aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x77
-rw-r--r--Documentation/ABI/testing/sysfs-class-ocxl11
-rw-r--r--Documentation/core-api/cpu_hotplug.rst7
-rw-r--r--Documentation/features/sched/membarrier-sync-core/arch-support.txt4
-rw-r--r--Documentation/memory-barriers.txt14
-rw-r--r--Documentation/powerpc/cpu_families.rst10
-rw-r--r--Documentation/powerpc/mpc52xx.rst2
-rw-r--r--Documentation/powerpc/vas-api.rst2
-rw-r--r--Documentation/virt/kvm/api.rst3
-rw-r--r--MAINTAINERS1
-rw-r--r--arch/powerpc/Kconfig14
-rw-r--r--arch/powerpc/Makefile3
-rw-r--r--arch/powerpc/boot/Makefile6
-rw-r--r--arch/powerpc/boot/dts/akebono.dts8
-rw-r--r--arch/powerpc/boot/dts/bluestone.dts2
-rw-r--r--arch/powerpc/boot/dts/canyonlands.dts4
-rw-r--r--arch/powerpc/boot/dts/currituck.dts6
-rw-r--r--arch/powerpc/boot/dts/glacier.dts4
-rw-r--r--arch/powerpc/boot/dts/haleakala.dts2
-rw-r--r--arch/powerpc/boot/dts/icon.dts4
-rw-r--r--arch/powerpc/boot/dts/katmai.dts6
-rw-r--r--arch/powerpc/boot/dts/kilauea.dts4
-rw-r--r--arch/powerpc/boot/dts/makalu.dts4
-rw-r--r--arch/powerpc/boot/dts/redwood.dts6
-rw-r--r--arch/powerpc/boot/main.c4
-rw-r--r--arch/powerpc/boot/ps3.c2
-rw-r--r--arch/powerpc/configs/44x/akebono_defconfig2
-rw-r--r--arch/powerpc/configs/44x/arches_defconfig2
-rw-r--r--arch/powerpc/configs/44x/bamboo_defconfig2
-rw-r--r--arch/powerpc/configs/44x/bluestone_defconfig2
-rw-r--r--arch/powerpc/configs/44x/canyonlands_defconfig2
-rw-r--r--arch/powerpc/configs/44x/currituck_defconfig2
-rw-r--r--arch/powerpc/configs/44x/eiger_defconfig2
-rw-r--r--arch/powerpc/configs/44x/fsp2_defconfig1
-rw-r--r--arch/powerpc/configs/44x/icon_defconfig2
-rw-r--r--arch/powerpc/configs/44x/iss476-smp_defconfig1
-rw-r--r--arch/powerpc/configs/44x/katmai_defconfig2
-rw-r--r--arch/powerpc/configs/44x/rainier_defconfig2
-rw-r--r--arch/powerpc/configs/44x/redwood_defconfig2
-rw-r--r--arch/powerpc/configs/44x/sam440ep_defconfig2
-rw-r--r--arch/powerpc/configs/44x/sequoia_defconfig2
-rw-r--r--arch/powerpc/configs/44x/taishan_defconfig2
-rw-r--r--arch/powerpc/configs/44x/warp_defconfig1
-rw-r--r--arch/powerpc/configs/85xx-hw.config1
-rw-r--r--arch/powerpc/configs/holly_defconfig1
-rw-r--r--arch/powerpc/configs/mvme5100_defconfig3
-rw-r--r--arch/powerpc/configs/powernv_defconfig1
-rw-r--r--arch/powerpc/configs/ps3_defconfig2
-rw-r--r--arch/powerpc/configs/pseries_defconfig1
-rw-r--r--arch/powerpc/configs/skiroot_defconfig1
-rw-r--r--arch/powerpc/configs/storcenter_defconfig1
-rw-r--r--arch/powerpc/crypto/crc32-vpmsum_core.S2
-rw-r--r--arch/powerpc/include/asm/asm-prototypes.h4
-rw-r--r--arch/powerpc/include/asm/barrier.h13
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash-4k.h21
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash-64k.h12
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash-pkey.h32
-rw-r--r--arch/powerpc/include/asm/book3s/64/kexec.h23
-rw-r--r--arch/powerpc/include/asm/book3s/64/mmu-hash.h8
-rw-r--r--arch/powerpc/include/asm/book3s/64/mmu.h11
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgalloc.h16
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h25
-rw-r--r--arch/powerpc/include/asm/book3s/64/pkeys.h27
-rw-r--r--arch/powerpc/include/asm/book3s/64/tlbflush-radix.h15
-rw-r--r--arch/powerpc/include/asm/cacheflush.h1
-rw-r--r--arch/powerpc/include/asm/cputable.h23
-rw-r--r--arch/powerpc/include/asm/cputime.h2
-rw-r--r--arch/powerpc/include/asm/exception-64e.h6
-rw-r--r--arch/powerpc/include/asm/exception-64s.h8
-rw-r--r--arch/powerpc/include/asm/fixmap.h2
-rw-r--r--arch/powerpc/include/asm/hvcall.h36
-rw-r--r--arch/powerpc/include/asm/hydra.h2
-rw-r--r--arch/powerpc/include/asm/icswx.h2
-rw-r--r--arch/powerpc/include/asm/imc-pmu.h5
-rw-r--r--arch/powerpc/include/asm/inst.h19
-rw-r--r--arch/powerpc/include/asm/kasan.h2
-rw-r--r--arch/powerpc/include/asm/kexec.h12
-rw-r--r--arch/powerpc/include/asm/kvm_book3s_asm.h2
-rw-r--r--arch/powerpc/include/asm/kvm_host.h6
-rw-r--r--arch/powerpc/include/asm/mce.h3
-rw-r--r--arch/powerpc/include/asm/mman.h30
-rw-r--r--arch/powerpc/include/asm/mmu.h23
-rw-r--r--arch/powerpc/include/asm/mmu_context.h2
-rw-r--r--arch/powerpc/include/asm/nohash/32/pgtable.h22
-rw-r--r--arch/powerpc/include/asm/nohash/64/pgtable.h2
-rw-r--r--arch/powerpc/include/asm/perf_event.h2
-rw-r--r--arch/powerpc/include/asm/perf_event_server.h14
-rw-r--r--arch/powerpc/include/asm/pkeys.h65
-rw-r--r--arch/powerpc/include/asm/plpar_wrappers.h52
-rw-r--r--arch/powerpc/include/asm/ppc-opcode.h565
-rw-r--r--arch/powerpc/include/asm/processor.h5
-rw-r--r--arch/powerpc/include/asm/reg.h7
-rw-r--r--arch/powerpc/include/asm/rtas.h3
-rw-r--r--arch/powerpc/include/asm/security_features.h2
-rw-r--r--arch/powerpc/include/asm/sstep.h6
-rw-r--r--arch/powerpc/include/asm/topology.h27
-rw-r--r--arch/powerpc/include/asm/xive.h1
-rw-r--r--arch/powerpc/include/uapi/asm/kvm.h5
-rw-r--r--arch/powerpc/include/uapi/asm/mman.h2
-rw-r--r--arch/powerpc/kernel/asm-offsets.c5
-rw-r--r--arch/powerpc/kernel/cacheinfo.c25
-rw-r--r--arch/powerpc/kernel/dt_cpu_ftrs.c50
-rw-r--r--arch/powerpc/kernel/entry_32.S6
-rw-r--r--arch/powerpc/kernel/entry_64.S19
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S2
-rw-r--r--arch/powerpc/kernel/fadump.c24
-rw-r--r--arch/powerpc/kernel/fpu.S4
-rw-r--r--arch/powerpc/kernel/kprobes.c2
-rw-r--r--arch/powerpc/kernel/mce.c16
-rw-r--r--arch/powerpc/kernel/mce_power.c84
-rw-r--r--arch/powerpc/kernel/misc_64.S14
-rw-r--r--arch/powerpc/kernel/paca.c15
-rw-r--r--arch/powerpc/kernel/process.c101
-rw-r--r--arch/powerpc/kernel/prom.c7
-rw-r--r--arch/powerpc/kernel/prom_init.c13
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-view.c27
-rw-r--r--arch/powerpc/kernel/rtas.c122
-rw-r--r--arch/powerpc/kernel/rtasd.c28
-rw-r--r--arch/powerpc/kernel/secure_boot.c18
-rw-r--r--arch/powerpc/kernel/security.c139
-rw-r--r--arch/powerpc/kernel/signal_32.c20
-rw-r--r--arch/powerpc/kernel/signal_64.c29
-rw-r--r--arch/powerpc/kernel/smp.c1
-rw-r--r--arch/powerpc/kernel/syscall_64.c8
-rw-r--r--arch/powerpc/kernel/sysfs.c8
-rw-r--r--arch/powerpc/kernel/trace/ftrace.c26
-rw-r--r--arch/powerpc/kernel/vdso.c2
-rw-r--r--arch/powerpc/kernel/vdso64/cacheflush.S9
-rw-r--r--arch/powerpc/kernel/vdso64/datapage.S28
-rw-r--r--arch/powerpc/kernel/vdso64/gettimeofday.S9
-rw-r--r--arch/powerpc/kernel/vdso64/sigtramp.S13
-rw-r--r--arch/powerpc/kernel/vector.S4
-rw-r--r--arch/powerpc/kexec/core_64.c2
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c3
-rw-r--r--arch/powerpc/kvm/book3s_hv.c44
-rw-r--r--arch/powerpc/kvm/book3s_hv_interrupts.S8
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S36
-rw-r--r--arch/powerpc/kvm/trace_hv.h2
-rw-r--r--arch/powerpc/lib/pmem.c44
-rw-r--r--arch/powerpc/lib/sstep.c12
-rw-r--r--arch/powerpc/lib/test_emulate_step.c540
-rw-r--r--arch/powerpc/lib/test_emulate_step_exec_instr.S2
-rw-r--r--arch/powerpc/mm/book3s64/hash_utils.c17
-rw-r--r--arch/powerpc/mm/book3s64/pgtable.c8
-rw-r--r--arch/powerpc/mm/book3s64/pkeys.c309
-rw-r--r--arch/powerpc/mm/book3s64/radix_pgtable.c215
-rw-r--r--arch/powerpc/mm/book3s64/radix_tlb.c82
-rw-r--r--arch/powerpc/mm/init_32.c2
-rw-r--r--arch/powerpc/mm/init_64.c5
-rw-r--r--arch/powerpc/mm/kasan/kasan_init_32.c29
-rw-r--r--arch/powerpc/mm/nohash/kaslr_booke.c1
-rw-r--r--arch/powerpc/mm/numa.c486
-rw-r--r--arch/powerpc/mm/pgtable-frag.c3
-rw-r--r--arch/powerpc/mm/ptdump/hashpagetable.c2
-rw-r--r--arch/powerpc/net/bpf_jit.h184
-rw-r--r--arch/powerpc/net/bpf_jit32.h34
-rw-r--r--arch/powerpc/net/bpf_jit64.h16
-rw-r--r--arch/powerpc/net/bpf_jit_comp.c134
-rw-r--r--arch/powerpc/net/bpf_jit_comp64.c298
-rw-r--r--arch/powerpc/perf/Makefile2
-rw-r--r--arch/powerpc/perf/core-book3s.c108
-rw-r--r--arch/powerpc/perf/generic-compat-pmu.c2
-rw-r--r--arch/powerpc/perf/hv-24x7.c54
-rw-r--r--arch/powerpc/perf/imc-pmu.c29
-rw-r--r--arch/powerpc/perf/internal.h1
-rw-r--r--arch/powerpc/perf/isa207-common.c91
-rw-r--r--arch/powerpc/perf/isa207-common.h37
-rw-r--r--arch/powerpc/perf/mpc7450-pmu.c23
-rw-r--r--arch/powerpc/perf/power10-events-list.h70
-rw-r--r--arch/powerpc/perf/power10-pmu.c419
-rw-r--r--arch/powerpc/perf/power5+-pmu.c19
-rw-r--r--arch/powerpc/perf/power5-pmu.c19
-rw-r--r--arch/powerpc/perf/power6-pmu.c18
-rw-r--r--arch/powerpc/perf/power7-pmu.c19
-rw-r--r--arch/powerpc/perf/power8-pmu.c2
-rw-r--r--arch/powerpc/perf/power9-pmu.c2
-rw-r--r--arch/powerpc/perf/ppc970-pmu.c26
-rw-r--r--arch/powerpc/platforms/85xx/Kconfig2
-rw-r--r--arch/powerpc/platforms/cell/Kconfig1
-rw-r--r--arch/powerpc/platforms/cell/spufs/coredump.c21
-rw-r--r--arch/powerpc/platforms/powernv/idle.c48
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda-tce.c2
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda.c34
-rw-r--r--arch/powerpc/platforms/powernv/setup.c10
-rw-r--r--arch/powerpc/platforms/powernv/vas-fault.c2
-rw-r--r--arch/powerpc/platforms/pseries/eeh_pseries.c232
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-cpu.c189
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-memory.c109
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c8
-rw-r--r--arch/powerpc/platforms/pseries/mobility.c31
-rw-r--r--arch/powerpc/platforms/pseries/offline_states.h38
-rw-r--r--arch/powerpc/platforms/pseries/papr_scm.c97
-rw-r--r--arch/powerpc/platforms/pseries/pmem.c7
-rw-r--r--arch/powerpc/platforms/pseries/smp.c28
-rw-r--r--arch/powerpc/platforms/pseries/suspend.c27
-rw-r--r--arch/powerpc/sysdev/xive/native.c2
-rw-r--r--arch/powerpc/xmon/xmon.c35
-rw-r--r--drivers/cpuidle/cpuidle-powernv.c14
-rw-r--r--drivers/cpuidle/cpuidle-pseries.c2
-rw-r--r--drivers/crypto/vmx/aesp8-ppc.pl2
-rw-r--r--drivers/crypto/vmx/ghashp8-ppc.pl2
-rw-r--r--drivers/macintosh/adb.c2
-rw-r--r--drivers/macintosh/therm_adt746x.c4
-rw-r--r--drivers/md/dm-writecache.c2
-rw-r--r--drivers/misc/ocxl/Kconfig2
-rw-r--r--drivers/misc/ocxl/config.c81
-rw-r--r--drivers/misc/ocxl/ocxl_internal.h6
-rw-r--r--drivers/misc/ocxl/sysfs.c35
-rw-r--r--drivers/nvdimm/of_pmem.c1
-rw-r--r--drivers/nvdimm/region_devs.c8
-rw-r--r--include/asm-generic/barrier.h10
-rw-r--r--include/linux/cpuhotplug.h1
-rw-r--r--include/linux/mm.h2
-rw-r--r--include/misc/ocxl-config.h1
-rw-r--r--include/trace/events/mmflags.h2
-rw-r--r--mm/ksm.c4
-rw-r--r--tools/arch/powerpc/include/uapi/asm/kvm.h5
-rw-r--r--tools/perf/arch/powerpc/util/book3s_hcalls.h2
-rw-r--r--tools/testing/selftests/powerpc/alignment/alignment_handler.c150
-rw-r--r--tools/testing/selftests/powerpc/include/instructions.h77
-rw-r--r--tools/testing/selftests/powerpc/include/reg.h6
-rw-r--r--tools/testing/selftests/powerpc/include/utils.h6
-rw-r--r--tools/testing/selftests/powerpc/math/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/math/Makefile2
-rw-r--r--tools/testing/selftests/powerpc/math/fpu_denormal.c38
-rw-r--r--tools/testing/selftests/powerpc/mm/.gitignore2
-rw-r--r--tools/testing/selftests/powerpc/mm/Makefile9
-rw-r--r--tools/testing/selftests/powerpc/mm/bad_accesses.c28
-rw-r--r--tools/testing/selftests/powerpc/mm/pkey_exec_prot.c388
-rw-r--r--tools/testing/selftests/powerpc/mm/prot_sao.c42
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/gunz_test.c4
-rw-r--r--tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c4
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/Makefile2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/ebb.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c1
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c7
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c2
-rw-r--r--tools/testing/selftests/powerpc/pmu/per_event_excludes.c7
-rw-r--r--tools/testing/selftests/powerpc/ptrace/core-pkey.c2
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c57
-rw-r--r--tools/testing/selftests/powerpc/stringloops/memcmp.c40
-rw-r--r--tools/testing/selftests/powerpc/utils.c28
249 files changed, 4619 insertions, 3105 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
index e8698afcd952..f7e32f218f73 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
@@ -43,6 +43,13 @@ Description: read only
This sysfs interface exposes the number of cores per chip
present in the system.
+What: /sys/devices/hv_24x7/interface/cpumask
+Date: July 2020
+Contact: Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
+Description: read only
+ This sysfs file exposes the cpumask which is designated to make
+ HCALLs to retrieve hv-24x7 pmu event counter data.
+
What: /sys/bus/event_source/devices/hv_24x7/event_descs/<event-name>
Date: February 2014
Contact: Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
diff --git a/Documentation/ABI/testing/sysfs-class-ocxl b/Documentation/ABI/testing/sysfs-class-ocxl
index b5b1fa197592..ae1276efa45a 100644
--- a/Documentation/ABI/testing/sysfs-class-ocxl
+++ b/Documentation/ABI/testing/sysfs-class-ocxl
@@ -33,3 +33,14 @@ Date: January 2018
Contact: linuxppc-dev@lists.ozlabs.org
Description: read/write
Give access the global mmio area for the AFU
+
+What: /sys/class/ocxl/<afu name>/reload_on_reset
+Date: February 2020
+Contact: linuxppc-dev@lists.ozlabs.org
+Description: read/write
+ Control whether the FPGA is reloaded on a link reset. Enabled
+ through a vendor-specific logic block on the FPGA.
+ 0 Do not reload FPGA image from flash
+ 1 Reload FPGA image from flash
+ unavailable
+ The device does not support this capability
diff --git a/Documentation/core-api/cpu_hotplug.rst b/Documentation/core-api/cpu_hotplug.rst
index 4a50ab7817f7..b1ae1ac159cf 100644
--- a/Documentation/core-api/cpu_hotplug.rst
+++ b/Documentation/core-api/cpu_hotplug.rst
@@ -50,13 +50,6 @@ Command Line Switches
This option is limited to the X86 and S390 architecture.
-``cede_offline={"off","on"}``
- Use this option to disable/enable putting offlined processors to an extended
- ``H_CEDE`` state on supported pseries platforms. If nothing is specified,
- ``cede_offline`` is set to "on".
-
- This option is limited to the PowerPC architecture.
-
``cpu0_hotplug``
Allow to shutdown CPU0.
diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
index 8a521a622966..52ad74a25f54 100644
--- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -5,7 +5,7 @@
#
# Architecture requirements
#
-# * arm/arm64
+# * arm/arm64/powerpc
#
# Rely on implicit context synchronization as a result of exception return
# when returning from IPI handler, and when returning to user-space.
@@ -45,7 +45,7 @@
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
- | powerpc: | TODO |
+ | powerpc: | ok |
| riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index eaabc3134294..ff07cd3b2f82 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1935,6 +1935,20 @@ There are some more advanced barrier functions:
relaxed I/O accessors and the Documentation/DMA-API.txt file for more
information on consistent memory.
+ (*) pmem_wmb();
+
+ This is for use with persistent memory to ensure that stores for which
+ modifications are written to persistent storage reached a platform
+ durability domain.
+
+ For example, after a non-temporal write to pmem region, we use pmem_wmb()
+ to ensure that stores have reached a platform durability domain. This ensures
+ that stores have updated persistent storage before any data access or
+ data transfer caused by subsequent instructions is initiated. This is
+ in addition to the ordering done by wmb().
+
+ For load from persistent memory, existing read memory barriers are sufficient
+ to ensure read ordering.
===============================
IMPLICIT KERNEL MEMORY BARRIERS
diff --git a/Documentation/powerpc/cpu_families.rst b/Documentation/powerpc/cpu_families.rst
index 1e063c5440c3..9b84e045e713 100644
--- a/Documentation/powerpc/cpu_families.rst
+++ b/Documentation/powerpc/cpu_families.rst
@@ -9,7 +9,9 @@ and are supported by arch/powerpc.
Book3S (aka sPAPR)
------------------
-- Hash MMU
+- Hash MMU (except 603 and e300)
+- Software loaded TLB (603 and e300)
+- Selectable Software loaded TLB in addition to hash MMU (755, 7450, e600)
- Mix of 32 & 64 bit::
+--------------+ +----------------+
@@ -24,9 +26,9 @@ Book3S (aka sPAPR)
| |
| |
v v
- +--------------+ +----------------+ +-------+
- | 604 | | 750 (G3) | ---> | 750CX |
- +--------------+ +----------------+ +-------+
+ +--------------+ +-----+ +----------------+ +-------+
+ | 604 | | 755 | <--- | 750 (G3) | ---> | 750CX |
+ +--------------+ +-----+ +----------------+ +-------+
| | |
| | |
v v v
diff --git a/Documentation/powerpc/mpc52xx.rst b/Documentation/powerpc/mpc52xx.rst
index 8676ac63e077..30260707c3fe 100644
--- a/Documentation/powerpc/mpc52xx.rst
+++ b/Documentation/powerpc/mpc52xx.rst
@@ -2,7 +2,7 @@
Linux 2.6.x on MPC52xx family
=============================
-For the latest info, go to http://www.246tNt.com/mpc52xx/
+For the latest info, go to https://www.246tNt.com/mpc52xx/
To compile/use :
diff --git a/Documentation/powerpc/vas-api.rst b/Documentation/powerpc/vas-api.rst
index 1217c2f1595e..788dc8375a0e 100644
--- a/Documentation/powerpc/vas-api.rst
+++ b/Documentation/powerpc/vas-api.rst
@@ -213,7 +213,7 @@ request buffers are not in memory. The operating system handles the fault by
updating CSB with the following data:
csb.flags = CSB_V;
- csb.cc = CSB_CC_TRANSLATION;
+ csb.cc = CSB_CC_FAULT_ADDRESS;
csb.ce = CSB_CE_TERMINATION;
csb.address = fault_address;
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 426f94582b7a..8cb6eb76c129 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -2156,9 +2156,12 @@ registers, find a list below:
PPC KVM_REG_PPC_MMCRA 64
PPC KVM_REG_PPC_MMCR2 64
PPC KVM_REG_PPC_MMCRS 64
+ PPC KVM_REG_PPC_MMCR3 64
PPC KVM_REG_PPC_SIAR 64
PPC KVM_REG_PPC_SDAR 64
PPC KVM_REG_PPC_SIER 64
+ PPC KVM_REG_PPC_SIER2 64
+ PPC KVM_REG_PPC_SIER3 64
PPC KVM_REG_PPC_PMC1 32
PPC KVM_REG_PPC_PMC2 32
PPC KVM_REG_PPC_PMC3 32
diff --git a/MAINTAINERS b/MAINTAINERS
index 7b5ffd646c6b..7de395dfbdd5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13187,7 +13187,6 @@ F: tools/pci/
PCI ENHANCED ERROR HANDLING (EEH) FOR POWERPC
M: Russell Currey <ruscur@russell.cc>
-M: Sam Bobroff <sbobroff@linux.ibm.com>
M: Oliver O'Halloran <oohall@gmail.com>
L: linuxppc-dev@lists.ozlabs.org
S: Supported
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9fa23eb320ff..81c0dee1cbff 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -131,6 +131,7 @@ config PPC
select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_MEMBARRIER_CALLBACKS
+ select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
select ARCH_HAS_STRICT_KERNEL_RWX if (PPC32 && !HIBERNATION)
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
@@ -833,13 +834,16 @@ config FORCE_MAX_ZONEORDER
this in mind when choosing a value for this option.
config PPC_SUBPAGE_PROT
- bool "Support setting protections for 4k subpages"
+ bool "Support setting protections for 4k subpages (subpage_prot syscall)"
+ default n
depends on PPC_BOOK3S_64 && PPC_64K_PAGES
help
- This option adds support for a system call to allow user programs
+ This option adds support for system call to allow user programs
to set access permissions (read/write, readonly, or no access)
on the 4k subpages of each 64k page.
+ If unsure, say N here.
+
config PPC_COPRO_BASE
bool
@@ -859,12 +863,8 @@ config PPC_DENORMALISATION
Add support for handling denormalisation of single precision
values. Useful for bare metal only. If unsure say Y here.
-config CMDLINE_BOOL
- bool "Default bootloader kernel arguments"
-
config CMDLINE
- string "Initial kernel command string" if CMDLINE_BOOL
- default "console=ttyS0,9600 console=tty0 root=/dev/sda2" if CMDLINE_BOOL
+ string "Initial kernel command string"
default ""
help
On some platforms, there is currently no way for the boot loader to
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index f310c32e88a4..3e8da9cf2eb9 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -246,7 +246,8 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
# often slow when they are implemented at all
KBUILD_CFLAGS += $(call cc-option,-mno-string)
-cpu-as-$(CONFIG_4xx) += -Wa,-m405
+cpu-as-$(CONFIG_40x) += -Wa,-m405
+cpu-as-$(CONFIG_44x) += -Wa,-m440
cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec)
cpu-as-$(CONFIG_E200) += -Wa,-me200
cpu-as-$(CONFIG_E500) += -Wa,-me500
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 63d7456b9518..4d43cb59b4a4 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -70,10 +70,10 @@ BOOTCFLAGS += -I$(objtree)/$(obj) -I$(srctree)/$(obj)
DTC_FLAGS ?= -p 1024
$(obj)/4xx.o: BOOTCFLAGS += -mcpu=405
-$(obj)/ebony.o: BOOTCFLAGS += -mcpu=405
+$(obj)/ebony.o: BOOTCFLAGS += -mcpu=440
$(obj)/cuboot-hotfoot.o: BOOTCFLAGS += -mcpu=405
-$(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=405
-$(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=405
+$(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=440
+$(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=440
$(obj)/cuboot-acadia.o: BOOTCFLAGS += -mcpu=405
$(obj)/treeboot-iss4xx.o: BOOTCFLAGS += -mcpu=405
$(obj)/treeboot-currituck.o: BOOTCFLAGS += -mcpu=405
diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts
index cd9d66041a3f..df18f8dc4642 100644
--- a/arch/powerpc/boot/dts/akebono.dts
+++ b/arch/powerpc/boot/dts/akebono.dts
@@ -248,7 +248,7 @@
};
};
- PCIE0: pciex@10100000000 {
+ PCIE0: pcie@10100000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -288,7 +288,7 @@
0x0 0x0 0x0 0x4 &MPIC 48 0x2 /* int D */>;
};
- PCIE1: pciex@20100000000 {
+ PCIE1: pcie@20100000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -328,7 +328,7 @@
0x0 0x0 0x0 0x4 &MPIC 56 0x2 /* int D */>;
};
- PCIE2: pciex@18100000000 {
+ PCIE2: pcie@18100000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -368,7 +368,7 @@
0x0 0x0 0x0 0x4 &MPIC 64 0x2 /* int D */>;
};
- PCIE3: pciex@28100000000 {
+ PCIE3: pcie@28100000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/bluestone.dts b/arch/powerpc/boot/dts/bluestone.dts
index cc965a1816b6..aa1ae94cd776 100644
--- a/arch/powerpc/boot/dts/bluestone.dts
+++ b/arch/powerpc/boot/dts/bluestone.dts
@@ -325,7 +325,7 @@
};
};
- PCIE0: pciex@d00000000 {
+ PCIE0: pcie@d00000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts
index 0d6ac92d0f5e..c5fbb08e0a6e 100644
--- a/arch/powerpc/boot/dts/canyonlands.dts
+++ b/arch/powerpc/boot/dts/canyonlands.dts
@@ -461,7 +461,7 @@
interrupt-map = < 0x0 0x0 0x0 0x0 &UIC1 0x0 0x8 >;
};
- PCIE0: pciex@d00000000 {
+ PCIE0: pcie@d00000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -503,7 +503,7 @@
0x0 0x0 0x0 0x4 &UIC3 0xf 0x4 /* swizzled int D */>;
};
- PCIE1: pciex@d20000000 {
+ PCIE1: pcie@d20000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/currituck.dts b/arch/powerpc/boot/dts/currituck.dts
index b6d87b9c2cef..aea8af810106 100644
--- a/arch/powerpc/boot/dts/currituck.dts
+++ b/arch/powerpc/boot/dts/currituck.dts
@@ -122,7 +122,7 @@
};
};
- PCIE0: pciex@10100000000 { // 4xGBIF1
+ PCIE0: pcie@10100000000 { // 4xGBIF1
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -160,7 +160,7 @@
0x0 0x0 0x0 0x4 &MPIC 49 0x2 /* int D */>;
};
- PCIE1: pciex@30100000000 { // 4xGBIF0
+ PCIE1: pcie@30100000000 { // 4xGBIF0
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -197,7 +197,7 @@
0x0 0x0 0x0 0x4 &MPIC 41 0x2 /* int D */>;
};
- PCIE2: pciex@38100000000 { // 2xGBIF0
+ PCIE2: pcie@38100000000 { // 2xGBIF0
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/glacier.dts b/arch/powerpc/boot/dts/glacier.dts
index a7a802f4ffdd..e84ff1afb58c 100644
--- a/arch/powerpc/boot/dts/glacier.dts
+++ b/arch/powerpc/boot/dts/glacier.dts
@@ -489,7 +489,7 @@
interrupt-map = < 0x0 0x0 0x0 0x0 &UIC1 0x0 0x8 >;
};
- PCIE0: pciex@d00000000 {
+ PCIE0: pcie@d00000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -531,7 +531,7 @@
0x0 0x0 0x0 0x4 &UIC3 0xf 0x4 /* swizzled int D */>;
};
- PCIE1: pciex@d20000000 {
+ PCIE1: pcie@d20000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/haleakala.dts b/arch/powerpc/boot/dts/haleakala.dts
index cb16dad43c92..f81ce8786d59 100644
--- a/arch/powerpc/boot/dts/haleakala.dts
+++ b/arch/powerpc/boot/dts/haleakala.dts
@@ -237,7 +237,7 @@
};
};
- PCIE0: pciex@a0000000 {
+ PCIE0: pcie@a0000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/icon.dts b/arch/powerpc/boot/dts/icon.dts
index 2e6e3a7b2604..fbaa60b8f87a 100644
--- a/arch/powerpc/boot/dts/icon.dts
+++ b/arch/powerpc/boot/dts/icon.dts
@@ -315,7 +315,7 @@
interrupt-map = <0x0 0x0 0x0 0x0 &UIC1 19 0x8>;
};
- PCIE0: pciex@d00000000 {
+ PCIE0: pcie@d00000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -356,7 +356,7 @@
0x0 0x0 0x0 0x4 &UIC3 0x3 0x4 /* swizzled int D */>;
};
- PCIE1: pciex@d20000000 {
+ PCIE1: pcie@d20000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/katmai.dts b/arch/powerpc/boot/dts/katmai.dts
index 02629e119b87..a8f353229fb7 100644
--- a/arch/powerpc/boot/dts/katmai.dts
+++ b/arch/powerpc/boot/dts/katmai.dts
@@ -319,7 +319,7 @@
>;
};
- PCIE0: pciex@d00000000 {
+ PCIE0: pcie@d00000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -360,7 +360,7 @@
0x0 0x0 0x0 0x4 &UIC3 0x3 0x4 /* swizzled int D */>;
};
- PCIE1: pciex@d20000000 {
+ PCIE1: pcie@d20000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -401,7 +401,7 @@
0x0 0x0 0x0 0x4 &UIC3 0x7 0x4 /* swizzled int D */>;
};
- PCIE2: pciex@d40000000 {
+ PCIE2: pcie@d40000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts
index 2a3413221cc1..a709fb47a180 100644
--- a/arch/powerpc/boot/dts/kilauea.dts
+++ b/arch/powerpc/boot/dts/kilauea.dts
@@ -322,7 +322,7 @@
};
};
- PCIE0: pciex@a0000000 {
+ PCIE0: pcie@a0000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -363,7 +363,7 @@
0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
};
- PCIE1: pciex@c0000000 {
+ PCIE1: pcie@c0000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/makalu.dts b/arch/powerpc/boot/dts/makalu.dts
index bf8fe1629392..c473cd911bca 100644
--- a/arch/powerpc/boot/dts/makalu.dts
+++ b/arch/powerpc/boot/dts/makalu.dts
@@ -268,7 +268,7 @@
};
};
- PCIE0: pciex@a0000000 {
+ PCIE0: pcie@a0000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -309,7 +309,7 @@
0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
};
- PCIE1: pciex@c0000000 {
+ PCIE1: pcie@c0000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/dts/redwood.dts b/arch/powerpc/boot/dts/redwood.dts
index f3e046fb49e2..f38035a1f4a1 100644
--- a/arch/powerpc/boot/dts/redwood.dts
+++ b/arch/powerpc/boot/dts/redwood.dts
@@ -235,7 +235,7 @@
has-new-stacr-staopc;
};
};
- PCIE0: pciex@d00000000 {
+ PCIE0: pcie@d00000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -276,7 +276,7 @@
0x0 0x0 0x0 0x4 &UIC3 0x3 0x4 /* swizzled int D */>;
};
- PCIE1: pciex@d20000000 {
+ PCIE1: pcie@d20000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
@@ -317,7 +317,7 @@
0x0 0x0 0x0 0x4 &UIC3 0x7 0x4 /* swizzled int D */>;
};
- PCIE2: pciex@d40000000 {
+ PCIE2: pcie@d40000000 {
device_type = "pci";
#interrupt-cells = <1>;
#size-cells = <2>;
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index a9d209135975..cae31a6e8f02 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -104,7 +104,7 @@ static struct addr_range prep_initrd(struct addr_range vmlinux, void *chosen,
{
/* If we have an image attached to us, it overrides anything
* supplied by the loader. */
- if (_initrd_end > _initrd_start) {
+ if (&_initrd_end > &_initrd_start) {
printf("Attached initrd image at 0x%p-0x%p\n\r",
_initrd_start, _initrd_end);
initrd_addr = (unsigned long)_initrd_start;
@@ -152,7 +152,7 @@ static void prep_esm_blob(struct addr_range vmlinux, void *chosen)
unsigned long esm_blob_addr, esm_blob_size;
/* Do we have an ESM (Enter Secure Mode) blob? */
- if (_esm_blob_end <= _esm_blob_start)
+ if (&_esm_blob_end <= &_esm_blob_start)
return;
printf("Attached ESM blob at 0x%p-0x%p\n\r",
diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c
index c52552a681c5..6e4efbdb6b7c 100644
--- a/arch/powerpc/boot/ps3.c
+++ b/arch/powerpc/boot/ps3.c
@@ -127,7 +127,7 @@ void platform_init(void)
ps3_repository_read_rm_size(&rm_size);
dt_fixup_memory(0, rm_size);
- if (_initrd_end > _initrd_start) {
+ if (&_initrd_end > &_initrd_start) {
setprop_val(chosen, "linux,initrd-start", (u32)(_initrd_start));
setprop_val(chosen, "linux,initrd-end", (u32)(_initrd_end));
}
diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig
index 7705a5c3f4ea..60d5fa2c3b93 100644
--- a/arch/powerpc/configs/44x/akebono_defconfig
+++ b/arch/powerpc/configs/44x/akebono_defconfig
@@ -19,8 +19,6 @@ CONFIG_HIGHMEM=y
CONFIG_HZ_100=y
CONFIG_IRQ_ALL_CPUS=y
# CONFIG_COMPACTION is not set
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
# CONFIG_SUSPEND is not set
CONFIG_NET=y
CONFIG_PACKET=y
diff --git a/arch/powerpc/configs/44x/arches_defconfig b/arch/powerpc/configs/44x/arches_defconfig
index 82c6f49b8dcb..41d04e70d4fb 100644
--- a/arch/powerpc/configs/44x/arches_defconfig
+++ b/arch/powerpc/configs/44x/arches_defconfig
@@ -11,8 +11,6 @@ CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_EBONY is not set
CONFIG_ARCHES=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig
index 679213214a75..acbce718eaa8 100644
--- a/arch/powerpc/configs/44x/bamboo_defconfig
+++ b/arch/powerpc/configs/44x/bamboo_defconfig
@@ -9,8 +9,6 @@ CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
CONFIG_BAMBOO=y
# CONFIG_EBONY is not set
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/bluestone_defconfig b/arch/powerpc/configs/44x/bluestone_defconfig
index 8006a5728afd..37088f250c9e 100644
--- a/arch/powerpc/configs/44x/bluestone_defconfig
+++ b/arch/powerpc/configs/44x/bluestone_defconfig
@@ -11,8 +11,6 @@ CONFIG_EXPERT=y
# CONFIG_COMPAT_BRK is not set
CONFIG_BLUESTONE=y
# CONFIG_EBONY is not set
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig
index ccc14eb7a2f1..61776ade572b 100644
--- a/arch/powerpc/configs/44x/canyonlands_defconfig
+++ b/arch/powerpc/configs/44x/canyonlands_defconfig
@@ -11,8 +11,6 @@ CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_EBONY is not set
CONFIG_CANYONLANDS=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/currituck_defconfig b/arch/powerpc/configs/44x/currituck_defconfig
index be76e066df01..34c86b3abecb 100644
--- a/arch/powerpc/configs/44x/currituck_defconfig
+++ b/arch/powerpc/configs/44x/currituck_defconfig
@@ -17,8 +17,6 @@ CONFIG_HIGHMEM=y
CONFIG_HZ_100=y
CONFIG_MATH_EMULATION=y
CONFIG_IRQ_ALL_CPUS=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
# CONFIG_SUSPEND is not set
CONFIG_NET=y
CONFIG_PACKET=y
diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig
index 1abaa63e067f..509300f400e2 100644
--- a/arch/powerpc/configs/44x/eiger_defconfig
+++ b/arch/powerpc/configs/44x/eiger_defconfig
@@ -10,8 +10,6 @@ CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_EBONY is not set
CONFIG_EIGER=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_PCIEPORTBUS=y
# CONFIG_PCIEASPM is not set
CONFIG_NET=y
diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig
index e67fc041ca3e..30845ce0885a 100644
--- a/arch/powerpc/configs/44x/fsp2_defconfig
+++ b/arch/powerpc/configs/44x/fsp2_defconfig
@@ -28,7 +28,6 @@ CONFIG_476FPE_ERR46=y
CONFIG_SWIOTLB=y
CONFIG_KEXEC=y
CONFIG_CRASH_DUMP=y
-CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="ip=on rw"
# CONFIG_SUSPEND is not set
# CONFIG_PCI is not set
diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig
index 7d7ff84c8200..930948a1da76 100644
--- a/arch/powerpc/configs/44x/icon_defconfig
+++ b/arch/powerpc/configs/44x/icon_defconfig
@@ -9,8 +9,6 @@ CONFIG_MODULE_UNLOAD=y
# CONFIG_EBONY is not set
CONFIG_ICON=y
CONFIG_HIGHMEM=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_PCIEPORTBUS=y
# CONFIG_PCIEASPM is not set
CONFIG_NET=y
diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig
index fb5c73a29bf4..2c3834eebca3 100644
--- a/arch/powerpc/configs/44x/iss476-smp_defconfig
+++ b/arch/powerpc/configs/44x/iss476-smp_defconfig
@@ -17,7 +17,6 @@ CONFIG_ISS4xx=y
CONFIG_HZ_100=y
CONFIG_MATH_EMULATION=y
CONFIG_IRQ_ALL_CPUS=y
-CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="root=/dev/issblk0"
# CONFIG_PCI is not set
CONFIG_ADVANCED_OPTIONS=y
diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig
index c6dc1445fc04..1a0f1c3e0ee9 100644
--- a/arch/powerpc/configs/44x/katmai_defconfig
+++ b/arch/powerpc/configs/44x/katmai_defconfig
@@ -9,8 +9,6 @@ CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_EBONY is not set
CONFIG_KATMAI=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/rainier_defconfig b/arch/powerpc/configs/44x/rainier_defconfig
index c83ad03182df..6dd67de06a0b 100644
--- a/arch/powerpc/configs/44x/rainier_defconfig
+++ b/arch/powerpc/configs/44x/rainier_defconfig
@@ -10,8 +10,6 @@ CONFIG_MODULE_UNLOAD=y
# CONFIG_EBONY is not set
CONFIG_RAINIER=y
CONFIG_MATH_EMULATION=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig
index 640fe1d5af28..e28d76416537 100644
--- a/arch/powerpc/configs/44x/redwood_defconfig
+++ b/arch/powerpc/configs/44x/redwood_defconfig
@@ -10,8 +10,6 @@ CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_EBONY is not set
CONFIG_REDWOOD=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_PCIEPORTBUS=y
# CONFIG_PCIEASPM is not set
CONFIG_NET=y
diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig
index 22dc0dadf576..ef09786d49b9 100644
--- a/arch/powerpc/configs/44x/sam440ep_defconfig
+++ b/arch/powerpc/configs/44x/sam440ep_defconfig
@@ -12,8 +12,6 @@ CONFIG_PARTITION_ADVANCED=y
CONFIG_AMIGA_PARTITION=y
# CONFIG_EBONY is not set
CONFIG_SAM440EP=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig
index 2c0973db8837..b4984eab43eb 100644
--- a/arch/powerpc/configs/44x/sequoia_defconfig
+++ b/arch/powerpc/configs/44x/sequoia_defconfig
@@ -11,8 +11,6 @@ CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_EBONY is not set
CONFIG_SEQUOIA=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig
index a2d355ca62b2..3ea5932ab852 100644
--- a/arch/powerpc/configs/44x/taishan_defconfig
+++ b/arch/powerpc/configs/44x/taishan_defconfig
@@ -9,8 +9,6 @@ CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_EBONY is not set
CONFIG_TAISHAN=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig
index af66c69c49fe..47252c2d7669 100644
--- a/arch/powerpc/configs/44x/warp_defconfig
+++ b/arch/powerpc/configs/44x/warp_defconfig
@@ -14,7 +14,6 @@ CONFIG_MODULE_UNLOAD=y
CONFIG_WARP=y
CONFIG_PPC4xx_GPIO=y
CONFIG_HZ_1000=y
-CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="ip=on"
# CONFIG_PCI is not set
CONFIG_NET=y
diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
index b507df6ac69f..524db76f47b7 100644
--- a/arch/powerpc/configs/85xx-hw.config
+++ b/arch/powerpc/configs/85xx-hw.config
@@ -67,7 +67,6 @@ CONFIG_MTD_CFI_AMDSTD=y
CONFIG_MTD_CFI_INTELEXT=y
CONFIG_MTD_CFI=y
CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_M25P80=y
CONFIG_MTD_NAND_FSL_ELBC=y
CONFIG_MTD_NAND_FSL_IFC=y
CONFIG_MTD_RAW_NAND=y
diff --git a/arch/powerpc/configs/holly_defconfig b/arch/powerpc/configs/holly_defconfig
index 067f433c8f5e..271daff47d1d 100644
--- a/arch/powerpc/configs/holly_defconfig
+++ b/arch/powerpc/configs/holly_defconfig
@@ -13,7 +13,6 @@ CONFIG_EMBEDDED6xx=y
CONFIG_PPC_HOLLY=y
CONFIG_GEN_RTC=y
CONFIG_BINFMT_MISC=y
-CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="console=ttyS0,115200"
# CONFIG_SECCOMP is not set
CONFIG_NET=y
diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig
index 0a0d046fc445..3d53d69ed36c 100644
--- a/arch/powerpc/configs/mvme5100_defconfig
+++ b/arch/powerpc/configs/mvme5100_defconfig
@@ -20,10 +20,9 @@ CONFIG_EMBEDDED6xx=y
CONFIG_MVME5100=y
CONFIG_KVM_GUEST=y
CONFIG_HZ_100=y
+CONFIG_CMDLINE="console=ttyS0,9600 ip=dhcp root=/dev/nfs"
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_COMPACTION is not set
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyS0,9600 ip=dhcp root=/dev/nfs"
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 2de9aadf0f50..afc0dd73a1e6 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -64,7 +64,6 @@ CONFIG_HWPOISON_INJECT=m
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_PPC_64K_PAGES=y
-CONFIG_PPC_SUBPAGE_PROT=y
CONFIG_SCHED_SMT=y
CONFIG_PM=y
CONFIG_HOTPLUG_PCI=y
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 81b55c880fc3..142f1321fa58 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -34,8 +34,6 @@ CONFIG_KEXEC=y
# CONFIG_SPARSEMEM_VMEMMAP is not set
# CONFIG_COMPACTION is not set
CONFIG_SCHED_SMT=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
CONFIG_PM=y
CONFIG_PM_DEBUG=y
# CONFIG_SECCOMP is not set
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index dfa4a726333b..894e8d85fb48 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -57,7 +57,6 @@ CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_PPC_64K_PAGES=y
-CONFIG_PPC_SUBPAGE_PROT=y
CONFIG_SCHED_SMT=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_RPA=m
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index ad6739ac63dc..b806a5d3a695 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -45,7 +45,6 @@ CONFIG_IRQ_ALL_CPUS=y
CONFIG_NUMA=y
CONFIG_PPC_64K_PAGES=y
CONFIG_SCHED_SMT=y
-CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="console=tty0 console=hvc0 ipr.fast_reboot=1 quiet"
# CONFIG_SECCOMP is not set
# CONFIG_PPC_MEM_KEYS is not set
diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig
index b964084e4056..47dcfaddc1ac 100644
--- a/arch/powerpc/configs/storcenter_defconfig
+++ b/arch/powerpc/configs/storcenter_defconfig
@@ -12,7 +12,6 @@ CONFIG_EMBEDDED6xx=y
CONFIG_STORCENTER=y
CONFIG_HZ_100=y
CONFIG_BINFMT_MISC=y
-CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="console=ttyS0,115200"
# CONFIG_SECCOMP is not set
CONFIG_NET=y
diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/crypto/crc32-vpmsum_core.S
index c3524eba4d0d..a16a717c809c 100644
--- a/arch/powerpc/crypto/crc32-vpmsum_core.S
+++ b/arch/powerpc/crypto/crc32-vpmsum_core.S
@@ -19,7 +19,7 @@
* We then use fixed point Barrett reduction to compute a mod n over GF(2)
* for n = CRC using POWER8 instructions. We use x = 32.
*
- * http://en.wikipedia.org/wiki/Barrett_reduction
+ * https://en.wikipedia.org/wiki/Barrett_reduction
*
* Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
*/
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index fb47bf5818c8..de14b1a34d56 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -144,13 +144,13 @@ void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
/* Patch sites */
-extern s32 patch__call_flush_count_cache;
+extern s32 patch__call_flush_branch_caches;
extern s32 patch__flush_count_cache_return;
extern s32 patch__flush_link_stack_return;
extern s32 patch__call_kvm_flush_link_stack;
extern s32 patch__memset_nocache, patch__memcpy_nocache;
-extern long flush_count_cache;
+extern long flush_branch_caches;
extern long kvm_flush_link_stack;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index 123adcefd40f..35c1b8f3aa68 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -7,6 +7,10 @@
#include <asm/asm-const.h>
+#ifndef __ASSEMBLY__
+#include <asm/ppc-opcode.h>
+#endif
+
/*
* Memory barrier.
* The sync instruction guarantees that all memory accesses initiated
@@ -97,6 +101,15 @@ do { \
#define barrier_nospec()
#endif /* CONFIG_PPC_BARRIER_NOSPEC */
+/*
+ * pmem_wmb() ensures that all stores for which the modification
+ * are written to persistent storage by preceding dcbfps/dcbstps
+ * instructions have updated persistent storage before any data
+ * access or data transfer caused by subsequent instructions is
+ * initiated.
+ */
+#define pmem_wmb() __asm__ __volatile__(PPC_PHWSYNC ::: "memory")
+
#include <asm-generic/barrier.h>
#endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 3f9ae3585ab9..082b98808701 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -34,11 +34,11 @@
#define H_PUD_TABLE_SIZE (sizeof(pud_t) << H_PUD_INDEX_SIZE)
#define H_PGD_TABLE_SIZE (sizeof(pgd_t) << H_PGD_INDEX_SIZE)
-#define H_PAGE_F_GIX_SHIFT 53
-#define H_PAGE_F_SECOND _RPAGE_RPN44 /* HPTE is in 2ndary HPTEG */
-#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41)
-#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */
-#define H_PAGE_HASHPTE _RPAGE_RSV2 /* software: PTE & hash are busy */
+#define H_PAGE_F_GIX_SHIFT _PAGE_PA_MAX
+#define H_PAGE_F_SECOND _RPAGE_PKEY_BIT0 /* HPTE is in 2ndary HPTEG */
+#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41)
+#define H_PAGE_BUSY _RPAGE_RSV1
+#define H_PAGE_HASHPTE _RPAGE_PKEY_BIT4
/* PTE flags to conserve for HPTE identification */
#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \
@@ -57,11 +57,12 @@
#define H_PMD_FRAG_NR (PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT)
/* memory key bits, only 8 keys supported */
-#define H_PTE_PKEY_BIT0 0
-#define H_PTE_PKEY_BIT1 0
-#define H_PTE_PKEY_BIT2 _RPAGE_RSV3
-#define H_PTE_PKEY_BIT3 _RPAGE_RSV4
-#define H_PTE_PKEY_BIT4 _RPAGE_RSV5
+#define H_PTE_PKEY_BIT4 0
+#define H_PTE_PKEY_BIT3 0
+#define H_PTE_PKEY_BIT2 _RPAGE_PKEY_BIT3
+#define H_PTE_PKEY_BIT1 _RPAGE_PKEY_BIT2
+#define H_PTE_PKEY_BIT0 _RPAGE_PKEY_BIT1
+
/*
* On all 4K setups, remap_4k_pfn() equates to remap_pfn_range()
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 0729c034e56f..f20de1149ebe 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -32,15 +32,15 @@
*/
#define H_PAGE_COMBO _RPAGE_RPN0 /* this is a combo 4k page */
#define H_PAGE_4K_PFN _RPAGE_RPN1 /* PFN is for a single 4k page */
-#define H_PAGE_BUSY _RPAGE_RPN44 /* software: PTE & hash are busy */
+#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */
#define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */
/* memory key bits. */
-#define H_PTE_PKEY_BIT0 _RPAGE_RSV1
-#define H_PTE_PKEY_BIT1 _RPAGE_RSV2
-#define H_PTE_PKEY_BIT2 _RPAGE_RSV3
-#define H_PTE_PKEY_BIT3 _RPAGE_RSV4
-#define H_PTE_PKEY_BIT4 _RPAGE_RSV5
+#define H_PTE_PKEY_BIT4 _RPAGE_PKEY_BIT4
+#define H_PTE_PKEY_BIT3 _RPAGE_PKEY_BIT3
+#define H_PTE_PKEY_BIT2 _RPAGE_PKEY_BIT2
+#define H_PTE_PKEY_BIT1 _RPAGE_PKEY_BIT1
+#define H_PTE_PKEY_BIT0 _RPAGE_PKEY_BIT0
/*
* We need to differentiate between explicit huge page and THP huge
diff --git a/arch/powerpc/include/asm/book3s/64/hash-pkey.h b/arch/powerpc/include/asm/book3s/64/hash-pkey.h
new file mode 100644
index 000000000000..795010897e5d
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/hash-pkey.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H
+
+static inline u64 hash__vmflag_to_pte_pkey_bits(u64 vm_flags)
+{
+ return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT0 : 0x0UL) |
+ ((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT1 : 0x0UL) |
+ ((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) |
+ ((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT3 : 0x0UL) |
+ ((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT4 : 0x0UL));
+}
+
+static inline u64 pte_to_hpte_pkey_bits(u64 pteflags)
+{
+ return (((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL) |
+ ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) |
+ ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) |
+ ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) |
+ ((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL));
+}
+
+static inline u16 hash__pte_to_pkey_bits(u64 pteflags)
+{
+ return (((pteflags & H_PTE_PKEY_BIT4) ? 0x10 : 0x0UL) |
+ ((pteflags & H_PTE_PKEY_BIT3) ? 0x8 : 0x0UL) |
+ ((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) |
+ ((pteflags & H_PTE_PKEY_BIT1) ? 0x2 : 0x0UL) |
+ ((pteflags & H_PTE_PKEY_BIT0) ? 0x1 : 0x0UL));
+}
+
+#endif
diff --git a/arch/powerpc/include/asm/book3s/64/kexec.h b/arch/powerpc/include/asm/book3s/64/kexec.h
new file mode 100644
index 000000000000..6b5c3a248ba2
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/kexec.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_POWERPC_BOOK3S_64_KEXEC_H_
+#define _ASM_POWERPC_BOOK3S_64_KEXEC_H_
+
+
+#define reset_sprs reset_sprs
+static inline void reset_sprs(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+ mtspr(SPRN_AMR, 0);
+ mtspr(SPRN_UAMOR, 0);
+ }
+
+ if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ mtspr(SPRN_IAMR, 0);
+ }
+
+ /* Do we need isync()? We are going via a kexec reset */
+ isync();
+}
+
+#endif
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 3fa1b962dc27..58fcc959f9d5 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -86,8 +86,8 @@
#define HPTE_R_PP0 ASM_CONST(0x8000000000000000)
#define HPTE_R_TS ASM_CONST(0x4000000000000000)
#define HPTE_R_KEY_HI ASM_CONST(0x3000000000000000)
-#define HPTE_R_KEY_BIT0 ASM_CONST(0x2000000000000000)
-#define HPTE_R_KEY_BIT1 ASM_CONST(0x1000000000000000)
+#define HPTE_R_KEY_BIT4 ASM_CONST(0x2000000000000000)
+#define HPTE_R_KEY_BIT3 ASM_CONST(0x1000000000000000)
#define HPTE_R_RPN_SHIFT 12
#define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000)
#define HPTE_R_RPN_3_0 ASM_CONST(0x01fffffffffff000)
@@ -103,8 +103,8 @@
#define HPTE_R_R ASM_CONST(0x0000000000000100)
#define HPTE_R_KEY_LO ASM_CONST(0x0000000000000e00)
#define HPTE_R_KEY_BIT2 ASM_CONST(0x0000000000000800)
-#define HPTE_R_KEY_BIT3 ASM_CONST(0x0000000000000400)
-#define HPTE_R_KEY_BIT4 ASM_CONST(0x0000000000000200)
+#define HPTE_R_KEY_BIT1 ASM_CONST(0x0000000000000400)
+#define HPTE_R_KEY_BIT0 ASM_CONST(0x0000000000000200)
#define HPTE_R_KEY (HPTE_R_KEY_LO | HPTE_R_KEY_HI)
#define HPTE_V_1TB_SEG ASM_CONST(0x4000000000000000)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 5393a535240c..55442d45c597 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -82,6 +82,11 @@ extern unsigned int mmu_pid_bits;
/* Base PID to allocate from */
extern unsigned int mmu_base_pid;
+/*
+ * memory block size used with radix translation.
+ */
+extern unsigned int __ro_after_init radix_mem_block_size;
+
#define PRTB_SIZE_SHIFT (mmu_pid_bits + 4)
#define PRTB_ENTRIES (1ul << mmu_pid_bits)
@@ -209,6 +214,12 @@ extern int mmu_io_psize;
void mmu_early_init_devtree(void);
void hash__early_init_devtree(void);
void radix__early_init_devtree(void);
+#ifdef CONFIG_PPC_MEM_KEYS
+void pkey_early_init_devtree(void);
+#else
+static inline void pkey_early_init_devtree(void) {}
+#endif
+
extern void hash__early_init_mmu(void);
extern void radix__early_init_mmu(void);
static inline void __init early_init_mmu(void)
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 69c5b051734f..e1af0b394ceb 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -107,9 +107,23 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
return pud;
}
+static inline void __pud_free(pud_t *pud)
+{
+ struct page *page = virt_to_page(pud);
+
+ /*
+ * Early pud pages allocated via memblock allocator
+ * can't be directly freed to slab
+ */
+ if (PageReserved(page))
+ free_reserved_page(page);
+ else
+ kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud);
+}
+
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
{
- kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud);
+ return __pud_free(pud);
}
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 25c3cb8272c0..6de56c3b33c4 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -20,9 +20,13 @@
#define _PAGE_RW (_PAGE_READ | _PAGE_WRITE)
#define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
#define _PAGE_PRIVILEGED 0x00008 /* kernel access only */
-#define _PAGE_SAO 0x00010 /* Strong access order */
+
+#define _PAGE_CACHE_CTL 0x00030 /* Bits for the folowing cache modes */
+ /* No bits set is normal cacheable memory */
+ /* 0x00010 unused, is SAO bit on radix POWER9 */
#define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */
#define _PAGE_TOLERANT 0x00030 /* tolerant memory, cache inhibited */
+
#define _PAGE_DIRTY 0x00080 /* C: page changed */
#define _PAGE_ACCESSED 0x00100 /* R: page referenced */
/*
@@ -32,11 +36,13 @@
#define _RPAGE_SW1 0x00800
#define _RPAGE_SW2 0x00400
#define _RPAGE_SW3 0x00200
-#define _RPAGE_RSV1 0x1000000000000000UL
-#define _RPAGE_RSV2 0x0800000000000000UL
-#define _RPAGE_RSV3 0x0400000000000000UL
-#define _RPAGE_RSV4 0x0200000000000000UL
-#define _RPAGE_RSV5 0x00040UL
+#define _RPAGE_RSV1 0x00040UL
+
+#define _RPAGE_PKEY_BIT4 0x1000000000000000UL
+#define _RPAGE_PKEY_BIT3 0x0800000000000000UL
+#define _RPAGE_PKEY_BIT2 0x0400000000000000UL
+#define _RPAGE_PKEY_BIT1 0x0200000000000000UL
+#define _RPAGE_PKEY_BIT0 0x0100000000000000UL
#define _PAGE_PTE 0x4000000000000000UL /* distinguishes PTEs from pointers */
#define _PAGE_PRESENT 0x8000000000000000UL /* pte contains a translation */
@@ -58,13 +64,12 @@
*/
#define _RPAGE_RPN0 0x01000
#define _RPAGE_RPN1 0x02000
-#define _RPAGE_RPN44 0x0100000000000000UL
#define _RPAGE_RPN43 0x0080000000000000UL
#define _RPAGE_RPN42 0x0040000000000000UL
#define _RPAGE_RPN41 0x0020000000000000UL
/* Max physical address bit as per radix table */
-#define _RPAGE_PA_MAX 57
+#define _RPAGE_PA_MAX 56
/*
* Max physical address bit we will use for now.
@@ -125,8 +130,6 @@
_PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \
_PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
-#define H_PTE_PKEY (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \
- H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4)
/*
* We define 2 sets of base prot bits, one for basic pages (ie,
* cacheable kernel and user pages) and one for non cacheable
@@ -825,8 +828,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
return hash__set_pte_at(mm, addr, ptep, pte, percpu);
}
-#define _PAGE_CACHE_CTL (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT)
-
#define pgprot_noncached pgprot_noncached
static inline pgprot_t pgprot_noncached(pgprot_t prot)
{
diff --git a/arch/powerpc/include/asm/book3s/64/pkeys.h b/arch/powerpc/include/asm/book3s/64/pkeys.h
new file mode 100644
index 000000000000..b7d9f4267bcd
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/pkeys.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _ASM_POWERPC_BOOK3S_64_PKEYS_H
+#define _ASM_POWERPC_BOOK3S_64_PKEYS_H
+
+#include <asm/book3s/64/hash-pkey.h>
+
+extern u64 __ro_after_init default_uamor;
+
+static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags)
+{
+ if (!mmu_has_feature(MMU_FTR_PKEY))
+ return 0x0UL;
+
+ if (radix_enabled())
+ BUG();
+ return hash__vmflag_to_pte_pkey_bits(vm_flags);
+}
+
+static inline u16 pte_to_pkey_bits(u64 pteflags)
+{
+ if (radix_enabled())
+ BUG();
+ return hash__pte_to_pkey_bits(pteflags);
+}
+
+#endif /*_ASM_POWERPC_KEYS_H */
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index ca8db193ae38..94439e0cefc9 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -2,10 +2,25 @@
#ifndef _ASM_POWERPC_TLBFLUSH_RADIX_H
#define _ASM_POWERPC_TLBFLUSH_RADIX_H
+#include <asm/hvcall.h>
+
struct vm_area_struct;
struct mm_struct;
struct mmu_gather;
+static inline u64 psize_to_rpti_pgsize(unsigned long psize)
+{
+ if (psize == MMU_PAGE_4K)
+ return H_RPTI_PAGE_4K;
+ if (psize == MMU_PAGE_64K)
+ return H_RPTI_PAGE_64K;
+ if (psize == MMU_PAGE_2M)
+ return H_RPTI_PAGE_2M;
+ if (psize == MMU_PAGE_1G)
+ return H_RPTI_PAGE_1G;
+ return H_RPTI_PAGE_ALL;
+}
+
static inline int mmu_get_ap(int psize)
{
return mmu_psize_defs[psize].ap;
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index de600b915a3c..54764c6e922d 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -6,6 +6,7 @@
#include <linux/mm.h>
#include <asm/cputable.h>
+#include <asm/cpu_has_feature.h>
#ifdef CONFIG_PPC_BOOK3S_64
/*
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index bac2252c839e..a461c3300804 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -191,14 +191,14 @@ static inline void cpu_feature_keys_init(void) { }
#define CPU_FTR_SPURR LONG_ASM_CONST(0x0000000001000000)
#define CPU_FTR_DSCR LONG_ASM_CONST(0x0000000002000000)
#define CPU_FTR_VSX LONG_ASM_CONST(0x0000000004000000)
-#define CPU_FTR_SAO LONG_ASM_CONST(0x0000000008000000)
+// Free LONG_ASM_CONST(0x0000000008000000)
#define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0000000010000000)
#define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0000000020000000)
#define CPU_FTR_ASYM_SMT LONG_ASM_CONST(0x0000000040000000)
#define CPU_FTR_STCX_CHECKS_ADDRESS LONG_ASM_CONST(0x0000000080000000)
#define CPU_FTR_POPCNTB LONG_ASM_CONST(0x0000000100000000)
#define CPU_FTR_POPCNTD LONG_ASM_CONST(0x0000000200000000)
-#define CPU_FTR_PKEY LONG_ASM_CONST(0x0000000400000000)
+/* LONG_ASM_CONST(0x0000000400000000) Free */
#define CPU_FTR_VMX_COPY LONG_ASM_CONST(0x0000000800000000)
#define CPU_FTR_TM LONG_ASM_CONST(0x0000001000000000)
#define CPU_FTR_CFAR LONG_ASM_CONST(0x0000002000000000)
@@ -435,32 +435,32 @@ static inline void cpu_feature_keys_init(void) { }
CPU_FTR_MMCRA | CPU_FTR_SMT | \
CPU_FTR_COHERENT_ICACHE | \
CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
- CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \
+ CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \
CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_CFAR | CPU_FTR_HVMODE | \
- CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX | CPU_FTR_PKEY)
+ CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX )
#define CPU_FTRS_POWER8 (CPU_FTR_LWSYNC | \
CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
CPU_FTR_MMCRA | CPU_FTR_SMT | \
CPU_FTR_COHERENT_ICACHE | \
CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
- CPU_FTR_DSCR | CPU_FTR_SAO | \
+ CPU_FTR_DSCR | \
CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
- CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_PKEY)
+ CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP )
#define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
#define CPU_FTRS_POWER9 (CPU_FTR_LWSYNC | \
CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
CPU_FTR_MMCRA | CPU_FTR_SMT | \
CPU_FTR_COHERENT_ICACHE | \
CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
- CPU_FTR_DSCR | CPU_FTR_SAO | \
+ CPU_FTR_DSCR | \
CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
- CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \
- CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR)
+ CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_P9_TLBIE_STQ_BUG | \
+ CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR)
#define CPU_FTRS_POWER9_DD2_0 (CPU_FTRS_POWER9 | CPU_FTR_P9_RADIX_PREFETCH_BUG)
#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | \
CPU_FTR_P9_RADIX_PREFETCH_BUG | \
@@ -473,12 +473,11 @@ static inline void cpu_feature_keys_init(void) { }
CPU_FTR_MMCRA | CPU_FTR_SMT | \
CPU_FTR_COHERENT_ICACHE | \
CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
- CPU_FTR_DSCR | CPU_FTR_SAO | \
+ CPU_FTR_DSCR | \
CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
- CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \
- CPU_FTR_ARCH_31)
+ CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_ARCH_31)
#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 | \
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 0fccd5ea1e9a..9335b93924b4 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -36,6 +36,8 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct)
return mulhdu((__force u64) ct, __cputime_usec_factor);
}
+#define cputime_to_nsecs(cputime) tb_to_ns((__force u64)cputime)
+
/*
* PPC64 uses PACA which is task independent for storing accounting data while
* PPC32 uses struct thread_info, therefore at task switch the accounting data
diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
index 54a98ef7d7fe..72b6657acd2d 100644
--- a/arch/powerpc/include/asm/exception-64e.h
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -204,7 +204,11 @@ exc_##label##_book3e:
LOAD_REG_ADDR(r3,interrupt_base_book3e);\
ori r3,r3,vector_offset@l; \
mtspr SPRN_IVOR##vector_number,r3;
-
+/*
+ * powerpc relies on return from interrupt/syscall being context synchronising
+ * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional
+ * synchronisation instructions.
