summaryrefslogtreecommitdiffstats
path: root/arch/powerpc
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/Kconfig214
-rw-r--r--arch/powerpc/Makefile24
-rw-r--r--arch/powerpc/Makefile.postlink34
-rw-r--r--arch/powerpc/boot/zImage.lds.S1
-rw-r--r--arch/powerpc/configs/85xx-hw.config3
-rw-r--r--arch/powerpc/configs/85xx/ge_imp3a_defconfig1
-rw-r--r--arch/powerpc/configs/85xx/xes_mpc85xx_defconfig1
-rw-r--r--arch/powerpc/configs/cell_defconfig1
-rw-r--r--arch/powerpc/configs/pasemi_defconfig1
-rw-r--r--arch/powerpc/configs/powernv_defconfig6
-rw-r--r--arch/powerpc/configs/ppc64_defconfig7
-rw-r--r--arch/powerpc/configs/ppc64e_defconfig1
-rw-r--r--arch/powerpc/configs/ppc6xx_defconfig3
-rw-r--r--arch/powerpc/configs/pseries_defconfig6
-rw-r--r--arch/powerpc/crypto/Makefile3
-rw-r--r--arch/powerpc/crypto/crc-vpmsum_test.c137
-rw-r--r--arch/powerpc/crypto/crc32-vpmsum_core.S755
-rw-r--r--arch/powerpc/crypto/crc32c-vpmsum_asm.S715
-rw-r--r--arch/powerpc/crypto/crc32c-vpmsum_glue.c5
-rw-r--r--arch/powerpc/crypto/crct10dif-vpmsum_asm.S850
-rw-r--r--arch/powerpc/crypto/crct10dif-vpmsum_glue.c128
-rw-r--r--arch/powerpc/include/asm/asm-prototypes.h4
-rw-r--r--arch/powerpc/include/asm/bitops.h12
-rw-r--r--arch/powerpc/include/asm/book3s/32/pgtable.h1
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash-4k.h2
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash-64k.h10
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash.h16
-rw-r--r--arch/powerpc/include/asm/book3s/64/hugetlb.h2
-rw-r--r--arch/powerpc/include/asm/book3s/64/mmu-hash.h200
-rw-r--r--arch/powerpc/include/asm/book3s/64/mmu.h9
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h146
-rw-r--r--arch/powerpc/include/asm/book3s/64/radix.h8
-rw-r--r--arch/powerpc/include/asm/bug.h4
-rw-r--r--arch/powerpc/include/asm/checksum.h2
-rw-r--r--arch/powerpc/include/asm/code-patching.h41
-rw-r--r--arch/powerpc/include/asm/cpuidle.h37
-rw-r--r--arch/powerpc/include/asm/cputable.h5
-rw-r--r--arch/powerpc/include/asm/dbell.h40
-rw-r--r--arch/powerpc/include/asm/debug.h2
-rw-r--r--arch/powerpc/include/asm/debugfs.h17
-rw-r--r--arch/powerpc/include/asm/disassemble.h5
-rw-r--r--arch/powerpc/include/asm/elf.h4
-rw-r--r--arch/powerpc/include/asm/exception-64s.h95
-rw-r--r--arch/powerpc/include/asm/extable.h29
-rw-r--r--arch/powerpc/include/asm/fadump.h2
-rw-r--r--arch/powerpc/include/asm/feature-fixups.h3
-rw-r--r--arch/powerpc/include/asm/head-64.h1
-rw-r--r--arch/powerpc/include/asm/hvcall.h10
-rw-r--r--arch/powerpc/include/asm/io.h102
-rw-r--r--arch/powerpc/include/asm/iommu.h32
-rw-r--r--arch/powerpc/include/asm/kprobes.h63
-rw-r--r--arch/powerpc/include/asm/kvm_book3s_64.h2
-rw-r--r--arch/powerpc/include/asm/kvm_book3s_asm.h4
-rw-r--r--arch/powerpc/include/asm/kvm_host.h63
-rw-r--r--arch/powerpc/include/asm/kvm_ppc.h106
-rw-r--r--arch/powerpc/include/asm/machdep.h2
-rw-r--r--arch/powerpc/include/asm/mce.h104
-rw-r--r--arch/powerpc/include/asm/mmu-book3e.h5
-rw-r--r--arch/powerpc/include/asm/mmu.h19
-rw-r--r--arch/powerpc/include/asm/mmu_context.h30
-rw-r--r--arch/powerpc/include/asm/nohash/32/pgtable.h1
-rw-r--r--arch/powerpc/include/asm/nohash/64/pgtable-4k.h3
-rw-r--r--arch/powerpc/include/asm/nohash/64/pgtable-64k.h1
-rw-r--r--arch/powerpc/include/asm/nohash/64/pgtable.h5
-rw-r--r--arch/powerpc/include/asm/nohash/pgtable.h2
-rw-r--r--arch/powerpc/include/asm/opal-api.h77
-rw-r--r--arch/powerpc/include/asm/opal.h41
-rw-r--r--arch/powerpc/include/asm/paca.h38
-rw-r--r--arch/powerpc/include/asm/page_64.h14
-rw-r--r--arch/powerpc/include/asm/pci.h9
-rw-r--r--arch/powerpc/include/asm/perf_event_server.h3
-rw-r--r--arch/powerpc/include/asm/powernv.h22
-rw-r--r--arch/powerpc/include/asm/ppc-opcode.h67
-rw-r--r--arch/powerpc/include/asm/processor.h41
-rw-r--r--arch/powerpc/include/asm/prom.h18
-rw-r--r--arch/powerpc/include/asm/reg.h4
-rw-r--r--arch/powerpc/include/asm/sections.h2
-rw-r--r--arch/powerpc/include/asm/smp.h21
-rw-r--r--arch/powerpc/include/asm/syscalls.h4
-rw-r--r--arch/powerpc/include/asm/systbl.h1
-rw-r--r--arch/powerpc/include/asm/thread_info.h14
-rw-r--r--arch/powerpc/include/asm/uaccess.h96
-rw-r--r--arch/powerpc/include/asm/unistd.h2
-rw-r--r--arch/powerpc/include/asm/xics.h2
-rw-r--r--arch/powerpc/include/asm/xive-regs.h97
-rw-r--r--arch/powerpc/include/asm/xive.h162
-rw-r--r--arch/powerpc/include/asm/xmon.h2
-rw-r--r--arch/powerpc/include/uapi/asm/kvm.h3
-rw-r--r--arch/powerpc/include/uapi/asm/mman.h16
-rw-r--r--arch/powerpc/include/uapi/asm/socket.h6
-rw-r--r--arch/powerpc/include/uapi/asm/unistd.h1
-rw-r--r--arch/powerpc/kernel/Makefile12
-rw-r--r--arch/powerpc/kernel/align.c27
-rw-r--r--arch/powerpc/kernel/asm-offsets.c19
-rw-r--r--arch/powerpc/kernel/cpu_setup_power.S36
-rw-r--r--arch/powerpc/kernel/cputable.c3
-rw-r--r--arch/powerpc/kernel/crash.c2
-rw-r--r--arch/powerpc/kernel/dbell.c58
-rw-r--r--arch/powerpc/kernel/eeh.c3
-rw-r--r--arch/powerpc/kernel/eeh_driver.c55
-rw-r--r--arch/powerpc/kernel/entry_32.S107
-rw-r--r--arch/powerpc/kernel/entry_64.S386
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S188
-rw-r--r--arch/powerpc/kernel/fadump.c93
-rw-r--r--arch/powerpc/kernel/head_32.S16
-rw-r--r--arch/powerpc/kernel/head_64.S3
-rw-r--r--arch/powerpc/kernel/idle_book3s.S315
-rw-r--r--arch/powerpc/kernel/iommu.c91
-rw-r--r--arch/powerpc/kernel/irq.c41
-rw-r--r--arch/powerpc/kernel/kprobes-ftrace.c104
-rw-r--r--arch/powerpc/kernel/kprobes.c214
-rw-r--r--arch/powerpc/kernel/mce.c106
-rw-r--r--arch/powerpc/kernel/mce_power.c591
-rw-r--r--arch/powerpc/kernel/misc_64.S4
-rw-r--r--arch/powerpc/kernel/nvram_64.c89
-rw-r--r--arch/powerpc/kernel/optprobes.c6
-rw-r--r--arch/powerpc/kernel/paca.c21
-rw-r--r--arch/powerpc/kernel/pci-common.c11
-rw-r--r--arch/powerpc/kernel/prom.c1
-rw-r--r--arch/powerpc/kernel/prom_init.c122
-rw-r--r--arch/powerpc/kernel/setup-common.c16
-rw-r--r--arch/powerpc/kernel/setup_64.c23
-rw-r--r--arch/powerpc/kernel/signal.c4
-rw-r--r--arch/powerpc/kernel/smp.c325
-rw-r--r--arch/powerpc/kernel/stacktrace.c9
-rw-r--r--arch/powerpc/kernel/swsusp.c1
-rw-r--r--arch/powerpc/kernel/syscalls.c16
-rw-r--r--arch/powerpc/kernel/sysfs.c12
-rw-r--r--arch/powerpc/kernel/time.c2
-rw-r--r--arch/powerpc/kernel/trace/Makefile29
-rw-r--r--arch/powerpc/kernel/trace/ftrace.c (renamed from arch/powerpc/kernel/ftrace.c)1
-rw-r--r--arch/powerpc/kernel/trace/ftrace_32.S118
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64.S85
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64_mprofile.S272
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64_pg.S68
-rw-r--r--arch/powerpc/kernel/trace/trace_clock.c (renamed from arch/powerpc/kernel/trace_clock.c)0
-rw-r--r--arch/powerpc/kernel/traps.c27
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S4
-rw-r--r--arch/powerpc/kvm/Kconfig6
-rw-r--r--arch/powerpc/kvm/Makefile4
-rw-r--r--arch/powerpc/kvm/book3s.c101
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu.c1
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_host.c17
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c6
-rw-r--r--arch/powerpc/kvm/book3s_64_vio.c315
-rw-r--r--arch/powerpc/kvm/book3s_64_vio_hv.c303
-rw-r--r--arch/powerpc/kvm/book3s_emulate.c34
-rw-r--r--arch/powerpc/kvm/book3s_hv.c77
-rw-r--r--arch/powerpc/kvm/book3s_hv_builtin.c135
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_mmu.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_xics.c15
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_xive.c47
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S62
-rw-r--r--arch/powerpc/kvm/book3s_pr.c14
-rw-r--r--arch/powerpc/kvm/book3s_pr_papr.c2
-rw-r--r--arch/powerpc/kvm/book3s_rtas.c21
-rw-r--r--arch/powerpc/kvm/book3s_xics.c40
-rw-r--r--arch/powerpc/kvm/book3s_xics.h7
-rw-r--r--arch/powerpc/kvm/book3s_xive.c1894
-rw-r--r--arch/powerpc/kvm/book3s_xive.h256
-rw-r--r--arch/powerpc/kvm/book3s_xive_template.c503
-rw-r--r--arch/powerpc/kvm/booke.c9
-rw-r--r--arch/powerpc/kvm/e500_mmu_host.c5
-rw-r--r--arch/powerpc/kvm/emulate.c8
-rw-r--r--arch/powerpc/kvm/emulate_loadstore.c472
-rw-r--r--arch/powerpc/kvm/irq.h1
-rw-r--r--arch/powerpc/kvm/powerpc.c344
-rw-r--r--arch/powerpc/lib/Makefile3
-rw-r--r--arch/powerpc/lib/code-patching.c4
-rw-r--r--arch/powerpc/lib/copy_32.S14
-rw-r--r--arch/powerpc/lib/copyuser_64.S35
-rw-r--r--arch/powerpc/lib/sstep.c102
-rw-r--r--arch/powerpc/lib/test_emulate_step.c434
-rw-r--r--arch/powerpc/lib/usercopy_64.c41
-rw-r--r--arch/powerpc/mm/dump_hashpagetable.c2
-rw-r--r--arch/powerpc/mm/dump_linuxpagetables.c106
-rw-r--r--arch/powerpc/mm/fault.c84
-rw-r--r--arch/powerpc/mm/hash_low_32.S2
-rw-r--r--arch/powerpc/mm/hash_native_64.c7
-rw-r--r--arch/powerpc/mm/hash_utils_64.c26
-rw-r--r--arch/powerpc/mm/hugetlbpage-book3e.c7
-rw-r--r--arch/powerpc/mm/hugetlbpage-radix.c11
-rw-r--r--arch/powerpc/mm/hugetlbpage.c18
-rw-r--r--arch/powerpc/mm/icswx.c2
-rw-r--r--arch/powerpc/mm/init_64.c43
-rw-r--r--arch/powerpc/mm/mmap.c53
-rw-r--r--arch/powerpc/mm/mmu_context_book3s64.c116
-rw-r--r--arch/powerpc/mm/mmu_context_iommu.c43
-rw-r--r--arch/powerpc/mm/mmu_context_nohash.c5
-rw-r--r--arch/powerpc/mm/numa.c7
-rw-r--r--arch/powerpc/mm/pgtable-radix.c4
-rw-r--r--arch/powerpc/mm/slb.c4
-rw-r--r--arch/powerpc/mm/slb_low.S82
-rw-r--r--arch/powerpc/mm/slice.c258
-rw-r--r--arch/powerpc/mm/subpage-prot.c3
-rw-r--r--arch/powerpc/mm/tlb-radix.c93
-rw-r--r--arch/powerpc/mm/tlb_nohash.c2
-rw-r--r--arch/powerpc/perf/core-book3s.c10
-rw-r--r--arch/powerpc/perf/isa207-common.c125
-rw-r--r--arch/powerpc/perf/isa207-common.h27
-rw-r--r--arch/powerpc/perf/power8-events-list.h6
-rw-r--r--arch/powerpc/perf/power8-pmu.c4
-rw-r--r--arch/powerpc/perf/power9-pmu.c2
-rw-r--r--arch/powerpc/platforms/44x/sam440ep.c2
-rw-r--r--arch/powerpc/platforms/52xx/Kconfig1
-rw-r--r--arch/powerpc/platforms/85xx/smp.c12
-rw-r--r--arch/powerpc/platforms/86xx/mpc86xx_smp.c1
-rw-r--r--arch/powerpc/platforms/Kconfig1
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype14
-rw-r--r--arch/powerpc/platforms/cell/axon_msi.c2
-rw-r--r--arch/powerpc/platforms/cell/interrupt.c2
-rw-r--r--arch/powerpc/platforms/cell/pervasive.c11
-rw-r--r--arch/powerpc/platforms/chrp/smp.c1
-rw-r--r--arch/powerpc/platforms/pasemi/idle.c11
-rw-r--r--arch/powerpc/platforms/powermac/smp.c3
-rw-r--r--arch/powerpc/platforms/powernv/Kconfig3
-rw-r--r--arch/powerpc/platforms/powernv/eeh-powernv.c7
-rw-r--r--arch/powerpc/platforms/powernv/idle.c109
-rw-r--r--arch/powerpc/platforms/powernv/npu-dma.c470
-rw-r--r--arch/powerpc/platforms/powernv/opal-lpc.c3
-rw-r--r--arch/powerpc/platforms/powernv/opal-sensor.c4
-rw-r--r--arch/powerpc/platforms/powernv/opal-wrappers.S75
-rw-r--r--arch/powerpc/platforms/powernv/opal-xscom.c27
-rw-r--r--arch/powerpc/platforms/powernv/opal.c101
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda.c98
-rw-r--r--arch/powerpc/platforms/powernv/pci.c6
-rw-r--r--arch/powerpc/platforms/powernv/pci.h17
-rw-r--r--arch/powerpc/platforms/powernv/powernv.h2
-rw-r--r--arch/powerpc/platforms/powernv/rng.c2
-rw-r--r--arch/powerpc/platforms/powernv/setup.c19
-rw-r--r--arch/powerpc/platforms/powernv/smp.c107
-rw-r--r--arch/powerpc/platforms/ps3/smp.c4
-rw-r--r--arch/powerpc/platforms/pseries/Kconfig3
-rw-r--r--arch/powerpc/platforms/pseries/dlpar.c1
-rw-r--r--arch/powerpc/platforms/pseries/dtl.c3
-rw-r--r--arch/powerpc/platforms/pseries/hvCall_inst.c10
-rw-r--r--arch/powerpc/platforms/pseries/ibmebus.c5
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c43
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c65
-rw-r--r--arch/powerpc/platforms/pseries/ras.c4
-rw-r--r--arch/powerpc/platforms/pseries/setup.c4
-rw-r--r--arch/powerpc/platforms/pseries/smp.c49
-rw-r--r--arch/powerpc/platforms/pseries/vio.c2
-rw-r--r--arch/powerpc/purgatory/trampoline.S12
-rw-r--r--arch/powerpc/sysdev/Kconfig1
-rw-r--r--arch/powerpc/sysdev/Makefile1
-rw-r--r--arch/powerpc/sysdev/axonram.c50
-rw-r--r--arch/powerpc/sysdev/scom.c3
-rw-r--r--arch/powerpc/sysdev/xics/icp-hv.c2
-rw-r--r--arch/powerpc/sysdev/xics/icp-native.c20
-rw-r--r--arch/powerpc/sysdev/xics/icp-opal.c12
-rw-r--r--arch/powerpc/sysdev/xics/xics-common.c23
-rw-r--r--arch/powerpc/sysdev/xive/Kconfig11
-rw-r--r--arch/powerpc/sysdev/xive/Makefile4
-rw-r--r--arch/powerpc/sysdev/xive/common.c1432
-rw-r--r--arch/powerpc/sysdev/xive/native.c716
-rw-r--r--arch/powerpc/sysdev/xive/xive-internal.h62
-rwxr-xr-xarch/powerpc/tools/gcc-check-mprofile-kernel.sh (renamed from arch/powerpc/scripts/gcc-check-mprofile-kernel.sh)0
-rwxr-xr-xarch/powerpc/tools/relocs_check.sh (renamed from arch/powerpc/relocs_check.sh)0
-rw-r--r--arch/powerpc/xmon/xmon.c241
260 files changed, 15364 insertions, 3662 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 494091762bd7..964da1891ea9 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -22,6 +22,48 @@ config MMU
bool
default y
+config ARCH_MMAP_RND_BITS_MAX
+ # On Book3S 64, the default virtual address space for 64-bit processes
+ # is 2^47 (128TB). As a maximum, allow randomisation to consume up to
+ # 32T of address space (2^45), which should ensure a reasonable gap
+ # between bottom-up and top-down allocations for applications that
+ # consume "normal" amounts of address space. Book3S 64 only supports 64K
+ # and 4K page sizes.
+ default 29 if PPC_BOOK3S_64 && PPC_64K_PAGES # 29 = 45 (32T) - 16 (64K)
+ default 33 if PPC_BOOK3S_64 # 33 = 45 (32T) - 12 (4K)
+ #
+ # On all other 64-bit platforms (currently only Book3E), the virtual
+ # address space is 2^46 (64TB). Allow randomisation to consume up to 16T
+ # of address space (2^44). Only 4K page sizes are supported.
+ default 32 if 64BIT # 32 = 44 (16T) - 12 (4K)
+ #
+ # For 32-bit, use the compat values, as they're the same.
+ default ARCH_MMAP_RND_COMPAT_BITS_MAX
+
+config ARCH_MMAP_RND_BITS_MIN
+ # Allow randomisation to consume up to 1GB of address space (2^30).
+ default 14 if 64BIT && PPC_64K_PAGES # 14 = 30 (1GB) - 16 (64K)
+ default 18 if 64BIT # 18 = 30 (1GB) - 12 (4K)
+ #
+ # For 32-bit, use the compat values, as they're the same.
+ default ARCH_MMAP_RND_COMPAT_BITS_MIN
+
+config ARCH_MMAP_RND_COMPAT_BITS_MAX
+ # Total virtual address space for 32-bit processes is 2^31 (2GB).
+ # Allow randomisation to consume up to 512MB of address space (2^29).
+ default 11 if PPC_256K_PAGES # 11 = 29 (512MB) - 18 (256K)
+ default 13 if PPC_64K_PAGES # 13 = 29 (512MB) - 16 (64K)
+ default 15 if PPC_16K_PAGES # 15 = 29 (512MB) - 14 (16K)
+ default 17 # 17 = 29 (512MB) - 12 (4K)
+
+config ARCH_MMAP_RND_COMPAT_BITS_MIN
+ # Total virtual address space for 32-bit processes is 2^31 (2GB).
+ # Allow randomisation to consume up to 8MB of address space (2^23).
+ default 5 if PPC_256K_PAGES # 5 = 23 (8MB) - 18 (256K)
+ default 7 if PPC_64K_PAGES # 7 = 23 (8MB) - 16 (64K)
+ default 9 if PPC_16K_PAGES # 9 = 23 (8MB) - 14 (16K)
+ default 11 # 11 = 23 (8MB) - 12 (4K)
+
config HAVE_SETUP_PER_CPU_AREA
def_bool PPC64
@@ -38,6 +80,11 @@ config NR_IRQS
/proc/interrupts. If you configure your system to have too few,
drivers will fail to load or worse - handle with care.
+config NMI_IPI
+ bool
+ depends on SMP && (DEBUGGER || KEXEC_CORE)
+ default y
+
config STACKTRACE_SUPPORT
bool
default y
@@ -80,93 +127,102 @@ config ARCH_HAS_DMA_SET_COHERENT_MASK
config PPC
bool
default y
- select BUILDTIME_EXTABLE_SORT
+ #
+ # Please keep this list sorted alphabetically.
+ #
+ select ARCH_HAS_DEVMEM_IS_ALLOWED
+ select ARCH_HAS_DMA_SET_COHERENT_MASK
+ select ARCH_HAS_ELF_RANDOMIZE
+ select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
+ select ARCH_HAS_SG_CHAIN
+ select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+ select ARCH_HAS_UBSAN_SANITIZE_ALL
+ select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
+ select ARCH_SUPPORTS_ATOMIC_RMW
+ select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
+ select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_CMPXCHG_LOCKREF if PPC64
+ select ARCH_WANT_IPC_PARSE_VERSION
+ select ARCH_WEAK_RELEASE_ACQUIRE
select BINFMT_ELF
- select ARCH_HAS_ELF_RANDOMIZE
- select OF
- select OF_EARLY_FLATTREE
- select OF_RESERVED_MEM
- select HAVE_FTRACE_MCOUNT_RECORD
+ select BUILDTIME_EXTABLE_SORT
+ select CLONE_BACKWARDS
+ select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
+ select EDAC_ATOMIC_SCRUB
+ select EDAC_SUPPORT
+ select GENERIC_ATOMIC64 if PPC32
+ select GENERIC_CLOCKEVENTS
+ select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+ select GENERIC_CMOS_UPDATE
+ select GENERIC_CPU_AUTOPROBE
+ select GENERIC_IRQ_SHOW
+ select GENERIC_IRQ_SHOW_LEVEL
+ select GENERIC_SMP_IDLE_THREAD
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
+ select GENERIC_TIME_VSYSCALL_OLD
+ select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_KGDB
+ select HAVE_ARCH_MMAP_RND_BITS
+ select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
+ select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_TRACEHOOK
+ select HAVE_CBPF_JIT if !PPC64
+ select HAVE_CONTEXT_TRACKING if PPC64
+ select HAVE_DEBUG_KMEMLEAK
+ select HAVE_DEBUG_STACKOVERFLOW
+ select HAVE_DMA_API_DEBUG
select HAVE_DYNAMIC_FTRACE
- select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
- select HAVE_FUNCTION_TRACER
+ select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
+ select HAVE_EBPF_JIT if PPC64
+ select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+ select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_TRACER
+ select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
- select SYSCTL_EXCEPTION_TRACE
- select VIRT_TO_BUS if !PPC64
+ select HAVE_GENERIC_RCU_GUP
+ select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
select HAVE_IDE
select HAVE_IOREMAP_PROT
- select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+ select HAVE_IRQ_EXIT_ON_IRQ_STACK
+ select HAVE_KERNEL_GZIP
select HAVE_KPROBES
- select HAVE_OPTPROBES if PPC64
- select HAVE_ARCH_KGDB
+ select HAVE_KPROBES_ON_FTRACE
select HAVE_KRETPROBES
- select HAVE_ARCH_TRACEHOOK
+ select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
- select HAVE_DMA_API_DEBUG
+ select HAVE_MOD_ARCH_SPECIFIC
+ select HAVE_NMI if PERF_EVENTS
select HAVE_OPROFILE
- select HAVE_DEBUG_KMEMLEAK
- select ARCH_HAS_SG_CHAIN
- select GENERIC_ATOMIC64 if PPC32
+ select HAVE_OPTPROBES if PPC64
select HAVE_PERF_EVENTS
+ select HAVE_PERF_EVENTS_NMI if PPC64
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
+ select HAVE_RCU_TABLE_FREE if SMP
select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
- select ARCH_WANT_IPC_PARSE_VERSION
- select SPARSE_IRQ
+ select HAVE_SYSCALL_TRACEPOINTS
+ select HAVE_VIRT_CPU_ACCOUNTING
select IRQ_DOMAIN
- select GENERIC_IRQ_SHOW
- select GENERIC_IRQ_SHOW_LEVEL
select IRQ_FORCED_THREADING
- select HAVE_RCU_TABLE_FREE if SMP
- select HAVE_SYSCALL_TRACEPOINTS
- select HAVE_CBPF_JIT if !PPC64
- select HAVE_EBPF_JIT if PPC64
- select HAVE_ARCH_JUMP_LABEL
- select ARCH_HAVE_NMI_SAFE_CMPXCHG
- select ARCH_HAS_GCOV_PROFILE_ALL
- select GENERIC_SMP_IDLE_THREAD
- select GENERIC_CMOS_UPDATE
- select GENERIC_TIME_VSYSCALL_OLD
- select GENERIC_CLOCKEVENTS
- select GENERIC_CLOCKEVENTS_BROADCAST if SMP
- select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
- select GENERIC_STRNCPY_FROM_USER
- select GENERIC_STRNLEN_USER
- select HAVE_MOD_ARCH_SPECIFIC
select MODULES_USE_ELF_RELA
- select CLONE_BACKWARDS
- select ARCH_USE_BUILTIN_BSWAP
- select OLD_SIGSUSPEND
- select OLD_SIGACTION if PPC32
- select HAVE_DEBUG_STACKOVERFLOW
- select HAVE_IRQ_EXIT_ON_IRQ_STACK
- select ARCH_USE_CMPXCHG_LOCKREF if PPC64
- select HAVE_ARCH_AUDITSYSCALL
- select ARCH_SUPPORTS_ATOMIC_RMW
- select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
select NO_BOOTMEM
- select HAVE_GENERIC_RCU_GUP
- select HAVE_PERF_EVENTS_NMI if PPC64
- select HAVE_NMI if PERF_EVENTS
- select EDAC_SUPPORT
- select EDAC_ATOMIC_SCRUB
- select ARCH_HAS_DMA_SET_COHERENT_MASK
- select ARCH_HAS_DEVMEM_IS_ALLOWED
- select HAVE_ARCH_SECCOMP_FILTER
- select ARCH_HAS_UBSAN_SANITIZE_ALL
- select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
- select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
- select GENERIC_CPU_AUTOPROBE
- select HAVE_VIRT_CPU_ACCOUNTING
- select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
- select HAVE_ARCH_HARDENED_USERCOPY
- select HAVE_KERNEL_GZIP
- select HAVE_CONTEXT_TRACKING if PPC64
+ select OF
+ select OF_EARLY_FLATTREE
+ select OF_RESERVED_MEM
+ select OLD_SIGACTION if PPC32
+ select OLD_SIGSUSPEND
+ select SPARSE_IRQ
+ select SYSCTL_EXCEPTION_TRACE
+ select VIRT_TO_BUS if !PPC64
+ #
+ # Please keep this list sorted alphabetically.
+ #
config GENERIC_CSUM
def_bool n
@@ -484,7 +540,7 @@ config KEXEC_FILE
config RELOCATABLE
bool "Build a relocatable kernel"
- depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE))
+ depends on PPC64 || (FLATMEM && (44x || FSL_BOOKE))
select NONSTATIC_KERNEL
select MODULE_REL_CRCS if MODVERSIONS
help
@@ -516,21 +572,23 @@ config RELOCATABLE_TEST
relocation code.
config CRASH_DUMP
- bool "Build a kdump crash kernel"
+ bool "Build a dump capture kernel"
depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP)
- select RELOCATABLE if (PPC64 && !COMPILE_TEST) || 44x || FSL_BOOKE
+ select RELOCATABLE if PPC64 || 44x || FSL_BOOKE
help
- Build a kernel suitable for use as a kdump capture kernel.
+ Build a kernel suitable for use as a dump capture kernel.
The same kernel binary can be used as production kernel and dump
capture kernel.
config FA_DUMP
bool "Firmware-assisted dump"
- depends on PPC64 && PPC_RTAS && CRASH_DUMP && KEXEC_CORE
+ depends on PPC64 && PPC_RTAS
+ select CRASH_CORE
+ select CRASH_DUMP
help
A robust mechanism to get reliable kernel crash dump with
assistance from firmware. This approach does not use kexec,
- instead firmware assists in booting the kdump kernel
+ instead firmware assists in booting the capture kernel
while preserving memory contents. Firmware-assisted dump
is meant to be a kdump replacement offering robustness and
speed not possible without system firmware assistance.
@@ -580,7 +638,7 @@ config ARCH_SPARSEMEM_ENABLE
config ARCH_SPARSEMEM_DEFAULT
def_bool y
- depends on (SMP && PPC_PSERIES) || PPC_PS3
+ depends on PPC_BOOK3S_64
config SYS_SUPPORTS_HUGETLBFS
bool
@@ -672,6 +730,16 @@ config PPC_256K_PAGES
endchoice
+config THREAD_SHIFT
+ int "Thread shift" if EXPERT
+ range 13 15
+ default "15" if PPC_256K_PAGES
+ default "14" if PPC64
+ default "13"
+ help
+ Used to define the stack size. The default is almost always what you
+ want. Only change this if you know what you are doing.
+
config FORCE_MAX_ZONEORDER
int "Maximum zone order"
range 8 9 if PPC64 && PPC_64K_PAGES
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 31286fa7873c..3e0f0e1fadef 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -72,8 +72,15 @@ GNUTARGET := powerpc
MULTIPLEWORD := -mmultiple
endif
-cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
+ifdef CONFIG_PPC64
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1)
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mcall-aixdesc)
+aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mabi=elfv2
+endif
+
cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
ifneq ($(cc-name),clang)
cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align
endif
@@ -113,7 +120,9 @@ ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2)
else
+CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1)
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc)
+AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1)
endif
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions)
@@ -127,7 +136,7 @@ CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64
endif
ifdef CONFIG_MPROFILE_KERNEL
- ifeq ($(shell $(srctree)/arch/powerpc/scripts/gcc-check-mprofile-kernel.sh $(CC) -I$(srctree)/include -D__KERNEL__),OK)
+ ifeq ($(shell $(srctree)/arch/powerpc/tools/gcc-check-mprofile-kernel.sh $(CC) -I$(srctree)/include -D__KERNEL__),OK)
CC_FLAGS_FTRACE := -pg -mprofile-kernel
KBUILD_CPPFLAGS += -DCC_USING_MPROFILE_KERNEL
else
@@ -265,17 +274,6 @@ PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2)
boot := arch/$(ARCH)/boot
-ifeq ($(CONFIG_RELOCATABLE),y)
-quiet_cmd_relocs_check = CALL $<
- cmd_relocs_check = $(CONFIG_SHELL) $< "$(OBJDUMP)" "$(obj)/vmlinux"
-
-PHONY += relocs_check
-relocs_check: arch/powerpc/relocs_check.sh vmlinux
- $(call cmd,relocs_check)
-
-zImage: relocs_check
-endif
-
$(BOOT_TARGETS1): vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
$(BOOT_TARGETS2): vmlinux
diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink
new file mode 100644
index 000000000000..3c22d64b2de9
--- /dev/null
+++ b/arch/powerpc/Makefile.postlink
@@ -0,0 +1,34 @@
+# ===========================================================================
+# Post-link powerpc pass
+# ===========================================================================
+#
+# 1. Check that vmlinux relocations look sane
+
+PHONY := __archpost
+__archpost:
+
+include include/config/auto.conf
+include scripts/Kbuild.include
+
+quiet_cmd_relocs_check = CHKREL $@
+ cmd_relocs_check = $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@"
+
+# `@true` prevents complaint when there is nothing to be done
+
+vmlinux: FORCE
+ @true
+ifdef CONFIG_RELOCATABLE
+ $(call if_changed,relocs_check)
+endif
+
+%.ko: FORCE
+ @true
+
+clean:
+ @true
+
+PHONY += FORCE clean
+
+FORCE:
+
+.PHONY: $(PHONY)
diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S
index 861e72109df2..f080abfc2f83 100644
--- a/arch/powerpc/boot/zImage.lds.S
+++ b/arch/powerpc/boot/zImage.lds.S
@@ -68,6 +68,7 @@ SECTIONS
}
#ifdef CONFIG_PPC64_BOOT_WRAPPER
+ . = ALIGN(256);
.got :
{
__toc_start = .;
diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
index 528ff0e714e6..c03d0fb16665 100644
--- a/arch/powerpc/configs/85xx-hw.config
+++ b/arch/powerpc/configs/85xx-hw.config
@@ -16,9 +16,8 @@ CONFIG_DAVICOM_PHY=y
CONFIG_DMADEVICES=y
CONFIG_E1000E=y
CONFIG_E1000=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_EDAC_MPC85XX=y
CONFIG_EDAC=y
+CONFIG_EDAC_MPC85XX=y
CONFIG_EEPROM_AT24=y
CONFIG_EEPROM_LEGACY=y
CONFIG_FB_FSL_DIU=y
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index c79283be5680..a917f7afb4f9 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -155,7 +155,6 @@ CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
CONFIG_USB_STORAGE=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_MPC85XX=y
CONFIG_RTC_CLASS=y
# CONFIG_RTC_INTF_PROC is not set
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index dbd961de251e..72900b84d3e0 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -116,7 +116,6 @@ CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
CONFIG_RTC_DRV_CMOS=y
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 2d7fcbe047ac..aa564599e368 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -179,7 +179,6 @@ CONFIG_INFINIBAND_MTHCA=m
CONFIG_INFINIBAND_IPOIB=m
CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_CELL=y
CONFIG_UIO=m
CONFIG_EXT2_FS=y
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 5553c5ce4274..fe43ff47bd2f 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -142,7 +142,6 @@ CONFIG_USB_UHCI_HCD=y
CONFIG_USB_SL811_HCD=y
CONFIG_USB_STORAGE=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_PASEMI=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index ac8b8332ed82..0695ce047d56 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -33,7 +33,7 @@ CONFIG_BLK_DEV_INITRD=y
CONFIG_BPF_SYSCALL=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
+CONFIG_OPROFILE=m
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
CONFIG_MODULES=y
@@ -261,7 +261,7 @@ CONFIG_NILFS2_FS=m
CONFIG_AUTOFS4_FS=m
CONFIG_FUSE_FS=m
CONFIG_OVERLAY_FS=m
-CONFIG_ISO9660_FS=m
+CONFIG_ISO9660_FS=y
CONFIG_UDF_FS=m
CONFIG_MSDOS_FS=y
CONFIG_VFAT_FS=m
@@ -306,7 +306,7 @@ CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPT_CRC32C_VPMSUM=m
+CONFIG_CRYPTO_CRC32C_VPMSUM=m
CONFIG_CRYPTO_MD5_PPC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_SHA256=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 4f1288b04303..5175028c56ce 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -19,7 +19,7 @@ CONFIG_BLK_DEV_INITRD=y
CONFIG_BPF_SYSCALL=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
+CONFIG_OPROFILE=m
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
CONFIG_MODULES=y
@@ -262,7 +262,6 @@ CONFIG_INFINIBAND_IPOIB_CM=y
CONFIG_INFINIBAND_SRP=m
CONFIG_INFINIBAND_ISER=m
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_PASEMI=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
@@ -291,7 +290,7 @@ CONFIG_NILFS2_FS=m
CONFIG_AUTOFS4_FS=m
CONFIG_FUSE_FS=m
CONFIG_OVERLAY_FS=m
-CONFIG_ISO9660_FS=m
+CONFIG_ISO9660_FS=y
CONFIG_UDF_FS=m
CONFIG_MSDOS_FS=y
CONFIG_VFAT_FS=m
@@ -340,7 +339,7 @@ CONFIG_PPC_EARLY_DEBUG=y
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPT_CRC32C_VPMSUM=m
+CONFIG_CRYPTO_CRC32C_VPMSUM=m
CONFIG_CRYPTO_MD5_PPC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_SHA256=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 11a3473f9e2e..6340e6c53c54 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -173,7 +173,6 @@ CONFIG_INFINIBAND_MTHCA=m
CONFIG_INFINIBAND_IPOIB=m
CONFIG_INFINIBAND_ISER=m
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
CONFIG_FS_DAX=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 1d2d69dd6409..18d0d60dadbf 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -988,8 +988,7 @@ CONFIG_LEDS_TRIGGER_BACKLIGHT=m
CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
CONFIG_ACCESSIBILITY=y
CONFIG_A11Y_BRAILLE_CONSOLE=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=m
+CONFIG_EDAC=m
CONFIG_RTC_CLASS=y
# CONFIG_RTC_HCTOSYS is not set
CONFIG_RTC_DRV_DS1307=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 4ff68b752618..1a61aa20dfba 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -34,7 +34,7 @@ CONFIG_BLK_DEV_INITRD=y
CONFIG_BPF_SYSCALL=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
+CONFIG_OPROFILE=m
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
CONFIG_MODULES=y
@@ -259,7 +259,7 @@ CONFIG_NILFS2_FS=m
CONFIG_AUTOFS4_FS=m
CONFIG_FUSE_FS=m
CONFIG_OVERLAY_FS=m
-CONFIG_ISO9660_FS=m
+CONFIG_ISO9660_FS=y
CONFIG_UDF_FS=m
CONFIG_MSDOS_FS=y
CONFIG_VFAT_FS=m
@@ -303,7 +303,7 @@ CONFIG_XMON=y
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPT_CRC32C_VPMSUM=m
+CONFIG_CRYPTO_CRC32C_VPMSUM=m
CONFIG_CRYPTO_MD5_PPC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_SHA256=y
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 87f40454bad3..67eca3af9fc7 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -10,6 +10,8 @@ obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
+obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o
aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
md5-ppc-y := md5-asm.o md5-glue.o
@@ -17,3 +19,4 @@ sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
+crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
new file mode 100644
index 000000000000..0153a9c6f4af
--- /dev/null
+++ b/arch/powerpc/crypto/crc-vpmsum_test.c
@@ -0,0 +1,137 @@
+/*
+ * CRC vpmsum tester
+ * Copyright 2017 Daniel Axtens, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/crc-t10dif.h>
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/switch_to.h>
+
+static unsigned long iterations = 10000;
+
+#define MAX_CRC_LENGTH 65535
+
+
+static int __init crc_test_init(void)
+{
+ u16 crc16 = 0, verify16 = 0;
+ u32 crc32 = 0, verify32 = 0;
+ __le32 verify32le = 0;
+ unsigned char *data;
+ unsigned long i;
+ int ret;
+
+ struct crypto_shash *crct10dif_tfm;
+ struct crypto_shash *crc32c_tfm;
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ data = kmalloc(MAX_CRC_LENGTH, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
+
+ if (IS_ERR(crct10dif_tfm)) {
+ pr_err("Error allocating crc-t10dif\n");
+ goto free_buf;
+ }
+
+ crc32c_tfm = crypto_alloc_shash("crc32c", 0, 0);
+
+ if (IS_ERR(crc32c_tfm)) {
+ pr_err("Error allocating crc32c\n");
+ goto free_16;
+ }
+
+ do {
+ SHASH_DESC_ON_STACK(crct10dif_shash, crct10dif_tfm);
+ SHASH_DESC_ON_STACK(crc32c_shash, crc32c_tfm);
+
+ crct10dif_shash->tfm = crct10dif_tfm;
+ ret = crypto_shash_init(crct10dif_shash);
+
+ if (ret) {
+ pr_err("Error initing crc-t10dif\n");
+ goto free_32;
+ }
+
+
+ crc32c_shash->tfm = crc32c_tfm;
+ ret = crypto_shash_init(crc32c_shash);
+
+ if (ret) {
+ pr_err("Error initing crc32c\n");
+ goto free_32;
+ }
+
+ pr_info("crc-vpmsum_test begins, %lu iterations\n", iterations);
+ for (i=0; i<iterations; i++) {
+ size_t len, offset;
+
+ get_random_bytes(data, MAX_CRC_LENGTH);
+ get_random_bytes(&len, sizeof(len));
+ get_random_bytes(&offset, sizeof(offset));
+
+ len %= MAX_CRC_LENGTH;
+ offset &= 15;
+ if (len <= offset)
+ continue;
+ len -= offset;
+
+ crypto_shash_update(crct10dif_shash, data+offset, len);
+ crypto_shash_final(crct10dif_shash, (u8 *)(&crc16));
+ verify16 = crc_t10dif_generic(verify16, data+offset, len);
+
+
+ if (crc16 != verify16) {
+ pr_err("FAILURE in CRC16: got 0x%04x expected 0x%04x (len %lu)\n",
+ crc16, verify16, len);
+ break;
+ }
+
+ crypto_shash_update(crc32c_shash, data+offset, len);
+ crypto_shash_final(crc32c_shash, (u8 *)(&crc32));
+ verify32 = le32_to_cpu(verify32le);
+ verify32le = ~cpu_to_le32(__crc32c_le(~verify32, data+offset, len));
+ if (crc32 != (u32)verify32le) {
+ pr_err("FAILURE in CRC32: got 0x%08x expected 0x%08x (len %lu)\n",
+ crc32, verify32, len);
+ break;
+ }
+ }
+ pr_info("crc-vpmsum_test done, completed %lu iterations\n", i);
+ } while (0);
+
+free_32:
+ crypto_free_shash(crc32c_tfm);
+
+free_16:
+ crypto_free_shash(crct10dif_tfm);
+
+free_buf:
+ kfree(data);
+
+ return 0;
+}
+
+static void __exit crc_test_exit(void) {}
+
+module_init(crc_test_init);
+module_exit(crc_test_exit);
+module_param(iterations, long, 0400);
+
+MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
+MODULE_DESCRIPTION("Vector polynomial multiply-sum CRC tester");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/crypto/crc32-vpmsum_core.S
new file mode 100644
index 000000000000..aadb59c96a27
--- /dev/null
+++ b/arch/powerpc/crypto/crc32-vpmsum_core.S
@@ -0,0 +1,755 @@
+/*
+ * Core of the accelerated CRC algorithm.
+ * In your file, define the constants and CRC_FUNCTION_NAME
+ * Then include this file.
+ *
+ * Calculate the checksum of data that is 16 byte aligned and a multiple of
+ * 16 bytes.
+ *
+ * The first step is to reduce it to 1024 bits. We do this in 8 parallel
+ * chunks in order to mask the latency of the vpmsum instructions. If we
+ * have more than 32 kB of data to checksum we repeat this step multiple
+ * times, passing in the previous 1024 bits.
+ *
+ * The next step is to reduce the 1024 bits to 64 bits. This step adds
+ * 32 bits of 0s to the end - this matches what a CRC does. We just
+ * calculate constants that land the data in this 32 bits.
+ *
+ * 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
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+*/
+
+#include <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+
+#define MAX_SIZE 32768
+
+ .text
+
+#if defined(__BIG_ENDIAN__) && defined(REFLECT)
+#define BYTESWAP_DATA
+#elif defined(__LITTLE_ENDIAN__) && !defined(REFLECT)
+#define BYTESWAP_DATA
+#else
+#undef BYTESWAP_DATA
+#endif
+
+#define off16 r25
+#define off32 r26
+#define off48 r27
+#define off64 r28
+#define off80 r29
+#define off96 r30
+#define off112 r31
+
+#define const1 v24
+#define const2 v25
+
+#define byteswap v26
+#define mask_32bit v27
+#define mask_64bit v28
+#define zeroes v29
+
+#ifdef BYTESWAP_DATA
+#define VPERM(A, B, C, D) vperm A, B, C, D
+#else
+#define VPERM(A, B, C, D)
+#endif
+
+/* unsigned int CRC_FUNCTION_NAME(unsigned int crc, void *p, unsigned long len) */
+FUNC_START(CRC_FUNCTION_NAME)
+ std r31,-8(r1)
+ std r30,-16(r1)
+ std r29,-24(r1)
+ std r28,-32(r1)
+ std r27,-40(r1)
+ std r26,-48(r1)
+ std r25,-56(r1)
+
+ li off16,16
+ li off32,32
+ li off48,48
+ li off64,64
+ li off80,80
+ li off96,96
+ li off112,112
+ li r0,0
+
+ /* Enough room for saving 10 non volatile VMX registers */
+ subi r6,r1,56+10*16
+ subi r7,r1,56+2*16
+
+ stvx v20,0,r6
+ stvx v21,off16,r6
+ stvx v22,off32,r6
+ stvx v23,off48,r6
+ stvx v24,off64,r6
+ stvx v25,off80,r6
+ stvx v26,off96,r6
+ stvx v27,off112,r6
+ stvx v28,0,r7
+ stvx v29,off16,r7
+
+ mr r10,r3
+
+ vxor zeroes,zeroes,zeroes
+ vspltisw v0,-1
+
+ vsldoi mask_32bit,zeroes,v0,4
+ vsldoi mask_64bit,zeroes,v0,8
+
+ /* Get the initial value into v8 */
+ vxor v8,v8,v8
+ MTVRD(v8, R3)
+#ifdef REFLECT
+ vsldoi v8,zeroes,v8,8 /* shift into bottom 32 bits */
+#else
+ vsldoi v8,v8,zeroes,4 /* shift into top 32 bits */
+#endif
+
+#ifdef BYTESWAP_DATA
+ addis r3,r2,.byteswap_constant@toc@ha
+ addi r3,r3,.byteswap_constant@toc@l
+
+ lvx byteswap,0,r3
+ addi r3,r3,16
+#endif
+
+ cmpdi r5,256
+ blt .Lshort
+
+ rldicr r6,r5,0,56
+
+ /* Checksum in blocks of MAX_SIZE */
+1: lis r7,MAX_SIZE@h
+ ori r7,r7,MAX_SIZE@l
+ mr r9,r7
+ cmpd r6,r7
+ bgt 2f
+ mr r7,r6
+2: subf r6,r7,r6
+
+ /* our main loop does 128 bytes at a time */
+ srdi r7,r7,7
+
+ /*
+ * Work out the offset into the constants table to start at. Each
+ * constant is 16 bytes, and it is used against 128 bytes of input
+ * data - 128 / 16 = 8
+ */
+ sldi r8,r7,4
+ srdi r9,r9,3
+ subf r8,r8,r9
+
+ /* We reduce our final 128 bytes in a separate step */
+ addi r7,r7,-1
+ mtctr r7
+
+ addis r3,r2,.constants@toc@ha
+ addi r3,r3,.constants@toc@l
+
+ /* Find the start of our constants */
+ add r3,r3,r8
+
+ /* zero v0-v7 which will contain our checksums */
+ vxor v0,v0,v0
+ vxor v1,v1,v1
+ vxor v2,v2,v2
+ vxor v3,v3,v3
+ vxor v4,v4,v4
+ vxor v5,v5,v5
+ vxor v6,v6,v6
+ vxor v7,v7,v7
+
+ lvx const1,0,r3
+
+ /*
+ * If we are looping back to consume more data we use the values
+ * already in v16-v23.
+ */
+ cmpdi r0,1
+ beq 2f
+
+ /* First warm up pass */
+ lvx v16,0,r4
+ lvx v17,off16,r4
+ VPERM(v16,v16,v16,byteswap)
+ VPERM(v17,v17,v17,byteswap)
+ lvx v18,off32,r4
+ lvx v19,off48,r4
+ VPERM(v18,v18,v18,byteswap)
+ VPERM(v19,v19,v19,byteswap)
+ lvx v20,off64,r4
+ lvx v21,off80,r4
+ VPERM(v20,v20,v20,byteswap)
+ VPERM(v21,v21,v21,byteswap)
+ lvx v22,off96,r4
+ lvx v23,off112,r4
+ VPERM(v22,v22,v22,byteswap)
+ VPERM(v23,v23,v23,byteswap)
+ addi r4,r4,8*16
+
+ /* xor in initial value */
+ vxor v16,v16,v8
+
+2: bdz .Lfirst_warm_up_done
+
+ addi r3,r3,16
+ lvx const2,0,r3
+
+ /* Second warm up pass */
+ VPMSUMD(v8,v16,const1)
+ lvx v16,0,r4
+ VPERM(v16,v16,v16,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v9,v17,const1)
+ lvx v17,off16,r4
+ VPERM(v17,v17,v17,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v10,v18,const1)
+ lvx v18,off32,r4
+ VPERM(v18,v18,v18,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v11,v19,const1)
+ lvx v19,off48,r4
+ VPERM(v19,v19,v19,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v12,v20,const1)
+ lvx v20,off64,r4
+ VPERM(v20,v20,v20,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v13,v21,const1)
+ lvx v21,off80,r4
+ VPERM(v21,v21,v21,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v14,v22,const1)
+ lvx v22,off96,r4
+ VPERM(v22,v22,v22,byteswap)
+ ori r2,r2,0
+
+ VPMSUMD(v15,v23,const1)
+ lvx v23,off112,r4
+ VPERM(v23,v23,v23,byteswap)
+
+ addi r4,r4,8*16
+
+ bdz .Lfirst_cool_down
+
+ /*
+ * main loop. We modulo schedule it such that it takes three iterations
+ * to complete - first iteration load, second iteration vpmsum, third
+ * iteration xor.
+ */
+ .balign 16
+4: lvx const1,0,r3
+ addi r3,r3,16
+ ori r2,r2,0
+
+ vxor v0,v0,v8
+ VPMSUMD(v8,v16,const2)
+ lvx v16,0,r4
+ VPERM(v16,v16,v16,byteswap)
+ ori r2,r2,0
+
+ vxor v1,v1,v9
+ VPMSUMD(v9,v17,const2)
+ lvx v17,off16,r4
+ VPERM(v17,v17,v17,byteswap)
+ ori r2,r2,0
+
+ vxor v2,v2,v10
+ VPMSUMD(v10,v18,const2)
+ lvx v18,off32,r4
+ VPERM(v18,v18,v18,byteswap)
+ ori r2,r2,0
+
+ vxor v3,v3,v11
+ VPMSUMD(v11,v19,const2)
+ lvx v19,off48,r4
+ VPERM(v19,v19,v19,byteswap)
+ lvx const2,0,r3
+ ori r2,r2,0
+
+ vxor v4,v4,v12
+ VPMSUMD(v12,v20,const1)
+ lvx v20,off64,r4
+ VPERM(v20,v20,v20,byteswap)
+ ori r2,r2,0
+
+ vxor v5,v5,v13
+ VPMSUMD(v13,v21,const1)
+ lvx v21,off80,r4
+ VPERM(v21,v21,v21,byteswap)
+ ori r2,r2,0
+
+ vxor v6,v6,v14
+ VPMSUMD(v14,v22,const1)
+ lvx v22,off96,r4
+ VPERM(v22,v22,v22,byteswap)
+ ori r2,r2,0
+
+ vxor v7,v7,v15
+ VPMSUMD(v15,v23,const1)
+ lvx v23,off112,r4
+ VPERM(v23,v23,v23,byteswap)
+
+ addi r4,r4,8*16
+
+ bdnz 4b
+
+.Lfirst_cool_down:
+ /* First cool down pass */
+ lvx const1,0,r3
+ addi r3,r3,16
+
+ vxor v0,v0,v8
+ VPMSUMD(v8,v16,const1)
+ ori r2,r2,0
+
+ vxor v1,v1,v9
+ VPMSUMD(v9,v17,const1)
+ ori r2,r2,0
+
+ vxor v2,v2,v10
+ VPMSUMD(v10,v18,const1)
+ ori r2,r2,0
+
+ vxor v3,v3,v11
+ VPMSUMD(v11,v19,const1)
+ ori r2,r2,0
+
+ vxor v4,v4,v12
+ VPMSUMD(v12,v20,const1)
+ ori r2,r2,0
+
+ vxor v5,v5,v13
+ VPMSUMD(v13,v21,const1)
+ ori r2,r2,0
+
+ vxor v6,v6,v14
+ VPMSUMD(v14,v22,const1)
+ ori r2,r2,0
+
+ vxor v7,v7,v15
+ VPMSUMD(v15,v23,const1)
+ ori r2,r2,0
+
+.Lsecond_cool_down:
+ /* Second cool down pass */
+ vxor v0,v0,v8
+ vxor v1,v1,v9
+ vxor v2,v2,v10
+ vxor v3,v3,v11
+ vxor v4,v4,v12
+ vxor v5,v5,v13
+ vxor v6,v6,v14
+ vxor v7,v7,v15
+
+#ifdef REFLECT
+ /*
+ * vpmsumd produces a 96 bit result in the least significant bits
+ * of the register. Since we are bit reflected we have to shift it
+ * left 32 bits so it occupies the least significant bits in the
+ * bit reflected domain.
+ */
+ vsldoi v0,v0,zeroes,4
+ vsldoi v1,v1,zeroes,4
+ vsldoi v2,v2,zeroes,4
+ vsldoi v3,v3,zeroes,4
+ vsldoi v4,v4,zeroes,4
+ vsldoi v5,v5,zeroes,4
+ vsldoi v6,v6,zeroes,4
+ vsldoi v7,v7,zeroes,4
+#endif
+
+ /* xor with last 1024 bits */
+ lvx v8,0,r4
+ lvx v9,off16,r4
+ VPERM(v8,v8,v8,byteswap)
+ VPERM(v9,v9,v9,byteswap)
+ lvx v10,off32,r4
+ lvx v11,off48,r4
+ VPERM(v10,v10,v10,byteswap)
+ VPERM(v11,v11,v11,byteswap)
+ lvx v12,off64,r4
+ lvx v13,off80,r4
+ VPERM(v12,v12,v12,byteswap)
+ VPERM(v13,v13,v13,byteswap)
+ lvx v14,off96,r4
+ lvx v15,off112,r4
+ VPERM(v14,v14,v14,byteswap)
+ VPERM(v15,v15,v15,byteswap)
+
+ addi r4,r4,8*16
+
+ vxor v16,v0,v8
+ vxor v17,v1,v9
+ vxor v18,v2,v10
+ vxor v19,v3,v11
+ vxor v20,v4,v12
+ vxor v21,v5,v13
+ vxor v22,v6,v14
+ vxor v23,v7,v15
+
+ li r0,1
+ cmpdi r6,0
+ addi r6,r6,128
+ bne 1b
+
+ /* Work out how many bytes we have left */
+ andi. r5,r5,127
+
+ /* Calculate where in the constant table we need to start */
+ subfic r6,r5,128
+ add r3,r3,r6
+
+ /* How many 16 byte chunks are in the tail */
+ srdi r7,r5,4
+ mtctr r7
+
+ /*
+ * Reduce the previously calculated 1024 bits to 64 bits, shifting
+ * 32 bits to include the trailing 32 bits of zeros
+ */
+ lvx v0,0,r3
+ lvx v1,off16,r3
+ lvx v2,off32,r3
+ lvx v3,off48,r3
+ lvx v4,off64,r3
+ lvx v5,off80,r3
+ lvx v6,off96,r3
+ lvx v7,off112,r3
+ addi r3,r3,8*16
+
+ VPMSUMW(v0,v16,v0)
+ VPMSUMW(v1,v17,v1)
+ VPMSUMW(v2,v18,v2)
+ VPMSUMW(v3,v19,v3)
+ VPMSUMW(v4,v20,v4)
+ VPMSUMW(v5,v21,v5)
+ VPMSUMW(v6,v22,v6)
+ VPMSUMW(v7,v23,v7)
+
+ /* Now reduce the tail (0 - 112 bytes) */
+ cmpdi r7,0
+ beq 1f
+
+ lvx v16,0,r4
+ lvx v17,0,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off16,r4
+ lvx v17,off16,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off32,r4
+ lvx v17,off32,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off48,r4
+ lvx v17,off48,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off64,r4
+ lvx v17,off64,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off80,r4
+ lvx v17,off80,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+ bdz 1f
+
+ lvx v16,off96,r4
+ lvx v17,off96,r3
+ VPERM(v16,v16,v16,byteswap)
+ VPMSUMW(v16,v16,v17)
+ vxor v0,v0,v16
+
+ /* Now xor all the parallel chunks together */
+1: vxor v0,v0,v1
+ vxor v2,v2,v3
+ vxor v4,v4,v5
+ vxor v6,v6,v7
+
+ vxor v0,v0,v2
+ vxor v4,v4,v6
+
+ vxor v0,v0,v4
+
+.Lbarrett_reduction:
+ /* Barrett constants */
+ addis r3,r2,.barrett_constants@toc@ha
+ addi r3,r3,.barrett_constants@toc@l
+
+ lvx const1,0,r3
+ lvx const2,off16,r3
+
+ vsldoi v1,v0,v0,8
+ vxor v0,v0,v1 /* xor two 64 bit results together */
+
+#ifdef REFLECT
+ /* shift left one bit */
+ vspltisb v1,1
+ vsl v0,v0,v1
+#endif
+
+ vand v0,v0,mask_64bit
+#ifndef REFLECT
+ /*
+ * Now for the Barrett reduction algorithm. The idea is to calculate q,
+ * the multiple of our polynomial that we need to subtract. By
+ * doing the computation 2x bits higher (ie 64 bits) and shifting the
+ * result back down 2x bits, we round down to the nearest multiple.
+ */
+ VPMSUMD(v1,v0,const1) /* ma */
+ vsldoi v1,zeroes,v1,8 /* q = floor(ma/(2^64)) */
+ VPMSUMD(v1,v1,const2) /* qn */
+ vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */
+
+ /*
+ * Get the result into r3. We need to shift it left 8 bytes:
+ * V0 [ 0 1 2 X ]
+ * V0 [ 0 X 2 3 ]
+ */
+ vsldoi v0,v0,zeroes,8 /* shift result into top 64 bits */
+#else
+ /*
+ * The reflected version of Barrett reduction. Instead of bit
+ * reflecting our data (which is expensive to do), we bit reflect our
+ * constants and our algorithm, which means the intermediate data in
+ * our vector registers goes from 0-63 instead of 63-0. We can reflect
+ * the algorithm because we don't carry in mod 2 arithmetic.
+ */
+ vand v1,v0,mask_32bit /* bottom 32 bits of a */
+ VPMSUMD(v1,v1,const1) /* ma */
+ vand v1,v1,mask_32bit /* bottom 32bits of ma */
+ VPMSUMD(v1,v1,const2) /* qn */
+ vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */
+
+ /*
+ * Since we are bit reflected, the result (ie the low 32 bits) is in
+ * the high 32 bits. We just need to shift it left 4 bytes
+ * V0 [ 0 1 X 3 ]
+ * V0 [ 0 X 2 3 ]
+ */
+ vsldoi v0,v0,zeroes,4 /* shift result into top 64 bits of */
+#endif
+
+ /* Get it into r3 */
+ MFVRD(R3, v0)
+
+.Lout:
+ subi r6,r1,56+10*16
+ subi r7,r1,56+2*16
+
+ lvx v20,0,r6
+ lvx v21,off16,r6
+ lvx v22,off32,r6
+ lvx v23,off48,r6
+ lvx v24,off64,r6
+ lvx v25,off80,r6
+ lvx v26,off96,r6
+ lvx v27,off112,r6
+ lvx v28,0,r7
+ lvx v29,off16,r7
+
+ ld r31,-8(r1)
+ ld r30,-16(r1)
+ ld r29,-24(r1)
+ ld r28,-32(r1)
+ ld r27,-40(r1)
+ ld r26,-48(r1)
+ ld r25,-56(r1)
+
+ blr
+
+.Lfirst_warm_up_done:
+ lvx const1,0,r3
+ addi r3,r3,16
+
+ VPMSUMD(v8,v16,const1)
+ VPMSUMD(v9,v17,const1)
+ VPMSUMD(v10,v18,const1)
+ VPMSUMD(v11,v19,const1)
+ VPMSUMD(v12,v20,const1)
+ VPMSUMD(v13,v21,const1)
+ VPMSUMD(v14,v22,const1)
+ VPMSUMD(v15,v23,const1)
+
+ b .Lsecond_cool_down
+
+.Lshort:
+ cmpdi r5,0
+ beq .Lzero
+
+ addis r3,r2,.short_constants@toc@ha
+ addi r3,r3,.short_constants@toc@l
+
+ /* Calculate where in the constant table we need to start */
+ subfic r6,r5,256
+ add r3,r3,r6
+
+ /* How many 16 byte chunks? */
+ srdi r7,r5,4
+ mtctr r7
+
+ vxor v19,v19,v19
+ vxor v20,v20,v20
+
+ lvx v0,0,r4
+ lvx v16,0,r3
+ VPERM(v0,v0,v16,byteswap)
+ vxor v0,v0,v8 /* xor in initial value */
+ VPMSUMW(v0,v0,v16)
+ bdz .Lv0
+
+ lvx v1,off16,r4
+ lvx v17,off16,r3
+ VPERM(v1,v1,v17,byteswap)
+ VPMSUMW(v1,v1,v17)
+ bdz .Lv1
+
+ lvx v2,off32,r4
+ lvx v16,off32,r3
+ VPERM(v2,v2,v16,byteswap)
+ VPMSUMW(v2,v2,v16)
+ bdz .Lv2
+
+ lvx v3,off48,r4
+ lvx v17,off48,r3
+ VPERM(v3,v3,v17,byteswap)
+ VPMSUMW(v3,v3,v17)
+ bdz .Lv3
+
+ lvx v4,off64,r4
+ lvx v16,off64,r3
+ VPERM(v4,v4,v16,byteswap)
+ VPMSUMW(v4,v4,v16)
+ bdz .Lv4
+
+ lvx v5,off80,r4
+ lvx v17,off80,r3
+ VPERM(v5,v5,v17,byteswap)
+ VPMSUMW(v5,v5,v17)
+ bdz .Lv5
+
+ lvx v6,off96,r4
+ lvx v16,off96,r3
+ VPERM(v6,v6,v16,byteswap)
+ VPMSUMW(v6,v6,v16)
+ bdz .Lv6
+
+ lvx v7,off112,r4
+ lvx v17,off112,r3
+ VPERM(v7,v7,v17,byteswap)
+ VPMSUMW(v7,v7,v17)
+ bdz .Lv7
+
+ addi r3,r3,128
+ addi r4,r4,128
+
+ lvx v8,0,r4
+ lvx v16,0,r3
+ VPERM(v8,v8,v16,byteswap)
+ VPMSUMW(v8,v8,v16)
+ bdz .Lv8
+
+ lvx v9,off16,r4
+ lvx v17,off16,r3
+ VPERM(v9,v9,v17,byteswap)
+ VPMSUMW(v9,v9,v17)
+ bdz .Lv9
+
+ lvx v10,off32,r4
+ lvx v16,off32,r3
+ VPERM(v10,v10,v16,byteswap)
+ VPMSUMW(v10,v10,v16)
+ bdz .Lv10
+
+ lvx v11,off48,r4
+ lvx v17,off48,r3
+ VPERM(v11,v11,v17,byteswap)
+ VPMSUMW(v11,v11,v17)
+ bdz .Lv11
+
+ lvx v12,off64,r4
+ lvx v16,off64,r3
+ VPERM(v12,v12,v16,byteswap)
+ VPMSUMW(v12,v12,v16)
+ bdz .Lv12
+
+ lvx v13,off80,r4
+ lvx v17,off80,r3
+ VPERM(v13,v13,v17,byteswap)
+ VPMSUMW(v13,v13,v17)
+ bdz .Lv13
+
+ lvx v14,off96,r4
+ lvx v16,off96,r3
+ VPERM(v14,v14,v16,byteswap)
+ VPMSUMW(v14,v14,v16)
+ bdz .Lv14
+
+ lvx v15,off112,r4
+ lvx v17,off112,r3
+ VPERM(v15,v15,v17,byteswap)
+ VPMSUMW(v15,v15,v17)
+
+.Lv15: vxor v19,v19,v15
+.Lv14: vxor v20,v20,v14
+.Lv13: vxor v19,v19,v13
+.Lv12: vxor v20,v20,v12
+.Lv11: vxor v19,v19,v11
+.Lv10: vxor v20,v20,v10
+.Lv9: vxor v19,v19,v9
+.Lv8: vxor v20,v20,v8
+.Lv7: vxor v19,v19,v7
+.Lv6: vxor v20,v20,v6
+.Lv5: vxor v19,v19,v5
+.Lv4: vxor v20,v20,v4
+.Lv3: vxor v19,v19,v3
+.Lv2: vxor v20,v20,v2
+.Lv1: vxor v19,v19,v1
+.Lv0: vxor v20,v20,v0
+
+ vxor v0,v19,v20
+
+ b .Lbarrett_reduction
+
+.Lzero:
+ mr r3,r10
+ b .Lout
+
+FUNC_END(CRC_FUNCTION_NAME)
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
index dc640b212299..d2bea48051a0 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_asm.S
+++ b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
@@ -1,20 +1,5 @@
/*
- * Calculate the checksum of data that is 16 byte aligned and a multiple of
- * 16 bytes.
- *
- * The first step is to reduce it to 1024 bits. We do this in 8 parallel
- * chunks in order to mask the latency of the vpmsum instructions. If we
- * have more than 32 kB of data to checksum we repeat this step multiple
- * times, passing in the previous 1024 bits.
- *
- * The next step is to reduce the 1024 bits to 64 bits. This step adds
- * 32 bits of 0s to the end - this matches what a CRC does. We just
- * calculate constants that land the data in this 32 bits.
- *
- * 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
+ * Calculate a crc32c with vpmsum acceleration
*
* Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
*
@@ -23,9 +8,6 @@
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
-#include <asm/ppc_asm.h>
-#include <asm/ppc-opcode.h>
-
.section .rodata
.balign 16
@@ -33,7 +15,6 @@
/* byte reverse permute constant */
.octa 0x0F0E0D0C0B0A09080706050403020100
-#define MAX_SIZE 32768
.constants:
/* Reduce 262144 kbits to 1024 bits */
@@ -860,694 +841,6 @@
/* 33 bit reflected Barrett constant n */
.octa 0x00000000000000000000000105ec76f1
- .text
-
-#if defined(__BIG_ENDIAN__)
-#define BYTESWAP_DATA
-#else
-#undef BYTESWAP_DATA
-#endif
-
-#define off16 r25
-#define off32 r26
-#define off48 r27
-#define off64 r28
-#define off80 r29
-#define off96 r30
-#define off112 r31
-
-#define const1 v24
-#define const2 v25
-
-#define byteswap v26
-#define mask_32bit v27
-#define mask_64bit v28
-#define zeroes v29
-
-#ifdef BYTESWAP_DATA
-#define VPERM(A, B, C, D) vperm A, B, C, D
-#else
-#define VPERM(A, B, C, D)
-#endif
-
-/* unsigned int __crc32c_vpmsum(unsigned int crc, void *p, unsigned long len) */
-FUNC_START(__crc32c_vpmsum)
- std r31,-8(r1)
- std r30,-16(r1)
- std r29,-24(r1)
- std r28,-32(r1)
- std r27,-40(r1)
- std r26,-48(r1)
- std r25,-56(r1)
-
- li off16,16
- li off32,32
- li off48,48
- li off64,64
- li off80,80
- li off96,96
- li off112,112
- li r0,0
-
- /* Enough room for saving 10 non volatile VMX registers */
- subi r6,r1,56+10*16
- subi r7,r1,56+2*16
-
- stvx v20,0,r6
- stvx v21,off16,r6
- stvx v22,off32,r6
- stvx v23,off48,r6
- stvx v24,off64,r6
- stvx v25,off80,r6
- stvx v26,off96,r6
- stvx v27,off112,r6
- stvx v28,0,r7
- stvx v29,off16,r7
-
- mr r10,r3
-
- vxor zeroes,zeroes,zeroes
- vspltisw v0,-1
-
- vsldoi mask_32bit,zeroes,v0,4
- vsldoi mask_64bit,zeroes,v0,8
-
- /* Get the initial value into v8 */
- vxor v8,v8,v8
- MTVRD(v8, R3)
- vsldoi v8,zeroes,v8,8 /* shift into bottom 32 bits */
-
-#ifdef BYTESWAP_DATA
- addis r3,r2,.byteswap_constant@toc@ha
- addi r3,r3,.byteswap_constant@toc@l
-
- lvx byteswap,0,r3
- addi r3,r3,16
-#endif
-
- cmpdi r5,256
- blt .Lshort
-
- rldicr r6,r5,0,56
-
- /* Checksum in blocks of MAX_SIZE */
-1: lis r7,MAX_SIZE@h
- ori r7,r7,MAX_SIZE@l
- mr r9,r7
- cmpd r6,r7
- bgt 2f
- mr r7,r6
-2: subf r6,r7,r6
-
- /* our main loop does 128 bytes at a time */
- srdi r7,r7,7
-
- /*
- * Work out the offset into the constants table to start at. Each
- * constant is 16 bytes, and it is used against 128 bytes of input
- * data - 128 / 16 = 8
- */
- sldi r8,r7,4
- srdi r9,r9,3
- subf r8,r8,r9
-
- /* We reduce our final 128 bytes in a separate step */
- addi r7,r7,-1
- mtctr r7
-
- addis r3,r2,.constants@toc@ha
- addi r3,r3,.constants@toc@l
-
- /* Find the start of our constants */
- add r3,r3,r8
-
- /* zero v0-v7 which will contain our checksums */
- vxor v0,v0,v0
- vxor v1,v1,v1
- vxor v2,v2,v2
- vxor v3,v3,v3
- vxor v4,v4,v4
- vxor v5,v5,v5
- vxor v6,v6,v6
- vxor v7,v7,v7
-
- lvx const1,0,r3
-
- /*
- * If we are looping back to consume more data we use the values
- * already in v16-v23.
- */
- cmpdi r0,1
- beq 2f
-
- /* First warm up pass */
- lvx v16,0,r4
- lvx v17,off16,r4
- VPERM(v16,v16,v16,byteswap)
- VPERM(v17,v17,v17,byteswap)
- lvx v18,off32,r4
- lvx v19,off48,r4
- VPERM(v18,v18,v18,byteswap)
- VPERM(v19,v19,v19,byteswap)
- lvx v20,off64,r4
- lvx v21,off80,r4
- VPERM(v20,v20,v20,byteswap)
- VPERM(v21,v21,v21,byteswap)
- lvx v22,off96,r4
- lvx v23,off112,r4
- VPERM(v22,v22,v22,byteswap)
- VPERM(v23,v23,v23,byteswap)
- addi r4,r4,8*16
-
- /* xor in initial value */
- vxor v16,v16,v8
-
-2: bdz .Lfirst_warm_up_done
-
- addi r3,r3,16
- lvx const2,0,r3
-
- /* Second warm up pass */
- VPMSUMD(v8,v16,const1)
- lvx v16,0,r4
- VPERM(v16,v16,v16,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v9,v17,const1)
- lvx v17,off16,r4
- VPERM(v17,v17,v17,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v10,v18,const1)
- lvx v18,off32,r4
- VPERM(v18,v18,v18,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v11,v19,const1)
- lvx v19,off48,r4
- VPERM(v19,v19,v19,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v12,v20,const1)
- lvx v20,off64,r4
- VPERM(v20,v20,v20,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v13,v21,const1)
- lvx v21,off80,r4
- VPERM(v21,v21,v21,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v14,v22,const1)
- lvx v22,off96,r4
- VPERM(v22,v22,v22,byteswap)
- ori r2,r2,0
-
- VPMSUMD(v15,v23,const1)
- lvx v23,off112,r4
- VPERM(v23,v23,v23,byteswap)
-
- addi r4,r4,8*16
-
- bdz .Lfirst_cool_down
-
- /*
- * main loop. We modulo schedule it such that it takes three iterations
- * to complete - first iteration load, second iteration vpmsum, third
- * iteration xor.
- */
- .balign 16
-4: lvx const1,0,r3
- addi r3,r3,16
- ori r2,r2,0
-
- vxor v0,v0,v8
- VPMSUMD(v8,v16,const2)
- lvx v16,0,r4
- VPERM(v16,v16,v16,byteswap)
- ori r2,r2,0
-
- vxor v1,v1,v9
- VPMSUMD(v9,v17,const2)
- lvx v17,off16,r4
- VPERM(v17,v17,v17,byteswap)
- ori r2,r2,0
-
- vxor v2,v2,v10
- VPMSUMD(v10,v18,const2)
- lvx v18,off32,r4
- VPERM(v18,v18,v18,byteswap)
- ori r2,r2,0
-
- vxor v3,v3,v11
- VPMSUMD(v11,v19,const2)
- lvx v19,off48,r4
- VPERM(v19,v19,v19,byteswap)
- lvx const2,0,r3
- ori r2,r2,0
-
- vxor v4,v4,v12
- VPMSUMD(v12,v20,const1)
- lvx v20,off64,r4
- VPERM(v20,v20,v20,byteswap)
- ori r2,r2,0
-
- vxor v5,v5,v13
- VPMSUMD(v13,v21,const1)
- lvx v21,off80,r4
- VPERM(v21,v21,v21,byteswap)
- ori r2,r2,0
-
- vxor v6,v6,v14
- VPMSUMD(v14,v22,const1)
- lvx v22,off96,r4
- VPERM(v22,v22,v22,byteswap)
- ori r2,r2,0
-
- vxor v7,v7,v15
- VPMSUMD(v15,v23,const1)
- lvx v23,off112,r4
- VPERM(v23,v23,v23,byteswap)
-
- addi r4,r4,8*16
-
- bdnz 4b
-
-.Lfirst_cool_down:
- /* First cool down pass */
- lvx const1,0,r3
- addi r3,r3,16
-
- vxor v0,v0,v8
- VPMSUMD(v8,v16,const1)
- ori r2,r2,0
-
- vxor v1,v1,v9
- VPMSUMD(v9,v17,const1)
- ori r2,r2,0
-
- vxor v2,v2,v10
- VPMSUMD(v10,v18,const1)
- ori r2,r2,0
-
- vxor v3,v3,v11
- VPMSUMD(v11,v19,const1)
- ori r2,r2,0
-
- vxor v4,v4,v12
- VPMSUMD(v12,v20,const1)
- ori r2,r2,0
-
- vxor v5,v5,v13
- VPMSUMD(v13,v21,const1)
- ori r2,r2,0
-
- vxor v6,v6,v14
- VPMSUMD(v14,v22,const1)
- ori r2,r2,0
-
- vxor v7,v7,v15
- VPMSUMD(v15,v23,const1)
- ori r2,r2,0
-
-.Lsecond_cool_down:
- /* Second cool down pass */
- vxor v0,v0,v8
- vxor v1,v1,v9
- vxor v2,v2,v10
- vxor v3,v3,v11
- vxor v4,v4,v12
- vxor v5,v5,v13
- vxor v6,v6,v14
- vxor v7,v7,v15
-
- /*
- * vpmsumd produces a 96 bit result in the least significant bits
- * of the register. Since we are bit reflected we have to shift it
- * left 32 bits so it occupies the least significant bits in the
- * bit reflected domain.
