h>
#include <asm/inst.h>
+/*
+ * Used to generate warnings if mmu or cpu feature check functions that
+ * use static keys before they are initialized.
+ */
+bool static_key_feature_checks_initialized __read_mostly;
+EXPORT_SYMBOL_GPL(static_key_feature_checks_initialized);
+
struct fixup_entry {
unsigned long mask;
unsigned long value;
@@ -679,6 +686,7 @@ void __init setup_feature_keys(void)
jump_label_init();
cpu_feature_keys_init();
mmu_feature_keys_init();
+ static_key_feature_checks_initialized = true;
}
static int __init check_features(void)
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 9398b2b746c4..b7c5e7fca8b9 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -244,15 +244,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
or r7,r7,r0
ori r10,r7,1 /* stream=1 */
- lis r8,0x8000 /* GO=1 */
- clrldi r8,r8,32
-
- dcbt 0,r6,0b01000
- dcbt 0,r7,0b01010
- dcbtst 0,r9,0b01000
- dcbtst 0,r10,0b01010
- eieio
- dcbt 0,r8,0b01010 /* GO */
+ DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8)
beq cr1,.Lunwind_stack_nonvmx_copy
diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index 5de4dd549f6e..bcc7e4dff8c3 100644
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -697,7 +697,15 @@ again:
}
release:
- qnodesp->count--; /* release the node */
+ /*
+ * Clear the lock before releasing the node, as another CPU might see stale
+ * values if an interrupt occurs after we increment qnodesp->count
+ * but before node->lock is initialized. The barrier ensures that
+ * there are no further stores to the node after it has been released.
+ */
+ node->lock = NULL;
+ barrier();
+ qnodesp->count--;
}
void queued_spin_lock_slowpath(struct qspinlock *lock)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 5766180f5380..ac3ee19531d8 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -780,8 +780,8 @@ static nokprobe_inline int emulate_stq(struct pt_regs *regs, unsigned long ea,
#endif /* __powerpc64 */
#ifdef CONFIG_VSX
-void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
- const void *mem, bool rev)
+static nokprobe_inline void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
+ const void *mem, bool rev)
{
int size, read_size;
int i, j;
@@ -863,11 +863,9 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
break;
}
}
-EXPORT_SYMBOL_GPL(emulate_vsx_load);
-NOKPROBE_SYMBOL(emulate_vsx_load);
-void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
- void *mem, bool rev)
+static nokprobe_inline void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
+ void *mem, bool rev)
{
int size, write_size;
int i, j;
@@ -955,8 +953,6 @@ void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
break;
}
}
-EXPORT_SYMBOL_GPL(emulate_vsx_store);
-NOKPROBE_SYMBOL(emulate_vsx_store);
static nokprobe_inline int do_vsx_load(struct instruction_op *op,
unsigned long ea, struct pt_regs *regs,
@@ -1429,7 +1425,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
return 1;
case 18: /* rfid, scary */
- if (regs->msr & MSR_PR)
+ if (user_mode(regs))
goto priv;
op->type = RFI;
return 0;
@@ -1742,13 +1738,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
return 1;
#endif
case 83: /* mfmsr */
- if (regs->msr & MSR_PR)
+ if (user_mode(regs))
goto priv;
op->type = MFMSR;
op->reg = rd;
return 0;
case 146: /* mtmsr */
- if (regs->msr & MSR_PR)
+ if (user_mode(regs))
goto priv;
op->type = MTMSR;
op->reg = rd;
@@ -1756,7 +1752,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
return 0;
#ifdef CONFIG_PPC64
case 178: /* mtmsrd */
- if (regs->msr & MSR_PR)
+ if (user_mode(regs))
goto priv;
op->type = MTMSR;
op->reg = rd;
@@ -3437,14 +3433,14 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
* stored in the thread_struct. If the instruction is in
* the kernel, we must not touch the state in the thread_struct.
*/
- if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP))
+ if (!user_mode(regs) && !(regs->msr & MSR_FP))
return 0;
err = do_fp_load(op, ea, regs, cross_endian);
break;
#endif
#ifdef CONFIG_ALTIVEC
case LOAD_VMX:
- if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC))
+ if (!user_mode(regs) && !(regs->msr & MSR_VEC))
return 0;
err = do_vec_load(op->reg, ea, size, regs, cross_endian);
break;
@@ -3459,7 +3455,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
*/
if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC))
msrbit = MSR_VEC;
- if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit))
+ if (!user_mode(regs) && !(regs->msr & msrbit))
return 0;
err = do_vsx_load(op, ea, regs, cross_endian);
break;
@@ -3495,8 +3491,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
}
#endif
if ((op->type & UPDATE) && size == sizeof(long) &&
- op->reg == 1 && op->update_reg == 1 &&
- !(regs->msr & MSR_PR) &&
+ op->reg == 1 && op->update_reg == 1 && !user_mode(regs) &&
ea >= regs->gpr[1] - STACK_INT_FRAME_SIZE) {
err = handle_stack_update(ea, regs);
break;
@@ -3508,14 +3503,14 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
#ifdef CONFIG_PPC_FPU
case STORE_FP:
- if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP))
+ if (!user_mode(regs) && !(regs->msr & MSR_FP))
return 0;
err = do_fp_store(op, ea, regs, cross_endian);
break;
#endif
#ifdef CONFIG_ALTIVEC
case STORE_VMX:
- if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC))
+ if (!user_mode(regs) && !(regs->msr & MSR_VEC))
return 0;
err = do_vec_store(op->reg, ea, size, regs, cross_endian);
break;
@@ -3530,7 +3525,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
*/
if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC))
msrbit = MSR_VEC;
- if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit))
+ if (!user_mode(regs) && !(regs->msr & msrbit))
return 0;
err = do_vsx_store(op, ea, regs, cross_endian);
break;
diff --git a/arch/powerpc/lib/test-code-patching.c b/arch/powerpc/lib/test-code-patching.c
index c44823292f73..1440d99630b3 100644
--- a/arch/powerpc/lib/test-code-patching.c
+++ b/arch/powerpc/lib/test-code-patching.c
@@ -6,7 +6,7 @@
#include <linux/vmalloc.h>
#include <linux/init.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
static int __init instr_is_branch_to_addr(const u32 *instr, unsigned long addr)
{
@@ -347,6 +347,137 @@ static void __init test_prefixed_patching(void)
check(!memcmp(iptr, expected, sizeof(expected)));
}
+static void __init test_multi_instruction_patching(void)
+{
+ u32 code[32];
+ void *buf;
+ u32 *addr32;
+ u64 *addr64;
+ ppc_inst_t inst64 = ppc_inst_prefix(OP_PREFIX << 26 | 3UL << 24, PPC_RAW_TRAP());
+ u32 inst32 = PPC_RAW_NOP();
+
+ buf = vzalloc(PAGE_SIZE * 8);
+ check(buf);
+ if (!buf)
+ return;
+
+ /* Test single page 32-bit repeated instruction */
+ addr32 = buf + PAGE_SIZE;
+ check(!patch_instructions(addr32 + 1, &inst32, 12, true));
+
+ check(addr32[0] == 0);
+ check(addr32[1] == inst32);
+ check(addr32[2] == inst32);
+ check(addr32[3] == inst32);
+ check(addr32[4] == 0);
+
+ /* Test single page 64-bit repeated instruction */
+ if (IS_ENABLED(CONFIG_PPC64)) {
+ check(ppc_inst_prefixed(inst64));
+
+ addr64 = buf + PAGE_SIZE * 2;
+ ppc_inst_write(code, inst64);
+ check(!patch_instructions((u32 *)(addr64 + 1), code, 24, true));
+
+ check(addr64[0] == 0);
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[1]), inst64));
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[2]), inst64));
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[3]), inst64));
+ check(addr64[4] == 0);
+ }
+
+ /* Test single page memcpy */
+ addr32 = buf + PAGE_SIZE * 3;
+
+ for (int i = 0; i < ARRAY_SIZE(code); i++)
+ code[i] = i + 1;
+
+ check(!patch_instructions(addr32 + 1, code, sizeof(code), false));
+
+ check(addr32[0] == 0);
+ check(!memcmp(&addr32[1], code, sizeof(code)));
+ check(addr32[ARRAY_SIZE(code) + 1] == 0);
+
+ /* Test multipage 32-bit repeated instruction */
+ addr32 = buf + PAGE_SIZE * 4 - 8;
+ check(!patch_instructions(addr32 + 1, &inst32, 12, true));
+
+ check(addr32[0] == 0);
+ check(addr32[1] == inst32);
+ check(addr32[2] == inst32);
+ check(addr32[3] == inst32);
+ check(addr32[4] == 0);
+
+ /* Test multipage 64-bit repeated instruction */
+ if (IS_ENABLED(CONFIG_PPC64)) {
+ check(ppc_inst_prefixed(inst64));
+
+ addr64 = buf + PAGE_SIZE * 5 - 8;
+ ppc_inst_write(code, inst64);
+ check(!patch_instructions((u32 *)(addr64 + 1), code, 24, true));
+
+ check(addr64[0] == 0);
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[1]), inst64));
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[2]), inst64));
+ check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[3]), inst64));
+ check(addr64[4] == 0);
+ }
+
+ /* Test multipage memcpy */
+ addr32 = buf + PAGE_SIZE * 6 - 12;
+
+ for (int i = 0; i < ARRAY_SIZE(code); i++)
+ code[i] = i + 1;
+
+ check(!patch_instructions(addr32 + 1, code, sizeof(code), false));
+
+ check(addr32[0] == 0);
+ check(!memcmp(&addr32[1], code, sizeof(code)));
+ check(addr32[ARRAY_SIZE(code) + 1] == 0);
+
+ vfree(buf);
+}
+
+static void __init test_data_patching(void)
+{
+ void *buf;
+ u32 *addr32;
+
+ buf = vzalloc(PAGE_SIZE);
+ check(buf);
+ if (!buf)
+ return;
+
+ addr32 = buf + 128;
+
+ addr32[1] = 0xA0A1A2A3;
+ addr32[2] = 0xB0B1B2B3;
+
+ check(!patch_uint(&addr32[1], 0xC0C1C2C3));
+
+ check(addr32[0] == 0);
+ check(addr32[1] == 0xC0C1C2C3);
+ check(addr32[2] == 0xB0B1B2B3);
+ check(addr32[3] == 0);
+
+ /* Unaligned patch_ulong() should fail */
+ if (IS_ENABLED(CONFIG_PPC64))
+ check(patch_ulong(&addr32[1], 0xD0D1D2D3) == -EINVAL);
+
+ check(!patch_ulong(&addr32[2], 0xD0D1D2D3));
+
+ check(addr32[0] == 0);
+ check(addr32[1] == 0xC0C1C2C3);
+ check(*(unsigned long *)(&addr32[2]) == 0xD0D1D2D3);
+
+ if (!IS_ENABLED(CONFIG_PPC64))
+ check(addr32[3] == 0);
+
+ check(addr32[4] == 0);
+
+ vfree(buf);
+}
+
static int __init test_code_patching(void)
{
pr_info("Running code patching self-tests ...\n");
@@ -356,6 +487,8 @@ static int __init test_code_patching(void)
test_create_function_call();
test_translate_branch();
test_prefixed_patching();
+ test_multi_instruction_patching();
+ test_data_patching();
return 0;
}
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 23c7805fb7b3..66b5b4fa1686 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -11,7 +11,7 @@
#include <asm/cpu_has_feature.h>
#include <asm/sstep.h>
#include <asm/ppc-opcode.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/inst.h>
#define MAX_SUBTESTS 16
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index d491da8d1838..58ed6bd613a6 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -45,7 +45,7 @@ int exit_vmx_usercopy(void)
* set and we are preemptible. The hack here is to schedule a
* decrementer to fire here and reschedule for us if necessary.
*/
- if (IS_ENABLED(CONFIG_PREEMPT) && need_resched())
+ if (IS_ENABLED(CONFIG_PREEMPTION) && need_resched())
set_dec(1);
return 0;
}
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 503a6e249940..0fe2f085c05a 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -3,8 +3,6 @@
# Makefile for the linux ppc-specific parts of the memory manager.
#
-ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-
obj-y := fault.o mem.o pgtable.o maccess.o pageattr.o \
init_$(BITS).o pgtable_$(BITS).o \
pgtable-frag.o ioremap.o ioremap_$(BITS).o \
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 5445587bfe84..be9c4106e22f 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -25,7 +25,7 @@
#include <asm/mmu.h>
#include <asm/machdep.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/sections.h>
#include <mm/mmu_decl.h>
@@ -184,7 +184,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
static bool is_module_segment(unsigned long addr)
{
- if (!IS_ENABLED(CONFIG_MODULES))
+ if (!IS_ENABLED(CONFIG_EXECMEM))
return false;
if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M))
return false;
@@ -193,7 +193,7 @@ static bool is_module_segment(unsigned long addr)
return true;
}
-void mmu_mark_initmem_nx(void)
+int mmu_mark_initmem_nx(void)
{
int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
int i;
@@ -223,6 +223,8 @@ void mmu_mark_initmem_nx(void)
update_bats();
+ BUILD_BUG_ON(ALIGN_DOWN(MODULES_VADDR, SZ_256M) < TASK_SIZE);
+
for (i = TASK_SIZE >> 28; i < 16; i++) {
/* Do not set NX on VM space for modules */
if (is_module_segment(i << 28))
@@ -230,9 +232,10 @@ void mmu_mark_initmem_nx(void)
mtsr(mfsr(i << 28) | 0x10000000, i << 28);
}
+ return 0;
}
-void mmu_mark_rodata_ro(void)
+int mmu_mark_rodata_ro(void)
{
int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
int i;
@@ -245,6 +248,8 @@ void mmu_mark_rodata_ro(void)
}
update_bats();
+
+ return 0;
}
/*
@@ -372,10 +377,7 @@ void __init MMU_init_hw(void)
* Find some memory for the hash table.
*/
if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
- Hash = memblock_alloc(Hash_size, Hash_size);
- if (!Hash)
- panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
- __func__, Hash_size, Hash_size);
+ Hash = memblock_alloc_or_panic(Hash_size, Hash_size);
_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
pr_info("Total memory = %lldMB; using %ldkB for hash table\n",
diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile
index cad2abc1730f..33af5795856a 100644
--- a/arch/powerpc/mm/book3s64/Makefile
+++ b/arch/powerpc/mm/book3s64/Makefile
@@ -1,7 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-ccflags-y := $(NO_MINIMAL_TOC)
-
obj-y += mmu_context.o pgtable.o trace.o
ifdef CONFIG_PPC_64S_HASH_MMU
CFLAGS_REMOVE_slb.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/powerpc/mm/book3s64/hash_hugepage.c b/arch/powerpc/mm/book3s64/hash_hugepage.c
index c0fabe6c5a12..15d6f3ea7178 100644
--- a/arch/powerpc/mm/book3s64/hash_hugepage.c
+++ b/arch/powerpc/mm/book3s64/hash_hugepage.c
@@ -59,16 +59,13 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
rflags = htab_convert_pte_flags(new_pmd, flags);
-#if 0
- if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
+ /*
+ * THPs are only supported on platforms that can do mixed page size
+ * segments (MPSS) and all such platforms have coherent icache. Hence we
+ * don't need to do lazy icache flush (hash_page_do_lazy_icache()) on
+ * noexecute fault.
+ */
- /*
- * No CPU has hugepages but lacks no execute, so we
- * don't need to worry about that case
- */
- rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
- }
-#endif
/*
* Find the slot index details for this ea, using base page size.
*/
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 0626a25b0d72..c8b4fa71d4a7 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -40,6 +40,7 @@
#include <linux/random.h>
#include <linux/elf-randomize.h>
#include <linux/of_fdt.h>
+#include <linux/kfence.h>
#include <asm/interrupt.h>
#include <asm/processor.h>
@@ -57,7 +58,7 @@
#include <asm/sections.h>
#include <asm/copro.h>
#include <asm/udbg.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/fadump.h>
#include <asm/firmware.h>
#include <asm/tm.h>
@@ -66,6 +67,7 @@
#include <asm/pte-walk.h>
#include <asm/asm-prototypes.h>
#include <asm/ultravisor.h>
+#include <asm/kfence.h>
#include <mm/mmu_decl.h>
@@ -123,9 +125,7 @@ EXPORT_SYMBOL_GPL(mmu_slb_size);
#ifdef CONFIG_PPC_64K_PAGES
int mmu_ci_restrictions;
#endif
-static u8 *linear_map_hash_slots;
-static unsigned long linear_map_hash_count;
-struct mmu_hash_ops mmu_hash_ops;
+struct mmu_hash_ops mmu_hash_ops __ro_after_init;
EXPORT_SYMBOL(mmu_hash_ops);
/*
@@ -273,6 +273,270 @@ void hash__tlbiel_all(unsigned int action)
WARN(1, "%s called on pre-POWER7 CPU\n", __func__);
}
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+static void kernel_map_linear_page(unsigned long vaddr, unsigned long idx,
+ u8 *slots, raw_spinlock_t *lock)
+{
+ unsigned long hash;
+ unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
+ unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
+ unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL), HPTE_USE_KERNEL_KEY);
+ long ret;
+
+ hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
+
+ /* Don't create HPTE entries for bad address */
+ if (!vsid)
+ return;
+
+ if (slots[idx] & 0x80)
+ return;
+
+ ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode,
+ HPTE_V_BOLTED,
+ mmu_linear_psize, mmu_kernel_ssize);
+
+ BUG_ON (ret < 0);
+ raw_spin_lock(lock);
+ BUG_ON(slots[idx] & 0x80);
+ slots[idx] = ret | 0x80;
+ raw_spin_unlock(lock);
+}
+
+static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long idx,
+ u8 *slots, raw_spinlock_t *lock)
+{
+ unsigned long hash, hslot, slot;
+ unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
+ unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
+
+ hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
+ raw_spin_lock(lock);
+ if (!(slots[idx] & 0x80)) {
+ raw_spin_unlock(lock);
+ return;
+ }
+ hslot = slots[idx] & 0x7f;
+ slots[idx] = 0;
+ raw_spin_unlock(lock);
+ if (hslot & _PTEIDX_SECONDARY)
+ hash = ~hash;
+ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+ slot += hslot & _PTEIDX_GROUP_IX;
+ mmu_hash_ops.hpte_invalidate(slot, vpn, mmu_linear_psize,
+ mmu_linear_psize,
+ mmu_kernel_ssize, 0);
+}
+#endif
+
+static inline bool hash_supports_debug_pagealloc(void)
+{
+ unsigned long max_hash_count = ppc64_rma_size / 4;
+ unsigned long linear_map_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
+
+ if (!debug_pagealloc_enabled() || linear_map_count > max_hash_count)
+ return false;
+ return true;
+}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+static u8 *linear_map_hash_slots;
+static unsigned long linear_map_hash_count;
+static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
+static void hash_debug_pagealloc_alloc_slots(void)
+{
+ if (!hash_supports_debug_pagealloc())
+ return;
+
+ linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
+ linear_map_hash_slots = memblock_alloc_try_nid(
+ linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT,
+ ppc64_rma_size, NUMA_NO_NODE);
+ if (!linear_map_hash_slots)
+ panic("%s: Failed to allocate %lu bytes max_addr=%pa\n",
+ __func__, linear_map_hash_count, &ppc64_rma_size);
+}
+
+static inline void hash_debug_pagealloc_add_slot(phys_addr_t paddr,
+ int slot)
+{
+ if (!debug_pagealloc_enabled() || !linear_map_hash_count)
+ return;
+ if ((paddr >> PAGE_SHIFT) < linear_map_hash_count)
+ linear_map_hash_slots[paddr >> PAGE_SHIFT] = slot | 0x80;
+}
+
+static int hash_debug_pagealloc_map_pages(struct page *page, int numpages,
+ int enable)
+{
+ unsigned long flags, vaddr, lmi;
+ int i;
+
+ if (!debug_pagealloc_enabled() || !linear_map_hash_count)
+ return 0;
+
+ local_irq_save(flags);
+ for (i = 0; i < numpages; i++, page++) {
+ vaddr = (unsigned long)page_address(page);
+ lmi = __pa(vaddr) >> PAGE_SHIFT;
+ if (lmi >= linear_map_hash_count)
+ continue;
+ if (enable)
+ kernel_map_linear_page(vaddr, lmi,
+ linear_map_hash_slots, &linear_map_hash_lock);
+ else
+ kernel_unmap_linear_page(vaddr, lmi,
+ linear_map_hash_slots, &linear_map_hash_lock);
+ }
+ local_irq_restore(flags);
+ return 0;
+}
+
+#else /* CONFIG_DEBUG_PAGEALLOC */
+static inline void hash_debug_pagealloc_alloc_slots(void) {}
+static inline void hash_debug_pagealloc_add_slot(phys_addr_t paddr, int slot) {}
+static int __maybe_unused
+hash_debug_pagealloc_map_pages(struct page *page, int numpages, int enable)
+{
+ return 0;
+}
+#endif /* CONFIG_DEBUG_PAGEALLOC */
+
+#ifdef CONFIG_KFENCE
+static u8 *linear_map_kf_hash_slots;
+static unsigned long linear_map_kf_hash_count;
+static DEFINE_RAW_SPINLOCK(linear_map_kf_hash_lock);
+
+static phys_addr_t kfence_pool;
+
+static inline void hash_kfence_alloc_pool(void)
+{
+ if (!kfence_early_init_enabled())
+ goto err;
+
+ /* allocate linear map for kfence within RMA region */
+ linear_map_kf_hash_count = KFENCE_POOL_SIZE >> PAGE_SHIFT;
+ linear_map_kf_hash_slots = memblock_alloc_try_nid(
+ linear_map_kf_hash_count, 1,
+ MEMBLOCK_LOW_LIMIT, ppc64_rma_size,
+ NUMA_NO_NODE);
+ if (!linear_map_kf_hash_slots) {
+ pr_err("%s: memblock for linear map (%lu) failed\n", __func__,
+ linear_map_kf_hash_count);
+ goto err;
+ }
+
+ /* allocate kfence pool early */
+ kfence_pool = memblock_phys_alloc_range(KFENCE_POOL_SIZE, PAGE_SIZE,
+ MEMBLOCK_LOW_LIMIT, MEMBLOCK_ALLOC_ANYWHERE);
+ if (!kfence_pool) {
+ pr_err("%s: memblock for kfence pool (%lu) failed\n", __func__,
+ KFENCE_POOL_SIZE);
+ memblock_free(linear_map_kf_hash_slots,
+ linear_map_kf_hash_count);
+ linear_map_kf_hash_count = 0;
+ goto err;
+ }
+ memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
+
+ return;
+err:
+ pr_info("Disabling kfence\n");
+ disable_kfence();
+}
+
+static inline void hash_kfence_map_pool(void)
+{
+ unsigned long kfence_pool_start, kfence_pool_end;
+ unsigned long prot = pgprot_val(PAGE_KERNEL);
+
+ if (!kfence_pool)
+ return;
+
+ kfence_pool_start = (unsigned long) __va(kfence_pool);
+ kfence_pool_end = kfence_pool_start + KFENCE_POOL_SIZE;
+ __kfence_pool = (char *) kfence_pool_start;
+ BUG_ON(htab_bolt_mapping(kfence_pool_start, kfence_pool_end,
+ kfence_pool, prot, mmu_linear_psize,
+ mmu_kernel_ssize));
+ memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
+}
+
+static inline void hash_kfence_add_slot(phys_addr_t paddr, int slot)
+{
+ unsigned long vaddr = (unsigned long) __va(paddr);
+ unsigned long lmi = (vaddr - (unsigned long)__kfence_pool)
+ >> PAGE_SHIFT;
+
+ if (!kfence_pool)
+ return;
+ BUG_ON(!is_kfence_address((void *)vaddr));
+ BUG_ON(lmi >= linear_map_kf_hash_count);
+ linear_map_kf_hash_slots[lmi] = slot | 0x80;
+}
+
+static int hash_kfence_map_pages(struct page *page, int numpages, int enable)
+{
+ unsigned long flags, vaddr, lmi;
+ int i;
+
+ WARN_ON_ONCE(!linear_map_kf_hash_count);
+ local_irq_save(flags);
+ for (i = 0; i < numpages; i++, page++) {
+ vaddr = (unsigned long)page_address(page);
+ lmi = (vaddr - (unsigned long)__kfence_pool) >> PAGE_SHIFT;
+
+ /* Ideally this should never happen */
+ if (lmi >= linear_map_kf_hash_count) {
+ WARN_ON_ONCE(1);
+ continue;
+ }
+
+ if (enable)
+ kernel_map_linear_page(vaddr, lmi,
+ linear_map_kf_hash_slots,
+ &linear_map_kf_hash_lock);
+ else
+ kernel_unmap_linear_page(vaddr, lmi,
+ linear_map_kf_hash_slots,
+ &linear_map_kf_hash_lock);
+ }
+ local_irq_restore(flags);
+ return 0;
+}
+#else
+static inline void hash_kfence_alloc_pool(void) {}
+static inline void hash_kfence_map_pool(void) {}
+static inline void hash_kfence_add_slot(phys_addr_t paddr, int slot) {}
+static int __maybe_unused
+hash_kfence_map_pages(struct page *page, int numpages, int enable)
+{
+ return 0;
+}
+#endif
+
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+int hash__kernel_map_pages(struct page *page, int numpages, int enable)
+{
+ void *vaddr = page_address(page);
+
+ if (is_kfence_address(vaddr))
+ return hash_kfence_map_pages(page, numpages, enable);
+ else
+ return hash_debug_pagealloc_map_pages(page, numpages, enable);
+}
+
+static void hash_linear_map_add_slot(phys_addr_t paddr, int slot)
+{
+ if (is_kfence_address(__va(paddr)))
+ hash_kfence_add_slot(paddr, slot);
+ else
+ hash_debug_pagealloc_add_slot(paddr, slot);
+}
+#else
+static void hash_linear_map_add_slot(phys_addr_t paddr, int slot) {}
+#endif
+
/*
* 'R' and 'C' update notes:
* - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
@@ -431,9 +695,8 @@ repeat:
break;
cond_resched();
- if (debug_pagealloc_enabled_or_kfence() &&
- (paddr >> PAGE_SHIFT) < linear_map_hash_count)
- linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
+ /* add slot info in debug_pagealloc / kfence linear map */
+ hash_linear_map_add_slot(paddr, ret);
}
return ret < 0 ? ret : 0;
}
@@ -814,7 +1077,7 @@ static void __init htab_init_page_sizes(void)
bool aligned = true;
init_hpte_page_sizes();
- if (!debug_pagealloc_enabled_or_kfence()) {
+ if (!hash_supports_debug_pagealloc() && !kfence_early_init_enabled()) {
/*
* Pick a size for the linear mapping. Currently, we only
* support 16M, 1M and 4K which is the default
@@ -1134,16 +1397,8 @@ static void __init htab_initialize(void)
prot = pgprot_val(PAGE_KERNEL);
- if (debug_pagealloc_enabled_or_kfence()) {
- linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
- linear_map_hash_slots = memblock_alloc_try_nid(
- linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT,
- ppc64_rma_size, NUMA_NO_NODE);
- if (!linear_map_hash_slots)
- panic("%s: Failed to allocate %lu bytes max_addr=%pa\n",
- __func__, linear_map_hash_count, &ppc64_rma_size);
- }
-
+ hash_debug_pagealloc_alloc_slots();
+ hash_kfence_alloc_pool();
/* create bolted the linear mapping in the hash table */
for_each_mem_range(i, &base, &end) {
size = end - base;
@@ -1160,6 +1415,7 @@ static void __init htab_initialize(void)
BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
prot, mmu_linear_psize, mmu_kernel_ssize));
}
+ hash_kfence_map_pool();
memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
/*
@@ -1233,10 +1489,6 @@ void __init hash__early_init_mmu(void)
__pmd_table_size = H_PMD_TABLE_SIZE;
__pud_table_size = H_PUD_TABLE_SIZE;
__pgd_table_size = H_PGD_TABLE_SIZE;
- /*
- * 4k use hugepd format, so for hash set then to
- * zero
- */
__pmd_val_bits = HASH_PMD_VAL_BITS;
__pud_val_bits = HASH_PUD_VAL_BITS;
__pgd_val_bits = HASH_PGD_VAL_BITS;
@@ -1546,6 +1798,13 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
goto bail;
}
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled()) {
+ if (hugeshift == PMD_SHIFT && psize == MMU_PAGE_16M)
+ hugeshift = mmu_psize_defs[MMU_PAGE_16M].shift;
+ if (hugeshift == PUD_SHIFT && psize == MMU_PAGE_16G)
+ hugeshift = mmu_psize_defs[MMU_PAGE_16G].shift;
+ }
+
/*
* Add _PAGE_PRESENT to the required access perm. If there are parallel
* updates to the pte that can possibly clear _PAGE_PTE, catch that too.
@@ -2117,81 +2376,6 @@ void hpt_do_stress(unsigned long ea, unsigned long hpte_group)
}
}
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
-
-static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
-{
- unsigned long hash;
- unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
- unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
- unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL), HPTE_USE_KERNEL_KEY);
- long ret;
-
- hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
-
- /* Don't create HPTE entries for bad address */
- if (!vsid)
- return;
-
- if (linear_map_hash_slots[lmi] & 0x80)
- return;
-
- ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode,
- HPTE_V_BOLTED,
- mmu_linear_psize, mmu_kernel_ssize);
-
- BUG_ON (ret < 0);
- raw_spin_lock(&linear_map_hash_lock);
- BUG_ON(linear_map_hash_slots[lmi] & 0x80);
- linear_map_hash_slots[lmi] = ret | 0x80;
- raw_spin_unlock(&linear_map_hash_lock);
-}
-
-static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
-{
- unsigned long hash, hidx, slot;
- unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
- unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
-
- hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
- raw_spin_lock(&linear_map_hash_lock);
- if (!(linear_map_hash_slots[lmi] & 0x80)) {
- raw_spin_unlock(&linear_map_hash_lock);
- return;
- }
- hidx = linear_map_hash_slots[lmi] & 0x7f;
- linear_map_hash_slots[lmi] = 0;
- raw_spin_unlock(&linear_map_hash_lock);
- if (hidx & _PTEIDX_SECONDARY)
- hash = ~hash;
- slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
- slot += hidx & _PTEIDX_GROUP_IX;
- mmu_hash_ops.hpte_invalidate(slot, vpn, mmu_linear_psize,
- mmu_linear_psize,
- mmu_kernel_ssize, 0);
-}
-
-void hash__kernel_map_pages(struct page *page, int numpages, int enable)
-{
- unsigned long flags, vaddr, lmi;
- int i;
-
- local_irq_save(flags);
- for (i = 0; i < numpages; i++, page++) {
- vaddr = (unsigned long)page_address(page);
- lmi = __pa(vaddr) >> PAGE_SHIFT;
- if (lmi >= linear_map_hash_count)
- continue;
- if (enable)
- kernel_map_linear_page(vaddr, lmi);
- else
- kernel_unmap_linear_page(vaddr, lmi);
- }
- local_irq_restore(flags);
-}
-#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_KFENCE */
-
void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
phys_addr_t first_memblock_size)
{
diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c
index 5a2e512e96db..83c3361b358b 100644
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -53,6 +53,16 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
/* If PTE permissions don't match, take page fault */
if (unlikely(!check_pte_access(access, old_pte)))
return 1;
+ /*
+ * If hash-4k, hugepages use seeral contiguous PxD entries
+ * so bail out and let mm make the page young or dirty
+ */
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES)) {
+ if (!(old_pte & _PAGE_ACCESSED))
+ return 1;
+ if ((access & _PAGE_WRITE) && !(old_pte & _PAGE_DIRTY))
+ return 1;
+ }
/*
* Try to lock the PTE, add ACCESSED and DIRTY if it was
diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c
index 1715b07c630c..4e1e45420bd4 100644
--- a/arch/powerpc/mm/book3s64/mmu_context.c
+++ b/arch/powerpc/mm/book3s64/mmu_context.c
@@ -253,7 +253,7 @@ static void pmd_frag_destroy(void *pmd_frag)
count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT;
/* We allow PTE_FRAG_NR fragments from a PTE page */
if (atomic_sub_and_test(PMD_FRAG_NR - count, &ptdesc->pt_frag_refcount)) {
- pagetable_pmd_dtor(ptdesc);
+ pagetable_dtor(ptdesc);
pagetable_free(ptdesc);
}
}
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 3438ab72c346..ce64abea9e3e 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -37,6 +37,19 @@ EXPORT_SYMBOL(__pmd_frag_nr);
unsigned long __pmd_frag_size_shift;
EXPORT_SYMBOL(__pmd_frag_size_shift);
+#ifdef CONFIG_KFENCE
+extern bool kfence_early_init;
+static int __init parse_kfence_early_init(char *arg)
+{
+ int val;
+
+ if (get_option(&arg, &val))
+ kfence_early_init = !!val;
+ return 0;
+}
+early_param("kfence.sample_interval", parse_kfence_early_init);
+#endif
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* This is called when relaxing access to a hugepage. It's also called in the page
@@ -113,7 +126,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
WARN_ON(pte_hw_valid(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
assert_spin_locked(pmd_lockptr(mm, pmdp));
- WARN_ON(!(pmd_large(pmd)));
+ WARN_ON(!(pmd_leaf(pmd)));
#endif
trace_hugepage_set_pmd(addr, pmd_val(pmd));
return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
@@ -130,7 +143,7 @@ void set_pud_at(struct mm_struct *mm, unsigned long addr,
WARN_ON(pte_hw_valid(pud_pte(*pudp)));
assert_spin_locked(pud_lockptr(mm, pudp));
- WARN_ON(!(pud_large(pud)));
+ WARN_ON(!(pud_leaf(pud)));
#endif
trace_hugepage_set_pud(addr, pud_val(pud));
return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud));
@@ -170,11 +183,23 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
{
unsigned long old_pmd;
+ VM_WARN_ON_ONCE(!pmd_present(*pmdp));
old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID);
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return __pmd(old_pmd);
}
+pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pudp)
+{
+ unsigned long old_pud;
+
+ VM_WARN_ON_ONCE(!pud_present(*pudp));
+ old_pud = pud_hugepage_update(vma->vm_mm, address, pudp, _PAGE_PRESENT, _PAGE_INVALID);
+ flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+ return __pud(old_pud);
+}
+
pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp, int full)
{
@@ -258,6 +283,15 @@ pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
pmdv &= _HPAGE_CHG_MASK;
return pmd_set_protbits(__pmd(pmdv), newprot);
}
+
+pud_t pud_modify(pud_t pud, pgprot_t newprot)
+{
+ unsigned long pudv;
+
+ pudv = pud_val(pud);
+ pudv &= _HPAGE_CHG_MASK;
+ return pud_set_protbits(__pud(pudv), newprot);
+}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/* For use by kexec, called with MMU off */
@@ -296,11 +330,7 @@ void __init mmu_partition_table_init(void)
unsigned long ptcr;
/* Initialize the Partition Table with no entries */
- partition_tb = memblock_alloc(patb_size, patb_size);
- if (!partition_tb)
- panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
- __func__, patb_size, patb_size);
-
+ partition_tb = memblock_alloc_or_panic(patb_size, patb_size);
ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12);
set_ptcr_when_no_uv(ptcr);
powernv_set_nmmu_ptcr(ptcr);
@@ -443,7 +473,7 @@ void pmd_fragment_free(unsigned long *pmd)
BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0);
if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) {
- pagetable_pmd_dtor(ptdesc);
+ pagetable_dtor(ptdesc);
pagetable_free(ptdesc);
}
}
@@ -460,18 +490,6 @@ static inline void pgtable_free(void *table, int index)
case PUD_INDEX:
__pud_free(table);
break;
-#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
- /* 16M hugepd directory at pud level */
- case HTLB_16M_INDEX:
- BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0);
- kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table);
- break;
- /* 16G hugepd directory at the pgd level */
- case HTLB_16G_INDEX:
- BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0);
- kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table);
- break;
-#endif
/* We don't free pgd table via RCU callback */
default:
BUG();
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index c6a4ac766b2b..311e2112d782 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -17,6 +17,7 @@
#include <linux/hugetlb.h>
#include <linux/string_helpers.h>
#include <linux/memory.h>
+#include <linux/kfence.h>
#include <asm/pgalloc.h>
#include <asm/mmu_context.h>
@@ -31,6 +32,7 @@
#include <asm/uaccess.h>
#include <asm/ultravisor.h>
#include <asm/set_memory.h>
+#include <asm/kfence.h>
#include <trace/events/thp.h>
@@ -204,14 +206,14 @@ static void radix__change_memory_range(unsigned long start, unsigned long end,
pudp = pud_alloc(&init_mm, p4dp, idx);
if (!pudp)
continue;
- if (pud_is_leaf(*pudp)) {
+ if (pud_leaf(*pudp)) {
ptep = (pte_t *)pudp;
goto update_the_pte;
}
pmdp = pmd_alloc(&init_mm, pudp, idx);
if (!pmdp)
continue;
- if (pmd_is_leaf(*pmdp)) {
+ if (pmd_leaf(*pmdp)) {
ptep = pmdp_ptep(pmdp);
goto update_the_pte;
}
@@ -293,7 +295,8 @@ static unsigned long next_boundary(unsigned long addr, unsigned long end)
static int __meminit create_physical_mapping(unsigned long start,
unsigned long end,
- int nid, pgprot_t _prot)
+ int nid, pgprot_t _prot,
+ unsigned long mapping_sz_limit)
{
unsigned long vaddr, addr, mapping_size = 0;
bool prev_exec, exec = false;
@@ -301,7 +304,10 @@ static int __meminit create_physical_mapping(unsigned long start,
int psize;
unsigned long max_mapping_size = memory_block_size;
- if (debug_pagealloc_enabled_or_kfence())
+ if (mapping_sz_limit < max_mapping_size)
+ max_mapping_size = mapping_sz_limit;
+
+ if (debug_pagealloc_enabled())
max_mapping_size = PAGE_SIZE;
start = ALIGN(start, PAGE_SIZE);
@@ -356,8 +362,62 @@ static int __meminit create_physical_mapping(unsigned long start,
return 0;
}
+#ifdef CONFIG_KFENCE
+static inline phys_addr_t alloc_kfence_pool(void)
+{
+ phys_addr_t kfence_pool;
+
+ /*
+ * TODO: Support to enable KFENCE after bootup depends on the ability to
+ * split page table mappings. As such support is not currently
+ * implemented for radix pagetables, support enabling KFENCE
+ * only at system startup for now.
+ *
+ * After support for splitting mappings is available on radix,
+ * alloc_kfence_pool() & map_kfence_pool() can be dropped and
+ * mapping for __kfence_pool memory can be
+ * split during arch_kfence_init_pool().
+ */
+ if (!kfence_early_init)
+ goto no_kfence;
+
+ kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
+ if (!kfence_pool)
+ goto no_kfence;
+
+ memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
+ return kfence_pool;
+
+no_kfence:
+ disable_kfence();
+ return 0;
+}
+
+static inline void map_kfence_pool(phys_addr_t kfence_pool)
+{
+ if (!kfence_pool)
+ return;
+
+ if (create_physical_mapping(kfence_pool, kfence_pool + KFENCE_POOL_SIZE,
+ -1, PAGE_KERNEL, PAGE_SIZE))
+ goto err;
+
+ memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
+ __kfence_pool = __va(kfence_pool);
+ return;
+
+err:
+ memblock_phys_free(kfence_pool, KFENCE_POOL_SIZE);
+ disable_kfence();
+}
+#else
+static inline phys_addr_t alloc_kfence_pool(void) { return 0; }
+static inline void map_kfence_pool(phys_addr_t kfence_pool) { }
+#endif
+
static void __init radix_init_pgtable(void)
{
+ phys_addr_t kfence_pool;
unsigned long rts_field;
phys_addr_t start, end;
u64 i;
@@ -365,6 +425,8 @@ static void __init radix_init_pgtable(void)
/* We don't support slb for radix */
slb_set_size(0);
+ kfence_pool = alloc_kfence_pool();
+
/*
* Create the linear mapping
*/
@@ -381,9 +443,11 @@ static void __init radix_init_pgtable(void)
}
WARN_ON(create_physical_mapping(start, end,
- -1, PAGE_KERNEL));
+ -1, PAGE_KERNEL, ~0UL));
}
+ map_kfence_pool(kfence_pool);
+
if (!cpu_has_feature(CPU_FTR_HVMODE) &&
cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
/*
@@ -767,7 +831,7 @@ static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
if (!pmd_present(*pmd))
continue;
- if (pmd_is_leaf(*pmd)) {
+ if (pmd_leaf(*pmd)) {
if (IS_ALIGNED(addr, PMD_SIZE) &&
IS_ALIGNED(next, PMD_SIZE)) {
if (!direct)
@@ -807,7 +871,7 @@ static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr,
if (!pud_present(*pud))
continue;
- if (pud_is_leaf(*pud)) {
+ if (pud_leaf(*pud)) {
if (!IS_ALIGNED(addr, PUD_SIZE) ||
!IS_ALIGNED(next, PUD_SIZE)) {
WARN_ONCE(1, "%s: unaligned range\n", __func__);
@@ -845,7 +909,7 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct,
if (!p4d_present(*p4d))
continue;
- if (p4d_is_leaf(*p4d)) {
+ if (p4d_leaf(*p4d)) {
if (!IS_ALIGNED(addr, P4D_SIZE) ||
!IS_ALIGNED(next, P4D_SIZE)) {
WARN_ONCE(1, "%s: unaligned range\n", __func__);
@@ -875,7 +939,7 @@ int __meminit radix__create_section_mapping(unsigned long start,
}
return create_physical_mapping(__pa(start), __pa(end),
- nid, prot);
+ nid, prot, ~0UL);
}
int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
@@ -924,7 +988,7 @@ bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
unsigned long addr, unsigned long next)
{
- int large = pmd_large(*pmdp);
+ int large = pmd_leaf(*pmdp);
if (large)
vmemmap_verify(pmdp_ptep(pmdp), node, addr, next);
@@ -1339,20 +1403,6 @@ void __ref radix__vmemmap_free(unsigned long start, unsigned long end,
#endif
#endif
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-void radix__kernel_map_pages(struct page *page, int numpages, int enable)
-{
- unsigned long addr;
-
- addr = (unsigned long)page_address(page);
-
- if (enable)
- set_memory_p(addr, numpages);
- else
- set_memory_np(addr, numpages);
-}
-#endif
-
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
@@ -1554,7 +1604,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
int pud_clear_huge(pud_t *pud)
{
- if (pud_is_leaf(*pud)) {
+ if (pud_leaf(*pud)) {
pud_clear(pud);
return 1;
}
@@ -1601,7 +1651,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
int pmd_clear_huge(pmd_t *pmd)
{
- if (pmd_is_leaf(*pmd)) {
+ if (pmd_leaf(*pmd)) {
pmd_clear(pmd);
return 1;
}
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index f2708c8629a5..6b783552403c 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -24,7 +24,7 @@
#include <linux/pgtable.h>
#include <asm/udbg.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include "internal.h"
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index c0b58afb9a47..bc9a39821d1c 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -282,12 +282,10 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
{
int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
unsigned long found, next_end;
- struct vm_unmapped_area_info info;
-
- info.flags = 0;
- info.length = len;
- info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
- info.align_offset = 0;
+ struct vm_unmapped_area_info info = {
+ .length = len,
+ .align_mask = PAGE_MASK & ((1ul << pshift) - 1),
+ };
/*
* Check till the allow max value for this mmap request
*/
@@ -326,13 +324,13 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
{
int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
unsigned long found, prev;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {
+ .flags = VM_UNMAPPED_AREA_TOPDOWN,
+ .length = len,
+ .align_mask = PAGE_MASK & ((1ul << pshift) - 1),
+ };
unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr);
- info.flags = VM_UNMAPPED_AREA_TOPDOWN;
- info.length = len;
- info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
- info.align_offset = 0;
/*
* If we are trying to allocate above DEFAULT_MAP_WINDOW
* Add the different to the mmap_base.
@@ -635,30 +633,58 @@ return_addr:
}
EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
+#ifdef CONFIG_HUGETLB_PAGE
+static int file_to_psize(struct file *file)
+{
+ struct hstate *hstate = hstate_file(file);
+
+ return shift_to_mmu_psize(huge_page_shift(hstate));
+}
+#else
+static int file_to_psize(struct file *file)
+{
+ return 0;
+}
+#endif
+
unsigned long arch_get_unmapped_area(struct file *filp,
unsigned long addr,
unsigned long len,
unsigned long pgoff,
- unsigned long flags)
+ unsigned long flags,
+ vm_flags_t vm_flags)
{
+ unsigned int psize;
+
if (radix_enabled())
- return generic_get_unmapped_area(filp, addr, len, pgoff, flags);
+ return generic_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags);
- return slice_get_unmapped_area(addr, len, flags,
- mm_ctx_user_psize(&current->mm->context), 0);
+ if (filp && is_file_hugepages(filp))
+ psize = file_to_psize(filp);
+ else
+ psize = mm_ctx_user_psize(&current->mm->context);
+
+ return slice_get_unmapped_area(addr, len, flags, psize, 0);
}
unsigned long arch_get_unmapped_area_topdown(struct file *filp,
const unsigned long addr0,
const unsigned long len,
const unsigned long pgoff,
- const unsigned long flags)
+ const unsigned long flags,
+ vm_flags_t vm_flags)
{
+ unsigned int psize;
+
if (radix_enabled())
- return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags);
+ return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags, vm_flags);
+
+ if (filp && is_file_hugepages(filp))
+ psize = file_to_psize(filp);
+ else
+ psize = mm_ctx_user_psize(&current->mm->context);
- return slice_get_unmapped_area(addr0, len, flags,
- mm_ctx_user_psize(&current->mm->context), 1);
+ return slice_get_unmapped_area(addr0, len, flags, psize, 1);
}
unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr)
@@ -788,20 +814,4 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
return 1UL << mmu_psize_to_shift(get_slice_psize(vma->vm_mm, vma->vm_start));
}
-
-static int file_to_psize(struct file *file)
-{
- struct hstate *hstate = hstate_file(file);
- return shift_to_mmu_psize(huge_page_shift(hstate));
-}
-
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
-{
- if (radix_enabled())
- return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
-
- return slice_get_unmapped_area(addr, len, flags, file_to_psize(file), 1);
-}
#endif
diff --git a/arch/powerpc/mm/cacheflush.c b/arch/powerpc/mm/cacheflush.c
index 15189592da09..7186516eca52 100644
--- a/arch/powerpc/mm/cacheflush.c
+++ b/arch/powerpc/mm/cacheflush.c
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(flush_icache_range);
#ifdef CONFIG_HIGHMEM
/**
- * flush_dcache_icache_phys() - Flush a page by it's physical address
+ * flush_dcache_icache_phys() - Flush a page by its physical address
* @physaddr: the physical address of the page
*/
static void flush_dcache_icache_phys(unsigned long physaddr)
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
index fde7790277f7..8dd7b340d51f 100644
--- a/arch/powerpc/mm/drmem.c
+++ b/arch/powerpc/mm/drmem.c
@@ -393,17 +393,17 @@ static const __be32 *of_get_usable_memory(struct device_node *dn)
int walk_drmem_lmbs(struct device_node *dn, void *data,
int (*func)(struct drmem_lmb *, const __be32 **, void *))
{
+ struct device_node *root = of_find_node_by_path("/");
const __be32 *prop, *usm;
int ret = -ENODEV;
- if (!of_root)
+ if (!root)
return ret;
/* Get the address & size cells */
- of_node_get(of_root);
- n_root_addr_cells = of_n_addr_cells(of_root);
- n_root_size_cells = of_n_size_cells(of_root);
- of_node_put(of_root);
+ n_root_addr_cells = of_n_addr_cells(root);
+ n_root_size_cells = of_n_size_cells(root);
+ of_node_put(root);
if (init_drmem_lmb_size(dn))
return ret;
@@ -491,10 +491,8 @@ static int __init drmem_init(void)
const __be32 *prop;
dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
- if (!dn) {
- pr_info("No dynamic reconfiguration memory found\n");
+ if (!dn)
return 0;
- }
if (init_drmem_lmb_size(dn)) {
of_node_put(dn);
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 53335ae21a40..c156fe0d53c3 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -71,23 +71,26 @@ static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long add
return __bad_area_nosemaphore(regs, address, SEGV_MAPERR);
}
-static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
+static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code,
+ struct mm_struct *mm, struct vm_area_struct *vma)
{
- struct mm_struct *mm = current->mm;
/*
* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
- mmap_read_unlock(mm);
+ if (mm)
+ mmap_read_unlock(mm);
+ else
+ vma_end_read(vma);
return __bad_area_nosemaphore(regs, address, si_code);
}
static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
+ struct mm_struct *mm,
struct vm_area_struct *vma)
{
- struct mm_struct *mm = current->mm;
int pkey;
/*
@@ -109,7 +112,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
*/
pkey = vma_pkey(vma);
- mmap_read_unlock(mm);
+ if (mm)
+ mmap_read_unlock(mm);
+ else
+ vma_end_read(vma);
/*
* If we are in kernel mode, bail out with a SEGV, this will
@@ -124,9 +130,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
return 0;
}
-static noinline int bad_access(struct pt_regs *regs, unsigned long address)
+static noinline int bad_access(struct pt_regs *regs, unsigned long address,
+ struct mm_struct *mm, struct vm_area_struct *vma)
{
- return __bad_area(regs, address, SEGV_ACCERR);
+ return __bad_area(regs, address, SEGV_ACCERR, mm, vma);
}
static int do_sigbus(struct pt_regs *regs, unsigned long address,
@@ -361,13 +368,13 @@ static void sanity_check_fault(bool is_write, bool is_user,
* Define the correct "is_write" bit in error_code based
* on the processor family
*/
-#if (defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+#ifdef CONFIG_BOOKE
#define page_fault_is_write(__err) ((__err) & ESR_DST)
#else
#define page_fault_is_write(__err) ((__err) & DSISR_ISSTORE)
#endif
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_BOOKE
#define page_fault_is_bad(__err) (0)
#elif defined(CONFIG_PPC_8xx)
#define page_fault_is_bad(__err) ((__err) & DSISR_NOEXEC_OR_G)
@@ -432,10 +439,16 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
/*
* The kernel should never take an execute fault nor should it
* take a page fault to a kernel address or a page fault to a user
- * address outside of dedicated places
+ * address outside of dedicated places.
+ *
+ * Rather than kfence directly reporting false negatives, search whether
+ * the NIP belongs to the fixup table for cases where fault could come
+ * from functions like copy_from_kernel_nofault().
*/
if (unlikely(!is_user && bad_kernel_fault(regs, error_code, address, is_write))) {
- if (kfence_handle_page_fault(address, is_write, regs))
+ if (is_kfence_address((void *)address) &&
+ !search_exception_tables(instruction_pointer(regs)) &&
+ kfence_handle_page_fault(address, is_write, regs))
return 0;
return SIGSEGV;
@@ -479,13 +492,13 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
if (unlikely(access_pkey_error(is_write, is_exec,
(error_code & DSISR_KEYFAULT), vma))) {
- vma_end_read(vma);
- goto lock_mmap;
+ count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ return bad_access_pkey(regs, address, NULL, vma);
}
if (unlikely(access_error(is_write, is_exec, vma))) {
- vma_end_read(vma);
- goto lock_mmap;
+ count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ return bad_access(regs, address, NULL, vma);
}
fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
@@ -521,10 +534,10 @@ retry:
if (unlikely(access_pkey_error(is_write, is_exec,
(error_code & DSISR_KEYFAULT), vma)))
- return bad_access_pkey(regs, address, vma);
+ return bad_access_pkey(regs, address, mm, vma);
if (unlikely(access_error(is_write, is_exec, vma)))
- return bad_access(regs, address);
+ return bad_access(regs, address, mm, vma);
/*
* If for any reason at all we couldn't handle the fault,
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0a540b37aab6..6b043180220a 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -28,8 +28,6 @@
bool hugetlb_disabled = false;
-#define hugepd_none(hpd) (hpd_val(hpd) == 0)
-
#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_basic_t)) - \
__builtin_ffs(sizeof(void *)))
@@ -42,156 +40,43 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long s
return __find_linux_pte(mm->pgd, addr, NULL, NULL);
}
-static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
- unsigned long address, unsigned int pdshift,
- unsigned int pshift, spinlock_t *ptl)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long sz)
{
- struct kmem_cache *cachep;
- pte_t *new;
- int i;
- int num_hugepd;
-
- if (pshift >= pdshift) {
- cachep = PGT_CACHE(PTE_T_ORDER);
- num_hugepd = 1 << (pshift - pdshift);
- } else {
- cachep = PGT_CACHE(pdshift - pshift);
- num_hugepd = 1;
- }
-
- if (!cachep) {
- WARN_ONCE(1, "No page table cache created for hugetlb tables");
- return -ENOMEM;
- }
-
- new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
- BUG_ON(pshift > HUGEPD_SHIFT_MASK);
- BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
+ addr &= ~(sz - 1);
- if (!new)
- return -ENOMEM;
+ p4d = p4d_offset(pgd_offset(mm, addr), addr);
+ if (!mm_pud_folded(mm) && sz >= P4D_SIZE)
+ return (pte_t *)p4d;
- /*
- * Make sure other cpus find the hugepd set only after a
- * properly initialized page table is visible to them.
- * For more details look for comment in __pte_alloc().
- */
- smp_wmb();
+ pud = pud_alloc(mm, p4d, addr);
+ if (!pud)
+ return NULL;
+ if (!mm_pmd_folded(mm) && sz >= PUD_SIZE)
+ return (pte_t *)pud;
- spin_lock(ptl);
- /*
- * We have multiple higher-level entries that point to the same
- * actual pte location. Fill in each as we go and backtrack on error.
- * We need all of these so the DTLB pgtable walk code can find the
- * right higher-level entry without knowing if it's a hugepage or not.
- */
- for (i = 0; i < num_hugepd; i++, hpdp++) {
- if (unlikely(!hugepd_none(*hpdp)))
- break;
- hugepd_populate(hpdp, new, pshift);
- }
- /* If we bailed from the for loop early, an error occurred, clean up */
- if (i < num_hugepd) {
- for (i = i - 1 ; i >= 0; i--, hpdp--)
- *hpdp = __hugepd(0);
- kmem_cache_free(cachep, new);
- } else {
- kmemleak_ignore(new);
- }
- spin_unlock(ptl);
- return 0;
-}
+ pmd = pmd_alloc(mm, pud, addr);
+ if (!pmd)
+ return NULL;
-/*
- * At this point we do the placement change only for BOOK3S 64. This would
- * possibly work on other subarchs.
- */
-pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long addr, unsigned long sz)
-{
- pgd_t *pg;
- p4d_t *p4;
- pud_t *pu;
- pmd_t *pm;
- hugepd_t *hpdp = NULL;
- unsigned pshift = __ffs(sz);
- unsigned pdshift = PGDIR_SHIFT;
- spinlock_t *ptl;
-
- addr &= ~(sz-1);
- pg = pgd_offset(mm, addr);
- p4 = p4d_offset(pg, addr);
+ if (sz >= PMD_SIZE) {
+ /* On 8xx, all hugepages are handled as contiguous PTEs */
+ if (IS_ENABLED(CONFIG_PPC_8xx)) {
+ int i;
-#ifdef CONFIG_PPC_BOOK3S_64
- if (pshift == PGDIR_SHIFT)
- /* 16GB huge page */
- return (pte_t *) p4;
- else if (pshift > PUD_SHIFT) {
- /*
- * We need to use hugepd table
- */
- ptl = &mm->page_table_lock;
- hpdp = (hugepd_t *)p4;
- } else {
- pdshift = PUD_SHIFT;
- pu = pud_alloc(mm, p4, addr);
- if (!pu)
- return NULL;
- if (pshift == PUD_SHIFT)
- return (pte_t *)pu;
- else if (pshift > PMD_SHIFT) {
- ptl = pud_lockptr(mm, pu);
- hpdp = (hugepd_t *)pu;
- } else {
- pdshift = PMD_SHIFT;
- pm = pmd_alloc(mm, pu, addr);
- if (!pm)
- return NULL;
- if (pshift == PMD_SHIFT)
- /* 16MB hugepage */
- return (pte_t *)pm;
- else {
- ptl = pmd_lockptr(mm, pm);
- hpdp = (hugepd_t *)pm;
+ for (i = 0; i < sz / PMD_SIZE; i++) {
+ if (!pte_alloc_huge(mm, pmd + i, addr))
+ return NULL;
}
}
+ return (pte_t *)pmd;
}
-#else
- if (pshift >= PGDIR_SHIFT) {
- ptl = &mm->page_table_lock;
- hpdp = (hugepd_t *)p4;
- } else {
- pdshift = PUD_SHIFT;
- pu = pud_alloc(mm, p4, addr);
- if (!pu)
- return NULL;
- if (pshift >= PUD_SHIFT) {
- ptl = pud_lockptr(mm, pu);
- hpdp = (hugepd_t *)pu;
- } else {
- pdshift = PMD_SHIFT;
- pm = pmd_alloc(mm, pu, addr);
- if (!pm)
- return NULL;
- ptl = pmd_lockptr(mm, pm);
- hpdp = (hugepd_t *)pm;
- }
- }
-#endif
- if (!hpdp)
- return NULL;
-
- if (IS_ENABLED(CONFIG_PPC_8xx) && pshift < PMD_SHIFT)
- return pte_alloc_huge(mm, (pmd_t *)hpdp, addr);
-
- BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
- if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr,
- pdshift, pshift, ptl))
- return NULL;
-
- return hugepte_offset(*hpdp, addr, pdshift);
+ return pte_alloc_huge(mm, pmd, addr);
}
#ifdef CONFIG_PPC_BOOK3S_64
@@ -226,7 +111,7 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate)
return 0;
m = phys_to_virt(gpage_freearray[--nr_gpages]);
gpage_freearray[nr_gpages] = 0;
- list_add(&m->list, &huge_boot_pages);
+ list_add(&m->list, &huge_boot_pages[0]);
m->hstate = hstate;
return 1;
}
@@ -248,264 +133,6 @@ int __init alloc_bootmem_huge_page(struct hstate *h, int nid)
return __alloc_bootmem_huge_page(h, nid);
}
-#ifndef CONFIG_PPC_BOOK3S_64
-#define HUGEPD_FREELIST_SIZE \
- ((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
-
-struct hugepd_freelist {
- struct rcu_head rcu;
- unsigned int index;
- void *ptes[];
-};
-
-static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur);
-
-static void hugepd_free_rcu_callback(struct rcu_head *head)
-{
- struct hugepd_freelist *batch =
- container_of(head, struct hugepd_freelist, rcu);
- unsigned int i;
-
- for (i = 0; i < batch->index; i++)
- kmem_cache_free(PGT_CACHE(PTE_T_ORDER), batch->ptes[i]);
-
- free_page((unsigned long)batch);
-}
-
-static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
-{
- struct hugepd_freelist **batchp;
-
- batchp = &get_cpu_var(hugepd_freelist_cur);
-
- if (atomic_read(&tlb->mm->mm_users) < 2 ||
- mm_is_thread_local(tlb->mm)) {
- kmem_cache_free(PGT_CACHE(PTE_T_ORDER), hugepte);
- put_cpu_var(hugepd_freelist_cur);
- return;
- }
-
- if (*batchp == NULL) {
- *batchp = (struct hugepd_freelist *)__get_free_page(GFP_ATOMIC);
- (*batchp)->index = 0;
- }
-
- (*batchp)->ptes[(*batchp)->index++] = hugepte;
- if ((*batchp)->index == HUGEPD_FREELIST_SIZE) {
- call_rcu(&(*batchp)->rcu, hugepd_free_rcu_callback);
- *batchp = NULL;
- }
- put_cpu_var(hugepd_freelist_cur);
-}
-#else
-static inline void hugepd_free(struct mmu_gather *tlb, void *hugepte) {}
-#endif
-
-/* Return true when the entry to be freed maps more than the area being freed */
-static bool range_is_outside_limits(unsigned long start, unsigned long end,
- unsigned long floor, unsigned long ceiling,
- unsigned long mask)
-{
- if ((start & mask) < floor)
- return true;
- if (ceiling) {
- ceiling &= mask;
- if (!ceiling)
- return true;
- }
- return end - 1 > ceiling - 1;
-}
-
-static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
- unsigned long start, unsigned long end,
- unsigned long floor, unsigned long ceiling)
-{
- pte_t *hugepte = hugepd_page(*hpdp);
- int i;
-
- unsigned long pdmask = ~((1UL << pdshift) - 1);
- unsigned int num_hugepd = 1;
- unsigned int shift = hugepd_shift(*hpdp);
-
- /* Note: On fsl the hpdp may be the first of several */
- if (shift > pdshift)
- num_hugepd = 1 << (shift - pdshift);
-
- if (range_is_outside_limits(start, end, floor, ceiling, pdmask))
- return;
-
- for (i = 0; i < num_hugepd; i++, hpdp++)
- *hpdp = __hugepd(0);
-
- if (shift >= pdshift)
- hugepd_free(tlb, hugepte);
- else
- pgtable_free_tlb(tlb, hugepte,
- get_hugepd_cache_index(pdshift - shift));
-}
-
-static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
- unsigned long addr, unsigned long end,
- unsigned long floor, unsigned long ceiling)
-{
- pgtable_t token = pmd_pgtable(*pmd);
-
- if (range_is_outside_limits(addr, end, floor, ceiling, PMD_MASK))
- return;
-
- pmd_clear(pmd);
- pte_free_tlb(tlb, token, addr);
- mm_dec_nr_ptes(tlb->mm);
-}
-
-static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
- unsigned long addr, unsigned long end,
- unsigned long floor, unsigned long ceiling)
-{
- pmd_t *pmd;
- unsigned long next;
- unsigned long start;
-
- start = addr;
- do {
- unsigned long more;
-
- pmd = pmd_offset(pud, addr);
- next = pmd_addr_end(addr, end);
- if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
- if (pmd_none_or_clear_bad(pmd))
- continue;
-
- /*
- * if it is not hugepd pointer, we should already find
- * it cleared.
- */
- WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx));
-
- hugetlb_free_pte_range(tlb, pmd, addr, end, floor, ceiling);
-
- continue;
- }
- /*
- * Increment next by the size of the huge mapping since
- * there may be more than one entry at this level for a
- * single hugepage, but all of them point to
- * the same kmem cache that holds the hugepte.