+ */
#define RFI_TO_KERNEL \
rfi
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 0c2fe7f042d1..ebe95aa04d53 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -68,6 +68,14 @@
*
* The nop instructions allow us to insert one or more instructions to flush the
* L1-D cache when returning to userspace or a guest.
+ *
+ * powerpc relies on return from interrupt/syscall being context synchronising
+ * (which hrfid, rfid, and rfscv are) to support ARCH_HAS_MEMBARRIER_SYNC_CORE
+ * without additional synchronisation instructions.
+ *
+ * soft-masked interrupt replay does not include a context-synchronising rfid,
+ * but those always return to kernel, the sync is only required when returning
+ * to user.
*/
#define RFI_FLUSH_SLOT \
RFI_FLUSH_FIXUP_SECTION; \
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index 29188810ba30..925cf89cbf4b 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -52,7 +52,7 @@ enum fixed_addresses {
FIX_HOLE,
/* reserve the top 128K for early debugging purposes */
FIX_EARLY_DEBUG_TOP = FIX_HOLE,
- FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+((128*1024)/PAGE_SIZE)-1,
+ FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1,
#ifdef CONFIG_HIGHMEM
FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index e90c073e437e..8d7ee3b533c4 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -237,7 +237,7 @@
#define H_CREATE_RPT 0x1A4
#define H_REMOVE_RPT 0x1A8
#define H_REGISTER_RPAGES 0x1AC
-#define H_DISABLE_AND_GETC 0x1B0
+#define H_DISABLE_AND_GET 0x1B0
#define H_ERROR_DATA 0x1B4
#define H_GET_HCA_INFO 0x1B8
#define H_GET_PERF_COUNT 0x1BC
@@ -305,7 +305,8 @@
#define H_SCM_UNBIND_ALL 0x3FC
#define H_SCM_HEALTH 0x400
#define H_SCM_PERFORMANCE_STATS 0x418
-#define MAX_HCALL_OPCODE H_SCM_PERFORMANCE_STATS
+#define H_RPT_INVALIDATE 0x448
+#define MAX_HCALL_OPCODE H_RPT_INVALIDATE
/* Scope args for H_SCM_UNBIND_ALL */
#define H_UNBIND_SCOPE_ALL (0x1)
@@ -389,6 +390,37 @@
#define PROC_TABLE_RADIX 0x04
#define PROC_TABLE_GTSE 0x01
+/*
+ * Defines for
+ * H_RPT_INVALIDATE - Invalidate RPT translation lookaside information.
+ */
+
+/* Type of translation to invalidate (type) */
+#define H_RPTI_TYPE_NESTED 0x0001 /* Invalidate nested guest partition-scope */
+#define H_RPTI_TYPE_TLB 0x0002 /* Invalidate TLB */
+#define H_RPTI_TYPE_PWC 0x0004 /* Invalidate Page Walk Cache */
+/* Invalidate Process Table Entries if H_RPTI_TYPE_NESTED is clear */
+#define H_RPTI_TYPE_PRT 0x0008
+/* Invalidate Partition Table Entries if H_RPTI_TYPE_NESTED is set */
+#define H_RPTI_TYPE_PAT 0x0008
+#define H_RPTI_TYPE_ALL (H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \
+ H_RPTI_TYPE_PRT)
+#define H_RPTI_TYPE_NESTED_ALL (H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \
+ H_RPTI_TYPE_PAT)
+
+/* Invalidation targets (target) */
+#define H_RPTI_TARGET_CMMU 0x01 /* All virtual processors in the partition */
+#define H_RPTI_TARGET_CMMU_LOCAL 0x02 /* Current virtual processor */
+/* All nest/accelerator agents in use by the partition */
+#define H_RPTI_TARGET_NMMU 0x04
+
+/* Page size mask (page sizes) */
+#define H_RPTI_PAGE_4K 0x01
+#define H_RPTI_PAGE_64K 0x02
+#define H_RPTI_PAGE_2M 0x04
+#define H_RPTI_PAGE_1G 0x08
+#define H_RPTI_PAGE_ALL (-1UL)
+
#ifndef __ASSEMBLY__
#include <linux/types.h>
diff --git a/arch/powerpc/include/asm/hydra.h b/arch/powerpc/include/asm/hydra.h
index b3b0f2d020f0..ae02eb53d6ef 100644
--- a/arch/powerpc/include/asm/hydra.h
+++ b/arch/powerpc/include/asm/hydra.h
@@ -10,7 +10,7 @@
*
* © Copyright 1995 Apple Computer, Inc. All rights reserved.
*
- * It's available online from http://www.cpu.lu/~mlan/ftp/MacTech.pdf
+ * It's available online from https://www.cpu.lu/~mlan/ftp/MacTech.pdf
* You can obtain paper copies of this book from computer bookstores or by
* writing Morgan Kaufmann Publishers, Inc., 340 Pine Street, Sixth Floor, San
* Francisco, CA 94104. Reference ISBN 1-55860-393-X.
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
index 965b1f39b2a5..b0c70a35fd0e 100644
--- a/arch/powerpc/include/asm/icswx.h
+++ b/arch/powerpc/include/asm/icswx.h
@@ -77,6 +77,8 @@ struct coprocessor_completion_block {
#define CSB_CC_CHAIN (37)
#define CSB_CC_SEQUENCE (38)
#define CSB_CC_HW (39)
+/* P9 DD2 NX Workbook 3.2 (Table 4-36): Address translation fault */
+#define CSB_CC_FAULT_ADDRESS (250)
#define CSB_SIZE (0x10)
#define CSB_ALIGN CSB_SIZE
diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h
index 4da4fcba0684..4f897993b710 100644
--- a/arch/powerpc/include/asm/imc-pmu.h
+++ b/arch/powerpc/include/asm/imc-pmu.h
@@ -99,6 +99,11 @@ struct trace_imc_data {
*/
#define IMC_TRACE_RECORD_TB1_MASK 0x3ffffffffffULL
+/*
+ * Bit 0:1 in third DW of IMC trace record
+ * specifies the MSR[HV PR] values.
+ */
+#define IMC_TRACE_RECORD_VAL_HVPR(x) ((x) >> 62)
/*
* Device tree parser code detects IMC pmu support and
diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h
index 45f3ec868258..cc73c1267572 100644
--- a/arch/powerpc/include/asm/inst.h
+++ b/arch/powerpc/include/asm/inst.h
@@ -122,6 +122,25 @@ static inline u64 ppc_inst_as_u64(struct ppc_inst x)
#endif
}
+#define PPC_INST_STR_LEN sizeof("00000000 00000000")
+
+static inline char *__ppc_inst_as_str(char str[PPC_INST_STR_LEN], struct ppc_inst x)
+{
+ if (ppc_inst_prefixed(x))
+ sprintf(str, "%08x %08x", ppc_inst_val(x), ppc_inst_suffix(x));
+ else
+ sprintf(str, "%08x", ppc_inst_val(x));
+
+ return str;
+}
+
+#define ppc_inst_as_str(x) \
+({ \
+ char __str[PPC_INST_STR_LEN]; \
+ __ppc_inst_as_str(__str, x); \
+ __str; \
+})
+
int probe_user_read_inst(struct ppc_inst *inst,
struct ppc_inst __user *nip);
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index be85c7005fb1..d635b96c7ea6 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -27,10 +27,12 @@
#ifdef CONFIG_KASAN
void kasan_early_init(void);
+void kasan_mmu_init(void);
void kasan_init(void);
void kasan_late_init(void);
#else
static inline void kasan_init(void) { }
+static inline void kasan_mmu_init(void) { }
static inline void kasan_late_init(void) { }
#endif
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index c68476818753..89f7e3462292 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -150,6 +150,18 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
}
#endif /* CONFIG_KEXEC_CORE */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#include <asm/book3s/64/kexec.h>
+#endif
+
+#ifndef reset_sprs
+#define reset_sprs reset_sprs
+static inline void reset_sprs(void)
+{
+}
+#endif
+
#endif /* ! __ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_KEXEC_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 45704f2716e2..078f4648ea27 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -119,7 +119,7 @@ struct kvmppc_host_state {
void __iomem *xive_tima_virt;
u32 saved_xirr;
u64 dabr;
- u64 host_mmcr[7]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER */
+ u64 host_mmcr[10]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER, MMCR3, SIER2/3 */
u32 host_pmc[8];
u64 host_purr;
u64 host_spurr;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 7e2d061d0445..e020d269416d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -637,12 +637,14 @@ struct kvm_vcpu_arch {
u32 ccr1;
u32 dbsr;
- u64 mmcr[5];
+ u64 mmcr[4]; /* MMCR0, MMCR1, MMCR2, MMCR3 */
+ u64 mmcra;
+ u64 mmcrs;
u32 pmc[8];
u32 spmc[2];
u64 siar;
u64 sdar;
- u64 sier;
+ u64 sier[3];
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
u64 tfhar;
u64 texasr;
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 376a395daf32..adf2cda67f9a 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -86,6 +86,7 @@ enum MCE_TlbErrorType {
enum MCE_UserErrorType {
MCE_USER_ERROR_INDETERMINATE = 0,
MCE_USER_ERROR_TLBIE = 1,
+ MCE_USER_ERROR_SCV = 2,
};
enum MCE_RaErrorType {
@@ -220,6 +221,8 @@ extern void machine_check_print_event_info(struct machine_check_event *evt,
unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr);
extern void mce_common_process_ue(struct pt_regs *regs,
struct mce_error_info *mce_err);
+int mce_register_notifier(struct notifier_block *nb);
+int mce_unregister_notifier(struct notifier_block *nb);
#ifdef CONFIG_PPC_BOOK3S_64
void flush_and_reload_slb(void);
#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index d610c2e07b28..7c07728af300 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -13,42 +13,20 @@
#include <linux/pkeys.h>
#include <asm/cpu_has_feature.h>
-/*
- * This file is included by linux/mman.h, so we can't use cacl_vm_prot_bits()
- * here. How important is the optimization?
- */
+#ifdef CONFIG_PPC_MEM_KEYS
static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
unsigned long pkey)
{
-#ifdef CONFIG_PPC_MEM_KEYS
- return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey));
-#else
- return ((prot & PROT_SAO) ? VM_SAO : 0);
-#endif
+ return pkey_to_vmflag_bits(pkey);
}
#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
{
-#ifdef CONFIG_PPC_MEM_KEYS
- return (vm_flags & VM_SAO) ?
- __pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) :
- __pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags));
-#else
- return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0);
-#endif
+ return __pgprot(vmflag_to_pte_pkey_bits(vm_flags));
}
#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
-
-static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
-{
- if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
- return false;
- if ((prot & PROT_SAO) && !cpu_has_feature(CPU_FTR_SAO))
- return false;
- return true;
-}
-#define arch_validate_prot arch_validate_prot
+#endif
#endif /* CONFIG_PPC64 */
#endif /* _ASM_POWERPC_MMAN_H */
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index f4ac25d4df05..255a1837e9f7 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -29,6 +29,19 @@
*/
/*
+ * Support for KUEP feature.
+ */
+#define MMU_FTR_KUEP ASM_CONST(0x00000400)
+
+/*
+ * Support for memory protection keys.
+ */
+#define MMU_FTR_PKEY ASM_CONST(0x00000800)
+
+/* Guest Translation Shootdown Enable */
+#define MMU_FTR_GTSE ASM_CONST(0x00001000)
+
+/*
* Support for 68 bit VA space. We added that from ISA 2.05
*/
#define MMU_FTR_68_BIT_VA ASM_CONST(0x00002000)
@@ -173,10 +186,18 @@ enum {
#endif
#ifdef CONFIG_PPC_RADIX_MMU
MMU_FTR_TYPE_RADIX |
+ MMU_FTR_GTSE |
#ifdef CONFIG_PPC_KUAP
MMU_FTR_RADIX_KUAP |
#endif /* CONFIG_PPC_KUAP */
#endif /* CONFIG_PPC_RADIX_MMU */
+#ifdef CONFIG_PPC_MEM_KEYS
+ MMU_FTR_PKEY |
+#endif
+#ifdef CONFIG_PPC_KUEP
+ MMU_FTR_KUEP |
+#endif /* CONFIG_PPC_KUAP */
+
0,
};
@@ -356,6 +377,8 @@ extern void setup_initial_memory_limit(phys_addr_t first_memblock_base,
phys_addr_t first_memblock_size);
static inline void mmu_early_init_devtree(void) { }
+static inline void pkey_early_init_devtree(void) {}
+
extern void *abatron_pteptrs[2];
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 1a474f6b1992..7f3658a97384 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -218,8 +218,6 @@ static inline void inc_mm_active_cpus(struct mm_struct *mm) { }
static inline void dec_mm_active_cpus(struct mm_struct *mm) { }
static inline void mm_context_add_copro(struct mm_struct *mm) { }
static inline void mm_context_remove_copro(struct mm_struct *mm) { }
-static inline void mm_context_add_vas_windows(struct mm_struct *mm) { }
-static inline void mm_context_remove_vas_windows(struct mm_struct *mm) { }
#endif
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index b0afbdd07740..b9e134d0f03a 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -249,6 +249,18 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
return old;
}
+
+#ifdef CONFIG_PPC_16K_PAGES
+#define __HAVE_ARCH_PTEP_GET
+static inline pte_t ptep_get(pte_t *ptep)
+{
+ pte_basic_t val = READ_ONCE(ptep->pte);
+ pte_t pte = {val, val, val, val};
+
+ return pte;
+}
+#endif /* CONFIG_PPC_16K_PAGES */
+
#else
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)
@@ -284,16 +296,6 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
return __pte(pte_update(mm, addr, ptep, ~0, 0, 0));
}
-#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
-#define __HAVE_ARCH_PTEP_GET
-static inline pte_t ptep_get(pte_t *ptep)
-{
- pte_t pte = {READ_ONCE(ptep->pte), 0, 0, 0};
-
- return pte;
-}
-#endif
-
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 6cb8aa357191..59ee9fa4ae09 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -82,8 +82,6 @@
*/
#include <asm/nohash/pte-book3e.h>
-#define _PAGE_SAO 0
-
#define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1))
/*
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index eed3954082fa..1e8b2e1ec1db 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -12,6 +12,8 @@
#ifdef CONFIG_PPC_PERF_CTRS
#include <asm/perf_event_server.h>
+#else
+static inline bool is_sier_available(void) { return false; }
#endif
#ifdef CONFIG_FSL_EMB_PERF_EVENT
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 3e9703f44c7c..86c9eb064b22 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -17,6 +17,13 @@
struct perf_event;
+struct mmcr_regs {
+ unsigned long mmcr0;
+ unsigned long mmcr1;
+ unsigned long mmcr2;
+ unsigned long mmcra;
+ unsigned long mmcr3;
+};
/*
* This struct provides the constants and functions needed to
* describe the PMU on a particular POWER-family CPU.
@@ -28,7 +35,7 @@ struct power_pmu {
unsigned long add_fields;
unsigned long test_adder;
int (*compute_mmcr)(u64 events[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[],
+ unsigned int hwc[], struct mmcr_regs *mmcr,
struct perf_event *pevents[]);
int (*get_constraint)(u64 event_id, unsigned long *mskp,
unsigned long *valp);
@@ -41,13 +48,13 @@ struct power_pmu {
unsigned long group_constraint_val;
u64 (*bhrb_filter_map)(u64 branch_sample_type);
void (*config_bhrb)(u64 pmu_bhrb_filter);
- void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
+ void (*disable_pmc)(unsigned int pmc, struct mmcr_regs *mmcr);
int (*limited_pmc_event)(u64 event_id);
u32 flags;
const struct attribute_group **attr_groups;
int n_generic;
int *generic_events;
- int (*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+ u64 (*cache_events)[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
@@ -69,6 +76,7 @@ struct power_pmu {
#define PPMU_HAS_SIER 0x00000040 /* Has SIER */
#define PPMU_ARCH_207S 0x00000080 /* PMC is architecture v2.07S */
#define PPMU_NO_SIAR 0x00000100 /* Do not use SIAR */
+#define PPMU_ARCH_31 0x00000200 /* Has MMCR3, SIER2 and SIER3 */
/*
* Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/pkeys.h b/arch/powerpc/include/asm/pkeys.h
index 2fe6cae14d10..a7951049e129 100644
--- a/arch/powerpc/include/asm/pkeys.h
+++ b/arch/powerpc/include/asm/pkeys.h
@@ -11,9 +11,7 @@
#include <linux/jump_label.h>
#include <asm/firmware.h>
-DECLARE_STATIC_KEY_TRUE(pkey_disabled);
-extern int pkeys_total; /* total pkeys as per device tree */
-extern u32 initial_allocation_mask; /* bits set for the initially allocated keys */
+extern int num_pkey;
extern u32 reserved_allocation_mask; /* bits set for reserved keys */
#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | \
@@ -25,48 +23,28 @@ extern u32 reserved_allocation_mask; /* bits set for reserved keys */
PKEY_DISABLE_WRITE | \
PKEY_DISABLE_EXECUTE)
+#ifdef CONFIG_PPC_BOOK3S_64
+#include <asm/book3s/64/pkeys.h>
+#else
+#error "Not supported"
+#endif
+
+
static inline u64 pkey_to_vmflag_bits(u16 pkey)
{
return (((u64)pkey << VM_PKEY_SHIFT) & ARCH_VM_PKEY_FLAGS);
}
-static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags)
-{
- if (static_branch_likely(&pkey_disabled))
- return 0x0UL;
-
- return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT4 : 0x0UL) |
- ((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT3 : 0x0UL) |
- ((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) |
- ((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT1 : 0x0UL) |
- ((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT0 : 0x0UL));
-}
-
static inline int vma_pkey(struct vm_area_struct *vma)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return 0;
return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT;
}
-#define arch_max_pkey() pkeys_total
-
-static inline u64 pte_to_hpte_pkey_bits(u64 pteflags)
+static inline int arch_max_pkey(void)
{
- return (((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL) |
- ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) |
- ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) |
- ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) |
- ((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL));
-}
-
-static inline u16 pte_to_pkey_bits(u64 pteflags)
-{
- return (((pteflags & H_PTE_PKEY_BIT0) ? 0x10 : 0x0UL) |
- ((pteflags & H_PTE_PKEY_BIT1) ? 0x8 : 0x0UL) |
- ((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) |
- ((pteflags & H_PTE_PKEY_BIT3) ? 0x2 : 0x0UL) |
- ((pteflags & H_PTE_PKEY_BIT4) ? 0x1 : 0x0UL));
+ return num_pkey;
}
#define pkey_alloc_mask(pkey) (0x1 << pkey)
@@ -114,9 +92,8 @@ static inline int mm_pkey_alloc(struct mm_struct *mm)
u32 all_pkeys_mask = (u32)(~(0x0));
int ret;
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return -1;
-
/*
* Are we out of pkeys? We must handle this specially because ffz()
* behavior is undefined if there are no zeros.
@@ -132,7 +109,7 @@ static inline int mm_pkey_alloc(struct mm_struct *mm)
static inline int mm_pkey_free(struct mm_struct *mm, int pkey)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return -1;
if (!mm_pkey_is_allocated(mm, pkey))
@@ -147,21 +124,13 @@ static inline int mm_pkey_free(struct mm_struct *mm, int pkey)
* Try to dedicate one of the protection keys to be used as an
* execute-only protection key.
*/
-extern int __execute_only_pkey(struct mm_struct *mm);
-static inline int execute_only_pkey(struct mm_struct *mm)
-{
- if (static_branch_likely(&pkey_disabled))
- return -1;
-
- return __execute_only_pkey(mm);
-}
-
+extern int execute_only_pkey(struct mm_struct *mm);
extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma,
int prot, int pkey);
static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
int prot, int pkey)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return 0;
/*
@@ -179,7 +148,7 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
unsigned long init_val)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return -EINVAL;
/*
@@ -196,7 +165,7 @@ static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
static inline bool arch_pkeys_enabled(void)
{
- return !static_branch_likely(&pkey_disabled);
+ return mmu_has_feature(MMU_FTR_PKEY);
}
extern void pkey_mm_init(struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 4497c8afb573..4293c5d2ddf4 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -334,6 +334,51 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
return rc;
}
+/*
+ * Wrapper to H_RPT_INVALIDATE hcall that handles return values appropriately
+ *
+ * - Returns H_SUCCESS on success
+ * - For H_BUSY return value, we retry the hcall.
+ * - For any other hcall failures, attempt a full flush once before
+ * resorting to BUG().
+ *
+ * Note: This hcall is expected to fail only very rarely. The correct
+ * error recovery of killing the process/guest will be eventually
+ * needed.
+ */
+static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type,
+ u64 page_sizes, u64 start, u64 end)
+{
+ long rc;
+ unsigned long all;
+
+ while (true) {
+ rc = plpar_hcall_norets(H_RPT_INVALIDATE, pid, target, type,
+ page_sizes, start, end);
+ if (rc == H_BUSY) {
+ cpu_relax();
+ continue;
+ } else if (rc == H_SUCCESS)
+ return rc;
+
+ /* Flush request failed, try with a full flush once */
+ if (type & H_RPTI_TYPE_NESTED)
+ all = H_RPTI_TYPE_NESTED | H_RPTI_TYPE_NESTED_ALL;
+ else
+ all = H_RPTI_TYPE_ALL;
+retry:
+ rc = plpar_hcall_norets(H_RPT_INVALIDATE, pid, target,
+ all, page_sizes, 0, -1UL);
+ if (rc == H_BUSY) {
+ cpu_relax();
+ goto retry;
+ } else if (rc == H_SUCCESS)
+ return rc;
+
+ BUG();
+ }
+}
+
#else /* !CONFIG_PPC_PSERIES */
static inline long plpar_set_ciabr(unsigned long ciabr)
@@ -346,6 +391,13 @@ static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex,
{
return 0;
}
+
+static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type,
+ u64 page_sizes, u64 start, u64 end)
+{
+ return 0;
+}
+
#endif /* CONFIG_PPC_PSERIES */
#endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 2a39c716c343..4c0bdafb6a7b 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -76,6 +76,19 @@
#define __REGA0_R30 30
#define __REGA0_R31 31
+#define IMM_L(i) ((uintptr_t)(i) & 0xffff)
+#define IMM_DS(i) ((uintptr_t)(i) & 0xfffc)
+
+/*
+ * 16-bit immediate helper macros: HA() is for use with sign-extending instrs
+ * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the
+ * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000).
+ */
+#define IMM_H(i) ((uintptr_t)(i)>>16)
+#define IMM_HA(i) (((uintptr_t)(i)>>16) + \
+ (((uintptr_t)(i) & 0x8000) >> 15))
+
+
/* opcode and xopcode for instructions */
#define OP_TRAP 3
#define OP_TRAP_64 2
@@ -195,56 +208,28 @@
#define OP_LQ 56
/* sorted alphabetically */
-#define PPC_INST_BHRBE 0x7c00025c
-#define PPC_INST_CLRBHRB 0x7c00035c
+#define PPC_INST_BCCTR_FLUSH 0x4c400420
#define PPC_INST_COPY 0x7c20060c
-#define PPC_INST_CP_ABORT 0x7c00068c
-#define PPC_INST_DARN 0x7c0005e6
#define PPC_INST_DCBA 0x7c0005ec
#define PPC_INST_DCBA_MASK 0xfc0007fe
-#define PPC_INST_DCBAL 0x7c2005ec
-#define PPC_INST_DCBZL 0x7c2007ec
-#define PPC_INST_ICBT 0x7c00002c
-#define PPC_INST_ICSWX 0x7c00032d
-#define PPC_INST_ICSWEPX 0x7c00076d
#define PPC_INST_ISEL 0x7c00001e
#define PPC_INST_ISEL_MASK 0xfc00003e
-#define PPC_INST_LDARX 0x7c0000a8
-#define PPC_INST_STDCX 0x7c0001ad
-#define PPC_INST_LQARX 0x7c000228
-#define PPC_INST_STQCX 0x7c00016d
#define PPC_INST_LSWI 0x7c0004aa
#define PPC_INST_LSWX 0x7c00042a
-#define PPC_INST_LWARX 0x7c000028
-#define PPC_INST_STWCX 0x7c00012d
#define PPC_INST_LWSYNC 0x7c2004ac
#define PPC_INST_SYNC 0x7c0004ac
#define PPC_INST_SYNC_MASK 0xfc0007fe
#define PPC_INST_ISYNC 0x4c00012c
-#define PPC_INST_LXVD2X 0x7c000698
#define PPC_INST_MCRXR 0x7c000400
#define PPC_INST_MCRXR_MASK 0xfc0007fe
#define PPC_INST_MFSPR_PVR 0x7c1f42a6
#define PPC_INST_MFSPR_PVR_MASK 0xfc1ffffe
-#define PPC_INST_MFTMR 0x7c0002dc
-#define PPC_INST_MSGSND 0x7c00019c
-#define PPC_INST_MSGCLR 0x7c0001dc
-#define PPC_INST_MSGSYNC 0x7c0006ec
-#define PPC_INST_MSGSNDP 0x7c00011c
-#define PPC_INST_MSGCLRP 0x7c00015c
#define PPC_INST_MTMSRD 0x7c000164
-#define PPC_INST_MTTMR 0x7c0003dc
#define PPC_INST_NOP 0x60000000
-#define PPC_INST_PASTE 0x7c20070d
#define PPC_INST_POPCNTB 0x7c0000f4
#define PPC_INST_POPCNTB_MASK 0xfc0007fe
-#define PPC_INST_POPCNTD 0x7c0003f4
-#define PPC_INST_POPCNTW 0x7c0002f4
#define PPC_INST_RFEBB 0x4c000124
-#define PPC_INST_RFCI 0x4c000066
-#define PPC_INST_RFDI 0x4c00004e
#define PPC_INST_RFID 0x4c000024
-#define PPC_INST_RFMCI 0x4c00004c
#define PPC_INST_MFSPR 0x7c0002a6
#define PPC_INST_MFSPR_DSCR 0x7c1102a6
#define PPC_INST_MFSPR_DSCR_MASK 0xfc1ffffe
@@ -254,131 +239,43 @@
#define PPC_INST_MFSPR_DSCR_USER_MASK 0xfc1ffffe
#define PPC_INST_MTSPR_DSCR_USER 0x7c0303a6
#define PPC_INST_MTSPR_DSCR_USER_MASK 0xfc1ffffe
-#define PPC_INST_MFVSRD 0x7c000066
-#define PPC_INST_MTVSRD 0x7c000166
#define PPC_INST_SC 0x44000002
-#define PPC_INST_SLBFEE 0x7c0007a7
-#define PPC_INST_SLBIA 0x7c0003e4
-
#define PPC_INST_STRING 0x7c00042a
#define PPC_INST_STRING_MASK 0xfc0007fe
#define PPC_INST_STRING_GEN_MASK 0xfc00067e
-
#define PPC_INST_STSWI 0x7c0005aa
#define PPC_INST_STSWX 0x7c00052a
-#define PPC_INST_STXVD2X 0x7c000798
-#define PPC_INST_TLBIE 0x7c000264
-#define PPC_INST_TLBIEL 0x7c000224
-#define PPC_INST_TLBILX 0x7c000024
-#define PPC_INST_WAIT 0x7c00007c
-#define PPC_INST_TLBIVAX 0x7c000624
-#define PPC_INST_TLBSRX_DOT 0x7c0006a5
-#define PPC_INST_VPMSUMW 0x10000488
-#define PPC_INST_VPMSUMD 0x100004c8
-#define PPC_INST_VPERMXOR 0x1000002d
-#define PPC_INST_XXLOR 0xf0000490
-#define PPC_INST_XXSWAPD 0xf0000250
-#define PPC_INST_XVCPSGNDP 0xf0000780
#define PPC_INST_TRECHKPT 0x7c0007dd
#define PPC_INST_TRECLAIM 0x7c00075d
-#define PPC_INST_TABORT 0x7c00071d
#define PPC_INST_TSR 0x7c0005dd
-
-#define PPC_INST_NAP 0x4c000364
-#define PPC_INST_SLEEP 0x4c0003a4
-#define PPC_INST_WINKLE 0x4c0003e4
-
-#define PPC_INST_STOP 0x4c0002e4
-
-/* A2 specific instructions */
-#define PPC_INST_ERATWE 0x7c0001a6
-#define PPC_INST_ERATRE 0x7c000166
-#define PPC_INST_ERATILX 0x7c000066
-#define PPC_INST_ERATIVAX 0x7c000666
-#define PPC_INST_ERATSX 0x7c000126
-#define PPC_INST_ERATSX_DOT 0x7c000127
-
-/* Misc instructions for BPF compiler */
-#define PPC_INST_LBZ 0x88000000
#define PPC_INST_LD 0xe8000000
-#define PPC_INST_LDX 0x7c00002a
-#define PPC_INST_LHZ 0xa0000000
-#define PPC_INST_LWZ 0x80000000
-#define PPC_INST_LHBRX 0x7c00062c
-#define PPC_INST_LDBRX 0x7c000428
-#define PPC_INST_STB 0x98000000
-#define PPC_INST_STH 0xb0000000
#define PPC_INST_STD 0xf8000000
-#define PPC_INST_STDX 0x7c00012a
-#define PPC_INST_STDU 0xf8000001
-#define PPC_INST_STW 0x90000000
-#define PPC_INST_STWU 0x94000000
#define PPC_INST_MFLR 0x7c0802a6
-#define PPC_INST_MTLR 0x7c0803a6
#define PPC_INST_MTCTR 0x7c0903a6
-#define PPC_INST_CMPWI 0x2c000000
-#define PPC_INST_CMPDI 0x2c200000
-#define PPC_INST_CMPW 0x7c000000
-#define PPC_INST_CMPD 0x7c200000
-#define PPC_INST_CMPLW 0x7c000040
-#define PPC_INST_CMPLD 0x7c200040
-#define PPC_INST_CMPLWI 0x28000000
-#define PPC_INST_CMPLDI 0x28200000
#define PPC_INST_ADDI 0x38000000
#define PPC_INST_ADDIS 0x3c000000
#define PPC_INST_ADD 0x7c000214
-#define PPC_INST_ADDC 0x7c000014
-#define PPC_INST_SUB 0x7c000050
#define PPC_INST_BLR 0x4e800020
-#define PPC_INST_BLRL 0x4e800021
#define PPC_INST_BCTR 0x4e800420
-#define PPC_INST_MULLD 0x7c0001d2
-#define PPC_INST_MULLW 0x7c0001d6
-#define PPC_INST_MULHWU 0x7c000016
-#define PPC_INST_MULLI 0x1c000000
-#define PPC_INST_MADDHD 0x10000030
-#define PPC_INST_MADDHDU 0x10000031
-#define PPC_INST_MADDLD 0x10000033
-#define PPC_INST_DIVWU 0x7c000396
+#define PPC_INST_BCTRL 0x4e800421
#define PPC_INST_DIVD 0x7c0003d2
-#define PPC_INST_DIVDU 0x7c000392
-#define PPC_INST_RLWINM 0x54000000
-#define PPC_INST_RLWINM_DOT 0x54000001
-#define PPC_INST_RLWIMI 0x50000000
-#define PPC_INST_RLDICL 0x78000000
#define PPC_INST_RLDICR 0x78000004
-#define PPC_INST_SLW 0x7c000030
-#define PPC_INST_SLD 0x7c000036
-#define PPC_INST_SRW 0x7c000430
-#define PPC_INST_SRAW 0x7c000630
-#define PPC_INST_SRAWI 0x7c000670
-#define PPC_INST_SRD 0x7c000436
-#define PPC_INST_SRAD 0x7c000634
-#define PPC_INST_SRADI 0x7c000674
-#define PPC_INST_AND 0x7c000038
-#define PPC_INST_ANDDOT 0x7c000039
-#define PPC_INST_OR 0x7c000378
-#define PPC_INST_XOR 0x7c000278
-#define PPC_INST_ANDI 0x70000000
#define PPC_INST_ORI 0x60000000
#define PPC_INST_ORIS 0x64000000
-#define PPC_INST_XORI 0x68000000
-#define PPC_INST_XORIS 0x6c000000
-#define PPC_INST_NEG 0x7c0000d0
-#define PPC_INST_EXTSW 0x7c0007b4
#define PPC_INST_BRANCH 0x48000000
#define PPC_INST_BRANCH_COND 0x40800000
-#define PPC_INST_LBZCIX 0x7c0006aa
-#define PPC_INST_STBCIX 0x7c0007aa
-#define PPC_INST_LWZX 0x7c00002e
-#define PPC_INST_LFSX 0x7c00042e
-#define PPC_INST_STFSX 0x7c00052e
-#define PPC_INST_LFDX 0x7c0004ae
-#define PPC_INST_STFDX 0x7c0005ae
-#define PPC_INST_LVX 0x7c0000ce
-#define PPC_INST_STVX 0x7c0001ce
-#define PPC_INST_VCMPEQUD 0x100000c7
-#define PPC_INST_VCMPEQUB 0x10000006
+
+/* Prefixes */
+#define PPC_INST_LFS 0xc0000000
+#define PPC_INST_STFS 0xd0000000
+#define PPC_INST_LFD 0xc8000000
+#define PPC_INST_STFD 0xd8000000
+#define PPC_PREFIX_MLS 0x06000000
+#define PPC_PREFIX_8LS 0x04000000
+
+/* Prefixed instructions */
+#define PPC_INST_PLD 0xe4000000
+#define PPC_INST_PSTD 0xf4000000
/* macros to insert fields into opcodes */
#define ___PPC_RA(a) (((a) & 0x1f) << 16)
@@ -411,6 +308,7 @@
#define __PPC_CT(t) (((t) & 0x0f) << 21)
#define __PPC_SPR(r) ((((r) & 0x1f) << 16) | ((((r) >> 5) & 0x1f) << 11))
#define __PPC_RC21 (0x1 << 10)
+#define __PPC_PRFX_R(r) (((r) & 0x1) << 20)
/*
* Both low and high 16 bits are added as SIGNED additions, so if low 16 bits
@@ -431,175 +329,272 @@
#define __PPC_EH(eh) 0
#endif
+/* Base instruction encoding */
+#define PPC_RAW_CP_ABORT (0x7c00068c)
+#define PPC_RAW_COPY(a, b) (PPC_INST_COPY | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_DARN(t, l) (0x7c0005e6 | ___PPC_RT(t) | (((l) & 0x3) << 16))
+#define PPC_RAW_DCBAL(a, b) (0x7c2005ec | __PPC_RA(a) | __PPC_RB(b))
+#define PPC_RAW_DCBZL(a, b) (0x7c2007ec | __PPC_RA(a) | __PPC_RB(b))
+#define PPC_RAW_LQARX(t, a, b, eh) (0x7c000228 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh))
+#define PPC_RAW_LDARX(t, a, b, eh) (0x7c0000a8 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh))
+#define PPC_RAW_LWARX(t, a, b, eh) (0x7c000028 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh))
+#define PPC_RAW_PHWSYNC (0x7c8004ac)
+#define PPC_RAW_PLWSYNC (0x7ca004ac)
+#define PPC_RAW_STQCX(t, a, b) (0x7c00016d | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_MADDHD(t, a, b, c) (0x10000030 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c))
+#define PPC_RAW_MADDHDU(t, a, b, c) (0x10000031 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c))
+#define PPC_RAW_MADDLD(t, a, b, c) (0x10000033 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c))
+#define PPC_RAW_MSGSND(b) (0x7c00019c | ___PPC_RB(b))
+#define PPC_RAW_MSGSYNC (0x7c0006ec)
+#define PPC_RAW_MSGCLR(b) (0x7c0001dc | ___PPC_RB(b))
+#define PPC_RAW_MSGSNDP(b) (0x7c00011c | ___PPC_RB(b))
+#define PPC_RAW_MSGCLRP(b) (0x7c00015c | ___PPC_RB(b))
+#define PPC_RAW_PASTE(a, b) (0x7c20070d | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_POPCNTB(a, s) (PPC_INST_POPCNTB | __PPC_RA(a) | __PPC_RS(s))
+#define PPC_RAW_POPCNTD(a, s) (0x7c0003f4 | __PPC_RA(a) | __PPC_RS(s))
+#define PPC_RAW_POPCNTW(a, s) (0x7c0002f4 | __PPC_RA(a) | __PPC_RS(s))
+#define PPC_RAW_RFCI (0x4c000066)
+#define PPC_RAW_RFDI (0x4c00004e)
+#define PPC_RAW_RFMCI (0x4c00004c)
+#define PPC_RAW_TLBILX(t, a, b) (0x7c000024 | __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_RAW_WAIT(w) (0x7c00007c | __PPC_WC(w))
+#define PPC_RAW_TLBIE(lp, a) (0x7c000264 | ___PPC_RB(a) | ___PPC_RS(lp))
+#define PPC_RAW_TLBIE_5(rb, rs, ric, prs, r) \
+ (0x7c000264 | ___PPC_RB(rb) | ___PPC_RS(rs) | ___PPC_RIC(ric) | ___PPC_PRS(prs) | ___PPC_R(r))
+#define PPC_RAW_TLBIEL(rb, rs, ric, prs, r) \
+ (0x7c000224 | ___PPC_RB(rb) | ___PPC_RS(rs) | ___PPC_RIC(ric) | ___PPC_PRS(prs) | ___PPC_R(r))
+#define PPC_RAW_TLBSRX_DOT(a, b) (0x7c0006a5 | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_RAW_TLBIVAX(a, b) (0x7c000624 | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_RAW_ERATWE(s, a, w) (0x7c0001a6 | __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
+#define PPC_RAW_ERATRE(s, a, w) (0x7c000166 | __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
+#define PPC_RAW_ERATILX(t, a, b) (0x7c000066 | __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_RAW_ERATIVAX(s, a, b) (0x7c000666 | __PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_RAW_ERATSX(t, a, w) (0x7c000126 | __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_RAW_ERATSX_DOT(t, a, w) (0x7c000127 | __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_RAW_SLBFEE_DOT(t, b) (0x7c0007a7 | __PPC_RT(t) | __PPC_RB(b))
+#define __PPC_RAW_SLBFEE_DOT(t, b) (0x7c0007a7 | ___PPC_RT(t) | ___PPC_RB(b))
+#define PPC_RAW_ICBT(c, a, b) (0x7c00002c | __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_RAW_LBZCIX(t, a, b) (0x7c0006aa | __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b))
+#define PPC_RAW_STBCIX(s, a, b) (0x7c0007aa | __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b))
+#define PPC_RAW_DCBFPS(a, b) (0x7c0000ac | ___PPC_RA(a) | ___PPC_RB(b) | (4 << 21))
+#define PPC_RAW_DCBSTPS(a, b) (0x7c0000ac | ___PPC_RA(a) | ___PPC_RB(b) | (6 << 21))
+/*
+ * Define what the VSX XX1 form instructions will look like, then add
+ * the 128 bit load store instructions based on that.
+ */
+#define VSX_XX1(s, a, b) (__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b))
+#define VSX_XX3(t, a, b) (__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b))
+#define PPC_RAW_STXVD2X(s, a, b) (0x7c000798 | VSX_XX1((s), a, b))
+#define PPC_RAW_LXVD2X(s, a, b) (0x7c000698 | VSX_XX1((s), a, b))
+#define PPC_RAW_MFVRD(a, t) (0x7c000066 | VSX_XX1((t) + 32, a, R0))
+#define PPC_RAW_MTVRD(t, a) (0x7c000166 | VSX_XX1((t) + 32, a, R0))
+#define PPC_RAW_VPMSUMW(t, a, b) (0x10000488 | VSX_XX3((t), a, b))
+#define PPC_RAW_VPMSUMD(t, a, b) (0x100004c8 | VSX_XX3((t), a, b))
+#define PPC_RAW_XXLOR(t, a, b) (0xf0000490 | VSX_XX3((t), a, b))
+#define PPC_RAW_XXSWAPD(t, a) (0xf0000250 | VSX_XX3((t), a, a))
+#define PPC_RAW_XVCPSGNDP(t, a, b) ((0xf0000780 | VSX_XX3((t), (a), (b))))
+#define PPC_RAW_VPERMXOR(vrt, vra, vrb, vrc) \
+ ((0x1000002d | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | (((vrc) & 0x1f) << 6)))
+#define PPC_RAW_NAP (0x4c000364)
+#define PPC_RAW_SLEEP (0x4c0003a4)
+#define PPC_RAW_WINKLE (0x4c0003e4)
+#define PPC_RAW_STOP (0x4c0002e4)
+#define PPC_RAW_CLRBHRB (0x7c00035c)
+#define PPC_RAW_MFBHRBE(r, n) (0x7c00025c | __PPC_RT(r) | (((n) & 0x3ff) << 11))
+#define PPC_RAW_TRECHKPT (PPC_INST_TRECHKPT)
+#define PPC_RAW_TRECLAIM(r) (PPC_INST_TRECLAIM | __PPC_RA(r))
+#define PPC_RAW_TABORT(r) (0x7c00071d | __PPC_RA(r))
+#define TMRN(x) ((((x) & 0x1f) << 16) | (((x) & 0x3e0) << 6))
+#define PPC_RAW_MTTMR(tmr, r) (0x7c0003dc | TMRN(tmr) | ___PPC_RS(r))
+#define PPC_RAW_MFTMR(tmr, r) (0x7c0002dc | TMRN(tmr) | ___PPC_RT(r))
+#define PPC_RAW_ICSWX(s, a, b) (0x7c00032d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_ICSWEPX(s, a, b) (0x7c00076d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_SLBIA(IH) (0x7c0003e4 | (((IH) & 0x7) << 21))
+#define PPC_RAW_VCMPEQUD_RC(vrt, vra, vrb) \
+ (0x100000c7 | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | __PPC_RC21)
+#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) (PPC_INST_LD | ___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) (PPC_INST_STD | ___PPC_RS(r) | ___PPC_RA(base) | IMM_DS(i))
+#define PPC_RAW_STDCX(s, a, b) (0x7c0001ad | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_LFSX(t, a, b) (0x7c00042e | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_STFSX(s, a, b) (0x7c00052e | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_LFDX(t, a, b) (0x7c0004ae | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_STFDX(s, a, b) (0x7c0005ae | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_LVX(t, a, b) (0x7c0000ce | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_STVX(s, a, b) (0x7c0001ce | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_ADD(t, a, b) (PPC_INST_ADD | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_ADD_DOT(t, a, b) (PPC_INST_ADD | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1)
+#define PPC_RAW_ADDC(t, a, b) (0x7c000014 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_ADDC_DOT(t, a, b) (0x7c000014 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1)
+#define PPC_RAW_NOP() (PPC_INST_NOP)
+#define PPC_RAW_BLR() (PPC_INST_BLR)
+#define PPC_RAW_BLRL() (0x4e800021)
+#define PPC_RAW_MTLR(r) (0x7c0803a6 | ___PPC_RT(r))
+#define PPC_RAW_BCTR() (PPC_INST_BCTR)
+#define PPC_RAW_MTCTR(r) (PPC_INST_MTCTR | ___PPC_RT(r))
+#define PPC_RAW_ADDI(d, a, i) (PPC_INST_ADDI | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i))
+#define PPC_RAW_LI(r, i) PPC_RAW_ADDI(r, 0, i)
+#define PPC_RAW_ADDIS(d, a, i) (PPC_INST_ADDIS | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i))
+#define PPC_RAW_LIS(r, i) PPC_RAW_ADDIS(r, 0, i)
+#define PPC_RAW_STDX(r, base, b) (0x7c00012a | ___PPC_RS(r) | ___PPC_RA(base) | ___PPC_RB(b))
+#define PPC_RAW_STDU(r, base, i) (0xf8000001 | ___PPC_RS(r) | ___PPC_RA(base) | ((i) & 0xfffc))
+#define PPC_RAW_STW(r, base, i) (0x90000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i))
+#define PPC_RAW_STWU(r, base, i) (0x94000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i))
+#define PPC_RAW_STH(r, base, i) (0xb0000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i))
+#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_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_LDBRX(r, base, b) (0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
+#define PPC_RAW_STWCX(s, a, b) (0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_CMPWI(a, i) (0x2c000000 | ___PPC_RA(a) | IMM_L(i))
+#define PPC_RAW_CMPDI(a, i) (0x2c200000 | ___PPC_RA(a) | IMM_L(i))
+#define PPC_RAW_CMPW(a, b) (0x7c000000 | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_CMPD(a, b) (0x7c200000 | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_CMPLWI(a, i) (0x28000000 | ___PPC_RA(a) | IMM_L(i))
+#define PPC_RAW_CMPLDI(a, i) (0x28200000 | ___PPC_RA(a) | IMM_L(i))
+#define PPC_RAW_CMPLW(a, b) (0x7c000040 | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_CMPLD(a, b) (0x7c200040 | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_SUB(d, a, b) (0x7c000050 | ___PPC_RT(d) | ___PPC_RB(a) | ___PPC_RA(b))
+#define PPC_RAW_MULD(d, a, b) (0x7c0001d2 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
+#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_DIVWU(d, a, b) (0x7c000396 | ___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_AND(d, a, b) (0x7c000038 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b))
+#define PPC_RAW_ANDI(d, a, i) (0x70000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i))
+#define PPC_RAW_AND_DOT(d, a, b) (0x7c000039 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b))
+#define PPC_RAW_OR(d, a, b) (0x7c000378 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b))
+#define PPC_RAW_MR(d, a) PPC_RAW_OR(d, a, a)
+#define PPC_RAW_ORI(d, a, i) (PPC_INST_ORI | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i))
+#define PPC_RAW_ORIS(d, a, i) (PPC_INST_ORIS | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i))
+#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_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))
+#define PPC_RAW_SRW(d, a, s) (0x7c000430 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_RAW_SRAW(d, a, s) (0x7c000630 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_RAW_SRAWI(d, a, i) (0x7c000670 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i))
+#define PPC_RAW_SRD(d, a, s) (0x7c000436 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_RAW_SRAD(d, a, s) (0x7c000634 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_RAW_SRADI(d, a, i) (0x7c000674 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i))
+#define PPC_RAW_RLWINM(d, a, i, mb, me) (0x54000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me))
+#define PPC_RAW_RLWINM_DOT(d, a, i, mb, me) \
+ (0x54000001 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me))
+#define PPC_RAW_RLWIMI(d, a, i, mb, me) (0x50000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me))
+#define PPC_RAW_RLDICL(d, a, i, mb) (0x78000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_MB64(mb))
+#define PPC_RAW_RLDICR(d, a, i, me) (PPC_INST_RLDICR | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_ME64(me))
+
+/* slwi = rlwinm Rx, Ry, n, 0, 31-n */
+#define PPC_RAW_SLWI(d, a, i) PPC_RAW_RLWINM(d, a, i, 0, 31-(i))
+/* srwi = rlwinm Rx, Ry, 32-n, n, 31 */
+#define PPC_RAW_SRWI(d, a, i) PPC_RAW_RLWINM(d, a, 32-(i), i, 31)
+/* sldi = rldicr Rx, Ry, n, 63-n */
+#define PPC_RAW_SLDI(d, a, i) PPC_RAW_RLDICR(d, a, i, 63-(i))
+/* sldi = rldicl Rx, Ry, 64-n, n */
+#define PPC_RAW_SRDI(d, a, i) PPC_RAW_RLDICL(d, a, 64-(i), i)
+
+#define PPC_RAW_NEG(d, a) (0x7c0000d0 | ___PPC_RT(d) | ___PPC_RA(a))
+
/* Deal with instructions that older assemblers aren't aware of */
-#define PPC_CP_ABORT stringify_in_c(.long PPC_INST_CP_ABORT)
-#define PPC_COPY(a, b) stringify_in_c(.long PPC_INST_COPY | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_DARN(t, l) stringify_in_c(.long PPC_INST_DARN | \
- ___PPC_RT(t) | \
- (((l) & 0x3) << 16))
-#define PPC_DCBAL(a, b) stringify_in_c(.long PPC_INST_DCBAL | \
- __PPC_RA(a) | __PPC_RB(b))
-#define PPC_DCBZL(a, b) stringify_in_c(.long PPC_INST_DCBZL | \
- __PPC_RA(a) | __PPC_RB(b))
-#define PPC_LQARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LQARX | \
- ___PPC_RT(t) | ___PPC_RA(a) | \
- ___PPC_RB(b) | __PPC_EH(eh))
-#define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LDARX | \
- ___PPC_RT(t) | ___PPC_RA(a) | \
- ___PPC_RB(b) | __PPC_EH(eh))
-#define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LWARX | \
- ___PPC_RT(t) | ___PPC_RA(a) | \
- ___PPC_RB(b) | __PPC_EH(eh))
-#define PPC_STQCX(t, a, b) stringify_in_c(.long PPC_INST_STQCX | \
- ___PPC_RT(t) | ___PPC_RA(a) | \
- ___PPC_RB(b))
-#define PPC_MADDHD(t, a, b, c) stringify_in_c(.long PPC_INST_MADDHD | \
- ___PPC_RT(t) | ___PPC_RA(a) | \
- ___PPC_RB(b) | ___PPC_RC(c))
-#define PPC_MADDHDU(t, a, b, c) stringify_in_c(.long PPC_INST_MADDHDU | \
- ___PPC_RT(t) | ___PPC_RA(a) | \
- ___PPC_RB(b) | ___PPC_RC(c))
-#define PPC_MADDLD(t, a, b, c) stringify_in_c(.long PPC_INST_MADDLD | \
- ___PPC_RT(t) | ___PPC_RA(a) | \
- ___PPC_RB(b) | ___PPC_RC(c))
-#define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \
- ___PPC_RB(b))
-#define PPC_MSGSYNC stringify_in_c(.long PPC_INST_MSGSYNC)
-#define PPC_MSGCLR(b) stringify_in_c(.long PPC_INST_MSGCLR | \
- ___PPC_RB(b))
-#define PPC_MSGSNDP(b) stringify_in_c(.long PPC_INST_MSGSNDP | \
- ___PPC_RB(b))
-#define PPC_MSGCLRP(b) stringify_in_c(.long PPC_INST_MSGCLRP | \
- ___PPC_RB(b))
-#define PPC_PASTE(a, b) stringify_in_c(.long PPC_INST_PASTE | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_INST_POPCNTB | \
- __PPC_RA(a) | __PPC_RS(s))
-#define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_INST_POPCNTD | \
- __PPC_RA(a) | __PPC_RS(s))
-#define PPC_POPCNTW(a, s) stringify_in_c(.long PPC_INST_POPCNTW | \
- __PPC_RA(a) | __PPC_RS(s))
-#define PPC_RFCI stringify_in_c(.long PPC_INST_RFCI)
-#define PPC_RFDI stringify_in_c(.long PPC_INST_RFDI)
-#define PPC_RFMCI stringify_in_c(.long PPC_INST_RFMCI)
-#define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_INST_TLBILX | \
- __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b))
+#define PPC_BCCTR_FLUSH stringify_in_c(.long PPC_INST_BCCTR_FLUSH)
+#define PPC_CP_ABORT stringify_in_c(.long PPC_RAW_CP_ABORT)
+#define PPC_COPY(a, b) stringify_in_c(.long PPC_RAW_COPY(a, b))
+#define PPC_DARN(t, l) stringify_in_c(.long PPC_RAW_DARN(t, l))
+#define PPC_DCBAL(a, b) stringify_in_c(.long PPC_RAW_DCBAL(a, b))
+#define PPC_DCBZL(a, b) stringify_in_c(.long PPC_RAW_DCBZL(a, b))
+#define PPC_LQARX(t, a, b, eh) stringify_in_c(.long PPC_RAW_LQARX(t, a, b, eh))
+#define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_RAW_LDARX(t, a, b, eh))
+#define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_RAW_LWARX(t, a, b, eh))
+#define PPC_STQCX(t, a, b) stringify_in_c(.long PPC_RAW_STQCX(t, a, b))
+#define PPC_MADDHD(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDHD(t, a, b, c))
+#define PPC_MADDHDU(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDHDU(t, a, b, c))
+#define PPC_MADDLD(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDLD(t, a, b, c))
+#define PPC_MSGSND(b) stringify_in_c(.long PPC_RAW_MSGSND(b))
+#define PPC_MSGSYNC stringify_in_c(.long PPC_RAW_MSGSYNC)
+#define PPC_MSGCLR(b) stringify_in_c(.long PPC_RAW_MSGCLR(b))
+#define PPC_MSGSNDP(b) stringify_in_c(.long PPC_RAW_MSGSNDP(b))
+#define PPC_MSGCLRP(b) stringify_in_c(.long PPC_RAW_MSGCLRP(b))
+#define PPC_PASTE(a, b) stringify_in_c(.long PPC_RAW_PASTE(a, b))
+#define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_RAW_POPCNTB(a, s))
+#define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_RAW_POPCNTD(a, s))
+#define PPC_POPCNTW(a, s) stringify_in_c(.long PPC_RAW_POPCNTW(a, s))
+#define PPC_RFCI stringify_in_c(.long PPC_RAW_RFCI)
+#define PPC_RFDI stringify_in_c(.long PPC_RAW_RFDI)
+#define PPC_RFMCI stringify_in_c(.long PPC_RAW_RFMCI)
+#define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_RAW_TLBILX(t, a, b))
#define PPC_TLBILX_ALL(a, b) PPC_TLBILX(0, a, b)
#define PPC_TLBILX_PID(a, b) PPC_TLBILX(1, a, b)
#define PPC_TLBILX_VA(a, b) PPC_TLBILX(3, a, b)
-#define PPC_WAIT(w) stringify_in_c(.long PPC_INST_WAIT | \
- __PPC_WC(w))
-#define PPC_TLBIE(lp,a) stringify_in_c(.long PPC_INST_TLBIE | \
- ___PPC_RB(a) | ___PPC_RS(lp))
-#define PPC_TLBIE_5(rb,rs,ric,prs,r) \
- stringify_in_c(.long PPC_INST_TLBIE | \
- ___PPC_RB(rb) | ___PPC_RS(rs) | \
- ___PPC_RIC(ric) | ___PPC_PRS(prs) | \
- ___PPC_R(r))
+#define PPC_WAIT(w) stringify_in_c(.long PPC_RAW_WAIT(w))
+#define PPC_TLBIE(lp, a) stringify_in_c(.long PPC_RAW_TLBIE(lp, a))
+#define PPC_TLBIE_5(rb, rs, ric, prs, r) \
+ stringify_in_c(.long PPC_RAW_TLBIE_5(rb, rs, ric, prs, r))
#define PPC_TLBIEL(rb,rs,ric,prs,r) \
- stringify_in_c(.long PPC_INST_TLBIEL | \
- ___PPC_RB(rb) | ___PPC_RS(rs) | \
- ___PPC_RIC(ric) | ___PPC_PRS(prs) | \
- ___PPC_R(r))
-#define PPC_TLBSRX_DOT(a,b) stringify_in_c(.long PPC_INST_TLBSRX_DOT | \
- __PPC_RA0(a) | __PPC_RB(b))
-#define PPC_TLBIVAX(a,b) stringify_in_c(.long PPC_INST_TLBIVAX | \
- __PPC_RA0(a) | __PPC_RB(b))
-
-#define PPC_ERATWE(s, a, w) stringify_in_c(.long PPC_INST_ERATWE | \
- __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
-#define PPC_ERATRE(s, a, w) stringify_in_c(.long PPC_INST_ERATRE | \
- __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
-#define PPC_ERATILX(t, a, b) stringify_in_c(.long PPC_INST_ERATILX | \
- __PPC_T_TLB(t) | __PPC_RA0(a) | \
- __PPC_RB(b))
-#define PPC_ERATIVAX(s, a, b) stringify_in_c(.long PPC_INST_ERATIVAX | \
- __PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b))
-#define PPC_ERATSX(t, a, w) stringify_in_c(.long PPC_INST_ERATSX | \
- __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
-#define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_INST_ERATSX_DOT | \
- __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
-#define PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \
- __PPC_RT(t) | __PPC_RB(b))
-#define __PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \
- ___PPC_RT(t) | ___PPC_RB(b))
-#define PPC_ICBT(c,a,b) stringify_in_c(.long PPC_INST_ICBT | \
- __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b))
+ stringify_in_c(.long PPC_RAW_TLBIEL(rb, rs, ric, prs, r))
+#define PPC_TLBSRX_DOT(a, b) stringify_in_c(.long PPC_RAW_TLBSRX_DOT(a, b))
+#define PPC_TLBIVAX(a, b) stringify_in_c(.long PPC_RAW_TLBIVAX(a, b))
+
+#define PPC_ERATWE(s, a, w) stringify_in_c(.long PPC_RAW_ERATWE(s, a, w))
+#define PPC_ERATRE(s, a, w) stringify_in_c(.long PPC_RAW_ERATRE(a, a, w))
+#define PPC_ERATILX(t, a, b) stringify_in_c(.long PPC_RAW_ERATILX(t, a, b))
+#define PPC_ERATIVAX(s, a, b) stringify_in_c(.long PPC_RAW_ERATIVAX(s, a, b))
+#define PPC_ERATSX(t, a, w) stringify_in_c(.long PPC_RAW_ERATSX(t, a, w))
+#define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_RAW_ERATSX_DOT(t, a, w))
+#define PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_RAW_SLBFEE_DOT(t, b))
+#define __PPC_SLBFEE_DOT(t, b) stringify_in_c(.long __PPC_RAW_SLBFEE_DOT(t, b))
+#define PPC_ICBT(c, a, b) stringify_in_c(.long PPC_RAW_ICBT(c, a, b))
/* PASemi instructions */
-#define LBZCIX(t,a,b) stringify_in_c(.long PPC_INST_LBZCIX | \
- __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b))
-#define STBCIX(s,a,b) stringify_in_c(.long PPC_INST_STBCIX | \
- __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b))
-
-/*
- * Define what the VSX XX1 form instructions will look like, then add
- * the 128 bit load store instructions based on that.