- */
- vsldoi v0,v0,zeroes,4
- vsldoi v1,v1,zeroes,4
- vsldoi v2,v2,zeroes,4
- vsldoi v3,v3,zeroes,4
- vsldoi v4,v4,zeroes,4
- vsldoi v5,v5,zeroes,4
- vsldoi v6,v6,zeroes,4
- vsldoi v7,v7,zeroes,4
-
- /* xor with last 1024 bits */
- lvx v8,0,r4
- lvx v9,off16,r4
- VPERM(v8,v8,v8,byteswap)
- VPERM(v9,v9,v9,byteswap)
- lvx v10,off32,r4
- lvx v11,off48,r4
- VPERM(v10,v10,v10,byteswap)
- VPERM(v11,v11,v11,byteswap)
- lvx v12,off64,r4
- lvx v13,off80,r4
- VPERM(v12,v12,v12,byteswap)
- VPERM(v13,v13,v13,byteswap)
- lvx v14,off96,r4
- lvx v15,off112,r4
- VPERM(v14,v14,v14,byteswap)
- VPERM(v15,v15,v15,byteswap)
-
- addi r4,r4,8*16
-
- vxor v16,v0,v8
- vxor v17,v1,v9
- vxor v18,v2,v10
- vxor v19,v3,v11
- vxor v20,v4,v12
- vxor v21,v5,v13
- vxor v22,v6,v14
- vxor v23,v7,v15
-
- li r0,1
- cmpdi r6,0
- addi r6,r6,128
- bne 1b
-
- /* Work out how many bytes we have left */
- andi. r5,r5,127
-
- /* Calculate where in the constant table we need to start */
- subfic r6,r5,128
- add r3,r3,r6
-
- /* How many 16 byte chunks are in the tail */
- srdi r7,r5,4
- mtctr r7
-
- /*
- * Reduce the previously calculated 1024 bits to 64 bits, shifting
- * 32 bits to include the trailing 32 bits of zeros
- */
- lvx v0,0,r3
- lvx v1,off16,r3
- lvx v2,off32,r3
- lvx v3,off48,r3
- lvx v4,off64,r3
- lvx v5,off80,r3
- lvx v6,off96,r3
- lvx v7,off112,r3
- addi r3,r3,8*16
-
- VPMSUMW(v0,v16,v0)
- VPMSUMW(v1,v17,v1)
- VPMSUMW(v2,v18,v2)
- VPMSUMW(v3,v19,v3)
- VPMSUMW(v4,v20,v4)
- VPMSUMW(v5,v21,v5)
- VPMSUMW(v6,v22,v6)
- VPMSUMW(v7,v23,v7)
-
- /* Now reduce the tail (0 - 112 bytes) */
- cmpdi r7,0
- beq 1f
-
- lvx v16,0,r4
- lvx v17,0,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off16,r4
- lvx v17,off16,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off32,r4
- lvx v17,off32,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off48,r4
- lvx v17,off48,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off64,r4
- lvx v17,off64,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off80,r4
- lvx v17,off80,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
- bdz 1f
-
- lvx v16,off96,r4
- lvx v17,off96,r3
- VPERM(v16,v16,v16,byteswap)
- VPMSUMW(v16,v16,v17)
- vxor v0,v0,v16
-
- /* Now xor all the parallel chunks together */
-1: vxor v0,v0,v1
- vxor v2,v2,v3
- vxor v4,v4,v5
- vxor v6,v6,v7
-
- vxor v0,v0,v2
- vxor v4,v4,v6
-
- vxor v0,v0,v4
-
-.Lbarrett_reduction:
- /* Barrett constants */
- addis r3,r2,.barrett_constants@toc@ha
- addi r3,r3,.barrett_constants@toc@l
-
- lvx const1,0,r3
- lvx const2,off16,r3
-
- vsldoi v1,v0,v0,8
- vxor v0,v0,v1 /* xor two 64 bit results together */
-
- /* shift left one bit */
- vspltisb v1,1
- vsl v0,v0,v1
-
- vand v0,v0,mask_64bit
-
- /*
- * The reflected version of Barrett reduction. Instead of bit
- * reflecting our data (which is expensive to do), we bit reflect our
- * constants and our algorithm, which means the intermediate data in
- * our vector registers goes from 0-63 instead of 63-0. We can reflect
- * the algorithm because we don't carry in mod 2 arithmetic.
- */
- vand v1,v0,mask_32bit /* bottom 32 bits of a */
- VPMSUMD(v1,v1,const1) /* ma */
- vand v1,v1,mask_32bit /* bottom 32bits of ma */
- VPMSUMD(v1,v1,const2) /* qn */
- vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */
-
- /*
- * Since we are bit reflected, the result (ie the low 32 bits) is in
- * the high 32 bits. We just need to shift it left 4 bytes
- * V0 [ 0 1 X 3 ]
- * V0 [ 0 X 2 3 ]
- */
- vsldoi v0,v0,zeroes,4 /* shift result into top 64 bits of */
-
- /* Get it into r3 */
- MFVRD(R3, v0)
-
-.Lout:
- subi r6,r1,56+10*16
- subi r7,r1,56+2*16
-
- lvx v20,0,r6
- lvx v21,off16,r6
- lvx v22,off32,r6
- lvx v23,off48,r6
- lvx v24,off64,r6
- lvx v25,off80,r6
- lvx v26,off96,r6
- lvx v27,off112,r6
- lvx v28,0,r7
- lvx v29,off16,r7
-
- ld r31,-8(r1)
- ld r30,-16(r1)
- ld r29,-24(r1)
- ld r28,-32(r1)
- ld r27,-40(r1)
- ld r26,-48(r1)
- ld r25,-56(r1)
-
- blr
-
-.Lfirst_warm_up_done:
- lvx const1,0,r3
- addi r3,r3,16
-
- VPMSUMD(v8,v16,const1)
- VPMSUMD(v9,v17,const1)
- VPMSUMD(v10,v18,const1)
- VPMSUMD(v11,v19,const1)
- VPMSUMD(v12,v20,const1)
- VPMSUMD(v13,v21,const1)
- VPMSUMD(v14,v22,const1)
- VPMSUMD(v15,v23,const1)
-
- b .Lsecond_cool_down
-
-.Lshort:
- cmpdi r5,0
- beq .Lzero
-
- addis r3,r2,.short_constants@toc@ha
- addi r3,r3,.short_constants@toc@l
-
- /* Calculate where in the constant table we need to start */
- subfic r6,r5,256
- add r3,r3,r6
-
- /* How many 16 byte chunks? */
- srdi r7,r5,4
- mtctr r7
-
- vxor v19,v19,v19
- vxor v20,v20,v20
-
- lvx v0,0,r4
- lvx v16,0,r3
- VPERM(v0,v0,v16,byteswap)
- vxor v0,v0,v8 /* xor in initial value */
- VPMSUMW(v0,v0,v16)
- bdz .Lv0
-
- lvx v1,off16,r4
- lvx v17,off16,r3
- VPERM(v1,v1,v17,byteswap)
- VPMSUMW(v1,v1,v17)
- bdz .Lv1
-
- lvx v2,off32,r4
- lvx v16,off32,r3
- VPERM(v2,v2,v16,byteswap)
- VPMSUMW(v2,v2,v16)
- bdz .Lv2
-
- lvx v3,off48,r4
- lvx v17,off48,r3
- VPERM(v3,v3,v17,byteswap)
- VPMSUMW(v3,v3,v17)
- bdz .Lv3
-
- lvx v4,off64,r4
- lvx v16,off64,r3
- VPERM(v4,v4,v16,byteswap)
- VPMSUMW(v4,v4,v16)
- bdz .Lv4
-
- lvx v5,off80,r4
- lvx v17,off80,r3
- VPERM(v5,v5,v17,byteswap)
- VPMSUMW(v5,v5,v17)
- bdz .Lv5
-
- lvx v6,off96,r4
- lvx v16,off96,r3
- VPERM(v6,v6,v16,byteswap)
- VPMSUMW(v6,v6,v16)
- bdz .Lv6
-
- lvx v7,off112,r4
- lvx v17,off112,r3
- VPERM(v7,v7,v17,byteswap)
- VPMSUMW(v7,v7,v17)
- bdz .Lv7
-
- addi r3,r3,128
- addi r4,r4,128
-
- lvx v8,0,r4
- lvx v16,0,r3
- VPERM(v8,v8,v16,byteswap)
- VPMSUMW(v8,v8,v16)
- bdz .Lv8
-
- lvx v9,off16,r4
- lvx v17,off16,r3
- VPERM(v9,v9,v17,byteswap)
- VPMSUMW(v9,v9,v17)
- bdz .Lv9
-
- lvx v10,off32,r4
- lvx v16,off32,r3
- VPERM(v10,v10,v16,byteswap)
- VPMSUMW(v10,v10,v16)
- bdz .Lv10
-
- lvx v11,off48,r4
- lvx v17,off48,r3
- VPERM(v11,v11,v17,byteswap)
- VPMSUMW(v11,v11,v17)
- bdz .Lv11
-
- lvx v12,off64,r4
- lvx v16,off64,r3
- VPERM(v12,v12,v16,byteswap)
- VPMSUMW(v12,v12,v16)
- bdz .Lv12
-
- lvx v13,off80,r4
- lvx v17,off80,r3
- VPERM(v13,v13,v17,byteswap)
- VPMSUMW(v13,v13,v17)
- bdz .Lv13
-
- lvx v14,off96,r4
- lvx v16,off96,r3
- VPERM(v14,v14,v16,byteswap)
- VPMSUMW(v14,v14,v16)
- bdz .Lv14
-
- lvx v15,off112,r4
- lvx v17,off112,r3
- VPERM(v15,v15,v17,byteswap)
- VPMSUMW(v15,v15,v17)
-
-.Lv15: vxor v19,v19,v15
-.Lv14: vxor v20,v20,v14
-.Lv13: vxor v19,v19,v13
-.Lv12: vxor v20,v20,v12
-.Lv11: vxor v19,v19,v11
-.Lv10: vxor v20,v20,v10
-.Lv9: vxor v19,v19,v9
-.Lv8: vxor v20,v20,v8
-.Lv7: vxor v19,v19,v7
-.Lv6: vxor v20,v20,v6
-.Lv5: vxor v19,v19,v5
-.Lv4: vxor v20,v20,v4
-.Lv3: vxor v19,v19,v3
-.Lv2: vxor v20,v20,v2
-.Lv1: vxor v19,v19,v1
-.Lv0: vxor v20,v20,v0
-
- vxor v0,v19,v20
-
- b .Lbarrett_reduction
-
-.Lzero:
- mr r3,r10
- b .Lout
-
-FUNC_END(__crc32_vpmsum)
+#define CRC_FUNCTION_NAME __crc32c_vpmsum
+#define REFLECT
+#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index 9fa046d56eba..f058e0c3e4d4 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -33,10 +33,13 @@ static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
}
if (len & ~VMX_ALIGN_MASK) {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+ disable_kernel_altivec();
pagefault_enable();
+ preempt_enable();
}
tail = len & VMX_ALIGN_MASK;
@@ -52,7 +55,7 @@ static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
{
u32 *key = crypto_tfm_ctx(tfm);
- *key = 0;
+ *key = ~0;
return 0;
}
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
new file mode 100644
index 000000000000..5e3d81a0af1b
--- /dev/null
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
@@ -0,0 +1,850 @@
+/*
+ * Calculate a CRC T10DIF with vpmsum acceleration
+ *
+ * Constants generated by crc32-vpmsum, available at
+ * https://github.com/antonblanchard/crc32-vpmsum
+ *
+ * crc32-vpmsum is
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ * and is available under the GPL v2 or later.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+ .section .rodata
+.balign 16
+
+.byteswap_constant:
+ /* byte reverse permute constant */
+ .octa 0x0F0E0D0C0B0A09080706050403020100
+
+.constants:
+
+ /* Reduce 262144 kbits to 1024 bits */
+ /* x^261184 mod p(x), x^261120 mod p(x) */
+ .octa 0x0000000056d300000000000052550000
+
+ /* x^260160 mod p(x), x^260096 mod p(x) */
+ .octa 0x00000000ee67000000000000a1e40000
+
+ /* x^259136 mod p(x), x^259072 mod p(x) */
+ .octa 0x0000000060830000000000004ad10000
+
+ /* x^258112 mod p(x), x^258048 mod p(x) */
+ .octa 0x000000008cfe0000000000009ab40000
+
+ /* x^257088 mod p(x), x^257024 mod p(x) */
+ .octa 0x000000003e93000000000000fdb50000
+
+ /* x^256064 mod p(x), x^256000 mod p(x) */
+ .octa 0x000000003c2000000000000045480000
+
+ /* x^255040 mod p(x), x^254976 mod p(x) */
+ .octa 0x00000000b1fc0000000000008d690000
+
+ /* x^254016 mod p(x), x^253952 mod p(x) */
+ .octa 0x00000000f82b00000000000024ad0000
+
+ /* x^252992 mod p(x), x^252928 mod p(x) */
+ .octa 0x0000000044420000000000009f1a0000
+
+ /* x^251968 mod p(x), x^251904 mod p(x) */
+ .octa 0x00000000e88c00000000000066ec0000
+
+ /* x^250944 mod p(x), x^250880 mod p(x) */
+ .octa 0x00000000385c000000000000c87d0000
+
+ /* x^249920 mod p(x), x^249856 mod p(x) */
+ .octa 0x000000003227000000000000c8ff0000
+
+ /* x^248896 mod p(x), x^248832 mod p(x) */
+ .octa 0x00000000a9a900000000000033440000
+
+ /* x^247872 mod p(x), x^247808 mod p(x) */
+ .octa 0x00000000abaa00000000000066eb0000
+
+ /* x^246848 mod p(x), x^246784 mod p(x) */
+ .octa 0x000000001ac3000000000000c4ef0000
+
+ /* x^245824 mod p(x), x^245760 mod p(x) */
+ .octa 0x0000000063f000000000000056f30000
+
+ /* x^244800 mod p(x), x^244736 mod p(x) */
+ .octa 0x0000000032cc00000000000002050000
+
+ /* x^243776 mod p(x), x^243712 mod p(x) */
+ .octa 0x00000000f8b5000000000000568e0000
+
+ /* x^242752 mod p(x), x^242688 mod p(x) */
+ .octa 0x000000008db100000000000064290000
+
+ /* x^241728 mod p(x), x^241664 mod p(x) */
+ .octa 0x0000000059ca0000000000006b660000
+
+ /* x^240704 mod p(x), x^240640 mod p(x) */
+ .octa 0x000000005f5c00000000000018f80000
+
+ /* x^239680 mod p(x), x^239616 mod p(x) */
+ .octa 0x0000000061af000000000000b6090000
+
+ /* x^238656 mod p(x), x^238592 mod p(x) */
+ .octa 0x00000000e29e000000000000099a0000
+
+ /* x^237632 mod p(x), x^237568 mod p(x) */
+ .octa 0x000000000975000000000000a8360000
+
+ /* x^236608 mod p(x), x^236544 mod p(x) */
+ .octa 0x0000000043900000000000004f570000
+
+ /* x^235584 mod p(x), x^235520 mod p(x) */
+ .octa 0x00000000f9cd000000000000134c0000
+
+ /* x^234560 mod p(x), x^234496 mod p(x) */
+ .octa 0x000000007c29000000000000ec380000
+
+ /* x^233536 mod p(x), x^233472 mod p(x) */
+ .octa 0x000000004c6a000000000000b0d10000
+
+ /* x^232512 mod p(x), x^232448 mod p(x) */
+ .octa 0x00000000e7290000000000007d3e0000
+
+ /* x^231488 mod p(x), x^231424 mod p(x) */
+ .octa 0x00000000f1ab000000000000f0b20000
+
+ /* x^230464 mod p(x), x^230400 mod p(x) */
+ .octa 0x0000000039db0000000000009c270000
+
+ /* x^229440 mod p(x), x^229376 mod p(x) */
+ .octa 0x000000005e2800000000000092890000
+
+ /* x^228416 mod p(x), x^228352 mod p(x) */
+ .octa 0x00000000d44e000000000000d5ee0000
+
+ /* x^227392 mod p(x), x^227328 mod p(x) */
+ .octa 0x00000000cd0a00000000000041f50000
+
+ /* x^226368 mod p(x), x^226304 mod p(x) */
+ .octa 0x00000000c5b400000000000010520000
+
+ /* x^225344 mod p(x), x^225280 mod p(x) */
+ .octa 0x00000000fd2100000000000042170000
+
+ /* x^224320 mod p(x), x^224256 mod p(x) */
+ .octa 0x000000002f2500000000000095c20000
+
+ /* x^223296 mod p(x), x^223232 mod p(x) */
+ .octa 0x000000001b0100000000000001ce0000
+
+ /* x^222272 mod p(x), x^222208 mod p(x) */
+ .octa 0x000000000d430000000000002aca0000
+
+ /* x^221248 mod p(x), x^221184 mod p(x) */
+ .octa 0x0000000030a6000000000000385e0000
+
+ /* x^220224 mod p(x), x^220160 mod p(x) */
+ .octa 0x00000000e37b0000000000006f7a0000
+
+ /* x^219200 mod p(x), x^219136 mod p(x) */
+ .octa 0x00000000873600000000000024320000
+
+ /* x^218176 mod p(x), x^218112 mod p(x) */
+ .octa 0x00000000e9fb000000000000bd9c0000
+
+ /* x^217152 mod p(x), x^217088 mod p(x) */
+ .octa 0x000000003b9500000000000054bc0000
+
+ /* x^216128 mod p(x), x^216064 mod p(x) */
+ .octa 0x00000000133e000000000000a4660000
+
+ /* x^215104 mod p(x), x^215040 mod p(x) */
+ .octa 0x00000000784500000000000079930000
+
+ /* x^214080 mod p(x), x^214016 mod p(x) */
+ .octa 0x00000000b9800000000000001bb80000
+
+ /* x^213056 mod p(x), x^212992 mod p(x) */
+ .octa 0x00000000687600000000000024400000
+
+ /* x^212032 mod p(x), x^211968 mod p(x) */
+ .octa 0x00000000aff300000000000029e10000
+
+ /* x^211008 mod p(x), x^210944 mod p(x) */
+ .octa 0x0000000024b50000000000005ded0000
+
+ /* x^209984 mod p(x), x^209920 mod p(x) */
+ .octa 0x0000000017e8000000000000b12e0000
+
+ /* x^208960 mod p(x), x^208896 mod p(x) */
+ .octa 0x00000000128400000000000026d20000
+
+ /* x^207936 mod p(x), x^207872 mod p(x) */
+ .octa 0x000000002115000000000000a32a0000
+
+ /* x^206912 mod p(x), x^206848 mod p(x) */
+ .octa 0x000000009595000000000000a1210000
+
+ /* x^205888 mod p(x), x^205824 mod p(x) */
+ .octa 0x00000000281e000000000000ee8b0000
+
+ /* x^204864 mod p(x), x^204800 mod p(x) */
+ .octa 0x0000000006010000000000003d0d0000
+
+ /* x^203840 mod p(x), x^203776 mod p(x) */
+ .octa 0x00000000e2b600000000000034e90000
+
+ /* x^202816 mod p(x), x^202752 mod p(x) */
+ .octa 0x000000001bd40000000000004cdb0000
+
+ /* x^201792 mod p(x), x^201728 mod p(x) */
+ .octa 0x00000000df2800000000000030e90000
+
+ /* x^200768 mod p(x), x^200704 mod p(x) */
+ .octa 0x0000000049c200000000000042590000
+
+ /* x^199744 mod p(x), x^199680 mod p(x) */
+ .octa 0x000000009b97000000000000df950000
+
+ /* x^198720 mod p(x), x^198656 mod p(x) */
+ .octa 0x000000006184000000000000da7b0000
+
+ /* x^197696 mod p(x), x^197632 mod p(x) */
+ .octa 0x00000000461700000000000012510000
+
+ /* x^196672 mod p(x), x^196608 mod p(x) */
+ .octa 0x000000009b40000000000000f37e0000
+
+ /* x^195648 mod p(x), x^195584 mod p(x) */
+ .octa 0x00000000eeb2000000000000ecf10000
+
+ /* x^194624 mod p(x), x^194560 mod p(x) */
+ .octa 0x00000000b2e800000000000050f20000
+
+ /* x^193600 mod p(x), x^193536 mod p(x) */
+ .octa 0x00000000f59a000000000000e0b30000
+
+ /* x^192576 mod p(x), x^192512 mod p(x) */
+ .octa 0x00000000467f0000000000004d5a0000
+
+ /* x^191552 mod p(x), x^191488 mod p(x) */
+ .octa 0x00000000da92000000000000bb010000
+
+ /* x^190528 mod p(x), x^190464 mod p(x) */
+ .octa 0x000000001e1000000000000022a40000
+
+ /* x^189504 mod p(x), x^189440 mod p(x) */
+ .octa 0x0000000058fe000000000000836f0000
+
+ /* x^188480 mod p(x), x^188416 mod p(x) */
+ .octa 0x00000000b9ce000000000000d78d0000
+
+ /* x^187456 mod p(x), x^187392 mod p(x) */
+ .octa 0x0000000022210000000000004f8d0000
+
+ /* x^186432 mod p(x), x^186368 mod p(x) */
+ .octa 0x00000000744600000000000033760000
+
+ /* x^185408 mod p(x), x^185344 mod p(x) */
+ .octa 0x000000001c2e000000000000a1e50000
+
+ /* x^184384 mod p(x), x^184320 mod p(x) */
+ .octa 0x00000000dcc8000000000000a1a40000
+
+ /* x^183360 mod p(x), x^183296 mod p(x) */
+ .octa 0x00000000910f00000000000019a20000
+
+ /* x^182336 mod p(x), x^182272 mod p(x) */
+ .octa 0x0000000055d5000000000000f6ae0000
+
+ /* x^181312 mod p(x), x^181248 mod p(x) */
+ .octa 0x00000000c8ba000000000000a7ac0000
+
+ /* x^180288 mod p(x), x^180224 mod p(x) */
+ .octa 0x0000000031f8000000000000eea20000
+
+ /* x^179264 mod p(x), x^179200 mod p(x) */
+ .octa 0x000000001966000000000000c4d90000
+
+ /* x^178240 mod p(x), x^178176 mod p(x) */
+ .octa 0x00000000b9810000000000002b470000
+
+ /* x^177216 mod p(x), x^177152 mod p(x) */
+ .octa 0x000000008303000000000000f7cf0000
+
+ /* x^176192 mod p(x), x^176128 mod p(x) */
+ .octa 0x000000002ce500000000000035b30000
+
+ /* x^175168 mod p(x), x^175104 mod p(x) */
+ .octa 0x000000002fae0000000000000c7c0000
+
+ /* x^174144 mod p(x), x^174080 mod p(x) */
+ .octa 0x00000000f50c0000000000009edf0000
+
+ /* x^173120 mod p(x), x^173056 mod p(x) */
+ .octa 0x00000000714f00000000000004cd0000
+
+ /* x^172096 mod p(x), x^172032 mod p(x) */
+ .octa 0x00000000c161000000000000541b0000
+
+ /* x^171072 mod p(x), x^171008 mod p(x) */
+ .octa 0x0000000021c8000000000000e2700000
+
+ /* x^170048 mod p(x), x^169984 mod p(x) */
+ .octa 0x00000000b93d00000000000009a60000
+
+ /* x^169024 mod p(x), x^168960 mod p(x) */
+ .octa 0x00000000fbcf000000000000761c0000
+
+ /* x^168000 mod p(x), x^167936 mod p(x) */
+ .octa 0x0000000026350000000000009db30000
+
+ /* x^166976 mod p(x), x^166912 mod p(x) */
+ .octa 0x00000000b64f0000000000003e9f0000
+
+ /* x^165952 mod p(x), x^165888 mod p(x) */
+ .octa 0x00000000bd0e00000000000078590000
+
+ /* x^164928 mod p(x), x^164864 mod p(x) */
+ .octa 0x00000000d9360000000000008bc80000
+
+ /* x^163904 mod p(x), x^163840 mod p(x) */
+ .octa 0x000000002f140000000000008c9f0000
+
+ /* x^162880 mod p(x), x^162816 mod p(x) */
+ .octa 0x000000006a270000000000006af70000
+
+ /* x^161856 mod p(x), x^161792 mod p(x) */
+ .octa 0x000000006685000000000000e5210000
+
+ /* x^160832 mod p(x), x^160768 mod p(x) */
+ .octa 0x0000000062da00000000000008290000
+
+ /* x^159808 mod p(x), x^159744 mod p(x) */
+ .octa 0x00000000bb4b000000000000e4d00000
+
+ /* x^158784 mod p(x), x^158720 mod p(x) */
+ .octa 0x00000000d2490000000000004ae10000
+
+ /* x^157760 mod p(x), x^157696 mod p(x) */
+ .octa 0x00000000c85b00000000000000e70000
+
+ /* x^156736 mod p(x), x^156672 mod p(x) */
+ .octa 0x00000000c37a00000000000015650000
+
+ /* x^155712 mod p(x), x^155648 mod p(x) */
+ .octa 0x0000000018530000000000001c2f0000
+
+ /* x^154688 mod p(x), x^154624 mod p(x) */
+ .octa 0x00000000b46600000000000037bd0000
+
+ /* x^153664 mod p(x), x^153600 mod p(x) */
+ .octa 0x00000000439b00000000000012190000
+
+ /* x^152640 mod p(x), x^152576 mod p(x) */
+ .octa 0x00000000b1260000000000005ece0000
+
+ /* x^151616 mod p(x), x^151552 mod p(x) */
+ .octa 0x00000000d8110000000000002a5e0000
+
+ /* x^150592 mod p(x), x^150528 mod p(x) */
+ .octa 0x00000000099f00000000000052330000
+
+ /* x^149568 mod p(x), x^149504 mod p(x) */
+ .octa 0x00000000f9f9000000000000f9120000
+
+ /* x^148544 mod p(x), x^148480 mod p(x) */
+ .octa 0x000000005cc00000000000000ddc0000
+
+ /* x^147520 mod p(x), x^147456 mod p(x) */
+ .octa 0x00000000343b00000000000012200000
+
+ /* x^146496 mod p(x), x^146432 mod p(x) */
+ .octa 0x000000009222000000000000d12b0000
+
+ /* x^145472 mod p(x), x^145408 mod p(x) */
+ .octa 0x00000000d781000000000000eb2d0000
+
+ /* x^144448 mod p(x), x^144384 mod p(x) */
+ .octa 0x000000000bf400000000000058970000
+
+ /* x^143424 mod p(x), x^143360 mod p(x) */
+ .octa 0x00000000094200000000000013690000
+
+ /* x^142400 mod p(x), x^142336 mod p(x) */
+ .octa 0x00000000d55100000000000051950000
+
+ /* x^141376 mod p(x), x^141312 mod p(x) */
+ .octa 0x000000008f11000000000000954b0000
+
+ /* x^140352 mod p(x), x^140288 mod p(x) */
+ .octa 0x00000000140f000000000000b29e0000
+
+ /* x^139328 mod p(x), x^139264 mod p(x) */
+ .octa 0x00000000c6db000000000000db5d0000
+
+ /* x^138304 mod p(x), x^138240 mod p(x) */
+ .octa 0x00000000715b000000000000dfaf0000
+
+ /* x^137280 mod p(x), x^137216 mod p(x) */
+ .octa 0x000000000dea000000000000e3b60000
+
+ /* x^136256 mod p(x), x^136192 mod p(x) */
+ .octa 0x000000006f94000000000000ddaf0000
+
+ /* x^135232 mod p(x), x^135168 mod p(x) */
+ .octa 0x0000000024e1000000000000e4f70000
+
+ /* x^134208 mod p(x), x^134144 mod p(x) */
+ .octa 0x000000008810000000000000aa110000
+
+ /* x^133184 mod p(x), x^133120 mod p(x) */
+ .octa 0x0000000030c2000000000000a8e60000
+
+ /* x^132160 mod p(x), x^132096 mod p(x) */
+ .octa 0x00000000e6d0000000000000ccf30000
+
+ /* x^131136 mod p(x), x^131072 mod p(x) */
+ .octa 0x000000004da000000000000079bf0000
+
+ /* x^130112 mod p(x), x^130048 mod p(x) */
+ .octa 0x000000007759000000000000b3a30000
+
+ /* x^129088 mod p(x), x^129024 mod p(x) */
+ .octa 0x00000000597400000000000028790000
+
+ /* x^128064 mod p(x), x^128000 mod p(x) */
+ .octa 0x000000007acd000000000000b5820000
+
+ /* x^127040 mod p(x), x^126976 mod p(x) */
+ .octa 0x00000000e6e400000000000026ad0000
+
+ /* x^126016 mod p(x), x^125952 mod p(x) */
+ .octa 0x000000006d49000000000000985b0000
+
+ /* x^124992 mod p(x), x^124928 mod p(x) */
+ .octa 0x000000000f0800000000000011520000
+
+ /* x^123968 mod p(x), x^123904 mod p(x) */
+ .octa 0x000000002c7f000000000000846c0000
+
+ /* x^122944 mod p(x), x^122880 mod p(x) */
+ .octa 0x000000005ce7000000000000ae1d0000
+
+ /* x^121920 mod p(x), x^121856 mod p(x) */
+ .octa 0x00000000d4cb000000000000e21d0000
+
+ /* x^120896 mod p(x), x^120832 mod p(x) */
+ .octa 0x000000003a2300000000000019bb0000
+
+ /* x^119872 mod p(x), x^119808 mod p(x) */
+ .octa 0x000000000e1700000000000095290000
+
+ /* x^118848 mod p(x), x^118784 mod p(x) */
+ .octa 0x000000006e6400000000000050d20000
+
+ /* x^117824 mod p(x), x^117760 mod p(x) */
+ .octa 0x000000008d5c0000000000000cd10000
+
+ /* x^116800 mod p(x), x^116736 mod p(x) */
+ .octa 0x00000000ef310000000000007b570000
+
+ /* x^115776 mod p(x), x^115712 mod p(x) */
+ .octa 0x00000000645d00000000000053d60000
+
+ /* x^114752 mod p(x), x^114688 mod p(x) */
+ .octa 0x0000000018fc00000000000077510000
+
+ /* x^113728 mod p(x), x^113664 mod p(x) */
+ .octa 0x000000000cb3000000000000a7b70000
+
+ /* x^112704 mod p(x), x^112640 mod p(x) */
+ .octa 0x00000000991b000000000000d0780000
+
+ /* x^111680 mod p(x), x^111616 mod p(x) */
+ .octa 0x00000000845a000000000000be3c0000
+
+ /* x^110656 mod p(x), x^110592 mod p(x) */
+ .octa 0x00000000d3a9000000000000df020000
+
+ /* x^109632 mod p(x), x^109568 mod p(x) */
+ .octa 0x0000000017d7000000000000063e0000
+
+ /* x^108608 mod p(x), x^108544 mod p(x) */
+ .octa 0x000000007a860000000000008ab40000
+
+ /* x^107584 mod p(x), x^107520 mod p(x) */
+ .octa 0x00000000fd7c000000000000c7bd0000
+
+ /* x^106560 mod p(x), x^106496 mod p(x) */
+ .octa 0x00000000a56b000000000000efd60000
+
+ /* x^105536 mod p(x), x^105472 mod p(x) */
+ .octa 0x0000000010e400000000000071380000
+
+ /* x^104512 mod p(x), x^104448 mod p(x) */
+ .octa 0x00000000994500000000000004d30000
+
+ /* x^103488 mod p(x), x^103424 mod p(x) */
+ .octa 0x00000000b83c0000000000003b0e0000
+
+ /* x^102464 mod p(x), x^102400 mod p(x) */
+ .octa 0x00000000d6c10000000000008b020000
+
+ /* x^101440 mod p(x), x^101376 mod p(x) */
+ .octa 0x000000009efc000000000000da940000
+
+ /* x^100416 mod p(x), x^100352 mod p(x) */
+ .octa 0x000000005e87000000000000f9f70000
+
+ /* x^99392 mod p(x), x^99328 mod p(x) */
+ .octa 0x000000006c9b00000000000045e40000
+
+ /* x^98368 mod p(x), x^98304 mod p(x) */
+ .octa 0x00000000178a00000000000083940000
+
+ /* x^97344 mod p(x), x^97280 mod p(x) */
+ .octa 0x00000000f0c8000000000000f0a00000
+
+ /* x^96320 mod p(x), x^96256 mod p(x) */
+ .octa 0x00000000f699000000000000b74b0000
+
+ /* x^95296 mod p(x), x^95232 mod p(x) */
+ .octa 0x00000000316d000000000000c1cf0000
+
+ /* x^94272 mod p(x), x^94208 mod p(x) */
+ .octa 0x00000000987e00000000000072680000
+
+ /* x^93248 mod p(x), x^93184 mod p(x) */
+ .octa 0x00000000acff000000000000e0ab0000
+
+ /* x^92224 mod p(x), x^92160 mod p(x) */
+ .octa 0x00000000a1f6000000000000c5a80000
+
+ /* x^91200 mod p(x), x^91136 mod p(x) */
+ .octa 0x0000000061bd000000000000cf690000
+
+ /* x^90176 mod p(x), x^90112 mod p(x) */
+ .octa 0x00000000c9f2000000000000cbcc0000
+
+ /* x^89152 mod p(x), x^89088 mod p(x) */
+ .octa 0x000000005a33000000000000de050000
+
+ /* x^88128 mod p(x), x^88064 mod p(x) */
+ .octa 0x00000000e416000000000000ccd70000
+
+ /* x^87104 mod p(x), x^87040 mod p(x) */
+ .octa 0x0000000058930000000000002f670000
+
+ /* x^86080 mod p(x), x^86016 mod p(x) */
+ .octa 0x00000000a9d3000000000000152f0000
+
+ /* x^85056 mod p(x), x^84992 mod p(x) */
+ .octa 0x00000000c114000000000000ecc20000
+
+ /* x^84032 mod p(x), x^83968 mod p(x) */
+ .octa 0x00000000b9270000000000007c890000
+
+ /* x^83008 mod p(x), x^82944 mod p(x) */
+ .octa 0x000000002e6000000000000006ee0000
+
+ /* x^81984 mod p(x), x^81920 mod p(x) */
+ .octa 0x00000000dfc600000000000009100000
+
+ /* x^80960 mod p(x), x^80896 mod p(x) */
+ .octa 0x000000004911000000000000ad4e0000
+
+ /* x^79936 mod p(x), x^79872 mod p(x) */
+ .octa 0x00000000ae1b000000000000b04d0000
+
+ /* x^78912 mod p(x), x^78848 mod p(x) */
+ .octa 0x0000000005fa000000000000e9900000
+
+ /* x^77888 mod p(x), x^77824 mod p(x) */
+ .octa 0x0000000004a1000000000000cc6f0000
+
+ /* x^76864 mod p(x), x^76800 mod p(x) */
+ .octa 0x00000000af73000000000000ed110000
+
+ /* x^75840 mod p(x), x^75776 mod p(x) */
+ .octa 0x0000000082530000000000008f7e0000
+
+ /* x^74816 mod p(x), x^74752 mod p(x) */
+ .octa 0x00000000cfdc000000000000594f0000
+
+ /* x^73792 mod p(x), x^73728 mod p(x) */
+ .octa 0x00000000a6b6000000000000a8750000
+
+ /* x^72768 mod p(x), x^72704 mod p(x) */
+ .octa 0x00000000fd76000000000000aa0c0000
+
+ /* x^71744 mod p(x), x^71680 mod p(x) */
+ .octa 0x0000000006f500000000000071db0000
+
+ /* x^70720 mod p(x), x^70656 mod p(x) */
+ .octa 0x0000000037ca000000000000ab0c0000
+
+ /* x^69696 mod p(x), x^69632 mod p(x) */
+ .octa 0x00000000d7ab000000000000b7a00000
+
+ /* x^68672 mod p(x), x^68608 mod p(x) */
+ .octa 0x00000000440800000000000090d30000
+
+ /* x^67648 mod p(x), x^67584 mod p(x) */
+ .octa 0x00000000186100000000000054730000
+
+ /* x^66624 mod p(x), x^66560 mod p(x) */
+ .octa 0x000000007368000000000000a3a20000
+
+ /* x^65600 mod p(x), x^65536 mod p(x) */
+ .octa 0x0000000026d0000000000000f9040000
+
+ /* x^64576 mod p(x), x^64512 mod p(x) */
+ .octa 0x00000000fe770000000000009c0a0000
+
+ /* x^63552 mod p(x), x^63488 mod p(x) */
+ .octa 0x000000002cba000000000000d1e70000
+
+ /* x^62528 mod p(x), x^62464 mod p(x) */
+ .octa 0x00000000f8bd0000000000005ac10000
+
+ /* x^61504 mod p(x), x^61440 mod p(x) */
+ .octa 0x000000007372000000000000d68d0000
+
+ /* x^60480 mod p(x), x^60416 mod p(x) */
+ .octa 0x00000000f37f00000000000089f60000
+
+ /* x^59456 mod p(x), x^59392 mod p(x) */
+ .octa 0x00000000078400000000000008a90000
+
+ /* x^58432 mod p(x), x^58368 mod p(x) */
+ .octa 0x00000000d3e400000000000042360000
+
+ /* x^57408 mod p(x), x^57344 mod p(x) */
+ .octa 0x00000000eba800000000000092d50000
+
+ /* x^56384 mod p(x), x^56320 mod p(x) */
+ .octa 0x00000000afbe000000000000b4d50000
+
+ /* x^55360 mod p(x), x^55296 mod p(x) */
+ .octa 0x00000000d8ca000000000000c9060000
+
+ /* x^54336 mod p(x), x^54272 mod p(x) */
+ .octa 0x00000000c2d00000000000008f4f0000
+
+ /* x^53312 mod p(x), x^53248 mod p(x) */
+ .octa 0x00000000373200000000000028690000
+
+ /* x^52288 mod p(x), x^52224 mod p(x) */
+ .octa 0x0000000046ae000000000000c3b30000
+
+ /* x^51264 mod p(x), x^51200 mod p(x) */
+ .octa 0x00000000b243000000000000f8700000
+
+ /* x^50240 mod p(x), x^50176 mod p(x) */
+ .octa 0x00000000f7f500000000000029eb0000
+
+ /* x^49216 mod p(x), x^49152 mod p(x) */
+ .octa 0x000000000c7e000000000000fe730000
+
+ /* x^48192 mod p(x), x^48128 mod p(x) */
+ .octa 0x00000000c38200000000000096000000
+
+ /* x^47168 mod p(x), x^47104 mod p(x) */
+ .octa 0x000000008956000000000000683c0000
+
+ /* x^46144 mod p(x), x^46080 mod p(x) */
+ .octa 0x00000000422d0000000000005f1e0000
+
+ /* x^45120 mod p(x), x^45056 mod p(x) */
+ .octa 0x00000000ac0f0000000000006f810000
+
+ /* x^44096 mod p(x), x^44032 mod p(x) */
+ .octa 0x00000000ce30000000000000031f0000
+
+ /* x^43072 mod p(x), x^43008 mod p(x) */
+ .octa 0x000000003d43000000000000455a0000
+
+ /* x^42048 mod p(x), x^41984 mod p(x) */
+ .octa 0x000000007ebe000000000000a6050000
+
+ /* x^41024 mod p(x), x^40960 mod p(x) */
+ .octa 0x00000000976e00000000000077eb0000
+
+ /* x^40000 mod p(x), x^39936 mod p(x) */
+ .octa 0x000000000872000000000000389c0000
+
+ /* x^38976 mod p(x), x^38912 mod p(x) */
+ .octa 0x000000008979000000000000c7b20000
+
+ /* x^37952 mod p(x), x^37888 mod p(x) */
+ .octa 0x000000005c1e0000000000001d870000
+
+ /* x^36928 mod p(x), x^36864 mod p(x) */
+ .octa 0x00000000aebb00000000000045810000
+
+ /* x^35904 mod p(x), x^35840 mod p(x) */
+ .octa 0x000000004f7e0000000000006d4a0000
+
+ /* x^34880 mod p(x), x^34816 mod p(x) */
+ .octa 0x00000000ea98000000000000b9200000
+
+ /* x^33856 mod p(x), x^33792 mod p(x) */
+ .octa 0x00000000f39600000000000022f20000
+
+ /* x^32832 mod p(x), x^32768 mod p(x) */
+ .octa 0x000000000bc500000000000041ca0000
+
+ /* x^31808 mod p(x), x^31744 mod p(x) */
+ .octa 0x00000000786400000000000078500000
+
+ /* x^30784 mod p(x), x^30720 mod p(x) */
+ .octa 0x00000000be970000000000009e7e0000
+
+ /* x^29760 mod p(x), x^29696 mod p(x) */
+ .octa 0x00000000dd6d000000000000a53c0000
+
+ /* x^28736 mod p(x), x^28672 mod p(x) */
+ .octa 0x000000004c3f00000000000039340000
+
+ /* x^27712 mod p(x), x^27648 mod p(x) */
+ .octa 0x0000000093a4000000000000b58e0000
+
+ /* x^26688 mod p(x), x^26624 mod p(x) */
+ .octa 0x0000000050fb00000000000062d40000
+
+ /* x^25664 mod p(x), x^25600 mod p(x) */
+ .octa 0x00000000f505000000000000a26f0000
+
+ /* x^24640 mod p(x), x^24576 mod p(x) */
+ .octa 0x0000000064f900000000000065e60000
+
+ /* x^23616 mod p(x), x^23552 mod p(x) */
+ .octa 0x00000000e8c2000000000000aad90000
+
+ /* x^22592 mod p(x), x^22528 mod p(x) */
+ .octa 0x00000000720b000000000000a3b00000
+
+ /* x^21568 mod p(x), x^21504 mod p(x) */
+ .octa 0x00000000e992000000000000d2680000
+
+ /* x^20544 mod p(x), x^20480 mod p(x) */
+ .octa 0x000000009132000000000000cf4c0000
+
+ /* x^19520 mod p(x), x^19456 mod p(x) */
+ .octa 0x00000000608a00000000000076610000
+
+ /* x^18496 mod p(x), x^18432 mod p(x) */
+ .octa 0x000000009948000000000000fb9f0000
+
+ /* x^17472 mod p(x), x^17408 mod p(x) */
+ .octa 0x00000000173000000000000003770000
+
+ /* x^16448 mod p(x), x^16384 mod p(x) */
+ .octa 0x000000006fe300000000000004880000
+
+ /* x^15424 mod p(x), x^15360 mod p(x) */
+ .octa 0x00000000e15300000000000056a70000
+
+ /* x^14400 mod p(x), x^14336 mod p(x) */
+ .octa 0x0000000092d60000000000009dfd0000
+
+ /* x^13376 mod p(x), x^13312 mod p(x) */
+ .octa 0x0000000002fd00000000000074c80000
+
+ /* x^12352 mod p(x), x^12288 mod p(x) */
+ .octa 0x00000000c78b000000000000a3ec0000
+
+ /* x^11328 mod p(x), x^11264 mod p(x) */
+ .octa 0x000000009262000000000000b3530000
+
+ /* x^10304 mod p(x), x^10240 mod p(x) */
+ .octa 0x0000000084f200000000000047bf0000
+
+ /* x^9280 mod p(x), x^9216 mod p(x) */
+ .octa 0x0000000067ee000000000000e97c0000
+
+ /* x^8256 mod p(x), x^8192 mod p(x) */
+ .octa 0x00000000535b00000000000091e10000
+
+ /* x^7232 mod p(x), x^7168 mod p(x) */
+ .octa 0x000000007ebb00000000000055060000
+
+ /* x^6208 mod p(x), x^6144 mod p(x) */
+ .octa 0x00000000c6a1000000000000fd360000
+
+ /* x^5184 mod p(x), x^5120 mod p(x) */
+ .octa 0x000000001be500000000000055860000
+
+ /* x^4160 mod p(x), x^4096 mod p(x) */
+ .octa 0x00000000ae0e0000000000005bd00000
+
+ /* x^3136 mod p(x), x^3072 mod p(x) */
+ .octa 0x0000000022040000000000008db20000
+
+ /* x^2112 mod p(x), x^2048 mod p(x) */
+ .octa 0x00000000c9eb000000000000efe20000
+
+ /* x^1088 mod p(x), x^1024 mod p(x) */
+ .octa 0x0000000039b400000000000051d10000
+
+.short_constants:
+
+ /* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
+ /* x^2048 mod p(x), x^2016 mod p(x), x^1984 mod p(x), x^1952 mod p(x) */
+ .octa 0xefe20000dccf00009440000033590000
+
+ /* x^1920 mod p(x), x^1888 mod p(x), x^1856 mod p(x), x^1824 mod p(x) */
+ .octa 0xee6300002f3f000062180000e0ed0000
+
+ /* x^1792 mod p(x), x^1760 mod p(x), x^1728 mod p(x), x^1696 mod p(x) */
+ .octa 0xcf5f000017ef0000ccbe000023d30000
+
+ /* x^1664 mod p(x), x^1632 mod p(x), x^1600 mod p(x), x^1568 mod p(x) */
+ .octa 0x6d0c0000a30e00000920000042630000
+
+ /* x^1536 mod p(x), x^1504 mod p(x), x^1472 mod p(x), x^1440 mod p(x) */
+ .octa 0x21d30000932b0000a7a00000efcc0000
+
+ /* x^1408 mod p(x), x^1376 mod p(x), x^1344 mod p(x), x^1312 mod p(x) */
+ .octa 0x10be00000b310000666f00000d1c0000
+
+ /* x^1280 mod p(x), x^1248 mod p(x), x^1216 mod p(x), x^1184 mod p(x) */
+ .octa 0x1f240000ce9e0000caad0000589e0000
+
+ /* x^1152 mod p(x), x^1120 mod p(x), x^1088 mod p(x), x^1056 mod p(x) */
+ .octa 0x29610000d02b000039b400007cf50000
+
+ /* x^1024 mod p(x), x^992 mod p(x), x^960 mod p(x), x^928 mod p(x) */
+ .octa 0x51d100009d9d00003c0e0000bfd60000
+
+ /* x^896 mod p(x), x^864 mod p(x), x^832 mod p(x), x^800 mod p(x) */
+ .octa 0xda390000ceae000013830000713c0000
+
+ /* x^768 mod p(x), x^736 mod p(x), x^704 mod p(x), x^672 mod p(x) */
+ .octa 0xb67800001e16000085c0000080a60000
+
+ /* x^640 mod p(x), x^608 mod p(x), x^576 mod p(x), x^544 mod p(x) */
+ .octa 0x0db40000f7f90000371d0000e6580000
+
+ /* x^512 mod p(x), x^480 mod p(x), x^448 mod p(x), x^416 mod p(x) */
+ .octa 0x87e70000044c0000aadb0000a4970000
+
+ /* x^384 mod p(x), x^352 mod p(x), x^320 mod p(x), x^288 mod p(x) */
+ .octa 0x1f990000ad180000d8b30000e7b50000
+
+ /* x^256 mod p(x), x^224 mod p(x), x^192 mod p(x), x^160 mod p(x) */
+ .octa 0xbe6c00006ee300004c1a000006df0000
+
+ /* x^128 mod p(x), x^96 mod p(x), x^64 mod p(x), x^32 mod p(x) */
+ .octa 0xfb0b00002d560000136800008bb70000
+
+
+.barrett_constants:
+ /* Barrett constant m - (4^32)/n */
+ .octa 0x000000000000000000000001f65a57f8 /* x^64 div p(x) */
+ /* Barrett constant n */
+ .octa 0x0000000000000000000000018bb70000
+
+#define CRC_FUNCTION_NAME __crct10dif_vpmsum
+#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
new file mode 100644
index 000000000000..02ea277863d1
--- /dev/null
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
@@ -0,0 +1,128 @@
+/*
+ * Calculate a CRC T10-DIF with vpmsum acceleration
+ *
+ * Copyright 2017, Daniel Axtens, IBM Corporation.
+ * [based on crc32c-vpmsum_glue.c]
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ */
+
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/switch_to.h>
+
+#define VMX_ALIGN 16
+#define VMX_ALIGN_MASK (VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT 64
+
+u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len);
+
+static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len)
+{
+ unsigned int prealign;
+ unsigned int tail;
+ u32 crc = crci;
+
+ if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+ return crc_t10dif_generic(crc, p, len);
+
+ if ((unsigned long)p & VMX_ALIGN_MASK) {
+ prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+ crc = crc_t10dif_generic(crc, p, prealign);
+ len -= prealign;
+ p += prealign;
+ }
+
+ if (len & ~VMX_ALIGN_MASK) {
+ crc <<= 16;
+ preempt_disable();
+ pagefault_disable();
+ enable_kernel_altivec();
+ crc = __crct10dif_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+ disable_kernel_altivec();
+ pagefault_enable();
+ preempt_enable();
+ crc >>= 16;
+ }
+
+ tail = len & VMX_ALIGN_MASK;
+ if (tail) {
+ p += len & ~VMX_ALIGN_MASK;
+ crc = crc_t10dif_generic(crc, p, tail);
+ }
+
+ return crc & 0xffff;
+}
+
+static int crct10dif_vpmsum_init(struct shash_desc *desc)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ *crc = 0;
+ return 0;
+}
+
+static int crct10dif_vpmsum_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ *crc = crct10dif_vpmsum(*crc, data, length);
+
+ return 0;
+}
+
+
+static int crct10dif_vpmsum_final(struct shash_desc *desc, u8 *out)
+{
+ u16 *crcp = shash_desc_ctx(desc);
+
+ *(u16 *)out = *crcp;
+ return 0;
+}
+
+static struct shash_alg alg = {
+ .init = crct10dif_vpmsum_init,
+ .update = crct10dif_vpmsum_update,
+ .final = crct10dif_vpmsum_final,
+ .descsize = CRC_T10DIF_DIGEST_SIZE,
+ .digestsize = CRC_T10DIF_DIGEST_SIZE,
+ .base = {
+ .cra_name = "crct10dif",
+ .cra_driver_name = "crct10dif-vpmsum",
+ .cra_priority = 200,
+ .cra_blocksize = CRC_T10DIF_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init crct10dif_vpmsum_mod_init(void)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ return crypto_register_shash(&alg);
+}
+
+static void __exit crct10dif_vpmsum_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crct10dif_vpmsum_mod_init);
+module_exit(crct10dif_vpmsum_mod_fini);
+
+MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
+MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-vpmsum");
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index f6c5264287e5..7330150bfe34 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -17,6 +17,8 @@
#include <asm/checksum.h>
#include <linux/uaccess.h>
#include <asm/epapr_hcalls.h>
+#include <asm/dcr.h>
+#include <asm/mmu_context.h>
#include <uapi/asm/ucontext.h>
@@ -120,6 +122,8 @@ extern s64 __ashrdi3(s64, int);
extern int __cmpdi2(s64, s64);
extern int __ucmpdi2(u64, u64);
+/* tracing */
void _mcount(void);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
#endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 73eb794d6163..33a24fdd7958 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -51,6 +51,18 @@
#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit))
#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
+/* Put a PPC bit into a "normal" bit position */
+#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit) \
+ ((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
+
+#define PPC_BITLSHIFT32(be) (32 - 1 - (be))
+#define PPC_BIT32(bit) (1UL << PPC_BITLSHIFT32(bit))
+#define PPC_BITMASK32(bs, be) ((PPC_BIT32(bs) - PPC_BIT32(be))|PPC_BIT32(bs))
+
+#define PPC_BITLSHIFT8(be) (8 - 1 - (be))
+#define PPC_BIT8(bit) (1UL << PPC_BITLSHIFT8(bit))
+#define PPC_BITMASK8(bs, be) ((PPC_BIT8(bs) - PPC_BIT8(be))|PPC_BIT8(bs))
+
#include <asm/barrier.h>
/* Macro for generating the ***_bits() functions */
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 012223638815..26ed228d4dc6 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -1,6 +1,7 @@
#ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H
#define _ASM_POWERPC_BOOK3S_32_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#include <asm/book3s/32/hash.h>
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 0c4e470571ca..b4b5e6b671ca 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -8,7 +8,7 @@
#define H_PTE_INDEX_SIZE 9
#define H_PMD_INDEX_SIZE 7
#define H_PUD_INDEX_SIZE 9
-#define H_PGD_INDEX_SIZE 9
+#define H_PGD_INDEX_SIZE 12
#ifndef __ASSEMBLY__
#define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index f3dd21efa2ea..214219dff87c 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -4,10 +4,14 @@
#define H_PTE_INDEX_SIZE 8
#define H_PMD_INDEX_SIZE 5
#define H_PUD_INDEX_SIZE 5
-#define H_PGD_INDEX_SIZE 12
+#define H_PGD_INDEX_SIZE 15
-#define H_PAGE_COMBO 0x00001000 /* this is a combo 4k page */
-#define H_PAGE_4K_PFN 0x00002000 /* PFN is for a single 4k page */
+/*
+ * 64k aligned address free up few of the lower bits of RPN for us
+ * We steal that here. For more deatils look at pte_pfn/pfn_pte()
+ */
+#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 */
/*
* We need to differentiate between explicit huge page and THP huge
* page, since THP huge page also need to track real subpage details
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index f7b721bbf918..4e957b027fe0 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -6,19 +6,13 @@
* Common bits between 4K and 64K pages in a linux-style PTE.
* Additional bits may be defined in pgtable-hash64-*.h
*
- * Note: We only support user read/write permissions. Supervisor always
- * have full read/write to pages above PAGE_OFFSET (pages below that
- * always use the user access permissions).
- *
- * We could create separate kernel read-only if we used the 3 PP bits
- * combinations that newer processors provide but we currently don't.
*/
-#define H_PAGE_BUSY 0x00800 /* software: PTE & hash are busy */
#define H_PTE_NONE_MASK _PAGE_HPTEFLAGS
-#define H_PAGE_F_GIX_SHIFT 57
-#define H_PAGE_F_GIX (7ul << 57) /* HPTE index within HPTEG */
-#define H_PAGE_F_SECOND (1ul << 60) /* HPTE is in 2ndary HPTEG */
-#define H_PAGE_HASHPTE (1ul << 61) /* PTE has associated HPTE */
+#define H_PAGE_F_GIX_SHIFT 56
+#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */
+#define H_PAGE_F_SECOND _RPAGE_RSV2 /* HPTE is in 2ndary HPTEG */
+#define H_PAGE_F_GIX (_RPAGE_RSV3 | _RPAGE_RSV4 | _RPAGE_RPN44)
+#define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */
#ifdef CONFIG_PPC_64K_PAGES
#include <asm/book3s/64/hash-64k.h>
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index c62f14d0bec1..6666cd366596 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -46,7 +46,7 @@ static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
*/
VM_WARN_ON(page_shift == mmu_psize_defs[MMU_PAGE_1G].shift);
if (page_shift == mmu_psize_defs[MMU_PAGE_2M].shift)
- return __pte(pte_val(entry) | _PAGE_LARGE);
+ return __pte(pte_val(entry) | R_PAGE_LARGE);
else
return entry;
}
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 52d8d1e4b772..6981a52b3887 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -39,6 +39,7 @@
/* Bits in the SLB VSID word */
#define SLB_VSID_SHIFT 12
+#define SLB_VSID_SHIFT_256M SLB_VSID_SHIFT
#define SLB_VSID_SHIFT_1T 24
#define SLB_VSID_SSIZE_SHIFT 62
#define SLB_VSID_B ASM_CONST(0xc000000000000000)
@@ -408,7 +409,7 @@ static inline unsigned long hpt_vpn(unsigned long ea,
static inline unsigned long hpt_hash(unsigned long vpn,
unsigned int shift, int ssize)
{
- int mask;
+ unsigned long mask;
unsigned long hash, vsid;
/* VPN_SHIFT can be atmost 12 */
@@ -491,13 +492,14 @@ extern void slb_set_size(u16 size);
* We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
* from mmu context id and effective segment id of the address.
*
- * For user processes max context id is limited to ((1ul << 19) - 5)
- * for kernel space, we use the top 4 context ids to map address as below
+ * For user processes max context id is limited to MAX_USER_CONTEXT.
+
+ * For kernel space, we use context ids 1-4 to map addresses as below:
* NOTE: each context only support 64TB now.
- * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ * 0x00001 - [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x00002 - [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x00003 - [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x00004 - [ 0xf000000000000000 - 0xf0003fffffffffff ]
*
* The proto-VSIDs are then scrambled into real VSIDs with the
* multiplicative hash:
@@ -511,20 +513,28 @@ extern void slb_set_size(u16 size);
* robust scattering in the hash table (at least based on some initial
* results).
*
- * We also consider VSID 0 special. We use VSID 0 for slb entries mapping
- * bad address. This enables us to consolidate bad address handling in
- * hash_page.
+ * We use VSID 0 to indicate an invalid VSID. The means we can't use context id
+ * 0, because a context id of 0 and an EA of 0 gives a proto-VSID of 0, which
+ * will produce a VSID of 0.
*
* We also need to avoid the last segment of the last context, because that
* would give a protovsid of 0x1fffffffff. That will result in a VSID 0
- * because of the modulo operation in vsid scramble. But the vmemmap
- * (which is what uses region 0xf) will never be close to 64TB in size
- * (it's 56 bytes per page of system memory).
+ * because of the modulo operation in vsid scramble.
*/
+/*
+ * Max Va bits we support as of now is 68 bits. We want 19 bit
+ * context ID.
+ * Restrictions:
+ * GPU has restrictions of not able to access beyond 128TB
+ * (47 bit effective address). We also cannot do more than 20bit PID.
+ * For p4 and p5 which can only do 65 bit VA, we restrict our CONTEXT_BITS
+ * to 16 bits (ie, we can only have 2^16 pids at the same time).
+ */
+#define VA_BITS 68
#define CONTEXT_BITS 19
-#define ESID_BITS 18
-#define ESID_BITS_1T 6
+#define ESID_BITS (VA_BITS - (SID_SHIFT + CONTEXT_BITS))
+#define ESID_BITS_1T (VA_BITS - (SID_SHIFT_1T + CONTEXT_BITS))
#define ESID_BITS_MASK ((1 << ESID_BITS) - 1)
#define ESID_BITS_1T_MASK ((1 << ESID_BITS_1T) - 1)
@@ -532,63 +542,70 @@ extern void slb_set_size(u16 size);
/*
* 256MB segment
* The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
- * available for user + kernel mapping. The top 4 contexts are used for
- * kernel mapping. Each segment contains 2^28 bytes. Each
- * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
- * (19 == 37 + 28 - 46).
+ * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts
+ * 1-4 are used for kernel mapping. Each segment contains 2^28 bytes. Each
+ * context maps 2^49 bytes (512TB).
+ *
+ * We also need to avoid the last segment of the last context, because that
+ * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
+ * because of the modulo operation in vsid scramble.
+ */
+#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2)
+#define MIN_USER_CONTEXT (5)
+
+/* Would be nice to use KERNEL_REGION_ID here */
+#define KERNEL_REGION_CONTEXT_OFFSET (0xc - 1)
+
+/*
+ * For platforms that support on 65bit VA we limit the context bits
*/
-#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 5)
+#define MAX_USER_CONTEXT_65BIT_VA ((ASM_CONST(1) << (65 - (SID_SHIFT + ESID_BITS))) - 2)
/*
* This should be computed such that protovosid * vsid_mulitplier
- * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus
+ * doesn't overflow 64 bits. The vsid_mutliplier should also be
+ * co-prime to vsid_modulus. We also need to make sure that number
+ * of bits in multiplied result (dividend) is less than twice the number of
+ * protovsid bits for our modulus optmization to work.
+ *
+ * The below table shows the current values used.
+ * |-------+------------+----------------------+------------+-------------------|
+ * | | Prime Bits | proto VSID_BITS_65VA | Total Bits | 2* prot VSID_BITS |
+ * |-------+------------+----------------------+------------+-------------------|
+ * | 1T | 24 | 25 | 49 | 50 |
+ * |-------+------------+----------------------+------------+-------------------|
+ * | 256MB | 24 | 37 | 61 | 74 |
+ * |-------+------------+----------------------+------------+-------------------|
+ *
+ * |-------+------------+----------------------+------------+--------------------|
+ * | | Prime Bits | proto VSID_BITS_68VA | Total Bits | 2* proto VSID_BITS |
+ * |-------+------------+----------------------+------------+--------------------|
+ * | 1T | 24 | 28 | 52 | 56 |
+ * |-------+------------+----------------------+------------+--------------------|
+ * | 256MB | 24 | 40 | 64 | 80 |
+ * |-------+------------+----------------------+------------+--------------------|
+ *
*/
#define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */
-#define VSID_BITS_256M (CONTEXT_BITS + ESID_BITS)
-#define VSID_MODULUS_256M ((1UL<<VSID_BITS_256M)-1)
+#define VSID_BITS_256M (VA_BITS - SID_SHIFT)
+#define VSID_BITS_65_256M (65 - SID_SHIFT)
+/*
+ * Modular multiplicative inverse of VSID_MULTIPLIER under modulo VSID_MODULUS
+ */
+#define VSID_MULINV_256M ASM_CONST(665548017062)
#define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */
-#define VSID_BITS_1T (CONTEXT_BITS + ESID_BITS_1T)
-#define VSID_MODULUS_1T ((1UL<<VSID_BITS_1T)-1)
-
+#define VSID_BITS_1T (VA_BITS - SID_SHIFT_1T)
+#define VSID_BITS_65_1T (65 - SID_SHIFT_1T)
+#define VSID_MULINV_1T ASM_CONST(209034062)
+/* 1TB VSID reserved for VRMA */
+#define VRMA_VSID 0x1ffffffUL
#define USER_VSID_RANGE (1UL << (ESID_BITS + SID_SHIFT))
-/*
- * This macro generates asm code to compute the VSID scramble
- * function. Used in slb_allocate() and do_stab_bolted. The function
- * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
- *
- * rt = register containing the proto-VSID and into which the
- * VSID will be stored
- * rx = scratch register (clobbered)
- *
- * - rt and rx must be different registers
- * - The answer will end up in the low VSID_BITS bits of rt. The higher
- * bits may contain other garbage, so you may need to mask the
- * result.
- */
-#define ASM_VSID_SCRAMBLE(rt, rx, size) \
- lis rx,VSID_MULTIPLIER_##size@h; \
- ori rx,rx,VSID_MULTIPLIER_##size@l; \
- mulld rt,rt,rx; /* rt = rt * MULTIPLIER */ \
- \
- srdi rx,rt,VSID_BITS_##size; \
- clrldi rt,rt,(64-VSID_BITS_##size); \
- add rt,rt,rx; /* add high and low bits */ \
- /* NOTE: explanation based on VSID_BITS_##size = 36 \
- * Now, r3 == VSID (mod 2^36-1), and lies between 0 and \
- * 2^36-1+2^28-1. That in particular means that if r3 >= \
- * 2^36-1, then r3+1 has the 2^36 bit set. So, if r3+1 has \
- * the bit clear, r3 already has the answer we want, if it \
- * doesn't, the answer is the low 36 bits of r3+1. So in all \
- * cases the answer is the low 36 bits of (r3 + ((r3+1) >> 36))*/\
- addi rx,rt,1; \
- srdi rx,rx,VSID_BITS_##size; /* extract 2^VSID_BITS bit */ \
- add rt,rt,rx
-
/* 4 bits per slice and we have one slice per 1TB */
-#define SLICE_ARRAY_SIZE (H_PGTABLE_RANGE >> 41)
+#define SLICE_ARRAY_SIZE (H_PGTABLE_RANGE >> 41)
+#define TASK_SLICE_ARRAY_SZ(x) ((x)->context.addr_limit >> 41)
#ifndef __ASSEMBLY__
@@ -634,7 +651,7 @@ static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
#define vsid_scramble(protovsid, size) \
((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size))
-#else /* 1 */
+/* simplified form avoiding mod operation */
#define vsid_scramble(protovsid, size) \
({ \
unsigned long x; \
@@ -642,6 +659,21 @@ static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \
(x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \
})
+
+#else /* 1 */
+static inline unsigned long vsid_scramble(unsigned long protovsid,
+ unsigned long vsid_multiplier, int vsid_bits)
+{
+ unsigned long vsid;
+ unsigned long vsid_modulus = ((1UL << vsid_bits) - 1);
+ /*
+ * We have same multipler for both 256 and 1T segements now
+ */
+ vsid = protovsid * vsid_multiplier;
+ vsid = (vsid >> vsid_bits) + (vsid & vsid_modulus);
+ return (vsid + ((vsid + 1) >> vsid_bits)) & vsid_modulus;
+}
+
#endif /* 1 */
/* Returns the segment size indicator for a user address */
@@ -656,36 +688,56 @@ static inline int user_segment_size(unsigned long addr)
static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
int ssize)
{
+ unsigned long va_bits = VA_BITS;
+ unsigned long vsid_bits;
+ unsigned long protovsid;
+
/*
* Bad address. We return VSID 0 for that
*/
if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
return 0;
- if (ssize == MMU_SEGSIZE_256M)
- return vsid_scramble((context << ESID_BITS)
- | ((ea >> SID_SHIFT) & ESID_BITS_MASK), 256M);
- return vsid_scramble((context << ESID_BITS_1T)
- | ((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK), 1T);
+ if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
+ va_bits = 65;
+
+ if (ssize == MMU_SEGSIZE_256M) {
+ vsid_bits = va_bits - SID_SHIFT;
+ protovsid = (context << ESID_BITS) |
+ ((ea >> SID_SHIFT) & ESID_BITS_MASK);
+ return vsid_scramble(protovsid, VSID_MULTIPLIER_256M, vsid_bits);
+ }
+ /* 1T segment */
+ vsid_bits = va_bits - SID_SHIFT_1T;
+ protovsid = (context << ESID_BITS_1T) |
+ ((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK);
+ return vsid_scramble(protovsid, VSID_MULTIPLIER_1T, vsid_bits);
}
/*
* This is only valid for addresses >= PAGE_OFFSET
- *
- * For kernel space, we use the top 4 context ids to map address as below
- * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ]
*/
static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
{
unsigned long context;
+ if (!is_kernel_addr(ea))
+ return 0;
+
/*
- * kernel take the top 4 context from the available range
+ * For kernel space, we use context ids 1-4 to map the address space as
+ * below:
+ *
+ * 0x00001 - [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x00002 - [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x00003 - [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x00004 - [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ *
+ * So we can compute the context from the region (top nibble) by
+ * subtracting 11, or 0xc - 1.
*/
- context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1;
+ context = (ea >> 60) - KERNEL_REGION_CONTEXT_OFFSET;
+
return get_vsid(context, ea, ssize);
}
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 805d4105e9bb..77529a3e3811 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -65,6 +65,8 @@ extern struct patb_entry *partition_tb;
* MAX_USER_CONTEXT * 16 bytes of space.
*/
#define PRTB_SIZE_SHIFT (CONTEXT_BITS + 4)
+#define PRTB_ENTRIES (1ul << CONTEXT_BITS)
+
/*
* Power9 currently only support 64K partition table size.
*/
@@ -73,13 +75,20 @@ extern struct patb_entry *partition_tb;
typedef unsigned long mm_context_id_t;
struct spinlock;
+/* Maximum possible number of NPUs in a system. */
+#define NV_MAX_NPUS 8
+
typedef struct {
mm_context_id_t id;
u16 user_psize; /* page size index */
+ /* NPU NMMU context */
+ struct npu_context *npu_context;
+
#ifdef CONFIG_PPC_MM_SLICES
u64 low_slices_psize; /* SLB page size encodings */
unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
+ unsigned long addr_limit;
#else
u16 sllp; /* SLB page size encoding */
#endif
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 1eeeb72c7015..85bc9875c3be 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1,15 +1,19 @@
#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
#define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
+#include <asm-generic/5level-fixup.h>
+
#ifndef __ASSEMBLY__
#include <linux/mmdebug.h>
#endif
+
/*
* Common bits between hash and Radix page table
*/
#define _PAGE_BIT_SWAP_TYPE 0
#define _PAGE_RO 0
+#define _PAGE_SHARED 0
#define _PAGE_EXEC 0x00001 /* execute permission */
#define _PAGE_WRITE 0x00002 /* write access allowed */
@@ -34,21 +38,47 @@
#define _RPAGE_RSV3 0x0400000000000000UL
#define _RPAGE_RSV4 0x0200000000000000UL
-#ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SOFT_DIRTY _RPAGE_SW3 /* software: software dirty tracking */
-#else
-#define _PAGE_SOFT_DIRTY 0x00000
-#endif
-#define _PAGE_SPECIAL _RPAGE_SW2 /* software: special page */
+#define _PAGE_PTE 0x4000000000000000UL /* distinguishes PTEs from pointers */
+#define _PAGE_PRESENT 0x8000000000000000UL /* pte contains a translation */
/*
- * For P9 DD1 only, we need to track whether the pte's huge.
+ * Top and bottom bits of RPN which can be used by hash
+ * translation mode, because we expect them to be zero
+ * otherwise.
*/
-#define _PAGE_LARGE _RPAGE_RSV1
+#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 _PAGE_PTE (1ul << 62) /* distinguishes PTEs from pointers */
-#define _PAGE_PRESENT (1ul << 63) /* pte contains a translation */
+/*
+ * Max physical address bit we will use for now.
+ *
+ * This is mostly a hardware limitation and for now Power9 has
+ * a 51 bit limit.
+ *
+ * This is different from the number of physical bit required to address
+ * the last byte of memory. That is defined by MAX_PHYSMEM_BITS.
+ * MAX_PHYSMEM_BITS is a linux limitation imposed by the maximum
+ * number of sections we can support (SECTIONS_SHIFT).
+ *
+ * This is different from Radix page table limitation above and
+ * should always be less than that. The limit is done such that
+ * we can overload the bits between _RPAGE_PA_MAX and _PAGE_PA_MAX
+ * for hash linux page table specific bits.
+ *
+ * In order to be compatible with future hardware generations we keep
+ * some offsets and limit this for now to 53
+ */
+#define _PAGE_PA_MAX 53
+
+#define _PAGE_SOFT_DIRTY _RPAGE_SW3 /* software: software dirty tracking */
+#define _PAGE_SPECIAL _RPAGE_SW2 /* software: special page */
/*
* Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
* Instead of fixing all of them, add an alternate define which
@@ -56,10 +86,11 @@
*/
#define _PAGE_NO_CACHE _PAGE_TOLERANT
/*
- * We support 57 bit real address in pte. Clear everything above 57, and
- * every thing below PAGE_SHIFT;
+ * We support _RPAGE_PA_MAX bit real address in pte. On the linux side
+ * we are limited by _PAGE_PA_MAX. Clear everything above _PAGE_PA_MAX
+ * and every thing below PAGE_SHIFT;
*/
-#define PTE_RPN_MASK (((1UL << 57) - 1) & (PAGE_MASK))
+#define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK))
/*
* set of bits not changed in pmd_modify. Even though we have hash specific bits
* in here, on radix we expect them to be zero.
@@ -202,10 +233,6 @@ extern unsigned long __pte_frag_nr;
extern unsigned long __pte_frag_size_shift;
#define PTE_FRAG_SIZE_SHIFT __pte_frag_size_shift
#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT)
-/*
- * Pgtable size used by swapper, init in asm code
- */
-#define MAX_PGD_TABLE_SIZE (sizeof(pgd_t) << RADIX_PGD_INDEX_SIZE)
#define PTRS_PER_PTE (1 << PTE_INDEX_SIZE)
#define PTRS_PER_PMD (1 << PMD_INDEX_SIZE)
@@ -347,23 +374,58 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
__r; \
})
+static inline int __pte_write(pte_t pte)
+{
+ return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+ /*
+ * Saved write ptes are prot none ptes that doesn't have
+ * privileged bit sit. We mark prot none as one which has
+ * present and pviliged bit set and RWX cleared. To mark
+ * protnone which used to have _PAGE_WRITE set we clear
+ * the privileged bit.
+ */
+ return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+}
+#else
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+ return false;
+}
+#endif
+
+static inline int pte_write(pte_t pte)
+{
+ return __pte_write(pte) || pte_savedwrite(pte);
+}
+
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
- if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
- return;
-
- pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+ if (__pte_write(*ptep))
+ pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+ else if (unlikely(pte_savedwrite(*ptep)))
+ pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
}
static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
- return;
-
- pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+ /*
+ * We should not find protnone for hugetlb, but this complete the
+ * interface.
+ */
+ if (__pte_write(*ptep))
+ pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+ else if (unlikely(pte_savedwrite(*ptep)))
+ pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
}
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
@@ -397,11 +459,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
pte_update(mm, addr, ptep, ~0UL, 0, 0);
}
-static inline int pte_write(pte_t pte)
-{
- return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
-}
-
static inline int pte_dirty(pte_t pte)
{
return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
@@ -465,19 +522,12 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
VM_BUG_ON(!pte_protnone(pte));
return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
}
-
-#define pte_savedwrite pte_savedwrite
-static inline bool pte_savedwrite(pte_t pte)
+#else
+#define pte_clear_savedwrite pte_clear_savedwrite
+static inline pte_t pte_clear_savedwrite(pte_t pte)
{
- /*
- * Saved write ptes are prot none ptes that doesn't have
- * privileged bit sit. We mark prot none as one which has
- * present and pviliged bit set and RWX cleared. To mark
- * protnone which used to have _PAGE_WRITE set we clear
- * the privileged bit.
- */
- VM_BUG_ON(!pte_protnone(pte));
- return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+ VM_WARN_ON(1);
+ return __pte(pte_val(pte) & ~_PAGE_WRITE);
}
#endif /* CONFIG_NUMA_BALANCING */
@@ -506,6 +556,8 @@ static inline unsigned long pte_pfn(pte_t pte)
/* Generic modifiers for PTE bits */
static inline pte_t pte_wrprotect(pte_t pte)
{
+ if (unlikely(pte_savedwrite(pte)))
+ return pte_clear_savedwrite(pte);
return __pte(pte_val(pte) & ~_PAGE_WRITE);
}
@@ -926,6 +978,7 @@ static inline int pmd_protnone(pmd_t pmd)
#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
+#define __pmd_write(pmd) __pte_write(pmd_pte(pmd))
#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd))
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -982,11 +1035,10 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp)
{
-
- if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
- return;
-
- pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+ if (__pmd_write((*pmdp)))
+ pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+ else if (unlikely(pmd_savedwrite(*pmdp)))
+ pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
}
static inline int pmd_trans_huge(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 9e0bb7cd6e22..ac16d1943022 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -11,6 +11,12 @@
#include <asm/book3s/64/radix-4k.h>
#endif
+/*
+ * For P9 DD1 only, we need to track whether the pte's huge.
+ */
+#define R_PAGE_LARGE _RPAGE_RSV1
+
+
#ifndef __ASSEMBLY__
#include <asm/book3s/64/tlbflush-radix.h>
#include <asm/cpu_has_feature.h>
@@ -252,7 +258,7 @@ static inline int radix__pmd_trans_huge(pmd_t pmd)
static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
{
if (cpu_has_feature(CPU_FTR_POWER9_DD1))
- return __pmd(pmd_val(pmd) | _PAGE_PTE | _PAGE_LARGE);
+ return __pmd(pmd_val(pmd) | _PAGE_PTE | R_PAGE_LARGE);
return __pmd(pmd_val(pmd) | _PAGE_PTE);
}
static inline void radix__pmdp_huge_split_prepare(struct vm_area_struct *vma,
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 3a39283333c3..f2c562a0a427 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -85,12 +85,12 @@
} \
} while (0)
-#define __WARN_TAINT(taint) do { \
+#define __WARN_FLAGS(flags) do { \
__asm__ __volatile__( \
"1: twi 31,0,0\n" \
_EMIT_BUG_ENTRY \
: : "i" (__FILE__), "i" (__LINE__), \
- "i" (BUGFLAG_TAINT(taint)), \
+ "i" (BUGFLAG_WARNING|(flags)), \
"i" (sizeof(struct bug_entry))); \
} while (0)
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 4e63787dc3be..842124b199b5 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -112,7 +112,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
#ifdef __powerpc64__
res += (__force u64)addend;
- return (__force __wsum)((u32)res + (res >> 32));
+ return (__force __wsum) from64to32(res);
#else
asm("addc %0,%0,%1;"
"addze %0,%0;"
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 8ab937771068..abef812de7f8 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -12,6 +12,8 @@
#include <asm/types.h>
#include <asm/ppc-opcode.h>
+#include <linux/string.h>
+#include <linux/kallsyms.h>
/* Flags for create_branch:
* "b" == create_branch(addr, target, 0);
@@ -99,6 +101,45 @@ static inline unsigned long ppc_global_function_entry(void *func)
#endif
}
+/*
+ * Wrapper around kallsyms_lookup() to return function entry address:
+ * - For ABIv1, we lookup the dot variant.