- */
- more = addr + (1UL << hugepd_shift(*(hugepd_t *)pmd));
- if (more > next)
- next = more;
-
- free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
- addr, next, floor, ceiling);
- } while (addr = next, addr != end);
-
- if (range_is_outside_limits(start, end, floor, ceiling, PUD_MASK))
- return;
-
- pmd = pmd_offset(pud, start & PUD_MASK);
- pud_clear(pud);
- pmd_free_tlb(tlb, pmd, start & PUD_MASK);
- mm_dec_nr_pmds(tlb->mm);
-}
-
-static void hugetlb_free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
- unsigned long addr, unsigned long end,
- unsigned long floor, unsigned long ceiling)
-{
- pud_t *pud;
- unsigned long next;
- unsigned long start;
-
- start = addr;
- do {
- pud = pud_offset(p4d, addr);
- next = pud_addr_end(addr, end);
- if (!is_hugepd(__hugepd(pud_val(*pud)))) {
- if (pud_none_or_clear_bad(pud))
- continue;
- hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
- ceiling);
- } else {
- unsigned long more;
- /*
- * Increment next by the size of the huge mapping since
- * there may be more than one entry at this level for a
- * single hugepage, but all of them point to
- * the same kmem cache that holds the hugepte.
- */
- more = addr + (1UL << hugepd_shift(*(hugepd_t *)pud));
- if (more > next)
- next = more;
-
- free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
- addr, next, floor, ceiling);
- }
- } while (addr = next, addr != end);
-
- if (range_is_outside_limits(start, end, floor, ceiling, PGDIR_MASK))
- return;
-
- pud = pud_offset(p4d, start & PGDIR_MASK);
- p4d_clear(p4d);
- pud_free_tlb(tlb, pud, start & PGDIR_MASK);
- mm_dec_nr_puds(tlb->mm);
-}
-
-/*
- * This function frees user-level page tables of a process.
- */
-void hugetlb_free_pgd_range(struct mmu_gather *tlb,
- unsigned long addr, unsigned long end,
- unsigned long floor, unsigned long ceiling)
-{
- pgd_t *pgd;
- p4d_t *p4d;
- unsigned long next;
-
- /*
- * Because there are a number of different possible pagetable
- * layouts for hugepage ranges, we limit knowledge of how
- * things should be laid out to the allocation path
- * (huge_pte_alloc(), above). Everything else works out the
- * structure as it goes from information in the hugepd
- * pointers. That means that we can't here use the
- * optimization used in the normal page free_pgd_range(), of
- * checking whether we're actually covering a large enough
- * range to have to do anything at the top level of the walk
- * instead of at the bottom.
- *
- * To make sense of this, you should probably go read the big
- * block comment at the top of the normal free_pgd_range(),
- * too.
- */
-
- do {
- next = pgd_addr_end(addr, end);
- pgd = pgd_offset(tlb->mm, addr);
- p4d = p4d_offset(pgd, addr);
- if (!is_hugepd(__hugepd(pgd_val(*pgd)))) {
- if (p4d_none_or_clear_bad(p4d))
- continue;
- hugetlb_free_pud_range(tlb, p4d, addr, next, floor, ceiling);
- } else {
- unsigned long more;
- /*
- * Increment next by the size of the huge mapping since
- * there may be more than one entry at the pgd level
- * for a single hugepage, but all of them point to the
- * same kmem cache that holds the hugepte.
- */
- more = addr + (1UL << hugepd_shift(*(hugepd_t *)pgd));
- if (more > next)
- next = more;
-
- free_hugepd_range(tlb, (hugepd_t *)p4d, PGDIR_SHIFT,
- addr, next, floor, ceiling);
- }
- } while (addr = next, addr != end);
-}
-
bool __init arch_hugetlb_valid_size(unsigned long size)
{
int shift = __ffs(size);
@@ -552,44 +179,14 @@ static int __init hugetlbpage_init(void)
for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
unsigned shift;
- unsigned pdshift;
if (!mmu_psize_defs[psize].shift)
continue;
shift = mmu_psize_to_shift(psize);
-#ifdef CONFIG_PPC_BOOK3S_64
- if (shift > PGDIR_SHIFT)
- continue;
- else if (shift > PUD_SHIFT)
- pdshift = PGDIR_SHIFT;
- else if (shift > PMD_SHIFT)
- pdshift = PUD_SHIFT;
- else
- pdshift = PMD_SHIFT;
-#else
- if (shift < PUD_SHIFT)
- pdshift = PMD_SHIFT;
- else if (shift < PGDIR_SHIFT)
- pdshift = PUD_SHIFT;
- else
- pdshift = PGDIR_SHIFT;
-#endif
-
if (add_huge_page_size(1ULL << shift) < 0)
continue;
- /*
- * if we have pdshift and shift value same, we don't
- * use pgt cache for hugepd.
- */
- if (pdshift > shift) {
- if (!IS_ENABLED(CONFIG_PPC_8xx))
- pgtable_cache_add(pdshift - shift);
- } else if (IS_ENABLED(CONFIG_PPC_E500) ||
- IS_ENABLED(CONFIG_PPC_8xx)) {
- pgtable_cache_add(PTE_T_ORDER);
- }
configured = true;
}
@@ -614,8 +211,6 @@ void __init gigantic_hugetlb_cma_reserve(void)
*/
order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT;
- if (order) {
- VM_WARN_ON(order <= MAX_PAGE_ORDER);
+ if (order)
hugetlb_cma_reserve(order);
- }
}
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index d3a7726ecf51..745097554bea 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -31,6 +31,10 @@ EXPORT_SYMBOL_GPL(kernstart_virt_addr);
bool disable_kuep = !IS_ENABLED(CONFIG_PPC_KUEP);
bool disable_kuap = !IS_ENABLED(CONFIG_PPC_KUAP);
+#ifdef CONFIG_KFENCE
+bool __ro_after_init kfence_disabled;
+bool __ro_after_init kfence_early_init = !!CONFIG_KFENCE_SAMPLE_INTERVAL;
+#endif
static int __init parse_nosmep(char *p)
{
@@ -70,7 +74,7 @@ void setup_kup(void)
#define CTOR(shift) static void ctor_##shift(void *addr) \
{ \
- memset(addr, 0, sizeof(void *) << (shift)); \
+ memset(addr, 0, sizeof(pgd_t) << (shift)); \
}
CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7);
@@ -114,18 +118,14 @@ EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */
void pgtable_cache_add(unsigned int shift)
{
char *name;
- unsigned long table_size = sizeof(void *) << shift;
+ unsigned long table_size = sizeof(pgd_t) << shift;
unsigned long align = table_size;
/* When batching pgtable pointers for RCU freeing, we store
* the index size in the low bits. Table alignment must be
* big enough to fit it.
- *
- * Likewise, hugeapge pagetable pointers contain a (different)
- * shift value in the low bits. All tables must be aligned so
- * as to leave enough 0 bits in the address to contain it. */
- unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
- HUGEPD_SHIFT_MASK + 1);
+ */
+ unsigned long minalign = MAX_PGTABLE_INDEX_SIZE + 1;
struct kmem_cache *new = NULL;
/* It would be nice if this was a BUILD_BUG_ON(), but at the
diff --git a/arch/powerpc/mm/kasan/8xx.c b/arch/powerpc/mm/kasan/8xx.c
index 2784224054f8..989d6cdf4141 100644
--- a/arch/powerpc/mm/kasan/8xx.c
+++ b/arch/powerpc/mm/kasan/8xx.c
@@ -6,28 +6,33 @@
#include <linux/memblock.h>
#include <linux/hugetlb.h>
+#include <asm/pgalloc.h>
+
static int __init
kasan_init_shadow_8M(unsigned long k_start, unsigned long k_end, void *block)
{
pmd_t *pmd = pmd_off_k(k_start);
unsigned long k_cur, k_next;
- for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd += 2, block += SZ_8M) {
- pte_basic_t *new;
+ for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd++, block += SZ_4M) {
+ pte_t *ptep;
+ int i;
k_next = pgd_addr_end(k_cur, k_end);
- k_next = pgd_addr_end(k_next, k_end);
if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte)
continue;
- new = memblock_alloc(sizeof(pte_basic_t), SZ_4K);
- if (!new)
+ ptep = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE);
+ if (!ptep)
return -ENOMEM;
- *new = pte_val(pte_mkhuge(pfn_pte(PHYS_PFN(__pa(block)), PAGE_KERNEL)));
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ pte_t pte = pte_mkhuge(pfn_pte(PHYS_PFN(__pa(block + i * PAGE_SIZE)), PAGE_KERNEL));
- hugepd_populate_kernel((hugepd_t *)pmd, (pte_t *)new, PAGE_SHIFT_8M);
- hugepd_populate_kernel((hugepd_t *)pmd + 1, (pte_t *)new, PAGE_SHIFT_8M);
+ __set_pte_at(&init_mm, k_cur, ptep + i, pte, 1);
+ }
+ pmd_populate_kernel(&init_mm, pmd, ptep);
+ *pmd = __pmd(pmd_val(*pmd) | _PMD_PAGE_8M);
}
return 0;
}
diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c
index aa9aa11927b2..03666d790a53 100644
--- a/arch/powerpc/mm/kasan/init_32.c
+++ b/arch/powerpc/mm/kasan/init_32.c
@@ -7,7 +7,7 @@
#include <linux/memblock.h>
#include <linux/sched/task.h>
#include <asm/pgalloc.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <mm/mmu_decl.h>
static pgprot_t __init kasan_prot_ro(void)
diff --git a/arch/powerpc/mm/kasan/init_book3e_64.c b/arch/powerpc/mm/kasan/init_book3e_64.c
index 11519e88dc6b..60c78aac0f63 100644
--- a/arch/powerpc/mm/kasan/init_book3e_64.c
+++ b/arch/powerpc/mm/kasan/init_book3e_64.c
@@ -40,19 +40,19 @@ static int __init kasan_map_kernel_page(unsigned long ea, unsigned long pa, pgpr
pgdp = pgd_offset_k(ea);
p4dp = p4d_offset(pgdp, ea);
if (kasan_pud_table(*p4dp)) {
- pudp = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
+ pudp = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
memcpy(pudp, kasan_early_shadow_pud, PUD_TABLE_SIZE);
p4d_populate(&init_mm, p4dp, pudp);
}
pudp = pud_offset(p4dp, ea);
if (kasan_pmd_table(*pudp)) {
- pmdp = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
+ pmdp = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
memcpy(pmdp, kasan_early_shadow_pmd, PMD_TABLE_SIZE);
pud_populate(&init_mm, pudp, pmdp);
}
pmdp = pmd_offset(pudp, ea);
if (kasan_pte_table(*pmdp)) {
- ptep = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
+ ptep = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
memcpy(ptep, kasan_early_shadow_pte, PTE_TABLE_SIZE);
pmd_populate_kernel(&init_mm, pmdp, ptep);
}
@@ -74,7 +74,7 @@ static void __init kasan_init_phys_region(void *start, void *end)
k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
- va = memblock_alloc(k_end - k_start, PAGE_SIZE);
+ va = memblock_alloc_or_panic(k_end - k_start, PAGE_SIZE);
for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE)
kasan_map_kernel_page(k_cur, __pa(va), PAGE_KERNEL);
}
@@ -112,7 +112,7 @@ void __init kasan_init(void)
pte_t zero_pte = pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL_RO);
for_each_mem_range(i, &start, &end)
- kasan_init_phys_region((void *)start, (void *)end);
+ kasan_init_phys_region(phys_to_virt(start), phys_to_virt(end));
if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
kasan_remove_zero_shadow((void *)VMALLOC_START, VMALLOC_SIZE);
diff --git a/arch/powerpc/mm/kasan/init_book3s_64.c b/arch/powerpc/mm/kasan/init_book3s_64.c
index 9300d641cf9a..7d959544c077 100644
--- a/arch/powerpc/mm/kasan/init_book3s_64.c
+++ b/arch/powerpc/mm/kasan/init_book3s_64.c
@@ -32,7 +32,7 @@ static void __init kasan_init_phys_region(void *start, void *end)
k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
- va = memblock_alloc(k_end - k_start, PAGE_SIZE);
+ va = memblock_alloc_or_panic(k_end - k_start, PAGE_SIZE);
for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE)
map_kernel_page(k_cur, __pa(va), PAGE_KERNEL);
}
@@ -62,7 +62,7 @@ void __init kasan_init(void)
}
for_each_mem_range(i, &start, &end)
- kasan_init_phys_region((void *)start, (void *)end);
+ kasan_init_phys_region(phys_to_virt(start), phys_to_virt(end));
for (i = 0; i < PTRS_PER_PTE; i++)
__set_pte_at(&init_mm, (unsigned long)kasan_early_shadow_page,
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 3a440004b97d..c7708c8fad29 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -16,6 +16,8 @@
#include <linux/highmem.h>
#include <linux/suspend.h>
#include <linux/dma-direct.h>
+#include <linux/execmem.h>
+#include <linux/vmalloc.h>
#include <asm/swiotlb.h>
#include <asm/machdep.h>
@@ -24,13 +26,13 @@
#include <asm/svm.h>
#include <asm/mmzone.h>
#include <asm/ftrace.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/setup.h>
#include <asm/fixmap.h>
#include <mm/mmu_decl.h>
-unsigned long long memory_limit;
+unsigned long long memory_limit __initdata;
unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
EXPORT_SYMBOL(empty_zero_page);
@@ -214,7 +216,7 @@ static int __init mark_nonram_nosave(void)
* everything else. GFP_DMA32 page allocations automatically fall back to
* ZONE_DMA.
*
- * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the
+ * By using 31-bit unconditionally, we can exploit zone_dma_limit to inform the
* generic DMA mapping code. 32-bit only devices (if not handled by an IOMMU
* anyway) will take a first dip into ZONE_NORMAL and get otherwise served by
* ZONE_DMA.
@@ -228,6 +230,7 @@ void __init paging_init(void)
{
unsigned long long total_ram = memblock_phys_mem_size();
phys_addr_t top_of_ram = memblock_end_of_DRAM();
+ int zone_dma_bits;
#ifdef CONFIG_HIGHMEM
unsigned long v = __fix_to_virt(FIX_KMAP_END);
@@ -254,6 +257,8 @@ void __init paging_init(void)
else
zone_dma_bits = 31;
+ zone_dma_limit = DMA_BIT_MASK(zone_dma_bits);
+
#ifdef CONFIG_ZONE_DMA
max_zone_pfns[ZONE_DMA] = min(max_low_pfn,
1UL << (zone_dma_bits - PAGE_SHIFT));
@@ -288,8 +293,6 @@ void __init mem_init(void)
swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags);
#endif
- high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
-
kasan_late_init();
memblock_free_all();
@@ -406,3 +409,80 @@ int devmem_is_allowed(unsigned long pfn)
* the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed.
*/
EXPORT_SYMBOL_GPL(walk_system_ram_range);
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+#if defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_BOOK3S_603)
+static void prealloc_execmem_pgtable(void)
+{
+ unsigned long va;
+
+ for (va = ALIGN_DOWN(MODULES_VADDR, PGDIR_SIZE); va < MODULES_END; va += PGDIR_SIZE)
+ pte_alloc_kernel(pmd_off_k(va), va);
+}
+#else
+static void prealloc_execmem_pgtable(void) { }
+#endif
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ pgprot_t kprobes_prot = strict_module_rwx_enabled() ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+ pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
+ unsigned long fallback_start = 0, fallback_end = 0;
+ unsigned long start, end;
+
+ /*
+ * BOOK3S_32 and 8xx define MODULES_VADDR for text allocations and
+ * allow allocating data in the entire vmalloc space
+ */
+#ifdef MODULES_VADDR
+ unsigned long limit = (unsigned long)_etext - SZ_32M;
+
+ 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) {
+ start = limit;
+ fallback_start = MODULES_VADDR;
+ fallback_end = MODULES_END;
+ } else {
+ start = MODULES_VADDR;
+ }
+
+ end = MODULES_END;
+#else
+ start = VMALLOC_START;
+ end = VMALLOC_END;
+#endif
+
+ prealloc_execmem_pgtable();
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = start,
+ .end = end,
+ .pgprot = prot,
+ .alignment = 1,
+ .fallback_start = fallback_start,
+ .fallback_end = fallback_end,
+ },
+ [EXECMEM_KPROBES] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = kprobes_prot,
+ .alignment = 1,
+ },
+ [EXECMEM_MODULE_DATA] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = 1,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index b24c19078eb1..3e3af29b4523 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -21,7 +21,7 @@ static inline void switch_mm_pgdir(struct task_struct *tsk,
#ifdef CONFIG_PPC_BOOK3S_32
tsk->thread.sr0 = mm->context.sr0;
#endif
-#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP)
tsk->thread.pid = mm->context.id;
#endif
}
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 72341b9fb552..b2d1eea09761 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -20,9 +20,9 @@
#include <asm/trace.h>
/*
- * On 40x and 8xx, we directly inline tlbia and tlbivax
+ * On 8xx, we directly inline tlbia
*/
-#if defined(CONFIG_40x) || defined(CONFIG_PPC_8xx)
+#ifdef CONFIG_PPC_8xx
static inline void _tlbil_all(void)
{
asm volatile ("sync; tlbia; isync" : : : "memory");
@@ -35,7 +35,7 @@ static inline void _tlbil_pid(unsigned int pid)
}
#define _tlbil_pid_noind(pid) _tlbil_pid(pid)
-#else /* CONFIG_40x || CONFIG_PPC_8xx */
+#else /* CONFIG_PPC_8xx */
extern void _tlbil_all(void);
extern void _tlbil_pid(unsigned int pid);
#ifdef CONFIG_PPC_BOOK3E_64
@@ -43,7 +43,7 @@ extern void _tlbil_pid_noind(unsigned int pid);
#else
#define _tlbil_pid_noind(pid) _tlbil_pid(pid)
#endif
-#endif /* !(CONFIG_40x || CONFIG_PPC_8xx) */
+#endif /* !CONFIG_PPC_8xx */
/*
* On 8xx, we directly inline tlbie, on others, it's extern
@@ -160,23 +160,17 @@ static inline unsigned long p_block_mapped(phys_addr_t pa) { return 0; }
#endif
#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_E500)
-void mmu_mark_initmem_nx(void);
-void mmu_mark_rodata_ro(void);
+int mmu_mark_initmem_nx(void);
+int mmu_mark_rodata_ro(void);
#else
-static inline void mmu_mark_initmem_nx(void) { }
-static inline void mmu_mark_rodata_ro(void) { }
+static inline int mmu_mark_initmem_nx(void) { return 0; }
+static inline int mmu_mark_rodata_ro(void) { return 0; }
#endif
#ifdef CONFIG_PPC_8xx
void __init mmu_mapin_immr(void);
#endif
-#ifdef CONFIG_DEBUG_WX
-void ptdump_check_wx(void);
-#else
-static inline void ptdump_check_wx(void) { }
-#endif
-
static inline bool debug_pagealloc_enabled_or_kfence(void)
{
return IS_ENABLED(CONFIG_KFENCE) || debug_pagealloc_enabled();
@@ -186,3 +180,5 @@ static inline bool debug_pagealloc_enabled_or_kfence(void)
int create_section_mapping(unsigned long start, unsigned long end,
int nid, pgprot_t prot);
#endif
+
+int hash__kernel_map_pages(struct page *page, int numpages, int enable);
diff --git a/arch/powerpc/mm/nohash/40x.c b/arch/powerpc/mm/nohash/40x.c
deleted file mode 100644
index e835e80c09db..000000000000
--- a/arch/powerpc/mm/nohash/40x.c
+++ /dev/null
@@ -1,161 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * This file contains the routines for initializing the MMU
- * on the 4xx series of chips.
- * -- paulus
- *
- * Derived from arch/ppc/mm/init.c:
- * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
- * and Cort Dougan (PReP) (cort@cs.nmt.edu)
- * Copyright (C) 1996 Paul Mackerras
- *
- * Derived from "arch/i386/mm/init.c"
- * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
- */
-
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/stddef.h>
-#include <linux/vmalloc.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/highmem.h>
-#include <linux/memblock.h>
-
-#include <asm/io.h>
-#include <asm/mmu_context.h>
-#include <asm/mmu.h>
-#include <linux/uaccess.h>
-#include <asm/smp.h>
-#include <asm/bootx.h>
-#include <asm/machdep.h>
-#include <asm/setup.h>
-
-#include <mm/mmu_decl.h>
-
-/*
- * MMU_init_hw does the chip-specific initialization of the MMU hardware.
- */
-void __init MMU_init_hw(void)
-{
- int i;
- unsigned long zpr;
-
- /*
- * The Zone Protection Register (ZPR) defines how protection will
- * be applied to every page which is a member of a given zone.
- * The zone index bits (of ZSEL) in the PTE are used for software
- * indicators. We use the 4 upper bits of virtual address to select
- * the zone. We set all zones above TASK_SIZE to zero, allowing
- * only kernel access as indicated in the PTE. For zones below
- * TASK_SIZE, we set a 01 binary (a value of 10 will not work)
- * to allow user access as indicated in the PTE. This also allows
- * kernel access as indicated in the PTE.
- */
-
- for (i = 0, zpr = 0; i < TASK_SIZE >> 28; i++)
- zpr |= 1 << (30 - i * 2);
-
- mtspr(SPRN_ZPR, zpr);
-
- flush_instruction_cache();
-
- /*
- * Set up the real-mode cache parameters for the exception vector
- * handlers (which are run in real-mode).
- */
-
- mtspr(SPRN_DCWR, 0x00000000); /* All caching is write-back */
-
- /*
- * Cache instruction and data space where the exception
- * vectors and the kernel live in real-mode.
- */
-
- mtspr(SPRN_DCCR, 0xFFFF0000); /* 2GByte of data space at 0x0. */
- mtspr(SPRN_ICCR, 0xFFFF0000); /* 2GByte of instr. space at 0x0. */
-}
-
-#define LARGE_PAGE_SIZE_16M (1<<24)
-#define LARGE_PAGE_SIZE_4M (1<<22)
-
-unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
-{
- unsigned long v, s, mapped;
- phys_addr_t p;
-
- v = KERNELBASE;
- p = 0;
- s = total_lowmem;
-
- if (IS_ENABLED(CONFIG_KFENCE))
- return 0;
-
- if (debug_pagealloc_enabled())
- return 0;
-
- if (strict_kernel_rwx_enabled())
- return 0;
-
- while (s >= LARGE_PAGE_SIZE_16M) {
- pmd_t *pmdp;
- unsigned long val = p | _PMD_SIZE_16M | _PAGE_EXEC | _PAGE_RW;
-
- pmdp = pmd_off_k(v);
- *pmdp++ = __pmd(val);
- *pmdp++ = __pmd(val);
- *pmdp++ = __pmd(val);
- *pmdp++ = __pmd(val);
-
- v += LARGE_PAGE_SIZE_16M;
- p += LARGE_PAGE_SIZE_16M;
- s -= LARGE_PAGE_SIZE_16M;
- }
-
- while (s >= LARGE_PAGE_SIZE_4M) {
- pmd_t *pmdp;
- unsigned long val = p | _PMD_SIZE_4M | _PAGE_EXEC | _PAGE_RW;
-
- pmdp = pmd_off_k(v);
- *pmdp = __pmd(val);
-
- v += LARGE_PAGE_SIZE_4M;
- p += LARGE_PAGE_SIZE_4M;
- s -= LARGE_PAGE_SIZE_4M;
- }
-
- mapped = total_lowmem - s;
-
- /* If the size of RAM is not an exact power of two, we may not
- * have covered RAM in its entirety with 16 and 4 MiB
- * pages. Consequently, restrict the top end of RAM currently
- * allocable so that calls to the MEMBLOCK to allocate PTEs for "tail"
- * coverage with normal-sized pages (or other reasons) do not
- * attempt to allocate outside the allowed range.
- */
- memblock_set_current_limit(mapped);
-
- return mapped;
-}
-
-void setup_initial_memory_limit(phys_addr_t first_memblock_base,
- phys_addr_t first_memblock_size)
-{
- /* We don't currently support the first MEMBLOCK not mapping 0
- * physical on those processors
- */
- BUG_ON(first_memblock_base != 0);
-
- /* 40x can only access 16MB at the moment (see head_40x.S) */
- memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
-}
diff --git a/arch/powerpc/mm/nohash/44x.c b/arch/powerpc/mm/nohash/44x.c
index 1beae802bb1c..6d10c6d8be71 100644
--- a/arch/powerpc/mm/nohash/44x.c
+++ b/arch/powerpc/mm/nohash/44x.c
@@ -24,7 +24,7 @@
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/cacheflush.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/smp.h>
#include <mm/mmu_decl.h>
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index 6be6421086ed..8b54f12d1889 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -11,6 +11,7 @@
#include <linux/hugetlb.h>
#include <asm/fixmap.h>
+#include <asm/pgalloc.h>
#include <mm/mmu_decl.h>
@@ -48,20 +49,6 @@ unsigned long p_block_mapped(phys_addr_t pa)
return 0;
}
-static pte_t __init *early_hugepd_alloc_kernel(hugepd_t *pmdp, unsigned long va)
-{
- if (hpd_val(*pmdp) == 0) {
- pte_t *ptep = memblock_alloc(sizeof(pte_basic_t), SZ_4K);
-
- if (!ptep)
- return NULL;
-
- hugepd_populate_kernel((hugepd_t *)pmdp, ptep, PAGE_SHIFT_8M);
- hugepd_populate_kernel((hugepd_t *)pmdp + 1, ptep, PAGE_SHIFT_8M);
- }
- return hugepte_offset(*(hugepd_t *)pmdp, va, PGDIR_SHIFT);
-}
-
static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
pgprot_t prot, int psize, bool new)
{
@@ -75,26 +62,36 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
if (WARN_ON(slab_is_available()))
return -EINVAL;
- if (psize == MMU_PAGE_512K)
+ if (psize == MMU_PAGE_512K) {
ptep = early_pte_alloc_kernel(pmdp, va);
- else
- ptep = early_hugepd_alloc_kernel((hugepd_t *)pmdp, va);
+ /* The PTE should never be already present */
+ if (WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
+ return -EINVAL;
+ } else {
+ if (WARN_ON(!pmd_none(*pmdp) || !pmd_none(*(pmdp + 1))))
+ return -EINVAL;
+
+ ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
+ pmd_populate_kernel(&init_mm, pmdp, ptep);
+
+ ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
+ pmd_populate_kernel(&init_mm, pmdp + 1, ptep);
+
+ ptep = (pte_t *)pmdp;
+ }
} else {
if (psize == MMU_PAGE_512K)
ptep = pte_offset_kernel(pmdp, va);
else
- ptep = hugepte_offset(*(hugepd_t *)pmdp, va, PGDIR_SHIFT);
+ ptep = (pte_t *)pmdp;
}
if (WARN_ON(!ptep))
return -ENOMEM;
- /* The PTE should never be already present */
- if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
- return -EINVAL;
-
set_huge_pte_at(&init_mm, va, ptep,
- pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize);
+ pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)),
+ 1UL << mmu_psize_to_shift(psize));
return 0;
}
@@ -119,23 +116,26 @@ void __init mmu_mapin_immr(void)
PAGE_KERNEL_NCG, MMU_PAGE_512K, true);
}
-static void mmu_mapin_ram_chunk(unsigned long offset, unsigned long top,
- pgprot_t prot, bool new)
+static int mmu_mapin_ram_chunk(unsigned long offset, unsigned long top,
+ pgprot_t prot, bool new)
{
unsigned long v = PAGE_OFFSET + offset;
unsigned long p = offset;
+ int err = 0;
WARN_ON(!IS_ALIGNED(offset, SZ_512K) || !IS_ALIGNED(top, SZ_512K));
- for (; p < ALIGN(p, SZ_8M) && p < top; p += SZ_512K, v += SZ_512K)
- __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
- for (; p < ALIGN_DOWN(top, SZ_8M) && p < top; p += SZ_8M, v += SZ_8M)
- __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_8M, new);
- for (; p < ALIGN_DOWN(top, SZ_512K) && p < top; p += SZ_512K, v += SZ_512K)
- __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
+ for (; p < ALIGN(p, SZ_8M) && p < top && !err; p += SZ_512K, v += SZ_512K)
+ err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
+ for (; p < ALIGN_DOWN(top, SZ_8M) && p < top && !err; p += SZ_8M, v += SZ_8M)
+ err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_8M, new);
+ for (; p < ALIGN_DOWN(top, SZ_512K) && p < top && !err; p += SZ_512K, v += SZ_512K)
+ err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
if (!new)
flush_tlb_kernel_range(PAGE_OFFSET + v, PAGE_OFFSET + top);
+
+ return err;
}
unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
@@ -150,11 +150,11 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
mmu_mapin_immr();
- mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_TEXT, true);
+ mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_X, true);
if (debug_pagealloc_enabled_or_kfence()) {
top = boundary;
} else {
- mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_TEXT, true);
+ mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_X, true);
mmu_mapin_ram_chunk(einittext8, top, PAGE_KERNEL, true);
}
@@ -166,27 +166,34 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
return top;
}
-void mmu_mark_initmem_nx(void)
+int mmu_mark_initmem_nx(void)
{
unsigned long etext8 = ALIGN(__pa(_etext), SZ_8M);
unsigned long sinittext = __pa(_sinittext);
unsigned long boundary = strict_kernel_rwx_enabled() ? sinittext : etext8;
unsigned long einittext8 = ALIGN(__pa(_einittext), SZ_8M);
+ int err = 0;
if (!debug_pagealloc_enabled_or_kfence())
- mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL, false);
+ err = mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL, false);
+
+ if (IS_ENABLED(CONFIG_PIN_TLB_TEXT))
+ mmu_pin_tlb(block_mapped_ram, false);
- mmu_pin_tlb(block_mapped_ram, false);
+ return err;
}
#ifdef CONFIG_STRICT_KERNEL_RWX
-void mmu_mark_rodata_ro(void)
+int mmu_mark_rodata_ro(void)
{
unsigned long sinittext = __pa(_sinittext);
+ int err;
- mmu_mapin_ram_chunk(0, sinittext, PAGE_KERNEL_ROX, false);
+ err = mmu_mapin_ram_chunk(0, sinittext, PAGE_KERNEL_ROX, false);
if (IS_ENABLED(CONFIG_PIN_TLB_DATA))
mmu_pin_tlb(block_mapped_ram, true);
+
+ return err;
}
#endif
@@ -200,6 +207,8 @@ void __init setup_initial_memory_limit(phys_addr_t first_memblock_base,
/* 8xx can only access 32MB at the moment */
memblock_set_current_limit(min_t(u64, first_memblock_size, SZ_32M));
+
+ BUILD_BUG_ON(ALIGN_DOWN(MODULES_VADDR, PGDIR_SIZE) < TASK_SIZE);
}
int pud_clear_huge(pud_t *pud)
diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile
index f3894e79d5f7..cf60c776c883 100644
--- a/arch/powerpc/mm/nohash/Makefile
+++ b/arch/powerpc/mm/nohash/Makefile
@@ -1,10 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
-ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-
obj-y += mmu_context.o tlb.o tlb_low.o kup.o
-obj-$(CONFIG_PPC_BOOK3E_64) += tlb_low_64e.o book3e_pgtable.o
-obj-$(CONFIG_40x) += 40x.o
+obj-$(CONFIG_PPC_BOOK3E_64) += tlb_64e.o tlb_low_64e.o book3e_pgtable.o
obj-$(CONFIG_44x) += 44x.o
obj-$(CONFIG_PPC_8xx) += 8xx.o
obj-$(CONFIG_PPC_E500) += e500.o
diff --git a/arch/powerpc/mm/nohash/book3e_pgtable.c b/arch/powerpc/mm/nohash/book3e_pgtable.c
index 1c5e4ecbebeb..062e8785c1bb 100644
--- a/arch/powerpc/mm/nohash/book3e_pgtable.c
+++ b/arch/powerpc/mm/nohash/book3e_pgtable.c
@@ -10,7 +10,7 @@
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/dma.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <mm/mmu_decl.h>
@@ -29,10 +29,10 @@ int __meminit vmemmap_create_mapping(unsigned long start,
_PAGE_KERNEL_RW;
/* PTEs only contain page size encodings up to 32M */
- BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf);
+ BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].shift - 10 > 0xf);
/* Encode the size in the PTE */
- flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8;
+ flags |= (mmu_psize_defs[mmu_vmemmap_psize].shift - 10) << 8;
/* For each PTE for that area, map things. Note that we don't
* increment phys because all PTEs are of the large size and
diff --git a/arch/powerpc/mm/nohash/e500.c b/arch/powerpc/mm/nohash/e500.c
index 921c3521ec11..266fb22131fc 100644
--- a/arch/powerpc/mm/nohash/e500.c
+++ b/arch/powerpc/mm/nohash/e500.c
@@ -285,19 +285,23 @@ void __init adjust_total_lowmem(void)
}
#ifdef CONFIG_STRICT_KERNEL_RWX
-void mmu_mark_rodata_ro(void)
+int mmu_mark_rodata_ro(void)
{
unsigned long remapped;
remapped = map_mem_in_cams(__max_low_memory, CONFIG_LOWMEM_CAM_NUM, false, false);
- WARN_ON(__max_low_memory != remapped);
+ if (WARN_ON(__max_low_memory != remapped))
+ return -EINVAL;
+
+ return 0;
}
#endif
-void mmu_mark_initmem_nx(void)
+int mmu_mark_initmem_nx(void)
{
/* Everything is done in mmu_mark_rodata_ro() */
+ return 0;
}
void setup_initial_memory_limit(phys_addr_t first_memblock_base,
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
index b4f2786a7d2b..5c8d1bb98b3e 100644
--- a/arch/powerpc/mm/nohash/kaslr_booke.c
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -13,7 +13,7 @@
#include <linux/delay.h>
#include <linux/memblock.h>
#include <linux/libfdt.h>
-#include <linux/crash_core.h>
+#include <linux/crash_reserve.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <asm/cacheflush.h>
@@ -173,7 +173,7 @@ static __init bool overlaps_region(const void *fdt, u32 start,
static void __init get_crash_kernel(void *fdt, unsigned long size)
{
-#ifdef CONFIG_CRASH_CORE
+#ifdef CONFIG_CRASH_RESERVE
unsigned long long crash_size, crash_base;
int ret;
@@ -376,7 +376,7 @@ notrace void __init kaslr_early_init(void *dt_ptr, phys_addr_t size)
create_kaslr_tlb_entry(1, tlb_virt, tlb_phys);
}
- /* Copy the kernel to it's new location and run */
+ /* Copy the kernel to its new location and run */
memcpy((void *)kernstart_virt_addr, (void *)_stext, kernel_sz);
flush_icache_range(kernstart_virt_addr, kernstart_virt_addr + kernel_sz);
diff --git a/arch/powerpc/mm/nohash/kup.c b/arch/powerpc/mm/nohash/kup.c
index e1f7de2e54ec..c20c4f357fbf 100644
--- a/arch/powerpc/mm/nohash/kup.c
+++ b/arch/powerpc/mm/nohash/kup.c
@@ -15,8 +15,6 @@
void setup_kuap(bool disabled)
{
if (disabled) {
- if (IS_ENABLED(CONFIG_40x))
- disable_kuep = true;
if (smp_processor_id() == boot_cpuid)
cur_cpu_spec->mmu_features &= ~MMU_FTR_KUAP;
return;
diff --git a/arch/powerpc/mm/nohash/mmu_context.c b/arch/powerpc/mm/nohash/mmu_context.c
index ccd5819b1bd9..a1a4e697251a 100644
--- a/arch/powerpc/mm/nohash/mmu_context.c
+++ b/arch/powerpc/mm/nohash/mmu_context.c
@@ -219,9 +219,6 @@ static void set_context(unsigned long id, pgd_t *pgd)
/* sync */
mb();
} else if (kuap_is_disabled()) {
- if (IS_ENABLED(CONFIG_40x))
- mb(); /* sync */
-
mtspr(SPRN_PID, id);
isync();
}
@@ -306,7 +303,7 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next,
if (IS_ENABLED(CONFIG_BDI_SWITCH))
abatron_pteptrs[1] = next->pgd;
set_context(id, next->pgd);
-#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP)
tsk->thread.pid = id;
#endif
raw_spin_unlock(&context_lock);
@@ -388,21 +385,11 @@ void __init mmu_context_init(void)
/*
* Allocate the maps used by context management
*/
- context_map = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES);
- if (!context_map)
- panic("%s: Failed to allocate %zu bytes\n", __func__,
- CTX_MAP_SIZE);
- context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1),
+ context_map = memblock_alloc_or_panic(CTX_MAP_SIZE, SMP_CACHE_BYTES);
+ context_mm = memblock_alloc_or_panic(sizeof(void *) * (LAST_CONTEXT + 1),
SMP_CACHE_BYTES);
- if (!context_mm)
- panic("%s: Failed to allocate %zu bytes\n", __func__,
- sizeof(void *) * (LAST_CONTEXT + 1));
if (IS_ENABLED(CONFIG_SMP)) {
- stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES);
- if (!stale_map[boot_cpuid])
- panic("%s: Failed to allocate %zu bytes\n", __func__,
- CTX_MAP_SIZE);
-
+ stale_map[boot_cpuid] = memblock_alloc_or_panic(CTX_MAP_SIZE, SMP_CACHE_BYTES);
cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE,
"powerpc/mmu/ctx:prepare",
mmu_ctx_cpu_prepare, mmu_ctx_cpu_dead);
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index 5ffa0af4328a..0a650742f3a0 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -37,7 +37,7 @@
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/cputhreads.h>
#include <asm/hugetlb.h>
#include <asm/paca.h>
@@ -53,37 +53,30 @@
struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
[MMU_PAGE_4K] = {
.shift = 12,
- .enc = BOOK3E_PAGESZ_4K,
},
[MMU_PAGE_2M] = {
.shift = 21,
- .enc = BOOK3E_PAGESZ_2M,
},
[MMU_PAGE_4M] = {
.shift = 22,
- .enc = BOOK3E_PAGESZ_4M,
},
[MMU_PAGE_16M] = {
.shift = 24,
- .enc = BOOK3E_PAGESZ_16M,
},
[MMU_PAGE_64M] = {
.shift = 26,
- .enc = BOOK3E_PAGESZ_64M,
},
[MMU_PAGE_256M] = {
.shift = 28,
- .enc = BOOK3E_PAGESZ_256M,
},
[MMU_PAGE_1G] = {
.shift = 30,
- .enc = BOOK3E_PAGESZ_1GB,
},
};
static inline int mmu_get_tsize(int psize)
{
- return mmu_psize_defs[psize].enc;
+ return mmu_psize_defs[psize].shift - 10;
}
#else
static inline int mmu_get_tsize(int psize)
@@ -110,28 +103,6 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
};
#endif
-/* The variables below are currently only used on 64-bit Book3E
- * though this will probably be made common with other nohash
- * implementations at some point
- */
-#ifdef CONFIG_PPC64
-
-int mmu_pte_psize; /* Page size used for PTE pages */
-int mmu_vmemmap_psize; /* Page size used for the virtual mem map */
-int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */
-unsigned long linear_map_top; /* Top of linear mapping */
-
-
-/*
- * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
- * exceptions. This is used for bolted and e6500 TLB miss handlers which
- * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
- * this is set to zero.
- */
-int extlb_level_exc;
-
-#endif /* CONFIG_PPC64 */
-
#ifdef CONFIG_PPC_E500
/* next_tlbcam_idx is used to round-robin tlbcam entry assignment */
DEFINE_PER_CPU(int, next_tlbcam_idx);
@@ -358,381 +329,7 @@ void tlb_flush(struct mmu_gather *tlb)
flush_tlb_mm(tlb->mm);
}
-/*
- * Below are functions specific to the 64-bit variant of Book3E though that
- * may change in the future
- */
-
-#ifdef CONFIG_PPC64
-
-/*
- * Handling of virtual linear page tables or indirect TLB entries
- * flushing when PTE pages are freed
- */
-void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
-{
- int tsize = mmu_psize_defs[mmu_pte_psize].enc;
-
- if (book3e_htw_mode != PPC_HTW_NONE) {
- unsigned long start = address & PMD_MASK;
- unsigned long end = address + PMD_SIZE;
- unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
-
- /* This isn't the most optimal, ideally we would factor out the
- * while preempt & CPU mask mucking around, or even the IPI but
- * it will do for now
- */
- while (start < end) {
- __flush_tlb_page(tlb->mm, start, tsize, 1);
- start += size;
- }
- } else {
- unsigned long rmask = 0xf000000000000000ul;
- unsigned long rid = (address & rmask) | 0x1000000000000000ul;
- unsigned long vpte = address & ~rmask;
-
- vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
- vpte |= rid;
- __flush_tlb_page(tlb->mm, vpte, tsize, 0);
- }
-}
-
-static void __init setup_page_sizes(void)
-{
- unsigned int tlb0cfg;
- unsigned int tlb0ps;
- unsigned int eptcfg;
- int i, psize;
-
-#ifdef CONFIG_PPC_E500
- unsigned int mmucfg = mfspr(SPRN_MMUCFG);
- int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E);
-
- if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
- unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
- unsigned int min_pg, max_pg;
-
- min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
- max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
-
- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
- struct mmu_psize_def *def;
- unsigned int shift;
-
- def = &mmu_psize_defs[psize];
- shift = def->shift;
-
- if (shift == 0 || shift & 1)
- continue;
-
- /* adjust to be in terms of 4^shift Kb */
- shift = (shift - 10) >> 1;
-
- if ((shift >= min_pg) && (shift <= max_pg))
- def->flags |= MMU_PAGE_SIZE_DIRECT;
- }
-
- goto out;
- }
-
- if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
- u32 tlb1cfg, tlb1ps;
-
- tlb0cfg = mfspr(SPRN_TLB0CFG);
- tlb1cfg = mfspr(SPRN_TLB1CFG);
- tlb1ps = mfspr(SPRN_TLB1PS);
- eptcfg = mfspr(SPRN_EPTCFG);
-
- if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
- book3e_htw_mode = PPC_HTW_E6500;
-
- /*
- * We expect 4K subpage size and unrestricted indirect size.
- * The lack of a restriction on indirect size is a Freescale
- * extension, indicated by PSn = 0 but SPSn != 0.
- */
- if (eptcfg != 2)
- book3e_htw_mode = PPC_HTW_NONE;
-
- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
- struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
- if (!def->shift)
- continue;
-
- if (tlb1ps & (1U << (def->shift - 10))) {
- def->flags |= MMU_PAGE_SIZE_DIRECT;
-
- if (book3e_htw_mode && psize == MMU_PAGE_2M)
- def->flags |= MMU_PAGE_SIZE_INDIRECT;
- }
- }
-
- goto out;
- }
-#endif
-
- tlb0cfg = mfspr(SPRN_TLB0CFG);
- tlb0ps = mfspr(SPRN_TLB0PS);
- eptcfg = mfspr(SPRN_EPTCFG);
-
- /* Look for supported direct sizes */
- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
- struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
- if (tlb0ps & (1U << (def->shift - 10)))
- def->flags |= MMU_PAGE_SIZE_DIRECT;
- }
-
- /* Indirect page sizes supported ? */
- if ((tlb0cfg & TLBnCFG_IND) == 0 ||
- (tlb0cfg & TLBnCFG_PT) == 0)
- goto out;
-
- book3e_htw_mode = PPC_HTW_IBM;
-
- /* Now, we only deal with one IND page size for each
- * direct size. Hopefully all implementations today are
- * unambiguous, but we might want to be careful in the
- * future.
- */
- for (i = 0; i < 3; i++) {
- unsigned int ps, sps;
-
- sps = eptcfg & 0x1f;
- eptcfg >>= 5;
- ps = eptcfg & 0x1f;
- eptcfg >>= 5;
- if (!ps || !sps)
- continue;
- for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
- struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
- if (ps == (def->shift - 10))
- def->flags |= MMU_PAGE_SIZE_INDIRECT;
- if (sps == (def->shift - 10))
- def->ind = ps + 10;
- }
- }
-
-out:
- /* Cleanup array and print summary */
- pr_info("MMU: Supported page sizes\n");
- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
- struct mmu_psize_def *def = &mmu_psize_defs[psize];
- const char *__page_type_names[] = {
- "unsupported",
- "direct",
- "indirect",
- "direct & indirect"
- };
- if (def->flags == 0) {
- def->shift = 0;
- continue;
- }
- pr_info(" %8ld KB as %s\n", 1ul << (def->shift - 10),
- __page_type_names[def->flags & 0x3]);
- }
-}
-
-static void __init setup_mmu_htw(void)
-{
- /*
- * If we want to use HW tablewalk, enable it by patching the TLB miss
- * handlers to branch to the one dedicated to it.
- */
-
- switch (book3e_htw_mode) {
- case PPC_HTW_IBM:
- patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e);
- patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e);
- break;
-#ifdef CONFIG_PPC_E500
- case PPC_HTW_E6500:
- extlb_level_exc = EX_TLB_SIZE;
- patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
- patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
- break;
-#endif
- }
- pr_info("MMU: Book3E HW tablewalk %s\n",
- book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
-}
-
-/*
- * Early initialization of the MMU TLB code
- */
-static void early_init_this_mmu(void)
-{
- unsigned int mas4;
-
- /* Set MAS4 based on page table setting */
-
- mas4 = 0x4 << MAS4_WIMGED_SHIFT;
- switch (book3e_htw_mode) {
- case PPC_HTW_E6500:
- mas4 |= MAS4_INDD;
- mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
- mas4 |= MAS4_TLBSELD(1);
- mmu_pte_psize = MMU_PAGE_2M;
- break;
-
- case PPC_HTW_IBM:
- mas4 |= MAS4_INDD;
- mas4 |= BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT;
- mmu_pte_psize = MMU_PAGE_1M;
- break;
-
- case PPC_HTW_NONE:
- mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
- mmu_pte_psize = mmu_virtual_psize;
- break;
- }
- mtspr(SPRN_MAS4, mas4);
-
-#ifdef CONFIG_PPC_E500
- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
- unsigned int num_cams;
- bool map = true;
-
- /* use a quarter of the TLBCAM for bolted linear map */
- num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
-
- /*
- * Only do the mapping once per core, or else the
- * transient mapping would cause problems.
- */
-#ifdef CONFIG_SMP
- if (hweight32(get_tensr()) > 1)
- map = false;
-#endif
-
- if (map)
- linear_map_top = map_mem_in_cams(linear_map_top,
- num_cams, false, true);
- }
-#endif
-
- /* A sync won't hurt us after mucking around with
- * the MMU configuration
- */
- mb();
-}
-
-static void __init early_init_mmu_global(void)
-{
- /* XXX This should be decided at runtime based on supported
- * page sizes in the TLB, but for now let's assume 16M is
- * always there and a good fit (which it probably is)
- *
- * Freescale booke only supports 4K pages in TLB0, so use that.
- */
- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
- mmu_vmemmap_psize = MMU_PAGE_4K;
- else
- mmu_vmemmap_psize = MMU_PAGE_16M;
-
- /* XXX This code only checks for TLB 0 capabilities and doesn't
- * check what page size combos are supported by the HW. It
- * also doesn't handle the case where a separate array holds
- * the IND entries from the array loaded by the PT.
- */
- /* Look for supported page sizes */
- setup_page_sizes();
-
- /* Look for HW tablewalk support */
- setup_mmu_htw();
-
-#ifdef CONFIG_PPC_E500
- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
- if (book3e_htw_mode == PPC_HTW_NONE) {
- extlb_level_exc = EX_TLB_SIZE;
- patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
- patch_exception(0x1e0,
- exc_instruction_tlb_miss_bolted_book3e);
- }
- }
-#endif
-
- /* Set the global containing the top of the linear mapping
- * for use by the TLB miss code
- */
- linear_map_top = memblock_end_of_DRAM();
-
- ioremap_bot = IOREMAP_BASE;
-}
-
-static void __init early_mmu_set_memory_limit(void)
-{
-#ifdef CONFIG_PPC_E500
- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
- /*
- * Limit memory so we dont have linear faults.
- * Unlike memblock_set_current_limit, which limits
- * memory available during early boot, this permanently
- * reduces the memory available to Linux. We need to
- * do this because highmem is not supported on 64-bit.
- */
- memblock_enforce_memory_limit(linear_map_top);
- }
-#endif
-
- memblock_set_current_limit(linear_map_top);
-}
-
-/* boot cpu only */
-void __init early_init_mmu(void)
-{
- early_init_mmu_global();
- early_init_this_mmu();
- early_mmu_set_memory_limit();
-}
-
-void early_init_mmu_secondary(void)
-{
- early_init_this_mmu();
-}
-
-void setup_initial_memory_limit(phys_addr_t first_memblock_base,
- phys_addr_t first_memblock_size)
-{
- /* On non-FSL Embedded 64-bit, we adjust the RMA size to match
- * the bolted TLB entry. We know for now that only 1G
- * entries are supported though that may eventually
- * change.
- *
- * on FSL Embedded 64-bit, usually all RAM is bolted, but with
- * unusual memory sizes it's possible for some RAM to not be mapped
- * (such RAM is not used at all by Linux, since we don't support
- * highmem on 64-bit). We limit ppc64_rma_size to what would be
- * mappable if this memblock is the only one. Additional memblocks
- * can only increase, not decrease, the amount that ends up getting
- * mapped. We still limit max to 1G even if we'll eventually map
- * more. This is due to what the early init code is set up to do.
- *
- * We crop it to the size of the first MEMBLOCK to
- * avoid going over total available memory just in case...
- */
-#ifdef CONFIG_PPC_E500
- if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
- unsigned long linear_sz;
- unsigned int num_cams;
-
- /* use a quarter of the TLBCAM for bolted linear map */
- num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
-
- linear_sz = map_mem_in_cams(first_memblock_size, num_cams,
- true, true);
-
- ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
- } else
-#endif
- ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
-
- /* Finally limit subsequent allocations */
- memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
-}
-#else /* ! CONFIG_PPC64 */
+#ifndef CONFIG_PPC64
void __init early_init_mmu(void)
{
unsigned long root = of_get_flat_dt_root();
diff --git a/arch/powerpc/mm/nohash/tlb_64e.c b/arch/powerpc/mm/nohash/tlb_64e.c
new file mode 100644
index 000000000000..4f925adf2695
--- /dev/null
+++ b/arch/powerpc/mm/nohash/tlb_64e.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2008,2009 Ben Herrenschmidt <benh@kernel.crashing.org>
+ * IBM Corp.
+ *
+ * Derived from arch/ppc/mm/init.c:
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ * and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ * Copyright (C) 1996 Paul Mackerras
+ *
+ * Derived from "arch/i386/mm/init.c"
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/memblock.h>
+
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+#include <asm/text-patching.h>
+#include <asm/cputhreads.h>
+
+#include <mm/mmu_decl.h>
+
+/* The variables below are currently only used on 64-bit Book3E
+ * though this will probably be made common with other nohash
+ * implementations at some point
+ */
+static int mmu_pte_psize; /* Page size used for PTE pages */
+int mmu_vmemmap_psize; /* Page size used for the virtual mem map */
+int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */
+unsigned long linear_map_top; /* Top of linear mapping */
+
+
+/*
+ * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
+ * exceptions. This is used for bolted and e6500 TLB miss handlers which
+ * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
+ * this is set to zero.
+ */
+int extlb_level_exc;
+
+/*
+ * Handling of virtual linear page tables or indirect TLB entries
+ * flushing when PTE pages are freed
+ */
+void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+ int tsize = mmu_psize_defs[mmu_pte_psize].shift - 10;
+
+ if (book3e_htw_mode != PPC_HTW_NONE) {
+ unsigned long start = address & PMD_MASK;
+ unsigned long end = address + PMD_SIZE;
+ unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
+
+ /* This isn't the most optimal, ideally we would factor out the
+ * while preempt & CPU mask mucking around, or even the IPI but
+ * it will do for now
+ */
+ while (start < end) {
+ __flush_tlb_page(tlb->mm, start, tsize, 1);
+ start += size;
+ }
+ } else {
+ unsigned long rmask = 0xf000000000000000ul;
+ unsigned long rid = (address & rmask) | 0x1000000000000000ul;
+ unsigned long vpte = address & ~rmask;
+
+ vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
+ vpte |= rid;
+ __flush_tlb_page(tlb->mm, vpte, tsize, 0);
+ }
+}
+
+static void __init setup_page_sizes(void)
+{
+ unsigned int tlb0cfg;
+ unsigned int eptcfg;
+ int psize;
+
+ unsigned int mmucfg = mfspr(SPRN_MMUCFG);
+
+ if ((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
+ unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
+ unsigned int min_pg, max_pg;
+
+ min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
+ max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
+
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+ struct mmu_psize_def *def;
+ unsigned int shift;
+
+ def = &mmu_psize_defs[psize];
+ shift = def->shift;
+
+ if (shift == 0 || shift & 1)
+ continue;
+
+ /* adjust to be in terms of 4^shift Kb */
+ shift = (shift - 10) >> 1;
+
+ if ((shift >= min_pg) && (shift <= max_pg))
+ def->flags |= MMU_PAGE_SIZE_DIRECT;
+ }
+
+ goto out;
+ }
+
+ if ((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
+ u32 tlb1cfg, tlb1ps;
+
+ tlb0cfg = mfspr(SPRN_TLB0CFG);
+ tlb1cfg = mfspr(SPRN_TLB1CFG);
+ tlb1ps = mfspr(SPRN_TLB1PS);
+ eptcfg = mfspr(SPRN_EPTCFG);
+
+ if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
+ book3e_htw_mode = PPC_HTW_E6500;
+
+ /*
+ * We expect 4K subpage size and unrestricted indirect size.
+ * The lack of a restriction on indirect size is a Freescale
+ * extension, indicated by PSn = 0 but SPSn != 0.
+ */
+ if (eptcfg != 2)
+ book3e_htw_mode = PPC_HTW_NONE;
+
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+ struct mmu_psize_def *def = &mmu_psize_defs[psize];
+
+ if (!def->shift)
+ continue;
+
+ if (tlb1ps & (1U << (def->shift - 10))) {
+ def->flags |= MMU_PAGE_SIZE_DIRECT;
+
+ if (book3e_htw_mode && psize == MMU_PAGE_2M)
+ def->flags |= MMU_PAGE_SIZE_INDIRECT;
+ }
+ }
+
+ goto out;
+ }
+out:
+ /* Cleanup array and print summary */
+ pr_info("MMU: Supported page sizes\n");
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+ struct mmu_psize_def *def = &mmu_psize_defs[psize];
+ const char *__page_type_names[] = {
+ "unsupported",
+ "direct",
+ "indirect",
+ "direct & indirect"
+ };
+ if (def->flags == 0) {
+ def->shift = 0;
+ continue;
+ }
+ pr_info(" %8ld KB as %s\n", 1ul << (def->shift - 10),
+ __page_type_names[def->flags & 0x3]);
+ }
+}
+
+/*
+ * Early initialization of the MMU TLB code
+ */
+static void early_init_this_mmu(void)
+{
+ unsigned int mas4;
+
+ /* Set MAS4 based on page table setting */
+
+ mas4 = 0x4 << MAS4_WIMGED_SHIFT;
+ switch (book3e_htw_mode) {
+ case PPC_HTW_E6500:
+ mas4 |= MAS4_INDD;
+ mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
+ mas4 |= MAS4_TLBSELD(1);
+ mmu_pte_psize = MMU_PAGE_2M;
+ break;
+
+ case PPC_HTW_NONE:
+ mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
+ mmu_pte_psize = mmu_virtual_psize;
+ break;
+ }
+ mtspr(SPRN_MAS4, mas4);
+
+ unsigned int num_cams;
+ bool map = true;
+
+ /* use a quarter of the TLBCAM for bolted linear map */
+ num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+
+ /*
+ * Only do the mapping once per core, or else the
+ * transient mapping would cause problems.
+ */
+#ifdef CONFIG_SMP
+ if (hweight32(get_tensr()) > 1)
+ map = false;
+#endif
+
+ if (map)
+ linear_map_top = map_mem_in_cams(linear_map_top,
+ num_cams, false, true);
+
+ /* A sync won't hurt us after mucking around with
+ * the MMU configuration
+ */
+ mb();
+}
+
+static void __init early_init_mmu_global(void)
+{
+ /*
+ * Freescale booke only supports 4K pages in TLB0, so use that.
+ */
+ mmu_vmemmap_psize = MMU_PAGE_4K;
+
+ /* XXX This code only checks for TLB 0 capabilities and doesn't
+ * check what page size combos are supported by the HW. It
+ * also doesn't handle the case where a separate array holds
+ * the IND entries from the array loaded by the PT.
+ */
+ /* Look for supported page sizes */
+ setup_page_sizes();
+
+ /*
+ * If we want to use HW tablewalk, enable it by patching the TLB miss
+ * handlers to branch to the one dedicated to it.
+ */
+ extlb_level_exc = EX_TLB_SIZE;
+ switch (book3e_htw_mode) {
+ case PPC_HTW_E6500:
+ patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
+ patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
+ break;
+ }
+
+ pr_info("MMU: Book3E HW tablewalk %s\n",
+ book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
+
+ /* Set the global containing the top of the linear mapping
+ * for use by the TLB miss code
+ */
+ linear_map_top = memblock_end_of_DRAM();
+
+ ioremap_bot = IOREMAP_BASE;
+}
+
+static void __init early_mmu_set_memory_limit(void)
+{
+ /*
+ * Limit memory so we dont have linear faults.
+ * Unlike memblock_set_current_limit, which limits
+ * memory available during early boot, this permanently
+ * reduces the memory available to Linux. We need to
+ * do this because highmem is not supported on 64-bit.
+ */
+ memblock_enforce_memory_limit(linear_map_top);
+
+ memblock_set_current_limit(linear_map_top);
+}
+
+/* boot cpu only */
+void __init early_init_mmu(void)
+{
+ early_init_mmu_global();
+ early_init_this_mmu();
+ early_mmu_set_memory_limit();
+}
+
+void early_init_mmu_secondary(void)
+{
+ early_init_this_mmu();
+}
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+ phys_addr_t first_memblock_size)
+{
+ /*
+ * On FSL Embedded 64-bit, usually all RAM is bolted, but with
+ * unusual memory sizes it's possible for some RAM to not be mapped
+ * (such RAM is not used at all by Linux, since we don't support
+ * highmem on 64-bit). We limit ppc64_rma_size to what would be
+ * mappable if this memblock is the only one. Additional memblocks
+ * can only increase, not decrease, the amount that ends up getting
+ * mapped. We still limit max to 1G even if we'll eventually map
+ * more. This is due to what the early init code is set up to do.
+ *
+ * We crop it to the size of the first MEMBLOCK to
+ * avoid going over total available memory just in case...
+ */
+ unsigned long linear_sz;
+ unsigned int num_cams;
+
+ /* use a quarter of the TLBCAM for bolted linear map */
+ num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+
+ linear_sz = map_mem_in_cams(first_memblock_size, num_cams, true, true);
+ ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
+
+ /* Finally limit subsequent allocations */
+ memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
+}
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index e1199608ff4d..c4d296e73731 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -32,32 +32,7 @@
#include <asm/asm-compat.h>
#include <asm/feature-fixups.h>
-#if defined(CONFIG_40x)
-
-/*
- * 40x implementation needs only tlbil_va
- */
-_GLOBAL(__tlbil_va)
- /* We run the search with interrupts disabled because we have to change
- * the PID and I don't want to preempt when that happens.
- */
- mfmsr r5
- mfspr r6,SPRN_PID
- wrteei 0
- mtspr SPRN_PID,r4
- tlbsx. r3, 0, r3
- mtspr SPRN_PID,r6
- wrtee r5
- bne 1f
- sync
- /* There are only 64 TLB entries, so r3 < 64, which means bit 25 is
- * clear. Since 25 is the V bit in the TLB_TAG, loading this value
- * will invalidate the TLB entry. */
- tlbwe r3, r3, TLB_TAG
- isync
-1: blr
-
-#elif defined(CONFIG_PPC_8xx)
+#if defined(CONFIG_PPC_8xx)
/*
* Nothing to do for 8xx, everything is inline
diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S
index 7e0b8fe1c279..de568297d5c5 100644
--- a/arch/powerpc/mm/nohash/tlb_low_64e.S
+++ b/arch/powerpc/mm/nohash/tlb_low_64e.S
@@ -450,11 +450,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SMT)
tlb_miss_huge_e6500:
beq tlb_miss_fault_e6500
- li r10,1
- andi. r15,r14,HUGEPD_SHIFT_MASK@l /* r15 = psize */
- rldimi r14,r10,63,0 /* Set PD_HUGE */
- xor r14,r14,r15 /* Clear size bits */
- ldx r14,0,r14
+ rlwinm r15,r14,32-_PAGE_PSIZE_SHIFT,0x1e
/*
* Now we build the MAS for a huge page.
@@ -465,7 +461,6 @@ tlb_miss_huge_e6500:
* MAS 2,3+7: Needs to be redone similar to non-tablewalk handler
*/
- subi r15,r15,10 /* Convert psize to tsize */
mfspr r10,SPRN_MAS1
rlwinm r10,r10,0,~MAS1_IND
rlwimi r10,r15,MAS1_TSIZE_SHIFT,MAS1_TSIZE_MASK
@@ -511,232 +506,6 @@ itlb_miss_fault_e6500:
tlb_epilog_bolted
b exc_instruction_storage_book3e
-/**********************************************************************
- * *
- * TLB miss handling for Book3E with TLB reservation and HES support *
- * *
- **********************************************************************/
-
-
-/* Data TLB miss */
- START_EXCEPTION(data_tlb_miss)
- TLB_MISS_PROLOG
-
- /* Now we handle the fault proper. We only save DEAR in normal
- * fault case since that's the only interesting values here.
- * We could probably also optimize by not saving SRR0/1 in the
- * linear mapping case but I'll leave that for later
- */
- mfspr r14,SPRN_ESR
- mfspr r16,SPRN_DEAR /* get faulting address */
- srdi r15,r16,44 /* get region */
- xoris r15,r15,0xc
- cmpldi cr0,r15,0 /* linear mapping ? */
- beq tlb_load_linear /* yes -> go to linear map load */
- cmpldi cr1,r15,1 /* vmalloc mapping ? */
-
- /* The page tables are mapped virtually linear. At this point, though,
- * we don't know whether we are trying to fault in a first level
- * virtual address or a virtual page table address. We can get that
- * from bit 0x1 of the region ID which we have set for a page table
- */
- andis. r10,r15,0x1
- bne- virt_page_table_tlb_miss
-
- std r14,EX_TLB_ESR(r12); /* save ESR */
- std r16,EX_TLB_DEAR(r12); /* save DEAR */
-
- /* We need _PAGE_PRESENT and _PAGE_ACCESSED set */
- li r11,_PAGE_PRESENT
- oris r11,r11,_PAGE_ACCESSED@h
-
- /* We do the user/kernel test for the PID here along with the RW test
- */
- srdi. r15,r16,60 /* Check for user region */
-
- /* We pre-test some combination of permissions to avoid double
- * faults:
- *
- * We move the ESR:ST bit into the position of _PAGE_BAP_SW in the PTE
- * ESR_ST is 0x00800000
- * _PAGE_BAP_SW is 0x00000010
- * So the shift is >> 19. This tests for supervisor writeability.