- */
-#define VSX_XX1(s, a, b) (__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b))
-#define VSX_XX3(t, a, b) (__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b))
-#define STXVD2X(s, a, b) stringify_in_c(.long PPC_INST_STXVD2X | \
- VSX_XX1((s), a, b))
-#define LXVD2X(s, a, b) stringify_in_c(.long PPC_INST_LXVD2X | \
- VSX_XX1((s), a, b))
-#define MFVRD(a, t) stringify_in_c(.long PPC_INST_MFVSRD | \
- VSX_XX1((t)+32, a, R0))
-#define MTVRD(t, a) stringify_in_c(.long PPC_INST_MTVSRD | \
- VSX_XX1((t)+32, a, R0))
-#define VPMSUMW(t, a, b) stringify_in_c(.long PPC_INST_VPMSUMW | \
- VSX_XX3((t), a, b))
-#define VPMSUMD(t, a, b) stringify_in_c(.long PPC_INST_VPMSUMD | \
- VSX_XX3((t), a, b))
-#define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \
- VSX_XX3((t), a, b))
-#define XXSWAPD(t, a) stringify_in_c(.long PPC_INST_XXSWAPD | \
- VSX_XX3((t), a, a))
-#define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_INST_XVCPSGNDP | \
- VSX_XX3((t), (a), (b))))
+#define LBZCIX(t, a, b) stringify_in_c(.long PPC_RAW_LBZCIX(t, a, b))
+#define STBCIX(s, a, b) stringify_in_c(.long PPC_RAW_STBCIX(s, a, b))
+#define PPC_DCBFPS(a, b) stringify_in_c(.long PPC_RAW_DCBFPS(a, b))
+#define PPC_DCBSTPS(a, b) stringify_in_c(.long PPC_RAW_DCBSTPS(a, b))
+#define PPC_PHWSYNC stringify_in_c(.long PPC_RAW_PHWSYNC)
+#define PPC_PLWSYNC stringify_in_c(.long PPC_RAW_PLWSYNC)
+#define STXVD2X(s, a, b) stringify_in_c(.long PPC_RAW_STXVD2X(s, a, b))
+#define LXVD2X(s, a, b) stringify_in_c(.long PPC_RAW_LXVD2X(s, a, b))
+#define MFVRD(a, t) stringify_in_c(.long PPC_RAW_MFVRD(a, t))
+#define MTVRD(t, a) stringify_in_c(.long PPC_RAW_MTVRD(t, a))
+#define VPMSUMW(t, a, b) stringify_in_c(.long PPC_RAW_VPMSUMW(t, a, b))
+#define VPMSUMD(t, a, b) stringify_in_c(.long PPC_RAW_VPMSUMD(t, a, b))
+#define XXLOR(t, a, b) stringify_in_c(.long PPC_RAW_XXLOR(t, a, b))
+#define XXSWAPD(t, a) stringify_in_c(.long PPC_RAW_XXSWAPD(t, a))
+#define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_RAW_XVCPSGNDP(t, a, b)))
#define VPERMXOR(vrt, vra, vrb, vrc) \
- stringify_in_c(.long (PPC_INST_VPERMXOR | \
- ___PPC_RT(vrt) | ___PPC_RA(vra) | \
- ___PPC_RB(vrb) | (((vrc) & 0x1f) << 6)))
+ stringify_in_c(.long (PPC_RAW_VPERMXOR(vrt, vra, vrb, vrc)))
-#define PPC_NAP stringify_in_c(.long PPC_INST_NAP)
-#define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP)
-#define PPC_WINKLE stringify_in_c(.long PPC_INST_WINKLE)
+#define PPC_NAP stringify_in_c(.long PPC_RAW_NAP)
+#define PPC_SLEEP stringify_in_c(.long PPC_RAW_SLEEP)
+#define PPC_WINKLE stringify_in_c(.long PPC_RAW_WINKLE)
-#define PPC_STOP stringify_in_c(.long PPC_INST_STOP)
+#define PPC_STOP stringify_in_c(.long PPC_RAW_STOP)
/* BHRB instructions */
-#define PPC_CLRBHRB stringify_in_c(.long PPC_INST_CLRBHRB)
-#define PPC_MFBHRBE(r, n) stringify_in_c(.long PPC_INST_BHRBE | \
- __PPC_RT(r) | \
- (((n) & 0x3ff) << 11))
+#define PPC_CLRBHRB stringify_in_c(.long PPC_RAW_CLRBHRB)
+#define PPC_MFBHRBE(r, n) stringify_in_c(.long PPC_RAW_MFBHRBE(r, n))
/* Transactional memory instructions */
-#define TRECHKPT stringify_in_c(.long PPC_INST_TRECHKPT)
-#define TRECLAIM(r) stringify_in_c(.long PPC_INST_TRECLAIM \
- | __PPC_RA(r))
-#define TABORT(r) stringify_in_c(.long PPC_INST_TABORT \
- | __PPC_RA(r))
+#define TRECHKPT stringify_in_c(.long PPC_RAW_TRECHKPT)
+#define TRECLAIM(r) stringify_in_c(.long PPC_RAW_TRECLAIM(r))
+#define TABORT(r) stringify_in_c(.long PPC_RAW_TABORT(r))
/* book3e thread control instructions */
-#define TMRN(x) ((((x) & 0x1f) << 16) | (((x) & 0x3e0) << 6))
-#define MTTMR(tmr, r) stringify_in_c(.long PPC_INST_MTTMR | \
- TMRN(tmr) | ___PPC_RS(r))
-#define MFTMR(tmr, r) stringify_in_c(.long PPC_INST_MFTMR | \
- TMRN(tmr) | ___PPC_RT(r))
+#define MTTMR(tmr, r) stringify_in_c(.long PPC_RAW_MTTMR(tmr, r))
+#define MFTMR(tmr, r) stringify_in_c(.long PPC_RAW_MFTMR(tmr, r))
/* Coprocessor instructions */
-#define PPC_ICSWX(s, a, b) stringify_in_c(.long PPC_INST_ICSWX | \
- ___PPC_RS(s) | \
- ___PPC_RA(a) | \
- ___PPC_RB(b))
-#define PPC_ICSWEPX(s, a, b) stringify_in_c(.long PPC_INST_ICSWEPX | \
- ___PPC_RS(s) | \
- ___PPC_RA(a) | \
- ___PPC_RB(b))
-
-#define PPC_SLBIA(IH) stringify_in_c(.long PPC_INST_SLBIA | \
- ((IH & 0x7) << 21))
+#define PPC_ICSWX(s, a, b) stringify_in_c(.long PPC_RAW_ICSWX(s, a, b))
+#define PPC_ICSWEPX(s, a, b) stringify_in_c(.long PPC_RAW_ICSWEPX(s, a, b))
+
+#define PPC_SLBIA(IH) stringify_in_c(.long PPC_RAW_SLBIA(IH))
/*
* These may only be used on ISA v3.0 or later (aka. CPU_FTR_ARCH_300, radix
@@ -611,12 +606,8 @@
#define PPC_RADIX_INVALIDATE_ERAT_USER PPC_SLBIA(3)
#define PPC_RADIX_INVALIDATE_ERAT_GUEST PPC_SLBIA(6)
-#define VCMPEQUD_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUD | \
- ___PPC_RT(vrt) | ___PPC_RA(vra) | \
- ___PPC_RB(vrb) | __PPC_RC21)
+#define VCMPEQUD_RC(vrt, vra, vrb) stringify_in_c(.long PPC_RAW_VCMPEQUD_RC(vrt, vra, vrb))
-#define VCMPEQUB_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUB | \
- ___PPC_RT(vrt) | ___PPC_RA(vra) | \
- ___PPC_RB(vrb) | __PPC_RC21)
+#define VCMPEQUB_RC(vrt, vra, vrb) stringify_in_c(.long PPC_RAW_VCMPEQUB_RC(vrt, vra, vrb))
#endif /* _ASM_POWERPC_PPC_OPCODE_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 52a67835057a..ed0d633ab5aa 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -237,7 +237,6 @@ struct thread_struct {
#ifdef CONFIG_PPC_MEM_KEYS
unsigned long amr;
unsigned long iamr;
- unsigned long uamor;
#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
void* kvm_shadow_vcpu; /* KVM internal data */
@@ -272,6 +271,10 @@ struct thread_struct {
unsigned mmcr0;
unsigned used_ebb;
+ unsigned long mmcr3;
+ unsigned long sier2;
+ unsigned long sier3;
+
#endif
};
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 88e6c78100d9..97efbe2973fa 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -876,7 +876,9 @@
#define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */
#define SPRN_MMCR1 798
#define SPRN_MMCR2 785
+#define SPRN_MMCR3 754
#define SPRN_UMMCR2 769
+#define SPRN_UMMCR3 738
#define SPRN_MMCRA 0x312
#define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */
#define MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -886,6 +888,7 @@
#define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */
#define MMCRA_SLOT_SHIFT 24
#define MMCRA_SAMPLE_ENABLE 0x00000001UL /* enable sampling */
+#define MMCRA_BHRB_DISABLE 0x2000000000UL // BHRB disable bit for ISA v3.1
#define POWER6_MMCRA_SDSYNC 0x0000080000000000ULL /* SDAR/SIAR synced */
#define POWER6_MMCRA_SIHV 0x0000040000000000ULL
#define POWER6_MMCRA_SIPR 0x0000020000000000ULL
@@ -918,6 +921,10 @@
#define SIER_SIHV 0x1000000 /* Sampled MSR_HV */
#define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */
#define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */
+#define SPRN_SIER2 752
+#define SPRN_SIER3 753
+#define SPRN_USIER2 736
+#define SPRN_USIER3 737
#define SPRN_SIAR 796
#define SPRN_SDAR 797
#define SPRN_TACR 888
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 014968f25f7e..55f9a154c95d 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -215,7 +215,6 @@ inline uint16_t pseries_errorlog_length(struct pseries_errorlog *sect)
#define PSERIES_HP_ELOG_ACTION_ADD 1
#define PSERIES_HP_ELOG_ACTION_REMOVE 2
-#define PSERIES_HP_ELOG_ACTION_READD 3
#define PSERIES_HP_ELOG_ID_DRC_NAME 1
#define PSERIES_HP_ELOG_ID_DRC_INDEX 2
@@ -253,8 +252,6 @@ extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
extern void rtas_progress(char *s, unsigned short hex);
extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
-extern int rtas_online_cpus_mask(cpumask_var_t cpus);
-extern int rtas_offline_cpus_mask(cpumask_var_t cpus);
extern int rtas_ibm_suspend_me(u64 handle);
struct rtc_time;
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index 7c05e95a5c44..fbb8fa32150f 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -63,6 +63,8 @@ static inline bool security_ftr_enabled(u64 feature)
// bcctr 2,0,0 triggers a hardware assisted count cache flush
#define SEC_FTR_BCCTR_FLUSH_ASSIST 0x0000000000000800ull
+// bcctr 2,0,0 triggers a hardware assisted link stack flush
+#define SEC_FTR_BCCTR_LINK_FLUSH_ASSIST 0x0000000000002000ull
// Features indicating need for Spectre/Meltdown mitigations
diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index eaa4fb6c8960..972ed0df154d 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -105,6 +105,12 @@ enum instruction_type {
#define MKOP(t, f, s) ((t) | (f) | SIZE(s))
+/* Prefix instruction operands */
+#define GET_PREFIX_RA(i) (((i) >> 16) & 0x1f)
+#define GET_PREFIX_R(i) ((i) & (1ul << 20))
+
+extern s32 patch__exec_instr;
+
struct instruction_op {
int type;
int reg;
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 2db7ba789720..f0b6300e7dd3 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -43,7 +43,6 @@ extern void __init dump_numa_cpu_topology(void);
extern int sysfs_add_device_to_node(struct device *dev, int nid);
extern void sysfs_remove_device_from_node(struct device *dev, int nid);
-extern int numa_update_cpu_topology(bool cpus_locked);
static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node)
{
@@ -78,11 +77,6 @@ static inline void sysfs_remove_device_from_node(struct device *dev,
{
}
-static inline int numa_update_cpu_topology(bool cpus_locked)
-{
- return 0;
-}
-
static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {}
static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
@@ -93,32 +87,12 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
#endif /* CONFIG_NUMA */
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
-extern int start_topology_update(void);
-extern int stop_topology_update(void);
-extern int prrn_is_enabled(void);
extern int find_and_online_cpu_nid(int cpu);
-extern int timed_topology_update(int nsecs);
#else
-static inline int start_topology_update(void)
-{
- return 0;
-}
-static inline int stop_topology_update(void)
-{
- return 0;
-}
-static inline int prrn_is_enabled(void)
-{
- return 0;
-}
static inline int find_and_online_cpu_nid(int cpu)
{
return 0;
}
-static inline int timed_topology_update(int nsecs)
-{
- return 0;
-}
#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
@@ -141,7 +115,6 @@ int get_physical_package_id(int cpu);
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_core_id(cpu) (cpu_to_core_id(cpu))
-int dlpar_cpu_readd(int cpu);
#endif
#endif
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index d08ea11b271c..309b4d65b74f 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -155,7 +155,6 @@ static inline void xive_smp_probe(void) { }
static inline int xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; }
static inline void xive_smp_setup_cpu(void) { }
static inline void xive_smp_disable_cpu(void) { }
-static inline void xive_kexec_teardown_cpu(int secondary) { }
static inline void xive_shutdown(void) { }
static inline void xive_flush_interrupt(void) { }
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 264e266a85bf..c3af3f324c5a 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -640,6 +640,11 @@ struct kvm_ppc_cpu_char {
#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
#define KVM_REG_PPC_PTCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
+/* POWER10 registers */
+#define KVM_REG_PPC_MMCR3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1)
+#define KVM_REG_PPC_SIER2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2)
+#define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index c0c737215b00..3a700351feca 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -11,7 +11,7 @@
#include <asm-generic/mman-common.h>
-#define PROT_SAO 0x10 /* Strong Access Ordering */
+#define PROT_SAO 0x10 /* Unsupported since v5.9 */
#define MAP_RENAME MAP_ANONYMOUS /* In SunOS terminology */
#define MAP_NORESERVE 0x40 /* don't reserve swap pages */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6657dc6b2336..8711c2164b45 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -559,6 +559,8 @@ int main(void)
OFFSET(VCPU_IRQ_PENDING, kvm_vcpu, arch.irq_pending);
OFFSET(VCPU_DBELL_REQ, kvm_vcpu, arch.doorbell_request);
OFFSET(VCPU_MMCR, kvm_vcpu, arch.mmcr);
+ OFFSET(VCPU_MMCRA, kvm_vcpu, arch.mmcra);
+ OFFSET(VCPU_MMCRS, kvm_vcpu, arch.mmcrs);
OFFSET(VCPU_PMC, kvm_vcpu, arch.pmc);
OFFSET(VCPU_SPMC, kvm_vcpu, arch.spmc);
OFFSET(VCPU_SIAR, kvm_vcpu, arch.siar);
@@ -696,6 +698,9 @@ int main(void)
HSTATE_FIELD(HSTATE_SDAR, host_mmcr[4]);
HSTATE_FIELD(HSTATE_MMCR2, host_mmcr[5]);
HSTATE_FIELD(HSTATE_SIER, host_mmcr[6]);
+ HSTATE_FIELD(HSTATE_MMCR3, host_mmcr[7]);
+ HSTATE_FIELD(HSTATE_SIER2, host_mmcr[8]);
+ HSTATE_FIELD(HSTATE_SIER3, host_mmcr[9]);
HSTATE_FIELD(HSTATE_PMC1, host_pmc[0]);
HSTATE_FIELD(HSTATE_PMC2, host_pmc[1]);
HSTATE_FIELD(HSTATE_PMC3, host_pmc[2]);
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 470336277c67..d8d4552af30a 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -647,12 +647,13 @@ static const struct cpumask *get_big_core_shared_cpu_map(int cpu, struct cache *
return &cache->shared_cpu_map;
}
-static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+static ssize_t
+show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bool list)
{
struct cache_index_dir *index;
struct cache *cache;
const struct cpumask *mask;
- int ret, cpu;
+ int cpu;
index = kobj_to_cache_index_dir(k);
cache = index->cache;
@@ -664,16 +665,25 @@ static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *att
mask = &cache->shared_cpu_map;
}
- ret = scnprintf(buf, PAGE_SIZE - 1, "%*pb\n",
- cpumask_pr_args(mask));
- buf[ret++] = '\n';
- buf[ret] = '\0';
- return ret;
+ return cpumap_print_to_pagebuf(list, buf, mask);
+}
+
+static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ return show_shared_cpumap(k, attr, buf, false);
+}
+
+static ssize_t shared_cpu_list_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ return show_shared_cpumap(k, attr, buf, true);
}
static struct kobj_attribute cache_shared_cpu_map_attr =
__ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL);
+static struct kobj_attribute cache_shared_cpu_list_attr =
+ __ATTR(shared_cpu_list, 0444, shared_cpu_list_show, NULL);
+
/* Attributes which should always be created -- the kobject/sysfs core
* does this automatically via kobj_type->default_attrs. This is the
* minimum data required to uniquely identify a cache.
@@ -682,6 +692,7 @@ static struct attribute *cache_index_default_attrs[] = {
&cache_type_attr.attr,
&cache_level_attr.attr,
&cache_shared_cpu_map_attr.attr,
+ &cache_shared_cpu_list_attr.attr,
NULL,
};
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 50b2d544361e..22ba7fba1147 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -24,7 +24,6 @@
/* Device-tree visible constants follow */
-#define ISA_V2_07B 2070
#define ISA_V3_0B 3000
#define ISA_V3_1 3100
@@ -67,6 +66,7 @@ struct dt_cpu_feature {
extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p10(struct pt_regs *regs);
static int hv_mode;
@@ -337,6 +337,7 @@ static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f)
#ifdef CONFIG_PPC_RADIX_MMU
cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+ cur_cpu_spec->mmu_features |= MMU_FTR_GTSE;
cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
return 1;
@@ -450,6 +451,39 @@ static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f)
return 1;
}
+static void init_pmu_power10(void)
+{
+ init_pmu_power9();
+
+ mtspr(SPRN_MMCR3, 0);
+ mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
+}
+
+static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f)
+{
+ hfscr_pmu_enable();
+
+ init_pmu_power10();
+ init_pmu_registers = init_pmu_power10;
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+
+ cur_cpu_spec->num_pmcs = 6;
+ cur_cpu_spec->pmc_type = PPC_PMC_IBM;
+ cur_cpu_spec->oprofile_cpu_type = "ppc64/power10";
+
+ return 1;
+}
+
+static int __init feat_enable_mce_power10(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->platform = "power10";
+ 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
@@ -623,7 +657,7 @@ static struct dt_cpu_feature_match __initdata
{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
{"processor-utilization-of-resources-register", feat_enable_purr, 0},
{"no-execute", feat_enable, 0},
- {"strong-access-ordering", feat_enable, CPU_FTR_SAO},
+ /* strong-access-ordering is unused */
{"cache-inhibited-large-page", feat_enable_large_ci, 0},
{"coprocessor-icswx", feat_enable, 0},
{"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},
@@ -639,7 +673,9 @@ static struct dt_cpu_feature_match __initdata
{"group-start-register", feat_enable, 0},
{"pc-relative-addressing", feat_enable, 0},
{"machine-check-power9", feat_enable_mce_power9, 0},
+ {"machine-check-power10", feat_enable_mce_power10, 0},
{"performance-monitor-power9", feat_enable_pmu_power9, 0},
+ {"performance-monitor-power10", feat_enable_pmu_power10, 0},
{"event-based-branch-v3", feat_enable, 0},
{"random-number-generator", feat_enable, 0},
{"system-call-vectored", feat_disable, 0},
@@ -675,12 +711,12 @@ static void __init cpufeatures_setup_start(u32 isa)
{
pr_info("setup for ISA %d\n", isa);
- if (isa >= 3000) {
+ if (isa >= ISA_V3_0B) {
cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_300;
cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_00;
}
- if (isa >= 3100) {
+ if (isa >= ISA_V3_1) {
cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_31;
cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_1;
}
@@ -777,12 +813,6 @@ static __init void cpufeatures_cpu_quirks(void)
}
update_tlbie_feature_flag(version);
- /*
- * PKEY was not in the initial base or feature node
- * specification, but it should become optional in the next
- * cpu feature version sequence.
- */
- cur_cpu_spec->cpu_features |= CPU_FTR_PKEY;
}
static void __init cpufeatures_setup_finished(void)
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 217ebdf5b00b..f4d0af8e1136 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -36,6 +36,12 @@
#include "head_32.h"
/*
+ * powerpc relies on return from interrupt/syscall being context synchronising
+ * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional
+ * synchronisation instructions.
+ */
+
+/*
* Align to 4k in order to ensure that all functions modyfing srr0/srr1
* fit into one page in order to not encounter a TLB miss between the
* modification of srr0/srr1 and the associated rfi.
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 223c4f008e63..33a42e42c56f 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -400,12 +400,12 @@ _GLOBAL(ret_from_fork)
_GLOBAL(ret_from_kernel_thread)
bl schedule_tail
REST_NVGPRS(r1)
- mtlr r14
+ mtctr r14
mr r3,r15
#ifdef PPC64_ELF_ABI_v2
mr r12,r14
#endif
- blrl
+ bctrl
li r3,0
b .Lsyscall_exit
@@ -426,10 +426,7 @@ _ASM_NOKPROBE_SYMBOL(save_nvgprs);
#define FLUSH_COUNT_CACHE \
1: nop; \
- patch_site 1b, patch__call_flush_count_cache
-
-
-#define BCCTR_FLUSH .long 0x4c400420
+ patch_site 1b, patch__call_flush_branch_caches
.macro nops number
.rept \number
@@ -438,8 +435,8 @@ _ASM_NOKPROBE_SYMBOL(save_nvgprs);
.endm
.balign 32
-.global flush_count_cache
-flush_count_cache:
+.global flush_branch_caches
+flush_branch_caches:
/* Save LR into r9 */
mflr r9
@@ -461,7 +458,7 @@ flush_count_cache:
li r9,0x7fff
mtctr r9
- BCCTR_FLUSH
+ PPC_BCCTR_FLUSH
2: nop
patch_site 2b patch__flush_count_cache_return
@@ -470,7 +467,7 @@ flush_count_cache:
.rept 278
.balign 32
- BCCTR_FLUSH
+ PPC_BCCTR_FLUSH
nops 7
.endr
@@ -524,7 +521,7 @@ _GLOBAL(_switch)
* kernel/sched/core.c).
*
* Uncacheable stores in the case of involuntary preemption must
- * be taken care of. The smp_mb__before_spin_lock() in __schedule()
+ * be taken care of. The smp_mb__after_spinlock() in __schedule()
* is implemented as hwsync on powerpc, which orders MMIO too. So
* long as there is an hwsync in the context switch path, it will
* be executed on the source CPU after the task has performed
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 8afc0e03d7d4..eda5ceef2381 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2641,7 +2641,7 @@ EXC_VIRT_NONE(0x5400, 0x100)
INT_DEFINE_BEGIN(denorm_exception)
IVEC=0x1500
IHSRR=1
- IBRANCH_COMMON=0
+ IBRANCH_TO_COMMON=0
IKVM_REAL=1
INT_DEFINE_END(denorm_exception)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 78ab9a6ee6ac..1858896d6809 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -32,11 +32,20 @@
#include <asm/fadump-internal.h>
#include <asm/setup.h>
+/*
+ * The CPU who acquired the lock to trigger the fadump crash should
+ * wait for other CPUs to enter.
+ *
+ * The timeout is in milliseconds.
+ */
+#define CRASH_TIMEOUT 500
+
static struct fw_dump fw_dump;
static void __init fadump_reserve_crash_area(u64 base);
struct kobject *fadump_kobj;
+static atomic_t cpus_in_fadump;
#ifndef CONFIG_PRESERVE_FA_DUMP
static DEFINE_MUTEX(fadump_mutex);
@@ -668,8 +677,11 @@ early_param("fadump_reserve_mem", early_fadump_reserve_mem);
void crash_fadump(struct pt_regs *regs, const char *str)
{
+ unsigned int msecs;
struct fadump_crash_info_header *fdh = NULL;
int old_cpu, this_cpu;
+ /* Do not include first CPU */
+ unsigned int ncpus = num_online_cpus() - 1;
if (!should_fadump_crash())
return;
@@ -685,6 +697,8 @@ void crash_fadump(struct pt_regs *regs, const char *str)
old_cpu = cmpxchg(&crashing_cpu, -1, this_cpu);
if (old_cpu != -1) {
+ atomic_inc(&cpus_in_fadump);
+
/*
* We can't loop here indefinitely. Wait as long as fadump
* is in force. If we race with fadump un-registration this
@@ -708,6 +722,16 @@ void crash_fadump(struct pt_regs *regs, const char *str)
fdh->online_mask = *cpu_online_mask;
+ /*
+ * If we came in via system reset, wait a while for the secondary
+ * CPUs to enter.
+ */
+ if (TRAP(&(fdh->regs)) == 0x100) {
+ msecs = CRASH_TIMEOUT;
+ while ((atomic_read(&cpus_in_fadump) < ncpus) && (--msecs > 0))
+ mdelay(1);
+ }
+
fw_dump.ops->fadump_trigger(fdh, str);
}
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index cac22cb97a8c..4ae39db70044 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -107,9 +107,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
or r12,r12,r4
std r12,_MSR(r1)
#endif
- /* Don't care if r4 overflows, this is desired behaviour */
- lbz r4,THREAD_LOAD_FP(r5)
- addi r4,r4,1
+ li r4,1
stb r4,THREAD_LOAD_FP(r5)
addi r10,r5,THREAD_FPSTATE
lfd fr0,FPSTATE_FPSCR(r10)
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 9cc792a3a6a9..6ab9b4d037c3 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -244,7 +244,7 @@ static int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
* So, we should never get here... but, its still
* good to catch them, just in case...
*/
- printk("Can't step on instruction %x\n", ppc_inst_val(insn));
+ printk("Can't step on instruction %s\n", ppc_inst_as_str(insn));
BUG();
} else {
/*
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index fd90c0eda229..c2fa8ee63720 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -49,6 +49,20 @@ static struct irq_work mce_ue_event_irq_work = {
DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
+static BLOCKING_NOTIFIER_HEAD(mce_notifier_list);
+
+int mce_register_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&mce_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(mce_register_notifier);
+
+int mce_unregister_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(mce_unregister_notifier);
+
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
@@ -278,6 +292,7 @@ static void machine_process_ue_event(struct work_struct *work)
while (__this_cpu_read(mce_ue_count) > 0) {
index = __this_cpu_read(mce_ue_count) - 1;
evt = this_cpu_ptr(&mce_ue_event_queue[index]);
+ blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
#ifdef CONFIG_MEMORY_FAILURE
/*
* This should probably queued elsewhere, but
@@ -370,6 +385,7 @@ void machine_check_print_event_info(struct machine_check_event *evt,
static const char *mc_user_types[] = {
"Indeterminate",
"tlbie(l) invalid",
+ "scv invalid",
};
static const char *mc_ra_types[] = {
"Indeterminate",
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index c3b522bff9b4..b7e173754a2e 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -243,6 +243,45 @@ static const struct mce_ierror_table mce_p9_ierror_table[] = {
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, 0, 0, 0, 0, 0, 0 } };
+static const struct mce_ierror_table mce_p10_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH_FOREIGN, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008080000, true,
+ MCE_ERROR_TYPE_USER,MCE_USER_ERROR_SCV, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x00000000080c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008100000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008140000, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, false }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x00000000081c0000, true, MCE_ECLASS_HARDWARE,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
+
struct mce_derror_table {
unsigned long dsisr_value;
bool dar_valid; /* dar is a valid indicator of faulting address */
@@ -361,6 +400,46 @@ static const struct mce_derror_table mce_p9_derror_table[] = {
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, false, 0, 0, 0, 0, 0 } };
+static const struct mce_derror_table mce_p10_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000200, false,
+ MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */
+ MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000020, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000010, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000008, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD_STORE_FOREIGN, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
+
static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
uint64_t *phys_addr)
{
@@ -657,3 +736,8 @@ long __machine_check_early_realmode_p9(struct pt_regs *regs)
return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table);
}
+
+long __machine_check_early_realmode_p10(struct pt_regs *regs)
+{
+ return mce_handle_error(regs, mce_p10_derror_table, mce_p10_ierror_table);
+}
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 1864605eca29..7bb46ad98207 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -413,20 +413,6 @@ _GLOBAL(kexec_sequence)
li r0,0
std r0,16(r1)
-BEGIN_FTR_SECTION
- /*
- * This is the best time to turn AMR/IAMR off.
- * key 0 is used in radix for supervisor<->user
- * protection, but on hash key 0 is reserved
- * ideally we want to enter with a clean state.
- * NOTE, we rely on r0 being 0 from above.
- */
- mtspr SPRN_IAMR,r0
-BEGIN_FTR_SECTION_NESTED(42)
- mtspr SPRN_AMOR,r0
-END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
/* save regs for local vars on new stack.
* yes, we won't go back, but ...
*/
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 2168372b792d..0ad15768d762 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -57,8 +57,8 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align,
#define LPPACA_SIZE 0x400
-static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align,
- unsigned long limit, int cpu)
+static void *__init alloc_shared_lppaca(unsigned long size, unsigned long limit,
+ int cpu)
{
size_t shared_lppaca_total_size = PAGE_ALIGN(nr_cpu_ids * LPPACA_SIZE);
static unsigned long shared_lppaca_size;
@@ -68,6 +68,13 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align,
if (!shared_lppaca) {
memblock_set_bottom_up(true);
+ /*
+ * See Documentation/powerpc/ultravisor.rst for more details.
+ *
+ * UV/HV data sharing is in PAGE_SIZE granularity. In order to
+ * minimize the number of pages shared, align the allocation to
+ * PAGE_SIZE.
+ */
shared_lppaca =
memblock_alloc_try_nid(shared_lppaca_total_size,
PAGE_SIZE, MEMBLOCK_LOW_LIMIT,
@@ -87,7 +94,7 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align,
* This is very early in boot, so no harm done if the kernel crashes at
* this point.
*/
- BUG_ON(shared_lppaca_size >= shared_lppaca_total_size);
+ BUG_ON(shared_lppaca_size > shared_lppaca_total_size);
return ptr;
}
@@ -122,7 +129,7 @@ static struct lppaca * __init new_lppaca(int cpu, unsigned long limit)
return NULL;
if (is_secure_guest())
- lp = alloc_shared_lppaca(LPPACA_SIZE, 0x400, limit, cpu);
+ lp = alloc_shared_lppaca(LPPACA_SIZE, limit, cpu);
else
lp = alloc_paca_data(LPPACA_SIZE, 0x400, limit, cpu);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 939935613cf1..e4fcc817c46c 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -471,49 +471,58 @@ EXPORT_SYMBOL(giveup_all);
#ifdef CONFIG_PPC_BOOK3S_64
#ifdef CONFIG_PPC_FPU
-static int restore_fp(struct task_struct *tsk)
+static bool should_restore_fp(void)
{
- if (tsk->thread.load_fp) {
- load_fp_state(&current->thread.fp_state);
+ if (current->thread.load_fp) {
current->thread.load_fp++;
- return 1;
+ return true;
}
- return 0;
+ return false;
+}
+
+static void do_restore_fp(void)
+{
+ load_fp_state(&current->thread.fp_state);
}
#else
-static int restore_fp(struct task_struct *tsk) { return 0; }
+static bool should_restore_fp(void) { return false; }
+static void do_restore_fp(void) { }
#endif /* CONFIG_PPC_FPU */
#ifdef CONFIG_ALTIVEC
-#define loadvec(thr) ((thr).load_vec)
-static int restore_altivec(struct task_struct *tsk)
+static bool should_restore_altivec(void)
{
- if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
- load_vr_state(&tsk->thread.vr_state);
- tsk->thread.used_vr = 1;
- tsk->thread.load_vec++;
-
- return 1;
+ if (cpu_has_feature(CPU_FTR_ALTIVEC) && (current->thread.load_vec)) {
+ current->thread.load_vec++;
+ return true;
}
- return 0;
+ return false;
+}
+
+static void do_restore_altivec(void)
+{
+ load_vr_state(&current->thread.vr_state);
+ current->thread.used_vr = 1;
}
#else
-#define loadvec(thr) 0
-static inline int restore_altivec(struct task_struct *tsk) { return 0; }
+static bool should_restore_altivec(void) { return false; }
+static void do_restore_altivec(void) { }
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
-static int restore_vsx(struct task_struct *tsk)
+static bool should_restore_vsx(void)
{
- if (cpu_has_feature(CPU_FTR_VSX)) {
- tsk->thread.used_vsr = 1;
- return 1;
- }
-
- return 0;
+ if (cpu_has_feature(CPU_FTR_VSX))
+ return true;
+ return false;
+}
+static void do_restore_vsx(void)
+{
+ current->thread.used_vsr = 1;
}
#else
-static inline int restore_vsx(struct task_struct *tsk) { return 0; }
+static bool should_restore_vsx(void) { return false; }
+static void do_restore_vsx(void) { }
#endif /* CONFIG_VSX */
/*
@@ -529,32 +538,42 @@ static inline int restore_vsx(struct task_struct *tsk) { return 0; }
void notrace restore_math(struct pt_regs *regs)
{
unsigned long msr;
-
- if (!MSR_TM_ACTIVE(regs->msr) &&
- !current->thread.load_fp && !loadvec(current->thread))
- return;
+ unsigned long new_msr = 0;
msr = regs->msr;
- msr_check_and_set(msr_all_available);
/*
- * Only reload if the bit is not set in the user MSR, the bit BEING set
- * indicates that the registers are hot
+ * new_msr tracks the facilities that are to be restored. Only reload
+ * if the bit is not set in the user MSR (if it is set, the registers
+ * are live for the user thread).
*/
- if ((!(msr & MSR_FP)) && restore_fp(current))
- msr |= MSR_FP | current->thread.fpexc_mode;
+ if ((!(msr & MSR_FP)) && should_restore_fp())
+ new_msr |= MSR_FP | current->thread.fpexc_mode;
- if ((!(msr & MSR_VEC)) && restore_altivec(current))
- msr |= MSR_VEC;
+ if ((!(msr & MSR_VEC)) && should_restore_altivec())
+ new_msr |= MSR_VEC;
- if ((msr & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC) &&
- restore_vsx(current)) {
- msr |= MSR_VSX;
+ if ((!(msr & MSR_VSX)) && should_restore_vsx()) {
+ if (((msr | new_msr) & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC))
+ new_msr |= MSR_VSX;
}
- msr_check_and_clear(msr_all_available);
+ if (new_msr) {
+ msr_check_and_set(new_msr);
+
+ if (new_msr & MSR_FP)
+ do_restore_fp();
+
+ if (new_msr & MSR_VEC)
+ do_restore_altivec();
- regs->msr = msr;
+ if (new_msr & MSR_VSX)
+ do_restore_vsx();
+
+ msr_check_and_clear(new_msr);
+
+ regs->msr |= new_msr;
+ }
}
#endif
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 9cc49f265c86..dfe0103ad131 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -163,7 +163,7 @@ static struct ibm_pa_feature {
{ .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE },
{ .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE },
#ifdef CONFIG_PPC_RADIX_MMU
- { .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX },
+ { .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX | MMU_FTR_GTSE },
#endif
{ .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
{ .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
@@ -815,6 +815,11 @@ void __init early_init_devtree(void *params)
/* Now try to figure out if we are running on LPAR and so on */
pseries_probe_fw_features();
+ /*
+ * Initialize pkey features and default AMR/IAMR values
+ */
+ pkey_early_init_devtree();
+
#ifdef CONFIG_PPC_PS3
/* Identify PS3 firmware */
if (of_flat_dt_is_compatible(of_get_flat_dt_root(), "sony,ps3"))
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 90c604d00b7d..cbc605cfdec0 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1336,12 +1336,15 @@ static void __init prom_check_platform_support(void)
}
}
- if (supported.radix_mmu && supported.radix_gtse &&
- IS_ENABLED(CONFIG_PPC_RADIX_MMU)) {
- /* Radix preferred - but we require GTSE for now */
- prom_debug("Asking for radix with GTSE\n");
+ if (supported.radix_mmu && IS_ENABLED(CONFIG_PPC_RADIX_MMU)) {
+ /* Radix preferred - Check if GTSE is also supported */
+ prom_debug("Asking for radix\n");
ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
- ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+ if (supported.radix_gtse)
+ ibm_architecture_vec.vec5.radix_ext =
+ OV5_FEAT(OV5_RADIX_GTSE);
+ else
+ prom_debug("Radix GTSE isn't supported\n");
} else if (supported.hash_mmu) {
/* Default to hash mmu (if we can) */
prom_debug("Asking for hash\n");
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index caeb5822a8f4..ac7d480cb9c1 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -488,14 +488,21 @@ static int pkey_active(struct task_struct *target, const struct user_regset *reg
static int pkey_get(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
{
+ int ret;
+
BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr));
- BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor));
if (!arch_pkeys_enabled())
return -ENODEV;
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.amr,
- 0, ELF_NPKEY * sizeof(unsigned long));
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.amr,
+ 0, 2 * sizeof(unsigned long));
+ if (ret)
+ return ret;
+
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &default_uamor,
+ 2 * sizeof(unsigned long), 3 * sizeof(unsigned long));
+ return ret;
}
static int pkey_set(struct task_struct *target, const struct user_regset *regset,
@@ -517,9 +524,17 @@ static int pkey_set(struct task_struct *target, const struct user_regset *regset
if (ret)
return ret;
- /* UAMOR determines which bits of the AMR can be set from userspace. */
- target->thread.amr = (new_amr & target->thread.uamor) |
- (target->thread.amr & ~target->thread.uamor);
+ /*
+ * UAMOR determines which bits of the AMR can be set from userspace.
+ * UAMOR value 0b11 indicates that the AMR value can be modified
+ * from userspace. If the kernel is using a specific key, we avoid
+ * userspace modifying the AMR value for that key by masking them
+ * via UAMOR 0b00.
+ *
+ * Pick the AMR values for the keys that kernel is using. This
+ * will be indicated by the ~default_uamor bits.
+ */
+ target->thread.amr = (new_amr & default_uamor) | (target->thread.amr & ~default_uamor);
return 0;
}
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index a09eba03f180..806d554ce357 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -843,96 +843,6 @@ static void rtas_percpu_suspend_me(void *info)
__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
}
-enum rtas_cpu_state {
- DOWN,
- UP,
-};
-
-#ifndef CONFIG_SMP
-static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
- cpumask_var_t cpus)
-{
- if (!cpumask_empty(cpus)) {
- cpumask_clear(cpus);
- return -EINVAL;
- } else
- return 0;
-}
-#else
-/* On return cpumask will be altered to indicate CPUs changed.
- * CPUs with states changed will be set in the mask,
- * CPUs with status unchanged will be unset in the mask. */
-static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
- cpumask_var_t cpus)
-{
- int cpu;
- int cpuret = 0;
- int ret = 0;
-
- if (cpumask_empty(cpus))
- return 0;
-
- for_each_cpu(cpu, cpus) {
- struct device *dev = get_cpu_device(cpu);
-
- switch (state) {
- case DOWN:
- cpuret = device_offline(dev);
- break;
- case UP:
- cpuret = device_online(dev);
- break;
- }
- if (cpuret < 0) {
- pr_debug("%s: cpu_%s for cpu#%d returned %d.\n",
- __func__,
- ((state == UP) ? "up" : "down"),
- cpu, cpuret);
- if (!ret)
- ret = cpuret;
- if (state == UP) {
- /* clear bits for unchanged cpus, return */
- cpumask_shift_right(cpus, cpus, cpu);
- cpumask_shift_left(cpus, cpus, cpu);
- break;
- } else {
- /* clear bit for unchanged cpu, continue */
- cpumask_clear_cpu(cpu, cpus);
- }
- }
- cond_resched();
- }
-
- return ret;
-}
-#endif
-
-int rtas_online_cpus_mask(cpumask_var_t cpus)
-{
- int ret;
-
- ret = rtas_cpu_state_change_mask(UP, cpus);
-
- if (ret) {
- cpumask_var_t tmp_mask;
-
- if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL))
- return ret;
-
- /* Use tmp_mask to preserve cpus mask from first failure */
- cpumask_copy(tmp_mask, cpus);
- rtas_offline_cpus_mask(tmp_mask);
- free_cpumask_var(tmp_mask);
- }
-
- return ret;
-}
-
-int rtas_offline_cpus_mask(cpumask_var_t cpus)
-{
- return rtas_cpu_state_change_mask(DOWN, cpus);
-}
-
int rtas_ibm_suspend_me(u64 handle)
{
long state;
@@ -940,8 +850,6 @@ int rtas_ibm_suspend_me(u64 handle)
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
struct rtas_suspend_me_data data;
DECLARE_COMPLETION_ONSTACK(done);
- cpumask_var_t offline_mask;
- int cpuret;
if (!rtas_service_present("ibm,suspend-me"))
return -ENOSYS;
@@ -962,9 +870,6 @@ int rtas_ibm_suspend_me(u64 handle)
return -EIO;
}
- if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL))
- return -ENOMEM;
-
atomic_set(&data.working, 0);
atomic_set(&data.done, 0);
atomic_set(&data.error, 0);
@@ -973,24 +878,8 @@ int rtas_ibm_suspend_me(u64 handle)
lock_device_hotplug();
- /* All present CPUs must be online */
- cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask);
- cpuret = rtas_online_cpus_mask(offline_mask);
- if (cpuret) {
- pr_err("%s: Could not bring present CPUs online.\n", __func__);
- atomic_set(&data.error, cpuret);
- goto out;
- }
-
cpu_hotplug_disable();
- /* Check if we raced with a CPU-Offline Operation */
- if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) {
- pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__);
- atomic_set(&data.error, -EAGAIN);
- goto out_hotplug_enable;
- }
-
/* Call function on all CPUs. One of us will make the
* rtas call
*/
@@ -1001,18 +890,11 @@ int rtas_ibm_suspend_me(u64 handle)
if (atomic_read(&data.error) != 0)
printk(KERN_ERR "Error doing global join\n");
-out_hotplug_enable:
- cpu_hotplug_enable();
- /* Take down CPUs not online prior to suspend */
- cpuret = rtas_offline_cpus_mask(offline_mask);
- if (cpuret)
- pr_warn("%s: Could not restore CPUs to offline state.\n",
- __func__);
+ cpu_hotplug_enable();
-out:
unlock_device_hotplug();
- free_cpumask_var(offline_mask);
+
return atomic_read(&data.error);
}
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 89b798f8f656..8561dfb33f24 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -273,37 +273,15 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
}
}
-#ifdef CONFIG_PPC_PSERIES
-static void handle_prrn_event(s32 scope)
-{
- /*
- * For PRRN, we must pass the negative of the scope value in
- * the RTAS event.
- */
- pseries_devicetree_update(-scope);
- numa_update_cpu_topology(false);
-}
-
static void handle_rtas_event(const struct rtas_error_log *log)
{
- if (rtas_error_type(log) != RTAS_TYPE_PRRN || !prrn_is_enabled())
+ if (!machine_is(pseries))
return;
- /* For PRRN Events the extended log length is used to denote
- * the scope for calling rtas update-nodes.
- */
- handle_prrn_event(rtas_error_extended_log_length(log));
+ if (rtas_error_type(log) == RTAS_TYPE_PRRN)
+ pr_info_ratelimited("Platform resource reassignment ignored.\n");
}
-#else
-
-static void handle_rtas_event(const struct rtas_error_log *log)
-{
- return;
-}
-
-#endif
-
static int rtas_log_open(struct inode * inode, struct file * file)
{
return 0;
diff --git a/arch/powerpc/kernel/secure_boot.c b/arch/powerpc/kernel/secure_boot.c
index 4b982324d368..f9af305d9579 100644
--- a/arch/powerpc/kernel/secure_boot.c
+++ b/arch/powerpc/kernel/secure_boot.c
@@ -23,12 +23,19 @@ bool is_ppc_secureboot_enabled(void)
{
struct device_node *node;
bool enabled = false;
+ u32 secureboot;
node = get_ppc_fw_sb_node();
enabled = of_property_read_bool(node, "os-secureboot-enforcing");
-
of_node_put(node);
+ if (enabled)
+ goto out;
+
+ if (!of_property_read_u32(of_root, "ibm,secure-boot", &secureboot))
+ enabled = (secureboot > 1);
+
+out:
pr_info("Secure boot mode %s\n", enabled ? "enabled" : "disabled");
return enabled;
@@ -38,12 +45,19 @@ bool is_ppc_trustedboot_enabled(void)
{
struct device_node *node;
bool enabled = false;
+ u32 trustedboot;
node = get_ppc_fw_sb_node();
enabled = of_property_read_bool(node, "trusted-enabled");
-
of_node_put(node);
+ if (enabled)
+ goto out;
+
+ if (!of_property_read_u32(of_root, "ibm,trusted-boot", &trustedboot))
+ enabled = (trustedboot > 0);
+
+out:
pr_info("Trusted boot mode %s\n", enabled ? "enabled" : "disabled");
return enabled;
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index d86701ce116b..c9876aab3142 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -21,13 +21,13 @@
u64 powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;
-enum count_cache_flush_type {
- COUNT_CACHE_FLUSH_NONE = 0x1,
- COUNT_CACHE_FLUSH_SW = 0x2,
- COUNT_CACHE_FLUSH_HW = 0x4,
+enum branch_cache_flush_type {
+ BRANCH_CACHE_FLUSH_NONE = 0x1,
+ BRANCH_CACHE_FLUSH_SW = 0x2,
+ BRANCH_CACHE_FLUSH_HW = 0x4,
};
-static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
-static bool link_stack_flush_enabled;
+static enum branch_cache_flush_type count_cache_flush_type = BRANCH_CACHE_FLUSH_NONE;
+static enum branch_cache_flush_type link_stack_flush_type = BRANCH_CACHE_FLUSH_NONE;
bool barrier_nospec_enabled;
static bool no_nospec;
@@ -219,24 +219,25 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
if (ccd)
seq_buf_printf(&s, "Indirect branch cache disabled");
- if (link_stack_flush_enabled)
- seq_buf_printf(&s, ", Software link stack flush");
-
- } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
+ } else if (count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) {
seq_buf_printf(&s, "Mitigation: Software count cache flush");
- if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW)
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW)
seq_buf_printf(&s, " (hardware accelerated)");
- if (link_stack_flush_enabled)
- seq_buf_printf(&s, ", Software link stack flush");
-
} else if (btb_flush_enabled) {
seq_buf_printf(&s, "Mitigation: Branch predictor state flush");
} else {
seq_buf_printf(&s, "Vulnerable");
}
+ if (bcs || ccd || count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) {
+ if (link_stack_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ seq_buf_printf(&s, ", Software link stack flush");
+ if (link_stack_flush_type == BRANCH_CACHE_FLUSH_HW)
+ seq_buf_printf(&s, " (hardware accelerated)");
+ }
+
seq_buf_printf(&s, "\n");
return s.len;
@@ -427,61 +428,79 @@ static __init int stf_barrier_debugfs_init(void)
device_initcall(stf_barrier_debugfs_init);
#endif /* CONFIG_DEBUG_FS */
-static void no_count_cache_flush(void)
+static void update_branch_cache_flush(void)
{
- count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
- pr_info("count-cache-flush: software flush disabled.\n");
-}
-
-static void toggle_count_cache_flush(bool enable)
-{
- if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) &&
- !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK))
- enable = false;
-
- if (!enable) {
- patch_instruction_site(&patch__call_flush_count_cache,
- ppc_inst(PPC_INST_NOP));
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ // This controls the branch from guest_exit_cont to kvm_flush_link_stack
+ if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
patch_instruction_site(&patch__call_kvm_flush_link_stack,
ppc_inst(PPC_INST_NOP));
-#endif
- pr_info("link-stack-flush: software flush disabled.\n");
- link_stack_flush_enabled = false;
- no_count_cache_flush();
- return;
+ } else {
+ // Could use HW flush, but that could also flush count cache
+ patch_branch_site(&patch__call_kvm_flush_link_stack,
+ (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
}
-
- // This enables the branch from _switch to flush_count_cache
- patch_branch_site(&patch__call_flush_count_cache,
- (u64)&flush_count_cache, BRANCH_SET_LINK);
-
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- // This enables the branch from guest_exit_cont to kvm_flush_link_stack
- patch_branch_site(&patch__call_kvm_flush_link_stack,
- (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
#endif
- pr_info("link-stack-flush: software flush enabled.\n");
- link_stack_flush_enabled = true;
+ // This controls the branch from _switch to flush_branch_caches
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE &&
+ link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
+ patch_instruction_site(&patch__call_flush_branch_caches,
+ ppc_inst(PPC_INST_NOP));
+ } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW &&
+ link_stack_flush_type == BRANCH_CACHE_FLUSH_HW) {
+ patch_instruction_site(&patch__call_flush_branch_caches,
+ ppc_inst(PPC_INST_BCCTR_FLUSH));
+ } else {
+ patch_branch_site(&patch__call_flush_branch_caches,
+ (u64)&flush_branch_caches, BRANCH_SET_LINK);
+
+ // If we just need to flush the link stack, early return
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE) {
+ patch_instruction_site(&patch__flush_link_stack_return,
+ ppc_inst(PPC_INST_BLR));
+
+ // If we have flush instruction, early return
+ } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW) {
+ patch_instruction_site(&patch__flush_count_cache_return,
+ ppc_inst(PPC_INST_BLR));
+ }
+ }
+}
- // If we just need to flush the link stack, patch an early return
- if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
- patch_instruction_site(&patch__flush_link_stack_return,
- ppc_inst(PPC_INST_BLR));
- no_count_cache_flush();
- return;
+static void toggle_branch_cache_flush(bool enable)
+{
+ if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+ if (count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_NONE;
+
+ pr_info("count-cache-flush: flush disabled.\n");
+ } else {
+ if (security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_HW;
+ pr_info("count-cache-flush: hardware flush enabled.\n");
+ } else {
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_SW;
+ pr_info("count-cache-flush: software flush enabled.\n");
+ }
}
- if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
- count_cache_flush_type = COUNT_CACHE_FLUSH_SW;
- pr_info("count-cache-flush: full software flush sequence enabled.\n");
- return;
+ if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) {
+ if (link_stack_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_NONE;
+
+ pr_info("link-stack-flush: flush disabled.\n");
+ } else {
+ if (security_ftr_enabled(SEC_FTR_BCCTR_LINK_FLUSH_ASSIST)) {
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_HW;
+ pr_info("link-stack-flush: hardware flush enabled.\n");
+ } else {
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_SW;
+ pr_info("link-stack-flush: software flush enabled.\n");
+ }
}
- patch_instruction_site(&patch__flush_count_cache_return, ppc_inst(PPC_INST_BLR));
- count_cache_flush_type = COUNT_CACHE_FLUSH_HW;
- pr_info("count-cache-flush: hardware assisted flush sequence enabled\n");
+ update_branch_cache_flush();
}
void setup_count_cache_flush(void)
@@ -505,7 +524,7 @@ void setup_count_cache_flush(void)
security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE))
security_ftr_set(SEC_FTR_FLUSH_LINK_STACK);
- toggle_count_cache_flush(enable);
+ toggle_branch_cache_flush(enable);
}
#ifdef CONFIG_DEBUG_FS
@@ -520,14 +539,14 @@ static int count_cache_flush_set(void *data, u64 val)
else
return -EINVAL;
- toggle_count_cache_flush(enable);
+ toggle_branch_cache_flush(enable);
return 0;
}
static int count_cache_flush_get(void *data, u64 *val)
{
- if (count_cache_flush_type == COUNT_CACHE_FLUSH_NONE)
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE)
*val = 0;
else
*val = 1;
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 1415c16ab628..96950f189b5a 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -102,22 +102,18 @@ static inline int save_general_regs(struct pt_regs *regs,
struct mcontext __user *frame)
{
elf_greg_t64 *gregs = (elf_greg_t64 *)regs;
- int i;
- /* Force usr to alway see softe as 1 (interrupts enabled) */
- elf_greg_t64 softe = 0x1;
+ int val, i;
WARN_ON(!FULL_REGS(regs));
for (i = 0; i <= PT_RESULT; i ++) {
- if (i == 14 && !FULL_REGS(regs))
- i = 32;
- if ( i == PT_SOFTE) {
- if(__put_user((unsigned int)softe, &frame->mc_gregs[i]))
- return -EFAULT;
- else
- continue;
- }
- if (__put_user((unsigned int)gregs[i], &frame->mc_gregs[i]))
+ /* Force usr to alway see softe as 1 (interrupts enabled) */
+ if (i == PT_SOFTE)
+ val = 1;
+ else
+ val = gregs[i];
+
+ if (__put_user(val, &frame->mc_gregs[i]))
return -EFAULT;
}
return 0;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 55e5f76554da..bfc939360bad 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -21,6 +21,7 @@
#include <linux/ptrace.h>
#include <linux/ratelimit.h>
#include <linux/syscalls.h>
+#include <linux/pagemap.h>
#include <asm/sigcontext.h>
#include <asm/ucontext.h>
@@ -39,8 +40,8 @@
#define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
#define FP_REGS_SIZE sizeof(elf_fpregset_t)
-#define TRAMP_TRACEBACK 3
-#define TRAMP_SIZE 6
+#define TRAMP_TRACEBACK 4
+#define TRAMP_SIZE 7
/*
* When we have signals to deliver, we set up on the user stack,
@@ -600,13 +601,15 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp)
int i;
long err = 0;
+ /* bctrl # call the handler */
+ err |= __put_user(PPC_INST_BCTRL, &tramp[0]);
/* addi r1, r1, __SIGNAL_FRAMESIZE # Pop the dummy stackframe */
err |= __put_user(PPC_INST_ADDI | __PPC_RT(R1) | __PPC_RA(R1) |
- (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]);
+ (__SIGNAL_FRAMESIZE & 0xffff), &tramp[1]);
/* li r0, __NR_[rt_]sigreturn| */
- err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[1]);
+ err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[2]);
/* sc */
- err |= __put_user(PPC_INST_SC, &tramp[2]);
+ err |= __put_user(PPC_INST_SC, &tramp[3]);
/* Minimal traceback info */
for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++)
@@ -632,7 +635,6 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp)
SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
struct ucontext __user *, new_ctx, long, ctx_size)
{
- unsigned char tmp;
sigset_t set;
unsigned long new_msr = 0;
int ctx_has_vsx_region = 0;
@@ -667,9 +669,8 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
}
if (new_ctx == NULL)
return 0;
- if (!access_ok(new_ctx, ctx_size)
- || __get_user(tmp, (u8 __user *) new_ctx)
- || __get_user(tmp, (u8 __user *) new_ctx + ctx_size - 1))
+ if (!access_ok(new_ctx, ctx_size) ||
+ fault_in_pages_readable((u8 __user *)new_ctx, ctx_size))
return -EFAULT;
/*
@@ -864,12 +865,12 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
/* Set up to return from userspace. */
if (vdso64_rt_sigtramp && tsk->mm->context.vdso_base) {
- regs->link = tsk->mm->context.vdso_base + vdso64_rt_sigtramp;
+ regs->nip = tsk->mm->context.vdso_base + vdso64_rt_sigtramp;
} else {
err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]);
if (err)
goto badframe;
- regs->link = (unsigned long) &frame->tramp[0];
+ regs->nip = (unsigned long) &frame->tramp[0];
}
/* Allocate a dummy caller frame for the signal handler. */
@@ -878,8 +879,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
/* Set up "regs" so we "return" to the signal handler. */
if (is_elf2_task()) {
- regs->nip = (unsigned long) ksig->ka.sa.sa_handler;
- regs->gpr[12] = regs->nip;
+ regs->ctr = (unsigned long) ksig->ka.sa.sa_handler;
+ regs->gpr[12] = regs->ctr;
} else {
/* Handler is *really* a pointer to the function descriptor for
* the signal routine. The first entry in the function
@@ -889,7 +890,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
func_descr_t __user *funct_desc_ptr =
(func_descr_t __user *) ksig->ka.sa.sa_handler;
- err |= get_user(regs->nip, &funct_desc_ptr->entry);
+ err |= get_user(regs->ctr, &funct_desc_ptr->entry);
err |= get_user(regs->gpr[2], &funct_desc_ptr->toc);
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 73199470c265..8261999c7d52 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -59,6 +59,7 @@
#include <asm/asm-prototypes.h>
#include <asm/cpu_has_feature.h>
#include <asm/ftrace.h>
+#include <asm/kup.h>
#ifdef DEBUG
#include <asm/udbg.h>
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index a783fd324cb0..8e50818aa50b 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -221,6 +221,13 @@ again:
else if (cpu_has_feature(CPU_FTR_ALTIVEC))
mathflags |= MSR_VEC;
+ /*
+ * If userspace MSR has all available FP bits set,
+ * then they are live and no need to restore. If not,
+ * it means the regs were given up and restore_math
+ * may decide to restore them (to avoid taking an FP
+ * fault).
+ */
if ((regs->msr & mathflags) != mathflags)
restore_math(regs);
}
@@ -293,6 +300,7 @@ again:
else if (cpu_has_feature(CPU_FTR_ALTIVEC))
mathflags |= MSR_VEC;
+ /* See above restore_math comment */
if ((regs->msr & mathflags) != mathflags)
restore_math(regs);
}
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 571b3259697e..46b4ebc33db7 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -622,8 +622,10 @@ SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
+SYSFS_PMCSETUP(mmcr3, SPRN_MMCR3);
static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
+static DEVICE_ATTR(mmcr3, 0600, show_mmcr3, store_mmcr3);
#endif /* HAS_PPC_PMC56 */
@@ -886,6 +888,9 @@ static int register_cpu_online(unsigned int cpu)
#ifdef CONFIG_PMU_SYSFS
if (cpu_has_feature(CPU_FTR_MMCRA))
device_create_file(s, &dev_attr_mmcra);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ device_create_file(s, &dev_attr_mmcr3);
#endif /* CONFIG_PMU_SYSFS */
if (cpu_has_feature(CPU_FTR_PURR)) {
@@ -980,6 +985,9 @@ static int unregister_cpu_online(unsigned int cpu)
#ifdef CONFIG_PMU_SYSFS
if (cpu_has_feature(CPU_FTR_MMCRA))
device_remove_file(s, &dev_attr_mmcra);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ device_remove_file(s, &dev_attr_mmcr3);
#endif /* CONFIG_PMU_SYSFS */
if (cpu_has_feature(CPU_FTR_PURR)) {
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index c1fede6ec934..42761ebec9f7 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -73,8 +73,8 @@ ftrace_modify_code(unsigned long ip, struct ppc_inst old, struct ppc_inst new)
/* Make sure it is what we expect it to be */
if (!ppc_inst_equal(replaced, old)) {
- pr_err("%p: replaced (%#x) != old (%#x)",
- (void *)ip, ppc_inst_val(replaced), ppc_inst_val(old));
+ pr_err("%p: replaced (%s) != old (%s)",
+ (void *)ip, ppc_inst_as_str(replaced), ppc_inst_as_str(old));
return -EINVAL;
}
@@ -137,7 +137,7 @@ __ftrace_make_nop(struct module *mod,
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %x\n", ppc_inst_val(op));
+ pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -172,8 +172,8 @@ __ftrace_make_nop(struct module *mod,
/* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
if (!ppc_inst_equal(op, ppc_inst(PPC_INST_MFLR)) &&
!ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
- pr_err("Unexpected instruction %08x around bl _mcount\n",
- ppc_inst_val(op));
+ pr_err("Unexpected instruction %s around bl _mcount\n",
+ ppc_inst_as_str(op));
return -EINVAL;
}
#else
@@ -203,7 +203,7 @@ __ftrace_make_nop(struct module *mod,
}
if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) {
- pr_err("Expected %08x found %08x\n", PPC_INST_LD_TOC, ppc_inst_val(op));
+ pr_err("Expected %08x found %s\n", PPC_INST_LD_TOC, ppc_inst_as_str(op));
return -EINVAL;
}
#endif /* CONFIG_MPROFILE_KERNEL */
@@ -231,7 +231,7 @@ __ftrace_make_nop(struct module *mod,
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %x\n", ppc_inst_val(op));
+ pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -406,7 +406,7 @@ static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %x\n", ppc_inst_val(op));
+ pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -533,8 +533,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
return -EFAULT;
if (!expected_nop_sequence(ip, op[0], op[1])) {
- pr_err("Unexpected call sequence at %p: %x %x\n",
- ip, ppc_inst_val(op[0]), ppc_inst_val(op[1]));
+ pr_err("Unexpected call sequence at %p: %s %s\n",
+ ip, ppc_inst_as_str(op[0]), ppc_inst_as_str(op[1]));
return -EINVAL;
}
@@ -597,7 +597,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
/* It should be pointing to a nop */
if (!ppc_inst_equal(op, ppc_inst(PPC_INST_NOP))) {
- pr_err("Expected NOP but have %x\n", ppc_inst_val(op));
+ pr_err("Expected NOP but have %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
@@ -654,7 +654,7 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
}
if (!ppc_inst_equal(op, ppc_inst(PPC_INST_NOP))) {
- pr_err("Unexpected call sequence at %p: %x\n", ip, ppc_inst_val(op));
+ pr_err("Unexpected call sequence at %p: %s\n", ip, ppc_inst_as_str(op));
return -EINVAL;
}
@@ -733,7 +733,7 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %x\n", ppc_inst_val(op));
+ pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op));
return -EINVAL;
}
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index e0f4ba45b6cc..8dad44262e75 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -677,7 +677,7 @@ int vdso_getcpu_init(void)
node = cpu_to_node(cpu);
WARN_ON_ONCE(node > 0xffff);
- val = (cpu & 0xfff) | ((node & 0xffff) << 16);
+ val = (cpu & 0xffff) | ((node & 0xffff) << 16);
mtspr(SPRN_SPRG_VDSO_WRITE, val);
get_paca()->sprg_vdso = val;
diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S
index 526f5ba2593e..cab14324242b 100644
--- a/arch/powerpc/kernel/vdso64/cacheflush.S
+++ b/arch/powerpc/kernel/vdso64/cacheflush.S
@@ -8,6 +8,7 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
.text
@@ -24,14 +25,12 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- mr r11,r3
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r10, r0
mtlr r12
- mr r10,r3
lwz r7,CFG_DCACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5 /* ensure we get enough */
lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10)
@@ -48,7 +47,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
lwz r7,CFG_ICACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5
lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10)
diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S
index dc84f5ae3802..067247d3efb9 100644
--- a/arch/powerpc/kernel/vdso64/datapage.S
+++ b/arch/powerpc/kernel/vdso64/datapage.S
@@ -10,35 +10,13 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
.text
.global __kernel_datapage_offset;
__kernel_datapage_offset:
.long 0
-V_FUNCTION_BEGIN(__get_datapage)
- .cfi_startproc
- /* We don't want that exposed or overridable as we want other objects
- * to be able to bl directly to here
- */
- .protected __get_datapage
- .hidden __get_datapage
-
- mflr r0
- .cfi_register lr,r0
-
- bcl 20,31,data_page_branch
-data_page_branch:
- mflr r3
- mtlr r0
- addi r3, r3, __kernel_datapage_offset-data_page_branch
- lwz r0,0(r3)
- .cfi_restore lr
- add r3,r0,r3
- blr
- .cfi_endproc
-V_FUNCTION_END(__get_datapage)
-
/*
* void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
*
@@ -53,7 +31,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
mflr r12
.cfi_register lr,r12
mr r4,r3
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
mtlr r12
addi r3,r3,CFG_SYSCALL_MAP64
cmpldi cr0,r4,0
@@ -75,7 +53,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
ld r3,CFG_TB_TICKS_PER_SEC(r3)
mtlr r12
crclr cr0*4+so
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 1c9a04703250..20f8be40c653 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -9,6 +9,7 @@
#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>
@@ -26,7 +27,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
mr r11,r3 /* r11 holds tv */
mr r10,r4 /* r10 holds tz */
- bl V_LOCAL_FUNC(__get_datapage) /* get data page */
+ get_datapage r3, r0
cmpldi r11,0 /* check if tv is NULL */
beq 2f
lis r7,1000000@ha /* load up USEC_PER_SEC */
@@ -71,7 +72,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
mr r11,r4 /* r11 saves tp */
- bl V_LOCAL_FUNC(__get_datapage) /* get data page */
+ get_datapage r3, r0
lis r7,NSEC_PER_SEC@h /* want nanoseconds */
ori r7,r7,NSEC_PER_SEC@l
beq cr5,70f
@@ -188,7 +189,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
mflr r12
.cfi_register lr,r12
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
lwz r5, CLOCK_HRTIMER_RES(r3)
mtlr r12
li r3,0
@@ -221,7 +222,7 @@ V_FUNCTION_BEGIN(__kernel_time)
.cfi_register lr,r12
mr r11,r3 /* r11 holds t */
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
ld r4,STAMP_XTIME_SEC(r3)
diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S
index a8cc0409d7d2..bbf68cd01088 100644
--- a/arch/powerpc/kernel/vdso64/sigtramp.S
+++ b/arch/powerpc/kernel/vdso64/sigtramp.S
@@ -6,6 +6,7 @@
* Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
* Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp.