+ * - For ABIv2, we return the local entry point.
+ */
+static inline unsigned long ppc_kallsyms_lookup_name(const char *name)
+{
+ unsigned long addr;
+#ifdef PPC64_ELF_ABI_v1
+ /* check for dot variant */
+ char dot_name[1 + KSYM_NAME_LEN];
+ bool dot_appended = false;
+
+ if (strnlen(name, KSYM_NAME_LEN) >= KSYM_NAME_LEN)
+ return 0;
+
+ if (name[0] != '.') {
+ dot_name[0] = '.';
+ dot_name[1] = '\0';
+ strlcat(dot_name, name, sizeof(dot_name));
+ dot_appended = true;
+ } else {
+ dot_name[0] = '\0';
+ strlcat(dot_name, name, sizeof(dot_name));
+ }
+ addr = kallsyms_lookup_name(dot_name);
+ if (!addr && dot_appended)
+ /* Let's try the original non-dot symbol lookup */
+ addr = kallsyms_lookup_name(name);
+#elif defined(PPC64_ELF_ABI_v2)
+ addr = kallsyms_lookup_name(name);
+ if (addr)
+ addr = ppc_function_entry((void *)addr);
+#else
+ addr = kallsyms_lookup_name(name);
+#endif
+ return addr;
+}
+
#ifdef CONFIG_PPC64
/*
* Some instruction encodings commonly used in dynamic ftracing
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index fd321eb423cb..52586f9956bb 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -2,13 +2,39 @@
#define _ASM_POWERPC_CPUIDLE_H
#ifdef CONFIG_PPC_POWERNV
-/* Used in powernv idle state management */
+/* Thread state used in powernv idle state management */
#define PNV_THREAD_RUNNING 0
#define PNV_THREAD_NAP 1
#define PNV_THREAD_SLEEP 2
#define PNV_THREAD_WINKLE 3
-#define PNV_CORE_IDLE_LOCK_BIT 0x100
-#define PNV_CORE_IDLE_THREAD_BITS 0x0FF
+
+/*
+ * Core state used in powernv idle for POWER8.
+ *
+ * The lock bit synchronizes updates to the state, as well as parts of the
+ * sleep/wake code (see kernel/idle_book3s.S).
+ *
+ * Bottom 8 bits track the idle state of each thread. Bit is cleared before
+ * the thread executes an idle instruction (nap/sleep/winkle).
+ *
+ * Then there is winkle tracking. A core does not lose complete state
+ * until every thread is in winkle. So the winkle count field counts the
+ * number of threads in winkle (small window of false positives is okay
+ * around the sleep/wake, so long as there are no false negatives).
+ *
+ * When the winkle count reaches 8 (the COUNT_ALL_BIT becomes set), then
+ * the THREAD_WINKLE_BITS are set, which indicate which threads have not
+ * yet woken from the winkle state.
+ */
+#define PNV_CORE_IDLE_LOCK_BIT 0x10000000
+
+#define PNV_CORE_IDLE_WINKLE_COUNT 0x00010000
+#define PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT 0x00080000
+#define PNV_CORE_IDLE_WINKLE_COUNT_BITS 0x000F0000
+#define PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT 8
+#define PNV_CORE_IDLE_THREAD_WINKLE_BITS 0x0000FF00
+
+#define PNV_CORE_IDLE_THREAD_BITS 0x000000FF
/*
* ============================ NOTE =================================
@@ -46,6 +72,7 @@ extern u32 pnv_fastsleep_workaround_at_exit[];
extern u64 pnv_first_deep_stop_state;
+unsigned long pnv_cpu_offline(unsigned int cpu);
int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags);
static inline void report_invalid_psscr_val(u64 psscr_val, int err)
{
@@ -70,8 +97,8 @@ static inline void report_invalid_psscr_val(u64 psscr_val, int err)
std r0,0(r1); \
ptesync; \
ld r0,0(r1); \
-1: cmpd cr0,r0,r0; \
- bne 1b; \
+236: cmpd cr0,r0,r0; \
+ bne 236b; \
IDLE_INST; \
#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index ab68d0ee7725..1f6847b107e4 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -471,10 +471,11 @@ enum {
CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
CPU_FTR_DSCR | CPU_FTR_SAO | \
CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
- CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
+ 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_ARCH_300)
-#define CPU_FTRS_POWER9_DD1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1)
+#define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
+ (~CPU_FTR_SAO))
#define CPU_FTRS_CELL (CPU_FTR_USE_TB | 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/dbell.h b/arch/powerpc/include/asm/dbell.h
index 378167377065..f70cbfe0ec04 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -35,33 +35,53 @@ enum ppc_dbell {
#ifdef CONFIG_PPC_BOOK3S
#define PPC_DBELL_MSGTYPE PPC_DBELL_SERVER
-#define SPRN_DOORBELL_CPUTAG SPRN_TIR
-#define PPC_DBELL_TAG_MASK 0x7f
static inline void _ppc_msgsnd(u32 msg)
{
- if (cpu_has_feature(CPU_FTR_HVMODE))
- __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
- else
- __asm__ __volatile__ (PPC_MSGSNDP(%0) : : "r" (msg));
+ __asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGSND(%1), PPC_MSGSNDP(%1), %0)
+ : : "i" (CPU_FTR_HVMODE), "r" (msg));
+}
+
+/* sync before sending message */
+static inline void ppc_msgsnd_sync(void)
+{
+ __asm__ __volatile__ ("sync" : : : "memory");
+}
+
+/* sync after taking message interrupt */
+static inline void ppc_msgsync(void)
+{
+ /* sync is not required when taking messages from the same core */
+ __asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGSYNC " ; lwsync", "", %0)
+ : : "i" (CPU_FTR_HVMODE|CPU_FTR_ARCH_300));
}
#else /* CONFIG_PPC_BOOK3S */
#define PPC_DBELL_MSGTYPE PPC_DBELL
-#define SPRN_DOORBELL_CPUTAG SPRN_PIR
-#define PPC_DBELL_TAG_MASK 0x3fff
static inline void _ppc_msgsnd(u32 msg)
{
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
}
+/* sync before sending message */
+static inline void ppc_msgsnd_sync(void)
+{
+ __asm__ __volatile__ ("sync" : : : "memory");
+}
+
+/* sync after taking message interrupt */
+static inline void ppc_msgsync(void)
+{
+}
+
#endif /* CONFIG_PPC_BOOK3S */
-extern void doorbell_cause_ipi(int cpu, unsigned long data);
+extern void doorbell_global_ipi(int cpu);
+extern void doorbell_core_ipi(int cpu);
+extern int doorbell_try_core_ipi(int cpu);
extern void doorbell_exception(struct pt_regs *regs);
-extern void doorbell_setup_this_cpu(void);
static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
{
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
index 86308f177f2d..5d5af3fddfd8 100644
--- a/arch/powerpc/include/asm/debug.h
+++ b/arch/powerpc/include/asm/debug.h
@@ -8,8 +8,6 @@
struct pt_regs;
-extern struct dentry *powerpc_debugfs_root;
-
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
extern int (*__debugger)(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/debugfs.h b/arch/powerpc/include/asm/debugfs.h
new file mode 100644
index 000000000000..4f3b39f3e3d2
--- /dev/null
+++ b/arch/powerpc/include/asm/debugfs.h
@@ -0,0 +1,17 @@
+#ifndef _ASM_POWERPC_DEBUGFS_H
+#define _ASM_POWERPC_DEBUGFS_H
+
+/*
+ * Copyright 2017, Michael Ellerman, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/debugfs.h>
+
+extern struct dentry *powerpc_debugfs_root;
+
+#endif /* _ASM_POWERPC_DEBUGFS_H */
diff --git a/arch/powerpc/include/asm/disassemble.h b/arch/powerpc/include/asm/disassemble.h
index 4852e849128b..c0a55050f70f 100644
--- a/arch/powerpc/include/asm/disassemble.h
+++ b/arch/powerpc/include/asm/disassemble.h
@@ -87,6 +87,11 @@ static inline unsigned int get_oc(u32 inst)
return (inst >> 11) & 0x7fff;
}
+static inline unsigned int get_tx_or_sx(u32 inst)
+{
+ return (inst) & 0x1;
+}
+
#define IS_XFORM(inst) (get_op(inst) == 31)
#define IS_DSFORM(inst) (get_op(inst) >= 56)
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 93b9b84568e8..09bde6e34f5d 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -144,8 +144,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
#define ARCH_DLINFO_CACHE_GEOMETRY \
NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size); \
NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i)); \
- NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size); \
- NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i)); \
+ NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1d.size); \
+ NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1d)); \
NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size); \
NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2)); \
NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size); \
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 14752eee3d0c..183d73b6ed99 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -167,17 +167,14 @@ BEGIN_FTR_SECTION_NESTED(943) \
std ra,offset(r13); \
END_FTR_SECTION_NESTED(ftr,ftr,943)
-#define EXCEPTION_PROLOG_0_PACA(area) \
+#define EXCEPTION_PROLOG_0(area) \
+ GET_PACA(r13); \
std r9,area+EX_R9(r13); /* save r9 */ \
OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); \
HMT_MEDIUM; \
std r10,area+EX_R10(r13); /* save r10 - r12 */ \
OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
-#define EXCEPTION_PROLOG_0(area) \
- GET_PACA(r13); \
- EXCEPTION_PROLOG_0_PACA(area)
-
#define __EXCEPTION_PROLOG_1(area, extra, vec) \
OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR); \
OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR); \
@@ -203,17 +200,26 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define EXCEPTION_PROLOG_PSERIES_1(label, h) \
__EXCEPTION_PROLOG_PSERIES_1(label, h)
+/* _NORI variant keeps MSR_RI clear */
+#define __EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) \
+ ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \
+ xori r10,r10,MSR_RI; /* Clear MSR_RI */ \
+ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \
+ LOAD_HANDLER(r12,label) \
+ mtspr SPRN_##h##SRR0,r12; \
+ mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \
+ mtspr SPRN_##h##SRR1,r10; \
+ h##rfid; \
+ b . /* prevent speculative execution */
+
+#define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) \
+ __EXCEPTION_PROLOG_PSERIES_1_NORI(label, h)
+
#define EXCEPTION_PROLOG_PSERIES(area, label, h, extra, vec) \
EXCEPTION_PROLOG_0(area); \
EXCEPTION_PROLOG_1(area, extra, vec); \
EXCEPTION_PROLOG_PSERIES_1(label, h);
-/* Have the PACA in r13 already */
-#define EXCEPTION_PROLOG_PSERIES_PACA(area, label, h, extra, vec) \
- EXCEPTION_PROLOG_0_PACA(area); \
- EXCEPTION_PROLOG_1(area, extra, vec); \
- EXCEPTION_PROLOG_PSERIES_1(label, h);
-
#define __KVMTEST(h, n) \
lbz r10,HSTATE_IN_GUEST(r13); \
cmpwi r10,0; \
@@ -236,9 +242,9 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
mtctr reg; \
bctr
-#define BRANCH_LINK_TO_FAR(reg, label) \
- __LOAD_FAR_HANDLER(reg, label); \
- mtctr reg; \
+#define BRANCH_LINK_TO_FAR(label) \
+ __LOAD_FAR_HANDLER(r12, label); \
+ mtctr r12; \
bctrl
/*
@@ -256,27 +262,25 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
ld r9,area+EX_R9(r13); \
bctr
-#define BRANCH_TO_KVM(reg, label) \
- __LOAD_FAR_HANDLER(reg, label); \
- mtctr reg; \
- bctr
-
#else
#define BRANCH_TO_COMMON(reg, label) \
b label
-#define BRANCH_LINK_TO_FAR(reg, label) \
+#define BRANCH_LINK_TO_FAR(label) \
bl label
-#define BRANCH_TO_KVM(reg, label) \
- b label
-
#define __BRANCH_TO_KVM_EXIT(area, label) \
ld r9,area+EX_R9(r13); \
b label
#endif
+/* Do not enable RI */
+#define EXCEPTION_PROLOG_PSERIES_NORI(area, label, h, extra, vec) \
+ EXCEPTION_PROLOG_0(area); \
+ EXCEPTION_PROLOG_1(area, extra, vec); \
+ EXCEPTION_PROLOG_PSERIES_1_NORI(label, h);
+
#define __KVM_HANDLER(area, h, n) \
BEGIN_FTR_SECTION_NESTED(947) \
@@ -325,6 +329,15 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define NOTEST(n)
+#define EXCEPTION_PROLOG_COMMON_1() \
+ std r9,_CCR(r1); /* save CR in stackframe */ \
+ std r11,_NIP(r1); /* save SRR0 in stackframe */ \
+ std r12,_MSR(r1); /* save SRR1 in stackframe */ \
+ std r10,0(r1); /* make stack chain pointer */ \
+ std r0,GPR0(r1); /* save r0 in stackframe */ \
+ std r10,GPR1(r1); /* save r1 in stackframe */ \
+
+
/*
* The common exception prolog is used for all except a few exceptions
* such as a segment miss on a kernel address. We have to be prepared
@@ -349,12 +362,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
addi r3,r13,area; /* r3 -> where regs are saved*/ \
RESTORE_CTR(r1, area); \
b bad_stack; \
-3: std r9,_CCR(r1); /* save CR in stackframe */ \
- std r11,_NIP(r1); /* save SRR0 in stackframe */ \
- std r12,_MSR(r1); /* save SRR1 in stackframe */ \
- std r10,0(r1); /* make stack chain pointer */ \
- std r0,GPR0(r1); /* save r0 in stackframe */ \
- std r10,GPR1(r1); /* save r1 in stackframe */ \
+3: EXCEPTION_PROLOG_COMMON_1(); \
beq 4f; /* if from kernel mode */ \
ACCOUNT_CPU_USER_ENTRY(r13, r9, r10); \
SAVE_PPR(area, r9, r10); \
@@ -522,7 +530,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label) \
EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec); \
- EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV)
+ EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV)
/*
* Our exception common code can be passed various "additions"
@@ -547,26 +555,39 @@ BEGIN_FTR_SECTION \
beql ppc64_runlatch_on_trampoline; \
END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
-#define EXCEPTION_COMMON(trap, label, hdlr, ret, additions) \
- EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \
+#define EXCEPTION_COMMON(area, trap, label, hdlr, ret, additions) \
+ EXCEPTION_PROLOG_COMMON(trap, area); \
/* Volatile regs are potentially clobbered here */ \
additions; \
addi r3,r1,STACK_FRAME_OVERHEAD; \
bl hdlr; \
b ret
+/*
+ * Exception where stack is already set in r1, r1 is saved in r10, and it
+ * continues rather than returns.
+ */
+#define EXCEPTION_COMMON_NORET_STACK(area, trap, label, hdlr, additions) \
+ EXCEPTION_PROLOG_COMMON_1(); \
+ EXCEPTION_PROLOG_COMMON_2(area); \
+ EXCEPTION_PROLOG_COMMON_3(trap); \
+ /* Volatile regs are potentially clobbered here */ \
+ additions; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ bl hdlr
+
#define STD_EXCEPTION_COMMON(trap, label, hdlr) \
- EXCEPTION_COMMON(trap, label, hdlr, ret_from_except, \
- ADD_NVGPRS;ADD_RECONCILE)
+ EXCEPTION_COMMON(PACA_EXGEN, trap, label, hdlr, \
+ ret_from_except, ADD_NVGPRS;ADD_RECONCILE)
/*
* Like STD_EXCEPTION_COMMON, but for exceptions that can occur
* in the idle task and therefore need the special idle handling
* (finish nap and runlatch)
*/
-#define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr) \
- EXCEPTION_COMMON(trap, label, hdlr, ret_from_except_lite, \
- FINISH_NAP;ADD_RECONCILE;RUNLATCH_ON)
+#define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr) \
+ EXCEPTION_COMMON(PACA_EXGEN, trap, label, hdlr, \
+ ret_from_except_lite, FINISH_NAP;ADD_RECONCILE;RUNLATCH_ON)
/*
* When the idle code in power4_idle puts the CPU into NAP mode,
diff --git a/arch/powerpc/include/asm/extable.h b/arch/powerpc/include/asm/extable.h
new file mode 100644
index 000000000000..07cc45cd86d9
--- /dev/null
+++ b/arch/powerpc/include/asm/extable.h
@@ -0,0 +1,29 @@
+#ifndef _ARCH_POWERPC_EXTABLE_H
+#define _ARCH_POWERPC_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative addresses: the first is
+ * the address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out what
+ * to do.
+ *
+ * All the routines below use bits of fixup code that are out of line with the
+ * main instruction path. This means when everything is well, we don't even
+ * have to jump over them. Further, they do not intrude on our cache or tlb
+ * entries.
+ */
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+struct exception_table_entry {
+ int insn;
+ int fixup;
+};
+
+static inline unsigned long extable_fixup(const struct exception_table_entry *x)
+{
+ return (unsigned long)&x->fixup + x->fixup;
+}
+
+#endif
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 0031806475f0..60b91084f33c 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -73,6 +73,8 @@
reg_entry++; \
})
+extern int crashing_cpu;
+
/* Kernel Dump section info */
struct fadump_section {
__be32 request_flag;
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index ddf54f5bbdd1..2de2319b99e2 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -66,6 +66,9 @@ label##5: \
#define END_FTR_SECTION(msk, val) \
END_FTR_SECTION_NESTED(msk, val, 97)
+#define END_FTR_SECTION_NESTED_IFSET(msk, label) \
+ END_FTR_SECTION_NESTED((msk), (msk), label)
+
#define END_FTR_SECTION_IFSET(msk) END_FTR_SECTION((msk), (msk))
#define END_FTR_SECTION_IFCLR(msk) END_FTR_SECTION((msk), 0)
diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h
index 5067048daad4..86eb87382031 100644
--- a/arch/powerpc/include/asm/head-64.h
+++ b/arch/powerpc/include/asm/head-64.h
@@ -213,6 +213,7 @@ name:
USE_TEXT_SECTION(); \
.balign IFETCH_ALIGN_BYTES; \
.global name; \
+ _ASM_NOKPROBE_SYMBOL(name); \
DEFINE_FIXED_SYMBOL(name); \
name:
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 3cc12a86ef5d..d73755fafbb0 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -377,16 +377,6 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...);
long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...);
long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...);
-/* For hcall instrumentation. One structure per-hcall, per-CPU */
-struct hcall_stats {
- unsigned long num_calls; /* number of calls (on this CPU) */
- unsigned long tb_total; /* total wall time (mftb) of calls. */
- unsigned long purr_total; /* total cpu time (PURR) of calls. */
- unsigned long tb_start;
- unsigned long purr_start;
-};
-#define HCALL_STAT_ARRAY_SIZE ((MAX_HCALL_OPCODE >> 2) + 1)
-
struct hvcall_mpp_data {
unsigned long entitled_mem;
unsigned long mapped_mem;
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 5ed292431b5b..422f99cf9924 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -25,8 +25,6 @@ extern struct pci_dev *isa_bridge_pcidev;
#endif
#include <linux/device.h>
-#include <linux/io.h>
-
#include <linux/compiler.h>
#include <asm/page.h>
#include <asm/byteorder.h>
@@ -192,24 +190,8 @@ DEF_MMIO_OUT_D(out_le32, 32, stw);
#endif /* __BIG_ENDIAN */
-/*
- * Cache inhibitied accessors for use in real mode, you don't want to use these
- * unless you know what you're doing.
- *
- * NB. These use the cpu byte ordering.
- */
-DEF_MMIO_OUT_X(out_rm8, 8, stbcix);
-DEF_MMIO_OUT_X(out_rm16, 16, sthcix);
-DEF_MMIO_OUT_X(out_rm32, 32, stwcix);
-DEF_MMIO_IN_X(in_rm8, 8, lbzcix);
-DEF_MMIO_IN_X(in_rm16, 16, lhzcix);
-DEF_MMIO_IN_X(in_rm32, 32, lwzcix);
-
#ifdef __powerpc64__
-DEF_MMIO_OUT_X(out_rm64, 64, stdcix);
-DEF_MMIO_IN_X(in_rm64, 64, ldcix);
-
#ifdef __BIG_ENDIAN__
DEF_MMIO_OUT_D(out_be64, 64, std);
DEF_MMIO_IN_D(in_be64, 64, ld);
@@ -242,35 +224,6 @@ static inline void out_be64(volatile u64 __iomem *addr, u64 val)
#endif
#endif /* __powerpc64__ */
-
-/*
- * Simple Cache inhibited accessors
- * Unlike the DEF_MMIO_* macros, these don't include any h/w memory
- * barriers, callers need to manage memory barriers on their own.
- * These can only be used in hypervisor real mode.
- */
-
-static inline u32 _lwzcix(unsigned long addr)
-{
- u32 ret;
-
- __asm__ __volatile__("lwzcix %0,0, %1"
- : "=r" (ret) : "r" (addr) : "memory");
- return ret;
-}
-
-static inline void _stbcix(u64 addr, u8 val)
-{
- __asm__ __volatile__("stbcix %0,0,%1"
- : : "r" (val), "r" (addr) : "memory");
-}
-
-static inline void _stwcix(u64 addr, u32 val)
-{
- __asm__ __volatile__("stwcix %0,0,%1"
- : : "r" (val), "r" (addr) : "memory");
-}
-
/*
* Low level IO stream instructions are defined out of line for now
*/
@@ -417,15 +370,64 @@ static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr)
}
/*
- * Real mode version of the above. stdcix is only supposed to be used
- * in hypervisor real mode as per the architecture spec.
+ * Real mode versions of the above. Those instructions are only supposed
+ * to be used in hypervisor real mode as per the architecture spec.
*/
+static inline void __raw_rm_writeb(u8 val, volatile void __iomem *paddr)
+{
+ __asm__ __volatile__("stbcix %0,0,%1"
+ : : "r" (val), "r" (paddr) : "memory");
+}
+
+static inline void __raw_rm_writew(u16 val, volatile void __iomem *paddr)
+{
+ __asm__ __volatile__("sthcix %0,0,%1"
+ : : "r" (val), "r" (paddr) : "memory");
+}
+
+static inline void __raw_rm_writel(u32 val, volatile void __iomem *paddr)
+{
+ __asm__ __volatile__("stwcix %0,0,%1"
+ : : "r" (val), "r" (paddr) : "memory");
+}
+
static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
{
__asm__ __volatile__("stdcix %0,0,%1"
: : "r" (val), "r" (paddr) : "memory");
}
+static inline u8 __raw_rm_readb(volatile void __iomem *paddr)
+{
+ u8 ret;
+ __asm__ __volatile__("lbzcix %0,0, %1"
+ : "=r" (ret) : "r" (paddr) : "memory");
+ return ret;
+}
+
+static inline u16 __raw_rm_readw(volatile void __iomem *paddr)
+{
+ u16 ret;
+ __asm__ __volatile__("lhzcix %0,0, %1"
+ : "=r" (ret) : "r" (paddr) : "memory");
+ return ret;
+}
+
+static inline u32 __raw_rm_readl(volatile void __iomem *paddr)
+{
+ u32 ret;
+ __asm__ __volatile__("lwzcix %0,0, %1"
+ : "=r" (ret) : "r" (paddr) : "memory");
+ return ret;
+}
+
+static inline u64 __raw_rm_readq(volatile void __iomem *paddr)
+{
+ u64 ret;
+ __asm__ __volatile__("ldcix %0,0, %1"
+ : "=r" (ret) : "r" (paddr) : "memory");
+ return ret;
+}
#endif /* __powerpc64__ */
/*
@@ -757,6 +759,8 @@ extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size,
extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size);
#define ioremap_nocache(addr, size) ioremap((addr), (size))
#define ioremap_uc(addr, size) ioremap((addr), (size))
+#define ioremap_cache(addr, size) \
+ ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL))
extern void iounmap(volatile void __iomem *addr);
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 2c1d50792944..8a8ce220d7d0 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -64,6 +64,11 @@ struct iommu_table_ops {
long index,
unsigned long *hpa,
enum dma_data_direction *direction);
+ /* Real mode */
+ int (*exchange_rm)(struct iommu_table *tbl,
+ long index,
+ unsigned long *hpa,
+ enum dma_data_direction *direction);
#endif
void (*clear)(struct iommu_table *tbl,
long index, long npages);
@@ -114,6 +119,7 @@ struct iommu_table {
struct list_head it_group_list;/* List of iommu_table_group_link */
unsigned long *it_userspace; /* userspace view of the table */
struct iommu_table_ops *it_ops;
+ struct kref it_kref;
};
#define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
@@ -146,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev)
extern int dma_iommu_dma_supported(struct device *dev, u64 mask);
-/* Frees table for an individual device node */
-extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
+extern struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl);
+extern int iommu_tce_table_put(struct iommu_table *tbl);
/* Initializes an iommu_table based in values set in the passed-in
* structure
@@ -208,6 +214,8 @@ extern void iommu_del_device(struct device *dev);
extern int __init tce_iommu_bus_notifier_init(void);
extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
unsigned long *hpa, enum dma_data_direction *direction);
+extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+ unsigned long *hpa, enum dma_data_direction *direction);
#else
static inline void iommu_register_group(struct iommu_table_group *table_group,
int pci_domain_number,
@@ -288,11 +296,21 @@ static inline void iommu_restore(void)
#endif
/* The API to support IOMMU operations for VFIO */
-extern int iommu_tce_clear_param_check(struct iommu_table *tbl,
- unsigned long ioba, unsigned long tce_value,
- unsigned long npages);
-extern int iommu_tce_put_param_check(struct iommu_table *tbl,
- unsigned long ioba, unsigned long tce);
+extern int iommu_tce_check_ioba(unsigned long page_shift,
+ unsigned long offset, unsigned long size,
+ unsigned long ioba, unsigned long npages);
+extern int iommu_tce_check_gpa(unsigned long page_shift,
+ unsigned long gpa);
+
+#define iommu_tce_clear_param_check(tbl, ioba, tce_value, npages) \
+ (iommu_tce_check_ioba((tbl)->it_page_shift, \
+ (tbl)->it_offset, (tbl)->it_size, \
+ (ioba), (npages)) || (tce_value))
+#define iommu_tce_put_param_check(tbl, ioba, gpa) \
+ (iommu_tce_check_ioba((tbl)->it_page_shift, \
+ (tbl)->it_offset, (tbl)->it_size, \
+ (ioba), 1) || \
+ iommu_tce_check_gpa((tbl)->it_page_shift, (gpa)))
extern void iommu_flush_tce(struct iommu_table *tbl);
extern int iommu_take_ownership(struct iommu_table *tbl);
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 0503c98b2117..a83821f33ea3 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -61,59 +61,6 @@ extern kprobe_opcode_t optprobe_template_end[];
#define MAX_OPTINSN_SIZE (optprobe_template_end - optprobe_template_entry)
#define RELATIVEJUMP_SIZE sizeof(kprobe_opcode_t) /* 4 bytes */
-#ifdef PPC64_ELF_ABI_v2
-/* PPC64 ABIv2 needs local entry point */
-#define kprobe_lookup_name(name, addr) \
-{ \
- addr = (kprobe_opcode_t *)kallsyms_lookup_name(name); \
- if (addr) \
- addr = (kprobe_opcode_t *)ppc_function_entry(addr); \
-}
-#elif defined(PPC64_ELF_ABI_v1)
-/*
- * 64bit powerpc ABIv1 uses function descriptors:
- * - Check for the dot variant of the symbol first.
- * - If that fails, try looking up the symbol provided.
- *
- * This ensures we always get to the actual symbol and not the descriptor.
- * Also handle <module:symbol> format.
- */
-#define kprobe_lookup_name(name, addr) \
-{ \
- char dot_name[MODULE_NAME_LEN + 1 + KSYM_NAME_LEN]; \
- const char *modsym; \
- bool dot_appended = false; \
- if ((modsym = strchr(name, ':')) != NULL) { \
- modsym++; \
- if (*modsym != '\0' && *modsym != '.') { \
- /* Convert to <module:.symbol> */ \
- strncpy(dot_name, name, modsym - name); \
- dot_name[modsym - name] = '.'; \
- dot_name[modsym - name + 1] = '\0'; \
- strncat(dot_name, modsym, \
- sizeof(dot_name) - (modsym - name) - 2);\
- dot_appended = true; \
- } else { \
- dot_name[0] = '\0'; \
- strncat(dot_name, name, sizeof(dot_name) - 1); \
- } \
- } else if (name[0] != '.') { \
- dot_name[0] = '.'; \
- dot_name[1] = '\0'; \
- strncat(dot_name, name, KSYM_NAME_LEN - 2); \
- dot_appended = true; \
- } else { \
- dot_name[0] = '\0'; \
- strncat(dot_name, name, KSYM_NAME_LEN - 1); \
- } \
- addr = (kprobe_opcode_t *)kallsyms_lookup_name(dot_name); \
- if (!addr && dot_appended) { \
- /* Let's try the original non-dot symbol lookup */ \
- addr = (kprobe_opcode_t *)kallsyms_lookup_name(name); \
- } \
-}
-#endif
-
#define flush_insn_slot(p) do { } while (0)
#define kretprobe_blacklist_size 0
@@ -156,6 +103,16 @@ extern int kprobe_exceptions_notify(struct notifier_block *self,
extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
extern int kprobe_handler(struct pt_regs *regs);
extern int kprobe_post_handler(struct pt_regs *regs);
+#ifdef CONFIG_KPROBES_ON_FTRACE
+extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb);
+#else
+static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ return 0;
+}
+#endif
#else
static inline int kprobe_handler(struct pt_regs *regs) { return 0; }
static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; }
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index d9b48f5bb606..d55c7f881ce7 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -49,8 +49,6 @@ static inline bool kvm_is_radix(struct kvm *kvm)
#define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */
#endif
-#define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */
-
/*
* We use a lock bit in HPTE dword 0 to synchronize updates and
* accesses to each HPTE, and another bit to indicate non-present
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index d318d432caa9..b148496ffe36 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -110,7 +110,9 @@ struct kvmppc_host_state {
u8 ptid;
struct kvm_vcpu *kvm_vcpu;
struct kvmppc_vcore *kvm_vcore;
- unsigned long xics_phys;
+ void __iomem *xics_phys;
+ void __iomem *xive_tima_phys;
+ void __iomem *xive_tima_virt;
u32 saved_xirr;
u64 dabr;
u64 host_mmcr[7]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 7bba8f415627..9c51ac4b8f36 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -45,9 +45,6 @@
#define __KVM_HAVE_ARCH_INTC_INITIALIZED
-#ifdef CONFIG_KVM_MMIO
-#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
-#endif
#define KVM_HALT_POLL_NS_DEFAULT 10000 /* 10 us */
/* These values are internal and can be increased later */
@@ -191,6 +188,13 @@ struct kvmppc_pginfo {
atomic_t refcnt;
};
+struct kvmppc_spapr_tce_iommu_table {
+ struct rcu_head rcu;
+ struct list_head next;
+ struct iommu_table *tbl;
+ struct kref kref;
+};
+
struct kvmppc_spapr_tce_table {
struct list_head list;
struct kvm *kvm;
@@ -199,12 +203,19 @@ struct kvmppc_spapr_tce_table {
u32 page_shift;
u64 offset; /* in pages */
u64 size; /* window size in pages */
+ struct list_head iommu_tables;
struct page *pages[0];
};
/* XICS components, defined in book3s_xics.c */
struct kvmppc_xics;
struct kvmppc_icp;
+extern struct kvm_device_ops kvm_xics_ops;
+
+/* XIVE components, defined in book3s_xive.c */
+struct kvmppc_xive;
+struct kvmppc_xive_vcpu;
+extern struct kvm_device_ops kvm_xive_ops;
struct kvmppc_passthru_irqmap;
@@ -293,6 +304,7 @@ struct kvm_arch {
#endif
#ifdef CONFIG_KVM_XICS
struct kvmppc_xics *xics;
+ struct kvmppc_xive *xive;
struct kvmppc_passthru_irqmap *pimap;
#endif
struct kvmppc_ops *kvm_ops;
@@ -345,6 +357,7 @@ struct kvmppc_pte {
bool may_read : 1;
bool may_write : 1;
bool may_execute : 1;
+ unsigned long wimg;
u8 page_size; /* MMU_PAGE_xxx */
};
@@ -421,7 +434,7 @@ struct kvmppc_passthru_irqmap {
#define KVMPPC_IRQ_DEFAULT 0
#define KVMPPC_IRQ_MPIC 1
-#define KVMPPC_IRQ_XICS 2
+#define KVMPPC_IRQ_XICS 2 /* Includes a XIVE option */
#define MMIO_HPTE_CACHE_SIZE 4
@@ -441,8 +454,28 @@ struct mmio_hpte_cache {
unsigned int index;
};
+#define KVMPPC_VSX_COPY_NONE 0
+#define KVMPPC_VSX_COPY_WORD 1
+#define KVMPPC_VSX_COPY_DWORD 2
+#define KVMPPC_VSX_COPY_DWORD_LOAD_DUMP 3
+
struct openpic;
+/* W0 and W1 of a XIVE thread management context */
+union xive_tma_w01 {
+ struct {
+ u8 nsr;
+ u8 cppr;
+ u8 ipb;
+ u8 lsmfb;
+ u8 ack;
+ u8 inc;
+ u8 age;
+ u8 pipr;
+ };
+ __be64 w01;
+};
+
struct kvm_vcpu_arch {
ulong host_stack;
u32 host_pid;
@@ -644,6 +677,21 @@ struct kvm_vcpu_arch {
u8 io_gpr; /* GPR used as IO source/target */
u8 mmio_host_swabbed;
u8 mmio_sign_extend;
+ /* conversion between single and double precision */
+ u8 mmio_sp64_extend;
+ /*
+ * Number of simulations for vsx.
+ * If we use 2*8bytes to simulate 1*16bytes,
+ * then the number should be 2 and
+ * mmio_vsx_copy_type=KVMPPC_VSX_COPY_DWORD.
+ * If we use 4*4bytes to simulate 1*16bytes,
+ * the number should be 4 and
+ * mmio_vsx_copy_type=KVMPPC_VSX_COPY_WORD.
+ */
+ u8 mmio_vsx_copy_nums;
+ u8 mmio_vsx_offset;
+ u8 mmio_vsx_copy_type;
+ u8 mmio_vsx_tx_sx_enabled;
u8 osi_needed;
u8 osi_enabled;
u8 papr_enabled;
@@ -688,6 +736,10 @@ struct kvm_vcpu_arch {
struct openpic *mpic; /* KVM_IRQ_MPIC */
#ifdef CONFIG_KVM_XICS
struct kvmppc_icp *icp; /* XICS presentation controller */
+ struct kvmppc_xive_vcpu *xive_vcpu; /* XIVE virtual CPU data */
+ __be32 xive_cam_word; /* Cooked W2 in proper endian with valid bit */
+ u32 xive_pushed; /* Is the VP pushed on the physical CPU ? */
+ union xive_tma_w01 xive_saved_state; /* W0..1 of XIVE thread state */
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -732,6 +784,8 @@ struct kvm_vcpu_arch {
};
#define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
+#define VCPU_VSX_FPR(vcpu, i, j) ((vcpu)->arch.fp.fpr[i][j])
+#define VCPU_VSX_VR(vcpu, i) ((vcpu)->arch.vr.vr[i])
/* Values for vcpu->arch.state */
#define KVMPPC_VCPU_NOTREADY 0
@@ -745,6 +799,7 @@ struct kvm_vcpu_arch {
#define KVM_MMIO_REG_FPR 0x0020
#define KVM_MMIO_REG_QPR 0x0040
#define KVM_MMIO_REG_FQPR 0x0060
+#define KVM_MMIO_REG_VSX 0x0080
#define __KVM_HAVE_ARCH_WQP
#define __KVM_HAVE_CREATE_DEVICE
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index dd11c4c8c56a..e0d88c38602b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -78,9 +78,15 @@ extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int rt, unsigned int bytes,
int is_default_endian);
+extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rt, unsigned int bytes,
+ int is_default_endian, int mmio_sign_extend);
extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
u64 val, unsigned int bytes,
int is_default_endian);
+extern int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ int rs, unsigned int bytes,
+ int is_default_endian);
extern int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
enum instruction_type type, u32 *inst);
@@ -132,6 +138,9 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
+extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu);
extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu);
extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
@@ -164,13 +173,19 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
struct kvm_memory_slot *memslot, unsigned long porder);
extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+ struct iommu_group *grp);
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+ struct iommu_group *grp);
extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce_64 *args);
extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
- struct kvm_vcpu *vcpu, unsigned long liobn);
-extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
- unsigned long ioba, unsigned long npages);
+ struct kvm *kvm, unsigned long liobn);
+#define kvmppc_ioba_validate(stt, ioba, npages) \
+ (iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \
+ (stt)->size, (ioba), (npages)) ? \
+ H_PARAMETER : H_SUCCESS)
extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt,
unsigned long tce);
extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
@@ -225,6 +240,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq);
extern int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp);
extern int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu);
extern void kvmppc_rtas_tokens_free(struct kvm *kvm);
+
extern int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server,
u32 priority);
extern int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server,
@@ -240,6 +256,7 @@ union kvmppc_one_reg {
u64 dval;
vector128 vval;
u64 vsxval[2];
+ u32 vsx32val[4];
struct {
u64 addr;
u64 length;
@@ -409,7 +426,15 @@ struct openpic;
extern void kvm_cma_reserve(void) __init;
static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
{
- paca[cpu].kvm_hstate.xics_phys = addr;
+ paca[cpu].kvm_hstate.xics_phys = (void __iomem *)addr;
+}
+
+static inline void kvmppc_set_xive_tima(int cpu,
+ unsigned long phys_addr,
+ void __iomem *virt_addr)
+{
+ paca[cpu].kvm_hstate.xive_tima_phys = (void __iomem *)phys_addr;
+ paca[cpu].kvm_hstate.xive_tima_virt = virt_addr;
}
static inline u32 kvmppc_get_xics_latch(void)
@@ -442,6 +467,11 @@ static inline void __init kvm_cma_reserve(void)
static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
{}
+static inline void kvmppc_set_xive_tima(int cpu,
+ unsigned long phys_addr,
+ void __iomem *virt_addr)
+{}
+
static inline u32 kvmppc_get_xics_latch(void)
{
return 0;
@@ -478,8 +508,6 @@ extern void kvmppc_free_host_rm_ops(void);
extern void kvmppc_free_pimap(struct kvm *kvm);
extern int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall);
extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu);
-extern int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server);
-extern int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args);
extern int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd);
extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu);
extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
@@ -494,6 +522,10 @@ extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, __be32 xirr,
struct kvmppc_irq_map *irq_map,
struct kvmppc_passthru_irqmap *pimap,
bool *again);
+
+extern int kvmppc_xics_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status);
+
extern int h_ipi_redirect;
#else
static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap(
@@ -507,16 +539,64 @@ static inline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall)
static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
{ return 0; }
static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { }
-static inline int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu,
- unsigned long server)
- { return -EINVAL; }
-static inline int kvm_vm_ioctl_xics_irq(struct kvm *kvm,
- struct kvm_irq_level *args)
- { return -ENOTTY; }
static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
{ return 0; }
#endif
+#ifdef CONFIG_KVM_XIVE
+/*
+ * Below the first "xive" is the "eXternal Interrupt Virtualization Engine"
+ * ie. P9 new interrupt controller, while the second "xive" is the legacy
+ * "eXternal Interrupt Vector Entry" which is the configuration of an
+ * interrupt on the "xics" interrupt controller on P8 and earlier. Those
+ * two function consume or produce a legacy "XIVE" state from the
+ * new "XIVE" interrupt controller.
+ */
+extern int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority);
+extern int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority);
+extern int kvmppc_xive_int_on(struct kvm *kvm, u32 irq);
+extern int kvmppc_xive_int_off(struct kvm *kvm, u32 irq);
+extern void kvmppc_xive_init_module(void);
+extern void kvmppc_xive_exit_module(void);
+
+extern int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu);
+extern void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu);
+extern int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc);
+extern int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc);
+extern u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu);
+extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
+
+extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status);
+#else
+static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority) { return -1; }
+static inline int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority) { return -1; }
+static inline int kvmppc_xive_int_on(struct kvm *kvm, u32 irq) { return -1; }
+static inline int kvmppc_xive_int_off(struct kvm *kvm, u32 irq) { return -1; }
+static inline void kvmppc_xive_init_module(void) { }
+static inline void kvmppc_xive_exit_module(void) { }
+
+static inline int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
+static inline void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
+static inline int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc) { return -ENODEV; }
+static inline int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc) { return -ENODEV; }
+static inline u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu) { return 0; }
+static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { return -ENOENT; }
+
+static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status) { return -ENODEV; }
+#endif /* CONFIG_KVM_XIVE */
+
/*
* Prototypes for functions called only from assembler code.
* Having prototypes reduces sparse errors.
@@ -554,6 +634,8 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
unsigned long slb_v, unsigned int status, bool data);
unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu);
+unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu);
+unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
unsigned long mfrr);
int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 5011b69107a7..f90b22c722e1 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -173,6 +173,8 @@ struct machdep_calls {
/* Called after scan and before resource survey */
void (*pcibios_fixup_phb)(struct pci_controller *hose);
+ resource_size_t (*pcibios_default_alignment)(void);
+
#ifdef CONFIG_PCI_IOV
void (*pcibios_fixup_sriov)(struct pci_dev *pdev);
resource_size_t (*pcibios_iov_resource_alignment)(struct pci_dev *, int resno);
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index f97d8cb6bdf6..81eff8631434 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -24,48 +24,6 @@
#include <linux/bitops.h>
-/*
- * Machine Check bits on power7 and power8
- */
-#define P7_SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) /* P8 too */
-
-/* SRR1 bits for machine check (On Power7 and Power8) */
-#define P7_SRR1_MC_IFETCH(srr1) ((srr1) & PPC_BITMASK(43, 45)) /* P8 too */
-
-#define P7_SRR1_MC_IFETCH_UE (0x1 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_PARITY (0x2 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_MULTIHIT (0x3 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_BOTH (0x4 << PPC_BITLSHIFT(45))
-#define P7_SRR1_MC_IFETCH_TLB_MULTIHIT (0x5 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_UE_TLB_RELOAD (0x6 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL (0x7 << PPC_BITLSHIFT(45))
-
-/* SRR1 bits for machine check (On Power8) */
-#define P8_SRR1_MC_IFETCH_ERAT_MULTIHIT (0x4 << PPC_BITLSHIFT(45))
-
-/* DSISR bits for machine check (On Power7 and Power8) */
-#define P7_DSISR_MC_UE (PPC_BIT(48)) /* P8 too */
-#define P7_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) /* P8 too */
-#define P7_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) /* P8 too */
-#define P7_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) /* P8 too */
-#define P7_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) /* P8 too */
-#define P7_DSISR_MC_SLB_MULTIHIT (PPC_BIT(56)) /* P8 too */
-#define P7_DSISR_MC_SLB_MULTIHIT_PARITY (PPC_BIT(57)) /* P8 too */
-
-/*
- * DSISR bits for machine check (Power8) in addition to above.
- * Secondary DERAT Multihit
- */
-#define P8_DSISR_MC_ERAT_MULTIHIT_SEC (PPC_BIT(54))
-
-/* SLB error bits */
-#define P7_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_ERAT_MULTIHIT | \
- P7_DSISR_MC_SLB_PARITY_MFSLB | \
- P7_DSISR_MC_SLB_MULTIHIT | \
- P7_DSISR_MC_SLB_MULTIHIT_PARITY)
-
-#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \
- P8_DSISR_MC_ERAT_MULTIHIT_SEC)
enum MCE_Version {
MCE_V1 = 1,
};
@@ -93,6 +51,9 @@ enum MCE_ErrorType {
MCE_ERROR_TYPE_SLB = 2,
MCE_ERROR_TYPE_ERAT = 3,
MCE_ERROR_TYPE_TLB = 4,
+ MCE_ERROR_TYPE_USER = 5,
+ MCE_ERROR_TYPE_RA = 6,
+ MCE_ERROR_TYPE_LINK = 7,
};
enum MCE_UeErrorType {
@@ -121,6 +82,32 @@ enum MCE_TlbErrorType {
MCE_TLB_ERROR_MULTIHIT = 2,
};
+enum MCE_UserErrorType {
+ MCE_USER_ERROR_INDETERMINATE = 0,
+ MCE_USER_ERROR_TLBIE = 1,
+};
+
+enum MCE_RaErrorType {
+ MCE_RA_ERROR_INDETERMINATE = 0,
+ MCE_RA_ERROR_IFETCH = 1,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 3,
+ MCE_RA_ERROR_LOAD = 4,
+ MCE_RA_ERROR_STORE = 5,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 6,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 7,
+ MCE_RA_ERROR_LOAD_STORE_FOREIGN = 8,
+};
+
+enum MCE_LinkErrorType {
+ MCE_LINK_ERROR_INDETERMINATE = 0,
+ MCE_LINK_ERROR_IFETCH_TIMEOUT = 1,
+ MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT = 2,
+ MCE_LINK_ERROR_LOAD_TIMEOUT = 3,
+ MCE_LINK_ERROR_STORE_TIMEOUT = 4,
+ MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT = 5,
+};
+
struct machine_check_event {
enum MCE_Version version:8; /* 0x00 */
uint8_t in_use; /* 0x01 */
@@ -166,6 +153,30 @@ struct machine_check_event {
uint64_t effective_address;
uint8_t reserved_2[16];
} tlb_error;
+
+ struct {
+ enum MCE_UserErrorType user_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } user_error;
+
+ struct {
+ enum MCE_RaErrorType ra_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } ra_error;
+
+ struct {
+ enum MCE_LinkErrorType link_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } link_error;
} u;
};
@@ -176,8 +187,12 @@ struct mce_error_info {
enum MCE_SlbErrorType slb_error_type:8;
enum MCE_EratErrorType erat_error_type:8;
enum MCE_TlbErrorType tlb_error_type:8;
+ enum MCE_UserErrorType user_error_type:8;
+ enum MCE_RaErrorType ra_error_type:8;
+ enum MCE_LinkErrorType link_error_type:8;
} u;
- uint8_t reserved[2];
+ enum MCE_Severity severity:8;
+ enum MCE_Initiator initiator:8;
};
#define MAX_MC_EVT 100
@@ -192,7 +207,8 @@ extern void save_mce_event(struct pt_regs *regs, long handled,
extern int get_mce_event(struct machine_check_event *mce, bool release);
extern void release_mce_event(void);
extern void machine_check_queue_event(void);
-extern void machine_check_print_event_info(struct machine_check_event *evt);
+extern void machine_check_print_event_info(struct machine_check_event *evt,
+ bool user_mode);
extern uint64_t get_mce_fault_addr(struct machine_check_event *evt);
#endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index b62a8d43a06c..7ca8d8e80ffa 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -229,11 +229,6 @@ typedef struct {
unsigned int id;
unsigned int active;
unsigned long vdso_base;
-#ifdef CONFIG_PPC_MM_SLICES
- u64 low_slices_psize; /* SLB page size encodings */
- u64 high_slices_psize; /* 4 bits per slice for now */
- u16 user_psize; /* page size index */
-#endif
#ifdef CONFIG_PPC_64K_PAGES
/* for 4K PTE fragment support */
void *pte_frag;
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 065e762fae85..78260409dc9c 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -29,6 +29,10 @@
*/
/*
+ * Support for 68 bit VA space. We added that from ISA 2.05
+ */
+#define MMU_FTR_68_BIT_VA ASM_CONST(0x00002000)
+/*
* Kernel read only support.
* We added the ppp value 0b110 in ISA 2.04.
*/
@@ -109,10 +113,10 @@
#define MMU_FTRS_POWER4 MMU_FTRS_DEFAULT_HPTE_ARCH_V2
#define MMU_FTRS_PPC970 MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA
#define MMU_FTRS_POWER5 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
-#define MMU_FTRS_POWER6 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO
-#define MMU_FTRS_POWER7 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO
-#define MMU_FTRS_POWER8 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO
-#define MMU_FTRS_POWER9 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO
+#define MMU_FTRS_POWER6 MMU_FTRS_POWER5 | MMU_FTR_KERNEL_RO | MMU_FTR_68_BIT_VA
+#define MMU_FTRS_POWER7 MMU_FTRS_POWER6
+#define MMU_FTRS_POWER8 MMU_FTRS_POWER6
+#define MMU_FTRS_POWER9 MMU_FTRS_POWER6
#define MMU_FTRS_CELL MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
MMU_FTR_CI_LARGE_PAGE
#define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
@@ -136,7 +140,7 @@ enum {
MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL |
MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE |
MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA |
- MMU_FTR_KERNEL_RO |
+ MMU_FTR_KERNEL_RO | MMU_FTR_68_BIT_VA |
#ifdef CONFIG_PPC_RADIX_MMU
MMU_FTR_TYPE_RADIX |
#endif
@@ -290,7 +294,10 @@ static inline bool early_radix_enabled(void)
#define MMU_PAGE_16G 14
#define MMU_PAGE_64G 15
-/* N.B. we need to change the type of hpte_page_sizes if this gets to be > 16 */
+/*
+ * N.B. we need to change the type of hpte_page_sizes if this gets to be > 16
+ * Also we need to change he type of mm_context.low/high_slices_psize.
+ */
#define MMU_PAGE_COUNT 16
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b9e3f0aca261..da7e9432fa8f 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -29,10 +29,14 @@ extern void mm_iommu_init(struct mm_struct *mm);
extern void mm_iommu_cleanup(struct mm_struct *mm);
extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
unsigned long ua, unsigned long size);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
+ struct mm_struct *mm, unsigned long ua, unsigned long size);
extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
unsigned long ua, unsigned long entries);
extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
unsigned long ua, unsigned long *hpa);
+extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+ unsigned long ua, unsigned long *hpa);
extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
#endif
@@ -51,7 +55,8 @@ static inline void switch_mmu_context(struct mm_struct *prev,
return switch_slb(tsk, next);
}
-extern int __init_new_context(void);
+extern int hash__alloc_context_id(void);
+extern void hash__reserve_context_id(int id);
extern void __destroy_context(int context_id);
static inline void mmu_context_init(void) { }
#else
@@ -70,8 +75,9 @@ extern void drop_cop(unsigned long acop, struct mm_struct *mm);
* switch_mm is the entry point called from the architecture independent
* code in kernel/sched/core.c
*/
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
- struct task_struct *tsk)
+static inline void switch_mm_irqs_off(struct mm_struct *prev,
+ struct mm_struct *next,
+ struct task_struct *tsk)
{
/* Mark this context has been used on the new CPU */
if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next)))
@@ -110,6 +116,18 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
switch_mmu_context(prev, next, tsk);
}
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+ struct task_struct *tsk)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ switch_mm_irqs_off(prev, next, tsk);
+ local_irq_restore(flags);
+}
+#define switch_mm_irqs_off switch_mm_irqs_off
+
+
#define deactivate_mm(tsk,mm) do { } while (0)
/*
@@ -163,11 +181,5 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
/* by default, allow everything */
return true;
}
-
-static inline bool arch_pte_access_permitted(pte_t pte, bool write)
-{
- /* by default, allow everything */
- return true;
-}
#endif /* __KERNEL__ */
#endif /* __ASM_POWERPC_MMU_CONTEXT_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index ba9921bf202e..5134ade2e850 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -1,6 +1,7 @@
#ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H
#define _ASM_POWERPC_NOHASH_32_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
index d0db98793dd8..9f4de0a1035e 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
@@ -1,5 +1,8 @@
#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
#define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
+
+#include <asm-generic/5level-fixup.h>
+
/*
* Entries per page directory level. The PTE level must use a 64b record
* for each page table entry. The PMD and PGD level use a 32b record for
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
index 55b28ef3409a..1facb584dd29 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
@@ -1,6 +1,7 @@
#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
#define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index c7f927e67d14..f0ff384d4ca5 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -88,11 +88,6 @@
#include <asm/nohash/pte-book3e.h>
#include <asm/pte-common.h>
-#ifdef CONFIG_PPC_MM_SLICES
-#define HAVE_ARCH_UNMAPPED_AREA
-#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
-#endif /* CONFIG_PPC_MM_SLICES */
-
#ifndef __ASSEMBLY__
/* pte_clear moved to later in this file */
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 0cd8a3852763..e5805ad78e12 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -230,7 +230,7 @@ static inline int hugepd_ok(hugepd_t hpd)
return ((hpd_val(hpd) & 0x4) != 0);
#else
/* We clear the top bit to indicate hugepd */
- return ((hpd_val(hpd) & PD_HUGE) == 0);
+ return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
#endif
}
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index a0aa285869b5..cb3e6242a78c 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -40,6 +40,8 @@
#define OPAL_I2C_ARBT_LOST -22
#define OPAL_I2C_NACK_RCVD -23
#define OPAL_I2C_STOP_ERR -24
+#define OPAL_XIVE_PROVISIONING -31
+#define OPAL_XIVE_FREE_ACTIVE -32
/* API Tokens (in r0) */
#define OPAL_INVALID_CALL -1
@@ -168,7 +170,27 @@
#define OPAL_INT_SET_MFRR 125
#define OPAL_PCI_TCE_KILL 126
#define OPAL_NMMU_SET_PTCR 127
-#define OPAL_LAST 127
+#define OPAL_XIVE_RESET 128
+#define OPAL_XIVE_GET_IRQ_INFO 129
+#define OPAL_XIVE_GET_IRQ_CONFIG 130
+#define OPAL_XIVE_SET_IRQ_CONFIG 131
+#define OPAL_XIVE_GET_QUEUE_INFO 132
+#define OPAL_XIVE_SET_QUEUE_INFO 133
+#define OPAL_XIVE_DONATE_PAGE 134
+#define OPAL_XIVE_ALLOCATE_VP_BLOCK 135
+#define OPAL_XIVE_FREE_VP_BLOCK 136
+#define OPAL_XIVE_GET_VP_INFO 137
+#define OPAL_XIVE_SET_VP_INFO 138
+#define OPAL_XIVE_ALLOCATE_IRQ 139
+#define OPAL_XIVE_FREE_IRQ 140
+#define OPAL_XIVE_SYNC 141
+#define OPAL_XIVE_DUMP 142
+#define OPAL_XIVE_RESERVED3 143
+#define OPAL_XIVE_RESERVED4 144
+#define OPAL_NPU_INIT_CONTEXT 146
+#define OPAL_NPU_DESTROY_CONTEXT 147
+#define OPAL_NPU_MAP_LPAR 148
+#define OPAL_LAST 148
/* Device tree flags */
@@ -928,6 +950,59 @@ enum {
OPAL_PCI_TCE_KILL_ALL,
};
+/* The xive operation mode indicates the active "API" and
+ * corresponds to the "mode" parameter of the opal_xive_reset()
+ * call
+ */
+enum {
+ OPAL_XIVE_MODE_EMU = 0,
+ OPAL_XIVE_MODE_EXPL = 1,
+};
+
+/* Flags for OPAL_XIVE_GET_IRQ_INFO */
+enum {
+ OPAL_XIVE_IRQ_TRIGGER_PAGE = 0x00000001,
+ OPAL_XIVE_IRQ_STORE_EOI = 0x00000002,
+ OPAL_XIVE_IRQ_LSI = 0x00000004,
+ OPAL_XIVE_IRQ_SHIFT_BUG = 0x00000008,
+ OPAL_XIVE_IRQ_MASK_VIA_FW = 0x00000010,
+ OPAL_XIVE_IRQ_EOI_VIA_FW = 0x00000020,
+};
+
+/* Flags for OPAL_XIVE_GET/SET_QUEUE_INFO */
+enum {
+ OPAL_XIVE_EQ_ENABLED = 0x00000001,
+ OPAL_XIVE_EQ_ALWAYS_NOTIFY = 0x00000002,
+ OPAL_XIVE_EQ_ESCALATE = 0x00000004,
+};
+
+/* Flags for OPAL_XIVE_GET/SET_VP_INFO */
+enum {
+ OPAL_XIVE_VP_ENABLED = 0x00000001,
+};
+
+/* "Any chip" replacement for chip ID for allocation functions */
+enum {
+ OPAL_XIVE_ANY_CHIP = 0xffffffff,
+};
+
+/* Xive sync options */
+enum {
+ /* This bits are cumulative, arg is a girq */
+ XIVE_SYNC_EAS = 0x00000001, /* Sync irq source */
+ XIVE_SYNC_QUEUE = 0x00000002, /* Sync irq target */
+};
+
+/* Dump options */
+enum {
+ XIVE_DUMP_TM_HYP = 0,
+ XIVE_DUMP_TM_POOL = 1,
+ XIVE_DUMP_TM_OS = 2,
+ XIVE_DUMP_TM_USER = 3,
+ XIVE_DUMP_VP = 4,
+ XIVE_DUMP_EMU_STATE = 5,
+};
+
#endif /* __ASSEMBLY__ */
#endif /* __OPAL_API_H */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 1ff03a6da76e..588fb1c23af9 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -29,6 +29,11 @@ extern struct device_node *opal_node;
/* API functions */
int64_t opal_invalid_call(void);
+int64_t opal_npu_destroy_context(uint64_t phb_id, uint64_t pid, uint64_t bdf);
+int64_t opal_npu_init_context(uint64_t phb_id, int pasid, uint64_t msr,
+ uint64_t bdf);
+int64_t opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid,
+ uint64_t lpcr);
int64_t opal_console_write(int64_t term_number, __be64 *length,
const uint8_t *buffer);
int64_t opal_console_read(int64_t term_number, __be64 *length,
@@ -226,6 +231,42 @@ int64_t opal_pci_tce_kill(uint64_t phb_id, uint32_t kill_type,
uint32_t pe_num, uint32_t tce_size,
uint64_t dma_addr, uint32_t npages);
int64_t opal_nmmu_set_ptcr(uint64_t chip_id, uint64_t ptcr);
+int64_t opal_xive_reset(uint64_t version);
+int64_t opal_xive_get_irq_info(uint32_t girq,
+ __be64 *out_flags,
+ __be64 *out_eoi_page,
+ __be64 *out_trig_page,
+ __be32 *out_esb_shift,
+ __be32 *out_src_chip);
+int64_t opal_xive_get_irq_config(uint32_t girq, __be64 *out_vp,
+ uint8_t *out_prio, __be32 *out_lirq);
+int64_t opal_xive_set_irq_config(uint32_t girq, uint64_t vp, uint8_t prio,
+ uint32_t lirq);
+int64_t opal_xive_get_queue_info(uint64_t vp, uint32_t prio,
+ __be64 *out_qpage,
+ __be64 *out_qsize,
+ __be64 *out_qeoi_page,
+ __be32 *out_escalate_irq,
+ __be64 *out_qflags);
+int64_t opal_xive_set_queue_info(uint64_t vp, uint32_t prio,
+ uint64_t qpage,
+ uint64_t qsize,
+ uint64_t qflags);
+int64_t opal_xive_donate_page(uint32_t chip_id, uint64_t addr);
+int64_t opal_xive_alloc_vp_block(uint32_t alloc_order);
+int64_t opal_xive_free_vp_block(uint64_t vp);
+int64_t opal_xive_get_vp_info(uint64_t vp,
+ __be64 *out_flags,
+ __be64 *out_cam_value,
+ __be64 *out_report_cl_pair,
+ __be32 *out_chip_id);
+int64_t opal_xive_set_vp_info(uint64_t vp,
+ uint64_t flags,
+ uint64_t report_cl_pair);
+int64_t opal_xive_allocate_irq(uint32_t chip_id);
+int64_t opal_xive_free_irq(uint32_t girq);
+int64_t opal_xive_sync(uint32_t type, uint32_t id);
+int64_t opal_xive_dump(uint32_t type, uint32_t id);
/* Internal functions */
extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 708c3e592eeb..1c09f8fe2ee8 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -99,7 +99,6 @@ struct paca_struct {
*/
/* used for most interrupts/exceptions */
u64 exgen[13] __attribute__((aligned(0x80)));
- u64 exmc[13]; /* used for machine checks */
u64 exslb[13]; /* used for SLB/segment table misses
* on the linear mapping */
/* SLB related definitions */
@@ -139,6 +138,7 @@ struct paca_struct {
#ifdef CONFIG_PPC_MM_SLICES
u64 mm_ctx_low_slices_psize;
unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE];
+ unsigned long addr_limit;
#else
u16 mm_ctx_user_psize;
u16 mm_ctx_sllp;
@@ -172,17 +172,31 @@ struct paca_struct {
u8 thread_mask;
/* Mask to denote subcore sibling threads */
u8 subcore_sibling_mask;
+ /*
+ * Pointer to an array which contains pointer
+ * to the sibling threads' paca.
+ */
+ struct paca_struct **thread_sibling_pacas;
#endif
+#ifdef CONFIG_PPC_STD_MMU_64
+ /* Non-maskable exceptions that are not performance critical */
+ u64 exnmi[13]; /* used for system reset (nmi) */
+ u64 exmc[13]; /* used for machine checks */
+#endif
#ifdef CONFIG_PPC_BOOK3S_64
- /* Exclusive emergency stack pointer for machine check exception. */
+ /* Exclusive stacks for system reset and machine check exception. */
+ void *nmi_emergency_sp;
void *mc_emergency_sp;
+
+ u16 in_nmi; /* In nmi handler */
+
/*
* Flag to check whether we are in machine check early handler
* and already using emergency stack.
*/
u16 in_mce;
- u8 hmi_event_available; /* HMI event is available */
+ u8 hmi_event_available; /* HMI event is available */
#endif
/* Stuff for accurate time accounting */
@@ -206,23 +220,7 @@ struct paca_struct {
#endif
};
-#ifdef CONFIG_PPC_BOOK3S
-static inline void copy_mm_to_paca(mm_context_t *context)
-{
- get_paca()->mm_ctx_id = context->id;
-#ifdef CONFIG_PPC_MM_SLICES
- get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize;
- memcpy(&get_paca()->mm_ctx_high_slices_psize,
- &context->high_slices_psize, SLICE_ARRAY_SIZE);
-#else
- get_paca()->mm_ctx_user_psize = context->user_psize;
- get_paca()->mm_ctx_sllp = context->sllp;
-#endif
-}
-#else
-static inline void copy_mm_to_paca(mm_context_t *context){}
-#endif
-
+extern void copy_mm_to_paca(struct mm_struct *mm);
extern struct paca_struct *paca;
extern void initialise_paca(struct paca_struct *new_paca, int cpu);
extern void setup_paca(struct paca_struct *new_paca);
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 3e83d2a20b6f..c4d9654bd637 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -98,21 +98,7 @@ extern u64 ppc64_pft_size;
#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT)
#define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT)
-/*
- * 1 bit per slice and we have one slice per 1TB
- * Right now we support only 64TB.
- * IF we change this we will have to change the type
- * of high_slices
- */
-#define SLICE_MASK_SIZE 8
-
#ifndef __ASSEMBLY__
-
-struct slice_mask {
- u16 low_slices;
- u64 high_slices;
-};
-
struct mm_struct;
extern unsigned long slice_get_unmapped_area(unsigned long addr,
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 93eded8d3843..c8975dac535f 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -77,12 +77,11 @@ extern int pci_domain_nr(struct pci_bus *bus);
extern int pci_proc_domain(struct pci_bus *bus);
struct vm_area_struct;
-/* Map a range of PCI memory or I/O space for a device into user space */
-int pci_mmap_page_range(struct pci_dev *pdev, struct vm_area_struct *vma,
- enum pci_mmap_state mmap_state, int write_combine);
-/* Tell drivers/pci/proc.c that we have pci_mmap_page_range() */
-#define HAVE_PCI_MMAP 1
+/* Tell drivers/pci/proc.c that we have pci_mmap_page_range() and it does WC */
+#define HAVE_PCI_MMAP 1
+#define arch_can_pci_mmap_io() 1
+#define arch_can_pci_mmap_wc() 1
extern int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val,
size_t count);
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index ae0a23091a9b..723bf48e7494 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -38,6 +38,9 @@ struct power_pmu {
unsigned long *valp);
int (*get_alternatives)(u64 event_id, unsigned int flags,
u64 alt[]);
+ void (*get_mem_data_src)(union perf_mem_data_src *dsrc,
+ u32 flags, struct pt_regs *regs);
+ void (*get_mem_weight)(u64 *weight);
u64 (*bhrb_filter_map)(u64 branch_sample_type);
void (*config_bhrb)(u64 pmu_bhrb_filter);
void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h
index 0e9c2402dd20..f62797702300 100644
--- a/arch/powerpc/include/asm/powernv.h
+++ b/arch/powerpc/include/asm/powernv.h
@@ -11,9 +11,31 @@
#define _ASM_POWERNV_H
#ifdef CONFIG_PPC_POWERNV
+#define NPU2_WRITE 1
extern void powernv_set_nmmu_ptcr(unsigned long ptcr);
+extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
+ unsigned long flags,
+ struct npu_context *(*cb)(struct npu_context *, void *),
+ void *priv);
+extern void pnv_npu2_destroy_context(struct npu_context *context,
+ struct pci_dev *gpdev);
+extern int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea,
+ unsigned long *flags, unsigned long *status,
+ int count);
#else
static inline void powernv_set_nmmu_ptcr(unsigned long ptcr) { }
+static inline struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
+ unsigned long flags,
+ struct npu_context *(*cb)(struct npu_context *, void *),
+ void *priv) { return ERR_PTR(-ENODEV); }
+static inline void pnv_npu2_destroy_context(struct npu_context *context,
+ struct pci_dev *gpdev) { }
+
+static inline int pnv_npu2_handle_fault(struct npu_context *context,
+ uintptr_t *ea, unsigned long *flags,
+ unsigned long *status, int count) {
+ return -ENODEV;
+}
#endif
#endif /* _ASM_POWERNV_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index d99bd442aacb..3a8d278e7421 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -86,32 +86,79 @@
#define OP_TRAP_64 2
#define OP_31_XOP_TRAP 4
+#define OP_31_XOP_LDX 21
#define OP_31_XOP_LWZX 23
+#define OP_31_XOP_LDUX 53
#define OP_31_XOP_DCBST 54
#define OP_31_XOP_LWZUX 55
#define OP_31_XOP_TRAP_64 68
#define OP_31_XOP_DCBF 86
#define OP_31_XOP_LBZX 87
+#define OP_31_XOP_STDX 149
#define OP_31_XOP_STWX 151
+#define OP_31_XOP_STDUX 181
+#define OP_31_XOP_STWUX 183
#define OP_31_XOP_STBX 215
#define OP_31_XOP_LBZUX 119
#define OP_31_XOP_STBUX 247
#define OP_31_XOP_LHZX 279
#define OP_31_XOP_LHZUX 311
#define OP_31_XOP_MFSPR 339
+#define OP_31_XOP_LWAX 341
#define OP_31_XOP_LHAX 343
+#define OP_31_XOP_LWAUX 373
#define OP_31_XOP_LHAUX 375
#define OP_31_XOP_STHX 407
#define OP_31_XOP_STHUX 439
#define OP_31_XOP_MTSPR 467
#define OP_31_XOP_DCBI 470
+#define OP_31_XOP_LDBRX 532
#define OP_31_XOP_LWBRX 534
#define OP_31_XOP_TLBSYNC 566
+#define OP_31_XOP_STDBRX 660
#define OP_31_XOP_STWBRX 662
+#define OP_31_XOP_STFSX 663
+#define OP_31_XOP_STFSUX 695
+#define OP_31_XOP_STFDX 727
+#define OP_31_XOP_STFDUX 759
#define OP_31_XOP_LHBRX 790
+#define OP_31_XOP_LFIWAX 855
+#define OP_31_XOP_LFIWZX 887
#define OP_31_XOP_STHBRX 918
+#define OP_31_XOP_STFIWX 983
+
+/* VSX Scalar Load Instructions */
+#define OP_31_XOP_LXSDX 588
+#define OP_31_XOP_LXSSPX 524
+#define OP_31_XOP_LXSIWAX 76
+#define OP_31_XOP_LXSIWZX 12
+
+/* VSX Scalar Store Instructions */
+#define OP_31_XOP_STXSDX 716
+#define OP_31_XOP_STXSSPX 652
+#define OP_31_XOP_STXSIWX 140
+
+/* VSX Vector Load Instructions */
+#define OP_31_XOP_LXVD2X 844
+#define OP_31_XOP_LXVW4X 780
+
+/* VSX Vector Load and Splat Instruction */
+#define OP_31_XOP_LXVDSX 332
+
+/* VSX Vector Store Instructions */
+#define OP_31_XOP_STXVD2X 972
+#define OP_31_XOP_STXVW4X 908
+
+#define OP_31_XOP_LFSX 535
+#define OP_31_XOP_LFSUX 567
+#define OP_31_XOP_LFDX 599
+#define OP_31_XOP_LFDUX 631
#define OP_LWZ 32
+#define OP_STFS 52
+#define OP_STFSU 53
+#define OP_STFD 54
+#define OP_STFDU 55
#define OP_LD 58
#define OP_LWZU 33
#define OP_LBZ 34
@@ -127,6 +174,17 @@
#define OP_LHAU 43
#define OP_STH 44
#define OP_STHU 45
+#define OP_LMW 46
+#define OP_STMW 47
+#define OP_LFS 48
+#define OP_LFSU 49
+#define OP_LFD 50
+#define OP_LFDU 51
+#define OP_STFS 52
+#define OP_STFSU 53
+#define OP_STFD 54
+#define OP_STFDU 55
+#define OP_LQ 56
/* sorted alphabetically */
#define PPC_INST_BHRBE 0x7c00025c
@@ -161,6 +219,7 @@
#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_MTTMR 0x7c0003dc
#define PPC_INST_NOP 0x60000000
@@ -284,6 +343,13 @@
#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
/* macros to insert fields into opcodes */
#define ___PPC_RA(a) (((a) & 0x1f) << 16)
@@ -338,6 +404,7 @@
___PPC_RB(b) | __PPC_EH(eh))
#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 | \
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index e0fecbcea2a2..a4b1d8d6b793 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -102,11 +102,25 @@ void release_thread(struct task_struct *);
#endif
#ifdef CONFIG_PPC64
-/* 64-bit user address space is 46-bits (64TB user VM) */
-#define TASK_SIZE_USER64 (0x0000400000000000UL)
+/*
+ * 64-bit user address space can have multiple limits
+ * For now supported values are:
+ */
+#define TASK_SIZE_64TB (0x0000400000000000UL)
+#define TASK_SIZE_128TB (0x0000800000000000UL)
+#define TASK_SIZE_512TB (0x0002000000000000UL)
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * Max value currently used:
+ */
+#define TASK_SIZE_USER64 TASK_SIZE_512TB
+#else
+#define TASK_SIZE_USER64 TASK_SIZE_64TB
+#endif
-/*
- * 32-bit user address space is 4GB - 1 page
+/*
+ * 32-bit user address space is 4GB - 1 page
* (this 1 page is needed so referencing of 0xFFFFFFFF generates EFAULT
*/
#define TASK_SIZE_USER32 (0x0000000100000000UL - (1*PAGE_SIZE))
@@ -114,26 +128,37 @@ void release_thread(struct task_struct *);
#define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \
TASK_SIZE_USER32 : TASK_SIZE_USER64)
#define TASK_SIZE TASK_SIZE_OF(current)
-
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
#define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
-#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_USER64 / 4))
+#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4))
#define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
#endif
+/*
+ * Initial task size value for user applications. For book3s 64 we start
+ * with 128TB and conditionally enable upto 512TB
+ */
+#ifdef CONFIG_PPC_BOOK3S_64
+#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \
+ TASK_SIZE_USER32 : TASK_SIZE_128TB)
+#else
+#define DEFAULT_MAP_WINDOW TASK_SIZE
+#endif
+
#ifdef __powerpc64__
-#define STACK_TOP_USER64 TASK_SIZE_USER64
+/* Limit stack to 128TB */
+#define STACK_TOP_USER64 TASK_SIZE_128TB
#define STACK_TOP_USER32 TASK_SIZE_USER32
#define STACK_TOP (is_32bit_task() ? \
STACK_TOP_USER32 : STACK_TOP_USER64)
-#define STACK_TOP_MAX STACK_TOP_USER64
+#define STACK_TOP_MAX TASK_SIZE_USER64
#else /* __powerpc64__ */
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 4a90634e8322..35c00d7a0cf8 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -160,12 +160,18 @@ struct of_drconf_cell {
#define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */
#define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */
#define OV5_XIVE_EXPLOIT 0x1701 /* XIVE exploitation supported */
-#define OV5_MMU_RADIX_300 0x1880 /* ISA v3.00 radix MMU supported */
-#define OV5_MMU_HASH_300 0x1840 /* ISA v3.00 hash MMU supported */
-#define OV5_MMU_SEGM_RADIX 0x1820 /* radix mode (no segmentation) */
-#define OV5_MMU_PROC_TBL 0x1810 /* hcall selects SLB or proc table */
-#define OV5_MMU_SLB 0x1800 /* always use SLB */
-#define OV5_MMU_GTSE 0x1808 /* Guest translation shootdown */
+/* MMU Base Architecture */
+#define OV5_MMU_SUPPORT 0x18C0 /* MMU Mode Support Mask */
+#define OV5_MMU_HASH 0x1800 /* Hash MMU Only */
+#define OV5_MMU_RADIX 0x1840 /* Radix MMU Only */
+#define OV5_MMU_EITHER 0x1880 /* Hash or Radix Supported */
+#define OV5_MMU_DYNAMIC 0x18C0 /* Hash or Radix Can Switch Later */
+#define OV5_NMMU 0x1820 /* Nest MMU Available */
+/* Hash Table Extensions */
+#define OV5_HASH_SEG_TBL 0x1980 /* In Memory Segment Tables Available */
+#define OV5_HASH_GTSE 0x1940 /* Guest Translation Shoot Down Avail */
+/* Radix Table Extensions */
+#define OV5_RADIX_GTSE 0x1A40 /* Guest Translation Shoot Down Avail */
/* Option Vector 6: IBM PAPR hints */
#define OV6_LINUX 0x02 /* Linux is our OS */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index fc879fd6bdae..d4f653c9259a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -310,6 +310,7 @@
#define SPRN_PMCR 0x374 /* Power Management Control Register */
/* HFSCR and FSCR bit numbers are the same */
+#define FSCR_SCV_LG 12 /* Enable System Call Vectored */
#define FSCR_MSGP_LG 10 /* Enable MSGP */
#define FSCR_TAR_LG 8 /* Enable Target Address Register */
#define FSCR_EBB_LG 7 /* Enable Event Based Branching */
@@ -320,6 +321,7 @@
#define FSCR_VECVSX_LG 1 /* Enable VMX/VSX */
#define FSCR_FP_LG 0 /* Enable Floating Point */
#define SPRN_FSCR 0x099 /* Facility Status & Control Register */
+#define FSCR_SCV __MASK(FSCR_SCV_LG)
#define FSCR_TAR __MASK(FSCR_TAR_LG)
#define FSCR_EBB __MASK(FSCR_EBB_LG)
#define FSCR_DSCR __MASK(FSCR_DSCR_LG)
@@ -365,6 +367,7 @@
#define LPCR_MER_SH 11
#define LPCR_GTSE ASM_CONST(0x0000000000000400) /* Guest Translation Shootdown Enable */
#define LPCR_TC ASM_CONST(0x0000000000000200) /* Translation control */
+#define LPCR_HEIC ASM_CONST(0x0000000000000010) /* Hypervisor External Interrupt Control */
#define LPCR_LPES 0x0000000c
#define LPCR_LPES0 ASM_CONST(0x0000000000000008) /* LPAR Env selector 0 */
#define LPCR_LPES1 ASM_CONST(0x0000000000000004) /* LPAR Env selector 1 */
@@ -656,6 +659,7 @@
#define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */
#define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */
#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 and 9 */
+#define SRR1_WAKEMCE_RESVD 0x003c0000 /* Unused/reserved value used by MCE wakeup to indicate cause to idle wakeup handler */
#define SRR1_WAKESYSERR 0x00300000 /* System error */
#define SRR1_WAKEEE 0x00200000 /* External interrupt */
#define SRR1_WAKEHVI 0x00240000 /* Hypervisor Virtualization Interrupt (P9) */
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 7dc006b58369..7902d6358854 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -6,6 +6,8 @@
#include <linux/uaccess.h>
#include <asm-generic/sections.h>
+extern char __head_end[];
+
#ifdef __powerpc64__
extern char __start_interrupts[];
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 32db16d2e7ad..ebddb2111d87 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -40,10 +40,12 @@ extern int cpu_to_chip_id(int cpu);
struct smp_ops_t {
void (*message_pass)(int cpu, int msg);
#ifdef CONFIG_PPC_SMP_MUXED_IPI
- void (*cause_ipi)(int cpu, unsigned long data);
+ void (*cause_ipi)(int cpu);
#endif
+ int (*cause_nmi_ipi)(int cpu);
void (*probe)(void);
int (*kick_cpu)(int nr);
+ int (*prepare_cpu)(int nr);
void (*setup_cpu)(int nr);
void (*bringup_done)(void);
void (*take_timebase)(void);
@@ -61,7 +63,6 @@ extern void smp_generic_take_timebase(void);
DECLARE_PER_CPU(unsigned int, cpu_pvr);
#ifdef CONFIG_HOTPLUG_CPU
-extern void migrate_irqs(void);
int generic_cpu_disable(void);
void generic_cpu_die(unsigned int cpu);
void generic_set_cpu_dead(unsigned int cpu);
@@ -112,23 +113,31 @@ extern int cpu_to_core_id(int cpu);
*
* Make sure this matches openpic_request_IPIs in open_pic.c, or what shows up
* in /proc/interrupts will be wrong!!! --Troy */
-#define PPC_MSG_CALL_FUNCTION 0
-#define PPC_MSG_RESCHEDULE 1
+#define PPC_MSG_CALL_FUNCTION 0
+#define PPC_MSG_RESCHEDULE 1
#define PPC_MSG_TICK_BROADCAST 2
-#define PPC_MSG_DEBUGGER_BREAK 3
+#define PPC_MSG_NMI_IPI 3
/* This is only used by the powernv kernel */
#define PPC_MSG_RM_HOST_ACTION 4
+#define NMI_IPI_ALL_OTHERS -2
+
+#ifdef CONFIG_NMI_IPI
+extern int smp_handle_nmi_ipi(struct pt_regs *regs);
+#else
+static inline int smp_handle_nmi_ipi(struct pt_regs *regs) { return 0; }
+#endif
+
/* for irq controllers that have dedicated ipis per message (4) */
extern int smp_request_message_ipi(int virq, int message);
extern const char *smp_ipi_name[];
/* for irq controllers with only a single ipi */
-extern void smp_muxed_ipi_set_data(int cpu, unsigned long data);
extern void smp_muxed_ipi_message_pass(int cpu, int msg);
extern void smp_muxed_ipi_set_message(int cpu, int msg);
extern irqreturn_t smp_ipi_demux(void);
+extern irqreturn_t smp_ipi_demux_relaxed(void);
void smp_init_pSeries(void);
void smp_init_cell(void);
diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h
index 23be8f1e7e64..16fab6898240 100644
--- a/arch/powerpc/include/asm/syscalls.h
+++ b/arch/powerpc/include/asm/syscalls.h
@@ -8,10 +8,10 @@
struct rtas_args;
-asmlinkage unsigned long sys_mmap(unsigned long addr, size_t len,
+asmlinkage long sys_mmap(unsigned long addr, size_t len,
unsigned long prot, unsigned long flags,
unsigned long fd, off_t offset);
-asmlinkage unsigned long sys_mmap2(unsigned long addr, size_t len,
+asmlinkage long sys_mmap2(unsigned long addr, size_t len,
unsigned long prot, unsigned long flags,
unsigned long fd, unsigned long pgoff);
asmlinkage long ppc64_personality(unsigned long personality);
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 4b369d83fe9c..1c9470881c4a 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -387,3 +387,4 @@ SYSCALL(copy_file_range)
COMPAT_SYS_SPU(preadv2)
COMPAT_SYS_SPU(pwritev2)
SYSCALL(kexec_file_load)
+SYSCALL(statx)
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 87e4b2d8dcd4..a941cc6fc3e9 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -10,15 +10,7 @@
#ifdef __KERNEL__
-/* We have 8k stacks on ppc32 and 16k on ppc64 */
-
-#if defined(CONFIG_PPC64)
-#define THREAD_SHIFT 14
-#elif defined(CONFIG_PPC_256K_PAGES)
-#define THREAD_SHIFT 15
-#else
-#define THREAD_SHIFT 13
-#endif
+#define THREAD_SHIFT CONFIG_THREAD_SHIFT
#define THREAD_SIZE (1 << THREAD_SHIFT)
@@ -92,6 +84,7 @@ static inline struct thread_info *current_thread_info(void)
TIF_NEED_RESCHED */
#define TIF_32BIT 4 /* 32 bit binary */
#define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */
+#define TIF_PATCH_PENDING 6 /* pending live patching update */
#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
#define TIF_SINGLESTEP 8 /* singlestepping active */
#define TIF_NOHZ 9 /* in adaptive nohz mode */
@@ -115,6 +108,7 @@ static inline struct thread_info *current_thread_info(void)
#define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG)
#define _TIF_32BIT (1<<TIF_32BIT)
#define _TIF_RESTORE_TM (1<<TIF_RESTORE_TM)
+#define _TIF_PATCH_PENDING (1<<TIF_PATCH_PENDING)
#define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT)
#define _TIF_SINGLESTEP (1<<TIF_SINGLESTEP)
#define _TIF_SECCOMP (1<<TIF_SECCOMP)
@@ -131,7 +125,7 @@ static inline struct thread_info *current_thread_info(void)
#define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
_TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- _TIF_RESTORE_TM)
+ _TIF_RESTORE_TM | _TIF_PATCH_PENDING)
#define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR)
/* Bits in local_flags */
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 0e6add3187bc..5c0d8a8cdae5 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -1,18 +1,11 @@
#ifndef _ARCH_POWERPC_UACCESS_H
#define _ARCH_POWERPC_UACCESS_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/errno.h>
#include <asm/asm-compat.h>
#include <asm/ppc_asm.h>
#include <asm/processor.h>
#include <asm/page.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
+#include <asm/extable.h>
/*
* The fs value determines whether argument validity checking should be
@@ -64,31 +57,6 @@
__access_ok((__force unsigned long)(addr), (size), get_fs()))
/*
- * The exception table consists of pairs of relative addresses: the first is
- * the address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out what
- * to do.