- * If the page happens to be supervisor writeable and not user
- * writeable, we will take a new fault later, but that should be
- * a rare enough case.
- *
- * We also move ESR_ST in _PAGE_DIRTY position
- * _PAGE_DIRTY is 0x00001000 so the shift is >> 11
- *
- * MAS1 is preset for all we need except for TID that needs to
- * be cleared for kernel translations
- */
- rlwimi r11,r14,32-19,27,27
- rlwimi r11,r14,32-16,19,19
- beq normal_tlb_miss_user
- /* XXX replace the RMW cycles with immediate loads + writes */
-1: mfspr r10,SPRN_MAS1
- rlwinm r10,r10,0,16,1 /* Clear TID */
- mtspr SPRN_MAS1,r10
- beq+ cr1,normal_tlb_miss
-
- /* We got a crappy address, just fault with whatever DEAR and ESR
- * are here
- */
- TLB_MISS_EPILOG_ERROR
- b exc_data_storage_book3e
-
-/* Instruction TLB miss */
- START_EXCEPTION(instruction_tlb_miss)
- TLB_MISS_PROLOG
-
- /* If we take a recursive fault, the second level handler may need
- * to know whether we are handling a data or instruction fault in
- * order to get to the right store fault handler. We provide that
- * info by writing a crazy value in ESR in our exception frame
- */
- li r14,-1 /* store to exception frame is done later */
-
- /* Now we handle the fault proper. We only save DEAR in the non
- * linear mapping case since we know the linear mapping case will
- * not re-enter. We could indeed optimize and also not save SRR0/1
- * in the linear mapping case but I'll leave that for later
- *
- * Faulting address is SRR0 which is already in r16
- */
- srdi r15,r16,44 /* get region */
- xoris r15,r15,0xc
- cmpldi cr0,r15,0 /* linear mapping ? */
- beq tlb_load_linear /* yes -> go to linear map load */
- cmpldi cr1,r15,1 /* vmalloc mapping ? */
-
- /* We do the user/kernel test for the PID here along with the RW test
- */
- li r11,_PAGE_PRESENT|_PAGE_BAP_UX /* Base perm */
- oris r11,r11,_PAGE_ACCESSED@h
-
- srdi. r15,r16,60 /* Check for user region */
- std r14,EX_TLB_ESR(r12) /* write crazy -1 to frame */
- beq normal_tlb_miss_user
-
- li r11,_PAGE_PRESENT|_PAGE_BAP_SX /* Base perm */
- oris r11,r11,_PAGE_ACCESSED@h
- /* XXX replace the RMW cycles with immediate loads + writes */
- mfspr r10,SPRN_MAS1
- rlwinm r10,r10,0,16,1 /* Clear TID */
- mtspr SPRN_MAS1,r10
- beq+ cr1,normal_tlb_miss
-
- /* We got a crappy address, just fault */
- TLB_MISS_EPILOG_ERROR
- b exc_instruction_storage_book3e
-
-/*
- * This is the guts of the first-level TLB miss handler for direct
- * misses. We are entered with:
- *
- * r16 = faulting address
- * r15 = region ID
- * r14 = crap (free to use)
- * r13 = PACA
- * r12 = TLB exception frame in PACA
- * r11 = PTE permission mask
- * r10 = crap (free to use)
- */
-normal_tlb_miss_user:
-#ifdef CONFIG_PPC_KUAP
- mfspr r14,SPRN_MAS1
- rlwinm. r14,r14,0,0x3fff0000
- beq- normal_tlb_miss_access_fault /* KUAP fault */
-#endif
-normal_tlb_miss:
- /* So we first construct the page table address. We do that by
- * shifting the bottom of the address (not the region ID) by
- * PAGE_SHIFT-3, clearing the bottom 3 bits (get a PTE ptr) and
- * or'ing the fourth high bit.
- *
- * NOTE: For 64K pages, we do things slightly differently in
- * order to handle the weird page table format used by linux
- */
- srdi r15,r16,44
- oris r10,r15,0x1
- rldicl r14,r16,64-(PAGE_SHIFT-3),PAGE_SHIFT-3+4
- sldi r15,r10,44
- clrrdi r14,r14,19
- or r10,r15,r14
-
- ld r14,0(r10)
-
-finish_normal_tlb_miss:
- /* Check if required permissions are met */
- andc. r15,r11,r14
- bne- normal_tlb_miss_access_fault
-
- /* Now we build the MAS:
- *
- * MAS 0 : Fully setup with defaults in MAS4 and TLBnCFG
- * MAS 1 : Almost fully setup
- * - PID already updated by caller if necessary
- * - TSIZE need change if !base page size, not
- * yet implemented for now
- * MAS 2 : Defaults not useful, need to be redone
- * MAS 3+7 : Needs to be done
- *
- * TODO: mix up code below for better scheduling
- */
- clrrdi r10,r16,12 /* Clear low crap in EA */
- rlwimi r10,r14,32-19,27,31 /* Insert WIMGE */
- mtspr SPRN_MAS2,r10
-
- /* Check page size, if not standard, update MAS1 */
- rldicl r10,r14,64-8,64-8
- cmpldi cr0,r10,BOOK3E_PAGESZ_4K
- beq- 1f
- mfspr r11,SPRN_MAS1
- rlwimi r11,r14,31,21,24
- rlwinm r11,r11,0,21,19
- mtspr SPRN_MAS1,r11
-1:
- /* Move RPN in position */
- rldicr r11,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
- clrldi r15,r11,12 /* Clear crap at the top */
- rlwimi r15,r14,32-8,22,25 /* Move in U bits */
- rlwimi r15,r14,32-2,26,31 /* Move in BAP bits */
-
- /* Mask out SW and UW if !DIRTY (XXX optimize this !) */
- andi. r11,r14,_PAGE_DIRTY
- bne 1f
- li r11,MAS3_SW|MAS3_UW
- andc r15,r15,r11
-1:
- srdi r16,r15,32
- mtspr SPRN_MAS3,r15
- mtspr SPRN_MAS7,r16
-
- tlbwe
-
-normal_tlb_miss_done:
- /* We don't bother with restoring DEAR or ESR since we know we are
- * level 0 and just going back to userland. They are only needed
- * if you are going to take an access fault
- */
- TLB_MISS_EPILOG_SUCCESS
- rfi
-
-normal_tlb_miss_access_fault:
- /* We need to check if it was an instruction miss */
- andi. r10,r11,_PAGE_BAP_UX
- bne 1f
- ld r14,EX_TLB_DEAR(r12)
- ld r15,EX_TLB_ESR(r12)
- mtspr SPRN_DEAR,r14
- mtspr SPRN_ESR,r15
- TLB_MISS_EPILOG_ERROR
- b exc_data_storage_book3e
-1: TLB_MISS_EPILOG_ERROR
- b exc_instruction_storage_book3e
-
-
/*
* This is the guts of the second-level TLB miss handler for direct
* misses. We are entered with:
@@ -893,201 +662,6 @@ virt_page_table_tlb_miss_whacko_fault:
TLB_MISS_EPILOG_ERROR
b exc_data_storage_book3e
-
-/**************************************************************
- * *
- * TLB miss handling for Book3E with hw page table support *
- * *
- **************************************************************/
-
-
-/* Data TLB miss */
- START_EXCEPTION(data_tlb_miss_htw)
- TLB_MISS_PROLOG
-
- /* Now we handle the fault proper. We only save DEAR in normal
- * fault case since that's the only interesting values here.
- * We could probably also optimize by not saving SRR0/1 in the
- * linear mapping case but I'll leave that for later
- */
- mfspr r14,SPRN_ESR
- mfspr r16,SPRN_DEAR /* get faulting address */
- srdi r11,r16,44 /* get region */
- xoris r11,r11,0xc
- cmpldi cr0,r11,0 /* linear mapping ? */
- beq tlb_load_linear /* yes -> go to linear map load */
- cmpldi cr1,r11,1 /* vmalloc mapping ? */
-
- /* We do the user/kernel test for the PID here along with the RW test
- */
- srdi. r11,r16,60 /* Check for user region */
- ld r15,PACAPGD(r13) /* Load user pgdir */
- beq htw_tlb_miss
-
- /* XXX replace the RMW cycles with immediate loads + writes */
-1: mfspr r10,SPRN_MAS1
- rlwinm r10,r10,0,16,1 /* Clear TID */
- mtspr SPRN_MAS1,r10
- ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */
- beq+ cr1,htw_tlb_miss
-
- /* We got a crappy address, just fault with whatever DEAR and ESR
- * are here
- */
- TLB_MISS_EPILOG_ERROR
- b exc_data_storage_book3e
-
-/* Instruction TLB miss */
- START_EXCEPTION(instruction_tlb_miss_htw)
- TLB_MISS_PROLOG
-
- /* If we take a recursive fault, the second level handler may need
- * to know whether we are handling a data or instruction fault in
- * order to get to the right store fault handler. We provide that
- * info by keeping a crazy value for ESR in r14
- */
- li r14,-1 /* store to exception frame is done later */
-
- /* Now we handle the fault proper. We only save DEAR in the non
- * linear mapping case since we know the linear mapping case will
- * not re-enter. We could indeed optimize and also not save SRR0/1
- * in the linear mapping case but I'll leave that for later
- *
- * Faulting address is SRR0 which is already in r16
- */
- srdi r11,r16,44 /* get region */
- xoris r11,r11,0xc
- cmpldi cr0,r11,0 /* linear mapping ? */
- beq tlb_load_linear /* yes -> go to linear map load */
- cmpldi cr1,r11,1 /* vmalloc mapping ? */
-
- /* We do the user/kernel test for the PID here along with the RW test
- */
- srdi. r11,r16,60 /* Check for user region */
- ld r15,PACAPGD(r13) /* Load user pgdir */
- beq htw_tlb_miss
-
- /* XXX replace the RMW cycles with immediate loads + writes */
-1: mfspr r10,SPRN_MAS1
- rlwinm r10,r10,0,16,1 /* Clear TID */
- mtspr SPRN_MAS1,r10
- ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */
- beq+ htw_tlb_miss
-
- /* We got a crappy address, just fault */
- TLB_MISS_EPILOG_ERROR
- b exc_instruction_storage_book3e
-
-
-/*
- * This is the guts of the second-level TLB miss handler for direct
- * misses. We are entered with:
- *
- * r16 = virtual page table faulting address
- * r15 = PGD pointer
- * r14 = ESR
- * r13 = PACA
- * r12 = TLB exception frame in PACA
- * r11 = crap (free to use)
- * r10 = crap (free to use)
- *
- * It can be re-entered by the linear mapping miss handler. However, to
- * avoid too much complication, it will save/restore things for us
- */
-htw_tlb_miss:
-#ifdef CONFIG_PPC_KUAP
- mfspr r10,SPRN_MAS1
- rlwinm. r10,r10,0,0x3fff0000
- beq- htw_tlb_miss_fault /* KUAP fault */
-#endif
- /* Search if we already have a TLB entry for that virtual address, and
- * if we do, bail out.
- *
- * MAS1:IND should be already set based on MAS4
- */
- PPC_TLBSRX_DOT(0,R16)
- beq htw_tlb_miss_done
-
- /* Now, we need to walk the page tables. First check if we are in
- * range.
- */
- rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
- bne- htw_tlb_miss_fault
-
- /* Get the PGD pointer */
- cmpldi cr0,r15,0
- beq- htw_tlb_miss_fault
-
- /* Get to PGD entry */
- rldicl r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3
- clrrdi r10,r11,3
- ldx r15,r10,r15
- cmpdi cr0,r15,0
- bge htw_tlb_miss_fault
-
- /* Get to PUD entry */
- rldicl r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3
- clrrdi r10,r11,3
- ldx r15,r10,r15
- cmpdi cr0,r15,0
- bge htw_tlb_miss_fault
-
- /* Get to PMD entry */
- rldicl r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
- clrrdi r10,r11,3
- ldx r15,r10,r15
- cmpdi cr0,r15,0
- bge htw_tlb_miss_fault
-
- /* Ok, we're all right, we can now create an indirect entry for
- * a 1M or 256M page.
- *
- * The last trick is now that because we use "half" pages for
- * the HTW (1M IND is 2K and 256M IND is 32K) we need to account
- * for an added LSB bit to the RPN. For 64K pages, there is no
- * problem as we already use 32K arrays (half PTE pages), but for
- * 4K page we need to extract a bit from the virtual address and
- * insert it into the "PA52" bit of the RPN.
- */
- rlwimi r15,r16,32-9,20,20
- /* Now we build the MAS:
- *
- * MAS 0 : Fully setup with defaults in MAS4 and TLBnCFG
- * MAS 1 : Almost fully setup
- * - PID already updated by caller if necessary
- * - TSIZE for now is base ind page size always
- * MAS 2 : Use defaults
- * MAS 3+7 : Needs to be done
- */
- ori r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT)
-
- srdi r16,r10,32
- mtspr SPRN_MAS3,r10
- mtspr SPRN_MAS7,r16
-
- tlbwe
-
-htw_tlb_miss_done:
- /* We don't bother with restoring DEAR or ESR since we know we are
- * level 0 and just going back to userland. They are only needed
- * if you are going to take an access fault
- */
- TLB_MISS_EPILOG_SUCCESS
- rfi
-
-htw_tlb_miss_fault:
- /* We need to check if it was an instruction miss. We know this
- * though because r14 would contain -1
- */
- cmpdi cr0,r14,-1
- beq 1f
- mtspr SPRN_DEAR,r16
- mtspr SPRN_ESR,r14
- TLB_MISS_EPILOG_ERROR
- b exc_data_storage_book3e
-1: TLB_MISS_EPILOG_ERROR
- b exc_instruction_storage_book3e
-
/*
* This is the guts of "any" level TLB miss handler for kernel linear
* mapping misses. We are entered with:
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index f6c4ace3b221..3c1da08304d0 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -43,11 +43,9 @@ static char *cmdline __initdata;
int numa_cpu_lookup_table[NR_CPUS];
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
-struct pglist_data *node_data[MAX_NUMNODES];
EXPORT_SYMBOL(numa_cpu_lookup_table);
EXPORT_SYMBOL(node_to_cpumask_map);
-EXPORT_SYMBOL(node_data);
static int primary_domain_index;
static int n_mem_addr_cells, n_mem_size_cells;
@@ -896,7 +894,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
static int __init parse_numa_properties(void)
{
- struct device_node *memory;
+ struct device_node *memory, *pci;
int default_nid = 0;
unsigned long i;
const __be32 *associativity;
@@ -1010,6 +1008,18 @@ new_range:
goto new_range;
}
+ for_each_node_by_name(pci, "pci") {
+ int nid = NUMA_NO_NODE;
+
+ associativity = of_get_associativity(pci);
+ if (associativity) {
+ nid = associativity_to_nid(associativity);
+ initialize_form1_numa_distance(associativity);
+ }
+ if (likely(nid >= 0) && !node_online(nid))
+ node_set_online(nid);
+ }
+
/*
* Now do the same thing for each MEMBLOCK listed in the
* ibm,dynamic-memory property in the
@@ -1083,27 +1093,9 @@ void __init dump_numa_cpu_topology(void)
static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
{
u64 spanned_pages = end_pfn - start_pfn;
- const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
- u64 nd_pa;
- void *nd;
- int tnid;
-
- nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
- if (!nd_pa)
- panic("Cannot allocate %zu bytes for node %d data\n",
- nd_size, nid);
-
- nd = __va(nd_pa);
-
- /* report and initialize */
- pr_info(" NODE_DATA [mem %#010Lx-%#010Lx]\n",
- nd_pa, nd_pa + nd_size - 1);
- tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
- if (tnid != nid)
- pr_info(" NODE_DATA(%d) on node %d\n", nid, tnid);
-
- node_data[nid] = nd;
- memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+
+ alloc_node_data(nid);
+
NODE_DATA(nid)->node_id = nid;
NODE_DATA(nid)->node_start_pfn = start_pfn;
NODE_DATA(nid)->node_spanned_pages = spanned_pages;
@@ -1111,7 +1103,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
static void __init find_possible_nodes(void)
{
- struct device_node *rtas;
+ struct device_node *rtas, *root;
const __be32 *domains = NULL;
int prop_length, max_nodes;
u32 i;
@@ -1132,10 +1124,12 @@ static void __init find_possible_nodes(void)
* If the LPAR is migratable, new nodes might be activated after a LPM,
* so we should consider the max number in that case.
*/
- if (!of_get_property(of_root, "ibm,migratable-partition", NULL))
+ root = of_find_node_by_path("/");
+ if (!of_get_property(root, "ibm,migratable-partition", NULL))
domains = of_get_property(rtas,
"ibm,current-associativity-domains",
&prop_length);
+ of_node_put(root);
if (!domains) {
domains = of_get_property(rtas, "ibm,max-associativity-domains",
&prop_length);
diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
index 6163e484bc6d..ac22bf28086f 100644
--- a/arch/powerpc/mm/pageattr.c
+++ b/arch/powerpc/mm/pageattr.c
@@ -14,6 +14,7 @@
#include <asm/page.h>
#include <asm/pgtable.h>
+#include <mm/mmu_decl.h>
static pte_basic_t pte_update_delta(pte_t *ptep, unsigned long addr,
unsigned long old, unsigned long new)
@@ -38,6 +39,10 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
/* Don't clear DIRTY bit */
pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_RO);
break;
+ case SET_MEMORY_ROX:
+ /* Don't clear DIRTY bit */
+ pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_ROX);
+ break;
case SET_MEMORY_RW:
pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_RW);
break;
@@ -97,3 +102,26 @@ int change_memory_attr(unsigned long addr, int numpages, long action)
return apply_to_existing_page_range(&init_mm, start, size,
change_page_attr, (void *)action);
}
+
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+#ifdef CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+ int err;
+ unsigned long addr = (unsigned long)page_address(page);
+
+ if (PageHighMem(page))
+ return;
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
+ err = hash__kernel_map_pages(page, numpages, enable);
+ else if (enable)
+ err = set_memory_p(addr, numpages);
+ else
+ err = set_memory_np(addr, numpages);
+
+ if (err)
+ panic("%s: changing memory protections failed\n", __func__);
+}
+#endif
+#endif
diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
index 8c31802f97e8..713268ccb1a0 100644
--- a/arch/powerpc/mm/pgtable-frag.c
+++ b/arch/powerpc/mm/pgtable-frag.c
@@ -25,7 +25,7 @@ void pte_frag_destroy(void *pte_frag)
count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
/* We allow PTE_FRAG_NR fragments from a PTE page */
if (atomic_sub_and_test(PTE_FRAG_NR - count, &ptdesc->pt_frag_refcount)) {
- pagetable_pte_dtor(ptdesc);
+ pagetable_dtor(ptdesc);
pagetable_free(ptdesc);
}
}
@@ -111,7 +111,7 @@ static void pte_free_now(struct rcu_head *head)
struct ptdesc *ptdesc;
ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
- pagetable_pte_dtor(ptdesc);
+ pagetable_dtor(ptdesc);
pagetable_free(ptdesc);
}
@@ -136,10 +136,10 @@ void pte_fragment_free(unsigned long *table, int kernel)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
{
- struct page *page;
+ struct folio *folio;
- page = virt_to_page(pgtable);
- SetPageActive(page);
+ folio = virt_to_folio(pgtable);
+ folio_set_active(folio);
pte_fragment_free((unsigned long *)pgtable, 0);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index a04ae4449a02..61df5aed7989 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -220,10 +220,7 @@ void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
break;
ptep++;
addr += PAGE_SIZE;
- /*
- * increment the pfn.
- */
- pte = pfn_pte(pte_pfn(pte) + 1, pte_pgprot((pte)));
+ pte = pte_next_pfn(pte);
}
}
@@ -300,11 +297,14 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
}
#if defined(CONFIG_PPC_8xx)
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
- pte_t pte, unsigned long sz)
+
+#if defined(CONFIG_SPLIT_PTE_PTLOCKS) || defined(CONFIG_SPLIT_PMD_PTLOCKS)
+/* We need the same lock to protect the PMD table and the two PTE tables. */
+#error "8M hugetlb folios are incompatible with split page table locks"
+#endif
+
+static void __set_huge_pte_at(pmd_t *pmd, pte_t *ptep, pte_basic_t val)
{
- pmd_t *pmd = pmd_off(mm, addr);
- pte_basic_t val;
pte_basic_t *entry = (pte_basic_t *)ptep;
int num, i;
@@ -314,15 +314,60 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
*/
VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
- pte = set_pte_filter(pte, addr);
-
- val = pte_val(pte);
-
num = number_of_cells_per_pte(pmd, val, 1);
for (i = 0; i < num; i++, entry++, val += SZ_4K)
*entry = val;
}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned long sz)
+{
+ pmd_t *pmdp = pmd_off(mm, addr);
+
+ pte = set_pte_filter(pte, addr);
+
+ if (sz == SZ_8M) { /* Flag both PMD entries as 8M and fill both page tables */
+ *pmdp = __pmd(pmd_val(*pmdp) | _PMD_PAGE_8M);
+ *(pmdp + 1) = __pmd(pmd_val(*(pmdp + 1)) | _PMD_PAGE_8M);
+
+ __set_huge_pte_at(pmdp, pte_offset_kernel(pmdp, 0), pte_val(pte));
+ __set_huge_pte_at(pmdp, pte_offset_kernel(pmdp + 1, 0), pte_val(pte) + SZ_4M);
+ } else {
+ __set_huge_pte_at(pmdp, ptep, pte_val(pte));
+ }
+}
+#else
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned long sz)
+{
+ unsigned long pdsize;
+ int i;
+
+ pte = set_pte_filter(pte, addr);
+
+ /*
+ * Make sure hardware valid bit is not set. We don't do
+ * tlb flush for this update.
+ */
+ VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
+
+ if (sz < PMD_SIZE)
+ pdsize = PAGE_SIZE;
+ else if (sz < PUD_SIZE)
+ pdsize = PMD_SIZE;
+ else if (sz < P4D_SIZE)
+ pdsize = PUD_SIZE;
+ else if (sz < PGDIR_SIZE)
+ pdsize = P4D_SIZE;
+ else
+ pdsize = PGDIR_SIZE;
+
+ for (i = 0; i < sz / pdsize; i++, ptep++, addr += pdsize) {
+ __set_pte_at(mm, addr, ptep, pte, 0);
+ pte = __pte(pte_val(pte) + ((unsigned long long)pdsize / PAGE_SIZE << PFN_PTE_SHIFT));
+ }
+}
#endif
#endif /* CONFIG_HUGETLB_PAGE */
@@ -353,7 +398,7 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
*/
if (pmd_none(*pmd))
return;
- pte = pte_offset_map_nolock(mm, pmd, addr, &ptl);
+ pte = pte_offset_map_ro_nolock(mm, pmd, addr, &ptl);
BUG_ON(!pte);
assert_spin_locked(ptl);
pte_unmap(pte);
@@ -370,11 +415,10 @@ unsigned long vmalloc_to_phys(void *va)
EXPORT_SYMBOL_GPL(vmalloc_to_phys);
/*
- * We have 4 cases for pgds and pmds:
+ * We have 3 cases for pgds and pmds:
* (1) invalid (all zeroes)
* (2) pointer to next table, as normal; bottom 6 bits == 0
* (3) leaf pte for huge page _PAGE_PTE set
- * (4) hugepd pointer, _PAGE_PTE = 0 and bits [2..6] indicate size of table
*
* So long as we atomically load page table pointers we are safe against teardown,
* we can follow the address down to the page and take a ref on it.
@@ -385,11 +429,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
bool *is_thp, unsigned *hpage_shift)
{
pgd_t *pgdp;
+#ifdef CONFIG_PPC64
p4d_t p4d, *p4dp;
pud_t pud, *pudp;
+#endif
pmd_t pmd, *pmdp;
pte_t *ret_pte;
- hugepd_t *hpdp = NULL;
unsigned pdshift;
if (hpage_shift)
@@ -404,8 +449,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
* page fault or a page unmap. The return pte_t * is still not
* stable. So should be checked there for above conditions.
* Top level is an exception because it is folded into p4d.
+ *
+ * On PPC32, P4D/PUD/PMD are folded into PGD so go straight to
+ * PMD level.
*/
pgdp = pgdir + pgd_index(ea);
+#ifdef CONFIG_PPC64
p4dp = p4d_offset(pgdp, ea);
p4d = READ_ONCE(*p4dp);
pdshift = P4D_SHIFT;
@@ -413,16 +462,11 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
if (p4d_none(p4d))
return NULL;
- if (p4d_is_leaf(p4d)) {
+ if (p4d_leaf(p4d)) {
ret_pte = (pte_t *)p4dp;
goto out;
}
- if (is_hugepd(__hugepd(p4d_val(p4d)))) {
- hpdp = (hugepd_t *)&p4d;
- goto out_huge;
- }
-
/*
* Even if we end up with an unmap, the pgtable will not
* be freed, because we do an rcu free and here we are
@@ -435,18 +479,16 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
if (pud_none(pud))
return NULL;
- if (pud_is_leaf(pud)) {
+ if (pud_leaf(pud)) {
ret_pte = (pte_t *)pudp;
goto out;
}
- if (is_hugepd(__hugepd(pud_val(pud)))) {
- hpdp = (hugepd_t *)&pud;
- goto out_huge;
- }
-
- pdshift = PMD_SHIFT;
pmdp = pmd_offset(&pud, ea);
+#else
+ pmdp = pmd_offset(pud_offset(p4d_offset(pgdp, ea), ea), ea);
+#endif
+ pdshift = PMD_SHIFT;
pmd = READ_ONCE(*pmdp);
/*
@@ -474,24 +516,13 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
goto out;
}
- if (pmd_is_leaf(pmd)) {
+ if (pmd_leaf(pmd)) {
ret_pte = (pte_t *)pmdp;
goto out;
}
- if (is_hugepd(__hugepd(pmd_val(pmd)))) {
- hpdp = (hugepd_t *)&pmd;
- goto out_huge;
- }
-
return pte_offset_kernel(&pmd, ea);
-out_huge:
- if (!hpdp)
- return NULL;
-
- ret_pte = hugepte_offset(*hpdp, ea, pdshift);
- pdshift = hugepd_shift(*hpdp);
out:
if (hpage_shift)
*hpage_shift = pdshift;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 5c02fd08d61e..15276068f657 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -48,15 +48,10 @@ notrace void __init early_ioremap_init(void)
early_ioremap_setup();
}
-static void __init *early_alloc_pgtable(unsigned long size)
+void __init *early_alloc_pgtable(unsigned long size)
{
- void *ptr = memblock_alloc(size, size);
+ return memblock_alloc_or_panic(size, size);
- if (!ptr)
- panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
- __func__, size, size);
-
- return ptr;
}
pte_t __init *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va)
@@ -130,32 +125,41 @@ void __init mapin_ram(void)
}
}
-void mark_initmem_nx(void)
+static int __mark_initmem_nx(void)
{
unsigned long numpages = PFN_UP((unsigned long)_einittext) -
PFN_DOWN((unsigned long)_sinittext);
+ int err;
- mmu_mark_initmem_nx();
+ err = mmu_mark_initmem_nx();
if (!v_block_mapped((unsigned long)_sinittext)) {
- set_memory_nx((unsigned long)_sinittext, numpages);
- set_memory_rw((unsigned long)_sinittext, numpages);
+ err = set_memory_nx((unsigned long)_sinittext, numpages);
+ if (err)
+ return err;
+ err = set_memory_rw((unsigned long)_sinittext, numpages);
}
+ return err;
+}
+
+void mark_initmem_nx(void)
+{
+ int err = __mark_initmem_nx();
+
+ if (err)
+ panic("%s() failed, err = %d\n", __func__, err);
}
#ifdef CONFIG_STRICT_KERNEL_RWX
-void mark_rodata_ro(void)
+static int __mark_rodata_ro(void)
{
unsigned long numpages;
if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX) && mmu_has_feature(MMU_FTR_HPTE_TABLE))
pr_warn("This platform has HASH MMU, STRICT_MODULE_RWX won't work\n");
- if (v_block_mapped((unsigned long)_stext + 1)) {
- mmu_mark_rodata_ro();
- ptdump_check_wx();
- return;
- }
+ if (v_block_mapped((unsigned long)_stext + 1))
+ return mmu_mark_rodata_ro();
/*
* mark text and rodata as read only. __end_rodata is set by
@@ -165,24 +169,14 @@ void mark_rodata_ro(void)
numpages = PFN_UP((unsigned long)__end_rodata) -
PFN_DOWN((unsigned long)_stext);
- set_memory_ro((unsigned long)_stext, numpages);
-
- // mark_initmem_nx() should have already run by now
- ptdump_check_wx();
+ return set_memory_ro((unsigned long)_stext, numpages);
}
-#endif
-#if defined(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && defined(CONFIG_DEBUG_PAGEALLOC)
-void __kernel_map_pages(struct page *page, int numpages, int enable)
+void mark_rodata_ro(void)
{
- unsigned long addr = (unsigned long)page_address(page);
-
- if (PageHighMem(page))
- return;
+ int err = __mark_rodata_ro();
- if (enable)
- set_memory_p(addr, numpages);
- else
- set_memory_np(addr, numpages);
+ if (err)
+ panic("%s() failed, err = %d\n", __func__, err);
}
-#endif /* CONFIG_DEBUG_PAGEALLOC */
+#endif
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 5ac1fd30341b..6621cfc3baf8 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -100,9 +100,9 @@ EXPORT_SYMBOL(__pte_frag_size_shift);
/* 4 level page table */
struct page *p4d_page(p4d_t p4d)
{
- if (p4d_is_leaf(p4d)) {
+ if (p4d_leaf(p4d)) {
if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
- VM_WARN_ON(!p4d_huge(p4d));
+ VM_WARN_ON(!p4d_leaf(p4d));
return pte_page(p4d_pte(p4d));
}
return virt_to_page(p4d_pgtable(p4d));
@@ -111,9 +111,9 @@ struct page *p4d_page(p4d_t p4d)
struct page *pud_page(pud_t pud)
{
- if (pud_is_leaf(pud)) {
+ if (pud_leaf(pud)) {
if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
- VM_WARN_ON(!pud_huge(pud));
+ VM_WARN_ON(!pud_leaf(pud));
return pte_page(pud_pte(pud));
}
return virt_to_page(pud_pgtable(pud));
@@ -125,14 +125,14 @@ struct page *pud_page(pud_t pud)
*/
struct page *pmd_page(pmd_t pmd)
{
- if (pmd_is_leaf(pmd)) {
+ if (pmd_leaf(pmd)) {
/*
* vmalloc_to_page may be called on any vmap address (not only
* vmalloc), and it uses pmd_page() etc., when huge vmap is
* enabled so these checks can't be used.
*/
if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
- VM_WARN_ON(!(pmd_large(pmd) || pmd_huge(pmd)));
+ VM_WARN_ON(!pmd_leaf(pmd));
return pte_page(pmd_pte(pmd));
}
return virt_to_page(pmd_page_vaddr(pmd));
@@ -150,9 +150,6 @@ void mark_rodata_ro(void)
radix__mark_rodata_ro();
else
hash__mark_rodata_ro();
-
- // mark_initmem_nx() should have already run by now
- ptdump_check_wx();
}
void mark_initmem_nx(void)
diff --git a/arch/powerpc/mm/ptdump/Makefile b/arch/powerpc/mm/ptdump/Makefile
index dc896d2874f3..0f7a050f327e 100644
--- a/arch/powerpc/mm/ptdump/Makefile
+++ b/arch/powerpc/mm/ptdump/Makefile
@@ -2,7 +2,7 @@
obj-y += ptdump.o
-obj-$(CONFIG_4xx) += shared.o
+obj-$(CONFIG_44x) += shared.o
obj-$(CONFIG_PPC_8xx) += 8xx.o
obj-$(CONFIG_PPC_E500) += shared.o
obj-$(CONFIG_PPC_BOOK3S_32) += shared.o
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index 9a601587836b..a6baa6166d94 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -491,7 +491,7 @@ static void walk_vmemmap(struct pg_state *st)
* Traverse the vmemmaped memory and dump pages that are in the hash
* pagetable.
*/
- while (ptr->list) {
+ while (ptr) {
hpte_find(st, ptr->virt_addr, mmu_vmemmap_psize);
ptr = ptr->list;
}
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 2313053fe679..9dc239967b77 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -184,13 +184,14 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
{
pte_t pte = __pte(st->current_flags);
- if (!IS_ENABLED(CONFIG_DEBUG_WX) || !st->check_wx)
+ if (!st->check_wx)
return;
if (!pte_write(pte) || !pte_exec(pte))
return;
- WARN_ONCE(1, "powerpc/mm: Found insecure W+X mapping at address %p/%pS\n",
+ WARN_ONCE(IS_ENABLED(CONFIG_DEBUG_WX),
+ "powerpc/mm: Found insecure W+X mapping at address %p/%pS\n",
(void *)st->start_address, (void *)st->start_address);
st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
@@ -326,8 +327,7 @@ static void __init build_pgtable_complete_mask(void)
pg_level[i].mask |= pg_level[i].flag[j].mask;
}
-#ifdef CONFIG_DEBUG_WX
-void ptdump_check_wx(void)
+bool ptdump_check_wx(void)
{
struct pg_state st = {
.seq = NULL,
@@ -343,15 +343,22 @@ void ptdump_check_wx(void)
}
};
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !mmu_has_feature(MMU_FTR_KERNEL_RO))
+ return true;
+
ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
- if (st.wx_pages)
+ if (st.wx_pages) {
pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n",
st.wx_pages);
- else
+
+ return false;
+ } else {
pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+
+ return true;
+ }
}
-#endif
static int __init ptdump_init(void)
{
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index cdea5dccaefe..6beacaec63d3 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -12,6 +12,7 @@
#include <asm/types.h>
#include <asm/ppc-opcode.h>
+#include <linux/build_bug.h>
#ifdef CONFIG_PPC64_ELF_ABI_V1
#define FUNCTION_DESCR_SIZE 24
@@ -21,6 +22,9 @@
#define CTX_NIA(ctx) ((unsigned long)ctx->idx * 4)
+#define SZL sizeof(unsigned long)
+#define BPF_INSN_SAFETY 64
+
#define PLANT_INSTR(d, idx, instr) \
do { if (d) { (d)[idx] = instr; } idx++; } while (0)
#define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr)
@@ -81,6 +85,18 @@
EMIT(PPC_RAW_ORI(d, d, (uintptr_t)(i) & \
0xffff)); \
} } while (0)
+#define PPC_LI_ADDR PPC_LI64
+
+#ifndef CONFIG_PPC_KERNEL_PCREL
+#define PPC64_LOAD_PACA() \
+ EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)))
+#else
+#define PPC64_LOAD_PACA() do {} while (0)
+#endif
+#else
+#define PPC_LI64(d, i) BUILD_BUG()
+#define PPC_LI_ADDR PPC_LI32
+#define PPC64_LOAD_PACA() BUILD_BUG()
#endif
/*
@@ -165,6 +181,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
u32 *addrs, int pass, bool extra_pass);
void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
+void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx);
void bpf_jit_realloc_regs(struct codegen_context *ctx);
int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr);
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 0f9a21783329..2991bb171a9b 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -18,15 +18,85 @@
#include <linux/bpf.h>
#include <asm/kprobes.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include "bpf_jit.h"
+/* These offsets are from bpf prog end and stay the same across progs */
+static int bpf_jit_ool_stub, bpf_jit_long_branch_stub;
+
static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
{
memset32(area, BREAKPOINT_INSTRUCTION, size / 4);
}
+void dummy_tramp(void);
+
+asm (
+" .pushsection .text, \"ax\", @progbits ;"
+" .global dummy_tramp ;"
+" .type dummy_tramp, @function ;"
+"dummy_tramp: ;"
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+" blr ;"
+#else
+/* LR is always in r11, so we don't need a 'mflr r11' here */
+" mtctr 11 ;"
+" mtlr 0 ;"
+" bctr ;"
+#endif
+" .size dummy_tramp, .-dummy_tramp ;"
+" .popsection ;"
+);
+
+void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
+{
+ int ool_stub_idx, long_branch_stub_idx;
+
+ /*
+ * Out-of-line stub:
+ * mflr r0
+ * [b|bl] tramp
+ * mtlr r0 // only with CONFIG_PPC_FTRACE_OUT_OF_LINE
+ * b bpf_func + 4
+ */
+ ool_stub_idx = ctx->idx;
+ EMIT(PPC_RAW_MFLR(_R0));
+ EMIT(PPC_RAW_NOP());
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+ EMIT(PPC_RAW_MTLR(_R0));
+ WARN_ON_ONCE(!is_offset_in_branch_range(4 - (long)ctx->idx * 4));
+ EMIT(PPC_RAW_BRANCH(4 - (long)ctx->idx * 4));
+
+ /*
+ * Long branch stub:
+ * .long <dummy_tramp_addr>
+ * mflr r11
+ * bcl 20,31,$+4
+ * mflr r12
+ * ld r12, -8-SZL(r12)
+ * mtctr r12
+ * mtlr r11 // needed to retain ftrace ABI
+ * bctr
+ */
+ if (image)
+ *((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp;
+ ctx->idx += SZL / 4;
+ long_branch_stub_idx = ctx->idx;
+ EMIT(PPC_RAW_MFLR(_R11));
+ EMIT(PPC_RAW_BCL4());
+ EMIT(PPC_RAW_MFLR(_R12));
+ EMIT(PPC_RAW_LL(_R12, _R12, -8-SZL));
+ EMIT(PPC_RAW_MTCTR(_R12));
+ EMIT(PPC_RAW_MTLR(_R11));
+ EMIT(PPC_RAW_BCTR());
+
+ if (!bpf_jit_ool_stub) {
+ bpf_jit_ool_stub = (ctx->idx - ool_stub_idx) * 4;
+ bpf_jit_long_branch_stub = (ctx->idx - long_branch_stub_idx) * 4;
+ }
+}
+
int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr)
{
if (!exit_addr || is_offset_in_branch_range(exit_addr - (ctx->idx * 4))) {
@@ -222,10 +292,10 @@ skip_init_ctx:
fp->bpf_func = (void *)fimage;
fp->jited = 1;
- fp->jited_len = proglen + FUNCTION_DESCR_SIZE;
+ fp->jited_len = cgctx.idx * 4 + FUNCTION_DESCR_SIZE;
if (!fp->is_func || extra_pass) {
- if (bpf_jit_binary_pack_finalize(fp, fhdr, hdr)) {
+ if (bpf_jit_binary_pack_finalize(fhdr, hdr)) {
fp = org_fp;
goto out_addrs;
}
@@ -348,7 +418,7 @@ void bpf_jit_free(struct bpf_prog *fp)
* before freeing it.
*/
if (jit_data) {
- bpf_jit_binary_pack_finalize(fp, jit_data->fhdr, jit_data->hdr);
+ bpf_jit_binary_pack_finalize(jit_data->fhdr, jit_data->hdr);
kvfree(jit_data->addrs);
kfree(jit_data);
}
@@ -359,3 +429,788 @@ void bpf_jit_free(struct bpf_prog *fp)
bpf_prog_unlock_free(fp);
}
+
+bool bpf_jit_supports_kfunc_call(void)
+{
+ return true;
+}
+
+bool bpf_jit_supports_far_kfunc_call(void)
+{
+ return IS_ENABLED(CONFIG_PPC64);
+}
+
+void *arch_alloc_bpf_trampoline(unsigned int size)
+{
+ return bpf_prog_pack_alloc(size, bpf_jit_fill_ill_insns);
+}
+
+void arch_free_bpf_trampoline(void *image, unsigned int size)
+{
+ bpf_prog_pack_free(image, size);
+}
+
+int arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+ return 0;
+}
+
+static int invoke_bpf_prog(u32 *image, u32 *ro_image, struct codegen_context *ctx,
+ struct bpf_tramp_link *l, int regs_off, int retval_off,
+ int run_ctx_off, bool save_ret)
+{
+ struct bpf_prog *p = l->link.prog;
+ ppc_inst_t branch_insn;
+ u32 jmp_idx;
+ int ret = 0;
+
+ /* Save cookie */
+ if (IS_ENABLED(CONFIG_PPC64)) {
+ PPC_LI64(_R3, l->cookie);
+ EMIT(PPC_RAW_STD(_R3, _R1, run_ctx_off + offsetof(struct bpf_tramp_run_ctx,
+ bpf_cookie)));
+ } else {
+ PPC_LI32(_R3, l->cookie >> 32);
+ PPC_LI32(_R4, l->cookie);
+ EMIT(PPC_RAW_STW(_R3, _R1,
+ run_ctx_off + offsetof(struct bpf_tramp_run_ctx, bpf_cookie)));
+ EMIT(PPC_RAW_STW(_R4, _R1,
+ run_ctx_off + offsetof(struct bpf_tramp_run_ctx, bpf_cookie) + 4));
+ }
+
+ /* __bpf_prog_enter(p, &bpf_tramp_run_ctx) */
+ PPC_LI_ADDR(_R3, p);
+ EMIT(PPC_RAW_MR(_R25, _R3));
+ EMIT(PPC_RAW_ADDI(_R4, _R1, run_ctx_off));
+ ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
+ (unsigned long)bpf_trampoline_enter(p));
+ if (ret)
+ return ret;
+
+ /* Remember prog start time returned by __bpf_prog_enter */
+ EMIT(PPC_RAW_MR(_R26, _R3));
+
+ /*
+ * if (__bpf_prog_enter(p) == 0)
+ * goto skip_exec_of_prog;
+ *
+ * Emit a nop to be later patched with conditional branch, once offset is known
+ */
+ EMIT(PPC_RAW_CMPLI(_R3, 0));
+ jmp_idx = ctx->idx;
+ EMIT(PPC_RAW_NOP());
+
+ /* p->bpf_func(ctx) */
+ EMIT(PPC_RAW_ADDI(_R3, _R1, regs_off));
+ if (!p->jited)
+ PPC_LI_ADDR(_R4, (unsigned long)p->insnsi);
+ if (!create_branch(&branch_insn, (u32 *)&ro_image[ctx->idx], (unsigned long)p->bpf_func,
+ BRANCH_SET_LINK)) {
+ if (image)
+ image[ctx->idx] = ppc_inst_val(branch_insn);
+ ctx->idx++;
+ } else {
+ EMIT(PPC_RAW_LL(_R12, _R25, offsetof(struct bpf_prog, bpf_func)));
+ EMIT(PPC_RAW_MTCTR(_R12));
+ EMIT(PPC_RAW_BCTRL());
+ }
+
+ if (save_ret)
+ EMIT(PPC_RAW_STL(_R3, _R1, retval_off));
+
+ /* Fix up branch */
+ if (image) {
+ if (create_cond_branch(&branch_insn, &image[jmp_idx],
+ (unsigned long)&image[ctx->idx], COND_EQ << 16))
+ return -EINVAL;
+ image[jmp_idx] = ppc_inst_val(branch_insn);
+ }
+
+ /* __bpf_prog_exit(p, start_time, &bpf_tramp_run_ctx) */
+ EMIT(PPC_RAW_MR(_R3, _R25));
+ EMIT(PPC_RAW_MR(_R4, _R26));
+ EMIT(PPC_RAW_ADDI(_R5, _R1, run_ctx_off));
+ ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
+ (unsigned long)bpf_trampoline_exit(p));
+
+ return ret;
+}
+
+static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context *ctx,
+ struct bpf_tramp_links *tl, int regs_off, int retval_off,
+ int run_ctx_off, u32 *branches)
+{
+ int i;
+
+ /*
+ * The first fmod_ret program will receive a garbage return value.
+ * Set this to 0 to avoid confusing the program.
+ */
+ EMIT(PPC_RAW_LI(_R3, 0));
+ EMIT(PPC_RAW_STL(_R3, _R1, retval_off));
+ for (i = 0; i < tl->nr_links; i++) {
+ if (invoke_bpf_prog(image, ro_image, ctx, tl->links[i], regs_off, retval_off,
+ run_ctx_off, true))
+ return -EINVAL;
+
+ /*
+ * mod_ret prog stored return value after prog ctx. Emit:
+ * if (*(u64 *)(ret_val) != 0)
+ * goto do_fexit;
+ */
+ EMIT(PPC_RAW_LL(_R3, _R1, retval_off));
+ EMIT(PPC_RAW_CMPLI(_R3, 0));
+
+ /*
+ * Save the location of the branch and generate a nop, which is
+ * replaced with a conditional jump once do_fexit (i.e. the
+ * start of the fexit invocation) is finalized.
+ */
+ branches[i] = ctx->idx;
+ EMIT(PPC_RAW_NOP());
+ }
+
+ return 0;
+}
+
+static void bpf_trampoline_setup_tail_call_cnt(u32 *image, struct codegen_context *ctx,
+ int func_frame_offset, int r4_off)
+{
+ if (IS_ENABLED(CONFIG_PPC64)) {
+ /* See bpf_jit_stack_tailcallcnt() */
+ int tailcallcnt_offset = 6 * 8;
+
+ EMIT(PPC_RAW_LL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
+ EMIT(PPC_RAW_STL(_R3, _R1, -tailcallcnt_offset));
+ } else {
+ /* See bpf_jit_stack_offsetof() and BPF_PPC_TC */
+ EMIT(PPC_RAW_LL(_R4, _R1, r4_off));
+ }
+}
+
+static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_context *ctx,
+ int func_frame_offset, int r4_off)
+{
+ if (IS_ENABLED(CONFIG_PPC64)) {
+ /* See bpf_jit_stack_tailcallcnt() */
+ int tailcallcnt_offset = 6 * 8;
+
+ EMIT(PPC_RAW_LL(_R3, _R1, -tailcallcnt_offset));
+ EMIT(PPC_RAW_STL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
+ } else {
+ /* See bpf_jit_stack_offsetof() and BPF_PPC_TC */
+ EMIT(PPC_RAW_STL(_R4, _R1, r4_off));
+ }
+}
+
+static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx, int func_frame_offset,
+ int nr_regs, int regs_off)
+{
+ int param_save_area_offset;
+
+ param_save_area_offset = func_frame_offset; /* the two frames we alloted */
+ param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */
+
+ for (int i = 0; i < nr_regs; i++) {
+ if (i < 8) {
+ EMIT(PPC_RAW_STL(_R3 + i, _R1, regs_off + i * SZL));
+ } else {
+ EMIT(PPC_RAW_LL(_R3, _R1, param_save_area_offset + i * SZL));
+ EMIT(PPC_RAW_STL(_R3, _R1, regs_off + i * SZL));
+ }
+ }
+}
+
+/* Used when restoring just the register parameters when returning back */
+static void bpf_trampoline_restore_args_regs(u32 *image, struct codegen_context *ctx,
+ int nr_regs, int regs_off)
+{
+ for (int i = 0; i < nr_regs && i < 8; i++)
+ EMIT(PPC_RAW_LL(_R3 + i, _R1, regs_off + i * SZL));
+}
+
+/* Used when we call into the traced function. Replicate parameter save area */
+static void bpf_trampoline_restore_args_stack(u32 *image, struct codegen_context *ctx,
+ int func_frame_offset, int nr_regs, int regs_off)
+{
+ int param_save_area_offset;
+
+ param_save_area_offset = func_frame_offset; /* the two frames we alloted */
+ param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */
+
+ for (int i = 8; i < nr_regs; i++) {
+ EMIT(PPC_RAW_LL(_R3, _R1, param_save_area_offset + i * SZL));
+ EMIT(PPC_RAW_STL(_R3, _R1, STACK_FRAME_MIN_SIZE + i * SZL));
+ }
+ bpf_trampoline_restore_args_regs(image, ctx, nr_regs, regs_off);
+}
+
+static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image,
+ void *rw_image_end, void *ro_image,
+ const struct btf_func_model *m, u32 flags,
+ struct bpf_tramp_links *tlinks,
+ void *func_addr)
+{
+ int regs_off, nregs_off, ip_off, run_ctx_off, retval_off, nvr_off, alt_lr_off, r4_off = 0;
+ int i, ret, nr_regs, bpf_frame_size = 0, bpf_dummy_frame_size = 0, func_frame_offset;
+ struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+ struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
+ struct codegen_context codegen_ctx, *ctx;
+ u32 *image = (u32 *)rw_image;
+ ppc_inst_t branch_insn;
+ u32 *branches = NULL;
+ bool save_ret;
+
+ if (IS_ENABLED(CONFIG_PPC32))
+ return -EOPNOTSUPP;
+
+ nr_regs = m->nr_args;
+ /* Extra registers for struct arguments */
+ for (i = 0; i < m->nr_args; i++)
+ if (m->arg_size[i] > SZL)
+ nr_regs += round_up(m->arg_size[i], SZL) / SZL - 1;
+
+ if (nr_regs > MAX_BPF_FUNC_ARGS)
+ return -EOPNOTSUPP;
+
+ ctx = &codegen_ctx;
+ memset(ctx, 0, sizeof(*ctx));
+
+ /*
+ * Generated stack layout:
+ *
+ * func prev back chain [ back chain ]
+ * [ ]
+ * bpf prog redzone/tailcallcnt [ ... ] 64 bytes (64-bit powerpc)
+ * [ ] --
+ * LR save area [ r0 save (64-bit) ] | header
+ * [ r0 save (32-bit) ] |
+ * dummy frame for unwind [ back chain 1 ] --
+ * [ padding ] align stack frame
+ * r4_off [ r4 (tailcallcnt) ] optional - 32-bit powerpc
+ * alt_lr_off [ real lr (ool stub)] optional - actual lr
+ * [ r26 ]
+ * nvr_off [ r25 ] nvr save area
+ * retval_off [ return value ]
+ * [ reg argN ]
+ * [ ... ]
+ * regs_off [ reg_arg1 ] prog ctx context
+ * nregs_off [ args count ]
+ * ip_off [ traced function ]
+ * [ ... ]
+ * run_ctx_off [ bpf_tramp_run_ctx ]
+ * [ reg argN ]
+ * [ ... ]
+ * param_save_area [ reg_arg1 ] min 8 doublewords, per ABI
+ * [ TOC save (64-bit) ] --
+ * [ LR save (64-bit) ] | header
+ * [ LR save (32-bit) ] |
+ * bpf trampoline frame [ back chain 2 ] --
+ *
+ */
+
+ /* Minimum stack frame header */
+ bpf_frame_size = STACK_FRAME_MIN_SIZE;
+
+ /*
+ * Room for parameter save area.
+ *
+ * As per the ABI, this is required if we call into the traced
+ * function (BPF_TRAMP_F_CALL_ORIG):
+ * - if the function takes more than 8 arguments for the rest to spill onto the stack
+ * - or, if the function has variadic arguments
+ * - or, if this functions's prototype was not available to the caller
+ *
+ * Reserve space for at least 8 registers for now. This can be optimized later.
+ */
+ bpf_frame_size += (nr_regs > 8 ? nr_regs : 8) * SZL;
+
+ /* Room for struct bpf_tramp_run_ctx */
+ run_ctx_off = bpf_frame_size;
+ bpf_frame_size += round_up(sizeof(struct bpf_tramp_run_ctx), SZL);
+
+ /* Room for IP address argument */
+ ip_off = bpf_frame_size;
+ if (flags & BPF_TRAMP_F_IP_ARG)
+ bpf_frame_size += SZL;
+
+ /* Room for args count */
+ nregs_off = bpf_frame_size;
+ bpf_frame_size += SZL;
+
+ /* Room for args */
+ regs_off = bpf_frame_size;
+ bpf_frame_size += nr_regs * SZL;
+
+ /* Room for return value of func_addr or fentry prog */
+ retval_off = bpf_frame_size;
+ save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
+ if (save_ret)
+ bpf_frame_size += SZL;
+
+ /* Room for nvr save area */
+ nvr_off = bpf_frame_size;
+ bpf_frame_size += 2 * SZL;
+
+ /* Optional save area for actual LR in case of ool ftrace */
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+ alt_lr_off = bpf_frame_size;
+ bpf_frame_size += SZL;
+ }
+
+ if (IS_ENABLED(CONFIG_PPC32)) {
+ if (nr_regs < 2) {
+ r4_off = bpf_frame_size;
+ bpf_frame_size += SZL;
+ } else {
+ r4_off = regs_off + SZL;
+ }
+ }
+
+ /* Padding to align stack frame, if any */
+ bpf_frame_size = round_up(bpf_frame_size, SZL * 2);
+
+ /* Dummy frame size for proper unwind - includes 64-bytes red zone for 64-bit powerpc */
+ bpf_dummy_frame_size = STACK_FRAME_MIN_SIZE + 64;
+
+ /* Offset to the traced function's stack frame */
+ func_frame_offset = bpf_dummy_frame_size + bpf_frame_size;
+
+ /* Create dummy frame for unwind, store original return value */
+ EMIT(PPC_RAW_STL(_R0, _R1, PPC_LR_STKOFF));
+ /* Protect red zone where tail call count goes */
+ EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_dummy_frame_size));
+
+ /* Create our stack frame */
+ EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_frame_size));
+
+ /* 64-bit: Save TOC and load kernel TOC */
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
+ EMIT(PPC_RAW_STD(_R2, _R1, 24));
+ PPC64_LOAD_PACA();
+ }
+
+ /* 32-bit: save tail call count in r4 */
+ if (IS_ENABLED(CONFIG_PPC32) && nr_regs < 2)
+ EMIT(PPC_RAW_STL(_R4, _R1, r4_off));
+
+ bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off);
+
+ /* Save our return address */
+ EMIT(PPC_RAW_MFLR(_R3));
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+ EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off));
+ else
+ EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+
+ /*
+ * Save ip address of the traced function.
+ * We could recover this from LR, but we will need to address for OOL trampoline,
+ * and optional GEP area.
+ */
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) || flags & BPF_TRAMP_F_IP_ARG) {
+ EMIT(PPC_RAW_LWZ(_R4, _R3, 4));
+ EMIT(PPC_RAW_SLWI(_R4, _R4, 6));
+ EMIT(PPC_RAW_SRAWI(_R4, _R4, 6));
+ EMIT(PPC_RAW_ADD(_R3, _R3, _R4));
+ EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
+ }
+
+ if (flags & BPF_TRAMP_F_IP_ARG)
+ EMIT(PPC_RAW_STL(_R3, _R1, ip_off));
+
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+ /* Fake our LR for unwind */
+ EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+
+ /* Save function arg count -- see bpf_get_func_arg_cnt() */
+ EMIT(PPC_RAW_LI(_R3, nr_regs));
+ EMIT(PPC_RAW_STL(_R3, _R1, nregs_off));
+
+ /* Save nv regs */
+ EMIT(PPC_RAW_STL(_R25, _R1, nvr_off));
+ EMIT(PPC_RAW_STL(_R26, _R1, nvr_off + SZL));
+
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ PPC_LI_ADDR(_R3, (unsigned long)im);
+ ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
+ (unsigned long)__bpf_tramp_enter);
+ if (ret)
+ return ret;
+ }
+
+ for (i = 0; i < fentry->nr_links; i++)
+ if (invoke_bpf_prog(image, ro_image, ctx, fentry->links[i], regs_off, retval_off,
+ run_ctx_off, flags & BPF_TRAMP_F_RET_FENTRY_RET))
+ return -EINVAL;
+
+ if (fmod_ret->nr_links) {
+ branches = kcalloc(fmod_ret->nr_links, sizeof(u32), GFP_KERNEL);
+ if (!branches)
+ return -ENOMEM;
+
+ if (invoke_bpf_mod_ret(image, ro_image, ctx, fmod_ret, regs_off, retval_off,
+ run_ctx_off, branches)) {
+ ret = -EINVAL;
+ goto cleanup;
+ }
+ }
+
+ /* Call the traced function */
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ /*
+ * The address in LR save area points to the correct point in the original function
+ * with both PPC_FTRACE_OUT_OF_LINE as well as with traditional ftrace instruction
+ * sequence
+ */
+ EMIT(PPC_RAW_LL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+ EMIT(PPC_RAW_MTCTR(_R3));
+
+ /* Replicate tail_call_cnt before calling the original BPF prog */
+ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+ bpf_trampoline_setup_tail_call_cnt(image, ctx, func_frame_offset, r4_off);
+
+ /* Restore args */
+ bpf_trampoline_restore_args_stack(image, ctx, func_frame_offset, nr_regs, regs_off);
+
+ /* Restore TOC for 64-bit */
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ EMIT(PPC_RAW_LD(_R2, _R1, 24));
+ EMIT(PPC_RAW_BCTRL());
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ PPC64_LOAD_PACA();
+
+ /* Store return value for bpf prog to access */
+ EMIT(PPC_RAW_STL(_R3, _R1, retval_off));
+
+ /* Restore updated tail_call_cnt */
+ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+ bpf_trampoline_restore_tail_call_cnt(image, ctx, func_frame_offset, r4_off);
+
+ /* Reserve space to patch branch instruction to skip fexit progs */
+ im->ip_after_call = &((u32 *)ro_image)[ctx->idx];
+ EMIT(PPC_RAW_NOP());
+ }
+
+ /* Update branches saved in invoke_bpf_mod_ret with address of do_fexit */
+ for (i = 0; i < fmod_ret->nr_links && image; i++) {
+ if (create_cond_branch(&branch_insn, &image[branches[i]],
+ (unsigned long)&image[ctx->idx], COND_NE << 16)) {
+ ret = -EINVAL;
+ goto cleanup;
+ }
+
+ image[branches[i]] = ppc_inst_val(branch_insn);
+ }
+
+ for (i = 0; i < fexit->nr_links; i++)
+ if (invoke_bpf_prog(image, ro_image, ctx, fexit->links[i], regs_off, retval_off,
+ run_ctx_off, false)) {
+ ret = -EINVAL;
+ goto cleanup;
+ }
+
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ im->ip_epilogue = &((u32 *)ro_image)[ctx->idx];
+ PPC_LI_ADDR(_R3, im);
+ ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
+ (unsigned long)__bpf_tramp_exit);
+ if (ret)
+ goto cleanup;
+ }
+
+ if (flags & BPF_TRAMP_F_RESTORE_REGS)
+ bpf_trampoline_restore_args_regs(image, ctx, nr_regs, regs_off);
+
+ /* Restore return value of func_addr or fentry prog */
+ if (save_ret)
+ EMIT(PPC_RAW_LL(_R3, _R1, retval_off));
+
+ /* Restore nv regs */
+ EMIT(PPC_RAW_LL(_R26, _R1, nvr_off + SZL));
+ EMIT(PPC_RAW_LL(_R25, _R1, nvr_off));
+
+ /* Epilogue */
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ EMIT(PPC_RAW_LD(_R2, _R1, 24));
+ if (flags & BPF_TRAMP_F_SKIP_FRAME) {
+ /* Skip the traced function and return to parent */
+ EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+ EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
+ EMIT(PPC_RAW_MTLR(_R0));
+ EMIT(PPC_RAW_BLR());
+ } else {
+ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+ EMIT(PPC_RAW_LL(_R0, _R1, alt_lr_off));
+ EMIT(PPC_RAW_MTLR(_R0));
+ EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+ EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
+ EMIT(PPC_RAW_BLR());
+ } else {
+ EMIT(PPC_RAW_LL(_R0, _R1, bpf_frame_size + PPC_LR_STKOFF));
+ EMIT(PPC_RAW_MTCTR(_R0));
+ EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+ EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
+ EMIT(PPC_RAW_MTLR(_R0));
+ EMIT(PPC_RAW_BCTR());
+ }
+ }
+
+ /* Make sure the trampoline generation logic doesn't overflow */
+ if (image && WARN_ON_ONCE(&image[ctx->idx] > (u32 *)rw_image_end - BPF_INSN_SAFETY)) {
+ ret = -EFAULT;
+ goto cleanup;
+ }
+ ret = ctx->idx * 4 + BPF_INSN_SAFETY * 4;
+
+cleanup:
+ kfree(branches);
+ return ret;
+}
+
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+ struct bpf_tramp_links *tlinks, void *func_addr)
+{
+ struct bpf_tramp_image im;
+ void *image;
+ int ret;
+
+ /*
+ * Allocate a temporary buffer for __arch_prepare_bpf_trampoline().
+ * This will NOT cause fragmentation in direct map, as we do not
+ * call set_memory_*() on this buffer.
+ *
+ * We cannot use kvmalloc here, because we need image to be in
+ * module memory range.
+ */
+ image = bpf_jit_alloc_exec(PAGE_SIZE);
+ if (!image)
+ return -ENOMEM;
+
+ ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image,
+ m, flags, tlinks, func_addr);
+ bpf_jit_free_exec(image);
+
+ return ret;
+}
+
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
+ const struct btf_func_model *m, u32 flags,
+ struct bpf_tramp_links *tlinks,
+ void *func_addr)
+{
+ u32 size = image_end - image;
+ void *rw_image, *tmp;
+ int ret;
+
+ /*
+ * rw_image doesn't need to be in module memory range, so we can
+ * use kvmalloc.
+ */
+ rw_image = kvmalloc(size, GFP_KERNEL);
+ if (!rw_image)
+ return -ENOMEM;
+
+ ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m,
+ flags, tlinks, func_addr);
+ if (ret < 0)
+ goto out;
+
+ if (bpf_jit_enable > 1)
+ bpf_jit_dump(1, ret - BPF_INSN_SAFETY * 4, 1, rw_image);
+
+ tmp = bpf_arch_text_copy(image, rw_image, size);
+ if (IS_ERR(tmp))
+ ret = PTR_ERR(tmp);
+
+out:
+ kvfree(rw_image);
+ return ret;
+}
+
+static int bpf_modify_inst(void *ip, ppc_inst_t old_inst, ppc_inst_t new_inst)
+{
+ ppc_inst_t org_inst;
+
+ if (copy_inst_from_kernel_nofault(&org_inst, ip)) {
+ pr_err("0x%lx: fetching instruction failed\n", (unsigned long)ip);
+ return -EFAULT;
+ }
+
+ if (!ppc_inst_equal(org_inst, old_inst)) {
+ pr_err("0x%lx: expected (%08lx) != found (%08lx)\n",
+ (unsigned long)ip, ppc_inst_as_ulong(old_inst), ppc_inst_as_ulong(org_inst));
+ return -EINVAL;
+ }
+
+ if (ppc_inst_equal(old_inst, new_inst))
+ return 0;
+
+ return patch_instruction(ip, new_inst);
+}
+
+static void do_isync(void *info __maybe_unused)
+{
+ isync();
+}
+
+/*
+ * A 3-step process for bpf prog entry:
+ * 1. At bpf prog entry, a single nop/b:
+ * bpf_func:
+ * [nop|b] ool_stub
+ * 2. Out-of-line stub:
+ * ool_stub:
+ * mflr r0
+ * [b|bl] <bpf_prog>/<long_branch_stub>
+ * mtlr r0 // CONFIG_PPC_FTRACE_OUT_OF_LINE only
+ * b bpf_func + 4
+ * 3. Long branch stub:
+ * long_branch_stub:
+ * .long <branch_addr>/<dummy_tramp>
+ * mflr r11
+ * bcl 20,31,$+4
+ * mflr r12
+ * ld r12, -16(r12)
+ * mtctr r12
+ * mtlr r11 // needed to retain ftrace ABI
+ * bctr
+ *
+ * dummy_tramp is used to reduce synchronization requirements.