*/
+#include <asm/cache.h> /* IFETCH_ALIGN_BYTES */
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/unistd.h>
@@ -14,21 +15,17 @@
.text
-/* The nop here is a hack. The dwarf2 unwind routines subtract 1 from
- the return address to get an address in the middle of the presumed
- call instruction. Since we don't have a call here, we artificially
- extend the range covered by the unwind info by padding before the
- real start. */
- nop
.balign 8
+ .balign IFETCH_ALIGN_BYTES
V_FUNCTION_BEGIN(__kernel_sigtramp_rt64)
-.Lsigrt_start = . - 4
+.Lsigrt_start:
+ bctrl /* call the handler */
addi r1, r1, __SIGNAL_FRAMESIZE
li r0,__NR_rt_sigreturn
sc
.Lsigrt_end:
V_FUNCTION_END(__kernel_sigtramp_rt64)
-/* The ".balign 8" above and the following zeros mimic the old stack
+/* The .balign 8 above and the following zeros mimic the old stack
trampoline layout. The last magic value is the ucontext pointer,
chosen in such a way that older libgcc unwind code returns a zero
for a sigcontext pointer. */
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index efc5b52f95d2..801dc28fdcca 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -76,9 +76,7 @@ _GLOBAL(load_up_altivec)
oris r12,r12,MSR_VEC@h
std r12,_MSR(r1)
#endif
- /* Don't care if r4 overflows, this is desired behaviour */
- lbz r4,THREAD_LOAD_VEC(r5)
- addi r4,r4,1
+ li r4,1
stb r4,THREAD_LOAD_VEC(r5)
addi r6,r5,THREAD_VRSTATE
li r4,1
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index b4184092172a..8a449b2d8715 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -152,6 +152,8 @@ static void kexec_smp_down(void *arg)
if (ppc_md.kexec_cpu_down)
ppc_md.kexec_cpu_down(0, 1);
+ reset_sprs();
+
kexec_smp_wait();
/* NOTREACHED */
}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index e738ea652192..6a73714759ba 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -40,7 +40,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
if (kvmhv_on_pseries())
return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
- __pa(to), __pa(from), n);
+ (to != NULL) ? __pa(to): 0,
+ (from != NULL) ? __pa(from): 0, n);
quadrant = 1;
if (!pid)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6bf66649ab92..0a0df31987f7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1679,10 +1679,22 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_UAMOR:
*val = get_reg_val(id, vcpu->arch.uamor);
break;
- case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
+ case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1:
i = id - KVM_REG_PPC_MMCR0;
*val = get_reg_val(id, vcpu->arch.mmcr[i]);
break;
+ case KVM_REG_PPC_MMCR2:
+ *val = get_reg_val(id, vcpu->arch.mmcr[2]);
+ break;
+ case KVM_REG_PPC_MMCRA:
+ *val = get_reg_val(id, vcpu->arch.mmcra);
+ break;
+ case KVM_REG_PPC_MMCRS:
+ *val = get_reg_val(id, vcpu->arch.mmcrs);
+ break;
+ case KVM_REG_PPC_MMCR3:
+ *val = get_reg_val(id, vcpu->arch.mmcr[3]);
+ break;
case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
i = id - KVM_REG_PPC_PMC1;
*val = get_reg_val(id, vcpu->arch.pmc[i]);
@@ -1698,7 +1710,13 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
*val = get_reg_val(id, vcpu->arch.sdar);
break;
case KVM_REG_PPC_SIER:
- *val = get_reg_val(id, vcpu->arch.sier);
+ *val = get_reg_val(id, vcpu->arch.sier[0]);
+ break;
+ case KVM_REG_PPC_SIER2:
+ *val = get_reg_val(id, vcpu->arch.sier[1]);
+ break;
+ case KVM_REG_PPC_SIER3:
+ *val = get_reg_val(id, vcpu->arch.sier[2]);
break;
case KVM_REG_PPC_IAMR:
*val = get_reg_val(id, vcpu->arch.iamr);
@@ -1900,10 +1918,22 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_UAMOR:
vcpu->arch.uamor = set_reg_val(id, *val);
break;
- case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
+ case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1:
i = id - KVM_REG_PPC_MMCR0;
vcpu->arch.mmcr[i] = set_reg_val(id, *val);
break;
+ case KVM_REG_PPC_MMCR2:
+ vcpu->arch.mmcr[2] = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_MMCRA:
+ vcpu->arch.mmcra = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_MMCRS:
+ vcpu->arch.mmcrs = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_MMCR3:
+ *val = get_reg_val(id, vcpu->arch.mmcr[3]);
+ break;
case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
i = id - KVM_REG_PPC_PMC1;
vcpu->arch.pmc[i] = set_reg_val(id, *val);
@@ -1919,7 +1949,13 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
vcpu->arch.sdar = set_reg_val(id, *val);
break;
case KVM_REG_PPC_SIER:
- vcpu->arch.sier = set_reg_val(id, *val);
+ vcpu->arch.sier[0] = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_SIER2:
+ vcpu->arch.sier[1] = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_SIER3:
+ vcpu->arch.sier[2] = set_reg_val(id, *val);
break;
case KVM_REG_PPC_IAMR:
vcpu->arch.iamr = set_reg_val(id, *val);
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 63fd81f3039d..59822cba454d 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -140,6 +140,14 @@ BEGIN_FTR_SECTION
std r8, HSTATE_MMCR2(r13)
std r9, HSTATE_SIER(r13)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
+ mfspr r5, SPRN_MMCR3
+ mfspr r6, SPRN_SIER2
+ mfspr r7, SPRN_SIER3
+ std r5, HSTATE_MMCR3(r13)
+ std r6, HSTATE_SIER2(r13)
+ std r7, HSTATE_SIER3(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
mfspr r3, SPRN_PMC1
mfspr r5, SPRN_PMC2
mfspr r6, SPRN_PMC3
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 71943892c81c..799d6d0f4ead 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -3428,7 +3428,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
mtspr SPRN_PMC6, r9
ld r3, VCPU_MMCR(r4)
ld r5, VCPU_MMCR + 8(r4)
- ld r6, VCPU_MMCR + 16(r4)
+ ld r6, VCPU_MMCRA(r4)
ld r7, VCPU_SIAR(r4)
ld r8, VCPU_SDAR(r4)
mtspr SPRN_MMCR1, r5
@@ -3436,14 +3436,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
mtspr SPRN_SIAR, r7
mtspr SPRN_SDAR, r8
BEGIN_FTR_SECTION
- ld r5, VCPU_MMCR + 24(r4)
+ ld r5, VCPU_MMCR + 24(r4)
+ ld r6, VCPU_SIER + 8(r4)
+ ld r7, VCPU_SIER + 16(r4)
+ mtspr SPRN_MMCR3, r5
+ mtspr SPRN_SIER2, r6
+ mtspr SPRN_SIER3, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
+BEGIN_FTR_SECTION
+ ld r5, VCPU_MMCR + 16(r4)
ld r6, VCPU_SIER(r4)
mtspr SPRN_MMCR2, r5
mtspr SPRN_SIER, r6
BEGIN_FTR_SECTION_NESTED(96)
lwz r7, VCPU_PMC + 24(r4)
lwz r8, VCPU_PMC + 28(r4)
- ld r9, VCPU_MMCR + 32(r4)
+ ld r9, VCPU_MMCRS(r4)
mtspr SPRN_SPMC1, r7
mtspr SPRN_SPMC2, r8
mtspr SPRN_MMCRS, r9
@@ -3496,6 +3504,14 @@ BEGIN_FTR_SECTION
mtspr SPRN_MMCR2, r8
mtspr SPRN_SIER, r9
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
+ ld r5, HSTATE_MMCR3(r13)
+ ld r6, HSTATE_SIER2(r13)
+ ld r7, HSTATE_SIER3(r13)
+ mtspr SPRN_MMCR3, r5
+ mtspr SPRN_SIER2, r6
+ mtspr SPRN_SIER3, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
mtspr SPRN_MMCR0, r3
isync
mtlr r0
@@ -3551,10 +3567,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mfspr r8, SPRN_SDAR
std r4, VCPU_MMCR(r9)
std r5, VCPU_MMCR + 8(r9)
- std r6, VCPU_MMCR + 16(r9)
+ std r6, VCPU_MMCRA(r9)
BEGIN_FTR_SECTION
- std r10, VCPU_MMCR + 24(r9)
+ std r10, VCPU_MMCR + 16(r9)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
+ mfspr r5, SPRN_MMCR3
+ mfspr r6, SPRN_SIER2
+ mfspr r7, SPRN_SIER3
+ std r5, VCPU_MMCR + 24(r9)
+ std r6, VCPU_SIER + 8(r9)
+ std r7, VCPU_SIER + 16(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
std r7, VCPU_SIAR(r9)
std r8, VCPU_SDAR(r9)
mfspr r3, SPRN_PMC1
@@ -3578,7 +3602,7 @@ BEGIN_FTR_SECTION_NESTED(96)
mfspr r8, SPRN_MMCRS
stw r6, VCPU_PMC + 24(r9)
stw r7, VCPU_PMC + 28(r9)
- std r8, VCPU_MMCR + 32(r9)
+ std r8, VCPU_MMCRS(r9)
lis r4, 0x8000
mtspr SPRN_MMCRS, r4
END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h
index 4a61a971c34e..830a126e095d 100644
--- a/arch/powerpc/kvm/trace_hv.h
+++ b/arch/powerpc/kvm/trace_hv.h
@@ -89,7 +89,7 @@
{H_CREATE_RPT, "H_CREATE_RPT"}, \
{H_REMOVE_RPT, "H_REMOVE_RPT"}, \
{H_REGISTER_RPAGES, "H_REGISTER_RPAGES"}, \
- {H_DISABLE_AND_GETC, "H_DISABLE_AND_GETC"}, \
+ {H_DISABLE_AND_GET, "H_DISABLE_AND_GET"}, \
{H_ERROR_DATA, "H_ERROR_DATA"}, \
{H_GET_HCA_INFO, "H_GET_HCA_INFO"}, \
{H_GET_PERF_COUNT, "H_GET_PERF_COUNT"}, \
diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c
index 0666a8d29596..21210fa676e5 100644
--- a/arch/powerpc/lib/pmem.c
+++ b/arch/powerpc/lib/pmem.c
@@ -9,20 +9,56 @@
#include <asm/cacheflush.h>
+static inline void __clean_pmem_range(unsigned long start, unsigned long stop)
+{
+ unsigned long shift = l1_dcache_shift();
+ unsigned long bytes = l1_dcache_bytes();
+ void *addr = (void *)(start & ~(bytes - 1));
+ unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+ unsigned long i;
+
+ for (i = 0; i < size >> shift; i++, addr += bytes)
+ asm volatile(PPC_DCBSTPS(%0, %1): :"i"(0), "r"(addr): "memory");
+}
+
+static inline void __flush_pmem_range(unsigned long start, unsigned long stop)
+{
+ unsigned long shift = l1_dcache_shift();
+ unsigned long bytes = l1_dcache_bytes();
+ void *addr = (void *)(start & ~(bytes - 1));
+ unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+ unsigned long i;
+
+ for (i = 0; i < size >> shift; i++, addr += bytes)
+ asm volatile(PPC_DCBFPS(%0, %1): :"i"(0), "r"(addr): "memory");
+}
+
+static inline void clean_pmem_range(unsigned long start, unsigned long stop)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ return __clean_pmem_range(start, stop);
+}
+
+static inline void flush_pmem_range(unsigned long start, unsigned long stop)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ return __flush_pmem_range(start, stop);
+}
+
/*
* CONFIG_ARCH_HAS_PMEM_API symbols
*/
void arch_wb_cache_pmem(void *addr, size_t size)
{
unsigned long start = (unsigned long) addr;
- flush_dcache_range(start, start + size);
+ clean_pmem_range(start, start + size);
}
EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
void arch_invalidate_pmem(void *addr, size_t size)
{
unsigned long start = (unsigned long) addr;
- flush_dcache_range(start, start + size);
+ flush_pmem_range(start, start + size);
}
EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
@@ -35,7 +71,7 @@ long __copy_from_user_flushcache(void *dest, const void __user *src,
unsigned long copied, start = (unsigned long) dest;
copied = __copy_from_user(dest, src, size);
- flush_dcache_range(start, start + size);
+ clean_pmem_range(start, start + size);
return copied;
}
@@ -45,7 +81,7 @@ void *memcpy_flushcache(void *dest, const void *src, size_t size)
unsigned long start = (unsigned long) dest;
memcpy(dest, src, size);
- flush_dcache_range(start, start + size);
+ clean_pmem_range(start, start + size);
return dest;
}
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index ab6a137c3862..4194119eff82 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -201,8 +201,8 @@ static nokprobe_inline unsigned long mlsd_8lsd_ea(unsigned int instr,
unsigned int dd;
unsigned long ea, d0, d1, d;
- prefix_r = instr & (1ul << 20);
- ra = (suffix >> 16) & 0x1f;
+ prefix_r = GET_PREFIX_R(instr);
+ ra = GET_PREFIX_RA(suffix);
d0 = instr & 0x3ffff;
d1 = suffix & 0xffff;
@@ -1343,8 +1343,8 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
switch (opcode) {
#ifdef __powerpc64__
case 1:
- prefix_r = word & (1ul << 20);
- ra = (suffix >> 16) & 0x1f;
+ prefix_r = GET_PREFIX_R(word);
+ ra = GET_PREFIX_RA(suffix);
rd = (suffix >> 21) & 0x1f;
op->reg = rd;
op->val = regs->gpr[rd];
@@ -2719,8 +2719,8 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
}
break;
case 1: /* Prefixed instructions */
- prefix_r = word & (1ul << 20);
- ra = (suffix >> 16) & 0x1f;
+ prefix_r = GET_PREFIX_R(word);
+ ra = GET_PREFIX_RA(suffix);
op->update_reg = ra;
rd = (suffix >> 21) & 0x1f;
op->reg = rd;
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 46af80279ebc..081b05480c47 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -13,54 +13,45 @@
#include <asm/code-patching.h>
#include <asm/inst.h>
-#define IMM_L(i) ((uintptr_t)(i) & 0xffff)
-#define IMM_DS(i) ((uintptr_t)(i) & 0xfffc)
-
-/*
- * Defined with TEST_ prefix so it does not conflict with other
- * definitions.
- */
-#define TEST_LD(r, base, i) ppc_inst(PPC_INST_LD | ___PPC_RT(r) | \
- ___PPC_RA(base) | IMM_DS(i))
-#define TEST_LWZ(r, base, i) ppc_inst(PPC_INST_LWZ | ___PPC_RT(r) | \
- ___PPC_RA(base) | IMM_L(i))
-#define TEST_LWZX(t, a, b) ppc_inst(PPC_INST_LWZX | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_STD(r, base, i) ppc_inst(PPC_INST_STD | ___PPC_RS(r) | \
- ___PPC_RA(base) | IMM_DS(i))
-#define TEST_LDARX(t, a, b, eh) ppc_inst(PPC_INST_LDARX | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b) | \
- __PPC_EH(eh))
-#define TEST_STDCX(s, a, b) ppc_inst(PPC_INST_STDCX | ___PPC_RS(s) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_LFSX(t, a, b) ppc_inst(PPC_INST_LFSX | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_STFSX(s, a, b) ppc_inst(PPC_INST_STFSX | ___PPC_RS(s) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_LFDX(t, a, b) ppc_inst(PPC_INST_LFDX | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_STFDX(s, a, b) ppc_inst(PPC_INST_STFDX | ___PPC_RS(s) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_LVX(t, a, b) ppc_inst(PPC_INST_LVX | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_STVX(s, a, b) ppc_inst(PPC_INST_STVX | ___PPC_RS(s) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_LXVD2X(s, a, b) ppc_inst(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
-#define TEST_STXVD2X(s, a, b) ppc_inst(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
-#define TEST_ADD(t, a, b) ppc_inst(PPC_INST_ADD | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_ADD_DOT(t, a, b) ppc_inst(PPC_INST_ADD | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b) | 0x1)
-#define TEST_ADDC(t, a, b) ppc_inst(PPC_INST_ADDC | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define TEST_ADDC_DOT(t, a, b) ppc_inst(PPC_INST_ADDC | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b) | 0x1)
-
#define MAX_SUBTESTS 16
#define IGNORE_GPR(n) (0x1UL << (n))
#define IGNORE_XER (0x1UL << 32)
#define IGNORE_CCR (0x1UL << 33)
+#define NEGATIVE_TEST (0x1UL << 63)
+
+#define TEST_PLD(r, base, i, pr) \
+ ppc_inst_prefix(PPC_PREFIX_8LS | __PPC_PRFX_R(pr) | IMM_H(i), \
+ PPC_INST_PLD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
+
+#define TEST_PLWZ(r, base, i, pr) \
+ ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \
+ PPC_RAW_LWZ(r, base, i))
+
+#define TEST_PSTD(r, base, i, pr) \
+ ppc_inst_prefix(PPC_PREFIX_8LS | __PPC_PRFX_R(pr) | IMM_H(i), \
+ PPC_INST_PSTD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
+
+#define TEST_PLFS(r, base, i, pr) \
+ ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \
+ PPC_INST_LFS | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
+
+#define TEST_PSTFS(r, base, i, pr) \
+ ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \
+ PPC_INST_STFS | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
+
+#define TEST_PLFD(r, base, i, pr) \
+ ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \
+ PPC_INST_LFD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
+
+#define TEST_PSTFD(r, base, i, pr) \
+ ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \
+ PPC_INST_STFD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
+
+#define TEST_PADDI(t, a, i, pr) \
+ ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \
+ PPC_RAW_ADDI(t, a, i))
+
static void __init init_pt_regs(struct pt_regs *regs)
{
@@ -105,7 +96,7 @@ static void __init test_ld(void)
regs.gpr[3] = (unsigned long) &a;
/* ld r5, 0(r3) */
- stepped = emulate_step(&regs, TEST_LD(5, 3, 0));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_LD(5, 3, 0)));
if (stepped == 1 && regs.gpr[5] == a)
show_result("ld", "PASS");
@@ -113,6 +104,29 @@ static void __init test_ld(void)
show_result("ld", "FAIL");
}
+static void __init test_pld(void)
+{
+ struct pt_regs regs;
+ unsigned long a = 0x23;
+ int stepped = -1;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ show_result("pld", "SKIP (!CPU_FTR_ARCH_31)");
+ return;
+ }
+
+ init_pt_regs(&regs);
+ regs.gpr[3] = (unsigned long)&a;
+
+ /* pld r5, 0(r3), 0 */
+ stepped = emulate_step(&regs, TEST_PLD(5, 3, 0, 0));
+
+ if (stepped == 1 && regs.gpr[5] == a)
+ show_result("pld", "PASS");
+ else
+ show_result("pld", "FAIL");
+}
+
static void __init test_lwz(void)
{
struct pt_regs regs;
@@ -123,7 +137,7 @@ static void __init test_lwz(void)
regs.gpr[3] = (unsigned long) &a;
/* lwz r5, 0(r3) */
- stepped = emulate_step(&regs, TEST_LWZ(5, 3, 0));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_LWZ(5, 3, 0)));
if (stepped == 1 && regs.gpr[5] == a)
show_result("lwz", "PASS");
@@ -131,6 +145,30 @@ static void __init test_lwz(void)
show_result("lwz", "FAIL");
}
+static void __init test_plwz(void)
+{
+ struct pt_regs regs;
+ unsigned int a = 0x4545;
+ int stepped = -1;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ show_result("plwz", "SKIP (!CPU_FTR_ARCH_31)");
+ return;
+ }
+
+ init_pt_regs(&regs);
+ regs.gpr[3] = (unsigned long)&a;
+
+ /* plwz r5, 0(r3), 0 */
+
+ stepped = emulate_step(&regs, TEST_PLWZ(5, 3, 0, 0));
+
+ if (stepped == 1 && regs.gpr[5] == a)
+ show_result("plwz", "PASS");
+ else
+ show_result("plwz", "FAIL");
+}
+
static void __init test_lwzx(void)
{
struct pt_regs regs;
@@ -143,7 +181,7 @@ static void __init test_lwzx(void)
regs.gpr[5] = 0x8765;
/* lwzx r5, r3, r4 */
- stepped = emulate_step(&regs, TEST_LWZX(5, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_LWZX(5, 3, 4)));
if (stepped == 1 && regs.gpr[5] == a[2])
show_result("lwzx", "PASS");
else
@@ -161,13 +199,36 @@ static void __init test_std(void)
regs.gpr[5] = 0x5678;
/* std r5, 0(r3) */
- stepped = emulate_step(&regs, TEST_STD(5, 3, 0));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_STD(5, 3, 0)));
if (stepped == 1 && regs.gpr[5] == a)
show_result("std", "PASS");
else
show_result("std", "FAIL");
}
+static void __init test_pstd(void)
+{
+ struct pt_regs regs;
+ unsigned long a = 0x1234;
+ int stepped = -1;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ show_result("pstd", "SKIP (!CPU_FTR_ARCH_31)");
+ return;
+ }
+
+ init_pt_regs(&regs);
+ regs.gpr[3] = (unsigned long)&a;
+ regs.gpr[5] = 0x5678;
+
+ /* pstd r5, 0(r3), 0 */
+ stepped = emulate_step(&regs, TEST_PSTD(5, 3, 0, 0));
+ if (stepped == 1 || regs.gpr[5] == a)
+ show_result("pstd", "PASS");
+ else
+ show_result("pstd", "FAIL");
+}
+
static void __init test_ldarx_stdcx(void)
{
struct pt_regs regs;
@@ -186,7 +247,7 @@ static void __init test_ldarx_stdcx(void)
regs.gpr[5] = 0x5678;
/* ldarx r5, r3, r4, 0 */
- stepped = emulate_step(&regs, TEST_LDARX(5, 3, 4, 0));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_LDARX(5, 3, 4, 0)));
/*
* Don't touch 'a' here. Touching 'a' can do Load/store
@@ -204,7 +265,7 @@ static void __init test_ldarx_stdcx(void)
regs.gpr[5] = 0x9ABC;
/* stdcx. r5, r3, r4 */
- stepped = emulate_step(&regs, TEST_STDCX(5, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_STDCX(5, 3, 4)));
/*
* Two possible scenarios that indicates successful emulation
@@ -244,7 +305,7 @@ static void __init test_lfsx_stfsx(void)
regs.gpr[4] = 0;
/* lfsx frt10, r3, r4 */
- stepped = emulate_step(&regs, TEST_LFSX(10, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_LFSX(10, 3, 4)));
if (stepped == 1)
show_result("lfsx", "PASS");
@@ -257,7 +318,7 @@ static void __init test_lfsx_stfsx(void)
c.a = 678.91;
/* stfsx frs10, r3, r4 */
- stepped = emulate_step(&regs, TEST_STFSX(10, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_STFSX(10, 3, 4)));
if (stepped == 1 && c.b == cached_b)
show_result("stfsx", "PASS");
@@ -265,6 +326,53 @@ static void __init test_lfsx_stfsx(void)
show_result("stfsx", "FAIL");
}
+static void __init test_plfs_pstfs(void)
+{
+ struct pt_regs regs;
+ union {
+ float a;
+ int b;
+ } c;
+ int cached_b;
+ int stepped = -1;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ show_result("pld", "SKIP (!CPU_FTR_ARCH_31)");
+ return;
+ }
+
+ init_pt_regs(&regs);
+
+
+ /*** plfs ***/
+
+ c.a = 123.45;
+ cached_b = c.b;
+
+ regs.gpr[3] = (unsigned long)&c.a;
+
+ /* plfs frt10, 0(r3), 0 */
+ stepped = emulate_step(&regs, TEST_PLFS(10, 3, 0, 0));
+
+ if (stepped == 1)
+ show_result("plfs", "PASS");
+ else
+ show_result("plfs", "FAIL");
+
+
+ /*** pstfs ***/
+
+ c.a = 678.91;
+
+ /* pstfs frs10, 0(r3), 0 */
+ stepped = emulate_step(&regs, TEST_PSTFS(10, 3, 0, 0));
+
+ if (stepped == 1 && c.b == cached_b)
+ show_result("pstfs", "PASS");
+ else
+ show_result("pstfs", "FAIL");
+}
+
static void __init test_lfdx_stfdx(void)
{
struct pt_regs regs;
@@ -287,7 +395,7 @@ static void __init test_lfdx_stfdx(void)
regs.gpr[4] = 0;
/* lfdx frt10, r3, r4 */
- stepped = emulate_step(&regs, TEST_LFDX(10, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_LFDX(10, 3, 4)));
if (stepped == 1)
show_result("lfdx", "PASS");
@@ -300,13 +408,60 @@ static void __init test_lfdx_stfdx(void)
c.a = 987654.32;
/* stfdx frs10, r3, r4 */
- stepped = emulate_step(&regs, TEST_STFDX(10, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_STFDX(10, 3, 4)));
if (stepped == 1 && c.b == cached_b)
show_result("stfdx", "PASS");
else
show_result("stfdx", "FAIL");
}
+
+static void __init test_plfd_pstfd(void)
+{
+ struct pt_regs regs;
+ union {
+ double a;
+ long b;
+ } c;
+ long cached_b;
+ int stepped = -1;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ show_result("pld", "SKIP (!CPU_FTR_ARCH_31)");
+ return;
+ }
+
+ init_pt_regs(&regs);
+
+
+ /*** plfd ***/
+
+ c.a = 123456.78;
+ cached_b = c.b;
+
+ regs.gpr[3] = (unsigned long)&c.a;
+
+ /* plfd frt10, 0(r3), 0 */
+ stepped = emulate_step(&regs, TEST_PLFD(10, 3, 0, 0));
+
+ if (stepped == 1)
+ show_result("plfd", "PASS");
+ else
+ show_result("plfd", "FAIL");
+
+
+ /*** pstfd ***/
+
+ c.a = 987654.32;
+
+ /* pstfd frs10, 0(r3), 0 */
+ stepped = emulate_step(&regs, TEST_PSTFD(10, 3, 0, 0));
+
+ if (stepped == 1 && c.b == cached_b)
+ show_result("pstfd", "PASS");
+ else
+ show_result("pstfd", "FAIL");
+}
#else
static void __init test_lfsx_stfsx(void)
{
@@ -314,11 +469,23 @@ static void __init test_lfsx_stfsx(void)
show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)");
}
+static void __init test_plfs_pstfs(void)
+{
+ show_result("plfs", "SKIP (CONFIG_PPC_FPU is not set)");
+ show_result("pstfs", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+
static void __init test_lfdx_stfdx(void)
{
show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)");
show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)");
}
+
+static void __init test_plfd_pstfd(void)
+{
+ show_result("plfd", "SKIP (CONFIG_PPC_FPU is not set)");
+ show_result("pstfd", "SKIP (CONFIG_PPC_FPU is not set)");
+}
#endif /* CONFIG_PPC_FPU */
#ifdef CONFIG_ALTIVEC
@@ -346,7 +513,7 @@ static void __init test_lvx_stvx(void)
regs.gpr[4] = 0;
/* lvx vrt10, r3, r4 */
- stepped = emulate_step(&regs, TEST_LVX(10, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_LVX(10, 3, 4)));
if (stepped == 1)
show_result("lvx", "PASS");
@@ -362,7 +529,7 @@ static void __init test_lvx_stvx(void)
c.b[3] = 498532;
/* stvx vrs10, r3, r4 */
- stepped = emulate_step(&regs, TEST_STVX(10, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_STVX(10, 3, 4)));
if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
@@ -403,7 +570,7 @@ static void __init test_lxvd2x_stxvd2x(void)
regs.gpr[4] = 0;
/* lxvd2x vsr39, r3, r4 */
- stepped = emulate_step(&regs, TEST_LXVD2X(39, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_LXVD2X(39, R3, R4)));
if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) {
show_result("lxvd2x", "PASS");
@@ -423,7 +590,7 @@ static void __init test_lxvd2x_stxvd2x(void)
c.b[3] = 4;
/* stxvd2x vsr39, r3, r4 */
- stepped = emulate_step(&regs, TEST_STXVD2X(39, 3, 4));
+ stepped = emulate_step(&regs, ppc_inst(PPC_RAW_STXVD2X(39, R3, R4)));
if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
cached_b[2] == c.b[2] && cached_b[3] == c.b[3] &&
@@ -447,18 +614,24 @@ static void __init test_lxvd2x_stxvd2x(void)
static void __init run_tests_load_store(void)
{
test_ld();
+ test_pld();
test_lwz();
+ test_plwz();
test_lwzx();
test_std();
+ test_pstd();
test_ldarx_stdcx();
test_lfsx_stfsx();
+ test_plfs_pstfs();
test_lfdx_stfdx();
+ test_plfd_pstfd();
test_lvx_stvx();
test_lxvd2x_stxvd2x();
}
struct compute_test {
char *mnemonic;
+ unsigned long cpu_feature;
struct {
char *descr;
unsigned long flags;
@@ -467,6 +640,11 @@ struct compute_test {
} subtests[MAX_SUBTESTS + 1];
};
+/* Extreme values for si0||si1 (the MLS:D-form 34 bit immediate field) */
+#define SI_MIN BIT(33)
+#define SI_MAX (BIT(33) - 1)
+#define SI_UMAX (BIT(34) - 1)
+
static struct compute_test compute_tests[] = {
{
.mnemonic = "nop",
@@ -485,7 +663,7 @@ static struct compute_test compute_tests[] = {
.subtests = {
{
.descr = "RA = LONG_MIN, RB = LONG_MIN",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN,
.gpr[22] = LONG_MIN,
@@ -493,7 +671,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = LONG_MIN, RB = LONG_MAX",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN,
.gpr[22] = LONG_MAX,
@@ -501,7 +679,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = LONG_MAX, RB = LONG_MAX",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MAX,
.gpr[22] = LONG_MAX,
@@ -509,7 +687,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = ULONG_MAX,
.gpr[22] = ULONG_MAX,
@@ -517,7 +695,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = ULONG_MAX, RB = 0x1",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = ULONG_MAX,
.gpr[22] = 0x1,
@@ -525,7 +703,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MIN, RB = INT_MIN",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = INT_MIN,
.gpr[22] = INT_MIN,
@@ -533,7 +711,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MIN, RB = INT_MAX",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = INT_MIN,
.gpr[22] = INT_MAX,
@@ -541,7 +719,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MAX, RB = INT_MAX",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = INT_MAX,
.gpr[22] = INT_MAX,
@@ -549,7 +727,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = UINT_MAX, RB = UINT_MAX",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = UINT_MAX,
.gpr[22] = UINT_MAX,
@@ -557,7 +735,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = UINT_MAX, RB = 0x1",
- .instr = TEST_ADD(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)),
.regs = {
.gpr[21] = UINT_MAX,
.gpr[22] = 0x1,
@@ -571,7 +749,7 @@ static struct compute_test compute_tests[] = {
{
.descr = "RA = LONG_MIN, RB = LONG_MIN",
.flags = IGNORE_CCR,
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN,
.gpr[22] = LONG_MIN,
@@ -579,7 +757,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = LONG_MIN, RB = LONG_MAX",
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN,
.gpr[22] = LONG_MAX,
@@ -588,7 +766,7 @@ static struct compute_test compute_tests[] = {
{
.descr = "RA = LONG_MAX, RB = LONG_MAX",
.flags = IGNORE_CCR,
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MAX,
.gpr[22] = LONG_MAX,
@@ -596,7 +774,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = ULONG_MAX,
.gpr[22] = ULONG_MAX,
@@ -604,7 +782,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = ULONG_MAX, RB = 0x1",
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = ULONG_MAX,
.gpr[22] = 0x1,
@@ -612,7 +790,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MIN, RB = INT_MIN",
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = INT_MIN,
.gpr[22] = INT_MIN,
@@ -620,7 +798,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MIN, RB = INT_MAX",
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = INT_MIN,
.gpr[22] = INT_MAX,
@@ -628,7 +806,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MAX, RB = INT_MAX",
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = INT_MAX,
.gpr[22] = INT_MAX,
@@ -636,7 +814,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = UINT_MAX, RB = UINT_MAX",
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = UINT_MAX,
.gpr[22] = UINT_MAX,
@@ -644,7 +822,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = UINT_MAX, RB = 0x1",
- .instr = TEST_ADD_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)),
.regs = {
.gpr[21] = UINT_MAX,
.gpr[22] = 0x1,
@@ -657,7 +835,7 @@ static struct compute_test compute_tests[] = {
.subtests = {
{
.descr = "RA = LONG_MIN, RB = LONG_MIN",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN,
.gpr[22] = LONG_MIN,
@@ -665,7 +843,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = LONG_MIN, RB = LONG_MAX",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN,
.gpr[22] = LONG_MAX,
@@ -673,7 +851,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = LONG_MAX, RB = LONG_MAX",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MAX,
.gpr[22] = LONG_MAX,
@@ -681,7 +859,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = ULONG_MAX,
.gpr[22] = ULONG_MAX,
@@ -689,7 +867,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = ULONG_MAX, RB = 0x1",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = ULONG_MAX,
.gpr[22] = 0x1,
@@ -697,7 +875,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MIN, RB = INT_MIN",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = INT_MIN,
.gpr[22] = INT_MIN,
@@ -705,7 +883,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MIN, RB = INT_MAX",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = INT_MIN,
.gpr[22] = INT_MAX,
@@ -713,7 +891,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MAX, RB = INT_MAX",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = INT_MAX,
.gpr[22] = INT_MAX,
@@ -721,7 +899,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = UINT_MAX, RB = UINT_MAX",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = UINT_MAX,
.gpr[22] = UINT_MAX,
@@ -729,7 +907,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = UINT_MAX, RB = 0x1",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = UINT_MAX,
.gpr[22] = 0x1,
@@ -737,7 +915,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = LONG_MIN | INT_MIN, RB = LONG_MIN | INT_MIN",
- .instr = TEST_ADDC(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN | (uint)INT_MIN,
.gpr[22] = LONG_MIN | (uint)INT_MIN,
@@ -751,7 +929,7 @@ static struct compute_test compute_tests[] = {
{
.descr = "RA = LONG_MIN, RB = LONG_MIN",
.flags = IGNORE_CCR,
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN,
.gpr[22] = LONG_MIN,
@@ -759,7 +937,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = LONG_MIN, RB = LONG_MAX",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN,
.gpr[22] = LONG_MAX,
@@ -768,7 +946,7 @@ static struct compute_test compute_tests[] = {
{
.descr = "RA = LONG_MAX, RB = LONG_MAX",
.flags = IGNORE_CCR,
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MAX,
.gpr[22] = LONG_MAX,
@@ -776,7 +954,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = ULONG_MAX,
.gpr[22] = ULONG_MAX,
@@ -784,7 +962,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = ULONG_MAX, RB = 0x1",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = ULONG_MAX,
.gpr[22] = 0x1,
@@ -792,7 +970,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MIN, RB = INT_MIN",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = INT_MIN,
.gpr[22] = INT_MIN,
@@ -800,7 +978,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MIN, RB = INT_MAX",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = INT_MIN,
.gpr[22] = INT_MAX,
@@ -808,7 +986,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = INT_MAX, RB = INT_MAX",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = INT_MAX,
.gpr[22] = INT_MAX,
@@ -816,7 +994,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = UINT_MAX, RB = UINT_MAX",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = UINT_MAX,
.gpr[22] = UINT_MAX,
@@ -824,7 +1002,7 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = UINT_MAX, RB = 0x1",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = UINT_MAX,
.gpr[22] = 0x1,
@@ -832,31 +1010,164 @@ static struct compute_test compute_tests[] = {
},
{
.descr = "RA = LONG_MIN | INT_MIN, RB = LONG_MIN | INT_MIN",
- .instr = TEST_ADDC_DOT(20, 21, 22),
+ .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)),
.regs = {
.gpr[21] = LONG_MIN | (uint)INT_MIN,
.gpr[22] = LONG_MIN | (uint)INT_MIN,
}
}
}
+ },
+ {
+ .mnemonic = "paddi",
+ .cpu_feature = CPU_FTR_ARCH_31,
+ .subtests = {
+ {
+ .descr = "RA = LONG_MIN, SI = SI_MIN, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_MIN, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = LONG_MIN,
+ }
+ },
+ {
+ .descr = "RA = LONG_MIN, SI = SI_MAX, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_MAX, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = LONG_MIN,
+ }
+ },
+ {
+ .descr = "RA = LONG_MAX, SI = SI_MAX, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_MAX, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = LONG_MAX,
+ }
+ },
+ {
+ .descr = "RA = ULONG_MAX, SI = SI_UMAX, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_UMAX, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = ULONG_MAX,
+ }
+ },
+ {
+ .descr = "RA = ULONG_MAX, SI = 0x1, R = 0",
+ .instr = TEST_PADDI(21, 22, 0x1, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = ULONG_MAX,
+ }
+ },
+ {
+ .descr = "RA = INT_MIN, SI = SI_MIN, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_MIN, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = INT_MIN,
+ }
+ },
+ {
+ .descr = "RA = INT_MIN, SI = SI_MAX, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_MAX, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = INT_MIN,
+ }
+ },
+ {
+ .descr = "RA = INT_MAX, SI = SI_MAX, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_MAX, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = INT_MAX,
+ }
+ },
+ {
+ .descr = "RA = UINT_MAX, SI = 0x1, R = 0",
+ .instr = TEST_PADDI(21, 22, 0x1, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = UINT_MAX,
+ }
+ },
+ {
+ .descr = "RA = UINT_MAX, SI = SI_MAX, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_MAX, 0),
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = UINT_MAX,
+ }
+ },
+ {
+ .descr = "RA is r0, SI = SI_MIN, R = 0",
+ .instr = TEST_PADDI(21, 0, SI_MIN, 0),
+ .regs = {
+ .gpr[21] = 0x0,
+ }
+ },
+ {
+ .descr = "RA = 0, SI = SI_MIN, R = 0",
+ .instr = TEST_PADDI(21, 22, SI_MIN, 0),
+ .regs = {
+ .gpr[21] = 0x0,
+ .gpr[22] = 0x0,
+ }
+ },
+ {
+ .descr = "RA is r0, SI = 0, R = 1",
+ .instr = TEST_PADDI(21, 0, 0, 1),
+ .regs = {
+ .gpr[21] = 0,
+ }
+ },
+ {
+ .descr = "RA is r0, SI = SI_MIN, R = 1",
+ .instr = TEST_PADDI(21, 0, SI_MIN, 1),
+ .regs = {
+ .gpr[21] = 0,
+ }
+ },
+ /* Invalid instruction form with R = 1 and RA != 0 */
+ {
+ .descr = "RA = R22(0), SI = 0, R = 1",
+ .instr = TEST_PADDI(21, 22, 0, 1),
+ .flags = NEGATIVE_TEST,
+ .regs = {
+ .gpr[21] = 0,
+ .gpr[22] = 0,
+ }
+ }
+ }
}
};
static int __init emulate_compute_instr(struct pt_regs *regs,
- struct ppc_inst instr)
+ struct ppc_inst instr,
+ bool negative)
{
+ int analysed;
struct instruction_op op;
if (!regs || !ppc_inst_val(instr))
return -EINVAL;
- if (analyse_instr(&op, regs, instr) != 1 ||
- GETTYPE(op.type) != COMPUTE) {
- pr_info("emulation failed, instruction = 0x%08x\n", ppc_inst_val(instr));
+ regs->nip = patch_site_addr(&patch__exec_instr);
+
+ analysed = analyse_instr(&op, regs, instr);
+ if (analysed != 1 || GETTYPE(op.type) != COMPUTE) {
+ if (negative)
+ return -EFAULT;
+ pr_info("emulation failed, instruction = %s\n", ppc_inst_as_str(instr));
return -EFAULT;
}
-
- emulate_update_regs(regs, &op);
+ if (analysed == 1 && negative)
+ pr_info("negative test failed, instruction = %s\n", ppc_inst_as_str(instr));
+ if (!negative)
+ emulate_update_regs(regs, &op);
return 0;
}
@@ -864,7 +1175,6 @@ static int __init execute_compute_instr(struct pt_regs *regs,
struct ppc_inst instr)
{
extern int exec_instr(struct pt_regs *regs);
- extern s32 patch__exec_instr;
if (!regs || !ppc_inst_val(instr))
return -EINVAL;
@@ -872,7 +1182,7 @@ static int __init execute_compute_instr(struct pt_regs *regs,
/* Patch the NOP with the actual instruction */
patch_instruction_site(&patch__exec_instr, instr);
if (exec_instr(regs)) {
- pr_info("execution failed, instruction = 0x%08x\n", ppc_inst_val(instr));
+ pr_info("execution failed, instruction = %s\n", ppc_inst_as_str(instr));
return -EFAULT;
}
@@ -894,15 +1204,21 @@ static void __init run_tests_compute(void)
struct pt_regs *regs, exp, got;
unsigned int i, j, k;
struct ppc_inst instr;
- bool ignore_gpr, ignore_xer, ignore_ccr, passed;
+ bool ignore_gpr, ignore_xer, ignore_ccr, passed, rc, negative;
for (i = 0; i < ARRAY_SIZE(compute_tests); i++) {
test = &compute_tests[i];
+ if (test->cpu_feature && !early_cpu_has_feature(test->cpu_feature)) {
+ show_result(test->mnemonic, "SKIP (!CPU_FTR)");
+ continue;
+ }
+
for (j = 0; j < MAX_SUBTESTS && test->subtests[j].descr; j++) {
instr = test->subtests[j].instr;
flags = test->subtests[j].flags;
regs = &test->subtests[j].regs;
+ negative = flags & NEGATIVE_TEST;
ignore_xer = flags & IGNORE_XER;
ignore_ccr = flags & IGNORE_CCR;
passed = true;
@@ -917,8 +1233,12 @@ static void __init run_tests_compute(void)
exp.msr = MSR_KERNEL;
got.msr = MSR_KERNEL;
- if (emulate_compute_instr(&got, instr) ||
- execute_compute_instr(&exp, instr)) {
+ rc = emulate_compute_instr(&got, instr, negative) != 0;
+ if (negative) {
+ /* skip executing instruction */
+ passed = rc;
+ goto print;
+ } else if (rc || execute_compute_instr(&exp, instr)) {
passed = false;
goto print;
}
diff --git a/arch/powerpc/lib/test_emulate_step_exec_instr.S b/arch/powerpc/lib/test_emulate_step_exec_instr.S
index 1580f34f4f4f..9ef941d958d8 100644
--- a/arch/powerpc/lib/test_emulate_step_exec_instr.S
+++ b/arch/powerpc/lib/test_emulate_step_exec_instr.S
@@ -80,7 +80,9 @@ _GLOBAL(exec_instr)
REST_NVGPRS(r31)
/* Placeholder for the test instruction */
+ .balign 64
1: nop
+ nop
patch_site 1b patch__exec_instr
/*
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 468169e33c86..9fdabea04990 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -232,8 +232,6 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
rflags |= HPTE_R_I;
else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
rflags |= (HPTE_R_I | HPTE_R_G);
- else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
- rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
else
/*
* Add memory coherence if cache inhibited is not set
@@ -596,7 +594,7 @@ static void __init htab_scan_page_sizes(void)
}
#ifdef CONFIG_HUGETLB_PAGE
- if (!hugetlb_disabled) {
+ if (!hugetlb_disabled && !early_radix_enabled() ) {
/* Reserve 16G huge page memory sections for huge pages */
of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL);
}
@@ -663,11 +661,10 @@ static void __init htab_init_page_sizes(void)
* Pick a size for the linear mapping. Currently, we only
* support 16M, 1M and 4K which is the default
*/
- if (IS_ENABLED(STRICT_KERNEL_RWX) &&
+ if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) &&
(unsigned long)_stext % 0x1000000) {
if (mmu_psize_defs[MMU_PAGE_16M].shift)
- pr_warn("Kernel not 16M aligned, "
- "disabling 16M linear map alignment");
+ pr_warn("Kernel not 16M aligned, disabling 16M linear map alignment\n");
aligned = false;
}
@@ -1111,6 +1108,10 @@ void hash__early_init_mmu_secondary(void)
if (cpu_has_feature(CPU_FTR_ARCH_206)
&& cpu_has_feature(CPU_FTR_HVMODE))
tlbiel_all();
+
+#ifdef CONFIG_PPC_MEM_KEYS
+ mtspr(SPRN_UAMOR, default_uamor);
+#endif
}
#endif /* CONFIG_SMP */
@@ -1706,10 +1707,6 @@ unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift,
return gslot;
}
-/*
- * WARNING: This is called from hash_low_64.S, if you change this prototype,
- * do not forget to update the assembly call site !
- */
void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
unsigned long flags)
{
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index c58ad1049909..e18ae50a275c 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -15,6 +15,7 @@
#include <asm/powernv.h>
#include <asm/firmware.h>
#include <asm/ultravisor.h>
+#include <asm/kexec.h>
#include <mm/mmu_decl.h>
#include <trace/events/thp.h>
@@ -165,6 +166,8 @@ void mmu_cleanup_all(void)
radix__mmu_cleanup_all();
else if (mmu_hash_ops.hpte_clear_all)
mmu_hash_ops.hpte_clear_all();
+
+ reset_sprs();
}
#ifdef CONFIG_MEMORY_HOTPLUG
@@ -339,6 +342,9 @@ void pmd_fragment_free(unsigned long *pmd)
{
struct page *page = virt_to_page(pmd);
+ if (PageReserved(page))
+ return free_reserved_page(page);
+
BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
if (atomic_dec_and_test(&page->pt_frag_refcount)) {
pgtable_pmd_page_dtor(page);
@@ -356,7 +362,7 @@ static inline void pgtable_free(void *table, int index)
pmd_fragment_free(table);
break;
case PUD_INDEX:
- kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table);
+ __pud_free(table);
break;
#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
/* 16M hugepd directory at pud level */
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 1199fc2bfaec..792b36aa9619 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -10,58 +10,97 @@
#include <asm/mmu.h>
#include <asm/setup.h>
#include <linux/pkeys.h>
-#include <linux/of_device.h>
+#include <linux/of_fdt.h>
-DEFINE_STATIC_KEY_TRUE(pkey_disabled);
-int pkeys_total; /* Total pkeys as per device tree */
-u32 initial_allocation_mask; /* Bits set for the initially allocated keys */
-u32 reserved_allocation_mask; /* Bits set for reserved keys */
-static bool pkey_execute_disable_supported;
-static bool pkeys_devtree_defined; /* property exported by device tree */
-static u64 pkey_amr_mask; /* Bits in AMR not to be touched */
-static u64 pkey_iamr_mask; /* Bits in AMR not to be touched */
-static u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */
+int num_pkey; /* Max number of pkeys supported */
+/*
+ * Keys marked in the reservation list cannot be allocated by userspace
+ */
+u32 reserved_allocation_mask __ro_after_init;
+
+/* Bits set for the initially allocated keys */
+static u32 initial_allocation_mask __ro_after_init;
+
+/*
+ * Even if we allocate keys with sys_pkey_alloc(), we need to make sure
+ * other thread still find the access denied using the same keys.
+ */
+static u64 default_amr = ~0x0UL;
+static u64 default_iamr = 0x5555555555555555UL;
+u64 default_uamor __ro_after_init;
+/*
+ * Key used to implement PROT_EXEC mmap. Denies READ/WRITE
+ * We pick key 2 because 0 is special key and 1 is reserved as per ISA.
+ */
static int execute_only_key = 2;
+static bool pkey_execute_disable_supported;
+
#define AMR_BITS_PER_PKEY 2
#define AMR_RD_BIT 0x1UL
#define AMR_WR_BIT 0x2UL
#define IAMR_EX_BIT 0x1UL
-#define PKEY_REG_BITS (sizeof(u64)*8)
+#define PKEY_REG_BITS (sizeof(u64) * 8)
#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey+1) * AMR_BITS_PER_PKEY))
-static void scan_pkey_feature(void)
+static int __init dt_scan_storage_keys(unsigned long node,
+ const char *uname, int depth,
+ void *data)
{
- u32 vals[2];
- struct device_node *cpu;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
+ int *pkeys_total = (int *) data;
- cpu = of_find_node_by_type(NULL, "cpu");
- if (!cpu)
- return;
+ /* We are scanning "cpu" nodes only */
+ if (type == NULL || strcmp(type, "cpu") != 0)
+ return 0;
- if (of_property_read_u32_array(cpu,
- "ibm,processor-storage-keys", vals, 2))
- return;
+ prop = of_get_flat_dt_prop(node, "ibm,processor-storage-keys", NULL);
+ if (!prop)
+ return 0;
+ *pkeys_total = be32_to_cpu(prop[0]);
+ return 1;
+}
+
+static int scan_pkey_feature(void)
+{
+ int ret;
+ int pkeys_total = 0;
/*
- * Since any pkey can be used for data or execute, we will just treat
- * all keys as equal and track them as one entity.
+ * Pkey is not supported with Radix translation.
*/
- pkeys_total = vals[0];
- pkeys_devtree_defined = true;
-}
+ if (early_radix_enabled())
+ return 0;
-static inline bool pkey_mmu_enabled(void)
-{
- if (firmware_has_feature(FW_FEATURE_LPAR))
- return pkeys_total;
- else
- return cpu_has_feature(CPU_FTR_PKEY);
+ ret = of_scan_flat_dt(dt_scan_storage_keys, &pkeys_total);
+ if (ret == 0) {
+ /*
+ * Let's assume 32 pkeys on P8/P9 bare metal, if its not defined by device
+ * tree. We make this exception since some version of skiboot forgot to
+ * expose this property on power8/9.
+ */
+ if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+ unsigned long pvr = mfspr(SPRN_PVR);
+
+ if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E ||
+ PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9)
+ pkeys_total = 32;
+ }
+ }
+
+ /*
+ * Adjust the upper limit, based on the number of bits supported by
+ * arch-neutral code.
+ */
+ pkeys_total = min_t(int, pkeys_total,
+ ((ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT) + 1));
+ return pkeys_total;
}
-static int pkey_initialize(void)
+void __init pkey_early_init_devtree(void)
{
- int os_reserved, i;
+ int pkeys_total, i;
/*
* We define PKEY_DISABLE_EXECUTE in addition to the arch-neutral
@@ -80,31 +119,14 @@ static int pkey_initialize(void)
!= (sizeof(u64) * BITS_PER_BYTE));
/* scan the device tree for pkey feature */
- scan_pkey_feature();
-
- /*
- * Let's assume 32 pkeys on P8 bare metal, if its not defined by device
- * tree. We make this exception since skiboot forgot to expose this
- * property on power8.
- */
- if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) &&
- cpu_has_feature(CPU_FTRS_POWER8))
- pkeys_total = 32;
-
- /*
- * Adjust the upper limit, based on the number of bits supported by
- * arch-neutral code.
- */
- pkeys_total = min_t(int, pkeys_total,
- ((ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT)+1));
+ pkeys_total = scan_pkey_feature();
+ if (!pkeys_total)
+ goto out;
- if (!pkey_mmu_enabled() || radix_enabled() || !pkeys_total)
- static_branch_enable(&pkey_disabled);
- else
- static_branch_disable(&pkey_disabled);
+ /* Allow all keys to be modified by default */
+ default_uamor = ~0x0UL;
- if (static_branch_likely(&pkey_disabled))
- return 0;
+ cur_cpu_spec->mmu_features |= MMU_FTR_PKEY;
/*
* The device tree cannot be relied to indicate support for
@@ -118,53 +140,86 @@ static int pkey_initialize(void)
#ifdef CONFIG_PPC_4K_PAGES
/*
* The OS can manage only 8 pkeys due to its inability to represent them
- * in the Linux 4K PTE.
+ * in the Linux 4K PTE. Mark all other keys reserved.
*/
- os_reserved = pkeys_total - 8;
+ num_pkey = min(8, pkeys_total);
#else
- os_reserved = 0;
+ num_pkey = pkeys_total;
#endif
- /* Bits are in LE format. */
- reserved_allocation_mask = (0x1 << 1) | (0x1 << execute_only_key);
-
- /* register mask is in BE format */
- pkey_amr_mask = ~0x0ul;
- pkey_amr_mask &= ~(0x3ul << pkeyshift(0));
-
- pkey_iamr_mask = ~0x0ul;
- pkey_iamr_mask &= ~(0x3ul << pkeyshift(0));
- pkey_iamr_mask &= ~(0x3ul << pkeyshift(execute_only_key));
-
- pkey_uamor_mask = ~0x0ul;
- pkey_uamor_mask &= ~(0x3ul << pkeyshift(0));
- pkey_uamor_mask &= ~(0x3ul << pkeyshift(execute_only_key));
-
- /* mark the rest of the keys as reserved and hence unavailable */
- for (i = (pkeys_total - os_reserved); i < pkeys_total; i++) {
- reserved_allocation_mask |= (0x1 << i);
- pkey_uamor_mask &= ~(0x3ul << pkeyshift(i));
- }
- initial_allocation_mask = reserved_allocation_mask | (0x1 << 0);
- if (unlikely((pkeys_total - os_reserved) <= execute_only_key)) {
+ if (unlikely(num_pkey <= execute_only_key) || !pkey_execute_disable_supported) {
/*
* Insufficient number of keys to support
* execute only key. Mark it unavailable.
- * Any AMR, UAMOR, IAMR bit set for
- * this key is irrelevant since this key
- * can never be allocated.
*/
execute_only_key = -1;
+ } else {
+ /*
+ * Mark the execute_only_pkey as not available for
+ * user allocation via pkey_alloc.
+ */
+ reserved_allocation_mask |= (0x1 << execute_only_key);
+
+ /*
+ * Deny READ/WRITE for execute_only_key.
+ * Allow execute in IAMR.
+ */
+ default_amr |= (0x3ul << pkeyshift(execute_only_key));
+ default_iamr &= ~(0x1ul << pkeyshift(execute_only_key));
+
+ /*
+ * Clear the uamor bits for this key.
+ */
+ default_uamor &= ~(0x3ul << pkeyshift(execute_only_key));
}
- return 0;
-}
+ /*
+ * Allow access for only key 0. And prevent any other modification.
+ */
+ default_amr &= ~(0x3ul << pkeyshift(0));
+ default_iamr &= ~(0x1ul << pkeyshift(0));
+ default_uamor &= ~(0x3ul << pkeyshift(0));
+ /*
+ * key 0 is special in that we want to consider it an allocated
+ * key which is preallocated. We don't allow changing AMR bits
+ * w.r.t key 0. But one can pkey_free(key0)
+ */
+ initial_allocation_mask |= (0x1 << 0);
+
+ /*
+ * key 1 is recommended not to be used. PowerISA(3.0) page 1015,
+ * programming note.
+ */
+ reserved_allocation_mask |= (0x1 << 1);
+ default_uamor &= ~(0x3ul << pkeyshift(1));
-arch_initcall(pkey_initialize);
+ /*
+ * Prevent the usage of OS reserved keys. Update UAMOR
+ * for those keys. Also mark the rest of the bits in the
+ * 32 bit mask as reserved.
+ */
+ for (i = num_pkey; i < 32 ; i++) {
+ reserved_allocation_mask |= (0x1 << i);
+ default_uamor &= ~(0x3ul << pkeyshift(i));
+ }
+ /*
+ * Prevent the allocation of reserved keys too.
+ */
+ initial_allocation_mask |= reserved_allocation_mask;
+
+ pr_info("Enabling pkeys with max key count %d\n", num_pkey);
+out:
+ /*
+ * Setup uamor on boot cpu
+ */
+ mtspr(SPRN_UAMOR, default_uamor);
+
+ return;
+}
void pkey_mm_init(struct mm_struct *mm)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
mm_pkey_allocation_map(mm) = initial_allocation_mask;
mm->context.execute_only_pkey = execute_only_key;
@@ -196,30 +251,6 @@ static inline void write_iamr(u64 value)
mtspr(SPRN_IAMR, value);
}
-static inline u64 read_uamor(void)
-{
- return mfspr(SPRN_UAMOR);
-}
-
-static inline void write_uamor(u64 value)
-{
- mtspr(SPRN_UAMOR, value);
-}
-
-static bool is_pkey_enabled(int pkey)
-{
- u64 uamor = read_uamor();
- u64 pkey_bits = 0x3ul << pkeyshift(pkey);
- u64 uamor_pkey_bits = (uamor & pkey_bits);
-
- /*
- * Both the bits in UAMOR corresponding to the key should be set or
- * reset.
- */
- WARN_ON(uamor_pkey_bits && (uamor_pkey_bits != pkey_bits));
- return !!(uamor_pkey_bits);
-}
-
static inline void init_amr(int pkey, u8 init_bits)
{
u64 new_amr_bits = (((u64)init_bits & 0x3UL) << pkeyshift(pkey));
@@ -245,8 +276,18 @@ int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
{
u64 new_amr_bits = 0x0ul;
u64 new_iamr_bits = 0x0ul;
+ u64 pkey_bits, uamor_pkey_bits;
+
+ /*
+ * Check whether the key is disabled by UAMOR.
+ */
+ pkey_bits = 0x3ul << pkeyshift(pkey);
+ uamor_pkey_bits = (default_uamor & pkey_bits);
- if (!is_pkey_enabled(pkey))
+ /*
+ * Both the bits in UAMOR corresponding to the key should be set
+ */
+ if (uamor_pkey_bits != pkey_bits)
return -EINVAL;
if (init_val & PKEY_DISABLE_EXECUTE) {
@@ -268,7 +309,7 @@ int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
void thread_pkey_regs_save(struct thread_struct *thread)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
/*
@@ -276,38 +317,33 @@ void thread_pkey_regs_save(struct thread_struct *thread)
*/
thread->amr = read_amr();
thread->iamr = read_iamr();
- thread->uamor = read_uamor();
}
void thread_pkey_regs_restore(struct thread_struct *new_thread,
struct thread_struct *old_thread)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
if (old_thread->amr != new_thread->amr)
write_amr(new_thread->amr);
if (old_thread->iamr != new_thread->iamr)
write_iamr(new_thread->iamr);
- if (old_thread->uamor != new_thread->uamor)
- write_uamor(new_thread->uamor);
}
void thread_pkey_regs_init(struct thread_struct *thread)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
- thread->amr = pkey_amr_mask;
- thread->iamr = pkey_iamr_mask;
- thread->uamor = pkey_uamor_mask;
+ thread->amr = default_amr;
+ thread->iamr = default_iamr;
- write_uamor(pkey_uamor_mask);
- write_amr(pkey_amr_mask);
- write_iamr(pkey_iamr_mask);
+ write_amr(default_amr);
+ write_iamr(default_iamr);
}
-int __execute_only_pkey(struct mm_struct *mm)
+int execute_only_pkey(struct mm_struct *mm)
{
return mm->context.execute_only_pkey;
}
@@ -353,21 +389,20 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute)
int pkey_shift;
u64 amr;
- if (!is_pkey_enabled(pkey))
- return true;
-
pkey_shift = pkeyshift(pkey);
- if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift)))
- return true;
+ if (execute)
+ return !(read_iamr() & (IAMR_EX_BIT << pkey_shift));
+
+ amr = read_amr();
+ if (write)
+ return !(amr & (AMR_WR_BIT << pkey_shift));
- amr = read_amr(); /* Delay reading amr until absolutely needed */
- return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) ||
- (write && !(amr & (AMR_WR_BIT << pkey_shift))));
+ return !(amr & (AMR_RD_BIT << pkey_shift));
}
bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return true;
return pkey_access_permitted(pte_to_pkey_bits(pte), write, execute);
@@ -384,7 +419,7 @@ bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
bool execute, bool foreign)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return true;
/*
* Do not enforce our key-permissions on a foreign vma.
@@ -397,7 +432,7 @@ bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
/* Duplicate the oldmm pkey state in mm: */
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index bb00e0cba119..a8f46a686219 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -15,7 +15,7 @@
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/string_helpers.h>
-#include <linux/stop_machine.h>
+#include <linux/memory.h>
#include <asm/pgalloc.h>
#include <asm/mmu_context.h>
@@ -34,6 +34,7 @@
unsigned int mmu_pid_bits;
unsigned int mmu_base_pid;
+unsigned int radix_mem_block_size __ro_after_init;
static __ref void *early_alloc_pgtable(unsigned long size, int nid,
unsigned long region_start, unsigned long region_end)
@@ -56,6 +57,13 @@ static __ref void *early_alloc_pgtable(unsigned long size, int nid,
return ptr;
}
+/*
+ * When allocating pud or pmd pointers, we allocate a complete page
+ * of PAGE_SIZE rather than PUD_TABLE_SIZE or PMD_TABLE_SIZE. This
+ * is to ensure that the page obtained from the memblock allocator
+ * can be completely used as page table page and can be freed
+ * correctly when the page table entries are removed.
+ */
static int early_map_kernel_page(unsigned long ea, unsigned long pa,
pgprot_t flags,
unsigned int map_page_size,
@@ -72,8 +80,8 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa,
pgdp = pgd_offset_k(ea);
p4dp = p4d_offset(pgdp, ea);
if (p4d_none(*p4dp)) {
- pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid,
- region_start, region_end);
+ pudp = early_alloc_pgtable(PAGE_SIZE, nid,
+ region_start, region_end);
p4d_populate(&init_mm, p4dp, pudp);
}
pudp = pud_offset(p4dp, ea);
@@ -82,8 +90,8 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa,
goto set_the_pte;
}
if (pud_none(*pudp)) {
- pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid,
- region_start, region_end);
+ pmdp = early_alloc_pgtable(PAGE_SIZE, nid, region_start,
+ region_end);
pud_populate(&init_mm, pudp, pmdp);
}
pmdp = pmd_offset(pudp, ea);
@@ -259,6 +267,7 @@ static unsigned long next_boundary(unsigned long addr, unsigned long end)
static int __meminit create_physical_mapping(unsigned long start,
unsigned long end,
+ unsigned long max_mapping_size,
int nid, pgprot_t _prot)
{
unsigned long vaddr, addr, mapping_size = 0;
@@ -272,6 +281,8 @@ static int __meminit create_physical_mapping(unsigned long start,
int rc;
gap = next_boundary(addr, end) - addr;
+ if (gap > max_mapping_size)
+ gap = max_mapping_size;
previous_size = mapping_size;
prev_exec = exec;
@@ -322,8 +333,9 @@ static void __init radix_init_pgtable(void)
/* We don't support slb for radix */
mmu_slb_size = 0;
+
/*
- * Create the linear mapping, using standard page size for now
+ * Create the linear mapping
*/
for_each_memblock(memory, reg) {
/*
@@ -339,6 +351,7 @@ static void __init radix_init_pgtable(void)
WARN_ON(create_physical_mapping(reg->base,
reg->base + reg->size,
+ radix_mem_block_size,
-1, PAGE_KERNEL));
}
@@ -479,6 +492,57 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
return 1;
}
+#ifdef CONFIG_MEMORY_HOTPLUG
+static int __init probe_memory_block_size(unsigned long node, const char *uname, int
+ depth, void *data)
+{
+ unsigned long *mem_block_size = (unsigned long *)data;
+ const __be64 *prop;
+ int len;
+
+ if (depth != 1)
+ return 0;
+
+ if (strcmp(uname, "ibm,dynamic-reconfiguration-memory"))
+ return 0;
+
+ prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len);
+ if (!prop || len < sizeof(__be64))
+ /*
+ * Nothing in the device tree
+ */
+ *mem_block_size = MIN_MEMORY_BLOCK_SIZE;
+ else
+ *mem_block_size = be64_to_cpup(prop);
+ return 1;
+}
+
+static unsigned long radix_memory_block_size(void)
+{
+ unsigned long mem_block_size = MIN_MEMORY_BLOCK_SIZE;
+
+ /*
+ * OPAL firmware feature is set by now. Hence we are ok
+ * to test OPAL feature.