- *
- * All the routines below use bits of fixup code that are out of line with the
- * main instruction path. This means when everything is well, we don't even
- * have to jump over them. Further, they do not intrude on our cache or tlb
- * entries.
- */
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-struct exception_table_entry {
- int insn;
- int fixup;
-};
-
-static inline unsigned long extable_fixup(const struct exception_table_entry *x)
-{
- return (unsigned long)&x->fixup + x->fixup;
-}
-
-/*
* These are the main single-value transfer routines. They automatically
* use the right size if we just have the right pointer type.
*
@@ -301,42 +269,19 @@ extern unsigned long __copy_tofrom_user(void __user *to,
#ifndef __powerpc64__
-static inline unsigned long copy_from_user(void *to,
- const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n))) {
- check_object_size(to, n, false);
- return __copy_tofrom_user((__force void __user *)to, from, n);
- }
- memset(to, 0, n);
- return n;
-}
-
-static inline unsigned long copy_to_user(void __user *to,
- const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n)) {
- check_object_size(from, n, true);
- return __copy_tofrom_user(to, (__force void __user *)from, n);
- }
- return n;
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
#else /* __powerpc64__ */
-#define __copy_in_user(to, from, size) \
- __copy_tofrom_user((to), (from), (size))
-
-extern unsigned long copy_from_user(void *to, const void __user *from,
- unsigned long n);
-extern unsigned long copy_to_user(void __user *to, const void *from,
- unsigned long n);
-extern unsigned long copy_in_user(void __user *to, const void __user *from,
- unsigned long n);
-
+static inline unsigned long
+raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
+{
+ return __copy_tofrom_user(to, from, n);
+}
#endif /* __powerpc64__ */
-static inline unsigned long __copy_from_user_inatomic(void *to,
+static inline unsigned long raw_copy_from_user(void *to,
const void __user *from, unsigned long n)
{
if (__builtin_constant_p(n) && (n <= 8)) {
@@ -360,12 +305,10 @@ static inline unsigned long __copy_from_user_inatomic(void *to,
return 0;
}
- check_object_size(to, n, false);
-
return __copy_tofrom_user((__force void __user *)to, from, n);
}
-static inline unsigned long __copy_to_user_inatomic(void __user *to,
+static inline unsigned long raw_copy_to_user(void __user *to,
const void *from, unsigned long n)
{
if (__builtin_constant_p(n) && (n <= 8)) {
@@ -389,25 +332,9 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to,
return 0;
}
- check_object_size(from, n, true);
-
return __copy_tofrom_user(to, (__force const void __user *)from, n);
}
-static inline unsigned long __copy_from_user(void *to,
- const void __user *from, unsigned long size)
-{
- might_fault();
- return __copy_from_user_inatomic(to, from, size);
-}
-
-static inline unsigned long __copy_to_user(void __user *to,
- const void *from, unsigned long size)
-{
- might_fault();
- return __copy_to_user_inatomic(to, from, size);
-}
-
extern unsigned long __clear_user(void __user *addr, unsigned long size);
static inline unsigned long clear_user(void __user *addr, unsigned long size)
@@ -422,7 +349,4 @@ extern long strncpy_from_user(char *dst, const char __user *src, long count);
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
#endif /* _ARCH_POWERPC_UACCESS_H */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index eb1acee91a20..9ba11dbcaca9 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
#include <uapi/asm/unistd.h>
-#define NR_syscalls 383
+#define NR_syscalls 384
#define __NR__exit __NR_exit
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index e0b9e576905a..7ce2c3ac2964 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -57,7 +57,7 @@ struct icp_ops {
void (*teardown_cpu)(void);
void (*flush_ipi)(void);
#ifdef CONFIG_SMP
- void (*cause_ipi)(int cpu, unsigned long data);
+ void (*cause_ipi)(int cpu);
irq_handler_t ipi_action;
#endif
};
diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h
new file mode 100644
index 000000000000..1d3f2be5ae39
--- /dev/null
+++ b/arch/powerpc/include/asm/xive-regs.h
@@ -0,0 +1,97 @@
+/*
+ * Copyright 2016,2017 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_POWERPC_XIVE_REGS_H
+#define _ASM_POWERPC_XIVE_REGS_H
+
+/*
+ * Thread Management (aka "TM") registers
+ */
+
+/* TM register offsets */
+#define TM_QW0_USER 0x000 /* All rings */
+#define TM_QW1_OS 0x010 /* Ring 0..2 */
+#define TM_QW2_HV_POOL 0x020 /* Ring 0..1 */
+#define TM_QW3_HV_PHYS 0x030 /* Ring 0..1 */
+
+/* Byte offsets inside a QW QW0 QW1 QW2 QW3 */
+#define TM_NSR 0x0 /* + + - + */
+#define TM_CPPR 0x1 /* - + - + */
+#define TM_IPB 0x2 /* - + + + */
+#define TM_LSMFB 0x3 /* - + + + */
+#define TM_ACK_CNT 0x4 /* - + - - */
+#define TM_INC 0x5 /* - + - + */
+#define TM_AGE 0x6 /* - + - + */
+#define TM_PIPR 0x7 /* - + - + */
+
+#define TM_WORD0 0x0
+#define TM_WORD1 0x4
+
+/*
+ * QW word 2 contains the valid bit at the top and other fields
+ * depending on the QW.
+ */
+#define TM_WORD2 0x8
+#define TM_QW0W2_VU PPC_BIT32(0)
+#define TM_QW0W2_LOGIC_SERV PPC_BITMASK32(1,31) // XX 2,31 ?
+#define TM_QW1W2_VO PPC_BIT32(0)
+#define TM_QW1W2_OS_CAM PPC_BITMASK32(8,31)
+#define TM_QW2W2_VP PPC_BIT32(0)
+#define TM_QW2W2_POOL_CAM PPC_BITMASK32(8,31)
+#define TM_QW3W2_VT PPC_BIT32(0)
+#define TM_QW3W2_LP PPC_BIT32(6)
+#define TM_QW3W2_LE PPC_BIT32(7)
+#define TM_QW3W2_T PPC_BIT32(31)
+
+/*
+ * In addition to normal loads to "peek" and writes (only when invalid)
+ * using 4 and 8 bytes accesses, the above registers support these
+ * "special" byte operations:
+ *
+ * - Byte load from QW0[NSR] - User level NSR (EBB)
+ * - Byte store to QW0[NSR] - User level NSR (EBB)
+ * - Byte load/store to QW1[CPPR] and QW3[CPPR] - CPPR access
+ * - Byte load from QW3[TM_WORD2] - Read VT||00000||LP||LE on thrd 0
+ * otherwise VT||0000000
+ * - Byte store to QW3[TM_WORD2] - Set VT bit (and LP/LE if present)
+ *
+ * Then we have all these "special" CI ops at these offset that trigger
+ * all sorts of side effects:
+ */
+#define TM_SPC_ACK_EBB 0x800 /* Load8 ack EBB to reg*/
+#define TM_SPC_ACK_OS_REG 0x810 /* Load16 ack OS irq to reg */
+#define TM_SPC_PUSH_USR_CTX 0x808 /* Store32 Push/Validate user context */
+#define TM_SPC_PULL_USR_CTX 0x808 /* Load32 Pull/Invalidate user context */
+#define TM_SPC_SET_OS_PENDING 0x812 /* Store8 Set OS irq pending bit */
+#define TM_SPC_PULL_OS_CTX 0x818 /* Load32/Load64 Pull/Invalidate OS context to reg */
+#define TM_SPC_PULL_POOL_CTX 0x828 /* Load32/Load64 Pull/Invalidate Pool context to reg*/
+#define TM_SPC_ACK_HV_REG 0x830 /* Load16 ack HV irq to reg */
+#define TM_SPC_PULL_USR_CTX_OL 0xc08 /* Store8 Pull/Inval usr ctx to odd line */
+#define TM_SPC_ACK_OS_EL 0xc10 /* Store8 ack OS irq to even line */
+#define TM_SPC_ACK_HV_POOL_EL 0xc20 /* Store8 ack HV evt pool to even line */
+#define TM_SPC_ACK_HV_EL 0xc30 /* Store8 ack HV irq to even line */
+/* XXX more... */
+
+/* NSR fields for the various QW ack types */
+#define TM_QW0_NSR_EB PPC_BIT8(0)
+#define TM_QW1_NSR_EO PPC_BIT8(0)
+#define TM_QW3_NSR_HE PPC_BITMASK8(0,1)
+#define TM_QW3_NSR_HE_NONE 0
+#define TM_QW3_NSR_HE_POOL 1
+#define TM_QW3_NSR_HE_PHYS 2
+#define TM_QW3_NSR_HE_LSI 3
+#define TM_QW3_NSR_I PPC_BIT8(2)
+#define TM_QW3_NSR_GRP_LVL PPC_BIT8(3,7)
+
+/* Utilities to manipulate these (originaly from OPAL) */
+#define MASK_TO_LSH(m) (__builtin_ffsl(m) - 1)
+#define GETFIELD(m, v) (((v) & (m)) >> MASK_TO_LSH(m))
+#define SETFIELD(m, v, val) \
+ (((v) & ~(m)) | ((((typeof(v))(val)) << MASK_TO_LSH(m)) & (m)))
+
+#endif /* _ASM_POWERPC_XIVE_REGS_H */
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
new file mode 100644
index 000000000000..c8a822acf962
--- /dev/null
+++ b/arch/powerpc/include/asm/xive.h
@@ -0,0 +1,162 @@
+/*
+ * Copyright 2016,2017 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_POWERPC_XIVE_H
+#define _ASM_POWERPC_XIVE_H
+
+#define XIVE_INVALID_VP 0xffffffff
+
+#ifdef CONFIG_PPC_XIVE
+
+/*
+ * Thread Interrupt Management Area (TIMA)
+ *
+ * This is a global MMIO region divided in 4 pages of varying access
+ * permissions, providing access to per-cpu interrupt management
+ * functions. It always identifies the CPU doing the access based
+ * on the PowerBus initiator ID, thus we always access via the
+ * same offset regardless of where the code is executing
+ */
+extern void __iomem *xive_tima;
+
+/*
+ * Offset in the TM area of our current execution level (provided by
+ * the backend)
+ */
+extern u32 xive_tima_offset;
+
+/*
+ * Per-irq data (irq_get_handler_data for normal IRQs), IPIs
+ * have it stored in the xive_cpu structure. We also cache
+ * for normal interrupts the current target CPU.
+ *
+ * This structure is setup by the backend for each interrupt.
+ */
+struct xive_irq_data {
+ u64 flags;
+ u64 eoi_page;
+ void __iomem *eoi_mmio;
+ u64 trig_page;
+ void __iomem *trig_mmio;
+ u32 esb_shift;
+ int src_chip;
+
+ /* Setup/used by frontend */
+ int target;
+ bool saved_p;
+};
+#define XIVE_IRQ_FLAG_STORE_EOI 0x01
+#define XIVE_IRQ_FLAG_LSI 0x02
+#define XIVE_IRQ_FLAG_SHIFT_BUG 0x04
+#define XIVE_IRQ_FLAG_MASK_FW 0x08
+#define XIVE_IRQ_FLAG_EOI_FW 0x10
+
+#define XIVE_INVALID_CHIP_ID -1
+
+/* A queue tracking structure in a CPU */
+struct xive_q {
+ __be32 *qpage;
+ u32 msk;
+ u32 idx;
+ u32 toggle;
+ u64 eoi_phys;
+ u32 esc_irq;
+ atomic_t count;
+ atomic_t pending_count;
+};
+
+/*
+ * "magic" Event State Buffer (ESB) MMIO offsets.
+ *
+ * Each interrupt source has a 2-bit state machine called ESB
+ * which can be controlled by MMIO. It's made of 2 bits, P and
+ * Q. P indicates that an interrupt is pending (has been sent
+ * to a queue and is waiting for an EOI). Q indicates that the
+ * interrupt has been triggered while pending.
+ *
+ * This acts as a coalescing mechanism in order to guarantee
+ * that a given interrupt only occurs at most once in a queue.
+ *
+ * When doing an EOI, the Q bit will indicate if the interrupt
+ * needs to be re-triggered.
+ *
+ * The following offsets into the ESB MMIO allow to read or
+ * manipulate the PQ bits. They must be used with an 8-bytes
+ * load instruction. They all return the previous state of the
+ * interrupt (atomically).
+ *
+ * Additionally, some ESB pages support doing an EOI via a
+ * store at 0 and some ESBs support doing a trigger via a
+ * separate trigger page.
+ */
+#define XIVE_ESB_GET 0x800
+#define XIVE_ESB_SET_PQ_00 0xc00
+#define XIVE_ESB_SET_PQ_01 0xd00
+#define XIVE_ESB_SET_PQ_10 0xe00
+#define XIVE_ESB_SET_PQ_11 0xf00
+
+#define XIVE_ESB_VAL_P 0x2
+#define XIVE_ESB_VAL_Q 0x1
+
+/* Global enable flags for the XIVE support */
+extern bool __xive_enabled;
+
+static inline bool xive_enabled(void) { return __xive_enabled; }
+
+extern bool xive_native_init(void);
+extern void xive_smp_probe(void);
+extern int xive_smp_prepare_cpu(unsigned int cpu);
+extern void xive_smp_setup_cpu(void);
+extern void xive_smp_disable_cpu(void);
+extern void xive_kexec_teardown_cpu(int secondary);
+extern void xive_shutdown(void);
+extern void xive_flush_interrupt(void);
+
+/* xmon hook */
+extern void xmon_xive_do_dump(int cpu);
+
+/* APIs used by KVM */
+extern u32 xive_native_default_eq_shift(void);
+extern u32 xive_native_alloc_vp_block(u32 max_vcpus);
+extern void xive_native_free_vp_block(u32 vp_base);
+extern int xive_native_populate_irq_data(u32 hw_irq,
+ struct xive_irq_data *data);
+extern void xive_cleanup_irq_data(struct xive_irq_data *xd);
+extern u32 xive_native_alloc_irq(void);
+extern void xive_native_free_irq(u32 irq);
+extern int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq);
+
+extern int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
+ __be32 *qpage, u32 order, bool can_escalate);
+extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio);
+
+extern void xive_native_sync_source(u32 hw_irq);
+extern bool is_xive_irq(struct irq_chip *chip);
+extern int xive_native_enable_vp(u32 vp_id);
+extern int xive_native_disable_vp(u32 vp_id);
+extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
+
+#else
+
+static inline bool xive_enabled(void) { return false; }
+
+static inline bool xive_native_init(void) { return false; }
+static inline void xive_smp_probe(void) { }
+extern 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) { }
+
+static inline u32 xive_native_alloc_vp_block(u32 max_vcpus) { return XIVE_INVALID_VP; }
+static inline void xive_native_free_vp_block(u32 vp_base) { }
+
+#endif
+
+#endif /* _ASM_POWERPC_XIVE_H */
diff --git a/arch/powerpc/include/asm/xmon.h b/arch/powerpc/include/asm/xmon.h
index 5eb8e599e5cc..eb42a0c6e1d9 100644
--- a/arch/powerpc/include/asm/xmon.h
+++ b/arch/powerpc/include/asm/xmon.h
@@ -29,5 +29,7 @@ static inline void xmon_register_spus(struct list_head *list) { };
extern int cpus_are_in_xmon(void);
#endif
+extern void xmon_printf(const char *format, ...);
+
#endif /* __KERNEL __ */
#endif /* __ASM_POWERPC_XMON_H */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 4edbe4bb0e8b..07fbeb927834 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -29,6 +29,9 @@
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_GUEST_DEBUG
+/* Not always available, but if it is, this is the correct offset. */
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
struct kvm_regs {
__u64 pc;
__u64 cr;
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index 03c06ba7464f..ab45cc2f3101 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -29,4 +29,20 @@
#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */
#define MAP_HUGETLB 0x40000 /* create a huge page mapping */
+/*
+ * When MAP_HUGETLB is set, bits [26:31] of the flags argument to mmap(2),
+ * encode the log2 of the huge page size. A value of zero indicates that the
+ * default huge page size should be used. To use a non-default huge page size,
+ * one of these defines can be used, or the size can be encoded by hand. Note
+ * that on most systems only a subset, or possibly none, of these sizes will be
+ * available.
+ */
+#define MAP_HUGE_512KB (19 << MAP_HUGE_SHIFT) /* 512KB HugeTLB Page */
+#define MAP_HUGE_1MB (20 << MAP_HUGE_SHIFT) /* 1MB HugeTLB Page */
+#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) /* 2MB HugeTLB Page */
+#define MAP_HUGE_8MB (23 << MAP_HUGE_SHIFT) /* 8MB HugeTLB Page */
+#define MAP_HUGE_16MB (24 << MAP_HUGE_SHIFT) /* 16MB HugeTLB Page */
+#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) /* 1GB HugeTLB Page */
+#define MAP_HUGE_16GB (34 << MAP_HUGE_SHIFT) /* 16GB HugeTLB Page */
+
#endif /* _UAPI_ASM_POWERPC_MMAN_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 44583a52f882..58e2ec0310fc 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -99,4 +99,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 2f26335a3c42..b85f14228857 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -393,5 +393,6 @@
#define __NR_preadv2 380
#define __NR_pwritev2 381
#define __NR_kexec_file_load 382
+#define __NR_statx 383
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 811f441a125f..b9db46ae545b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -25,8 +25,6 @@ CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_prom_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_btext.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_prom.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
-# do not trace tracer code
-CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
# timers used by tracing
CFLAGS_REMOVE_time.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
endif
@@ -97,6 +95,7 @@ obj-$(CONFIG_BOOTX_TEXT) += btext.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_OPTPROBES) += optprobes.o optprobes_head.o
+obj-$(CONFIG_KPROBES_ON_FTRACE) += kprobes-ftrace.o
obj-$(CONFIG_UPROBES) += uprobes.o
obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
@@ -118,10 +117,7 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o
obj-$(CONFIG_PPC_IO_WORKAROUNDS) += io-workarounds.o
-obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
-obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
-obj-$(CONFIG_TRACING) += trace_clock.o
+obj-y += trace/
ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
obj-y += iomap.o
@@ -142,14 +138,14 @@ obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
# Disable GCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_prom_init.o := n
UBSAN_SANITIZE_prom_init.o := n
-GCOV_PROFILE_ftrace.o := n
-UBSAN_SANITIZE_ftrace.o := n
GCOV_PROFILE_machine_kexec_64.o := n
UBSAN_SANITIZE_machine_kexec_64.o := n
GCOV_PROFILE_machine_kexec_32.o := n
UBSAN_SANITIZE_machine_kexec_32.o := n
GCOV_PROFILE_kprobes.o := n
UBSAN_SANITIZE_kprobes.o := n
+GCOV_PROFILE_kprobes-ftrace.o := n
+UBSAN_SANITIZE_kprobes-ftrace.o := n
UBSAN_SANITIZE_vdso.o := n
extra-$(CONFIG_PPC_FPU) += fpu.o
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index cbc7c42cdb74..ec7a8b099dd9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -807,14 +807,25 @@ int fix_alignment(struct pt_regs *regs)
nb = aligninfo[instr].len;
flags = aligninfo[instr].flags;
- /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
- if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
- nb = 8;
- flags = LD+SW;
- } else if (IS_XFORM(instruction) &&
- ((instruction >> 1) & 0x3ff) == 660) {
- nb = 8;
- flags = ST+SW;
+ /*
+ * Handle some cases which give overlaps in the DSISR values.
+ */
+ if (IS_XFORM(instruction)) {
+ switch (get_xop(instruction)) {
+ case 532: /* ldbrx */
+ nb = 8;
+ flags = LD+SW;
+ break;
+ case 660: /* stdbrx */
+ nb = 8;
+ flags = ST+SW;
+ break;
+ case 20: /* lwarx */
+ case 84: /* ldarx */
+ case 116: /* lharx */
+ case 276: /* lqarx */
+ return 0; /* not emulated ever */
+ }
}
/* Byteswap little endian loads and stores */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4367e7df51a1..709e23425317 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -185,6 +185,7 @@ int main(void)
#ifdef CONFIG_PPC_MM_SLICES
OFFSET(PACALOWSLICESPSIZE, paca_struct, mm_ctx_low_slices_psize);
OFFSET(PACAHIGHSLICEPSIZE, paca_struct, mm_ctx_high_slices_psize);
+ DEFINE(PACA_ADDR_LIMIT, offsetof(struct paca_struct, addr_limit));
DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
#endif /* CONFIG_PPC_MM_SLICES */
#endif
@@ -219,6 +220,7 @@ int main(void)
OFFSET(PACA_EXGEN, paca_struct, exgen);
OFFSET(PACA_EXMC, paca_struct, exmc);
OFFSET(PACA_EXSLB, paca_struct, exslb);
+ OFFSET(PACA_EXNMI, paca_struct, exnmi);
OFFSET(PACALPPACAPTR, paca_struct, lppaca_ptr);
OFFSET(PACA_SLBSHADOWPTR, paca_struct, slb_shadow_ptr);
OFFSET(SLBSHADOW_STACKVSID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid);
@@ -232,7 +234,9 @@ int main(void)
OFFSET(PACAEMERGSP, paca_struct, emergency_sp);
#ifdef CONFIG_PPC_BOOK3S_64
OFFSET(PACAMCEMERGSP, paca_struct, mc_emergency_sp);
+ OFFSET(PACA_NMI_EMERG_SP, paca_struct, nmi_emergency_sp);
OFFSET(PACA_IN_MCE, paca_struct, in_mce);
+ OFFSET(PACA_IN_NMI, paca_struct, in_nmi);
#endif
OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);
@@ -399,8 +403,8 @@ int main(void)
DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
#endif
-#ifdef MAX_PGD_TABLE_SIZE
- DEFINE(PGD_TABLE_SIZE, MAX_PGD_TABLE_SIZE);
+#ifdef CONFIG_PPC_BOOK3S_64
+ DEFINE(PGD_TABLE_SIZE, (sizeof(pgd_t) << max(RADIX_PGD_INDEX_SIZE, H_PGD_INDEX_SIZE)));
#else
DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE);
#endif
@@ -630,6 +634,8 @@ int main(void)
HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
+ HSTATE_FIELD(HSTATE_XIVE_TIMA_PHYS, xive_tima_phys);
+ HSTATE_FIELD(HSTATE_XIVE_TIMA_VIRT, xive_tima_virt);
HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
HSTATE_FIELD(HSTATE_PTID, ptid);
@@ -715,6 +721,14 @@ int main(void)
OFFSET(VCPU_HOST_MAS6, kvm_vcpu, arch.host_mas6);
#endif
+#ifdef CONFIG_KVM_XICS
+ DEFINE(VCPU_XIVE_SAVED_STATE, offsetof(struct kvm_vcpu,
+ arch.xive_saved_state));
+ DEFINE(VCPU_XIVE_CAM_WORD, offsetof(struct kvm_vcpu,
+ arch.xive_cam_word));
+ DEFINE(VCPU_XIVE_PUSHED, offsetof(struct kvm_vcpu, arch.xive_pushed));
+#endif
+
#ifdef CONFIG_KVM_EXIT_TIMING
OFFSET(VCPU_TIMING_EXIT_TBU, kvm_vcpu, arch.timing_exit.tv32.tbu);
OFFSET(VCPU_TIMING_EXIT_TBL, kvm_vcpu, arch.timing_exit.tv32.tbl);
@@ -727,6 +741,7 @@ int main(void)
OFFSET(PACA_THREAD_IDLE_STATE, paca_struct, thread_idle_state);
OFFSET(PACA_THREAD_MASK, paca_struct, thread_mask);
OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask);
+ OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas);
#endif
DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 7fe8c79e6937..10cb2896b2ae 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -29,7 +29,8 @@ _GLOBAL(__setup_cpu_power7)
li r0,0
mtspr SPRN_LPID,r0
mfspr r3,SPRN_LPCR
- bl __init_LPCR
+ li r4,(LPCR_LPES1 >> LPCR_LPES_SH)
+ bl __init_LPCR_ISA206
bl __init_tlb_power7
mtlr r11
blr
@@ -42,7 +43,8 @@ _GLOBAL(__restore_cpu_power7)
li r0,0
mtspr SPRN_LPID,r0
mfspr r3,SPRN_LPCR
- bl __init_LPCR
+ li r4,(LPCR_LPES1 >> LPCR_LPES_SH)
+ bl __init_LPCR_ISA206
bl __init_tlb_power7
mtlr r11
blr
@@ -59,7 +61,8 @@ _GLOBAL(__setup_cpu_power8)
mtspr SPRN_LPID,r0
mfspr r3,SPRN_LPCR
ori r3, r3, LPCR_PECEDH
- bl __init_LPCR
+ li r4,0 /* LPES = 0 */
+ bl __init_LPCR_ISA206
bl __init_HFSCR
bl __init_tlb_power8
bl __init_PMU_HV
@@ -80,7 +83,8 @@ _GLOBAL(__restore_cpu_power8)
mtspr SPRN_LPID,r0
mfspr r3,SPRN_LPCR
ori r3, r3, LPCR_PECEDH
- bl __init_LPCR
+ li r4,0 /* LPES = 0 */
+ bl __init_LPCR_ISA206
bl __init_HFSCR
bl __init_tlb_power8
bl __init_PMU_HV
@@ -99,11 +103,12 @@ _GLOBAL(__setup_cpu_power9)
mtspr SPRN_PSSCR,r0
mtspr SPRN_LPID,r0
mfspr r3,SPRN_LPCR
- LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE)
+ LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
or r3, r3, r4
LOAD_REG_IMMEDIATE(r4, LPCR_UPRT | LPCR_HR)
andc r3, r3, r4
- bl __init_LPCR
+ li r4,0 /* LPES = 0 */
+ bl __init_LPCR_ISA300
bl __init_HFSCR
bl __init_tlb_power9
bl __init_PMU_HV
@@ -122,11 +127,12 @@ _GLOBAL(__restore_cpu_power9)
mtspr SPRN_PSSCR,r0
mtspr SPRN_LPID,r0
mfspr r3,SPRN_LPCR
- LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE)
+ LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
or r3, r3, r4
LOAD_REG_IMMEDIATE(r4, LPCR_UPRT | LPCR_HR)
andc r3, r3, r4
- bl __init_LPCR
+ li r4,0 /* LPES = 0 */
+ bl __init_LPCR_ISA300
bl __init_HFSCR
bl __init_tlb_power9
bl __init_PMU_HV
@@ -144,9 +150,9 @@ __init_hvmode_206:
std r5,CPU_SPEC_FEATURES(r4)
blr
-__init_LPCR:
+__init_LPCR_ISA206:
/* Setup a sane LPCR:
- * Called with initial LPCR in R3
+ * Called with initial LPCR in R3 and desired LPES 2-bit value in R4
*
* LPES = 0b01 (HSRR0/1 used for 0x500)
* PECE = 0b111
@@ -157,16 +163,18 @@ __init_LPCR:
*
* Other bits untouched for now
*/
- li r5,1
- rldimi r3,r5, LPCR_LPES_SH, 64-LPCR_LPES_SH-2
+ li r5,0x10
+ rldimi r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5
+
+ /* POWER9 has no VRMASD */
+__init_LPCR_ISA300:
+ rldimi r3,r4, LPCR_LPES_SH, 64-LPCR_LPES_SH-2
ori r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
li r5,4
rldimi r3,r5, LPCR_DPFD_SH, 64-LPCR_DPFD_SH-3
clrrdi r3,r3,1 /* clear HDICE */
li r5,4
rldimi r3,r5, LPCR_VC_SH, 0
- li r5,0x10
- rldimi r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5
mtspr SPRN_LPCR,r3
isync
blr
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index bb7a1890aeb7..e79b9daa873c 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -77,6 +77,7 @@ extern void __flush_tlb_power8(unsigned int action);
extern void __flush_tlb_power9(unsigned int action);
extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_E500)
extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -540,6 +541,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power9,
.cpu_restore = __restore_cpu_power9,
.flush_tlb = __flush_tlb_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
.platform = "power9",
},
{ /* Power9 */
@@ -559,6 +561,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power9,
.cpu_restore = __restore_cpu_power9,
.flush_tlb = __flush_tlb_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
.platform = "power9",
},
{ /* Cell Broadband Engine */
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 47b63de81f9b..cbabb5adccd9 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -43,8 +43,6 @@
#define IPI_TIMEOUT 10000
#define REAL_MODE_TIMEOUT 10000
-/* This keeps a track of which one is the crashing cpu. */
-int crashing_cpu = -1;
static int time_to_dump;
#define CRASH_HANDLER_MAX 3
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 2128f3a96c32..b6fe883b1016 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -20,18 +20,60 @@
#include <asm/kvm_ppc.h>
#ifdef CONFIG_SMP
-void doorbell_setup_this_cpu(void)
+
+/*
+ * Doorbells must only be used if CPU_FTR_DBELL is available.
+ * msgsnd is used in HV, and msgsndp is used in !HV.
+ *
+ * These should be used by platform code that is aware of restrictions.
+ * Other arch code should use ->cause_ipi.
+ *
+ * doorbell_global_ipi() sends a dbell to any target CPU.
+ * Must be used only by architectures that address msgsnd target
+ * by PIR/get_hard_smp_processor_id.
+ */
+void doorbell_global_ipi(int cpu)
{
- unsigned long tag = mfspr(SPRN_DOORBELL_CPUTAG) & PPC_DBELL_TAG_MASK;
+ u32 tag = get_hard_smp_processor_id(cpu);
- smp_muxed_ipi_set_data(smp_processor_id(), tag);
+ kvmppc_set_host_ipi(cpu, 1);
+ /* Order previous accesses vs. msgsnd, which is treated as a store */
+ ppc_msgsnd_sync();
+ ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
}
-void doorbell_cause_ipi(int cpu, unsigned long data)
+/*
+ * doorbell_core_ipi() sends a dbell to a target CPU in the same core.
+ * Must be used only by architectures that address msgsnd target
+ * by TIR/cpu_thread_in_core.
+ */
+void doorbell_core_ipi(int cpu)
{
+ u32 tag = cpu_thread_in_core(cpu);
+
+ kvmppc_set_host_ipi(cpu, 1);
/* Order previous accesses vs. msgsnd, which is treated as a store */
- mb();
- ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, data);
+ ppc_msgsnd_sync();
+ ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
+}
+
+/*
+ * Attempt to cause a core doorbell if destination is on the same core.
+ * Returns 1 on success, 0 on failure.
+ */
+int doorbell_try_core_ipi(int cpu)
+{
+ int this_cpu = get_cpu();
+ int ret = 0;
+
+ if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
+ doorbell_core_ipi(cpu);
+ ret = 1;
+ }
+
+ put_cpu();
+
+ return ret;
}
void doorbell_exception(struct pt_regs *regs)
@@ -40,12 +82,14 @@ void doorbell_exception(struct pt_regs *regs)
irq_enter();
+ ppc_msgsync();
+
may_hard_irq_enable();
kvmppc_set_host_ipi(smp_processor_id(), 0);
__this_cpu_inc(irq_stat.doorbell_irqs);
- smp_ipi_demux();
+ smp_ipi_demux_relaxed(); /* already performed the barrier */
irq_exit();
set_irq_regs(old_regs);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 9de7f79e702b..63992b2d8e15 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -22,7 +22,6 @@
*/
#include <linux/delay.h>
-#include <linux/debugfs.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/list.h>
@@ -37,7 +36,7 @@
#include <linux/of.h>
#include <linux/atomic.h>
-#include <asm/debug.h>
+#include <asm/debugfs.h>
#include <asm/eeh.h>
#include <asm/eeh_event.h>
#include <asm/io.h>
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index b94887165a10..c405c79e50cd 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -724,7 +724,16 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
*/
#define MAX_WAIT_FOR_RECOVERY 300
-static void eeh_handle_normal_event(struct eeh_pe *pe)
+/**
+ * eeh_handle_normal_event - Handle EEH events on a specific PE
+ * @pe: EEH PE
+ *
+ * Attempts to recover the given PE. If recovery fails or the PE has failed
+ * too many times, remove the PE.
+ *
+ * Returns true if @pe should no longer be used, else false.
+ */
+static bool eeh_handle_normal_event(struct eeh_pe *pe)
{
struct pci_bus *frozen_bus;
struct eeh_dev *edev, *tmp;
@@ -736,13 +745,18 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
if (!frozen_bus) {
pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
__func__, pe->phb->global_number, pe->addr);
- return;
+ return false;
}
eeh_pe_update_time_stamp(pe);
pe->freeze_count++;
- if (pe->freeze_count > eeh_max_freezes)
- goto excess_failures;
+ if (pe->freeze_count > eeh_max_freezes) {
+ pr_err("EEH: PHB#%x-PE#%x has failed %d times in the\n"
+ "last hour and has been permanently disabled.\n",
+ pe->phb->global_number, pe->addr,
+ pe->freeze_count);
+ goto hard_fail;
+ }
pr_warn("EEH: This PCI device has failed %d times in the last hour\n",
pe->freeze_count);
@@ -870,27 +884,18 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
pr_info("EEH: Notify device driver to resume\n");
eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
- return;
+ return false;
-excess_failures:
+hard_fail:
/*
* About 90% of all real-life EEH failures in the field
* are due to poorly seated PCI cards. Only 10% or so are
* due to actual, failed cards.
*/
- pr_err("EEH: PHB#%x-PE#%x has failed %d times in the\n"
- "last hour and has been permanently disabled.\n"
- "Please try reseating or replacing it.\n",
- pe->phb->global_number, pe->addr,
- pe->freeze_count);
- goto perm_error;
-
-hard_fail:
pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n"
"Please try reseating or replacing it\n",
pe->phb->global_number, pe->addr);
-perm_error:
eeh_slot_error_detail(pe, EEH_LOG_PERM);
/* Notify all devices that they're about to go down. */
@@ -915,10 +920,21 @@ perm_error:
pci_lock_rescan_remove();
pci_hp_remove_devices(frozen_bus);
pci_unlock_rescan_remove();
+
+ /* The passed PE should no longer be used */
+ return true;
}
}
+ return false;
}
+/**
+ * eeh_handle_special_event - Handle EEH events without a specific failing PE
+ *
+ * Called when an EEH event is detected but can't be narrowed down to a
+ * specific PE. Iterates through possible failures and handles them as
+ * necessary.
+ */
static void eeh_handle_special_event(void)
{
struct eeh_pe *pe, *phb_pe;
@@ -982,7 +998,14 @@ static void eeh_handle_special_event(void)
*/
if (rc == EEH_NEXT_ERR_FROZEN_PE ||
rc == EEH_NEXT_ERR_FENCED_PHB) {
- eeh_handle_normal_event(pe);
+ /*
+ * eeh_handle_normal_event() can make the PE stale if it
+ * determines that the PE cannot possibly be recovered.
+ * Don't modify the PE state if that's the case.
+ */
+ if (eeh_handle_normal_event(pe))
+ continue;
+
eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
} else {
pci_lock_rescan_remove();
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index a38600949f3a..8587059ad848 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -31,7 +31,6 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
-#include <asm/ftrace.h>
#include <asm/ptrace.h>
#include <asm/export.h>
@@ -1315,109 +1314,3 @@ machine_check_in_rtas:
/* XXX load up BATs and panic */
#endif /* CONFIG_PPC_RTAS */
-
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-_GLOBAL(mcount)
-_GLOBAL(_mcount)
- /*
- * It is required that _mcount on PPC32 must preserve the
- * link register. But we have r0 to play with. We use r0
- * to push the return address back to the caller of mcount
- * into the ctr register, restore the link register and
- * then jump back using the ctr register.
- */
- mflr r0
- mtctr r0
- lwz r0, 4(r1)
- mtlr r0
- bctr
-
-_GLOBAL(ftrace_caller)
- MCOUNT_SAVE_FRAME
- /* r3 ends up with link register */
- subi r3, r3, MCOUNT_INSN_SIZE
-.globl ftrace_call
-ftrace_call:
- bl ftrace_stub
- nop
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
- b ftrace_graph_stub
-_GLOBAL(ftrace_graph_stub)
-#endif
- MCOUNT_RESTORE_FRAME
- /* old link register ends up in ctr reg */
- bctr
-#else
-_GLOBAL(mcount)
-_GLOBAL(_mcount)
-
- MCOUNT_SAVE_FRAME
-
- subi r3, r3, MCOUNT_INSN_SIZE
- LOAD_REG_ADDR(r5, ftrace_trace_function)
- lwz r5,0(r5)
-
- mtctr r5
- bctrl
- nop
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- b ftrace_graph_caller
-#endif
- MCOUNT_RESTORE_FRAME
- bctr
-#endif
-EXPORT_SYMBOL(_mcount)
-
-_GLOBAL(ftrace_stub)
- blr
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-_GLOBAL(ftrace_graph_caller)
- /* load r4 with local address */
- lwz r4, 44(r1)
- subi r4, r4, MCOUNT_INSN_SIZE
-
- /* Grab the LR out of the caller stack frame */
- lwz r3,52(r1)
-
- bl prepare_ftrace_return
- nop
-
- /*
- * prepare_ftrace_return gives us the address we divert to.
- * Change the LR in the callers stack frame to this.
- */
- stw r3,52(r1)
-
- MCOUNT_RESTORE_FRAME
- /* old link register ends up in ctr reg */
- bctr
-
-_GLOBAL(return_to_handler)
- /* need to save return values */
- stwu r1, -32(r1)
- stw r3, 20(r1)
- stw r4, 16(r1)
- stw r31, 12(r1)
- mr r31, r1
-
- bl ftrace_return_to_handler
- nop
-
- /* return value has real return address */
- mtlr r3
-
- lwz r3, 20(r1)
- lwz r4, 16(r1)
- lwz r31,12(r1)
- lwz r1, 0(r1)
-
- /* Jump back to real return address */
- blr
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6432d4bf08c8..bfbad08a1207 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -20,7 +20,6 @@
#include <linux/errno.h>
#include <linux/err.h>
-#include <linux/magic.h>
#include <asm/unistd.h>
#include <asm/processor.h>
#include <asm/page.h>
@@ -33,7 +32,6 @@
#include <asm/bug.h>
#include <asm/ptrace.h>
#include <asm/irqflags.h>
-#include <asm/ftrace.h>
#include <asm/hw_irq.h>
#include <asm/context_tracking.h>
#include <asm/tm.h>
@@ -689,7 +687,7 @@ resume_kernel:
addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
- lwz r3,GPR1(r1)
+ ld r3,GPR1(r1)
subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
mr r4,r1 /* src: current exception frame */
mr r1,r3 /* Reroute the trampoline frame to r1 */
@@ -703,8 +701,8 @@ resume_kernel:
addi r6,r6,8
bdnz 2b
- /* Do real store operation to complete stwu */
- lwz r5,GPR1(r1)
+ /* Do real store operation to complete stdu */
+ ld r5,GPR1(r1)
std r8,0(r5)
/* Clear _TIF_EMULATE_STACK_STORE flag */
@@ -1173,381 +1171,3 @@ _GLOBAL(enter_prom)
ld r0,16(r1)
mtlr r0
blr
-
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-_GLOBAL(mcount)
-_GLOBAL(_mcount)
-EXPORT_SYMBOL(_mcount)
- mflr r12
- mtctr r12
- mtlr r0
- bctr
-
-#ifndef CC_USING_MPROFILE_KERNEL
-_GLOBAL_TOC(ftrace_caller)
- /* Taken from output of objdump from lib64/glibc */
- mflr r3
- ld r11, 0(r1)
- stdu r1, -112(r1)
- std r3, 128(r1)
- ld r4, 16(r11)
- subi r3, r3, MCOUNT_INSN_SIZE
-.globl ftrace_call
-ftrace_call:
- bl ftrace_stub
- nop
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
- b ftrace_graph_stub
-_GLOBAL(ftrace_graph_stub)
-#endif
- ld r0, 128(r1)
- mtlr r0
- addi r1, r1, 112
-
-#else /* CC_USING_MPROFILE_KERNEL */
-/*
- *
- * ftrace_caller() is the function that replaces _mcount() when ftrace is
- * active.
- *
- * We arrive here after a function A calls function B, and we are the trace
- * function for B. When we enter r1 points to A's stack frame, B has not yet
- * had a chance to allocate one yet.
- *
- * Additionally r2 may point either to the TOC for A, or B, depending on
- * whether B did a TOC setup sequence before calling us.
- *
- * On entry the LR points back to the _mcount() call site, and r0 holds the
- * saved LR as it was on entry to B, ie. the original return address at the
- * call site in A.
- *
- * Our job is to save the register state into a struct pt_regs (on the stack)
- * and then arrange for the ftrace function to be called.
- */
-_GLOBAL(ftrace_caller)
- /* Save the original return address in A's stack frame */
- std r0,LRSAVE(r1)
-
- /* Create our stack frame + pt_regs */
- stdu r1,-SWITCH_FRAME_SIZE(r1)
-
- /* Save all gprs to pt_regs */
- SAVE_8GPRS(0,r1)
- SAVE_8GPRS(8,r1)
- SAVE_8GPRS(16,r1)
- SAVE_8GPRS(24,r1)
-
- /* Load special regs for save below */
- mfmsr r8
- mfctr r9
- mfxer r10
- mfcr r11
-
- /* Get the _mcount() call site out of LR */
- mflr r7
- /* Save it as pt_regs->nip & pt_regs->link */
- std r7, _NIP(r1)
- std r7, _LINK(r1)
-
- /* Save callee's TOC in the ABI compliant location */
- std r2, 24(r1)
- ld r2,PACATOC(r13) /* get kernel TOC in r2 */
-
- addis r3,r2,function_trace_op@toc@ha
- addi r3,r3,function_trace_op@toc@l
- ld r5,0(r3)
-
-#ifdef CONFIG_LIVEPATCH
- mr r14,r7 /* remember old NIP */
-#endif
- /* Calculate ip from nip-4 into r3 for call below */
- subi r3, r7, MCOUNT_INSN_SIZE
-
- /* Put the original return address in r4 as parent_ip */
- mr r4, r0
-
- /* Save special regs */
- std r8, _MSR(r1)
- std r9, _CTR(r1)
- std r10, _XER(r1)
- std r11, _CCR(r1)
-
- /* Load &pt_regs in r6 for call below */
- addi r6, r1 ,STACK_FRAME_OVERHEAD
-
- /* ftrace_call(r3, r4, r5, r6) */
-.globl ftrace_call
-ftrace_call:
- bl ftrace_stub
- nop
-
- /* Load ctr with the possibly modified NIP */
- ld r3, _NIP(r1)
- mtctr r3
-#ifdef CONFIG_LIVEPATCH
- cmpd r14,r3 /* has NIP been altered? */
-#endif
-
- /* Restore gprs */
- REST_8GPRS(0,r1)
- REST_8GPRS(8,r1)
- REST_8GPRS(16,r1)
- REST_8GPRS(24,r1)
-
- /* Restore callee's TOC */
- ld r2, 24(r1)
-
- /* Pop our stack frame */
- addi r1, r1, SWITCH_FRAME_SIZE
-
- /* Restore original LR for return to B */
- ld r0, LRSAVE(r1)
- mtlr r0
-
-#ifdef CONFIG_LIVEPATCH
- /* Based on the cmpd above, if the NIP was altered handle livepatch */
- bne- livepatch_handler
-#endif
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- stdu r1, -112(r1)
-.globl ftrace_graph_call
-ftrace_graph_call:
- b ftrace_graph_stub
-_GLOBAL(ftrace_graph_stub)
- addi r1, r1, 112
-#endif
-
- ld r0,LRSAVE(r1) /* restore callee's lr at _mcount site */
- mtlr r0
- bctr /* jump after _mcount site */
-#endif /* CC_USING_MPROFILE_KERNEL */
-
-_GLOBAL(ftrace_stub)
- blr
-
-#ifdef CONFIG_LIVEPATCH
- /*
- * This function runs in the mcount context, between two functions. As
- * such it can only clobber registers which are volatile and used in
- * function linkage.
- *
- * We get here when a function A, calls another function B, but B has
- * been live patched with a new function C.
- *
- * On entry:
- * - we have no stack frame and can not allocate one
- * - LR points back to the original caller (in A)
- * - CTR holds the new NIP in C
- * - r0 & r12 are free
- *
- * r0 can't be used as the base register for a DS-form load or store, so
- * we temporarily shuffle r1 (stack pointer) into r0 and then put it back.
- */
-livepatch_handler:
- CURRENT_THREAD_INFO(r12, r1)
-
- /* Save stack pointer into r0 */
- mr r0, r1
-
- /* Allocate 3 x 8 bytes */
- ld r1, TI_livepatch_sp(r12)
- addi r1, r1, 24
- std r1, TI_livepatch_sp(r12)
-
- /* Save toc & real LR on livepatch stack */
- std r2, -24(r1)
- mflr r12
- std r12, -16(r1)
-
- /* Store stack end marker */
- lis r12, STACK_END_MAGIC@h
- ori r12, r12, STACK_END_MAGIC@l
- std r12, -8(r1)
-
- /* Restore real stack pointer */
- mr r1, r0
-
- /* Put ctr in r12 for global entry and branch there */
- mfctr r12
- bctrl
-
- /*
- * Now we are returning from the patched function to the original
- * caller A. We are free to use r0 and r12, and we can use r2 until we
- * restore it.
- */
-
- CURRENT_THREAD_INFO(r12, r1)
-
- /* Save stack pointer into r0 */
- mr r0, r1
-
- ld r1, TI_livepatch_sp(r12)
-
- /* Check stack marker hasn't been trashed */
- lis r2, STACK_END_MAGIC@h
- ori r2, r2, STACK_END_MAGIC@l
- ld r12, -8(r1)
-1: tdne r12, r2
- EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
-
- /* Restore LR & toc from livepatch stack */
- ld r12, -16(r1)
- mtlr r12
- ld r2, -24(r1)
-
- /* Pop livepatch stack frame */
- CURRENT_THREAD_INFO(r12, r0)
- subi r1, r1, 24
- std r1, TI_livepatch_sp(r12)
-
- /* Restore real stack pointer */
- mr r1, r0
-
- /* Return to original caller of live patched function */
- blr
-#endif
-
-
-#else
-_GLOBAL_TOC(_mcount)
-EXPORT_SYMBOL(_mcount)
- /* Taken from output of objdump from lib64/glibc */
- mflr r3
- ld r11, 0(r1)
- stdu r1, -112(r1)
- std r3, 128(r1)
- ld r4, 16(r11)
-
- subi r3, r3, MCOUNT_INSN_SIZE
- LOAD_REG_ADDR(r5,ftrace_trace_function)
- ld r5,0(r5)
- ld r5,0(r5)
- mtctr r5
- bctrl
- nop
-
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- b ftrace_graph_caller
-#endif
- ld r0, 128(r1)
- mtlr r0
- addi r1, r1, 112
-_GLOBAL(ftrace_stub)
- blr
-
-#endif /* CONFIG_DYNAMIC_FTRACE */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-#ifndef CC_USING_MPROFILE_KERNEL
-_GLOBAL(ftrace_graph_caller)
- /* load r4 with local address */
- ld r4, 128(r1)
- subi r4, r4, MCOUNT_INSN_SIZE
-
- /* Grab the LR out of the caller stack frame */
- ld r11, 112(r1)
- ld r3, 16(r11)
-
- bl prepare_ftrace_return
- nop
-
- /*
- * prepare_ftrace_return gives us the address we divert to.
- * Change the LR in the callers stack frame to this.
- */
- ld r11, 112(r1)
- std r3, 16(r11)
-
- ld r0, 128(r1)
- mtlr r0
- addi r1, r1, 112
- blr
-
-#else /* CC_USING_MPROFILE_KERNEL */
-_GLOBAL(ftrace_graph_caller)
- /* with -mprofile-kernel, parameter regs are still alive at _mcount */
- std r10, 104(r1)
- std r9, 96(r1)
- std r8, 88(r1)
- std r7, 80(r1)
- std r6, 72(r1)
- std r5, 64(r1)
- std r4, 56(r1)
- std r3, 48(r1)
-
- /* Save callee's TOC in the ABI compliant location */
- std r2, 24(r1)
- ld r2, PACATOC(r13) /* get kernel TOC in r2 */
-
- mfctr r4 /* ftrace_caller has moved local addr here */
- std r4, 40(r1)
- mflr r3 /* ftrace_caller has restored LR from stack */
- subi r4, r4, MCOUNT_INSN_SIZE
-
- bl prepare_ftrace_return
- nop
-
- /*
- * prepare_ftrace_return gives us the address we divert to.
- * Change the LR to this.
- */
- mtlr r3
-
- ld r0, 40(r1)
- mtctr r0
- ld r10, 104(r1)
- ld r9, 96(r1)
- ld r8, 88(r1)
- ld r7, 80(r1)
- ld r6, 72(r1)
- ld r5, 64(r1)
- ld r4, 56(r1)
- ld r3, 48(r1)
-
- /* Restore callee's TOC */
- ld r2, 24(r1)
-
- addi r1, r1, 112
- mflr r0
- std r0, LRSAVE(r1)
- bctr
-#endif /* CC_USING_MPROFILE_KERNEL */
-
-_GLOBAL(return_to_handler)
- /* need to save return values */
- std r4, -32(r1)
- std r3, -24(r1)
- /* save TOC */
- std r2, -16(r1)
- std r31, -8(r1)
- mr r31, r1
- stdu r1, -112(r1)
-
- /*
- * We might be called from a module.
- * Switch to our TOC to run inside the core kernel.
- */
- ld r2, PACATOC(r13)
-
- bl ftrace_return_to_handler
- nop
-
- /* return value has real return address */
- mtlr r3
-
- ld r1, 0(r1)
- ld r4, -32(r1)
- ld r3, -24(r1)
- ld r2, -16(r1)
- ld r31, -8(r1)
-
- /* Jump back to real return address */
- blr
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-#endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 857bf7c5b946..a9312b52fe6f 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -116,9 +116,11 @@ EXC_VIRT_NONE(0x4000, 0x100)
EXC_REAL_BEGIN(system_reset, 0x100, 0x100)
SET_SCRATCH0(r13)
- GET_PACA(r13)
- clrrdi r13,r13,1 /* Last bit of HSPRG0 is set if waking from winkle */
- EXCEPTION_PROLOG_PSERIES_PACA(PACA_EXGEN, system_reset_common, EXC_STD,
+ /*
+ * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
+ * being used, so a nested NMI exception would corrupt it.
+ */
+ EXCEPTION_PROLOG_PSERIES_NORI(PACA_EXNMI, system_reset_common, EXC_STD,
IDLETEST, 0x100)
EXC_REAL_END(system_reset, 0x100, 0x100)
@@ -126,34 +128,37 @@ EXC_VIRT_NONE(0x4100, 0x100)
#ifdef CONFIG_PPC_P7_NAP
EXC_COMMON_BEGIN(system_reset_idle_common)
-BEGIN_FTR_SECTION
- GET_PACA(r13) /* Restore HSPRG0 to get the winkle bit in r13 */
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
- bl pnv_restore_hyp_resource
+ b pnv_powersave_wakeup
+#endif
- li r0,PNV_THREAD_RUNNING
- stb r0,PACA_THREAD_IDLE_STATE(r13) /* Clear thread state */
+EXC_COMMON_BEGIN(system_reset_common)
+ /*
+ * Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able
+ * to recover, but nested NMI will notice in_nmi and not recover
+ * because of the use of the NMI stack. in_nmi reentrancy is tested in
+ * system_reset_exception.
+ */
+ lhz r10,PACA_IN_NMI(r13)
+ addi r10,r10,1
+ sth r10,PACA_IN_NMI(r13)
+ li r10,MSR_RI
+ mtmsrd r10,1
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- li r0,KVM_HWTHREAD_IN_KERNEL
- stb r0,HSTATE_HWTHREAD_STATE(r13)
- /* Order setting hwthread_state vs. testing hwthread_req */
- sync
- lbz r0,HSTATE_HWTHREAD_REQ(r13)
- cmpwi r0,0
- beq 1f
- BRANCH_TO_KVM(r10, kvm_start_guest)
-1:
-#endif
+ mr r10,r1
+ ld r1,PACA_NMI_EMERG_SP(r13)
+ subi r1,r1,INT_FRAME_SIZE
+ EXCEPTION_COMMON_NORET_STACK(PACA_EXNMI, 0x100,
+ system_reset, system_reset_exception,
+ ADD_NVGPRS;ADD_RECONCILE)
- /* Return SRR1 from power7_nap() */
- mfspr r3,SPRN_SRR1
- blt cr3,2f
- b pnv_wakeup_loss
-2: b pnv_wakeup_noloss
-#endif
+ /*
+ * The stack is no longer in use, decrement in_nmi.
+ */
+ lhz r10,PACA_IN_NMI(r13)
+ subi r10,r10,1
+ sth r10,PACA_IN_NMI(r13)
-EXC_COMMON(system_reset_common, 0x100, system_reset_exception)
+ b ret_from_except
#ifdef CONFIG_PPC_PSERIES
/*
@@ -161,8 +166,9 @@ EXC_COMMON(system_reset_common, 0x100, system_reset_exception)
*/
TRAMP_REAL_BEGIN(system_reset_fwnmi)
SET_SCRATCH0(r13) /* save r13 */
- EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
- NOTEST, 0x100)
+ /* See comment at system_reset exception */
+ EXCEPTION_PROLOG_PSERIES_NORI(PACA_EXNMI, system_reset_common,
+ EXC_STD, NOTEST, 0x100)
#endif /* CONFIG_PPC_PSERIES */
@@ -172,14 +178,6 @@ EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
* vector
*/
SET_SCRATCH0(r13) /* save r13 */
- /*
- * Running native on arch 2.06 or later, we may wakeup from winkle
- * inside machine check. If yes, then last bit of HSPRG0 would be set
- * to 1. Hence clear it unconditionally.
- */
- GET_PACA(r13)
- clrrdi r13,r13,1
- SET_PACA(r13)
EXCEPTION_PROLOG_0(PACA_EXMC)
BEGIN_FTR_SECTION
b machine_check_powernv_early
@@ -212,6 +210,12 @@ BEGIN_FTR_SECTION
* NOTE: We are here with MSR_ME=0 (off), which means we risk a
* checkstop if we get another machine check exception before we do
* rfid with MSR_ME=1.
+ *
+ * This interrupt can wake directly from idle. If that is the case,
+ * the machine check is handled then the idle wakeup code is called
+ * to restore state. In that case, the POWER9 DD1 idle PACA workaround
+ * is not applied in the early machine check code, which will cause
+ * bugs.
*/
mr r11,r1 /* Save r1 */
lhz r10,PACA_IN_MCE(r13)
@@ -268,20 +272,11 @@ machine_check_fwnmi:
machine_check_pSeries_0:
EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200)
/*
- * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the
- * difference that MSR_RI is not enabled, because PACA_EXMC is being
- * used, so nested machine check corrupts it. machine_check_common
- * enables MSR_RI.
+ * MSR_RI is not enabled, because PACA_EXMC is being used, so a
+ * nested machine check corrupts it. machine_check_common enables
+ * MSR_RI.
*/
- ld r10,PACAKMSR(r13)
- xori r10,r10,MSR_RI
- mfspr r11,SPRN_SRR0
- LOAD_HANDLER(r12, machine_check_common)
- mtspr SPRN_SRR0,r12
- mfspr r12,SPRN_SRR1
- mtspr SPRN_SRR1,r10
- rfid
- b . /* prevent speculative execution */
+ EXCEPTION_PROLOG_PSERIES_1_NORI(machine_check_common, EXC_STD)
TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
@@ -340,6 +335,37 @@ EXC_COMMON_BEGIN(machine_check_common)
/* restore original r1. */ \
ld r1,GPR1(r1)
+#ifdef CONFIG_PPC_P7_NAP
+/*
+ * This is an idle wakeup. Low level machine check has already been
+ * done. Queue the event then call the idle code to do the wake up.
+ */
+EXC_COMMON_BEGIN(machine_check_idle_common)
+ bl machine_check_queue_event
+
+ /*
+ * We have not used any non-volatile GPRs here, and as a rule
+ * most exception code including machine check does not.
+ * Therefore PACA_NAPSTATELOST does not need to be set. Idle
+ * wakeup will restore volatile registers.
+ *
+ * Load the original SRR1 into r3 for pnv_powersave_wakeup_mce.
+ *
+ * Then decrement MCE nesting after finishing with the stack.
+ */
+ ld r3,_MSR(r1)
+
+ lhz r11,PACA_IN_MCE(r13)
+ subi r11,r11,1
+ sth r11,PACA_IN_MCE(r13)
+
+ /* Turn off the RI bit because SRR1 is used by idle wakeup code. */
+ /* Recoverability could be improved by reducing the use of SRR1. */
+ li r11,0
+ mtmsrd r11,1
+
+ b pnv_powersave_wakeup_mce
+#endif
/*
* Handle machine check early in real mode. We come here with
* ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack.
@@ -352,6 +378,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
bl machine_check_early
std r3,RESULT(r1) /* Save result */
ld r12,_MSR(r1)
+
#ifdef CONFIG_PPC_P7_NAP
/*
* Check if thread was in power saving mode. We come here when any
@@ -362,48 +389,14 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
*
* Go back to nap/sleep/winkle mode again if (b) is true.
*/
- rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */
- beq 4f /* No, it wasn;t */
- /* Thread was in power saving mode. Go back to nap again. */
- cmpwi r11,2
- blt 3f
- /* Supervisor/Hypervisor state loss */
- li r0,1
- stb r0,PACA_NAPSTATELOST(r13)
-3: bl machine_check_queue_event
- MACHINE_CHECK_HANDLER_WINDUP
- GET_PACA(r13)
- ld r1,PACAR1(r13)
- /*
- * Check what idle state this CPU was in and go back to same mode
- * again.
- */
- lbz r3,PACA_THREAD_IDLE_STATE(r13)
- cmpwi r3,PNV_THREAD_NAP
- bgt 10f
- IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
- /* No return */
-10:
- cmpwi r3,PNV_THREAD_SLEEP
- bgt 2f
- IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
- /* No return */
-
-2:
- /*
- * Go back to winkle. Please note that this thread was woken up in
- * machine check from winkle and have not restored the per-subcore
- * state. Hence before going back to winkle, set last bit of HSPRG0
- * to 1. This will make sure that if this thread gets woken up
- * again at reset vector 0x100 then it will get chance to restore
- * the subcore state.
- */
- ori r13,r13,1
- SET_PACA(r13)
- IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
- /* No return */
+ BEGIN_FTR_SECTION
+ rlwinm. r11,r12,47-31,30,31
+ beq- 4f
+ BRANCH_TO_COMMON(r10, machine_check_idle_common)
4:
+ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
#endif
+
/*
* Check if we are coming from hypervisor userspace. If yes then we
* continue in host kernel in V mode to deliver the MC event.
@@ -968,21 +961,16 @@ EXC_VIRT_NONE(0x4e60, 0x20)
TRAMP_KVM_HV(PACA_EXGEN, 0xe60)
TRAMP_REAL_BEGIN(hmi_exception_early)
EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, 0xe60)
- mr r10,r1 /* Save r1 */
- ld r1,PACAEMERGSP(r13) /* Use emergency stack */
+ mr r10,r1 /* Save r1 */
+ ld r1,PACAEMERGSP(r13) /* Use emergency stack for realmode */
subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
- std r9,_CCR(r1) /* save CR in stackframe */
mfspr r11,SPRN_HSRR0 /* Save HSRR0 */
- std r11,_NIP(r1) /* save HSRR0 in stackframe */
- mfspr r12,SPRN_HSRR1 /* Save SRR1 */
- std r12,_MSR(r1) /* save SRR1 in stackframe */
- std r10,0(r1) /* make stack chain pointer */
- std r0,GPR0(r1) /* save r0 in stackframe */
- std r10,GPR1(r1) /* save r1 in stackframe */
+ mfspr r12,SPRN_HSRR1 /* Save HSRR1 */
+ EXCEPTION_PROLOG_COMMON_1()
EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN)
EXCEPTION_PROLOG_COMMON_3(0xe60)
addi r3,r1,STACK_FRAME_OVERHEAD
- BRANCH_LINK_TO_FAR(r4, hmi_exception_realmode)
+ BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */
/* Windup the stack. */
/* Move original HSRR0 and HSRR1 into the respective regs */
ld r9,_MSR(r1)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 8ff0dd4e77a7..466569e26278 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -30,17 +30,16 @@
#include <linux/string.h>
#include <linux/memblock.h>
#include <linux/delay.h>
-#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/crash_dump.h>
#include <linux/kobject.h>
#include <linux/sysfs.h>
+#include <asm/debugfs.h>
#include <asm/page.h>
#include <asm/prom.h>
#include <asm/rtas.h>
#include <asm/fadump.h>
-#include <asm/debug.h>
#include <asm/setup.h>
static struct fw_dump fw_dump;
@@ -210,14 +209,20 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
*/
static inline unsigned long fadump_calculate_reserve_size(void)
{
- unsigned long size;
+ int ret;
+ unsigned long long base, size;
/*
- * Check if the size is specified through fadump_reserve_mem= cmdline
- * option. If yes, then use that.
+ * Check if the size is specified through crashkernel= cmdline
+ * option. If yes, then use that but ignore base as fadump
+ * reserves memory at end of RAM.
*/
- if (fw_dump.reserve_bootvar)
+ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+ &size, &base);
+ if (ret == 0 && size > 0) {
+ fw_dump.reserve_bootvar = (unsigned long)size;
return fw_dump.reserve_bootvar;
+ }
/* divide by 20 to get 5% of value */
size = memblock_end_of_DRAM() / 20;
@@ -319,15 +324,34 @@ int __init fadump_reserve_mem(void)
pr_debug("fadumphdr_addr = %p\n",
(void *) fw_dump.fadumphdr_addr);
} else {
- /* Reserve the memory at the top of memory. */
size = get_fadump_area_size();
- base = memory_boundary - size;
- memblock_reserve(base, size);
- printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
- "for firmware-assisted dump\n",
- (unsigned long)(size >> 20),
- (unsigned long)(base >> 20));
+
+ /*
+ * Reserve memory at an offset closer to bottom of the RAM to
+ * minimize the impact of memory hot-remove operation. We can't
+ * use memblock_find_in_range() here since it doesn't allocate
+ * from bottom to top.
+ */
+ for (base = fw_dump.boot_memory_size;
+ base <= (memory_boundary - size);
+ base += size) {
+ if (memblock_is_region_memory(base, size) &&
+ !memblock_is_region_reserved(base, size))
+ break;
+ }
+ if ((base > (memory_boundary - size)) ||
+ memblock_reserve(base, size)) {
+ pr_err("Failed to reserve memory\n");
+ return 0;
+ }
+
+ pr_info("Reserved %ldMB of memory at %ldMB for firmware-"
+ "assisted dump (System RAM: %ldMB)\n",
+ (unsigned long)(size >> 20),
+ (unsigned long)(base >> 20),
+ (unsigned long)(memblock_phys_mem_size() >> 20));
}
+
fw_dump.reserve_dump_area_start = base;
fw_dump.reserve_dump_area_size = size;
return 1;
@@ -353,15 +377,6 @@ static int __init early_fadump_param(char *p)
}
early_param("fadump", early_fadump_param);
-/* Look for fadump_reserve_mem= cmdline option */
-static int __init early_fadump_reserve_mem(char *p)
-{
- if (p)
- fw_dump.reserve_bootvar = memparse(p, &p);
- return 0;
-}
-early_param("fadump_reserve_mem", early_fadump_reserve_mem);
-
static void register_fw_dump(struct fadump_mem_struct *fdm)
{
int rc;
@@ -509,34 +524,6 @@ fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
return reg_entry;
}
-static u32 *fadump_append_elf_note(u32 *buf, char *name, unsigned type,
- void *data, size_t data_len)
-{
- struct elf_note note;
-
- note.n_namesz = strlen(name) + 1;
- note.n_descsz = data_len;
- note.n_type = type;
- memcpy(buf, &note, sizeof(note));
- buf += (sizeof(note) + 3)/4;
- memcpy(buf, name, note.n_namesz);
- buf += (note.n_namesz + 3)/4;
- memcpy(buf, data, note.n_descsz);
- buf += (note.n_descsz + 3)/4;
-
- return buf;
-}
-
-static void fadump_final_note(u32 *buf)
-{
- struct elf_note note;
-
- note.n_namesz = 0;
- note.n_descsz = 0;
- note.n_type = 0;
- memcpy(buf, &note, sizeof(note));
-}
-
static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
{
struct elf_prstatus prstatus;
@@ -547,8 +534,8 @@ static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
* prstatus.pr_pid = ????
*/
elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
- buf = fadump_append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
- &prstatus, sizeof(prstatus));
+ buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+ &prstatus, sizeof(prstatus));
return buf;
}
@@ -689,7 +676,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
}
}
- fadump_final_note(note_buf);
+ final_note(note_buf);
if (fdh) {
pr_debug("Updating elfcore header (%llx) with cpu notes\n",
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 1607be7c0ef2..e22734278458 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -735,11 +735,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
EXCEPTION(0x2c00, Trap_2c, unknown_exception, EXC_XFER_EE)
EXCEPTION(0x2d00, Trap_2d, unknown_exception, EXC_XFER_EE)
EXCEPTION(0x2e00, Trap_2e, unknown_exception, EXC_XFER_EE)
- EXCEPTION(0x2f00, MOLTrampoline, unknown_exception, EXC_XFER_EE_LITE)
-
- .globl mol_trampoline
- .set mol_trampoline, i0x2f00
- EXPORT_SYMBOL(mol_trampoline)
+ EXCEPTION(0x2f00, Trap_2f, unknown_exception, EXC_XFER_EE)
. = 0x3000
@@ -1278,16 +1274,6 @@ EXPORT_SYMBOL(empty_zero_page)
swapper_pg_dir:
.space PGD_TABLE_SIZE
- .globl intercept_table
-intercept_table:
- .long 0, 0, i0x200, i0x300, i0x400, 0, i0x600, i0x700
- .long i0x800, 0, 0, 0, 0, i0xd00, 0, 0
- .long 0, 0, 0, i0x1300, 0, 0, 0, 0
- .long 0, 0, 0, 0, 0, 0, 0, 0
- .long 0, 0, 0, 0, 0, 0, 0, 0
- .long 0, 0, 0, 0, 0, 0, 0, 0
-EXPORT_SYMBOL(intercept_table)
-
/* Room for two PTE pointers, usually the kernel and current user pointers
* to their respective root page table.
*/
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 1dc5eae2ced3..0ddc602b33a4 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -949,7 +949,8 @@ start_here_multiplatform:
LOAD_REG_ADDR(r3,init_thread_union)
/* set up a stack pointer */
- addi r1,r3,THREAD_SIZE
+ LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
+ add r1,r3,r1
li r0,0
stdu r0,-STACK_FRAME_OVERHEAD(r1)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 5f61cc0349c0..07d4e0ad60db 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -20,6 +20,7 @@
#include <asm/kvm_book3s_asm.h>
#include <asm/opal.h>
#include <asm/cpuidle.h>
+#include <asm/exception-64s.h>
#include <asm/book3s/64/mmu-hash.h>
#include <asm/mmu.h>
@@ -94,12 +95,12 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
core_idle_lock_held:
HMT_LOW
3: lwz r15,0(r14)
- andi. r15,r15,PNV_CORE_IDLE_LOCK_BIT
+ andis. r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
bne 3b
HMT_MEDIUM
lwarx r15,0,r14
- andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
- bne core_idle_lock_held
+ andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ bne- core_idle_lock_held
blr
/*
@@ -113,7 +114,7 @@ core_idle_lock_held:
*
* Address to 'rfid' to in r5
*/
-_GLOBAL(pnv_powersave_common)
+pnv_powersave_common:
/* Use r3 to pass state nap/sleep/winkle */
/* NAP is a state loss, we create a regs frame on the
* stack, fill it up with the state we care about and
@@ -188,8 +189,8 @@ pnv_enter_arch207_idle_mode:
/* The following store to HSTATE_HWTHREAD_STATE(r13) */
/* MUST occur in real mode, i.e. with the MMU off, */
/* and the MMU must stay off until we clear this flag */
- /* and test HSTATE_HWTHREAD_REQ(r13) in the system */
- /* reset interrupt vector in exceptions-64s.S. */
+ /* and test HSTATE_HWTHREAD_REQ(r13) in */
+ /* pnv_powersave_wakeup in this file. */
/* The reason is that another thread can switch the */
/* MMU to a guest context whenever this flag is set */
/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on, */
@@ -209,15 +210,20 @@ pnv_enter_arch207_idle_mode:
/* Sleep or winkle */
lbz r7,PACA_THREAD_MASK(r13)
ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
+ li r5,0
+ beq cr3,3f
+ lis r5,PNV_CORE_IDLE_WINKLE_COUNT@h
+3:
lwarx_loop1:
lwarx r15,0,r14
- andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
- bnel core_idle_lock_held
+ andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ bnel- core_idle_lock_held
+ add r15,r15,r5 /* Add if winkle */
andc r15,r15,r7 /* Clear thread bit */
- andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS
+ andi. r9,r15,PNV_CORE_IDLE_THREAD_BITS
/*
* If cr0 = 0, then current thread is the last thread of the core entering
@@ -240,7 +246,7 @@ common_enter: /* common code for all the threads entering sleep or winkle */
IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
fastsleep_workaround_at_entry:
- ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
+ oris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
stwcx. r15,0,r14
bne- lwarx_loop1
isync
@@ -250,10 +256,10 @@ fastsleep_workaround_at_entry:
li r4,1
bl opal_config_cpu_idle_state
- /* Clear Lock bit */
- li r0,0
+ /* Unlock */
+ xoris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
lwsync
- stw r0,0(r14)
+ stw r15,0(r14)
b common_enter
enter_winkle:
@@ -276,19 +282,21 @@ power_enter_stop:
*/
andis. r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
clrldi r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
- bne 1f
+ bne .Lhandle_esl_ec_set
IDLE_STATE_ENTER_SEQ(PPC_STOP)
li r3,0 /* Since we didn't lose state, return 0 */
b pnv_wakeup_noloss
+
+.Lhandle_esl_ec_set:
/*
* Check if the requested state is a deep idle state.