+ *
+ * When attaching a bpf trampoline to a bpf prog, we do not need any
+ * synchronization here since we always have a valid branch target regardless
+ * of the order in which the above stores are seen. dummy_tramp ensures that
+ * the long_branch stub goes to a valid destination on other cpus, even when
+ * the branch to the long_branch stub is seen before the updated trampoline
+ * address.
+ *
+ * However, when detaching a bpf trampoline from a bpf prog, or if changing
+ * the bpf trampoline address, we need synchronization to ensure that other
+ * cpus can no longer branch into the older trampoline so that it can be
+ * safely freed. bpf_tramp_image_put() uses rcu_tasks to ensure all cpus
+ * make forward progress, but we still need to ensure that other cpus
+ * execute isync (or some CSI) so that they don't go back into the
+ * trampoline again.
+ */
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
+ void *old_addr, void *new_addr)
+{
+ unsigned long bpf_func, bpf_func_end, size, offset;
+ ppc_inst_t old_inst, new_inst;
+ int ret = 0, branch_flags;
+ char name[KSYM_NAME_LEN];
+
+ if (IS_ENABLED(CONFIG_PPC32))
+ return -EOPNOTSUPP;
+
+ bpf_func = (unsigned long)ip;
+ branch_flags = poke_type == BPF_MOD_CALL ? BRANCH_SET_LINK : 0;
+
+ /* We currently only support poking bpf programs */
+ if (!__bpf_address_lookup(bpf_func, &size, &offset, name)) {
+ pr_err("%s (0x%lx): kernel/modules are not supported\n", __func__, bpf_func);
+ return -EOPNOTSUPP;
+ }
+
+ /*
+ * If we are not poking at bpf prog entry, then we are simply patching in/out
+ * an unconditional branch instruction at im->ip_after_call
+ */
+ if (offset) {
+ if (poke_type != BPF_MOD_JUMP) {
+ pr_err("%s (0x%lx): calls are not supported in bpf prog body\n", __func__,
+ bpf_func);
+ return -EOPNOTSUPP;
+ }
+ old_inst = ppc_inst(PPC_RAW_NOP());
+ if (old_addr)
+ if (create_branch(&old_inst, ip, (unsigned long)old_addr, 0))
+ return -ERANGE;
+ new_inst = ppc_inst(PPC_RAW_NOP());
+ if (new_addr)
+ if (create_branch(&new_inst, ip, (unsigned long)new_addr, 0))
+ return -ERANGE;
+ mutex_lock(&text_mutex);
+ ret = bpf_modify_inst(ip, old_inst, new_inst);
+ mutex_unlock(&text_mutex);
+
+ /* Make sure all cpus see the new instruction */
+ smp_call_function(do_isync, NULL, 1);
+ return ret;
+ }
+
+ bpf_func_end = bpf_func + size;
+
+ /* Address of the jmp/call instruction in the out-of-line stub */
+ ip = (void *)(bpf_func_end - bpf_jit_ool_stub + 4);
+
+ if (!is_offset_in_branch_range((long)ip - 4 - bpf_func)) {
+ pr_err("%s (0x%lx): bpf prog too large, ool stub out of branch range\n", __func__,
+ bpf_func);
+ return -ERANGE;
+ }
+
+ old_inst = ppc_inst(PPC_RAW_NOP());
+ if (old_addr) {
+ if (is_offset_in_branch_range(ip - old_addr))
+ create_branch(&old_inst, ip, (unsigned long)old_addr, branch_flags);
+ else
+ create_branch(&old_inst, ip, bpf_func_end - bpf_jit_long_branch_stub,
+ branch_flags);
+ }
+ new_inst = ppc_inst(PPC_RAW_NOP());
+ if (new_addr) {
+ if (is_offset_in_branch_range(ip - new_addr))
+ create_branch(&new_inst, ip, (unsigned long)new_addr, branch_flags);
+ else
+ create_branch(&new_inst, ip, bpf_func_end - bpf_jit_long_branch_stub,
+ branch_flags);
+ }
+
+ mutex_lock(&text_mutex);
+
+ /*
+ * 1. Update the address in the long branch stub:
+ * If new_addr is out of range, we will have to use the long branch stub, so patch new_addr
+ * here. Otherwise, revert to dummy_tramp, but only if we had patched old_addr here.
+ */
+ if ((new_addr && !is_offset_in_branch_range(new_addr - ip)) ||
+ (old_addr && !is_offset_in_branch_range(old_addr - ip)))
+ ret = patch_ulong((void *)(bpf_func_end - bpf_jit_long_branch_stub - SZL),
+ (new_addr && !is_offset_in_branch_range(new_addr - ip)) ?
+ (unsigned long)new_addr : (unsigned long)dummy_tramp);
+ if (ret)
+ goto out;
+
+ /* 2. Update the branch/call in the out-of-line stub */
+ ret = bpf_modify_inst(ip, old_inst, new_inst);
+ if (ret)
+ goto out;
+
+ /* 3. Update instruction at bpf prog entry */
+ ip = (void *)bpf_func;
+ if (!old_addr || !new_addr) {
+ if (!old_addr) {
+ old_inst = ppc_inst(PPC_RAW_NOP());
+ create_branch(&new_inst, ip, bpf_func_end - bpf_jit_ool_stub, 0);
+ } else {
+ new_inst = ppc_inst(PPC_RAW_NOP());
+ create_branch(&old_inst, ip, bpf_func_end - bpf_jit_ool_stub, 0);
+ }
+ ret = bpf_modify_inst(ip, old_inst, new_inst);
+ }
+
+out:
+ mutex_unlock(&text_mutex);
+
+ /*
+ * Sync only if we are not attaching a trampoline to a bpf prog so the older
+ * trampoline can be freed safely.
+ */
+ if (old_addr)
+ smp_call_function(do_isync, NULL, 1);
+
+ return ret;
+}
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index 2f39c50ca729..c4db278dae36 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -127,13 +127,16 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
{
int i;
+ /* Instruction for trampoline attach */
+ EMIT(PPC_RAW_NOP());
+
/* Initialize tail_call_cnt, to be skipped if we do tail calls. */
if (ctx->seen & SEEN_TAILCALL)
EMIT(PPC_RAW_LI(_R4, 0));
else
EMIT(PPC_RAW_NOP());
-#define BPF_TAILCALL_PROLOGUE_SIZE 4
+#define BPF_TAILCALL_PROLOGUE_SIZE 8
if (bpf_has_stack_frame(ctx))
EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
@@ -198,6 +201,8 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
bpf_jit_emit_common_epilogue(image, ctx);
EMIT(PPC_RAW_BLR());
+
+ bpf_jit_build_fentry_stubs(image, ctx);
}
/* Relative offset needs to be calculated based on final image location */
@@ -450,10 +455,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
}
break;
case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
- EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, src_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVW(dst_reg, src2_reg, src_reg));
+ else
+ EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, src_reg));
break;
case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
- EMIT(PPC_RAW_DIVWU(_R0, src2_reg, src_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVW(_R0, src2_reg, src_reg));
+ else
+ EMIT(PPC_RAW_DIVWU(_R0, src2_reg, src_reg));
EMIT(PPC_RAW_MULW(_R0, src_reg, _R0));
EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0));
break;
@@ -467,10 +478,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
if (imm == 1) {
EMIT(PPC_RAW_MR(dst_reg, src2_reg));
} else if (is_power_of_2((u32)imm)) {
- EMIT(PPC_RAW_SRWI(dst_reg, src2_reg, ilog2(imm)));
+ if (off)
+ EMIT(PPC_RAW_SRAWI(dst_reg, src2_reg, ilog2(imm)));
+ else
+ EMIT(PPC_RAW_SRWI(dst_reg, src2_reg, ilog2(imm)));
} else {
PPC_LI32(_R0, imm);
- EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, _R0));
+ if (off)
+ EMIT(PPC_RAW_DIVW(dst_reg, src2_reg, _R0));
+ else
+ EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, _R0));
}
break;
case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
@@ -480,11 +497,19 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
if (!is_power_of_2((u32)imm)) {
bpf_set_seen_register(ctx, tmp_reg);
PPC_LI32(tmp_reg, imm);
- EMIT(PPC_RAW_DIVWU(_R0, src2_reg, tmp_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVW(_R0, src2_reg, tmp_reg));
+ else
+ EMIT(PPC_RAW_DIVWU(_R0, src2_reg, tmp_reg));
EMIT(PPC_RAW_MULW(_R0, tmp_reg, _R0));
EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0));
} else if (imm == 1) {
EMIT(PPC_RAW_LI(dst_reg, 0));
+ } else if (off) {
+ EMIT(PPC_RAW_SRAWI(_R0, src2_reg, ilog2(imm)));
+ EMIT(PPC_RAW_ADDZE(_R0, _R0));
+ EMIT(PPC_RAW_SLWI(_R0, _R0, ilog2(imm)));
+ EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0));
} else {
imm = ilog2((u32)imm);
EMIT(PPC_RAW_RLWINM(dst_reg, src2_reg, 0, 32 - imm, 31));
@@ -497,11 +522,21 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
imm = -imm;
if (!is_power_of_2(imm))
return -EOPNOTSUPP;
- if (imm == 1)
+ if (imm == 1) {
EMIT(PPC_RAW_LI(dst_reg, 0));
- else
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
+ } else if (off) {
+ EMIT(PPC_RAW_SRAWI(dst_reg_h, src2_reg_h, 31));
+ EMIT(PPC_RAW_XOR(dst_reg, src2_reg, dst_reg_h));
+ EMIT(PPC_RAW_SUBFC(dst_reg, dst_reg_h, dst_reg));
+ EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 32 - ilog2(imm), 31));
+ EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg_h));
+ EMIT(PPC_RAW_SUBFC(dst_reg, dst_reg_h, dst_reg));
+ EMIT(PPC_RAW_SUBFE(dst_reg_h, dst_reg_h, dst_reg_h));
+ } else {
EMIT(PPC_RAW_RLWINM(dst_reg, src2_reg, 0, 32 - ilog2(imm), 31));
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
+ }
break;
case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */
if (!imm)
@@ -727,15 +762,30 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
* MOV
*/
case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
- if (dst_reg == src_reg)
- break;
- EMIT(PPC_RAW_MR(dst_reg, src_reg));
- EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h));
+ if (off == 8) {
+ EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
+ EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31));
+ } else if (off == 16) {
+ EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
+ EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31));
+ } else if (off == 32 && dst_reg == src_reg) {
+ EMIT(PPC_RAW_SRAWI(dst_reg_h, src_reg, 31));
+ } else if (off == 32) {
+ EMIT(PPC_RAW_MR(dst_reg, src_reg));
+ EMIT(PPC_RAW_SRAWI(dst_reg_h, src_reg, 31));
+ } else if (dst_reg != src_reg) {
+ EMIT(PPC_RAW_MR(dst_reg, src_reg));
+ EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h));
+ }
break;
case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
/* special mov32 for zext */
if (imm == 1)
EMIT(PPC_RAW_LI(dst_reg_h, 0));
+ else if (off == 8)
+ EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
+ else if (off == 16)
+ EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
else if (dst_reg != src_reg)
EMIT(PPC_RAW_MR(dst_reg, src_reg));
break;
@@ -751,6 +801,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
* BPF_FROM_BE/LE
*/
case BPF_ALU | BPF_END | BPF_FROM_LE:
+ case BPF_ALU64 | BPF_END | BPF_FROM_LE:
switch (imm) {
case 16:
/* Copy 16 bits to upper part */
@@ -785,6 +836,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
EMIT(PPC_RAW_MR(dst_reg_h, tmp_reg));
break;
}
+ if (BPF_CLASS(code) == BPF_ALU64 && imm != 64)
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
case BPF_ALU | BPF_END | BPF_FROM_BE:
switch (imm) {
@@ -852,6 +905,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
/* Get offset into TMP_REG */
EMIT(PPC_RAW_LI(tmp_reg, off));
+ /*
+ * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync'
+ * before and after the operation.
+ *
+ * This is a requirement in the Linux Kernel Memory Model.
+ * See __cmpxchg_u32() in asm/cmpxchg.h as an example.
+ */
+ if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP))
+ EMIT(PPC_RAW_SYNC());
tmp_idx = ctx->idx * 4;
/* load value from memory into r0 */
EMIT(PPC_RAW_LWARX(_R0, tmp_reg, dst_reg, 0));
@@ -905,6 +967,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
/* For the BPF_FETCH variant, get old data into src_reg */
if (imm & BPF_FETCH) {
+ /* Emit 'sync' to enforce full ordering */
+ if (IS_ENABLED(CONFIG_SMP))
+ EMIT(PPC_RAW_SYNC());
EMIT(PPC_RAW_MR(ret_reg, ax_reg));
if (!fp->aux->verifier_zext)
EMIT(PPC_RAW_LI(ret_reg - 1, 0)); /* higher 32-bit */
@@ -918,11 +983,17 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
* BPF_LDX
*/
case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src + off) */
+ case BPF_LDX | BPF_MEMSX | BPF_B:
case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */
+ case BPF_LDX | BPF_MEMSX | BPF_H:
case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */
+ case BPF_LDX | BPF_MEMSX | BPF_W:
case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
/*
@@ -931,7 +1002,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
* load only if addr is kernel address (see is_kernel_addr()), otherwise
* set dst_reg=0 and move on.
*/
- if (BPF_MODE(code) == BPF_PROBE_MEM) {
+ if (BPF_MODE(code) == BPF_PROBE_MEM || BPF_MODE(code) == BPF_PROBE_MEMSX) {
PPC_LI32(_R0, TASK_SIZE - off);
EMIT(PPC_RAW_CMPLW(src_reg, _R0));
PPC_BCC_SHORT(COND_GT, (ctx->idx + 4) * 4);
@@ -953,30 +1024,48 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
* as there are two load instructions for dst_reg_h & dst_reg
* respectively.
*/
- if (size == BPF_DW)
+ if (size == BPF_DW ||
+ (size == BPF_B && BPF_MODE(code) == BPF_PROBE_MEMSX))
PPC_JMP((ctx->idx + 3) * 4);
else
PPC_JMP((ctx->idx + 2) * 4);
}
- switch (size) {
- case BPF_B:
- EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
- break;
- case BPF_H:
- EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
- break;
- case BPF_W:
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
- break;
- case BPF_DW:
- EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
- break;
- }
+ if (BPF_MODE(code) == BPF_MEMSX || BPF_MODE(code) == BPF_PROBE_MEMSX) {
+ switch (size) {
+ case BPF_B:
+ EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+ EMIT(PPC_RAW_EXTSB(dst_reg, dst_reg));
+ break;
+ case BPF_H:
+ EMIT(PPC_RAW_LHA(dst_reg, src_reg, off));
+ break;
+ case BPF_W:
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+ break;
+ }
+ if (!fp->aux->verifier_zext)
+ EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31));
- if (size != BPF_DW && !fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
+ } else {
+ switch (size) {
+ case BPF_B:
+ EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+ break;
+ case BPF_H:
+ EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+ break;
+ case BPF_W:
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+ break;
+ case BPF_DW:
+ EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
+ break;
+ }
+ if (size != BPF_DW && !fp->aux->verifier_zext)
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
+ }
if (BPF_MODE(code) == BPF_PROBE_MEM) {
int insn_idx = ctx->idx - 1;
@@ -1068,6 +1157,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
case BPF_JMP | BPF_JA:
PPC_JMP(addrs[i + 1 + off]);
break;
+ case BPF_JMP32 | BPF_JA:
+ PPC_JMP(addrs[i + 1 + imm]);
+ break;
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGT | BPF_X:
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 79f23974a320..233703b06d7c 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -84,7 +84,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
}
/*
- * When not setting up our own stackframe, the redzone usage is:
+ * When not setting up our own stackframe, the redzone (288 bytes) usage is:
*
* [ prev sp ] <-------------
* [ ... ] |
@@ -92,7 +92,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
* [ nv gpr save area ] 5*8
* [ tail_call_cnt ] 8
* [ local_tmp_var ] 16
- * [ unused red zone ] 208 bytes protected
+ * [ unused red zone ] 224
*/
static int bpf_jit_stack_local(struct codegen_context *ctx)
{
@@ -126,6 +126,9 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
{
int i;
+ /* Instruction for trampoline attach */
+ EMIT(PPC_RAW_NOP());
+
#ifndef CONFIG_PPC_KERNEL_PCREL
if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)));
@@ -200,31 +203,59 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
EMIT(PPC_RAW_BLR());
+
+ bpf_jit_build_fentry_stubs(image, ctx);
}
-static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u64 func)
+int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
{
unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0;
long reladdr;
- if (WARN_ON_ONCE(!core_kernel_text(func_addr)))
- return -EINVAL;
-
- if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
- reladdr = func_addr - CTX_NIA(ctx);
-
- if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) {
- pr_err("eBPF: address of %ps out of range of pcrel address.\n",
- (void *)func);
- return -ERANGE;
- }
- /* pla r12,addr */
- EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr));
- EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr));
+ /* bpf to bpf call, func is not known in the initial pass. Emit 5 nops as a placeholder */
+ if (!func) {
+ for (int i = 0; i < 5; i++)
+ EMIT(PPC_RAW_NOP());
+ /* elfv1 needs an additional instruction to load addr from descriptor */
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1))
+ EMIT(PPC_RAW_NOP());
EMIT(PPC_RAW_MTCTR(_R12));
- EMIT(PPC_RAW_BCTR());
+ EMIT(PPC_RAW_BCTRL());
+ return 0;
+ }
+
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ reladdr = func_addr - local_paca->kernelbase;
+ if (reladdr < (long)SZ_8G && reladdr >= -(long)SZ_8G) {
+ EMIT(PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase)));
+ /* Align for subsequent prefix instruction */
+ if (!IS_ALIGNED((unsigned long)fimage + CTX_NIA(ctx), 8))
+ EMIT(PPC_RAW_NOP());
+ /* paddi r12,r12,addr */
+ EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(0) | IMM_H18(reladdr));
+ EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | ___PPC_RA(_R12) | IMM_L(reladdr));
} else {
+ unsigned long pc = (unsigned long)fimage + CTX_NIA(ctx);
+ bool alignment_needed = !IS_ALIGNED(pc, 8);
+
+ reladdr = func_addr - (alignment_needed ? pc + 4 : pc);
+
+ if (reladdr < (long)SZ_8G && reladdr >= -(long)SZ_8G) {
+ if (alignment_needed)
+ EMIT(PPC_RAW_NOP());
+ /* pla r12,addr */
+ EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr));
+ EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr));
+ } else {
+ /* We can clobber r12 */
+ PPC_LI64(_R12, func);
+ }
+ }
+ EMIT(PPC_RAW_MTCTR(_R12));
+ EMIT(PPC_RAW_BCTRL());
+#else
+ if (core_kernel_text(func_addr)) {
reladdr = func_addr - kernel_toc_addr();
if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
pr_err("eBPF: address of %ps out of range of kernel_toc.\n", (void *)func);
@@ -235,40 +266,34 @@ static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u
EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr)));
EMIT(PPC_RAW_MTCTR(_R12));
EMIT(PPC_RAW_BCTRL());
+ } else {
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1)) {
+ /* func points to the function descriptor */
+ PPC_LI64(bpf_to_ppc(TMP_REG_2), func);
+ /* Load actual entry point from function descriptor */
+ EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0));
+ /* ... and move it to CTR */
+ EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_1)));
+ /*
+ * Load TOC from function descriptor at offset 8.
+ * We can clobber r2 since we get called through a
+ * function pointer (so caller will save/restore r2).
+ */
+ if (is_module_text_address(func_addr))
+ EMIT(PPC_RAW_LD(_R2, bpf_to_ppc(TMP_REG_2), 8));
+ } else {
+ PPC_LI64(_R12, func);
+ EMIT(PPC_RAW_MTCTR(_R12));
+ }
+ EMIT(PPC_RAW_BCTRL());
+ /*
+ * Load r2 with kernel TOC as kernel TOC is used if function address falls
+ * within core kernel text.
+ */
+ if (is_module_text_address(func_addr))
+ EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)));
}
-
- return 0;
-}
-
-int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
-{
- unsigned int i, ctx_idx = ctx->idx;
-
- if (WARN_ON_ONCE(func && is_module_text_address(func)))
- return -EINVAL;
-
- /* skip past descriptor if elf v1 */
- func += FUNCTION_DESCR_SIZE;
-
- /* Load function address into r12 */
- PPC_LI64(_R12, func);
-
- /* For bpf-to-bpf function calls, the callee's address is unknown
- * until the last extra pass. As seen above, we use PPC_LI64() to
- * load the callee's address, but this may optimize the number of
- * instructions required based on the nature of the address.
- *
- * Since we don't want the number of instructions emitted to increase,
- * we pad the optimized PPC_LI64() call with NOPs to guarantee that
- * we always have a five-instruction sequence, which is the maximum
- * that PPC_LI64() can emit.
- */
- if (!image)
- for (i = ctx->idx - ctx_idx; i < 5; i++)
- EMIT(PPC_RAW_NOP());
-
- EMIT(PPC_RAW_MTCTR(_R12));
- EMIT(PPC_RAW_BCTRL());
+#endif
return 0;
}
@@ -283,9 +308,9 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
*/
int b2p_bpf_array = bpf_to_ppc(BPF_REG_2);
int b2p_index = bpf_to_ppc(BPF_REG_3);
- int bpf_tailcall_prologue_size = 8;
+ int bpf_tailcall_prologue_size = 12;
- if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
+ if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL) && IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
bpf_tailcall_prologue_size += 4; /* skip past the toc load */
/*
@@ -467,20 +492,33 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
if (BPF_OP(code) == BPF_MOD) {
- EMIT(PPC_RAW_DIVWU(tmp1_reg, dst_reg, src_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVW(tmp1_reg, dst_reg, src_reg));
+ else
+ EMIT(PPC_RAW_DIVWU(tmp1_reg, dst_reg, src_reg));
+
EMIT(PPC_RAW_MULW(tmp1_reg, src_reg, tmp1_reg));
EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg));
} else
- EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, src_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVW(dst_reg, dst_reg, src_reg));
+ else
+ EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
if (BPF_OP(code) == BPF_MOD) {
- EMIT(PPC_RAW_DIVDU(tmp1_reg, dst_reg, src_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVD(tmp1_reg, dst_reg, src_reg));
+ else
+ EMIT(PPC_RAW_DIVDU(tmp1_reg, dst_reg, src_reg));
EMIT(PPC_RAW_MULD(tmp1_reg, src_reg, tmp1_reg));
EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg));
} else
- EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, src_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVD(dst_reg, dst_reg, src_reg));
+ else
+ EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */
@@ -501,19 +539,31 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
switch (BPF_CLASS(code)) {
case BPF_ALU:
if (BPF_OP(code) == BPF_MOD) {
- EMIT(PPC_RAW_DIVWU(tmp2_reg, dst_reg, tmp1_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVW(tmp2_reg, dst_reg, tmp1_reg));
+ else
+ EMIT(PPC_RAW_DIVWU(tmp2_reg, dst_reg, tmp1_reg));
EMIT(PPC_RAW_MULW(tmp1_reg, tmp1_reg, tmp2_reg));
EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg));
} else
- EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, tmp1_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVW(dst_reg, dst_reg, tmp1_reg));
+ else
+ EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, tmp1_reg));
break;
case BPF_ALU64:
if (BPF_OP(code) == BPF_MOD) {
- EMIT(PPC_RAW_DIVDU(tmp2_reg, dst_reg, tmp1_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVD(tmp2_reg, dst_reg, tmp1_reg));
+ else
+ EMIT(PPC_RAW_DIVDU(tmp2_reg, dst_reg, tmp1_reg));
EMIT(PPC_RAW_MULD(tmp1_reg, tmp1_reg, tmp2_reg));
EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg));
} else
- EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, tmp1_reg));
+ if (off)
+ EMIT(PPC_RAW_DIVD(dst_reg, dst_reg, tmp1_reg));
+ else
+ EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, tmp1_reg));
break;
}
goto bpf_alu32_trunc;
@@ -633,8 +683,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
/* special mov32 for zext */
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31));
break;
- }
- EMIT(PPC_RAW_MR(dst_reg, src_reg));
+ } else if (off == 8) {
+ EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
+ } else if (off == 16) {
+ EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
+ } else if (off == 32) {
+ EMIT(PPC_RAW_EXTSW(dst_reg, src_reg));
+ } else if (dst_reg != src_reg)
+ EMIT(PPC_RAW_MR(dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
@@ -656,11 +712,12 @@ bpf_alu32_trunc:
*/
case BPF_ALU | BPF_END | BPF_FROM_LE:
case BPF_ALU | BPF_END | BPF_FROM_BE:
+ case BPF_ALU64 | BPF_END | BPF_FROM_LE:
#ifdef __BIG_ENDIAN__
if (BPF_SRC(code) == BPF_FROM_BE)
goto emit_clear;
#else /* !__BIG_ENDIAN__ */
- if (BPF_SRC(code) == BPF_FROM_LE)
+ if (BPF_CLASS(code) == BPF_ALU && BPF_SRC(code) == BPF_FROM_LE)
goto emit_clear;
#endif
switch (imm) {
@@ -803,6 +860,15 @@ emit_clear:
/* Get offset into TMP_REG_1 */
EMIT(PPC_RAW_LI(tmp1_reg, off));
+ /*
+ * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync'
+ * before and after the operation.
+ *
+ * This is a requirement in the Linux Kernel Memory Model.
+ * See __cmpxchg_u64() in asm/cmpxchg.h as an example.
+ */
+ if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP))
+ EMIT(PPC_RAW_SYNC());
tmp_idx = ctx->idx * 4;
/* load value from memory into TMP_REG_2 */
if (size == BPF_DW)
@@ -865,6 +931,9 @@ emit_clear:
PPC_BCC_SHORT(COND_NE, tmp_idx);
if (imm & BPF_FETCH) {
+ /* Emit 'sync' to enforce full ordering */
+ if (IS_ENABLED(CONFIG_SMP))
+ EMIT(PPC_RAW_SYNC());
EMIT(PPC_RAW_MR(ret_reg, _R0));
/*
* Skip unnecessary zero-extension for 32-bit cmpxchg.
@@ -881,13 +950,19 @@ emit_clear:
*/
/* dst = *(u8 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_B:
+ case BPF_LDX | BPF_MEMSX | BPF_B:
case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
/* dst = *(u16 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_H:
+ case BPF_LDX | BPF_MEMSX | BPF_H:
case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
/* dst = *(u32 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_W:
+ case BPF_LDX | BPF_MEMSX | BPF_W:
case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
/* dst = *(u64 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_DW:
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
@@ -897,7 +972,7 @@ emit_clear:
* load only if addr is kernel address (see is_kernel_addr()), otherwise
* set dst_reg=0 and move on.
*/
- if (BPF_MODE(code) == BPF_PROBE_MEM) {
+ if (BPF_MODE(code) == BPF_PROBE_MEM || BPF_MODE(code) == BPF_PROBE_MEMSX) {
EMIT(PPC_RAW_ADDI(tmp1_reg, src_reg, off));
if (IS_ENABLED(CONFIG_PPC_BOOK3E_64))
PPC_LI64(tmp2_reg, 0x8000000000000000ul);
@@ -910,30 +985,47 @@ emit_clear:
* Check if 'off' is word aligned for BPF_DW, because
* we might generate two instructions.
*/
- if (BPF_SIZE(code) == BPF_DW && (off & 3))
+ if ((BPF_SIZE(code) == BPF_DW ||
+ (BPF_SIZE(code) == BPF_B && BPF_MODE(code) == BPF_PROBE_MEMSX)) &&
+ (off & 3))
PPC_JMP((ctx->idx + 3) * 4);
else
PPC_JMP((ctx->idx + 2) * 4);
}
- switch (size) {
- case BPF_B:
- EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
- break;
- case BPF_H:
- EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
- break;
- case BPF_W:
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
- break;
- case BPF_DW:
- if (off % 4) {
- EMIT(PPC_RAW_LI(tmp1_reg, off));
- EMIT(PPC_RAW_LDX(dst_reg, src_reg, tmp1_reg));
- } else {
- EMIT(PPC_RAW_LD(dst_reg, src_reg, off));
+ if (BPF_MODE(code) == BPF_MEMSX || BPF_MODE(code) == BPF_PROBE_MEMSX) {
+ switch (size) {
+ case BPF_B:
+ EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+ EMIT(PPC_RAW_EXTSB(dst_reg, dst_reg));
+ break;
+ case BPF_H:
+ EMIT(PPC_RAW_LHA(dst_reg, src_reg, off));
+ break;
+ case BPF_W:
+ EMIT(PPC_RAW_LWA(dst_reg, src_reg, off));
+ break;
+ }
+ } else {
+ switch (size) {
+ case BPF_B:
+ EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+ break;
+ case BPF_H:
+ EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+ break;
+ case BPF_W:
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+ break;
+ case BPF_DW:
+ if (off % 4) {
+ EMIT(PPC_RAW_LI(tmp1_reg, off));
+ EMIT(PPC_RAW_LDX(dst_reg, src_reg, tmp1_reg));
+ } else {
+ EMIT(PPC_RAW_LD(dst_reg, src_reg, off));
+ }
+ break;
}
- break;
}
if (size != BPF_DW && insn_is_zext(&insn[i + 1]))
@@ -992,11 +1084,7 @@ emit_clear:
if (ret < 0)
return ret;
- if (func_addr_fixed)
- ret = bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
- else
- ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
-
+ ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
if (ret)
return ret;
@@ -1010,6 +1098,9 @@ emit_clear:
case BPF_JMP | BPF_JA:
PPC_JMP(addrs[i + 1 + off]);
break;
+ case BPF_JMP32 | BPF_JA:
+ PPC_JMP(addrs[i + 1 + imm]);
+ break;
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGT | BPF_X:
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index 308a2e40d7be..1d2972229e3a 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -14,7 +14,7 @@
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/ptrace.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/inst.h>
#define PERF_8xx_ID_CPU_CYCLES 1
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 4f53d0b97539..ac2cf58d62db 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -16,6 +16,8 @@ obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o
obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o
+obj-$(CONFIG_VPA_PMU) += vpa-pmu.o
+
obj-$(CONFIG_PPC_8xx) += 8xx-pmu.o
obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 6b4434dd0ff3..26aa26482c9a 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -51,7 +51,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
lr = regs->link;
sp = regs->gpr[1];
- perf_callchain_store(entry, perf_instruction_pointer(regs));
+ perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
if (!validate_sp(sp, current))
return;
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index ea8cfe3806dc..ddcc2d8aa64a 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -139,7 +139,7 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
long level = 0;
unsigned int __user *fp, *uregs;
- next_ip = perf_instruction_pointer(regs);
+ next_ip = perf_arch_instruction_pointer(regs);
lr = regs->link;
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 488e8a21a11e..115d1c105e8a 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -74,7 +74,7 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
struct signal_frame_64 __user *sigframe;
unsigned long __user *fp, *uregs;
- next_ip = perf_instruction_pointer(regs);
+ next_ip = perf_arch_instruction_pointer(regs);
lr = regs->link;
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index b7ff680cde96..2b79171ee185 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -16,7 +16,7 @@
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/ptrace.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/hw_irq.h>
#include <asm/interrupt.h>
@@ -256,7 +256,7 @@ static bool regs_sipr(struct pt_regs *regs)
static inline u32 perf_flags_from_msr(struct pt_regs *regs)
{
- if (regs->msr & MSR_PR)
+ if (user_mode(regs))
return PERF_RECORD_MISC_USER;
if ((regs->msr & MSR_HV) && freeze_events_kernel != MMCR0_FCHV)
return PERF_RECORD_MISC_HYPERVISOR;
@@ -266,51 +266,44 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs)
static inline u32 perf_get_misc_flags(struct pt_regs *regs)
{
bool use_siar = regs_use_siar(regs);
- unsigned long mmcra = regs->dsisr;
- int marked = mmcra & MMCRA_SAMPLE_ENABLE;
+ unsigned long siar;
+ unsigned long addr;
if (!use_siar)
return perf_flags_from_msr(regs);
/*
- * Check the address in SIAR to identify the
- * privilege levels since the SIER[MSR_HV, MSR_PR]
- * bits are not set for marked events in power10
- * DD1.
- */
- if (marked && (ppmu->flags & PPMU_P10_DD1)) {
- unsigned long siar = mfspr(SPRN_SIAR);
- if (siar) {
- if (is_kernel_addr(siar))
- return PERF_RECORD_MISC_KERNEL;
- return PERF_RECORD_MISC_USER;
- } else {
- if (is_kernel_addr(regs->nip))
- return PERF_RECORD_MISC_KERNEL;
- return PERF_RECORD_MISC_USER;
- }
- }
-
- /*
* If we don't have flags in MMCRA, rather than using
* the MSR, we intuit the flags from the address in
* SIAR which should give slightly more reliable
* results
*/
if (ppmu->flags & PPMU_NO_SIPR) {
- unsigned long siar = mfspr(SPRN_SIAR);
+ siar = mfspr(SPRN_SIAR);
if (is_kernel_addr(siar))
return PERF_RECORD_MISC_KERNEL;
return PERF_RECORD_MISC_USER;
}
/* PR has priority over HV, so order below is important */
- if (regs_sipr(regs))
- return PERF_RECORD_MISC_USER;
-
- if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV))
+ if (regs_sipr(regs)) {
+ if (!(ppmu->flags & PPMU_P10))
+ return PERF_RECORD_MISC_USER;
+ } else if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV))
return PERF_RECORD_MISC_HYPERVISOR;
+ /*
+ * Check the address in SIAR to identify the
+ * privilege levels since the SIER[MSR_HV, MSR_PR]
+ * bits are not set correctly in power10 sometimes
+ */
+ if (ppmu->flags & PPMU_P10) {
+ siar = mfspr(SPRN_SIAR);
+ addr = siar ? siar : regs->nip;
+ if (!is_kernel_addr(addr))
+ return PERF_RECORD_MISC_USER;
+ }
+
return PERF_RECORD_MISC_KERNEL;
}
@@ -2339,7 +2332,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
* Called from generic code to get the misc flags (i.e. processor mode)
* for an event_id.
*/
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
{
u32 flags = perf_get_misc_flags(regs);
@@ -2353,7 +2346,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
* Called from generic code to get the instruction pointer
* for an event_id.
*/
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
{
unsigned long siar = mfspr(SPRN_SIAR);
@@ -2593,6 +2586,8 @@ static int __init init_ppc64_pmu(void)
return 0;
else if (!init_power10_pmu())
return 0;
+ else if (!init_power11_pmu())
+ return 0;
else if (!init_ppc970_pmu())
return 0;
else
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 057ec2e3451d..d400fa391c27 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -425,16 +425,6 @@ static char *memdup_to_str(char *maybe_str, int max_len, gfp_t gfp)
return kasprintf(gfp, "%.*s", max_len, maybe_str);
}
-static ssize_t device_show_string(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct dev_ext_attribute *d;
-
- d = container_of(attr, struct dev_ext_attribute, attr);
-
- return sprintf(buf, "%s\n", (char *)d->var);
-}
-
static ssize_t cpumask_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 27f18119fda1..241551d1282f 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -695,6 +695,20 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index,
ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE);
+
+ /*
+ * ret value as 'H_PARAMETER' with detail_rc as 'GEN_BUF_TOO_SMALL',
+ * specifies that the current buffer size cannot accommodate
+ * all the information and a partial buffer returned.
+ * Since in this function we are only accessing data for a given starting index,
+ * we don't need to accommodate whole data and can get required count by
+ * accessing first entry data.
+ * Hence hcall fails only incase the ret value is other than H_SUCCESS or
+ * H_PARAMETER with detail_rc value as GEN_BUF_TOO_SMALL(0x1B).
+ */
+ if (ret == H_PARAMETER && be32_to_cpu(arg->params.detail_rc) == 0x1B)
+ ret = 0;
+
if (ret) {
pr_devel("hcall failed: 0x%lx\n", ret);
goto out;
@@ -759,6 +773,7 @@ static int h_gpci_event_init(struct perf_event *event)
{
u64 count;
u8 length;
+ unsigned long ret;
/* Not our event */
if (event->attr.type != event->pmu->type)
@@ -789,13 +804,23 @@ static int h_gpci_event_init(struct perf_event *event)
}
/* check if the request works... */
- if (single_gpci_request(event_get_request(event),
+ ret = single_gpci_request(event_get_request(event),
event_get_starting_index(event),
event_get_secondary_index(event),
event_get_counter_info_version(event),
event_get_offset(event),
length,
- &count)) {
+ &count);
+
+ /*
+ * ret value as H_AUTHORITY implies that partition is not permitted to retrieve
+ * performance information, and required to set
+ * "Enable Performance Information Collection" option.
+ */
+ if (ret == H_AUTHORITY)
+ return -EPERM;
+
+ if (ret) {
pr_devel("gpci hcall failed\n");
return -EINVAL;
}
diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h
index 4c18b5504326..a70ac471a5a5 100644
--- a/arch/powerpc/perf/internal.h
+++ b/arch/powerpc/perf/internal.h
@@ -10,4 +10,5 @@ int __init init_power7_pmu(void);
int __init init_power8_pmu(void);
int __init init_power9_pmu(void);
int __init init_power10_pmu(void);
+int __init init_power11_pmu(void);
int __init init_generic_compat_pmu(void);
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index 9b5133e361a7..bb57b7cfe640 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -593,7 +593,8 @@ static struct power_pmu power10_pmu = {
.get_mem_weight = isa207_get_mem_weight,
.disable_pmc = isa207_disable_pmc,
.flags = PPMU_HAS_SIER | PPMU_ARCH_207S |
- PPMU_ARCH_31 | PPMU_HAS_ATTR_CONFIG1,
+ PPMU_ARCH_31 | PPMU_HAS_ATTR_CONFIG1 |
+ PPMU_P10,
.n_generic = ARRAY_SIZE(power10_generic_events),
.generic_events = power10_generic_events,
.cache_events = &power10_cache_events,
@@ -634,3 +635,30 @@ int __init init_power10_pmu(void)
return 0;
}
+
+static struct power_pmu power11_pmu;
+
+int __init init_power11_pmu(void)
+{
+ unsigned int pvr;
+ int rc;
+
+ pvr = mfspr(SPRN_PVR);
+ if (PVR_VER(pvr) != PVR_POWER11)
+ return -ENODEV;
+
+ /* Set the PERF_REG_EXTENDED_MASK here */
+ PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31;
+
+ power11_pmu = power10_pmu;
+ power11_pmu.name = "Power11";
+
+ rc = register_power_pmu(&power11_pmu);
+ if (rc)
+ return rc;
+
+ /* Tell userspace that EBB is supported */
+ cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+
+ return 0;
+}
diff --git a/arch/powerpc/perf/vpa-pmu.c b/arch/powerpc/perf/vpa-pmu.c
new file mode 100644
index 000000000000..6a5bfd2a13b5
--- /dev/null
+++ b/arch/powerpc/perf/vpa-pmu.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Performance monitoring support for Virtual Processor Area(VPA) based counters
+ *
+ * Copyright (C) 2024 IBM Corporation
+ */
+#define pr_fmt(fmt) "vpa_pmu: " fmt
+
+#include <linux/module.h>
+#include <linux/perf_event.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s_64.h>
+
+#define MODULE_VERS "1.0"
+#define MODULE_NAME "pseries_vpa_pmu"
+
+#define EVENT(_name, _code) enum{_name = _code}
+
+#define VPA_PMU_EVENT_VAR(_id) event_attr_##_id
+#define VPA_PMU_EVENT_PTR(_id) (&event_attr_##_id.attr.attr)
+
+static ssize_t vpa_pmu_events_sysfs_show(struct device *dev,
+ struct device_attribute *attr, char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+ return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+#define VPA_PMU_EVENT_ATTR(_name, _id) \
+ PMU_EVENT_ATTR(_name, VPA_PMU_EVENT_VAR(_id), _id, \
+ vpa_pmu_events_sysfs_show)
+
+EVENT(L1_TO_L2_CS_LAT, 0x1);
+EVENT(L2_TO_L1_CS_LAT, 0x2);
+EVENT(L2_RUNTIME_AGG, 0x3);
+
+VPA_PMU_EVENT_ATTR(l1_to_l2_lat, L1_TO_L2_CS_LAT);
+VPA_PMU_EVENT_ATTR(l2_to_l1_lat, L2_TO_L1_CS_LAT);
+VPA_PMU_EVENT_ATTR(l2_runtime_agg, L2_RUNTIME_AGG);
+
+static struct attribute *vpa_pmu_events_attr[] = {
+ VPA_PMU_EVENT_PTR(L1_TO_L2_CS_LAT),
+ VPA_PMU_EVENT_PTR(L2_TO_L1_CS_LAT),
+ VPA_PMU_EVENT_PTR(L2_RUNTIME_AGG),
+ NULL
+};
+
+static const struct attribute_group vpa_pmu_events_group = {
+ .name = "events",
+ .attrs = vpa_pmu_events_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-31");
+static struct attribute *vpa_pmu_format_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group vpa_pmu_format_group = {
+ .name = "format",
+ .attrs = vpa_pmu_format_attr,
+};
+
+static const struct attribute_group *vpa_pmu_attr_groups[] = {
+ &vpa_pmu_events_group,
+ &vpa_pmu_format_group,
+ NULL
+};
+
+static int vpa_pmu_event_init(struct perf_event *event)
+{
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ /* it does not support event sampling mode */
+ if (is_sampling_event(event))
+ return -EOPNOTSUPP;
+
+ /* no branch sampling */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
+ /* Invalid event code */
+ if ((event->attr.config <= 0) || (event->attr.config > 3))
+ return -EINVAL;
+
+ return 0;
+}
+
+static unsigned long get_counter_data(struct perf_event *event)
+{
+ unsigned int config = event->attr.config;
+ u64 data;
+
+ switch (config) {
+ case L1_TO_L2_CS_LAT:
+ if (event->attach_state & PERF_ATTACH_TASK)
+ data = kvmhv_get_l1_to_l2_cs_time_vcpu();
+ else
+ data = kvmhv_get_l1_to_l2_cs_time();
+ break;
+ case L2_TO_L1_CS_LAT:
+ if (event->attach_state & PERF_ATTACH_TASK)
+ data = kvmhv_get_l2_to_l1_cs_time_vcpu();
+ else
+ data = kvmhv_get_l2_to_l1_cs_time();
+ break;
+ case L2_RUNTIME_AGG:
+ if (event->attach_state & PERF_ATTACH_TASK)
+ data = kvmhv_get_l2_runtime_agg_vcpu();
+ else
+ data = kvmhv_get_l2_runtime_agg();
+ break;
+ default:
+ data = 0;
+ break;
+ }
+
+ return data;
+}
+
+static int vpa_pmu_add(struct perf_event *event, int flags)
+{
+ u64 data;
+
+ kvmhv_set_l2_counters_status(smp_processor_id(), true);
+
+ data = get_counter_data(event);
+ local64_set(&event->hw.prev_count, data);
+
+ return 0;
+}
+
+static void vpa_pmu_read(struct perf_event *event)
+{
+ u64 prev_data, new_data, final_data;
+
+ prev_data = local64_read(&event->hw.prev_count);
+ new_data = get_counter_data(event);
+ final_data = new_data - prev_data;
+
+ local64_add(final_data, &event->count);
+}
+
+static void vpa_pmu_del(struct perf_event *event, int flags)
+{
+ vpa_pmu_read(event);
+
+ /*
+ * Disable vpa counter accumulation
+ */
+ kvmhv_set_l2_counters_status(smp_processor_id(), false);
+}
+
+static struct pmu vpa_pmu = {
+ .task_ctx_nr = perf_sw_context,
+ .name = "vpa_pmu",
+ .event_init = vpa_pmu_event_init,
+ .add = vpa_pmu_add,
+ .del = vpa_pmu_del,
+ .read = vpa_pmu_read,
+ .attr_groups = vpa_pmu_attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+};
+
+static int __init pseries_vpa_pmu_init(void)
+{
+ /*
+ * List of current Linux on Power platforms and
+ * this driver is supported only in PowerVM LPAR
+ * (L1) platform.
+ *
+ * Enabled Linux on Power Platforms
+ * ----------------------------------------
+ * [X] PowerVM LPAR (L1)
+ * [ ] KVM Guest On PowerVM KoP(L2)
+ * [ ] Baremetal(PowerNV)
+ * [ ] KVM Guest On PowerNV
+ */
+ if (!firmware_has_feature(FW_FEATURE_LPAR) || is_kvm_guest())
+ return -ENODEV;
+
+ perf_pmu_register(&vpa_pmu, vpa_pmu.name, -1);
+ pr_info("Virtual Processor Area PMU registered.\n");
+
+ return 0;
+}
+
+static void __exit pseries_vpa_pmu_cleanup(void)
+{
+ perf_pmu_unregister(&vpa_pmu);
+ pr_info("Virtual Processor Area PMU unregistered.\n");
+}
+
+module_init(pseries_vpa_pmu_init);
+module_exit(pseries_vpa_pmu_cleanup);
+MODULE_DESCRIPTION("Perf Driver for pSeries VPA pmu counter");
+MODULE_AUTHOR("Kajol Jain <kjain@linux.ibm.com>");
+MODULE_AUTHOR("Madhavan Srinivasan <maddy@linux.ibm.com>");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
deleted file mode 100644
index b3c466c50535..000000000000
--- a/arch/powerpc/platforms/40x/Kconfig
+++ /dev/null
@@ -1,78 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config ACADIA
- bool "Acadia"
- depends on 40x
- select PPC40x_SIMPLE
- select 405EZ
- help
- This option enables support for the AMCC 405EZ Acadia evaluation board.
-
-config HOTFOOT
- bool "Hotfoot"
- depends on 40x
- select PPC40x_SIMPLE
- select FORCE_PCI
- help
- This option enables support for the ESTEEM 195E Hotfoot board.
-
-config KILAUEA
- bool "Kilauea"
- depends on 40x
- select 405EX
- select PPC40x_SIMPLE
- select PPC4xx_PCI_EXPRESS
- select FORCE_PCI
- select PCI_MSI
- help
- This option enables support for the AMCC PPC405EX evaluation board.
-
-config MAKALU
- bool "Makalu"
- depends on 40x
- select 405EX
- select FORCE_PCI
- select PPC4xx_PCI_EXPRESS
- select PPC40x_SIMPLE
- help
- This option enables support for the AMCC PPC405EX board.
-
-config OBS600
- bool "OpenBlockS 600"
- depends on 40x
- select 405EX
- select PPC40x_SIMPLE
- help
- This option enables support for PlatHome OpenBlockS 600 server
-
-config PPC40x_SIMPLE
- bool "Simple PowerPC 40x board support"
- depends on 40x
- help
- This option enables the simple PowerPC 40x platform support.
-
-config 405EX
- bool
- select IBM_EMAC_EMAC4 if IBM_EMAC
- select IBM_EMAC_RGMII if IBM_EMAC
-
-config 405EZ
- bool
- select IBM_EMAC_NO_FLOW_CTRL if IBM_EMAC
- select IBM_EMAC_MAL_CLR_ICINTSTAT if IBM_EMAC
- select IBM_EMAC_MAL_COMMON_ERR if IBM_EMAC
-
-config PPC4xx_GPIO
- bool "PPC4xx GPIO support"
- depends on 40x
- select GPIOLIB
- select OF_GPIO_MM_GPIOCHIP
- help
- Enable gpiolib support for ppc40x based boards
-
-config APM8018X
- bool "APM8018X"
- depends on 40x
- select PPC40x_SIMPLE
- help
- This option enables support for the AppliedMicro APM8018X evaluation
- board.
diff --git a/arch/powerpc/platforms/40x/Makefile b/arch/powerpc/platforms/40x/Makefile
deleted file mode 100644
index 122de98527c4..000000000000
--- a/arch/powerpc/platforms/40x/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_PPC40x_SIMPLE) += ppc40x_simple.o
diff --git a/arch/powerpc/platforms/40x/ppc40x_simple.c b/arch/powerpc/platforms/40x/ppc40x_simple.c
deleted file mode 100644
index e454e9d2eff1..000000000000
--- a/arch/powerpc/platforms/40x/ppc40x_simple.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Generic PowerPC 40x platform support
- *
- * Copyright 2008 IBM Corporation
- *
- * This implements simple platform support for PowerPC 44x chips. This is
- * mostly used for eval boards or other simple and "generic" 44x boards. If
- * your board has custom functions or hardware, then you will likely want to
- * implement your own board.c file to accommodate it.
- */
-
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/ppc4xx.h>
-#include <asm/time.h>
-#include <asm/udbg.h>
-#include <asm/uic.h>
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-
-static const struct of_device_id ppc40x_of_bus[] __initconst = {
- { .compatible = "ibm,plb3", },
- { .compatible = "ibm,plb4", },
- { .compatible = "ibm,opb", },
- { .compatible = "ibm,ebc", },
- { .compatible = "simple-bus", },
- {},
-};
-
-static int __init ppc40x_device_probe(void)
-{
- of_platform_bus_probe(NULL, ppc40x_of_bus, NULL);
-
- return 0;
-}
-machine_device_initcall(ppc40x_simple, ppc40x_device_probe);
-
-/* This is the list of boards that can be supported by this simple
- * platform code. This does _not_ mean the boards are compatible,
- * as they most certainly are not from a device tree perspective.
- * However, their differences are handled by the device tree and the
- * drivers and therefore they don't need custom board support files.
- *
- * Again, if your board needs to do things differently then create a
- * board.c file for it rather than adding it to this list.
- */
-static const char * const board[] __initconst = {
- "amcc,acadia",
- "amcc,haleakala",
- "amcc,kilauea",
- "amcc,makalu",
- "apm,klondike",
- "est,hotfoot",
- "plathome,obs600",
- NULL
-};
-
-static int __init ppc40x_probe(void)
-{
- if (of_device_compatible_match(of_root, board)) {
- pci_set_flags(PCI_REASSIGN_ALL_RSRC);
- return 1;
- }
-
- return 0;
-}
-
-define_machine(ppc40x_simple) {
- .name = "PowerPC 40x Platform",
- .probe = ppc40x_probe,
- .progress = udbg_progress,
- .init_IRQ = uic_init_tree,
- .get_irq = uic_get_irq,
- .restart = ppc4xx_reset_system,
-};
diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile
index 5ba031f57652..ca7b1bb442d9 100644
--- a/arch/powerpc/platforms/44x/Makefile
+++ b/arch/powerpc/platforms/44x/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-obj-y += misc_44x.o machine_check.o
+obj-y += misc_44x.o machine_check.o uic.o soc.o
ifneq ($(CONFIG_PPC4xx_CPM),y)
obj-y += idle.o
endif
@@ -12,3 +12,7 @@ obj-$(CONFIG_CANYONLANDS)+= canyonlands.o
obj-$(CONFIG_CURRITUCK) += ppc476.o
obj-$(CONFIG_AKEBONO) += ppc476.o
obj-$(CONFIG_FSP2) += fsp2.o
+obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_PPC4xx_HSTA_MSI) += hsta_msi.o
+obj-$(CONFIG_PPC4xx_CPM) += cpm.o
+obj-$(CONFIG_PPC4xx_GPIO) += gpio.o
diff --git a/arch/powerpc/platforms/4xx/cpm.c b/arch/powerpc/platforms/44x/cpm.c
index 670f8ad4465b..670f8ad4465b 100644
--- a/arch/powerpc/platforms/4xx/cpm.c
+++ b/arch/powerpc/platforms/44x/cpm.c
diff --git a/arch/powerpc/platforms/4xx/gpio.c b/arch/powerpc/platforms/44x/gpio.c
index e5f2319e5cbe..e5f2319e5cbe 100644
--- a/arch/powerpc/platforms/4xx/gpio.c
+++ b/arch/powerpc/platforms/44x/gpio.c
diff --git a/arch/powerpc/platforms/4xx/hsta_msi.c b/arch/powerpc/platforms/44x/hsta_msi.c
index c6bd846b0d65..c6bd846b0d65 100644
--- a/arch/powerpc/platforms/4xx/hsta_msi.c
+++ b/arch/powerpc/platforms/44x/hsta_msi.c
diff --git a/arch/powerpc/platforms/44x/machine_check.c b/arch/powerpc/platforms/44x/machine_check.c
index 5d19daacd78a..85ff33a8d9b6 100644
--- a/arch/powerpc/platforms/44x/machine_check.c
+++ b/arch/powerpc/platforms/44x/machine_check.c
@@ -9,6 +9,21 @@
#include <asm/reg.h>
#include <asm/cacheflush.h>
+int machine_check_4xx(struct pt_regs *regs)
+{
+ unsigned long reason = regs->esr;
+
+ if (reason & ESR_IMCP) {
+ printk("Instruction");
+ mtspr(SPRN_ESR, reason & ~ESR_IMCP);
+ } else
+ printk("Data");
+
+ printk(" machine check in kernel mode.\n");
+
+ return 0;
+}
+
int machine_check_440A(struct pt_regs *regs)
{
unsigned long reason = regs->esr;
diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/44x/pci.c
index 48626615b18b..364aeb86ab64 100644
--- a/arch/powerpc/platforms/4xx/pci.c
+++ b/arch/powerpc/platforms/44x/pci.c
@@ -94,10 +94,8 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose,
struct resource *res)
{
u64 size;
- const u32 *ranges;
- int rlen;
- int pna = of_n_addr_cells(hose->dn);
- int np = pna + 5;
+ struct of_range_parser parser;
+ struct of_range range;
/* Default */
res->start = 0;
@@ -105,18 +103,15 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose,
res->end = size - 1;
res->flags = IORESOURCE_MEM | IORESOURCE_PREFETCH;
- /* Get dma-ranges property */
- ranges = of_get_property(hose->dn, "dma-ranges", &rlen);
- if (ranges == NULL)
+ if (of_pci_dma_range_parser_init(&parser, hose->dn))
goto out;
- /* Walk it */
- while ((rlen -= np * 4) >= 0) {
- u32 pci_space = ranges[0];
- u64 pci_addr = of_read_number(ranges + 1, 2);
- u64 cpu_addr = of_translate_dma_address(hose->dn, ranges + 3);
- size = of_read_number(ranges + pna + 3, 2);
- ranges += np;
+ for_each_of_range(&parser, &range) {
+ u32 pci_space = range.flags;
+ u64 pci_addr = range.bus_addr;
+ u64 cpu_addr = range.cpu_addr;
+ size = range.size;
+
if (cpu_addr == OF_BAD_ADDR || size == 0)
continue;
@@ -1263,102 +1258,6 @@ static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = {
#endif /* CONFIG_44x */
-#ifdef CONFIG_40x
-
-static int __init ppc405ex_pciex_core_init(struct device_node *np)
-{
- /* Nothing to do, return 2 ports */
- return 2;
-}
-
-static void __init ppc405ex_pcie_phy_reset(struct ppc4xx_pciex_port *port)
-{
- /* Assert the PE0_PHY reset */
- mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x01010000);
- msleep(1);
-
- /* deassert the PE0_hotreset */
- if (port->endpoint)
- mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x01111000);
- else
- mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x01101000);
-
- /* poll for phy !reset */
- /* XXX FIXME add timeout */
- while (!(mfdcri(SDR0, port->sdr_base + PESDRn_405EX_PHYSTA) & 0x00001000))
- ;
-
- /* deassert the PE0_gpl_utl_reset */
- mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x00101000);
-}
-
-static int __init ppc405ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
-{
- u32 val;
-
- if (port->endpoint)
- val = PTYPE_LEGACY_ENDPOINT;
- else
- val = PTYPE_ROOT_PORT;
-
- mtdcri(SDR0, port->sdr_base + PESDRn_DLPSET,
- 1 << 24 | val << 20 | LNKW_X1 << 12);
-
- mtdcri(SDR0, port->sdr_base + PESDRn_UTLSET1, 0x00000000);
- mtdcri(SDR0, port->sdr_base + PESDRn_UTLSET2, 0x01010000);
- mtdcri(SDR0, port->sdr_base + PESDRn_405EX_PHYSET1, 0x720F0000);
- mtdcri(SDR0, port->sdr_base + PESDRn_405EX_PHYSET2, 0x70600003);
-
- /*
- * Only reset the PHY when no link is currently established.
- * This is for the Atheros PCIe board which has problems to establish
- * the link (again) after this PHY reset. All other currently tested
- * PCIe boards don't show this problem.
- * This has to be re-tested and fixed in a later release!
- */
- val = mfdcri(SDR0, port->sdr_base + PESDRn_LOOP);
- if (!(val & 0x00001000))
- ppc405ex_pcie_phy_reset(port);
-
- dcr_write(port->dcrs, DCRO_PEGPL_CFG, 0x10000000); /* guarded on */
-
- port->has_ibpre = 1;
-
- return ppc4xx_pciex_port_reset_sdr(port);
-}
-
-static int ppc405ex_pciex_init_utl(struct ppc4xx_pciex_port *port)
-{
- dcr_write(port->dcrs, DCRO_PEGPL_SPECIAL, 0x0);
-
- /*
- * Set buffer allocations and then assert VRB and TXE.
- */
- out_be32(port->utl_base + PEUTL_OUTTR, 0x02000000);
- out_be32(port->utl_base + PEUTL_INTR, 0x02000000);
- out_be32(port->utl_base + PEUTL_OPDBSZ, 0x04000000);
- out_be32(port->utl_base + PEUTL_PBBSZ, 0x21000000);
- out_be32(port->utl_base + PEUTL_IPHBSZ, 0x02000000);
- out_be32(port->utl_base + PEUTL_IPDBSZ, 0x04000000);
- out_be32(port->utl_base + PEUTL_RCIRQEN, 0x00f00000);
- out_be32(port->utl_base + PEUTL_PCTL, 0x80800066);
-
- out_be32(port->utl_base + PEUTL_PBCTL, 0x08000000);
-
- return 0;
-}
-
-static struct ppc4xx_pciex_hwops ppc405ex_pcie_hwops __initdata =
-{
- .want_sdr = true,
- .core_init = ppc405ex_pciex_core_init,
- .port_init_hw = ppc405ex_pciex_init_port_hw,
- .setup_utl = ppc405ex_pciex_init_utl,
- .check_link = ppc4xx_pciex_check_link_sdr,
-};
-
-#endif /* CONFIG_40x */
-
#ifdef CONFIG_476FPE
static int __init ppc_476fpe_pciex_core_init(struct device_node *np)
{
@@ -1427,10 +1326,6 @@ static int __init ppc4xx_pciex_check_core_init(struct device_node *np)
if (of_device_is_compatible(np, "ibm,plb-pciex-apm821xx"))
ppc4xx_pciex_hwops = &apm821xx_pcie_hwops;
#endif /* CONFIG_44x */
-#ifdef CONFIG_40x
- if (of_device_is_compatible(np, "ibm,plb-pciex-405ex"))
- ppc4xx_pciex_hwops = &ppc405ex_pcie_hwops;
-#endif
#ifdef CONFIG_476FPE
if (of_device_is_compatible(np, "ibm,plb-pciex-476fpe")
|| of_device_is_compatible(np, "ibm,plb-pciex-476gtr"))
diff --git a/arch/powerpc/platforms/4xx/pci.h b/arch/powerpc/platforms/44x/pci.h
index bb4821938ab1..bb4821938ab1 100644
--- a/arch/powerpc/platforms/4xx/pci.h
+++ b/arch/powerpc/platforms/44x/pci.h
diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c
index 164cbcd4588e..e7b7bdaad341 100644
--- a/arch/powerpc/platforms/44x/ppc476.c
+++ b/arch/powerpc/platforms/44x/ppc476.c
@@ -95,7 +95,7 @@ static int avr_probe(struct i2c_client *client)
}
static const struct i2c_device_id avr_id[] = {
- { "akebono-avr", 0 },
+ { "akebono-avr" },
{ }
};
diff --git a/arch/powerpc/platforms/4xx/soc.c b/arch/powerpc/platforms/44x/soc.c
index 5412e6b21e10..5412e6b21e10 100644
--- a/arch/powerpc/platforms/4xx/soc.c
+++ b/arch/powerpc/platforms/44x/soc.c
diff --git a/arch/powerpc/platforms/4xx/uic.c b/arch/powerpc/platforms/44x/uic.c
index e3e148b9dd18..e3e148b9dd18 100644
--- a/arch/powerpc/platforms/4xx/uic.c
+++ b/arch/powerpc/platforms/44x/uic.c
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index bf0188dcb918..a5001d32f978 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -8,6 +8,7 @@
#include <linux/err.h>
#include <linux/init.h>
#include <linux/of_platform.h>
+#include <linux/platform_device.h>
#include <linux/kthread.h>
#include <linux/leds.h>
#include <linux/i2c.h>
diff --git a/arch/powerpc/platforms/4xx/Makefile b/arch/powerpc/platforms/4xx/Makefile
deleted file mode 100644
index 2071a0abe09b..000000000000
--- a/arch/powerpc/platforms/4xx/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-y += uic.o machine_check.o
-obj-$(CONFIG_4xx_SOC) += soc.o
-obj-$(CONFIG_PCI) += pci.o
-obj-$(CONFIG_PPC4xx_HSTA_MSI) += hsta_msi.o
-obj-$(CONFIG_PPC4xx_CPM) += cpm.o
-obj-$(CONFIG_PPC4xx_GPIO) += gpio.o
diff --git a/arch/powerpc/platforms/4xx/machine_check.c b/arch/powerpc/platforms/4xx/machine_check.c
deleted file mode 100644
index a905da1d6f41..000000000000
--- a/arch/powerpc/platforms/4xx/machine_check.c
+++ /dev/null
@@ -1,23 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- */
-
-#include <linux/kernel.h>
-#include <linux/printk.h>
-#include <linux/ptrace.h>
-
-#include <asm/reg.h>
-
-int machine_check_4xx(struct pt_regs *regs)
-{
- unsigned long reason = regs->esr;
-
- if (reason & ESR_IMCP) {
- printk("Instruction");
- mtspr(SPRN_ESR, reason & ~ESR_IMCP);
- } else
- printk("Data");
- printk(" machine check in kernel mode.\n");
-
- return 0;
-}
diff --git a/arch/powerpc/platforms/512x/mpc512x_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c
index 0d58ab257cd9..d4fa6c302ccf 100644
--- a/arch/powerpc/platforms/512x/mpc512x_generic.c
+++ b/arch/powerpc/platforms/512x/mpc512x_generic.c
@@ -32,9 +32,6 @@ static const char * const board[] __initconst = {
*/
static int __init mpc512x_generic_probe(void)
{
- if (!of_device_compatible_match(of_root, board))
- return 0;
-
mpc512x_init_early();
return 1;
@@ -42,6 +39,7 @@ static int __init mpc512x_generic_probe(void)
define_machine(mpc512x_generic) {
.name = "MPC512x generic",
+ .compatibles = board,
.probe = mpc512x_generic_probe,
.init = mpc512x_init,
.setup_arch = mpc512x_setup_arch,
diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
index 4a25b6b48615..9668b052cd4b 100644
--- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
+++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
@@ -504,7 +504,7 @@ MODULE_DEVICE_TABLE(of, mpc512x_lpbfifo_match);
static struct platform_driver mpc512x_lpbfifo_driver = {
.probe = mpc512x_lpbfifo_probe,
- .remove_new = mpc512x_lpbfifo_remove,
+ .remove = mpc512x_lpbfifo_remove,
.driver = {
.name = DRV_NAME,
.of_match_table = mpc512x_lpbfifo_match,
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index 8f75e9574c27..8c1f3b629fc7 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -279,7 +279,7 @@ static void __init mpc512x_setup_diu(void)
* and so negatively affect boot time. Instead we reserve the
* already configured frame buffer area so that it won't be
* destroyed. The starting address of the area to reserve and
- * also it's length is passed to memblock_reserve(). It will be
+ * also its length is passed to memblock_reserve(). It will be
* freed later on first open of fbdev, when splash image is not
* needed any more.