+ */
+ if (firmware_has_feature(FW_FEATURE_OPAL))
+ mem_block_size = 1UL * 1024 * 1024 * 1024;
+ else
+ of_scan_flat_dt(probe_memory_block_size, &mem_block_size);
+
+ return mem_block_size;
+}
+
+#else /* CONFIG_MEMORY_HOTPLUG */
+
+static unsigned long radix_memory_block_size(void)
+{
+ return 1UL * 1024 * 1024 * 1024;
+}
+
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+
void __init radix__early_init_devtree(void)
{
int rc;
@@ -487,17 +551,27 @@ void __init radix__early_init_devtree(void)
* Try to find the available page sizes in the device-tree
*/
rc = of_scan_flat_dt(radix_dt_scan_page_sizes, NULL);
- if (rc != 0) /* Found */
- goto found;
+ if (!rc) {
+ /*
+ * No page size details found in device tree.
+ * Let's assume we have page 4k and 64k support
+ */
+ mmu_psize_defs[MMU_PAGE_4K].shift = 12;
+ mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
+
+ mmu_psize_defs[MMU_PAGE_64K].shift = 16;
+ mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
+ }
+
/*
- * let's assume we have page 4k and 64k support
+ * Max mapping size used when mapping pages. We don't use
+ * ppc_md.memory_block_size() here because this get called
+ * early and we don't have machine probe called yet. Also
+ * the pseries implementation only check for ibm,lmb-size.
+ * All hypervisor supporting radix do expose that device
+ * tree node.
*/
- mmu_psize_defs[MMU_PAGE_4K].shift = 12;
- mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
-
- mmu_psize_defs[MMU_PAGE_64K].shift = 16;
- mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
-found:
+ radix_mem_block_size = radix_memory_block_size();
return;
}
@@ -519,8 +593,10 @@ void setup_kuep(bool disabled)
if (disabled || !early_radix_enabled())
return;
- if (smp_processor_id() == boot_cpuid)
+ if (smp_processor_id() == boot_cpuid) {
pr_info("Activating Kernel Userspace Execution Prevention\n");
+ cur_cpu_spec->mmu_features |= MMU_FTR_KUEP;
+ }
/*
* Radix always uses key0 of the IAMR to determine if an access is
@@ -544,6 +620,10 @@ void setup_kuap(bool disabled)
/* Make sure userspace can't change the AMR */
mtspr(SPRN_UAMOR, 0);
+
+ /*
+ * Set the default kernel AMR values on all cpus.
+ */
mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
isync();
}
@@ -700,30 +780,19 @@ static void free_pmd_table(pmd_t *pmd_start, pud_t *pud)
pud_clear(pud);
}
-struct change_mapping_params {
- pte_t *pte;
- unsigned long start;
- unsigned long end;
- unsigned long aligned_start;
- unsigned long aligned_end;
-};
-
-static int __meminit stop_machine_change_mapping(void *data)
+static void free_pud_table(pud_t *pud_start, p4d_t *p4d)
{
- struct change_mapping_params *params =
- (struct change_mapping_params *)data;
+ pud_t *pud;
+ int i;
- if (!data)
- return -1;
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ pud = pud_start + i;
+ if (!pud_none(*pud))
+ return;
+ }
- spin_unlock(&init_mm.page_table_lock);
- pte_clear(&init_mm, params->aligned_start, params->pte);
- create_physical_mapping(__pa(params->aligned_start),
- __pa(params->start), -1, PAGE_KERNEL);
- create_physical_mapping(__pa(params->end), __pa(params->aligned_end),
- -1, PAGE_KERNEL);
- spin_lock(&init_mm.page_table_lock);
- return 0;
+ pud_free(&init_mm, pud_start);
+ p4d_clear(p4d);
}
static void remove_pte_table(pte_t *pte_start, unsigned long addr,
@@ -754,52 +823,6 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr,
}
}
-/*
- * clear the pte and potentially split the mapping helper
- */
-static void __meminit split_kernel_mapping(unsigned long addr, unsigned long end,
- unsigned long size, pte_t *pte)
-{
- unsigned long mask = ~(size - 1);
- unsigned long aligned_start = addr & mask;
- unsigned long aligned_end = addr + size;
- struct change_mapping_params params;
- bool split_region = false;
-
- if ((end - addr) < size) {
- /*
- * We're going to clear the PTE, but not flushed
- * the mapping, time to remap and flush. The
- * effects if visible outside the processor or
- * if we are running in code close to the
- * mapping we cleared, we are in trouble.
- */
- if (overlaps_kernel_text(aligned_start, addr) ||
- overlaps_kernel_text(end, aligned_end)) {
- /*
- * Hack, just return, don't pte_clear
- */
- WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel "
- "text, not splitting\n", addr, end);
- return;
- }
- split_region = true;
- }
-
- if (split_region) {
- params.pte = pte;
- params.start = addr;
- params.end = end;
- params.aligned_start = addr & ~(size - 1);
- params.aligned_end = min_t(unsigned long, aligned_end,
- (unsigned long)__va(memblock_end_of_DRAM()));
- stop_machine(stop_machine_change_mapping, &params, NULL);
- return;
- }
-
- pte_clear(&init_mm, addr, pte);
-}
-
static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
unsigned long end)
{
@@ -815,7 +838,12 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
continue;
if (pmd_is_leaf(*pmd)) {
- split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd);
+ if (!IS_ALIGNED(addr, PMD_SIZE) ||
+ !IS_ALIGNED(next, PMD_SIZE)) {
+ WARN_ONCE(1, "%s: unaligned range\n", __func__);
+ continue;
+ }
+ pte_clear(&init_mm, addr, (pte_t *)pmd);
continue;
}
@@ -840,7 +868,12 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr,
continue;
if (pud_is_leaf(*pud)) {
- split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud);
+ if (!IS_ALIGNED(addr, PUD_SIZE) ||
+ !IS_ALIGNED(next, PUD_SIZE)) {
+ WARN_ONCE(1, "%s: unaligned range\n", __func__);
+ continue;
+ }
+ pte_clear(&init_mm, addr, (pte_t *)pud);
continue;
}
@@ -868,12 +901,19 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end)
continue;
if (p4d_is_leaf(*p4d)) {
- split_kernel_mapping(addr, end, P4D_SIZE, (pte_t *)p4d);
+ if (!IS_ALIGNED(addr, P4D_SIZE) ||
+ !IS_ALIGNED(next, P4D_SIZE)) {
+ WARN_ONCE(1, "%s: unaligned range\n", __func__);
+ continue;
+ }
+
+ pte_clear(&init_mm, addr, (pte_t *)pgd);
continue;
}
pud_base = (pud_t *)p4d_page_vaddr(*p4d);
remove_pud_table(pud_base, addr, next);
+ free_pud_table(pud_base, p4d);
}
spin_unlock(&init_mm.page_table_lock);
@@ -889,7 +929,8 @@ int __meminit radix__create_section_mapping(unsigned long start,
return -1;
}
- return create_physical_mapping(__pa(start), __pa(end), nid, prot);
+ return create_physical_mapping(__pa(start), __pa(end),
+ radix_mem_block_size, nid, prot);
}
int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index b5cc9b23cf02..0d233763441f 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -16,6 +16,7 @@
#include <asm/tlbflush.h>
#include <asm/trace.h>
#include <asm/cputhreads.h>
+#include <asm/plpar_wrappers.h>
#define RIC_FLUSH_TLB 0
#define RIC_FLUSH_PWC 1
@@ -694,7 +695,14 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
goto local;
}
- if (cputlb_use_tlbie()) {
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU;
+
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB,
+ H_RPTI_PAGE_ALL, 0, -1UL);
+ } else if (cputlb_use_tlbie()) {
if (mm_needs_flush_escalation(mm))
_tlbie_pid(pid, RIC_FLUSH_ALL);
else
@@ -727,7 +735,16 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
goto local;
}
}
- if (cputlb_use_tlbie())
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU;
+ unsigned long type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
+ H_RPTI_TYPE_PRT;
+
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, type,
+ H_RPTI_PAGE_ALL, 0, -1UL);
+ } else if (cputlb_use_tlbie())
_tlbie_pid(pid, RIC_FLUSH_ALL);
else
_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL);
@@ -760,7 +777,19 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
exit_flush_lazy_tlbs(mm);
goto local;
}
- if (cputlb_use_tlbie())
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt, pg_sizes, size;
+
+ tgt = H_RPTI_TARGET_CMMU;
+ pg_sizes = psize_to_rpti_pgsize(psize);
+ size = 1UL << mmu_psize_to_shift(psize);
+
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB,
+ pg_sizes, vmaddr,
+ vmaddr + size);
+ } else if (cputlb_use_tlbie())
_tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
else
_tlbiel_va_multicast(mm, vmaddr, pid, psize, RIC_FLUSH_TLB);
@@ -810,7 +839,14 @@ static inline void _tlbiel_kernel_broadcast(void)
*/
void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- if (cputlb_use_tlbie())
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU | H_RPTI_TARGET_NMMU;
+ unsigned long type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
+ H_RPTI_TYPE_PRT;
+
+ pseries_rpt_invalidate(0, tgt, type, H_RPTI_PAGE_ALL,
+ start, end);
+ } else if (cputlb_use_tlbie())
_tlbie_pid(0, RIC_FLUSH_ALL);
else
_tlbiel_kernel_broadcast();
@@ -864,7 +900,17 @@ is_local:
nr_pages > tlb_local_single_page_flush_ceiling);
}
- if (full) {
+ if (!mmu_has_feature(MMU_FTR_GTSE) && !local) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU;
+ unsigned long pg_sizes = psize_to_rpti_pgsize(mmu_virtual_psize);
+
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+ pg_sizes |= psize_to_rpti_pgsize(MMU_PAGE_2M);
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB, pg_sizes,
+ start, end);
+ } else if (full) {
if (local) {
_tlbiel_pid(pid, RIC_FLUSH_TLB);
} else {
@@ -1046,7 +1092,17 @@ is_local:
nr_pages > tlb_local_single_page_flush_ceiling);
}
- if (full) {
+ if (!mmu_has_feature(MMU_FTR_GTSE) && !local) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU;
+ unsigned long type = H_RPTI_TYPE_TLB;
+ unsigned long pg_sizes = psize_to_rpti_pgsize(psize);
+
+ if (also_pwc)
+ type |= H_RPTI_TYPE_PWC;
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, type, pg_sizes, start, end);
+ } else if (full) {
if (local) {
_tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
} else {
@@ -1111,7 +1167,19 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
exit_flush_lazy_tlbs(mm);
goto local;
}
- if (cputlb_use_tlbie())
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt, type, pg_sizes;
+
+ tgt = H_RPTI_TARGET_CMMU;
+ type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
+ H_RPTI_TYPE_PRT;
+ pg_sizes = psize_to_rpti_pgsize(mmu_virtual_psize);
+
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, type, pg_sizes,
+ addr, end);
+ } else if (cputlb_use_tlbie())
_tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
else
_tlbiel_va_range_multicast(mm,
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 5a5469eb3174..bf1717f8d5f4 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -171,6 +171,8 @@ void __init MMU_init(void)
btext_unmap();
#endif
+ kasan_mmu_init();
+
setup_kup();
/* Shortly after that, the entire linear mapping will be available */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index bc73abf0bc25..152aa0200cef 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -407,12 +407,15 @@ static void __init early_check_vec5(void)
if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
OV5_FEAT(OV5_RADIX_GTSE))) {
pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
- }
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_GTSE;
+ } else
+ cur_cpu_spec->mmu_features |= MMU_FTR_GTSE;
/* Do radix anyway - the hypervisor said we had to */
cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
} else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) {
/* Hypervisor only supports hash - disable radix */
cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_GTSE;
}
}
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 0760e1e754e4..019b0c0bbbf3 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -117,14 +117,27 @@ static void __init kasan_unmap_early_shadow_vmalloc(void)
kasan_update_early_region(k_start, k_end, __pte(0));
}
-static void __init kasan_mmu_init(void)
+void __init kasan_mmu_init(void)
{
int ret;
+
+ if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ||
+ IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+ ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+ if (ret)
+ panic("kasan: kasan_init_shadow_page_tables() failed");
+ }
+}
+
+void __init kasan_init(void)
+{
struct memblock_region *reg;
for_each_memblock(memory, reg) {
phys_addr_t base = reg->base;
phys_addr_t top = min(base + reg->size, total_lowmem);
+ int ret;
if (base >= top)
continue;
@@ -134,20 +147,6 @@ static void __init kasan_mmu_init(void)
panic("kasan: kasan_init_region() failed");
}
- if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ||
- IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
- ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END);
-
- if (ret)
- panic("kasan: kasan_init_shadow_page_tables() failed");
- }
-
-}
-
-void __init kasan_init(void)
-{
- kasan_mmu_init();
-
kasan_remap_early_shadow_ro();
clear_page(kasan_early_shadow_page);
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
index 4a75f2d9bf0e..bce0e5349978 100644
--- a/arch/powerpc/mm/nohash/kaslr_booke.c
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -14,6 +14,7 @@
#include <linux/memblock.h>
#include <linux/libfdt.h>
#include <linux/crash_core.h>
+#include <asm/cacheflush.h>
#include <asm/pgalloc.h>
#include <asm/prom.h>
#include <asm/kdump.h>
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9fcf2d195830..e437a9ac4956 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -984,28 +984,6 @@ static int __init early_numa(char *p)
}
early_param("numa", early_numa);
-/*
- * The platform can inform us through one of several mechanisms
- * (post-migration device tree updates, PRRN or VPHN) that the NUMA
- * assignment of a resource has changed. This controls whether we act
- * on that. Disabled by default.
- */
-static bool topology_updates_enabled;
-
-static int __init early_topology_updates(char *p)
-{
- if (!p)
- return 0;
-
- if (!strcmp(p, "on")) {
- pr_warn("Caution: enabling topology updates\n");
- topology_updates_enabled = true;
- }
-
- return 0;
-}
-early_param("topology_updates", early_topology_updates);
-
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Find the node associated with a hot added memory section for
@@ -1144,98 +1122,9 @@ u64 memory_hotplug_max(void)
/* Virtual Processor Home Node (VPHN) support */
#ifdef CONFIG_PPC_SPLPAR
-struct topology_update_data {
- struct topology_update_data *next;
- unsigned int cpu;
- int old_nid;
- int new_nid;
-};
-
-#define TOPOLOGY_DEF_TIMER_SECS 60
-
-static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
-static cpumask_t cpu_associativity_changes_mask;
-static int vphn_enabled;
-static int prrn_enabled;
-static void reset_topology_timer(void);
-static int topology_timer_secs = 1;
static int topology_inited;
/*
- * Change polling interval for associativity changes.
- */
-int timed_topology_update(int nsecs)
-{
- if (vphn_enabled) {
- if (nsecs > 0)
- topology_timer_secs = nsecs;
- else
- topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
-
- reset_topology_timer();
- }
-
- return 0;
-}
-
-/*
- * Store the current values of the associativity change counters in the
- * hypervisor.
- */
-static void setup_cpu_associativity_change_counters(void)
-{
- int cpu;
-
- /* The VPHN feature supports a maximum of 8 reference points */
- BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8);
-
- for_each_possible_cpu(cpu) {
- int i;
- u8 *counts = vphn_cpu_change_counts[cpu];
- volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
-
- for (i = 0; i < distance_ref_points_depth; i++)
- counts[i] = hypervisor_counts[i];
- }
-}
-
-/*
- * The hypervisor maintains a set of 8 associativity change counters in
- * the VPA of each cpu that correspond to the associativity levels in the
- * ibm,associativity-reference-points property. When an associativity
- * level changes, the corresponding counter is incremented.
- *
- * Set a bit in cpu_associativity_changes_mask for each cpu whose home
- * node associativity levels have changed.
- *
- * Returns the number of cpus with unhandled associativity changes.
- */
-static int update_cpu_associativity_changes_mask(void)
-{
- int cpu;
- cpumask_t *changes = &cpu_associativity_changes_mask;
-
- for_each_possible_cpu(cpu) {
- int i, changed = 0;
- u8 *counts = vphn_cpu_change_counts[cpu];
- volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
-
- for (i = 0; i < distance_ref_points_depth; i++) {
- if (hypervisor_counts[i] != counts[i]) {
- counts[i] = hypervisor_counts[i];
- changed = 1;
- }
- }
- if (changed) {
- cpumask_or(changes, changes, cpu_sibling_mask(cpu));
- cpu = cpu_last_thread_sibling(cpu);
- }
- }
-
- return cpumask_weight(changes);
-}
-
-/*
* Retrieve the new associativity information for a virtual processor's
* home node.
*/
@@ -1250,7 +1139,6 @@ static long vphn_get_associativity(unsigned long cpu,
switch (rc) {
case H_SUCCESS:
dbg("VPHN hcall succeeded. Reset polling...\n");
- timed_topology_update(0);
goto out;
case H_FUNCTION:
@@ -1269,8 +1157,6 @@ static long vphn_get_associativity(unsigned long cpu,
, rc);
break;
}
-
- stop_topology_update();
out:
return rc;
}
@@ -1314,380 +1200,8 @@ int find_and_online_cpu_nid(int cpu)
return new_nid;
}
-/*
- * Update the CPU maps and sysfs entries for a single CPU when its NUMA
- * characteristics change. This function doesn't perform any locking and is
- * only safe to call from stop_machine().
- */
-static int update_cpu_topology(void *data)
-{
- struct topology_update_data *update;
- unsigned long cpu;
-
- if (!data)
- return -EINVAL;
-
- cpu = smp_processor_id();
-
- for (update = data; update; update = update->next) {
- int new_nid = update->new_nid;
- if (cpu != update->cpu)
- continue;
-
- unmap_cpu_from_node(cpu);
- map_cpu_to_node(cpu, new_nid);
- set_cpu_numa_node(cpu, new_nid);
- set_cpu_numa_mem(cpu, local_memory_node(new_nid));
- vdso_getcpu_init();
- }
-
- return 0;
-}
-
-static int update_lookup_table(void *data)
-{
- struct topology_update_data *update;
-
- if (!data)
- return -EINVAL;
-
- /*
- * Upon topology update, the numa-cpu lookup table needs to be updated
- * for all threads in the core, including offline CPUs, to ensure that
- * future hotplug operations respect the cpu-to-node associativity
- * properly.
- */
- for (update = data; update; update = update->next) {
- int nid, base, j;
-
- nid = update->new_nid;
- base = cpu_first_thread_sibling(update->cpu);
-
- for (j = 0; j < threads_per_core; j++) {
- update_numa_cpu_lookup_table(base + j, nid);
- }
- }
-
- return 0;
-}
-
-/*
- * Update the node maps and sysfs entries for each cpu whose home node
- * has changed. Returns 1 when the topology has changed, and 0 otherwise.
- *
- * cpus_locked says whether we already hold cpu_hotplug_lock.
- */
-int numa_update_cpu_topology(bool cpus_locked)
-{
- unsigned int cpu, sibling, changed = 0;
- struct topology_update_data *updates, *ud;
- cpumask_t updated_cpus;
- struct device *dev;
- int weight, new_nid, i = 0;
-
- if (!prrn_enabled && !vphn_enabled && topology_inited)
- return 0;
-
- weight = cpumask_weight(&cpu_associativity_changes_mask);
- if (!weight)
- return 0;
-
- updates = kcalloc(weight, sizeof(*updates), GFP_KERNEL);
- if (!updates)
- return 0;
-
- cpumask_clear(&updated_cpus);
-
- for_each_cpu(cpu, &cpu_associativity_changes_mask) {
- /*
- * If siblings aren't flagged for changes, updates list
- * will be too short. Skip on this update and set for next
- * update.
- */
- if (!cpumask_subset(cpu_sibling_mask(cpu),
- &cpu_associativity_changes_mask)) {
- pr_info("Sibling bits not set for associativity "
- "change, cpu%d\n", cpu);
- cpumask_or(&cpu_associativity_changes_mask,
- &cpu_associativity_changes_mask,
- cpu_sibling_mask(cpu));
- cpu = cpu_last_thread_sibling(cpu);
- continue;
- }
-
- new_nid = find_and_online_cpu_nid(cpu);
-
- if (new_nid == numa_cpu_lookup_table[cpu]) {
- cpumask_andnot(&cpu_associativity_changes_mask,
- &cpu_associativity_changes_mask,
- cpu_sibling_mask(cpu));
- dbg("Assoc chg gives same node %d for cpu%d\n",
- new_nid, cpu);
- cpu = cpu_last_thread_sibling(cpu);
- continue;
- }
-
- for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
- ud = &updates[i++];
- ud->next = &updates[i];
- ud->cpu = sibling;
- ud->new_nid = new_nid;
- ud->old_nid = numa_cpu_lookup_table[sibling];
- cpumask_set_cpu(sibling, &updated_cpus);
- }
- cpu = cpu_last_thread_sibling(cpu);
- }
-
- /*
- * Prevent processing of 'updates' from overflowing array
- * where last entry filled in a 'next' pointer.
- */
- if (i)
- updates[i-1].next = NULL;
-
- pr_debug("Topology update for the following CPUs:\n");
- if (cpumask_weight(&updated_cpus)) {
- for (ud = &updates[0]; ud; ud = ud->next) {
- pr_debug("cpu %d moving from node %d "
- "to %d\n", ud->cpu,
- ud->old_nid, ud->new_nid);
- }
- }
-
- /*
- * In cases where we have nothing to update (because the updates list
- * is too short or because the new topology is same as the old one),
- * skip invoking update_cpu_topology() via stop-machine(). This is
- * necessary (and not just a fast-path optimization) since stop-machine
- * can end up electing a random CPU to run update_cpu_topology(), and
- * thus trick us into setting up incorrect cpu-node mappings (since
- * 'updates' is kzalloc()'ed).
- *
- * And for the similar reason, we will skip all the following updating.
- */
- if (!cpumask_weight(&updated_cpus))
- goto out;
-
- if (cpus_locked)
- stop_machine_cpuslocked(update_cpu_topology, &updates[0],
- &updated_cpus);
- else
- stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
-
- /*
- * Update the numa-cpu lookup table with the new mappings, even for
- * offline CPUs. It is best to perform this update from the stop-
- * machine context.
- */
- if (cpus_locked)
- stop_machine_cpuslocked(update_lookup_table, &updates[0],
- cpumask_of(raw_smp_processor_id()));
- else
- stop_machine(update_lookup_table, &updates[0],
- cpumask_of(raw_smp_processor_id()));
-
- for (ud = &updates[0]; ud; ud = ud->next) {
- unregister_cpu_under_node(ud->cpu, ud->old_nid);
- register_cpu_under_node(ud->cpu, ud->new_nid);
-
- dev = get_cpu_device(ud->cpu);
- if (dev)
- kobject_uevent(&dev->kobj, KOBJ_CHANGE);
- cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask);
- changed = 1;
- }
-
-out:
- kfree(updates);
- return changed;
-}
-
-int arch_update_cpu_topology(void)
-{
- return numa_update_cpu_topology(true);
-}
-
-static void topology_work_fn(struct work_struct *work)
-{
- rebuild_sched_domains();
-}
-static DECLARE_WORK(topology_work, topology_work_fn);
-
-static void topology_schedule_update(void)
-{
- schedule_work(&topology_work);
-}
-
-static void topology_timer_fn(struct timer_list *unused)
-{
- if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
- topology_schedule_update();
- else if (vphn_enabled) {
- if (update_cpu_associativity_changes_mask() > 0)
- topology_schedule_update();
- reset_topology_timer();
- }
-}
-static struct timer_list topology_timer;
-
-static void reset_topology_timer(void)
-{
- if (vphn_enabled)
- mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
-}
-
-#ifdef CONFIG_SMP
-
-static int dt_update_callback(struct notifier_block *nb,
- unsigned long action, void *data)
-{
- struct of_reconfig_data *update = data;
- int rc = NOTIFY_DONE;
-
- switch (action) {
- case OF_RECONFIG_UPDATE_PROPERTY:
- if (of_node_is_type(update->dn, "cpu") &&
- !of_prop_cmp(update->prop->name, "ibm,associativity")) {
- u32 core_id;
- of_property_read_u32(update->dn, "reg", &core_id);
- rc = dlpar_cpu_readd(core_id);
- rc = NOTIFY_OK;
- }
- break;
- }
-
- return rc;
-}
-
-static struct notifier_block dt_update_nb = {
- .notifier_call = dt_update_callback,
-};
-
-#endif
-
-/*
- * Start polling for associativity changes.
- */
-int start_topology_update(void)
-{
- int rc = 0;
-
- if (!topology_updates_enabled)
- return 0;
-
- if (firmware_has_feature(FW_FEATURE_PRRN)) {
- if (!prrn_enabled) {
- prrn_enabled = 1;
-#ifdef CONFIG_SMP
- rc = of_reconfig_notifier_register(&dt_update_nb);
-#endif
- }
- }
- if (firmware_has_feature(FW_FEATURE_VPHN) &&
- lppaca_shared_proc(get_lppaca())) {
- if (!vphn_enabled) {
- vphn_enabled = 1;
- setup_cpu_associativity_change_counters();
- timer_setup(&topology_timer, topology_timer_fn,
- TIMER_DEFERRABLE);
- reset_topology_timer();
- }
- }
-
- pr_info("Starting topology update%s%s\n",
- (prrn_enabled ? " prrn_enabled" : ""),
- (vphn_enabled ? " vphn_enabled" : ""));
-
- return rc;
-}
-
-/*
- * Disable polling for VPHN associativity changes.
- */
-int stop_topology_update(void)
-{
- int rc = 0;
-
- if (!topology_updates_enabled)
- return 0;
-
- if (prrn_enabled) {
- prrn_enabled = 0;
-#ifdef CONFIG_SMP
- rc = of_reconfig_notifier_unregister(&dt_update_nb);
-#endif
- }
- if (vphn_enabled) {
- vphn_enabled = 0;
- rc = del_timer_sync(&topology_timer);
- }
-
- pr_info("Stopping topology update\n");
-
- return rc;
-}
-
-int prrn_is_enabled(void)
-{
- return prrn_enabled;
-}
-
-static int topology_read(struct seq_file *file, void *v)
-{
- if (vphn_enabled || prrn_enabled)
- seq_puts(file, "on\n");
- else
- seq_puts(file, "off\n");
-
- return 0;
-}
-
-static int topology_open(struct inode *inode, struct file *file)
-{
- return single_open(file, topology_read, NULL);
-}
-
-static ssize_t topology_write(struct file *file, const char __user *buf,
- size_t count, loff_t *off)
-{
- char kbuf[4]; /* "on" or "off" plus null. */
- int read_len;
-
- read_len = count < 3 ? count : 3;
- if (copy_from_user(kbuf, buf, read_len))
- return -EINVAL;
-
- kbuf[read_len] = '\0';
-
- if (!strncmp(kbuf, "on", 2)) {
- topology_updates_enabled = true;
- start_topology_update();
- } else if (!strncmp(kbuf, "off", 3)) {
- stop_topology_update();
- topology_updates_enabled = false;
- } else
- return -EINVAL;
-
- return count;
-}
-
-static const struct proc_ops topology_proc_ops = {
- .proc_read = seq_read,
- .proc_write = topology_write,
- .proc_open = topology_open,
- .proc_release = single_release,
-};
-
static int topology_update_init(void)
{
- start_topology_update();
-
- if (vphn_enabled)
- topology_schedule_update();
-
- if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_proc_ops))
- return -ENOMEM;
-
topology_inited = 1;
return 0;
}
diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
index ee4bd6d38602..97ae4935da79 100644
--- a/arch/powerpc/mm/pgtable-frag.c
+++ b/arch/powerpc/mm/pgtable-frag.c
@@ -110,6 +110,9 @@ void pte_fragment_free(unsigned long *table, int kernel)
{
struct page *page = virt_to_page(table);
+ if (PageReserved(page))
+ return free_reserved_page(page);
+
BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
if (atomic_dec_and_test(&page->pt_frag_refcount)) {
if (!kernel)
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index a2c33efc7ce8..5b8bd34cd3a1 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -258,7 +258,7 @@ static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *
for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) {
lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes);
- if (lpar_rc != H_SUCCESS)
+ if (lpar_rc)
continue;
for (j = 0; j < 4; j++) {
if (HPTE_V_COMPARE(ptes[j].v, want_v) &&
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 55d4377ccfae..d0a67a1bbaf1 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -11,6 +11,7 @@
#ifndef __ASSEMBLY__
#include <asm/types.h>
+#include <asm/ppc-opcode.h>
#ifdef PPC64_ELF_ABI_v1
#define FUNCTION_DESCR_SIZE 24
@@ -18,167 +19,10 @@
#define FUNCTION_DESCR_SIZE 0
#endif
-/*
- * 16-bit immediate helper macros: HA() is for use with sign-extending instrs
- * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the
- * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000).
- */
-#define IMM_H(i) ((uintptr_t)(i)>>16)
-#define IMM_HA(i) (((uintptr_t)(i)>>16) + \
- (((uintptr_t)(i) & 0x8000) >> 15))
-#define IMM_L(i) ((uintptr_t)(i) & 0xffff)
-
#define PLANT_INSTR(d, idx, instr) \
do { if (d) { (d)[idx] = instr; } idx++; } while (0)
#define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr)
-#define PPC_NOP() EMIT(PPC_INST_NOP)
-#define PPC_BLR() EMIT(PPC_INST_BLR)
-#define PPC_BLRL() EMIT(PPC_INST_BLRL)
-#define PPC_MTLR(r) EMIT(PPC_INST_MTLR | ___PPC_RT(r))
-#define PPC_BCTR() EMIT(PPC_INST_BCTR)
-#define PPC_MTCTR(r) EMIT(PPC_INST_MTCTR | ___PPC_RT(r))
-#define PPC_ADDI(d, a, i) EMIT(PPC_INST_ADDI | ___PPC_RT(d) | \
- ___PPC_RA(a) | IMM_L(i))
-#define PPC_MR(d, a) PPC_OR(d, a, a)
-#define PPC_LI(r, i) PPC_ADDI(r, 0, i)
-#define PPC_ADDIS(d, a, i) EMIT(PPC_INST_ADDIS | \
- ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i))
-#define PPC_LIS(r, i) PPC_ADDIS(r, 0, i)
-#define PPC_STD(r, base, i) EMIT(PPC_INST_STD | ___PPC_RS(r) | \
- ___PPC_RA(base) | ((i) & 0xfffc))
-#define PPC_STDX(r, base, b) EMIT(PPC_INST_STDX | ___PPC_RS(r) | \
- ___PPC_RA(base) | ___PPC_RB(b))
-#define PPC_STDU(r, base, i) EMIT(PPC_INST_STDU | ___PPC_RS(r) | \
- ___PPC_RA(base) | ((i) & 0xfffc))
-#define PPC_STW(r, base, i) EMIT(PPC_INST_STW | ___PPC_RS(r) | \
- ___PPC_RA(base) | IMM_L(i))
-#define PPC_STWU(r, base, i) EMIT(PPC_INST_STWU | ___PPC_RS(r) | \
- ___PPC_RA(base) | IMM_L(i))
-#define PPC_STH(r, base, i) EMIT(PPC_INST_STH | ___PPC_RS(r) | \
- ___PPC_RA(base) | IMM_L(i))
-#define PPC_STB(r, base, i) EMIT(PPC_INST_STB | ___PPC_RS(r) | \
- ___PPC_RA(base) | IMM_L(i))
-
-#define PPC_LBZ(r, base, i) EMIT(PPC_INST_LBZ | ___PPC_RT(r) | \
- ___PPC_RA(base) | IMM_L(i))
-#define PPC_LD(r, base, i) EMIT(PPC_INST_LD | ___PPC_RT(r) | \
- ___PPC_RA(base) | ((i) & 0xfffc))
-#define PPC_LDX(r, base, b) EMIT(PPC_INST_LDX | ___PPC_RT(r) | \
- ___PPC_RA(base) | ___PPC_RB(b))
-#define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | ___PPC_RT(r) | \
- ___PPC_RA(base) | IMM_L(i))
-#define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | ___PPC_RT(r) | \
- ___PPC_RA(base) | IMM_L(i))
-#define PPC_LHBRX(r, base, b) EMIT(PPC_INST_LHBRX | ___PPC_RT(r) | \
- ___PPC_RA(base) | ___PPC_RB(b))
-#define PPC_LDBRX(r, base, b) EMIT(PPC_INST_LDBRX | ___PPC_RT(r) | \
- ___PPC_RA(base) | ___PPC_RB(b))
-
-#define PPC_BPF_LDARX(t, a, b, eh) EMIT(PPC_INST_LDARX | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b) | \
- __PPC_EH(eh))
-#define PPC_BPF_LWARX(t, a, b, eh) EMIT(PPC_INST_LWARX | ___PPC_RT(t) | \
- ___PPC_RA(a) | ___PPC_RB(b) | \
- __PPC_EH(eh))
-#define PPC_BPF_STWCX(s, a, b) EMIT(PPC_INST_STWCX | ___PPC_RS(s) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_BPF_STDCX(s, a, b) EMIT(PPC_INST_STDCX | ___PPC_RS(s) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i))
-#define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i))
-#define PPC_CMPW(a, b) EMIT(PPC_INST_CMPW | ___PPC_RA(a) | \
- ___PPC_RB(b))
-#define PPC_CMPD(a, b) EMIT(PPC_INST_CMPD | ___PPC_RA(a) | \
- ___PPC_RB(b))
-#define PPC_CMPLWI(a, i) EMIT(PPC_INST_CMPLWI | ___PPC_RA(a) | IMM_L(i))
-#define PPC_CMPLDI(a, i) EMIT(PPC_INST_CMPLDI | ___PPC_RA(a) | IMM_L(i))
-#define PPC_CMPLW(a, b) EMIT(PPC_INST_CMPLW | ___PPC_RA(a) | \
- ___PPC_RB(b))
-#define PPC_CMPLD(a, b) EMIT(PPC_INST_CMPLD | ___PPC_RA(a) | \
- ___PPC_RB(b))
-
-#define PPC_SUB(d, a, b) EMIT(PPC_INST_SUB | ___PPC_RT(d) | \
- ___PPC_RB(a) | ___PPC_RA(b))
-#define PPC_ADD(d, a, b) EMIT(PPC_INST_ADD | ___PPC_RT(d) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_MULD(d, a, b) EMIT(PPC_INST_MULLD | ___PPC_RT(d) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_MULW(d, a, b) EMIT(PPC_INST_MULLW | ___PPC_RT(d) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_MULHWU(d, a, b) EMIT(PPC_INST_MULHWU | ___PPC_RT(d) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_MULI(d, a, i) EMIT(PPC_INST_MULLI | ___PPC_RT(d) | \
- ___PPC_RA(a) | IMM_L(i))
-#define PPC_DIVWU(d, a, b) EMIT(PPC_INST_DIVWU | ___PPC_RT(d) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_DIVDU(d, a, b) EMIT(PPC_INST_DIVDU | ___PPC_RT(d) | \
- ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_AND(d, a, b) EMIT(PPC_INST_AND | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(b))
-#define PPC_ANDI(d, a, i) EMIT(PPC_INST_ANDI | ___PPC_RA(d) | \
- ___PPC_RS(a) | IMM_L(i))
-#define PPC_AND_DOT(d, a, b) EMIT(PPC_INST_ANDDOT | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(b))
-#define PPC_OR(d, a, b) EMIT(PPC_INST_OR | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(b))
-#define PPC_MR(d, a) PPC_OR(d, a, a)
-#define PPC_ORI(d, a, i) EMIT(PPC_INST_ORI | ___PPC_RA(d) | \
- ___PPC_RS(a) | IMM_L(i))
-#define PPC_ORIS(d, a, i) EMIT(PPC_INST_ORIS | ___PPC_RA(d) | \
- ___PPC_RS(a) | IMM_L(i))
-#define PPC_XOR(d, a, b) EMIT(PPC_INST_XOR | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(b))
-#define PPC_XORI(d, a, i) EMIT(PPC_INST_XORI | ___PPC_RA(d) | \
- ___PPC_RS(a) | IMM_L(i))
-#define PPC_XORIS(d, a, i) EMIT(PPC_INST_XORIS | ___PPC_RA(d) | \
- ___PPC_RS(a) | IMM_L(i))
-#define PPC_EXTSW(d, a) EMIT(PPC_INST_EXTSW | ___PPC_RA(d) | \
- ___PPC_RS(a))
-#define PPC_SLW(d, a, s) EMIT(PPC_INST_SLW | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(s))
-#define PPC_SLD(d, a, s) EMIT(PPC_INST_SLD | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(s))
-#define PPC_SRW(d, a, s) EMIT(PPC_INST_SRW | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(s))
-#define PPC_SRAW(d, a, s) EMIT(PPC_INST_SRAW | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(s))
-#define PPC_SRAWI(d, a, i) EMIT(PPC_INST_SRAWI | ___PPC_RA(d) | \
- ___PPC_RS(a) | __PPC_SH(i))
-#define PPC_SRD(d, a, s) EMIT(PPC_INST_SRD | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(s))
-#define PPC_SRAD(d, a, s) EMIT(PPC_INST_SRAD | ___PPC_RA(d) | \
- ___PPC_RS(a) | ___PPC_RB(s))
-#define PPC_SRADI(d, a, i) EMIT(PPC_INST_SRADI | ___PPC_RA(d) | \
- ___PPC_RS(a) | __PPC_SH64(i))
-#define PPC_RLWINM(d, a, i, mb, me) EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \
- ___PPC_RS(a) | __PPC_SH(i) | \
- __PPC_MB(mb) | __PPC_ME(me))
-#define PPC_RLWINM_DOT(d, a, i, mb, me) EMIT(PPC_INST_RLWINM_DOT | \
- ___PPC_RA(d) | ___PPC_RS(a) | \
- __PPC_SH(i) | __PPC_MB(mb) | \
- __PPC_ME(me))
-#define PPC_RLWIMI(d, a, i, mb, me) EMIT(PPC_INST_RLWIMI | ___PPC_RA(d) | \
- ___PPC_RS(a) | __PPC_SH(i) | \
- __PPC_MB(mb) | __PPC_ME(me))
-#define PPC_RLDICL(d, a, i, mb) EMIT(PPC_INST_RLDICL | ___PPC_RA(d) | \
- ___PPC_RS(a) | __PPC_SH64(i) | \
- __PPC_MB64(mb))
-#define PPC_RLDICR(d, a, i, me) EMIT(PPC_INST_RLDICR | ___PPC_RA(d) | \
- ___PPC_RS(a) | __PPC_SH64(i) | \
- __PPC_ME64(me))
-
-/* slwi = rlwinm Rx, Ry, n, 0, 31-n */
-#define PPC_SLWI(d, a, i) PPC_RLWINM(d, a, i, 0, 31-(i))
-/* srwi = rlwinm Rx, Ry, 32-n, n, 31 */
-#define PPC_SRWI(d, a, i) PPC_RLWINM(d, a, 32-(i), i, 31)
-/* sldi = rldicr Rx, Ry, n, 63-n */
-#define PPC_SLDI(d, a, i) PPC_RLDICR(d, a, i, 63-(i))
-/* sldi = rldicl Rx, Ry, 64-n, n */
-#define PPC_SRDI(d, a, i) PPC_RLDICL(d, a, 64-(i), i)
-
-#define PPC_NEG(d, a) EMIT(PPC_INST_NEG | ___PPC_RT(d) | ___PPC_RA(a))
-
/* Long jump; (unconditional 'branch') */
#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \
(((dest) - (ctx->idx * 4)) & 0x03fffffc))
@@ -191,11 +35,11 @@
#define PPC_LI32(d, i) do { \
if ((int)(uintptr_t)(i) >= -32768 && \
(int)(uintptr_t)(i) < 32768) \
- PPC_LI(d, i); \
+ EMIT(PPC_RAW_LI(d, i)); \
else { \
- PPC_LIS(d, IMM_H(i)); \
+ EMIT(PPC_RAW_LIS(d, IMM_H(i))); \
if (IMM_L(i)) \
- PPC_ORI(d, d, IMM_L(i)); \
+ EMIT(PPC_RAW_ORI(d, d, IMM_L(i))); \
} } while(0)
#define PPC_LI64(d, i) do { \
@@ -204,19 +48,21 @@
PPC_LI32(d, i); \
else { \
if (!((uintptr_t)(i) & 0xffff800000000000ULL)) \
- PPC_LI(d, ((uintptr_t)(i) >> 32) & 0xffff); \
+ EMIT(PPC_RAW_LI(d, ((uintptr_t)(i) >> 32) & \
+ 0xffff)); \
else { \
- PPC_LIS(d, ((uintptr_t)(i) >> 48)); \
+ EMIT(PPC_RAW_LIS(d, ((uintptr_t)(i) >> 48))); \
if ((uintptr_t)(i) & 0x0000ffff00000000ULL) \
- PPC_ORI(d, d, \
- ((uintptr_t)(i) >> 32) & 0xffff); \
+ EMIT(PPC_RAW_ORI(d, d, \
+ ((uintptr_t)(i) >> 32) & 0xffff)); \
} \
- PPC_SLDI(d, d, 32); \
+ EMIT(PPC_RAW_SLDI(d, d, 32)); \
if ((uintptr_t)(i) & 0x00000000ffff0000ULL) \
- PPC_ORIS(d, d, \
- ((uintptr_t)(i) >> 16) & 0xffff); \
+ EMIT(PPC_RAW_ORIS(d, d, \
+ ((uintptr_t)(i) >> 16) & 0xffff)); \
if ((uintptr_t)(i) & 0x000000000000ffffULL) \
- PPC_ORI(d, d, (uintptr_t)(i) & 0xffff); \
+ EMIT(PPC_RAW_ORI(d, d, (uintptr_t)(i) & \
+ 0xffff)); \
} } while (0)
#ifdef CONFIG_PPC64
@@ -240,7 +86,7 @@ static inline bool is_nearbranch(int offset)
#define PPC_BCC(cond, dest) do { \
if (is_nearbranch((dest) - (ctx->idx * 4))) { \
PPC_BCC_SHORT(cond, dest); \
- PPC_NOP(); \
+ EMIT(PPC_RAW_NOP()); \
} else { \
/* Flip the 'T or F' bit to invert comparison */ \
PPC_BCC_SHORT(cond ^ COND_CMP_TRUE, (ctx->idx+2)*4); \
diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h
index 4ec2a9f14f84..448dfd4d98e1 100644
--- a/arch/powerpc/net/bpf_jit32.h
+++ b/arch/powerpc/net/bpf_jit32.h
@@ -72,21 +72,21 @@ DECLARE_LOAD_FUNC(sk_load_half);
DECLARE_LOAD_FUNC(sk_load_byte);
DECLARE_LOAD_FUNC(sk_load_byte_msh);
-#define PPC_LBZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LBZ(r, base, i); \
- else { PPC_ADDIS(r, base, IMM_HA(i)); \
- PPC_LBZ(r, r, IMM_L(i)); } } while(0)
+#define PPC_LBZ_OFFS(r, base, i) do { if ((i) < 32768) EMIT(PPC_RAW_LBZ(r, base, i)); \
+ else { EMIT(PPC_RAW_ADDIS(r, base, IMM_HA(i))); \
+ EMIT(PPC_RAW_LBZ(r, r, IMM_L(i))); } } while(0)
-#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i); \
- else { PPC_ADDIS(r, base, IMM_HA(i)); \
- PPC_LD(r, r, IMM_L(i)); } } while(0)
+#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) EMIT(PPC_RAW_LD(r, base, i)); \
+ else { EMIT(PPC_RAW_ADDIS(r, base, IMM_HA(i))); \
+ EMIT(PPC_RAW_LD(r, r, IMM_L(i))); } } while(0)
-#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LWZ(r, base, i); \
- else { PPC_ADDIS(r, base, IMM_HA(i)); \
- PPC_LWZ(r, r, IMM_L(i)); } } while(0)
+#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) EMIT(PPC_RAW_LWZ(r, base, i)); \
+ else { EMIT(PPC_RAW_ADDIS(r, base, IMM_HA(i))); \
+ EMIT(PPC_RAW_LWZ(r, r, IMM_L(i))); } } while(0)
-#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LHZ(r, base, i); \
- else { PPC_ADDIS(r, base, IMM_HA(i)); \
- PPC_LHZ(r, r, IMM_L(i)); } } while(0)
+#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) EMIT(PPC_RAW_LHZ(r, base, i)); \
+ else { EMIT(PPC_RAW_ADDIS(r, base, IMM_HA(i))); \
+ EMIT(PPC_RAW_LHZ(r, r, IMM_L(i))); } } while(0)
#ifdef CONFIG_PPC64
#define PPC_LL_OFFS(r, base, i) do { PPC_LD_OFFS(r, base, i); } while(0)
@@ -107,20 +107,20 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
} while(0)
#endif
#else
-#define PPC_BPF_LOAD_CPU(r) do { PPC_LI(r, 0); } while(0)
+#define PPC_BPF_LOAD_CPU(r) do { EMIT(PPC_RAW_LI(r, 0)); } while(0)
#endif
#define PPC_LHBRX_OFFS(r, base, i) \
- do { PPC_LI32(r, i); PPC_LHBRX(r, r, base); } while(0)
+ do { PPC_LI32(r, i); EMIT(PPC_RAW_LHBRX(r, r, base)); } while(0)
#ifdef __LITTLE_ENDIAN__
#define PPC_NTOHS_OFFS(r, base, i) PPC_LHBRX_OFFS(r, base, i)
#else
#define PPC_NTOHS_OFFS(r, base, i) PPC_LHZ_OFFS(r, base, i)
#endif
-#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0)
-#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0)
-#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0)
+#define PPC_BPF_LL(r, base, i) do { EMIT(PPC_RAW_LWZ(r, base, i)); } while(0)
+#define PPC_BPF_STL(r, base, i) do { EMIT(PPC_RAW_STW(r, base, i)); } while(0)
+#define PPC_BPF_STLU(r, base, i) do { EMIT(PPC_RAW_STWU(r, base, i)); } while(0)
#define SEEN_DATAREF 0x10000 /* might call external helpers */
#define SEEN_XREG 0x20000 /* X reg is used */
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index cf3a7e337f02..2e33c6673ff9 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -70,19 +70,21 @@ static const int b2p[] = {
*/
#define PPC_BPF_LL(r, base, i) do { \
if ((i) % 4) { \
- PPC_LI(b2p[TMP_REG_2], (i)); \
- PPC_LDX(r, base, b2p[TMP_REG_2]); \
+ EMIT(PPC_RAW_LI(b2p[TMP_REG_2], (i)));\
+ EMIT(PPC_RAW_LDX(r, base, \
+ b2p[TMP_REG_2])); \
} else \
- PPC_LD(r, base, i); \
+ EMIT(PPC_RAW_LD(r, base, i)); \
} while(0)
#define PPC_BPF_STL(r, base, i) do { \
if ((i) % 4) { \
- PPC_LI(b2p[TMP_REG_2], (i)); \
- PPC_STDX(r, base, b2p[TMP_REG_2]); \
+ EMIT(PPC_RAW_LI(b2p[TMP_REG_2], (i)));\
+ EMIT(PPC_RAW_STDX(r, base, \
+ b2p[TMP_REG_2])); \
} else \
- PPC_STD(r, base, i); \
+ EMIT(PPC_RAW_STD(r, base, i)); \
} while(0)
-#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0)
+#define PPC_BPF_STLU(r, base, i) do { EMIT(PPC_RAW_STDU(r, base, i)); } while(0)
#define SEEN_FUNC 0x1000 /* might call external helpers */
#define SEEN_STACK 0x2000 /* uses BPF stack */
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 0acc9d5fb19e..16d09b36fe06 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -61,7 +61,7 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image,
PPC_LWZ_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff,
data_len));
PPC_LWZ_OFFS(r_HL, r_skb, offsetof(struct sk_buff, len));
- PPC_SUB(r_HL, r_HL, r_scratch1);
+ EMIT(PPC_RAW_SUB(r_HL, r_HL, r_scratch1));
PPC_LL_OFFS(r_D, r_skb, offsetof(struct sk_buff, data));
}
@@ -70,12 +70,12 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image,
* TODO: Could also detect whether first instr. sets X and
* avoid this (as below, with A).
*/
- PPC_LI(r_X, 0);
+ EMIT(PPC_RAW_LI(r_X, 0));
}
/* make sure we dont leak kernel information to user */
if (bpf_needs_clear_a(&filter[0]))
- PPC_LI(r_A, 0);
+ EMIT(PPC_RAW_LI(r_A, 0));
}
static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
@@ -83,10 +83,10 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
int i;
if (ctx->seen & (SEEN_MEM | SEEN_DATAREF)) {
- PPC_ADDI(1, 1, BPF_PPC_STACKFRAME);
+ EMIT(PPC_RAW_ADDI(1, 1, BPF_PPC_STACKFRAME));
if (ctx->seen & SEEN_DATAREF) {
PPC_BPF_LL(0, 1, PPC_LR_STKOFF);
- PPC_MTLR(0);
+ EMIT(PPC_RAW_MTLR(0));
PPC_BPF_LL(r_D, 1, -(REG_SZ*(32-r_D)));
PPC_BPF_LL(r_HL, 1, -(REG_SZ*(32-r_HL)));
}
@@ -100,7 +100,7 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
}
/* The RETs have left a return value in R3. */
- PPC_BLR();
+ EMIT(PPC_RAW_BLR());
}
#define CHOOSE_LOAD_FUNC(K, func) \
@@ -134,124 +134,124 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
/*** ALU ops ***/
case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */
ctx->seen |= SEEN_XREG;
- PPC_ADD(r_A, r_A, r_X);
+ EMIT(PPC_RAW_ADD(r_A, r_A, r_X));
break;
case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */
if (!K)
break;
- PPC_ADDI(r_A, r_A, IMM_L(K));
+ EMIT(PPC_RAW_ADDI(r_A, r_A, IMM_L(K)));
if (K >= 32768)
- PPC_ADDIS(r_A, r_A, IMM_HA(K));
+ EMIT(PPC_RAW_ADDIS(r_A, r_A, IMM_HA(K)));
break;
case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */
ctx->seen |= SEEN_XREG;
- PPC_SUB(r_A, r_A, r_X);
+ EMIT(PPC_RAW_SUB(r_A, r_A, r_X));
break;
case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */
if (!K)
break;
- PPC_ADDI(r_A, r_A, IMM_L(-K));
+ EMIT(PPC_RAW_ADDI(r_A, r_A, IMM_L(-K)));
if (K >= 32768)
- PPC_ADDIS(r_A, r_A, IMM_HA(-K));
+ EMIT(PPC_RAW_ADDIS(r_A, r_A, IMM_HA(-K)));
break;
case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */
ctx->seen |= SEEN_XREG;
- PPC_MULW(r_A, r_A, r_X);
+ EMIT(PPC_RAW_MULW(r_A, r_A, r_X));
break;
case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
if (K < 32768)
- PPC_MULI(r_A, r_A, K);
+ EMIT(PPC_RAW_MULI(r_A, r_A, K));
else {
PPC_LI32(r_scratch1, K);
- PPC_MULW(r_A, r_A, r_scratch1);
+ EMIT(PPC_RAW_MULW(r_A, r_A, r_scratch1));
}
break;
case BPF_ALU | BPF_MOD | BPF_X: /* A %= X; */
case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */
ctx->seen |= SEEN_XREG;
- PPC_CMPWI(r_X, 0);
+ EMIT(PPC_RAW_CMPWI(r_X, 0));
if (ctx->pc_ret0 != -1) {
PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]);
} else {
PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12);
- PPC_LI(r_ret, 0);
+ EMIT(PPC_RAW_LI(r_ret, 0));
PPC_JMP(exit_addr);
}
if (code == (BPF_ALU | BPF_MOD | BPF_X)) {
- PPC_DIVWU(r_scratch1, r_A, r_X);
- PPC_MULW(r_scratch1, r_X, r_scratch1);
- PPC_SUB(r_A, r_A, r_scratch1);
+ EMIT(PPC_RAW_DIVWU(r_scratch1, r_A, r_X));
+ EMIT(PPC_RAW_MULW(r_scratch1, r_X, r_scratch1));
+ EMIT(PPC_RAW_SUB(r_A, r_A, r_scratch1));
} else {
- PPC_DIVWU(r_A, r_A, r_X);
+ EMIT(PPC_RAW_DIVWU(r_A, r_A, r_X));
}
break;
case BPF_ALU | BPF_MOD | BPF_K: /* A %= K; */
PPC_LI32(r_scratch2, K);
- PPC_DIVWU(r_scratch1, r_A, r_scratch2);
- PPC_MULW(r_scratch1, r_scratch2, r_scratch1);
- PPC_SUB(r_A, r_A, r_scratch1);
+ EMIT(PPC_RAW_DIVWU(r_scratch1, r_A, r_scratch2));
+ EMIT(PPC_RAW_MULW(r_scratch1, r_scratch2, r_scratch1));
+ EMIT(PPC_RAW_SUB(r_A, r_A, r_scratch1));
break;
case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */
if (K == 1)
break;
PPC_LI32(r_scratch1, K);
- PPC_DIVWU(r_A, r_A, r_scratch1);
+ EMIT(PPC_RAW_DIVWU(r_A, r_A, r_scratch1));
break;
case BPF_ALU | BPF_AND | BPF_X:
ctx->seen |= SEEN_XREG;
- PPC_AND(r_A, r_A, r_X);
+ EMIT(PPC_RAW_AND(r_A, r_A, r_X));
break;
case BPF_ALU | BPF_AND | BPF_K:
if (!IMM_H(K))
- PPC_ANDI(r_A, r_A, K);
+ EMIT(PPC_RAW_ANDI(r_A, r_A, K));
else {
PPC_LI32(r_scratch1, K);
- PPC_AND(r_A, r_A, r_scratch1);
+ EMIT(PPC_RAW_AND(r_A, r_A, r_scratch1));
}
break;
case BPF_ALU | BPF_OR | BPF_X:
ctx->seen |= SEEN_XREG;
- PPC_OR(r_A, r_A, r_X);
+ EMIT(PPC_RAW_OR(r_A, r_A, r_X));
break;
case BPF_ALU | BPF_OR | BPF_K:
if (IMM_L(K))
- PPC_ORI(r_A, r_A, IMM_L(K));
+ EMIT(PPC_RAW_ORI(r_A, r_A, IMM_L(K)));
if (K >= 65536)
- PPC_ORIS(r_A, r_A, IMM_H(K));
+ EMIT(PPC_RAW_ORIS(r_A, r_A, IMM_H(K)));
break;
case BPF_ANC | SKF_AD_ALU_XOR_X:
case BPF_ALU | BPF_XOR | BPF_X: /* A ^= X */
ctx->seen |= SEEN_XREG;
- PPC_XOR(r_A, r_A, r_X);
+ EMIT(PPC_RAW_XOR(r_A, r_A, r_X));
break;
case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */
if (IMM_L(K))
- PPC_XORI(r_A, r_A, IMM_L(K));
+ EMIT(PPC_RAW_XORI(r_A, r_A, IMM_L(K)));
if (K >= 65536)
- PPC_XORIS(r_A, r_A, IMM_H(K));
+ EMIT(PPC_RAW_XORIS(r_A, r_A, IMM_H(K)));
break;
case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */
ctx->seen |= SEEN_XREG;
- PPC_SLW(r_A, r_A, r_X);
+ EMIT(PPC_RAW_SLW(r_A, r_A, r_X));
break;
case BPF_ALU | BPF_LSH | BPF_K:
if (K == 0)
break;
else
- PPC_SLWI(r_A, r_A, K);
+ EMIT(PPC_RAW_SLWI(r_A, r_A, K));
break;
case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */
ctx->seen |= SEEN_XREG;
- PPC_SRW(r_A, r_A, r_X);
+ EMIT(PPC_RAW_SRW(r_A, r_A, r_X));
break;
case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */
if (K == 0)
break;
else
- PPC_SRWI(r_A, r_A, K);
+ EMIT(PPC_RAW_SRWI(r_A, r_A, K));
break;
case BPF_ALU | BPF_NEG:
- PPC_NEG(r_A, r_A);
+ EMIT(PPC_RAW_NEG(r_A, r_A));
break;
case BPF_RET | BPF_K:
PPC_LI32(r_ret, K);
@@ -277,24 +277,24 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
if (ctx->seen)
PPC_JMP(exit_addr);
else
- PPC_BLR();
+ EMIT(PPC_RAW_BLR());
}
break;
case BPF_RET | BPF_A:
- PPC_MR(r_ret, r_A);
+ EMIT(PPC_RAW_MR(r_ret, r_A));
if (i != flen - 1) {
if (ctx->seen)
PPC_JMP(exit_addr);
else
- PPC_BLR();
+ EMIT(PPC_RAW_BLR());
}
break;
case BPF_MISC | BPF_TAX: /* X = A */
- PPC_MR(r_X, r_A);
+ EMIT(PPC_RAW_MR(r_X, r_A));
break;
case BPF_MISC | BPF_TXA: /* A = X */
ctx->seen |= SEEN_XREG;
- PPC_MR(r_A, r_X);
+ EMIT(PPC_RAW_MR(r_A, r_X));
break;
/*** Constant loads/M[] access ***/
@@ -305,19 +305,19 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
PPC_LI32(r_X, K);
break;
case BPF_LD | BPF_MEM: /* A = mem[K] */
- PPC_MR(r_A, r_M + (K & 0xf));
+ EMIT(PPC_RAW_MR(r_A, r_M + (K & 0xf)));
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_LDX | BPF_MEM: /* X = mem[K] */
- PPC_MR(r_X, r_M + (K & 0xf));
+ EMIT(PPC_RAW_MR(r_X, r_M + (K & 0xf)));
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_ST: /* mem[K] = A */
- PPC_MR(r_M + (K & 0xf), r_A);
+ EMIT(PPC_RAW_MR(r_M + (K & 0xf), r_A));
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_STX: /* mem[K] = X */
- PPC_MR(r_M + (K & 0xf), r_X);
+ EMIT(PPC_RAW_MR(r_M + (K & 0xf), r_X));
ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */
@@ -346,13 +346,13 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
type) != 2);
PPC_LL_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff,
dev));
- PPC_CMPDI(r_scratch1, 0);
+ EMIT(PPC_RAW_CMPDI(r_scratch1, 0));
if (ctx->pc_ret0 != -1) {
PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]);
} else {
/* Exit, returning 0; first pass hits here. */
PPC_BCC_SHORT(COND_NE, ctx->idx * 4 + 12);
- PPC_LI(r_ret, 0);
+ EMIT(PPC_RAW_LI(r_ret, 0));
PPC_JMP(exit_addr);
}
if (code == (BPF_ANC | SKF_AD_IFINDEX)) {
@@ -383,9 +383,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
PPC_LBZ_OFFS(r_A, r_skb, PKT_VLAN_PRESENT_OFFSET());
if (PKT_VLAN_PRESENT_BIT)
- PPC_SRWI(r_A, r_A, PKT_VLAN_PRESENT_BIT);
+ EMIT(PPC_RAW_SRWI(r_A, r_A, PKT_VLAN_PRESENT_BIT));
if (PKT_VLAN_PRESENT_BIT < 7)
- PPC_ANDI(r_A, r_A, 1);
+ EMIT(PPC_RAW_ANDI(r_A, r_A, 1));
break;
case BPF_ANC | SKF_AD_QUEUE:
BUILD_BUG_ON(sizeof_field(struct sk_buff,
@@ -395,8 +395,8 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
break;
case BPF_ANC | SKF_AD_PKTTYPE:
PPC_LBZ_OFFS(r_A, r_skb, PKT_TYPE_OFFSET());
- PPC_ANDI(r_A, r_A, PKT_TYPE_MAX);
- PPC_SRWI(r_A, r_A, 5);
+ EMIT(PPC_RAW_ANDI(r_A, r_A, PKT_TYPE_MAX));
+ EMIT(PPC_RAW_SRWI(r_A, r_A, 5));
break;
case BPF_ANC | SKF_AD_CPU:
PPC_BPF_LOAD_CPU(r_A);
@@ -414,9 +414,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
/* Load from [K]. */
ctx->seen |= SEEN_DATAREF;
PPC_FUNC_ADDR(r_scratch1, func);
- PPC_MTLR(r_scratch1);
+ EMIT(PPC_RAW_MTLR(r_scratch1));
PPC_LI32(r_addr, K);
- PPC_BLRL();
+ EMIT(PPC_RAW_BLRL());
/*
* Helper returns 'lt' condition on error, and an
* appropriate return value in r3
@@ -440,11 +440,11 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
*/
ctx->seen |= SEEN_DATAREF | SEEN_XREG;
PPC_FUNC_ADDR(r_scratch1, func);
- PPC_MTLR(r_scratch1);
- PPC_ADDI(r_addr, r_X, IMM_L(K));
+ EMIT(PPC_RAW_MTLR(r_scratch1));
+ EMIT(PPC_RAW_ADDI(r_addr, r_X, IMM_L(K)));
if (K >= 32768)
- PPC_ADDIS(r_addr, r_addr, IMM_HA(K));
- PPC_BLRL();
+ EMIT(PPC_RAW_ADDIS(r_addr, r_addr, IMM_HA(K)));
+ EMIT(PPC_RAW_BLRL());
/* If error, cr0.LT set */
PPC_BCC(COND_LT, exit_addr);
break;
@@ -489,30 +489,30 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JEQ | BPF_X:
ctx->seen |= SEEN_XREG;
- PPC_CMPLW(r_A, r_X);
+ EMIT(PPC_RAW_CMPLW(r_A, r_X));
break;
case BPF_JMP | BPF_JSET | BPF_X:
ctx->seen |= SEEN_XREG;
- PPC_AND_DOT(r_scratch1, r_A, r_X);
+ EMIT(PPC_RAW_AND_DOT(r_scratch1, r_A, r_X));
break;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGE | BPF_K:
if (K < 32768)
- PPC_CMPLWI(r_A, K);
+ EMIT(PPC_RAW_CMPLWI(r_A, K));
else {
PPC_LI32(r_scratch1, K);
- PPC_CMPLW(r_A, r_scratch1);
+ EMIT(PPC_RAW_CMPLW(r_A, r_scratch1));
}
break;
case BPF_JMP | BPF_JSET | BPF_K:
if (K < 32768)
/* PPC_ANDI is /only/ dot-form */
- PPC_ANDI(r_scratch1, r_A, K);
+ EMIT(PPC_RAW_ANDI(r_scratch1, r_A, K));
else {
PPC_LI32(r_scratch1, K);
- PPC_AND_DOT(r_scratch1, r_A,
- r_scratch1);
+ EMIT(PPC_RAW_AND_DOT(r_scratch1, r_A,
+ r_scratch1));
}
break;
}
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index be3517ef0574..022103c6a201 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -95,12 +95,12 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
* invoked through a tail call.