*/
-1: LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+ LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
ld r4,ADDROFF(pnv_first_deep_stop_state)(r5)
cmpd r3,r4
- bge 2f
+ bge .Lhandle_deep_stop
IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP)
-2:
+.Lhandle_deep_stop:
/*
* Entering deep idle state.
* Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
@@ -299,8 +307,8 @@ power_enter_stop:
lwarx_loop_stop:
lwarx r15,0,r14
- andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
- bnel core_idle_lock_held
+ andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ bnel- core_idle_lock_held
andc r15,r15,r7 /* Clear thread bit */
stwcx. r15,0,r14
@@ -373,17 +381,113 @@ _GLOBAL(power9_idle_stop)
li r4,1
b pnv_powersave_common
/* No return */
+
/*
- * Called from reset vector. Check whether we have woken up with
- * hypervisor state loss. If yes, restore hypervisor state and return
- * back to reset vector.
+ * On waking up from stop 0,1,2 with ESL=1 on POWER9 DD1,
+ * HSPRG0 will be set to the HSPRG0 value of one of the
+ * threads in this core. Thus the value we have in r13
+ * may not be this thread's paca pointer.
*
- * r13 - Contents of HSPRG0
+ * Fortunately, the TIR remains invariant. Since this thread's
+ * paca pointer is recorded in all its sibling's paca, we can
+ * correctly recover this thread's paca pointer if we
+ * know the index of this thread in the core.
+ *
+ * This index can be obtained from the TIR.
+ *
+ * i.e, thread's position in the core = TIR.
+ * If this value is i, then this thread's paca is
+ * paca->thread_sibling_pacas[i].
+ */
+power9_dd1_recover_paca:
+ mfspr r4, SPRN_TIR
+ /*
+ * Since each entry in thread_sibling_pacas is 8 bytes
+ * we need to left-shift by 3 bits. Thus r4 = i * 8
+ */
+ sldi r4, r4, 3
+ /* Get &paca->thread_sibling_pacas[0] in r5 */
+ ld r5, PACA_SIBLING_PACA_PTRS(r13)
+ /* Load paca->thread_sibling_pacas[i] into r13 */
+ ldx r13, r4, r5
+ SET_PACA(r13)
+ /*
+ * Indicate that we have lost NVGPR state
+ * which needs to be restored from the stack.
+ */
+ li r3, 1
+ stb r0,PACA_NAPSTATELOST(r13)
+ blr
+
+/*
+ * Called from machine check handler for powersave wakeups.
+ * Low level machine check processing has already been done. Now just
+ * go through the wake up path to get everything in order.
+ *
+ * r3 - The original SRR1 value.
+ * Original SRR[01] have been clobbered.
+ * MSR_RI is clear.
+ */
+.global pnv_powersave_wakeup_mce
+pnv_powersave_wakeup_mce:
+ /* Set cr3 for pnv_powersave_wakeup */
+ rlwinm r11,r3,47-31,30,31
+ cmpwi cr3,r11,2
+
+ /*
+ * Now put the original SRR1 with SRR1_WAKEMCE_RESVD as the wake
+ * reason into SRR1, which allows reuse of the system reset wakeup
+ * code without being mistaken for another type of wakeup.
+ */
+ oris r3,r3,SRR1_WAKEMCE_RESVD@h
+ mtspr SPRN_SRR1,r3
+
+ b pnv_powersave_wakeup
+
+/*
+ * Called from reset vector for powersave wakeups.
* cr3 - set to gt if waking up with partial/complete hypervisor state loss
*/
-_GLOBAL(pnv_restore_hyp_resource)
+.global pnv_powersave_wakeup
+pnv_powersave_wakeup:
+ ld r2, PACATOC(r13)
+
BEGIN_FTR_SECTION
- ld r2,PACATOC(r13);
+BEGIN_FTR_SECTION_NESTED(70)
+ bl power9_dd1_recover_paca
+END_FTR_SECTION_NESTED_IFSET(CPU_FTR_POWER9_DD1, 70)
+ bl pnv_restore_hyp_resource_arch300
+FTR_SECTION_ELSE
+ bl pnv_restore_hyp_resource_arch207
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
+
+ li r0,PNV_THREAD_RUNNING
+ stb r0,PACA_THREAD_IDLE_STATE(r13) /* Clear thread state */
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ li r0,KVM_HWTHREAD_IN_KERNEL
+ stb r0,HSTATE_HWTHREAD_STATE(r13)
+ /* Order setting hwthread_state vs. testing hwthread_req */
+ sync
+ lbz r0,HSTATE_HWTHREAD_REQ(r13)
+ cmpwi r0,0
+ beq 1f
+ b kvm_start_guest
+1:
+#endif
+
+ /* Return SRR1 from power7_nap() */
+ mfspr r3,SPRN_SRR1
+ blt cr3,pnv_wakeup_noloss
+ b pnv_wakeup_loss
+
+/*
+ * Check whether we have woken up with hypervisor state loss.
+ * If yes, restore hypervisor state and return back to link.
+ *
+ * cr3 - set to gt if waking up with partial/complete hypervisor state loss
+ */
+pnv_restore_hyp_resource_arch300:
/*
* POWER ISA 3. Use PSSCR to determine if we
* are waking up from deep idle state
@@ -398,31 +502,19 @@ BEGIN_FTR_SECTION
*/
rldicl r5,r5,4,60
cmpd cr4,r5,r4
- bge cr4,pnv_wakeup_tb_loss
- /*
- * Waking up without hypervisor state loss. Return to
- * reset vector
- */
- blr
+ bge cr4,pnv_wakeup_tb_loss /* returns to caller */
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+ blr /* Waking up without hypervisor state loss. */
+/* Same calling convention as arch300 */
+pnv_restore_hyp_resource_arch207:
/*
* POWER ISA 2.07 or less.
- * Check if last bit of HSPGR0 is set. This indicates whether we are
- * waking up from winkle.
+ * Check if we slept with sleep or winkle.
*/
- clrldi r5,r13,63
- clrrdi r13,r13,1
-
- /* Now that we are sure r13 is corrected, load TOC */
- ld r2,PACATOC(r13);
- cmpwi cr4,r5,1
- mtspr SPRN_HSPRG0,r13
-
- lbz r0,PACA_THREAD_IDLE_STATE(r13)
- cmpwi cr2,r0,PNV_THREAD_NAP
- bgt cr2,pnv_wakeup_tb_loss /* Either sleep or Winkle */
+ lbz r4,PACA_THREAD_IDLE_STATE(r13)
+ cmpwi cr2,r4,PNV_THREAD_NAP
+ bgt cr2,pnv_wakeup_tb_loss /* Either sleep or Winkle */
/*
* We fall through here if PACA_THREAD_IDLE_STATE shows we are waking
@@ -431,8 +523,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
*/
bgt cr3,.
- blr /* Return back to System Reset vector from where
- pnv_restore_hyp_resource was invoked */
+ blr /* Waking up without hypervisor state loss */
/*
* Called if waking up from idle state which can cause either partial or
@@ -442,14 +533,33 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
*
* r13 - PACA
* cr3 - gt if waking up with partial/complete hypervisor state loss
+ *
+ * If ISA300:
* cr4 - gt or eq if waking up from complete hypervisor state loss.
+ *
+ * If ISA207:
+ * r4 - PACA_THREAD_IDLE_STATE
*/
-_GLOBAL(pnv_wakeup_tb_loss)
+pnv_wakeup_tb_loss:
ld r1,PACAR1(r13)
/*
- * Before entering any idle state, the NVGPRs are saved in the stack
- * and they are restored before switching to the process context. Hence
- * until they are restored, they are free to be used.
+ * Before entering any idle state, the NVGPRs are saved in the stack.
+ * If there was a state loss, or PACA_NAPSTATELOST was set, then the
+ * NVGPRs are restored. If we are here, it is likely that state is lost,
+ * but not guaranteed -- neither ISA207 nor ISA300 tests to reach
+ * here are the same as the test to restore NVGPRS:
+ * PACA_THREAD_IDLE_STATE test for ISA207, PSSCR test for ISA300,
+ * and SRR1 test for restoring NVGPRs.
+ *
+ * We are about to clobber NVGPRs now, so set NAPSTATELOST to
+ * guarantee they will always be restored. This might be tightened
+ * with careful reading of specs (particularly for ISA300) but this
+ * is already a slow wakeup path and it's simpler to be safe.
+ */
+ li r0,1
+ stb r0,PACA_NAPSTATELOST(r13)
+
+ /*
*
* Save SRR1 and LR in NVGPRs as they might be clobbered in
* opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
@@ -457,18 +567,19 @@ _GLOBAL(pnv_wakeup_tb_loss)
* is required to return back to reset vector after hypervisor state
* restore is complete.
*/
+ mr r18,r4
mflr r17
mfspr r16,SPRN_SRR1
BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
- lbz r7,PACA_THREAD_MASK(r13)
ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
-lwarx_loop2:
- lwarx r15,0,r14
- andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
+ lbz r7,PACA_THREAD_MASK(r13)
+
/*
+ * Take the core lock to synchronize against other threads.
+ *
* Lock bit is set in one of the 2 cases-
* a. In the sleep/winkle enter path, the last thread is executing
* fastsleep workaround code.
@@ -476,23 +587,93 @@ lwarx_loop2:
* workaround undo code or resyncing timebase or restoring context
* In either case loop until the lock bit is cleared.
*/
- bnel core_idle_lock_held
+1:
+ lwarx r15,0,r14
+ andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ bnel- core_idle_lock_held
+ oris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ stwcx. r15,0,r14
+ bne- 1b
+ isync
- cmpwi cr2,r15,0
+ andi. r9,r15,PNV_CORE_IDLE_THREAD_BITS
+ cmpwi cr2,r9,0
/*
* At this stage
* cr2 - eq if first thread to wakeup in core
* cr3- gt if waking up with partial/complete hypervisor state loss
+ * ISA300:
* cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
- ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
- stwcx. r15,0,r14
- bne- lwarx_loop2
- isync
-
BEGIN_FTR_SECTION
+ /*
+ * Were we in winkle?
+ * If yes, check if all threads were in winkle, decrement our
+ * winkle count, set all thread winkle bits if all were in winkle.
+ * Check if our thread has a winkle bit set, and set cr4 accordingly
+ * (to match ISA300, above). Pseudo-code for core idle state
+ * transitions for ISA207 is as follows (everything happens atomically
+ * due to store conditional and/or lock bit):
+ *
+ * nap_idle() { }
+ * nap_wake() { }
+ *
+ * sleep_idle()
+ * {
+ * core_idle_state &= ~thread_in_core
+ * }
+ *
+ * sleep_wake()
+ * {
+ * bool first_in_core, first_in_subcore;
+ *
+ * first_in_core = (core_idle_state & IDLE_THREAD_BITS) == 0;
+ * first_in_subcore = (core_idle_state & SUBCORE_SIBLING_MASK) == 0;
+ *
+ * core_idle_state |= thread_in_core;
+ * }
+ *
+ * winkle_idle()
+ * {
+ * core_idle_state &= ~thread_in_core;
+ * core_idle_state += 1 << WINKLE_COUNT_SHIFT;
+ * }
+ *
+ * winkle_wake()
+ * {
+ * bool first_in_core, first_in_subcore, winkle_state_lost;
+ *
+ * first_in_core = (core_idle_state & IDLE_THREAD_BITS) == 0;
+ * first_in_subcore = (core_idle_state & SUBCORE_SIBLING_MASK) == 0;
+ *
+ * core_idle_state |= thread_in_core;
+ *
+ * if ((core_idle_state & WINKLE_MASK) == (8 << WINKLE_COUNT_SIHFT))
+ * core_idle_state |= THREAD_WINKLE_BITS;
+ * core_idle_state -= 1 << WINKLE_COUNT_SHIFT;
+ *
+ * winkle_state_lost = core_idle_state &
+ * (thread_in_core << WINKLE_THREAD_SHIFT);
+ * core_idle_state &= ~(thread_in_core << WINKLE_THREAD_SHIFT);
+ * }
+ *
+ */
+ cmpwi r18,PNV_THREAD_WINKLE
+ bne 2f
+ andis. r9,r15,PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT@h
+ subis r15,r15,PNV_CORE_IDLE_WINKLE_COUNT@h
+ beq 2f
+ ori r15,r15,PNV_CORE_IDLE_THREAD_WINKLE_BITS /* all were winkle */
+2:
+ /* Shift thread bit to winkle mask, then test if this thread is set,
+ * and remove it from the winkle bits */
+ slwi r8,r7,8
+ and r8,r8,r15
+ andc r15,r15,r8
+ cmpwi cr4,r8,1 /* cr4 will be gt if our bit is set, lt if not */
+
lbz r4,PACA_SUBCORE_SIBLING_MASK(r13)
and r4,r4,r15
cmpwi r4,0 /* Check if first in subcore */
@@ -577,7 +758,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
mtspr SPRN_WORC,r4
clear_lock:
- andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS
+ xoris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
lwsync
stw r15,0(r14)
@@ -635,8 +816,7 @@ hypervisor_state_restored:
mtspr SPRN_SRR1,r16
mtlr r17
- blr /* Return back to System Reset vector from where
- pnv_restore_hyp_resource was invoked */
+ blr /* return to pnv_powersave_wakeup */
fastsleep_workaround_at_exit:
li r3,1
@@ -648,7 +828,8 @@ fastsleep_workaround_at_exit:
* R3 here contains the value that will be returned to the caller
* of power7_nap.
*/
-_GLOBAL(pnv_wakeup_loss)
+.global pnv_wakeup_loss
+pnv_wakeup_loss:
ld r1,PACAR1(r13)
BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
@@ -668,7 +849,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
* R3 here contains the value that will be returned to the caller
* of power7_nap.
*/
-_GLOBAL(pnv_wakeup_noloss)
+pnv_wakeup_noloss:
lbz r0,PACA_NAPSTATELOST(r13)
cmpwi r0,0
bne pnv_wakeup_loss
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 5f202a566ec5..f2b724cd9e64 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -711,13 +711,16 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
return tbl;
}
-void iommu_free_table(struct iommu_table *tbl, const char *node_name)
+static void iommu_table_free(struct kref *kref)
{
unsigned long bitmap_sz;
unsigned int order;
+ struct iommu_table *tbl;
- if (!tbl)
- return;
+ tbl = container_of(kref, struct iommu_table, it_kref);
+
+ if (tbl->it_ops->free)
+ tbl->it_ops->free(tbl);
if (!tbl->it_map) {
kfree(tbl);
@@ -733,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
/* verify that table contains no entries */
if (!bitmap_empty(tbl->it_map, tbl->it_size))
- pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);
+ pr_warn("%s: Unexpected TCEs\n", __func__);
/* calculate bitmap size in bytes */
bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
@@ -746,6 +749,24 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
kfree(tbl);
}
+struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl)
+{
+ if (kref_get_unless_zero(&tbl->it_kref))
+ return tbl;
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_get);
+
+int iommu_tce_table_put(struct iommu_table *tbl)
+{
+ if (WARN_ON(!tbl))
+ return 0;
+
+ return kref_put(&tbl->it_kref, iommu_table_free);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_put);
+
/* Creates TCEs for a user provided buffer. The user buffer must be
* contiguous real kernel storage (not vmalloc). The address passed here
* comprises a page address and offset into that page. The dma_addr_t
@@ -942,47 +963,36 @@ void iommu_flush_tce(struct iommu_table *tbl)
}
EXPORT_SYMBOL_GPL(iommu_flush_tce);
-int iommu_tce_clear_param_check(struct iommu_table *tbl,
- unsigned long ioba, unsigned long tce_value,
- unsigned long npages)
+int iommu_tce_check_ioba(unsigned long page_shift,
+ unsigned long offset, unsigned long size,
+ unsigned long ioba, unsigned long npages)
{
- /* tbl->it_ops->clear() does not support any value but 0 */
- if (tce_value)
- return -EINVAL;
+ unsigned long mask = (1UL << page_shift) - 1;
- if (ioba & ~IOMMU_PAGE_MASK(tbl))
+ if (ioba & mask)
return -EINVAL;
- ioba >>= tbl->it_page_shift;
- if (ioba < tbl->it_offset)
+ ioba >>= page_shift;
+ if (ioba < offset)
return -EINVAL;
- if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
+ if ((ioba + 1) > (offset + size))
return -EINVAL;
return 0;
}
-EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
+EXPORT_SYMBOL_GPL(iommu_tce_check_ioba);
-int iommu_tce_put_param_check(struct iommu_table *tbl,
- unsigned long ioba, unsigned long tce)
+int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
{
- if (tce & ~IOMMU_PAGE_MASK(tbl))
- return -EINVAL;
-
- if (ioba & ~IOMMU_PAGE_MASK(tbl))
- return -EINVAL;
+ unsigned long mask = (1UL << page_shift) - 1;
- ioba >>= tbl->it_page_shift;
- if (ioba < tbl->it_offset)
- return -EINVAL;
-
- if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
+ if (gpa & mask)
return -EINVAL;
return 0;
}
-EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
+EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
unsigned long *hpa, enum dma_data_direction *direction)
@@ -1004,6 +1014,31 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
}
EXPORT_SYMBOL_GPL(iommu_tce_xchg);
+#ifdef CONFIG_PPC_BOOK3S_64
+long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+ unsigned long *hpa, enum dma_data_direction *direction)
+{
+ long ret;
+
+ ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+
+ if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+ (*direction == DMA_BIDIRECTIONAL))) {
+ struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT);
+
+ if (likely(pg)) {
+ SetPageDirty(pg);
+ } else {
+ tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+ ret = -EFAULT;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm);
+#endif
+
int iommu_take_ownership(struct iommu_table *tbl)
{
unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index a018f5cae899..5c291df30fe3 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -65,7 +65,6 @@
#include <asm/machdep.h>
#include <asm/udbg.h>
#include <asm/smp.h>
-#include <asm/debug.h>
#include <asm/livepatch.h>
#include <asm/asm-prototypes.h>
@@ -442,46 +441,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
return sum;
}
-#ifdef CONFIG_HOTPLUG_CPU
-void migrate_irqs(void)
-{
- struct irq_desc *desc;
- unsigned int irq;
- static int warned;
- cpumask_var_t mask;
- const struct cpumask *map = cpu_online_mask;
-
- alloc_cpumask_var(&mask, GFP_KERNEL);
-
- for_each_irq_desc(irq, desc) {
- struct irq_data *data;
- struct irq_chip *chip;
-
- data = irq_desc_get_irq_data(desc);
- if (irqd_is_per_cpu(data))
- continue;
-
- chip = irq_data_get_irq_chip(data);
-
- cpumask_and(mask, irq_data_get_affinity_mask(data), map);
- if (cpumask_any(mask) >= nr_cpu_ids) {
- pr_warn("Breaking affinity for irq %i\n", irq);
- cpumask_copy(mask, map);
- }
- if (chip->irq_set_affinity)
- chip->irq_set_affinity(data, mask, true);
- else if (desc->action && !(warned++))
- pr_err("Cannot set affinity for irq %i\n", irq);
- }
-
- free_cpumask_var(mask);
-
- local_irq_enable();
- mdelay(1);
- local_irq_disable();
-}
-#endif
-
static inline void check_stack_overflow(void)
{
#ifdef CONFIG_DEBUG_STACKOVERFLOW
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
new file mode 100644
index 000000000000..6c089d9757c9
--- /dev/null
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -0,0 +1,104 @@
+/*
+ * Dynamic Ftrace based Kprobes Optimization
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) Hitachi Ltd., 2012
+ * Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
+ * IBM Corporation
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/ftrace.h>
+
+static nokprobe_inline
+int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb, unsigned long orig_nip)
+{
+ /*
+ * Emulate singlestep (and also recover regs->nip)
+ * as if there is a nop
+ */
+ regs->nip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+ if (unlikely(p->post_handler)) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ p->post_handler(p, regs, 0);
+ }
+ __this_cpu_write(current_kprobe, NULL);
+ if (orig_nip)
+ regs->nip = orig_nip;
+ return 1;
+}
+
+int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ if (kprobe_ftrace(p))
+ return __skip_singlestep(p, regs, kcb, 0);
+ else
+ return 0;
+}
+NOKPROBE_SYMBOL(skip_singlestep);
+
+/* Ftrace callback handler for kprobes */
+void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
+ struct ftrace_ops *ops, struct pt_regs *regs)
+{
+ struct kprobe *p;
+ struct kprobe_ctlblk *kcb;
+ unsigned long flags;
+
+ /* Disable irq for emulating a breakpoint and avoiding preempt */
+ local_irq_save(flags);
+ hard_irq_disable();
+
+ p = get_kprobe((kprobe_opcode_t *)nip);
+ if (unlikely(!p) || kprobe_disabled(p))
+ goto end;
+
+ kcb = get_kprobe_ctlblk();
+ if (kprobe_running()) {
+ kprobes_inc_nmissed_count(p);
+ } else {
+ unsigned long orig_nip = regs->nip;
+
+ /*
+ * On powerpc, NIP is *before* this instruction for the
+ * pre handler
+ */
+ regs->nip -= MCOUNT_INSN_SIZE;
+
+ __this_cpu_write(current_kprobe, p);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+ if (!p->pre_handler || !p->pre_handler(p, regs))
+ __skip_singlestep(p, regs, kcb, orig_nip);
+ /*
+ * If pre_handler returns !0, it sets regs->nip and
+ * resets current kprobe.
+ */
+ }
+end:
+ local_irq_restore(flags);
+}
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);
+
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+ p->ainsn.insn = NULL;
+ p->ainsn.boostable = -1;
+ return 0;
+}
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index fce05a38851c..160ae0fa7d0d 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -35,6 +35,7 @@
#include <asm/code-patching.h>
#include <asm/cacheflush.h>
#include <asm/sstep.h>
+#include <asm/sections.h>
#include <linux/uaccess.h>
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
@@ -42,7 +43,86 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
-int __kprobes arch_prepare_kprobe(struct kprobe *p)
+bool arch_within_kprobe_blacklist(unsigned long addr)
+{
+ return (addr >= (unsigned long)__kprobes_text_start &&
+ addr < (unsigned long)__kprobes_text_end) ||
+ (addr >= (unsigned long)_stext &&
+ addr < (unsigned long)__head_end);
+}
+
+kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
+{
+ kprobe_opcode_t *addr;
+
+#ifdef PPC64_ELF_ABI_v2
+ /* PPC64 ABIv2 needs local entry point */
+ addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
+ if (addr && !offset) {
+#ifdef CONFIG_KPROBES_ON_FTRACE
+ unsigned long faddr;
+ /*
+ * Per livepatch.h, ftrace location is always within the first
+ * 16 bytes of a function on powerpc with -mprofile-kernel.
+ */
+ faddr = ftrace_location_range((unsigned long)addr,
+ (unsigned long)addr + 16);
+ if (faddr)
+ addr = (kprobe_opcode_t *)faddr;
+ else
+#endif
+ addr = (kprobe_opcode_t *)ppc_function_entry(addr);
+ }
+#elif defined(PPC64_ELF_ABI_v1)
+ /*
+ * 64bit powerpc ABIv1 uses function descriptors:
+ * - Check for the dot variant of the symbol first.
+ * - If that fails, try looking up the symbol provided.
+ *
+ * This ensures we always get to the actual symbol and not
+ * the descriptor.
+ *
+ * Also handle <module:symbol> format.
+ */
+ char dot_name[MODULE_NAME_LEN + 1 + KSYM_NAME_LEN];
+ const char *modsym;
+ bool dot_appended = false;
+ if ((modsym = strchr(name, ':')) != NULL) {
+ modsym++;
+ if (*modsym != '\0' && *modsym != '.') {
+ /* Convert to <module:.symbol> */
+ strncpy(dot_name, name, modsym - name);
+ dot_name[modsym - name] = '.';
+ dot_name[modsym - name + 1] = '\0';
+ strncat(dot_name, modsym,
+ sizeof(dot_name) - (modsym - name) - 2);
+ dot_appended = true;
+ } else {
+ dot_name[0] = '\0';
+ strncat(dot_name, name, sizeof(dot_name) - 1);
+ }
+ } else if (name[0] != '.') {
+ dot_name[0] = '.';
+ dot_name[1] = '\0';
+ strncat(dot_name, name, KSYM_NAME_LEN - 2);
+ dot_appended = true;
+ } else {
+ dot_name[0] = '\0';
+ strncat(dot_name, name, KSYM_NAME_LEN - 1);
+ }
+ addr = (kprobe_opcode_t *)kallsyms_lookup_name(dot_name);
+ if (!addr && dot_appended) {
+ /* Let's try the original non-dot symbol lookup */
+ addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
+ }
+#else
+ addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
+#endif
+
+ return addr;
+}
+
+int arch_prepare_kprobe(struct kprobe *p)
{
int ret = 0;
kprobe_opcode_t insn = *p->addr;
@@ -74,30 +154,34 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
p->ainsn.boostable = 0;
return ret;
}
+NOKPROBE_SYMBOL(arch_prepare_kprobe);
-void __kprobes arch_arm_kprobe(struct kprobe *p)
+void arch_arm_kprobe(struct kprobe *p)
{
*p->addr = BREAKPOINT_INSTRUCTION;
flush_icache_range((unsigned long) p->addr,
(unsigned long) p->addr + sizeof(kprobe_opcode_t));
}
+NOKPROBE_SYMBOL(arch_arm_kprobe);
-void __kprobes arch_disarm_kprobe(struct kprobe *p)
+void arch_disarm_kprobe(struct kprobe *p)
{
*p->addr = p->opcode;
flush_icache_range((unsigned long) p->addr,
(unsigned long) p->addr + sizeof(kprobe_opcode_t));
}
+NOKPROBE_SYMBOL(arch_disarm_kprobe);
-void __kprobes arch_remove_kprobe(struct kprobe *p)
+void arch_remove_kprobe(struct kprobe *p)
{
if (p->ainsn.insn) {
free_insn_slot(p->ainsn.insn, 0);
p->ainsn.insn = NULL;
}
}
+NOKPROBE_SYMBOL(arch_remove_kprobe);
-static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
+static nokprobe_inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
{
enable_single_step(regs);
@@ -110,37 +194,80 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
regs->nip = (unsigned long)p->ainsn.insn;
}
-static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+static nokprobe_inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
kcb->prev_kprobe.kp = kprobe_running();
kcb->prev_kprobe.status = kcb->kprobe_status;
kcb->prev_kprobe.saved_msr = kcb->kprobe_saved_msr;
}
-static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+static nokprobe_inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
kcb->kprobe_status = kcb->prev_kprobe.status;
kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr;
}
-static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
+static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
__this_cpu_write(current_kprobe, p);
kcb->kprobe_saved_msr = regs->msr;
}
-void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
- struct pt_regs *regs)
+bool arch_function_offset_within_entry(unsigned long offset)
+{
+#ifdef PPC64_ELF_ABI_v2
+#ifdef CONFIG_KPROBES_ON_FTRACE
+ return offset <= 16;
+#else
+ return offset <= 8;
+#endif
+#else
+ return !offset;
+#endif
+}
+
+void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
{
ri->ret_addr = (kprobe_opcode_t *)regs->link;
/* Replace the return addr with trampoline addr */
regs->link = (unsigned long)kretprobe_trampoline;
}
+NOKPROBE_SYMBOL(arch_prepare_kretprobe);
-int __kprobes kprobe_handler(struct pt_regs *regs)
+int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
+{
+ int ret;
+ unsigned int insn = *p->ainsn.insn;
+
+ /* regs->nip is also adjusted if emulate_step returns 1 */
+ ret = emulate_step(regs, insn);
+ if (ret > 0) {
+ /*
+ * Once this instruction has been boosted
+ * successfully, set the boostable flag
+ */
+ if (unlikely(p->ainsn.boostable == 0))
+ p->ainsn.boostable = 1;
+ } else if (ret < 0) {
+ /*
+ * We don't allow kprobes on mtmsr(d)/rfi(d), etc.
+ * So, we should never get here... but, its still
+ * good to catch them, just in case...
+ */
+ printk("Can't step on instruction %x\n", insn);
+ BUG();
+ } else if (ret == 0)
+ /* This instruction can't be boosted */
+ p->ainsn.boostable = -1;
+
+ return ret;
+}
+NOKPROBE_SYMBOL(try_to_emulate);
+
+int kprobe_handler(struct pt_regs *regs)
{
struct kprobe *p;
int ret = 0;
@@ -177,10 +304,17 @@ int __kprobes kprobe_handler(struct pt_regs *regs)
*/
save_previous_kprobe(kcb);
set_current_kprobe(p, regs, kcb);
- kcb->kprobe_saved_msr = regs->msr;
kprobes_inc_nmissed_count(p);
prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_REENTER;
+ if (p->ainsn.boostable >= 0) {
+ ret = try_to_emulate(p, regs);
+
+ if (ret > 0) {
+ restore_previous_kprobe(kcb);
+ return 1;
+ }
+ }
return 1;
} else {
if (*addr != BREAKPOINT_INSTRUCTION) {
@@ -197,7 +331,9 @@ int __kprobes kprobe_handler(struct pt_regs *regs)
}
p = __this_cpu_read(current_kprobe);
if (p->break_handler && p->break_handler(p, regs)) {
- goto ss_probe;
+ if (!skip_singlestep(p, regs, kcb))
+ goto ss_probe;
+ ret = 1;
}
}
goto no_kprobe;
@@ -235,18 +371,9 @@ int __kprobes kprobe_handler(struct pt_regs *regs)
ss_probe:
if (p->ainsn.boostable >= 0) {
- unsigned int insn = *p->ainsn.insn;
+ ret = try_to_emulate(p, regs);
- /* regs->nip is also adjusted if emulate_step returns 1 */
- ret = emulate_step(regs, insn);
if (ret > 0) {
- /*
- * Once this instruction has been boosted
- * successfully, set the boostable flag
- */
- if (unlikely(p->ainsn.boostable == 0))
- p->ainsn.boostable = 1;
-
if (p->post_handler)
p->post_handler(p, regs, 0);
@@ -254,17 +381,7 @@ ss_probe:
reset_current_kprobe();
preempt_enable_no_resched();
return 1;
- } else if (ret < 0) {
- /*
- * We don't allow kprobes on mtmsr(d)/rfi(d), etc.
- * So, we should never get here... but, its still
- * good to catch them, just in case...
- */
- printk("Can't step on instruction %x\n", insn);
- BUG();
- } else if (ret == 0)
- /* This instruction can't be boosted */
- p->ainsn.boostable = -1;
+ }
}
prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_HIT_SS;
@@ -274,6 +391,7 @@ no_kprobe:
preempt_enable_no_resched();
return ret;
}
+NOKPROBE_SYMBOL(kprobe_handler);
/*
* Function return probe trampoline:
@@ -291,8 +409,7 @@ asm(".global kretprobe_trampoline\n"
/*
* Called when the probe at kretprobe trampoline is hit
*/
-static int __kprobes trampoline_probe_handler(struct kprobe *p,
- struct pt_regs *regs)
+static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
{
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
@@ -361,6 +478,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
*/
return 1;
}
+NOKPROBE_SYMBOL(trampoline_probe_handler);
/*
* Called after single-stepping. p->addr is the address of the
@@ -370,7 +488,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
* single-stepped a copy of the instruction. The address of this
* copy is p->ainsn.insn.
*/
-int __kprobes kprobe_post_handler(struct pt_regs *regs)
+int kprobe_post_handler(struct pt_regs *regs)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -410,8 +528,9 @@ out:
return 1;
}
+NOKPROBE_SYMBOL(kprobe_post_handler);
-int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -474,13 +593,15 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
}
return 0;
}
+NOKPROBE_SYMBOL(kprobe_fault_handler);
unsigned long arch_deref_entry_point(void *entry)
{
return ppc_global_function_entry(entry);
}
+NOKPROBE_SYMBOL(arch_deref_entry_point);
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
struct jprobe *jp = container_of(p, struct jprobe, kp);
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -497,17 +618,20 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
return 1;
}
+NOKPROBE_SYMBOL(setjmp_pre_handler);
-void __used __kprobes jprobe_return(void)
+void __used jprobe_return(void)
{
asm volatile("trap" ::: "memory");
}
+NOKPROBE_SYMBOL(jprobe_return);
-static void __used __kprobes jprobe_return_end(void)
+static void __used jprobe_return_end(void)
{
-};
+}
+NOKPROBE_SYMBOL(jprobe_return_end);
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -520,6 +644,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
preempt_enable_no_resched();
return 1;
}
+NOKPROBE_SYMBOL(longjmp_break_handler);
static struct kprobe trampoline_p = {
.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
@@ -531,10 +656,11 @@ int __init arch_init_kprobes(void)
return register_kprobe(&trampoline_p);
}
-int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+int arch_trampoline_kprobe(struct kprobe *p)
{
if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline)
return 1;
return 0;
}
+NOKPROBE_SYMBOL(arch_trampoline_kprobe);
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index c6923ff45131..5f9eada3519b 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -58,6 +58,15 @@ static void mce_set_error_info(struct machine_check_event *mce,
case MCE_ERROR_TYPE_TLB:
mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
break;
+ case MCE_ERROR_TYPE_USER:
+ mce->u.user_error.user_error_type = mce_err->u.user_error_type;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce->u.link_error.link_error_type = mce_err->u.link_error_type;
+ break;
case MCE_ERROR_TYPE_UNKNOWN:
default:
break;
@@ -90,13 +99,14 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->gpr3 = regs->gpr[3];
mce->in_use = 1;
- mce->initiator = MCE_INITIATOR_CPU;
/* Mark it recovered if we have handled it and MSR(RI=1). */
if (handled && (regs->msr & MSR_RI))
mce->disposition = MCE_DISPOSITION_RECOVERED;
else
mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
- mce->severity = MCE_SEV_ERROR_SYNC;
+
+ mce->initiator = mce_err->initiator;
+ mce->severity = mce_err->severity;
/*
* Populate the mce error_type and type-specific error_type.
@@ -115,6 +125,15 @@ void save_mce_event(struct pt_regs *regs, long handled,
} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
mce->u.erat_error.effective_address_provided = true;
mce->u.erat_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_USER) {
+ mce->u.user_error.effective_address_provided = true;
+ mce->u.user_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_RA) {
+ mce->u.ra_error.effective_address_provided = true;
+ mce->u.ra_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_LINK) {
+ mce->u.link_error.effective_address_provided = true;
+ mce->u.link_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
mce->u.ue_error.effective_address_provided = true;
mce->u.ue_error.effective_address = addr;
@@ -202,6 +221,8 @@ static void machine_check_process_queued_event(struct irq_work *work)
{
int index;
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
/*
* For now just print it to console.
* TODO: log this error event to FSP or nvram.
@@ -209,12 +230,13 @@ static void machine_check_process_queued_event(struct irq_work *work)
while (__this_cpu_read(mce_queue_count) > 0) {
index = __this_cpu_read(mce_queue_count) - 1;
machine_check_print_event_info(
- this_cpu_ptr(&mce_event_queue[index]));
+ this_cpu_ptr(&mce_event_queue[index]), false);
__this_cpu_dec(mce_queue_count);
}
}
-void machine_check_print_event_info(struct machine_check_event *evt)
+void machine_check_print_event_info(struct machine_check_event *evt,
+ bool user_mode)
{
const char *level, *sevstr, *subtype;
static const char *mc_ue_types[] = {
@@ -239,6 +261,29 @@ void machine_check_print_event_info(struct machine_check_event *evt)
"Parity",
"Multihit",
};
+ static const char *mc_user_types[] = {
+ "Indeterminate",
+ "tlbie(l) invalid",
+ };
+ static const char *mc_ra_types[] = {
+ "Indeterminate",
+ "Instruction fetch (bad)",
+ "Page table walk ifetch (bad)",
+ "Page table walk ifetch (foreign)",
+ "Load (bad)",
+ "Store (bad)",
+ "Page table walk Load/Store (bad)",
+ "Page table walk Load/Store (foreign)",
+ "Load/Store (foreign)",
+ };
+ static const char *mc_link_types[] = {
+ "Indeterminate",
+ "Instruction fetch (timeout)",
+ "Page table walk ifetch (timeout)",
+ "Load (timeout)",
+ "Store (timeout)",
+ "Page table walk Load/Store (timeout)",
+ };
/* Print things out */
if (evt->version != MCE_V1) {
@@ -268,7 +313,16 @@ void machine_check_print_event_info(struct machine_check_event *evt)
printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
evt->disposition == MCE_DISPOSITION_RECOVERED ?
- "Recovered" : "[Not recovered");
+ "Recovered" : "Not recovered");
+
+ if (user_mode) {
+ printk("%s NIP: [%016llx] PID: %d Comm: %s\n", level,
+ evt->srr0, current->pid, current->comm);
+ } else {
+ printk("%s NIP [%016llx]: %pS\n", level, evt->srr0,
+ (void *)evt->srr0);
+ }
+
printk("%s Initiator: %s\n", level,
evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
switch (evt->error_type) {
@@ -315,6 +369,36 @@ void machine_check_print_event_info(struct machine_check_event *evt)
printk("%s Effective address: %016llx\n",
level, evt->u.tlb_error.effective_address);
break;
+ case MCE_ERROR_TYPE_USER:
+ subtype = evt->u.user_error.user_error_type <
+ ARRAY_SIZE(mc_user_types) ?
+ mc_user_types[evt->u.user_error.user_error_type]
+ : "Unknown";
+ printk("%s Error type: User [%s]\n", level, subtype);
+ if (evt->u.user_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.user_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_RA:
+ subtype = evt->u.ra_error.ra_error_type <
+ ARRAY_SIZE(mc_ra_types) ?
+ mc_ra_types[evt->u.ra_error.ra_error_type]
+ : "Unknown";
+ printk("%s Error type: Real address [%s]\n", level, subtype);
+ if (evt->u.ra_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.ra_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ subtype = evt->u.link_error.link_error_type <
+ ARRAY_SIZE(mc_link_types) ?
+ mc_link_types[evt->u.link_error.link_error_type]
+ : "Unknown";
+ printk("%s Error type: Link [%s]\n", level, subtype);
+ if (evt->u.link_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.link_error.effective_address);
+ break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
printk("%s Error type: Unknown\n", level);
@@ -341,6 +425,18 @@ uint64_t get_mce_fault_addr(struct machine_check_event *evt)
if (evt->u.tlb_error.effective_address_provided)
return evt->u.tlb_error.effective_address;
break;
+ case MCE_ERROR_TYPE_USER:
+ if (evt->u.user_error.effective_address_provided)
+ return evt->u.user_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ if (evt->u.ra_error.effective_address_provided)
+ return evt->u.ra_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ if (evt->u.link_error.effective_address_provided)
+ return evt->u.link_error.effective_address;
+ break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
break;
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 7353991c4ece..f913139bb0c2 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -72,10 +72,14 @@ void __flush_tlb_power8(unsigned int action)
void __flush_tlb_power9(unsigned int action)
{
+ unsigned int num_sets;
+
if (radix_enabled())
- flush_tlb_206(POWER9_TLB_SETS_RADIX, action);
+ num_sets = POWER9_TLB_SETS_RADIX;
+ else
+ num_sets = POWER9_TLB_SETS_HASH;
- flush_tlb_206(POWER9_TLB_SETS_HASH, action);
+ flush_tlb_206(num_sets, action);
}
@@ -116,145 +120,396 @@ static void flush_and_reload_slb(void)
}
#endif
-static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
+static void flush_erat(void)
{
- long handled = 1;
+ asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
+}
- /*
- * flush and reload SLBs for SLB errors and flush TLBs for TLB errors.
- * reset the error bits whenever we handle them so that at the end
- * we can check whether we handled all of them or not.
- * */
+#define MCE_FLUSH_SLB 1
+#define MCE_FLUSH_TLB 2
+#define MCE_FLUSH_ERAT 3
+
+static int mce_flush(int what)
+{
#ifdef CONFIG_PPC_STD_MMU_64
- if (dsisr & slb_error_bits) {
+ if (what == MCE_FLUSH_SLB) {
flush_and_reload_slb();
- /* reset error bits */
- dsisr &= ~(slb_error_bits);
+ return 1;
}
- if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
- if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
+#endif
+ if (what == MCE_FLUSH_ERAT) {
+ flush_erat();
+ return 1;
+ }
+ if (what == MCE_FLUSH_TLB) {
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
- /* reset error bits */
- dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
+ return 1;
+ }
}
-#endif
- /* Any other errors we don't understand? */
- if (dsisr & 0xffffffffUL)
- handled = 0;
- return handled;
+ return 0;
}
-static long mce_handle_derror_p7(uint64_t dsisr)
+#define SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42))
+
+struct mce_ierror_table {
+ unsigned long srr1_mask;
+ unsigned long srr1_value;
+ bool nip_valid; /* nip is a valid indicator of faulting address */
+ unsigned int error_type;
+ unsigned int error_subtype;
+ unsigned int initiator;
+ unsigned int severity;
+};
+
+static const struct mce_ierror_table mce_p7_ierror_table[] = {
+{ 0x00000000001c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, 0, 0, 0, 0, 0 } };
+
+static const struct mce_ierror_table mce_p8_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008000000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_IFETCH_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008040000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, 0, 0, 0, 0, 0 } };
+
+static const struct mce_ierror_table mce_p9_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008000000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_IFETCH_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008040000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x00000000080c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008100000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008140000, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x0000000008180000, false,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_STORE_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x00000000081c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 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 */
+ unsigned int error_type;
+ unsigned int error_subtype;
+ unsigned int initiator;
+ unsigned int severity;
+};
+
+static const struct mce_derror_table mce_p7_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, false, 0, 0, 0, 0 } };
+
+static const struct mce_derror_table mce_p8_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00002000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00001000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000200, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, /* SECONDARY ERAT */
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, false, 0, 0, 0, 0 } };
+
+static const struct mce_derror_table mce_p9_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00002000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00001000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000200, false,
+ MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000020, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000010, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000008, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD_STORE_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, false, 0, 0, 0, 0 } };
+
+static int mce_handle_ierror(struct pt_regs *regs,
+ const struct mce_ierror_table table[],
+ struct mce_error_info *mce_err, uint64_t *addr)
{
- return mce_handle_derror(dsisr, P7_DSISR_MC_SLB_ERRORS);
-}
-
-static long mce_handle_common_ierror(uint64_t srr1)
-{
- long handled = 0;
+ uint64_t srr1 = regs->msr;
+ int handled = 0;
+ int i;
+
+ *addr = 0;
+
+ for (i = 0; table[i].srr1_mask; i++) {
+ if ((srr1 & table[i].srr1_mask) != table[i].srr1_value)
+ continue;
+
+ /* attempt to correct the error */
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_SLB:
+ handled = mce_flush(MCE_FLUSH_SLB);
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ handled = mce_flush(MCE_FLUSH_ERAT);
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ handled = mce_flush(MCE_FLUSH_TLB);
+ break;
+ }
- switch (P7_SRR1_MC_IFETCH(srr1)) {
- case 0:
- break;
-#ifdef CONFIG_PPC_STD_MMU_64
- case P7_SRR1_MC_IFETCH_SLB_PARITY:
- case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
- /* flush and reload SLBs for SLB errors. */
- flush_and_reload_slb();
- handled = 1;
- break;
- case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
- if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
- cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
- handled = 1;
+ /* now fill in mce_error_info */
+ mce_err->error_type = table[i].error_type;
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce_err->u.ue_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce_err->u.slb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce_err->u.erat_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce_err->u.tlb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_USER:
+ mce_err->u.user_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce_err->u.ra_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce_err->u.link_error_type = table[i].error_subtype;
+ break;
}
- break;
-#endif
- default:
- break;
+ mce_err->severity = table[i].severity;
+ mce_err->initiator = table[i].initiator;
+ if (table[i].nip_valid)
+ *addr = regs->nip;
+ return handled;
}
- return handled;
+ mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
+ mce_err->severity = MCE_SEV_ERROR_SYNC;
+ mce_err->initiator = MCE_INITIATOR_CPU;
+
+ return 0;
}
-static long mce_handle_ierror_p7(uint64_t srr1)
+static int mce_handle_derror(struct pt_regs *regs,
+ const struct mce_derror_table table[],
+ struct mce_error_info *mce_err, uint64_t *addr)
{
- long handled = 0;
+ uint64_t dsisr = regs->dsisr;
+ int handled = 0;
+ int found = 0;
+ int i;
+
+ *addr = 0;
+
+ for (i = 0; table[i].dsisr_value; i++) {
+ if (!(dsisr & table[i].dsisr_value))
+ continue;
+
+ /* attempt to correct the error */
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_SLB:
+ if (mce_flush(MCE_FLUSH_SLB))
+ handled = 1;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ if (mce_flush(MCE_FLUSH_ERAT))
+ handled = 1;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ if (mce_flush(MCE_FLUSH_TLB))
+ handled = 1;
+ break;
+ }
- handled = mce_handle_common_ierror(srr1);
+ /*
+ * Attempt to handle multiple conditions, but only return
+ * one. Ensure uncorrectable errors are first in the table
+ * to match.
+ */
+ if (found)
+ continue;
+
+ /* now fill in mce_error_info */
+ mce_err->error_type = table[i].error_type;
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce_err->u.ue_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce_err->u.slb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce_err->u.erat_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce_err->u.tlb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_USER:
+ mce_err->u.user_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce_err->u.ra_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce_err->u.link_error_type = table[i].error_subtype;
+ break;
+ }
+ mce_err->severity = table[i].severity;
+ mce_err->initiator = table[i].initiator;
+ if (table[i].dar_valid)
+ *addr = regs->dar;
-#ifdef CONFIG_PPC_STD_MMU_64
- if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
- flush_and_reload_slb();
- handled = 1;
+ found = 1;
}
-#endif
- return handled;
-}
-static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1)
-{
- switch (P7_SRR1_MC_IFETCH(srr1)) {
- case P7_SRR1_MC_IFETCH_SLB_PARITY:
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
- break;
- case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
- break;
- case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
- mce_err->error_type = MCE_ERROR_TYPE_TLB;
- mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
- break;
- case P7_SRR1_MC_IFETCH_UE:
- case P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL:
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
- break;
- case P7_SRR1_MC_IFETCH_UE_TLB_RELOAD:
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type =
- MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
- break;
- }
-}
+ if (found)
+ return handled;
-static void mce_get_ierror_p7(struct mce_error_info *mce_err, uint64_t srr1)
-{
- mce_get_common_ierror(mce_err, srr1);
- if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
- }
-}
+ mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
+ mce_err->severity = MCE_SEV_ERROR_SYNC;
+ mce_err->initiator = MCE_INITIATOR_CPU;
-static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr)
-{
- if (dsisr & P7_DSISR_MC_UE) {
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
- } else if (dsisr & P7_DSISR_MC_UE_TABLEWALK) {
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type =
- MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
- } else if (dsisr & P7_DSISR_MC_ERAT_MULTIHIT) {
- mce_err->error_type = MCE_ERROR_TYPE_ERAT;
- mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
- } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
- } else if (dsisr & P7_DSISR_MC_SLB_PARITY_MFSLB) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
- } else if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
- mce_err->error_type = MCE_ERROR_TYPE_TLB;
- mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
- } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT_PARITY) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
- }
+ return 0;
}
static long mce_handle_ue_error(struct pt_regs *regs)
@@ -275,100 +530,42 @@ static long mce_handle_ue_error(struct pt_regs *regs)
return handled;
}
-long __machine_check_early_realmode_p7(struct pt_regs *regs)
+static long mce_handle_error(struct pt_regs *regs,
+ const struct mce_derror_table dtable[],
+ const struct mce_ierror_table itable[])
{
- uint64_t srr1, nip, addr;
- long handled = 1;
- struct mce_error_info mce_error_info = { 0 };
-
- srr1 = regs->msr;
- nip = regs->nip;
+ struct mce_error_info mce_err = { 0 };
+ uint64_t addr;
+ uint64_t srr1 = regs->msr;
+ long handled;
- /*
- * Handle memory errors depending whether this was a load/store or
- * ifetch exception. Also, populate the mce error_type and
- * type-specific error_type from either SRR1 or DSISR, depending
- * whether this was a load/store or ifetch exception
- */
- if (P7_SRR1_MC_LOADSTORE(srr1)) {
- handled = mce_handle_derror_p7(regs->dsisr);
- mce_get_derror_p7(&mce_error_info, regs->dsisr);
- addr = regs->dar;
- } else {
- handled = mce_handle_ierror_p7(srr1);
- mce_get_ierror_p7(&mce_error_info, srr1);
- addr = regs->nip;
- }
+ if (SRR1_MC_LOADSTORE(srr1))
+ handled = mce_handle_derror(regs, dtable, &mce_err, &addr);
+ else
+ handled = mce_handle_ierror(regs, itable, &mce_err, &addr);
- /* Handle UE error. */
- if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+ if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
handled = mce_handle_ue_error(regs);
- save_mce_event(regs, handled, &mce_error_info, nip, addr);
- return handled;
-}
+ save_mce_event(regs, handled, &mce_err, regs->nip, addr);
-static void mce_get_ierror_p8(struct mce_error_info *mce_err, uint64_t srr1)
-{
- mce_get_common_ierror(mce_err, srr1);
- if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
- mce_err->error_type = MCE_ERROR_TYPE_ERAT;
- mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
- }
-}
-
-static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr)
-{
- mce_get_derror_p7(mce_err, dsisr);
- if (dsisr & P8_DSISR_MC_ERAT_MULTIHIT_SEC) {
- mce_err->error_type = MCE_ERROR_TYPE_ERAT;
- mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
- }
+ return handled;
}
-static long mce_handle_ierror_p8(uint64_t srr1)
+long __machine_check_early_realmode_p7(struct pt_regs *regs)
{
- long handled = 0;
-
- handled = mce_handle_common_ierror(srr1);
+ /* P7 DD1 leaves top bits of DSISR undefined */
+ regs->dsisr &= 0x0000ffff;
-#ifdef CONFIG_PPC_STD_MMU_64
- if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
- flush_and_reload_slb();
- handled = 1;
- }
-#endif
- return handled;
+ return mce_handle_error(regs, mce_p7_derror_table, mce_p7_ierror_table);
}
-static long mce_handle_derror_p8(uint64_t dsisr)
+long __machine_check_early_realmode_p8(struct pt_regs *regs)
{
- return mce_handle_derror(dsisr, P8_DSISR_MC_SLB_ERRORS);
+ return mce_handle_error(regs, mce_p8_derror_table, mce_p8_ierror_table);
}
-long __machine_check_early_realmode_p8(struct pt_regs *regs)
+long __machine_check_early_realmode_p9(struct pt_regs *regs)
{
- uint64_t srr1, nip, addr;
- long handled = 1;
- struct mce_error_info mce_error_info = { 0 };
-
- srr1 = regs->msr;
- nip = regs->nip;
-
- if (P7_SRR1_MC_LOADSTORE(srr1)) {
- handled = mce_handle_derror_p8(regs->dsisr);
- mce_get_derror_p8(&mce_error_info, regs->dsisr);
- addr = regs->dar;
- } else {
- handled = mce_handle_ierror_p8(srr1);
- mce_get_ierror_p8(&mce_error_info, srr1);
- addr = regs->nip;
- }
-
- /* Handle UE error. */
- if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
- handled = mce_handle_ue_error(regs);
-
- save_mce_event(regs, handled, &mce_error_info, nip, addr);
- return handled;
+ return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table);
}
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index ae179cb1bb3c..c119044cad0d 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -67,7 +67,7 @@ PPC64_CACHES:
* flush all bytes from start through stop-1 inclusive
*/
-_GLOBAL(flush_icache_range)
+_GLOBAL_TOC(flush_icache_range)
BEGIN_FTR_SECTION
PURGE_PREFETCHED_INS
blr
@@ -120,7 +120,7 @@ EXPORT_SYMBOL(flush_icache_range)
*
* flush all bytes from start to stop-1 inclusive
*/
-_GLOBAL(flush_dcache_range)
+_GLOBAL_TOC(flush_dcache_range)
/*
* Flush the data cache to memory
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index d5e2b8309939..eae61b044e9e 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -389,51 +389,40 @@ static int nvram_pstore_open(struct pstore_info *psi)
/**
* nvram_pstore_write - pstore write callback for nvram
- * @type: Type of message logged
- * @reason: reason behind dump (oops/panic)
- * @id: identifier to indicate the write performed
- * @part: pstore writes data to registered buffer in parts,
- * part number will indicate the same.
- * @count: Indicates oops count
- * @compressed: Flag to indicate the log is compressed
- * @size: number of bytes written to the registered buffer
- * @psi: registered pstore_info structure
+ * @record: pstore record to write, with @id to be set
*
* Called by pstore_dump() when an oops or panic report is logged in the
* printk buffer.
* Returns 0 on successful write.
*/
-static int nvram_pstore_write(enum pstore_type_id type,
- enum kmsg_dump_reason reason,
- u64 *id, unsigned int part, int count,
- bool compressed, size_t size,
- struct pstore_info *psi)
+static int nvram_pstore_write(struct pstore_record *record)
{
int rc;
unsigned int err_type = ERR_TYPE_KERNEL_PANIC;
struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
/* part 1 has the recent messages from printk buffer */
- if (part > 1 || (type != PSTORE_TYPE_DMESG))
+ if (record->part > 1 || (record->type != PSTORE_TYPE_DMESG))
return -1;
if (clobbering_unread_rtas_event())
return -1;
oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
- oops_hdr->report_length = cpu_to_be16(size);
+ oops_hdr->report_length = cpu_to_be16(record->size);
oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
- if (compressed)
+ if (record->compressed)
err_type = ERR_TYPE_KERNEL_PANIC_GZ;
rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
- (int) (sizeof(*oops_hdr) + size), err_type, count);
+ (int) (sizeof(*oops_hdr) + record->size), err_type,
+ record->count);
if (rc != 0)
return rc;
- *id = part;
+ record->id = record->part;
return 0;
}
@@ -442,10 +431,7 @@ static int nvram_pstore_write(enum pstore_type_id type,
* Returns the length of the data we read from each partition.
* Returns 0 if we've been called before.
*/
-static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
- int *count, struct timespec *time, char **buf,
- bool *compressed, ssize_t *ecc_notice_size,
- struct pstore_info *psi)
+static ssize_t nvram_pstore_read(struct pstore_record *record)
{
struct oops_log_info *oops_hdr;
unsigned int err_type, id_no, size = 0;
@@ -459,40 +445,40 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
switch (nvram_type_ids[read_type]) {
case PSTORE_TYPE_DMESG:
part = &oops_log_partition;
- *type = PSTORE_TYPE_DMESG;
+ record->type = PSTORE_TYPE_DMESG;
break;
case PSTORE_TYPE_PPC_COMMON:
sig = NVRAM_SIG_SYS;
part = &common_partition;
- *type = PSTORE_TYPE_PPC_COMMON;
- *id = PSTORE_TYPE_PPC_COMMON;
- time->tv_sec = 0;
- time->tv_nsec = 0;
+ record->type = PSTORE_TYPE_PPC_COMMON;
+ record->id = PSTORE_TYPE_PPC_COMMON;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
break;
#ifdef CONFIG_PPC_PSERIES
case PSTORE_TYPE_PPC_RTAS:
part = &rtas_log_partition;
- *type = PSTORE_TYPE_PPC_RTAS;
- time->tv_sec = last_rtas_event;
- time->tv_nsec = 0;
+ record->type = PSTORE_TYPE_PPC_RTAS;
+ record->time.tv_sec = last_rtas_event;
+ record->time.tv_nsec = 0;
break;
case PSTORE_TYPE_PPC_OF:
sig = NVRAM_SIG_OF;
part = &of_config_partition;
- *type = PSTORE_TYPE_PPC_OF;
- *id = PSTORE_TYPE_PPC_OF;
- time->tv_sec = 0;
- time->tv_nsec = 0;
+ record->type = PSTORE_TYPE_PPC_OF;
+ record->id = PSTORE_TYPE_PPC_OF;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
break;
#endif
#ifdef CONFIG_PPC_POWERNV
case PSTORE_TYPE_PPC_OPAL:
sig = NVRAM_SIG_FW;
part = &skiboot_partition;
- *type = PSTORE_TYPE_PPC_OPAL;
- *id = PSTORE_TYPE_PPC_OPAL;
- time->tv_sec = 0;
- time->tv_nsec = 0;
+ record->type = PSTORE_TYPE_PPC_OPAL;
+ record->id = PSTORE_TYPE_PPC_OPAL;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
break;
#endif
default:
@@ -520,10 +506,10 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
return 0;
}
- *count = 0;
+ record->count = 0;
if (part->os_partition)
- *id = id_no;
+ record->id = id_no;
if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
size_t length, hdr_size;
@@ -533,34 +519,35 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
/* Old format oops header had 2-byte record size */
hdr_size = sizeof(u16);
length = be16_to_cpu(oops_hdr->version);
- time->tv_sec = 0;
- time->tv_nsec = 0;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
} else {
hdr_size = sizeof(*oops_hdr);
length = be16_to_cpu(oops_hdr->report_length);
- time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
- time->tv_nsec = 0;
+ record->time.tv_sec = be64_to_cpu(oops_hdr->timestamp);
+ record->time.tv_nsec = 0;
}
- *buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
+ record->buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
kfree(buff);
- if (*buf == NULL)
+ if (record->buf == NULL)
return -ENOMEM;
- *ecc_notice_size = 0;
+ record->ecc_notice_size = 0;
if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
- *compressed = true;
+ record->compressed = true;
else
- *compressed = false;
+ record->compressed = false;
return length;
}
- *buf = buff;
+ record->buf = buff;
return part->size;
}
static struct pstore_info nvram_pstore_info = {
.owner = THIS_MODULE,
.name = "nvram",
+ .flags = PSTORE_FLAGS_DMESG,
.open = nvram_pstore_open,
.read = nvram_pstore_read,
.write = nvram_pstore_write,
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 2282bf4e63cd..ec60ed0d4aad 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -243,10 +243,10 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
/*
* 2. branch to optimized_callback() and emulate_step()
*/
- kprobe_lookup_name("optimized_callback", op_callback_addr);
- kprobe_lookup_name("emulate_step", emulate_step_addr);
+ op_callback_addr = (kprobe_opcode_t *)ppc_kallsyms_lookup_name("optimized_callback");
+ emulate_step_addr = (kprobe_opcode_t *)ppc_kallsyms_lookup_name("emulate_step");
if (!op_callback_addr || !emulate_step_addr) {
- WARN(1, "kprobe_lookup_name() failed\n");
+ WARN(1, "Unable to lookup optimized_callback()/emulate_step()\n");
goto error;
}
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index dfc479df9634..8d63627e067f 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -245,3 +245,24 @@ void __init free_unused_pacas(void)
free_lppacas();
}
+
+void copy_mm_to_paca(struct mm_struct *mm)
+{
+#ifdef CONFIG_PPC_BOOK3S
+ mm_context_t *context = &mm->context;
+
+ get_paca()->mm_ctx_id = context->id;
+#ifdef CONFIG_PPC_MM_SLICES
+ VM_BUG_ON(!mm->context.addr_limit);
+ get_paca()->addr_limit = mm->context.addr_limit;
+ get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize;
+ memcpy(&get_paca()->mm_ctx_high_slices_psize,
+ &context->high_slices_psize, TASK_SLICE_ARRAY_SZ(mm));
+#else /* CONFIG_PPC_MM_SLICES */
+ get_paca()->mm_ctx_user_psize = context->user_psize;
+ get_paca()->mm_ctx_sllp = context->sllp;
+#endif
+#else /* CONFIG_PPC_BOOK3S */
+ return;
+#endif
+}
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index ffda24a38dda..341a7469cab8 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -233,6 +233,14 @@ void pcibios_reset_secondary_bus(struct pci_dev *dev)
pci_reset_secondary_bus(dev);
}
+resource_size_t pcibios_default_alignment(void)
+{
+ if (ppc_md.pcibios_default_alignment)
+ return ppc_md.pcibios_default_alignment();
+
+ return 0;
+}
+
#ifdef CONFIG_PCI_IOV
resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno)
{
@@ -513,7 +521,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
*
* Returns a negative error code on failure, zero on success.
*/
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, int bar,
+ struct vm_area_struct *vma,
enum pci_mmap_state mmap_state, int write_combine)
{
resource_size_t offset =
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f5d399e46193..d2f0afeae5a0 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -55,7 +55,6 @@
#include <asm/kexec.h>
#include <asm/opal.h>
#include <asm/fadump.h>
-#include <asm/debug.h>
#include <asm/epapr_hcalls.h>
#include <asm/firmware.h>
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a3944540fe0d..dd8a04f3053a 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -168,6 +168,14 @@ static unsigned long __initdata prom_tce_alloc_start;
static unsigned long __initdata prom_tce_alloc_end;
#endif
+static bool __initdata prom_radix_disable;
+
+struct platform_support {
+ bool hash_mmu;
+ bool radix_mmu;
+ bool radix_gtse;
+};
+
/* Platforms codes are now obsolete in the kernel. Now only used within this
* file and ultimately gone too. Feel free to change them if you need, they
* are not shared with anything outside of this file anymore
@@ -626,6 +634,12 @@ static void __init early_cmdline_parse(void)
prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
#endif
}
+
+ opt = strstr(prom_cmd_line, "disable_radix");
+ if (opt) {
+ prom_debug("Radix disabled from cmdline\n");
+ prom_radix_disable = true;
+ }
}
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
@@ -695,6 +709,8 @@ struct option_vector5 {
u8 byte22;
u8 intarch;
u8 mmu;
+ u8 hash_ext;
+ u8 radix_ext;
} __packed;
struct option_vector6 {
@@ -799,7 +815,7 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
.virt_base = cpu_to_be32(0xffffffff),
.virt_size = cpu_to_be32(0xffffffff),
.load_base = cpu_to_be32(0xffffffff),
- .min_rma = cpu_to_be32(256), /* 256MB min RMA */
+ .min_rma = cpu_to_be32(512), /* 512MB min RMA */
.min_load = cpu_to_be32(0xffffffff), /* full client load */
.min_rma_percent = 0, /* min RMA percentage of total RAM */
.max_pft_size = 48, /* max log_2(hash table size) */
@@ -850,8 +866,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
.reserved3 = 0,
.subprocessors = 1,
.intarch = 0,
- .mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) |
- OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE),
+ .mmu = 0,
+ .hash_ext = 0,
+ .radix_ext = 0,
},
/* option vector 6: IBM PAPR hints */
@@ -990,6 +1007,92 @@ static int __init prom_count_smt_threads(void)
}
+static void __init prom_parse_mmu_model(u8 val,
+ struct platform_support *support)
+{
+ switch (val) {
+ case OV5_FEAT(OV5_MMU_DYNAMIC):
+ case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */
+ prom_debug("MMU - either supported\n");
+ support->radix_mmu = !prom_radix_disable;
+ support->hash_mmu = true;
+ break;
+ case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */
+ prom_debug("MMU - radix only\n");
+ if (prom_radix_disable) {
+ /*
+ * If we __have__ to do radix, we're better off ignoring
+ * the command line rather than not booting.
+ */
+ prom_printf("WARNING: Ignoring cmdline option disable_radix\n");
+ }
+ support->radix_mmu = true;
+ break;
+ case OV5_FEAT(OV5_MMU_HASH):
+ prom_debug("MMU - hash only\n");
+ support->hash_mmu = true;
+ break;
+ default:
+ prom_debug("Unknown mmu support option: 0x%x\n", val);
+ break;
+ }
+}
+
+static void __init prom_parse_platform_support(u8 index, u8 val,
+ struct platform_support *support)
+{
+ switch (index) {
+ case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */
+ prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
+ break;
+ case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
+ if (val & OV5_FEAT(OV5_RADIX_GTSE)) {
+ prom_debug("Radix - GTSE supported\n");
+ support->radix_gtse = true;
+ }
+ break;
+ }
+}
+
+static void __init prom_check_platform_support(void)
+{
+ struct platform_support supported = {
+ .hash_mmu = false,
+ .radix_mmu = false,
+ .radix_gtse = false
+ };
+ int prop_len = prom_getproplen(prom.chosen,
+ "ibm,arch-vec-5-platform-support");
+ if (prop_len > 1) {
+ int i;
+ u8 vec[prop_len];
+ prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
+ prop_len);
+ prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support",
+ &vec, sizeof(vec));
+ for (i = 0; i < prop_len; i += 2) {
+ prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2
+ , vec[i]
+ , vec[i + 1]);
+ prom_parse_platform_support(vec[i], vec[i + 1],
+ &supported);
+ }
+ }
+
+ if (supported.radix_mmu && supported.radix_gtse) {
+ /* Radix preferred - but we require GTSE for now */
+ prom_debug("Asking for radix with GTSE\n");
+ ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
+ ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+ } else if (supported.hash_mmu) {
+ /* Default to hash mmu (if we can) */
+ prom_debug("Asking for hash\n");
+ ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH);
+ } else {
+ /* We're probably on a legacy hypervisor */
+ prom_debug("Assuming legacy hash support\n");
+ }
+}
static void __init prom_send_capabilities(void)
{
@@ -997,6 +1100,9 @@ static void __init prom_send_capabilities(void)
prom_arg_t ret;
u32 cores;
+ /* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */
+ prom_check_platform_support();
+
root = call_prom("open", 1, 1, ADDR("/"));
if (root != 0) {
/* We need to tell the FW about the number of cores we support.
@@ -2993,6 +3099,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
*/
prom_check_initrd(r3, r4);
+ /*
+ * Do early parsing of command line
+ */
+ early_cmdline_parse();
+
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
/*
* On pSeries, inform the firmware about our capabilities
@@ -3009,11 +3120,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
copy_and_flush(0, kbase, 0x100, 0);
/*
- * Do early parsing of command line
- */
- early_cmdline_parse();
-
- /*
* Initialize memory management within prom_init
*/
prom_init_mem();
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 4697da895133..69e077180db6 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -31,11 +31,11 @@
#include <linux/unistd.h>
#include <linux/serial.h>
#include <linux/serial_8250.h>
-#include <linux/debugfs.h>
#include <linux/percpu.h>
#include <linux/memblock.h>
#include <linux/of_platform.h>
#include <linux/hugetlb.h>
+#include <asm/debugfs.h>
#include <asm/io.h>
#include <asm/paca.h>
#include <asm/prom.h>
@@ -125,6 +125,11 @@ int ppc_do_canonicalize_irqs;
EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
#endif
+#ifdef CONFIG_CRASH_CORE
+/* This keeps a track of which one is the crashing cpu. */
+int crashing_cpu = -1;
+#endif
+
/* also used by kexec */
void machine_shutdown(void)
{
@@ -920,6 +925,15 @@ void __init setup_arch(char **cmdline_p)
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = klimit;
+
+#ifdef CONFIG_PPC_MM_SLICES
+#ifdef CONFIG_PPC64
+ init_mm.context.addr_limit = TASK_SIZE_128TB;
+#else
+#error "context.addr_limit not initialized."
+#endif
+#endif
+
#ifdef CONFIG_PPC_64K_PAGES
init_mm.context.pte_frag = NULL;
#endif
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index adf2084f214b..0d4dcaeaafcb 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -230,12 +230,21 @@ static void cpu_ready_for_interrupts(void)
* If we are not in hypervisor mode the job is done once for
* the whole partition in configure_exceptions().
*/
- if (early_cpu_has_feature(CPU_FTR_HVMODE) &&
- early_cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ if (cpu_has_feature(CPU_FTR_HVMODE) &&
+ cpu_has_feature(CPU_FTR_ARCH_207S)) {
unsigned long lpcr = mfspr(SPRN_LPCR);
mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
}
+ /*
+ * Fixup HFSCR:TM based on CPU features. The bit is set by our
+ * early asm init because at that point we haven't updated our
+ * CPU features from firmware and device-tree. Here we have,
+ * so let's do it.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
+ mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
+
/* Set IR and DR in PACA MSR */
get_paca()->kernel_msr = MSR_KERNEL;
}
@@ -408,7 +417,10 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
info->line_size = lsize;
info->block_size = bsize;
info->log_block_size = __ilog2(bsize);
- info->blocks_per_page = PAGE_SIZE / bsize;
+ if (bsize)
+ info->blocks_per_page = PAGE_SIZE / bsize;
+ else
+ info->blocks_per_page = 0;
if (sets == 0)
info->assoc = 0xffff;
@@ -625,6 +637,11 @@ void __init emergency_stack_init(void)
paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
+ /* emergency stack for NMI exception handling. */
+ ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+ klp_init_thread_info(ti);
+ paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+
/* emergency stack for machine check exception handling. */
ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
klp_init_thread_info(ti);
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 3a3671172436..e9436c5e1e09 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -14,6 +14,7 @@
#include <linux/uprobes.h>
#include <linux/key.h>
#include <linux/context_tracking.h>
+#include <linux/livepatch.h>
#include <asm/hw_breakpoint.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
@@ -162,6 +163,9 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
tracehook_notify_resume(regs);
}
+ if (thread_info_flags & _TIF_PATCH_PENDING)
+ klp_update_patch_state(current);
+
user_enter();
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 46f89e66a273..df2a41647d8e 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -39,6 +39,7 @@
#include <asm/irq.h>
#include <asm/hw_irq.h>
#include <asm/kvm_ppc.h>
+#include <asm/dbell.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/prom.h>
@@ -86,8 +87,6 @@ volatile unsigned int cpu_callin_map[NR_CPUS];
int smt_enabled_at_boot = 1;
-static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;
-
/*
* Returns 1 if the specified cpu should be brought up during boot.
* Used to inhibit booting threads if they've been disabled or
@@ -158,32 +157,33 @@ static irqreturn_t tick_broadcast_ipi_action(int irq, void *data)
return IRQ_HANDLED;
}
-static irqreturn_t debug_ipi_action(int irq, void *data)
+#ifdef CONFIG_NMI_IPI
+static irqreturn_t nmi_ipi_action(int irq, void *data)
{
- if (crash_ipi_function_ptr) {
- crash_ipi_function_ptr(get_irq_regs());
- return IRQ_HANDLED;
- }
-
-#ifdef CONFIG_DEBUGGER
- debugger_ipi(get_irq_regs());
-#endif /* CONFIG_DEBUGGER */
-
+ smp_handle_nmi_ipi(get_irq_regs());
return IRQ_HANDLED;
}
+#endif
static irq_handler_t smp_ipi_action[] = {
[PPC_MSG_CALL_FUNCTION] = call_function_action,
[PPC_MSG_RESCHEDULE] = reschedule_action,
[PPC_MSG_TICK_BROADCAST] = tick_broadcast_ipi_action,
- [PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action,
+#ifdef CONFIG_NMI_IPI
+ [PPC_MSG_NMI_IPI] = nmi_ipi_action,
+#endif
};
+/*
+ * The NMI IPI is a fallback and not truly non-maskable. It is simpler
+ * than going through the call function infrastructure, and strongly
+ * serialized, so it is more appropriate for debugging.
+ */
const char *smp_ipi_name[] = {
[PPC_MSG_CALL_FUNCTION] = "ipi call function",
[PPC_MSG_RESCHEDULE] = "ipi reschedule",
[PPC_MSG_TICK_BROADCAST] = "ipi tick-broadcast",
- [PPC_MSG_DEBUGGER_BREAK] = "ipi debugger",
+ [PPC_MSG_NMI_IPI] = "nmi ipi",
};
/* optional function to request ipi, for controllers with >= 4 ipis */
@@ -191,14 +191,13 @@ int smp_request_message_ipi(int virq, int msg)
{
int err;
- if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) {
+ if (msg < 0 || msg > PPC_MSG_NMI_IPI)
return -EINVAL;
- }
-#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC_CORE)
- if (msg == PPC_MSG_DEBUGGER_BREAK) {
+#ifndef CONFIG_NMI_IPI
+ if (msg == PPC_MSG_NMI_IPI)
return 1;
- }
#endif
+
err = request_irq(virq, smp_ipi_action[msg],
IRQF_PERCPU | IRQF_NO_THREAD | IRQF_NO_SUSPEND,
smp_ipi_name[msg], NULL);
@@ -211,17 +210,9 @@ int smp_request_message_ipi(int virq, int msg)
#ifdef CONFIG_PPC_SMP_MUXED_IPI
struct cpu_messages {
long messages; /* current messages */
- unsigned long data; /* data for cause ipi */
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message);
-void smp_muxed_ipi_set_data(int cpu, unsigned long data)
-{
- struct cpu_messages *info = &per_cpu(ipi_message, cpu);
-
- info->data = data;
-}
-
void smp_muxed_ipi_set_message(int cpu, int msg)
{
struct cpu_messages *info = &per_cpu(ipi_message, cpu);
@@ -236,14 +227,13 @@ void smp_muxed_ipi_set_message(int cpu, int msg)
void smp_muxed_ipi_message_pass(int cpu, int msg)
{
- struct cpu_messages *info = &per_cpu(ipi_message, cpu);
-
smp_muxed_ipi_set_message(cpu, msg);
+
/*
* cause_ipi functions are required to include a full barrier
* before doing whatever causes the IPI.
*/
- smp_ops->cause_ipi(cpu, info->data);
+ smp_ops->cause_ipi(cpu);
}
#ifdef __BIG_ENDIAN__
@@ -254,11 +244,18 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
irqreturn_t smp_ipi_demux(void)
{
- struct cpu_messages *info = this_cpu_ptr(&ipi_message);
- unsigned long all;
-
mb(); /* order any irq clear */
+ return smp_ipi_demux_relaxed();
+}
+
+/* sync-free variant. Callers should ensure synchronization */
+irqreturn_t smp_ipi_demux_relaxed(void)
+{
+ struct cpu_messages *info;
+ unsigned long all;
+
+ info = this_cpu_ptr(&ipi_message);
do {
all = xchg(&info->messages, 0);
#if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
@@ -278,8 +275,10 @@ irqreturn_t smp_ipi_demux(void)
scheduler_ipi();
if (all & IPI_MESSAGE(PPC_MSG_TICK_BROADCAST))
tick_broadcast_ipi_handler();
- if (all & IPI_MESSAGE(PPC_MSG_DEBUGGER_BREAK))
- debug_ipi_action(0, NULL);
+#ifdef CONFIG_NMI_IPI
+ if (all & IPI_MESSAGE(PPC_MSG_NMI_IPI))
+ nmi_ipi_action(0, NULL);
+#endif
} while (info->messages);
return IRQ_HANDLED;
@@ -316,6 +315,187 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
do_message_pass(cpu, PPC_MSG_CALL_FUNCTION);
}
+#ifdef CONFIG_NMI_IPI
+
+/*
+ * "NMI IPI" system.
+ *
+ * NMI IPIs may not be recoverable, so should not be used as ongoing part of
+ * a running system. They can be used for crash, debug, halt/reboot, etc.
+ *
+ * NMI IPIs are globally single threaded. No more than one in progress at
+ * any time.
+ *
+ * The IPI call waits with interrupts disabled until all targets enter the
+ * NMI handler, then the call returns.
+ *
+ * No new NMI can be initiated until targets exit the handler.
+ *
+ * The IPI call may time out without all targets entering the NMI handler.
+ * In that case, there is some logic to recover (and ignore subsequent
+ * NMI interrupts that may eventually be raised), but the platform interrupt
+ * handler may not be able to distinguish this from other exception causes,
+ * which may cause a crash.