*/
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index aa82e6b437f3..a7172f9ebaad 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -13,6 +13,7 @@
#include <generated/utsrelease.h>
#include <linux/pci.h>
#include <linux/of.h>
+#include <linux/seq_file.h>
#include <asm/dma.h>
#include <asm/time.h>
#include <asm/machdep.h>
@@ -195,8 +196,10 @@ static void __init efika_setup_arch(void)
static int __init efika_probe(void)
{
- const char *model = of_get_property(of_root, "model", NULL);
+ struct device_node *root = of_find_node_by_path("/");
+ const char *model = of_get_property(root, "model", NULL);
+ of_node_put(root);
if (model == NULL)
return 0;
if (strcmp(model, "EFIKA5K2"))
diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c
index 0fd67b3ffc3e..0a161d82a3a8 100644
--- a/arch/powerpc/platforms/52xx/lite5200.c
+++ b/arch/powerpc/platforms/52xx/lite5200.c
@@ -172,17 +172,9 @@ static const char * const board[] __initconst = {
NULL,
};
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init lite5200_probe(void)
-{
- return of_device_compatible_match(of_root, board);
-}
-
define_machine(lite5200) {
.name = "lite5200",
- .probe = lite5200_probe,
+ .compatibles = board,
.setup_arch = lite5200_setup_arch,
.discover_phbs = mpc52xx_setup_pci,
.init = mpc52xx_declare_of_platform_devices,
diff --git a/arch/powerpc/platforms/52xx/lite5200_sleep.S b/arch/powerpc/platforms/52xx/lite5200_sleep.S
index 0b12647e7b42..0ec2522ee4ad 100644
--- a/arch/powerpc/platforms/52xx/lite5200_sleep.S
+++ b/arch/powerpc/platforms/52xx/lite5200_sleep.S
@@ -203,7 +203,8 @@ lite5200_wakeup:
/* HIDs, MSR */
LOAD_SPRN(HID1, 0x19)
- LOAD_SPRN(HID2, 0x1a)
+ /* FIXME: Should this use HID2_G2_LE? */
+ LOAD_SPRN(HID2_750FX, 0x1a)
/* address translation is tricky (see turn_on_mmu) */
@@ -283,7 +284,8 @@ SYM_FUNC_START_LOCAL(save_regs)
SAVE_SPRN(HID0, 0x18)
SAVE_SPRN(HID1, 0x19)
- SAVE_SPRN(HID2, 0x1a)
+ /* FIXME: Should this use HID2_G2_LE? */
+ SAVE_SPRN(HID2_750FX, 0x1a)
mfmsr r10
stw r10, (4*0x1b)(r4)
/*SAVE_SPRN(LR, 0x1c) have to save it before the call */
diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index f1e85e86f5e5..7e0e4c34a40b 100644
--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
+++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
@@ -59,17 +59,9 @@ static const char *board[] __initdata = {
NULL
};
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init mpc5200_simple_probe(void)
-{
- return of_device_compatible_match(of_root, board);
-}
-
define_machine(mpc5200_simple_platform) {
.name = "mpc5200-simple-platform",
- .probe = mpc5200_simple_probe,
+ .compatibles = board,
.setup_arch = mpc5200_simple_setup_arch,
.discover_phbs = mpc52xx_setup_pci,
.init = mpc52xx_declare_of_platform_devices,
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index b4938e344f71..253421ffb4e5 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -12,12 +12,10 @@
#undef DEBUG
-#include <linux/gpio.h>
#include <linux/kernel.h>
#include <linux/spinlock.h>
#include <linux/of_address.h>
#include <linux/of_platform.h>
-#include <linux/of_gpio.h>
#include <linux/export.h>
#include <asm/io.h>
#include <asm/mpc52xx.h>
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 581059527c36..1ea591ec6083 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -48,6 +48,7 @@
* the output mode. This driver does not change the output mode setting.
*/
+#include <linux/gpio/driver.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/io.h>
@@ -56,7 +57,6 @@
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
-#include <linux/of_gpio.h>
#include <linux/platform_device.h>
#include <linux/kernel.h>
#include <linux/property.h>
@@ -644,7 +644,6 @@ static int mpc52xx_wdt_release(struct inode *inode, struct file *file)
static const struct file_operations mpc52xx_wdt_fops = {
.owner = THIS_MODULE,
- .llseek = no_llseek,
.write = mpc52xx_wdt_write,
.unlocked_ioctl = mpc52xx_wdt_ioctl,
.compat_ioctl = compat_ptr_ioctl,
diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c
index 3dc65ce1f175..8f918916e631 100644
--- a/arch/powerpc/platforms/82xx/ep8248e.c
+++ b/arch/powerpc/platforms/82xx/ep8248e.c
@@ -128,7 +128,7 @@ static int ep8248e_mdio_probe(struct platform_device *ofdev)
bus->name = "ep8248e-mdio-bitbang";
bus->parent = &ofdev->dev;
- snprintf(bus->id, MII_BUS_ID_SIZE, "%x", res.start);
+ snprintf(bus->id, MII_BUS_ID_SIZE, "%pa", &res.start);
ret = of_mdiobus_register(bus, ofdev->dev.of_node);
if (ret)
diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c
index c86da3f2b74b..99f0f0f41876 100644
--- a/arch/powerpc/platforms/82xx/km82xx.c
+++ b/arch/powerpc/platforms/82xx/km82xx.c
@@ -27,15 +27,15 @@
static void __init km82xx_pic_init(void)
{
- struct device_node *np = of_find_compatible_node(NULL, NULL,
- "fsl,pq2-pic");
+ struct device_node *np __free(device_node);
+ np = of_find_compatible_node(NULL, NULL, "fsl,pq2-pic");
+
if (!np) {
pr_err("PIC init: can not find cpm-pic node\n");
return;
}
cpm2_pic_init(np);
- of_node_put(np);
}
struct cpm_pin {
diff --git a/arch/powerpc/platforms/83xx/mpc830x_rdb.c b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
index 534bb227480d..63b6d213726a 100644
--- a/arch/powerpc/platforms/83xx/mpc830x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
@@ -34,19 +34,11 @@ static const char *board[] __initdata = {
NULL
};
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init mpc830x_rdb_probe(void)
-{
- return of_device_compatible_match(of_root, board);
-}
-
machine_device_initcall(mpc830x_rdb, mpc83xx_declare_of_platform_devices);
define_machine(mpc830x_rdb) {
.name = "MPC830x RDB",
- .probe = mpc830x_rdb_probe,
+ .compatibles = board,
.setup_arch = mpc830x_rdb_setup_arch,
.discover_phbs = mpc83xx_setup_pci,
.init_IRQ = mpc83xx_ipic_init_IRQ,
diff --git a/arch/powerpc/platforms/83xx/mpc831x_rdb.c b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
index 7b901ab3b864..5c39966762e4 100644
--- a/arch/powerpc/platforms/83xx/mpc831x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
@@ -34,19 +34,11 @@ static const char *board[] __initdata = {
NULL
};
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init mpc831x_rdb_probe(void)
-{
- return of_device_compatible_match(of_root, board);
-}
-
machine_device_initcall(mpc831x_rdb, mpc83xx_declare_of_platform_devices);
define_machine(mpc831x_rdb) {
.name = "MPC831x RDB",
- .probe = mpc831x_rdb_probe,
+ .compatibles = board,
.setup_arch = mpc831x_rdb_setup_arch,
.discover_phbs = mpc83xx_setup_pci,
.init_IRQ = mpc83xx_ipic_init_IRQ,
diff --git a/arch/powerpc/platforms/83xx/mpc837x_rdb.c b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
index 39e78018dd0b..45823e147933 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
@@ -61,17 +61,9 @@ static const char * const board[] __initconst = {
NULL
};
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init mpc837x_rdb_probe(void)
-{
- return of_device_compatible_match(of_root, board);
-}
-
define_machine(mpc837x_rdb) {
.name = "MPC837x RDB/WLAN",
- .probe = mpc837x_rdb_probe,
+ .compatibles = board,
.setup_arch = mpc837x_rdb_setup_arch,
.discover_phbs = mpc83xx_setup_pci,
.init_IRQ = mpc83xx_ipic_init_IRQ,
diff --git a/arch/powerpc/platforms/83xx/suspend-asm.S b/arch/powerpc/platforms/83xx/suspend-asm.S
index bc6bd4d0ae96..6a62ed6082c9 100644
--- a/arch/powerpc/platforms/83xx/suspend-asm.S
+++ b/arch/powerpc/platforms/83xx/suspend-asm.S
@@ -68,7 +68,8 @@ _GLOBAL(mpc83xx_enter_deep_sleep)
mfspr r5, SPRN_HID0
mfspr r6, SPRN_HID1
- mfspr r7, SPRN_HID2
+ /* FIXME: Should this use SPRN_HID2_G2_LE? */
+ mfspr r7, SPRN_HID2_750FX
stw r5, SS_HID+0(r3)
stw r6, SS_HID+4(r3)
@@ -396,7 +397,8 @@ mpc83xx_deep_resume:
mtspr SPRN_HID0, r5
mtspr SPRN_HID1, r6
- mtspr SPRN_HID2, r7
+ /* FIXME: Should this use SPRN_HID2_G2_LE? */
+ mtspr SPRN_HID2_750FX, r7
lwz r4, SS_IABR+0(r3)
lwz r5, SS_IABR+4(r3)
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index c9664e46b03d..99bd4355f28e 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -206,7 +206,8 @@ static int mpc83xx_suspend_enter(suspend_state_t state)
out_be32(&pmc_regs->config1,
in_be32(&pmc_regs->config1) | PMCCR1_POWER_OFF);
- enable_kernel_fp();
+ if (IS_ENABLED(CONFIG_PPC_FPU))
+ enable_kernel_fp();
mpc83xx_enter_deep_sleep(immrbase);
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 9315a3b69d6d..604c1b4b6d45 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -40,27 +40,6 @@ config BSC9132_QDS
and dual StarCore SC3850 DSP cores.
Manufacturer : Freescale Semiconductor, Inc
-config MPC8540_ADS
- bool "Freescale MPC8540 ADS"
- select DEFAULT_UIMAGE
- help
- This option enables support for the MPC 8540 ADS board
-
-config MPC8560_ADS
- bool "Freescale MPC8560 ADS"
- select DEFAULT_UIMAGE
- select CPM2
- help
- This option enables support for the MPC 8560 ADS board
-
-config MPC85xx_CDS
- bool "Freescale MPC85xx CDS"
- select DEFAULT_UIMAGE
- select PPC_I8259
- select HAVE_RAPIDIO
- help
- This option enables support for the MPC85xx CDS board
-
config MPC85xx_MDS
bool "Freescale MPC8568 MDS / MPC8569 MDS / P1021 MDS"
select DEFAULT_UIMAGE
diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c
index 2eb62bff86d4..3ad8096fcf16 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_qds.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c
@@ -19,7 +19,7 @@
#include "mpc85xx.h"
#include "smp.h"
-void __init bsc913x_qds_pic_init(void)
+static void __init bsc913x_qds_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
index 161f006cb3bb..dcd358c28201 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_rdb.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
@@ -15,7 +15,7 @@
#include "mpc85xx.h"
-void __init bsc913x_rdb_pic_init(void)
+static void __init bsc913x_rdb_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index 645fcca77cde..c44400e95f55 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -149,7 +149,7 @@ static int __init corenet_generic_probe(void)
extern struct smp_ops_t smp_85xx_ops;
#endif
- if (of_device_compatible_match(of_root, boards))
+ if (of_machine_compatible_match(boards))
return 1;
/* Check if we're running under the Freescale hypervisor */
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index 9c3b44a1952e..477852f1a726 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -38,7 +38,7 @@
void __iomem *imp3a_regs;
-void __init ge_imp3a_pic_init(void)
+static void __init ge_imp3a_pic_init(void)
{
struct mpic *mpic;
struct device_node *np;
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index 751395cbf022..e635b27ee718 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -114,7 +114,7 @@ static int gpio_halt_probe(struct platform_device *pdev)
return ret;
}
-static int gpio_halt_remove(struct platform_device *pdev)
+static void gpio_halt_remove(struct platform_device *pdev)
{
free_irq(halt_irq, pdev);
cancel_work_sync(&gpio_halt_wq);
@@ -124,8 +124,6 @@ static int gpio_halt_remove(struct platform_device *pdev)
gpiod_put(halt_gpio);
halt_gpio = NULL;
-
- return 0;
}
static const struct of_device_id gpio_halt_match[] = {
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 40aa58206888..32fa5fb557c0 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -23,7 +23,7 @@
#include <asm/mpic.h>
#include <asm/cacheflush.h>
#include <asm/dbell.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/cputhreads.h>
#include <asm/fsl_pm.h>
@@ -398,6 +398,7 @@ static void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
hard_irq_disable();
mpic_teardown_this_cpu(secondary);
+#ifdef CONFIG_CRASH_DUMP
if (cpu == crashing_cpu && cpu_thread_in_core(cpu) != 0) {
/*
* We enter the crash kernel on whatever cpu crashed,
@@ -406,9 +407,11 @@ static void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
*/
disable_threadbit = 1;
disable_cpu = cpu_first_thread_sibling(cpu);
- } else if (sibling != crashing_cpu &&
- cpu_thread_in_core(cpu) == 0 &&
- cpu_thread_in_core(sibling) != 0) {
+ } else if (sibling == crashing_cpu) {
+ return;
+ }
+#endif
+ if (cpu_thread_in_core(cpu) == 0 && cpu_thread_in_core(sibling) != 0) {
disable_threadbit = 2;
disable_cpu = sibling;
}
diff --git a/arch/powerpc/platforms/85xx/t1042rdb_diu.c b/arch/powerpc/platforms/85xx/t1042rdb_diu.c
index 767eed98a0a8..d4fbb6eff38a 100644
--- a/arch/powerpc/platforms/85xx/t1042rdb_diu.c
+++ b/arch/powerpc/platforms/85xx/t1042rdb_diu.c
@@ -149,4 +149,5 @@ static int __init t1042rdb_diu_init(void)
early_initcall(t1042rdb_diu_init);
+MODULE_DESCRIPTION("Freescale T1042 DIU driver");
MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index 6be1b9809db6..f74d446c53f0 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -112,17 +112,9 @@ static const char * const board[] __initconst = {
NULL
};
-/*
- * Called very early, device-tree isn't unflattened
- */
-static int __init tqm85xx_probe(void)
-{
- return of_device_compatible_match(of_root, board);
-}
-
define_machine(tqm85xx) {
.name = "TQM85xx",
- .probe = tqm85xx_probe,
+ .compatibles = board,
.setup_arch = tqm85xx_setup_arch,
.init_IRQ = tqm85xx_pic_init,
.show_cpuinfo = tqm85xx_show_cpuinfo,
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
index 8a7e55acf090..9be33e41af6d 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
@@ -12,7 +12,7 @@
#include <linux/delay.h>
#include <linux/pgtable.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/page.h>
#include <asm/pci-bridge.h>
#include <asm/mpic.h>
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index a14d9d8997a4..8623aebfac48 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -195,6 +195,13 @@ config PIN_TLB_IMMR
CONFIG_PIN_TLB_DATA is also selected, it will reduce
CONFIG_PIN_TLB_DATA to 24 Mbytes.
+config PIN_TLB_TEXT
+ bool "Pinned TLB for TEXT"
+ depends on PIN_TLB
+ default y
+ help
+ This pins kernel text with 8M pages.
+
endmenu
endmenu
diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c
index b24d4102fbf6..1dc095ad48fc 100644
--- a/arch/powerpc/platforms/8xx/cpm1.c
+++ b/arch/powerpc/platforms/8xx/cpm1.c
@@ -45,7 +45,7 @@
#include <sysdev/fsl_soc.h>
#ifdef CONFIG_8xx_GPIO
-#include <linux/gpio/legacy-of-mm-gpiochip.h>
+#include <linux/gpio/driver.h>
#endif
#define CPM_MAP_SIZE (0x4000)
@@ -376,7 +376,8 @@ int __init cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode)
#ifdef CONFIG_8xx_GPIO
struct cpm1_gpio16_chip {
- struct of_mm_gpio_chip mm_gc;
+ struct gpio_chip gc;
+ void __iomem *regs;
spinlock_t lock;
/* shadowed data register to clear/set bits safely */
@@ -386,19 +387,17 @@ struct cpm1_gpio16_chip {
int irq[16];
};
-static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc)
+static void cpm1_gpio16_save_regs(struct cpm1_gpio16_chip *cpm1_gc)
{
- struct cpm1_gpio16_chip *cpm1_gc =
- container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc);
- struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+ struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
cpm1_gc->cpdata = in_be16(&iop->dat);
}
static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+ struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
+ struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
u16 pin_mask;
pin_mask = 1 << (15 - gpio);
@@ -406,11 +405,9 @@ static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio)
return !!(in_be16(&iop->dat) & pin_mask);
}
-static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask,
- int value)
+static void __cpm1_gpio16_set(struct cpm1_gpio16_chip *cpm1_gc, u16 pin_mask, int value)
{
- struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
- struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+ struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
if (value)
cpm1_gc->cpdata |= pin_mask;
@@ -422,38 +419,35 @@ static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask,
static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
unsigned long flags;
u16 pin_mask = 1 << (15 - gpio);
spin_lock_irqsave(&cpm1_gc->lock, flags);
- __cpm1_gpio16_set(mm_gc, pin_mask, value);
+ __cpm1_gpio16_set(cpm1_gc, pin_mask, value);
spin_unlock_irqrestore(&cpm1_gc->lock, flags);
}
static int cpm1_gpio16_to_irq(struct gpio_chip *gc, unsigned int gpio)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
return cpm1_gc->irq[gpio] ? : -ENXIO;
}
static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
- struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+ struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
+ struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
unsigned long flags;
u16 pin_mask = 1 << (15 - gpio);
spin_lock_irqsave(&cpm1_gc->lock, flags);
setbits16(&iop->dir, pin_mask);
- __cpm1_gpio16_set(mm_gc, pin_mask, val);
+ __cpm1_gpio16_set(cpm1_gc, pin_mask, val);
spin_unlock_irqrestore(&cpm1_gc->lock, flags);
@@ -462,9 +456,8 @@ static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
static int cpm1_gpio16_dir_in(struct gpio_chip *gc, unsigned int gpio)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
- struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+ struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
+ struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
unsigned long flags;
u16 pin_mask = 1 << (15 - gpio);
@@ -481,11 +474,10 @@ int cpm1_gpiochip_add16(struct device *dev)
{
struct device_node *np = dev->of_node;
struct cpm1_gpio16_chip *cpm1_gc;
- struct of_mm_gpio_chip *mm_gc;
struct gpio_chip *gc;
u16 mask;
- cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL);
+ cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL);
if (!cpm1_gc)
return -ENOMEM;
@@ -499,10 +491,8 @@ int cpm1_gpiochip_add16(struct device *dev)
cpm1_gc->irq[i] = irq_of_parse_and_map(np, j++);
}
- mm_gc = &cpm1_gc->mm_gc;
- gc = &mm_gc->gc;
-
- mm_gc->save_regs = cpm1_gpio16_save_regs;
+ gc = &cpm1_gc->gc;
+ gc->base = -1;
gc->ngpio = 16;
gc->direction_input = cpm1_gpio16_dir_in;
gc->direction_output = cpm1_gpio16_dir_out;
@@ -512,30 +502,39 @@ int cpm1_gpiochip_add16(struct device *dev)
gc->parent = dev;
gc->owner = THIS_MODULE;
- return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc);
+ gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np);
+ if (!gc->label)
+ return -ENOMEM;
+
+ cpm1_gc->regs = devm_of_iomap(dev, np, 0, NULL);
+ if (IS_ERR(cpm1_gc->regs))
+ return PTR_ERR(cpm1_gc->regs);
+
+ cpm1_gpio16_save_regs(cpm1_gc);
+
+ return devm_gpiochip_add_data(dev, gc, cpm1_gc);
}
struct cpm1_gpio32_chip {
- struct of_mm_gpio_chip mm_gc;
+ struct gpio_chip gc;
+ void __iomem *regs;
spinlock_t lock;
/* shadowed data register to clear/set bits safely */
u32 cpdata;
};
-static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
+static void cpm1_gpio32_save_regs(struct cpm1_gpio32_chip *cpm1_gc)
{
- struct cpm1_gpio32_chip *cpm1_gc =
- container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc);
- struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+ struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
cpm1_gc->cpdata = in_be32(&iop->dat);
}
static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+ struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
+ struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
u32 pin_mask;
pin_mask = 1 << (31 - gpio);
@@ -543,11 +542,9 @@ static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio)
return !!(in_be32(&iop->dat) & pin_mask);
}
-static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask,
- int value)
+static void __cpm1_gpio32_set(struct cpm1_gpio32_chip *cpm1_gc, u32 pin_mask, int value)
{
- struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
- struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+ struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
if (value)
cpm1_gc->cpdata |= pin_mask;
@@ -559,30 +556,28 @@ static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask,
static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
unsigned long flags;
u32 pin_mask = 1 << (31 - gpio);
spin_lock_irqsave(&cpm1_gc->lock, flags);
- __cpm1_gpio32_set(mm_gc, pin_mask, value);
+ __cpm1_gpio32_set(cpm1_gc, pin_mask, value);
spin_unlock_irqrestore(&cpm1_gc->lock, flags);
}
static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
- struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+ struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
+ struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
unsigned long flags;
u32 pin_mask = 1 << (31 - gpio);
spin_lock_irqsave(&cpm1_gc->lock, flags);
setbits32(&iop->dir, pin_mask);
- __cpm1_gpio32_set(mm_gc, pin_mask, val);
+ __cpm1_gpio32_set(cpm1_gc, pin_mask, val);
spin_unlock_irqrestore(&cpm1_gc->lock, flags);
@@ -591,9 +586,8 @@ static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
static int cpm1_gpio32_dir_in(struct gpio_chip *gc, unsigned int gpio)
{
- struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
- struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
- struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+ struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
+ struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
unsigned long flags;
u32 pin_mask = 1 << (31 - gpio);
@@ -610,19 +604,16 @@ int cpm1_gpiochip_add32(struct device *dev)
{
struct device_node *np = dev->of_node;
struct cpm1_gpio32_chip *cpm1_gc;
- struct of_mm_gpio_chip *mm_gc;
struct gpio_chip *gc;
- cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL);
+ cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL);
if (!cpm1_gc)
return -ENOMEM;
spin_lock_init(&cpm1_gc->lock);
- mm_gc = &cpm1_gc->mm_gc;
- gc = &mm_gc->gc;
-
- mm_gc->save_regs = cpm1_gpio32_save_regs;
+ gc = &cpm1_gc->gc;
+ gc->base = -1;
gc->ngpio = 32;
gc->direction_input = cpm1_gpio32_dir_in;
gc->direction_output = cpm1_gpio32_dir_out;
@@ -631,7 +622,17 @@ int cpm1_gpiochip_add32(struct device *dev)
gc->parent = dev;
gc->owner = THIS_MODULE;
- return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc);
+ gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np);
+ if (!gc->label)
+ return -ENOMEM;
+
+ cpm1_gc->regs = devm_of_iomap(dev, np, 0, NULL);
+ if (IS_ERR(cpm1_gc->regs))
+ return PTR_ERR(cpm1_gc->regs);
+
+ cpm1_gpio32_save_regs(cpm1_gc);
+
+ return devm_gpiochip_add_data(dev, gc, cpm1_gc);
}
#endif /* CONFIG_8xx_GPIO */
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 1fd253f92a77..a454149ae02f 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -7,7 +7,6 @@ source "arch/powerpc/platforms/chrp/Kconfig"
source "arch/powerpc/platforms/512x/Kconfig"
source "arch/powerpc/platforms/52xx/Kconfig"
source "arch/powerpc/platforms/powermac/Kconfig"
-source "arch/powerpc/platforms/maple/Kconfig"
source "arch/powerpc/platforms/pasemi/Kconfig"
source "arch/powerpc/platforms/ps3/Kconfig"
source "arch/powerpc/platforms/cell/Kconfig"
@@ -18,7 +17,6 @@ source "arch/powerpc/platforms/85xx/Kconfig"
source "arch/powerpc/platforms/86xx/Kconfig"
source "arch/powerpc/platforms/embedded6xx/Kconfig"
source "arch/powerpc/platforms/44x/Kconfig"
-source "arch/powerpc/platforms/40x/Kconfig"
source "arch/powerpc/platforms/amigaone/Kconfig"
source "arch/powerpc/platforms/book3s/Kconfig"
source "arch/powerpc/platforms/microwatt/Kconfig"
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index b2d8c0da2ad9..1453ccc900c4 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -43,19 +43,10 @@ config PPC_8xx
select HAVE_ARCH_VMAP_STACK
select HUGETLBFS
-config 40x
- bool "AMCC 40x"
- select PPC_DCR_NATIVE
- select PPC_UDBG_16550
- select 4xx_SOC
- select HAVE_PCI
- select PPC_KUEP if PPC_KUAP
-
config 44x
bool "AMCC 44x, 46x or 47x"
select PPC_DCR_NATIVE
select PPC_UDBG_16550
- select 4xx_SOC
select HAVE_PCI
select PHYS_64BIT
select PPC_KUEP
@@ -93,11 +84,8 @@ config PPC_BOOK3S_64
bool "Server processors"
select PPC_FPU
select PPC_HAVE_PMU_SUPPORT
- select HAVE_ARCH_TRANSPARENT_HUGEPAGE
- select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
select ARCH_ENABLE_SPLIT_PMD_PTLOCK
- select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_SUPPORTS_HUGETLBFS
select ARCH_SUPPORTS_NUMA_BALANCING
select HAVE_MOVE_PMD
@@ -117,6 +105,14 @@ config PPC_BOOK3E_64
endchoice
+config PPC_THP
+ def_bool y
+ depends on PPC_BOOK3S_64
+ depends on PPC_RADIX_MMU || (PPC_64S_HASH_MMU && PAGE_SIZE_64KB)
+ select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+
choice
prompt "CPU selection"
help
@@ -194,11 +190,6 @@ config E6500_CPU
depends on !CC_IS_CLANG
select PPC_HAS_LBARX_LHARX
-config 405_CPU
- bool "40x family"
- depends on 40x
- depends on !CC_IS_CLANG
-
config 440_CPU
bool "440 (44x family)"
depends on 44x
@@ -264,7 +255,6 @@ config TARGET_CPU
default "e6500" if E6500_CPU
default "power4" if POWERPC64_CPU && !CPU_LITTLE_ENDIAN
default "power8" if POWERPC64_CPU && CPU_LITTLE_ENDIAN
- default "405" if 405_CPU
default "440" if 440_CPU
default "464" if 464_CPU
default "476" if 476_CPU
@@ -340,7 +330,7 @@ config FSL_EMB_PERF_EVENT_E500
config 4xx
bool
- depends on 40x || 44x
+ depends on 44x
default y
config BOOKE
@@ -348,11 +338,6 @@ config BOOKE
depends on PPC_E500 || 44x
default y
-config BOOKE_OR_40x
- bool
- depends on BOOKE || 40x
- default y
-
config PTE_64BIT
bool
depends on 44x || PPC_E500 || PPC_86xx
@@ -495,8 +480,8 @@ config PPC_KERNEL_PCREL
This option builds the kernel with the pc relative ABI model.
config PPC_KUEP
- bool "Kernel Userspace Execution Prevention" if !40x
- default y if !40x
+ bool "Kernel Userspace Execution Prevention"
+ default y
help
Enable support for Kernel Userspace Execution Prevention (KUEP)
@@ -582,7 +567,7 @@ config NR_CPUS
config NOT_COHERENT_CACHE
bool
- depends on 4xx || PPC_8xx || PPC_MPC512x || \
+ depends on 44x || PPC_8xx || PPC_MPC512x || \
GAMECUBE_COMMON || AMIGAONE
select ARCH_HAS_DMA_PREP_COHERENT
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index 94470fb27c99..3cee4a842736 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -4,8 +4,6 @@ obj-$(CONFIG_FSL_ULI1575) += fsl_uli1575.o
obj-$(CONFIG_PPC_PMAC) += powermac/
obj-$(CONFIG_PPC_CHRP) += chrp/
-obj-$(CONFIG_4xx) += 4xx/
-obj-$(CONFIG_40x) += 40x/
obj-$(CONFIG_44x) += 44x/
obj-$(CONFIG_PPC_MPC512x) += 512x/
obj-$(CONFIG_PPC_MPC52xx) += 52xx/
@@ -16,7 +14,6 @@ obj-$(CONFIG_FSL_SOC_BOOKE) += 85xx/
obj-$(CONFIG_PPC_86xx) += 86xx/
obj-$(CONFIG_PPC_POWERNV) += powernv/
obj-$(CONFIG_PPC_PSERIES) += pseries/
-obj-$(CONFIG_PPC_MAPLE) += maple/
obj-$(CONFIG_PPC_PASEMI) += pasemi/
obj-$(CONFIG_PPC_CELL) += cell/
obj-$(CONFIG_PPC_PS3) += ps3/
diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c
index 6c6e714a7521..2c8dc0886912 100644
--- a/arch/powerpc/platforms/amigaone/setup.c
+++ b/arch/powerpc/platforms/amigaone/setup.c
@@ -25,7 +25,7 @@
extern void __flush_disable_L1(void);
-void amigaone_show_cpuinfo(struct seq_file *m)
+static void amigaone_show_cpuinfo(struct seq_file *m)
{
seq_printf(m, "vendor\t\t: Eyetech Ltd.\n");
}
@@ -65,7 +65,7 @@ static int __init amigaone_add_bridge(struct device_node *dev)
return 0;
}
-void __init amigaone_setup_arch(void)
+static void __init amigaone_setup_arch(void)
{
if (ppc_md.progress)
ppc_md.progress("Linux/PPC "UTS_RELEASE"\n", 0);
@@ -83,7 +83,7 @@ static void __init amigaone_discover_phbs(void)
BUG_ON(phb != 0);
}
-void __init amigaone_init_IRQ(void)
+static void __init amigaone_init_IRQ(void)
{
struct device_node *pic, *np = NULL;
const unsigned long *prop = NULL;
@@ -123,7 +123,7 @@ static int __init request_isa_regions(void)
}
machine_device_initcall(amigaone, request_isa_regions);
-void __noreturn amigaone_restart(char *cmd)
+static void __noreturn amigaone_restart(char *cmd)
{
local_irq_disable();
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index f381b177ea06..0b6365d85d11 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -464,7 +464,43 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+/*
+ * During mmap() paste address, mapping VMA is saved in VAS window
+ * struct which is used to unmap during migration if the window is
+ * still open. But the user space can remove this mapping with
+ * munmap() before closing the window and the VMA address will
+ * be invalid. Set VAS window VMA to NULL in this function which
+ * is called before VMA free.
+ */
+static void vas_mmap_close(struct vm_area_struct *vma)
+{
+ struct file *fp = vma->vm_file;
+ struct coproc_instance *cp_inst = fp->private_data;
+ struct vas_window *txwin;
+
+ /* Should not happen */
+ if (!cp_inst || !cp_inst->txwin) {
+ pr_err("No attached VAS window for the paste address mmap\n");
+ return;
+ }
+
+ txwin = cp_inst->txwin;
+ /*
+ * task_ref.vma is set in coproc_mmap() during mmap paste
+ * address. So it has to be the same VMA that is getting freed.
+ */
+ if (WARN_ON(txwin->task_ref.vma != vma)) {
+ pr_err("Invalid paste address mmaping\n");
+ return;
+ }
+
+ mutex_lock(&txwin->task_ref.mmap_mutex);
+ txwin->task_ref.vma = NULL;
+ mutex_unlock(&txwin->task_ref.mmap_mutex);
+}
+
static const struct vm_operations_struct vas_vm_ops = {
+ .close = vas_mmap_close,
.fault = vas_mmap_fault,
};
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 28dc86744cac..d243f7fd8982 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -112,7 +112,7 @@ static void axon_msi_cascade(struct irq_desc *desc)
pr_devel("axon_msi: woff %x roff %x msi %x\n",
write_offset, msic->read_offset, msi);
- if (msi < nr_irqs && irq_get_chip_data(msi) == msic) {
+ if (msi < irq_get_nr_irqs() && irq_get_chip_data(msi) == msic) {
generic_handle_irq(msi);
msic->fifo_virt[idx] = cpu_to_le32(0xffffffff);
} else {
diff --git a/arch/powerpc/platforms/cell/cbe_powerbutton.c b/arch/powerpc/platforms/cell/cbe_powerbutton.c
index a3ee397486f6..3d121acdf69b 100644
--- a/arch/powerpc/platforms/cell/cbe_powerbutton.c
+++ b/arch/powerpc/platforms/cell/cbe_powerbutton.c
@@ -101,5 +101,6 @@ static void __exit cbe_powerbutton_exit(void)
module_init(cbe_powerbutton_init);
module_exit(cbe_powerbutton_exit);
+MODULE_DESCRIPTION("Driver for powerbutton on IBM cell blades");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c
index 2f45428e32c8..c295c6714f9b 100644
--- a/arch/powerpc/platforms/cell/cbe_thermal.c
+++ b/arch/powerpc/platforms/cell/cbe_thermal.c
@@ -381,6 +381,7 @@ static void __exit thermal_exit(void)
}
module_exit(thermal_exit);
+MODULE_DESCRIPTION("Cell processor thermal driver");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
index ca7849e113d7..79172ba36eca 100644
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
@@ -129,5 +129,6 @@ static struct cpufreq_governor spu_governor = {
cpufreq_governor_init(spu_governor);
cpufreq_governor_exit(spu_governor);
+MODULE_DESCRIPTION("SPU-aware cpufreq governor for the cell processor");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 1202a69b0a20..62c9679b8ca3 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -424,23 +424,6 @@ static void __init cell_iommu_setup_hardware(struct cbe_iommu *iommu,
cell_iommu_enable_hardware(iommu);
}
-#if 0/* Unused for now */
-static struct iommu_window *find_window(struct cbe_iommu *iommu,
- unsigned long offset, unsigned long size)
-{
- struct iommu_window *window;
-
- /* todo: check for overlapping (but not equal) windows) */
-
- list_for_each_entry(window, &(iommu->windows), list) {
- if (window->offset == offset && window->size == size)
- return window;
- }
-
- return NULL;
-}
-#endif
-
static inline u32 cell_iommu_get_ioid(struct device_node *np)
{
const u32 *ioid;
@@ -796,58 +779,41 @@ static int __init cell_iommu_init_disabled(void)
static u64 cell_iommu_get_fixed_address(struct device *dev)
{
- u64 cpu_addr, size, best_size, dev_addr = OF_BAD_ADDR;
+ u64 best_size, dev_addr = OF_BAD_ADDR;
struct device_node *np;
- const u32 *ranges = NULL;
- int i, len, best, naddr, nsize, pna, range_size;
+ struct of_range_parser parser;
+ struct of_range range;
/* We can be called for platform devices that have no of_node */
np = of_node_get(dev->of_node);
if (!np)
goto out;
- while (1) {
- naddr = of_n_addr_cells(np);
- nsize = of_n_size_cells(np);
- np = of_get_next_parent(np);
- if (!np)
- break;
-
- ranges = of_get_property(np, "dma-ranges", &len);
+ while ((np = of_get_next_parent(np))) {
+ if (of_pci_dma_range_parser_init(&parser, np))
+ continue;
- /* Ignore empty ranges, they imply no translation required */
- if (ranges && len > 0)
+ if (of_range_count(&parser))
break;
}
- if (!ranges) {
+ if (!np) {
dev_dbg(dev, "iommu: no dma-ranges found\n");
goto out;
}
- len /= sizeof(u32);
-
- pna = of_n_addr_cells(np);
- range_size = naddr + nsize + pna;
-
- /* dma-ranges format:
- * child addr : naddr cells
- * parent addr : pna cells
- * size : nsize cells
- */
- for (i = 0, best = -1, best_size = 0; i < len; i += range_size) {
- cpu_addr = of_translate_dma_address(np, ranges + i + naddr);
- size = of_read_number(ranges + i + naddr + pna, nsize);
+ best_size = 0;
+ for_each_of_range(&parser, &range) {
+ if (!range.cpu_addr)
+ continue;
- if (cpu_addr == 0 && size > best_size) {
- best = i;
- best_size = size;
+ if (range.size > best_size) {
+ best_size = range.size;
+ dev_addr = range.bus_addr;
}
}
- if (best >= 0) {
- dev_addr = of_read_number(ranges + best, naddr);
- } else
+ if (!best_size)
dev_dbg(dev, "iommu: no suitable range found!\n");
out:
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index 30394c6f8894..0e8f20ecca08 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -35,7 +35,7 @@
#include <asm/firmware.h>
#include <asm/rtas.h>
#include <asm/cputhreads.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include "interrupt.h"
#include <asm/udbg.h>
@@ -54,6 +54,7 @@ static cpumask_t of_spin_map;
/**
* smp_startup_cpu() - start the given cpu
+ * @lcpu: Logical CPU ID of the CPU to be started.
*
* At boot time, there is nothing to do for primary threads which were
* started from Open Firmware. For anything else, call RTAS with the
diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c
index 87ad7d563cfa..000894e07b02 100644
--- a/arch/powerpc/platforms/cell/spu_syscalls.c
+++ b/arch/powerpc/platforms/cell/spu_syscalls.c
@@ -36,6 +36,9 @@ static inline struct spufs_calls *spufs_calls_get(void)
static inline void spufs_calls_put(struct spufs_calls *calls)
{
+ if (!calls)
+ return;
+
BUG_ON(calls != spufs_calls);
/* we don't need to rcu this, as we hold a reference to the module */
@@ -53,82 +56,55 @@ static inline void spufs_calls_put(struct spufs_calls *calls) { }
#endif /* CONFIG_SPU_FS_MODULE */
+DEFINE_CLASS(spufs_calls, struct spufs_calls *, spufs_calls_put(_T), spufs_calls_get(), void)
+
SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags,
umode_t, mode, int, neighbor_fd)
{
- long ret;
- struct spufs_calls *calls;
-
- calls = spufs_calls_get();
+ CLASS(spufs_calls, calls)();
if (!calls)
return -ENOSYS;
if (flags & SPU_CREATE_AFFINITY_SPU) {
- struct fd neighbor = fdget(neighbor_fd);
- ret = -EBADF;
- if (neighbor.file) {
- ret = calls->create_thread(name, flags, mode, neighbor.file);
- fdput(neighbor);
- }
- } else
- ret = calls->create_thread(name, flags, mode, NULL);
-
- spufs_calls_put(calls);
- return ret;
+ CLASS(fd, neighbor)(neighbor_fd);
+ if (fd_empty(neighbor))
+ return -EBADF;
+ return calls->create_thread(name, flags, mode, fd_file(neighbor));
+ } else {
+ return calls->create_thread(name, flags, mode, NULL);
+ }
}
SYSCALL_DEFINE3(spu_run,int, fd, __u32 __user *, unpc, __u32 __user *, ustatus)
{
- long ret;
- struct fd arg;
- struct spufs_calls *calls;
-
- calls = spufs_calls_get();
+ CLASS(spufs_calls, calls)();
if (!calls)
return -ENOSYS;
- ret = -EBADF;
- arg = fdget(fd);
- if (arg.file) {
- ret = calls->spu_run(arg.file, unpc, ustatus);
- fdput(arg);
- }
+ CLASS(fd, arg)(fd);
+ if (fd_empty(arg))
+ return -EBADF;
- spufs_calls_put(calls);
- return ret;
+ return calls->spu_run(fd_file(arg), unpc, ustatus);
}
#ifdef CONFIG_COREDUMP
int elf_coredump_extra_notes_size(void)
{
- struct spufs_calls *calls;
- int ret;
-
- calls = spufs_calls_get();
+ CLASS(spufs_calls, calls)();
if (!calls)
return 0;
- ret = calls->coredump_extra_notes_size();
-
- spufs_calls_put(calls);
-
- return ret;
+ return calls->coredump_extra_notes_size();
}
int elf_coredump_extra_notes_write(struct coredump_params *cprm)
{
- struct spufs_calls *calls;
- int ret;
-
- calls = spufs_calls_get();
+ CLASS(spufs_calls, calls)();
if (!calls)
return 0;
- ret = calls->coredump_extra_notes_write(cprm);
-
- spufs_calls_put(calls);
-
- return ret;
+ return calls->coredump_extra_notes_write(cprm);
}
#endif
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 18daafbe2e65..301ee7d8b7df 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -73,9 +73,7 @@ static struct spu_context *coredump_next_context(int *fd)
return NULL;
*fd = n - 1;
- rcu_read_lock();
- file = lookup_fdget_rcu(*fd);
- rcu_read_unlock();
+ file = fget_raw(*fd);
if (file) {
ctx = SPUFS_I(file_inode(file))->i_ctx;
get_spu_context(ctx);
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 02a8158c469d..d5a2c77bc908 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -453,7 +453,6 @@ static const struct file_operations spufs_cntl_fops = {
.release = spufs_cntl_release,
.read = simple_attr_read,
.write = simple_attr_write,
- .llseek = no_llseek,
.mmap = spufs_cntl_mmap,
};
@@ -634,7 +633,6 @@ static ssize_t spufs_mbox_read(struct file *file, char __user *buf,
static const struct file_operations spufs_mbox_fops = {
.open = spufs_pipe_open,
.read = spufs_mbox_read,
- .llseek = no_llseek,
};
static ssize_t spufs_mbox_stat_read(struct file *file, char __user *buf,
@@ -664,7 +662,6 @@ static ssize_t spufs_mbox_stat_read(struct file *file, char __user *buf,
static const struct file_operations spufs_mbox_stat_fops = {
.open = spufs_pipe_open,
.read = spufs_mbox_stat_read,
- .llseek = no_llseek,
};
/* low-level ibox access function */
@@ -769,7 +766,6 @@ static const struct file_operations spufs_ibox_fops = {
.open = spufs_pipe_open,
.read = spufs_ibox_read,
.poll = spufs_ibox_poll,
- .llseek = no_llseek,
};
static ssize_t spufs_ibox_stat_read(struct file *file, char __user *buf,
@@ -797,7 +793,6 @@ static ssize_t spufs_ibox_stat_read(struct file *file, char __user *buf,
static const struct file_operations spufs_ibox_stat_fops = {
.open = spufs_pipe_open,
.read = spufs_ibox_stat_read,
- .llseek = no_llseek,
};
/* low-level mailbox write */
@@ -901,7 +896,6 @@ static const struct file_operations spufs_wbox_fops = {
.open = spufs_pipe_open,
.write = spufs_wbox_write,
.poll = spufs_wbox_poll,
- .llseek = no_llseek,
};
static ssize_t spufs_wbox_stat_read(struct file *file, char __user *buf,
@@ -929,7 +923,6 @@ static ssize_t spufs_wbox_stat_read(struct file *file, char __user *buf,
static const struct file_operations spufs_wbox_stat_fops = {
.open = spufs_pipe_open,
.read = spufs_wbox_stat_read,
- .llseek = no_llseek,
};
static int spufs_signal1_open(struct inode *inode, struct file *file)
@@ -1056,7 +1049,6 @@ static const struct file_operations spufs_signal1_fops = {
.read = spufs_signal1_read,
.write = spufs_signal1_write,
.mmap = spufs_signal1_mmap,
- .llseek = no_llseek,
};
static const struct file_operations spufs_signal1_nosched_fops = {
@@ -1064,7 +1056,6 @@ static const struct file_operations spufs_signal1_nosched_fops = {
.release = spufs_signal1_release,
.write = spufs_signal1_write,
.mmap = spufs_signal1_mmap,
- .llseek = no_llseek,
};
static int spufs_signal2_open(struct inode *inode, struct file *file)
@@ -1195,7 +1186,6 @@ static const struct file_operations spufs_signal2_fops = {
.read = spufs_signal2_read,
.write = spufs_signal2_write,
.mmap = spufs_signal2_mmap,
- .llseek = no_llseek,
};
static const struct file_operations spufs_signal2_nosched_fops = {
@@ -1203,7 +1193,6 @@ static const struct file_operations spufs_signal2_nosched_fops = {
.release = spufs_signal2_release,
.write = spufs_signal2_write,
.mmap = spufs_signal2_mmap,
- .llseek = no_llseek,
};
/*
@@ -1343,7 +1332,6 @@ static const struct file_operations spufs_mss_fops = {
.open = spufs_mss_open,
.release = spufs_mss_release,
.mmap = spufs_mss_mmap,
- .llseek = no_llseek,
};
static vm_fault_t
@@ -1401,7 +1389,6 @@ static const struct file_operations spufs_psmap_fops = {
.open = spufs_psmap_open,
.release = spufs_psmap_release,
.mmap = spufs_psmap_mmap,
- .llseek = no_llseek,
};
@@ -1704,23 +1691,11 @@ static int spufs_mfc_flush(struct file *file, fl_owner_t id)
ret = spu_acquire(ctx);
if (ret)
- goto out;
-#if 0
-/* this currently hangs */
- ret = spufs_wait(ctx->mfc_wq,
- ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2));
- if (ret)
- goto out;
- ret = spufs_wait(ctx->mfc_wq,
- ctx->ops->read_mfc_tagstatus(ctx) == ctx->tagwait);
- if (ret)
- goto out;
-#else
- ret = 0;
-#endif
+ return ret;
+
spu_release(ctx);
-out:
- return ret;
+
+ return 0;
}
static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int datasync)
@@ -1744,7 +1719,6 @@ static const struct file_operations spufs_mfc_fops = {
.flush = spufs_mfc_flush,
.fsync = spufs_mfc_fsync,
.mmap = spufs_mfc_mmap,
- .llseek = no_llseek,
};
static int spufs_npc_set(void *data, u64 val)
@@ -2114,7 +2088,6 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
static const struct file_operations spufs_dma_info_fops = {
.open = spufs_info_open,
.read = spufs_dma_info_read,
- .llseek = no_llseek,
};
static void spufs_get_proxydma_info(struct spu_context *ctx,
@@ -2171,7 +2144,6 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf,
static const struct file_operations spufs_proxydma_info_fops = {
.open = spufs_info_open,
.read = spufs_proxydma_info_read,
- .llseek = no_llseek,
};
static int spufs_show_tid(struct seq_file *s, void *private)
@@ -2454,7 +2426,6 @@ static const struct file_operations spufs_switch_log_fops = {
.read = spufs_switch_log_read,
.poll = spufs_switch_log_poll,
.release = spufs_switch_log_release,
- .llseek = no_llseek,
};
/**
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 030de2b8c145..70236d1df3d3 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -822,6 +822,7 @@ static void __exit spufs_exit(void)
}
module_exit(spufs_exit);
+MODULE_DESCRIPTION("SPU file system");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnd Bergmann <arndb@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 99bd027a7f7c..610ca8570682 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -868,7 +868,7 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio)
}
/**
- * spu_deactivate - unbind a context from it's physical spu
+ * spu_deactivate - unbind a context from its physical spu
* @ctx: spu context to unbind
*
* Unbind @ctx from the physical spu it is running on and schedule
diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c
index 0eedae96498c..d3bf56a46656 100644
--- a/arch/powerpc/platforms/chrp/nvram.c
+++ b/arch/powerpc/platforms/chrp/nvram.c
@@ -92,4 +92,5 @@ void __init chrp_nvram_init(void)
return;
}
+MODULE_DESCRIPTION("PPC NVRAM device driver");
MODULE_LICENSE("GPL v2");
diff --git a/arch/powerpc/platforms/chrp/pegasos_eth.c b/arch/powerpc/platforms/chrp/pegasos_eth.c
index 5c4f1a9ca154..6f4a41a9352a 100644
--- a/arch/powerpc/platforms/chrp/pegasos_eth.c
+++ b/arch/powerpc/platforms/chrp/pegasos_eth.c
@@ -14,7 +14,7 @@
#include <linux/ioport.h>
#include <linux/device.h>
#include <linux/platform_device.h>
-#include <linux/mv643xx.h>
+#include <linux/mv643xx_eth.h>
#include <linux/pci.h>
#define PEGASOS2_MARVELL_REGBASE (0xf1000000)
@@ -25,12 +25,15 @@
#define PEGASOS2_SRAM_BASE_ETH_PORT0 (PEGASOS2_SRAM_BASE)
#define PEGASOS2_SRAM_BASE_ETH_PORT1 (PEGASOS2_SRAM_BASE_ETH_PORT0 + (PEGASOS2_SRAM_SIZE / 2) )
-
#define PEGASOS2_SRAM_RXRING_SIZE (PEGASOS2_SRAM_SIZE/4)
#define PEGASOS2_SRAM_TXRING_SIZE (PEGASOS2_SRAM_SIZE/4)
#undef BE_VERBOSE
+#define MV64340_BASE_ADDR_ENABLE 0x278
+#define MV64340_INTEGRATED_SRAM_BASE_ADDR 0x268
+#define MV64340_SRAM_CONFIG 0x380
+
static struct resource mv643xx_eth_shared_resources[] = {
[0] = {
.name = "ethernet shared base",
diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c
index 9c10aac40c7b..4012f206ec63 100644
--- a/arch/powerpc/platforms/embedded6xx/linkstation.c
+++ b/arch/powerpc/platforms/embedded6xx/linkstation.c
@@ -13,6 +13,7 @@
#include <linux/kernel.h>
#include <linux/initrd.h>
#include <linux/of_platform.h>
+#include <linux/seq_file.h>
#include <asm/time.h>
#include <asm/mpic.h>
@@ -99,9 +100,6 @@ static void __init linkstation_init_IRQ(void)
mpic_init(mpic);
}
-extern void avr_uart_configure(void);
-extern void avr_uart_send(const char);
-
static void __noreturn linkstation_restart(char *cmd)
{
local_irq_disable();
diff --git a/arch/powerpc/platforms/embedded6xx/mpc10x.h b/arch/powerpc/platforms/embedded6xx/mpc10x.h
index 5ad12023e562..ebc258fa4858 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc10x.h
+++ b/arch/powerpc/platforms/embedded6xx/mpc10x.h
@@ -156,4 +156,7 @@ int mpc10x_disable_store_gathering(struct pci_controller *hose);
/* For MPC107 boards that use the built-in openpic */
void mpc10x_set_openpic(void);
+void avr_uart_configure(void);
+void avr_uart_send(const char c);
+
#endif /* __PPC_KERNEL_MPC10X_H */
diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c
index 00bec0f051be..5ca41972ef22 100644
--- a/arch/powerpc/platforms/embedded6xx/mvme5100.c
+++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c
@@ -14,6 +14,7 @@
#include <linux/of_irq.h>
#include <linux/of_platform.h>
+#include <linux/seq_file.h>
#include <asm/i8259.h>
#include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/maple/Kconfig b/arch/powerpc/platforms/maple/Kconfig
deleted file mode 100644
index 4c058cc57c90..000000000000
--- a/arch/powerpc/platforms/maple/Kconfig
+++ /dev/null
@@ -1,19 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config PPC_MAPLE
- depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN
- bool "Maple 970FX Evaluation Board"
- select FORCE_PCI
- select MPIC
- select U3_DART
- select MPIC_U3_HT_IRQS
- select GENERIC_TBSYNC
- select PPC_UDBG_16550
- select PPC_970_NAP
- select PPC_64S_HASH_MMU
- select PPC_HASH_MMU_NATIVE
- select PPC_RTAS
- select MMIO_NVRAM
- select ATA_NONSTANDARD if ATA
- help
- This option enables support for the Maple 970FX Evaluation Board.
- For more information, refer to <http://www.970eval.com>
diff --git a/arch/powerpc/platforms/maple/maple.h b/arch/powerpc/platforms/maple/maple.h
deleted file mode 100644
index 4f358b55c341..000000000000
--- a/arch/powerpc/platforms/maple/maple.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Declarations for maple-specific code.
- *
- * Maple is the name of a PPC970 evaluation board.
- */
-extern int maple_set_rtc_time(struct rtc_time *tm);
-extern void maple_get_rtc_time(struct rtc_time *tm);
-extern time64_t maple_get_boot_time(void);
-extern void maple_calibrate_decr(void);
-extern void maple_pci_init(void);
-extern void maple_pci_irq_fixup(struct pci_dev *dev);
-extern int maple_pci_get_legacy_ide_irq(struct pci_dev *dev, int channel);
-
-extern struct pci_controller_ops maple_pci_controller_ops;
diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
deleted file mode 100644
index b911b31717cc..000000000000
--- a/arch/powerpc/platforms/maple/pci.c
+++ /dev/null
@@ -1,672 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org),
- * IBM Corp.
- */
-
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/string.h>
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/of_irq.h>
-
-#include <asm/sections.h>
-#include <asm/io.h>
-#include <asm/pci-bridge.h>
-#include <asm/machdep.h>
-#include <asm/iommu.h>
-#include <asm/ppc-pci.h>
-#include <asm/isa-bridge.h>
-
-#include "maple.h"
-
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
-static struct pci_controller *u3_agp, *u3_ht, *u4_pcie;
-
-static int __init fixup_one_level_bus_range(struct device_node *node, int higher)
-{
- for (; node; node = node->sibling) {
- const int *bus_range;
- const unsigned int *class_code;
- int len;
-
- /* For PCI<->PCI bridges or CardBus bridges, we go down */
- class_code = of_get_property(node, "class-code", NULL);
- if (!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI &&
- (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS))
- continue;
- bus_range = of_get_property(node, "bus-range", &len);
- if (bus_range != NULL && len > 2 * sizeof(int)) {
- if (bus_range[1] > higher)
- higher = bus_range[1];
- }
- higher = fixup_one_level_bus_range(node->child, higher);
- }
- return higher;
-}
-
-/* This routine fixes the "bus-range" property of all bridges in the
- * system since they tend to have their "last" member wrong on macs
- *
- * Note that the bus numbers manipulated here are OF bus numbers, they
- * are not Linux bus numbers.
- */
-static void __init fixup_bus_range(struct device_node *bridge)
-{
- int *bus_range;
- struct property *prop;
- int len;
-
- /* Lookup the "bus-range" property for the hose */
- prop = of_find_property(bridge, "bus-range", &len);
- if (prop == NULL || prop->value == NULL || len < 2 * sizeof(int)) {
- printk(KERN_WARNING "Can't get bus-range for %pOF\n",
- bridge);
- return;
- }
- bus_range = prop->value;
- bus_range[1] = fixup_one_level_bus_range(bridge->child, bus_range[1]);
-}
-
-
-static unsigned long u3_agp_cfa0(u8 devfn, u8 off)
-{
- return (1 << (unsigned long)PCI_SLOT(devfn)) |
- ((unsigned long)PCI_FUNC(devfn) << 8) |
- ((unsigned long)off & 0xFCUL);
-}
-
-static unsigned long u3_agp_cfa1(u8 bus, u8 devfn, u8 off)
-{
- return ((unsigned long)bus << 16) |
- ((unsigned long)devfn << 8) |
- ((unsigned long)off & 0xFCUL) |
- 1UL;
-}
-
-static volatile void __iomem *u3_agp_cfg_access(struct pci_controller* hose,
- u8 bus, u8 dev_fn, u8 offset)
-{
- unsigned int caddr;
-
- if (bus == hose->first_busno) {
- if (dev_fn < (11 << 3))
- return NULL;
- caddr = u3_agp_cfa0(dev_fn, offset);
- } else
- caddr = u3_agp_cfa1(bus, dev_fn, offset);
-
- /* Uninorth will return garbage if we don't read back the value ! */
- do {
- out_le32(hose->cfg_addr, caddr);
- } while (in_le32(hose->cfg_addr) != caddr);
-
- offset &= 0x07;
- return hose->cfg_data + offset;
-}
-
-static int u3_agp_read_config(struct pci_bus *bus, unsigned int devfn,
- int offset, int len, u32 *val)
-{
- struct pci_controller *hose;
- volatile void __iomem *addr;
-
- hose = pci_bus_to_host(bus);
- if (hose == NULL)
- return PCIBIOS_DEVICE_NOT_FOUND;
-
- addr = u3_agp_cfg_access(hose, bus->number, devfn, offset);
- if (!addr)
- return PCIBIOS_DEVICE_NOT_FOUND;
- /*
- * Note: the caller has already checked that offset is
- * suitably aligned and that len is 1, 2 or 4.
- */
- switch (len) {
- case 1:
- *val = in_8(addr);
- break;
- case 2:
- *val = in_le16(addr);
- break;
- default:
- *val = in_le32(addr);
- break;
- }
- return PCIBIOS_SUCCESSFUL;
-}
-
-static int u3_agp_write_config(struct pci_bus *bus, unsigned int devfn,
- int offset, int len, u32 val)
-{
- struct pci_controller *hose;
- volatile void __iomem *addr;
-
- hose = pci_bus_to_host(bus);
- if (hose == NULL)
- return PCIBIOS_DEVICE_NOT_FOUND;
-
- addr = u3_agp_cfg_access(hose, bus->number, devfn, offset);
- if (!addr)
- return PCIBIOS_DEVICE_NOT_FOUND;
- /*
- * Note: the caller has already checked that offset is
- * suitably aligned and that len is 1, 2 or 4.
- */
- switch (len) {
- case 1:
- out_8(addr, val);
- break;
- case 2:
- out_le16(addr, val);
- break;
- default:
- out_le32(addr, val);
- break;
- }
- return PCIBIOS_SUCCESSFUL;
-}
-
-static struct pci_ops u3_agp_pci_ops =
-{
- .read = u3_agp_read_config,
- .write = u3_agp_write_config,
-};
-
-static unsigned long u3_ht_cfa0(u8 devfn, u8 off)
-{
- return (devfn << 8) | off;
-}
-
-static unsigned long u3_ht_cfa1(u8 bus, u8 devfn, u8 off)
-{
- return u3_ht_cfa0(devfn, off) + (bus << 16) + 0x01000000UL;
-}
-
-static volatile void __iomem *u3_ht_cfg_access(struct pci_controller* hose,
- u8 bus, u8 devfn, u8 offset)
-{
- if (bus == hose->first_busno) {
- if (PCI_SLOT(devfn) == 0)
- return NULL;
- return hose->cfg_data + u3_ht_cfa0(devfn, offset);
- } else
- return hose->cfg_data + u3_ht_cfa1(bus, devfn, offset);
-}
-
-static int u3_ht_root_read_config(struct pci_controller *hose, u8 offset,
- int len, u32 *val)
-{
- volatile void __iomem *addr;
-
- addr = hose->cfg_addr;
- addr += ((offset & ~3) << 2) + (4 - len - (offset & 3));
-
- switch (len) {
- case 1:
- *val = in_8(addr);
- break;
- case 2:
- *val = in_be16(addr);
- break;
- default:
- *val = in_be32(addr);
- break;
- }
-
- return PCIBIOS_SUCCESSFUL;
-}
-
-static int u3_ht_root_write_config(struct pci_controller *hose, u8 offset,
- int len, u32 val)
-{
- volatile void __iomem *addr;
-
- addr = hose->cfg_addr + ((offset & ~3) << 2) + (4 - len - (offset & 3));
-
- if (offset >= PCI_BASE_ADDRESS_0 && offset < PCI_CAPABILITY_LIST)
- return PCIBIOS_SUCCESSFUL;
-
- switch (len) {
- case 1:
- out_8(addr, val);
- break;
- case 2:
- out_be16(addr, val);
- break;
- default:
- out_be32(addr, val);
- break;
- }
-
- return PCIBIOS_SUCCESSFUL;
-}
-
-static int u3_ht_read_config(struct pci_bus *bus, unsigned int devfn,
- int offset, int len, u32 *val)
-{
- struct pci_controller *hose;
- volatile void __iomem *addr;
-
- hose = pci_bus_to_host(bus);
- if (hose == NULL)
- return PCIBIOS_DEVICE_NOT_FOUND;
-
- if (bus->number == hose->first_busno && devfn == PCI_DEVFN(0, 0))
- return u3_ht_root_read_config(hose, offset, len, val);
-
- if (offset > 0xff)
- return PCIBIOS_BAD_REGISTER_NUMBER;
-
- addr = u3_ht_cfg_access(hose, bus->number, devfn, offset);
- if (!addr)
- return PCIBIOS_DEVICE_NOT_FOUND;
-
- /*
- * Note: the caller has already checked that offset is
- * suitably aligned and that len is 1, 2 or 4.
- */
- switch (len) {
- case 1:
- *val = in_8(addr);
- break;
- case 2:
- *val = in_le16(addr);
- break;
- default:
- *val = in_le32(addr);
- break;
- }
- return PCIBIOS_SUCCESSFUL;
-}
-
-static int u3_ht_write_config(struct pci_bus *bus, unsigned int devfn,
- int offset, int len, u32 val)
-{
- struct pci_controller *hose;
- volatile void __iomem *addr;
-
- hose = pci_bus_to_host(bus);
- if (hose == NULL)
- return PCIBIOS_DEVICE_NOT_FOUND;
-
- if (bus->number == hose->first_busno && devfn == PCI_DEVFN(0, 0))
- return u3_ht_root_write_config(hose, offset, len, val);
-
- if (offset > 0xff)
- return PCIBIOS_BAD_REGISTER_NUMBER;
-
- addr = u3_ht_cfg_access(hose, bus->number, devfn, offset);
- if (!addr)
- return PCIBIOS_DEVICE_NOT_FOUND;
- /*
- * Note: the caller has already checked that offset is
- * suitably aligned and that len is 1, 2 or 4.