*/
if (ctx->seen & SEEN_TAILCALL) {
- PPC_LI(b2p[TMP_REG_1], 0);
+ EMIT(PPC_RAW_LI(b2p[TMP_REG_1], 0));
/* this goes in the redzone */
PPC_BPF_STL(b2p[TMP_REG_1], 1, -(BPF_PPC_STACK_SAVE + 8));
} else {
- PPC_NOP();
- PPC_NOP();
+ EMIT(PPC_RAW_NOP());
+ EMIT(PPC_RAW_NOP());
}
#define BPF_TAILCALL_PROLOGUE_SIZE 8
@@ -129,8 +129,8 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
/* Setup frame pointer to point to the bpf stack area */
if (bpf_is_seen_register(ctx, BPF_REG_FP))
- PPC_ADDI(b2p[BPF_REG_FP], 1,
- STACK_FRAME_MIN_SIZE + ctx->stack_size);
+ EMIT(PPC_RAW_ADDI(b2p[BPF_REG_FP], 1,
+ STACK_FRAME_MIN_SIZE + ctx->stack_size));
}
static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx)
@@ -144,10 +144,10 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
/* Tear down our stack frame */
if (bpf_has_stack_frame(ctx)) {
- PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
+ EMIT(PPC_RAW_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size));
if (ctx->seen & SEEN_FUNC) {
PPC_BPF_LL(0, 1, PPC_LR_STKOFF);
- PPC_MTLR(0);
+ EMIT(PPC_RAW_MTLR(0));
}
}
}
@@ -157,9 +157,9 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
bpf_jit_emit_common_epilogue(image, ctx);
/* Move result to r3 */
- PPC_MR(3, b2p[BPF_REG_0]);
+ EMIT(PPC_RAW_MR(3, b2p[BPF_REG_0]));
- PPC_BLR();
+ EMIT(PPC_RAW_BLR());
}
static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx,
@@ -171,7 +171,7 @@ static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx,
/* Load actual entry point from function descriptor */
PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
/* ... and move it to LR */
- PPC_MTLR(b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_MTLR(b2p[TMP_REG_1]));
/*
* Load TOC from function descriptor at offset 8.
* We can clobber r2 since we get called through a
@@ -182,9 +182,9 @@ static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx,
#else
/* We can clobber r12 */
PPC_FUNC_ADDR(12, func);
- PPC_MTLR(12);
+ EMIT(PPC_RAW_MTLR(12));
#endif
- PPC_BLRL();
+ EMIT(PPC_RAW_BLRL());
}
static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx,
@@ -206,7 +206,7 @@ static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx,
* that PPC_LI64() can emit.
*/
for (i = ctx->idx - ctx_idx; i < 5; i++)
- PPC_NOP();
+ EMIT(PPC_RAW_NOP());
#ifdef PPC64_ELF_ABI_v1
/*
@@ -220,8 +220,8 @@ static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx,
PPC_BPF_LL(12, 12, 0);
#endif
- PPC_MTLR(12);
- PPC_BLRL();
+ EMIT(PPC_RAW_MTLR(12));
+ EMIT(PPC_RAW_BLRL());
}
static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
@@ -239,9 +239,9 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
* if (index >= array->map.max_entries)
* goto out;
*/
- PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries));
- PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31);
- PPC_CMPLW(b2p_index, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)));
+ EMIT(PPC_RAW_RLWINM(b2p_index, b2p_index, 0, 0, 31));
+ EMIT(PPC_RAW_CMPLW(b2p_index, b2p[TMP_REG_1]));
PPC_BCC(COND_GE, out);
/*
@@ -249,42 +249,42 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
* goto out;
*/
PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
- PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT);
+ EMIT(PPC_RAW_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT));
PPC_BCC(COND_GT, out);
/*
* tail_call_cnt++;
*/
- PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], 1);
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], 1));
PPC_BPF_STL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
/* prog = array->ptrs[index]; */
- PPC_MULI(b2p[TMP_REG_1], b2p_index, 8);
- PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array);
+ EMIT(PPC_RAW_MULI(b2p[TMP_REG_1], b2p_index, 8));
+ EMIT(PPC_RAW_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array));
PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
/*
* if (prog == NULL)
* goto out;
*/
- PPC_CMPLDI(b2p[TMP_REG_1], 0);
+ EMIT(PPC_RAW_CMPLDI(b2p[TMP_REG_1], 0));
PPC_BCC(COND_EQ, out);
/* goto *(prog->bpf_func + prologue_size); */
PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
#ifdef PPC64_ELF_ABI_v1
/* skip past the function descriptor */
- PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1],
- FUNCTION_DESCR_SIZE + BPF_TAILCALL_PROLOGUE_SIZE);
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1],
+ FUNCTION_DESCR_SIZE + BPF_TAILCALL_PROLOGUE_SIZE));
#else
- PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], BPF_TAILCALL_PROLOGUE_SIZE);
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], BPF_TAILCALL_PROLOGUE_SIZE));
#endif
- PPC_MTCTR(b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_MTCTR(b2p[TMP_REG_1]));
/* tear down stack, restore NVRs, ... */
bpf_jit_emit_common_epilogue(image, ctx);
- PPC_BCTR();
+ EMIT(PPC_RAW_BCTR());
/* out: */
}
@@ -340,11 +340,11 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
*/
case BPF_ALU | BPF_ADD | BPF_X: /* (u32) dst += (u32) src */
case BPF_ALU64 | BPF_ADD | BPF_X: /* dst += src */
- PPC_ADD(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_ADD(dst_reg, dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU | BPF_SUB | BPF_X: /* (u32) dst -= (u32) src */
case BPF_ALU64 | BPF_SUB | BPF_X: /* dst -= src */
- PPC_SUB(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_SUB(dst_reg, dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */
case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
@@ -354,53 +354,53 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
imm = -imm;
if (imm) {
if (imm >= -32768 && imm < 32768)
- PPC_ADDI(dst_reg, dst_reg, IMM_L(imm));
+ EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm)));
else {
PPC_LI32(b2p[TMP_REG_1], imm);
- PPC_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]));
}
}
goto bpf_alu32_trunc;
case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */
case BPF_ALU64 | BPF_MUL | BPF_X: /* dst *= src */
if (BPF_CLASS(code) == BPF_ALU)
- PPC_MULW(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_MULW(dst_reg, dst_reg, src_reg));
else
- PPC_MULD(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_MULD(dst_reg, dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU | BPF_MUL | BPF_K: /* (u32) dst *= (u32) imm */
case BPF_ALU64 | BPF_MUL | BPF_K: /* dst *= imm */
if (imm >= -32768 && imm < 32768)
- PPC_MULI(dst_reg, dst_reg, IMM_L(imm));
+ EMIT(PPC_RAW_MULI(dst_reg, dst_reg, IMM_L(imm)));
else {
PPC_LI32(b2p[TMP_REG_1], imm);
if (BPF_CLASS(code) == BPF_ALU)
- PPC_MULW(dst_reg, dst_reg,
- b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_MULW(dst_reg, dst_reg,
+ b2p[TMP_REG_1]));
else
- PPC_MULD(dst_reg, dst_reg,
- b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_MULD(dst_reg, dst_reg,
+ b2p[TMP_REG_1]));
}
goto bpf_alu32_trunc;
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) {
- PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg);
- PPC_MULW(b2p[TMP_REG_1], src_reg,
- b2p[TMP_REG_1]);
- PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg));
+ EMIT(PPC_RAW_MULW(b2p[TMP_REG_1], src_reg,
+ b2p[TMP_REG_1]));
+ EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]));
} else
- PPC_DIVWU(dst_reg, dst_reg, src_reg);
+ 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) {
- PPC_DIVDU(b2p[TMP_REG_1], dst_reg, src_reg);
- PPC_MULD(b2p[TMP_REG_1], src_reg,
- b2p[TMP_REG_1]);
- PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_DIVDU(b2p[TMP_REG_1], dst_reg, src_reg));
+ EMIT(PPC_RAW_MULD(b2p[TMP_REG_1], src_reg,
+ b2p[TMP_REG_1]));
+ EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]));
} else
- PPC_DIVDU(dst_reg, dst_reg, src_reg);
+ 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 */
@@ -415,35 +415,37 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
switch (BPF_CLASS(code)) {
case BPF_ALU:
if (BPF_OP(code) == BPF_MOD) {
- PPC_DIVWU(b2p[TMP_REG_2], dst_reg,
- b2p[TMP_REG_1]);
- PPC_MULW(b2p[TMP_REG_1],
+ EMIT(PPC_RAW_DIVWU(b2p[TMP_REG_2],
+ dst_reg,
+ b2p[TMP_REG_1]));
+ EMIT(PPC_RAW_MULW(b2p[TMP_REG_1],
b2p[TMP_REG_1],
- b2p[TMP_REG_2]);
- PPC_SUB(dst_reg, dst_reg,
- b2p[TMP_REG_1]);
+ b2p[TMP_REG_2]));
+ EMIT(PPC_RAW_SUB(dst_reg, dst_reg,
+ b2p[TMP_REG_1]));
} else
- PPC_DIVWU(dst_reg, dst_reg,
- b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg,
+ b2p[TMP_REG_1]));
break;
case BPF_ALU64:
if (BPF_OP(code) == BPF_MOD) {
- PPC_DIVDU(b2p[TMP_REG_2], dst_reg,
- b2p[TMP_REG_1]);
- PPC_MULD(b2p[TMP_REG_1],
+ EMIT(PPC_RAW_DIVDU(b2p[TMP_REG_2],
+ dst_reg,
+ b2p[TMP_REG_1]));
+ EMIT(PPC_RAW_MULD(b2p[TMP_REG_1],
b2p[TMP_REG_1],
- b2p[TMP_REG_2]);
- PPC_SUB(dst_reg, dst_reg,
- b2p[TMP_REG_1]);
+ b2p[TMP_REG_2]));
+ EMIT(PPC_RAW_SUB(dst_reg, dst_reg,
+ b2p[TMP_REG_1]));
} else
- PPC_DIVDU(dst_reg, dst_reg,
- b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg,
+ b2p[TMP_REG_1]));
break;
}
goto bpf_alu32_trunc;
case BPF_ALU | BPF_NEG: /* (u32) dst = -dst */
case BPF_ALU64 | BPF_NEG: /* dst = -dst */
- PPC_NEG(dst_reg, dst_reg);
+ EMIT(PPC_RAW_NEG(dst_reg, dst_reg));
goto bpf_alu32_trunc;
/*
@@ -451,101 +453,101 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
*/
case BPF_ALU | BPF_AND | BPF_X: /* (u32) dst = dst & src */
case BPF_ALU64 | BPF_AND | BPF_X: /* dst = dst & src */
- PPC_AND(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_AND(dst_reg, dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU | BPF_AND | BPF_K: /* (u32) dst = dst & imm */
case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */
if (!IMM_H(imm))
- PPC_ANDI(dst_reg, dst_reg, IMM_L(imm));
+ EMIT(PPC_RAW_ANDI(dst_reg, dst_reg, IMM_L(imm)));
else {
/* Sign-extended */
PPC_LI32(b2p[TMP_REG_1], imm);
- PPC_AND(dst_reg, dst_reg, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_AND(dst_reg, dst_reg, b2p[TMP_REG_1]));
}
goto bpf_alu32_trunc;
case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */
case BPF_ALU64 | BPF_OR | BPF_X: /* dst = dst | src */
- PPC_OR(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_OR(dst_reg, dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU | BPF_OR | BPF_K:/* dst = (u32) dst | (u32) imm */
case BPF_ALU64 | BPF_OR | BPF_K:/* dst = dst | imm */
if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) {
/* Sign-extended */
PPC_LI32(b2p[TMP_REG_1], imm);
- PPC_OR(dst_reg, dst_reg, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_1]));
} else {
if (IMM_L(imm))
- PPC_ORI(dst_reg, dst_reg, IMM_L(imm));
+ EMIT(PPC_RAW_ORI(dst_reg, dst_reg, IMM_L(imm)));
if (IMM_H(imm))
- PPC_ORIS(dst_reg, dst_reg, IMM_H(imm));
+ EMIT(PPC_RAW_ORIS(dst_reg, dst_reg, IMM_H(imm)));
}
goto bpf_alu32_trunc;
case BPF_ALU | BPF_XOR | BPF_X: /* (u32) dst ^= src */
case BPF_ALU64 | BPF_XOR | BPF_X: /* dst ^= src */
- PPC_XOR(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_XOR(dst_reg, dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU | BPF_XOR | BPF_K: /* (u32) dst ^= (u32) imm */
case BPF_ALU64 | BPF_XOR | BPF_K: /* dst ^= imm */
if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) {
/* Sign-extended */
PPC_LI32(b2p[TMP_REG_1], imm);
- PPC_XOR(dst_reg, dst_reg, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_XOR(dst_reg, dst_reg, b2p[TMP_REG_1]));
} else {
if (IMM_L(imm))
- PPC_XORI(dst_reg, dst_reg, IMM_L(imm));
+ EMIT(PPC_RAW_XORI(dst_reg, dst_reg, IMM_L(imm)));
if (IMM_H(imm))
- PPC_XORIS(dst_reg, dst_reg, IMM_H(imm));
+ EMIT(PPC_RAW_XORIS(dst_reg, dst_reg, IMM_H(imm)));
}
goto bpf_alu32_trunc;
case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
/* slw clears top 32 bits */
- PPC_SLW(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_SLW(dst_reg, dst_reg, src_reg));
/* skip zero extension move, but set address map. */
if (insn_is_zext(&insn[i + 1]))
addrs[++i] = ctx->idx * 4;
break;
case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
- PPC_SLD(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_SLD(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */
/* with imm 0, we still need to clear top 32 bits */
- PPC_SLWI(dst_reg, dst_reg, imm);
+ EMIT(PPC_RAW_SLWI(dst_reg, dst_reg, imm));
if (insn_is_zext(&insn[i + 1]))
addrs[++i] = ctx->idx * 4;
break;
case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */
if (imm != 0)
- PPC_SLDI(dst_reg, dst_reg, imm);
+ EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, imm));
break;
case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
- PPC_SRW(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_SRW(dst_reg, dst_reg, src_reg));
if (insn_is_zext(&insn[i + 1]))
addrs[++i] = ctx->idx * 4;
break;
case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
- PPC_SRD(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_SRD(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
- PPC_SRWI(dst_reg, dst_reg, imm);
+ EMIT(PPC_RAW_SRWI(dst_reg, dst_reg, imm));
if (insn_is_zext(&insn[i + 1]))
addrs[++i] = ctx->idx * 4;
break;
case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
if (imm != 0)
- PPC_SRDI(dst_reg, dst_reg, imm);
+ EMIT(PPC_RAW_SRDI(dst_reg, dst_reg, imm));
break;
case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */
- PPC_SRAW(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_SRAW(dst_reg, dst_reg, src_reg));
goto bpf_alu32_trunc;
case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
- PPC_SRAD(dst_reg, dst_reg, src_reg);
+ EMIT(PPC_RAW_SRAD(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU | BPF_ARSH | BPF_K: /* (s32) dst >>= imm */
- PPC_SRAWI(dst_reg, dst_reg, imm);
+ EMIT(PPC_RAW_SRAWI(dst_reg, dst_reg, imm));
goto bpf_alu32_trunc;
case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */
if (imm != 0)
- PPC_SRADI(dst_reg, dst_reg, imm);
+ EMIT(PPC_RAW_SRADI(dst_reg, dst_reg, imm));
break;
/*
@@ -555,10 +557,10 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
if (imm == 1) {
/* special mov32 for zext */
- PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
+ EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31));
break;
}
- PPC_MR(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 */
@@ -572,7 +574,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
bpf_alu32_trunc:
/* Truncate to 32-bits */
if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext)
- PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
+ EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31));
break;
/*
@@ -590,11 +592,11 @@ bpf_alu32_trunc:
switch (imm) {
case 16:
/* Rotate 8 bits left & mask with 0x0000ff00 */
- PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 16, 23);
+ EMIT(PPC_RAW_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 16, 23));
/* Rotate 8 bits right & insert LSB to reg */
- PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 24, 31);
+ EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 24, 31));
/* Move result back to dst_reg */
- PPC_MR(dst_reg, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1]));
break;
case 32:
/*
@@ -602,12 +604,12 @@ bpf_alu32_trunc:
* 2 bytes are already in their final position
* -- byte 2 and 4 (of bytes 1, 2, 3 and 4)
*/
- PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 0, 31);
+ EMIT(PPC_RAW_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 0, 31));
/* Rotate 24 bits and insert byte 1 */
- PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 0, 7);
+ EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 0, 7));
/* Rotate 24 bits and insert byte 3 */
- PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 16, 23);
- PPC_MR(dst_reg, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 16, 23));
+ EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1]));
break;
case 64:
/*
@@ -619,8 +621,8 @@ bpf_alu32_trunc:
* same across all passes
*/
PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx));
- PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx));
- PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx)));
+ EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1]));
break;
}
break;
@@ -629,14 +631,14 @@ emit_clear:
switch (imm) {
case 16:
/* zero-extend 16 bits into 64 bits */
- PPC_RLDICL(dst_reg, dst_reg, 0, 48);
+ EMIT(PPC_RAW_RLDICL(dst_reg, dst_reg, 0, 48));
if (insn_is_zext(&insn[i + 1]))
addrs[++i] = ctx->idx * 4;
break;
case 32:
if (!fp->aux->verifier_zext)
/* zero-extend 32 bits into 64 bits */
- PPC_RLDICL(dst_reg, dst_reg, 0, 32);
+ EMIT(PPC_RAW_RLDICL(dst_reg, dst_reg, 0, 32));
break;
case 64:
/* nop */
@@ -650,18 +652,18 @@ emit_clear:
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
case BPF_ST | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = imm */
if (BPF_CLASS(code) == BPF_ST) {
- PPC_LI(b2p[TMP_REG_1], imm);
+ EMIT(PPC_RAW_LI(b2p[TMP_REG_1], imm));
src_reg = b2p[TMP_REG_1];
}
- PPC_STB(src_reg, dst_reg, off);
+ EMIT(PPC_RAW_STB(src_reg, dst_reg, off));
break;
case BPF_STX | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = src */
case BPF_ST | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = imm */
if (BPF_CLASS(code) == BPF_ST) {
- PPC_LI(b2p[TMP_REG_1], imm);
+ EMIT(PPC_RAW_LI(b2p[TMP_REG_1], imm));
src_reg = b2p[TMP_REG_1];
}
- PPC_STH(src_reg, dst_reg, off);
+ EMIT(PPC_RAW_STH(src_reg, dst_reg, off));
break;
case BPF_STX | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = src */
case BPF_ST | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = imm */
@@ -669,7 +671,7 @@ emit_clear:
PPC_LI32(b2p[TMP_REG_1], imm);
src_reg = b2p[TMP_REG_1];
}
- PPC_STW(src_reg, dst_reg, off);
+ EMIT(PPC_RAW_STW(src_reg, dst_reg, off));
break;
case BPF_STX | BPF_MEM | BPF_DW: /* (u64 *)(dst + off) = src */
case BPF_ST | BPF_MEM | BPF_DW: /* *(u64 *)(dst + off) = imm */
@@ -686,24 +688,24 @@ emit_clear:
/* *(u32 *)(dst + off) += src */
case BPF_STX | BPF_XADD | BPF_W:
/* Get EA into TMP_REG_1 */
- PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off));
tmp_idx = ctx->idx * 4;
/* load value from memory into TMP_REG_2 */
- PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
+ EMIT(PPC_RAW_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0));
/* add value from src_reg into this */
- PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
+ EMIT(PPC_RAW_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg));
/* store result back */
- PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]));
/* we're done if this succeeded */
PPC_BCC_SHORT(COND_NE, tmp_idx);
break;
/* *(u64 *)(dst + off) += src */
case BPF_STX | BPF_XADD | BPF_DW:
- PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off));
tmp_idx = ctx->idx * 4;
- PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
- PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
- PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0));
+ EMIT(PPC_RAW_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg));
+ EMIT(PPC_RAW_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]));
PPC_BCC_SHORT(COND_NE, tmp_idx);
break;
@@ -712,19 +714,19 @@ emit_clear:
*/
/* dst = *(u8 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_B:
- PPC_LBZ(dst_reg, src_reg, off);
+ EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
if (insn_is_zext(&insn[i + 1]))
addrs[++i] = ctx->idx * 4;
break;
/* dst = *(u16 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_H:
- PPC_LHZ(dst_reg, src_reg, off);
+ EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
if (insn_is_zext(&insn[i + 1]))
addrs[++i] = ctx->idx * 4;
break;
/* dst = *(u32 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_W:
- PPC_LWZ(dst_reg, src_reg, off);
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
if (insn_is_zext(&insn[i + 1]))
addrs[++i] = ctx->idx * 4;
break;
@@ -775,7 +777,7 @@ emit_clear:
else
bpf_jit_emit_func_call_rel(image, ctx, func_addr);
/* move return value from r3 to BPF_REG_0 */
- PPC_MR(b2p[BPF_REG_0], 3);
+ EMIT(PPC_RAW_MR(b2p[BPF_REG_0], 3));
break;
/*
@@ -860,9 +862,9 @@ cond_branch:
case BPF_JMP32 | BPF_JNE | BPF_X:
/* unsigned comparison */
if (BPF_CLASS(code) == BPF_JMP32)
- PPC_CMPLW(dst_reg, src_reg);
+ EMIT(PPC_RAW_CMPLW(dst_reg, src_reg));
else
- PPC_CMPLD(dst_reg, src_reg);
+ EMIT(PPC_RAW_CMPLD(dst_reg, src_reg));
break;
case BPF_JMP | BPF_JSGT | BPF_X:
case BPF_JMP | BPF_JSLT | BPF_X:
@@ -874,21 +876,21 @@ cond_branch:
case BPF_JMP32 | BPF_JSLE | BPF_X:
/* signed comparison */
if (BPF_CLASS(code) == BPF_JMP32)
- PPC_CMPW(dst_reg, src_reg);
+ EMIT(PPC_RAW_CMPW(dst_reg, src_reg));
else
- PPC_CMPD(dst_reg, src_reg);
+ EMIT(PPC_RAW_CMPD(dst_reg, src_reg));
break;
case BPF_JMP | BPF_JSET | BPF_X:
case BPF_JMP32 | BPF_JSET | BPF_X:
if (BPF_CLASS(code) == BPF_JMP) {
- PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
- src_reg);
+ EMIT(PPC_RAW_AND_DOT(b2p[TMP_REG_1], dst_reg,
+ src_reg));
} else {
int tmp_reg = b2p[TMP_REG_1];
- PPC_AND(tmp_reg, dst_reg, src_reg);
- PPC_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0,
- 31);
+ EMIT(PPC_RAW_AND(tmp_reg, dst_reg, src_reg));
+ EMIT(PPC_RAW_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0,
+ 31));
}
break;
case BPF_JMP | BPF_JNE | BPF_K:
@@ -912,19 +914,19 @@ cond_branch:
*/
if (imm >= 0 && imm < 32768) {
if (is_jmp32)
- PPC_CMPLWI(dst_reg, imm);
+ EMIT(PPC_RAW_CMPLWI(dst_reg, imm));
else
- PPC_CMPLDI(dst_reg, imm);
+ EMIT(PPC_RAW_CMPLDI(dst_reg, imm));
} else {
/* sign-extending load */
PPC_LI32(b2p[TMP_REG_1], imm);
/* ... but unsigned comparison */
if (is_jmp32)
- PPC_CMPLW(dst_reg,
- b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_CMPLW(dst_reg,
+ b2p[TMP_REG_1]));
else
- PPC_CMPLD(dst_reg,
- b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_CMPLD(dst_reg,
+ b2p[TMP_REG_1]));
}
break;
}
@@ -945,17 +947,17 @@ cond_branch:
*/
if (imm >= -32768 && imm < 32768) {
if (is_jmp32)
- PPC_CMPWI(dst_reg, imm);
+ EMIT(PPC_RAW_CMPWI(dst_reg, imm));
else
- PPC_CMPDI(dst_reg, imm);
+ EMIT(PPC_RAW_CMPDI(dst_reg, imm));
} else {
PPC_LI32(b2p[TMP_REG_1], imm);
if (is_jmp32)
- PPC_CMPW(dst_reg,
- b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_CMPW(dst_reg,
+ b2p[TMP_REG_1]));
else
- PPC_CMPD(dst_reg,
- b2p[TMP_REG_1]);
+ EMIT(PPC_RAW_CMPD(dst_reg,
+ b2p[TMP_REG_1]));
}
break;
}
@@ -964,19 +966,19 @@ cond_branch:
/* andi does not sign-extend the immediate */
if (imm >= 0 && imm < 32768)
/* PPC_ANDI is _only/always_ dot-form */
- PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm);
+ EMIT(PPC_RAW_ANDI(b2p[TMP_REG_1], dst_reg, imm));
else {
int tmp_reg = b2p[TMP_REG_1];
PPC_LI32(tmp_reg, imm);
if (BPF_CLASS(code) == BPF_JMP) {
- PPC_AND_DOT(tmp_reg, dst_reg,
- tmp_reg);
+ EMIT(PPC_RAW_AND_DOT(tmp_reg, dst_reg,
+ tmp_reg));
} else {
- PPC_AND(tmp_reg, dst_reg,
- tmp_reg);
- PPC_RLWINM_DOT(tmp_reg, tmp_reg,
- 0, 0, 31);
+ EMIT(PPC_RAW_AND(tmp_reg, dst_reg,
+ tmp_reg));
+ EMIT(PPC_RAW_RLWINM_DOT(tmp_reg, tmp_reg,
+ 0, 0, 31));
}
}
break;
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 53d614e98537..c02854dea2b2 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o
obj64-$(CONFIG_PPC_PERF_CTRS) += ppc970-pmu.o power5-pmu.o \
power5+-pmu.o power6-pmu.o power7-pmu.o \
isa207-common.o power8-pmu.o power9-pmu.o \
- generic-compat-pmu.o
+ generic-compat-pmu.o power10-pmu.o
obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o
obj-$(CONFIG_PPC_POWERNV) += imc-pmu.o
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index cd6a742ac6ef..e29c846bf35d 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -37,12 +37,7 @@ struct cpu_hw_events {
struct perf_event *event[MAX_HWEVENTS];
u64 events[MAX_HWEVENTS];
unsigned int flags[MAX_HWEVENTS];
- /*
- * The order of the MMCR array is:
- * - 64-bit, MMCR0, MMCR1, MMCRA, MMCR2
- * - 32-bit, MMCR0, MMCR1, MMCR2
- */
- unsigned long mmcr[4];
+ struct mmcr_regs mmcr;
struct perf_event *limited_counter[MAX_LIMITED_HWCOUNTERS];
u8 limited_hwidx[MAX_LIMITED_HWCOUNTERS];
u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
@@ -77,6 +72,11 @@ static unsigned int freeze_events_kernel = MMCR0_FCS;
/*
* 32-bit doesn't have MMCRA but does have an MMCR2,
* and a few other names are different.
+ * Also 32-bit doesn't have MMCR3, SIER2 and SIER3.
+ * Define them as zero knowing that any code path accessing
+ * these registers (via mtspr/mfspr) are done under ppmu flag
+ * check for PPMU_ARCH_31 and we will not enter that code path
+ * for 32-bit.
*/
#ifdef CONFIG_PPC32
@@ -90,7 +90,11 @@ static unsigned int freeze_events_kernel = MMCR0_FCS;
#define MMCR0_PMCC_U6 0
#define SPRN_MMCRA SPRN_MMCR2
+#define SPRN_MMCR3 0
+#define SPRN_SIER2 0
+#define SPRN_SIER3 0
#define MMCRA_SAMPLE_ENABLE 0
+#define MMCRA_BHRB_DISABLE 0
static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
{
@@ -121,7 +125,7 @@ static void ebb_event_add(struct perf_event *event) { }
static void ebb_switch_out(unsigned long mmcr0) { }
static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
{
- return cpuhw->mmcr[0];
+ return cpuhw->mmcr.mmcr0;
}
static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
@@ -466,8 +470,11 @@ static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *
* addresses at this point. Check the privileges before
* exporting it to userspace (avoid exposure of regions
* where we could have speculative execution)
+ * Incase of ISA v3.1, BHRB will capture only user-space
+ * addresses, hence include a check before filtering code
*/
- if (is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
+ if (!(ppmu->flags & PPMU_ARCH_31) &&
+ is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
continue;
/* Branches are read most recent first (ie. mfbhrb 0 is
@@ -586,11 +593,16 @@ static void ebb_switch_out(unsigned long mmcr0)
current->thread.sdar = mfspr(SPRN_SDAR);
current->thread.mmcr0 = mmcr0 & MMCR0_USER_MASK;
current->thread.mmcr2 = mfspr(SPRN_MMCR2) & MMCR2_USER_MASK;
+ if (ppmu->flags & PPMU_ARCH_31) {
+ current->thread.mmcr3 = mfspr(SPRN_MMCR3);
+ current->thread.sier2 = mfspr(SPRN_SIER2);
+ current->thread.sier3 = mfspr(SPRN_SIER3);
+ }
}
static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
{
- unsigned long mmcr0 = cpuhw->mmcr[0];
+ unsigned long mmcr0 = cpuhw->mmcr.mmcr0;
if (!ebb)
goto out;
@@ -624,7 +636,13 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
* unfreeze counters, it should not set exclude_xxx in its events and
* instead manage the MMCR2 entirely by itself.
*/
- mtspr(SPRN_MMCR2, cpuhw->mmcr[3] | current->thread.mmcr2);
+ mtspr(SPRN_MMCR2, cpuhw->mmcr.mmcr2 | current->thread.mmcr2);
+
+ if (ppmu->flags & PPMU_ARCH_31) {
+ mtspr(SPRN_MMCR3, current->thread.mmcr3);
+ mtspr(SPRN_SIER2, current->thread.sier2);
+ mtspr(SPRN_SIER3, current->thread.sier3);
+ }
out:
return mmcr0;
}
@@ -845,6 +863,11 @@ void perf_event_print_debug(void)
pr_info("EBBRR: %016lx BESCR: %016lx\n",
mfspr(SPRN_EBBRR), mfspr(SPRN_BESCR));
}
+
+ if (ppmu->flags & PPMU_ARCH_31) {
+ pr_info("MMCR3: %016lx SIER2: %016lx SIER3: %016lx\n",
+ mfspr(SPRN_MMCR3), mfspr(SPRN_SIER2), mfspr(SPRN_SIER3));
+ }
#endif
pr_info("SIAR: %016lx SDAR: %016lx SIER: %016lx\n",
mfspr(SPRN_SIAR), sdar, sier);
@@ -1196,7 +1219,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0)
static void power_pmu_disable(struct pmu *pmu)
{
struct cpu_hw_events *cpuhw;
- unsigned long flags, mmcr0, val;
+ unsigned long flags, mmcr0, val, mmcra;
if (!ppmu)
return;
@@ -1229,12 +1252,24 @@ static void power_pmu_disable(struct pmu *pmu)
mb();
isync();
+ val = mmcra = cpuhw->mmcr.mmcra;
+
/*
* Disable instruction sampling if it was enabled
*/
- if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
- mtspr(SPRN_MMCRA,
- cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
+ if (cpuhw->mmcr.mmcra & MMCRA_SAMPLE_ENABLE)
+ val &= ~MMCRA_SAMPLE_ENABLE;
+
+ /* Disable BHRB via mmcra (BHRBRD) for p10 */
+ if (ppmu->flags & PPMU_ARCH_31)
+ val |= MMCRA_BHRB_DISABLE;
+
+ /*
+ * Write SPRN_MMCRA if mmcra has either disabled
+ * instruction sampling or BHRB.
+ */
+ if (val != mmcra) {
+ mtspr(SPRN_MMCRA, mmcra);
mb();
isync();
}
@@ -1308,18 +1343,20 @@ static void power_pmu_enable(struct pmu *pmu)
* (possibly updated for removal of events).
*/
if (!cpuhw->n_added) {
- mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
- mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
+ mtspr(SPRN_MMCRA, cpuhw->mmcr.mmcra & ~MMCRA_SAMPLE_ENABLE);
+ mtspr(SPRN_MMCR1, cpuhw->mmcr.mmcr1);
+ if (ppmu->flags & PPMU_ARCH_31)
+ mtspr(SPRN_MMCR3, cpuhw->mmcr.mmcr3);
goto out_enable;
}
/*
* Clear all MMCR settings and recompute them for the new set of events.
*/
- memset(cpuhw->mmcr, 0, sizeof(cpuhw->mmcr));
+ memset(&cpuhw->mmcr, 0, sizeof(cpuhw->mmcr));
if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_events, hwc_index,
- cpuhw->mmcr, cpuhw->event)) {
+ &cpuhw->mmcr, cpuhw->event)) {
/* shouldn't ever get here */
printk(KERN_ERR "oops compute_mmcr failed\n");
goto out;
@@ -1333,11 +1370,11 @@ static void power_pmu_enable(struct pmu *pmu)
*/
event = cpuhw->event[0];
if (event->attr.exclude_user)
- cpuhw->mmcr[0] |= MMCR0_FCP;
+ cpuhw->mmcr.mmcr0 |= MMCR0_FCP;
if (event->attr.exclude_kernel)
- cpuhw->mmcr[0] |= freeze_events_kernel;
+ cpuhw->mmcr.mmcr0 |= freeze_events_kernel;
if (event->attr.exclude_hv)
- cpuhw->mmcr[0] |= MMCR0_FCHV;
+ cpuhw->mmcr.mmcr0 |= MMCR0_FCHV;
}
/*
@@ -1346,12 +1383,15 @@ static void power_pmu_enable(struct pmu *pmu)
* Then unfreeze the events.
*/
ppc_set_pmu_inuse(1);
- mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
- mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
- mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE))
+ mtspr(SPRN_MMCRA, cpuhw->mmcr.mmcra & ~MMCRA_SAMPLE_ENABLE);
+ mtspr(SPRN_MMCR1, cpuhw->mmcr.mmcr1);
+ mtspr(SPRN_MMCR0, (cpuhw->mmcr.mmcr0 & ~(MMCR0_PMC1CE | MMCR0_PMCjCE))
| MMCR0_FC);
if (ppmu->flags & PPMU_ARCH_207S)
- mtspr(SPRN_MMCR2, cpuhw->mmcr[3]);
+ mtspr(SPRN_MMCR2, cpuhw->mmcr.mmcr2);
+
+ if (ppmu->flags & PPMU_ARCH_31)
+ mtspr(SPRN_MMCR3, cpuhw->mmcr.mmcr3);
/*
* Read off any pre-existing events that need to move
@@ -1402,7 +1442,7 @@ static void power_pmu_enable(struct pmu *pmu)
perf_event_update_userpage(event);
}
cpuhw->n_limited = n_lim;
- cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
+ cpuhw->mmcr.mmcr0 |= MMCR0_PMXE | MMCR0_FCECE;
out_enable:
pmao_restore_workaround(ebb);
@@ -1418,9 +1458,9 @@ static void power_pmu_enable(struct pmu *pmu)
/*
* Enable instruction sampling if necessary
*/
- if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
+ if (cpuhw->mmcr.mmcra & MMCRA_SAMPLE_ENABLE) {
mb();
- mtspr(SPRN_MMCRA, cpuhw->mmcr[2]);
+ mtspr(SPRN_MMCRA, cpuhw->mmcr.mmcra);
}
out:
@@ -1550,7 +1590,7 @@ static void power_pmu_del(struct perf_event *event, int ef_flags)
cpuhw->flags[i-1] = cpuhw->flags[i];
}
--cpuhw->n_events;
- ppmu->disable_pmc(event->hw.idx - 1, cpuhw->mmcr);
+ ppmu->disable_pmc(event->hw.idx - 1, &cpuhw->mmcr);
if (event->hw.idx) {
write_pmc(event->hw.idx, 0);
event->hw.idx = 0;
@@ -1571,7 +1611,7 @@ static void power_pmu_del(struct perf_event *event, int ef_flags)
}
if (cpuhw->n_events == 0) {
/* disable exceptions if no events are running */
- cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE);
+ cpuhw->mmcr.mmcr0 &= ~(MMCR0_PMXE | MMCR0_FCECE);
}
if (has_branch_stack(event))
@@ -1795,7 +1835,7 @@ static void hw_perf_event_destroy(struct perf_event *event)
static int hw_perf_cache_event(u64 config, u64 *eventp)
{
unsigned long type, op, result;
- int ev;
+ u64 ev;
if (!ppmu->cache_events)
return -EINVAL;
@@ -2240,7 +2280,7 @@ static void __perf_event_interrupt(struct pt_regs *regs)
* XXX might want to use MSR.PM to keep the events frozen until
* we get back out of this interrupt.
*/
- write_mmcr0(cpuhw, cpuhw->mmcr[0]);
+ write_mmcr0(cpuhw, cpuhw->mmcr.mmcr0);
if (nmi)
nmi_exit();
@@ -2262,7 +2302,7 @@ static int power_pmu_prepare_cpu(unsigned int cpu)
if (ppmu) {
memset(cpuhw, 0, sizeof(*cpuhw));
- cpuhw->mmcr[0] = MMCR0_FC;
+ cpuhw->mmcr.mmcr0 = MMCR0_FC;
}
return 0;
}
@@ -2308,6 +2348,8 @@ static int __init init_ppc64_pmu(void)
return 0;
else if (!init_power9_pmu())
return 0;
+ else if (!init_power10_pmu())
+ return 0;
else if (!init_ppc970_pmu())
return 0;
else
diff --git a/arch/powerpc/perf/generic-compat-pmu.c b/arch/powerpc/perf/generic-compat-pmu.c
index 5e5a54d5588e..eb8a6aaf4cc1 100644
--- a/arch/powerpc/perf/generic-compat-pmu.c
+++ b/arch/powerpc/perf/generic-compat-pmu.c
@@ -101,7 +101,7 @@ static int compat_generic_events[] = {
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int generic_compat_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 generic_compat_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0,
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index db213eb7cb02..cdb7bfbd157e 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -31,6 +31,8 @@ static int interface_version;
/* Whether we have to aggregate result data for some domains. */
static bool aggregate_result_elements;
+static cpumask_t hv_24x7_cpumask;
+
static bool domain_is_valid(unsigned domain)
{
switch (domain) {
@@ -446,6 +448,12 @@ static ssize_t device_show_string(struct device *dev,
return sprintf(buf, "%s\n", (char *)d->var);
}
+static ssize_t cpumask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return cpumap_print_to_pagebuf(true, buf, &hv_24x7_cpumask);
+}
+
static ssize_t sockets_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -1113,6 +1121,7 @@ static DEVICE_ATTR_RO(domains);
static DEVICE_ATTR_RO(sockets);
static DEVICE_ATTR_RO(chipspersocket);
static DEVICE_ATTR_RO(coresperchip);
+static DEVICE_ATTR_RO(cpumask);
static struct bin_attribute *if_bin_attrs[] = {
&bin_attr_catalog,
@@ -1126,6 +1135,7 @@ static struct attribute *if_attrs[] = {
&dev_attr_sockets.attr,
&dev_attr_chipspersocket.attr,
&dev_attr_coresperchip.attr,
+ &dev_attr_cpumask.attr,
NULL,
};
@@ -1641,6 +1651,45 @@ static struct pmu h_24x7_pmu = {
.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
+static int ppc_hv_24x7_cpu_online(unsigned int cpu)
+{
+ if (cpumask_empty(&hv_24x7_cpumask))
+ cpumask_set_cpu(cpu, &hv_24x7_cpumask);
+
+ return 0;
+}
+
+static int ppc_hv_24x7_cpu_offline(unsigned int cpu)
+{
+ int target;
+
+ /* Check if exiting cpu is used for collecting 24x7 events */
+ if (!cpumask_test_and_clear_cpu(cpu, &hv_24x7_cpumask))
+ return 0;
+
+ /* Find a new cpu to collect 24x7 events */
+ target = cpumask_last(cpu_active_mask);
+
+ if (target < 0 || target >= nr_cpu_ids) {
+ pr_err("hv_24x7: CPU hotplug init failed\n");
+ return -1;
+ }
+
+ /* Migrate 24x7 events to the new target */
+ cpumask_set_cpu(target, &hv_24x7_cpumask);
+ perf_pmu_migrate_context(&h_24x7_pmu, cpu, target);
+
+ return 0;
+}
+
+static int hv_24x7_cpu_hotplug_init(void)
+{
+ return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE,
+ "perf/powerpc/hv_24x7:online",
+ ppc_hv_24x7_cpu_online,
+ ppc_hv_24x7_cpu_offline);
+}
+
static int hv_24x7_init(void)
{
int r;
@@ -1685,6 +1734,11 @@ static int hv_24x7_init(void)
if (r)
return r;
+ /* init cpuhotplug */
+ r = hv_24x7_cpu_hotplug_init();
+ if (r)
+ return r;
+
r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
if (r)
return r;
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 0edcfd0b491d..a45d694a5d5d 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -1288,11 +1288,30 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem,
header->size = sizeof(*header) + event->header_size;
header->misc = 0;
- if (is_kernel_addr(data->ip))
- header->misc |= PERF_RECORD_MISC_KERNEL;
- else
- header->misc |= PERF_RECORD_MISC_USER;
-
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ switch (IMC_TRACE_RECORD_VAL_HVPR(mem->val)) {
+ case 0:/* when MSR HV and PR not set in the trace-record */
+ header->misc |= PERF_RECORD_MISC_GUEST_KERNEL;
+ break;
+ case 1: /* MSR HV is 0 and PR is 1 */
+ header->misc |= PERF_RECORD_MISC_GUEST_USER;
+ break;
+ case 2: /* MSR HV is 1 and PR is 0 */
+ header->misc |= PERF_RECORD_MISC_HYPERVISOR;
+ break;
+ case 3: /* MSR HV is 1 and PR is 1 */
+ header->misc |= PERF_RECORD_MISC_USER;
+ break;
+ default:
+ pr_info("IMC: Unable to set the flag based on MSR bits\n");
+ break;
+ }
+ } else {
+ if (is_kernel_addr(data->ip))
+ header->misc |= PERF_RECORD_MISC_KERNEL;
+ else
+ header->misc |= PERF_RECORD_MISC_USER;
+ }
perf_event_header__init_id(header, data, event);
return 0;
diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h
index f755c64da137..80bbf72bfec2 100644
--- a/arch/powerpc/perf/internal.h
+++ b/arch/powerpc/perf/internal.h
@@ -9,4 +9,5 @@ extern int init_power6_pmu(void);
extern int init_power7_pmu(void);
extern int init_power8_pmu(void);
extern int init_power9_pmu(void);
+extern int init_power10_pmu(void);
extern int init_generic_compat_pmu(void);
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 4c86da5eb28a..964437adec18 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -55,7 +55,9 @@ static bool is_event_valid(u64 event)
{
u64 valid_mask = EVENT_VALID_MASK;
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ valid_mask = p10_EVENT_VALID_MASK;
+ else if (cpu_has_feature(CPU_FTR_ARCH_300))
valid_mask = p9_EVENT_VALID_MASK;
return !(event & ~valid_mask);
@@ -69,6 +71,14 @@ static inline bool is_event_marked(u64 event)
return false;
}
+static unsigned long sdar_mod_val(u64 event)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ return p10_SDAR_MODE(event);
+
+ return p9_SDAR_MODE(event);
+}
+
static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
{
/*
@@ -79,7 +89,7 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
* MMCRA[SDAR_MODE] will be programmed as "0b01" for continous sampling
* mode and will be un-changed when setting MMCRA[63] (Marked events).
*
- * Incase of Power9:
+ * Incase of Power9/power10:
* Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'),
* or if group already have any marked events.
* For rest
@@ -90,8 +100,8 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE))
*mmcra &= MMCRA_SDAR_MODE_NO_UPDATES;
- else if (p9_SDAR_MODE(event))
- *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+ else if (sdar_mod_val(event))
+ *mmcra |= sdar_mod_val(event) << MMCRA_SDAR_MODE_SHIFT;
else
*mmcra |= MMCRA_SDAR_MODE_DCACHE;
} else
@@ -134,7 +144,11 @@ static bool is_thresh_cmp_valid(u64 event)
/*
* Check the mantissa upper two bits are not zero, unless the
* exponent is also zero. See the THRESH_CMP_MANTISSA doc.
+ * Power10: thresh_cmp is replaced by l2_l3 event select.
*/
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ return false;
+
cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
exp = cmp >> 7;
@@ -251,7 +265,12 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
unit = (event >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
- cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK;
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ cache = (event >> EVENT_CACHE_SEL_SHIFT) &
+ p10_EVENT_CACHE_SEL_MASK;
+ else
+ cache = (event >> EVENT_CACHE_SEL_SHIFT) &
+ EVENT_CACHE_SEL_MASK;
ebb = (event >> EVENT_EBB_SHIFT) & EVENT_EBB_MASK;
if (pmc) {
@@ -283,7 +302,10 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
}
if (unit >= 6 && unit <= 9) {
- if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (cpu_has_feature(CPU_FTR_ARCH_31) && (unit == 6)) {
+ mask |= CNST_L2L3_GROUP_MASK;
+ value |= CNST_L2L3_GROUP_VAL(event >> p10_L2L3_EVENT_SHIFT);
+ } else if (cpu_has_feature(CPU_FTR_ARCH_300)) {
mask |= CNST_CACHE_GROUP_MASK;
value |= CNST_CACHE_GROUP_VAL(event & 0xff);
@@ -363,10 +385,11 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
}
int isa207_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[],
+ unsigned int hwc[], struct mmcr_regs *mmcr,
struct perf_event *pevents[])
{
unsigned long mmcra, mmcr1, mmcr2, unit, combine, psel, cache, val;
+ unsigned long mmcr3;
unsigned int pmc, pmc_inuse;
int i;
@@ -379,7 +402,14 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
pmc_inuse |= 1 << pmc;
}
- mmcra = mmcr1 = mmcr2 = 0;
+ mmcra = mmcr1 = mmcr2 = mmcr3 = 0;
+
+ /*
+ * Disable bhrb unless explicitly requested
+ * by setting MMCRA (BHRBRD) bit.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ mmcra |= MMCRA_BHRB_DISABLE;
/* Second pass: assign PMCs, set all MMCR1 fields */
for (i = 0; i < n_ev; ++i) {
@@ -438,8 +468,17 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcra |= val << MMCRA_THR_CTL_SHIFT;
val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK;
mmcra |= val << MMCRA_THR_SEL_SHIFT;
- val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
- mmcra |= thresh_cmp_val(val);
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ val = (event[i] >> EVENT_THR_CMP_SHIFT) &
+ EVENT_THR_CMP_MASK;
+ mmcra |= thresh_cmp_val(val);
+ }
+ }
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31) && (unit == 6)) {
+ val = (event[i] >> p10_L2L3_EVENT_SHIFT) &
+ p10_EVENT_L2L3_SEL_MASK;
+ mmcr2 |= val << p10_L2L3_SEL_SHIFT;
}
if (event[i] & EVENT_WANTS_BHRB) {
@@ -447,6 +486,11 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcra |= val << MMCRA_IFM_SHIFT;
}
+ /* set MMCRA (BHRBRD) to 0 if there is user request for BHRB */
+ if (cpu_has_feature(CPU_FTR_ARCH_31) &&
+ (has_branch_stack(pevents[i]) || (event[i] & EVENT_WANTS_BHRB)))
+ mmcra &= ~MMCRA_BHRB_DISABLE;
+
if (pevents[i]->attr.exclude_user)
mmcr2 |= MMCR2_FCP(pmc);
@@ -460,34 +504,43 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcr2 |= MMCR2_FCS(pmc);
}
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ if (pmc <= 4) {
+ val = (event[i] >> p10_EVENT_MMCR3_SHIFT) &
+ p10_EVENT_MMCR3_MASK;
+ mmcr3 |= val << MMCR3_SHIFT(pmc);
+ }
+ }
+
hwc[i] = pmc - 1;
}
/* Return MMCRx values */
- mmcr[0] = 0;
+ mmcr->mmcr0 = 0;
/* pmc_inuse is 1-based */
if (pmc_inuse & 2)
- mmcr[0] = MMCR0_PMC1CE;
+ mmcr->mmcr0 = MMCR0_PMC1CE;
if (pmc_inuse & 0x7c)
- mmcr[0] |= MMCR0_PMCjCE;
+ mmcr->mmcr0 |= MMCR0_PMCjCE;
/* If we're not using PMC 5 or 6, freeze them */
if (!(pmc_inuse & 0x60))
- mmcr[0] |= MMCR0_FC56;
+ mmcr->mmcr0 |= MMCR0_FC56;
- mmcr[1] = mmcr1;
- mmcr[2] = mmcra;
- mmcr[3] = mmcr2;
+ mmcr->mmcr1 = mmcr1;
+ mmcr->mmcra = mmcra;
+ mmcr->mmcr2 = mmcr2;
+ mmcr->mmcr3 = mmcr3;
return 0;
}
-void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+void isa207_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr)
{
if (pmc <= 3)
- mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1));
+ mmcr->mmcr1 &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1));
}
static int find_alternative(u64 event, const unsigned int ev_alt[][MAX_ALT], int size)
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 63fd4f3f6013..044de65e96b9 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -87,6 +87,31 @@
EVENT_LINUX_MASK | \
EVENT_PSEL_MASK))
+/* Contants to support power10 raw encoding format */
+#define p10_SDAR_MODE_SHIFT 22
+#define p10_SDAR_MODE_MASK 0x3ull
+#define p10_SDAR_MODE(v) (((v) >> p10_SDAR_MODE_SHIFT) & \
+ p10_SDAR_MODE_MASK)
+#define p10_EVENT_L2L3_SEL_MASK 0x1f
+#define p10_L2L3_SEL_SHIFT 3
+#define p10_L2L3_EVENT_SHIFT 40
+#define p10_EVENT_THRESH_MASK 0xffffull
+#define p10_EVENT_CACHE_SEL_MASK 0x3ull
+#define p10_EVENT_MMCR3_MASK 0x7fffull
+#define p10_EVENT_MMCR3_SHIFT 45
+
+#define p10_EVENT_VALID_MASK \
+ ((p10_SDAR_MODE_MASK << p10_SDAR_MODE_SHIFT | \
+ (p10_EVENT_THRESH_MASK << EVENT_THRESH_SHIFT) | \
+ (EVENT_SAMPLE_MASK << EVENT_SAMPLE_SHIFT) | \
+ (p10_EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT) | \
+ (EVENT_PMC_MASK << EVENT_PMC_SHIFT) | \
+ (EVENT_UNIT_MASK << EVENT_UNIT_SHIFT) | \
+ (p9_EVENT_COMBINE_MASK << p9_EVENT_COMBINE_SHIFT) | \
+ (p10_EVENT_MMCR3_MASK << p10_EVENT_MMCR3_SHIFT) | \
+ (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \
+ EVENT_LINUX_MASK | \
+ EVENT_PSEL_MASK))
/*
* Layout of constraint bits:
*
@@ -135,6 +160,9 @@
#define CNST_CACHE_PMC4_VAL (1ull << 54)
#define CNST_CACHE_PMC4_MASK CNST_CACHE_PMC4_VAL
+#define CNST_L2L3_GROUP_VAL(v) (((v) & 0x1full) << 55)
+#define CNST_L2L3_GROUP_MASK CNST_L2L3_GROUP_VAL(0x1f)
+
/*
* For NC we are counting up to 4 events. This requires three bits, and we need
* the fifth event to overflow and set the 4th bit. To achieve that we bias the
@@ -191,7 +219,7 @@
#define MMCRA_THR_CTR_EXP(v) (((v) >> MMCRA_THR_CTR_EXP_SHIFT) &\
MMCRA_THR_CTR_EXP_MASK)
-/* MMCR1 Threshold Compare bit constant for power9 */
+/* MMCRA Threshold Compare bit constant for power9 */
#define p9_MMCRA_THR_CMP_SHIFT 45
/* Bits in MMCR2 for PowerISA v2.07 */
@@ -202,6 +230,9 @@
#define MAX_ALT 2
#define MAX_PMU_COUNTERS 6
+/* Bits in MMCR3 for PowerISA v3.10 */
+#define MMCR3_SHIFT(pmc) (49 - (15 * ((pmc) - 1)))
+
#define ISA207_SIER_TYPE_SHIFT 15
#define ISA207_SIER_TYPE_MASK (0x7ull << ISA207_SIER_TYPE_SHIFT)
@@ -217,9 +248,9 @@
int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp);
int isa207_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[],
+ unsigned int hwc[], struct mmcr_regs *mmcr,
struct perf_event *pevents[]);
-void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[]);
+void isa207_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr);
int isa207_get_alternatives(u64 event, u64 alt[], int size, unsigned int flags,
const unsigned int ev_alt[][MAX_ALT]);
void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
diff --git a/arch/powerpc/perf/mpc7450-pmu.c b/arch/powerpc/perf/mpc7450-pmu.c
index 4d5ef92511d1..1919e9df9165 100644
--- a/arch/powerpc/perf/mpc7450-pmu.c
+++ b/arch/powerpc/perf/mpc7450-pmu.c
@@ -257,7 +257,7 @@ static const u32 pmcsel_mask[N_COUNTER] = {
* Compute MMCR0/1/2 values for a set of events.
*/
static int mpc7450_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[],
- unsigned long mmcr[],
+ struct mmcr_regs *mmcr,
struct perf_event *pevents[])
{
u8 event_index[N_CLASSES][N_COUNTER];
@@ -321,9 +321,16 @@ static int mpc7450_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[],
mmcr0 |= MMCR0_PMCnCE;
/* Return MMCRx values */
- mmcr[0] = mmcr0;
- mmcr[1] = mmcr1;
- mmcr[2] = mmcr2;
+ mmcr->mmcr0 = mmcr0;
+ mmcr->mmcr1 = mmcr1;
+ mmcr->mmcr2 = mmcr2;
+ /*
+ * 32-bit doesn't have an MMCRA and uses SPRN_MMCR2 to define
+ * SPRN_MMCRA. So assign mmcra of cpu_hw_events with `mmcr2`
+ * value to ensure that any write to this SPRN_MMCRA will
+ * use mmcr2 value.
+ */
+ mmcr->mmcra = mmcr2;
return 0;
}
@@ -331,12 +338,12 @@ static int mpc7450_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[],
* Disable counting by a PMC.
* Note that the pmc argument is 0-based here, not 1-based.
*/
-static void mpc7450_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+static void mpc7450_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr)
{
if (pmc <= 1)
- mmcr[0] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
+ mmcr->mmcr0 &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
else
- mmcr[1] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
+ mmcr->mmcr1 &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
}
static int mpc7450_generic_events[] = {
@@ -354,7 +361,7 @@ static int mpc7450_generic_events[] = {
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x225 },
[C(OP_WRITE)] = { 0, 0x227 },
diff --git a/arch/powerpc/perf/power10-events-list.h b/arch/powerpc/perf/power10-events-list.h
new file mode 100644
index 000000000000..60c1b8111082
--- /dev/null
+++ b/arch/powerpc/perf/power10-events-list.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Performance counter support for POWER10 processors.
+ *
+ * Copyright 2020 Madhavan Srinivasan, IBM Corporation.
+ * Copyright 2020 Athira Rajeev, IBM Corporation.
+ */
+
+/*
+ * Power10 event codes.
+ */
+EVENT(PM_RUN_CYC, 0x600f4);
+EVENT(PM_DISP_STALL_CYC, 0x100f8);
+EVENT(PM_EXEC_STALL, 0x30008);
+EVENT(PM_RUN_INST_CMPL, 0x500fa);
+EVENT(PM_BR_CMPL, 0x4d05e);
+EVENT(PM_BR_MPRED_CMPL, 0x400f6);
+
+/* All L1 D cache load references counted at finish, gated by reject */
+EVENT(PM_LD_REF_L1, 0x100fc);
+/* Load Missed L1 */
+EVENT(PM_LD_MISS_L1, 0x3e054);
+/* Store Missed L1 */
+EVENT(PM_ST_MISS_L1, 0x300f0);
+/* L1 cache data prefetches */
+EVENT(PM_LD_PREFETCH_CACHE_LINE_MISS, 0x1002c);
+/* Demand iCache Miss */
+EVENT(PM_L1_ICACHE_MISS, 0x200fc);
+/* Instruction fetches from L1 */
+EVENT(PM_INST_FROM_L1, 0x04080);
+/* Instruction Demand sectors wriittent into IL1 */
+EVENT(PM_INST_FROM_L1MISS, 0x03f00000001c040);
+/* Instruction prefetch written into IL1 */
+EVENT(PM_IC_PREF_REQ, 0x040a0);
+/* The data cache was reloaded from local core's L3 due to a demand load */
+EVENT(PM_DATA_FROM_L3, 0x01340000001c040);
+/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
+EVENT(PM_DATA_FROM_L3MISS, 0x300fe);
+/* Data PTEG reload */
+EVENT(PM_DTLB_MISS, 0x300fc);
+/* ITLB Reloaded */
+EVENT(PM_ITLB_MISS, 0x400fc);
+
+EVENT(PM_RUN_CYC_ALT, 0x0001e);
+EVENT(PM_RUN_INST_CMPL_ALT, 0x00002);
+
+/*
+ * Memory Access Events
+ *
+ * Primary PMU event used here is PM_MRK_INST_CMPL (0x401e0)
+ * To enable capturing of memory profiling, these MMCRA bits
+ * needs to be programmed and corresponding raw event format
+ * encoding.
+ *
+ * MMCRA bits encoding needed are
+ * SM (Sampling Mode)
+ * EM (Eligibility for Random Sampling)
+ * TECE (Threshold Event Counter Event)
+ * TS (Threshold Start Event)
+ * TE (Threshold End Event)
+ *
+ * Corresponding Raw Encoding bits:
+ * sample [EM,SM]
+ * thresh_sel (TECE)
+ * thresh start (TS)
+ * thresh end (TE)
+ */
+
+EVENT(MEM_LOADS, 0x34340401e0);
+EVENT(MEM_STORES, 0x343c0401e0);
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
new file mode 100644
index 000000000000..f7cff7f36a1c
--- /dev/null
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -0,0 +1,419 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Performance counter support for POWER10 processors.
+ *
+ * Copyright 2020 Madhavan Srinivasan, IBM Corporation.
+ * Copyright 2020 Athira Rajeev, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "power10-pmu: " fmt
+
+#include "isa207-common.h"
+#include "internal.h"
+
+/*
+ * Raw event encoding for Power10:
+ *
+ * 60 56 52 48 44 40 36 32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ * | | [ ] [ src_match ] [ src_mask ] | [ ] [ l2l3_sel ] [ thresh_ctl ]
+ * | | | | | |
+ * | | *- IFM (Linux) | | thresh start/stop -*
+ * | *- BHRB (Linux) | src_sel
+ * *- EBB (Linux) *invert_bit
+ *
+ * 28 24 20 16 12 8 4 0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ * [ ] [ sample ] [ ] [ ] [ pmc ] [unit ] [ ] m [ pmcxsel ]
+ * | | | | | |
+ * | | | | | *- mark
+ * | | | *- L1/L2/L3 cache_sel |
+ * | | sdar_mode |
+ * | *- sampling mode for marked events *- combine
+ * |
+ * *- thresh_sel
+ *
+ * Below uses IBM bit numbering.
+ *
+ * MMCR1[x:y] = unit (PMCxUNIT)
+ * MMCR1[24] = pmc1combine[0]
+ * MMCR1[25] = pmc1combine[1]
+ * MMCR1[26] = pmc2combine[0]
+ * MMCR1[27] = pmc2combine[1]
+ * MMCR1[28] = pmc3combine[0]
+ * MMCR1[29] = pmc3combine[1]
+ * MMCR1[30] = pmc4combine[0]
+ * MMCR1[31] = pmc4combine[1]
+ *
+ * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011
+ * MMCR1[20:27] = thresh_ctl
+ * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001
+ * MMCR1[20:27] = thresh_ctl
+ * else
+ * MMCRA[48:55] = thresh_ctl (THRESH START/END)
+ *
+ * if thresh_sel:
+ * MMCRA[45:47] = thresh_sel
+ *
+ * if l2l3_sel:
+ * MMCR2[56:60] = l2l3_sel[0:4]
+ *
+ * MMCR1[16] = cache_sel[0]
+ * MMCR1[17] = cache_sel[1]
+ *
+ * if mark:
+ * MMCRA[63] = 1 (SAMPLE_ENABLE)
+ * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG)
+ * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE)
+ *
+ * if EBB and BHRB:
+ * MMCRA[32:33] = IFM
+ *
+ * MMCRA[SDAR_MODE] = sdar_mode[0:1]
+ */
+
+/*
+ * Some power10 event codes.