+ */
+
+static atomic_t __nmi_ipi_lock = ATOMIC_INIT(0);
+static struct cpumask nmi_ipi_pending_mask;
+static int nmi_ipi_busy_count = 0;
+static void (*nmi_ipi_function)(struct pt_regs *) = NULL;
+
+static void nmi_ipi_lock_start(unsigned long *flags)
+{
+ raw_local_irq_save(*flags);
+ hard_irq_disable();
+ while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
+ raw_local_irq_restore(*flags);
+ cpu_relax();
+ raw_local_irq_save(*flags);
+ hard_irq_disable();
+ }
+}
+
+static void nmi_ipi_lock(void)
+{
+ while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
+ cpu_relax();
+}
+
+static void nmi_ipi_unlock(void)
+{
+ smp_mb();
+ WARN_ON(atomic_read(&__nmi_ipi_lock) != 1);
+ atomic_set(&__nmi_ipi_lock, 0);
+}
+
+static void nmi_ipi_unlock_end(unsigned long *flags)
+{
+ nmi_ipi_unlock();
+ raw_local_irq_restore(*flags);
+}
+
+/*
+ * Platform NMI handler calls this to ack
+ */
+int smp_handle_nmi_ipi(struct pt_regs *regs)
+{
+ void (*fn)(struct pt_regs *);
+ unsigned long flags;
+ int me = raw_smp_processor_id();
+ int ret = 0;
+
+ /*
+ * Unexpected NMIs are possible here because the interrupt may not
+ * be able to distinguish NMI IPIs from other types of NMIs, or
+ * because the caller may have timed out.
+ */
+ nmi_ipi_lock_start(&flags);
+ if (!nmi_ipi_busy_count)
+ goto out;
+ if (!cpumask_test_cpu(me, &nmi_ipi_pending_mask))
+ goto out;
+
+ fn = nmi_ipi_function;
+ if (!fn)
+ goto out;
+
+ cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
+ nmi_ipi_busy_count++;
+ nmi_ipi_unlock();
+
+ ret = 1;
+
+ fn(regs);
+
+ nmi_ipi_lock();
+ nmi_ipi_busy_count--;
+out:
+ nmi_ipi_unlock_end(&flags);
+
+ return ret;
+}
+
+static void do_smp_send_nmi_ipi(int cpu)
+{
+ if (smp_ops->cause_nmi_ipi && smp_ops->cause_nmi_ipi(cpu))
+ return;
+
+ if (cpu >= 0) {
+ do_message_pass(cpu, PPC_MSG_NMI_IPI);
+ } else {
+ int c;
+
+ for_each_online_cpu(c) {
+ if (c == raw_smp_processor_id())
+ continue;
+ do_message_pass(c, PPC_MSG_NMI_IPI);
+ }
+ }
+}
+
+/*
+ * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS.
+ * - fn is the target callback function.
+ * - delay_us > 0 is the delay before giving up waiting for targets to
+ * enter the handler, == 0 specifies indefinite delay.
+ */
+static int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
+{
+ unsigned long flags;
+ int me = raw_smp_processor_id();
+ int ret = 1;
+
+ BUG_ON(cpu == me);
+ BUG_ON(cpu < 0 && cpu != NMI_IPI_ALL_OTHERS);
+
+ if (unlikely(!smp_ops))
+ return 0;
+
+ /* Take the nmi_ipi_busy count/lock with interrupts hard disabled */
+ nmi_ipi_lock_start(&flags);
+ while (nmi_ipi_busy_count) {
+ nmi_ipi_unlock_end(&flags);
+ cpu_relax();
+ nmi_ipi_lock_start(&flags);
+ }
+
+ nmi_ipi_function = fn;
+
+ if (cpu < 0) {
+ /* ALL_OTHERS */
+ cpumask_copy(&nmi_ipi_pending_mask, cpu_online_mask);
+ cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
+ } else {
+ /* cpumask starts clear */
+ cpumask_set_cpu(cpu, &nmi_ipi_pending_mask);
+ }
+ nmi_ipi_busy_count++;
+ nmi_ipi_unlock();
+
+ do_smp_send_nmi_ipi(cpu);
+
+ while (!cpumask_empty(&nmi_ipi_pending_mask)) {
+ udelay(1);
+ if (delay_us) {
+ delay_us--;
+ if (!delay_us)
+ break;
+ }
+ }
+
+ nmi_ipi_lock();
+ if (!cpumask_empty(&nmi_ipi_pending_mask)) {
+ /* Could not gather all CPUs */
+ ret = 0;
+ cpumask_clear(&nmi_ipi_pending_mask);
+ }
+ nmi_ipi_busy_count--;
+ nmi_ipi_unlock_end(&flags);
+
+ return ret;
+}
+#endif /* CONFIG_NMI_IPI */
+
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
void tick_broadcast(const struct cpumask *mask)
{
@@ -326,29 +506,22 @@ void tick_broadcast(const struct cpumask *mask)
}
#endif
-#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
-void smp_send_debugger_break(void)
+#ifdef CONFIG_DEBUGGER
+void debugger_ipi_callback(struct pt_regs *regs)
{
- int cpu;
- int me = raw_smp_processor_id();
-
- if (unlikely(!smp_ops))
- return;
+ debugger_ipi(regs);
+}
- for_each_online_cpu(cpu)
- if (cpu != me)
- do_message_pass(cpu, PPC_MSG_DEBUGGER_BREAK);
+void smp_send_debugger_break(void)
+{
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, debugger_ipi_callback, 1000000);
}
#endif
#ifdef CONFIG_KEXEC_CORE
void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
{
- crash_ipi_function_ptr = crash_ipi_callback;
- if (crash_ipi_callback) {
- mb();
- smp_send_debugger_break();
- }
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_ipi_callback, 1000000);
}
#endif
@@ -439,7 +612,21 @@ int generic_cpu_disable(void)
#ifdef CONFIG_PPC64
vdso_data->processorCount--;
#endif
- migrate_irqs();
+ /* Update affinity of all IRQs previously aimed at this CPU */
+ irq_migrate_all_off_this_cpu();
+
+ /*
+ * Depending on the details of the interrupt controller, it's possible
+ * that one of the interrupts we just migrated away from this CPU is
+ * actually already pending on this CPU. If we leave it in that state
+ * the interrupt will never be EOI'ed, and will never fire again. So
+ * temporarily enable interrupts here, to allow any pending interrupt to
+ * be received (and EOI'ed), before we take this CPU offline.
+ */
+ local_irq_enable();
+ mdelay(1);
+ local_irq_disable();
+
return 0;
}
@@ -521,6 +708,16 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
cpu_idle_thread_init(cpu, tidle);
+ /*
+ * The platform might need to allocate resources prior to bringing
+ * up the CPU
+ */
+ if (smp_ops->prepare_cpu) {
+ rc = smp_ops->prepare_cpu(cpu);
+ if (rc)
+ return rc;
+ }
+
/* Make sure callin-map entry is 0 (can be leftover a CPU
* hotplug
*/
@@ -787,24 +984,21 @@ static struct sched_domain_topology_level powerpc_topology[] = {
{ NULL, },
};
-void __init smp_cpus_done(unsigned int max_cpus)
+static __init long smp_setup_cpu_workfn(void *data __always_unused)
{
- cpumask_var_t old_mask;
+ smp_ops->setup_cpu(boot_cpuid);
+ return 0;
+}
- /* We want the setup_cpu() here to be called from CPU 0, but our
- * init thread may have been "borrowed" by another CPU in the meantime
- * se we pin us down to CPU 0 for a short while
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+ /*
+ * We want the setup_cpu() here to be called on the boot CPU, but
+ * init might run on any CPU, so make sure it's invoked on the boot
+ * CPU.
*/
- alloc_cpumask_var(&old_mask, GFP_NOWAIT);
- cpumask_copy(old_mask, &current->cpus_allowed);
- set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
-
if (smp_ops && smp_ops->setup_cpu)
- smp_ops->setup_cpu(boot_cpuid);
-
- set_cpus_allowed_ptr(current, old_mask);
-
- free_cpumask_var(old_mask);
+ work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL);
if (smp_ops && smp_ops->bringup_done)
smp_ops->bringup_done();
@@ -812,7 +1006,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
dump_numa_cpu_topology();
set_sched_topology(powerpc_topology);
-
}
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 66711958493c..d534ed901538 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -59,7 +59,14 @@ EXPORT_SYMBOL_GPL(save_stack_trace);
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
- save_context_stack(trace, tsk->thread.ksp, tsk, 0);
+ unsigned long sp;
+
+ if (tsk == current)
+ sp = current_stack_pointer();
+ else
+ sp = tsk->thread.ksp;
+
+ save_context_stack(trace, sp, tsk, 0);
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index 6ae9bd5086a4..0050b2d2ff7a 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -10,6 +10,7 @@
*/
#include <linux/sched.h>
+#include <linux/suspend.h>
#include <asm/current.h>
#include <asm/mmu_context.h>
#include <asm/switch_to.h>
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index de04c9fbb5cd..a877bf8269fe 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -42,11 +42,11 @@
#include <asm/unistd.h>
#include <asm/asm-prototypes.h>
-static inline unsigned long do_mmap2(unsigned long addr, size_t len,
+static inline long do_mmap2(unsigned long addr, size_t len,
unsigned long prot, unsigned long flags,
unsigned long fd, unsigned long off, int shift)
{
- unsigned long ret = -EINVAL;
+ long ret = -EINVAL;
if (!arch_validate_prot(prot))
goto out;
@@ -62,16 +62,16 @@ out:
return ret;
}
-unsigned long sys_mmap2(unsigned long addr, size_t len,
- unsigned long prot, unsigned long flags,
- unsigned long fd, unsigned long pgoff)
+SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, unsigned long, pgoff)
{
return do_mmap2(addr, len, prot, flags, fd, pgoff, PAGE_SHIFT-12);
}
-unsigned long sys_mmap(unsigned long addr, size_t len,
- unsigned long prot, unsigned long flags,
- unsigned long fd, off_t offset)
+SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, off_t, offset)
{
return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT);
}
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index c1fb255a60d6..4437c70c7c2b 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -710,6 +710,10 @@ static int register_cpu_online(unsigned int cpu)
struct device_attribute *attrs, *pmc_attrs;
int i, nattrs;
+ /* For cpus present at boot a reference was already grabbed in register_cpu() */
+ if (!s->of_node)
+ s->of_node = of_get_cpu_node(cpu, NULL);
+
#ifdef CONFIG_PPC64
if (cpu_has_feature(CPU_FTR_SMT))
device_create_file(s, &dev_attr_smt_snooze_delay);
@@ -785,9 +789,9 @@ static int register_cpu_online(unsigned int cpu)
return 0;
}
+#ifdef CONFIG_HOTPLUG_CPU
static int unregister_cpu_online(unsigned int cpu)
{
-#ifdef CONFIG_HOTPLUG_CPU
struct cpu *c = &per_cpu(cpu_devices, cpu);
struct device *s = &c->dev;
struct device_attribute *attrs, *pmc_attrs;
@@ -864,9 +868,13 @@ static int unregister_cpu_online(unsigned int cpu)
}
#endif
cacheinfo_cpu_offline(cpu);
-#endif /* CONFIG_HOTPLUG_CPU */
+ of_node_put(s->of_node);
+ s->of_node = NULL;
return 0;
}
+#else /* !CONFIG_HOTPLUG_CPU */
+#define unregister_cpu_online NULL
+#endif
#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
ssize_t arch_cpu_probe(const char *buf, size_t count)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 07b90725855e..2b33cfaac7b8 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -995,8 +995,10 @@ static void __init init_decrementer_clockevent(void)
decrementer_clockevent.max_delta_ns =
clockevent_delta2ns(decrementer_max, &decrementer_clockevent);
+ decrementer_clockevent.max_delta_ticks = decrementer_max;
decrementer_clockevent.min_delta_ns =
clockevent_delta2ns(2, &decrementer_clockevent);
+ decrementer_clockevent.min_delta_ticks = 2;
register_decrementer_clockevent(cpu);
}
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
new file mode 100644
index 000000000000..729dffc5f7bc
--- /dev/null
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -0,0 +1,29 @@
+#
+# Makefile for the powerpc trace subsystem
+#
+
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
+ifdef CONFIG_FUNCTION_TRACER
+# do not trace tracer code
+CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+endif
+
+obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_32.o
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64.o
+ifdef CONFIG_MPROFILE_KERNEL
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_mprofile.o
+else
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o
+endif
+obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
+obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
+obj-$(CONFIG_TRACING) += trace_clock.o
+
+obj-$(CONFIG_PPC64) += $(obj64-y)
+obj-$(CONFIG_PPC32) += $(obj32-y)
+
+# Disable GCOV & sanitizers in odd or sensitive code
+GCOV_PROFILE_ftrace.o := n
+UBSAN_SANITIZE_ftrace.o := n
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 5c9f50c1aa99..32509de6ce4c 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -21,6 +21,7 @@
#include <linux/init.h>
#include <linux/list.h>
+#include <asm/asm-prototypes.h>
#include <asm/cacheflush.h>
#include <asm/code-patching.h>
#include <asm/ftrace.h>
diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S
new file mode 100644
index 000000000000..afef2c076282
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_32.S
@@ -0,0 +1,118 @@
+/*
+ * Split from entry_32.S
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/magic.h>
+#include <asm/reg.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/export.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+ /*
+ * It is required that _mcount on PPC32 must preserve the
+ * link register. But we have r0 to play with. We use r0
+ * to push the return address back to the caller of mcount
+ * into the ctr register, restore the link register and
+ * then jump back using the ctr register.
+ */
+ mflr r0
+ mtctr r0
+ lwz r0, 4(r1)
+ mtlr r0
+ bctr
+
+_GLOBAL(ftrace_caller)
+ MCOUNT_SAVE_FRAME
+ /* r3 ends up with link register */
+ subi r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+ bl ftrace_stub
+ nop
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ b ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+ MCOUNT_RESTORE_FRAME
+ /* old link register ends up in ctr reg */
+ bctr
+#else
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+
+ MCOUNT_SAVE_FRAME
+
+ subi r3, r3, MCOUNT_INSN_SIZE
+ LOAD_REG_ADDR(r5, ftrace_trace_function)
+ lwz r5,0(r5)
+
+ mtctr r5
+ bctrl
+ nop
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ b ftrace_graph_caller
+#endif
+ MCOUNT_RESTORE_FRAME
+ bctr
+#endif
+EXPORT_SYMBOL(_mcount)
+
+_GLOBAL(ftrace_stub)
+ blr
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+ /* load r4 with local address */
+ lwz r4, 44(r1)
+ subi r4, r4, MCOUNT_INSN_SIZE
+
+ /* Grab the LR out of the caller stack frame */
+ lwz r3,52(r1)
+
+ bl prepare_ftrace_return
+ nop
+
+ /*
+ * prepare_ftrace_return gives us the address we divert to.
+ * Change the LR in the callers stack frame to this.
+ */
+ stw r3,52(r1)
+
+ MCOUNT_RESTORE_FRAME
+ /* old link register ends up in ctr reg */
+ bctr
+
+_GLOBAL(return_to_handler)
+ /* need to save return values */
+ stwu r1, -32(r1)
+ stw r3, 20(r1)
+ stw r4, 16(r1)
+ stw r31, 12(r1)
+ mr r31, r1
+
+ bl ftrace_return_to_handler
+ nop
+
+ /* return value has real return address */
+ mtlr r3
+
+ lwz r3, 20(r1)
+ lwz r4, 16(r1)
+ lwz r31,12(r1)
+ lwz r1, 0(r1)
+
+ /* Jump back to real return address */
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_64.S b/arch/powerpc/kernel/trace/ftrace_64.S
new file mode 100644
index 000000000000..e5ccea19821e
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_64.S
@@ -0,0 +1,85 @@
+/*
+ * Split from entry_64.S
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/magic.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ppc-opcode.h>
+#include <asm/export.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
+ mflr r12
+ mtctr r12
+ mtlr r0
+ bctr
+
+#else /* CONFIG_DYNAMIC_FTRACE */
+_GLOBAL_TOC(_mcount)
+EXPORT_SYMBOL(_mcount)
+ /* Taken from output of objdump from lib64/glibc */
+ mflr r3
+ ld r11, 0(r1)
+ stdu r1, -112(r1)
+ std r3, 128(r1)
+ ld r4, 16(r11)
+
+ subi r3, r3, MCOUNT_INSN_SIZE
+ LOAD_REG_ADDR(r5,ftrace_trace_function)
+ ld r5,0(r5)
+ ld r5,0(r5)
+ mtctr r5
+ bctrl
+ nop
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ b ftrace_graph_caller
+#endif
+ ld r0, 128(r1)
+ mtlr r0
+ addi r1, r1, 112
+_GLOBAL(ftrace_stub)
+ blr
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(return_to_handler)
+ /* need to save return values */
+ std r4, -32(r1)
+ std r3, -24(r1)
+ /* save TOC */
+ std r2, -16(r1)
+ std r31, -8(r1)
+ mr r31, r1
+ stdu r1, -112(r1)
+
+ /*
+ * We might be called from a module.
+ * Switch to our TOC to run inside the core kernel.
+ */
+ ld r2, PACATOC(r13)
+
+ bl ftrace_return_to_handler
+ nop
+
+ /* return value has real return address */
+ mtlr r3
+
+ ld r1, 0(r1)
+ ld r4, -32(r1)
+ ld r3, -24(r1)
+ ld r2, -16(r1)
+ ld r31, -8(r1)
+
+ /* Jump back to real return address */
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
new file mode 100644
index 000000000000..7c933a99f5d5
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -0,0 +1,272 @@
+/*
+ * Split from ftrace_64.S
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/magic.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ppc-opcode.h>
+#include <asm/export.h>
+#include <asm/thread_info.h>
+#include <asm/bug.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ *
+ * ftrace_caller() is the function that replaces _mcount() when ftrace is
+ * active.
+ *
+ * We arrive here after a function A calls function B, and we are the trace
+ * function for B. When we enter r1 points to A's stack frame, B has not yet
+ * had a chance to allocate one yet.
+ *
+ * Additionally r2 may point either to the TOC for A, or B, depending on
+ * whether B did a TOC setup sequence before calling us.
+ *
+ * On entry the LR points back to the _mcount() call site, and r0 holds the
+ * saved LR as it was on entry to B, ie. the original return address at the
+ * call site in A.
+ *
+ * Our job is to save the register state into a struct pt_regs (on the stack)
+ * and then arrange for the ftrace function to be called.
+ */
+_GLOBAL(ftrace_caller)
+ /* Save the original return address in A's stack frame */
+ std r0,LRSAVE(r1)
+
+ /* Create our stack frame + pt_regs */
+ stdu r1,-SWITCH_FRAME_SIZE(r1)
+
+ /* Save all gprs to pt_regs */
+ SAVE_8GPRS(0,r1)
+ SAVE_8GPRS(8,r1)
+ SAVE_8GPRS(16,r1)
+ SAVE_8GPRS(24,r1)
+
+ /* Load special regs for save below */
+ mfmsr r8
+ mfctr r9
+ mfxer r10
+ mfcr r11
+
+ /* Get the _mcount() call site out of LR */
+ mflr r7
+ /* Save it as pt_regs->nip */
+ std r7, _NIP(r1)
+ /* Save the read LR in pt_regs->link */
+ std r0, _LINK(r1)
+
+ /* Save callee's TOC in the ABI compliant location */
+ std r2, 24(r1)
+ ld r2,PACATOC(r13) /* get kernel TOC in r2 */
+
+ addis r3,r2,function_trace_op@toc@ha
+ addi r3,r3,function_trace_op@toc@l
+ ld r5,0(r3)
+
+#ifdef CONFIG_LIVEPATCH
+ mr r14,r7 /* remember old NIP */
+#endif
+ /* Calculate ip from nip-4 into r3 for call below */
+ subi r3, r7, MCOUNT_INSN_SIZE
+
+ /* Put the original return address in r4 as parent_ip */
+ mr r4, r0
+
+ /* Save special regs */
+ std r8, _MSR(r1)
+ std r9, _CTR(r1)
+ std r10, _XER(r1)
+ std r11, _CCR(r1)
+
+ /* Load &pt_regs in r6 for call below */
+ addi r6, r1 ,STACK_FRAME_OVERHEAD
+
+ /* ftrace_call(r3, r4, r5, r6) */
+.globl ftrace_call
+ftrace_call:
+ bl ftrace_stub
+ nop
+
+ /* Load ctr with the possibly modified NIP */
+ ld r3, _NIP(r1)
+ mtctr r3
+#ifdef CONFIG_LIVEPATCH
+ cmpd r14,r3 /* has NIP been altered? */
+#endif
+
+ /* Restore gprs */
+ REST_8GPRS(0,r1)
+ REST_8GPRS(8,r1)
+ REST_8GPRS(16,r1)
+ REST_8GPRS(24,r1)
+
+ /* Restore possibly modified LR */
+ ld r0, _LINK(r1)
+ mtlr r0
+
+ /* Restore callee's TOC */
+ ld r2, 24(r1)
+
+ /* Pop our stack frame */
+ addi r1, r1, SWITCH_FRAME_SIZE
+
+#ifdef CONFIG_LIVEPATCH
+ /* Based on the cmpd above, if the NIP was altered handle livepatch */
+ bne- livepatch_handler
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ b ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+
+ bctr /* jump after _mcount site */
+
+_GLOBAL(ftrace_stub)
+ blr
+
+#ifdef CONFIG_LIVEPATCH
+ /*
+ * This function runs in the mcount context, between two functions. As
+ * such it can only clobber registers which are volatile and used in
+ * function linkage.
+ *
+ * We get here when a function A, calls another function B, but B has
+ * been live patched with a new function C.
+ *
+ * On entry:
+ * - we have no stack frame and can not allocate one
+ * - LR points back to the original caller (in A)
+ * - CTR holds the new NIP in C
+ * - r0 & r12 are free
+ *
+ * r0 can't be used as the base register for a DS-form load or store, so
+ * we temporarily shuffle r1 (stack pointer) into r0 and then put it back.
+ */
+livepatch_handler:
+ CURRENT_THREAD_INFO(r12, r1)
+
+ /* Save stack pointer into r0 */
+ mr r0, r1
+
+ /* Allocate 3 x 8 bytes */
+ ld r1, TI_livepatch_sp(r12)
+ addi r1, r1, 24
+ std r1, TI_livepatch_sp(r12)
+
+ /* Save toc & real LR on livepatch stack */
+ std r2, -24(r1)
+ mflr r12
+ std r12, -16(r1)
+
+ /* Store stack end marker */
+ lis r12, STACK_END_MAGIC@h
+ ori r12, r12, STACK_END_MAGIC@l
+ std r12, -8(r1)
+
+ /* Restore real stack pointer */
+ mr r1, r0
+
+ /* Put ctr in r12 for global entry and branch there */
+ mfctr r12
+ bctrl
+
+ /*
+ * Now we are returning from the patched function to the original
+ * caller A. We are free to use r0 and r12, and we can use r2 until we
+ * restore it.
+ */
+
+ CURRENT_THREAD_INFO(r12, r1)
+
+ /* Save stack pointer into r0 */
+ mr r0, r1
+
+ ld r1, TI_livepatch_sp(r12)
+
+ /* Check stack marker hasn't been trashed */
+ lis r2, STACK_END_MAGIC@h
+ ori r2, r2, STACK_END_MAGIC@l
+ ld r12, -8(r1)
+1: tdne r12, r2
+ EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
+
+ /* Restore LR & toc from livepatch stack */
+ ld r12, -16(r1)
+ mtlr r12
+ ld r2, -24(r1)
+
+ /* Pop livepatch stack frame */
+ CURRENT_THREAD_INFO(r12, r0)
+ subi r1, r1, 24
+ std r1, TI_livepatch_sp(r12)
+
+ /* Restore real stack pointer */
+ mr r1, r0
+
+ /* Return to original caller of live patched function */
+ blr
+#endif /* CONFIG_LIVEPATCH */
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+ stdu r1, -112(r1)
+ /* with -mprofile-kernel, parameter regs are still alive at _mcount */
+ std r10, 104(r1)
+ std r9, 96(r1)
+ std r8, 88(r1)
+ std r7, 80(r1)
+ std r6, 72(r1)
+ std r5, 64(r1)
+ std r4, 56(r1)
+ std r3, 48(r1)
+
+ /* Save callee's TOC in the ABI compliant location */
+ std r2, 24(r1)
+ ld r2, PACATOC(r13) /* get kernel TOC in r2 */
+
+ mfctr r4 /* ftrace_caller has moved local addr here */
+ std r4, 40(r1)
+ mflr r3 /* ftrace_caller has restored LR from stack */
+ subi r4, r4, MCOUNT_INSN_SIZE
+
+ bl prepare_ftrace_return
+ nop
+
+ /*
+ * prepare_ftrace_return gives us the address we divert to.
+ * Change the LR to this.
+ */
+ mtlr r3
+
+ ld r0, 40(r1)
+ mtctr r0
+ ld r10, 104(r1)
+ ld r9, 96(r1)
+ ld r8, 88(r1)
+ ld r7, 80(r1)
+ ld r6, 72(r1)
+ ld r5, 64(r1)
+ ld r4, 56(r1)
+ ld r3, 48(r1)
+
+ /* Restore callee's TOC */
+ ld r2, 24(r1)
+
+ addi r1, r1, 112
+ mflr r0
+ std r0, LRSAVE(r1)
+ bctr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg.S
new file mode 100644
index 000000000000..f095358da96e
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.S
@@ -0,0 +1,68 @@
+/*
+ * Split from ftrace_64.S
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/magic.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ppc-opcode.h>
+#include <asm/export.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+_GLOBAL_TOC(ftrace_caller)
+ /* Taken from output of objdump from lib64/glibc */
+ mflr r3
+ ld r11, 0(r1)
+ stdu r1, -112(r1)
+ std r3, 128(r1)
+ ld r4, 16(r11)
+ subi r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+ bl ftrace_stub
+ nop
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ b ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+ ld r0, 128(r1)
+ mtlr r0
+ addi r1, r1, 112
+
+_GLOBAL(ftrace_stub)
+ blr
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+ /* load r4 with local address */
+ ld r4, 128(r1)
+ subi r4, r4, MCOUNT_INSN_SIZE
+
+ /* Grab the LR out of the caller stack frame */
+ ld r11, 112(r1)
+ ld r3, 16(r11)
+
+ bl prepare_ftrace_return
+ nop
+
+ /*
+ * prepare_ftrace_return gives us the address we divert to.
+ * Change the LR in the callers stack frame to this.
+ */
+ ld r11, 112(r1)
+ std r3, 16(r11)
+
+ ld r0, 128(r1)
+ mtlr r0
+ addi r1, r1, 112
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace_clock.c b/arch/powerpc/kernel/trace/trace_clock.c
index 49170690946d..49170690946d 100644
--- a/arch/powerpc/kernel/trace_clock.c
+++ b/arch/powerpc/kernel/trace/trace_clock.c
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index ff365f9de27a..d4e545d27ef9 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -35,13 +35,13 @@
#include <linux/backlight.h>
#include <linux/bug.h>
#include <linux/kdebug.h>
-#include <linux/debugfs.h>
#include <linux/ratelimit.h>
#include <linux/context_tracking.h>
#include <asm/emulated_ops.h>
#include <asm/pgtable.h>
#include <linux/uaccess.h>
+#include <asm/debugfs.h>
#include <asm/io.h>
#include <asm/machdep.h>
#include <asm/rtas.h>
@@ -279,18 +279,35 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
void system_reset_exception(struct pt_regs *regs)
{
+ /*
+ * Avoid crashes in case of nested NMI exceptions. Recoverability
+ * is determined by RI and in_nmi
+ */
+ bool nested = in_nmi();
+ if (!nested)
+ nmi_enter();
+
/* See if any machine dependent calls */
if (ppc_md.system_reset_exception) {
if (ppc_md.system_reset_exception(regs))
- return;
+ goto out;
}
die("System Reset", regs, SIGABRT);
+out:
+#ifdef CONFIG_PPC_BOOK3S_64
+ BUG_ON(get_paca()->in_nmi == 0);
+ if (get_paca()->in_nmi > 1)
+ panic("Unrecoverable nested System Reset");
+#endif
/* Must die if the interrupt is not recoverable */
if (!(regs->msr & MSR_RI))
panic("Unrecoverable System Reset");
+ if (!nested)
+ nmi_exit();
+
/* What should we do here? We could issue a shutdown or hard reset. */
}
@@ -306,8 +323,6 @@ long machine_check_early(struct pt_regs *regs)
__this_cpu_inc(irq_stat.mce_exceptions);
- add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
handled = cur_cpu_spec->machine_check_early(regs);
return handled;
@@ -741,6 +756,8 @@ void machine_check_exception(struct pt_regs *regs)
__this_cpu_inc(irq_stat.mce_exceptions);
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
/* See if any machine dependent calls. In theory, we would want
* to call the CPU first, and call the ppc_md. one if the CPU
* one returns a positive number. However there is existing code
@@ -1440,6 +1457,8 @@ void facility_unavailable_exception(struct pt_regs *regs)
[FSCR_TM_LG] = "TM",
[FSCR_EBB_LG] = "EBB",
[FSCR_TAR_LG] = "TAR",
+ [FSCR_MSGP_LG] = "MSGP",
+ [FSCR_SCV_LG] = "SCV",
};
char *facility = "unknown";
u64 value;
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 7394b770ae1f..2f793be3d2b1 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -77,6 +77,8 @@ SECTIONS
#endif
} :kernel
+ __head_end = .;
+
/*
* If the build dies here, it's likely code in head_64.S is referencing
* labels it can't reach, and the linker inserting stubs without the
@@ -312,6 +314,8 @@ SECTIONS
NOSAVE_DATA
}
+ BUG_TABLE
+
. = ALIGN(PAGE_SIZE);
_edata = .;
PROVIDE32 (edata = .);
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 029be26b5a17..24de532c1736 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -67,6 +67,7 @@ config KVM_BOOK3S_64
select KVM_BOOK3S_64_HANDLER
select KVM
select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
+ select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
---help---
Support running unmodified book3s_64 and book3s_32 guest kernels
in virtual machines on book3s_64 host processors.
@@ -196,6 +197,11 @@ config KVM_XICS
Specification) interrupt controller architecture used on
IBM POWER (pSeries) servers.
+config KVM_XIVE
+ bool
+ default y
+ depends on KVM_XICS && PPC_XIVE_NATIVE && KVM_BOOK3S_HV_POSSIBLE
+
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index b87ccde2137a..d91a2604c496 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -74,7 +74,7 @@ kvm-hv-y += \
book3s_64_mmu_radix.o
kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
- book3s_hv_rm_xics.o
+ book3s_hv_rm_xics.o book3s_hv_rm_xive.o
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
@@ -89,6 +89,8 @@ endif
kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
book3s_xics.o
+kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+
kvm-book3s_64-module-objs := \
$(common-objs-y) \
book3s.o \
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index b6b5c185bd92..72d977e30952 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -20,6 +20,10 @@
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/miscdevice.h>
+#include <linux/gfp.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
#include <asm/reg.h>
#include <asm/cputable.h>
@@ -31,10 +35,7 @@
#include <asm/kvm_book3s.h>
#include <asm/mmu_context.h>
#include <asm/page.h>
-#include <linux/gfp.h>
-#include <linux/sched.h>
-#include <linux/vmalloc.h>
-#include <linux/highmem.h>
+#include <asm/xive.h>
#include "book3s.h"
#include "trace.h"
@@ -197,6 +198,24 @@ void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
}
EXPORT_SYMBOL_GPL(kvmppc_core_queue_program);
+void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu)
+{
+ /* might as well deliver this straight away */
+ kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, 0);
+}
+
+void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu)
+{
+ /* might as well deliver this straight away */
+ kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_ALTIVEC, 0);
+}
+
+void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu)
+{
+ /* might as well deliver this straight away */
+ kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_VSX, 0);
+}
+
void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
{
kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
@@ -578,11 +597,14 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
break;
#ifdef CONFIG_KVM_XICS
case KVM_REG_PPC_ICP_STATE:
- if (!vcpu->arch.icp) {
+ if (!vcpu->arch.icp && !vcpu->arch.xive_vcpu) {
r = -ENXIO;
break;
}
- *val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
+ if (xive_enabled())
+ *val = get_reg_val(id, kvmppc_xive_get_icp(vcpu));
+ else
+ *val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
break;
#endif /* CONFIG_KVM_XICS */
case KVM_REG_PPC_FSCR:
@@ -648,12 +670,14 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
#endif /* CONFIG_VSX */
#ifdef CONFIG_KVM_XICS
case KVM_REG_PPC_ICP_STATE:
- if (!vcpu->arch.icp) {
+ if (!vcpu->arch.icp && !vcpu->arch.xive_vcpu) {
r = -ENXIO;
break;
}
- r = kvmppc_xics_set_icp(vcpu,
- set_reg_val(id, *val));
+ if (xive_enabled())
+ r = kvmppc_xive_set_icp(vcpu, set_reg_val(id, *val));
+ else
+ r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val));
break;
#endif /* CONFIG_KVM_XICS */
case KVM_REG_PPC_FSCR:
@@ -924,6 +948,50 @@ int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hcall)
return kvm->arch.kvm_ops->hcall_implemented(hcall);
}
+#ifdef CONFIG_KVM_XICS
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
+{
+ if (xive_enabled())
+ return kvmppc_xive_set_irq(kvm, irq_source_id, irq, level,
+ line_status);
+ else
+ return kvmppc_xics_set_irq(kvm, irq_source_id, irq, level,
+ line_status);
+}
+
+int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *irq_entry,
+ struct kvm *kvm, int irq_source_id,
+ int level, bool line_status)
+{
+ return kvm_set_irq(kvm, irq_source_id, irq_entry->gsi,
+ level, line_status);
+}
+static int kvmppc_book3s_set_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ return kvm_set_irq(kvm, irq_source_id, e->gsi, level, line_status);
+}
+
+int kvm_irq_map_gsi(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *entries, int gsi)
+{
+ entries->gsi = gsi;
+ entries->type = KVM_IRQ_ROUTING_IRQCHIP;
+ entries->set = kvmppc_book3s_set_irq;
+ entries->irqchip.irqchip = 0;
+ entries->irqchip.pin = gsi;
+ return 1;
+}
+
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ return pin;
+}
+
+#endif /* CONFIG_KVM_XICS */
+
static int kvmppc_book3s_init(void)
{
int r;
@@ -934,12 +1002,25 @@ static int kvmppc_book3s_init(void)
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
r = kvmppc_book3s_init_pr();
#endif
- return r;
+#ifdef CONFIG_KVM_XICS
+#ifdef CONFIG_KVM_XIVE
+ if (xive_enabled()) {
+ kvmppc_xive_init_module();
+ kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
+ } else
+#endif
+ kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
+#endif
+ return r;
}
static void kvmppc_book3s_exit(void)
{
+#ifdef CONFIG_KVM_XICS
+ if (xive_enabled())
+ kvmppc_xive_exit_module();
+#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
kvmppc_book3s_exit_pr();
#endif
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 70153578131a..29ebe2fd5867 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -319,6 +319,7 @@ do_second:
gpte->may_execute = true;
gpte->may_read = false;
gpte->may_write = false;
+ gpte->wimg = r & HPTE_R_WIMG;
switch (pp) {
case 0:
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index a587e8f4fd26..9a4614cd0e53 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -145,6 +145,8 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
else
kvmppc_mmu_flush_icache(pfn);
+ rflags = (rflags & ~HPTE_R_WIMG) | orig_pte->wimg;
+
/*
* Use 64K pages if possible; otherwise, on 64K page kernels,
* we need to transfer 4 more bits from guest real to host real addr.
@@ -177,12 +179,15 @@ map_again:
ret = mmu_hash_ops.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
hpsize, hpsize, MMU_SEGSIZE_256M);
- if (ret < 0) {
+ if (ret == -1) {
/* If we couldn't map a primary PTE, try a secondary */
hash = ~hash;
vflags ^= HPTE_V_SECONDARY;
attempt++;
goto map_again;
+ } else if (ret < 0) {
+ r = -EIO;
+ goto out_unlock;
} else {
trace_kvm_book3s_64_mmu_map(rflags, hpteg,
vpn, hpaddr, orig_pte);
@@ -229,6 +234,7 @@ void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
{
+ unsigned long vsid_bits = VSID_BITS_65_256M;
struct kvmppc_sid_map *map;
struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
u16 sid_map_mask;
@@ -257,7 +263,12 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
kvmppc_mmu_pte_flush(vcpu, 0, 0);
kvmppc_mmu_flush_segments(vcpu);
}
- map->host_vsid = vsid_scramble(vcpu_book3s->proto_vsid_next++, 256M);
+
+ if (mmu_has_feature(MMU_FTR_68_BIT_VA))
+ vsid_bits = VSID_BITS_256M;
+
+ map->host_vsid = vsid_scramble(vcpu_book3s->proto_vsid_next++,
+ VSID_MULTIPLIER_256M, vsid_bits);
map->guest_vsid = gvsid;
map->valid = true;
@@ -390,7 +401,7 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
int err;
- err = __init_new_context();
+ err = hash__alloc_context_id();
if (err < 0)
return -1;
vcpu3s->context_id[0] = err;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index f3158fb16de3..710e491206ed 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -601,7 +601,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
hva, NULL, NULL);
if (ptep) {
pte = kvmppc_read_update_linux_pte(ptep, 1);
- if (pte_write(pte))
+ if (__pte_write(pte))
write_ok = 1;
}
local_irq_restore(flags);
@@ -1487,6 +1487,10 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
/* start new resize */
resize = kzalloc(sizeof(*resize), GFP_KERNEL);
+ if (!resize) {
+ ret = -ENOMEM;
+ goto out;
+ }
resize->order = shift;
resize->kvm = kvm;
INIT_WORK(&resize->work, resize_hpt_prepare_work);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 3e26cd4979f9..a160c14304eb 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -28,6 +28,8 @@
#include <linux/hugetlb.h>
#include <linux/list.h>
#include <linux/anon_inodes.h>
+#include <linux/iommu.h>
+#include <linux/file.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -40,6 +42,7 @@
#include <asm/udbg.h>
#include <asm/iommu.h>
#include <asm/tce.h>
+#include <asm/mmu_context.h>
static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
{
@@ -91,6 +94,137 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
return ret;
}
+static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
+{
+ struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
+ struct kvmppc_spapr_tce_iommu_table, rcu);
+
+ iommu_tce_table_put(stit->tbl);
+
+ kfree(stit);
+}
+
+static void kvm_spapr_tce_liobn_put(struct kref *kref)
+{
+ struct kvmppc_spapr_tce_iommu_table *stit = container_of(kref,
+ struct kvmppc_spapr_tce_iommu_table, kref);
+
+ list_del_rcu(&stit->next);
+
+ call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
+}
+
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+ struct iommu_group *grp)
+{
+ int i;
+ struct kvmppc_spapr_tce_table *stt;
+ struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
+ struct iommu_table_group *table_group = NULL;
+
+ list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+
+ table_group = iommu_group_get_iommudata(grp);
+ if (WARN_ON(!table_group))
+ continue;
+
+ list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ if (table_group->tables[i] != stit->tbl)
+ continue;
+
+ kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
+ return;
+ }
+ }
+ }
+}
+
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+ struct iommu_group *grp)
+{
+ struct kvmppc_spapr_tce_table *stt = NULL;
+ bool found = false;
+ struct iommu_table *tbl = NULL;
+ struct iommu_table_group *table_group;
+ long i;
+ struct kvmppc_spapr_tce_iommu_table *stit;
+ struct fd f;
+
+ f = fdget(tablefd);
+ if (!f.file)
+ return -EBADF;
+
+ list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+ if (stt == f.file->private_data) {
+ found = true;
+ break;
+ }
+ }
+
+ fdput(f);
+
+ if (!found)
+ return -EINVAL;
+
+ table_group = iommu_group_get_iommudata(grp);
+ if (WARN_ON(!table_group))
+ return -EFAULT;
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbltmp = table_group->tables[i];
+
+ if (!tbltmp)
+ continue;
+ /*
+ * Make sure hardware table parameters are exactly the same;
+ * this is used in the TCE handlers where boundary checks
+ * use only the first attached table.
+ */
+ if ((tbltmp->it_page_shift == stt->page_shift) &&
+ (tbltmp->it_offset == stt->offset) &&
+ (tbltmp->it_size == stt->size)) {
+ /*
+ * Reference the table to avoid races with
+ * add/remove DMA windows.
+ */
+ tbl = iommu_tce_table_get(tbltmp);
+ break;
+ }
+ }
+ if (!tbl)
+ return -EINVAL;
+
+ list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
+ if (tbl != stit->tbl)
+ continue;
+
+ if (!kref_get_unless_zero(&stit->kref)) {
+ /* stit is being destroyed */
+ iommu_tce_table_put(tbl);
+ return -ENOTTY;
+ }
+ /*
+ * The table is already known to this KVM, we just increased
+ * its KVM reference counter and can return.
+ */
+ return 0;
+ }
+
+ stit = kzalloc(sizeof(*stit), GFP_KERNEL);
+ if (!stit) {
+ iommu_tce_table_put(tbl);
+ return -ENOMEM;
+ }
+
+ stit->tbl = tbl;
+ kref_init(&stit->kref);
+
+ list_add_rcu(&stit->next, &stt->iommu_tables);
+
+ return 0;
+}
+
static void release_spapr_tce_table(struct rcu_head *head)
{
struct kvmppc_spapr_tce_table *stt = container_of(head,
@@ -130,9 +264,18 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
{
struct kvmppc_spapr_tce_table *stt = filp->private_data;
+ struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
list_del_rcu(&stt->list);
+ list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+ WARN_ON(!kref_read(&stit->kref));
+ while (1) {
+ if (kref_put(&stit->kref, kvm_spapr_tce_liobn_put))
+ break;
+ }
+ }
+
kvm_put_kvm(stt->kvm);
kvmppc_account_memlimit(
@@ -164,7 +307,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
return -EBUSY;
}
- size = args->size;
+ size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
npages = kvmppc_tce_pages(size);
ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
if (ret) {
@@ -183,6 +326,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
stt->offset = args->offset;
stt->size = size;
stt->kvm = kvm;
+ INIT_LIST_HEAD_RCU(&stt->iommu_tables);
for (i = 0; i < npages; i++) {
stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
@@ -211,15 +355,106 @@ fail:
return ret;
}
+static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+ unsigned long hpa = 0;
+ enum dma_data_direction dir = DMA_NONE;
+
+ iommu_tce_xchg(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ struct mm_iommu_table_group_mem_t *mem = NULL;
+ const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+ unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+ if (!pua)
+ /* it_userspace allocation might be delayed */
+ return H_TOO_HARD;
+
+ mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
+ if (!mem)
+ return H_TOO_HARD;
+
+ mm_iommu_mapped_dec(mem);
+
+ *pua = 0;
+
+ return H_SUCCESS;
+}
+
+static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ enum dma_data_direction dir = DMA_NONE;
+ unsigned long hpa = 0;
+ long ret;
+
+ if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
+ return H_HARDWARE;
+
+ if (dir == DMA_NONE)
+ return H_SUCCESS;
+
+ ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+ if (ret != H_SUCCESS)
+ iommu_tce_xchg(tbl, entry, &hpa, &dir);
+
+ return ret;
+}
+
+long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+ unsigned long entry, unsigned long ua,
+ enum dma_data_direction dir)
+{
+ long ret;
+ unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+ struct mm_iommu_table_group_mem_t *mem;
+
+ if (!pua)
+ /* it_userspace allocation might be delayed */
+ return H_TOO_HARD;
+
+ mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+ if (!mem)
+ /* This only handles v2 IOMMU type, v1 is handled via ioctl() */
+ return H_TOO_HARD;
+
+ if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+ return H_HARDWARE;
+
+ if (mm_iommu_mapped_inc(mem))
+ return H_CLOSED;
+
+ ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
+ if (WARN_ON_ONCE(ret)) {
+ mm_iommu_mapped_dec(mem);
+ return H_HARDWARE;
+ }
+
+ if (dir != DMA_NONE)
+ kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+ *pua = ua;
+
+ return 0;
+}
+
long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce)
{
- struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
- long ret;
+ struct kvmppc_spapr_tce_table *stt;
+ long ret, idx;
+ struct kvmppc_spapr_tce_iommu_table *stit;
+ unsigned long entry, ua = 0;
+ enum dma_data_direction dir;
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */
+ stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -231,7 +466,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (ret != H_SUCCESS)
return ret;
- kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+ dir = iommu_tce_direction(tce);
+ if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+ tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+ return H_PARAMETER;
+
+ entry = ioba >> stt->page_shift;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ if (dir == DMA_NONE) {
+ ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+ stit->tbl, entry);
+ } else {
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
+ entry, ua, dir);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ }
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ return ret;
+
+ WARN_ON_ONCE(1);
+ kvmppc_clear_tce(stit->tbl, entry);
+ }
+
+ kvmppc_tce_put(stt, entry, tce);
return H_SUCCESS;
}
@@ -246,8 +509,9 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
unsigned long entry, ua = 0;
u64 __user *tces;
u64 tce;
+ struct kvmppc_spapr_tce_iommu_table *stit;
- stt = kvmppc_find_table(vcpu, liobn);
+ stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -284,6 +548,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
if (ret != H_SUCCESS)
goto unlock_exit;
+ if (kvmppc_gpa_to_ua(vcpu->kvm,
+ tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+ &ua, NULL))
+ return H_PARAMETER;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_tce_iommu_map(vcpu->kvm,
+ stit->tbl, entry + i, ua,
+ iommu_tce_direction(tce));
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ goto unlock_exit;
+
+ WARN_ON_ONCE(1);
+ kvmppc_clear_tce(stit->tbl, entry);
+ }
+
kvmppc_tce_put(stt, entry + i, tce);
}
@@ -300,8 +584,9 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
{
struct kvmppc_spapr_tce_table *stt;
long i, ret;
+ struct kvmppc_spapr_tce_iommu_table *stit;
- stt = kvmppc_find_table(vcpu, liobn);
+ stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -313,6 +598,24 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
return H_PARAMETER;
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+ for (i = 0; i < npages; ++i) {
+ ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+ stit->tbl, entry + i);
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ return ret;
+
+ WARN_ON_ONCE(1);
+ kvmppc_clear_tce(stit->tbl, entry);
+ }
+ }
+
for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index e4c4ea973e57..eda0a8f6fae8 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -40,6 +40,31 @@
#include <asm/iommu.h>
#include <asm/tce.h>
+#ifdef CONFIG_BUG
+
+#define WARN_ON_ONCE_RM(condition) ({ \
+ static bool __section(.data.unlikely) __warned; \
+ int __ret_warn_once = !!(condition); \
+ \
+ if (unlikely(__ret_warn_once && !__warned)) { \
+ __warned = true; \
+ pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n", \
+ __stringify(condition), \
+ __func__, __LINE__); \
+ dump_stack(); \
+ } \
+ unlikely(__ret_warn_once); \
+})
+
+#else
+
+#define WARN_ON_ONCE_RM(condition) ({ \
+ int __ret_warn_on = !!(condition); \
+ unlikely(__ret_warn_on); \
+})
+
+#endif
+
#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64))
/*
@@ -48,10 +73,9 @@
* WARNING: This will be called in real or virtual mode on HV KVM and virtual
* mode on PR KVM
*/
-struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu,
+struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
unsigned long liobn)
{
- struct kvm *kvm = vcpu->kvm;
struct kvmppc_spapr_tce_table *stt;
list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list)
@@ -63,27 +87,6 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu,
EXPORT_SYMBOL_GPL(kvmppc_find_table);
/*
- * Validates IO address.
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- * mode on PR KVM
- */
-long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
- unsigned long ioba, unsigned long npages)
-{
- unsigned long mask = (1ULL << stt->page_shift) - 1;
- unsigned long idx = ioba >> stt->page_shift;
-
- if ((ioba & mask) || (idx < stt->offset) ||
- (idx - stt->offset + npages > stt->size) ||
- (idx + npages < idx))
- return H_PARAMETER;
-
- return H_SUCCESS;
-}
-EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
-
-/*
* Validates TCE address.
* At the moment flags and page mask are validated.
* As the host kernel does not access those addresses (just puts them
@@ -96,10 +99,14 @@ EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
*/
long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce)
{
- unsigned long page_mask = ~((1ULL << stt->page_shift) - 1);
- unsigned long mask = ~(page_mask | TCE_PCI_WRITE | TCE_PCI_READ);
+ unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+ enum dma_data_direction dir = iommu_tce_direction(tce);
+
+ /* Allow userspace to poison TCE table */
+ if (dir == DMA_NONE)
+ return H_SUCCESS;
- if (tce & mask)
+ if (iommu_tce_check_gpa(stt->page_shift, gpa))
return H_PARAMETER;
return H_SUCCESS;
@@ -179,15 +186,122 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+ unsigned long hpa = 0;
+ enum dma_data_direction dir = DMA_NONE;
+
+ iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ struct mm_iommu_table_group_mem_t *mem = NULL;
+ const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+ unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+ if (!pua)
+ /* it_userspace allocation might be delayed */
+ return H_TOO_HARD;
+
+ pua = (void *) vmalloc_to_phys(pua);
+ if (WARN_ON_ONCE_RM(!pua))
+ return H_HARDWARE;
+
+ mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
+ if (!mem)
+ return H_TOO_HARD;
+
+ mm_iommu_mapped_dec(mem);
+
+ *pua = 0;
+
+ return H_SUCCESS;
+}
+
+static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ enum dma_data_direction dir = DMA_NONE;
+ unsigned long hpa = 0;
+ long ret;
+
+ if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
+ /*
+ * real mode xchg can fail if struct page crosses
+ * a page boundary
+ */
+ return H_TOO_HARD;
+
+ if (dir == DMA_NONE)
+ return H_SUCCESS;
+
+ ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+ if (ret)
+ iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+
+ return ret;
+}
+
+static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+ unsigned long entry, unsigned long ua,
+ enum dma_data_direction dir)
+{
+ long ret;
+ unsigned long hpa = 0;
+ unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+ struct mm_iommu_table_group_mem_t *mem;
+
+ if (!pua)
+ /* it_userspace allocation might be delayed */
+ return H_TOO_HARD;
+
+ mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+ if (!mem)
+ return H_TOO_HARD;
+
+ if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+ return H_HARDWARE;
+
+ pua = (void *) vmalloc_to_phys(pua);
+ if (WARN_ON_ONCE_RM(!pua))
+ return H_HARDWARE;
+
+ if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
+ return H_CLOSED;
+
+ ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+ if (ret) {
+ mm_iommu_mapped_dec(mem);
+ /*
+ * real mode xchg can fail if struct page crosses
+ * a page boundary
+ */
+ return H_TOO_HARD;
+ }
+
+ if (dir != DMA_NONE)
+ kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+ *pua = ua;
+
+ return 0;
+}
+
long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce)
{
- struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+ struct kvmppc_spapr_tce_table *stt;
long ret;
+ struct kvmppc_spapr_tce_iommu_table *stit;
+ unsigned long entry, ua = 0;
+ enum dma_data_direction dir;
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */
+ stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -199,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (ret != H_SUCCESS)
return ret;
- kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+ dir = iommu_tce_direction(tce);
+ if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+ tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+ return H_PARAMETER;
+
+ entry = ioba >> stt->page_shift;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ if (dir == DMA_NONE)
+ ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+ stit->tbl, entry);
+ else
+ ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+ stit->tbl, entry, ua, dir);
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ return ret;
+
+ WARN_ON_ONCE_RM(1);
+ kvmppc_rm_clear_tce(stit->tbl, entry);
+ }
+
+ kvmppc_tce_put(stt, entry, tce);
return H_SUCCESS;
}
@@ -239,8 +378,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
long i, ret = H_SUCCESS;
unsigned long tces, entry, ua = 0;
unsigned long *rmap = NULL;
+ bool prereg = false;
+ struct kvmppc_spapr_tce_iommu_table *stit;
- stt = kvmppc_find_table(vcpu, liobn);
+ stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -259,23 +400,49 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
if (ret != H_SUCCESS)
return ret;
- if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
- return H_TOO_HARD;
+ if (mm_iommu_preregistered(vcpu->kvm->mm)) {
+ /*
+ * We get here if guest memory was pre-registered which
+ * is normally VFIO case and gpa->hpa translation does not
+ * depend on hpt.
+ */
+ struct mm_iommu_table_group_mem_t *mem;
- rmap = (void *) vmalloc_to_phys(rmap);
+ if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+ return H_TOO_HARD;
- /*
- * Synchronize with the MMU notifier callbacks in
- * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
- * While we have the rmap lock, code running on other CPUs
- * cannot finish unmapping the host real page that backs
- * this guest real page, so we are OK to access the host
- * real page.
- */
- lock_rmap(rmap);
- if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
- ret = H_TOO_HARD;
- goto unlock_exit;
+ mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
+ if (mem)
+ prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+ }
+
+ if (!prereg) {
+ /*
+ * This is usually a case of a guest with emulated devices only
+ * when TCE list is not in preregistered memory.
+ * We do not require memory to be preregistered in this case
+ * so lock rmap and do __find_linux_pte_or_hugepte().
+ */
+ if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+ return H_TOO_HARD;
+
+ rmap = (void *) vmalloc_to_phys(rmap);
+ if (WARN_ON_ONCE_RM(!rmap))
+ return H_HARDWARE;
+
+ /*
+ * Synchronize with the MMU notifier callbacks in
+ * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
+ * While we have the rmap lock, code running on other CPUs
+ * cannot finish unmapping the host real page that backs
+ * this guest real page, so we are OK to access the host
+ * real page.
+ */
+ lock_rmap(rmap);
+ if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
+ ret = H_TOO_HARD;
+ goto unlock_exit;
+ }
}
for (i = 0; i < npages; ++i) {
@@ -285,11 +452,33 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
if (ret != H_SUCCESS)
goto unlock_exit;
+ ua = 0;
+ if (kvmppc_gpa_to_ua(vcpu->kvm,
+ tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+ &ua, NULL))
+ return H_PARAMETER;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+ stit->tbl, entry + i, ua,
+ iommu_tce_direction(tce));
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ goto unlock_exit;
+
+ WARN_ON_ONCE_RM(1);
+ kvmppc_rm_clear_tce(stit->tbl, entry);
+ }
+
kvmppc_tce_put(stt, entry + i, tce);
}
unlock_exit:
- unlock_rmap(rmap);
+ if (rmap)
+ unlock_rmap(rmap);
return ret;
}
@@ -300,8 +489,9 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
{
struct kvmppc_spapr_tce_table *stt;
long i, ret;
+ struct kvmppc_spapr_tce_iommu_table *stit;
- stt = kvmppc_find_table(vcpu, liobn);
+ stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -313,6 +503,24 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
return H_PARAMETER;
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+ for (i = 0; i < npages; ++i) {
+ ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+ stit->tbl, entry + i);
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ return ret;
+
+ WARN_ON_ONCE_RM(1);
+ kvmppc_rm_clear_tce(stit->tbl, entry);
+ }
+ }
+
for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
@@ -322,12 +530,13 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba)
{
- struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+ struct kvmppc_spapr_tce_table *stt;
long ret;
unsigned long idx;
struct page *page;
u64 *tbl;
+ stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 8359752b3efc..68d68983948e 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -503,10 +503,18 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
break;
unprivileged:
default:
- printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn);
-#ifndef DEBUG_SPR
- emulated = EMULATE_FAIL;
-#endif
+ pr_info_ratelimited("KVM: invalid SPR write: %d\n", sprn);
+ if (sprn & 0x10) {
+ if (kvmppc_get_msr(vcpu) & MSR_PR) {
+ kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+ emulated = EMULATE_AGAIN;
+ }
+ } else {
+ if ((kvmppc_get_msr(vcpu) & MSR_PR) || sprn == 0) {
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ emulated = EMULATE_AGAIN;
+ }
+ }
break;
}
@@ -648,10 +656,20 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
break;
default:
unprivileged:
- printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn);
-#ifndef DEBUG_SPR
- emulated = EMULATE_FAIL;
-#endif
+ pr_info_ratelimited("KVM: invalid SPR read: %d\n", sprn);
+ if (sprn & 0x10) {
+ if (kvmppc_get_msr(vcpu) & MSR_PR) {
+ kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+ emulated = EMULATE_AGAIN;
+ }
+ } else {
+ if ((kvmppc_get_msr(vcpu) & MSR_PR) || sprn == 0 ||
+ sprn == 4 || sprn == 5 || sprn == 6) {
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ emulated = EMULATE_AGAIN;
+ }
+ }
+
break;
}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1ec86d9e2a82..42b7a4fd57d9 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -35,6 +35,15 @@
#include <linux/srcu.h>
#include <linux/miscdevice.h>
#include <linux/debugfs.h>
+#include <linux/gfp.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
+#include <linux/hugetlb.h>
+#include <linux/kvm_irqfd.h>
+#include <linux/irqbypass.h>
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/of.h>
#include <asm/reg.h>
#include <asm/cputable.h>
@@ -58,15 +67,7 @@
#include <asm/mmu.h>
#include <asm/opal.h>
#include <asm/xics.h>
-#include <linux/gfp.h>
-#include <linux/vmalloc.h>
-#include <linux/highmem.h>
-#include <linux/hugetlb.h>
-#include <linux/kvm_irqfd.h>
-#include <linux/irqbypass.h>
-#include <linux/module.h>
-#include <linux/compiler.h>
-#include <linux/of.h>
+#include <asm/xive.h>
#include "book3s.h"
@@ -837,6 +838,10 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_IPOLL:
case H_XIRR_X:
if (kvmppc_xics_enabled(vcpu)) {
+ if (xive_enabled()) {
+ ret = H_NOT_AVAILABLE;
+ return RESUME_GUEST;
+ }
ret = kvmppc_xics_hcall(vcpu, req);
break;
}
@@ -2947,8 +2952,12 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
r = kvmppc_book3s_hv_page_fault(run, vcpu,
vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
- } else if (r == RESUME_PASSTHROUGH)
- r = kvmppc_xics_rm_complete(vcpu, 0);
+ } else if (r == RESUME_PASSTHROUGH) {
+ if (WARN_ON(xive_enabled()))
+ r = H_SUCCESS;
+ else
+ r = kvmppc_xics_rm_complete(vcpu, 0);
+ }
} while (is_kvmppc_resume_guest(r));
out:
@@ -3400,10 +3409,20 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
/*
* On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed)
* Set HVICE bit to enable hypervisor virtualization interrupts.
+ * Set HEIC to prevent OS interrupts to go to hypervisor (should
+ * be unnecessary but better safe than sorry in case we re-enable
+ * EE in HV mode with this LPCR still set)
*/
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
lpcr &= ~LPCR_VPM0;
- lpcr |= LPCR_HVICE;
+ lpcr |= LPCR_HVICE | LPCR_HEIC;
+
+ /*
+ * If xive is enabled, we route 0x500 interrupts directly
+ * to the guest.
+ */
+ if (xive_enabled())
+ lpcr |= LPCR_LPES;
}
/*
@@ -3533,7 +3552,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
struct kvmppc_irq_map *irq_map;
struct kvmppc_passthru_irqmap *pimap;
struct irq_chip *chip;
- int i;
+ int i, rc = 0;
if (!kvm_irq_bypass)
return 1;
@@ -3558,10 +3577,10 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
/*
* For now, we only support interrupts for which the EOI operation
* is an OPAL call followed by a write to XIRR, since that's
- * what our real-mode EOI code does.
+ * what our real-mode EOI code does, or a XIVE interrupt
*/
chip = irq_data_get_irq_chip(&desc->irq_data);
- if (!chip || !is_pnv_opal_msi(chip)) {
+ if (!chip || !(is_pnv_opal_msi(chip) || is_xive_irq(chip))) {
pr_warn("kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (%d,%d)\n",
host_irq, guest_gsi);
mutex_unlock(&kvm->lock);
@@ -3603,7 +3622,12 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
if (i == pimap->n_mapped)
pimap->n_mapped++;
- kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
+ if (xive_enabled())
+ rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc);
+ else
+ kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
+ if (rc)
+ irq_map->r_hwirq = 0;
mutex_unlock(&kvm->lock);
@@ -3614,7 +3638,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
{
struct irq_desc *desc;
struct kvmppc_passthru_irqmap *pimap;
- int i;
+ int i, rc = 0;
if (!kvm_irq_bypass)
return 0;
@@ -3624,11 +3648,9 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
return -EIO;
mutex_lock(&kvm->lock);
+ if (!kvm->arch.pimap)
+ goto unlock;
- if (kvm->arch.pimap == NULL) {
- mutex_unlock(&kvm->lock);
- return 0;
- }
pimap = kvm->arch.pimap;
for (i = 0; i < pimap->n_mapped; i++) {
@@ -3641,18 +3663,21 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
return -ENODEV;
}
- kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
+ if (xive_enabled())
+ rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc);
+ else
+ kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
- /* invalidate the entry */
+ /* invalidate the entry (what do do on error from the above ?) */
pimap->mapped[i].r_hwirq = 0;
/*
* We don't free this structure even when the count goes to
* zero. The structure is freed when we destroy the VM.
*/
-
+ unlock:
mutex_unlock(&kvm->lock);
- return 0;
+ return rc;
}
static int kvmppc_irq_bypass_add_producer_hv(struct irq_bypass_consumer *cons,
@@ -3930,7 +3955,7 @@ static int kvmppc_book3s_init_hv(void)
* indirectly, via OPAL.
*/
#ifdef CONFIG_SMP
- if (!get_paca()->kvm_hstate.xics_phys) {
+ if (!xive_enabled() && !local_paca->kvm_hstate.xics_phys) {
struct device_node *np;
np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 4d6c64b3041c..88a65923c649 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -23,6 +23,7 @@
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
#include <asm/xics.h>
+#include <asm/xive.h>
#include <asm/dbell.h>
#include <asm/cputhreads.h>
#include <asm/io.h>
@@ -31,6 +32,24 @@
#define KVM_CMA_CHUNK_ORDER 18
+#include "book3s_xics.h"
+#include "book3s_xive.h"
+
+/*
+ * The XIVE module will populate these when it loads
+ */
+unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
+unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
+int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
+int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_xirr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_ipoll);
+EXPORT_SYMBOL_GPL(__xive_vm_h_ipi);
+EXPORT_SYMBOL_GPL(__xive_vm_h_cppr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_eoi);
+
/*
* Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
* should be power of 2.
@@ -100,7 +119,8 @@ void __init kvm_cma_reserve(void)
(unsigned long)selected_size / SZ_1M);
align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
cma_declare_contiguous(0, selected_size, 0, align_size,
- KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma);
+ KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, "kvm_cma",
+ &kvm_cma);
}
}
@@ -193,12 +213,6 @@ long kvmppc_h_random(struct kvm_vcpu *vcpu)
return H_HARDWARE;
}
-static inline void rm_writeb(unsigned long paddr, u8 val)
-{
- __asm__ __volatile__("stbcix %0,0,%1"
- : : "r" (val), "r" (paddr) : "memory");
-}
-
/*
* Send an interrupt or message to another CPU.
* The caller needs to include any barrier needed to order writes
@@ -206,7 +220,7 @@ static inline void rm_writeb(unsigned long paddr, u8 val)
*/
void kvmhv_rm_send_ipi(int cpu)
{
- unsigned long xics_phys;
+ void __iomem *xics_phys;
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
/* On POWER9 we can use msgsnd for any destination cpu. */
@@ -215,6 +229,7 @@ void kvmhv_rm_send_ipi(int cpu)
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
return;
}
+
/* On POWER8 for IPIs to threads in the same core, use msgsnd. */
if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
cpu_first_thread_sibling(cpu) ==
@@ -224,10 +239,14 @@ void kvmhv_rm_send_ipi(int cpu)
return;
}
+ /* We should never reach this */
+ if (WARN_ON_ONCE(xive_enabled()))
+ return;
+
/* Else poke the target with an IPI */
xics_phys = paca[cpu].kvm_hstate.xics_phys;
if (xics_phys)
- rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ __raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
else
opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY);
}
@@ -386,6 +405,9 @@ long kvmppc_read_intr(void)
long rc;
bool again;
+ if (xive_enabled())
+ return 1;
+
do {
again = false;
rc = kvmppc_read_one_intr(&again);
@@ -397,13 +419,16 @@ long kvmppc_read_intr(void)
static long kvmppc_read_one_intr(bool *again)
{
- unsigned long xics_phys;
+ void __iomem *xics_phys;
u32 h_xirr;
__be32 xirr;
u32 xisr;
u8 host_ipi;
int64_t rc;
+ if (xive_enabled())
+ return 1;
+
/* see if a host IPI is pending */
host_ipi = local_paca->kvm_hstate.host_ipi;
if (host_ipi)
@@ -415,7 +440,7 @@ static long kvmppc_read_one_intr(bool *again)
if (!xics_phys)
rc = opal_int_get_xirr(&xirr, false);
else
- xirr = _lwzcix(xics_phys + XICS_XIRR);
+ xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
if (rc < 0)
return 1;
@@ -445,8 +470,8 @@ static long kvmppc_read_one_intr(bool *again)
if (xisr == XICS_IPI) {
rc = 0;
if (xics_phys) {
- _stbcix(xics_phys + XICS_MFRR, 0xff);
- _stwcix(xics_phys + XICS_XIRR, xirr);
+ __raw_rm_writeb(0xff, xics_phys + XICS_MFRR);
+ __raw_rm_writel(xirr, xics_phys + XICS_XIRR);
} else {
opal_int_set_mfrr(hard_smp_processor_id(), 0xff);
rc = opal_int_eoi(h_xirr);
@@ -471,7 +496,8 @@ static long kvmppc_read_one_intr(bool *again)
* we need to resend that IPI, bummer
*/
if (xics_phys)
- _stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ __raw_rm_writeb(IPI_PRIORITY,
+ xics_phys + XICS_MFRR);
else
opal_int_set_mfrr(hard_smp_processor_id(),
IPI_PRIORITY);
@@ -487,3 +513,84 @@ static long kvmppc_read_one_intr(bool *again)
return kvmppc_check_passthru(xisr, xirr, again);
}
+
+#ifdef CONFIG_KVM_XICS
+static inline bool is_rm(void)
+{
+ return !(mfmsr() & MSR_DR);
+}
+
+unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_xirr(vcpu);
+ if (unlikely(!__xive_vm_h_xirr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_xirr(vcpu);
+ } else
+ return xics_rm_h_xirr(vcpu);
+}
+
+unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.gpr[5] = get_tb();
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_xirr(vcpu);
+ if (unlikely(!__xive_vm_h_xirr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_xirr(vcpu);
+ } else
+ return xics_rm_h_xirr(vcpu);
+}
+
+unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_ipoll(vcpu, server);
+ if (unlikely(!__xive_vm_h_ipoll))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_ipoll(vcpu, server);
+ } else
+ return H_TOO_HARD;
+}
+
+int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_ipi(vcpu, server, mfrr);
+ if (unlikely(!__xive_vm_h_ipi))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_ipi(vcpu, server, mfrr);
+ } else
+ return xics_rm_h_ipi(vcpu, server, mfrr);
+}
+
+int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_cppr(vcpu, cppr);
+ if (unlikely(!__xive_vm_h_cppr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_cppr(vcpu, cppr);
+ } else
+ return xics_rm_h_cppr(vcpu, cppr);
+}
+
+int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_eoi(vcpu, xirr);
+ if (unlikely(!__xive_vm_h_eoi))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_eoi(vcpu, xirr);
+ } else
+ return xics_rm_h_eoi(vcpu, xirr);
+}
+#endif /* CONFIG_KVM_XICS */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6fca970373ee..ce6f2121fffe 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -256,7 +256,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
}
pte = kvmppc_read_update_linux_pte(ptep, writing);
if (pte_present(pte) && !pte_protnone(pte)) {
- if (writing && !pte_write(pte))
+ if (writing && !__pte_write(pte))
/* make the actual HPTE be read-only */
ptel = hpte_make_readonly(ptel);
is_ci = pte_ci(pte);
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index e78542d99cd6..2a862618f072 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -16,7 +16,6 @@
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/xics.h>
-#include <asm/debug.h>
#include <asm/synch.h>
#include <asm/cputhreads.h>
#include <asm/pgtable.h>
@@ -485,7 +484,7 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
}
-unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
+unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
@@ -523,8 +522,8 @@ unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
return check_too_hard(xics, icp);
}
-int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
- unsigned long mfrr)
+int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
@@ -610,7 +609,7 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
return check_too_hard(xics, this_icp);
}
-int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
+int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
@@ -730,7 +729,7 @@ static int ics_rm_eoi(struct kvm_vcpu *vcpu, u32 irq)
return check_too_hard(xics, icp);
}
-int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
+int xics_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
{
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
struct kvmppc_icp *icp = vcpu->arch.icp;
@@ -766,7 +765,7 @@ unsigned long eoi_rc;
static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
{
- unsigned long xics_phys;
+ void __iomem *xics_phys;
int64_t rc;
rc = pnv_opal_pci_msi_eoi(c, hwirq);
@@ -779,7 +778,7 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
/* EOI it */
xics_phys = local_paca->kvm_hstate.xics_phys;
if (xics_phys) {
- _stwcix(xics_phys + XICS_XIRR, xirr);
+ __raw_rm_writel(xirr, xics_phys + XICS_XIRR);
} else {
rc = opal_int_eoi(be32_to_cpu(xirr));
*again = rc > 0;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xive.c b/arch/powerpc/kvm/book3s_hv_rm_xive.c
new file mode 100644
index 000000000000..abf5f01b6eb1
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_rm_xive.c
@@ -0,0 +1,47 @@
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/kernel_stat.h>
+
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xics.h>
+#include <asm/debug.h>
+#include <asm/synch.h>
+#include <asm/cputhreads.h>
+#include <asm/pgtable.h>
+#include <asm/ppc-opcode.h>
+#include <asm/pnv-pci.h>
+#include <asm/opal.h>
+#include <asm/smp.h>
+#include <asm/asm-prototypes.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+
+#include "book3s_xive.h"
+
+/* XXX */
+#include <asm/udbg.h>
+//#define DBG(fmt...) udbg_printf(fmt)
+#define DBG(fmt...) do { } while(0)
+
+static inline void __iomem *get_tima_phys(void)
+{
+ return local_paca->kvm_hstate.xive_tima_phys;
+}
+
+#undef XIVE_RUNTIME_CHECKS
+#define X_PFX xive_rm_
+#define X_STATIC
+#define X_STAT_PFX stat_rm_
+#define __x_tima get_tima_phys()
+#define __x_eoi_page(xd) ((void __iomem *)((xd)->eoi_page))
+#define __x_trig_page(xd) ((void __iomem *)((xd)->trig_page))
+#define __x_readb __raw_rm_readb
+#define __x_writeb __raw_rm_writeb
+#define __x_readw __raw_rm_readw
+#define __x_readq __raw_rm_readq
+#define __x_writeq __raw_rm_writeq
+
+#include "book3s_xive_template.c"
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 7c6477d1840a..bdb3f76ceb6b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -30,6 +30,7 @@
#include <asm/book3s/64/mmu-hash.h>
#include <asm/tm.h>
#include <asm/opal.h>
+#include <asm/xive-regs.h>
#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
@@ -970,6 +971,23 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
cmpwi r3, 512 /* 1 microsecond */
blt hdec_soon
+#ifdef CONFIG_KVM_XICS
+ /* We are entering the guest on that thread, push VCPU to XIVE */
+ ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
+ cmpldi cr0, r10, r0
+ beq no_xive
+ ld r11, VCPU_XIVE_SAVED_STATE(r4)
+ li r9, TM_QW1_OS
+ stdcix r11,r9,r10
+ eieio
+ lwz r11, VCPU_XIVE_CAM_WORD(r4)
+ li r9, TM_QW1_OS + TM_WORD2
+ stwcix r11,r9,r10
+ li r9, 1
+ stw r9, VCPU_XIVE_PUSHED(r4)
+no_xive:
+#endif /* CONFIG_KVM_XICS */
+
deliver_guest_interrupt:
ld r6, VCPU_CTR(r4)
ld r7, VCPU_XER(r4)
@@ -1307,6 +1325,42 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
blt deliver_guest_interrupt
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
+#ifdef CONFIG_KVM_XICS
+ /* We are exiting, pull the VP from the XIVE */
+ lwz r0, VCPU_XIVE_PUSHED(r9)
+ cmpwi cr0, r0, 0
+ beq 1f
+ li r7, TM_SPC_PULL_OS_CTX
+ li r6, TM_QW1_OS
+ mfmsr r0
+ andi. r0, r0, MSR_IR /* in real mode? */
+ beq 2f
+ ld r10, HSTATE_XIVE_TIMA_VIRT(r13)
+ cmpldi cr0, r10, 0
+ beq 1f
+ /* First load to pull the context, we ignore the value */
+ lwzx r11, r7, r10
+ eieio
+ /* Second load to recover the context state (Words 0 and 1) */
+ ldx r11, r6, r10
+ b 3f
+2: ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
+ cmpldi cr0, r10, 0
+ beq 1f
+ /* First load to pull the context, we ignore the value */
+ lwzcix r11, r7, r10
+ eieio
+ /* Second load to recover the context state (Words 0 and 1) */
+ ldcix r11, r6, r10
+3: std r11, VCPU_XIVE_SAVED_STATE(r9)
+ /* Fixup some of the state for the next load */
+ li r10, 0
+ li r0, 0xff
+ stw r10, VCPU_XIVE_PUSHED(r9)
+ stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
+ stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
+1:
+#endif /* CONFIG_KVM_XICS */
/* Save more register state */
mfdar r6
mfdsisr r7
@@ -2011,7 +2065,7 @@ hcall_real_table:
.long DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table
- .long 0 /* 0x70 - H_IPOLL */
+ .long DOTSYM(kvmppc_rm_h_ipoll) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table
#else
.long 0 /* 0x64 - H_EOI */
@@ -2181,7 +2235,11 @@ hcall_real_table:
.long 0 /* 0x2f0 */
.long 0 /* 0x2f4 */
.long 0 /* 0x2f8 */
- .long 0 /* 0x2fc */
+#ifdef CONFIG_KVM_XICS
+ .long DOTSYM(kvmppc_rm_h_xirr_x) - hcall_real_table
+#else
+ .long 0 /* 0x2fc - H_XIRR_X*/
+#endif
.long DOTSYM(kvmppc_h_random) - hcall_real_table
.globl hcall_real_table_end
hcall_real_table_end:
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index d4dfc0ca2a44..69a09444d46e 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -349,7 +349,7 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
if (msr & MSR_POW) {
if (!vcpu->arch.pending_exceptions) {
kvm_vcpu_block(vcpu);
- clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+ kvm_clear_request(KVM_REQ_UNHALT, vcpu);
vcpu->stat.halt_wakeup++;
/* Unset POW bit after we woke up */
@@ -537,8 +537,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
int r = RESUME_GUEST;
int relocated;
int page_found = 0;
- struct kvmppc_pte pte;
- bool is_mmio = false;
+ struct kvmppc_pte pte = { 0 };
bool dr = (kvmppc_get_msr(vcpu) & MSR_DR) ? true : false;
bool ir = (kvmppc_get_msr(vcpu) & MSR_IR) ? true : false;
u64 vsid;
@@ -616,8 +615,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
/* Page not found in guest SLB */
kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
- } else if (!is_mmio &&
- kvmppc_visible_gpa(vcpu, pte.raddr)) {
+ } else if (kvmppc_visible_gpa(vcpu, pte.raddr)) {
if (data && !(vcpu->arch.fault_dsisr & DSISR_NOHPTE)) {
/*
* There is already a host HPTE there, presumably
@@ -627,7 +625,11 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
kvmppc_mmu_unmap_page(vcpu, &pte);
}
/* The guest's PTE is not mapped yet. Map on the host */
- kvmppc_mmu_map_page(vcpu, &pte, iswrite);
+ if (kvmppc_mmu_map_page(vcpu, &pte, iswrite) == -EIO) {
+ /* Exit KVM if mapping failed */
+ run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ return RESUME_HOST;
+ }
if (data)
vcpu->stat.sp_storage++;
else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index f102616febc7..bcbeeb62dd13 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -344,7 +344,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
case H_CEDE:
kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE);
kvm_vcpu_block(vcpu);
- clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+ kvm_clear_request(KVM_REQ_UNHALT, vcpu);
vcpu->stat.halt_wakeup++;
return EMULATE_DONE;
case H_LOGICAL_CI_LOAD:
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index 20528701835b..2d3b2b1cc272 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -16,6 +16,7 @@
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/rtas.h>
+#include <asm/xive.h>
#ifdef CONFIG_KVM_XICS
static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -32,7 +33,10 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
server = be32_to_cpu(args->args[1]);
priority = be32_to_cpu(args->args[2]);
- rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
+ if (xive_enabled())
+ rc = kvmppc_xive_set_xive(vcpu->kvm, irq, server, priority);
+ else
+ rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
if (rc)
rc = -3;
out:
@@ -52,7 +56,10 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
irq = be32_to_cpu(args->args[0]);
server = priority = 0;
- rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
+ if (xive_enabled())
+ rc = kvmppc_xive_get_xive(vcpu->kvm, irq, &server, &priority);
+ else
+ rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
if (rc) {
rc = -3;
goto out;
@@ -76,7 +83,10 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
irq = be32_to_cpu(args->args[0]);
- rc = kvmppc_xics_int_off(vcpu->kvm, irq);
+ if (xive_enabled())
+ rc = kvmppc_xive_int_off(vcpu->kvm, irq);
+ else
+ rc = kvmppc_xics_int_off(vcpu->kvm, irq);
if (rc)
rc = -3;
out:
@@ -95,7 +105,10 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
irq = be32_to_cpu(args->args[0]);
- rc = kvmppc_xics_int_on(vcpu->kvm, irq);
+ if (xive_enabled())
+ rc = kvmppc_xive_int_on(vcpu->kvm, irq);
+ else
+ rc = kvmppc_xics_int_on(vcpu->kvm, irq);
if (rc)
rc = -3;
out:
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index e48803e2918d..d329b2add7e2 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -19,10 +19,9 @@
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/xics.h>
-#include <asm/debug.h>
+#include <asm/debugfs.h>
#include <asm/time.h>
-#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include "book3s_xics.h"
@@ -1084,7 +1083,7 @@ static struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm,
return xics->ics[icsid];
}
-int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server_num)
+static int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server_num)
{
struct kvmppc_icp *icp;
@@ -1307,8 +1306,8 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr)
return 0;
}
-int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
- bool line_status)
+int kvmppc_xics_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
{
struct kvmppc_xics *xics = kvm->arch.xics;
@@ -1317,14 +1316,6 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
return ics_deliver_irq(xics, irq, level);
}
-int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *irq_entry,
- struct kvm *kvm, int irq_source_id,
- int level, bool line_status)
-{
- return kvm_set_irq(kvm, irq_source_id, irq_entry->gsi,
- level, line_status);
-}
-
static int xics_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
struct kvmppc_xics *xics = dev->private;
@@ -1458,29 +1449,6 @@ void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu)
vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
}
-static int xics_set_irq(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level,
- bool line_status)
-{
- return kvm_set_irq(kvm, irq_source_id, e->gsi, level, line_status);
-}
-
-int kvm_irq_map_gsi(struct kvm *kvm,
- struct kvm_kernel_irq_routing_entry *entries, int gsi)
-{
- entries->gsi = gsi;
- entries->type = KVM_IRQ_ROUTING_IRQCHIP;
- entries->set = xics_set_irq;
- entries->irqchip.irqchip = 0;
- entries->irqchip.pin = gsi;
- return 1;
-}
-
-int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
- return pin;
-}
-
void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long irq,
unsigned long host_irq)
{
diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h
index ec5474cf70c6..453c9e518c19 100644
--- a/arch/powerpc/kvm/book3s_xics.h
+++ b/arch/powerpc/kvm/book3s_xics.h
@@ -10,6 +10,7 @@
#ifndef _KVM_PPC_BOOK3S_XICS_H
#define _KVM_PPC_BOOK3S_XICS_H
+#ifdef CONFIG_KVM_XICS
/*
* We use a two-level tree to store interrupt source information.