- */
- switch (len) {
- case 1:
- out_8(addr, val);
- break;
- case 2:
- out_le16(addr, val);
- break;
- default:
- out_le32(addr, val);
- break;
- }
- return PCIBIOS_SUCCESSFUL;
-}
-
-static struct pci_ops u3_ht_pci_ops =
-{
- .read = u3_ht_read_config,
- .write = u3_ht_write_config,
-};
-
-static unsigned int u4_pcie_cfa0(unsigned int devfn, unsigned int off)
-{
- return (1 << PCI_SLOT(devfn)) |
- (PCI_FUNC(devfn) << 8) |
- ((off >> 8) << 28) |
- (off & 0xfcu);
-}
-
-static unsigned int u4_pcie_cfa1(unsigned int bus, unsigned int devfn,
- unsigned int off)
-{
- return (bus << 16) |
- (devfn << 8) |
- ((off >> 8) << 28) |
- (off & 0xfcu) | 1u;
-}
-
-static volatile void __iomem *u4_pcie_cfg_access(struct pci_controller* hose,
- u8 bus, u8 dev_fn, int offset)
-{
- unsigned int caddr;
-
- if (bus == hose->first_busno)
- caddr = u4_pcie_cfa0(dev_fn, offset);
- else
- caddr = u4_pcie_cfa1(bus, dev_fn, offset);
-
- /* Uninorth will return garbage if we don't read back the value ! */
- do {
- out_le32(hose->cfg_addr, caddr);
- } while (in_le32(hose->cfg_addr) != caddr);
-
- offset &= 0x03;
- return hose->cfg_data + offset;
-}
-
-static int u4_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
- int offset, int len, u32 *val)
-{
- struct pci_controller *hose;
- volatile void __iomem *addr;
-
- hose = pci_bus_to_host(bus);
- if (hose == NULL)
- return PCIBIOS_DEVICE_NOT_FOUND;
- if (offset >= 0x1000)
- return PCIBIOS_BAD_REGISTER_NUMBER;
- addr = u4_pcie_cfg_access(hose, bus->number, devfn, offset);
- if (!addr)
- return PCIBIOS_DEVICE_NOT_FOUND;
- /*
- * Note: the caller has already checked that offset is
- * suitably aligned and that len is 1, 2 or 4.
- */
- switch (len) {
- case 1:
- *val = in_8(addr);
- break;
- case 2:
- *val = in_le16(addr);
- break;
- default:
- *val = in_le32(addr);
- break;
- }
- return PCIBIOS_SUCCESSFUL;
-}
-static int u4_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
- int offset, int len, u32 val)
-{
- struct pci_controller *hose;
- volatile void __iomem *addr;
-
- hose = pci_bus_to_host(bus);
- if (hose == NULL)
- return PCIBIOS_DEVICE_NOT_FOUND;
- if (offset >= 0x1000)
- return PCIBIOS_BAD_REGISTER_NUMBER;
- addr = u4_pcie_cfg_access(hose, bus->number, devfn, offset);
- if (!addr)
- return PCIBIOS_DEVICE_NOT_FOUND;
- /*
- * Note: the caller has already checked that offset is
- * suitably aligned and that len is 1, 2 or 4.
- */
- switch (len) {
- case 1:
- out_8(addr, val);
- break;
- case 2:
- out_le16(addr, val);
- break;
- default:
- out_le32(addr, val);
- break;
- }
- return PCIBIOS_SUCCESSFUL;
-}
-
-static struct pci_ops u4_pcie_pci_ops =
-{
- .read = u4_pcie_read_config,
- .write = u4_pcie_write_config,
-};
-
-static void __init setup_u3_agp(struct pci_controller* hose)
-{
- /* On G5, we move AGP up to high bus number so we don't need
- * to reassign bus numbers for HT. If we ever have P2P bridges
- * on AGP, we'll have to move pci_assign_all_buses to the
- * pci_controller structure so we enable it for AGP and not for
- * HT childs.
- * We hard code the address because of the different size of
- * the reg address cell, we shall fix that by killing struct
- * reg_property and using some accessor functions instead
- */
- hose->first_busno = 0xf0;
- hose->last_busno = 0xff;
- hose->ops = &u3_agp_pci_ops;
- hose->cfg_addr = ioremap(0xf0000000 + 0x800000, 0x1000);
- hose->cfg_data = ioremap(0xf0000000 + 0xc00000, 0x1000);
-
- u3_agp = hose;
-}
-
-static void __init setup_u4_pcie(struct pci_controller* hose)
-{
- /* We currently only implement the "non-atomic" config space, to
- * be optimised later.
- */
- hose->ops = &u4_pcie_pci_ops;
- hose->cfg_addr = ioremap(0xf0000000 + 0x800000, 0x1000);
- hose->cfg_data = ioremap(0xf0000000 + 0xc00000, 0x1000);
-
- u4_pcie = hose;
-}
-
-static void __init setup_u3_ht(struct pci_controller* hose)
-{
- hose->ops = &u3_ht_pci_ops;
-
- /* We hard code the address because of the different size of
- * the reg address cell, we shall fix that by killing struct
- * reg_property and using some accessor functions instead
- */
- hose->cfg_data = ioremap(0xf2000000, 0x02000000);
- hose->cfg_addr = ioremap(0xf8070000, 0x1000);
-
- hose->first_busno = 0;
- hose->last_busno = 0xef;
-
- u3_ht = hose;
-}
-
-static int __init maple_add_bridge(struct device_node *dev)
-{
- int len;
- struct pci_controller *hose;
- char* disp_name;
- const int *bus_range;
- int primary = 1;
-
- DBG("Adding PCI host bridge %pOF\n", dev);
-
- bus_range = of_get_property(dev, "bus-range", &len);
- if (bus_range == NULL || len < 2 * sizeof(int)) {
- printk(KERN_WARNING "Can't get bus-range for %pOF, assume bus 0\n",
- dev);
- }
-
- hose = pcibios_alloc_controller(dev);
- if (hose == NULL)
- return -ENOMEM;
- hose->first_busno = bus_range ? bus_range[0] : 0;
- hose->last_busno = bus_range ? bus_range[1] : 0xff;
- hose->controller_ops = maple_pci_controller_ops;
-
- disp_name = NULL;
- if (of_device_is_compatible(dev, "u3-agp")) {
- setup_u3_agp(hose);
- disp_name = "U3-AGP";
- primary = 0;
- } else if (of_device_is_compatible(dev, "u3-ht")) {
- setup_u3_ht(hose);
- disp_name = "U3-HT";
- primary = 1;
- } else if (of_device_is_compatible(dev, "u4-pcie")) {
- setup_u4_pcie(hose);
- disp_name = "U4-PCIE";
- primary = 0;
- }
- printk(KERN_INFO "Found %s PCI host bridge. Firmware bus number: %d->%d\n",
- disp_name, hose->first_busno, hose->last_busno);
-
- /* Interpret the "ranges" property */
- /* This also maps the I/O region and sets isa_io/mem_base */
- pci_process_bridge_OF_ranges(hose, dev, primary);
-
- /* Fixup "bus-range" OF property */
- fixup_bus_range(dev);
-
- /* Check for legacy IOs */
- isa_bridge_find_early(hose);
-
- /* create pci_dn's for DT nodes under this PHB */
- pci_devs_phb_init_dynamic(hose);
-
- return 0;
-}
-
-
-void maple_pci_irq_fixup(struct pci_dev *dev)
-{
- DBG(" -> maple_pci_irq_fixup\n");
-
- /* Fixup IRQ for PCIe host */
- if (u4_pcie != NULL && dev->bus->number == 0 &&
- pci_bus_to_host(dev->bus) == u4_pcie) {
- printk(KERN_DEBUG "Fixup U4 PCIe IRQ\n");
- dev->irq = irq_create_mapping(NULL, 1);
- if (dev->irq)
- irq_set_irq_type(dev->irq, IRQ_TYPE_LEVEL_LOW);
- }
-
- /* Hide AMD8111 IDE interrupt when in legacy mode so
- * the driver calls pci_get_legacy_ide_irq()
- */
- if (dev->vendor == PCI_VENDOR_ID_AMD &&
- dev->device == PCI_DEVICE_ID_AMD_8111_IDE &&
- (dev->class & 5) != 5) {
- dev->irq = 0;
- }
-
- DBG(" <- maple_pci_irq_fixup\n");
-}
-
-static int maple_pci_root_bridge_prepare(struct pci_host_bridge *bridge)
-{
- struct pci_controller *hose = pci_bus_to_host(bridge->bus);
- struct device_node *np, *child;
-
- if (hose != u3_agp)
- return 0;
-
- /* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
- * assume there is no P2P bridge on the AGP bus, which should be a
- * safe assumptions hopefully.
- */
- np = hose->dn;
- PCI_DN(np)->busno = 0xf0;
- for_each_child_of_node(np, child)
- PCI_DN(child)->busno = 0xf0;
-
- return 0;
-}
-
-void __init maple_pci_init(void)
-{
- struct device_node *np, *root;
- struct device_node *ht = NULL;
-
- /* Probe root PCI hosts, that is on U3 the AGP host and the
- * HyperTransport host. That one is actually "kept" around
- * and actually added last as it's resource management relies
- * on the AGP resources to have been setup first
- */
- root = of_find_node_by_path("/");
- if (root == NULL) {
- printk(KERN_CRIT "maple_find_bridges: can't find root of device tree\n");
- return;
- }
- for_each_child_of_node(root, np) {
- if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "ht"))
- continue;
- if ((of_device_is_compatible(np, "u4-pcie") ||
- of_device_is_compatible(np, "u3-agp")) &&
- maple_add_bridge(np) == 0)
- of_node_get(np);
-
- if (of_device_is_compatible(np, "u3-ht")) {
- of_node_get(np);
- ht = np;
- }
- }
- of_node_put(root);
-
- /* Now setup the HyperTransport host if we found any
- */
- if (ht && maple_add_bridge(ht) != 0)
- of_node_put(ht);
-
- ppc_md.pcibios_root_bridge_prepare = maple_pci_root_bridge_prepare;
-
- /* Tell pci.c to not change any resource allocations. */
- pci_add_flags(PCI_PROBE_ONLY);
-}
-
-int maple_pci_get_legacy_ide_irq(struct pci_dev *pdev, int channel)
-{
- struct device_node *np;
- unsigned int defirq = channel ? 15 : 14;
- unsigned int irq;
-
- if (pdev->vendor != PCI_VENDOR_ID_AMD ||
- pdev->device != PCI_DEVICE_ID_AMD_8111_IDE)
- return defirq;
-
- np = pci_device_to_OF_node(pdev);
- if (np == NULL) {
- printk("Failed to locate OF node for IDE %s\n",
- pci_name(pdev));
- return defirq;
- }
- irq = irq_of_parse_and_map(np, channel & 0x1);
- if (!irq) {
- printk("Failed to map onboard IDE interrupt for channel %d\n",
- channel);
- return defirq;
- }
- return irq;
-}
-
-static void quirk_ipr_msi(struct pci_dev *dev)
-{
- /* Something prevents MSIs from the IPR from working on Bimini,
- * and the driver has no smarts to recover. So disable MSI
- * on it for now. */
-
- if (machine_is(maple)) {
- dev->no_msi = 1;
- dev_info(&dev->dev, "Quirk disabled MSI\n");
- }
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_OBSIDIAN,
- quirk_ipr_msi);
-
-struct pci_controller_ops maple_pci_controller_ops = {
-};
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
deleted file mode 100644
index f329a03edf4a..000000000000
--- a/arch/powerpc/platforms/maple/setup.c
+++ /dev/null
@@ -1,363 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Maple (970 eval board) setup code
- *
- * (c) Copyright 2004 Benjamin Herrenschmidt (benh@kernel.crashing.org),
- * IBM Corp.
- */
-
-#undef DEBUG
-
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/tty.h>
-#include <linux/string.h>
-#include <linux/delay.h>
-#include <linux/ioport.h>
-#include <linux/major.h>
-#include <linux/initrd.h>
-#include <linux/vt_kern.h>
-#include <linux/console.h>
-#include <linux/pci.h>
-#include <linux/adb.h>
-#include <linux/cuda.h>
-#include <linux/pmu.h>
-#include <linux/irq.h>
-#include <linux/seq_file.h>
-#include <linux/root_dev.h>
-#include <linux/serial.h>
-#include <linux/smp.h>
-#include <linux/bitops.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/platform_device.h>
-#include <linux/memblock.h>
-
-#include <asm/processor.h>
-#include <asm/sections.h>
-#include <asm/io.h>
-#include <asm/pci-bridge.h>
-#include <asm/iommu.h>
-#include <asm/machdep.h>
-#include <asm/dma.h>
-#include <asm/cputable.h>
-#include <asm/time.h>
-#include <asm/mpic.h>
-#include <asm/rtas.h>
-#include <asm/udbg.h>
-#include <asm/nvram.h>
-
-#include "maple.h"
-
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-static unsigned long maple_find_nvram_base(void)
-{
- struct device_node *rtcs;
- unsigned long result = 0;
-
- /* find NVRAM device */
- rtcs = of_find_compatible_node(NULL, "nvram", "AMD8111");
- if (rtcs) {
- struct resource r;
- if (of_address_to_resource(rtcs, 0, &r)) {
- printk(KERN_EMERG "Maple: Unable to translate NVRAM"
- " address\n");
- goto bail;
- }
- if (!(r.flags & IORESOURCE_IO)) {
- printk(KERN_EMERG "Maple: NVRAM address isn't PIO!\n");
- goto bail;
- }
- result = r.start;
- } else
- printk(KERN_EMERG "Maple: Unable to find NVRAM\n");
- bail:
- of_node_put(rtcs);
- return result;
-}
-
-static void __noreturn maple_restart(char *cmd)
-{
- unsigned int maple_nvram_base;
- const unsigned int *maple_nvram_offset, *maple_nvram_command;
- struct device_node *sp;
-
- maple_nvram_base = maple_find_nvram_base();
- if (maple_nvram_base == 0)
- goto fail;
-
- /* find service processor device */
- sp = of_find_node_by_name(NULL, "service-processor");
- if (!sp) {
- printk(KERN_EMERG "Maple: Unable to find Service Processor\n");
- goto fail;
- }
- maple_nvram_offset = of_get_property(sp, "restart-addr", NULL);
- maple_nvram_command = of_get_property(sp, "restart-value", NULL);
- of_node_put(sp);
-
- /* send command */
- outb_p(*maple_nvram_command, maple_nvram_base + *maple_nvram_offset);
- for (;;) ;
- fail:
- printk(KERN_EMERG "Maple: Manual Restart Required\n");
- for (;;) ;
-}
-
-static void __noreturn maple_power_off(void)
-{
- unsigned int maple_nvram_base;
- const unsigned int *maple_nvram_offset, *maple_nvram_command;
- struct device_node *sp;
-
- maple_nvram_base = maple_find_nvram_base();
- if (maple_nvram_base == 0)
- goto fail;
-
- /* find service processor device */
- sp = of_find_node_by_name(NULL, "service-processor");
- if (!sp) {
- printk(KERN_EMERG "Maple: Unable to find Service Processor\n");
- goto fail;
- }
- maple_nvram_offset = of_get_property(sp, "power-off-addr", NULL);
- maple_nvram_command = of_get_property(sp, "power-off-value", NULL);
- of_node_put(sp);
-
- /* send command */
- outb_p(*maple_nvram_command, maple_nvram_base + *maple_nvram_offset);
- for (;;) ;
- fail:
- printk(KERN_EMERG "Maple: Manual Power-Down Required\n");
- for (;;) ;
-}
-
-static void __noreturn maple_halt(void)
-{
- maple_power_off();
-}
-
-#ifdef CONFIG_SMP
-static struct smp_ops_t maple_smp_ops = {
- .probe = smp_mpic_probe,
- .message_pass = smp_mpic_message_pass,
- .kick_cpu = smp_generic_kick_cpu,
- .setup_cpu = smp_mpic_setup_cpu,
- .give_timebase = smp_generic_give_timebase,
- .take_timebase = smp_generic_take_timebase,
-};
-#endif /* CONFIG_SMP */
-
-static void __init maple_use_rtas_reboot_and_halt_if_present(void)
-{
- if (rtas_function_implemented(RTAS_FN_SYSTEM_REBOOT) &&
- rtas_function_implemented(RTAS_FN_POWER_OFF)) {
- ppc_md.restart = rtas_restart;
- pm_power_off = rtas_power_off;
- ppc_md.halt = rtas_halt;
- }
-}
-
-static void __init maple_setup_arch(void)
-{
- /* init to some ~sane value until calibrate_delay() runs */
- loops_per_jiffy = 50000000;
-
- /* Setup SMP callback */
-#ifdef CONFIG_SMP
- smp_ops = &maple_smp_ops;
-#endif
- maple_use_rtas_reboot_and_halt_if_present();
-
- printk(KERN_DEBUG "Using native/NAP idle loop\n");
-
- mmio_nvram_init();
-}
-
-/*
- * This is almost identical to pSeries and CHRP. We need to make that
- * code generic at one point, with appropriate bits in the device-tree to
- * identify the presence of an HT APIC
- */
-static void __init maple_init_IRQ(void)
-{
- struct device_node *root, *np, *mpic_node = NULL;
- const unsigned int *opprop;
- unsigned long openpic_addr = 0;
- int naddr, n, i, opplen, has_isus = 0;
- struct mpic *mpic;
- unsigned int flags = 0;
-
- /* Locate MPIC in the device-tree. Note that there is a bug
- * in Maple device-tree where the type of the controller is
- * open-pic and not interrupt-controller
- */
-
- for_each_node_by_type(np, "interrupt-controller")
- if (of_device_is_compatible(np, "open-pic")) {
- mpic_node = np;
- break;
- }
- if (mpic_node == NULL)
- for_each_node_by_type(np, "open-pic") {
- mpic_node = np;
- break;
- }
- if (mpic_node == NULL) {
- printk(KERN_ERR
- "Failed to locate the MPIC interrupt controller\n");
- return;
- }
-
- /* Find address list in /platform-open-pic */
- root = of_find_node_by_path("/");
- naddr = of_n_addr_cells(root);
- opprop = of_get_property(root, "platform-open-pic", &opplen);
- if (opprop) {
- openpic_addr = of_read_number(opprop, naddr);
- has_isus = (opplen > naddr);
- printk(KERN_DEBUG "OpenPIC addr: %lx, has ISUs: %d\n",
- openpic_addr, has_isus);
- }
-
- BUG_ON(openpic_addr == 0);
-
- /* Check for a big endian MPIC */
- if (of_property_read_bool(np, "big-endian"))
- flags |= MPIC_BIG_ENDIAN;
-
- /* XXX Maple specific bits */
- flags |= MPIC_U3_HT_IRQS;
- /* All U3/U4 are big-endian, older SLOF firmware doesn't encode this */
- flags |= MPIC_BIG_ENDIAN;
-
- /* Setup the openpic driver. More device-tree junks, we hard code no
- * ISUs for now. I'll have to revisit some stuffs with the folks doing
- * the firmware for those
- */
- mpic = mpic_alloc(mpic_node, openpic_addr, flags,
- /*has_isus ? 16 :*/ 0, 0, " MPIC ");
- BUG_ON(mpic == NULL);
-
- /* Add ISUs */
- opplen /= sizeof(u32);
- for (n = 0, i = naddr; i < opplen; i += naddr, n++) {
- unsigned long isuaddr = of_read_number(opprop + i, naddr);
- mpic_assign_isu(mpic, n, isuaddr);
- }
-
- /* All ISUs are setup, complete initialization */
- mpic_init(mpic);
- ppc_md.get_irq = mpic_get_irq;
- of_node_put(mpic_node);
- of_node_put(root);
-}
-
-static void __init maple_progress(char *s, unsigned short hex)
-{
- printk("*** %04x : %s\n", hex, s ? s : "");
-}
-
-
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init maple_probe(void)
-{
- if (!of_machine_is_compatible("Momentum,Maple") &&
- !of_machine_is_compatible("Momentum,Apache"))
- return 0;
-
- pm_power_off = maple_power_off;
-
- iommu_init_early_dart(&maple_pci_controller_ops);
-
- return 1;
-}
-
-#ifdef CONFIG_EDAC
-/*
- * Register a platform device for CPC925 memory controller on
- * all boards with U3H (CPC925) bridge.
- */
-static int __init maple_cpc925_edac_setup(void)
-{
- struct platform_device *pdev;
- struct device_node *np = NULL;
- struct resource r;
- int ret;
- volatile void __iomem *mem;
- u32 rev;
-
- np = of_find_node_by_type(NULL, "memory-controller");
- if (!np) {
- printk(KERN_ERR "%s: Unable to find memory-controller node\n",
- __func__);
- return -ENODEV;
- }
-
- ret = of_address_to_resource(np, 0, &r);
- of_node_put(np);
-
- if (ret < 0) {
- printk(KERN_ERR "%s: Unable to get memory-controller reg\n",
- __func__);
- return -ENODEV;
- }
-
- mem = ioremap(r.start, resource_size(&r));
- if (!mem) {
- printk(KERN_ERR "%s: Unable to map memory-controller memory\n",
- __func__);
- return -ENOMEM;
- }
-
- rev = __raw_readl(mem);
- iounmap(mem);
-
- if (rev < 0x34 || rev > 0x3f) { /* U3H */
- printk(KERN_ERR "%s: Non-CPC925(U3H) bridge revision: %02x\n",
- __func__, rev);
- return 0;
- }
-
- pdev = platform_device_register_simple("cpc925_edac", 0, &r, 1);
- if (IS_ERR(pdev))
- return PTR_ERR(pdev);
-
- printk(KERN_INFO "%s: CPC925 platform device created\n", __func__);
-
- return 0;
-}
-machine_device_initcall(maple, maple_cpc925_edac_setup);
-#endif
-
-define_machine(maple) {
- .name = "Maple",
- .probe = maple_probe,
- .setup_arch = maple_setup_arch,
- .discover_phbs = maple_pci_init,
- .init_IRQ = maple_init_IRQ,
- .pci_irq_fixup = maple_pci_irq_fixup,
- .pci_get_legacy_ide_irq = maple_pci_get_legacy_ide_irq,
- .restart = maple_restart,
- .halt = maple_halt,
- .get_boot_time = maple_get_boot_time,
- .set_rtc_time = maple_set_rtc_time,
- .get_rtc_time = maple_get_rtc_time,
- .progress = maple_progress,
- .power_save = power4_idle,
-};
diff --git a/arch/powerpc/platforms/maple/time.c b/arch/powerpc/platforms/maple/time.c
deleted file mode 100644
index 91606411d2e0..000000000000
--- a/arch/powerpc/platforms/maple/time.c
+++ /dev/null
@@ -1,170 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * (c) Copyright 2004 Benjamin Herrenschmidt (benh@kernel.crashing.org),
- * IBM Corp.
- */
-
-#undef DEBUG
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/time.h>
-#include <linux/adb.h>
-#include <linux/pmu.h>
-#include <linux/interrupt.h>
-#include <linux/mc146818rtc.h>
-#include <linux/bcd.h>
-#include <linux/of_address.h>
-
-#include <asm/sections.h>
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/time.h>
-
-#include "maple.h"
-
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
-static int maple_rtc_addr;
-
-static int maple_clock_read(int addr)
-{
- outb_p(addr, maple_rtc_addr);
- return inb_p(maple_rtc_addr+1);
-}
-
-static void maple_clock_write(unsigned long val, int addr)
-{
- outb_p(addr, maple_rtc_addr);
- outb_p(val, maple_rtc_addr+1);
-}
-
-void maple_get_rtc_time(struct rtc_time *tm)
-{
- do {
- tm->tm_sec = maple_clock_read(RTC_SECONDS);
- tm->tm_min = maple_clock_read(RTC_MINUTES);
- tm->tm_hour = maple_clock_read(RTC_HOURS);
- tm->tm_mday = maple_clock_read(RTC_DAY_OF_MONTH);
- tm->tm_mon = maple_clock_read(RTC_MONTH);
- tm->tm_year = maple_clock_read(RTC_YEAR);
- } while (tm->tm_sec != maple_clock_read(RTC_SECONDS));
-
- if (!(maple_clock_read(RTC_CONTROL) & RTC_DM_BINARY)
- || RTC_ALWAYS_BCD) {
- tm->tm_sec = bcd2bin(tm->tm_sec);
- tm->tm_min = bcd2bin(tm->tm_min);
- tm->tm_hour = bcd2bin(tm->tm_hour);
- tm->tm_mday = bcd2bin(tm->tm_mday);
- tm->tm_mon = bcd2bin(tm->tm_mon);
- tm->tm_year = bcd2bin(tm->tm_year);
- }
- if ((tm->tm_year + 1900) < 1970)
- tm->tm_year += 100;
-
- tm->tm_wday = -1;
-}
-
-int maple_set_rtc_time(struct rtc_time *tm)
-{
- unsigned char save_control, save_freq_select;
- int sec, min, hour, mon, mday, year;
-
- spin_lock(&rtc_lock);
-
- save_control = maple_clock_read(RTC_CONTROL); /* tell the clock it's being set */
-
- maple_clock_write((save_control|RTC_SET), RTC_CONTROL);
-
- save_freq_select = maple_clock_read(RTC_FREQ_SELECT); /* stop and reset prescaler */
-
- maple_clock_write((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
-
- sec = tm->tm_sec;
- min = tm->tm_min;
- hour = tm->tm_hour;
- mon = tm->tm_mon;
- mday = tm->tm_mday;
- year = tm->tm_year;
-
- if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
- sec = bin2bcd(sec);
- min = bin2bcd(min);
- hour = bin2bcd(hour);
- mon = bin2bcd(mon);
- mday = bin2bcd(mday);
- year = bin2bcd(year);
- }
- maple_clock_write(sec, RTC_SECONDS);
- maple_clock_write(min, RTC_MINUTES);
- maple_clock_write(hour, RTC_HOURS);
- maple_clock_write(mon, RTC_MONTH);
- maple_clock_write(mday, RTC_DAY_OF_MONTH);
- maple_clock_write(year, RTC_YEAR);
-
- /* The following flags have to be released exactly in this order,
- * otherwise the DS12887 (popular MC146818A clone with integrated
- * battery and quartz) will not reset the oscillator and will not
- * update precisely 500 ms later. You won't find this mentioned in
- * the Dallas Semiconductor data sheets, but who believes data
- * sheets anyway ... -- Markus Kuhn
- */
- maple_clock_write(save_control, RTC_CONTROL);
- maple_clock_write(save_freq_select, RTC_FREQ_SELECT);
-
- spin_unlock(&rtc_lock);
-
- return 0;
-}
-
-static struct resource rtc_iores = {
- .name = "rtc",
- .flags = IORESOURCE_IO | IORESOURCE_BUSY,
-};
-
-time64_t __init maple_get_boot_time(void)
-{
- struct rtc_time tm;
- struct device_node *rtcs;
-
- rtcs = of_find_compatible_node(NULL, "rtc", "pnpPNP,b00");
- if (rtcs) {
- struct resource r;
- if (of_address_to_resource(rtcs, 0, &r)) {
- printk(KERN_EMERG "Maple: Unable to translate RTC"
- " address\n");
- goto bail;
- }
- if (!(r.flags & IORESOURCE_IO)) {
- printk(KERN_EMERG "Maple: RTC address isn't PIO!\n");
- goto bail;
- }
- maple_rtc_addr = r.start;
- printk(KERN_INFO "Maple: Found RTC at IO 0x%x\n",
- maple_rtc_addr);
- }
- bail:
- of_node_put(rtcs);
- if (maple_rtc_addr == 0) {
- maple_rtc_addr = RTC_PORT(0); /* legacy address */
- printk(KERN_INFO "Maple: No device node for RTC, assuming "
- "legacy address (0x%x)\n", maple_rtc_addr);
- }
-
- rtc_iores.start = maple_rtc_addr;
- rtc_iores.end = maple_rtc_addr + 7;
- request_resource(&ioport_resource, &rtc_iores);
-
- maple_get_rtc_time(&tm);
- return rtc_tm_to_time64(&tm);
-}
-
diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c
index fd130fe7a65a..e4538d471256 100644
--- a/arch/powerpc/platforms/pasemi/gpio_mdio.c
+++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c
@@ -260,7 +260,7 @@ out:
}
-static int gpio_mdio_remove(struct platform_device *dev)
+static void gpio_mdio_remove(struct platform_device *dev)
{
struct mii_bus *bus = dev_get_drvdata(&dev->dev);
@@ -271,8 +271,6 @@ static int gpio_mdio_remove(struct platform_device *dev)
kfree(bus->priv);
bus->priv = NULL;
mdiobus_free(bus);
-
- return 0;
}
static const struct of_device_id gpio_mdio_match[] =
diff --git a/arch/powerpc/platforms/pasemi/pasemi.h b/arch/powerpc/platforms/pasemi/pasemi.h
index 018c30665e1b..6f6743b8e48d 100644
--- a/arch/powerpc/platforms/pasemi/pasemi.h
+++ b/arch/powerpc/platforms/pasemi/pasemi.h
@@ -5,7 +5,6 @@
extern time64_t pas_get_boot_time(void);
extern void pas_pci_init(void);
struct pci_dev;
-extern void pas_pci_irq_fixup(struct pci_dev *dev);
extern void pas_pci_dma_dev_setup(struct pci_dev *dev);
void __iomem *__init pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset);
diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c
index f27d31414737..60f990a336c4 100644
--- a/arch/powerpc/platforms/pasemi/pci.c
+++ b/arch/powerpc/platforms/pasemi/pci.c
@@ -270,16 +270,18 @@ static int __init pas_add_bridge(struct device_node *dev)
void __init pas_pci_init(void)
{
+ struct device_node *root = of_find_node_by_path("/");
struct device_node *np;
int res;
pci_set_flags(PCI_SCAN_ALL_PCIE_DEVS);
- np = of_find_compatible_node(of_root, NULL, "pasemi,rootbus");
+ np = of_find_compatible_node(root, NULL, "pasemi,rootbus");
if (np) {
res = pas_add_bridge(np);
of_node_put(np);
}
+ of_node_put(root);
}
void __iomem *__init pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset)
diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig
index 8bdae0caf21e..84f101ec53a9 100644
--- a/arch/powerpc/platforms/powermac/Kconfig
+++ b/arch/powerpc/platforms/powermac/Kconfig
@@ -2,7 +2,7 @@
config PPC_PMAC
bool "Apple PowerMac based machines"
depends on PPC_BOOK3S && CPU_BIG_ENDIAN
- select ADB_CUDA if POWER_RESET && PPC32
+ select ADB_CUDA if POWER_RESET && ADB
select MPIC
select FORCE_PCI
select PPC_INDIRECT_PCI if PPC32
diff --git a/arch/powerpc/platforms/powermac/backlight.c b/arch/powerpc/platforms/powermac/backlight.c
index aeb79a8b3e10..79741370c40c 100644
--- a/arch/powerpc/platforms/powermac/backlight.c
+++ b/arch/powerpc/platforms/powermac/backlight.c
@@ -9,7 +9,6 @@
*/
#include <linux/kernel.h>
-#include <linux/fb.h>
#include <linux/backlight.h>
#include <linux/adb.h>
#include <linux/pmu.h>
@@ -58,43 +57,10 @@ struct backlight_device *pmac_backlight;
int pmac_has_backlight_type(const char *type)
{
struct device_node* bk_node = of_find_node_by_name(NULL, "backlight");
+ int i = of_property_match_string(bk_node, "backlight-control", type);
- if (bk_node) {
- const char *prop = of_get_property(bk_node,
- "backlight-control", NULL);
- if (prop && strncmp(prop, type, strlen(type)) == 0) {
- of_node_put(bk_node);
- return 1;
- }
- of_node_put(bk_node);
- }
-
- return 0;
-}
-
-int pmac_backlight_curve_lookup(struct fb_info *info, int value)
-{
- int level = (FB_BACKLIGHT_LEVELS - 1);
-
- if (info && info->bl_dev) {
- int i, max = 0;
-
- /* Look for biggest value */
- for (i = 0; i < FB_BACKLIGHT_LEVELS; i++)
- max = max((int)info->bl_curve[i], max);
-
- /* Look for nearest value */
- for (i = 0; i < FB_BACKLIGHT_LEVELS; i++) {
- int diff = abs(info->bl_curve[i] - value);
- if (diff < max) {
- max = diff;
- level = i;
- }
- }
-
- }
-
- return level;
+ of_node_put(bk_node);
+ return i >= 0;
}
static void pmac_backlight_key_worker(struct work_struct *work)
diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c
index 81c9fbae88b1..2cc257f75c50 100644
--- a/arch/powerpc/platforms/powermac/feature.c
+++ b/arch/powerpc/platforms/powermac/feature.c
@@ -2333,7 +2333,6 @@ static struct pmac_mb_def pmac_mb_defs[] = {
PMAC_TYPE_POWERMAC_G5, g5_features,
0,
},
-#ifdef CONFIG_PPC64
{ "PowerMac7,3", "PowerMac G5",
PMAC_TYPE_POWERMAC_G5, g5_features,
0,
@@ -2359,7 +2358,6 @@ static struct pmac_mb_def pmac_mb_defs[] = {
0,
},
#endif /* CONFIG_PPC64 */
-#endif /* CONFIG_PPC64 */
};
/*
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index fe2e0249cbc2..a112d26185a0 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -514,10 +514,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr)
printk(KERN_ERR "nvram: no address\n");
return -EINVAL;
}
- nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES);
- if (!nvram_image)
- panic("%s: Failed to allocate %u bytes\n", __func__,
- NVRAM_SIZE);
+ nvram_image = memblock_alloc_or_panic(NVRAM_SIZE, SMP_CACHE_BYTES);
nvram_data = ioremap(addr, NVRAM_SIZE*2);
nvram_naddrs = 1; /* Make sure we get the correct case */
diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c
index 085e0ad20eba..8253de737373 100644
--- a/arch/powerpc/platforms/powermac/pfunc_base.c
+++ b/arch/powerpc/platforms/powermac/pfunc_base.c
@@ -313,7 +313,7 @@ static void __init uninorth_install_pfunc(void)
/*
* Install handlers for the hwclock child if any
*/
- for (np = NULL; (np = of_get_next_child(uninorth_node, np)) != NULL;)
+ for_each_child_of_node(uninorth_node, np)
if (of_node_name_eq(np, "hw-clock")) {
unin_hwclock = np;
break;
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 7135ea1d7db6..2202bf77c7a3 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -2,7 +2,7 @@
/*
* Support for the interrupt controllers found on Power Macintosh,
* currently Apple's "Grand Central" interrupt controller in all
- * it's incarnations. OpenPIC support used on newer machines is
+ * its incarnations. OpenPIC support used on newer machines is
* in a separate file
*
* Copyright (C) 1997 Paul Mackerras (paulus@samba.org)
diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S
index d497a60003d2..822ed70cdcbf 100644
--- a/arch/powerpc/platforms/powermac/sleep.S
+++ b/arch/powerpc/platforms/powermac/sleep.S
@@ -176,7 +176,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
* memory location containing the PC to resume from
* at address 0.
* - On Core99, we must store the wakeup vector at
- * address 0x80 and eventually it's parameters
+ * address 0x80 and eventually its parameters
* at address 0x84. I've have some trouble with those
* parameters however and I no longer use them.
*/
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 15644be31990..09e7fe24fac1 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -35,7 +35,7 @@
#include <asm/ptrace.h>
#include <linux/atomic.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/irq.h>
#include <asm/page.h>
#include <asm/sections.h>
@@ -827,7 +827,7 @@ static int smp_core99_kick_cpu(int nr)
mdelay(1);
/* Restore our exception vector */
- patch_instruction(vector, ppc_inst(save_vector));
+ patch_uint(vector, save_vector);
local_irq_restore(flags);
if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu done", 0x347);
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index af3a5d37a149..db3370d1673c 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -99,7 +99,6 @@ static ssize_t pnv_eeh_ei_write(struct file *filp,
static const struct file_operations pnv_eeh_ei_fops = {
.open = simple_open,
- .llseek = no_llseek,
.write = pnv_eeh_ei_write,
};
@@ -860,7 +859,7 @@ static int pnv_eeh_bridge_reset(struct pci_dev *pdev, int option)
int64_t rc;
/* Hot reset to the bus if firmware cannot handle */
- if (!dn || !of_get_property(dn, "ibm,reset-by-firmware", NULL))
+ if (!dn || !of_property_present(dn, "ibm,reset-by-firmware"))
return __pnv_eeh_bridge_reset(pdev, option);
pr_debug("%s: FW reset PCI bus %04x:%02x with option %d\n",
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index ad41dffe4d92..d98b933e4984 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -18,7 +18,7 @@
#include <asm/opal.h>
#include <asm/cputhreads.h>
#include <asm/cpuidle.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/smp.h>
#include <asm/runlatch.h>
#include <asm/dbell.h>
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 877720c64515..4ac9808e55a4 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -88,26 +88,6 @@ static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
}
}
-static void memtrace_clear_range(unsigned long start_pfn,
- unsigned long nr_pages)
-{
- unsigned long pfn;
-
- /* As HIGHMEM does not apply, use clear_page() directly. */
- for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
- if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
- cond_resched();
- clear_page(__va(PFN_PHYS(pfn)));
- }
- /*
- * Before we go ahead and use this range as cache inhibited range
- * flush the cache.
- */
- flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn),
- (unsigned long)pfn_to_kaddr(start_pfn + nr_pages),
- FLUSH_CHUNK_SIZE);
-}
-
static u64 memtrace_alloc_node(u32 nid, u64 size)
{
const unsigned long nr_pages = PHYS_PFN(size);
@@ -119,17 +99,18 @@ static u64 memtrace_alloc_node(u32 nid, u64 size)
* by alloc_contig_pages().
*/
page = alloc_contig_pages(nr_pages, GFP_KERNEL | __GFP_THISNODE |
- __GFP_NOWARN, nid, NULL);
+ __GFP_NOWARN | __GFP_ZERO, nid, NULL);
if (!page)
return 0;
start_pfn = page_to_pfn(page);
/*
- * Clear the range while we still have a linear mapping.
- *
- * TODO: use __GFP_ZERO with alloc_contig_pages() once supported.
+ * Before we go ahead and use this range as cache inhibited range
+ * flush the cache.
*/
- memtrace_clear_range(start_pfn, nr_pages);
+ flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn),
+ (unsigned long)pfn_to_kaddr(start_pfn + nr_pages),
+ FLUSH_CHUNK_SIZE);
/*
* Set pages PageOffline(), to indicate that nobody (e.g., hibernation,
diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c
index bb7657115f1d..c9a9b759cc92 100644
--- a/arch/powerpc/platforms/powernv/opal-core.c
+++ b/arch/powerpc/platforms/powernv/opal-core.c
@@ -16,7 +16,7 @@
#include <linux/kobject.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
-#include <linux/crash_core.h>
+#include <linux/vmcore_info.h>
#include <linux/of.h>
#include <asm/page.h>
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 16c5860f1372..608e4b68c5ea 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -210,7 +210,7 @@ static struct attribute *dump_default_attrs[] = {
};
ATTRIBUTE_GROUPS(dump_default);
-static struct kobj_type dump_ktype = {
+static const struct kobj_type dump_ktype = {
.sysfs_ops = &dump_sysfs_ops,
.release = &dump_release,
.default_groups = dump_default_groups,
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 554fdd7f88b8..5db1e733143b 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -146,7 +146,7 @@ static struct attribute *elog_default_attrs[] = {
};
ATTRIBUTE_GROUPS(elog_default);
-static struct kobj_type elog_ktype = {
+static const struct kobj_type elog_ktype = {
.sysfs_ops = &elog_sysfs_ops,
.release = &elog_release,
.default_groups = elog_default_groups,
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 964f464b1b0e..c9c1dfb35464 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -513,8 +513,8 @@ out:
final_note(note_buf);
pr_debug("Updating elfcore header (%llx) with cpu notes\n",
- fdh->elfcorehdr_addr);
- fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr));
+ fadump_conf->elfcorehdr_addr);
+ fadump_update_elfcore_header((char *)fadump_conf->elfcorehdr_addr);
return 0;
}
@@ -526,12 +526,7 @@ static int __init opal_fadump_process(struct fw_dump *fadump_conf)
if (!opal_fdm_active || !fadump_conf->fadumphdr_addr)
return rc;
- /* Validate the fadump crash info header */
fdh = __va(fadump_conf->fadumphdr_addr);
- if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
- pr_err("Crash info header is not valid.\n");
- return rc;
- }
#ifdef CONFIG_OPAL_CORE
/*
@@ -545,18 +540,7 @@ static int __init opal_fadump_process(struct fw_dump *fadump_conf)
kernel_initiated = true;
#endif
- rc = opal_fadump_build_cpu_notes(fadump_conf, fdh);
- if (rc)
- return rc;
-
- /*
- * We are done validating dump info and elfcore header is now ready
- * to be exported. set elfcorehdr_addr so that vmcore module will
- * export the elfcore header through '/proc/vmcore'.
- */
- elfcorehdr_addr = fdh->elfcorehdr_addr;
-
- return rc;
+ return opal_fadump_build_cpu_notes(fadump_conf, fdh);
}
static void opal_fadump_region_show(struct fw_dump *fadump_conf,
@@ -615,6 +599,12 @@ static void opal_fadump_trigger(struct fadump_crash_info_header *fdh,
pr_emerg("No backend support for MPIPL!\n");
}
+/* FADUMP_MAX_MEM_REGS or lower */
+static int opal_fadump_max_boot_mem_rgns(void)
+{
+ return FADUMP_MAX_MEM_REGS;
+}
+
static struct fadump_ops opal_fadump_ops = {
.fadump_init_mem_struct = opal_fadump_init_mem_struct,
.fadump_get_metadata_size = opal_fadump_get_metadata_size,
@@ -627,6 +617,7 @@ static struct fadump_ops opal_fadump_ops = {
.fadump_process = opal_fadump_process,
.fadump_region_show = opal_fadump_region_show,
.fadump_trigger = opal_fadump_trigger,
+ .fadump_max_boot_mem_rgns = opal_fadump_max_boot_mem_rgns,
};
void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
@@ -674,8 +665,10 @@ void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
}
}
- fadump_conf->ops = &opal_fadump_ops;
- fadump_conf->fadump_supported = 1;
+ fadump_conf->ops = &opal_fadump_ops;
+ fadump_conf->fadump_supported = 1;
+ /* TODO: Add support to pass additional parameters */
+ fadump_conf->param_area_supported = 0;
/*
* Firmware supports 32-bit field for size. Align it to PAGE_SIZE
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index 56a1f7ce78d2..d92759c21fae 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -282,6 +282,7 @@ int __init opal_event_init(void)
name, NULL);
if (rc) {
pr_warn("Error %d requesting OPAL irq %d\n", rc, (int)r->start);
+ kfree(name);
continue;
}
}
diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c
index 6c3bc4b4da98..bb4218fa796e 100644
--- a/arch/powerpc/platforms/powernv/opal-kmsg.c
+++ b/arch/powerpc/platforms/powernv/opal-kmsg.c
@@ -20,13 +20,13 @@
* message, it just ensures that OPAL completely flushes the console buffer.
*/
static void kmsg_dump_opal_console_flush(struct kmsg_dumper *dumper,
- enum kmsg_dump_reason reason)
+ struct kmsg_dump_detail *detail)
{
/*
* Outside of a panic context the pollers will continue to run,
* so we don't need to do any special flushing.
*/
- if (reason != KMSG_DUMP_PANIC)
+ if (detail->reason != KMSG_DUMP_PANIC)
return;
opal_flush_console(0);
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index a16f07cdab26..8a7f39e106bd 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -393,7 +393,7 @@ void __init opal_lpc_init(void)
for_each_compatible_node(np, NULL, "ibm,power8-lpc") {
if (!of_device_is_available(np))
continue;
- if (!of_get_property(np, "primary", NULL))
+ if (!of_property_present(np, "primary"))
continue;
opal_lpc_chip_id = of_get_ibm_chip_id(np);
of_node_put(np);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index b66b06efcef1..dc246ed4b7b4 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -425,12 +425,11 @@ static int opal_prd_probe(struct platform_device *pdev)
return 0;
}
-static int opal_prd_remove(struct platform_device *pdev)
+static void opal_prd_remove(struct platform_device *pdev)
{
misc_deregister(&opal_prd_dev);
opal_message_notifier_unregister(OPAL_MSG_PRD, &opal_prd_event_nb);
opal_message_notifier_unregister(OPAL_MSG_PRD2, &opal_prd_event_nb2);
- return 0;
}
static const struct of_device_id opal_prd_match[] = {
@@ -444,7 +443,7 @@ static struct platform_driver opal_prd_driver = {
.of_match_table = opal_prd_match,
},
.probe = opal_prd_probe,
- .remove = opal_prd_remove,
+ .remove = opal_prd_remove,
};
module_platform_driver(opal_prd_driver);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 45dd77e3ccf6..9ec265fcaff4 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -180,10 +180,7 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node,
/*
* Allocate a buffer to hold the MC recoverable ranges.
*/
- mc_recoverable_range = memblock_alloc(size, __alignof__(u64));
- if (!mc_recoverable_range)
- panic("%s: Failed to allocate %u bytes align=0x%lx\n",
- __func__, size, __alignof__(u64));
+ mc_recoverable_range = memblock_alloc_or_panic(size, __alignof__(u64));
for (i = 0; i < mc_recoverable_range_len; i++) {
mc_recoverable_range[i].start_addr =
@@ -792,14 +789,6 @@ static int __init opal_sysfs_init(void)
return 0;
}
-static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
- struct bin_attribute *bin_attr, char *buf,
- loff_t off, size_t count)
-{
- return memory_read_from_buffer(buf, count, &off, bin_attr->private,
- bin_attr->size);
-}
-
static int opal_add_one_export(struct kobject *parent, const char *export_name,
struct device_node *np, const char *prop_name)
{
@@ -826,7 +815,7 @@ static int opal_add_one_export(struct kobject *parent, const char *export_name,
sysfs_bin_attr_init(attr);
attr->attr.name = name;
attr->attr.mode = 0400;
- attr->read = export_attr_read;
+ attr->read_new = sysfs_bin_attr_simple_read;
attr->private = __va(vals[0]);
attr->size = vals[1];
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 23f5b5093ec1..b0a14e48175c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1537,7 +1537,8 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
}
}
-static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
+static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group,
+ struct device *dev __maybe_unused)
{
struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
table_group);
@@ -1562,7 +1563,8 @@ static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
return 0;
}
-static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
+static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group,
+ struct device *dev __maybe_unused)
{
struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
table_group);
diff --git a/arch/powerpc/platforms/powernv/pci-sriov.c b/arch/powerpc/platforms/powernv/pci-sriov.c
index 59882da3e742..cc7b1dd54ac6 100644
--- a/arch/powerpc/platforms/powernv/pci-sriov.c
+++ b/arch/powerpc/platforms/powernv/pci-sriov.c
@@ -238,7 +238,7 @@ void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev)
} else if (pdev->is_physfn) {
/*
* For PFs adjust their allocated IOV resources to match what
- * the PHB can support using it's M64 BAR table.
+ * the PHB can support using its M64 BAR table.
*/
pnv_pci_ioda_fixup_iov_resources(pdev);
}
@@ -658,7 +658,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
list_add_tail(&pe->list, &phb->ioda.pe_list);
mutex_unlock(&phb->ioda.pe_list_mutex);
- /* associate this pe to it's pdn */
+ /* associate this pe to its pdn */
list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) {
if (vf_pdn->busno == vf_bus &&
vf_pdn->devfn == vf_devfn) {
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 957f2b47a3c0..93fba1f8661f 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -274,7 +274,6 @@ int pnv_pci_cfg_write(struct pci_dn *pdn,
int where, int size, u32 val);
extern struct iommu_table *pnv_pci_table_alloc(int nid);
-extern void pnv_pci_init_ioda_hub(struct device_node *np);
extern void pnv_pci_init_ioda2_phb(struct device_node *np);
extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 9e1a25398f98..8f41ef364fc6 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -28,7 +28,7 @@
#include <asm/xive.h>
#include <asm/opal.h>
#include <asm/runlatch.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/dbell.h>
#include <asm/kvm_ppc.h>
#include <asm/ppc-opcode.h>
@@ -36,6 +36,7 @@
#include <asm/kexec.h>
#include <asm/reg.h>
#include <asm/powernv.h>
+#include <asm/systemcfg.h>
#include "powernv.h"
@@ -136,7 +137,9 @@ static int pnv_smp_cpu_disable(void)
* the generic fixup_irqs. --BenH.
*/
set_cpu_online(cpu, false);
- vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+ systemcfg->processorCount--;
+#endif
if (cpu == boot_cpuid)
boot_cpuid = cpumask_any(cpu_online_mask);
if (xive_enabled())
@@ -434,7 +437,7 @@ void __init pnv_smp_init(void)
smp_ops = &pnv_smp_ops;
#ifdef CONFIG_HOTPLUG_CPU
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
crash_wake_offline = 1;
#endif
#endif
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index b664838008c1..5147df3a18ac 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1059,7 +1059,7 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
}
} else {
/*
- * Interrupt hanlder or fault window setup failed. Means
+ * Interrupt handler or fault window setup failed. Means
* NX can not generate fault for page fault. So not
* opening for user space tx window.
*/
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index e9c1087dd42e..706194e5f0b4 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -67,6 +67,7 @@ config PS3_VUART
config PS3_PS3AV
depends on PPC_PS3
tristate "PS3 AV settings driver" if PS3_ADVANCED
+ select VIDEO
select PS3_VUART
default y
help
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index 878bc160246e..61722133eb2d 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -178,7 +178,7 @@ fail_malloc:
return result;
}
-static int __ref ps3_setup_uhc_device(
+static int __init ps3_setup_uhc_device(
const struct ps3_repository_device *repo, enum ps3_match_id match_id,
enum ps3_interrupt_type interrupt_type, enum ps3_reg_type reg_type)
{
@@ -770,49 +770,51 @@ static struct task_struct *probe_task;
static int ps3_probe_thread(void *data)
{
- struct ps3_notification_device dev;
+ struct {
+ struct ps3_notification_device dev;
+ u8 buf[512];
+ } *local;
+ struct ps3_notify_cmd *notify_cmd;
+ struct ps3_notify_event *notify_event;
int res;
unsigned int irq;
u64 lpar;
- void *buf;
- struct ps3_notify_cmd *notify_cmd;
- struct ps3_notify_event *notify_event;
pr_debug(" -> %s:%u: kthread started\n", __func__, __LINE__);
- buf = kzalloc(512, GFP_KERNEL);
- if (!buf)
+ local = kzalloc(sizeof(*local), GFP_KERNEL);
+ if (!local)
return -ENOMEM;
- lpar = ps3_mm_phys_to_lpar(__pa(buf));
- notify_cmd = buf;
- notify_event = buf;
+ lpar = ps3_mm_phys_to_lpar(__pa(&local->buf));
+ notify_cmd = (struct ps3_notify_cmd *)&local->buf;
+ notify_event = (struct ps3_notify_event *)&local->buf;
/* dummy system bus device */
- dev.sbd.bus_id = (u64)data;
- dev.sbd.dev_id = PS3_NOTIFICATION_DEV_ID;
- dev.sbd.interrupt_id = PS3_NOTIFICATION_INTERRUPT_ID;
+ local->dev.sbd.bus_id = (u64)data;
+ local->dev.sbd.dev_id = PS3_NOTIFICATION_DEV_ID;
+ local->dev.sbd.interrupt_id = PS3_NOTIFICATION_INTERRUPT_ID;
- res = lv1_open_device(dev.sbd.bus_id, dev.sbd.dev_id, 0);
+ res = lv1_open_device(local->dev.sbd.bus_id, local->dev.sbd.dev_id, 0);
if (res) {
pr_err("%s:%u: lv1_open_device failed %s\n", __func__,
__LINE__, ps3_result(res));
goto fail_free;
}
- res = ps3_sb_event_receive_port_setup(&dev.sbd, PS3_BINDING_CPU_ANY,
- &irq);
+ res = ps3_sb_event_receive_port_setup(&local->dev.sbd,
+ PS3_BINDING_CPU_ANY, &irq);
if (res) {
pr_err("%s:%u: ps3_sb_event_receive_port_setup failed %d\n",
__func__, __LINE__, res);
goto fail_close_device;
}
- spin_lock_init(&dev.lock);
- rcuwait_init(&dev.wait);
+ spin_lock_init(&local->dev.lock);
+ rcuwait_init(&local->dev.wait);
res = request_irq(irq, ps3_notification_interrupt, 0,
- "ps3_notification", &dev);
+ "ps3_notification", &local->dev);
if (res) {
pr_err("%s:%u: request_irq failed %d\n", __func__, __LINE__,
res);
@@ -823,7 +825,7 @@ static int ps3_probe_thread(void *data)
notify_cmd->operation_code = 0; /* must be zero */
notify_cmd->event_mask = 1UL << notify_region_probe;
- res = ps3_notification_read_write(&dev, lpar, 1);
+ res = ps3_notification_read_write(&local->dev, lpar, 1);
if (res)
goto fail_free_irq;
@@ -834,36 +836,37 @@ static int ps3_probe_thread(void *data)
memset(notify_event, 0, sizeof(*notify_event));
- res = ps3_notification_read_write(&dev, lpar, 0);
+ res = ps3_notification_read_write(&local->dev, lpar, 0);
if (res)
break;
pr_debug("%s:%u: notify event type 0x%llx bus id %llu dev id %llu"
" type %llu port %llu\n", __func__, __LINE__,
- notify_event->event_type, notify_event->bus_id,
- notify_event->dev_id, notify_event->dev_type,
- notify_event->dev_port);
+ notify_event->event_type, notify_event->bus_id,
+ notify_event->dev_id, notify_event->dev_type,
+ notify_event->dev_port);
if (notify_event->event_type != notify_region_probe ||
- notify_event->bus_id != dev.sbd.bus_id) {
+ notify_event->bus_id != local->dev.sbd.bus_id) {
pr_warn("%s:%u: bad notify_event: event %llu, dev_id %llu, dev_type %llu\n",
__func__, __LINE__, notify_event->event_type,
notify_event->dev_id, notify_event->dev_type);
continue;
}
- ps3_find_and_add_device(dev.sbd.bus_id, notify_event->dev_id);
+ ps3_find_and_add_device(local->dev.sbd.bus_id,
+ notify_event->dev_id);
} while (!kthread_should_stop());
fail_free_irq:
- free_irq(irq, &dev);
+ free_irq(irq, &local->dev);
fail_sb_event_receive_port_destroy:
- ps3_sb_event_receive_port_destroy(&dev.sbd, irq);
+ ps3_sb_event_receive_port_destroy(&local->dev.sbd, irq);
fail_close_device:
- lv1_close_device(dev.sbd.bus_id, dev.sbd.dev_id);
+ lv1_close_device(local->dev.sbd.bus_id, local->dev.sbd.dev_id);
fail_free:
- kfree(buf);
+ kfree(local);
probe_task = NULL;
diff --git a/arch/powerpc/platforms/ps3/hvcall.S b/arch/powerpc/platforms/ps3/hvcall.S
index 509e30ad01bb..e8ab3d6b03bd 100644
--- a/arch/powerpc/platforms/ps3/hvcall.S
+++ b/arch/powerpc/platforms/ps3/hvcall.S
@@ -9,6 +9,7 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
+#include <asm/ptrace.h>
#define lv1call .long 0x44000022; extsw r3, r3
@@ -16,12 +17,14 @@
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
+ stdu r1, -STACK_FRAME_MIN_SIZE(r1); \
li r11, API_NUMBER; \
lv1call; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE; \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -38,18 +41,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- stdu r3, -8(r1); \
+ std r3, -8(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-8(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 8; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+8; \
ld r11, -8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -57,21 +61,22 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r3, -8(r1); \
- stdu r4, -16(r1); \
+ std r4, -16(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-16(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 16; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+16; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
std r5, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -79,16 +84,17 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r3, -8(r1); \
std r4, -16(r1); \
- stdu r5, -24(r1); \
+ std r5, -24(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-24(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 24; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+24; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -96,7 +102,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -24(r1); \
std r6, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -104,7 +110,7 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r3, -8(r1); \
std r4, -16(r1); \
@@ -112,12 +118,13 @@ _GLOBAL(_##API_NAME) \
std r6, -32(r1); \
std r7, -40(r1); \
std r8, -48(r1); \
- stdu r9, -56(r1); \
+ std r9, -56(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-56(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 56; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+56; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -133,7 +140,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -56(r1); \
std r10, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -141,18 +148,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- stdu r4, -8(r1); \
+ std r4, -8(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-8(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 8; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+8; \
ld r11, -8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -160,21 +168,22 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r4, -8(r1); \
- stdu r5, -16(r1); \
+ std r5, -16(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-16(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 16; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+16; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
std r5, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -182,16 +191,17 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r4, -8(r1); \
std r5, -16(r1); \
- stdu r6, -24(r1); \
+ std r6, -24(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-24(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 24; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+24; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -199,7 +209,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -24(r1); \
std r6, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -207,17 +217,18 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r4, -8(r1); \
std r5, -16(r1); \
std r6, -24(r1); \
- stdu r7, -32(r1); \
+ std r7, -32(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-32(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 32; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+32; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -227,7 +238,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -32(r1); \
std r7, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -235,18 +246,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r4, -8(r1); \
std r5, -16(r1); \
std r6, -24(r1); \
std r7, -32(r1); \
- stdu r8, -40(r1); \
+ std r8, -40(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-40(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 40; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+40; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -258,7 +270,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -40(r1); \
std r8, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -266,19 +278,20 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r4, -8(r1); \
std r5, -16(r1); \
std r6, -24(r1); \
std r7, -32(r1); \
std r8, -40(r1); \
- stdu r9, -48(r1); \
+ std r9, -48(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-48(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 48; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+48; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -292,7 +305,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -48(r1); \
std r9, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -300,7 +313,7 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r4, -8(r1); \
std r5, -16(r1); \
@@ -308,12 +321,13 @@ _GLOBAL(_##API_NAME) \
std r7, -32(r1); \
std r8, -40(r1); \
std r9, -48(r1); \
- stdu r10, -56(r1); \
+ std r10, -56(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-56(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 56; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+56; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -329,7 +343,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -56(r1); \
std r10, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -337,18 +351,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- stdu r5, -8(r1); \
+ std r5, -8(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-8(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 8; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+8; \
ld r11, -8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -356,21 +371,22 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r5, -8(r1); \
- stdu r6, -16(r1); \
+ std r6, -16(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-16(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 16; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+16; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
std r5, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -378,16 +394,17 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r5, -8(r1); \
std r6, -16(r1); \
- stdu r7, -24(r1); \
+ std r7, -24(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-24(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 24; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+24; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -395,7 +412,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -24(r1); \
std r6, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -403,17 +420,18 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r5, -8(r1); \
std r6, -16(r1); \
std r7, -24(r1); \
- stdu r8, -32(r1); \
+ std r8, -32(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-32(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 32; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+32;\
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -423,7 +441,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -32(r1); \
std r7, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -431,18 +449,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r5, -8(r1); \
std r6, -16(r1); \
std r7, -24(r1); \
std r8, -32(r1); \
- stdu r9, -40(r1); \
+ std r9, -40(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-40(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 40; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+40; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -454,7 +473,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -40(r1); \
std r8, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -462,18 +481,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- stdu r6, -8(r1); \
+ std r6, -8(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-8(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 8; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+8; \
ld r11, -8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -481,21 +501,22 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r6, -8(r1); \
- stdu r7, -16(r1); \
+ std r7, -16(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-16(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 16; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+16; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
std r5, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -503,16 +524,17 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r6, -8(r1); \
std r7, -16(r1); \
- stdu r8, -24(r1); \
+ std r8, -24(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-24(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 24; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+24; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -520,7 +542,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -24(r1); \
std r6, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -528,18 +550,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- stdu r7, -8(r1); \
+ std r7, -8(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-8(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 8; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+8; \
ld r11, -8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -547,21 +570,22 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r7, -8(r1); \
- stdu r8, -16(r1); \
+ std r8, -16(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-16(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 16; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+16; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
std r5, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -569,16 +593,17 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r7, -8(r1); \
std r8, -16(r1); \
- stdu r9, -24(r1); \
+ std r9, -24(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-24(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 24; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+24; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -586,7 +611,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -24(r1); \
std r6, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -594,18 +619,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- stdu r8, -8(r1); \
+ std r8, -8(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-8(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 8; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+8; \
ld r11, -8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -613,21 +639,22 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r8, -8(r1); \
- stdu r9, -16(r1); \
+ std r9, -16(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-16(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 16; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+16; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
std r5, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -635,16 +662,17 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r8, -8(r1); \
std r9, -16(r1); \
- stdu r10, -24(r1); \
+ std r10, -24(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-24(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 24; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+24; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
@@ -652,7 +680,7 @@ _GLOBAL(_##API_NAME) \
ld r11, -24(r1); \
std r6, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -660,18 +688,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- stdu r9, -8(r1); \
+ std r9, -8(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-8(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 8; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+8; \
ld r11, -8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -679,21 +708,22 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r9, -8(r1); \
- stdu r10, -16(r1); \
+ std r10, -16(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-16(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 16; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+16; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
std r5, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -701,23 +731,24 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
std r9, -8(r1); \
- stdu r10, -16(r1); \
+ std r10, -16(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-16(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 16; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+16; \
ld r11, -8(r1); \
std r4, 0(r11); \
ld r11, -16(r1); \
std r5, 0(r11); \
- ld r11, 48+8*8(r1); \
+ ld r11, STK_PARAM_AREA+8*8(r1); \
std r6, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -725,18 +756,19 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- stdu r10, -8(r1); \
+ std r10, -8(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE-8(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- addi r1, r1, 8; \
+ addi r1, r1, STACK_FRAME_MIN_SIZE+8; \
ld r11, -8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -744,27 +776,29 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
\
- std r10, 48+8*7(r1); \
+ std r10, STK_PARAM_AREA+8*7(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- ld r11, 48+8*7(r1); \
+ addi r1, r1, STACK_FRAME_MIN_SIZE; \
+ ld r11, STK_PARAM_AREA+8*7(r1); \
std r4, 0(r11); \
- ld r11, 48+8*8(r1); \
+ ld r11, STK_PARAM_AREA+8*8(r1); \
std r5, 0(r11); \
- ld r11, 48+8*9(r1); \
+ ld r11, STK_PARAM_AREA+8*9(r1); \
std r6, 0(r11); \
- ld r11, 48+8*10(r1); \
+ ld r11, STK_PARAM_AREA+8*10(r1); \
std r7, 0(r11); \
- ld r11, 48+8*11(r1); \
+ ld r11, STK_PARAM_AREA+8*11(r1); \
std r8, 0(r11); \
- ld r11, 48+8*12(r1); \
+ ld r11, STK_PARAM_AREA+8*12(r1); \
std r9, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
@@ -772,15 +806,17 @@ _GLOBAL(_##API_NAME) \
_GLOBAL(_##API_NAME) \
\
mflr r0; \
- std r0, 16(r1); \
+ std r0, LRSAVE(r1); \
+ stdu r1, -STACK_FRAME_MIN_SIZE(r1); \
\
li r11, API_NUMBER; \
lv1call; \
\
- ld r11, 48+8*8(r1); \
+ addi r1, r1, STACK_FRAME_MIN_SIZE; \
+ ld r11, STK_PARAM_AREA+8*8(r1); \
std r4, 0(r11); \
\
- ld r0, 16(r1); \
+ ld r0, LRSAVE(r1); \
mtlr r0; \
blr
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 49871427f599..af3fe9f04f24 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -378,9 +378,9 @@ int ps3_send_event_locally(unsigned int virq)
/**
* ps3_sb_event_receive_port_setup - Setup a system bus event receive port.