+ */
+#define EVENT(_name, _code) enum{_name = _code}
+
+#include "power10-events-list.h"
+
+#undef EVENT
+
+/* MMCRA IFM bits - POWER10 */
+#define POWER10_MMCRA_IFM1 0x0000000040000000UL
+#define POWER10_MMCRA_IFM2 0x0000000080000000UL
+#define POWER10_MMCRA_IFM3 0x00000000C0000000UL
+#define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL
+
+/* Table of alternatives, sorted by column 0 */
+static const unsigned int power10_event_alternatives[][MAX_ALT] = {
+ { PM_RUN_CYC_ALT, PM_RUN_CYC },
+ { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL },
+};
+
+static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+ int num_alt = 0;
+
+ num_alt = isa207_get_alternatives(event, alt,
+ ARRAY_SIZE(power10_event_alternatives), flags,
+ power10_event_alternatives);
+
+ return num_alt;
+}
+
+GENERIC_EVENT_ATTR(cpu-cycles, PM_RUN_CYC);
+GENERIC_EVENT_ATTR(instructions, PM_RUN_INST_CMPL);
+GENERIC_EVENT_ATTR(branch-instructions, PM_BR_CMPL);
+GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED_CMPL);
+GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1);
+GENERIC_EVENT_ATTR(mem-loads, MEM_LOADS);
+GENERIC_EVENT_ATTR(mem-stores, MEM_STORES);
+
+CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1);
+CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1);
+CACHE_EVENT_ATTR(L1-dcache-prefetches, PM_LD_PREFETCH_CACHE_LINE_MISS);
+CACHE_EVENT_ATTR(L1-dcache-store-misses, PM_ST_MISS_L1);
+CACHE_EVENT_ATTR(L1-icache-load-misses, PM_L1_ICACHE_MISS);
+CACHE_EVENT_ATTR(L1-icache-loads, PM_INST_FROM_L1);
+CACHE_EVENT_ATTR(L1-icache-prefetches, PM_IC_PREF_REQ);
+CACHE_EVENT_ATTR(LLC-load-misses, PM_DATA_FROM_L3MISS);
+CACHE_EVENT_ATTR(LLC-loads, PM_DATA_FROM_L3);
+CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL);
+CACHE_EVENT_ATTR(branch-loads, PM_BR_CMPL);
+CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS);
+CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS);
+
+static struct attribute *power10_events_attr[] = {
+ GENERIC_EVENT_PTR(PM_RUN_CYC),
+ GENERIC_EVENT_PTR(PM_RUN_INST_CMPL),
+ GENERIC_EVENT_PTR(PM_BR_CMPL),
+ GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL),
+ GENERIC_EVENT_PTR(PM_LD_REF_L1),
+ GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+ GENERIC_EVENT_PTR(MEM_LOADS),
+ GENERIC_EVENT_PTR(MEM_STORES),
+ CACHE_EVENT_PTR(PM_LD_MISS_L1),
+ CACHE_EVENT_PTR(PM_LD_REF_L1),
+ CACHE_EVENT_PTR(PM_LD_PREFETCH_CACHE_LINE_MISS),
+ CACHE_EVENT_PTR(PM_ST_MISS_L1),
+ CACHE_EVENT_PTR(PM_L1_ICACHE_MISS),
+ CACHE_EVENT_PTR(PM_INST_FROM_L1),
+ CACHE_EVENT_PTR(PM_IC_PREF_REQ),
+ CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS),
+ CACHE_EVENT_PTR(PM_DATA_FROM_L3),
+ CACHE_EVENT_PTR(PM_BR_MPRED_CMPL),
+ CACHE_EVENT_PTR(PM_BR_CMPL),
+ CACHE_EVENT_PTR(PM_DTLB_MISS),
+ CACHE_EVENT_PTR(PM_ITLB_MISS),
+ NULL
+};
+
+static struct attribute_group power10_pmu_events_group = {
+ .name = "events",
+ .attrs = power10_events_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-59");
+PMU_FORMAT_ATTR(pmcxsel, "config:0-7");
+PMU_FORMAT_ATTR(mark, "config:8");
+PMU_FORMAT_ATTR(combine, "config:10-11");
+PMU_FORMAT_ATTR(unit, "config:12-15");
+PMU_FORMAT_ATTR(pmc, "config:16-19");
+PMU_FORMAT_ATTR(cache_sel, "config:20-21");
+PMU_FORMAT_ATTR(sdar_mode, "config:22-23");
+PMU_FORMAT_ATTR(sample_mode, "config:24-28");
+PMU_FORMAT_ATTR(thresh_sel, "config:29-31");
+PMU_FORMAT_ATTR(thresh_stop, "config:32-35");
+PMU_FORMAT_ATTR(thresh_start, "config:36-39");
+PMU_FORMAT_ATTR(l2l3_sel, "config:40-44");
+PMU_FORMAT_ATTR(src_sel, "config:45-46");
+PMU_FORMAT_ATTR(invert_bit, "config:47");
+PMU_FORMAT_ATTR(src_mask, "config:48-53");
+PMU_FORMAT_ATTR(src_match, "config:54-59");
+
+static struct attribute *power10_pmu_format_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_pmcxsel.attr,
+ &format_attr_mark.attr,
+ &format_attr_combine.attr,
+ &format_attr_unit.attr,
+ &format_attr_pmc.attr,
+ &format_attr_cache_sel.attr,
+ &format_attr_sdar_mode.attr,
+ &format_attr_sample_mode.attr,
+ &format_attr_thresh_sel.attr,
+ &format_attr_thresh_stop.attr,
+ &format_attr_thresh_start.attr,
+ &format_attr_l2l3_sel.attr,
+ &format_attr_src_sel.attr,
+ &format_attr_invert_bit.attr,
+ &format_attr_src_mask.attr,
+ &format_attr_src_match.attr,
+ NULL,
+};
+
+static struct attribute_group power10_pmu_format_group = {
+ .name = "format",
+ .attrs = power10_pmu_format_attr,
+};
+
+static const struct attribute_group *power10_pmu_attr_groups[] = {
+ &power10_pmu_format_group,
+ &power10_pmu_events_group,
+ NULL,
+};
+
+static int power10_generic_events[] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC,
+ [PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL,
+ [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1,
+ [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1,
+};
+
+static u64 power10_bhrb_filter_map(u64 branch_sample_type)
+{
+ u64 pmu_bhrb_filter = 0;
+
+ /* BHRB and regular PMU events share the same privilege state
+ * filter configuration. BHRB is always recorded along with a
+ * regular PMU event. As the privilege state filter is handled
+ * in the basic PMC configuration of the accompanying regular
+ * PMU event, we ignore any separate BHRB specific request.
+ */
+
+ /* No branch filter requested */
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY)
+ return pmu_bhrb_filter;
+
+ /* Invalid branch filter options - HW does not support */
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+ return -1;
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL) {
+ pmu_bhrb_filter |= POWER10_MMCRA_IFM2;
+ return pmu_bhrb_filter;
+ }
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_COND) {
+ pmu_bhrb_filter |= POWER10_MMCRA_IFM3;
+ return pmu_bhrb_filter;
+ }
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_CALL)
+ return -1;
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) {
+ pmu_bhrb_filter |= POWER10_MMCRA_IFM1;
+ return pmu_bhrb_filter;
+ }
+
+ /* Every thing else is unsupported */
+ return -1;
+}
+
+static void power10_config_bhrb(u64 pmu_bhrb_filter)
+{
+ pmu_bhrb_filter &= POWER10_MMCRA_BHRB_MASK;
+
+ /* Enable BHRB filter in PMU */
+ mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
+}
+
+#define C(x) PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static u64 power10_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_LD_REF_L1,
+ [C(RESULT_MISS)] = PM_LD_MISS_L1,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_ST_MISS_L1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_LD_PREFETCH_CACHE_LINE_MISS,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_INST_FROM_L1,
+ [C(RESULT_MISS)] = PM_L1_ICACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = PM_INST_FROM_L1MISS,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_IC_PREF_REQ,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_DATA_FROM_L3,
+ [C(RESULT_MISS)] = PM_DATA_FROM_L3MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_DTLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_BR_CMPL,
+ [C(RESULT_MISS)] = PM_BR_MPRED_CMPL,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+};
+
+#undef C
+
+static struct power_pmu power10_pmu = {
+ .name = "POWER10",
+ .n_counter = MAX_PMU_COUNTERS,
+ .add_fields = ISA207_ADD_FIELDS,
+ .test_adder = ISA207_TEST_ADDER,
+ .group_constraint_mask = CNST_CACHE_PMC4_MASK,
+ .group_constraint_val = CNST_CACHE_PMC4_VAL,
+ .compute_mmcr = isa207_compute_mmcr,
+ .config_bhrb = power10_config_bhrb,
+ .bhrb_filter_map = power10_bhrb_filter_map,
+ .get_constraint = isa207_get_constraint,
+ .get_alternatives = power10_get_alternatives,
+ .get_mem_data_src = isa207_get_mem_data_src,
+ .get_mem_weight = isa207_get_mem_weight,
+ .disable_pmc = isa207_disable_pmc,
+ .flags = PPMU_HAS_SIER | PPMU_ARCH_207S |
+ PPMU_ARCH_31,
+ .n_generic = ARRAY_SIZE(power10_generic_events),
+ .generic_events = power10_generic_events,
+ .cache_events = &power10_cache_events,
+ .attr_groups = power10_pmu_attr_groups,
+ .bhrb_nr = 32,
+};
+
+int init_power10_pmu(void)
+{
+ int rc;
+
+ /* Comes from cpu_specs[] */
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10"))
+ return -ENODEV;
+
+ rc = register_power_pmu(&power10_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/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c
index f8574547fc6b..a62b2cd7914f 100644
--- a/arch/powerpc/perf/power5+-pmu.c
+++ b/arch/powerpc/perf/power5+-pmu.c
@@ -448,7 +448,8 @@ static int power5p_marked_instr_event(u64 event)
}
static int power5p_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
+ unsigned int hwc[], struct mmcr_regs *mmcr,
+ struct perf_event *pevents[])
{
unsigned long mmcr1 = 0;
unsigned long mmcra = 0;
@@ -586,20 +587,20 @@ static int power5p_compute_mmcr(u64 event[], int n_ev,
}
/* Return MMCRx values */
- mmcr[0] = 0;
+ mmcr->mmcr0 = 0;
if (pmc_inuse & 1)
- mmcr[0] = MMCR0_PMC1CE;
+ mmcr->mmcr0 = MMCR0_PMC1CE;
if (pmc_inuse & 0x3e)
- mmcr[0] |= MMCR0_PMCjCE;
- mmcr[1] = mmcr1;
- mmcr[2] = mmcra;
+ mmcr->mmcr0 |= MMCR0_PMCjCE;
+ mmcr->mmcr1 = mmcr1;
+ mmcr->mmcra = mmcra;
return 0;
}
-static void power5p_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+static void power5p_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr)
{
if (pmc <= 3)
- mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
+ mmcr->mmcr1 &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
}
static int power5p_generic_events[] = {
@@ -618,7 +619,7 @@ static int power5p_generic_events[] = {
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x1c10a8, 0x3c1088 },
[C(OP_WRITE)] = { 0x2c10a8, 0xc10c3 },
diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c
index da52ecab7c9a..8732b587cf71 100644
--- a/arch/powerpc/perf/power5-pmu.c
+++ b/arch/powerpc/perf/power5-pmu.c
@@ -379,7 +379,8 @@ static int power5_marked_instr_event(u64 event)
}
static int power5_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
+ unsigned int hwc[], struct mmcr_regs *mmcr,
+ struct perf_event *pevents[])
{
unsigned long mmcr1 = 0;
unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
@@ -528,20 +529,20 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
}
/* Return MMCRx values */
- mmcr[0] = 0;
+ mmcr->mmcr0 = 0;
if (pmc_inuse & 1)
- mmcr[0] = MMCR0_PMC1CE;
+ mmcr->mmcr0 = MMCR0_PMC1CE;
if (pmc_inuse & 0x3e)
- mmcr[0] |= MMCR0_PMCjCE;
- mmcr[1] = mmcr1;
- mmcr[2] = mmcra;
+ mmcr->mmcr0 |= MMCR0_PMCjCE;
+ mmcr->mmcr1 = mmcr1;
+ mmcr->mmcra = mmcra;
return 0;
}
-static void power5_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+static void power5_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr)
{
if (pmc <= 3)
- mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
+ mmcr->mmcr1 &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
}
static int power5_generic_events[] = {
@@ -560,7 +561,7 @@ static int power5_generic_events[] = {
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x4c1090, 0x3c1088 },
[C(OP_WRITE)] = { 0x3c1090, 0xc10c3 },
diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c
index 3929cacf72ed..0e318cf87129 100644
--- a/arch/powerpc/perf/power6-pmu.c
+++ b/arch/powerpc/perf/power6-pmu.c
@@ -171,7 +171,7 @@ static int power6_marked_instr_event(u64 event)
* Assign PMC numbers and compute MMCR1 value for a set of events
*/
static int p6_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
+ unsigned int hwc[], struct mmcr_regs *mmcr, struct perf_event *pevents[])
{
unsigned long mmcr1 = 0;
unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
@@ -243,13 +243,13 @@ static int p6_compute_mmcr(u64 event[], int n_ev,
if (pmc < 4)
mmcr1 |= (unsigned long)psel << MMCR1_PMCSEL_SH(pmc);
}
- mmcr[0] = 0;
+ mmcr->mmcr0 = 0;
if (pmc_inuse & 1)
- mmcr[0] = MMCR0_PMC1CE;
+ mmcr->mmcr0 = MMCR0_PMC1CE;
if (pmc_inuse & 0xe)
- mmcr[0] |= MMCR0_PMCjCE;
- mmcr[1] = mmcr1;
- mmcr[2] = mmcra;
+ mmcr->mmcr0 |= MMCR0_PMCjCE;
+ mmcr->mmcr1 = mmcr1;
+ mmcr->mmcra = mmcra;
return 0;
}
@@ -457,11 +457,11 @@ static int p6_get_alternatives(u64 event, unsigned int flags, u64 alt[])
return nalt;
}
-static void p6_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+static void p6_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr)
{
/* Set PMCxSEL to 0 to disable PMCx */
if (pmc <= 3)
- mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
+ mmcr->mmcr1 &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
}
static int power6_generic_events[] = {
@@ -481,7 +481,7 @@ static int power6_generic_events[] = {
* are event codes.
* The "DTLB" and "ITLB" events relate to the DERAT and IERAT.
*/
-static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x280030, 0x80080 },
[C(OP_WRITE)] = { 0x180032, 0x80088 },
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index a137813a3076..5e0bf09cf077 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -242,7 +242,8 @@ static int power7_marked_instr_event(u64 event)
}
static int power7_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
+ unsigned int hwc[], struct mmcr_regs *mmcr,
+ struct perf_event *pevents[])
{
unsigned long mmcr1 = 0;
unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
@@ -298,20 +299,20 @@ static int power7_compute_mmcr(u64 event[], int n_ev,
}
/* Return MMCRx values */
- mmcr[0] = 0;
+ mmcr->mmcr0 = 0;
if (pmc_inuse & 1)
- mmcr[0] = MMCR0_PMC1CE;
+ mmcr->mmcr0 = MMCR0_PMC1CE;
if (pmc_inuse & 0x3e)
- mmcr[0] |= MMCR0_PMCjCE;
- mmcr[1] = mmcr1;
- mmcr[2] = mmcra;
+ mmcr->mmcr0 |= MMCR0_PMCjCE;
+ mmcr->mmcr1 = mmcr1;
+ mmcr->mmcra = mmcra;
return 0;
}
-static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+static void power7_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr)
{
if (pmc <= 3)
- mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
+ mmcr->mmcr1 &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
}
static int power7_generic_events[] = {
@@ -332,7 +333,7 @@ static int power7_generic_events[] = {
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0xc880, 0x400f0 },
[C(OP_WRITE)] = { 0, 0x300f0 },
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 3a5fcc20ff31..5282e8415ddf 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -253,7 +253,7 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter)
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 08c3ef796198..05dae38b969a 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -310,7 +310,7 @@ static void power9_config_bhrb(u64 pmu_bhrb_filter)
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c
index 4035d93d87ab..d35223fb112c 100644
--- a/arch/powerpc/perf/ppc970-pmu.c
+++ b/arch/powerpc/perf/ppc970-pmu.c
@@ -253,7 +253,8 @@ static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[])
}
static int p970_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
+ unsigned int hwc[], struct mmcr_regs *mmcr,
+ struct perf_event *pevents[])
{
unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0;
unsigned int pmc, unit, byte, psel;
@@ -393,27 +394,26 @@ static int p970_compute_mmcr(u64 event[], int n_ev,
mmcra |= 0x2000; /* mark only one IOP per PPC instruction */
/* Return MMCRx values */
- mmcr[0] = mmcr0;
- mmcr[1] = mmcr1;
- mmcr[2] = mmcra;
+ mmcr->mmcr0 = mmcr0;
+ mmcr->mmcr1 = mmcr1;
+ mmcr->mmcra = mmcra;
return 0;
}
-static void p970_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+static void p970_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr)
{
- int shift, i;
+ int shift;
+ /*
+ * Setting the PMCxSEL field to 0x08 disables PMC x.
+ */
if (pmc <= 1) {
shift = MMCR0_PMC1SEL_SH - 7 * pmc;
- i = 0;
+ mmcr->mmcr0 = (mmcr->mmcr0 & ~(0x1fUL << shift)) | (0x08UL << shift);
} else {
shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2);
- i = 1;
+ mmcr->mmcr1 = (mmcr->mmcr1 & ~(0x1fUL << shift)) | (0x08UL << shift);
}
- /*
- * Setting the PMCxSEL field to 0x08 disables PMC x.
- */
- mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift);
}
static int ppc970_generic_events[] = {
@@ -432,7 +432,7 @@ static int ppc970_generic_events[] = {
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x8810, 0x3810 },
[C(OP_WRITE)] = { 0x7810, 0x813 },
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index fa3d29dcb57e..b77cbb0a50e1 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -160,7 +160,7 @@ config XES_MPC85xx
computers from Extreme Engineering Solutions (X-ES) based on
Freescale MPC85xx processors.
Manufacturer: Extreme Engineering Solutions, Inc.
- URL: <http://www.xes-inc.com/>
+ URL: <https://www.xes-inc.com/>
config STX_GP3
bool "Silicon Turnkey Express GP3"
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 0f7c8241912b..f2ff359041ee 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -44,6 +44,7 @@ config SPU_FS
tristate "SPU file system"
default m
depends on PPC_CELL
+ depends on COREDUMP
select SPU_BASE
help
The SPU file system is used to access Synergistic Processing
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 3b75e8f60609..026c181a98c5 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -66,13 +66,20 @@ static int match_context(const void *v, struct file *file, unsigned fd)
*/
static struct spu_context *coredump_next_context(int *fd)
{
+ struct spu_context *ctx;
struct file *file;
int n = iterate_fd(current->files, *fd, match_context, NULL);
if (!n)
return NULL;
*fd = n - 1;
+
+ rcu_read_lock();
file = fcheck(*fd);
- return SPUFS_I(file_inode(file))->i_ctx;
+ ctx = SPUFS_I(file_inode(file))->i_ctx;
+ get_spu_context(ctx);
+ rcu_read_unlock();
+
+ return ctx;
}
int spufs_coredump_extra_notes_size(void)
@@ -83,17 +90,23 @@ int spufs_coredump_extra_notes_size(void)
fd = 0;
while ((ctx = coredump_next_context(&fd)) != NULL) {
rc = spu_acquire_saved(ctx);
- if (rc)
+ if (rc) {
+ put_spu_context(ctx);
break;
+ }
+
rc = spufs_ctx_note_size(ctx, fd);
spu_release_saved(ctx);
- if (rc < 0)
+ if (rc < 0) {
+ put_spu_context(ctx);
break;
+ }
size += rc;
/* start searching the next fd next time */
fd++;
+ put_spu_context(ctx);
}
return size;
@@ -105,7 +118,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
size_t sz = spufs_coredump_read[i].size;
char fullname[80];
struct elf_note en;
- size_t ret;
+ int ret;
sprintf(fullname, "SPU/%d/%s", dfd, spufs_coredump_read[i].name);
en.n_namesz = strlen(fullname) + 1;
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 2dd467383a88..77513a80cef9 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -48,7 +48,7 @@ static bool default_stop_found;
* First stop state levels when SPR and TB loss can occur.
*/
static u64 pnv_first_tb_loss_level = MAX_STOP_STATE + 1;
-static u64 pnv_first_spr_loss_level = MAX_STOP_STATE + 1;
+static u64 deep_spr_loss_state = MAX_STOP_STATE + 1;
/*
* psscr value and mask of the deepest stop idle state.
@@ -73,9 +73,6 @@ static int pnv_save_sprs_for_deep_states(void)
*/
uint64_t lpcr_val = mfspr(SPRN_LPCR);
uint64_t hid0_val = mfspr(SPRN_HID0);
- uint64_t hid1_val = mfspr(SPRN_HID1);
- uint64_t hid4_val = mfspr(SPRN_HID4);
- uint64_t hid5_val = mfspr(SPRN_HID5);
uint64_t hmeer_val = mfspr(SPRN_HMEER);
uint64_t msr_val = MSR_IDLE;
uint64_t psscr_val = pnv_deepest_stop_psscr_val;
@@ -117,6 +114,9 @@ static int pnv_save_sprs_for_deep_states(void)
/* Only p8 needs to set extra HID regiters */
if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+ uint64_t hid1_val = mfspr(SPRN_HID1);
+ uint64_t hid4_val = mfspr(SPRN_HID4);
+ uint64_t hid5_val = mfspr(SPRN_HID5);
rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val);
if (rc != 0)
@@ -611,6 +611,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
unsigned long srr1;
unsigned long pls;
unsigned long mmcr0 = 0;
+ unsigned long mmcra = 0;
struct p9_sprs sprs = {}; /* avoid false used-uninitialised */
bool sprs_saved = false;
@@ -657,7 +658,22 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
*/
mmcr0 = mfspr(SPRN_MMCR0);
}
- if ((psscr & PSSCR_RL_MASK) >= pnv_first_spr_loss_level) {
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ /*
+ * POWER10 uses MMCRA (BHRBRD) as BHRB disable bit.
+ * If the user hasn't asked for the BHRB to be
+ * written, the value of MMCRA[BHRBRD] is 1.
+ * On wakeup from stop, MMCRA[BHRBD] will be 0,
+ * since it is previleged resource and will be lost.
+ * Thus, if we do not save and restore the MMCRA[BHRBD],
+ * hardware will be needlessly writing to the BHRB
+ * in problem mode.
+ */
+ mmcra = mfspr(SPRN_MMCRA);
+ }
+
+ if ((psscr & PSSCR_RL_MASK) >= deep_spr_loss_state) {
sprs.lpcr = mfspr(SPRN_LPCR);
sprs.hfscr = mfspr(SPRN_HFSCR);
sprs.fscr = mfspr(SPRN_FSCR);
@@ -700,8 +716,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));
if ((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS) {
- unsigned long mmcra;
-
/*
* We don't need an isync after the mtsprs here because the
* upcoming mtmsrd is execution synchronizing.
@@ -721,6 +735,10 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
mtspr(SPRN_MMCR0, mmcr0);
}
+ /* Reload MMCRA to restore BHRB disable bit for POWER10 */
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ mtspr(SPRN_MMCRA, mmcra);
+
/*
* DD2.2 and earlier need to set then clear bit 60 in MMCRA
* to ensure the PMU starts running.
@@ -741,7 +759,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
* just always test PSSCR for SPR/TB state loss.
*/
pls = (psscr & PSSCR_PLS) >> PSSCR_PLS_SHIFT;
- if (likely(pls < pnv_first_spr_loss_level)) {
+ if (likely(pls < deep_spr_loss_state)) {
if (sprs_saved)
atomic_stop_thread_idle();
goto out;
@@ -1088,7 +1106,7 @@ static void __init pnv_power9_idle_init(void)
* the deepest loss-less (OPAL_PM_STOP_INST_FAST) stop state.
*/
pnv_first_tb_loss_level = MAX_STOP_STATE + 1;
- pnv_first_spr_loss_level = MAX_STOP_STATE + 1;
+ deep_spr_loss_state = MAX_STOP_STATE + 1;
for (i = 0; i < nr_pnv_idle_states; i++) {
int err;
struct pnv_idle_states_t *state = &pnv_idle_states[i];
@@ -1099,8 +1117,8 @@ static void __init pnv_power9_idle_init(void)
pnv_first_tb_loss_level = psscr_rl;
if ((state->flags & OPAL_PM_LOSE_FULL_CONTEXT) &&
- (pnv_first_spr_loss_level > psscr_rl))
- pnv_first_spr_loss_level = psscr_rl;
+ (deep_spr_loss_state > psscr_rl))
+ deep_spr_loss_state = psscr_rl;
/*
* The idle code does not deal with TB loss occurring
@@ -1111,8 +1129,8 @@ static void __init pnv_power9_idle_init(void)
* compatibility.
*/
if ((state->flags & OPAL_PM_TIMEBASE_STOP) &&
- (pnv_first_spr_loss_level > psscr_rl))
- pnv_first_spr_loss_level = psscr_rl;
+ (deep_spr_loss_state > psscr_rl))
+ deep_spr_loss_state = psscr_rl;
err = validate_psscr_val_mask(&state->psscr_val,
&state->psscr_mask,
@@ -1158,7 +1176,7 @@ static void __init pnv_power9_idle_init(void)
}
pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%llx\n",
- pnv_first_spr_loss_level);
+ deep_spr_loss_state);
pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%llx\n",
pnv_first_tb_loss_level);
@@ -1205,7 +1223,7 @@ static void __init pnv_probe_idle_states(void)
return;
}
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ if (pvr_version_is(PVR_POWER9))
pnv_power9_idle_init();
for (i = 0; i < nr_pnv_idle_states; i++)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
index f923359d8afc..5218f5da2737 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
@@ -166,7 +166,7 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index,
if (!ptce) {
ptce = pnv_tce(tbl, false, idx, alloc);
if (!ptce)
- return alloc ? H_HARDWARE : H_TOO_HARD;
+ return -ENOMEM;
}
if (newtce & TCE_PCI_WRITE)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 73a63efcf855..31c3e6d58c41 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1490,7 +1490,7 @@ static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
}
}
-void pnv_pci_sriov_disable(struct pci_dev *pdev)
+static void pnv_pci_sriov_disable(struct pci_dev *pdev)
{
struct pci_bus *bus;
struct pci_controller *hose;
@@ -1600,7 +1600,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
}
}
-int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+static int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
{
struct pci_bus *bus;
struct pci_controller *hose;
@@ -1715,7 +1715,7 @@ m64_failed:
return ret;
}
-int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
+static int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
{
pnv_pci_sriov_disable(pdev);
@@ -1724,7 +1724,7 @@ int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
return 0;
}
-int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+static int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
{
/* Allocate PCI data */
add_sriov_vf_pdns(pdev);
@@ -1885,19 +1885,6 @@ static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev,
return false;
}
-static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
-{
- struct pci_dev *dev;
-
- list_for_each_entry(dev, &bus->devices, bus_list) {
- set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
- dev->dev.archdata.dma_offset = pe->tce_bypass_base;
-
- if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
- pnv_ioda_setup_bus_dma(pe, dev->subordinate);
- }
-}
-
static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb,
bool real_mode)
{
@@ -2547,6 +2534,19 @@ static long pnv_pci_ioda2_create_table_userspace(
return ret;
}
+static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
+ dev->dev.archdata.dma_offset = pe->tce_bypass_base;
+
+ if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
+ pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+ }
+}
+
static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
{
struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 3bc188da82ba..7fcb88623081 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -399,7 +399,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
static unsigned long pnv_memory_block_size(void)
{
- return 256UL * 1024 * 1024;
+ /*
+ * We map the kernel linear region with 1GB large pages on radix. For
+ * memory hot unplug to work our memory block size must be at least
+ * this size.
+ */
+ if (radix_enabled())
+ return radix_mem_block_size;
+ else
+ return 256UL * 1024 * 1024;
}
#endif
diff --git a/arch/powerpc/platforms/powernv/vas-fault.c b/arch/powerpc/platforms/powernv/vas-fault.c
index 266a6ca5e15e..3d21fce254b7 100644
--- a/arch/powerpc/platforms/powernv/vas-fault.c
+++ b/arch/powerpc/platforms/powernv/vas-fault.c
@@ -79,7 +79,7 @@ static void update_csb(struct vas_window *window,
csb_addr = (void __user *)be64_to_cpu(crb->csb_addr);
memset(&csb, 0, sizeof(csb));
- csb.cc = CSB_CC_TRANSLATION;
+ csb.cc = CSB_CC_FAULT_ADDRESS;
csb.ce = CSB_CE_TERMINATION;
csb.cs = 0;
csb.count = 0;
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ace117f99d94..47760fb515cc 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -24,6 +24,7 @@
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
+#include <linux/crash_dump.h>
#include <asm/eeh.h>
#include <asm/eeh_event.h>
@@ -80,6 +81,152 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
eeh_probe_device(pdev);
}
+
+/**
+ * pseries_eeh_get_config_addr - Retrieve config address
+ *
+ * Retrieve the assocated config address. Actually, there're 2 RTAS
+ * function calls dedicated for the purpose. We need implement
+ * it through the new function and then the old one. Besides,
+ * you should make sure the config address is figured out from
+ * FDT node before calling the function.
+ *
+ * It's notable that zero'ed return value means invalid PE config
+ * address.
+ */
+static int pseries_eeh_get_config_addr(struct pci_controller *phb, int config_addr)
+{
+ int ret = 0;
+ int rets[3];
+
+ if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) {
+ /*
+ * First of all, we need to make sure there has one PE
+ * associated with the device. Otherwise, PE address is
+ * meaningless.
+ */
+ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
+ config_addr, BUID_HI(phb->buid),
+ BUID_LO(phb->buid), 1);
+ if (ret || (rets[0] == 0))
+ return 0;
+
+ /* Retrieve the associated PE config address */
+ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
+ config_addr, BUID_HI(phb->buid),
+ BUID_LO(phb->buid), 0);
+ if (ret) {
+ pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n",
+ __func__, phb->global_number, config_addr);
+ return 0;
+ }
+
+ return rets[0];
+ }
+
+ if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) {
+ ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets,
+ config_addr, BUID_HI(phb->buid),
+ BUID_LO(phb->buid), 0);
+ if (ret) {
+ pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n",
+ __func__, phb->global_number, config_addr);
+ return 0;
+ }
+
+ return rets[0];
+ }
+
+ return ret;
+}
+
+/**
+ * pseries_eeh_phb_reset - Reset the specified PHB
+ * @phb: PCI controller
+ * @config_adddr: the associated config address
+ * @option: reset option
+ *
+ * Reset the specified PHB/PE
+ */
+static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, int option)
+{
+ int ret;
+
+ /* Reset PE through RTAS call */
+ ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
+ config_addr, BUID_HI(phb->buid),
+ BUID_LO(phb->buid), option);
+
+ /* If fundamental-reset not supported, try hot-reset */
+ if (option == EEH_RESET_FUNDAMENTAL &&
+ ret == -8) {
+ option = EEH_RESET_HOT;
+ ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
+ config_addr, BUID_HI(phb->buid),
+ BUID_LO(phb->buid), option);
+ }
+
+ /* We need reset hold or settlement delay */
+ if (option == EEH_RESET_FUNDAMENTAL ||
+ option == EEH_RESET_HOT)
+ msleep(EEH_PE_RST_HOLD_TIME);
+ else
+ msleep(EEH_PE_RST_SETTLE_TIME);
+
+ return ret;
+}
+
+/**
+ * pseries_eeh_phb_configure_bridge - Configure PCI bridges in the indicated PE
+ * @phb: PCI controller
+ * @config_adddr: the associated config address
+ *
+ * The function will be called to reconfigure the bridges included
+ * in the specified PE so that the mulfunctional PE would be recovered
+ * again.
+ */
+static int pseries_eeh_phb_configure_bridge(struct pci_controller *phb, int config_addr)
+{
+ int ret;
+ /* Waiting 0.2s maximum before skipping configuration */
+ int max_wait = 200;
+
+ while (max_wait > 0) {
+ ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
+ config_addr, BUID_HI(phb->buid),
+ BUID_LO(phb->buid));
+
+ if (!ret)
+ return ret;
+ if (ret < 0)
+ break;
+
+ /*
+ * If RTAS returns a delay value that's above 100ms, cut it
+ * down to 100ms in case firmware made a mistake. For more
+ * on how these delay values work see rtas_busy_delay_time
+ */
+ if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+ ret <= RTAS_EXTENDED_DELAY_MAX)
+ ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+ max_wait -= rtas_busy_delay_time(ret);
+
+ if (max_wait < 0)
+ break;
+
+ rtas_busy_delay(ret);
+ }
+
+ pr_warn("%s: Unable to configure bridge PHB#%x-PE#%x (%d)\n",
+ __func__, phb->global_number, config_addr, ret);
+ /* PAPR defines -3 as "Parameter Error" for this function: */
+ if (ret == -3)
+ return -EINVAL;
+ else
+ return -EIO;
+}
+
/*
* Buffer for reporting slot-error-detail rtas calls. Its here
* in BSS, and not dynamically alloced, so that it ends up in
@@ -96,6 +243,10 @@ static int eeh_error_buf_size;
*/
static int pseries_eeh_init(void)
{
+ struct pci_controller *phb;
+ struct pci_dn *pdn;
+ int addr, config_addr;
+
/* figure out EEH RTAS function call tokens */
ibm_set_eeh_option = rtas_token("ibm,set-eeh-option");
ibm_set_slot_reset = rtas_token("ibm,set-slot-reset");
@@ -148,6 +299,22 @@ static int pseries_eeh_init(void)
/* Set EEH machine dependent code */
ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device;
+ if (is_kdump_kernel() || reset_devices) {
+ pr_info("Issue PHB reset ...\n");
+ list_for_each_entry(phb, &hose_list, list_node) {
+ pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list);
+ addr = (pdn->busno << 16) | (pdn->devfn << 8);
+ config_addr = pseries_eeh_get_config_addr(phb, addr);
+ /* invalid PE config addr */
+ if (config_addr == 0)
+ continue;
+
+ pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL);
+ pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE);
+ pseries_eeh_phb_configure_bridge(phb, config_addr);
+ }
+ }
+
return 0;
}
@@ -569,35 +736,13 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay)
static int pseries_eeh_reset(struct eeh_pe *pe, int option)
{
int config_addr;
- int ret;
/* Figure out PE address */
config_addr = pe->config_addr;
if (pe->addr)
config_addr = pe->addr;
- /* Reset PE through RTAS call */
- ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
- config_addr, BUID_HI(pe->phb->buid),
- BUID_LO(pe->phb->buid), option);
-
- /* If fundamental-reset not supported, try hot-reset */
- if (option == EEH_RESET_FUNDAMENTAL &&
- ret == -8) {
- option = EEH_RESET_HOT;
- ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
- config_addr, BUID_HI(pe->phb->buid),
- BUID_LO(pe->phb->buid), option);
- }
-
- /* We need reset hold or settlement delay */
- if (option == EEH_RESET_FUNDAMENTAL ||
- option == EEH_RESET_HOT)
- msleep(EEH_PE_RST_HOLD_TIME);
- else
- msleep(EEH_PE_RST_SETTLE_TIME);
-
- return ret;
+ return pseries_eeh_phb_reset(pe->phb, config_addr, option);
}
/**
@@ -641,56 +786,17 @@ static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, u
* pseries_eeh_configure_bridge - Configure PCI bridges in the indicated PE
* @pe: EEH PE
*
- * The function will be called to reconfigure the bridges included
- * in the specified PE so that the mulfunctional PE would be recovered
- * again.
*/
static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
{
int config_addr;
- int ret;
- /* Waiting 0.2s maximum before skipping configuration */
- int max_wait = 200;
/* Figure out the PE address */
config_addr = pe->config_addr;
if (pe->addr)
config_addr = pe->addr;
- while (max_wait > 0) {
- ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
- config_addr, BUID_HI(pe->phb->buid),
- BUID_LO(pe->phb->buid));
-
- if (!ret)
- return ret;
- if (ret < 0)
- break;
-
- /*
- * If RTAS returns a delay value that's above 100ms, cut it
- * down to 100ms in case firmware made a mistake. For more
- * on how these delay values work see rtas_busy_delay_time
- */
- if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
- ret <= RTAS_EXTENDED_DELAY_MAX)
- ret = RTAS_EXTENDED_DELAY_MIN+2;
-
- max_wait -= rtas_busy_delay_time(ret);
-
- if (max_wait < 0)
- break;
-
- rtas_busy_delay(ret);
- }
-
- pr_warn("%s: Unable to configure bridge PHB#%x-PE#%x (%d)\n",
- __func__, pe->phb->global_number, pe->addr, ret);
- /* PAPR defines -3 as "Parameter Error" for this function: */
- if (ret == -3)
- return -EINVAL;
- else
- return -EIO;
+ return pseries_eeh_phb_configure_bridge(pe->phb, config_addr);
}
/**
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 3e8cbfe7a80f..4bad7a83addc 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -35,54 +35,10 @@
#include <asm/topology.h>
#include "pseries.h"
-#include "offline_states.h"
/* This version can't take the spinlock, because it never returns */
static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
-static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
- CPU_STATE_OFFLINE;
-static DEFINE_PER_CPU(enum cpu_state_vals, current_state) = CPU_STATE_OFFLINE;
-
-static enum cpu_state_vals default_offline_state = CPU_STATE_OFFLINE;
-
-static bool cede_offline_enabled __read_mostly = true;
-
-/*
- * Enable/disable cede_offline when available.
- */
-static int __init setup_cede_offline(char *str)
-{
- return (kstrtobool(str, &cede_offline_enabled) == 0);
-}
-
-__setup("cede_offline=", setup_cede_offline);
-
-enum cpu_state_vals get_cpu_current_state(int cpu)
-{
- return per_cpu(current_state, cpu);
-}
-
-void set_cpu_current_state(int cpu, enum cpu_state_vals state)
-{
- per_cpu(current_state, cpu) = state;
-}
-
-enum cpu_state_vals get_preferred_offline_state(int cpu)
-{
- return per_cpu(preferred_offline_state, cpu);
-}
-
-void set_preferred_offline_state(int cpu, enum cpu_state_vals state)
-{
- per_cpu(preferred_offline_state, cpu) = state;
-}
-
-void set_default_offline_state(int cpu)
-{
- per_cpu(preferred_offline_state, cpu) = default_offline_state;
-}
-
static void rtas_stop_self(void)
{
static struct rtas_args args;
@@ -101,9 +57,7 @@ static void rtas_stop_self(void)
static void pseries_mach_cpu_die(void)
{
- unsigned int cpu = smp_processor_id();
unsigned int hwcpu = hard_smp_processor_id();
- u8 cede_latency_hint = 0;
local_irq_disable();
idle_task_exit();
@@ -112,49 +66,6 @@ static void pseries_mach_cpu_die(void)
else
xics_teardown_cpu();
- if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
- set_cpu_current_state(cpu, CPU_STATE_INACTIVE);
- if (ppc_md.suspend_disable_cpu)
- ppc_md.suspend_disable_cpu();
-
- cede_latency_hint = 2;
-
- get_lppaca()->idle = 1;
- if (!lppaca_shared_proc(get_lppaca()))
- get_lppaca()->donate_dedicated_cpu = 1;
-
- while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
- while (!prep_irq_for_idle()) {
- local_irq_enable();
- local_irq_disable();
- }
-
- extended_cede_processor(cede_latency_hint);
- }
-
- local_irq_disable();
-
- if (!lppaca_shared_proc(get_lppaca()))
- get_lppaca()->donate_dedicated_cpu = 0;
- get_lppaca()->idle = 0;
-
- if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
- unregister_slb_shadow(hwcpu);
-
- hard_irq_disable();
- /*
- * Call to start_secondary_resume() will not return.
- * Kernel stack will be reset and start_secondary()
- * will be called to continue the online operation.
- */
- start_secondary_resume();
- }
- }
-
- /* Requested state is CPU_STATE_OFFLINE at this point */
- WARN_ON(get_preferred_offline_state(cpu) != CPU_STATE_OFFLINE);
-
- set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
unregister_slb_shadow(hwcpu);
rtas_stop_self();
@@ -200,24 +111,13 @@ static void pseries_cpu_die(unsigned int cpu)
int cpu_status = 1;
unsigned int pcpu = get_hard_smp_processor_id(cpu);
- if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
- cpu_status = 1;
- for (tries = 0; tries < 5000; tries++) {
- if (get_cpu_current_state(cpu) == CPU_STATE_INACTIVE) {
- cpu_status = 0;
- break;
- }
- msleep(1);
- }
- } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
+ for (tries = 0; tries < 25; tries++) {
+ cpu_status = smp_query_cpu_stopped(pcpu);
+ if (cpu_status == QCSS_STOPPED ||
+ cpu_status == QCSS_HARDWARE_ERROR)
+ break;
+ cpu_relax();
- for (tries = 0; tries < 25; tries++) {
- cpu_status = smp_query_cpu_stopped(pcpu);
- if (cpu_status == QCSS_STOPPED ||
- cpu_status == QCSS_HARDWARE_ERROR)
- break;
- cpu_relax();
- }
}
if (cpu_status != 0) {
@@ -359,28 +259,14 @@ static int dlpar_offline_cpu(struct device_node *dn)
if (get_hard_smp_processor_id(cpu) != thread)
continue;
- if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
+ if (!cpu_online(cpu))
break;
- if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
- set_preferred_offline_state(cpu,
- CPU_STATE_OFFLINE);
- cpu_maps_update_done();
- timed_topology_update(1);
- rc = device_offline(get_cpu_device(cpu));
- if (rc)
- goto out;
- cpu_maps_update_begin();
- break;
- }
-
- /*
- * The cpu is in CPU_STATE_INACTIVE.
- * Upgrade it's state to CPU_STATE_OFFLINE.
- */
- set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
- WARN_ON(plpar_hcall_norets(H_PROD, thread) != H_SUCCESS);
- __cpu_die(cpu);
+ cpu_maps_update_done();
+ rc = device_offline(get_cpu_device(cpu));
+ if (rc)
+ goto out;
+ cpu_maps_update_begin();
break;
}
if (cpu == num_possible_cpus()) {
@@ -414,10 +300,7 @@ static int dlpar_online_cpu(struct device_node *dn)
for_each_present_cpu(cpu) {
if (get_hard_smp_processor_id(cpu) != thread)
continue;
- BUG_ON(get_cpu_current_state(cpu)
- != CPU_STATE_OFFLINE);
cpu_maps_update_done();
- timed_topology_update(1);
find_and_online_cpu_nid(cpu);
rc = device_online(get_cpu_device(cpu));
if (rc) {
@@ -896,25 +779,6 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add)
return rc;
}
-int dlpar_cpu_readd(int cpu)
-{
- struct device_node *dn;
- struct device *dev;
- u32 drc_index;
- int rc;
-
- dev = get_cpu_device(cpu);
- dn = dev->of_node;
-
- rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index);
-
- rc = dlpar_cpu_remove_by_index(drc_index);
- if (!rc)
- rc = dlpar_cpu_add(drc_index);
-
- return rc;
-}
-
int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
{
u32 count, drc_index;
@@ -1013,27 +877,8 @@ static struct notifier_block pseries_smp_nb = {
.notifier_call = pseries_smp_notifier,
};
-#define MAX_CEDE_LATENCY_LEVELS 4
-#define CEDE_LATENCY_PARAM_LENGTH 10
-#define CEDE_LATENCY_PARAM_MAX_LENGTH \
- (MAX_CEDE_LATENCY_LEVELS * CEDE_LATENCY_PARAM_LENGTH * sizeof(char))
-#define CEDE_LATENCY_TOKEN 45
-
-static char cede_parameters[CEDE_LATENCY_PARAM_MAX_LENGTH];
-
-static int parse_cede_parameters(void)
-{
- memset(cede_parameters, 0, CEDE_LATENCY_PARAM_MAX_LENGTH);
- return rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
- NULL,
- CEDE_LATENCY_TOKEN,
- __pa(cede_parameters),
- CEDE_LATENCY_PARAM_MAX_LENGTH);
-}
-
static int __init pseries_cpu_hotplug_init(void)
{
- int cpu;
int qcss_tok;
#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
@@ -1056,16 +901,8 @@ static int __init pseries_cpu_hotplug_init(void)
smp_ops->cpu_die = pseries_cpu_die;
/* Processors can be added/removed only on LPAR */
- if (firmware_has_feature(FW_FEATURE_LPAR)) {
+ if (firmware_has_feature(FW_FEATURE_LPAR))
of_reconfig_notifier_register(&pseries_smp_nb);
- cpu_maps_update_begin();
- if (cede_offline_enabled && parse_cede_parameters() == 0) {
- default_offline_state = CPU_STATE_INACTIVE;
- for_each_online_cpu(cpu)
- set_default_offline_state(cpu);
- }
- cpu_maps_update_done();
- }
return 0;
}
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 5ace2f9a277e..5d545b78111f 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -22,12 +22,10 @@
#include <asm/drmem.h>
#include "pseries.h"
-static bool rtas_hp_event;
-
unsigned long pseries_memory_block_size(void)
{
struct device_node *np;
- unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE;
+ u64 memblock_size = MIN_MEMORY_BLOCK_SIZE;
struct resource r;
np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
@@ -487,40 +485,6 @@ static int dlpar_memory_remove_by_index(u32 drc_index)
return rc;
}
-static int dlpar_memory_readd_by_index(u32 drc_index)
-{
- struct drmem_lmb *lmb;
- int lmb_found;
- int rc;
-
- pr_info("Attempting to update LMB, drc index %x\n", drc_index);
-
- lmb_found = 0;
- for_each_drmem_lmb(lmb) {
- if (lmb->drc_index == drc_index) {
- lmb_found = 1;
- rc = dlpar_remove_lmb(lmb);
- if (!rc) {
- rc = dlpar_add_lmb(lmb);
- if (rc)
- dlpar_release_drc(lmb->drc_index);
- }
- break;
- }
- }
-
- if (!lmb_found)
- rc = -EINVAL;
-
- if (rc)
- pr_info("Failed to update memory at %llx\n",
- lmb->base_addr);
- else
- pr_info("Memory at %llx was updated\n", lmb->base_addr);
-
- return rc;
-}
-
static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
{
struct drmem_lmb *lmb, *start_lmb, *end_lmb;
@@ -617,10 +581,6 @@ static int dlpar_memory_remove_by_index(u32 drc_index)
{
return -EOPNOTSUPP;
}
-static int dlpar_memory_readd_by_index(u32 drc_index)
-{
- return -EOPNOTSUPP;
-}
static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
{
@@ -903,21 +863,14 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
}
break;
- case PSERIES_HP_ELOG_ACTION_READD:
- drc_index = hp_elog->_drc_u.drc_index;
- rc = dlpar_memory_readd_by_index(drc_index);
- break;
default:
pr_err("Invalid action (%d) specified\n", hp_elog->action);
rc = -EINVAL;
break;
}
- if (!rc) {
- rtas_hp_event = true;
+ if (!rc)
rc = drmem_update_dt();
- rtas_hp_event = false;
- }
unlock_device_hotplug();
return rc;
@@ -953,60 +906,6 @@ static int pseries_add_mem_node(struct device_node *np)
return (ret < 0) ? -EINVAL : 0;
}
-static int pseries_update_drconf_memory(struct of_reconfig_data *pr)
-{
- struct of_drconf_cell_v1 *new_drmem, *old_drmem;
- unsigned long memblock_size;
- u32 entries;
- __be32 *p;
- int i, rc = -EINVAL;
-
- if (rtas_hp_event)
- return 0;
-
- memblock_size = pseries_memory_block_size();
- if (!memblock_size)
- return -EINVAL;
-
- if (!pr->old_prop)
- return 0;
-
- p = (__be32 *) pr->old_prop->value;
- if (!p)
- return -EINVAL;
-
- /* The first int of the property is the number of lmb's described
- * by the property. This is followed by an array of of_drconf_cell
- * entries. Get the number of entries and skip to the array of
- * of_drconf_cell's.
- */
- entries = be32_to_cpu(*p++);
- old_drmem = (struct of_drconf_cell_v1 *)p;
-
- p = (__be32 *)pr->prop->value;
- p++;
- new_drmem = (struct of_drconf_cell_v1 *)p;
-
- for (i = 0; i < entries; i++) {
- if ((be32_to_cpu(old_drmem[i].flags) & DRCONF_MEM_ASSIGNED) &&
- (!(be32_to_cpu(new_drmem[i].flags) & DRCONF_MEM_ASSIGNED))) {
- rc = pseries_remove_memblock(
- be64_to_cpu(old_drmem[i].base_addr),
- memblock_size);
- break;
- } else if ((!(be32_to_cpu(old_drmem[i].flags) &
- DRCONF_MEM_ASSIGNED)) &&
- (be32_to_cpu(new_drmem[i].flags) &
- DRCONF_MEM_ASSIGNED)) {
- rc = memblock_add(be64_to_cpu(old_drmem[i].base_addr),
- memblock_size);
- rc = (rc < 0) ? -EINVAL : 0;
- break;
- }
- }
- return rc;
-}
-
static int pseries_memory_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
@@ -1020,10 +919,6 @@ static int pseries_memory_notifier(struct notifier_block *nb,
case OF_RECONFIG_DETACH_NODE:
err = pseries_remove_mem_node(rd->dn);
break;
- case OF_RECONFIG_UPDATE_PROPERTY:
- if (!strcmp(rd->prop->name, "ibm,dynamic-memory"))
- err = pseries_update_drconf_memory(rd);
- break;
}
return notifier_from_errno(err);
}
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index fd26f3d21d7b..f82569a505f1 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -1680,9 +1680,11 @@ static int pseries_lpar_register_process_table(unsigned long base,
if (table_size)
flags |= PROC_TABLE_NEW;
- if (radix_enabled())
- flags |= PROC_TABLE_RADIX | PROC_TABLE_GTSE;
- else
+ if (radix_enabled()) {
+ flags |= PROC_TABLE_RADIX;
+ if (mmu_has_feature(MMU_FTR_GTSE))
+ flags |= PROC_TABLE_GTSE;
+ } else
flags |= PROC_TABLE_HPT_SLB;
for (;;) {
rc = plpar_hcall_norets(H_REGISTER_PROC_TBL, flags, base,
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 10d982997736..78cd772a579b 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -244,29 +244,6 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
return rc;
}
-static void prrn_update_node(__be32 phandle)
-{
- struct pseries_hp_errorlog hp_elog;
- struct device_node *dn;
-
- /*
- * If a node is found from a the given phandle, the phandle does not
- * represent the drc index of an LMB and we can ignore.
- */
- dn = of_find_node_by_phandle(be32_to_cpu(phandle));
- if (dn) {
- of_node_put(dn);
- return;
- }
-
- hp_elog.resource = PSERIES_HP_ELOG_RESOURCE_MEM;
- hp_elog.action = PSERIES_HP_ELOG_ACTION_READD;
- hp_elog.id_type = PSERIES_HP_ELOG_ID_DRC_INDEX;
- hp_elog._drc_u.drc_index = phandle;
-
- handle_dlpar_errorlog(&hp_elog);
-}
-
int pseries_devicetree_update(s32 scope)
{
char *rtas_buf;
@@ -305,10 +282,6 @@ int pseries_devicetree_update(s32 scope)
break;
case UPDATE_DT_NODE:
update_dt_node(phandle, scope);
-
- if (scope == PRRN_SCOPE)
- prrn_update_node(phandle);
-
break;
case ADD_DT_NODE:
drc_index = *data++;
@@ -388,8 +361,6 @@ static ssize_t migration_store(struct class *class,
if (rc)
return rc;
- stop_topology_update();
-
do {
rc = rtas_ibm_suspend_me(streamid);
if (rc == -EAGAIN)
@@ -401,8 +372,6 @@ static ssize_t migration_store(struct class *class,
post_mobility_fixup();
- start_topology_update();
-
return count;
}
diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h
deleted file mode 100644
index 51414aee2862..000000000000
--- a/arch/powerpc/platforms/pseries/offline_states.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _OFFLINE_STATES_H_
-#define _OFFLINE_STATES_H_
-
-/* Cpu offline states go here */
-enum cpu_state_vals {
- CPU_STATE_OFFLINE,
- CPU_STATE_INACTIVE,
- CPU_STATE_ONLINE,
- CPU_MAX_OFFLINE_STATES
-};
-
-#ifdef CONFIG_HOTPLUG_CPU
-extern enum cpu_state_vals get_cpu_current_state(int cpu);
-extern void set_cpu_current_state(int cpu, enum cpu_state_vals state);
-extern void set_preferred_offline_state(int cpu, enum cpu_state_vals state);
-extern void set_default_offline_state(int cpu);
-#else
-static inline enum cpu_state_vals get_cpu_current_state(int cpu)
-{
- return CPU_STATE_ONLINE;
-}
-
-static inline void set_cpu_current_state(int cpu, enum cpu_state_vals state)
-{
-}
-
-static inline void set_preferred_offline_state(int cpu, enum cpu_state_vals state)
-{
-}
-
-static inline void set_default_offline_state(int cpu)
-{
-}
-#endif
-
-extern enum cpu_state_vals get_preferred_offline_state(int cpu);
-#endif
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 9c569078a09f..8fd441d32487 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -13,9 +13,11 @@
#include <linux/platform_device.h>
#include <linux/delay.h>
#include <linux/seq_buf.h>
+#include <linux/nd.h>
#include <asm/plpar_wrappers.h>
#include <asm/papr_pdsm.h>
+#include <asm/mce.h>
#define BIND_ANY_ADDR (~0ul)
@@ -80,6 +82,7 @@ struct papr_scm_priv {
struct resource res;
struct nd_region *region;
struct nd_interleave_set nd_set;
+ struct list_head region_list;
/* Protect dimm health data from concurrent read/writes */
struct mutex health_mutex;
@@ -91,6 +94,9 @@ struct papr_scm_priv {
u64 health_bitmap;
};
+LIST_HEAD(papr_nd_regions);
+DEFINE_MUTEX(papr_ndr_lock);
+
static int drc_pmem_bind(struct papr_scm_priv *p)
{
unsigned long ret[PLPAR_HCALL_BUFSIZE];
@@ -759,6 +765,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
dev_info(dev, "Region registered with target node %d and online node %d",
target_nid, online_nid);
+ mutex_lock(&papr_ndr_lock);
+ list_add_tail(&p->region_list, &papr_nd_regions);
+ mutex_unlock(&papr_ndr_lock);
+
return 0;
err: nvdimm_bus_unregister(p->bus);
@@ -766,6 +776,68 @@ err: nvdimm_bus_unregister(p->bus);
return -ENXIO;
}
+static void papr_scm_add_badblock(struct nd_region *region,
+ struct nvdimm_bus *bus, u64 phys_addr)
+{
+ u64 aligned_addr = ALIGN_DOWN(phys_addr, L1_CACHE_BYTES);
+
+ if (nvdimm_bus_add_badrange(bus, aligned_addr, L1_CACHE_BYTES)) {
+ pr_err("Bad block registration for 0x%llx failed\n", phys_addr);
+ return;
+ }
+
+ pr_debug("Add memory range (0x%llx - 0x%llx) as bad range\n",
+ aligned_addr, aligned_addr + L1_CACHE_BYTES);
+
+ nvdimm_region_notify(region, NVDIMM_REVALIDATE_POISON);
+}
+
+static int handle_mce_ue(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct machine_check_event *evt = data;
+ struct papr_scm_priv *p;
+ u64 phys_addr;
+ bool found = false;
+
+ if (evt->error_type != MCE_ERROR_TYPE_UE)
+ return NOTIFY_DONE;
+
+ if (list_empty(&papr_nd_regions))
+ return NOTIFY_DONE;
+
+ /*
+ * The physical address obtained here is PAGE_SIZE aligned, so get the
+ * exact address from the effective address
+ */
+ phys_addr = evt->u.ue_error.physical_address +
+ (evt->u.ue_error.effective_address & ~PAGE_MASK);
+
+ if (!evt->u.ue_error.physical_address_provided ||
+ !is_zone_device_page(pfn_to_page(phys_addr >> PAGE_SHIFT)))
+ return NOTIFY_DONE;
+
+ /* mce notifier is called from a process context, so mutex is safe */
+ mutex_lock(&papr_ndr_lock);
+ list_for_each_entry(p, &papr_nd_regions, region_list) {
+ if (phys_addr >= p->res.start && phys_addr <= p->res.end) {
+ found = true;
+ break;
+ }
+ }
+
+ if (found)
+ papr_scm_add_badblock(p->region, p->bus, phys_addr);
+
+ mutex_unlock(&papr_ndr_lock);
+
+ return found ? NOTIFY_OK : NOTIFY_DONE;
+}
+
+static struct notifier_block mce_ue_nb = {
+ .notifier_call = handle_mce_ue
+};
+
static int papr_scm_probe(struct platform_device *pdev)
{
struct device_node *dn = pdev->dev.of_node;
@@ -866,6 +938,10 @@ static int papr_scm_remove(struct platform_device *pdev)
{
struct papr_scm_priv *p = platform_get_drvdata(pdev);
+ mutex_lock(&papr_ndr_lock);
+ list_del(&p->region_list);
+ mutex_unlock(&papr_ndr_lock);
+
nvdimm_bus_unregister(p->bus);
drc_pmem_unbind(p);
kfree(p->bus_desc.provider_name);
@@ -876,6 +952,7 @@ static int papr_scm_remove(struct platform_device *pdev)
static const struct of_device_id papr_scm_match[] = {
{ .compatible = "ibm,pmemory" },
+ { .compatible = "ibm,pmemory-v2" },
{ },
};
@@ -888,7 +965,25 @@ static struct platform_driver papr_scm_driver = {
},
};
-module_platform_driver(papr_scm_driver);
+static int __init papr_scm_init(void)
+{
+ int ret;
+
+ ret = platform_driver_register(&papr_scm_driver);
+ if (!ret)
+ mce_register_notifier(&mce_ue_nb);
+
+ return ret;
+}
+module_init(papr_scm_init);
+
+static void __exit papr_scm_exit(void)
+{
+ mce_unregister_notifier(&mce_ue_nb);
+ platform_driver_unregister(&papr_scm_driver);
+}
+module_exit(papr_scm_exit);
+
MODULE_DEVICE_TABLE(of, papr_scm_match);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("IBM Corporation");
diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c
index f860a897a9e0..e1dc5d3254df 100644
--- a/arch/powerpc/platforms/pseries/pmem.c
+++ b/arch/powerpc/platforms/pseries/pmem.c
@@ -24,7 +24,6 @@
#include <asm/topology.h>
#include "pseries.h"
-#include "offline_states.h"
static struct device_node *pmem_node;
@@ -147,6 +146,12 @@ const struct of_device_id drc_pmem_match[] = {
static int pseries_pmem_init(void)
{
+ /*
+ * Only supported on POWER8 and above.
+ */
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return 0;
+
pmem_node = of_find_node_by_type(NULL, "ibm,persistent-memory");
if (!pmem_node)
return 0;
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 6891710833be..7ebacac03dc3 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -44,8 +44,6 @@
#include <asm/svm.h>
#include "pseries.h"
-#include "offline_states.h"
-
/*
* The Primary thread of each non-boot processor was started from the OF client
@@ -108,10 +106,7 @@ static inline int smp_startup_cpu(unsigned int lcpu)
/* Fixup atomic count: it exited inside IRQ handler. */
task_thread_info(paca_ptrs[lcpu]->__current)->preempt_count = 0;
-#ifdef CONFIG_HOTPLUG_CPU
- if (get_cpu_current_state(lcpu) == CPU_STATE_INACTIVE)
- goto out;
-#endif
+
/*
* If the RTAS start-cpu token does not exist then presume the
* cpu is already spinning.
@@ -126,9 +121,6 @@ static inline int smp_startup_cpu(unsigned int lcpu)
return 0;
}
-#ifdef CONFIG_HOTPLUG_CPU
-out:
-#endif
return 1;
}
@@ -143,10 +135,6 @@ static void smp_setup_cpu(int cpu)
vpa_init(cpu);
cpumask_clear_cpu(cpu, of_spin_mask);
-#ifdef CONFIG_HOTPLUG_CPU
- set_cpu_current_state(cpu, CPU_STATE_ONLINE);
- set_default_offline_state(cpu);
-#endif
}
static int smp_pSeries_kick_cpu(int nr)
@@ -163,20 +151,6 @@ static int smp_pSeries_kick_cpu(int nr)
* the processor will continue on to secondary_start
*/
paca_ptrs[nr]->cpu_start = 1;
-#ifdef CONFIG_HOTPLUG_CPU
- set_preferred_offline_state(nr, CPU_STATE_ONLINE);
-
- if (get_cpu_current_state(nr) == CPU_STATE_INACTIVE) {
- long rc;
- unsigned long hcpuid;
-
- hcpuid = get_hard_smp_processor_id(nr);
- rc = plpar_hcall_norets(H_PROD, hcpuid);
- if (rc != H_SUCCESS)
- printk(KERN_ERR "Error: Prod to wake up processor %d "
- "Ret= %ld\n", nr, rc);
- }
-#endif
return 0;
}
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 0a24a5a185f0..81e0ac58d620 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -132,15 +132,11 @@ static ssize_t store_hibernate(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
- cpumask_var_t offline_mask;
int rc;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL))
- return -ENOMEM;
-
stream_id = simple_strtoul(buf, NULL, 16);
do {
@@ -149,33 +145,14 @@ static ssize_t store_hibernate(struct device *dev,
ssleep(1);
} while (rc == -EAGAIN);
- if (!rc) {
- /* All present CPUs must be online */
- cpumask_andnot(offline_mask, cpu_present_mask,
- cpu_online_mask);
- rc = rtas_online_cpus_mask(offline_mask);
- if (rc) {
- pr_err("%s: Could not bring present CPUs online.\n",
- __func__);
- goto out;
- }
-
- stop_topology_update();
+ if (!rc)
rc = pm_suspend(PM_SUSPEND_MEM);
- start_topology_update();
-
- /* Take down CPUs not online prior to suspend */
- if (!rtas_offline_cpus_mask(offline_mask))
- pr_warn("%s: Could not restore CPUs to offline "
- "state.\n", __func__);
- }
stream_id = 0;
if (!rc)
rc = count;
-out:
- free_cpumask_var(offline_mask);
+
return rc;
}
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 71b881e554fc..cb58ec7ce77a 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -18,6 +18,7 @@
#include <linux/delay.h>
#include <linux/cpumask.h>
#include <linux/mm.h>
+#include <linux/kmemleak.h>
#include <asm/machdep.h>
#include <asm/prom.h>
@@ -647,6 +648,7 @@ static bool xive_native_provision_pages(void)
pr_err("Failed to allocate provisioning page\n");
return false;
}
+ kmemleak_ignore(p);
opal_xive_donate_page(chip, __pa(p));
}
return true;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 3203c3606737..8fb1f857c11c 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -481,6 +481,13 @@ static inline int unrecoverable_excp(struct pt_regs *regs)
#endif
}
+static void xmon_touch_watchdogs(void)
+{
+ touch_softlockup_watchdog_sync();
+ rcu_cpu_stall_reset();
+ touch_nmi_watchdog();
+}
+
static int xmon_core(struct pt_regs *regs, int fromipi)
{
int cmd = 0;
@@ -718,7 +725,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
else
insert_cpu_bpts();
- touch_nmi_watchdog();
+ xmon_touch_watchdogs();
local_irq_restore(flags);
return cmd != 'X' && cmd != EOF;
@@ -2023,6 +2030,18 @@ static void dump_300_sprs(void)
#endif
}
+static void dump_310_sprs(void)
+{
+#ifdef CONFIG_PPC64
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return;
+
+ printf("mmcr3 = %.16lx, sier2 = %.16lx, sier3 = %.16lx\n",
+ mfspr(SPRN_MMCR3), mfspr(SPRN_SIER2), mfspr(SPRN_SIER3));
+
+#endif
+}
+
static void dump_one_spr(int spr, bool show_unimplemented)
{
unsigned long val;
@@ -2077,6 +2096,7 @@ static void super_regs(void)
dump_206_sprs();
dump_207_sprs();
dump_300_sprs();
+ dump_310_sprs();
return;
}
@@ -2935,11 +2955,10 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
int nr, dotted;
unsigned long first_adr;
struct ppc_inst inst, last_inst = ppc_inst(0);
- unsigned char val[4];
dotted = 0;
- for (first_adr = adr; count > 0; --count, adr += 4) {
- nr = mread(adr, val, 4);
+ for (first_adr = adr; count > 0; --count, adr += ppc_inst_len(inst)) {
+ nr = mread_instr(adr, &inst);
if (nr == 0) {
if (praddr) {
const char *x = fault_chars[fault_type];
@@ -2947,7 +2966,6 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
}
break;
}
- inst = ppc_inst(GETWORD(val));
if (adr > first_adr && ppc_inst_equal(inst, last_inst)) {
if (!dotted) {
printf(" ...\n");
@@ -2958,9 +2976,12 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
dotted = 0;
last_inst = inst;
if (praddr)
- printf(REG" %.8x", adr, ppc_inst_val(inst));
+ printf(REG" %s", adr, ppc_inst_as_str(inst));
printf("\t");
- dump_func(ppc_inst_val(inst), adr);
+ if (!ppc_inst_prefixed(inst))
+ dump_func(ppc_inst_val(inst), adr);
+ else
+ dump_func(ppc_inst_as_u64(inst), adr);
printf("\n");
}
return adr - first_adr;
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 1b299e801f74..addaa6e6718b 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -244,20 +244,6 @@ static inline void add_powernv_state(int index, const char *name,
stop_psscr_table[index].mask = psscr_mask;
}
-/*
- * Returns 0 if prop1_len == prop2_len. Else returns -1
- */
-static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
- const char *prop2, int prop2_len)
-{
- if (prop1_len == prop2_len)
- return 0;
-
- pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n",
- prop1, prop2);
- return -1;
-}
-
extern u32 pnv_get_supported_cpuidle_states(void);
static int powernv_add_idle_states(void)
{
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 6513ef2af66a..3e058ad2bb51 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -22,7 +22,7 @@
#include <asm/idle.h>
#include <asm/plpar_wrappers.h>
-struct cpuidle_driver pseries_idle_driver = {
+static struct cpuidle_driver pseries_idle_driver = {
.name = "pseries_idle",
.owner = THIS_MODULE,
};
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index db874367b602..50a0a18f35da 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -50,7 +50,7 @@
# 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 http://www.openssl.org/~appro/cryptogams/.
+# details see https://www.openssl.org/~appro/cryptogams/.