* There are up to 1024 ICS nodes, each of which can represent
@@ -144,5 +145,11 @@ static inline struct kvmppc_ics *kvmppc_xics_find_ics(struct kvmppc_xics *xics,
return ics;
}
+extern unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu);
+extern int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int xics_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
+#endif /* CONFIG_KVM_XICS */
#endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
new file mode 100644
index 000000000000..ffe1da95033a
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -0,0 +1,1894 @@
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "xive-kvm: " fmt
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xics.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/time.h>
+#include <asm/opal.h>
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "book3s_xive.h"
+
+
+/*
+ * Virtual mode variants of the hcalls for use on radix/radix
+ * with AIL. They require the VCPU's VP to be "pushed"
+ *
+ * We still instanciate them here because we use some of the
+ * generated utility functions as well in this file.
+ */
+#define XIVE_RUNTIME_CHECKS
+#define X_PFX xive_vm_
+#define X_STATIC static
+#define X_STAT_PFX stat_vm_
+#define __x_tima xive_tima
+#define __x_eoi_page(xd) ((void __iomem *)((xd)->eoi_mmio))
+#define __x_trig_page(xd) ((void __iomem *)((xd)->trig_mmio))
+#define __x_readb __raw_readb
+#define __x_writeb __raw_writeb
+#define __x_readw __raw_readw
+#define __x_readq __raw_readq
+#define __x_writeq __raw_writeq
+
+#include "book3s_xive_template.c"
+
+/*
+ * We leave a gap of a couple of interrupts in the queue to
+ * account for the IPI and additional safety guard.
+ */
+#define XIVE_Q_GAP 2
+
+/*
+ * This is a simple trigger for a generic XIVE IRQ. This must
+ * only be called for interrupts that support a trigger page
+ */
+static bool xive_irq_trigger(struct xive_irq_data *xd)
+{
+ /* This should be only for MSIs */
+ if (WARN_ON(xd->flags & XIVE_IRQ_FLAG_LSI))
+ return false;
+
+ /* Those interrupts should always have a trigger page */
+ if (WARN_ON(!xd->trig_mmio))
+ return false;
+
+ out_be64(xd->trig_mmio, 0);
+
+ return true;
+}
+
+static irqreturn_t xive_esc_irq(int irq, void *data)
+{
+ struct kvm_vcpu *vcpu = data;
+
+ /* We use the existing H_PROD mechanism to wake up the target */
+ vcpu->arch.prodded = 1;
+ smp_mb();
+ if (vcpu->arch.ceded)
+ kvmppc_fast_vcpu_kick(vcpu);
+
+ return IRQ_HANDLED;
+}
+
+static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_q *q = &xc->queues[prio];
+ char *name = NULL;
+ int rc;
+
+ /* Already there ? */
+ if (xc->esc_virq[prio])
+ return 0;
+
+ /* Hook up the escalation interrupt */
+ xc->esc_virq[prio] = irq_create_mapping(NULL, q->esc_irq);
+ if (!xc->esc_virq[prio]) {
+ pr_err("Failed to map escalation interrupt for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ return -EIO;
+ }
+
+ /*
+ * Future improvement: start with them disabled
+ * and handle DD2 and later scheme of merged escalation
+ * interrupts
+ */
+ name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d",
+ vcpu->kvm->arch.lpid, xc->server_num, prio);
+ if (!name) {
+ pr_err("Failed to allocate escalation irq name for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ rc = -ENOMEM;
+ goto error;
+ }
+ rc = request_irq(xc->esc_virq[prio], xive_esc_irq,
+ IRQF_NO_THREAD, name, vcpu);
+ if (rc) {
+ pr_err("Failed to request escalation interrupt for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ goto error;
+ }
+ xc->esc_virq_names[prio] = name;
+ return 0;
+error:
+ irq_dispose_mapping(xc->esc_virq[prio]);
+ xc->esc_virq[prio] = 0;
+ kfree(name);
+ return rc;
+}
+
+static int xive_provision_queue(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = xc->xive;
+ struct xive_q *q = &xc->queues[prio];
+ void *qpage;
+ int rc;
+
+ if (WARN_ON(q->qpage))
+ return 0;
+
+ /* Allocate the queue and retrieve infos on current node for now */
+ qpage = (__be32 *)__get_free_pages(GFP_KERNEL, xive->q_page_order);
+ if (!qpage) {
+ pr_err("Failed to allocate queue %d for VCPU %d\n",
+ prio, xc->server_num);
+ return -ENOMEM;;
+ }
+ memset(qpage, 0, 1 << xive->q_order);
+
+ /*
+ * Reconfigure the queue. This will set q->qpage only once the
+ * queue is fully configured. This is a requirement for prio 0
+ * as we will stop doing EOIs for every IPI as soon as we observe
+ * qpage being non-NULL, and instead will only EOI when we receive
+ * corresponding queue 0 entries
+ */
+ rc = xive_native_configure_queue(xc->vp_id, q, prio, qpage,
+ xive->q_order, true);
+ if (rc)
+ pr_err("Failed to configure queue %d for VCPU %d\n",
+ prio, xc->server_num);
+ return rc;
+}
+
+/* Called with kvm_lock held */
+static int xive_check_provisioning(struct kvm *kvm, u8 prio)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvm_vcpu *vcpu;
+ int i, rc;
+
+ lockdep_assert_held(&kvm->lock);
+
+ /* Already provisioned ? */
+ if (xive->qmap & (1 << prio))
+ return 0;
+
+ pr_devel("Provisioning prio... %d\n", prio);
+
+ /* Provision each VCPU and enable escalations */
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!vcpu->arch.xive_vcpu)
+ continue;
+ rc = xive_provision_queue(vcpu, prio);
+ if (rc == 0)
+ xive_attach_escalation(vcpu, prio);
+ if (rc)
+ return rc;
+ }
+
+ /* Order previous stores and mark it as provisioned */
+ mb();
+ xive->qmap |= (1 << prio);
+ return 0;
+}
+
+static void xive_inc_q_pending(struct kvm *kvm, u32 server, u8 prio)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvmppc_xive_vcpu *xc;
+ struct xive_q *q;
+
+ /* Locate target server */
+ vcpu = kvmppc_xive_find_server(kvm, server);
+ if (!vcpu) {
+ pr_warn("%s: Can't find server %d\n", __func__, server);
+ return;
+ }
+ xc = vcpu->arch.xive_vcpu;
+ if (WARN_ON(!xc))
+ return;
+
+ q = &xc->queues[prio];
+ atomic_inc(&q->pending_count);
+}
+
+static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_q *q;
+ u32 max;
+
+ if (WARN_ON(!xc))
+ return -ENXIO;
+ if (!xc->valid)
+ return -ENXIO;
+
+ q = &xc->queues[prio];
+ if (WARN_ON(!q->qpage))
+ return -ENXIO;
+
+ /* Calculate max number of interrupts in that queue. */
+ max = (q->msk + 1) - XIVE_Q_GAP;
+ return atomic_add_unless(&q->count, 1, max) ? 0 : -EBUSY;
+}
+
+static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
+{
+ struct kvm_vcpu *vcpu;
+ int i, rc;
+
+ /* Locate target server */
+ vcpu = kvmppc_xive_find_server(kvm, *server);
+ if (!vcpu) {
+ pr_devel("Can't find server %d\n", *server);
+ return -EINVAL;
+ }
+
+ pr_devel("Finding irq target on 0x%x/%d...\n", *server, prio);
+
+ /* Try pick it */
+ rc = xive_try_pick_queue(vcpu, prio);
+ if (rc == 0)
+ return rc;
+
+ pr_devel(" .. failed, looking up candidate...\n");
+
+ /* Failed, pick another VCPU */
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!vcpu->arch.xive_vcpu)
+ continue;
+ rc = xive_try_pick_queue(vcpu, prio);
+ if (rc == 0) {
+ *server = vcpu->arch.xive_vcpu->server_num;
+ pr_devel(" found on 0x%x/%d\n", *server, prio);
+ return rc;
+ }
+ }
+ pr_devel(" no available target !\n");
+
+ /* No available target ! */
+ return -EBUSY;
+}
+
+static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state)
+{
+ struct xive_irq_data *xd;
+ u32 hw_num;
+ u8 old_prio;
+ u64 val;
+
+ /*
+ * Take the lock, set masked, try again if racing
+ * with H_EOI
+ */
+ for (;;) {
+ arch_spin_lock(&sb->lock);
+ old_prio = state->guest_priority;
+ state->guest_priority = MASKED;
+ mb();
+ if (!state->in_eoi)
+ break;
+ state->guest_priority = old_prio;
+ arch_spin_unlock(&sb->lock);
+ }
+
+ /* No change ? Bail */
+ if (old_prio == MASKED)
+ return old_prio;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ /*
+ * If the interrupt is marked as needing masking via
+ * firmware, we do it here. Firmware masking however
+ * is "lossy", it won't return the old p and q bits
+ * and won't set the interrupt to a state where it will
+ * record queued ones. If this is an issue we should do
+ * lazy masking instead.
+ *
+ * For now, we work around this in unmask by forcing
+ * an interrupt whenever we unmask a non-LSI via FW
+ * (if ever).
+ */
+ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
+ xive_native_configure_irq(hw_num,
+ xive->vp_base + state->act_server,
+ MASKED, state->number);
+ /* set old_p so we can track if an H_EOI was done */
+ state->old_p = true;
+ state->old_q = false;
+ } else {
+ /* Set PQ to 10, return old P and old Q and remember them */
+ val = xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_10);
+ state->old_p = !!(val & 2);
+ state->old_q = !!(val & 1);
+
+ /*
+ * Synchronize hardware to sensure the queues are updated
+ * when masking
+ */
+ xive_native_sync_source(hw_num);
+ }
+
+ return old_prio;
+}
+
+static void xive_lock_for_unmask(struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state)
+{
+ /*
+ * Take the lock try again if racing with H_EOI
+ */
+ for (;;) {
+ arch_spin_lock(&sb->lock);
+ if (!state->in_eoi)
+ break;
+ arch_spin_unlock(&sb->lock);
+ }
+}
+
+static void xive_finish_unmask(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state,
+ u8 prio)
+{
+ struct xive_irq_data *xd;
+ u32 hw_num;
+
+ /* If we aren't changing a thing, move on */
+ if (state->guest_priority != MASKED)
+ goto bail;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ /*
+ * See command in xive_lock_and_mask() concerning masking
+ * via firmware.
+ */
+ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
+ xive_native_configure_irq(hw_num,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+ /* If an EOI is needed, do it here */
+ if (!state->old_p)
+ xive_vm_source_eoi(hw_num, xd);
+ /* If this is not an LSI, force a trigger */
+ if (!(xd->flags & OPAL_XIVE_IRQ_LSI))
+ xive_irq_trigger(xd);
+ goto bail;
+ }
+
+ /* Old Q set, set PQ to 11 */
+ if (state->old_q)
+ xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_11);
+
+ /*
+ * If not old P, then perform an "effective" EOI,
+ * on the source. This will handle the cases where
+ * FW EOI is needed.
+ */
+ if (!state->old_p)
+ xive_vm_source_eoi(hw_num, xd);
+
+ /* Synchronize ordering and mark unmasked */
+ mb();
+bail:
+ state->guest_priority = prio;
+}
+
+/*
+ * Target an interrupt to a given server/prio, this will fallback
+ * to another server if necessary and perform the HW targetting
+ * updates as needed
+ *
+ * NOTE: Must be called with the state lock held
+ */
+static int xive_target_interrupt(struct kvm *kvm,
+ struct kvmppc_xive_irq_state *state,
+ u32 server, u8 prio)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ u32 hw_num;
+ int rc;
+
+ /*
+ * This will return a tentative server and actual
+ * priority. The count for that new target will have
+ * already been incremented.
+ */
+ rc = xive_select_target(kvm, &server, prio);
+
+ /*
+ * We failed to find a target ? Not much we can do
+ * at least until we support the GIQ.
+ */
+ if (rc)
+ return rc;
+
+ /*
+ * Increment the old queue pending count if there
+ * was one so that the old queue count gets adjusted later
+ * when observed to be empty.
+ */
+ if (state->act_priority != MASKED)
+ xive_inc_q_pending(kvm,
+ state->act_server,
+ state->act_priority);
+ /*
+ * Update state and HW
+ */
+ state->act_priority = prio;
+ state->act_server = server;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, NULL);
+
+ return xive_native_configure_irq(hw_num,
+ xive->vp_base + server,
+ prio, state->number);
+}
+
+/*
+ * Targetting rules: In order to avoid losing track of
+ * pending interrupts accross mask and unmask, which would
+ * allow queue overflows, we implement the following rules:
+ *
+ * - Unless it was never enabled (or we run out of capacity)
+ * an interrupt is always targetted at a valid server/queue
+ * pair even when "masked" by the guest. This pair tends to
+ * be the last one used but it can be changed under some
+ * circumstances. That allows us to separate targetting
+ * from masking, we only handle accounting during (re)targetting,
+ * this also allows us to let an interrupt drain into its target
+ * queue after masking, avoiding complex schemes to remove
+ * interrupts out of remote processor queues.
+ *
+ * - When masking, we set PQ to 10 and save the previous value
+ * of P and Q.
+ *
+ * - When unmasking, if saved Q was set, we set PQ to 11
+ * otherwise we leave PQ to the HW state which will be either
+ * 10 if nothing happened or 11 if the interrupt fired while
+ * masked. Effectively we are OR'ing the previous Q into the
+ * HW Q.
+ *
+ * Then if saved P is clear, we do an effective EOI (Q->P->Trigger)
+ * which will unmask the interrupt and shoot a new one if Q was
+ * set.
+ *
+ * Otherwise (saved P is set) we leave PQ unchanged (so 10 or 11,
+ * effectively meaning an H_EOI from the guest is still expected
+ * for that interrupt).
+ *
+ * - If H_EOI occurs while masked, we clear the saved P.
+ *
+ * - When changing target, we account on the new target and
+ * increment a separate "pending" counter on the old one.
+ * This pending counter will be used to decrement the old
+ * target's count when its queue has been observed empty.
+ */
+
+int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u8 new_act_prio;
+ int rc = 0;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("set_xive ! irq 0x%x server 0x%x prio %d\n",
+ irq, server, priority);
+
+ /* First, check provisioning of queues */
+ if (priority != MASKED)
+ rc = xive_check_provisioning(xive->kvm,
+ xive_prio_from_guest(priority));
+ if (rc) {
+ pr_devel(" provisioning failure %d !\n", rc);
+ return rc;
+ }
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * We first handle masking/unmasking since the locking
+ * might need to be retried due to EOIs, we'll handle
+ * targetting changes later. These functions will return
+ * with the SB lock held.
+ *
+ * xive_lock_and_mask() will also set state->guest_priority
+ * but won't otherwise change other fields of the state.
+ *
+ * xive_lock_for_unmask will not actually unmask, this will
+ * be done later by xive_finish_unmask() once the targetting
+ * has been done, so we don't try to unmask an interrupt
+ * that hasn't yet been targetted.
+ */
+ if (priority == MASKED)
+ xive_lock_and_mask(xive, sb, state);
+ else
+ xive_lock_for_unmask(sb, state);
+
+
+ /*
+ * Then we handle targetting.
+ *
+ * First calculate a new "actual priority"
+ */
+ new_act_prio = state->act_priority;
+ if (priority != MASKED)
+ new_act_prio = xive_prio_from_guest(priority);
+
+ pr_devel(" new_act_prio=%x act_server=%x act_prio=%x\n",
+ new_act_prio, state->act_server, state->act_priority);
+
+ /*
+ * Then check if we actually need to change anything,
+ *
+ * The condition for re-targetting the interrupt is that
+ * we have a valid new priority (new_act_prio is not 0xff)
+ * and either the server or the priority changed.
+ *
+ * Note: If act_priority was ff and the new priority is
+ * also ff, we don't do anything and leave the interrupt
+ * untargetted. An attempt of doing an int_on on an
+ * untargetted interrupt will fail. If that is a problem
+ * we could initialize interrupts with valid default
+ */
+
+ if (new_act_prio != MASKED &&
+ (state->act_server != server ||
+ state->act_priority != new_act_prio))
+ rc = xive_target_interrupt(kvm, state, server, new_act_prio);
+
+ /*
+ * Perform the final unmasking of the interrupt source
+ * if necessary
+ */
+ if (priority != MASKED)
+ xive_finish_unmask(xive, sb, state, priority);
+
+ /*
+ * Finally Update saved_priority to match. Only int_on/off
+ * set this field to a different value.
+ */
+ state->saved_priority = priority;
+
+ arch_spin_unlock(&sb->lock);
+ return rc;
+}
+
+int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+ arch_spin_lock(&sb->lock);
+ *server = state->guest_server;
+ *priority = state->guest_priority;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+int kvmppc_xive_int_on(struct kvm *kvm, u32 irq)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ pr_devel("int_on(irq=0x%x)\n", irq);
+
+ /*
+ * Check if interrupt was not targetted
+ */
+ if (state->act_priority == MASKED) {
+ pr_devel("int_on on untargetted interrupt\n");
+ return -EINVAL;
+ }
+
+ /* If saved_priority is 0xff, do nothing */
+ if (state->saved_priority == MASKED)
+ return 0;
+
+ /*
+ * Lock and unmask it.
+ */
+ xive_lock_for_unmask(sb, state);
+ xive_finish_unmask(xive, sb, state, state->saved_priority);
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+int kvmppc_xive_int_off(struct kvm *kvm, u32 irq)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ pr_devel("int_off(irq=0x%x)\n", irq);
+
+ /*
+ * Lock and mask
+ */
+ state->saved_priority = xive_lock_and_mask(xive, sb, state);
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+static bool xive_restore_pending_irq(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return false;
+ state = &sb->irq_state[idx];
+ if (!state->valid)
+ return false;
+
+ /*
+ * Trigger the IPI. This assumes we never restore a pass-through
+ * interrupt which should be safe enough
+ */
+ xive_irq_trigger(&state->ipi_data);
+
+ return true;
+}
+
+u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ return 0;
+
+ /* Return the per-cpu state for state saving/migration */
+ return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT |
+ (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT;
+}
+
+int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+ u8 cppr, mfrr;
+ u32 xisr;
+
+ if (!xc || !xive)
+ return -ENOENT;
+
+ /* Grab individual state fields. We don't use pending_pri */
+ cppr = icpval >> KVM_REG_PPC_ICP_CPPR_SHIFT;
+ xisr = (icpval >> KVM_REG_PPC_ICP_XISR_SHIFT) &
+ KVM_REG_PPC_ICP_XISR_MASK;
+ mfrr = icpval >> KVM_REG_PPC_ICP_MFRR_SHIFT;
+
+ pr_devel("set_icp vcpu %d cppr=0x%x mfrr=0x%x xisr=0x%x\n",
+ xc->server_num, cppr, mfrr, xisr);
+
+ /*
+ * We can't update the state of a "pushed" VCPU, but that
+ * shouldn't happen.
+ */
+ if (WARN_ON(vcpu->arch.xive_pushed))
+ return -EIO;
+
+ /* Update VCPU HW saved state */
+ vcpu->arch.xive_saved_state.cppr = cppr;
+ xc->hw_cppr = xc->cppr = cppr;
+
+ /*
+ * Update MFRR state. If it's not 0xff, we mark the VCPU as
+ * having a pending MFRR change, which will re-evaluate the
+ * target. The VCPU will thus potentially get a spurious
+ * interrupt but that's not a big deal.
+ */
+ xc->mfrr = mfrr;
+ if (mfrr < cppr)
+ xive_irq_trigger(&xc->vp_ipi_data);
+
+ /*
+ * Now saved XIRR is "interesting". It means there's something in
+ * the legacy "1 element" queue... for an IPI we simply ignore it,
+ * as the MFRR restore will handle that. For anything else we need
+ * to force a resend of the source.
+ * However the source may not have been setup yet. If that's the
+ * case, we keep that info and increment a counter in the xive to
+ * tell subsequent xive_set_source() to go look.
+ */
+ if (xisr > XICS_IPI && !xive_restore_pending_irq(xive, xisr)) {
+ xc->delayed_irq = xisr;
+ xive->delayed_irqs++;
+ pr_devel(" xisr restore delayed\n");
+ }
+
+ return 0;
+}
+
+int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ struct irq_data *host_data = irq_desc_get_irq_data(host_desc);
+ unsigned int host_irq = irq_desc_get_irq(host_desc);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(host_data);
+ u16 idx;
+ u8 prio;
+ int rc;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("set_mapped girq 0x%lx host HW irq 0x%x...\n",guest_irq, hw_irq);
+
+ sb = kvmppc_xive_find_source(xive, guest_irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * Mark the passed-through interrupt as going to a VCPU,
+ * this will prevent further EOIs and similar operations
+ * from the XIVE code. It will also mask the interrupt
+ * to either PQ=10 or 11 state, the latter if the interrupt
+ * is pending. This will allow us to unmask or retrigger it
+ * after routing it to the guest with a simple EOI.
+ *
+ * The "state" argument is a "token", all it needs is to be
+ * non-NULL to switch to passed-through or NULL for the
+ * other way around. We may not yet have an actual VCPU
+ * target here and we don't really care.
+ */
+ rc = irq_set_vcpu_affinity(host_irq, state);
+ if (rc) {
+ pr_err("Failed to set VCPU affinity for irq %d\n", host_irq);
+ return rc;
+ }
+
+ /*
+ * Mask and read state of IPI. We need to know if its P bit
+ * is set as that means it's potentially already using a
+ * queue entry in the target
+ */
+ prio = xive_lock_and_mask(xive, sb, state);
+ pr_devel(" old IPI prio %02x P:%d Q:%d\n", prio,
+ state->old_p, state->old_q);
+
+ /* Turn the IPI hard off */
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+
+ /* Grab info about irq */
+ state->pt_number = hw_irq;
+ state->pt_data = irq_data_get_irq_handler_data(host_data);
+
+ /*
+ * Configure the IRQ to match the existing configuration of
+ * the IPI if it was already targetted. Otherwise this will
+ * mask the interrupt in a lossy way (act_priority is 0xff)
+ * which is fine for a never started interrupt.
+ */
+ xive_native_configure_irq(hw_irq,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+
+ /*
+ * We do an EOI to enable the interrupt (and retrigger if needed)
+ * if the guest has the interrupt unmasked and the P bit was *not*
+ * set in the IPI. If it was set, we know a slot may still be in
+ * use in the target queue thus we have to wait for a guest
+ * originated EOI
+ */
+ if (prio != MASKED && !state->old_p)
+ xive_vm_source_eoi(hw_irq, state->pt_data);
+
+ /* Clear old_p/old_q as they are no longer relevant */
+ state->old_p = state->old_q = false;
+
+ /* Restore guest prio (unlocks EOI) */
+ mb();
+ state->guest_priority = prio;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_set_mapped);
+
+int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ unsigned int host_irq = irq_desc_get_irq(host_desc);
+ u16 idx;
+ u8 prio;
+ int rc;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("clr_mapped girq 0x%lx...\n", guest_irq);
+
+ sb = kvmppc_xive_find_source(xive, guest_irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * Mask and read state of IRQ. We need to know if its P bit
+ * is set as that means it's potentially already using a
+ * queue entry in the target
+ */
+ prio = xive_lock_and_mask(xive, sb, state);
+ pr_devel(" old IRQ prio %02x P:%d Q:%d\n", prio,
+ state->old_p, state->old_q);
+
+ /*
+ * If old_p is set, the interrupt is pending, we switch it to
+ * PQ=11. This will force a resend in the host so the interrupt
+ * isn't lost to whatver host driver may pick it up
+ */
+ if (state->old_p)
+ xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_11);
+
+ /* Release the passed-through interrupt to the host */
+ rc = irq_set_vcpu_affinity(host_irq, NULL);
+ if (rc) {
+ pr_err("Failed to clr VCPU affinity for irq %d\n", host_irq);
+ return rc;
+ }
+
+ /* Forget about the IRQ */
+ state->pt_number = 0;
+ state->pt_data = NULL;
+
+ /* Reconfigure the IPI */
+ xive_native_configure_irq(state->ipi_number,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+
+ /*
+ * If old_p is set (we have a queue entry potentially
+ * occupied) or the interrupt is masked, we set the IPI
+ * to PQ=10 state. Otherwise we just re-enable it (PQ=00).
+ */
+ if (prio == MASKED || state->old_p)
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_10);
+ else
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_00);
+
+ /* Restore guest prio (unlocks EOI) */
+ mb();
+ state->guest_priority = prio;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_clr_mapped);
+
+static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ int i, j;
+
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++) {
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[j];
+
+ if (!state->valid)
+ continue;
+ if (state->act_priority == MASKED)
+ continue;
+ if (state->act_server != xc->server_num)
+ continue;
+
+ /* Clean it up */
+ arch_spin_lock(&sb->lock);
+ state->act_priority = MASKED;
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+ if (state->pt_number) {
+ xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(state->pt_number, 0, MASKED, 0);
+ }
+ arch_spin_unlock(&sb->lock);
+ }
+ }
+}
+
+void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = xc->xive;
+ int i;
+
+ pr_devel("cleanup_vcpu(cpu=%d)\n", xc->server_num);
+
+ /* Ensure no interrupt is still routed to that VP */
+ xc->valid = false;
+ kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+ /* Mask the VP IPI */
+ xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_01);
+
+ /* Disable the VP */
+ xive_native_disable_vp(xc->vp_id);
+
+ /* Free the queues & associated interrupts */
+ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+ struct xive_q *q = &xc->queues[i];
+
+ /* Free the escalation irq */
+ if (xc->esc_virq[i]) {
+ free_irq(xc->esc_virq[i], vcpu);
+ irq_dispose_mapping(xc->esc_virq[i]);
+ kfree(xc->esc_virq_names[i]);
+ }
+ /* Free the queue */
+ xive_native_disable_queue(xc->vp_id, q, i);
+ if (q->qpage) {
+ free_pages((unsigned long)q->qpage,
+ xive->q_page_order);
+ q->qpage = NULL;
+ }
+ }
+
+ /* Free the IPI */
+ if (xc->vp_ipi) {
+ xive_cleanup_irq_data(&xc->vp_ipi_data);
+ xive_native_free_irq(xc->vp_ipi);
+ }
+ /* Free the VP */
+ kfree(xc);
+}
+
+int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu)
+{
+ struct kvmppc_xive *xive = dev->private;
+ struct kvmppc_xive_vcpu *xc;
+ int i, r = -EBUSY;
+
+ pr_devel("connect_vcpu(cpu=%d)\n", cpu);
+
+ if (dev->ops != &kvm_xive_ops) {
+ pr_devel("Wrong ops !\n");
+ return -EPERM;
+ }
+ if (xive->kvm != vcpu->kvm)
+ return -EPERM;
+ if (vcpu->arch.irq_type)
+ return -EBUSY;
+ if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
+ pr_devel("Duplicate !\n");
+ return -EEXIST;
+ }
+ if (cpu >= KVM_MAX_VCPUS) {
+ pr_devel("Out of bounds !\n");
+ return -EINVAL;
+ }
+ xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+ if (!xc)
+ return -ENOMEM;
+
+ /* We need to synchronize with queue provisioning */
+ mutex_lock(&vcpu->kvm->lock);
+ vcpu->arch.xive_vcpu = xc;
+ xc->xive = xive;
+ xc->vcpu = vcpu;
+ xc->server_num = cpu;
+ xc->vp_id = xive->vp_base + cpu;
+ xc->mfrr = 0xff;
+ xc->valid = true;
+
+ r = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id);
+ if (r)
+ goto bail;
+
+ /* Configure VCPU fields for use by assembly push/pull */
+ vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
+ vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
+
+ /* Allocate IPI */
+ xc->vp_ipi = xive_native_alloc_irq();
+ if (!xc->vp_ipi) {
+ r = -EIO;
+ goto bail;
+ }
+ pr_devel(" IPI=0x%x\n", xc->vp_ipi);
+
+ r = xive_native_populate_irq_data(xc->vp_ipi, &xc->vp_ipi_data);
+ if (r)
+ goto bail;
+
+ /*
+ * Initialize queues. Initially we set them all for no queueing
+ * and we enable escalation for queue 0 only which we'll use for
+ * our mfrr change notifications. If the VCPU is hot-plugged, we
+ * do handle provisioning however.
+ */
+ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+ struct xive_q *q = &xc->queues[i];
+
+ /* Is queue already enabled ? Provision it */
+ if (xive->qmap & (1 << i)) {
+ r = xive_provision_queue(vcpu, i);
+ if (r == 0)
+ xive_attach_escalation(vcpu, i);
+ if (r)
+ goto bail;
+ } else {
+ r = xive_native_configure_queue(xc->vp_id,
+ q, i, NULL, 0, true);
+ if (r) {
+ pr_err("Failed to configure queue %d for VCPU %d\n",
+ i, cpu);
+ goto bail;
+ }
+ }
+ }
+
+ /* If not done above, attach priority 0 escalation */
+ r = xive_attach_escalation(vcpu, 0);
+ if (r)
+ goto bail;
+
+ /* Enable the VP */
+ r = xive_native_enable_vp(xc->vp_id);
+ if (r)
+ goto bail;
+
+ /* Route the IPI */
+ r = xive_native_configure_irq(xc->vp_ipi, xc->vp_id, 0, XICS_IPI);
+ if (!r)
+ xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_00);
+
+bail:
+ mutex_unlock(&vcpu->kvm->lock);
+ if (r) {
+ kvmppc_xive_cleanup_vcpu(vcpu);
+ return r;
+ }
+
+ vcpu->arch.irq_type = KVMPPC_IRQ_XICS;
+ return 0;
+}
+
+/*
+ * Scanning of queues before/after migration save
+ */
+static void xive_pre_save_set_queued(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return;
+
+ state = &sb->irq_state[idx];
+
+ /* Some sanity checking */
+ if (!state->valid) {
+ pr_err("invalid irq 0x%x in cpu queue!\n", irq);
+ return;
+ }
+
+ /*
+ * If the interrupt is in a queue it should have P set.
+ * We warn so that gets reported. A backtrace isn't useful
+ * so no need to use a WARN_ON.
+ */
+ if (!state->saved_p)
+ pr_err("Interrupt 0x%x is marked in a queue but P not set !\n", irq);
+
+ /* Set flag */
+ state->in_queue = true;
+}
+
+static void xive_pre_save_mask_irq(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ u32 irq)
+{
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[irq];
+
+ if (!state->valid)
+ return;
+
+ /* Mask and save state, this will also sync HW queues */
+ state->saved_scan_prio = xive_lock_and_mask(xive, sb, state);
+
+ /* Transfer P and Q */
+ state->saved_p = state->old_p;
+ state->saved_q = state->old_q;
+
+ /* Unlock */
+ arch_spin_unlock(&sb->lock);
+}
+
+static void xive_pre_save_unmask_irq(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ u32 irq)
+{
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[irq];
+
+ if (!state->valid)
+ return;
+
+ /*
+ * Lock / exclude EOI (not technically necessary if the
+ * guest isn't running concurrently. If this becomes a
+ * performance issue we can probably remove the lock.
+ */
+ xive_lock_for_unmask(sb, state);
+
+ /* Restore mask/prio if it wasn't masked */
+ if (state->saved_scan_prio != MASKED)
+ xive_finish_unmask(xive, sb, state, state->saved_scan_prio);
+
+ /* Unlock */
+ arch_spin_unlock(&sb->lock);
+}
+
+static void xive_pre_save_queue(struct kvmppc_xive *xive, struct xive_q *q)
+{
+ u32 idx = q->idx;
+ u32 toggle = q->toggle;
+ u32 irq;
+
+ do {
+ irq = __xive_read_eq(q->qpage, q->msk, &idx, &toggle);
+ if (irq > XICS_IPI)
+ xive_pre_save_set_queued(xive, irq);
+ } while(irq);
+}
+
+static void xive_pre_save_scan(struct kvmppc_xive *xive)
+{
+ struct kvm_vcpu *vcpu = NULL;
+ int i, j;
+
+ /*
+ * See comment in xive_get_source() about how this
+ * work. Collect a stable state for all interrupts
+ */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ xive_pre_save_mask_irq(xive, sb, j);
+ }
+
+ /* Then scan the queues and update the "in_queue" flag */
+ kvm_for_each_vcpu(i, vcpu, xive->kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ if (!xc)
+ continue;
+ for (j = 0; j < KVMPPC_XIVE_Q_COUNT; j++) {
+ if (xc->queues[i].qpage)
+ xive_pre_save_queue(xive, &xc->queues[i]);
+ }
+ }
+
+ /* Finally restore interrupt states */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ xive_pre_save_unmask_irq(xive, sb, j);
+ }
+}
+
+static void xive_post_save_scan(struct kvmppc_xive *xive)
+{
+ u32 i, j;
+
+ /* Clear all the in_queue flags */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ sb->irq_state[j].in_queue = false;
+ }
+
+ /* Next get_source() will do a new scan */
+ xive->saved_src_count = 0;
+}
+
+/*
+ * This returns the source configuration and state to user space.
+ */
+static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u64 __user *ubufp = (u64 __user *) addr;
+ u64 val, prio;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -ENOENT;
+
+ state = &sb->irq_state[idx];
+
+ if (!state->valid)
+ return -ENOENT;
+
+ pr_devel("get_source(%ld)...\n", irq);
+
+ /*
+ * So to properly save the state into something that looks like a
+ * XICS migration stream we cannot treat interrupts individually.
+ *
+ * We need, instead, mask them all (& save their previous PQ state)
+ * to get a stable state in the HW, then sync them to ensure that
+ * any interrupt that had already fired hits its queue, and finally
+ * scan all the queues to collect which interrupts are still present
+ * in the queues, so we can set the "pending" flag on them and
+ * they can be resent on restore.
+ *
+ * So we do it all when the "first" interrupt gets saved, all the
+ * state is collected at that point, the rest of xive_get_source()
+ * will merely collect and convert that state to the expected
+ * userspace bit mask.
+ */
+ if (xive->saved_src_count == 0)
+ xive_pre_save_scan(xive);
+ xive->saved_src_count++;
+
+ /* Convert saved state into something compatible with xics */
+ val = state->guest_server;
+ prio = state->saved_scan_prio;
+
+ if (prio == MASKED) {
+ val |= KVM_XICS_MASKED;
+ prio = state->saved_priority;
+ }
+ val |= prio << KVM_XICS_PRIORITY_SHIFT;
+ if (state->lsi) {
+ val |= KVM_XICS_LEVEL_SENSITIVE;
+ if (state->saved_p)
+ val |= KVM_XICS_PENDING;
+ } else {
+ if (state->saved_p)
+ val |= KVM_XICS_PRESENTED;
+
+ if (state->saved_q)
+ val |= KVM_XICS_QUEUED;
+
+ /*
+ * We mark it pending (which will attempt a re-delivery)
+ * if we are in a queue *or* we were masked and had
+ * Q set which is equivalent to the XICS "masked pending"
+ * state
+ */
+ if (state->in_queue || (prio == MASKED && state->saved_q))
+ val |= KVM_XICS_PENDING;
+ }
+
+ /*
+ * If that was the last interrupt saved, reset the
+ * in_queue flags
+ */
+ if (xive->saved_src_count == xive->src_count)
+ xive_post_save_scan(xive);
+
+ /* Copy the result to userspace */
+ if (put_user(val, ubufp))
+ return -EFAULT;
+
+ return 0;
+}
+
+static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *xive,
+ int irq)
+{
+ struct kvm *kvm = xive->kvm;
+ struct kvmppc_xive_src_block *sb;
+ int i, bid;
+
+ bid = irq >> KVMPPC_XICS_ICS_SHIFT;
+
+ mutex_lock(&kvm->lock);
+
+ /* block already exists - somebody else got here first */
+ if (xive->src_blocks[bid])
+ goto out;
+
+ /* Create the ICS */
+ sb = kzalloc(sizeof(*sb), GFP_KERNEL);
+ if (!sb)
+ goto out;
+
+ sb->id = bid;
+
+ for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+ sb->irq_state[i].number = (bid << KVMPPC_XICS_ICS_SHIFT) | i;
+ sb->irq_state[i].guest_priority = MASKED;
+ sb->irq_state[i].saved_priority = MASKED;
+ sb->irq_state[i].act_priority = MASKED;
+ }
+ smp_wmb();
+ xive->src_blocks[bid] = sb;
+
+ if (bid > xive->max_sbid)
+ xive->max_sbid = bid;
+
+out:
+ mutex_unlock(&kvm->lock);
+ return xive->src_blocks[bid];
+}
+
+static bool xive_check_delayed_irq(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvm *kvm = xive->kvm;
+ struct kvm_vcpu *vcpu = NULL;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ continue;
+
+ if (xc->delayed_irq == irq) {
+ xc->delayed_irq = 0;
+ xive->delayed_irqs--;
+ return true;
+ }
+ }
+ return false;
+}
+
+static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u64 __user *ubufp = (u64 __user *) addr;
+ u16 idx;
+ u64 val;
+ u8 act_prio, guest_prio;
+ u32 server;
+ int rc = 0;
+
+ if (irq < KVMPPC_XICS_FIRST_IRQ || irq >= KVMPPC_XICS_NR_IRQS)
+ return -ENOENT;
+
+ pr_devel("set_source(irq=0x%lx)\n", irq);
+
+ /* Find the source */
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb) {
+ pr_devel("No source, creating source block...\n");
+ sb = xive_create_src_block(xive, irq);
+ if (!sb) {
+ pr_devel("Failed to create block...\n");
+ return -ENOMEM;
+ }
+ }
+ state = &sb->irq_state[idx];
+
+ /* Read user passed data */
+ if (get_user(val, ubufp)) {
+ pr_devel("fault getting user info !\n");
+ return -EFAULT;
+ }
+
+ server = val & KVM_XICS_DESTINATION_MASK;
+ guest_prio = val >> KVM_XICS_PRIORITY_SHIFT;
+
+ pr_devel(" val=0x016%llx (server=0x%x, guest_prio=%d)\n",
+ val, server, guest_prio);
+ /*
+ * If the source doesn't already have an IPI, allocate
+ * one and get the corresponding data
+ */
+ if (!state->ipi_number) {
+ state->ipi_number = xive_native_alloc_irq();
+ if (state->ipi_number == 0) {
+ pr_devel("Failed to allocate IPI !\n");
+ return -ENOMEM;
+ }
+ xive_native_populate_irq_data(state->ipi_number, &state->ipi_data);
+ pr_devel(" src_ipi=0x%x\n", state->ipi_number);
+ }
+
+ /*
+ * We use lock_and_mask() to set us in the right masked
+ * state. We will override that state from the saved state
+ * further down, but this will handle the cases of interrupts
+ * that need FW masking. We set the initial guest_priority to
+ * 0 before calling it to ensure it actually performs the masking.
+ */
+ state->guest_priority = 0;
+ xive_lock_and_mask(xive, sb, state);
+
+ /*
+ * Now, we select a target if we have one. If we don't we
+ * leave the interrupt untargetted. It means that an interrupt
+ * can become "untargetted" accross migration if it was masked
+ * by set_xive() but there is little we can do about it.
+ */
+
+ /* First convert prio and mark interrupt as untargetted */
+ act_prio = xive_prio_from_guest(guest_prio);
+ state->act_priority = MASKED;
+ state->guest_server = server;
+
+ /*
+ * We need to drop the lock due to the mutex below. Hopefully
+ * nothing is touching that interrupt yet since it hasn't been
+ * advertized to a running guest yet
+ */
+ arch_spin_unlock(&sb->lock);
+
+ /* If we have a priority target the interrupt */
+ if (act_prio != MASKED) {
+ /* First, check provisioning of queues */
+ mutex_lock(&xive->kvm->lock);
+ rc = xive_check_provisioning(xive->kvm, act_prio);
+ mutex_unlock(&xive->kvm->lock);
+
+ /* Target interrupt */
+ if (rc == 0)
+ rc = xive_target_interrupt(xive->kvm, state,
+ server, act_prio);
+ /*
+ * If provisioning or targetting failed, leave it
+ * alone and masked. It will remain disabled until
+ * the guest re-targets it.
+ */
+ }
+
+ /*
+ * Find out if this was a delayed irq stashed in an ICP,
+ * in which case, treat it as pending
+ */
+ if (xive->delayed_irqs && xive_check_delayed_irq(xive, irq)) {
+ val |= KVM_XICS_PENDING;
+ pr_devel(" Found delayed ! forcing PENDING !\n");
+ }
+
+ /* Cleanup the SW state */
+ state->old_p = false;
+ state->old_q = false;
+ state->lsi = false;
+ state->asserted = false;
+
+ /* Restore LSI state */
+ if (val & KVM_XICS_LEVEL_SENSITIVE) {
+ state->lsi = true;
+ if (val & KVM_XICS_PENDING)
+ state->asserted = true;
+ pr_devel(" LSI ! Asserted=%d\n", state->asserted);
+ }
+
+ /*
+ * Restore P and Q. If the interrupt was pending, we
+ * force both P and Q, which will trigger a resend.
+ *
+ * That means that a guest that had both an interrupt
+ * pending (queued) and Q set will restore with only
+ * one instance of that interrupt instead of 2, but that
+ * is perfectly fine as coalescing interrupts that haven't
+ * been presented yet is always allowed.
+ */
+ if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
+ state->old_p = true;
+ if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING)
+ state->old_q = true;
+
+ pr_devel(" P=%d, Q=%d\n", state->old_p, state->old_q);
+
+ /*
+ * If the interrupt was unmasked, update guest priority and
+ * perform the appropriate state transition and do a
+ * re-trigger if necessary.
+ */
+ if (val & KVM_XICS_MASKED) {
+ pr_devel(" masked, saving prio\n");
+ state->guest_priority = MASKED;
+ state->saved_priority = guest_prio;
+ } else {
+ pr_devel(" unmasked, restoring to prio %d\n", guest_prio);
+ xive_finish_unmask(xive, sb, state, guest_prio);
+ state->saved_priority = guest_prio;
+ }
+
+ /* Increment the number of valid sources and mark this one valid */
+ if (!state->valid)
+ xive->src_count++;
+ state->valid = true;
+
+ return 0;
+}
+
+int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+
+ /* Perform locklessly .... (we need to do some RCUisms here...) */
+ state = &sb->irq_state[idx];
+ if (!state->valid)
+ return -EINVAL;
+
+ /* We don't allow a trigger on a passed-through interrupt */
+ if (state->pt_number)
+ return -EINVAL;
+
+ if ((level == 1 && state->lsi) || level == KVM_INTERRUPT_SET_LEVEL)
+ state->asserted = 1;
+ else if (level == 0 || level == KVM_INTERRUPT_UNSET) {
+ state->asserted = 0;
+ return 0;
+ }
+
+ /* Trigger the IPI */
+ xive_irq_trigger(&state->ipi_data);
+
+ return 0;
+}
+
+static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ struct kvmppc_xive *xive = dev->private;
+
+ /* We honor the existing XICS ioctl */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ return xive_set_source(xive, attr->attr, attr->addr);
+ }
+ return -ENXIO;
+}
+
+static int xive_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ struct kvmppc_xive *xive = dev->private;
+
+ /* We honor the existing XICS ioctl */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ return xive_get_source(xive, attr->attr, attr->addr);
+ }
+ return -ENXIO;
+}
+
+static int xive_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ /* We honor the same limits as XICS, at least for now */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ if (attr->attr >= KVMPPC_XICS_FIRST_IRQ &&
+ attr->attr < KVMPPC_XICS_NR_IRQS)
+ return 0;
+ break;
+ }
+ return -ENXIO;
+}
+
+static void kvmppc_xive_cleanup_irq(u32 hw_num, struct xive_irq_data *xd)
+{
+ xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(hw_num, 0, MASKED, 0);
+ xive_cleanup_irq_data(xd);
+}
+
+static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
+{
+ int i;
+
+ for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[i];
+
+ if (!state->valid)
+ continue;
+
+ kvmppc_xive_cleanup_irq(state->ipi_number, &state->ipi_data);
+ xive_native_free_irq(state->ipi_number);
+
+ /* Pass-through, cleanup too */
+ if (state->pt_number)
+ kvmppc_xive_cleanup_irq(state->pt_number, state->pt_data);
+
+ state->valid = false;
+ }
+}
+
+static void kvmppc_xive_free(struct kvm_device *dev)
+{
+ struct kvmppc_xive *xive = dev->private;
+ struct kvm *kvm = xive->kvm;
+ int i;
+
+ debugfs_remove(xive->dentry);
+
+ if (kvm)
+ kvm->arch.xive = NULL;
+
+ /* Mask and free interrupts */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ if (xive->src_blocks[i])
+ kvmppc_xive_free_sources(xive->src_blocks[i]);
+ kfree(xive->src_blocks[i]);
+ xive->src_blocks[i] = NULL;
+ }
+
+ if (xive->vp_base != XIVE_INVALID_VP)
+ xive_native_free_vp_block(xive->vp_base);
+
+
+ kfree(xive);
+ kfree(dev);
+}
+
+static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
+{
+ struct kvmppc_xive *xive;
+ struct kvm *kvm = dev->kvm;
+ int ret = 0;
+
+ pr_devel("Creating xive for partition\n");
+
+ xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+ if (!xive)
+ return -ENOMEM;
+
+ dev->private = xive;
+ xive->dev = dev;
+ xive->kvm = kvm;
+
+ /* Already there ? */
+ if (kvm->arch.xive)
+ ret = -EEXIST;
+ else
+ kvm->arch.xive = xive;
+
+ /* We use the default queue size set by the host */
+ xive->q_order = xive_native_default_eq_shift();
+ if (xive->q_order < PAGE_SHIFT)
+ xive->q_page_order = 0;
+ else
+ xive->q_page_order = xive->q_order - PAGE_SHIFT;
+
+ /* Allocate a bunch of VPs */
+ xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
+ pr_devel("VP_Base=%x\n", xive->vp_base);
+
+ if (xive->vp_base == XIVE_INVALID_VP)
+ ret = -ENOMEM;
+
+ if (ret) {
+ kfree(xive);
+ return ret;
+ }
+
+ return 0;
+}
+
+
+static int xive_debug_show(struct seq_file *m, void *private)
+{
+ struct kvmppc_xive *xive = m->private;
+ struct kvm *kvm = xive->kvm;
+ struct kvm_vcpu *vcpu;
+ u64 t_rm_h_xirr = 0;
+ u64 t_rm_h_ipoll = 0;
+ u64 t_rm_h_cppr = 0;
+ u64 t_rm_h_eoi = 0;
+ u64 t_rm_h_ipi = 0;
+ u64 t_vm_h_xirr = 0;
+ u64 t_vm_h_ipoll = 0;
+ u64 t_vm_h_cppr = 0;
+ u64 t_vm_h_eoi = 0;
+ u64 t_vm_h_ipi = 0;
+ unsigned int i;
+
+ if (!kvm)
+ return 0;
+
+ seq_printf(m, "=========\nVCPU state\n=========\n");
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ continue;
+
+ seq_printf(m, "cpu server %#x CPPR:%#x HWCPPR:%#x"
+ " MFRR:%#x PEND:%#x h_xirr: R=%lld V=%lld\n",
+ xc->server_num, xc->cppr, xc->hw_cppr,
+ xc->mfrr, xc->pending,
+ xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
+
+ t_rm_h_xirr += xc->stat_rm_h_xirr;
+ t_rm_h_ipoll += xc->stat_rm_h_ipoll;
+ t_rm_h_cppr += xc->stat_rm_h_cppr;
+ t_rm_h_eoi += xc->stat_rm_h_eoi;
+ t_rm_h_ipi += xc->stat_rm_h_ipi;
+ t_vm_h_xirr += xc->stat_vm_h_xirr;
+ t_vm_h_ipoll += xc->stat_vm_h_ipoll;
+ t_vm_h_cppr += xc->stat_vm_h_cppr;
+ t_vm_h_eoi += xc->stat_vm_h_eoi;
+ t_vm_h_ipi += xc->stat_vm_h_ipi;
+ }
+
+ seq_printf(m, "Hcalls totals\n");
+ seq_printf(m, " H_XIRR R=%10lld V=%10lld\n", t_rm_h_xirr, t_vm_h_xirr);
+ seq_printf(m, " H_IPOLL R=%10lld V=%10lld\n", t_rm_h_ipoll, t_vm_h_ipoll);
+ seq_printf(m, " H_CPPR R=%10lld V=%10lld\n", t_rm_h_cppr, t_vm_h_cppr);
+ seq_printf(m, " H_EOI R=%10lld V=%10lld\n", t_rm_h_eoi, t_vm_h_eoi);
+ seq_printf(m, " H_IPI R=%10lld V=%10lld\n", t_rm_h_ipi, t_vm_h_ipi);
+
+ return 0;
+}
+
+static int xive_debug_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, xive_debug_show, inode->i_private);
+}
+
+static const struct file_operations xive_debug_fops = {
+ .open = xive_debug_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void xive_debugfs_init(struct kvmppc_xive *xive)
+{
+ char *name;
+
+ name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive);
+ if (!name) {
+ pr_err("%s: no memory for name\n", __func__);
+ return;
+ }
+
+ xive->dentry = debugfs_create_file(name, S_IRUGO, powerpc_debugfs_root,
+ xive, &xive_debug_fops);
+
+ pr_debug("%s: created %s\n", __func__, name);
+ kfree(name);
+}
+
+static void kvmppc_xive_init(struct kvm_device *dev)
+{
+ struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private;
+
+ /* Register some debug interfaces */
+ xive_debugfs_init(xive);
+}
+
+struct kvm_device_ops kvm_xive_ops = {
+ .name = "kvm-xive",
+ .create = kvmppc_xive_create,
+ .init = kvmppc_xive_init,
+ .destroy = kvmppc_xive_free,
+ .set_attr = xive_set_attr,
+ .get_attr = xive_get_attr,
+ .has_attr = xive_has_attr,
+};
+
+void kvmppc_xive_init_module(void)
+{
+ __xive_vm_h_xirr = xive_vm_h_xirr;
+ __xive_vm_h_ipoll = xive_vm_h_ipoll;
+ __xive_vm_h_ipi = xive_vm_h_ipi;
+ __xive_vm_h_cppr = xive_vm_h_cppr;
+ __xive_vm_h_eoi = xive_vm_h_eoi;
+}
+
+void kvmppc_xive_exit_module(void)
+{
+ __xive_vm_h_xirr = NULL;
+ __xive_vm_h_ipoll = NULL;
+ __xive_vm_h_ipi = NULL;
+ __xive_vm_h_cppr = NULL;
+ __xive_vm_h_eoi = NULL;
+}
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
new file mode 100644
index 000000000000..5938f7644dc1
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -0,0 +1,256 @@
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _KVM_PPC_BOOK3S_XIVE_H
+#define _KVM_PPC_BOOK3S_XIVE_H
+
+#ifdef CONFIG_KVM_XICS
+#include "book3s_xics.h"
+
+/*
+ * State for one guest irq source.
+ *
+ * For each guest source we allocate a HW interrupt in the XIVE
+ * which we use for all SW triggers. It will be unused for
+ * pass-through but it's easier to keep around as the same
+ * guest interrupt can alternatively be emulated or pass-through
+ * if a physical device is hot unplugged and replaced with an
+ * emulated one.
+ *
+ * This state structure is very similar to the XICS one with
+ * additional XIVE specific tracking.
+ */
+struct kvmppc_xive_irq_state {
+ bool valid; /* Interrupt entry is valid */
+
+ u32 number; /* Guest IRQ number */
+ u32 ipi_number; /* XIVE IPI HW number */
+ struct xive_irq_data ipi_data; /* XIVE IPI associated data */
+ u32 pt_number; /* XIVE Pass-through number if any */
+ struct xive_irq_data *pt_data; /* XIVE Pass-through associated data */
+
+ /* Targetting as set by guest */
+ u32 guest_server; /* Current guest selected target */
+ u8 guest_priority; /* Guest set priority */
+ u8 saved_priority; /* Saved priority when masking */
+
+ /* Actual targetting */
+ u32 act_server; /* Actual server */
+ u8 act_priority; /* Actual priority */
+
+ /* Various state bits */
+ bool in_eoi; /* Synchronize with H_EOI */
+ bool old_p; /* P bit state when masking */
+ bool old_q; /* Q bit state when masking */
+ bool lsi; /* level-sensitive interrupt */
+ bool asserted; /* Only for emulated LSI: current state */
+
+ /* Saved for migration state */
+ bool in_queue;
+ bool saved_p;
+ bool saved_q;
+ u8 saved_scan_prio;
+};
+
+/* Select the "right" interrupt (IPI vs. passthrough) */
+static inline void kvmppc_xive_select_irq(struct kvmppc_xive_irq_state *state,
+ u32 *out_hw_irq,
+ struct xive_irq_data **out_xd)
+{
+ if (state->pt_number) {
+ if (out_hw_irq)
+ *out_hw_irq = state->pt_number;
+ if (out_xd)
+ *out_xd = state->pt_data;
+ } else {
+ if (out_hw_irq)
+ *out_hw_irq = state->ipi_number;
+ if (out_xd)
+ *out_xd = &state->ipi_data;
+ }
+}
+
+/*
+ * This corresponds to an "ICS" in XICS terminology, we use it
+ * as a mean to break up source information into multiple structures.
+ */
+struct kvmppc_xive_src_block {
+ arch_spinlock_t lock;
+ u16 id;
+ struct kvmppc_xive_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
+};
+
+
+struct kvmppc_xive {
+ struct kvm *kvm;
+ struct kvm_device *dev;
+ struct dentry *dentry;
+
+ /* VP block associated with the VM */
+ u32 vp_base;
+
+ /* Blocks of sources */
+ struct kvmppc_xive_src_block *src_blocks[KVMPPC_XICS_MAX_ICS_ID + 1];
+ u32 max_sbid;
+
+ /*
+ * For state save, we lazily scan the queues on the first interrupt
+ * being migrated. We don't have a clean way to reset that flags
+ * so we keep track of the number of valid sources and how many of
+ * them were migrated so we can reset when all of them have been
+ * processed.
+ */
+ u32 src_count;
+ u32 saved_src_count;
+
+ /*
+ * Some irqs are delayed on restore until the source is created,
+ * keep track here of how many of them
+ */
+ u32 delayed_irqs;
+
+ /* Which queues (priorities) are in use by the guest */
+ u8 qmap;
+
+ /* Queue orders */
+ u32 q_order;
+ u32 q_page_order;
+
+};
+
+#define KVMPPC_XIVE_Q_COUNT 8
+
+struct kvmppc_xive_vcpu {
+ struct kvmppc_xive *xive;
+ struct kvm_vcpu *vcpu;
+ bool valid;
+
+ /* Server number. This is the HW CPU ID from a guest perspective */
+ u32 server_num;
+
+ /*
+ * HW VP corresponding to this VCPU. This is the base of the VP
+ * block plus the server number.
+ */
+ u32 vp_id;
+ u32 vp_chip_id;
+ u32 vp_cam;
+
+ /* IPI used for sending ... IPIs */
+ u32 vp_ipi;
+ struct xive_irq_data vp_ipi_data;
+
+ /* Local emulation state */
+ uint8_t cppr; /* guest CPPR */
+ uint8_t hw_cppr;/* Hardware CPPR */
+ uint8_t mfrr;
+ uint8_t pending;
+
+ /* Each VP has 8 queues though we only provision some */
+ struct xive_q queues[KVMPPC_XIVE_Q_COUNT];
+ u32 esc_virq[KVMPPC_XIVE_Q_COUNT];
+ char *esc_virq_names[KVMPPC_XIVE_Q_COUNT];
+
+ /* Stash a delayed irq on restore from migration (see set_icp) */
+ u32 delayed_irq;
+
+ /* Stats */
+ u64 stat_rm_h_xirr;
+ u64 stat_rm_h_ipoll;
+ u64 stat_rm_h_cppr;
+ u64 stat_rm_h_eoi;
+ u64 stat_rm_h_ipi;
+ u64 stat_vm_h_xirr;
+ u64 stat_vm_h_ipoll;
+ u64 stat_vm_h_cppr;
+ u64 stat_vm_h_eoi;
+ u64 stat_vm_h_ipi;
+};
+
+static inline struct kvm_vcpu *kvmppc_xive_find_server(struct kvm *kvm, u32 nr)
+{
+ struct kvm_vcpu *vcpu = NULL;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu->arch.xive_vcpu && nr == vcpu->arch.xive_vcpu->server_num)
+ return vcpu;
+ }
+ return NULL;
+}
+
+static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmppc_xive *xive,
+ u32 irq, u16 *source)
+{
+ u32 bid = irq >> KVMPPC_XICS_ICS_SHIFT;
+ u16 src = irq & KVMPPC_XICS_SRC_MASK;
+
+ if (source)
+ *source = src;
+ if (bid > KVMPPC_XICS_MAX_ICS_ID)
+ return NULL;
+ return xive->src_blocks[bid];
+}
+
+/*
+ * Mapping between guest priorities and host priorities
+ * is as follow.
+ *
+ * Guest request for 0...6 are honored. Guest request for anything
+ * higher results in a priority of 7 being applied.
+ *
+ * However, when XIRR is returned via H_XIRR, 7 is translated to 0xb
+ * in order to match AIX expectations
+ *
+ * Similar mapping is done for CPPR values
+ */
+static inline u8 xive_prio_from_guest(u8 prio)
+{
+ if (prio == 0xff || prio < 8)
+ return prio;
+ return 7;
+}
+
+static inline u8 xive_prio_to_guest(u8 prio)
+{
+ if (prio == 0xff || prio < 7)
+ return prio;
+ return 0xb;
+}
+
+static inline u32 __xive_read_eq(__be32 *qpage, u32 msk, u32 *idx, u32 *toggle)
+{
+ u32 cur;
+
+ if (!qpage)
+ return 0;
+ cur = be32_to_cpup(qpage + *idx);
+ if ((cur >> 31) == *toggle)
+ return 0;
+ *idx = (*idx + 1) & msk;
+ if (*idx == 0)
+ (*toggle) ^= 1;
+ return cur & 0x7fffffff;
+}
+
+extern unsigned long xive_rm_h_xirr(struct kvm_vcpu *vcpu);
+extern unsigned long xive_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
+extern int xive_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int xive_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int xive_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
+
+extern unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
+extern unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
+extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
+
+#endif /* CONFIG_KVM_XICS */
+#endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
new file mode 100644
index 000000000000..023a31133c37
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -0,0 +1,503 @@
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+/* File to be included by other .c files */
+
+#define XGLUE(a,b) a##b
+#define GLUE(a,b) XGLUE(a,b)
+
+static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
+{
+ u8 cppr;
+ u16 ack;
+
+ /* XXX DD1 bug workaround: Check PIPR vs. CPPR first ! */
+
+ /* Perform the acknowledge OS to register cycle. */
+ ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG));
+
+ /* Synchronize subsequent queue accesses */
+ mb();
+
+ /* XXX Check grouping level */
+
+ /* Anything ? */
+ if (!((ack >> 8) & TM_QW1_NSR_EO))
+ return;
+
+ /* Grab CPPR of the most favored pending interrupt */
+ cppr = ack & 0xff;
+ if (cppr < 8)
+ xc->pending |= 1 << cppr;
+
+#ifdef XIVE_RUNTIME_CHECKS
+ /* Check consistency */
+ if (cppr >= xc->hw_cppr)
+ pr_warn("KVM-XIVE: CPU %d odd ack CPPR, got %d at %d\n",
+ smp_processor_id(), cppr, xc->hw_cppr);
+#endif
+
+ /*
+ * Update our image of the HW CPPR. We don't yet modify
+ * xc->cppr, this will be done as we scan for interrupts
+ * in the queues.
+ */
+ xc->hw_cppr = cppr;
+}
+
+static u8 GLUE(X_PFX,esb_load)(struct xive_irq_data *xd, u32 offset)
+{
+ u64 val;
+
+ if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG)
+ offset |= offset << 4;
+
+ val =__x_readq(__x_eoi_page(xd) + offset);
+#ifdef __LITTLE_ENDIAN__
+ val >>= 64-8;
+#endif
+ return (u8)val;
+}
+
+
+static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
+{
+ /* If the XIVE supports the new "store EOI facility, use it */
+ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
+ __x_writeq(0, __x_eoi_page(xd));
+ else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) {
+ opal_int_eoi(hw_irq);
+ } else {
+ uint64_t eoi_val;
+
+ /*
+ * Otherwise for EOI, we use the special MMIO that does
+ * a clear of both P and Q and returns the old Q,
+ * except for LSIs where we use the "EOI cycle" special
+ * load.
+ *
+ * This allows us to then do a re-trigger if Q was set
+ * rather than synthetizing an interrupt in software
+ *
+ * For LSIs, using the HW EOI cycle works around a problem
+ * on P9 DD1 PHBs where the other ESB accesses don't work
+ * properly.
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_LSI)
+ __x_readq(__x_eoi_page(xd));
+ else {
+ eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00);
+
+ /* Re-trigger if needed */
+ if ((eoi_val & 1) && __x_trig_page(xd))
+ __x_writeq(0, __x_trig_page(xd));
+ }
+ }
+}
+
+enum {
+ scan_fetch,
+ scan_poll,
+ scan_eoi,
+};
+
+static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
+ u8 pending, int scan_type)
+{
+ u32 hirq = 0;
+ u8 prio = 0xff;
+
+ /* Find highest pending priority */
+ while ((xc->mfrr != 0xff || pending != 0) && hirq == 0) {
+ struct xive_q *q;
+ u32 idx, toggle;
+ __be32 *qpage;
+
+ /*
+ * If pending is 0 this will return 0xff which is what
+ * we want
+ */
+ prio = ffs(pending) - 1;
+
+ /*
+ * If the most favoured prio we found pending is less
+ * favored (or equal) than a pending IPI, we return
+ * the IPI instead.
+ *
+ * Note: If pending was 0 and mfrr is 0xff, we will
+ * not spurriously take an IPI because mfrr cannot
+ * then be smaller than cppr.
+ */
+ if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
+ prio = xc->mfrr;
+ hirq = XICS_IPI;
+ break;
+ }
+
+ /* Don't scan past the guest cppr */
+ if (prio >= xc->cppr || prio > 7)
+ break;
+
+ /* Grab queue and pointers */
+ q = &xc->queues[prio];
+ idx = q->idx;
+ toggle = q->toggle;
+
+ /*
+ * Snapshot the queue page. The test further down for EOI
+ * must use the same "copy" that was used by __xive_read_eq
+ * since qpage can be set concurrently and we don't want
+ * to miss an EOI.
+ */
+ qpage = READ_ONCE(q->qpage);
+
+skip_ipi:
+ /*
+ * Try to fetch from the queue. Will return 0 for a
+ * non-queueing priority (ie, qpage = 0).
+ */
+ hirq = __xive_read_eq(qpage, q->msk, &idx, &toggle);
+
+ /*
+ * If this was a signal for an MFFR change done by
+ * H_IPI we skip it. Additionally, if we were fetching
+ * we EOI it now, thus re-enabling reception of a new
+ * such signal.
+ *
+ * We also need to do that if prio is 0 and we had no
+ * page for the queue. In this case, we have non-queued
+ * IPI that needs to be EOId.
+ *
+ * This is safe because if we have another pending MFRR
+ * change that wasn't observed above, the Q bit will have
+ * been set and another occurrence of the IPI will trigger.
+ */
+ if (hirq == XICS_IPI || (prio == 0 && !qpage)) {
+ if (scan_type == scan_fetch)
+ GLUE(X_PFX,source_eoi)(xc->vp_ipi,
+ &xc->vp_ipi_data);
+ /* Loop back on same queue with updated idx/toggle */
+#ifdef XIVE_RUNTIME_CHECKS
+ WARN_ON(hirq && hirq != XICS_IPI);
+#endif
+ if (hirq)
+ goto skip_ipi;
+ }
+
+ /* If fetching, update queue pointers */
+ if (scan_type == scan_fetch) {
+ q->idx = idx;
+ q->toggle = toggle;
+ }
+
+ /* Something found, stop searching */
+ if (hirq)
+ break;
+
+ /* Clear the pending bit on the now empty queue */
+ pending &= ~(1 << prio);
+
+ /*
+ * Check if the queue count needs adjusting due to
+ * interrupts being moved away.
+ */
+ if (atomic_read(&q->pending_count)) {
+ int p = atomic_xchg(&q->pending_count, 0);
+ if (p) {
+#ifdef XIVE_RUNTIME_CHECKS
+ WARN_ON(p > atomic_read(&q->count));
+#endif
+ atomic_sub(p, &q->count);
+ }
+ }
+ }
+
+ /* If we are just taking a "peek", do nothing else */
+ if (scan_type == scan_poll)
+ return hirq;
+
+ /* Update the pending bits */
+ xc->pending = pending;
+
+ /*
+ * If this is an EOI that's it, no CPPR adjustment done here,
+ * all we needed was cleanup the stale pending bits and check
+ * if there's anything left.
+ */
+ if (scan_type == scan_eoi)
+ return hirq;
+
+ /*
+ * If we found an interrupt, adjust what the guest CPPR should
+ * be as if we had just fetched that interrupt from HW.
+ */
+ if (hirq)
+ xc->cppr = prio;
+ /*
+ * If it was an IPI the HW CPPR might have been lowered too much
+ * as the HW interrupt we use for IPIs is routed to priority 0.
+ *
+ * We re-sync it here.
+ */
+ if (xc->cppr != xc->hw_cppr) {
+ xc->hw_cppr = xc->cppr;
+ __x_writeb(xc->cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+ }
+
+ return hirq;
+}
+
+X_STATIC unsigned long GLUE(X_PFX,h_xirr)(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 old_cppr;
+ u32 hirq;
+
+ pr_devel("H_XIRR\n");
+
+ xc->GLUE(X_STAT_PFX,h_xirr)++;
+
+ /* First collect pending bits from HW */
+ GLUE(X_PFX,ack_pending)(xc);
+
+ /*
+ * Cleanup the old-style bits if needed (they may have been
+ * set by pull or an escalation interrupts).
+ */
+ if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions))
+ clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
+ &vcpu->arch.pending_exceptions);
+
+ pr_devel(" new pending=0x%02x hw_cppr=%d cppr=%d\n",
+ xc->pending, xc->hw_cppr, xc->cppr);
+
+ /* Grab previous CPPR and reverse map it */
+ old_cppr = xive_prio_to_guest(xc->cppr);
+
+ /* Scan for actual interrupts */
+ hirq = GLUE(X_PFX,scan_interrupts)(xc, xc->pending, scan_fetch);
+
+ pr_devel(" got hirq=0x%x hw_cppr=%d cppr=%d\n",
+ hirq, xc->hw_cppr, xc->cppr);
+
+#ifdef XIVE_RUNTIME_CHECKS
+ /* That should never hit */
+ if (hirq & 0xff000000)
+ pr_warn("XIVE: Weird guest interrupt number 0x%08x\n", hirq);
+#endif
+
+ /*
+ * XXX We could check if the interrupt is masked here and
+ * filter it. If we chose to do so, we would need to do:
+ *
+ * if (masked) {
+ * lock();
+ * if (masked) {
+ * old_Q = true;
+ * hirq = 0;
+ * }
+ * unlock();
+ * }
+ */
+
+ /* Return interrupt and old CPPR in GPR4 */
+ vcpu->arch.gpr[4] = hirq | (old_cppr << 24);
+
+ return H_SUCCESS;
+}
+
+X_STATIC unsigned long GLUE(X_PFX,h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 pending = xc->pending;
+ u32 hirq;
+ u8 pipr;
+
+ pr_devel("H_IPOLL(server=%ld)\n", server);
+
+ xc->GLUE(X_STAT_PFX,h_ipoll)++;
+
+ /* Grab the target VCPU if not the current one */
+ if (xc->server_num != server) {
+ vcpu = kvmppc_xive_find_server(vcpu->kvm, server);
+ if (!vcpu)
+ return H_PARAMETER;
+ xc = vcpu->arch.xive_vcpu;
+
+ /* Scan all priorities */
+ pending = 0xff;
+ } else {
+ /* Grab pending interrupt if any */
+ pipr = __x_readb(__x_tima + TM_QW1_OS + TM_PIPR);
+ if (pipr < 8)
+ pending |= 1 << pipr;
+ }
+
+ hirq = GLUE(X_PFX,scan_interrupts)(xc, pending, scan_poll);
+
+ /* Return interrupt and old CPPR in GPR4 */
+ vcpu->arch.gpr[4] = hirq | (xc->cppr << 24);
+
+ return H_SUCCESS;
+}
+
+static void GLUE(X_PFX,push_pending_to_hw)(struct kvmppc_xive_vcpu *xc)
+{
+ u8 pending, prio;
+
+ pending = xc->pending;
+ if (xc->mfrr != 0xff) {
+ if (xc->mfrr < 8)
+ pending |= 1 << xc->mfrr;
+ else
+ pending |= 0x80;
+ }
+ if (!pending)
+ return;
+ prio = ffs(pending) - 1;
+
+ __x_writeb(prio, __x_tima + TM_SPC_SET_OS_PENDING);
+}
+
+X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 old_cppr;
+
+ pr_devel("H_CPPR(cppr=%ld)\n", cppr);
+
+ xc->GLUE(X_STAT_PFX,h_cppr)++;
+
+ /* Map CPPR */
+ cppr = xive_prio_from_guest(cppr);
+
+ /* Remember old and update SW state */
+ old_cppr = xc->cppr;
+ xc->cppr = cppr;
+
+ /*
+ * We are masking less, we need to look for pending things
+ * to deliver and set VP pending bits accordingly to trigger
+ * a new interrupt otherwise we might miss MFRR changes for
+ * which we have optimized out sending an IPI signal.
+ */
+ if (cppr > old_cppr)
+ GLUE(X_PFX,push_pending_to_hw)(xc);
+
+ /* Apply new CPPR */
+ xc->hw_cppr = cppr;
+ __x_writeb(cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+
+ return H_SUCCESS;
+}
+
+X_STATIC int GLUE(X_PFX,h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr)
+{
+ struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_irq_data *xd;
+ u8 new_cppr = xirr >> 24;
+ u32 irq = xirr & 0x00ffffff, hw_num;
+ u16 src;
+ int rc = 0;
+
+ pr_devel("H_EOI(xirr=%08lx)\n", xirr);
+
+ xc->GLUE(X_STAT_PFX,h_eoi)++;
+
+ xc->cppr = xive_prio_from_guest(new_cppr);
+
+ /*
+ * IPIs are synthetized from MFRR and thus don't need
+ * any special EOI handling. The underlying interrupt
+ * used to signal MFRR changes is EOId when fetched from
+ * the queue.