+ * @dev: The system bus device instance.
* @cpu: enum ps3_cpu_binding indicating the cpu the interrupt should be
* serviced on.
- * @dev: The system bus device instance.
* @virq: The assigned Linux virq.
*
* An event irq represents a virtual device interrupt. The interrupt_id
diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c
index 1abe33fbe529..b8c030eab138 100644
--- a/arch/powerpc/platforms/ps3/repository.c
+++ b/arch/powerpc/platforms/ps3/repository.c
@@ -940,7 +940,7 @@ int __init ps3_repository_read_vuart_sysmgr_port(unsigned int *port)
/**
* ps3_repository_read_boot_dat_info - Get address and size of cell_ext_os_area.
- * address: lpar address of cell_ext_os_area
+ * @lpar_addr: lpar address of cell_ext_os_area
* @size: size of cell_ext_os_area
*/
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 5144f11359f7..150c09b58ae8 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -115,10 +115,7 @@ static void __init prealloc(struct ps3_prealloc *p)
if (!p->size)
return;
- p->address = memblock_alloc(p->size, p->align);
- if (!p->address)
- panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
- __func__, p->size, p->align);
+ p->address = memblock_alloc_or_panic(p->size, p->align);
printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size,
p->address);
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index d6b5f5ecd515..afbaabf182d0 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -333,10 +333,10 @@ int ps3_mmio_region_init(struct ps3_system_bus_device *dev,
EXPORT_SYMBOL_GPL(ps3_mmio_region_init);
static int ps3_system_bus_match(struct device *_dev,
- struct device_driver *_drv)
+ const struct device_driver *_drv)
{
int result;
- struct ps3_system_bus_driver *drv = ps3_drv_to_system_bus_drv(_drv);
+ const struct ps3_system_bus_driver *drv = ps3_drv_to_system_bus_drv(_drv);
struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
if (!dev->match_sub_id)
@@ -453,10 +453,9 @@ static ssize_t modalias_show(struct device *_dev, struct device_attribute *a,
char *buf)
{
struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
- int len = snprintf(buf, PAGE_SIZE, "ps3:%d:%d\n", dev->match_id,
- dev->match_sub_id);
- return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len;
+ return sysfs_emit(buf, "ps3:%d:%d\n", dev->match_id,
+ dev->match_sub_id);
}
static DEVICE_ATTR_RO(modalias);
@@ -695,7 +694,7 @@ static const struct dma_map_ops ps3_sb_dma_ops = {
.unmap_page = ps3_unmap_page,
.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,
};
@@ -709,7 +708,7 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = {
.unmap_page = ps3_unmap_page,
.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/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index afc0f6a61337..42fc66e97539 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -140,6 +140,20 @@ config HV_PERF_CTRS
If unsure, select Y.
+config VPA_PMU
+ tristate "VPA PMU events"
+ depends on KVM_BOOK3S_64_HV && HV_PERF_CTRS
+ help
+ Enable access to the VPA PMU counters via perf. This enables
+ code that support measurement for KVM on PowerVM(KoP) feature.
+ PAPR hypervisor has introduced three new counters in the VPA area
+ of LPAR CPUs for KVM L2 guest observability. Two for context switches
+ from host to guest and vice versa, and one counter for getting
+ the total time spent inside the KVM guest. This config enables code
+ that access these software counters via perf.
+
+ If unsure, Select N.
+
config IBMVIO
depends on PPC_PSERIES
bool
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index f936962a2946..7bf506f6b8c8 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -1,5 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
-ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
ccflags-$(CONFIG_PPC_PSERIES_DEBUG) += -DDEBUG
obj-y := lpar.o hvCall.o nvram.o reconfig.o \
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 47f8eabd1bee..213aa26dc8b3 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -23,6 +23,7 @@
#include <linux/uaccess.h>
#include <asm/rtas.h>
#include <asm/rtas-work-area.h>
+#include <asm/prom.h>
static struct workqueue_struct *pseries_hp_wq;
@@ -250,11 +251,8 @@ int dlpar_detach_node(struct device_node *dn)
struct device_node *child;
int rc;
- child = of_get_next_child(dn, NULL);
- while (child) {
+ for_each_child_of_node(dn, child)
dlpar_detach_node(child);
- child = of_get_next_child(dn, child);
- }
rc = of_detach_node(dn);
if (rc)
@@ -264,6 +262,20 @@ int dlpar_detach_node(struct device_node *dn)
return 0;
}
+static int dlpar_changeset_attach_cc_nodes(struct of_changeset *ocs,
+ struct device_node *dn)
+{
+ int rc;
+
+ rc = of_changeset_attach_node(ocs, dn);
+
+ if (!rc && dn->child)
+ rc = dlpar_changeset_attach_cc_nodes(ocs, dn->child);
+ if (!rc && dn->sibling)
+ rc = dlpar_changeset_attach_cc_nodes(ocs, dn->sibling);
+
+ return rc;
+}
#define DR_ENTITY_SENSE 9003
#define DR_ENTITY_PRESENT 1
@@ -330,27 +342,206 @@ int dlpar_unisolate_drc(u32 drc_index)
return 0;
}
-int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
+static struct device_node *
+get_device_node_with_drc_index(u32 index)
+{
+ struct device_node *np = NULL;
+ u32 node_index;
+ int rc;
+
+ for_each_node_with_property(np, "ibm,my-drc-index") {
+ rc = of_property_read_u32(np, "ibm,my-drc-index",
+ &node_index);
+ if (rc) {
+ pr_err("%s: %pOF: of_property_read_u32 %s: %d\n",
+ __func__, np, "ibm,my-drc-index", rc);
+ of_node_put(np);
+ return NULL;
+ }
+
+ if (index == node_index)
+ break;
+ }
+
+ return np;
+}
+
+static struct device_node *
+get_device_node_with_drc_info(u32 index)
+{
+ struct device_node *np = NULL;
+ struct of_drc_info drc;
+ struct property *info;
+ const __be32 *value;
+ u32 node_index;
+ int i, j, count;
+
+ for_each_node_with_property(np, "ibm,drc-info") {
+ info = of_find_property(np, "ibm,drc-info", NULL);
+ if (info == NULL) {
+ /* XXX can this happen? */
+ of_node_put(np);
+ return NULL;
+ }
+ value = of_prop_next_u32(info, NULL, &count);
+ if (value == NULL)
+ continue;
+ value++;
+ for (i = 0; i < count; i++) {
+ if (of_read_drc_info_cell(&info, &value, &drc))
+ break;
+ if (index > drc.last_drc_index)
+ continue;
+ node_index = drc.drc_index_start;
+ for (j = 0; j < drc.num_sequential_elems; j++) {
+ if (index == node_index)
+ return np;
+ node_index += drc.sequential_inc;
+ }
+ }
+ }
+
+ return NULL;
+}
+
+static int dlpar_hp_dt_add(u32 index)
+{
+ struct device_node *np, *nodes;
+ struct of_changeset ocs;
+ int rc;
+
+ /*
+ * Do not add device node(s) if already exists in the
+ * device tree.
+ */
+ np = get_device_node_with_drc_index(index);
+ if (np) {
+ pr_err("%s: Adding device node for index (%d), but "
+ "already exists in the device tree\n",
+ __func__, index);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ np = get_device_node_with_drc_info(index);
+
+ if (!np)
+ return -EIO;
+
+ /* Next, configure the connector. */
+ nodes = dlpar_configure_connector(cpu_to_be32(index), np);
+ if (!nodes) {
+ rc = -EIO;
+ goto out;
+ }
+
+ /*
+ * Add the new nodes from dlpar_configure_connector() onto
+ * the device-tree.
+ */
+ of_changeset_init(&ocs);
+ rc = dlpar_changeset_attach_cc_nodes(&ocs, nodes);
+
+ if (!rc)
+ rc = of_changeset_apply(&ocs);
+ else
+ dlpar_free_cc_nodes(nodes);
+
+ of_changeset_destroy(&ocs);
+
+out:
+ of_node_put(np);
+ return rc;
+}
+
+static int changeset_detach_node_recursive(struct of_changeset *ocs,
+ struct device_node *node)
{
+ struct device_node *child;
int rc;
- /* pseries error logs are in BE format, convert to cpu type */
- switch (hp_elog->id_type) {
- case PSERIES_HP_ELOG_ID_DRC_COUNT:
- hp_elog->_drc_u.drc_count =
- be32_to_cpu(hp_elog->_drc_u.drc_count);
+ for_each_child_of_node(node, child) {
+ rc = changeset_detach_node_recursive(ocs, child);
+ if (rc) {
+ of_node_put(child);
+ return rc;
+ }
+ }
+
+ return of_changeset_detach_node(ocs, node);
+}
+
+static int dlpar_hp_dt_remove(u32 drc_index)
+{
+ struct device_node *np;
+ struct of_changeset ocs;
+ u32 index;
+ int rc = 0;
+
+ /*
+ * Prune all nodes with a matching index.
+ */
+ of_changeset_init(&ocs);
+
+ for_each_node_with_property(np, "ibm,my-drc-index") {
+ rc = of_property_read_u32(np, "ibm,my-drc-index", &index);
+ if (rc) {
+ pr_err("%s: %pOF: of_property_read_u32 %s: %d\n",
+ __func__, np, "ibm,my-drc-index", rc);
+ of_node_put(np);
+ goto out;
+ }
+
+ if (index == drc_index) {
+ rc = changeset_detach_node_recursive(&ocs, np);
+ if (rc) {
+ of_node_put(np);
+ goto out;
+ }
+ }
+ }
+
+ rc = of_changeset_apply(&ocs);
+
+out:
+ of_changeset_destroy(&ocs);
+ return rc;
+}
+
+static int dlpar_hp_dt(struct pseries_hp_errorlog *phpe)
+{
+ u32 drc_index;
+ int rc;
+
+ if (phpe->id_type != PSERIES_HP_ELOG_ID_DRC_INDEX)
+ return -EINVAL;
+
+ drc_index = be32_to_cpu(phpe->_drc_u.drc_index);
+
+ lock_device_hotplug();
+
+ switch (phpe->action) {
+ case PSERIES_HP_ELOG_ACTION_ADD:
+ rc = dlpar_hp_dt_add(drc_index);
break;
- case PSERIES_HP_ELOG_ID_DRC_INDEX:
- hp_elog->_drc_u.drc_index =
- be32_to_cpu(hp_elog->_drc_u.drc_index);
+ case PSERIES_HP_ELOG_ACTION_REMOVE:
+ rc = dlpar_hp_dt_remove(drc_index);
+ break;
+ default:
+ pr_err("Invalid action (%d) specified\n", phpe->action);
+ rc = -EINVAL;
break;
- case PSERIES_HP_ELOG_ID_DRC_IC:
- hp_elog->_drc_u.ic.count =
- be32_to_cpu(hp_elog->_drc_u.ic.count);
- hp_elog->_drc_u.ic.index =
- be32_to_cpu(hp_elog->_drc_u.ic.index);
}
+ unlock_device_hotplug();
+
+ return rc;
+}
+
+int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
+{
+ int rc;
+
switch (hp_elog->resource) {
case PSERIES_HP_ELOG_RESOURCE_MEM:
rc = dlpar_memory(hp_elog);
@@ -361,6 +552,9 @@ int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
case PSERIES_HP_ELOG_RESOURCE_PMEM:
rc = dlpar_hp_pmem(hp_elog);
break;
+ case PSERIES_HP_ELOG_RESOURCE_DT:
+ rc = dlpar_hp_dt(hp_elog);
+ break;
default:
pr_warn_ratelimited("Invalid resource (%d) specified\n",
@@ -413,6 +607,8 @@ static int dlpar_parse_resource(char **cmd, struct pseries_hp_errorlog *hp_elog)
hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM;
} else if (sysfs_streq(arg, "cpu")) {
hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_CPU;
+ } else if (sysfs_streq(arg, "dt")) {
+ hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_DT;
} else {
pr_err("Invalid resource specified.\n");
return -EINVAL;
@@ -554,7 +750,7 @@ dlpar_store_out:
static ssize_t dlpar_show(const struct class *class, const struct class_attribute *attr,
char *buf)
{
- return sprintf(buf, "%s\n", "memory,cpu");
+ return sprintf(buf, "%s\n", "memory,cpu,dt");
}
static CLASS_ATTR_RW(dlpar);
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 3f1cdccebc9c..f293588b8c7b 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -191,7 +191,7 @@ static int dtl_enable(struct dtl *dtl)
return -EBUSY;
/* ensure there are no other conflicting dtl users */
- if (!read_trylock(&dtl_access_lock))
+ if (!down_read_trylock(&dtl_access_lock))
return -EBUSY;
n_entries = dtl_buf_entries;
@@ -199,7 +199,7 @@ static int dtl_enable(struct dtl *dtl)
if (!buf) {
printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
__func__, dtl->cpu);
- read_unlock(&dtl_access_lock);
+ up_read(&dtl_access_lock);
return -ENOMEM;
}
@@ -217,7 +217,7 @@ static int dtl_enable(struct dtl *dtl)
spin_unlock(&dtl->lock);
if (rc) {
- read_unlock(&dtl_access_lock);
+ up_read(&dtl_access_lock);
kmem_cache_free(dtl_cache, buf);
}
@@ -232,7 +232,7 @@ static void dtl_disable(struct dtl *dtl)
dtl->buf = NULL;
dtl->buf_entries = 0;
spin_unlock(&dtl->lock);
- read_unlock(&dtl_access_lock);
+ up_read(&dtl_access_lock);
}
/* file interface */
@@ -325,7 +325,6 @@ static const struct file_operations dtl_fops = {
.open = dtl_file_open,
.release = dtl_file_release,
.read = dtl_file_read,
- .llseek = no_llseek,
};
static struct dentry *dtl_dir;
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b1ae0c0d1187..b12ef382fec7 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -580,8 +580,10 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay)
switch(rets[0]) {
case 0:
- result = EEH_STATE_MMIO_ACTIVE |
- EEH_STATE_DMA_ACTIVE;
+ result = EEH_STATE_MMIO_ACTIVE |
+ EEH_STATE_DMA_ACTIVE |
+ EEH_STATE_MMIO_ENABLED |
+ EEH_STATE_DMA_ENABLED;
break;
case 1:
result = EEH_STATE_RESET_ACTIVE |
@@ -784,6 +786,43 @@ static int pseries_notify_resume(struct eeh_dev *edev)
}
#endif
+/**
+ * pseries_eeh_err_inject - Inject specified error to the indicated PE
+ * @pe: the indicated PE
+ * @type: error type
+ * @func: specific error type
+ * @addr: address
+ * @mask: address mask
+ * The routine is called to inject specified error, which is
+ * determined by @type and @func, to the indicated PE
+ */
+static int pseries_eeh_err_inject(struct eeh_pe *pe, int type, int func,
+ unsigned long addr, unsigned long mask)
+{
+ struct eeh_dev *pdev;
+
+ /* Check on PCI error type */
+ if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
+ return -EINVAL;
+
+ switch (func) {
+ case EEH_ERR_FUNC_LD_MEM_ADDR:
+ case EEH_ERR_FUNC_LD_MEM_DATA:
+ case EEH_ERR_FUNC_ST_MEM_ADDR:
+ case EEH_ERR_FUNC_ST_MEM_DATA:
+ /* injects a MMIO error for all pdev's belonging to PE */
+ pci_lock_rescan_remove();
+ list_for_each_entry(pdev, &pe->edevs, entry)
+ eeh_pe_inject_mmio_error(pdev->pdev);
+ pci_unlock_rescan_remove();
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ return 0;
+}
+
static struct eeh_ops pseries_eeh_ops = {
.name = "pseries",
.probe = pseries_eeh_probe,
@@ -792,7 +831,7 @@ static struct eeh_ops pseries_eeh_ops = {
.reset = pseries_eeh_reset,
.get_log = pseries_eeh_get_log,
.configure_bridge = pseries_eeh_configure_bridge,
- .err_inject = NULL,
+ .err_inject = pseries_eeh_err_inject,
.read_config = pseries_eeh_read_config,
.write_config = pseries_eeh_write_config,
.next_error = NULL,
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index e62835a12d73..bc6926dbf148 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -33,6 +33,7 @@
#include <asm/xive.h>
#include <asm/plpar_wrappers.h>
#include <asm/topology.h>
+#include <asm/systemcfg.h>
#include "pseries.h"
@@ -83,7 +84,9 @@ static int pseries_cpu_disable(void)
int cpu = smp_processor_id();
set_cpu_online(cpu, false);
- vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+ systemcfg->processorCount--;
+#endif
/*fix boot_cpuid here*/
if (cpu == boot_cpuid)
@@ -757,7 +760,7 @@ int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
u32 drc_index;
int rc;
- drc_index = hp_elog->_drc_u.drc_index;
+ drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index);
lock_device_hotplug();
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 3fe3ddb30c04..38dc4f7c9296 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -817,16 +817,16 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
case PSERIES_HP_ELOG_ACTION_ADD:
switch (hp_elog->id_type) {
case PSERIES_HP_ELOG_ID_DRC_COUNT:
- count = hp_elog->_drc_u.drc_count;
+ count = be32_to_cpu(hp_elog->_drc_u.drc_count);
rc = dlpar_memory_add_by_count(count);
break;
case PSERIES_HP_ELOG_ID_DRC_INDEX:
- drc_index = hp_elog->_drc_u.drc_index;
+ drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index);
rc = dlpar_memory_add_by_index(drc_index);
break;
case PSERIES_HP_ELOG_ID_DRC_IC:
- count = hp_elog->_drc_u.ic.count;
- drc_index = hp_elog->_drc_u.ic.index;
+ count = be32_to_cpu(hp_elog->_drc_u.ic.count);
+ drc_index = be32_to_cpu(hp_elog->_drc_u.ic.index);
rc = dlpar_memory_add_by_ic(count, drc_index);
break;
default:
@@ -838,16 +838,16 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
case PSERIES_HP_ELOG_ACTION_REMOVE:
switch (hp_elog->id_type) {
case PSERIES_HP_ELOG_ID_DRC_COUNT:
- count = hp_elog->_drc_u.drc_count;
+ count = be32_to_cpu(hp_elog->_drc_u.drc_count);
rc = dlpar_memory_remove_by_count(count);
break;
case PSERIES_HP_ELOG_ID_DRC_INDEX:
- drc_index = hp_elog->_drc_u.drc_index;
+ drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index);
rc = dlpar_memory_remove_by_index(drc_index);
break;
case PSERIES_HP_ELOG_ID_DRC_IC:
- count = hp_elog->_drc_u.ic.count;
- drc_index = hp_elog->_drc_u.ic.index;
+ count = be32_to_cpu(hp_elog->_drc_u.ic.count);
+ drc_index = be32_to_cpu(hp_elog->_drc_u.ic.index);
rc = dlpar_memory_remove_by_ic(count, drc_index);
break;
default:
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index 998e3aff2457..3436b0af795e 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -55,7 +55,7 @@ static struct device ibmebus_bus_device = { /* fake "parent" device */
.init_name = "ibmebus",
};
-struct bus_type ibmebus_bus_type;
+const struct bus_type ibmebus_bus_type;
/* These devices will automatically be added to the bus during init */
static const struct of_device_id ibmebus_matches[] __initconst = {
@@ -339,7 +339,7 @@ static struct attribute *ibmbus_bus_attrs[] = {
};
ATTRIBUTE_GROUPS(ibmbus_bus);
-static int ibmebus_bus_bus_match(struct device *dev, struct device_driver *drv)
+static int ibmebus_bus_bus_match(struct device *dev, const struct device_driver *drv)
{
const struct of_device_id *matches = drv->of_match_table;
@@ -432,7 +432,7 @@ static int ibmebus_bus_modalias(const struct device *dev, struct kobj_uevent_env
return of_device_uevent_modalias(dev, env);
}
-struct bus_type ibmebus_bus_type = {
+const struct bus_type ibmebus_bus_type = {
.name = "ibmebus",
.uevent = ibmebus_bus_modalias,
.bus_groups = ibmbus_bus_groups,
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index e8c4129697b1..ae6f7a235d8b 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -21,6 +21,7 @@
#include <linux/dma-mapping.h>
#include <linux/crash_dump.h>
#include <linux/memory.h>
+#include <linux/vmalloc.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/iommu.h>
@@ -67,6 +68,10 @@ static struct iommu_table *iommu_pseries_alloc_table(int node)
return tbl;
}
+#ifdef CONFIG_IOMMU_API
+static struct iommu_table_group_ops spapr_tce_table_group_ops;
+#endif
+
static struct iommu_table_group *iommu_pseries_alloc_group(int node)
{
struct iommu_table_group *table_group;
@@ -102,7 +107,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
#endif
/* Default DMA window table is at index 0, while DDW at 1. SR-IOV
- * adapters only have table on index 1.
+ * adapters only have table on index 0(if not direct mapped).
*/
if (table_group->tables[0])
iommu_tce_table_put(table_group->tables[0]);
@@ -143,7 +148,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
}
-static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
+static void tce_clear_pSeries(struct iommu_table *tbl, long index, long npages)
{
__be64 *tcep;
@@ -162,6 +167,39 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
return be64_to_cpu(*tcep);
}
+#ifdef CONFIG_IOMMU_API
+static long pseries_tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
+{
+ unsigned long cb = ALIGN(sizeof(tbl->it_userspace[0]) * tbl->it_size, PAGE_SIZE);
+ unsigned long *uas;
+
+ if (tbl->it_indirect_levels) /* Impossible */
+ return -EPERM;
+
+ WARN_ON(tbl->it_userspace);
+
+ uas = vzalloc(cb);
+ if (!uas)
+ return -ENOMEM;
+
+ tbl->it_userspace = (__be64 *) uas;
+
+ return 0;
+}
+#endif
+
+static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
+{
+ vfree(tbl->it_userspace);
+ tbl->it_userspace = NULL;
+}
+
+static void tce_free_pSeries(struct iommu_table *tbl)
+{
+ if (!tbl->it_userspace)
+ tce_iommu_userspace_view_free(tbl);
+}
+
static void tce_free_pSeriesLP(unsigned long liobn, long, long, long);
static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
@@ -576,7 +614,7 @@ struct iommu_table_ops iommu_table_lpar_multi_ops;
struct iommu_table_ops iommu_table_pseries_ops = {
.set = tce_build_pSeries,
- .clear = tce_free_pSeries,
+ .clear = tce_clear_pSeries,
.get = tce_get_pseries
};
@@ -685,17 +723,47 @@ static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
return rc;
}
+
+static __be64 *tce_useraddr_pSeriesLP(struct iommu_table *tbl, long index,
+ bool __always_unused alloc)
+{
+ return tbl->it_userspace ? &tbl->it_userspace[index - tbl->it_offset] : NULL;
+}
#endif
struct iommu_table_ops iommu_table_lpar_multi_ops = {
.set = tce_buildmulti_pSeriesLP,
#ifdef CONFIG_IOMMU_API
.xchg_no_kill = tce_exchange_pseries,
+ .useraddrptr = tce_useraddr_pSeriesLP,
#endif
.clear = tce_freemulti_pSeriesLP,
- .get = tce_get_pSeriesLP
+ .get = tce_get_pSeriesLP,
+ .free = tce_free_pSeries
};
+#ifdef CONFIG_IOMMU_API
+/*
+ * When the DMA window properties might have been removed,
+ * the parent node has the table_group setup on it.
+ */
+static struct device_node *pci_dma_find_parent_node(struct pci_dev *dev,
+ struct iommu_table_group *table_group)
+{
+ struct device_node *dn = pci_device_to_OF_node(dev);
+ struct pci_dn *rpdn;
+
+ for (; dn && PCI_DN(dn); dn = dn->parent) {
+ rpdn = PCI_DN(dn);
+
+ if (table_group == rpdn->table_group)
+ return dn;
+ }
+
+ return NULL;
+}
+#endif
+
/*
* Find nearest ibm,dma-window (default DMA window) or direct DMA window or
* dynamic 64bit DMA window, walking up the device tree.
@@ -786,8 +854,16 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
* parent bus. During reboot, there will be ibm,dma-window property to
* define DMA window. For kdump, there will at least be default window or DDW
* or both.
+ * There is an exception to the above. In case the PE goes into frozen
+ * state, firmware may not provide ibm,dma-window property at the time
+ * of LPAR boot up.
*/
+ if (!pdn) {
+ pr_debug(" no ibm,dma-window property !\n");
+ return;
+ }
+
ppci = PCI_DN(pdn);
pr_debug(" parent is %pOF, iommu_table: 0x%p\n",
@@ -804,13 +880,6 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
be32_to_cpu(prop.tce_shift), NULL,
&iommu_table_lpar_multi_ops);
- /* Only for normal boot with default window. Doesn't matter even
- * if we set these with DDW which is 64bit during kdump, since
- * these will not be used during kdump.
- */
- ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
- ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
-
if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
panic("Failed to initialize iommu table");
@@ -909,7 +978,7 @@ static void __remove_dma_window(struct device_node *np, u32 *ddw_avail, u64 liob
}
static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
- struct property *win)
+ struct property *win, bool cleanup)
{
struct dynamic_dma_window_prop *dwp;
u64 liobn;
@@ -917,11 +986,44 @@ static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
dwp = win->value;
liobn = (u64)be32_to_cpu(dwp->liobn);
- clean_dma_window(np, dwp);
+ if (cleanup)
+ clean_dma_window(np, dwp);
__remove_dma_window(np, ddw_avail, liobn);
}
-static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_name)
+static void copy_property(struct device_node *pdn, const char *from, const char *to)
+{
+ struct property *src, *dst;
+
+ src = of_find_property(pdn, from, NULL);
+ if (!src)
+ return;
+
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ if (!dst)
+ return;
+
+ dst->name = kstrdup(to, GFP_KERNEL);
+ dst->value = kmemdup(src->value, src->length, GFP_KERNEL);
+ dst->length = src->length;
+ if (!dst->name || !dst->value)
+ return;
+
+ if (of_add_property(pdn, dst)) {
+ pr_err("Unable to add DMA window property for %pOF", pdn);
+ goto free_prop;
+ }
+
+ return;
+
+free_prop:
+ kfree(dst->name);
+ kfree(dst->value);
+ kfree(dst);
+}
+
+static int remove_dma_window_named(struct device_node *np, bool remove_prop, const char *win_name,
+ bool cleanup)
{
struct property *win;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
@@ -936,13 +1038,20 @@ static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_
if (ret)
return 0;
-
if (win->length >= sizeof(struct dynamic_dma_window_prop))
- remove_dma_window(np, ddw_avail, win);
+ remove_dma_window(np, ddw_avail, win, cleanup);
if (!remove_prop)
return 0;
+ /* Default window property if removed is lost as reset-pe doesn't restore it.
+ * Though FDT has a copy of it, the DLPAR hotplugged devices will not have a
+ * node on FDT until next reboot. So, back it up.
+ */
+ if ((strcmp(win_name, "ibm,dma-window") == 0) &&
+ !of_find_property(np, "ibm,dma-window-saved", NULL))
+ copy_property(np, win_name, "ibm,dma-window-saved");
+
ret = of_remove_property(np, win);
if (ret)
pr_warn("%pOF: failed to remove DMA window property: %d\n",
@@ -1000,7 +1109,7 @@ static void find_existing_ddw_windows_named(const char *name)
for_each_node_with_property(pdn, name) {
dma64 = of_get_property(pdn, name, &len);
if (!dma64 || len < sizeof(*dma64)) {
- remove_ddw(pdn, true, name);
+ remove_dma_window_named(pdn, true, name, true);
continue;
}
@@ -1296,7 +1405,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
struct ddw_query_response query;
struct ddw_create_response create;
int page_shift;
- u64 win_addr;
+ u64 win_addr, dynamic_offset = 0;
const char *win_name;
struct device_node *dn;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
@@ -1304,6 +1413,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
struct property *win64;
struct failed_ddw_pdn *fpdn;
bool default_win_removed = false, direct_mapping = false;
+ bool dynamic_mapping = false;
bool pmem_present;
struct pci_dn *pci = PCI_DN(pdn);
struct property *default_win = NULL;
@@ -1377,7 +1487,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
if (reset_win_ext)
goto out_failed;
- remove_dma_window(pdn, ddw_avail, default_win);
+ remove_dma_window(pdn, ddw_avail, default_win, true);
default_win_removed = true;
/* Query again, to check if the window is available */
@@ -1399,7 +1509,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
goto out_failed;
}
-
/*
* The "ibm,pmemory" can appear anywhere in the address space.
* Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS
@@ -1424,14 +1533,42 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
1ULL << page_shift);
len = order_base_2(query.largest_available_block << page_shift);
- win_name = DMA64_PROPNAME;
+
+ dynamic_mapping = true;
} else {
direct_mapping = !default_win_removed ||
(len == MAX_PHYSMEM_BITS) ||
(!pmem_present && (len == max_ram_len));
- win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME;
+
+ /* DDW is big enough to direct map RAM. If there is vPMEM, check
+ * if enough space is left in DDW where we can dynamically
+ * allocate TCEs for vPMEM. For now, this Hybrid sharing of DDW
+ * is only for SR-IOV devices.
+ */
+ if (default_win_removed && pmem_present && !direct_mapping) {
+ /* DDW is big enough to be split */
+ if ((query.largest_available_block << page_shift) >=
+ MIN_DDW_VPMEM_DMA_WINDOW + (1ULL << max_ram_len)) {
+ direct_mapping = true;
+
+ /* offset of the Dynamic part of DDW */
+ dynamic_offset = 1ULL << max_ram_len;
+ }
+
+ /* DDW will at least have dynamic allocation */
+ dynamic_mapping = true;
+
+ /* create max size DDW possible */
+ len = order_base_2(query.largest_available_block
+ << page_shift);
+ }
}
+ /* Even if the DDW is split into both direct mapped RAM and dynamically
+ * mapped vPMEM, the DDW property in OF will be marked as Direct.
+ */
+ win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME;
+
ret = create_ddw(dev, ddw_avail, &create, page_shift, len);
if (ret != 0)
goto out_failed;
@@ -1459,9 +1596,9 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
if (!window)
goto out_del_prop;
- if (direct_mapping) {
- window->direct = true;
+ window->direct = direct_mapping;
+ if (direct_mapping) {
/* DDW maps the whole partition, so enable direct DMA mapping */
ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
win64->value, tce_setrange_multi_pSeriesLP_walk);
@@ -1473,12 +1610,18 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
clean_dma_window(pdn, win64->value);
goto out_del_list;
}
- } else {
+ if (default_win_removed) {
+ iommu_tce_table_put(pci->table_group->tables[0]);
+ pci->table_group->tables[0] = NULL;
+ set_iommu_table_base(&dev->dev, NULL);
+ }
+ }
+
+ if (dynamic_mapping) {
struct iommu_table *newtbl;
int i;
unsigned long start = 0, end = 0;
-
- window->direct = false;
+ u64 dynamic_addr, dynamic_len;
for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
@@ -1498,20 +1641,27 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
goto out_del_list;
}
- iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr,
- 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
- iommu_init_table(newtbl, pci->phb->node, start, end);
+ /* If the DDW is split between directly mapped RAM and Dynamic
+ * mapped for TCES, offset into the DDW where the dynamic part
+ * begins.
+ */
+ dynamic_addr = win_addr + dynamic_offset;
+ dynamic_len = (1UL << len) - dynamic_offset;
+ iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn,
+ dynamic_addr, dynamic_len, page_shift, NULL,
+ &iommu_table_lpar_multi_ops);
+ iommu_init_table(newtbl, pci->phb->node,
+ start >> page_shift, end >> page_shift);
- pci->table_group->tables[1] = newtbl;
+ pci->table_group->tables[default_win_removed ? 0 : 1] = newtbl;
set_iommu_table_base(&dev->dev, newtbl);
}
if (default_win_removed) {
- iommu_tce_table_put(pci->table_group->tables[0]);
- pci->table_group->tables[0] = NULL;
-
/* default_win is valid here because default_win_removed == true */
+ if (!of_find_property(pdn, "ibm,dma-window-saved", NULL))
+ copy_property(pdn, "ibm,dma-window", "ibm,dma-window-saved");
of_remove_property(pdn, default_win);
dev_info(&dev->dev, "Removed default DMA window for %pOF\n", pdn);
}
@@ -1551,17 +1701,81 @@ out_failed:
out_unlock:
mutex_unlock(&dma_win_init_mutex);
- /*
- * If we have persistent memory and the window size is only as big
- * as RAM, then we failed to create a window to cover persistent
- * memory and need to set the DMA limit.
+ /* If we have persistent memory and the window size is not big enough
+ * to directly map both RAM and vPMEM, then we need to set DMA limit.
*/
- if (pmem_present && direct_mapping && len == max_ram_len)
- dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len);
+ if (pmem_present && direct_mapping && len != MAX_PHYSMEM_BITS)
+ dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset +
+ (1ULL << max_ram_len);
return direct_mapping;
}
+static __u64 query_page_size_to_mask(u32 query_page_size)
+{
+ const long shift[] = {
+ (SZ_4K), (SZ_64K), (SZ_16M),
+ (SZ_32M), (SZ_64M), (SZ_128M),
+ (SZ_256M), (SZ_16G), (SZ_2M)
+ };
+ int i, ret = 0;
+
+ for (i = 0; i < ARRAY_SIZE(shift); i++) {
+ if (query_page_size & (1 << i))
+ ret |= shift[i];
+ }
+
+ return ret;
+}
+
+static void spapr_tce_init_table_group(struct pci_dev *pdev,
+ struct device_node *pdn,
+ struct dynamic_dma_window_prop prop)
+{
+ struct iommu_table_group *table_group = PCI_DN(pdn)->table_group;
+ u32 ddw_avail[DDW_APPLICABLE_SIZE];
+
+ struct ddw_query_response query;
+ int ret;
+
+ /* Only for normal boot with default window. Doesn't matter during
+ * kdump, since these will not be used during kdump.
+ */
+ if (is_kdump_kernel())
+ return;
+
+ if (table_group->max_dynamic_windows_supported != 0)
+ return; /* already initialized */
+
+ table_group->tce32_start = be64_to_cpu(prop.dma_base);
+ table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
+
+ if (!of_find_property(pdn, "ibm,dma-window", NULL))
+ dev_err(&pdev->dev, "default dma window missing!\n");
+
+ ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+ &ddw_avail[0], DDW_APPLICABLE_SIZE);
+ if (ret) {
+ table_group->max_dynamic_windows_supported = -1;
+ return;
+ }
+
+ ret = query_ddw(pdev, ddw_avail, &query, pdn);
+ if (ret) {
+ dev_err(&pdev->dev, "%s: query_ddw failed\n", __func__);
+ table_group->max_dynamic_windows_supported = -1;
+ return;
+ }
+
+ if (query.windows_available == 0)
+ table_group->max_dynamic_windows_supported = 1;
+ else
+ table_group->max_dynamic_windows_supported = IOMMU_TABLE_GROUP_MAX_TABLES;
+
+ table_group->max_levels = 1;
+ table_group->pgsizes |= query_page_size_to_mask(query.page_size);
+}
+
static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
{
struct device_node *pdn, *dn;
@@ -1601,13 +1815,6 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
be32_to_cpu(prop.tce_shift), NULL,
&iommu_table_lpar_multi_ops);
- /* Only for normal boot with default window. Doesn't matter even
- * if we set these with DDW which is 64bit during kdump, since
- * these will not be used during kdump.
- */
- pci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
- pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
-
iommu_init_table(tbl, pci->phb->node, 0, 0);
iommu_register_group(pci->table_group,
pci_domain_nr(pci->phb->bus), 0);
@@ -1616,6 +1823,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
pr_debug(" found DMA window, table: %p\n", pci->table_group);
}
+ spapr_tce_init_table_group(dev, pdn, prop);
+
set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
iommu_add_device(pci->table_group, &dev->dev);
}
@@ -1643,6 +1852,496 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
return false;
}
+#ifdef CONFIG_IOMMU_API
+/*
+ * A simple iommu_table_group_ops which only allows reusing the existing
+ * iommu_table. This handles VFIO for POWER7 or the nested KVM.
+ * The ops does not allow creating windows and only allows reusing the existing
+ * one if it matches table_group->tce32_start/tce32_size/page_shift.
+ */
+static unsigned long spapr_tce_get_table_size(__u32 page_shift,
+ __u64 window_size, __u32 levels)
+{
+ unsigned long size;
+
+ if (levels > 1)
+ return ~0U;
+ size = window_size >> (page_shift - 3);
+ return size;
+}
+
+static struct pci_dev *iommu_group_get_first_pci_dev(struct iommu_group *group)
+{
+ struct pci_dev *pdev = NULL;
+ int ret;
+
+ /* No IOMMU group ? */
+ if (!group)
+ return NULL;
+
+ ret = iommu_group_for_each_dev(group, &pdev, dev_has_iommu_table);
+ if (!ret || !pdev)
+ return NULL;
+ return pdev;
+}
+
+static void restore_default_dma_window(struct pci_dev *pdev, struct device_node *pdn)
+{
+ reset_dma_window(pdev, pdn);
+ copy_property(pdn, "ibm,dma-window-saved", "ibm,dma-window");
+}
+
+static long remove_dynamic_dma_windows(struct pci_dev *pdev, struct device_node *pdn)
+{
+ struct pci_dn *pci = PCI_DN(pdn);
+ struct dma_win *window;
+ bool direct_mapping;
+ int len;
+
+ if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len, &direct_mapping)) {
+ remove_dma_window_named(pdn, true, direct_mapping ?
+ DIRECT64_PROPNAME : DMA64_PROPNAME, true);
+ if (!direct_mapping) {
+ WARN_ON(!pci->table_group->tables[0] && !pci->table_group->tables[1]);
+
+ if (pci->table_group->tables[1]) {
+ iommu_tce_table_put(pci->table_group->tables[1]);
+ pci->table_group->tables[1] = NULL;
+ } else if (pci->table_group->tables[0]) {
+ /* Default window was removed and only the DDW exists */
+ iommu_tce_table_put(pci->table_group->tables[0]);
+ pci->table_group->tables[0] = NULL;
+ }
+ }
+ spin_lock(&dma_win_list_lock);
+ list_for_each_entry(window, &dma_win_list, list) {
+ if (window->device == pdn) {
+ list_del(&window->list);
+ kfree(window);
+ break;
+ }
+ }
+ spin_unlock(&dma_win_list_lock);
+ }
+
+ return 0;
+}
+
+static long pseries_setup_default_iommu_config(struct iommu_table_group *table_group,
+ struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ const __be32 *default_prop;
+ long liobn, offset, size;
+ struct device_node *pdn;
+ struct iommu_table *tbl;
+ struct pci_dn *pci;
+
+ pdn = pci_dma_find_parent_node(pdev, table_group);
+ if (!pdn || !PCI_DN(pdn)) {
+ dev_warn(&pdev->dev, "No table_group configured for the node %pOF\n", pdn);
+ return -1;
+ }
+ pci = PCI_DN(pdn);
+
+ /* The default window is restored if not present already on removal of DDW.
+ * However, if used by VFIO SPAPR sub driver, the user's order of removal of
+ * windows might have been different to not leading to auto restoration,
+ * suppose the DDW was removed first followed by the default one.
+ * So, restore the default window with reset-pe-dma call explicitly.
+ */
+ restore_default_dma_window(pdev, pdn);
+
+ default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+ of_parse_dma_window(pdn, default_prop, &liobn, &offset, &size);
+ tbl = iommu_pseries_alloc_table(pci->phb->node);
+ if (!tbl) {
+ dev_err(&pdev->dev, "couldn't create new IOMMU table\n");
+ return -1;
+ }
+
+ iommu_table_setparms_common(tbl, pci->phb->bus->number, liobn, offset,
+ size, IOMMU_PAGE_SHIFT_4K, NULL,
+ &iommu_table_lpar_multi_ops);
+ iommu_init_table(tbl, pci->phb->node, 0, 0);
+
+ pci->table_group->tables[0] = tbl;
+ set_iommu_table_base(&pdev->dev, tbl);
+
+ return 0;
+}
+
+static bool is_default_window_request(struct iommu_table_group *table_group, __u32 page_shift,
+ __u64 window_size)
+{
+ if ((window_size <= table_group->tce32_size) &&
+ (page_shift == IOMMU_PAGE_SHIFT_4K))
+ return true;
+
+ return false;
+}
+
+static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
+ __u32 page_shift, __u64 window_size, __u32 levels,
+ struct iommu_table **ptbl)
+{
+ struct pci_dev *pdev = iommu_group_get_first_pci_dev(table_group->group);
+ u32 ddw_avail[DDW_APPLICABLE_SIZE];
+ struct ddw_create_response create;
+ unsigned long liobn, offset, size;
+ unsigned long start = 0, end = 0;
+ struct ddw_query_response query;
+ const __be32 *default_prop;
+ struct failed_ddw_pdn *fpdn;
+ unsigned int window_shift;
+ struct device_node *pdn;
+ struct iommu_table *tbl;
+ struct dma_win *window;
+ struct property *win64;
+ struct pci_dn *pci;
+ u64 win_addr;
+ int len, i;
+ long ret;
+
+ if (!is_power_of_2(window_size) || levels > 1)
+ return -EINVAL;
+
+ window_shift = order_base_2(window_size);
+
+ mutex_lock(&dma_win_init_mutex);
+
+ ret = -ENODEV;
+
+ pdn = pci_dma_find_parent_node(pdev, table_group);
+ if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+ dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+ goto out_failed;
+ }
+ pci = PCI_DN(pdn);
+
+ /* If the enable DDW failed for the pdn, dont retry! */
+ list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) {
+ if (fpdn->pdn == pdn) {
+ dev_info(&pdev->dev, "%pOF in failed DDW device list\n", pdn);
+ goto out_unlock;
+ }
+ }
+
+ tbl = iommu_pseries_alloc_table(pci->phb->node);
+ if (!tbl) {
+ dev_dbg(&pdev->dev, "couldn't create new IOMMU table\n");
+ goto out_unlock;
+ }
+
+ if (num == 0) {
+ bool direct_mapping;
+ /* The request is not for default window? Ensure there is no DDW window already */
+ if (!is_default_window_request(table_group, page_shift, window_size)) {
+ if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
+ &direct_mapping)) {
+ dev_warn(&pdev->dev, "%pOF: 64-bit window already present.", pdn);
+ ret = -EPERM;
+ goto out_unlock;
+ }
+ } else {
+ /* Request is for Default window, ensure there is no DDW if there is a
+ * need to reset. reset-pe otherwise removes the DDW also
+ */
+ default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+ if (!default_prop) {
+ if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
+ &direct_mapping)) {
+ dev_warn(&pdev->dev, "%pOF: Attempt to create window#0 when 64-bit window is present. Preventing the attempt as that would destroy the 64-bit window",
+ pdn);
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
+ restore_default_dma_window(pdev, pdn);
+
+ default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+ of_parse_dma_window(pdn, default_prop, &liobn, &offset, &size);
+ /* Limit the default window size to window_size */
+ iommu_table_setparms_common(tbl, pci->phb->bus->number, liobn,
+ offset, 1UL << window_shift,
+ IOMMU_PAGE_SHIFT_4K, NULL,
+ &iommu_table_lpar_multi_ops);
+ iommu_init_table(tbl, pci->phb->node,
+ start >> IOMMU_PAGE_SHIFT_4K,
+ end >> IOMMU_PAGE_SHIFT_4K);
+
+ table_group->tables[0] = tbl;
+
+ mutex_unlock(&dma_win_init_mutex);
+
+ goto exit;
+ }
+ }
+ }
+
+ ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+ &ddw_avail[0], DDW_APPLICABLE_SIZE);
+ if (ret) {
+ dev_info(&pdev->dev, "ibm,ddw-applicable not found\n");
+ goto out_failed;
+ }
+ ret = -ENODEV;
+
+ pr_err("%s: Calling query %pOF\n", __func__, pdn);
+ ret = query_ddw(pdev, ddw_avail, &query, pdn);
+ if (ret)
+ goto out_failed;
+ ret = -ENODEV;
+
+ len = window_shift;
+ if (query.largest_available_block < (1ULL << (len - page_shift))) {
+ dev_dbg(&pdev->dev, "can't map window 0x%llx with %llu %llu-sized pages\n",
+ 1ULL << len, query.largest_available_block,
+ 1ULL << page_shift);
+ ret = -EINVAL; /* Retry with smaller window size */
+ goto out_unlock;
+ }
+
+ if (create_ddw(pdev, ddw_avail, &create, page_shift, len)) {
+ pr_err("%s: Create ddw failed %pOF\n", __func__, pdn);
+ goto out_failed;
+ }
+
+ win_addr = ((u64)create.addr_hi << 32) | create.addr_lo;
+ win64 = ddw_property_create(DMA64_PROPNAME, create.liobn, win_addr, page_shift, len);
+ if (!win64)
+ goto remove_window;
+
+ ret = of_add_property(pdn, win64);
+ if (ret) {
+ dev_err(&pdev->dev, "unable to add DMA window property for %pOF: %ld", pdn, ret);
+ goto free_property;
+ }
+ ret = -ENODEV;
+
+ window = ddw_list_new_entry(pdn, win64->value);
+ if (!window)
+ goto remove_property;
+
+ window->direct = false;
+
+ for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
+ const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
+
+ /* Look for MMIO32 */
+ if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
+ start = pci->phb->mem_resources[i].start;
+ end = pci->phb->mem_resources[i].end;
+ break;
+ }
+ }
+
+ /* New table for using DDW instead of the default DMA window */
+ iommu_table_setparms_common(tbl, pci->phb->bus->number, create.liobn, win_addr,
+ 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
+ iommu_init_table(tbl, pci->phb->node, start >> page_shift, end >> page_shift);
+
+ pci->table_group->tables[num] = tbl;
+ set_iommu_table_base(&pdev->dev, tbl);
+ pdev->dev.archdata.dma_offset = win_addr;
+
+ spin_lock(&dma_win_list_lock);
+ list_add(&window->list, &dma_win_list);
+ spin_unlock(&dma_win_list_lock);
+
+ mutex_unlock(&dma_win_init_mutex);
+
+ goto exit;
+
+remove_property:
+ of_remove_property(pdn, win64);
+free_property:
+ kfree(win64->name);
+ kfree(win64->value);
+ kfree(win64);
+remove_window:
+ __remove_dma_window(pdn, ddw_avail, create.liobn);
+
+out_failed:
+ fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
+ if (!fpdn)
+ goto out_unlock;
+ fpdn->pdn = pdn;
+ list_add(&fpdn->list, &failed_ddw_pdn_list);
+
+out_unlock:
+ mutex_unlock(&dma_win_init_mutex);
+
+ return ret;
+exit:
+ /* Allocate the userspace view */
+ pseries_tce_iommu_userspace_view_alloc(tbl);
+ tbl->it_allocated_size = spapr_tce_get_table_size(page_shift, window_size, levels);
+
+ *ptbl = iommu_tce_table_get(tbl);
+
+ return 0;
+}
+
+static bool is_default_window_table(struct iommu_table_group *table_group, struct iommu_table *tbl)
+{
+ if (((tbl->it_size << tbl->it_page_shift) <= table_group->tce32_size) &&
+ (tbl->it_page_shift == IOMMU_PAGE_SHIFT_4K))
+ return true;
+
+ return false;
+}
+
+static long spapr_tce_set_window(struct iommu_table_group *table_group,
+ int num, struct iommu_table *tbl)
+{
+ return tbl == table_group->tables[num] ? 0 : -EPERM;
+}
+
+static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
+{
+ struct pci_dev *pdev = iommu_group_get_first_pci_dev(table_group->group);
+ struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
+ struct iommu_table *tbl = table_group->tables[num];
+ struct failed_ddw_pdn *fpdn;
+ struct dma_win *window;
+ const char *win_name;
+ int ret = -ENODEV;
+
+ if (!tbl) /* The table was never created OR window was never opened */
+ return 0;
+
+ mutex_lock(&dma_win_init_mutex);
+
+ if ((num == 0) && is_default_window_table(table_group, tbl))
+ win_name = "ibm,dma-window";
+ else
+ win_name = DMA64_PROPNAME;
+
+ pdn = pci_dma_find(dn, NULL);
+ if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+ dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+ goto out_failed;
+ }
+
+ /* Dont clear the TCEs, User should have done it */
+ if (remove_dma_window_named(pdn, true, win_name, false)) {
+ pr_err("%s: The existing DDW removal failed for node %pOF\n", __func__, pdn);
+ goto out_failed; /* Could not remove it either! */
+ }
+
+ if (strcmp(win_name, DMA64_PROPNAME) == 0) {
+ spin_lock(&dma_win_list_lock);
+ list_for_each_entry(window, &dma_win_list, list) {
+ if (window->device == pdn) {
+ list_del(&window->list);
+ kfree(window);
+ break;
+ }
+ }
+ spin_unlock(&dma_win_list_lock);
+ }
+
+ iommu_tce_table_put(table_group->tables[num]);
+ table_group->tables[num] = NULL;
+
+ ret = 0;
+
+ goto out_unlock;
+
+out_failed:
+ fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
+ if (!fpdn)
+ goto out_unlock;
+ fpdn->pdn = pdn;
+ list_add(&fpdn->list, &failed_ddw_pdn_list);
+
+out_unlock:
+ mutex_unlock(&dma_win_init_mutex);
+
+ return ret;
+}
+
+static long spapr_tce_take_ownership(struct iommu_table_group *table_group, struct device *dev)
+{
+ struct iommu_table *tbl = table_group->tables[0];
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct device_node *dn = pci_device_to_OF_node(pdev);
+ struct device_node *pdn;
+
+ /* SRIOV VFs using direct map by the host driver OR multifunction devices
+ * where the ownership was taken on the attempt by the first function
+ */
+ if (!tbl && (table_group->max_dynamic_windows_supported != 1))
+ return 0;
+
+ mutex_lock(&dma_win_init_mutex);
+
+ pdn = pci_dma_find(dn, NULL);
+ if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+ dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+ mutex_unlock(&dma_win_init_mutex);
+ return -1;
+ }
+
+ /*
+ * Though rtas call reset-pe removes the DDW, it doesn't clear the entries on the table
+ * if there are any. In case of direct map, the entries will be left over, which
+ * is fine for PEs with 2 DMA windows where the second window is created with create-pe
+ * at which point the table is cleared. However, on VFs having only one DMA window, the
+ * default window would end up seeing the entries left over from the direct map done
+ * on the second window. So, remove the ddw explicitly so that clean_dma_window()
+ * cleans up the entries if any.
+ */
+ if (remove_dynamic_dma_windows(pdev, pdn)) {
+ dev_warn(&pdev->dev, "The existing DDW removal failed for node %pOF\n", pdn);
+ mutex_unlock(&dma_win_init_mutex);
+ return -1;
+ }
+
+ /* The table_group->tables[0] is not null now, it must be the default window
+ * Remove it, let the userspace create it as it needs.
+ */
+ if (table_group->tables[0]) {
+ remove_dma_window_named(pdn, true, "ibm,dma-window", true);
+ iommu_tce_table_put(tbl);
+ table_group->tables[0] = NULL;
+ }
+ set_iommu_table_base(dev, NULL);
+
+ mutex_unlock(&dma_win_init_mutex);
+
+ return 0;
+}
+
+static void spapr_tce_release_ownership(struct iommu_table_group *table_group, struct device *dev)
+{
+ struct iommu_table *tbl = table_group->tables[0];
+
+ if (tbl) { /* Default window already restored */
+ return;
+ }
+
+ mutex_lock(&dma_win_init_mutex);
+
+ /* Restore the default window */
+ pseries_setup_default_iommu_config(table_group, dev);
+
+ mutex_unlock(&dma_win_init_mutex);
+
+ return;
+}
+
+static struct iommu_table_group_ops spapr_tce_table_group_ops = {
+ .get_table_size = spapr_tce_get_table_size,
+ .create_table = spapr_tce_create_table,
+ .set_window = spapr_tce_set_window,
+ .unset_window = spapr_tce_unset_window,
+ .take_ownership = spapr_tce_take_ownership,
+ .release_ownership = spapr_tce_release_ownership,
+};
+#endif
+
static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
void *data)
{
@@ -1704,8 +2403,8 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
* we have to remove the property when releasing
* the device node.
*/
- if (remove_ddw(np, false, DIRECT64_PROPNAME))
- remove_ddw(np, false, DMA64_PROPNAME);
+ if (remove_dma_window_named(np, false, DIRECT64_PROPNAME, true))
+ remove_dma_window_named(np, false, DMA64_PROPNAME, true);
if (pci && pci->table_group)
iommu_pseries_free_group(pci->table_group,
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 096d09ed89f6..431be156ca9b 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -61,11 +61,3 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
} else
xics_kexec_teardown_cpu(secondary);
}
-
-void pseries_machine_kexec(struct kimage *image)
-{
- if (firmware_has_feature(FW_FEATURE_SET_MODE))
- pseries_disable_reloc_on_exc();
-
- default_machine_kexec(image);
-}
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 4e9916bb03d7..6a415febc53b 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -16,6 +16,7 @@
#include <linux/export.h>
#include <linux/jump_label.h>
#include <linux/delay.h>
+#include <linux/seq_file.h>
#include <linux/stop_machine.h>
#include <linux/spinlock.h>
#include <linux/cpuhotplug.h>
@@ -169,7 +170,7 @@ struct vcpu_dispatch_data {
*/
#define NR_CPUS_H NR_CPUS
-DEFINE_RWLOCK(dtl_access_lock);
+DECLARE_RWSEM(dtl_access_lock);
static DEFINE_PER_CPU(struct vcpu_dispatch_data, vcpu_disp_data);
static DEFINE_PER_CPU(u64, dtl_entry_ridx);
static DEFINE_PER_CPU(struct dtl_worker, dtl_workers);
@@ -463,7 +464,7 @@ static int dtl_worker_enable(unsigned long *time_limit)
{
int rc = 0, state;
- if (!write_trylock(&dtl_access_lock)) {
+ if (!down_write_trylock(&dtl_access_lock)) {
rc = -EBUSY;
goto out;
}
@@ -479,7 +480,7 @@ static int dtl_worker_enable(unsigned long *time_limit)
pr_err("vcpudispatch_stats: unable to setup workqueue for DTL processing\n");
free_dtl_buffers(time_limit);
reset_global_dtl_mask();
- write_unlock(&dtl_access_lock);
+ up_write(&dtl_access_lock);
rc = -EINVAL;
goto out;
}
@@ -494,7 +495,7 @@ static void dtl_worker_disable(unsigned long *time_limit)
cpuhp_remove_state(dtl_worker_state);
free_dtl_buffers(time_limit);
reset_global_dtl_mask();
- write_unlock(&dtl_access_lock);
+ up_write(&dtl_access_lock);
}
static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p,
@@ -1886,10 +1887,10 @@ out:
* h_get_mpp
* H_GET_MPP hcall returns info in 7 parms
*/
-int h_get_mpp(struct hvcall_mpp_data *mpp_data)
+long h_get_mpp(struct hvcall_mpp_data *mpp_data)
{
- int rc;
- unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+ long rc;
rc = plpar_hcall9(H_GET_MPP, retbuf);
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 1c151d77e74b..cc22924f159f 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -29,7 +29,6 @@
#include <asm/firmware.h>
#include <asm/rtas.h>
#include <asm/time.h>
-#include <asm/vdso_datapage.h>
#include <asm/vio.h>
#include <asm/mmu.h>
#include <asm/machdep.h>
@@ -113,8 +112,8 @@ struct hvcall_ppp_data {
*/
static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
{
- unsigned long rc;
- unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+ long rc;
rc = plpar_hcall9(H_GET_PPP, retbuf);
@@ -170,20 +169,24 @@ out:
kfree(buf);
}
-static unsigned h_pic(unsigned long *pool_idle_time,
- unsigned long *num_procs)
+static long h_pic(unsigned long *pool_idle_time,
+ unsigned long *num_procs)
{
- unsigned long rc;
- unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+ long rc;
+ unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = {0};
rc = plpar_hcall(H_PIC, retbuf);
- *pool_idle_time = retbuf[0];
- *num_procs = retbuf[1];
+ if (pool_idle_time)
+ *pool_idle_time = retbuf[0];
+ if (num_procs)
+ *num_procs = retbuf[1];
return rc;
}
+unsigned long boot_pool_idle_time;
+
/*
* parse_ppp_data
* Parse out the data returned from h_get_ppp and h_pic
@@ -193,7 +196,7 @@ static void parse_ppp_data(struct seq_file *m)
struct hvcall_ppp_data ppp_data;
struct device_node *root;
const __be32 *perf_level;
- int rc;
+ long rc;
rc = h_get_ppp(&ppp_data);
if (rc)
@@ -215,9 +218,15 @@ static void parse_ppp_data(struct seq_file *m)
seq_printf(m, "pool_capacity=%d\n",
ppp_data.active_procs_in_pool * 100);
- h_pic(&pool_idle_time, &pool_procs);
- seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
- seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+ /* In case h_pic call is not successful, this would result in
+ * APP values being wrong in tools like lparstat.
+ */
+
+ if (h_pic(&pool_idle_time, &pool_procs) == H_SUCCESS) {
+ seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
+ seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+ seq_printf(m, "boot_pool_idle_time=%ld\n", boot_pool_idle_time);
+ }
}
seq_printf(m, "unallocated_capacity_weight=%d\n",
@@ -346,9 +355,13 @@ static int read_rtas_lpar_name(struct seq_file *m)
*/
static int read_dt_lpar_name(struct seq_file *m)
{
+ struct device_node *root = of_find_node_by_path("/");
const char *name;
+ int ret;
- if (of_property_read_string(of_root, "ibm,partition-name", &name))
+ ret = of_property_read_string(root, "ibm,partition-name", &name);
+ of_node_put(root);
+ if (ret)
return -ENOENT;
seq_printf(m, "partition_name=%s\n", name);
@@ -357,8 +370,8 @@ static int read_dt_lpar_name(struct seq_file *m)
static void read_lpar_name(struct seq_file *m)
{
- if (read_rtas_lpar_name(m) && read_dt_lpar_name(m))
- pr_err_once("Error can't get the LPAR name");
+ if (read_rtas_lpar_name(m))
+ read_dt_lpar_name(m);
}
#define SPLPAR_MAXLENGTH 1026*(sizeof(char))
@@ -516,7 +529,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL);
if (lrdrp == NULL) {
- partition_potential_processors = vdso_data->processorCount;
+ partition_potential_processors = num_possible_cpus();
} else {
partition_potential_processors = be32_to_cpup(lrdrp + 4);
}
@@ -539,7 +552,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
} else { /* non SPLPAR case */
seq_printf(m, "system_active_processors=%d\n",
- partition_potential_processors);
+ partition_active_processors);
seq_printf(m, "system_potential_processors=%d\n",
partition_potential_processors);
@@ -788,6 +801,7 @@ static const struct proc_ops lparcfg_proc_ops = {
static int __init lparcfg_init(void)
{
umode_t mode = 0444;
+ long retval;
/* Allow writing if we have FW_FEATURE_SPLPAR */
if (firmware_has_feature(FW_FEATURE_SPLPAR))
@@ -797,6 +811,16 @@ static int __init lparcfg_init(void)
printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
return -EIO;
}
+
+ /* If this call fails, it would result in APP values
+ * being wrong for since boot reports of lparstat
+ */
+ retval = h_pic(&boot_pool_idle_time, NULL);
+
+ if (retval != H_SUCCESS)
+ pr_debug("H_PIC failed during lparcfg init retval: %ld\n",
+ retval);
+
return 0;
}
machine_device_initcall(pseries, lparcfg_init);
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 1798f0f14d58..62bd8e2d5d4c 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -53,7 +53,7 @@ struct update_props_workarea {
static unsigned int nmi_wd_lpm_factor = 200;
#ifdef CONFIG_SYSCTL
-static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
+static const struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
{
.procname = "nmi_wd_lpm_factor",
.data = &nmi_wd_lpm_factor,
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 423ee1d5bd94..fdc2f7f38dc9 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -9,6 +9,7 @@
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/msi.h>
+#include <linux/seq_file.h>
#include <asm/rtas.h>
#include <asm/hw_irq.h>
@@ -26,6 +27,7 @@ static int query_token, change_token;
#define RTAS_CHANGE_MSI_FN 3
#define RTAS_CHANGE_MSIX_FN 4
#define RTAS_CHANGE_32MSI_FN 5
+#define RTAS_CHANGE_32MSIX_FN 6
/* RTAS Helpers */
@@ -41,7 +43,7 @@ static int rtas_change_msi(struct pci_dn *pdn, u32 func, u32 num_irqs)
seq_num = 1;
do {
if (func == RTAS_CHANGE_MSI_FN || func == RTAS_CHANGE_MSIX_FN ||
- func == RTAS_CHANGE_32MSI_FN)
+ func == RTAS_CHANGE_32MSI_FN || func == RTAS_CHANGE_32MSIX_FN)
rc = rtas_call(change_token, 6, 4, rtas_ret, addr,
BUID_HI(buid), BUID_LO(buid),
func, num_irqs, seq_num);
@@ -406,8 +408,12 @@ again:
if (use_32bit_msi_hack && rc > 0)
rtas_hack_32bit_msi_gen2(pdev);
- } else
- rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec);
+ } else {
+ if (pdev->no_64bit_msi)
+ rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSIX_FN, nvec);
+ else
+ rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec);
+ }
if (rc != nvec) {
if (nvec != nvec_in) {
diff --git a/arch/powerpc/platforms/pseries/papr-vpd.c b/arch/powerpc/platforms/pseries/papr-vpd.c
index c29e85db5f35..1574176e3ffc 100644
--- a/arch/powerpc/platforms/pseries/papr-vpd.c
+++ b/arch/powerpc/platforms/pseries/papr-vpd.c
@@ -156,10 +156,7 @@ static int vpd_blob_extend(struct vpd_blob *blob, const char *data, size_t len)
const char *old_ptr = blob->data;
char *new_ptr;
- new_ptr = old_ptr ?