# ====================================================================
#
# This module implements support for AES instructions as per PowerISA
diff --git a/drivers/crypto/vmx/ghashp8-ppc.pl b/drivers/crypto/vmx/ghashp8-ppc.pl
index 38b06503ede0..09bba1852eec 100644
--- a/drivers/crypto/vmx/ghashp8-ppc.pl
+++ b/drivers/crypto/vmx/ghashp8-ppc.pl
@@ -13,7 +13,7 @@
# 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 http://www.openssl.org/~appro/cryptogams/.
+# details see https://www.openssl.org/~appro/cryptogams/.
# ====================================================================
#
# GHASH for for PowerISA v2.07.
diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c
index e49d1f287a17..73b396189039 100644
--- a/drivers/macintosh/adb.c
+++ b/drivers/macintosh/adb.c
@@ -163,7 +163,7 @@ static int adb_scan_bus(void)
* See if anybody actually moved. This is suggested
* by HW TechNote 01:
*
- * http://developer.apple.com/technotes/hw/hw_01.html
+ * https://developer.apple.com/technotes/hw/hw_01.html
*/
adb_request(&req, NULL, ADBREQ_SYNC | ADBREQ_REPLY, 1,
(highFree << 4) | 0xf);
diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c
index 8f7725dc2166..7e218437730c 100644
--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -5,8 +5,8 @@
* Copyright (C) 2003, 2004 Colin Leroy, Rasmus Rohde, Benjamin Herrenschmidt
*
* Documentation from 115254175ADT7467_pra.pdf and 3686221171167ADT7460_b.pdf
- * http://www.onsemi.com/PowerSolutions/product.do?id=ADT7467
- * http://www.onsemi.com/PowerSolutions/product.do?id=ADT7460
+ * https://www.onsemi.com/PowerSolutions/product.do?id=ADT7467
+ * https://www.onsemi.com/PowerSolutions/product.do?id=ADT7460
*
*/
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 74f3c506f084..00534fa4a384 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -536,7 +536,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc)
static void writecache_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
{
if (WC_MODE_PMEM(wc))
- wmb();
+ pmem_wmb();
else
ssd_commit_flushed(wc, wait_for_ios);
}
diff --git a/drivers/misc/ocxl/Kconfig b/drivers/misc/ocxl/Kconfig
index 2d2266c1439e..6551007a066c 100644
--- a/drivers/misc/ocxl/Kconfig
+++ b/drivers/misc/ocxl/Kconfig
@@ -23,7 +23,7 @@ config OCXL
The ocxl driver enables userspace programs to access these
accelerators through devices in /dev/ocxl/.
- For more information, see http://opencapi.org.
+ For more information, see https://opencapi.org.
This is not to be confused with the support for IBM CAPI
accelerators (CONFIG_CXL), which are PCI-based instead of a
diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c
index c8e19bfb5ef9..42f7a1298775 100644
--- a/drivers/misc/ocxl/config.c
+++ b/drivers/misc/ocxl/config.c
@@ -71,6 +71,20 @@ static int find_dvsec_afu_ctrl(struct pci_dev *dev, u8 afu_idx)
return 0;
}
+/**
+ * get_function_0() - Find a related PCI device (function 0)
+ * @device: PCI device to match
+ *
+ * Returns a pointer to the related device, or null if not found
+ */
+static struct pci_dev *get_function_0(struct pci_dev *dev)
+{
+ unsigned int devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
+
+ return pci_get_domain_bus_and_slot(pci_domain_nr(dev->bus),
+ dev->bus->number, devfn);
+}
+
static void read_pasid(struct pci_dev *dev, struct ocxl_fn_config *fn)
{
u16 val;
@@ -159,14 +173,15 @@ static int read_dvsec_afu_info(struct pci_dev *dev, struct ocxl_fn_config *fn)
static int read_dvsec_vendor(struct pci_dev *dev)
{
int pos;
- u32 cfg, tlx, dlx;
+ u32 cfg, tlx, dlx, reset_reload;
/*
- * vendor specific DVSEC is optional
+ * vendor specific DVSEC, for IBM images only. Some older
+ * images may not have it
*
- * It's currently only used on function 0 to specify the
- * version of some logic blocks. Some older images may not
- * even have it so we ignore any errors
+ * It's only used on function 0 to specify the version of some
+ * logic blocks and to give access to special registers to
+ * enable host-based flashing.
*/
if (PCI_FUNC(dev->devfn) != 0)
return 0;
@@ -178,11 +193,67 @@ static int read_dvsec_vendor(struct pci_dev *dev)
pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_CFG_VERS, &cfg);
pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_TLX_VERS, &tlx);
pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_DLX_VERS, &dlx);
+ pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+ &reset_reload);
dev_dbg(&dev->dev, "Vendor specific DVSEC:\n");
dev_dbg(&dev->dev, " CFG version = 0x%x\n", cfg);
dev_dbg(&dev->dev, " TLX version = 0x%x\n", tlx);
dev_dbg(&dev->dev, " DLX version = 0x%x\n", dlx);
+ dev_dbg(&dev->dev, " ResetReload = 0x%x\n", reset_reload);
+ return 0;
+}
+
+static int get_dvsec_vendor0(struct pci_dev *dev, struct pci_dev **dev0,
+ int *out_pos)
+{
+ int pos;
+
+ if (PCI_FUNC(dev->devfn) != 0) {
+ dev = get_function_0(dev);
+ if (!dev)
+ return -1;
+ }
+ pos = find_dvsec(dev, OCXL_DVSEC_VENDOR_ID);
+ if (!pos)
+ return -1;
+ *dev0 = dev;
+ *out_pos = pos;
+ return 0;
+}
+
+int ocxl_config_get_reset_reload(struct pci_dev *dev, int *val)
+{
+ struct pci_dev *dev0;
+ u32 reset_reload;
+ int pos;
+
+ if (get_dvsec_vendor0(dev, &dev0, &pos))
+ return -1;
+
+ pci_read_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+ &reset_reload);
+ *val = !!(reset_reload & BIT(0));
+ return 0;
+}
+
+int ocxl_config_set_reset_reload(struct pci_dev *dev, int val)
+{
+ struct pci_dev *dev0;
+ u32 reset_reload;
+ int pos;
+
+ if (get_dvsec_vendor0(dev, &dev0, &pos))
+ return -1;
+
+ pci_read_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+ &reset_reload);
+ if (val)
+ reset_reload |= BIT(0);
+ else
+ reset_reload &= ~BIT(0);
+ pci_write_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+ reset_reload);
return 0;
}
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index 345bf843a38e..af9a84aeee6f 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -113,6 +113,12 @@ void ocxl_actag_afu_free(struct ocxl_fn *fn, u32 start, u32 size);
int ocxl_config_get_pasid_info(struct pci_dev *dev, int *count);
/*
+ * Control whether the FPGA is reloaded on a link reset
+ */
+int ocxl_config_get_reset_reload(struct pci_dev *dev, int *val);
+int ocxl_config_set_reset_reload(struct pci_dev *dev, int val);
+
+/*
* Check if an AFU index is valid for the given function.
*
* AFU indexes can be sparse, so a driver should check all indexes up
diff --git a/drivers/misc/ocxl/sysfs.c b/drivers/misc/ocxl/sysfs.c
index 58f1ba264206..25c78df8055d 100644
--- a/drivers/misc/ocxl/sysfs.c
+++ b/drivers/misc/ocxl/sysfs.c
@@ -51,11 +51,46 @@ static ssize_t contexts_show(struct device *device,
afu->pasid_count, afu->pasid_max);
}
+static ssize_t reload_on_reset_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct ocxl_afu *afu = to_afu(device);
+ struct ocxl_fn *fn = afu->fn;
+ struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+ int val;
+
+ if (ocxl_config_get_reset_reload(pci_dev, &val))
+ return scnprintf(buf, PAGE_SIZE, "unavailable\n");
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t reload_on_reset_store(struct device *device,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ocxl_afu *afu = to_afu(device);
+ struct ocxl_fn *fn = afu->fn;
+ struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+ int rc, val;
+
+ rc = kstrtoint(buf, 0, &val);
+ if (rc || (val != 0 && val != 1))
+ return -EINVAL;
+
+ if (ocxl_config_set_reset_reload(pci_dev, val))
+ return -ENODEV;
+
+ return count;
+}
+
static struct device_attribute afu_attrs[] = {
__ATTR_RO(global_mmio_size),
__ATTR_RO(pp_mmio_size),
__ATTR_RO(afu_version),
__ATTR_RO(contexts),
+ __ATTR_RW(reload_on_reset),
};
static ssize_t global_mmio_read(struct file *filp, struct kobject *kobj,
diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c
index 6826a274a1f1..10dbdcdfb9ce 100644
--- a/drivers/nvdimm/of_pmem.c
+++ b/drivers/nvdimm/of_pmem.c
@@ -90,6 +90,7 @@ static int of_pmem_region_remove(struct platform_device *pdev)
static const struct of_device_id of_pmem_region_match[] = {
{ .compatible = "pmem-region" },
+ { .compatible = "pmem-region-v2" },
{ },
};
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 4502f9c4708d..c3237c2b03a6 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -1206,13 +1206,13 @@ int generic_nvdimm_flush(struct nd_region *nd_region)
idx = this_cpu_add_return(flush_idx, hash_32(current->pid + idx, 8));
/*
- * The first wmb() is needed to 'sfence' all previous writes
- * such that they are architecturally visible for the platform
- * buffer flush. Note that we've already arranged for pmem
+ * The pmem_wmb() is needed to 'sfence' all
+ * previous writes such that they are architecturally visible for
+ * the platform buffer flush. Note that we've already arranged for pmem
* writes to avoid the cache via memcpy_flushcache(). The final
* wmb() ensures ordering for the NVDIMM flush write.
*/
- wmb();
+ pmem_wmb();
for (i = 0; i < nd_region->ndr_mappings; i++)
if (ndrd_get_flush_wpq(ndrd, i, 0))
writeq(1, ndrd_get_flush_wpq(ndrd, i, idx));
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 2eacaf7d62f6..b589bb216ee5 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -257,5 +257,15 @@ do { \
})
#endif
+/*
+ * pmem_wmb() ensures that all stores for which the modification
+ * are written to persistent storage by preceding instructions have
+ * updated persistent storage before any data access or data transfer
+ * caused by subsequent instructions is initiated.
+ */
+#ifndef pmem_wmb
+#define pmem_wmb() wmb()
+#endif
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 191772d4a4d7..a2710e654b64 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -181,6 +181,7 @@ enum cpuhp_state {
CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE,
+ CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE,
CPUHP_AP_WATCHDOG_ONLINE,
CPUHP_AP_WORKQUEUE_ONLINE,
CPUHP_AP_RCUTREE_ONLINE,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index dc7b87310c10..6c8333d6c991 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -317,8 +317,6 @@ extern unsigned int kobjsize(const void *objp);
#if defined(CONFIG_X86)
# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */
-#elif defined(CONFIG_PPC)
-# define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */
#elif defined(CONFIG_PARISC)
# define VM_GROWSUP VM_ARCH_1
#elif defined(CONFIG_IA64)
diff --git a/include/misc/ocxl-config.h b/include/misc/ocxl-config.h
index 3526fa996a22..ccfd3b463517 100644
--- a/include/misc/ocxl-config.h
+++ b/include/misc/ocxl-config.h
@@ -41,5 +41,6 @@
#define OCXL_DVSEC_VENDOR_CFG_VERS 0x0C
#define OCXL_DVSEC_VENDOR_TLX_VERS 0x10
#define OCXL_DVSEC_VENDOR_DLX_VERS 0x20
+#define OCXL_DVSEC_VENDOR_RESET_RELOAD 0x38
#endif /* _OCXL_CONFIG_H_ */
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 5fb752034386..939092dbcb8b 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -114,8 +114,6 @@ IF_HAVE_PG_IDLE(PG_idle, "idle" )
#if defined(CONFIG_X86)
#define __VM_ARCH_SPECIFIC_1 {VM_PAT, "pat" }
-#elif defined(CONFIG_PPC)
-#define __VM_ARCH_SPECIFIC_1 {VM_SAO, "sao" }
#elif defined(CONFIG_PARISC) || defined(CONFIG_IA64)
#define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP, "growsup" }
#elif !defined(CONFIG_MMU)
diff --git a/mm/ksm.c b/mm/ksm.c
index 4102034cd55a..d1cfa18689b5 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2452,10 +2452,6 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
if (vma_is_dax(vma))
return 0;
-#ifdef VM_SAO
- if (*vm_flags & VM_SAO)
- return 0;
-#endif
#ifdef VM_SPARC_ADI
if (*vm_flags & VM_SPARC_ADI)
return 0;
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 264e266a85bf..c3af3f324c5a 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -640,6 +640,11 @@ struct kvm_ppc_cpu_char {
#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
#define KVM_REG_PPC_PTCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
+/* POWER10 registers */
+#define KVM_REG_PPC_MMCR3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1)
+#define KVM_REG_PPC_SIER2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2)
+#define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h
index 54cfa0530e86..488f4339b83c 100644
--- a/tools/perf/arch/powerpc/util/book3s_hcalls.h
+++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h
@@ -84,7 +84,7 @@
{0x1a4, "H_CREATE_RPT"}, \
{0x1a8, "H_REMOVE_RPT"}, \
{0x1ac, "H_REGISTER_RPAGES"}, \
- {0x1b0, "H_DISABLE_AND_GETC"}, \
+ {0x1b0, "H_DISABLE_AND_GET"}, \
{0x1b4, "H_ERROR_DATA"}, \
{0x1b8, "H_GET_HCA_INFO"}, \
{0x1bc, "H_GET_PERF_COUNT"}, \
diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
index 0453c50c949c..55ef15184057 100644
--- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c
+++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
@@ -9,7 +9,17 @@
* This selftest exercises the powerpc alignment fault handler.
*
* We create two sets of source and destination buffers, one in regular memory,
- * the other cache-inhibited (we use /dev/fb0 for this).
+ * the other cache-inhibited (by default we use /dev/fb0 for this, but an
+ * alterative path for cache-inhibited memory may be provided).
+ *
+ * One way to get cache-inhibited memory is to use the "mem" kernel parameter
+ * to limit the kernel to less memory than actually exists. Addresses above
+ * the limit may still be accessed but will be treated as cache-inhibited. For
+ * example, if there is actually 4GB of memory and the parameter "mem=3GB" is
+ * used, memory from address 0xC0000000 onwards is treated as cache-inhibited.
+ * To access this region /dev/mem is used. The kernel should be configured
+ * without CONFIG_STRICT_DEVMEM. In this case use:
+ * ./alignment_handler /dev/mem 0xc0000000
*
* We initialise the source buffers, then use whichever set of load/store
* instructions is under test to copy bytes from the source buffers to the
@@ -48,11 +58,14 @@
#include <asm/cputable.h>
#include "utils.h"
+#include "instructions.h"
int bufsize;
int debug;
int testing;
volatile int gotsig;
+char *cipath = "/dev/fb0";
+long cioffset;
void sighandler(int sig, siginfo_t *info, void *ctx)
{
@@ -84,6 +97,17 @@ void sighandler(int sig, siginfo_t *info, void *ctx)
} \
rc |= do_test(#name, test_##name)
+#define TESTP(name, ld_op, st_op, ld_reg, st_reg) \
+ void test_##name(char *s, char *d) \
+ { \
+ asm volatile( \
+ ld_op(ld_reg, %0, 0, 0) \
+ st_op(st_reg, %1, 0, 0) \
+ :: "r"(s), "r"(d), "r"(0) \
+ : "memory", "vs0", "vs32", "r31"); \
+ } \
+ rc |= do_test(#name, test_##name)
+
#define LOAD_VSX_XFORM_TEST(op) TEST(op, op, stxvd2x, XFORM, 32, 32)
#define STORE_VSX_XFORM_TEST(op) TEST(op, lxvd2x, op, XFORM, 32, 32)
#define LOAD_VSX_DFORM_TEST(op) TEST(op, op, stxv, DFORM, 32, 32)
@@ -103,6 +127,17 @@ void sighandler(int sig, siginfo_t *info, void *ctx)
#define LOAD_FLOAT_XFORM_TEST(op) TEST(op, op, stfdx, XFORM, 0, 0)
#define STORE_FLOAT_XFORM_TEST(op) TEST(op, lfdx, op, XFORM, 0, 0)
+#define LOAD_MLS_PREFIX_TEST(op) TESTP(op, op, PSTD, 31, 31)
+#define STORE_MLS_PREFIX_TEST(op) TESTP(op, PLD, op, 31, 31)
+
+#define LOAD_8LS_PREFIX_TEST(op) TESTP(op, op, PSTD, 31, 31)
+#define STORE_8LS_PREFIX_TEST(op) TESTP(op, PLD, op, 31, 31)
+
+#define LOAD_FLOAT_MLS_PREFIX_TEST(op) TESTP(op, op, PSTFD, 0, 0)
+#define STORE_FLOAT_MLS_PREFIX_TEST(op) TESTP(op, PLFD, op, 0, 0)
+
+#define LOAD_VSX_8LS_PREFIX_TEST(op, tail) TESTP(op, op, PSTXV ## tail, 0, 32)
+#define STORE_VSX_8LS_PREFIX_TEST(op, tail) TESTP(op, PLXV ## tail, op, 32, 0)
/* FIXME: Unimplemented tests: */
// STORE_DFORM_TEST(stq) /* FIXME: need two registers for quad */
@@ -195,17 +230,18 @@ int do_test(char *test_name, void (*test_func)(char *, char *))
printf("\tDoing %s:\t", test_name);
- fd = open("/dev/fb0", O_RDWR);
+ fd = open(cipath, O_RDWR);
if (fd < 0) {
printf("\n");
- perror("Can't open /dev/fb0 now?");
+ perror("Can't open ci file now?");
return 1;
}
- ci0 = mmap(NULL, bufsize, PROT_WRITE, MAP_SHARED,
- fd, 0x0);
- ci1 = mmap(NULL, bufsize, PROT_WRITE, MAP_SHARED,
- fd, bufsize);
+ ci0 = mmap(NULL, bufsize, PROT_WRITE | PROT_READ, MAP_SHARED,
+ fd, cioffset);
+ ci1 = mmap(NULL, bufsize, PROT_WRITE | PROT_READ, MAP_SHARED,
+ fd, cioffset + bufsize);
+
if ((ci0 == MAP_FAILED) || (ci1 == MAP_FAILED)) {
printf("\n");
perror("mmap failed");
@@ -270,11 +306,11 @@ int do_test(char *test_name, void (*test_func)(char *, char *))
return rc;
}
-static bool can_open_fb0(void)
+static bool can_open_cifile(void)
{
int fd;
- fd = open("/dev/fb0", O_RDWR);
+ fd = open(cipath, O_RDWR);
if (fd < 0)
return false;
@@ -286,7 +322,7 @@ int test_alignment_handler_vsx_206(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
printf("VSX: 2.06B\n");
@@ -304,7 +340,7 @@ int test_alignment_handler_vsx_207(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
printf("VSX: 2.07B\n");
@@ -320,7 +356,7 @@ int test_alignment_handler_vsx_300(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00));
printf("VSX: 3.00B\n");
@@ -348,11 +384,30 @@ int test_alignment_handler_vsx_300(void)
return rc;
}
+int test_alignment_handler_vsx_prefix(void)
+{
+ int rc = 0;
+
+ SKIP_IF(!can_open_cifile());
+ SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+
+ printf("VSX: PREFIX\n");
+ LOAD_VSX_8LS_PREFIX_TEST(PLXSD, 0);
+ LOAD_VSX_8LS_PREFIX_TEST(PLXSSP, 0);
+ LOAD_VSX_8LS_PREFIX_TEST(PLXV0, 0);
+ LOAD_VSX_8LS_PREFIX_TEST(PLXV1, 1);
+ STORE_VSX_8LS_PREFIX_TEST(PSTXSD, 0);
+ STORE_VSX_8LS_PREFIX_TEST(PSTXSSP, 0);
+ STORE_VSX_8LS_PREFIX_TEST(PSTXV0, 0);
+ STORE_VSX_8LS_PREFIX_TEST(PSTXV1, 1);
+ return rc;
+}
+
int test_alignment_handler_integer(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
printf("Integer\n");
LOAD_DFORM_TEST(lbz);
@@ -408,7 +463,7 @@ int test_alignment_handler_integer_206(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
printf("Integer: 2.06\n");
@@ -419,11 +474,32 @@ int test_alignment_handler_integer_206(void)
return rc;
}
+int test_alignment_handler_integer_prefix(void)
+{
+ int rc = 0;
+
+ SKIP_IF(!can_open_cifile());
+ SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+
+ printf("Integer: PREFIX\n");
+ LOAD_MLS_PREFIX_TEST(PLBZ);
+ LOAD_MLS_PREFIX_TEST(PLHZ);
+ LOAD_MLS_PREFIX_TEST(PLHA);
+ LOAD_MLS_PREFIX_TEST(PLWZ);
+ LOAD_8LS_PREFIX_TEST(PLWA);
+ LOAD_8LS_PREFIX_TEST(PLD);
+ STORE_MLS_PREFIX_TEST(PSTB);
+ STORE_MLS_PREFIX_TEST(PSTH);
+ STORE_MLS_PREFIX_TEST(PSTW);
+ STORE_8LS_PREFIX_TEST(PSTD);
+ return rc;
+}
+
int test_alignment_handler_vmx(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
SKIP_IF(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC));
printf("VMX\n");
@@ -451,7 +527,7 @@ int test_alignment_handler_fp(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
printf("Floating point\n");
LOAD_FLOAT_DFORM_TEST(lfd);
@@ -479,7 +555,7 @@ int test_alignment_handler_fp_205(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_05));
printf("Floating point: 2.05\n");
@@ -497,7 +573,7 @@ int test_alignment_handler_fp_206(void)
{
int rc = 0;
- SKIP_IF(!can_open_fb0());
+ SKIP_IF(!can_open_cifile());
SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
printf("Floating point: 2.06\n");
@@ -507,13 +583,32 @@ int test_alignment_handler_fp_206(void)
return rc;
}
+
+int test_alignment_handler_fp_prefix(void)
+{
+ int rc = 0;
+
+ SKIP_IF(!can_open_cifile());
+ SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+
+ printf("Floating point: PREFIX\n");
+ LOAD_FLOAT_DFORM_TEST(lfs);
+ LOAD_FLOAT_MLS_PREFIX_TEST(PLFS);
+ LOAD_FLOAT_MLS_PREFIX_TEST(PLFD);
+ STORE_FLOAT_MLS_PREFIX_TEST(PSTFS);
+ STORE_FLOAT_MLS_PREFIX_TEST(PSTFD);
+ return rc;
+}
+
void usage(char *prog)
{
- printf("Usage: %s [options]\n", prog);
+ printf("Usage: %s [options] [path [offset]]\n", prog);
printf(" -d Enable debug error output\n");
printf("\n");
- printf("This test requires a POWER8 or POWER9 CPU and a usable ");
- printf("framebuffer at /dev/fb0.\n");
+ printf("This test requires a POWER8, POWER9 or POWER10 CPU ");
+ printf("and either a usable framebuffer at /dev/fb0 or ");
+ printf("the path to usable cache inhibited memory and optional ");
+ printf("offset to be provided\n");
}
int main(int argc, char *argv[])
@@ -533,6 +628,13 @@ int main(int argc, char *argv[])
exit(1);
}
}
+ argc -= optind;
+ argv += optind;
+
+ if (argc > 0)
+ cipath = argv[0];
+ if (argc > 1)
+ cioffset = strtol(argv[1], 0, 0x10);
bufsize = getpagesize();
@@ -552,10 +654,14 @@ int main(int argc, char *argv[])
"test_alignment_handler_vsx_207");
rc |= test_harness(test_alignment_handler_vsx_300,
"test_alignment_handler_vsx_300");
+ rc |= test_harness(test_alignment_handler_vsx_prefix,
+ "test_alignment_handler_vsx_prefix");
rc |= test_harness(test_alignment_handler_integer,
"test_alignment_handler_integer");
rc |= test_harness(test_alignment_handler_integer_206,
"test_alignment_handler_integer_206");
+ rc |= test_harness(test_alignment_handler_integer_prefix,
+ "test_alignment_handler_integer_prefix");
rc |= test_harness(test_alignment_handler_vmx,
"test_alignment_handler_vmx");
rc |= test_harness(test_alignment_handler_fp,
@@ -564,5 +670,7 @@ int main(int argc, char *argv[])
"test_alignment_handler_fp_205");
rc |= test_harness(test_alignment_handler_fp_206,
"test_alignment_handler_fp_206");
+ rc |= test_harness(test_alignment_handler_fp_prefix,
+ "test_alignment_handler_fp_prefix");
return rc;
}
diff --git a/tools/testing/selftests/powerpc/include/instructions.h b/tools/testing/selftests/powerpc/include/instructions.h
index f36061eb6f0f..4efa6314bd96 100644
--- a/tools/testing/selftests/powerpc/include/instructions.h
+++ b/tools/testing/selftests/powerpc/include/instructions.h
@@ -66,4 +66,81 @@ static inline int paste_last(void *i)
#define PPC_INST_PASTE __PASTE(0, 0, 0, 0)
#define PPC_INST_PASTE_LAST __PASTE(0, 0, 1, 1)
+/* This defines the prefixed load/store instructions */
+#ifdef __ASSEMBLY__
+# define stringify_in_c(...) __VA_ARGS__
+#else
+# define __stringify_in_c(...) #__VA_ARGS__
+# define stringify_in_c(...) __stringify_in_c(__VA_ARGS__) " "
+#endif
+
+#define __PPC_RA(a) (((a) & 0x1f) << 16)
+#define __PPC_RS(s) (((s) & 0x1f) << 21)
+#define __PPC_RT(t) __PPC_RS(t)
+#define __PPC_PREFIX_R(r) (((r) & 0x1) << 20)
+
+#define PPC_PREFIX_MLS 0x06000000
+#define PPC_PREFIX_8LS 0x04000000
+
+#define PPC_INST_LBZ 0x88000000
+#define PPC_INST_LHZ 0xa0000000
+#define PPC_INST_LHA 0xa8000000
+#define PPC_INST_LWZ 0x80000000
+#define PPC_INST_STB 0x98000000
+#define PPC_INST_STH 0xb0000000
+#define PPC_INST_STW 0x90000000
+#define PPC_INST_STD 0xf8000000
+#define PPC_INST_LFS 0xc0000000
+#define PPC_INST_LFD 0xc8000000
+#define PPC_INST_STFS 0xd0000000
+#define PPC_INST_STFD 0xd8000000
+
+#define PREFIX_MLS(instr, t, a, r, d) stringify_in_c(.balign 64, , 4;) \
+ stringify_in_c(.long PPC_PREFIX_MLS | \
+ __PPC_PREFIX_R(r) | \
+ (((d) >> 16) & 0x3ffff);) \
+ stringify_in_c(.long (instr) | \
+ __PPC_RT(t) | \
+ __PPC_RA(a) | \
+ ((d) & 0xffff);\n)
+
+#define PREFIX_8LS(instr, t, a, r, d) stringify_in_c(.balign 64, , 4;) \
+ stringify_in_c(.long PPC_PREFIX_8LS | \
+ __PPC_PREFIX_R(r) | \
+ (((d) >> 16) & 0x3ffff);) \
+ stringify_in_c(.long (instr) | \
+ __PPC_RT(t) | \
+ __PPC_RA(a) | \
+ ((d) & 0xffff);\n)
+
+/* Prefixed Integer Load/Store instructions */
+#define PLBZ(t, a, r, d) PREFIX_MLS(PPC_INST_LBZ, t, a, r, d)
+#define PLHZ(t, a, r, d) PREFIX_MLS(PPC_INST_LHZ, t, a, r, d)
+#define PLHA(t, a, r, d) PREFIX_MLS(PPC_INST_LHA, t, a, r, d)
+#define PLWZ(t, a, r, d) PREFIX_MLS(PPC_INST_LWZ, t, a, r, d)
+#define PLWA(t, a, r, d) PREFIX_8LS(0xa4000000, t, a, r, d)
+#define PLD(t, a, r, d) PREFIX_8LS(0xe4000000, t, a, r, d)
+#define PLQ(t, a, r, d) PREFIX_8LS(0xe0000000, t, a, r, d)
+#define PSTB(s, a, r, d) PREFIX_MLS(PPC_INST_STB, s, a, r, d)
+#define PSTH(s, a, r, d) PREFIX_MLS(PPC_INST_STH, s, a, r, d)
+#define PSTW(s, a, r, d) PREFIX_MLS(PPC_INST_STW, s, a, r, d)
+#define PSTD(s, a, r, d) PREFIX_8LS(0xf4000000, s, a, r, d)
+#define PSTQ(s, a, r, d) PREFIX_8LS(0xf0000000, s, a, r, d)
+
+/* Prefixed Floating-Point Load/Store Instructions */
+#define PLFS(frt, a, r, d) PREFIX_MLS(PPC_INST_LFS, frt, a, r, d)
+#define PLFD(frt, a, r, d) PREFIX_MLS(PPC_INST_LFD, frt, a, r, d)
+#define PSTFS(frs, a, r, d) PREFIX_MLS(PPC_INST_STFS, frs, a, r, d)
+#define PSTFD(frs, a, r, d) PREFIX_MLS(PPC_INST_STFD, frs, a, r, d)
+
+/* Prefixed VSX Load/Store Instructions */
+#define PLXSD(vrt, a, r, d) PREFIX_8LS(0xa8000000, vrt, a, r, d)
+#define PLXSSP(vrt, a, r, d) PREFIX_8LS(0xac000000, vrt, a, r, d)
+#define PLXV0(s, a, r, d) PREFIX_8LS(0xc8000000, s, a, r, d)
+#define PLXV1(s, a, r, d) PREFIX_8LS(0xcc000000, s, a, r, d)
+#define PSTXSD(vrs, a, r, d) PREFIX_8LS(0xb8000000, vrs, a, r, d)
+#define PSTXSSP(vrs, a, r, d) PREFIX_8LS(0xbc000000, vrs, a, r, d)
+#define PSTXV0(s, a, r, d) PREFIX_8LS(0xd8000000, s, a, r, d)
+#define PSTXV1(s, a, r, d) PREFIX_8LS(0xdc000000, s, a, r, d)
+
#endif /* _SELFTESTS_POWERPC_INSTRUCTIONS_H */
diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h
index 022c5076b2c5..c0f2742a3a59 100644
--- a/tools/testing/selftests/powerpc/include/reg.h
+++ b/tools/testing/selftests/powerpc/include/reg.h
@@ -57,6 +57,12 @@
#define SPRN_PPR 896 /* Program Priority Register */
#define SPRN_AMR 13 /* Authority Mask Register - problem state */
+#define set_amr(v) asm volatile("isync;" \
+ "mtspr " __stringify(SPRN_AMR) ",%0;" \
+ "isync" : \
+ : "r" ((unsigned long)(v)) \
+ : "memory")
+
/* TEXASR register bits */
#define TEXASR_FC 0xFE00000000000000
#define TEXASR_FP 0x0100000000000000
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index e089a0c30d9a..9dbe607cc5ec 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -60,6 +60,7 @@ static inline bool have_hwcap2(unsigned long ftr2)
#endif
bool is_ppc64le(void);
+int using_hash_mmu(bool *using_hash);
/* Yes, this is evil */
#define FAIL_IF(x) \
@@ -101,6 +102,11 @@ do { \
#define PPC_FEATURE2_ARCH_3_00 0x00800000
#endif
+/* POWER10 feature */
+#ifndef PPC_FEATURE2_ARCH_3_1
+#define PPC_FEATURE2_ARCH_3_1 0x00040000
+#endif
+
#if defined(__powerpc64__)
#define UCONTEXT_NIA(UC) (UC)->uc_mcontext.gp_regs[PT_NIP]
#define UCONTEXT_MSR(UC) (UC)->uc_mcontext.gp_regs[PT_MSR]
diff --git a/tools/testing/selftests/powerpc/math/.gitignore b/tools/testing/selftests/powerpc/math/.gitignore
index e31ca6f453ed..d0c23b2e4b60 100644
--- a/tools/testing/selftests/powerpc/math/.gitignore
+++ b/tools/testing/selftests/powerpc/math/.gitignore
@@ -6,3 +6,4 @@ vmx_preempt
fpu_signal
vmx_signal
vsx_preempt
+fpu_denormal
diff --git a/tools/testing/selftests/powerpc/math/Makefile b/tools/testing/selftests/powerpc/math/Makefile
index 11a10d7a2bbd..4e2049d2fd8d 100644
--- a/tools/testing/selftests/powerpc/math/Makefile
+++ b/tools/testing/selftests/powerpc/math/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt
+TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal fpu_denormal vmx_syscall vmx_preempt vmx_signal vsx_preempt
top_srcdir = ../../../../..
include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/math/fpu_denormal.c b/tools/testing/selftests/powerpc/math/fpu_denormal.c
new file mode 100644
index 000000000000..5f96682abaa8
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/fpu_denormal.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright IBM Corp. 2020
+ *
+ * This test attempts to cause a FP denormal exception on POWER8 CPUs. Unfortunately
+ * if the denormal handler is not configured or working properly, this can cause a bad
+ * crash in kernel mode when the kernel tries to save FP registers when the process
+ * exits.
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "utils.h"
+
+static int test_denormal_fpu(void)
+{
+ unsigned int m32;
+ unsigned long m64;
+ volatile float f;
+ volatile double d;
+
+ /* try to induce lfs <denormal> ; stfd */
+
+ m32 = 0x00715fcf; /* random denormal */
+ memcpy((float *)&f, &m32, sizeof(f));
+ d = f;
+ memcpy(&m64, (double *)&d, sizeof(d));
+
+ FAIL_IF((long)(m64 != 0x380c57f3c0000000)); /* renormalised value */
+
+ return 0;
+}
+
+int main(int argc, char *argv[])
+{
+ return test_harness(test_denormal_fpu, "fpu_denormal");
+}
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 2ca523255b1b..8d041f508a51 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -2,9 +2,9 @@
hugetlb_vs_thp_test
subpage_prot
tempfile
-prot_sao
segv_errors
wild_bctr
large_vm_fork_separation
bad_accesses
tlbie_test
+pkey_exec_prot
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index b9103c4bb414..5a86d59441dc 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -2,21 +2,20 @@
noarg:
$(MAKE) -C ../
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
- large_vm_fork_separation bad_accesses
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot segv_errors wild_bctr \
+ large_vm_fork_separation bad_accesses pkey_exec_prot
TEST_GEN_PROGS_EXTENDED := tlbie_test
TEST_GEN_FILES := tempfile
top_srcdir = ../../../../..
include ../../lib.mk
-$(TEST_GEN_PROGS): ../harness.c
-
-$(OUTPUT)/prot_sao: ../utils.c
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
$(OUTPUT)/wild_bctr: CFLAGS += -m64
$(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
$(OUTPUT)/bad_accesses: CFLAGS += -m64
+$(OUTPUT)/pkey_exec_prot: CFLAGS += -m64
$(OUTPUT)/tempfile:
dd if=/dev/zero of=$@ bs=64k count=1
diff --git a/tools/testing/selftests/powerpc/mm/bad_accesses.c b/tools/testing/selftests/powerpc/mm/bad_accesses.c
index adc465f499ef..a864ed7e2008 100644
--- a/tools/testing/selftests/powerpc/mm/bad_accesses.c
+++ b/tools/testing/selftests/powerpc/mm/bad_accesses.c
@@ -64,34 +64,6 @@ int bad_access(char *p, bool write)
return 0;
}
-static int using_hash_mmu(bool *using_hash)
-{
- char line[128];
- FILE *f;
- int rc;
-
- f = fopen("/proc/cpuinfo", "r");
- FAIL_IF(!f);
-
- rc = 0;
- while (fgets(line, sizeof(line), f) != NULL) {
- if (strcmp(line, "MMU : Hash\n") == 0) {
- *using_hash = true;
- goto out;
- }
-
- if (strcmp(line, "MMU : Radix\n") == 0) {
- *using_hash = false;
- goto out;
- }
- }
-
- rc = -1;
-out:
- fclose(f);
- return rc;
-}
-
static int test(void)
{
unsigned long i, j, addr, region_shift, page_shift, page_size;
diff --git a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
new file mode 100644
index 000000000000..7c7c93425c5e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright 2020, Sandipan Das, IBM Corp.
+ *
+ * Test if applying execute protection on pages using memory
+ * protection keys works as expected.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+
+#include <unistd.h>
+#include <sys/mman.h>
+
+#include "reg.h"
+#include "utils.h"
+
+/*
+ * Older versions of libc use the Intel-specific access rights.
+ * Hence, override the definitions as they might be incorrect.
+ */
+#undef PKEY_DISABLE_ACCESS
+#define PKEY_DISABLE_ACCESS 0x3
+
+#undef PKEY_DISABLE_WRITE
+#define PKEY_DISABLE_WRITE 0x2
+
+#undef PKEY_DISABLE_EXECUTE
+#define PKEY_DISABLE_EXECUTE 0x4
+
+/* Older versions of libc do not not define this */
+#ifndef SEGV_PKUERR
+#define SEGV_PKUERR 4
+#endif
+
+#define SI_PKEY_OFFSET 0x20
+
+#define SYS_pkey_mprotect 386
+#define SYS_pkey_alloc 384
+#define SYS_pkey_free 385
+
+#define PKEY_BITS_PER_PKEY 2
+#define NR_PKEYS 32
+#define PKEY_BITS_MASK ((1UL << PKEY_BITS_PER_PKEY) - 1)
+
+#define PPC_INST_NOP 0x60000000
+#define PPC_INST_TRAP 0x7fe00008
+#define PPC_INST_BLR 0x4e800020
+
+#define sigsafe_err(msg) ({ \
+ ssize_t nbytes __attribute__((unused)); \
+ nbytes = write(STDERR_FILENO, msg, strlen(msg)); })
+
+static inline unsigned long pkeyreg_get(void)
+{
+ return mfspr(SPRN_AMR);
+}
+
+static inline void pkeyreg_set(unsigned long amr)
+{
+ set_amr(amr);
+}
+
+static void pkey_set_rights(int pkey, unsigned long rights)
+{
+ unsigned long amr, shift;
+
+ shift = (NR_PKEYS - pkey - 1) * PKEY_BITS_PER_PKEY;
+ amr = pkeyreg_get();
+ amr &= ~(PKEY_BITS_MASK << shift);
+ amr |= (rights & PKEY_BITS_MASK) << shift;
+ pkeyreg_set(amr);
+}
+
+static int sys_pkey_mprotect(void *addr, size_t len, int prot, int pkey)
+{
+ return syscall(SYS_pkey_mprotect, addr, len, prot, pkey);
+}
+
+static int sys_pkey_alloc(unsigned long flags, unsigned long rights)
+{
+ return syscall(SYS_pkey_alloc, flags, rights);
+}
+
+static int sys_pkey_free(int pkey)
+{
+ return syscall(SYS_pkey_free, pkey);
+}
+
+static volatile sig_atomic_t fault_pkey, fault_code, fault_type;
+static volatile sig_atomic_t remaining_faults;
+static volatile unsigned int *fault_addr;
+static unsigned long pgsize, numinsns;
+static unsigned int *insns;
+
+static void trap_handler(int signum, siginfo_t *sinfo, void *ctx)
+{
+ /* Check if this fault originated from the expected address */
+ if (sinfo->si_addr != (void *) fault_addr)
+ sigsafe_err("got a fault for an unexpected address\n");
+
+ _exit(1);
+}
+
+static void segv_handler(int signum, siginfo_t *sinfo, void *ctx)
+{
+ int signal_pkey;
+
+ /*
+ * In older versions of libc, siginfo_t does not have si_pkey as
+ * a member.
+ */
+#ifdef si_pkey
+ signal_pkey = sinfo->si_pkey;
+#else
+ signal_pkey = *((int *)(((char *) sinfo) + SI_PKEY_OFFSET));
+#endif
+
+ fault_code = sinfo->si_code;
+
+ /* Check if this fault originated from the expected address */
+ if (sinfo->si_addr != (void *) fault_addr) {
+ sigsafe_err("got a fault for an unexpected address\n");
+ _exit(1);
+ }
+
+ /* Check if too many faults have occurred for a single test case */
+ if (!remaining_faults) {
+ sigsafe_err("got too many faults for the same address\n");
+ _exit(1);
+ }
+
+
+ /* Restore permissions in order to continue */
+ switch (fault_code) {
+ case SEGV_ACCERR:
+ if (mprotect(insns, pgsize, PROT_READ | PROT_WRITE)) {
+ sigsafe_err("failed to set access permissions\n");
+ _exit(1);
+ }
+ break;
+ case SEGV_PKUERR:
+ if (signal_pkey != fault_pkey) {
+ sigsafe_err("got a fault for an unexpected pkey\n");
+ _exit(1);
+ }
+
+ switch (fault_type) {
+ case PKEY_DISABLE_ACCESS:
+ pkey_set_rights(fault_pkey, 0);
+ break;
+ case PKEY_DISABLE_EXECUTE:
+ /*
+ * Reassociate the exec-only pkey with the region
+ * to be able to continue. Unlike AMR, we cannot
+ * set IAMR directly from userspace to restore the
+ * permissions.
+ */
+ if (mprotect(insns, pgsize, PROT_EXEC)) {
+ sigsafe_err("failed to set execute permissions\n");
+ _exit(1);
+ }
+ break;
+ default:
+ sigsafe_err("got a fault with an unexpected type\n");
+ _exit(1);
+ }
+ break;
+ default:
+ sigsafe_err("got a fault with an unexpected code\n");
+ _exit(1);
+ }
+
+ remaining_faults--;
+}
+
+static int pkeys_unsupported(void)
+{
+ bool hash_mmu = false;
+ int pkey;
+
+ /* Protection keys are currently supported on Hash MMU only */
+ FAIL_IF(using_hash_mmu(&hash_mmu));
+ SKIP_IF(!hash_mmu);
+
+ /* Check if the system call is supported */
+ pkey = sys_pkey_alloc(0, 0);
+ SKIP_IF(pkey < 0);
+ sys_pkey_free(pkey);
+
+ return 0;
+}
+
+static int test(void)
+{
+ struct sigaction segv_act, trap_act;
+ int pkey, ret, i;
+
+ ret = pkeys_unsupported();
+ if (ret)
+ return ret;
+
+ /* Setup SIGSEGV handler */
+ segv_act.sa_handler = 0;
+ segv_act.sa_sigaction = segv_handler;
+ FAIL_IF(sigprocmask(SIG_SETMASK, 0, &segv_act.sa_mask) != 0);
+ segv_act.sa_flags = SA_SIGINFO;
+ segv_act.sa_restorer = 0;
+ FAIL_IF(sigaction(SIGSEGV, &segv_act, NULL) != 0);
+
+ /* Setup SIGTRAP handler */
+ trap_act.sa_handler = 0;
+ trap_act.sa_sigaction = trap_handler;
+ FAIL_IF(sigprocmask(SIG_SETMASK, 0, &trap_act.sa_mask) != 0);
+ trap_act.sa_flags = SA_SIGINFO;
+ trap_act.sa_restorer = 0;
+ FAIL_IF(sigaction(SIGTRAP, &trap_act, NULL) != 0);
+
+ /* Setup executable region */
+ pgsize = getpagesize();
+ numinsns = pgsize / sizeof(unsigned int);
+ insns = (unsigned int *) mmap(NULL, pgsize, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ FAIL_IF(insns == MAP_FAILED);
+
+ /* Write the instruction words */
+ for (i = 1; i < numinsns - 1; i++)
+ insns[i] = PPC_INST_NOP;
+
+ /*
+ * Set the first instruction as an unconditional trap. If
+ * the last write to this address succeeds, this should
+ * get overwritten by a no-op.
+ */
+ insns[0] = PPC_INST_TRAP;
+
+ /*
+ * Later, to jump to the executable region, we use a branch
+ * and link instruction (bctrl) which sets the return address
+ * automatically in LR. Use that to return back.
+ */
+ insns[numinsns - 1] = PPC_INST_BLR;
+
+ /* Allocate a pkey that restricts execution */
+ pkey = sys_pkey_alloc(0, PKEY_DISABLE_EXECUTE);
+ FAIL_IF(pkey < 0);
+
+ /*
+ * Pick the first instruction's address from the executable
+ * region.
+ */
+ fault_addr = insns;
+
+ /* The following two cases will avoid SEGV_PKUERR */
+ fault_type = -1;
+ fault_pkey = -1;
+
+ /*
+ * Read an instruction word from the address when AMR bits
+ * are not set i.e. the pkey permits both read and write
+ * access.
+ *
+ * This should not generate a fault as having PROT_EXEC
+ * implies PROT_READ on GNU systems. The pkey currently
+ * restricts execution only based on the IAMR bits. The
+ * AMR bits are cleared.
+ */
+ remaining_faults = 0;
+ FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+ printf("read from %p, pkey is execute-disabled, access-enabled\n",
+ (void *) fault_addr);
+ i = *fault_addr;
+ FAIL_IF(remaining_faults != 0);
+
+ /*
+ * Write an instruction word to the address when AMR bits
+ * are not set i.e. the pkey permits both read and write
+ * access.
+ *
+ * This should generate an access fault as having just
+ * PROT_EXEC also restricts writes. The pkey currently
+ * restricts execution only based on the IAMR bits. The
+ * AMR bits are cleared.
+ */
+ remaining_faults = 1;
+ FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+ printf("write to %p, pkey is execute-disabled, access-enabled\n",
+ (void *) fault_addr);
+ *fault_addr = PPC_INST_TRAP;
+ FAIL_IF(remaining_faults != 0 || fault_code != SEGV_ACCERR);
+
+ /* The following three cases will generate SEGV_PKUERR */
+ fault_type = PKEY_DISABLE_ACCESS;
+ fault_pkey = pkey;
+
+ /*
+ * Read an instruction word from the address when AMR bits
+ * are set i.e. the pkey permits neither read nor write
+ * access.
+ *
+ * This should generate a pkey fault based on AMR bits only
+ * as having PROT_EXEC implicitly allows reads.
+ */
+ remaining_faults = 1;
+ FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+ printf("read from %p, pkey is execute-disabled, access-disabled\n",
+ (void *) fault_addr);
+ pkey_set_rights(pkey, PKEY_DISABLE_ACCESS);
+ i = *fault_addr;
+ FAIL_IF(remaining_faults != 0 || fault_code != SEGV_PKUERR);
+
+ /*
+ * Write an instruction word to the address when AMR bits
+ * are set i.e. the pkey permits neither read nor write
+ * access.
+ *
+ * This should generate two faults. First, a pkey fault
+ * based on AMR bits and then an access fault since
+ * PROT_EXEC does not allow writes.
+ */
+ remaining_faults = 2;
+ FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+ printf("write to %p, pkey is execute-disabled, access-disabled\n",
+ (void *) fault_addr);
+ pkey_set_rights(pkey, PKEY_DISABLE_ACCESS);
+ *fault_addr = PPC_INST_NOP;
+ FAIL_IF(remaining_faults != 0 || fault_code != SEGV_ACCERR);
+
+ /*
+ * Jump to the executable region when AMR bits are set i.e.
+ * the pkey permits neither read nor write access.
+ *
+ * This should generate a pkey fault based on IAMR bits which
+ * are set to not permit execution. AMR bits should not affect
+ * execution.
+ *
+ * This also checks if the overwrite of the first instruction
+ * word from a trap to a no-op succeeded.
+ */
+ fault_addr = insns;
+ fault_type = PKEY_DISABLE_EXECUTE;
+ fault_pkey = pkey;
+ remaining_faults = 1;
+ FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+ pkey_set_rights(pkey, PKEY_DISABLE_ACCESS);
+ printf("execute at %p, pkey is execute-disabled, access-disabled\n",
+ (void *) fault_addr);
+ asm volatile("mtctr %0; bctrl" : : "r"(insns));
+ FAIL_IF(remaining_faults != 0 || fault_code != SEGV_PKUERR);
+
+ /*
+ * Free the current pkey and allocate a new one that is
+ * fully permissive.
+ */
+ sys_pkey_free(pkey);
+ pkey = sys_pkey_alloc(0, 0);
+
+ /*
+ * Jump to the executable region when AMR bits are not set
+ * i.e. the pkey permits read and write access.
+ *
+ * This should not generate any faults as the IAMR bits are
+ * also not set and hence will the pkey will not restrict
+ * execution.
+ */
+ fault_pkey = pkey;
+ remaining_faults = 0;
+ FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+ printf("execute at %p, pkey is execute-enabled, access-enabled\n",
+ (void *) fault_addr);
+ asm volatile("mtctr %0; bctrl" : : "r"(insns));
+ FAIL_IF(remaining_faults != 0);
+
+ /* Cleanup */
+ munmap((void *) insns, pgsize);
+ sys_pkey_free(pkey);
+
+ return 0;
+}
+
+int main(void)
+{
+ test_harness(test, "pkey_exec_prot");
+}
diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
deleted file mode 100644
index e2eed65b7735..000000000000
--- a/tools/testing/selftests/powerpc/mm/prot_sao.c
+++ /dev/null
@@ -1,42 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright 2016, Michael Ellerman, IBM Corp.
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/mman.h>
-
-#include <asm/cputable.h>
-
-#include "utils.h"
-
-#define SIZE (64 * 1024)
-
-int test_prot_sao(void)
-{
- char *p;
-
- /* 2.06 or later should support SAO */
- SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
-
- /*
- * Ensure we can ask for PROT_SAO.
- * We can't really verify that it does the right thing, but at least we
- * confirm the kernel will accept it.
- */
- p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO,
- MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
- FAIL_IF(p == MAP_FAILED);
-
- /* Write to the mapping, to at least cause a fault */
- memset(p, 0xaa, SIZE);
-
- return 0;
-}
-
-int main(void)
-{
- return test_harness(test_prot_sao, "prot-sao");
-}
diff --git a/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c b/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c
index 6ee0fded0391..7c23d3dd7d6d 100644
--- a/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c
+++ b/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c
@@ -698,13 +698,13 @@ restart_nx:
switch (cc) {
- case ERR_NX_TRANSLATION:
+ case ERR_NX_AT_FAULT:
/* We touched the pages ahead of time. In the most common case
* we shouldn't be here. But may be some pages were paged out.
* Kernel should have placed the faulting address to fsaddr.
*/
- NXPRT(fprintf(stderr, "ERR_NX_TRANSLATION %p\n",
+ NXPRT(fprintf(stderr, "ERR_NX_AT_FAULT %p\n",
(void *)cmdp->crb.csb.fsaddr));
if (pgfault_retries == NX_MAX_FAULTS) {
diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
index 7496a83f9c9d..02dffb65de48 100644
--- a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
+++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
@@ -306,13 +306,13 @@ int compress_file(int argc, char **argv, void *handle)
lzcounts, cmdp, handle);
if (cc != ERR_NX_OK && cc != ERR_NX_TPBC_GT_SPBC &&
- cc != ERR_NX_TRANSLATION) {
+ cc != ERR_NX_AT_FAULT) {
fprintf(stderr, "nx error: cc= %d\n", cc);
exit(-1);
}
/* Page faults are handled by the user code */
- if (cc == ERR_NX_TRANSLATION) {
+ if (cc == ERR_NX_AT_FAULT) {
NXPRT(fprintf(stderr, "page fault: cc= %d, ", cc));
NXPRT(fprintf(stderr, "try= %d, fsa= %08llx\n",
fault_tries,
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index ca35dd8848b0..af3df79d8163 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -7,7 +7,7 @@ noarg:
# The EBB handler is 64-bit code and everything links against it
CFLAGS += -m64
-TMPOUT = $(OUTPUT)/
+TMPOUT = $(OUTPUT)/TMPDIR/
# Toolchains may build PIE by default which breaks the assembly
no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
$(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index a2d7b0e3dca9..a26ac122c759 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
-
dump_ebb_state();
event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index bc893813483e..bb9f587fa76e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
-
dump_ebb_state();
event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index dcd351d20328..9ae795ce314e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
-
dump_ebb_state();
printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index 94c99c12c0f2..4b45a2e70f62 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
-
dump_ebb_state();
event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index dfbc5c3ad52d..21537d6eb6b7 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
-
dump_ebb_state();
event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index ca2f7d729155..b208bf6ad58d 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
-
dump_ebb_state();
FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index ac3e6e182614..ba2681a12cc7 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
ebb_freeze_pmcs();
ebb_global_disable();
- count_pmc(4, sample_period);
mtspr(SPRN_PMC4, 0xdead);
dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index b8242e9d97d2..791d37ba327b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
- count_pmc(2, sample_period);
- count_pmc(3, sample_period);
- count_pmc(4, sample_period);
- count_pmc(5, sample_period);
- count_pmc(6, sample_period);
-
dump_ebb_state();
for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index a05c0e18ded6..9b0f70d59702 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
-
dump_summary_ebb_state();
event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index 153ebc92234f..2904c741e04e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(1, sample_period);
-
dump_ebb_state();
if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index eadad75ed7e6..b29f8ba22d1e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
ebb_global_disable();
ebb_freeze_pmcs();
- count_pmc(2, sample_period);
-
dump_ebb_state();
printf("PMC5/6 overflow %d\n", pmc56_overflowed);
diff --git a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c
index 2756fe2efdc5..2d37942bf72b 100644
--- a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c
+++ b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c
@@ -12,6 +12,8 @@
#include <string.h>
#include <sys/prctl.h>
+#include <asm/cputable.h>
+
#include "event.h"
#include "lib.h"
#include "utils.h"
@@ -23,12 +25,9 @@
static int per_event_excludes(void)
{
struct event *e, events[4];
- char *platform;
int i;
- platform = (char *)get_auxv_entry(AT_BASE_PLATFORM);
- FAIL_IF(!platform);
- SKIP_IF(strcmp(platform, "power8") != 0);
+ SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07));
/*
* We need to create the events disabled, otherwise the running/enabled
diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c
index d5c64fee032d..bbc05ffc5860 100644
--- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c
@@ -150,7 +150,7 @@ static int child(struct shared_info *info)
printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n",
user_write, info->amr, pkey1, pkey2, pkey3);
- mtspr(SPRN_AMR, info->amr);
+ set_amr(info->amr);
/*
* We won't use pkey3. This tests whether the kernel restores the UAMOR
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
index bdbbbe8431e0..bc454f899124 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
@@ -44,7 +44,7 @@ struct shared_info {
unsigned long amr2;
/* AMR value that ptrace should refuse to write to the child. */
- unsigned long amr3;
+ unsigned long invalid_amr;
/* IAMR value the parent expects to read from the child. */
unsigned long expected_iamr;
@@ -57,8 +57,8 @@ struct shared_info {
* (even though they're valid ones) because userspace doesn't have
* access to those registers.
*/
- unsigned long new_iamr;
- unsigned long new_uamor;
+ unsigned long invalid_iamr;
+ unsigned long invalid_uamor;
};
static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
@@ -66,11 +66,6 @@ static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
return syscall(__NR_pkey_alloc, flags, init_access_rights);
}
-static int sys_pkey_free(int pkey)
-{
- return syscall(__NR_pkey_free, pkey);
-}
-
static int child(struct shared_info *info)
{
unsigned long reg;
@@ -100,33 +95,37 @@ static int child(struct shared_info *info)
info->amr1 |= 3ul << pkeyshift(pkey1);
info->amr2 |= 3ul << pkeyshift(pkey2);
- info->amr3 |= info->amr2 | 3ul << pkeyshift(pkey3);
+ /*
+ * invalid amr value where we try to force write
+ * things which are deined by a uamor setting.
+ */
+ info->invalid_amr = info->amr2 | (~0x0UL & ~info->expected_uamor);
+ /*
+ * if PKEY_DISABLE_EXECUTE succeeded we should update the expected_iamr
+ */
if (disable_execute)
info->expected_iamr |= 1ul << pkeyshift(pkey1);
else
info->expected_iamr &= ~(1ul << pkeyshift(pkey1));
- info->expected_iamr &= ~(1ul << pkeyshift(pkey2) | 1ul << pkeyshift(pkey3));
-
- info->expected_uamor |= 3ul << pkeyshift(pkey1) |
- 3ul << pkeyshift(pkey2);
- info->new_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2);
- info->new_uamor |= 3ul << pkeyshift(pkey1);
+ /*
+ * We allocated pkey2 and pkey 3 above. Clear the IAMR bits.
+ */
+ info->expected_iamr &= ~(1ul << pkeyshift(pkey2));
+ info->expected_iamr &= ~(1ul << pkeyshift(pkey3));
/*
- * We won't use pkey3. We just want a plausible but invalid key to test
- * whether ptrace will let us write to AMR bits we are not supposed to.
- *
- * This also tests whether the kernel restores the UAMOR permissions
- * after a key is freed.
+ * Create an IAMR value different from expected value.
+ * Kernel will reject an IAMR and UAMOR change.
*/
- sys_pkey_free(pkey3);
+ info->invalid_iamr = info->expected_iamr | (1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2));
+ info->invalid_uamor = info->expected_uamor & ~(0x3ul << pkeyshift(pkey1));
printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n",
user_write, info->amr1, pkey1, pkey2, pkey3);
- mtspr(SPRN_AMR, info->amr1);
+ set_amr(info->amr1);
/* Wait for parent to read our AMR value and write a new one. */
ret = prod_parent(&info->child_sync);
@@ -196,9 +195,9 @@ static int parent(struct shared_info *info, pid_t pid)
PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync);
PARENT_FAIL_IF(ret, &info->child_sync);
- info->amr1 = info->amr2 = info->amr3 = regs[0];
- info->expected_iamr = info->new_iamr = regs[1];
- info->expected_uamor = info->new_uamor = regs[2];
+ info->amr1 = info->amr2 = regs[0];
+ info->expected_iamr = regs[1];
+ info->expected_uamor = regs[2];
/* Wake up child so that it can set itself up. */
ret = prod_child(&info->child_sync);
@@ -234,10 +233,10 @@ static int parent(struct shared_info *info, pid_t pid)
return ret;
/* Write invalid AMR value in child. */
- ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr3, 1);
+ ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->invalid_amr, 1);
PARENT_FAIL_IF(ret, &info->child_sync);
- printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr3);
+ printf("%-30s AMR: %016lx\n", ptrace_write_running, info->invalid_amr);
/* Wake up child so that it can verify it didn't change. */
ret = prod_child(&info->child_sync);
@@ -249,7 +248,7 @@ static int parent(struct shared_info *info, pid_t pid)
/* Try to write to IAMR. */
regs[0] = info->amr1;
- regs[1] = info->new_iamr;
+ regs[1] = info->invalid_iamr;
ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 2);
PARENT_FAIL_IF(!ret, &info->child_sync);
@@ -257,7 +256,7 @@ static int parent(struct shared_info *info, pid_t pid)
ptrace_write_running, regs[0], regs[1]);
/* Try to write to IAMR and UAMOR. */
- regs[2] = info->new_uamor;
+ regs[2] = info->invalid_uamor;
ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 3);
PARENT_FAIL_IF(!ret, &info->child_sync);
diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp.c b/tools/testing/selftests/powerpc/stringloops/memcmp.c
index b1fa7546957f..e4605ca850dc 100644
--- a/tools/testing/selftests/powerpc/stringloops/memcmp.c
+++ b/tools/testing/selftests/powerpc/stringloops/memcmp.c
@@ -2,6 +2,7 @@
#include <malloc.h>
#include <stdlib.h>
#include <string.h>
+#include <sys/mman.h>
#include <time.h>
#include "utils.h"
@@ -13,6 +14,9 @@
#define LARGE_MAX_OFFSET 32
#define LARGE_SIZE_START 4096
+/* This is big enough to fit LARGE_SIZE and works on 4K & 64K kernels */
+#define MAP_SIZE (64 * 1024)
+
#define MAX_OFFSET_DIFF_S1_S2 48
int vmx_count;
@@ -68,25 +72,25 @@ static void test_one(char *s1, char *s2, unsigned long max_offset,
static int testcase(bool islarge)
{
- char *s1;
- char *s2;
- unsigned long i;
-
- unsigned long comp_size = (islarge ? LARGE_SIZE : SIZE);
- unsigned long alloc_size = comp_size + MAX_OFFSET_DIFF_S1_S2;
- int iterations = islarge ? LARGE_ITERATIONS : ITERATIONS;
-
- s1 = memalign(128, alloc_size);
- if (!s1) {
- perror("memalign");
- exit(1);
- }
+ unsigned long i, comp_size, alloc_size;
+ char *p, *s1, *s2;
+ int iterations;
- s2 = memalign(128, alloc_size);
- if (!s2) {
- perror("memalign");
- exit(1);
- }
+ comp_size = (islarge ? LARGE_SIZE : SIZE);
+ alloc_size = comp_size + MAX_OFFSET_DIFF_S1_S2;
+ iterations = islarge ? LARGE_ITERATIONS : ITERATIONS;
+
+ p = mmap(NULL, 4 * MAP_SIZE, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ FAIL_IF(p == MAP_FAILED);
+
+ /* Put s1/s2 at the end of a page */
+ s1 = p + MAP_SIZE - alloc_size;
+ s2 = p + 3 * MAP_SIZE - alloc_size;
+
+ /* And unmap the subsequent page to force a fault if we overread */
+ munmap(p + MAP_SIZE, MAP_SIZE);
+ munmap(p + 3 * MAP_SIZE, MAP_SIZE);
srandom(time(0));
diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
index 5ee0e98c4896..933678f1ed0a 100644
--- a/tools/testing/selftests/powerpc/utils.c
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -293,3 +293,31 @@ void set_dscr(unsigned long val)
asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
}
+
+int using_hash_mmu(bool *using_hash)
+{
+ char line[128];
+ FILE *f;
+ int rc;
+
+ f = fopen("/proc/cpuinfo", "r");
+ FAIL_IF(!f);
+
+ rc = 0;
+ while (fgets(line, sizeof(line), f) != NULL) {
+ if (strcmp(line, "MMU : Hash\n") == 0) {
+ *using_hash = true;
+ goto out;
+ }
+
+ if (strcmp(line, "MMU : Radix\n") == 0) {
+ *using_hash = false;
+ goto out;
+ }
+ }
+
+ rc = -1;
+out:
+ fclose(f);
+ return rc;
+}