- kvrealloc(old_ptr, old_len, new_len, GFP_KERNEL_ACCOUNT) :
- kvmalloc(len, GFP_KERNEL_ACCOUNT);
-
+ new_ptr = kvrealloc(old_ptr, new_len, GFP_KERNEL_ACCOUNT);
if (!new_ptr)
return -ENOMEM;
diff --git a/arch/powerpc/platforms/pseries/papr_platform_attributes.c b/arch/powerpc/platforms/pseries/papr_platform_attributes.c
index 526c621b098b..eea2041b270b 100644
--- a/arch/powerpc/platforms/pseries/papr_platform_attributes.c
+++ b/arch/powerpc/platforms/pseries/papr_platform_attributes.c
@@ -101,10 +101,12 @@ retry:
esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * max_esi_attrs);
temp_buf = krealloc(buf, esi_buf_size, GFP_KERNEL);
- if (temp_buf)
+ if (temp_buf) {
buf = temp_buf;
- else
- return -ENOMEM;
+ } else {
+ ret = -ENOMEM;
+ goto out_buf;
+ }
goto retry;
}
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 1a53e048ceb7..f7c9271bda58 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -6,6 +6,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/ioport.h>
+#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/ndctl.h>
#include <linux/sched.h>
@@ -16,9 +17,10 @@
#include <linux/nd.h>
#include <asm/plpar_wrappers.h>
-#include <asm/papr_pdsm.h>
+#include <uapi/linux/papr_pdsm.h>
+#include <linux/papr_scm.h>
#include <asm/mce.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/perf_event.h>
#define BIND_ANY_ADDR (~0ul)
@@ -29,46 +31,6 @@
(1ul << ND_CMD_SET_CONFIG_DATA) | \
(1ul << ND_CMD_CALL))
-/* DIMM health bitmap indicators */
-/* SCM device is unable to persist memory contents */
-#define PAPR_PMEM_UNARMED (1ULL << (63 - 0))
-/* SCM device failed to persist memory contents */
-#define PAPR_PMEM_SHUTDOWN_DIRTY (1ULL << (63 - 1))
-/* SCM device contents are persisted from previous IPL */
-#define PAPR_PMEM_SHUTDOWN_CLEAN (1ULL << (63 - 2))
-/* SCM device contents are not persisted from previous IPL */
-#define PAPR_PMEM_EMPTY (1ULL << (63 - 3))
-/* SCM device memory life remaining is critically low */
-#define PAPR_PMEM_HEALTH_CRITICAL (1ULL << (63 - 4))
-/* SCM device will be garded off next IPL due to failure */
-#define PAPR_PMEM_HEALTH_FATAL (1ULL << (63 - 5))
-/* SCM contents cannot persist due to current platform health status */
-#define PAPR_PMEM_HEALTH_UNHEALTHY (1ULL << (63 - 6))
-/* SCM device is unable to persist memory contents in certain conditions */
-#define PAPR_PMEM_HEALTH_NON_CRITICAL (1ULL << (63 - 7))
-/* SCM device is encrypted */
-#define PAPR_PMEM_ENCRYPTED (1ULL << (63 - 8))
-/* SCM device has been scrubbed and locked */
-#define PAPR_PMEM_SCRUBBED_AND_LOCKED (1ULL << (63 - 9))
-
-/* Bits status indicators for health bitmap indicating unarmed dimm */
-#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED | \
- PAPR_PMEM_HEALTH_UNHEALTHY)
-
-/* Bits status indicators for health bitmap indicating unflushed dimm */
-#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY)
-
-/* Bits status indicators for health bitmap indicating unrestored dimm */
-#define PAPR_PMEM_BAD_RESTORE_MASK (PAPR_PMEM_EMPTY)
-
-/* Bit status indicators for smart event notification */
-#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \
- PAPR_PMEM_HEALTH_FATAL | \
- PAPR_PMEM_HEALTH_UNHEALTHY)
-
-#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS)
-#define PAPR_SCM_PERF_STATS_VERSION 0x1
-
/* Struct holding a single performance metric */
struct papr_scm_perf_stat {
u8 stat_id[8];
@@ -582,7 +544,7 @@ static int drc_pmem_query_health(struct papr_scm_priv *p)
/* Jiffies offset for which the health data is assumed to be same */
cache_timeout = p->lasthealth_jiffies +
- msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000);
+ secs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL);
/* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */
if (time_after(jiffies, cache_timeout))
@@ -1521,7 +1483,7 @@ err: kfree(p);
return rc;
}
-static int papr_scm_remove(struct platform_device *pdev)
+static void papr_scm_remove(struct platform_device *pdev)
{
struct papr_scm_priv *p = platform_get_drvdata(pdev);
@@ -1538,8 +1500,6 @@ static int papr_scm_remove(struct platform_device *pdev)
pdev->archdata.priv = NULL;
kfree(p->bus_desc.provider_name);
kfree(p);
-
- return 0;
}
static const struct of_device_id papr_scm_match[] = {
@@ -1577,5 +1537,6 @@ static void __exit papr_scm_exit(void)
module_exit(papr_scm_exit);
MODULE_DEVICE_TABLE(of, papr_scm_match);
+MODULE_DESCRIPTION("PAPR Storage Class Memory interface driver");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("IBM Corporation");
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 1772ae3d193d..6dbc73eb2ca2 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -18,33 +18,6 @@
#include <asm/pci.h>
#include "pseries.h"
-#if 0
-void pcibios_name_device(struct pci_dev *dev)
-{
- struct device_node *dn;
-
- /*
- * Add IBM loc code (slot) as a prefix to the device names for service
- */
- dn = pci_device_to_OF_node(dev);
- if (dn) {
- const char *loc_code = of_get_property(dn, "ibm,loc-code",
- NULL);
- if (loc_code) {
- int loc_len = strlen(loc_code);
- if (loc_len < sizeof(dev->dev.name)) {
- memmove(dev->dev.name+loc_len+1, dev->dev.name,
- sizeof(dev->dev.name)-loc_len-1);
- memcpy(dev->dev.name, loc_code, loc_len);
- dev->dev.name[loc_len] = ' ';
- dev->dev.name[sizeof(dev->dev.name)-1] = '\0';
- }
- }
- }
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_name_device);
-#endif
-
#ifdef CONFIG_PCI_IOV
#define MAX_VFS_FOR_MAP_PE 256
struct pe_map_bar_entry {
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 4448386268d9..52e2623a741d 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -11,6 +11,7 @@
#include <linux/pci.h>
#include <linux/export.h>
+#include <linux/node.h>
#include <asm/pci-bridge.h>
#include <asm/ppc-pci.h>
#include <asm/firmware.h>
@@ -21,9 +22,22 @@
struct pci_controller *init_phb_dynamic(struct device_node *dn)
{
struct pci_controller *phb;
+ int nid;
pr_debug("PCI: Initializing new hotplug PHB %pOF\n", dn);
+ nid = of_node_to_nid(dn);
+ if (likely((nid) >= 0)) {
+ if (!node_online(nid)) {
+ if (__register_one_node(nid)) {
+ pr_err("PCI: Failed to register node %d\n", nid);
+ } else {
+ update_numa_distance(dn);
+ node_set_online(nid);
+ }
+ }
+ }
+
phb = pcibios_alloc_controller(dn);
if (!phb)
return NULL;
diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c
index febe18f251d0..b1667ed05f98 100644
--- a/arch/powerpc/platforms/pseries/plpks.c
+++ b/arch/powerpc/platforms/pseries/plpks.c
@@ -415,8 +415,7 @@ static int plpks_confirm_object_flushed(struct label *label,
break;
}
- usleep_range(PLPKS_FLUSH_SLEEP,
- PLPKS_FLUSH_SLEEP + PLPKS_FLUSH_SLEEP_RANGE);
+ fsleep(PLPKS_FLUSH_SLEEP);
timeout = timeout + PLPKS_FLUSH_SLEEP;
} while (timeout < PLPKS_MAX_TIMEOUT);
@@ -464,9 +463,10 @@ int plpks_signed_update_var(struct plpks_var *var, u64 flags)
continuetoken = retbuf[0];
if (pseries_status_to_err(rc) == -EBUSY) {
- int delay_ms = get_longbusy_msecs(rc);
- mdelay(delay_ms);
- timeout += delay_ms;
+ int delay_us = get_longbusy_msecs(rc) * 1000;
+
+ fsleep(delay_us);
+ timeout += delay_us;
}
rc = pseries_status_to_err(rc);
} while (rc == -EBUSY && timeout < PLPKS_MAX_TIMEOUT);
@@ -683,7 +683,7 @@ void __init plpks_early_init_devtree(void)
out:
fdt_nop_property(fdt, chosen_node, "ibm,plpks-pw");
// Since we've cleared the password, we must update the FDT checksum
- early_init_dt_verify(fdt);
+ early_init_dt_verify(fdt, __pa(fdt));
}
static __init int pseries_plpks_init(void)
diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c
index 3c290b9ed01b..0f1d45f32e4a 100644
--- a/arch/powerpc/platforms/pseries/pmem.c
+++ b/arch/powerpc/platforms/pseries/pmem.c
@@ -121,7 +121,7 @@ int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog)
return -EINVAL;
}
- drc_index = hp_elog->_drc_u.drc_index;
+ drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index);
lock_device_hotplug();
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index bba4ad192b0f..3968a6970fa8 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -38,7 +38,6 @@ static inline void smp_init_pseries(void) { }
#endif
extern void pseries_kexec_cpu_down(int crash_shutdown, int secondary);
-void pseries_machine_kexec(struct kimage *image);
extern void pSeries_final_fixup(void);
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c
index b5853e9fcc3c..eceb3289383e 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.c
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
@@ -18,6 +18,7 @@
#include <asm/page.h>
#include <asm/rtas.h>
+#include <asm/setup.h>
#include <asm/fadump.h>
#include <asm/fadump-internal.h>
@@ -29,9 +30,6 @@ static const struct rtas_fadump_mem_struct *fdm_active;
static void rtas_fadump_update_config(struct fw_dump *fadump_conf,
const struct rtas_fadump_mem_struct *fdm)
{
- fadump_conf->boot_mem_dest_addr =
- be64_to_cpu(fdm->rmr_region.destination_address);
-
fadump_conf->fadumphdr_addr = (fadump_conf->boot_mem_dest_addr +
fadump_conf->boot_memory_size);
}
@@ -43,20 +41,56 @@ static void rtas_fadump_update_config(struct fw_dump *fadump_conf,
static void __init rtas_fadump_get_config(struct fw_dump *fadump_conf,
const struct rtas_fadump_mem_struct *fdm)
{
- fadump_conf->boot_mem_addr[0] =
- be64_to_cpu(fdm->rmr_region.source_address);
- fadump_conf->boot_mem_sz[0] = be64_to_cpu(fdm->rmr_region.source_len);
- fadump_conf->boot_memory_size = fadump_conf->boot_mem_sz[0];
+ unsigned long base, size, last_end, hole_size;
- fadump_conf->boot_mem_top = fadump_conf->boot_memory_size;
- fadump_conf->boot_mem_regs_cnt = 1;
+ last_end = 0;
+ hole_size = 0;
+ fadump_conf->boot_memory_size = 0;
+ fadump_conf->boot_mem_regs_cnt = 0;
+ pr_debug("Boot memory regions:\n");
+ for (int i = 0; i < be16_to_cpu(fdm->header.dump_num_sections); i++) {
+ int type = be16_to_cpu(fdm->rgn[i].source_data_type);
+ u64 addr;
- /*
- * Start address of reserve dump area (permanent reservation) for
- * re-registering FADump after dump capture.
- */
- fadump_conf->reserve_dump_area_start =
- be64_to_cpu(fdm->cpu_state_data.destination_address);
+ switch (type) {
+ case RTAS_FADUMP_CPU_STATE_DATA:
+ addr = be64_to_cpu(fdm->rgn[i].destination_address);
+
+ fadump_conf->cpu_state_dest_vaddr = (u64)__va(addr);
+ /*
+ * Start address of reserve dump area (permanent reservation) for
+ * re-registering FADump after dump capture.
+ */
+ fadump_conf->reserve_dump_area_start = addr;
+ break;
+ case RTAS_FADUMP_HPTE_REGION:
+ /* Not processed currently. */
+ break;
+ case RTAS_FADUMP_REAL_MODE_REGION:
+ base = be64_to_cpu(fdm->rgn[i].source_address);
+ size = be64_to_cpu(fdm->rgn[i].source_len);
+ pr_debug("\t[%03d] base: 0x%lx, size: 0x%lx\n", i, base, size);
+ if (!base) {
+ fadump_conf->boot_mem_dest_addr =
+ be64_to_cpu(fdm->rgn[i].destination_address);
+ }
+
+ fadump_conf->boot_mem_addr[fadump_conf->boot_mem_regs_cnt] = base;
+ fadump_conf->boot_mem_sz[fadump_conf->boot_mem_regs_cnt] = size;
+ fadump_conf->boot_memory_size += size;
+ hole_size += (base - last_end);
+ last_end = base + size;
+ fadump_conf->boot_mem_regs_cnt++;
+ break;
+ case RTAS_FADUMP_PARAM_AREA:
+ fadump_conf->param_area = be64_to_cpu(fdm->rgn[i].destination_address);
+ break;
+ default:
+ pr_warn("Section type %d unsupported on this kernel. Ignoring!\n", type);
+ break;
+ }
+ }
+ fadump_conf->boot_mem_top = fadump_conf->boot_memory_size + hole_size;
rtas_fadump_update_config(fadump_conf, fdm);
}
@@ -64,16 +98,15 @@ static void __init rtas_fadump_get_config(struct fw_dump *fadump_conf,
static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
{
u64 addr = fadump_conf->reserve_dump_area_start;
+ u16 sec_cnt = 0;
memset(&fdm, 0, sizeof(struct rtas_fadump_mem_struct));
addr = addr & PAGE_MASK;
fdm.header.dump_format_version = cpu_to_be32(0x00000001);
- fdm.header.dump_num_sections = cpu_to_be16(3);
fdm.header.dump_status_flag = 0;
fdm.header.offset_first_dump_section =
- cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct,
- cpu_state_data));
+ cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct, rgn));
/*
* Fields for disk dump option.
@@ -89,25 +122,22 @@ static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
/* Kernel dump sections */
/* cpu state data section. */
- fdm.cpu_state_data.request_flag =
- cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
- fdm.cpu_state_data.source_data_type =
- cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA);
- fdm.cpu_state_data.source_address = 0;
- fdm.cpu_state_data.source_len =
- cpu_to_be64(fadump_conf->cpu_state_data_size);
- fdm.cpu_state_data.destination_address = cpu_to_be64(addr);
+ fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+ fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA);
+ fdm.rgn[sec_cnt].source_address = 0;
+ fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->cpu_state_data_size);
+ fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr);
addr += fadump_conf->cpu_state_data_size;
+ sec_cnt++;
/* hpte region section */
- fdm.hpte_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
- fdm.hpte_region.source_data_type =
- cpu_to_be16(RTAS_FADUMP_HPTE_REGION);
- fdm.hpte_region.source_address = 0;
- fdm.hpte_region.source_len =
- cpu_to_be64(fadump_conf->hpte_region_size);
- fdm.hpte_region.destination_address = cpu_to_be64(addr);
+ fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+ fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_HPTE_REGION);
+ fdm.rgn[sec_cnt].source_address = 0;
+ fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->hpte_region_size);
+ fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr);
addr += fadump_conf->hpte_region_size;
+ sec_cnt++;
/*
* Align boot memory area destination address to page boundary to
@@ -115,14 +145,29 @@ static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
*/
addr = PAGE_ALIGN(addr);
- /* RMA region section */
- fdm.rmr_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
- fdm.rmr_region.source_data_type =
- cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION);
- fdm.rmr_region.source_address = cpu_to_be64(0);
- fdm.rmr_region.source_len = cpu_to_be64(fadump_conf->boot_memory_size);
- fdm.rmr_region.destination_address = cpu_to_be64(addr);
- addr += fadump_conf->boot_memory_size;
+ /* First boot memory region destination address */
+ fadump_conf->boot_mem_dest_addr = addr;
+ for (int i = 0; i < fadump_conf->boot_mem_regs_cnt; i++) {
+ /* Boot memory regions */
+ fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+ fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION);
+ fdm.rgn[sec_cnt].source_address = cpu_to_be64(fadump_conf->boot_mem_addr[i]);
+ fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->boot_mem_sz[i]);
+ fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr);
+ addr += fadump_conf->boot_mem_sz[i];
+ sec_cnt++;
+ }
+
+ /* Parameters area */
+ if (fadump_conf->param_area) {
+ fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+ fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_PARAM_AREA);
+ fdm.rgn[sec_cnt].source_address = cpu_to_be64(fadump_conf->param_area);
+ fdm.rgn[sec_cnt].source_len = cpu_to_be64(COMMAND_LINE_SIZE);
+ fdm.rgn[sec_cnt].destination_address = cpu_to_be64(fadump_conf->param_area);
+ sec_cnt++;
+ }
+ fdm.header.dump_num_sections = cpu_to_be16(sec_cnt);
rtas_fadump_update_config(fadump_conf, &fdm);
@@ -136,14 +181,21 @@ static u64 rtas_fadump_get_bootmem_min(void)
static int rtas_fadump_register(struct fw_dump *fadump_conf)
{
- unsigned int wait_time;
+ unsigned int wait_time, fdm_size;
int rc, err = -EIO;
+ /*
+ * Platform requires the exact size of the Dump Memory Structure.
+ * Avoid including any unused rgns in the calculation, as this
+ * could result in a parameter error (-3) from the platform.
+ */
+ fdm_size = sizeof(struct rtas_fadump_section_header);
+ fdm_size += be16_to_cpu(fdm.header.dump_num_sections) * sizeof(struct rtas_fadump_section);
+
/* TODO: Add upper time limit for the delay */
do {
rc = rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1,
- NULL, FADUMP_REGISTER, &fdm,
- sizeof(struct rtas_fadump_mem_struct));
+ NULL, FADUMP_REGISTER, &fdm, fdm_size);
wait_time = rtas_busy_delay_time(rc);
if (wait_time)
@@ -161,9 +213,7 @@ static int rtas_fadump_register(struct fw_dump *fadump_conf)
pr_err("Failed to register. Hardware Error(%d).\n", rc);
break;
case -3:
- if (!is_fadump_boot_mem_contiguous())
- pr_err("Can't have holes in boot memory area.\n");
- else if (!is_fadump_reserved_mem_contiguous())
+ if (!is_fadump_reserved_mem_contiguous())
pr_err("Can't have holes in reserved memory area.\n");
pr_err("Failed to register. Parameter Error(%d).\n", rc);
@@ -316,11 +366,9 @@ static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf)
u32 num_cpus, *note_buf;
int i, rc = 0, cpu = 0;
struct pt_regs regs;
- unsigned long addr;
void *vaddr;
- addr = be64_to_cpu(fdm_active->cpu_state_data.destination_address);
- vaddr = __va(addr);
+ vaddr = (void *)fadump_conf->cpu_state_dest_vaddr;
reg_header = vaddr;
if (be64_to_cpu(reg_header->magic_number) !=
@@ -375,11 +423,8 @@ static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf)
}
final_note(note_buf);
- if (fdh) {
- pr_debug("Updating elfcore header (%llx) with cpu notes\n",
- fdh->elfcorehdr_addr);
- fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr));
- }
+ pr_debug("Updating elfcore header (%llx) with cpu notes\n", fadump_conf->elfcorehdr_addr);
+ fadump_update_elfcore_header((char *)fadump_conf->elfcorehdr_addr);
return 0;
error_out:
@@ -389,57 +434,66 @@ error_out:
}
/*
- * Validate and process the dump data stored by firmware before exporting
- * it through '/proc/vmcore'.
+ * Validate and process the dump data stored by the firmware, and update
+ * the CPU notes of elfcorehdr.
*/
static int __init rtas_fadump_process(struct fw_dump *fadump_conf)
{
- struct fadump_crash_info_header *fdh;
- int rc = 0;
-
if (!fdm_active || !fadump_conf->fadumphdr_addr)
return -EINVAL;
/* Check if the dump data is valid. */
- if ((be16_to_cpu(fdm_active->header.dump_status_flag) ==
- RTAS_FADUMP_ERROR_FLAG) ||
- (fdm_active->cpu_state_data.error_flags != 0) ||
- (fdm_active->rmr_region.error_flags != 0)) {
- pr_err("Dump taken by platform is not valid\n");
- return -EINVAL;
- }
- if ((fdm_active->rmr_region.bytes_dumped !=
- fdm_active->rmr_region.source_len) ||
- !fdm_active->cpu_state_data.bytes_dumped) {
- pr_err("Dump taken by platform is incomplete\n");
- return -EINVAL;
- }
+ for (int i = 0; i < be16_to_cpu(fdm_active->header.dump_num_sections); i++) {
+ int type = be16_to_cpu(fdm_active->rgn[i].source_data_type);
+ int rc = 0;
- /* Validate the fadump crash info header */
- fdh = __va(fadump_conf->fadumphdr_addr);
- if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
- pr_err("Crash info header is not valid.\n");
- return -EINVAL;
+ switch (type) {
+ case RTAS_FADUMP_CPU_STATE_DATA:
+ case RTAS_FADUMP_HPTE_REGION:
+ case RTAS_FADUMP_REAL_MODE_REGION:
+ if (fdm_active->rgn[i].error_flags != 0) {
+ pr_err("Dump taken by platform is not valid (%d)\n", i);
+ rc = -EINVAL;
+ }
+ if (fdm_active->rgn[i].bytes_dumped != fdm_active->rgn[i].source_len) {
+ pr_err("Dump taken by platform is incomplete (%d)\n", i);
+ rc = -EINVAL;
+ }
+ if (rc) {
+ pr_warn("Region type: %u src addr: 0x%llx dest addr: 0x%llx\n",
+ be16_to_cpu(fdm_active->rgn[i].source_data_type),
+ be64_to_cpu(fdm_active->rgn[i].source_address),
+ be64_to_cpu(fdm_active->rgn[i].destination_address));
+ return rc;
+ }
+ break;
+ case RTAS_FADUMP_PARAM_AREA:
+ if (fdm_active->rgn[i].bytes_dumped != fdm_active->rgn[i].source_len ||
+ fdm_active->rgn[i].error_flags != 0) {
+ pr_warn("Failed to process additional parameters! Proceeding anyway..\n");
+ fadump_conf->param_area = 0;
+ }
+ break;
+ default:
+ /*
+ * If the first/crashed kernel added a new region type that the
+ * second/fadump kernel doesn't recognize, skip it and process
+ * assuming backward compatibility.
+ */
+ pr_warn("Unknown region found: type: %u src addr: 0x%llx dest addr: 0x%llx\n",
+ be16_to_cpu(fdm_active->rgn[i].source_data_type),
+ be64_to_cpu(fdm_active->rgn[i].source_address),
+ be64_to_cpu(fdm_active->rgn[i].destination_address));
+ break;
+ }
}
- rc = rtas_fadump_build_cpu_notes(fadump_conf);
- if (rc)
- return rc;
-
- /*
- * We are done validating dump info and elfcore header is now ready
- * to be exported. set elfcorehdr_addr so that vmcore module will
- * export the elfcore header through '/proc/vmcore'.
- */
- elfcorehdr_addr = fdh->elfcorehdr_addr;
-
- return 0;
+ return rtas_fadump_build_cpu_notes(fadump_conf);
}
static void rtas_fadump_region_show(struct fw_dump *fadump_conf,
struct seq_file *m)
{
- const struct rtas_fadump_section *cpu_data_section;
const struct rtas_fadump_mem_struct *fdm_ptr;
if (fdm_active)
@@ -447,27 +501,49 @@ static void rtas_fadump_region_show(struct fw_dump *fadump_conf,
else
fdm_ptr = &fdm;
- cpu_data_section = &(fdm_ptr->cpu_state_data);
- seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
- be64_to_cpu(cpu_data_section->destination_address),
- be64_to_cpu(cpu_data_section->destination_address) +
- be64_to_cpu(cpu_data_section->source_len) - 1,
- be64_to_cpu(cpu_data_section->source_len),
- be64_to_cpu(cpu_data_section->bytes_dumped));
-
- seq_printf(m, "HPTE:[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
- be64_to_cpu(fdm_ptr->hpte_region.destination_address),
- be64_to_cpu(fdm_ptr->hpte_region.destination_address) +
- be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1,
- be64_to_cpu(fdm_ptr->hpte_region.source_len),
- be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped));
-
- seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ",
- be64_to_cpu(fdm_ptr->rmr_region.source_address),
- be64_to_cpu(fdm_ptr->rmr_region.destination_address));
- seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n",
- be64_to_cpu(fdm_ptr->rmr_region.source_len),
- be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped));
+
+ for (int i = 0; i < be16_to_cpu(fdm_ptr->header.dump_num_sections); i++) {
+ int type = be16_to_cpu(fdm_ptr->rgn[i].source_data_type);
+
+ switch (type) {
+ case RTAS_FADUMP_CPU_STATE_DATA:
+ seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
+ be64_to_cpu(fdm_ptr->rgn[i].destination_address),
+ be64_to_cpu(fdm_ptr->rgn[i].destination_address) +
+ be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1,
+ be64_to_cpu(fdm_ptr->rgn[i].source_len),
+ be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped));
+ break;
+ case RTAS_FADUMP_HPTE_REGION:
+ seq_printf(m, "HPTE:[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
+ be64_to_cpu(fdm_ptr->rgn[i].destination_address),
+ be64_to_cpu(fdm_ptr->rgn[i].destination_address) +
+ be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1,
+ be64_to_cpu(fdm_ptr->rgn[i].source_len),
+ be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped));
+ break;
+ case RTAS_FADUMP_REAL_MODE_REGION:
+ seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ",
+ be64_to_cpu(fdm_ptr->rgn[i].source_address),
+ be64_to_cpu(fdm_ptr->rgn[i].destination_address));
+ seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n",
+ be64_to_cpu(fdm_ptr->rgn[i].source_len),
+ be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped));
+ break;
+ case RTAS_FADUMP_PARAM_AREA:
+ seq_printf(m, "\n[%#016llx-%#016llx]: cmdline append: '%s'\n",
+ be64_to_cpu(fdm_ptr->rgn[i].destination_address),
+ be64_to_cpu(fdm_ptr->rgn[i].destination_address) +
+ be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1,
+ (char *)__va(be64_to_cpu(fdm_ptr->rgn[i].destination_address)));
+ break;
+ default:
+ seq_printf(m, "Unknown region type %d : Src: %#016llx, Dest: %#016llx, ",
+ type, be64_to_cpu(fdm_ptr->rgn[i].source_address),
+ be64_to_cpu(fdm_ptr->rgn[i].destination_address));
+ break;
+ }
+ }
/* Dump is active. Show preserved area start address. */
if (fdm_active) {
@@ -483,6 +559,20 @@ static void rtas_fadump_trigger(struct fadump_crash_info_header *fdh,
rtas_os_term((char *)msg);
}
+/* FADUMP_MAX_MEM_REGS or lower */
+static int rtas_fadump_max_boot_mem_rgns(void)
+{
+ /*
+ * Version 1 of Kernel Assisted Dump Memory Structure (PAPR) supports 10 sections.
+ * With one each section taken for CPU state data & HPTE respectively, 8 sections
+ * can be used for boot memory regions.
+ *
+ * If new region(s) is(are) defined, maximum boot memory regions will decrease
+ * proportionally.
+ */
+ return RTAS_FADUMP_MAX_BOOT_MEM_REGS;
+}
+
static struct fadump_ops rtas_fadump_ops = {
.fadump_init_mem_struct = rtas_fadump_init_mem_struct,
.fadump_get_bootmem_min = rtas_fadump_get_bootmem_min,
@@ -492,6 +582,7 @@ static struct fadump_ops rtas_fadump_ops = {
.fadump_process = rtas_fadump_process,
.fadump_region_show = rtas_fadump_region_show,
.fadump_trigger = rtas_fadump_trigger,
+ .fadump_max_boot_mem_rgns = rtas_fadump_max_boot_mem_rgns,
};
void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
@@ -508,9 +599,10 @@ void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
if (!token)
return;
- fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token);
- fadump_conf->ops = &rtas_fadump_ops;
- fadump_conf->fadump_supported = 1;
+ fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token);
+ fadump_conf->ops = &rtas_fadump_ops;
+ fadump_conf->fadump_supported = 1;
+ fadump_conf->param_area_supported = 1;
/* Firmware supports 64-bit value for size, align it to pagesize. */
fadump_conf->max_copy_size = ALIGN_DOWN(U64_MAX, PAGE_SIZE);
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h
index fd59bd7ca9c3..c109abf6befd 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.h
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.h
@@ -23,12 +23,24 @@
#define RTAS_FADUMP_HPTE_REGION 0x0002
#define RTAS_FADUMP_REAL_MODE_REGION 0x0011
+/* OS defined sections */
+#define RTAS_FADUMP_PARAM_AREA 0x0100
+
/* Dump request flag */
#define RTAS_FADUMP_REQUEST_FLAG 0x00000001
/* Dump status flag */
#define RTAS_FADUMP_ERROR_FLAG 0x2000
+/*
+ * The Firmware Assisted Dump Memory structure supports a maximum of 10 sections
+ * in the dump memory structure. Presently, three sections are used for
+ * CPU state data, HPTE & Parameters area, while the remaining seven sections
+ * can be used for boot memory regions.
+ */
+#define MAX_SECTIONS 10
+#define RTAS_FADUMP_MAX_BOOT_MEM_REGS 7
+
/* Kernel Dump section info */
struct rtas_fadump_section {
__be32 request_flag;
@@ -61,20 +73,15 @@ struct rtas_fadump_section_header {
* Firmware Assisted dump memory structure. This structure is required for
* registering future kernel dump with power firmware through rtas call.
*
- * No disk dump option. Hence disk dump path string section is not included.
+ * In version 1, the platform permits one section header, dump-disk path
+ * and ten sections.
+ *
+ * Note: No disk dump option. Hence disk dump path string section is not
+ * included.
*/
struct rtas_fadump_mem_struct {
struct rtas_fadump_section_header header;
-
- /* Kernel dump sections */
- struct rtas_fadump_section cpu_state_data;
- struct rtas_fadump_section hpte_region;
-
- /*
- * TODO: Extend multiple boot memory regions support in the kernel
- * for this platform.
- */
- struct rtas_fadump_section rmr_region;
+ struct rtas_fadump_section rgn[MAX_SECTIONS];
};
/*
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index ecea85c74c43..b10a25325238 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -343,8 +343,8 @@ static int alloc_dispatch_log_kmem_cache(void)
{
void (*ctor)(void *) = get_dtl_cache_ctor();
- dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
- DISPATCH_LOG_BYTES, 0, ctor);
+ dtl_cache = kmem_cache_create_usercopy("dtl", DISPATCH_LOG_BYTES,
+ DISPATCH_LOG_BYTES, 0, 0, DISPATCH_LOG_BYTES, ctor);
if (!dtl_cache) {
pr_warn("Failed to create dispatch trace log buffer cache\n");
pr_warn("Stolen time statistics will be unreliable\n");
@@ -1029,9 +1029,11 @@ static void __init pseries_add_hw_description(void)
return;
}
- if (of_property_read_bool(of_root, "ibm,powervm-partition") ||
- of_property_read_bool(of_root, "ibm,fw-net-version"))
+ dn = of_find_node_by_path("/");
+ if (of_property_read_bool(dn, "ibm,powervm-partition") ||
+ of_property_read_bool(dn, "ibm,fw-net-version"))
seq_buf_printf(&ppc_hw_desc, "hv:phyp ");
+ of_node_put(dn);
}
/*
@@ -1091,7 +1093,11 @@ static void pseries_power_off(void)
static int __init pSeries_probe(void)
{
- if (!of_node_is_type(of_root, "chrp"))
+ struct device_node *root = of_find_node_by_path("/");
+ bool ret = of_node_is_type(root, "chrp");
+
+ of_node_put(root);
+ if (!ret)
return 0;
/* Cell blades firmware claims to be chrp while it's not. Until this
@@ -1153,7 +1159,6 @@ define_machine(pseries) {
.machine_check_exception = pSeries_machine_check_exception,
.machine_check_log_err = pSeries_machine_check_log_err,
#ifdef CONFIG_KEXEC_CORE
- .machine_kexec = pseries_machine_kexec,
.kexec_cpu_down = pseries_kexec_cpu_down,
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index c597711ef20a..db99725e752b 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -39,7 +39,7 @@
#include <asm/xive.h>
#include <asm/dbell.h>
#include <asm/plpar_wrappers.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/svm.h>
#include <asm/kvm_guest.h>
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index 3b4045d508ec..384c9dc1899a 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -8,6 +8,7 @@
#include <linux/mm.h>
#include <linux/memblock.h>
+#include <linux/mem_encrypt.h>
#include <linux/cc_platform.h>
#include <asm/machdep.h>
#include <asm/svm.h>
diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c
index f9f682724e77..9e05a0e99cad 100644
--- a/arch/powerpc/platforms/pseries/vas-sysfs.c
+++ b/arch/powerpc/platforms/pseries/vas-sysfs.c
@@ -162,13 +162,13 @@ static const struct sysfs_ops vas_sysfs_ops = {
.store = vas_type_store,
};
-static struct kobj_type vas_def_attr_type = {
+static const struct kobj_type vas_def_attr_type = {
.release = vas_type_release,
.sysfs_ops = &vas_sysfs_ops,
.default_groups = vas_def_capab_groups,
};
-static struct kobj_type vas_qos_attr_type = {
+static const struct kobj_type vas_qos_attr_type = {
.release = vas_type_release,
.sysfs_ops = &vas_sysfs_ops,
.default_groups = vas_qos_capab_groups,
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index 71d52a670d95..c25eb1a38185 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -38,7 +38,27 @@ static long hcall_return_busy_check(long rc)
{
/* Check if we are stalled for some time */
if (H_IS_LONG_BUSY(rc)) {
- msleep(get_longbusy_msecs(rc));
+ unsigned int ms;
+ /*
+ * Allocate, Modify and Deallocate HCALLs returns
+ * H_LONG_BUSY_ORDER_1_MSEC or H_LONG_BUSY_ORDER_10_MSEC
+ * for the long delay. So the sleep time should always
+ * be either 1 or 10msecs, but in case if the HCALL
+ * returns the long delay > 10 msecs, clamp the sleep
+ * time to 10msecs.
+ */
+ ms = clamp(get_longbusy_msecs(rc), 1, 10);
+
+ /*
+ * msleep() will often sleep at least 20 msecs even
+ * though the hypervisor suggests that the OS reissue
+ * HCALLs after 1 or 10msecs. Also the delay hint from
+ * the HCALL is just a suggestion. So OK to pause for
+ * less time than the hinted delay. Use usleep_range()
+ * to ensure we don't sleep much longer than actually
+ * needed.
+ */
+ usleep_range(ms * (USEC_PER_MSEC / 10), ms * USEC_PER_MSEC);
rc = H_BUSY;
} else if (rc == H_BUSY) {
cond_resched();
@@ -228,7 +248,7 @@ static irqreturn_t pseries_vas_irq_handler(int irq, void *data)
struct pseries_vas_window *txwin = data;
/*
- * The thread hanlder will process this interrupt if it is
+ * The thread handler will process this interrupt if it is
* already running.
*/
atomic_inc(&txwin->pending_faults);
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 2dc9cbc4bcd8..ac1d2d2c9a88 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -611,7 +611,7 @@ static const struct dma_map_ops vio_dma_mapping_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,
};
@@ -991,18 +991,6 @@ static DEVICE_ATTR_RO(cmo_allocated);
static DEVICE_ATTR_RW(cmo_desired);
static DEVICE_ATTR_RW(cmo_allocs_failed);
-static struct attribute *vio_cmo_dev_attrs[] = {
- &dev_attr_name.attr,
- &dev_attr_devspec.attr,
- &dev_attr_modalias.attr,
- &dev_attr_cmo_entitled.attr,
- &dev_attr_cmo_allocated.attr,
- &dev_attr_cmo_desired.attr,
- &dev_attr_cmo_allocs_failed.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(vio_cmo_dev);
-
/* sysfs bus functions and data structures for CMO */
#define viobus_cmo_rd_attr(name) \
@@ -1062,11 +1050,7 @@ static struct attribute *vio_bus_attrs[] = {
};
ATTRIBUTE_GROUPS(vio_bus);
-static void __init vio_cmo_sysfs_init(void)
-{
- vio_bus_type.dev_groups = vio_cmo_dev_groups;
- vio_bus_type.bus_groups = vio_bus_groups;
-}
+static void __init vio_cmo_sysfs_init(void) { }
#else /* CONFIG_PPC_SMLPAR */
int vio_cmo_entitlement_update(size_t new_entitlement) { return 0; }
void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) {}
@@ -1584,14 +1568,6 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
}
static DEVICE_ATTR_RO(modalias);
-static struct attribute *vio_dev_attrs[] = {
- &dev_attr_name.attr,
- &dev_attr_devspec.attr,
- &dev_attr_modalias.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(vio_dev);
-
void vio_unregister_device(struct vio_dev *viodev)
{
device_unregister(&viodev->dev);
@@ -1600,10 +1576,10 @@ void vio_unregister_device(struct vio_dev *viodev)
}
EXPORT_SYMBOL(vio_unregister_device);
-static int vio_bus_match(struct device *dev, struct device_driver *drv)
+static int vio_bus_match(struct device *dev, const struct device_driver *drv)
{
const struct vio_dev *vio_dev = to_vio_dev(dev);
- struct vio_driver *vio_drv = to_vio_driver(drv);
+ const struct vio_driver *vio_drv = to_vio_driver(drv);
const struct vio_device_id *ids = vio_drv->id_table;
return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL);
@@ -1616,17 +1592,45 @@ static int vio_hotplug(const struct device *dev, struct kobj_uevent_env *env)
const char *cp;
dn = dev->of_node;
- if (!dn)
- return -ENODEV;
- cp = of_get_property(dn, "compatible", NULL);
- if (!cp)
- return -ENODEV;
+ if (dn && (cp = of_get_property(dn, "compatible", NULL)))
+ add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp);
- add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp);
return 0;
}
-struct bus_type vio_bus_type = {
+#ifdef CONFIG_PPC_SMLPAR
+static struct attribute *vio_cmo_dev_attrs[] = {
+ &dev_attr_name.attr,
+ &dev_attr_devspec.attr,
+ &dev_attr_modalias.attr,
+ &dev_attr_cmo_entitled.attr,
+ &dev_attr_cmo_allocated.attr,
+ &dev_attr_cmo_desired.attr,
+ &dev_attr_cmo_allocs_failed.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(vio_cmo_dev);
+
+const struct bus_type vio_bus_type = {
+ .name = "vio",
+ .dev_groups = vio_cmo_dev_groups,
+ .bus_groups = vio_bus_groups,
+ .uevent = vio_hotplug,
+ .match = vio_bus_match,
+ .probe = vio_bus_probe,
+ .remove = vio_bus_remove,
+ .shutdown = vio_bus_shutdown,
+};
+#else /* CONFIG_PPC_SMLPAR */
+static struct attribute *vio_dev_attrs[] = {
+ &dev_attr_name.attr,
+ &dev_attr_devspec.attr,
+ &dev_attr_modalias.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(vio_dev);
+
+const struct bus_type vio_bus_type = {
.name = "vio",
.dev_groups = vio_dev_groups,
.uevent = vio_hotplug,
@@ -1635,6 +1639,7 @@ struct bus_type vio_bus_type = {
.remove = vio_bus_remove,
.shutdown = vio_bus_shutdown,
};
+#endif /* CONFIG_PPC_SMLPAR */
/**
* vio_get_attribute: - get attribute for virtual device
@@ -1684,7 +1689,7 @@ struct vio_dev *vio_find_node(struct device_node *vnode)
/* construct the kobject name from the device node */
if (of_node_is_type(vnode_parent, "vdevice")) {
const __be32 *prop;
-
+
prop = of_get_property(vnode, "reg", NULL);
if (!prop)
goto out;
diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile
index 78473d69cd2b..e9890085953e 100644
--- a/arch/powerpc/purgatory/Makefile
+++ b/arch/powerpc/purgatory/Makefile
@@ -1,8 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-
targets += trampoline_$(BITS).o purgatory.ro
# When profile-guided optimization is enabled, llvm emits two different
diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig
index 5aa92ff3622d..18ff2c4a814a 100644
--- a/arch/powerpc/sysdev/Kconfig
+++ b/arch/powerpc/sysdev/Kconfig
@@ -5,12 +5,12 @@
config PPC4xx_PCI_EXPRESS
bool
- depends on PCI && 4xx
+ depends on PCI && 44x
config PPC4xx_HSTA_MSI
bool
depends on PCI_MSI
- depends on PCI && 4xx
+ depends on PCI && 44x
config PPC_MSI_BITMAP
bool
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 9cb1d029511a..24a177d164f1 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -1,7 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-
mpic-msi-obj-$(CONFIG_PCI_MSI) += mpic_msi.o mpic_u3msi.o
obj-$(CONFIG_MPIC) += mpic.o $(mpic-msi-obj-y)
obj-$(CONFIG_MPIC_TIMER) += mpic_timer.o
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 98096bbfd62e..c0d10c149661 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -24,7 +24,6 @@
#include <linux/suspend.h>
#include <linux/memblock.h>
#include <linux/gfp.h>
-#include <linux/kmemleak.h>
#include <linux/of_address.h>
#include <asm/io.h>
#include <asm/iommu.h>
@@ -243,9 +242,6 @@ static void __init allocate_dart(void)
if (!dart_tablebase)
panic("Failed to allocate 16MB below 2GB for DART table\n");
- /* There is no point scanning the DART space for leaks*/
- kmemleak_no_scan((void *)dart_tablebase);
-
/* Allocate a spare page to map all invalid DART pages. We need to do
* that to work around what looks like a problem with the HT bridge
* prefetching into invalid pages and corrupting data
diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c
index 39186ad6b3c3..3dabc9621810 100644
--- a/arch/powerpc/sysdev/fsl_gtm.c
+++ b/arch/powerpc/sysdev/fsl_gtm.c
@@ -77,7 +77,7 @@ struct gtm {
static LIST_HEAD(gtms);
/**
- * gtm_get_timer - request GTM timer to use it with the rest of GTM API
+ * gtm_get_timer16 - request GTM timer to use it with the rest of GTM API
* Context: non-IRQ
*
* This function reserves GTM timer for later use. It returns gtm_timer
@@ -110,7 +110,7 @@ struct gtm_timer *gtm_get_timer16(void)
EXPORT_SYMBOL(gtm_get_timer16);
/**
- * gtm_get_specific_timer - request specific GTM timer
+ * gtm_get_specific_timer16 - request specific GTM timer
* @gtm: specific GTM, pass here GTM's device_node->data
* @timer: specific timer number, Timer1 is 0.
* Context: non-IRQ
@@ -260,7 +260,7 @@ int gtm_set_timer16(struct gtm_timer *tmr, unsigned long usec, bool reload)
EXPORT_SYMBOL(gtm_set_timer16);
/**
- * gtm_set_exact_utimer16 - (re)set 16 bits timer
+ * gtm_set_exact_timer16 - (re)set 16 bits timer
* @tmr: pointer to the gtm_timer structure obtained from gtm_get_timer
* @usec: timer interval in microseconds
* @reload: if set, the timer will reset upon expiry rather than
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 558ec68d768e..7b9a5ea9cad9 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -75,7 +75,7 @@ static void fsl_msi_print_chip(struct irq_data *irqd, struct seq_file *p)
srs = (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK;
cascade_virq = msi_data->cascade_array[srs]->virq;
- seq_printf(p, " fsl-msi-%d", cascade_virq);
+ seq_printf(p, "fsl-msi-%d", cascade_virq);
}
@@ -320,7 +320,7 @@ static irqreturn_t fsl_msi_cascade(int irq, void *data)
return ret;
}
-static int fsl_of_msi_remove(struct platform_device *ofdev)
+static void fsl_of_msi_remove(struct platform_device *ofdev)
{
struct fsl_msi *msi = platform_get_drvdata(ofdev);
int virq, i;
@@ -343,8 +343,6 @@ static int fsl_of_msi_remove(struct platform_device *ofdev)
if ((msi->feature & FSL_PIC_IP_MASK) != FSL_PIC_IP_VMPIC)
iounmap(msi->msi_regs);
kfree(msi);
-
- return 0;
}
static struct lock_class_key fsl_msi_irq_class;
@@ -566,10 +564,12 @@ static const struct fsl_msi_feature ipic_msi_feature = {
.msiir_offset = 0x38,
};
+#ifdef CONFIG_EPAPR_PARAVIRT
static const struct fsl_msi_feature vmpic_msi_feature = {
.fsl_pic_ip = FSL_PIC_IP_VMPIC,
.msiir_offset = 0,
};
+#endif
static const struct of_device_id fsl_of_msi_ids[] = {
{
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index dabbdd356664..d94cf36b0f65 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -49,7 +49,7 @@
#define DBG(fmt...)
#endif
-struct bus_type mpic_subsys = {
+const struct bus_type mpic_subsys = {
.name = "mpic",
.dev_name = "mpic",
};
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 0b6e37f3ffb8..456a4f64ae0a 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -124,10 +124,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count,
if (bmp->bitmap_from_slab)
bmp->bitmap = kzalloc(size, GFP_KERNEL);
else {
- bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES);
- if (!bmp->bitmap)
- panic("%s: Failed to allocate %u bytes\n", __func__,
- size);
+ bmp->bitmap = memblock_alloc_or_panic(size, SMP_CACHE_BYTES);
/* the bitmap won't be freed from memblock allocator */
kmemleak_not_leak(bmp->bitmap);
}
diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c
index fcf8d1516210..2511e586fe31 100644
--- a/arch/powerpc/sysdev/pmi.c
+++ b/arch/powerpc/sysdev/pmi.c
@@ -173,7 +173,7 @@ out:
return rc;
}
-static int pmi_of_remove(struct platform_device *dev)
+static void pmi_of_remove(struct platform_device *dev)
{
struct pmi_handler *handler, *tmp;
@@ -189,8 +189,6 @@ static int pmi_of_remove(struct platform_device *dev)
kfree(data);
data = NULL;
-
- return 0;
}
static struct platform_driver pmi_of_platform_driver = {
diff --git a/arch/powerpc/sysdev/rtc_cmos_setup.c b/arch/powerpc/sysdev/rtc_cmos_setup.c
index 47cc87bd6a33..9a232ae5e360 100644
--- a/arch/powerpc/sysdev/rtc_cmos_setup.c
+++ b/arch/powerpc/sysdev/rtc_cmos_setup.c
@@ -66,4 +66,5 @@ static int __init add_rtc(void)
}
fs_initcall(add_rtc);
+MODULE_DESCRIPTION("PPC RTC CMOS driver");
MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index a289cb97c1d7..a6c388bdf5d0 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -383,7 +383,7 @@ static unsigned int xive_get_irq(void)
* CPU.
*
* If we find that there is indeed more in there, we call
- * force_external_irq_replay() to make Linux synthetize an
+ * force_external_irq_replay() to make Linux synthesize an
* external interrupt on the next call to local_irq_restore().
*/
static void xive_do_queue_eoi(struct xive_cpu *xc)
@@ -726,7 +726,7 @@ static int xive_irq_set_affinity(struct irq_data *d,
pr_debug("%s: irq %d/0x%x\n", __func__, d->irq, hw_irq);
/* Is this valid ? */
- if (cpumask_any_and(cpumask, cpu_online_mask) >= nr_cpu_ids)
+ if (!cpumask_intersects(cpumask, cpu_online_mask))
return -EINVAL;
/*
@@ -874,7 +874,7 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state)
*
* This also tells us that it's in flight to a host queue
* or has already been fetched but hasn't been EOIed yet
- * by the host. This it's potentially using up a host
+ * by the host. Thus it's potentially using up a host
* queue slot. This is important to know because as long
* as this is the case, we must not hard-unmask it when
* "returning" that interrupt to the host.
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index f1c0fa6ece21..a0934b516933 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -415,7 +415,7 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
return;
}
- /* Grab it's CAM value */
+ /* Grab its CAM value */
rc = opal_xive_get_vp_info(vp, NULL, &vp_cam_be, NULL, NULL);
if (rc) {
pr_err("Failed to get pool VP info CPU %d\n", cpu);
@@ -559,9 +559,7 @@ bool __init xive_native_init(void)
struct device_node *np;
struct resource r;
void __iomem *tima;
- struct property *prop;
u8 max_prio = 7;
- const __be32 *p;
u32 val, cpu;
s64 rc;
@@ -592,7 +590,7 @@ bool __init xive_native_init(void)
max_prio = val - 1;
/* Iterate the EQ sizes and pick one */
- of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, p, val) {
+ of_property_for_each_u32(np, "ibm,xive-eq-sizes", val) {
xive_queue_shift = val;
if (val == PAGE_SHIFT)
break;
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index e45419264391..5aedbe3e8e6a 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -7,6 +7,7 @@
#include <linux/types.h>
#include <linux/irq.h>
+#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/init.h>
@@ -814,7 +815,6 @@ bool __init xive_spapr_init(void)
struct device_node *np;
struct resource r;
void __iomem *tima;
- struct property *prop;
u8 max_prio;
u32 val;
u32 len;
@@ -866,7 +866,7 @@ bool __init xive_spapr_init(void)
}
/* Iterate the EQ sizes and pick one */
- of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, reg, val) {
+ of_property_for_each_u32(np, "ibm,xive-eq-sizes", val) {
xive_queue_shift = val;
if (val == PAGE_SHIFT)
break;
diff --git a/arch/powerpc/platforms/maple/Makefile b/arch/powerpc/tools/.gitignore
index 19f35ab828a7..ec380a14a09a 100644
--- a/arch/powerpc/platforms/maple/Makefile
+++ b/arch/powerpc/tools/.gitignore
@@ -1,2 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
-obj-y += setup.o pci.o time.o
+/vmlinux.arch.S
diff --git a/arch/powerpc/tools/Makefile b/arch/powerpc/tools/Makefile
new file mode 100644
index 000000000000..e1f7afcd9fdf
--- /dev/null
+++ b/arch/powerpc/tools/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+quiet_cmd_gen_ftrace_ool_stubs = GEN $@
+ cmd_gen_ftrace_ool_stubs = $< "$(CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE)" "$(CONFIG_64BIT)" \
+ "$(OBJDUMP)" vmlinux.o $@
+
+$(obj)/vmlinux.arch.S: $(src)/ftrace-gen-ool-stubs.sh vmlinux.o FORCE
+ $(call if_changed,gen_ftrace_ool_stubs)
+
+targets += vmlinux.arch.S
diff --git a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
new file mode 100755
index 000000000000..bac186bdf64a
--- /dev/null
+++ b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
@@ -0,0 +1,52 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+# Error out on error
+set -e
+
+num_ool_stubs_text_builtin="$1"
+is_64bit="$2"
+objdump="$3"
+vmlinux_o="$4"
+arch_vmlinux_S="$5"
+
+RELOCATION=R_PPC64_ADDR64
+if [ -z "$is_64bit" ]; then
+ RELOCATION=R_PPC_ADDR32
+fi
+
+num_ool_stubs_total=$($objdump -r -j __patchable_function_entries "$vmlinux_o" |
+ grep -c "$RELOCATION")
+num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries "$vmlinux_o" |
+ grep -e ".init.text" -e ".text.startup" | grep -c "$RELOCATION")
+num_ool_stubs_text=$((num_ool_stubs_total - num_ool_stubs_inittext))
+
+if [ "$num_ool_stubs_text" -gt "$num_ool_stubs_text_builtin" ]; then
+ num_ool_stubs_text_end=$((num_ool_stubs_text - num_ool_stubs_text_builtin))
+else
+ num_ool_stubs_text_end=0
+fi
+
+cat > "$arch_vmlinux_S" <<EOF
+#include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
+#include <linux/linkage.h>
+
+.pushsection .tramp.ftrace.text,"aw"
+SYM_DATA(ftrace_ool_stub_text_end_count, .long $num_ool_stubs_text_end)
+
+SYM_START(ftrace_ool_stub_text_end, SYM_L_GLOBAL, .balign SZL)
+#if $num_ool_stubs_text_end
+ .space $num_ool_stubs_text_end * FTRACE_OOL_STUB_SIZE
+#endif
+SYM_CODE_END(ftrace_ool_stub_text_end)
+.popsection
+
+.pushsection .tramp.ftrace.init,"aw"
+SYM_DATA(ftrace_ool_stub_inittext_count, .long $num_ool_stubs_inittext)
+
+SYM_START(ftrace_ool_stub_inittext, SYM_L_GLOBAL, .balign SZL)
+ .space $num_ool_stubs_inittext * FTRACE_OOL_STUB_SIZE
+SYM_CODE_END(ftrace_ool_stub_inittext)
+.popsection
+EOF
diff --git a/arch/powerpc/tools/ftrace_check.sh b/arch/powerpc/tools/ftrace_check.sh
new file mode 100755
index 000000000000..405e7e306617
--- /dev/null
+++ b/arch/powerpc/tools/ftrace_check.sh
@@ -0,0 +1,50 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# This script checks vmlinux to ensure that all functions can call ftrace_caller() either directly,
+# or through the stub, ftrace_tramp_text, at the end of kernel text.
+
+# Error out if any command fails
+set -e
+
+# Allow for verbose output
+if [ "$V" = "1" ]; then
+ set -x
+fi
+
+if [ $# -lt 2 ]; then
+ echo "$0 [path to nm] [path to vmlinux]" 1>&2
+ exit 1
+fi
+
+# Have Kbuild supply the path to nm so we handle cross compilation.
+nm="$1"
+vmlinux="$2"
+
+stext_addr=$($nm "$vmlinux" | grep -e " [TA] _stext$" | \
+ cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+ftrace_caller_addr=$($nm "$vmlinux" | grep -e " T ftrace_caller$" | \
+ cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+ftrace_tramp_addr=$($nm "$vmlinux" | grep -e " T ftrace_tramp_text$" | \
+ cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+
+ftrace_caller_offset=$(echo "ibase=16;$ftrace_caller_addr - $stext_addr" | bc)
+ftrace_tramp_offset=$(echo "ibase=16;$ftrace_tramp_addr - $ftrace_caller_addr" | bc)
+sz_32m=$(printf "%d" 0x2000000)
+sz_64m=$(printf "%d" 0x4000000)
+
+# ftrace_caller - _stext < 32M
+if [ "$ftrace_caller_offset" -ge "$sz_32m" ]; then
+ echo "ERROR: ftrace_caller (0x$ftrace_caller_addr) is beyond 32MiB of _stext" 1>&2
+ echo "ERROR: consider disabling CONFIG_FUNCTION_TRACER, or reducing the size \
+ of kernel text" 1>&2
+ exit 1
+fi
+
+# ftrace_tramp_text - ftrace_caller < 64M
+if [ "$ftrace_tramp_offset" -ge "$sz_64m" ]; then
+ echo "ERROR: kernel text extends beyond 64MiB from ftrace_caller" 1>&2
+ echo "ERROR: consider disabling CONFIG_FUNCTION_TRACER, or reducing the size \
+ of kernel text" 1>&2
+ exit 1
+fi
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index 682c7c0a6f77..d778011060a8 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -10,8 +10,6 @@ KCSAN_SANITIZE := n
# Disable ftrace for the entire directory
ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
-ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-
# Clang stores addresses on the stack causing the frame size to blow
# out. See https://github.com/ClangBuiltLinux/linux/issues/252
ccflags-$(CONFIG_CC_IS_CLANG) += -Wframe-larger-than=4096
diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c
index 75fa98221d48..af105e1bc3fc 100644
--- a/arch/powerpc/xmon/ppc-dis.c
+++ b/arch/powerpc/xmon/ppc-dis.c
@@ -122,32 +122,21 @@ int print_insn_powerpc (unsigned long insn, unsigned long memaddr)
bool insn_is_short;
ppc_cpu_t dialect;
- dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON
- | PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_ALTIVEC;
+ dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON;
- if (cpu_has_feature(CPU_FTRS_POWER5))
- dialect |= PPC_OPCODE_POWER5;
+ if (IS_ENABLED(CONFIG_PPC64))
+ dialect |= PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_CELL |
+ PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 | PPC_OPCODE_POWER8 |
+ PPC_OPCODE_POWER9;
- if (cpu_has_feature(CPU_FTRS_CELL))
- dialect |= (PPC_OPCODE_CELL | PPC_OPCODE_ALTIVEC);
+ if (cpu_has_feature(CPU_FTR_TM))
+ dialect |= PPC_OPCODE_HTM;
- if (cpu_has_feature(CPU_FTRS_POWER6))
- dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_ALTIVEC);
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ dialect |= PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2;
- if (cpu_has_feature(CPU_FTRS_POWER7))
- dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
- | PPC_OPCODE_ALTIVEC | PPC_OPCODE_VSX);
-
- if (cpu_has_feature(CPU_FTRS_POWER8))
- dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
- | PPC_OPCODE_POWER8 | PPC_OPCODE_HTM
- | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 | PPC_OPCODE_VSX);
-
- if (cpu_has_feature(CPU_FTRS_POWER9))
- dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
- | PPC_OPCODE_POWER8 | PPC_OPCODE_POWER9 | PPC_OPCODE_HTM
- | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2
- | PPC_OPCODE_VSX | PPC_OPCODE_VSX3);
+ if (cpu_has_feature(CPU_FTR_VSX))
+ dialect |= PPC_OPCODE_VSX | PPC_OPCODE_VSX3;
/* Get the major opcode of the insn. */
opcode = NULL;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index b3b94cd37713..268859e4df87 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -50,7 +50,7 @@
#include <asm/xive.h>
#include <asm/opal.h>
#include <asm/firmware.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
#include <asm/sections.h>
#include <asm/inst.h>
#include <asm/interrupt.h>
@@ -643,10 +643,8 @@ static int xmon_core(struct pt_regs *regs, volatile int fromipi)
touch_nmi_watchdog();
} else {
cmd = 1;
-#ifdef CONFIG_SMP
if (xmon_batch)
cmd = batch_cmds(regs);
-#endif
if (!locked_down && cmd)
cmd = cmds(regs);
if (locked_down || cmd != 0) {
@@ -1352,7 +1350,7 @@ static int cpu_cmd(void)
}
termch = cpu;
- if (!scanhex(&cpu)) {
+ if (!scanhex(&cpu) || cpu >= num_possible_cpus()) {
/* print cpus waiting or in xmon */
printf("cpus stopped:");
last_cpu = first_cpu = NR_CPUS;
@@ -1820,8 +1818,8 @@ static void print_bug_trap(struct pt_regs *regs)
const struct bug_entry *bug;
unsigned long addr;
- if (regs->msr & MSR_PR)
- return; /* not in kernel */
+ if (user_mode(regs))
+ return;
addr = regs->nip; /* address of trap instruction */
if (!is_kernel_addr(addr))
return;
@@ -2625,9 +2623,9 @@ static void dump_one_paca(int cpu)
printf("paca for cpu 0x%x @ %px:\n", cpu, p);
- printf(" %-*s = %s\n", 25, "possible", cpu_possible(cpu) ? "yes" : "no");
- printf(" %-*s = %s\n", 25, "present", cpu_present(cpu) ? "yes" : "no");
- printf(" %-*s = %s\n", 25, "online", cpu_online(cpu) ? "yes" : "no");
+ printf(" %-*s = %s\n", 25, "possible", str_yes_no(cpu_possible(cpu)));
+ printf(" %-*s = %s\n", 25, "present", str_yes_no(cpu_present(cpu)));
+ printf(" %-*s = %s\n", 25, "online", str_yes_no(cpu_online(cpu)));
#define DUMP(paca, name, format) \
printf(" %-*s = "format"\t(0x%lx)\n", 25, #name, 18, paca->name, \
@@ -2774,7 +2772,7 @@ static void dump_pacas(void)
termch = c; /* Put c back, it wasn't 'a' */
- if (scanhex(&num))
+ if (scanhex(&num) && num < num_possible_cpus())
dump_one_paca(num);
else
dump_one_paca(xmon_owner);
@@ -2847,7 +2845,7 @@ static void dump_xives(void)
termch = c; /* Put c back, it wasn't 'a' */
- if (scanhex(&num))
+ if (scanhex(&num) && num < num_possible_cpus())
dump_one_xive(num);
else
dump_one_xive(xmon_owner);
@@ -3342,7 +3340,7 @@ static void show_pte(unsigned long addr)
return;
}
- if (p4d_is_leaf(*p4dp)) {
+ if (p4d_leaf(*p4dp)) {
format_pte(p4dp, p4d_val(*p4dp));
return;
}
@@ -3356,7 +3354,7 @@ static void show_pte(unsigned long addr)
return;
}
- if (pud_is_leaf(*pudp)) {
+ if (pud_leaf(*pudp)) {
format_pte(pudp, pud_val(*pudp));
return;
}
@@ -3370,7 +3368,7 @@ static void show_pte(unsigned long addr)
return;
}
- if (pmd_is_leaf(*pmdp)) {
+ if (pmd_leaf(*pmdp)) {
format_pte(pmdp, pmd_val(*pmdp));
return;
}
@@ -3545,7 +3543,7 @@ scanhex(unsigned long *vp)
}
} else if (c == '$') {
int i;
- for (i=0; i<63; i++) {
+ for (i = 0; i < (KSYM_NAME_LEN - 1); i++) {
c = inchar();
if (isspace(c) || c == '\0') {
termch = c;
@@ -3664,7 +3662,7 @@ symbol_lookup(void)
int type = inchar();
unsigned long addr, cpu;
void __percpu *ptr = NULL;
- static char tmp[64];
+ static char tmp[KSYM_NAME_LEN];
switch (type) {
case 'a':
@@ -3673,7 +3671,7 @@ symbol_lookup(void)
termch = 0;
break;
case 's':
- getstring(tmp, 64);
+ getstring(tmp, KSYM_NAME_LEN);
if (setjmp(bus_error_jmp) == 0) {
catch_memory_errors = 1;
sync();
@@ -3688,7 +3686,7 @@ symbol_lookup(void)
termch = 0;
break;
case 'p':
- getstring(tmp, 64);
+ getstring(tmp, KSYM_NAME_LEN);
if (setjmp(bus_error_jmp) == 0) {
catch_memory_errors = 1;
sync();