+ */
+ if (irq == XICS_IPI || irq == 0)
+ goto bail;
+
+ /* Find interrupt source */
+ sb = kvmppc_xive_find_source(xive, irq, &src);
+ if (!sb) {
+ pr_devel(" source not found !\n");
+ rc = H_PARAMETER;
+ goto bail;
+ }
+ state = &sb->irq_state[src];
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ state->in_eoi = true;
+ mb();
+
+again:
+ if (state->guest_priority == MASKED) {
+ arch_spin_lock(&sb->lock);
+ if (state->guest_priority != MASKED) {
+ arch_spin_unlock(&sb->lock);
+ goto again;
+ }
+ pr_devel(" EOI on saved P...\n");
+
+ /* Clear old_p, that will cause unmask to perform an EOI */
+ state->old_p = false;
+
+ arch_spin_unlock(&sb->lock);
+ } else {
+ pr_devel(" EOI on source...\n");
+
+ /* Perform EOI on the source */
+ GLUE(X_PFX,source_eoi)(hw_num, xd);
+
+ /* If it's an emulated LSI, check level and resend */
+ if (state->lsi && state->asserted)
+ __x_writeq(0, __x_trig_page(xd));
+
+ }
+
+ mb();
+ state->in_eoi = false;
+bail:
+
+ /* Re-evaluate pending IRQs and update HW */
+ GLUE(X_PFX,scan_interrupts)(xc, xc->pending, scan_eoi);
+ GLUE(X_PFX,push_pending_to_hw)(xc);
+ pr_devel(" after scan pending=%02x\n", xc->pending);
+
+ /* Apply new CPPR */
+ xc->hw_cppr = xc->cppr;
+ __x_writeb(xc->cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+
+ return rc;
+}
+
+X_STATIC int GLUE(X_PFX,h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ pr_devel("H_IPI(server=%08lx,mfrr=%ld)\n", server, mfrr);
+
+ xc->GLUE(X_STAT_PFX,h_ipi)++;
+
+ /* Find target */
+ vcpu = kvmppc_xive_find_server(vcpu->kvm, server);
+ if (!vcpu)
+ return H_PARAMETER;
+ xc = vcpu->arch.xive_vcpu;
+
+ /* Locklessly write over MFRR */
+ xc->mfrr = mfrr;
+
+ /* Shoot the IPI if most favored than target cppr */
+ if (mfrr < xc->cppr)
+ __x_writeq(0, __x_trig_page(&xc->vp_ipi_data));
+
+ return H_SUCCESS;
+}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 0514cbd4e533..3eaac3809977 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -300,6 +300,11 @@ void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags)
kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM);
}
+void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu)
+{
+ kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL);
+}
+
void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
{
kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DECREMENTER);
@@ -579,7 +584,7 @@ static void arm_next_watchdog(struct kvm_vcpu *vcpu)
* userspace, so clear the KVM_REQ_WATCHDOG request.
*/
if ((vcpu->arch.tsr & (TSR_ENW | TSR_WIS)) != (TSR_ENW | TSR_WIS))
- clear_bit(KVM_REQ_WATCHDOG, &vcpu->requests);
+ kvm_clear_request(KVM_REQ_WATCHDOG, vcpu);
spin_lock_irqsave(&vcpu->arch.wdt_lock, flags);
nr_jiffies = watchdog_next_timeout(vcpu);
@@ -690,7 +695,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
if (vcpu->arch.shared->msr & MSR_WE) {
local_irq_enable();
kvm_vcpu_block(vcpu);
- clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+ kvm_clear_request(KVM_REQ_UNHALT, vcpu);
hard_irq_disable();
kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 0fda4230f6c0..77fd043b3ecc 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -797,9 +797,8 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
host_tlb_params[0].sets =
host_tlb_params[0].entries / host_tlb_params[0].ways;
host_tlb_params[1].sets = 1;
-
- vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
- host_tlb_params[1].entries,
+ vcpu_e500->h2g_tlb1_rmap = kcalloc(host_tlb_params[1].entries,
+ sizeof(*vcpu_e500->h2g_tlb1_rmap),
GFP_KERNEL);
if (!vcpu_e500->h2g_tlb1_rmap)
return -EINVAL;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index b379146de55b..c873ffe55362 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -259,10 +259,18 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
case OP_31_XOP_MFSPR:
emulated = kvmppc_emulate_mfspr(vcpu, sprn, rt);
+ if (emulated == EMULATE_AGAIN) {
+ emulated = EMULATE_DONE;
+ advance = 0;
+ }
break;
case OP_31_XOP_MTSPR:
emulated = kvmppc_emulate_mtspr(vcpu, sprn, rs);
+ if (emulated == EMULATE_AGAIN) {
+ emulated = EMULATE_DONE;
+ advance = 0;
+ }
break;
case OP_31_XOP_TLBSYNC:
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 6d3c0ee1d744..af833531af31 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -34,18 +34,38 @@
#include "timing.h"
#include "trace.h"
-/* XXX to do:
- * lhax
- * lhaux
- * lswx
- * lswi
- * stswx
- * stswi
- * lha
- * lhau
- * lmw
- * stmw
+#ifdef CONFIG_PPC_FPU
+static bool kvmppc_check_fp_disabled(struct kvm_vcpu *vcpu)
+{
+ if (!(kvmppc_get_msr(vcpu) & MSR_FP)) {
+ kvmppc_core_queue_fpunavail(vcpu);
+ return true;
+ }
+
+ return false;
+}
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_VSX
+static bool kvmppc_check_vsx_disabled(struct kvm_vcpu *vcpu)
+{
+ if (!(kvmppc_get_msr(vcpu) & MSR_VSX)) {
+ kvmppc_core_queue_vsx_unavail(vcpu);
+ return true;
+ }
+
+ return false;
+}
+#endif /* CONFIG_VSX */
+
+/*
+ * XXX to do:
+ * lfiwax, lfiwzx
+ * vector loads and stores
*
+ * Instructions that trap when used on cache-inhibited mappings
+ * are not emulated here: multiple and string instructions,
+ * lq/stq, and the load-reserve/store-conditional instructions.
*/
int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
{
@@ -66,6 +86,19 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
rs = get_rs(inst);
rt = get_rt(inst);
+ /*
+ * if mmio_vsx_tx_sx_enabled == 0, copy data between
+ * VSR[0..31] and memory
+ * if mmio_vsx_tx_sx_enabled == 1, copy data between
+ * VSR[32..63] and memory
+ */
+ vcpu->arch.mmio_vsx_tx_sx_enabled = get_tx_or_sx(inst);
+ vcpu->arch.mmio_vsx_copy_nums = 0;
+ vcpu->arch.mmio_vsx_offset = 0;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_NONE;
+ vcpu->arch.mmio_sp64_extend = 0;
+ vcpu->arch.mmio_sign_extend = 0;
+
switch (get_op(inst)) {
case 31:
switch (get_xop(inst)) {
@@ -73,6 +106,11 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
break;
+ case OP_31_XOP_LWZUX:
+ emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
case OP_31_XOP_LBZX:
emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
break;
@@ -82,22 +120,36 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
break;
+ case OP_31_XOP_STDX:
+ emulated = kvmppc_handle_store(run, vcpu,
+ kvmppc_get_gpr(vcpu, rs), 8, 1);
+ break;
+
+ case OP_31_XOP_STDUX:
+ emulated = kvmppc_handle_store(run, vcpu,
+ kvmppc_get_gpr(vcpu, rs), 8, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
case OP_31_XOP_STWX:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 4, 1);
+ kvmppc_get_gpr(vcpu, rs), 4, 1);
+ break;
+
+ case OP_31_XOP_STWUX:
+ emulated = kvmppc_handle_store(run, vcpu,
+ kvmppc_get_gpr(vcpu, rs), 4, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
break;
case OP_31_XOP_STBX:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 1, 1);
+ kvmppc_get_gpr(vcpu, rs), 1, 1);
break;
case OP_31_XOP_STBUX:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 1, 1);
+ kvmppc_get_gpr(vcpu, rs), 1, 1);
kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
break;
@@ -105,6 +157,11 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
break;
+ case OP_31_XOP_LHAUX:
+ emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
case OP_31_XOP_LHZX:
emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
break;
@@ -116,14 +173,12 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
case OP_31_XOP_STHX:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 2, 1);
+ kvmppc_get_gpr(vcpu, rs), 2, 1);
break;
case OP_31_XOP_STHUX:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 2, 1);
+ kvmppc_get_gpr(vcpu, rs), 2, 1);
kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
break;
@@ -143,8 +198,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
case OP_31_XOP_STWBRX:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 4, 0);
+ kvmppc_get_gpr(vcpu, rs), 4, 0);
break;
case OP_31_XOP_LHBRX:
@@ -153,10 +207,258 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
case OP_31_XOP_STHBRX:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 2, 0);
+ kvmppc_get_gpr(vcpu, rs), 2, 0);
+ break;
+
+ case OP_31_XOP_LDBRX:
+ emulated = kvmppc_handle_load(run, vcpu, rt, 8, 0);
+ break;
+
+ case OP_31_XOP_STDBRX:
+ emulated = kvmppc_handle_store(run, vcpu,
+ kvmppc_get_gpr(vcpu, rs), 8, 0);
+ break;
+
+ case OP_31_XOP_LDX:
+ emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
+ break;
+
+ case OP_31_XOP_LDUX:
+ emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+ case OP_31_XOP_LWAX:
+ emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
+ break;
+
+ case OP_31_XOP_LWAUX:
+ emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+#ifdef CONFIG_PPC_FPU
+ case OP_31_XOP_LFSX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 4, 1);
+ break;
+
+ case OP_31_XOP_LFSUX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 4, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+ case OP_31_XOP_LFDX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 8, 1);
+ break;
+
+ case OP_31_XOP_LFDUX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 8, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+ case OP_31_XOP_LFIWAX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_loads(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 4, 1);
+ break;
+
+ case OP_31_XOP_LFIWZX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 4, 1);
+ break;
+
+ case OP_31_XOP_STFSX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs), 4, 1);
+ break;
+
+ case OP_31_XOP_STFSUX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs), 4, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+ case OP_31_XOP_STFDX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs), 8, 1);
+ break;
+
+ case OP_31_XOP_STFDUX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs), 8, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+ case OP_31_XOP_STFIWX:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs), 4, 1);
+ break;
+#endif
+
+#ifdef CONFIG_VSX
+ case OP_31_XOP_LXSDX:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
+ emulated = kvmppc_handle_vsx_load(run, vcpu,
+ KVM_MMIO_REG_VSX|rt, 8, 1, 0);
+ break;
+
+ case OP_31_XOP_LXSSPX:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_vsx_load(run, vcpu,
+ KVM_MMIO_REG_VSX|rt, 4, 1, 0);
+ break;
+
+ case OP_31_XOP_LXSIWAX:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
+ emulated = kvmppc_handle_vsx_load(run, vcpu,
+ KVM_MMIO_REG_VSX|rt, 4, 1, 1);
+ break;
+
+ case OP_31_XOP_LXSIWZX:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
+ emulated = kvmppc_handle_vsx_load(run, vcpu,
+ KVM_MMIO_REG_VSX|rt, 4, 1, 0);
+ break;
+
+ case OP_31_XOP_LXVD2X:
+ /*
+ * In this case, the official load/store process is like this:
+ * Step1, exit from vm by page fault isr, then kvm save vsr.
+ * Please see guest_exit_cont->store_fp_state->SAVE_32VSRS
+ * as reference.
+ *
+ * Step2, copy data between memory and VCPU
+ * Notice: for LXVD2X/STXVD2X/LXVW4X/STXVW4X, we use
+ * 2copies*8bytes or 4copies*4bytes
+ * to simulate one copy of 16bytes.
+ * Also there is an endian issue here, we should notice the
+ * layout of memory.
+ * Please see MARCO of LXVD2X_ROT/STXVD2X_ROT as more reference.
+ * If host is little-endian, kvm will call XXSWAPD for
+ * LXVD2X_ROT/STXVD2X_ROT.
+ * So, if host is little-endian,
+ * the postion of memeory should be swapped.
+ *
+ * Step3, return to guest, kvm reset register.
+ * Please see kvmppc_hv_entry->load_fp_state->REST_32VSRS
+ * as reference.
+ */
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 2;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
+ emulated = kvmppc_handle_vsx_load(run, vcpu,
+ KVM_MMIO_REG_VSX|rt, 8, 1, 0);
+ break;
+
+ case OP_31_XOP_LXVW4X:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 4;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
+ emulated = kvmppc_handle_vsx_load(run, vcpu,
+ KVM_MMIO_REG_VSX|rt, 4, 1, 0);
+ break;
+
+ case OP_31_XOP_LXVDSX:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ vcpu->arch.mmio_vsx_copy_type =
+ KVMPPC_VSX_COPY_DWORD_LOAD_DUMP;
+ emulated = kvmppc_handle_vsx_load(run, vcpu,
+ KVM_MMIO_REG_VSX|rt, 8, 1, 0);
+ break;
+
+ case OP_31_XOP_STXSDX:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
+ emulated = kvmppc_handle_vsx_store(run, vcpu,
+ rs, 8, 1);
break;
+ case OP_31_XOP_STXSSPX:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_vsx_store(run, vcpu,
+ rs, 4, 1);
+ break;
+
+ case OP_31_XOP_STXSIWX:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_offset = 1;
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
+ emulated = kvmppc_handle_vsx_store(run, vcpu,
+ rs, 4, 1);
+ break;
+
+ case OP_31_XOP_STXVD2X:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 2;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
+ emulated = kvmppc_handle_vsx_store(run, vcpu,
+ rs, 8, 1);
+ break;
+
+ case OP_31_XOP_STXVW4X:
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_vsx_copy_nums = 4;
+ vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
+ emulated = kvmppc_handle_vsx_store(run, vcpu,
+ rs, 4, 1);
+ break;
+#endif /* CONFIG_VSX */
default:
emulated = EMULATE_FAIL;
break;
@@ -167,10 +469,60 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
break;
- /* TBD: Add support for other 64 bit load variants like ldu, ldux, ldx etc. */
+#ifdef CONFIG_PPC_FPU
+ case OP_STFS:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs),
+ 4, 1);
+ break;
+
+ case OP_STFSU:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs),
+ 4, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+ case OP_STFD:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs),
+ 8, 1);
+ break;
+
+ case OP_STFDU:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, rs),
+ 8, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+#endif
+
case OP_LD:
rt = get_rt(inst);
- emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
+ switch (inst & 3) {
+ case 0: /* ld */
+ emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
+ break;
+ case 1: /* ldu */
+ emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+ case 2: /* lwa */
+ emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
+ break;
+ default:
+ emulated = EMULATE_FAIL;
+ }
break;
case OP_LWZU:
@@ -193,31 +545,37 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
4, 1);
break;
- /* TBD: Add support for other 64 bit store variants like stdu, stdux, stdx etc. */
case OP_STD:
rs = get_rs(inst);
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 8, 1);
+ switch (inst & 3) {
+ case 0: /* std */
+ emulated = kvmppc_handle_store(run, vcpu,
+ kvmppc_get_gpr(vcpu, rs), 8, 1);
+ break;
+ case 1: /* stdu */
+ emulated = kvmppc_handle_store(run, vcpu,
+ kvmppc_get_gpr(vcpu, rs), 8, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+ default:
+ emulated = EMULATE_FAIL;
+ }
break;
case OP_STWU:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 4, 1);
+ kvmppc_get_gpr(vcpu, rs), 4, 1);
kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
break;
case OP_STB:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 1, 1);
+ kvmppc_get_gpr(vcpu, rs), 1, 1);
break;
case OP_STBU:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 1, 1);
+ kvmppc_get_gpr(vcpu, rs), 1, 1);
kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
break;
@@ -241,16 +599,48 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
case OP_STH:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 2, 1);
+ kvmppc_get_gpr(vcpu, rs), 2, 1);
break;
case OP_STHU:
emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 2, 1);
+ kvmppc_get_gpr(vcpu, rs), 2, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+#ifdef CONFIG_PPC_FPU
+ case OP_LFS:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 4, 1);
+ break;
+
+ case OP_LFSU:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.mmio_sp64_extend = 1;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 4, 1);
+ kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+ break;
+
+ case OP_LFD:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 8, 1);
+ break;
+
+ case OP_LFDU:
+ if (kvmppc_check_fp_disabled(vcpu))
+ return EMULATE_DONE;
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|rt, 8, 1);
kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
break;
+#endif
default:
emulated = EMULATE_FAIL;
diff --git a/arch/powerpc/kvm/irq.h b/arch/powerpc/kvm/irq.h
index 5a9a10b90762..3f1be85a83bc 100644
--- a/arch/powerpc/kvm/irq.h
+++ b/arch/powerpc/kvm/irq.h
@@ -12,6 +12,7 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
#endif
#ifdef CONFIG_KVM_XICS
ret = ret || (kvm->arch.xics != NULL);
+ ret = ret || (kvm->arch.xive != NULL);
#endif
smp_rmb();
return ret;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 95c91a9de351..f7cf2cd564ef 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -37,6 +37,9 @@
#include <asm/cputhreads.h>
#include <asm/irqflags.h>
#include <asm/iommu.h>
+#include <asm/switch_to.h>
+#include <asm/xive.h>
+
#include "timing.h"
#include "irq.h"
#include "../mm/mmu_decl.h"
@@ -232,7 +235,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
case EV_HCALL_TOKEN(EV_IDLE):
r = EV_SUCCESS;
kvm_vcpu_block(vcpu);
- clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+ kvm_clear_request(KVM_REQ_UNHALT, vcpu);
break;
default:
r = EV_UNIMPLEMENTED;
@@ -524,11 +527,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
/* We support this only for PR */
r = !hv_enabled;
break;
-#ifdef CONFIG_KVM_MMIO
- case KVM_CAP_COALESCED_MMIO:
- r = KVM_COALESCED_MMIO_PAGE_OFFSET;
- break;
-#endif
#ifdef CONFIG_KVM_MPIC
case KVM_CAP_IRQ_MPIC:
r = 1;
@@ -538,6 +536,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CAP_SPAPR_TCE:
case KVM_CAP_SPAPR_TCE_64:
+ /* fallthrough */
+ case KVM_CAP_SPAPR_TCE_VFIO:
case KVM_CAP_PPC_RTAS:
case KVM_CAP_PPC_FIXUP_HCALL:
case KVM_CAP_PPC_ENABLE_HCALL:
@@ -699,7 +699,10 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu);
break;
case KVMPPC_IRQ_XICS:
- kvmppc_xics_free_icp(vcpu);
+ if (xive_enabled())
+ kvmppc_xive_cleanup_vcpu(vcpu);
+ else
+ kvmppc_xics_free_icp(vcpu);
break;
}
@@ -806,6 +809,129 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
kvm->arch.kvm_ops->irq_bypass_del_producer(cons, prod);
}
+#ifdef CONFIG_VSX
+static inline int kvmppc_get_vsr_dword_offset(int index)
+{
+ int offset;
+
+ if ((index != 0) && (index != 1))
+ return -1;
+
+#ifdef __BIG_ENDIAN
+ offset = index;
+#else
+ offset = 1 - index;
+#endif
+
+ return offset;
+}
+
+static inline int kvmppc_get_vsr_word_offset(int index)
+{
+ int offset;
+
+ if ((index > 3) || (index < 0))
+ return -1;
+
+#ifdef __BIG_ENDIAN
+ offset = index;
+#else
+ offset = 3 - index;
+#endif
+ return offset;
+}
+
+static inline void kvmppc_set_vsr_dword(struct kvm_vcpu *vcpu,
+ u64 gpr)
+{
+ union kvmppc_one_reg val;
+ int offset = kvmppc_get_vsr_dword_offset(vcpu->arch.mmio_vsx_offset);
+ int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+
+ if (offset == -1)
+ return;
+
+ if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
+ val.vval = VCPU_VSX_VR(vcpu, index);
+ val.vsxval[offset] = gpr;
+ VCPU_VSX_VR(vcpu, index) = val.vval;
+ } else {
+ VCPU_VSX_FPR(vcpu, index, offset) = gpr;
+ }
+}
+
+static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu,
+ u64 gpr)
+{
+ union kvmppc_one_reg val;
+ int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+
+ if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
+ val.vval = VCPU_VSX_VR(vcpu, index);
+ val.vsxval[0] = gpr;
+ val.vsxval[1] = gpr;
+ VCPU_VSX_VR(vcpu, index) = val.vval;
+ } else {
+ VCPU_VSX_FPR(vcpu, index, 0) = gpr;
+ VCPU_VSX_FPR(vcpu, index, 1) = gpr;
+ }
+}
+
+static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu,
+ u32 gpr32)
+{
+ union kvmppc_one_reg val;
+ int offset = kvmppc_get_vsr_word_offset(vcpu->arch.mmio_vsx_offset);
+ int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+ int dword_offset, word_offset;
+
+ if (offset == -1)
+ return;
+
+ if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
+ val.vval = VCPU_VSX_VR(vcpu, index);
+ val.vsx32val[offset] = gpr32;
+ VCPU_VSX_VR(vcpu, index) = val.vval;
+ } else {
+ dword_offset = offset / 2;
+ word_offset = offset % 2;
+ val.vsxval[0] = VCPU_VSX_FPR(vcpu, index, dword_offset);
+ val.vsx32val[word_offset] = gpr32;
+ VCPU_VSX_FPR(vcpu, index, dword_offset) = val.vsxval[0];
+ }
+}
+#endif /* CONFIG_VSX */
+
+#ifdef CONFIG_PPC_FPU
+static inline u64 sp_to_dp(u32 fprs)
+{
+ u64 fprd;
+
+ preempt_disable();
+ enable_kernel_fp();
+ asm ("lfs%U1%X1 0,%1; stfd%U0%X0 0,%0" : "=m" (fprd) : "m" (fprs)
+ : "fr0");
+ preempt_enable();
+ return fprd;
+}
+
+static inline u32 dp_to_sp(u64 fprd)
+{
+ u32 fprs;
+
+ preempt_disable();
+ enable_kernel_fp();
+ asm ("lfd%U1%X1 0,%1; stfs%U0%X0 0,%0" : "=m" (fprs) : "m" (fprd)
+ : "fr0");
+ preempt_enable();
+ return fprs;
+}
+
+#else
+#define sp_to_dp(x) (x)
+#define dp_to_sp(x) (x)
+#endif /* CONFIG_PPC_FPU */
+
static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
struct kvm_run *run)
{
@@ -832,6 +958,10 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
}
}
+ /* conversion between single and double precision */
+ if ((vcpu->arch.mmio_sp64_extend) && (run->mmio.len == 4))
+ gpr = sp_to_dp(gpr);
+
if (vcpu->arch.mmio_sign_extend) {
switch (run->mmio.len) {
#ifdef CONFIG_PPC64
@@ -848,8 +978,6 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
}
}
- kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
-
switch (vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) {
case KVM_MMIO_REG_GPR:
kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
@@ -866,6 +994,17 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
break;
#endif
+#ifdef CONFIG_VSX
+ case KVM_MMIO_REG_VSX:
+ if (vcpu->arch.mmio_vsx_copy_type == KVMPPC_VSX_COPY_DWORD)
+ kvmppc_set_vsr_dword(vcpu, gpr);
+ else if (vcpu->arch.mmio_vsx_copy_type == KVMPPC_VSX_COPY_WORD)
+ kvmppc_set_vsr_word(vcpu, gpr);
+ else if (vcpu->arch.mmio_vsx_copy_type ==
+ KVMPPC_VSX_COPY_DWORD_LOAD_DUMP)
+ kvmppc_set_vsr_dword_dump(vcpu, gpr);
+ break;
+#endif
default:
BUG();
}
@@ -932,6 +1071,35 @@ int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
return __kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian, 1);
}
+#ifdef CONFIG_VSX
+int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rt, unsigned int bytes,
+ int is_default_endian, int mmio_sign_extend)
+{
+ enum emulation_result emulated = EMULATE_DONE;
+
+ /* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */
+ if ( (vcpu->arch.mmio_vsx_copy_nums > 4) ||
+ (vcpu->arch.mmio_vsx_copy_nums < 0) ) {
+ return EMULATE_FAIL;
+ }
+
+ while (vcpu->arch.mmio_vsx_copy_nums) {
+ emulated = __kvmppc_handle_load(run, vcpu, rt, bytes,
+ is_default_endian, mmio_sign_extend);
+
+ if (emulated != EMULATE_DONE)
+ break;
+
+ vcpu->arch.paddr_accessed += run->mmio.len;
+
+ vcpu->arch.mmio_vsx_copy_nums--;
+ vcpu->arch.mmio_vsx_offset++;
+ }
+ return emulated;
+}
+#endif /* CONFIG_VSX */
+
int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
u64 val, unsigned int bytes, int is_default_endian)
{
@@ -957,6 +1125,9 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
vcpu->mmio_needed = 1;
vcpu->mmio_is_write = 1;
+ if ((vcpu->arch.mmio_sp64_extend) && (bytes == 4))
+ val = dp_to_sp(val);
+
/* Store the value at the lowest bytes in 'data'. */
if (!host_swabbed) {
switch (bytes) {
@@ -990,6 +1161,129 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
}
EXPORT_SYMBOL_GPL(kvmppc_handle_store);
+#ifdef CONFIG_VSX
+static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
+{
+ u32 dword_offset, word_offset;
+ union kvmppc_one_reg reg;
+ int vsx_offset = 0;
+ int copy_type = vcpu->arch.mmio_vsx_copy_type;
+ int result = 0;
+
+ switch (copy_type) {
+ case KVMPPC_VSX_COPY_DWORD:
+ vsx_offset =
+ kvmppc_get_vsr_dword_offset(vcpu->arch.mmio_vsx_offset);
+
+ if (vsx_offset == -1) {
+ result = -1;
+ break;
+ }
+
+ if (!vcpu->arch.mmio_vsx_tx_sx_enabled) {
+ *val = VCPU_VSX_FPR(vcpu, rs, vsx_offset);
+ } else {
+ reg.vval = VCPU_VSX_VR(vcpu, rs);
+ *val = reg.vsxval[vsx_offset];
+ }
+ break;
+
+ case KVMPPC_VSX_COPY_WORD:
+ vsx_offset =
+ kvmppc_get_vsr_word_offset(vcpu->arch.mmio_vsx_offset);
+
+ if (vsx_offset == -1) {
+ result = -1;
+ break;
+ }
+
+ if (!vcpu->arch.mmio_vsx_tx_sx_enabled) {
+ dword_offset = vsx_offset / 2;
+ word_offset = vsx_offset % 2;
+ reg.vsxval[0] = VCPU_VSX_FPR(vcpu, rs, dword_offset);
+ *val = reg.vsx32val[word_offset];
+ } else {
+ reg.vval = VCPU_VSX_VR(vcpu, rs);
+ *val = reg.vsx32val[vsx_offset];
+ }
+ break;
+
+ default:
+ result = -1;
+ break;
+ }
+
+ return result;
+}
+
+int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ int rs, unsigned int bytes, int is_default_endian)
+{
+ u64 val;
+ enum emulation_result emulated = EMULATE_DONE;
+
+ vcpu->arch.io_gpr = rs;
+
+ /* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */
+ if ( (vcpu->arch.mmio_vsx_copy_nums > 4) ||
+ (vcpu->arch.mmio_vsx_copy_nums < 0) ) {
+ return EMULATE_FAIL;
+ }
+
+ while (vcpu->arch.mmio_vsx_copy_nums) {
+ if (kvmppc_get_vsr_data(vcpu, rs, &val) == -1)
+ return EMULATE_FAIL;
+
+ emulated = kvmppc_handle_store(run, vcpu,
+ val, bytes, is_default_endian);
+
+ if (emulated != EMULATE_DONE)
+ break;
+
+ vcpu->arch.paddr_accessed += run->mmio.len;
+
+ vcpu->arch.mmio_vsx_copy_nums--;
+ vcpu->arch.mmio_vsx_offset++;
+ }
+
+ return emulated;
+}
+
+static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu,
+ struct kvm_run *run)
+{
+ enum emulation_result emulated = EMULATE_FAIL;
+ int r;
+
+ vcpu->arch.paddr_accessed += run->mmio.len;
+
+ if (!vcpu->mmio_is_write) {
+ emulated = kvmppc_handle_vsx_load(run, vcpu, vcpu->arch.io_gpr,
+ run->mmio.len, 1, vcpu->arch.mmio_sign_extend);
+ } else {
+ emulated = kvmppc_handle_vsx_store(run, vcpu,
+ vcpu->arch.io_gpr, run->mmio.len, 1);
+ }
+
+ switch (emulated) {
+ case EMULATE_DO_MMIO:
+ run->exit_reason = KVM_EXIT_MMIO;
+ r = RESUME_HOST;
+ break;
+ case EMULATE_FAIL:
+ pr_info("KVM: MMIO emulation failed (VSX repeat)\n");
+ run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ r = RESUME_HOST;
+ break;
+ default:
+ r = RESUME_GUEST;
+ break;
+ }
+ return r;
+}
+#endif /* CONFIG_VSX */
+
int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
{
int r = 0;
@@ -1092,13 +1386,24 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
int r;
sigset_t sigsaved;
- if (vcpu->sigset_active)
- sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
-
if (vcpu->mmio_needed) {
+ vcpu->mmio_needed = 0;
if (!vcpu->mmio_is_write)
kvmppc_complete_mmio_load(vcpu, run);
- vcpu->mmio_needed = 0;
+#ifdef CONFIG_VSX
+ if (vcpu->arch.mmio_vsx_copy_nums > 0) {
+ vcpu->arch.mmio_vsx_copy_nums--;
+ vcpu->arch.mmio_vsx_offset++;
+ }
+
+ if (vcpu->arch.mmio_vsx_copy_nums > 0) {
+ r = kvmppc_emulate_mmio_vsx_loadstore(vcpu, run);
+ if (r == RESUME_HOST) {
+ vcpu->mmio_needed = 1;
+ return r;
+ }
+ }
+#endif
} else if (vcpu->arch.osi_needed) {
u64 *gprs = run->osi.gprs;
int i;
@@ -1120,6 +1425,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
#endif
}
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
if (run->immediate_exit)
r = -EINTR;
else
@@ -1219,8 +1527,12 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
r = -EPERM;
dev = kvm_device_from_filp(f.file);
- if (dev)
- r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
+ if (dev) {
+ if (xive_enabled())
+ r = kvmppc_xive_connect_vcpu(dev, vcpu, cap->args[1]);
+ else
+ r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
+ }
fdput(f);
break;
@@ -1244,7 +1556,7 @@ bool kvm_arch_intc_initialized(struct kvm *kvm)
return true;
#endif
#ifdef CONFIG_KVM_XICS
- if (kvm->arch.xics)
+ if (kvm->arch.xics || kvm->arch.xive)
return true;
#endif
return false;
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 0e649d72fe8d..ed7dfce331e0 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -14,12 +14,13 @@ obj-y += string.o alloc.o crtsavres.o code-patching.o \
obj-$(CONFIG_PPC32) += div64.o copy_32.o
-obj64-y += copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \
+obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \
memcpy_64.o memcmp_64.o
obj64-$(CONFIG_SMP) += locks.o
obj64-$(CONFIG_ALTIVEC) += vmx-helper.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
obj-y += checksum_$(BITS).o checksum_wrappers.o
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 0d3002b7e2b4..500b0f6a0b64 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -8,6 +8,7 @@
*/
#include <linux/kernel.h>
+#include <linux/kprobes.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/mm.h>
@@ -59,7 +60,7 @@ bool is_offset_in_branch_range(long offset)
* Helper to check if a given instruction is a conditional branch
* Derived from the conditional checks in analyse_instr()
*/
-bool __kprobes is_conditional_branch(unsigned int instr)
+bool is_conditional_branch(unsigned int instr)
{
unsigned int opcode = instr >> 26;
@@ -75,6 +76,7 @@ bool __kprobes is_conditional_branch(unsigned int instr)
}
return false;
}
+NOKPROBE_SYMBOL(is_conditional_branch);
unsigned int create_branch(const unsigned int *addr,
unsigned long target, int flags)
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index ff0d894d7ff9..8aedbb5f4b86 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -477,18 +477,6 @@ _GLOBAL(__copy_tofrom_user)
bdnz 130b
/* then clear out the destination: r3 bytes starting at 4(r6) */
132: mfctr r3
- srwi. r0,r3,2
- li r9,0
- mtctr r0
- beq 113f
-112: stwu r9,4(r6)
- bdnz 112b
-113: andi. r0,r3,3
- mtctr r0
- beq 120f
-114: stb r9,4(r6)
- addi r6,r6,1
- bdnz 114b
120: blr
EX_TABLE(30b,108b)
@@ -497,7 +485,5 @@ _GLOBAL(__copy_tofrom_user)
EX_TABLE(41b,111b)
EX_TABLE(130b,132b)
EX_TABLE(131b,120b)
- EX_TABLE(112b,120b)
- EX_TABLE(114b,120b)
EXPORT_SYMBOL(__copy_tofrom_user)
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index aee6e24e81ab..08da06e1bd72 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -319,32 +319,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
blr
/*
- * here we have trapped again, need to clear ctr bytes starting at r3
+ * here we have trapped again, amount remaining is in ctr.
*/
-143: mfctr r5
- li r0,0
- mr r4,r3
- mr r3,r5 /* return the number of bytes not copied */
-1: andi. r9,r4,7
- beq 3f
-90: stb r0,0(r4)
- addic. r5,r5,-1
- addi r4,r4,1
- bne 1b
- blr
-3: cmpldi cr1,r5,8
- srdi r9,r5,3
- andi. r5,r5,7
- blt cr1,93f
- mtctr r9
-91: std r0,0(r4)
- addi r4,r4,8
- bdnz 91b
-93: beqlr
- mtctr r5
-92: stb r0,0(r4)
- addi r4,r4,1
- bdnz 92b
+143: mfctr r3
blr
/*
@@ -389,10 +366,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
ld r5,-8(r1)
add r6,r6,r5
subf r3,r3,r6 /* #bytes not copied */
-190:
-191:
-192:
- blr /* #bytes not copied in r3 */
+ blr
EX_TABLE(20b,120b)
EX_TABLE(220b,320b)
@@ -451,9 +425,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
EX_TABLE(88b,188b)
EX_TABLE(43b,143b)
EX_TABLE(89b,189b)
- EX_TABLE(90b,190b)
- EX_TABLE(91b,191b)
- EX_TABLE(92b,192b)
/*
* Routine to copy a whole page of data, optimized for POWER4.
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 846dba2c6360..33117f8a0882 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -49,7 +49,8 @@ extern int do_stxvd2x(int rn, unsigned long ea);
/*
* Emulate the truncation of 64 bit values in 32-bit mode.
*/
-static unsigned long truncate_if_32bit(unsigned long msr, unsigned long val)
+static nokprobe_inline unsigned long truncate_if_32bit(unsigned long msr,
+ unsigned long val)
{
#ifdef __powerpc64__
if ((msr & MSR_64BIT) == 0)
@@ -61,7 +62,7 @@ static unsigned long truncate_if_32bit(unsigned long msr, unsigned long val)
/*
* Determine whether a conditional branch instruction would branch.
*/
-static int __kprobes branch_taken(unsigned int instr, struct pt_regs *regs)
+static nokprobe_inline int branch_taken(unsigned int instr, struct pt_regs *regs)
{
unsigned int bo = (instr >> 21) & 0x1f;
unsigned int bi;
@@ -81,8 +82,7 @@ static int __kprobes branch_taken(unsigned int instr, struct pt_regs *regs)
return 1;
}
-
-static long __kprobes address_ok(struct pt_regs *regs, unsigned long ea, int nb)
+static nokprobe_inline long address_ok(struct pt_regs *regs, unsigned long ea, int nb)
{
if (!user_mode(regs))
return 1;
@@ -92,7 +92,7 @@ static long __kprobes address_ok(struct pt_regs *regs, unsigned long ea, int nb)
/*
* Calculate effective address for a D-form instruction
*/
-static unsigned long __kprobes dform_ea(unsigned int instr, struct pt_regs *regs)
+static nokprobe_inline unsigned long dform_ea(unsigned int instr, struct pt_regs *regs)
{
int ra;
unsigned long ea;
@@ -109,7 +109,7 @@ static unsigned long __kprobes dform_ea(unsigned int instr, struct pt_regs *regs
/*
* Calculate effective address for a DS-form instruction
*/
-static unsigned long __kprobes dsform_ea(unsigned int instr, struct pt_regs *regs)
+static nokprobe_inline unsigned long dsform_ea(unsigned int instr, struct pt_regs *regs)
{
int ra;
unsigned long ea;
@@ -126,8 +126,8 @@ static unsigned long __kprobes dsform_ea(unsigned int instr, struct pt_regs *reg
/*
* Calculate effective address for an X-form instruction
*/
-static unsigned long __kprobes xform_ea(unsigned int instr,
- struct pt_regs *regs)
+static nokprobe_inline unsigned long xform_ea(unsigned int instr,
+ struct pt_regs *regs)
{
int ra, rb;
unsigned long ea;
@@ -145,33 +145,33 @@ static unsigned long __kprobes xform_ea(unsigned int instr,
* Return the largest power of 2, not greater than sizeof(unsigned long),
* such that x is a multiple of it.
*/
-static inline unsigned long max_align(unsigned long x)
+static nokprobe_inline unsigned long max_align(unsigned long x)
{
x |= sizeof(unsigned long);
return x & -x; /* isolates rightmost bit */
}
-static inline unsigned long byterev_2(unsigned long x)
+static nokprobe_inline unsigned long byterev_2(unsigned long x)
{
return ((x >> 8) & 0xff) | ((x & 0xff) << 8);
}
-static inline unsigned long byterev_4(unsigned long x)
+static nokprobe_inline unsigned long byterev_4(unsigned long x)
{
return ((x >> 24) & 0xff) | ((x >> 8) & 0xff00) |
((x & 0xff00) << 8) | ((x & 0xff) << 24);
}
#ifdef __powerpc64__
-static inline unsigned long byterev_8(unsigned long x)
+static nokprobe_inline unsigned long byterev_8(unsigned long x)
{
return (byterev_4(x) << 32) | byterev_4(x >> 32);
}
#endif
-static int __kprobes read_mem_aligned(unsigned long *dest, unsigned long ea,
- int nb)
+static nokprobe_inline int read_mem_aligned(unsigned long *dest,
+ unsigned long ea, int nb)
{
int err = 0;
unsigned long x = 0;
@@ -197,8 +197,8 @@ static int __kprobes read_mem_aligned(unsigned long *dest, unsigned long ea,
return err;
}
-static int __kprobes read_mem_unaligned(unsigned long *dest, unsigned long ea,
- int nb, struct pt_regs *regs)
+static nokprobe_inline int read_mem_unaligned(unsigned long *dest,
+ unsigned long ea, int nb, struct pt_regs *regs)
{
int err;
unsigned long x, b, c;
@@ -248,7 +248,7 @@ static int __kprobes read_mem_unaligned(unsigned long *dest, unsigned long ea,
* Read memory at address ea for nb bytes, return 0 for success
* or -EFAULT if an error occurred.
*/
-static int __kprobes read_mem(unsigned long *dest, unsigned long ea, int nb,
+static int read_mem(unsigned long *dest, unsigned long ea, int nb,
struct pt_regs *regs)
{
if (!address_ok(regs, ea, nb))
@@ -257,9 +257,10 @@ static int __kprobes read_mem(unsigned long *dest, unsigned long ea, int nb,
return read_mem_aligned(dest, ea, nb);
return read_mem_unaligned(dest, ea, nb, regs);
}
+NOKPROBE_SYMBOL(read_mem);
-static int __kprobes write_mem_aligned(unsigned long val, unsigned long ea,
- int nb)
+static nokprobe_inline int write_mem_aligned(unsigned long val,
+ unsigned long ea, int nb)
{
int err = 0;
@@ -282,8 +283,8 @@ static int __kprobes write_mem_aligned(unsigned long val, unsigned long ea,
return err;
}
-static int __kprobes write_mem_unaligned(unsigned long val, unsigned long ea,
- int nb, struct pt_regs *regs)
+static nokprobe_inline int write_mem_unaligned(unsigned long val,
+ unsigned long ea, int nb, struct pt_regs *regs)
{
int err;
unsigned long c;
@@ -325,7 +326,7 @@ static int __kprobes write_mem_unaligned(unsigned long val, unsigned long ea,
* Write memory at address ea for nb bytes, return 0 for success
* or -EFAULT if an error occurred.
*/
-static int __kprobes write_mem(unsigned long val, unsigned long ea, int nb,
+static int write_mem(unsigned long val, unsigned long ea, int nb,
struct pt_regs *regs)
{
if (!address_ok(regs, ea, nb))
@@ -334,13 +335,14 @@ static int __kprobes write_mem(unsigned long val, unsigned long ea, int nb,
return write_mem_aligned(val, ea, nb);
return write_mem_unaligned(val, ea, nb, regs);
}
+NOKPROBE_SYMBOL(write_mem);
#ifdef CONFIG_PPC_FPU
/*
* Check the address and alignment, and call func to do the actual
* load or store.
*/
-static int __kprobes do_fp_load(int rn, int (*func)(int, unsigned long),
+static int do_fp_load(int rn, int (*func)(int, unsigned long),
unsigned long ea, int nb,
struct pt_regs *regs)
{
@@ -380,8 +382,9 @@ static int __kprobes do_fp_load(int rn, int (*func)(int, unsigned long),
return err;
return (*func)(rn, ptr);
}
+NOKPROBE_SYMBOL(do_fp_load);
-static int __kprobes do_fp_store(int rn, int (*func)(int, unsigned long),
+static int do_fp_store(int rn, int (*func)(int, unsigned long),
unsigned long ea, int nb,
struct pt_regs *regs)
{
@@ -425,11 +428,12 @@ static int __kprobes do_fp_store(int rn, int (*func)(int, unsigned long),
}
return err;
}
+NOKPROBE_SYMBOL(do_fp_store);
#endif
#ifdef CONFIG_ALTIVEC
/* For Altivec/VMX, no need to worry about alignment */
-static int __kprobes do_vec_load(int rn, int (*func)(int, unsigned long),
+static nokprobe_inline int do_vec_load(int rn, int (*func)(int, unsigned long),
unsigned long ea, struct pt_regs *regs)
{
if (!address_ok(regs, ea & ~0xfUL, 16))
@@ -437,7 +441,7 @@ static int __kprobes do_vec_load(int rn, int (*func)(int, unsigned long),
return (*func)(rn, ea);
}
-static int __kprobes do_vec_store(int rn, int (*func)(int, unsigned long),
+static nokprobe_inline int do_vec_store(int rn, int (*func)(int, unsigned long),
unsigned long ea, struct pt_regs *regs)
{
if (!address_ok(regs, ea & ~0xfUL, 16))
@@ -447,7 +451,7 @@ static int __kprobes do_vec_store(int rn, int (*func)(int, unsigned long),
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
-static int __kprobes do_vsx_load(int rn, int (*func)(int, unsigned long),
+static nokprobe_inline int do_vsx_load(int rn, int (*func)(int, unsigned long),
unsigned long ea, struct pt_regs *regs)
{
int err;
@@ -465,7 +469,7 @@ static int __kprobes do_vsx_load(int rn, int (*func)(int, unsigned long),
return err;
}
-static int __kprobes do_vsx_store(int rn, int (*func)(int, unsigned long),
+static nokprobe_inline int do_vsx_store(int rn, int (*func)(int, unsigned long),
unsigned long ea, struct pt_regs *regs)
{
int err;
@@ -522,7 +526,7 @@ static int __kprobes do_vsx_store(int rn, int (*func)(int, unsigned long),
: "=r" (err) \
: "r" (addr), "i" (-EFAULT), "0" (err))
-static void __kprobes set_cr0(struct pt_regs *regs, int rd)
+static nokprobe_inline void set_cr0(struct pt_regs *regs, int rd)
{
long val = regs->gpr[rd];
@@ -539,7 +543,7 @@ static void __kprobes set_cr0(struct pt_regs *regs, int rd)
regs->ccr |= 0x20000000;
}
-static void __kprobes add_with_carry(struct pt_regs *regs, int rd,
+static nokprobe_inline void add_with_carry(struct pt_regs *regs, int rd,
unsigned long val1, unsigned long val2,
unsigned long carry_in)
{
@@ -560,7 +564,7 @@ static void __kprobes add_with_carry(struct pt_regs *regs, int rd,
regs->xer &= ~XER_CA;
}
-static void __kprobes do_cmp_signed(struct pt_regs *regs, long v1, long v2,
+static nokprobe_inline void do_cmp_signed(struct pt_regs *regs, long v1, long v2,
int crfld)
{
unsigned int crval, shift;
@@ -576,7 +580,7 @@ static void __kprobes do_cmp_signed(struct pt_regs *regs, long v1, long v2,
regs->ccr = (regs->ccr & ~(0xf << shift)) | (crval << shift);
}
-static void __kprobes do_cmp_unsigned(struct pt_regs *regs, unsigned long v1,
+static nokprobe_inline void do_cmp_unsigned(struct pt_regs *regs, unsigned long v1,
unsigned long v2, int crfld)
{
unsigned int crval, shift;
@@ -592,7 +596,7 @@ static void __kprobes do_cmp_unsigned(struct pt_regs *regs, unsigned long v1,
regs->ccr = (regs->ccr & ~(0xf << shift)) | (crval << shift);
}
-static int __kprobes trap_compare(long v1, long v2)
+static nokprobe_inline int trap_compare(long v1, long v2)
{
int ret = 0;
@@ -631,7 +635,7 @@ static int __kprobes trap_compare(long v1, long v2)
* Returns 1 if the instruction has been executed, or 0 if not.
* Sets *op to indicate what the instruction does.
*/
-int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs,
+int analyse_instr(struct instruction_op *op, struct pt_regs *regs,
unsigned int instr)
{
unsigned int opcode, ra, rb, rd, spr, u;
@@ -1692,6 +1696,7 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs,
#endif
}
EXPORT_SYMBOL_GPL(analyse_instr);
+NOKPROBE_SYMBOL(analyse_instr);
/*
* For PPC32 we always use stwu with r1 to change the stack pointer.
@@ -1701,7 +1706,7 @@ EXPORT_SYMBOL_GPL(analyse_instr);
* don't emulate the real store operation. We will do real store
* operation safely in exception return code by checking this flag.
*/
-static __kprobes int handle_stack_update(unsigned long ea, struct pt_regs *regs)
+static nokprobe_inline int handle_stack_update(unsigned long ea, struct pt_regs *regs)
{
#ifdef CONFIG_PPC32
/*
@@ -1721,7 +1726,7 @@ static __kprobes int handle_stack_update(unsigned long ea, struct pt_regs *regs)
return 0;
}
-static __kprobes void do_signext(unsigned long *valp, int size)
+static nokprobe_inline void do_signext(unsigned long *valp, int size)
{
switch (size) {
case 2:
@@ -1733,7 +1738,7 @@ static __kprobes void do_signext(unsigned long *valp, int size)
}
}
-static __kprobes void do_byterev(unsigned long *valp, int size)
+static nokprobe_inline void do_byterev(unsigned long *valp, int size)
{
switch (size) {
case 2:
@@ -1757,7 +1762,7 @@ static __kprobes void do_byterev(unsigned long *valp, int size)
* or -1 if the instruction is one that should not be stepped,
* such as an rfid, or a mtmsrd that would clear MSR_RI.
*/
-int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
+int emulate_step(struct pt_regs *regs, unsigned int instr)
{
struct instruction_op op;
int r, err, size;
@@ -1799,8 +1804,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto instr_done;
case LARX:
- if (regs->msr & MSR_LE)
- return 0;
if (op.ea & (size - 1))
break; /* can't handle misaligned */
if (!address_ok(regs, op.ea, size))
@@ -1823,8 +1826,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto ldst_done;
case STCX:
- if (regs->msr & MSR_LE)
- return 0;
if (op.ea & (size - 1))
break; /* can't handle misaligned */
if (!address_ok(regs, op.ea, size))
@@ -1849,8 +1850,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto ldst_done;
case LOAD:
- if (regs->msr & MSR_LE)
- return 0;
err = read_mem(&regs->gpr[op.reg], op.ea, size, regs);
if (!err) {
if (op.type & SIGNEXT)
@@ -1862,8 +1861,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
#ifdef CONFIG_PPC_FPU
case LOAD_FP:
- if (regs->msr & MSR_LE)
- return 0;
if (size == 4)
err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
else
@@ -1872,15 +1869,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
#endif
#ifdef CONFIG_ALTIVEC
case LOAD_VMX:
- if (regs->msr & MSR_LE)
- return 0;
err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
goto ldst_done;
#endif
#ifdef CONFIG_VSX
case LOAD_VSX:
- if (regs->msr & MSR_LE)
- return 0;
err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
goto ldst_done;
#endif
@@ -1903,8 +1896,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto instr_done;
case STORE:
- if (regs->msr & MSR_LE)
- return 0;
if ((op.type & UPDATE) && size == sizeof(long) &&
op.reg == 1 && op.update_reg == 1 &&
!(regs->msr & MSR_PR) &&
@@ -1917,8 +1908,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
#ifdef CONFIG_PPC_FPU
case STORE_FP:
- if (regs->msr & MSR_LE)
- return 0;
if (size == 4)
err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
else
@@ -1927,15 +1916,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
#endif
#ifdef CONFIG_ALTIVEC
case STORE_VMX:
- if (regs->msr & MSR_LE)
- return 0;
err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
goto ldst_done;
#endif
#ifdef CONFIG_VSX
case STORE_VSX:
- if (regs->msr & MSR_LE)
- return 0;
err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
goto ldst_done;
#endif
@@ -2008,3 +1993,4 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
return 1;
}
+NOKPROBE_SYMBOL(emulate_step);
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
new file mode 100644
index 000000000000..2534c1447554
--- /dev/null
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -0,0 +1,434 @@
+/*
+ * Simple sanity test for emulate_step load/store instructions.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "emulate_step_test: " fmt
+
+#include <linux/ptrace.h>
+#include <asm/sstep.h>
+#include <asm/ppc-opcode.h>
+
+#define IMM_L(i) ((uintptr_t)(i) & 0xffff)
+
+/*
+ * Defined with TEST_ prefix so it does not conflict with other
+ * definitions.
+ */
+#define TEST_LD(r, base, i) (PPC_INST_LD | ___PPC_RT(r) | \
+ ___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZ(r, base, i) (PPC_INST_LWZ | ___PPC_RT(r) | \
+ ___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZX(t, a, b) (PPC_INST_LWZX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STD(r, base, i) (PPC_INST_STD | ___PPC_RS(r) | \
+ ___PPC_RA(base) | ((i) & 0xfffc))
+#define TEST_LDARX(t, a, b, eh) (PPC_INST_LDARX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b) | \
+ __PPC_EH(eh))
+#define TEST_STDCX(s, a, b) (PPC_INST_STDCX | ___PPC_RS(s) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFSX(t, a, b) (PPC_INST_LFSX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFSX(s, a, b) (PPC_INST_STFSX | ___PPC_RS(s) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFDX(t, a, b) (PPC_INST_LFDX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFDX(s, a, b) (PPC_INST_STFDX | ___PPC_RS(s) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LVX(t, a, b) (PPC_INST_LVX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STVX(s, a, b) (PPC_INST_STVX | ___PPC_RS(s) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LXVD2X(s, a, b) (PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_STXVD2X(s, a, b) (PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+
+
+static void __init init_pt_regs(struct pt_regs *regs)
+{
+ static unsigned long msr;
+ static bool msr_cached;
+
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ if (likely(msr_cached)) {
+ regs->msr = msr;
+ return;
+ }
+
+ asm volatile("mfmsr %0" : "=r"(regs->msr));
+
+ regs->msr |= MSR_FP;
+ regs->msr |= MSR_VEC;
+ regs->msr |= MSR_VSX;
+
+ msr = regs->msr;
+ msr_cached = true;
+}
+
+static void __init show_result(char *ins, char *result)
+{
+ pr_info("%-14s : %s\n", ins, result);
+}
+
+static void __init test_ld(void)
+{
+ struct pt_regs regs;
+ unsigned long a = 0x23;
+ int stepped = -1;
+
+ init_pt_regs(&regs);
+ regs.gpr[3] = (unsigned long) &a;
+
+ /* ld r5, 0(r3) */
+ stepped = emulate_step(&regs, TEST_LD(5, 3, 0));
+
+ if (stepped == 1 && regs.gpr[5] == a)
+ show_result("ld", "PASS");
+ else
+ show_result("ld", "FAIL");
+}
+
+static void __init test_lwz(void)
+{
+ struct pt_regs regs;
+ unsigned int a = 0x4545;
+ int stepped = -1;
+
+ init_pt_regs(&regs);
+ regs.gpr[3] = (unsigned long) &a;
+
+ /* lwz r5, 0(r3) */
+ stepped = emulate_step(&regs, TEST_LWZ(5, 3, 0));
+
+ if (stepped == 1 && regs.gpr[5] == a)
+ show_result("lwz", "PASS");
+ else
+ show_result("lwz", "FAIL");
+}
+
+static void __init test_lwzx(void)
+{
+ struct pt_regs regs;
+ unsigned int a[3] = {0x0, 0x0, 0x1234};
+ int stepped = -1;
+
+ init_pt_regs(&regs);
+ regs.gpr[3] = (unsigned long) a;
+ regs.gpr[4] = 8;
+ regs.gpr[5] = 0x8765;
+
+ /* lwzx r5, r3, r4 */
+ stepped = emulate_step(&regs, TEST_LWZX(5, 3, 4));
+ if (stepped == 1 && regs.gpr[5] == a[2])
+ show_result("lwzx", "PASS");
+ else
+ show_result("lwzx", "FAIL");
+}
+
+static void __init test_std(void)
+{
+ struct pt_regs regs;
+ unsigned long a = 0x1234;
+ int stepped = -1;
+
+ init_pt_regs(&regs);
+ regs.gpr[3] = (unsigned long) &a;
+ regs.gpr[5] = 0x5678;
+
+ /* std r5, 0(r3) */
+ stepped = emulate_step(&regs, TEST_STD(5, 3, 0));
+ if (stepped == 1 || regs.gpr[5] == a)
+ show_result("std", "PASS");
+ else
+ show_result("std", "FAIL");
+}
+
+static void __init test_ldarx_stdcx(void)
+{
+ struct pt_regs regs;
+ unsigned long a = 0x1234;
+ int stepped = -1;
+ unsigned long cr0_eq = 0x1 << 29; /* eq bit of CR0 */
+
+ init_pt_regs(&regs);
+ asm volatile("mfcr %0" : "=r"(regs.ccr));
+
+
+ /*** ldarx ***/
+
+ regs.gpr[3] = (unsigned long) &a;
+ regs.gpr[4] = 0;
+ regs.gpr[5] = 0x5678;
+
+ /* ldarx r5, r3, r4, 0 */
+ stepped = emulate_step(&regs, TEST_LDARX(5, 3, 4, 0));
+
+ /*
+ * Don't touch 'a' here. Touching 'a' can do Load/store
+ * of 'a' which result in failure of subsequent stdcx.
+ * Instead, use hardcoded value for comparison.
+ */
+ if (stepped <= 0 || regs.gpr[5] != 0x1234) {
+ show_result("ldarx / stdcx.", "FAIL (ldarx)");
+ return;
+ }
+
+
+ /*** stdcx. ***/
+
+ regs.gpr[5] = 0x9ABC;
+
+ /* stdcx. r5, r3, r4 */
+ stepped = emulate_step(&regs, TEST_STDCX(5, 3, 4));
+
+ /*
+ * Two possible scenarios that indicates successful emulation
+ * of stdcx. :
+ * 1. Reservation is active and store is performed. In this
+ * case cr0.eq bit will be set to 1.
+ * 2. Reservation is not active and store is not performed.
+ * In this case cr0.eq bit will be set to 0.
+ */
+ if (stepped == 1 && ((regs.gpr[5] == a && (regs.ccr & cr0_eq))
+ || (regs.gpr[5] != a && !(regs.ccr & cr0_eq))))
+ show_result("ldarx / stdcx.", "PASS");
+ else
+ show_result("ldarx / stdcx.", "FAIL (stdcx.)");
+}
+
+#ifdef CONFIG_PPC_FPU
+static void __init test_lfsx_stfsx(void)
+{
+ struct pt_regs regs;
+ union {
+ float a;
+ int b;
+ } c;
+ int cached_b;
+ int stepped = -1;
+
+ init_pt_regs(&regs);
+
+
+ /*** lfsx ***/
+
+ c.a = 123.45;
+ cached_b = c.b;
+
+ regs.gpr[3] = (unsigned long) &c.a;
+ regs.gpr[4] = 0;
+
+ /* lfsx frt10, r3, r4 */
+ stepped = emulate_step(&regs, TEST_LFSX(10, 3, 4));
+
+ if (stepped == 1)
+ show_result("lfsx", "PASS");
+ else
+ show_result("lfsx", "FAIL");
+
+
+ /*** stfsx ***/
+
+ c.a = 678.91;
+
+ /* stfsx frs10, r3, r4 */
+ stepped = emulate_step(&regs, TEST_STFSX(10, 3, 4));
+
+ if (stepped == 1 && c.b == cached_b)
+ show_result("stfsx", "PASS");
+ else
+ show_result("stfsx", "FAIL");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+ struct pt_regs regs;
+ union {
+ double a;
+ long b;
+ } c;
+ long cached_b;
+ int stepped = -1;
+
+ init_pt_regs(&regs);
+
+
+ /*** lfdx ***/
+
+ c.a = 123456.78;
+ cached_b = c.b;
+
+ regs.gpr[3] = (unsigned long) &c.a;
+ regs.gpr[4] = 0;
+
+ /* lfdx frt10, r3, r4 */
+ stepped = emulate_step(&regs, TEST_LFDX(10, 3, 4));
+
+ if (stepped == 1)
+ show_result("lfdx", "PASS");
+ else
+ show_result("lfdx", "FAIL");
+
+
+ /*** stfdx ***/
+
+ c.a = 987654.32;
+
+ /* stfdx frs10, r3, r4 */
+ stepped = emulate_step(&regs, TEST_STFDX(10, 3, 4));
+
+ if (stepped == 1 && c.b == cached_b)
+ show_result("stfdx", "PASS");
+ else
+ show_result("stfdx", "FAIL");
+}
+#else
+static void __init test_lfsx_stfsx(void)
+{
+ show_result("lfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+ show_result("stfsx", "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)");
+}
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static void __init test_lvx_stvx(void)
+{
+ struct pt_regs regs;
+ union {
+ vector128 a;
+ u32 b[4];
+ } c;
+ u32 cached_b[4];
+ int stepped = -1;
+
+ init_pt_regs(&regs);
+
+
+ /*** lvx ***/
+
+ cached_b[0] = c.b[0] = 923745;
+ cached_b[1] = c.b[1] = 2139478;
+ cached_b[2] = c.b[2] = 9012;
+ cached_b[3] = c.b[3] = 982134;
+
+ regs.gpr[3] = (unsigned long) &c.a;
+ regs.gpr[4] = 0;
+
+ /* lvx vrt10, r3, r4 */
+ stepped = emulate_step(&regs, TEST_LVX(10, 3, 4));
+
+ if (stepped == 1)
+ show_result("lvx", "PASS");
+ else
+ show_result("lvx", "FAIL");
+
+
+ /*** stvx ***/
+
+ c.b[0] = 4987513;
+ c.b[1] = 84313948;
+ c.b[2] = 71;
+ c.b[3] = 498532;
+
+ /* stvx vrs10, r3, r4 */
+ stepped = emulate_step(&regs, TEST_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])
+ show_result("stvx", "PASS");
+ else
+ show_result("stvx", "FAIL");
+}
+#else
+static void __init test_lvx_stvx(void)
+{
+ show_result("lvx", "SKIP (CONFIG_ALTIVEC is not set)");
+ show_result("stvx", "SKIP (CONFIG_ALTIVEC is not set)");
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static void __init test_lxvd2x_stxvd2x(void)
+{
+ struct pt_regs regs;
+ union {
+ vector128 a;
+ u32 b[4];
+ } c;
+ u32 cached_b[4];
+ int stepped = -1;
+
+ init_pt_regs(&regs);
+
+
+ /*** lxvd2x ***/
+
+ cached_b[0] = c.b[0] = 18233;
+ cached_b[1] = c.b[1] = 34863571;
+ cached_b[2] = c.b[2] = 834;
+ cached_b[3] = c.b[3] = 6138911;
+
+ regs.gpr[3] = (unsigned long) &c.a;
+ regs.gpr[4] = 0;
+
+ /* lxvd2x vsr39, r3, r4 */
+ stepped = emulate_step(&regs, TEST_LXVD2X(39, 3, 4));
+
+ if (stepped == 1)
+ show_result("lxvd2x", "PASS");
+ else
+ show_result("lxvd2x", "FAIL");
+
+
+ /*** stxvd2x ***/
+
+ c.b[0] = 21379463;
+ c.b[1] = 87;
+ c.b[2] = 374234;
+ c.b[3] = 4;
+
+ /* stxvd2x vsr39, r3, r4 */
+ stepped = emulate_step(&regs, TEST_STXVD2X(39, 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])
+ show_result("stxvd2x", "PASS");
+ else
+ show_result("stxvd2x", "FAIL");
+}
+#else
+static void __init test_lxvd2x_stxvd2x(void)
+{
+ show_result("lxvd2x", "SKIP (CONFIG_VSX is not set)");
+ show_result("stxvd2x", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+static int __init test_emulate_step(void)
+{
+ test_ld();
+ test_lwz();
+ test_lwzx();
+ test_std();
+ test_ldarx_stdcx();
+ test_lfsx_stfsx();
+ test_lfdx_stfdx();
+ test_lvx_stvx();
+ test_lxvd2x_stxvd2x();
+
+ return 0;
+}
+late_initcall(test_emulate_step);
diff --git a/arch/powerpc/lib/usercopy_64.c b/arch/powerpc/lib/usercopy_64.c
deleted file mode 100644
index 9bd3a3dad78d..000000000000
--- a/arch/powerpc/lib/usercopy_64.c
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * Functions which are too large to be inlined.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#include <linux/module.h>
-#include <linux/uaccess.h>
-
-unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n)))
- n = __copy_from_user(to, from, n);
- else
- memset(to, 0, n);
- return n;
-}
-
-unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_WRITE, to, n)))
- n = __copy_to_user(to, from, n);
- return n;
-}
-
-unsigned long copy_in_user(void __user *to, const void __user *from,
- unsigned long n)
-{
- might_sleep();
- if (likely(access_ok(VERIFY_READ, from, n) &&
- access_ok(VERIFY_WRITE, to, n)))
- n =__copy_tofrom_user(to, from, n);
- return n;
-}
-
-EXPORT_SYMBOL(copy_from_user);
-EXPORT_SYMBOL(copy_to_user);
-EXPORT_SYMBOL(copy_in_user);
-
diff --git a/arch/powerpc/mm/dump_hashpagetable.c b/arch/powerpc/mm/dump_hashpagetable.c
index d979709a0239..c6b900f54c07 100644
--- a/arch/powerpc/mm/dump_hashpagetable.c
+++ b/arch/powerpc/mm/dump_hashpagetable.c
@@ -468,7 +468,7 @@ static void walk_linearmapping(struct pg_state *st)
unsigned long psize = 1 << mmu_psize_defs[mmu_linear_psize].shift;
for (addr = PAGE_OFFSET; addr < PAGE_OFFSET +
- memblock_phys_mem_size(); addr += psize)
+ memblock_end_of_DRAM(); addr += psize)
hpte_find(st, addr, mmu_linear_psize);
}
diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c
index 49abaf4dc8e3..d659345a98d6 100644
--- a/arch/powerpc/mm/dump_linuxpagetables.c
+++ b/arch/powerpc/mm/dump_linuxpagetables.c
@@ -26,6 +26,10 @@
#include <asm/page.h>
#include <asm/pgalloc.h>
+#ifdef CONFIG_PPC32
+#define KERN_VIRT_START 0
+#endif
+
/*
* To visualise what is happening,
*
@@ -56,6 +60,8 @@ struct pg_state {
struct seq_file *seq;
const struct addr_marker *marker;
unsigned long start_address;
+ unsigned long start_pa;
+ unsigned long last_pa;
unsigned int level;
u64 current_flags;
};
@@ -69,6 +75,7 @@ static struct addr_marker address_markers[] = {
{ 0, "Start of kernel VM" },
{ 0, "vmalloc() Area" },
{ 0, "vmalloc() End" },
+#ifdef CONFIG_PPC64
{ 0, "isa I/O start" },
{ 0, "isa I/O end" },
{ 0, "phb I/O start" },
@@ -76,6 +83,20 @@ static struct addr_marker address_markers[] = {
{ 0, "I/O remap start" },
{ 0, "I/O remap end" },
{ 0, "vmemmap start" },
+#else
+ { 0, "Early I/O remap start" },
+ { 0, "Early I/O remap end" },
+#ifdef CONFIG_NOT_COHERENT_CACHE
+ { 0, "Consistent mem start" },
+ { 0, "Consistent mem end" },
+#endif
+#ifdef CONFIG_HIGHMEM
+ { 0, "Highmem PTEs start" },
+ { 0, "Highmem PTEs end" },
+#endif
+ { 0, "Fixmap start" },
+ { 0, "Fixmap end" },
+#endif
{ -1, NULL },
};
@@ -100,8 +121,13 @@ static const struct flag_info flag_array[] = {
.set = "user",
.clear = " ",
}, {
+#if _PAGE_RO == 0
.mask = _PAGE_RW,
.val = _PAGE_RW,
+#else
+ .mask = _PAGE_RO,
+ .val = 0,
+#endif
.set = "rw",
.clear = "ro",
}, {
@@ -154,11 +180,24 @@ static const struct flag_info flag_array[] = {
.clear = " ",
}, {
#endif
+#ifndef CONFIG_PPC_BOOK3S_64
.mask = _PAGE_NO_CACHE,
.val = _PAGE_NO_CACHE,
.set = "no cache",
.clear = " ",
}, {
+#else
+ .mask = _PAGE_NON_IDEMPOTENT,
+ .val = _PAGE_NON_IDEMPOTENT,
+ .set = "non-idempotent",
+ .clear = " ",
+ }, {
+ .mask = _PAGE_TOLERANT,
+ .val = _PAGE_TOLERANT,
+ .set = "tolerant",
+ .clear = " ",
+ }, {
+#endif
#ifdef CONFIG_PPC_BOOK3S_64
.mask = H_PAGE_BUSY,
.val = H_PAGE_BUSY,
@@ -188,6 +227,10 @@ static const struct flag_info flag_array[] = {
.mask = _PAGE_SPECIAL,
.val = _PAGE_SPECIAL,
.set = "special",
+ }, {
+ .mask = _PAGE_SHARED,
+ .val = _PAGE_SHARED,
+ .set = "shared",
}
};
@@ -252,7 +295,14 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
const char *unit = units;
unsigned long delta;
- seq_printf(st->seq, "0x%016lx-0x%016lx ", st->start_address, addr-1);
+#ifdef CONFIG_PPC64
+ seq_printf(st->seq, "0x%016lx-0x%016lx ", st->start_address, addr-1);
+ seq_printf(st->seq, "0x%016lx ", st->start_pa);
+#else
+ seq_printf(st->seq, "0x%08lx-0x%08lx ", st->start_address, addr - 1);
+ seq_printf(st->seq, "0x%08lx ", st->start_pa);
+#endif
+
delta = (addr - st->start_address) >> 10;
/* Work out what appropriate unit to use */
while (!(delta & 1023) && unit[1]) {
@@ -267,11 +317,15 @@ static void note_page(struct pg_state *st, unsigned long addr,
unsigned int level, u64 val)
{
u64 flag = val & pg_level[level].mask;
+ u64 pa = val & PTE_RPN_MASK;
+
/* At first no level is set */
if (!st->level) {
st->level = level;
st->current_flags = flag;
st->start_address = addr;
+ st->start_pa = pa;
+ st->last_pa = pa;
seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
/*
* Dump the section of virtual memory when:
@@ -279,9 +333,11 @@ static void note_page(struct pg_state *st, unsigned long addr,
* - we change levels in the tree.
* - the address is in a different section of memory and is thus
* used for a different purpose, regardless of the flags.
+ * - the pa of this page is not adjacent to the last inspected page
*/
} else if (flag != st->current_flags || level != st->level ||
- addr >= st->marker[1].start_address) {
+ addr >= st->marker[1].start_address ||
+ pa != st->last_pa + PAGE_SIZE) {
/* Check the PTE flags */
if (st->current_flags) {
@@ -305,8 +361,12 @@ static void note_page(struct pg_state *st, unsigned long addr,
seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
}
st->start_address = addr;
+ st->start_pa = pa;
+ st->last_pa = pa;
st->current_flags = flag;
st->level = level;
+ } else {
+ st->last_pa = pa;
}
}
@@ -377,20 +437,38 @@ static void walk_pagetables(struct pg_state *st)
static void populate_markers(void)
{
- address_markers[0].start_address = PAGE_OFFSET;
- address_markers[1].start_address = VMALLOC_START;
- address_markers[2].start_address = VMALLOC_END;
- address_markers[3].start_address = ISA_IO_BASE;
- address_markers[4].start_address = ISA_IO_END;
- address_markers[5].start_address = PHB_IO_BASE;
- address_markers[6].start_address = PHB_IO_END;
- address_markers[7].start_address = IOREMAP_BASE;
- address_markers[8].start_address = IOREMAP_END;
+ int i = 0;
+
+ address_markers[i++].start_address = PAGE_OFFSET;
+ address_markers[i++].start_address = VMALLOC_START;
+ address_markers[i++].start_address = VMALLOC_END;
+#ifdef CONFIG_PPC64
+ address_markers[i++].start_address = ISA_IO_BASE;
+ address_markers[i++].start_address = ISA_IO_END;
+ address_markers[i++].start_address = PHB_IO_BASE;
+ address_markers[i++].start_address = PHB_IO_END;
+ address_markers[i++].start_address = IOREMAP_BASE;
+ address_markers[i++].start_address = IOREMAP_END;
#ifdef CONFIG_PPC_STD_MMU_64
- address_markers[9].start_address = H_VMEMMAP_BASE;
+ address_markers[i++].start_address = H_VMEMMAP_BASE;
#else
- address_markers[9].start_address = VMEMMAP_BASE;
+ address_markers[i++].start_address = VMEMMAP_BASE;
+#endif
+#else /* !CONFIG_PPC64 */
+ address_markers[i++].start_address = ioremap_bot;
+ address_markers[i++].start_address = IOREMAP_TOP;
+#ifdef CONFIG_NOT_COHERENT_CACHE
+ address_markers[i++].start_address = IOREMAP_TOP;
+ address_markers[i++].start_address = IOREMAP_TOP +
+ CONFIG_CONSISTENT_SIZE;
+#endif
+#ifdef CONFIG_HIGHMEM
+ address_markers[i++].start_address = PKMAP_BASE;
+ address_markers[i++].start_address = PKMAP_ADDR(LAST_PKMAP);
#endif
+ address_markers[i++].start_address = FIXADDR_START;
+ address_markers[i++].start_address = FIXADDR_TOP;
+#endif /* CONFIG_PPC64 */
}
static int ptdump_show(struct seq_file *m, void *v)
@@ -435,7 +513,7 @@ static int ptdump_init(void)
populate_markers();
build_pgtable_complete_mask();
- debugfs_file = debugfs_create_file("kernel_pagetables", 0400, NULL,
+ debugfs_file = debugfs_create_file("kernel_page_tables", 0400, NULL,
NULL, &ptdump_fops);
return debugfs_file ? 0 : -ENOMEM;
}
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 51def8a515be..3a7d580fdc59 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -120,8 +120,6 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address,
siginfo_t info;
unsigned int lsb = 0;
- up_read(&current->mm->mmap_sem);
-
if (!user_mode(regs))
return MM_FAULT_ERR(SIGBUS);
@@ -154,13 +152,6 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
* continue the pagefault.
*/
if (fatal_signal_pending(current)) {
- /*
- * If we have retry set, the mmap semaphore will have
- * alrady been released in __lock_page_or_retry(). Else
- * we release it now.
- */
- if (!(fault & VM_FAULT_RETRY))
- up_read(&current->mm->mmap_sem);
/* Coming from kernel, we need to deal with uaccess fixups */
if (user_mode(regs))
return MM_FAULT_RETURN;
@@ -173,8 +164,6 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
/* Out of memory */
if (fault & VM_FAULT_OOM) {
- up_read(&current->mm->mmap_sem);
-
/*
* We ran out of memory, or some other thing happened to us that
* made us unable to handle the page fault gracefully.
@@ -298,7 +287,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
* can result in fault, which will cause a deadlock when called with
* mmap_sem held
*/
- if (user_mode(regs))
+ if (!is_exec && user_mode(regs))
store_update_sp = store_updates_sp(regs);
if (user_mode(regs))
@@ -458,9 +447,30 @@ good_area:
* the fault.
*/
fault = handle_mm_fault(vma, address, flags);
+
+ /*
+ * Handle the retry right now, the mmap_sem has been released in that
+ * case.
+ */
+ if (unlikely(fault & VM_FAULT_RETRY)) {
+ /* We retry only once */
+ if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ /*
+ * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+ * of starvation.
+ */
+ flags &= ~FAULT_FLAG_ALLOW_RETRY;
+ flags |= FAULT_FLAG_TRIED;
+ if (!fatal_signal_pending(current))
+ goto retry;
+ }
+ /* We will enter mm_fault_error() below */
+ } else
+ up_read(&current->mm->mmap_sem);
+
if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
if (fault & VM_FAULT_SIGSEGV)
- goto bad_area;
+ goto bad_area_nosemaphore;
rc = mm_fault_error(regs, address, fault);
if (rc >= MM_FAULT_RETURN)
goto bail;
@@ -469,41 +479,29 @@ good_area:
}
/*
- * Major/minor page fault accounting is only done on the
- * initial attempt. If we go through a retry, it is extremely
- * likely that the page will be found in page cache at that point.
+ * Major/minor page fault accounting.
*/
- if (flags & FAULT_FLAG_ALLOW_RETRY) {
- if (fault & VM_FAULT_MAJOR) {
- current->maj_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
- regs, address);
+ if (fault & VM_FAULT_MAJOR) {
+ current->maj_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
+ regs, address);
#ifdef CONFIG_PPC_SMLPAR
- if (firmware_has_feature(FW_FEATURE_CMO)) {
- u32 page_ins;
-
- preempt_disable();
- page_ins = be32_to_cpu(get_lppaca()->page_ins);
- page_ins += 1 << PAGE_FACTOR;
- get_lppaca()->page_ins = cpu_to_be32(page_ins);
- preempt_enable();
- }
-#endif /* CONFIG_PPC_SMLPAR */
- } else {
- current->min_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
- regs, address);
- }
- if (fault & VM_FAULT_RETRY) {
- /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
- * of starvation. */
- flags &= ~FAULT_FLAG_ALLOW_RETRY;
- flags |= FAULT_FLAG_TRIED;
- goto retry;
+ if (firmware_has_feature(FW_FEATURE_CMO)) {
+ u32 page_ins;
+
+ preempt_disable();
+ page_ins = be32_to_cpu(get_lppaca()->page_ins);
+ page_ins += 1 << PAGE_FACTOR;
+ get_lppaca()->page_ins = cpu_to_be32(page_ins);
+ preempt_enable();
}
+#endif /* CONFIG_PPC_SMLPAR */
+ } else {
+ current->min_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
+ regs, address);
}
- up_read(&mm->mmap_sem);
goto bail;
bad_area:
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 09cc50c8dace..6f962e5cb5e1 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -31,10 +31,8 @@
#ifdef CONFIG_SMP
.section .bss
.align 2
- .globl mmu_hash_lock
mmu_hash_lock:
.space 4
-EXPORT_SYMBOL(mmu_hash_lock)
#endif /* CONFIG_SMP */
/*
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index cc332608e656..65bb8f33b399 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -638,6 +638,10 @@ static void native_flush_hash_range(unsigned long number, int local)
unsigned long psize = batch->psize;
int ssize = batch->ssize;
int i;
+ unsigned int use_local;
+
+ use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
+ mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
local_irq_save(flags);
@@ -667,8 +671,7 @@ static void native_flush_hash_range(unsigned long number, int local)
} pte_iterate_hashed_end();
}
- if (mmu_has_feature(MMU_FTR_TLBIEL) &&
- mmu_psize_defs[psize].tlbiel && local) {
+ if (use_local) {
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
vpn = batch->vpn[i];
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index c554768b1fa2..f2095ce9d4b0 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -35,9 +35,8 @@
#include <linux/memblock.h>
#include <linux/context_tracking.h>
#include <linux/libfdt.h>
-#include <linux/debugfs.h>
-#include <asm/debug.h>
+#include <asm/debugfs.h>
#include <asm/processor.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
@@ -927,11 +926,6 @@ static void __init htab_initialize(void)
}
#endif /* CONFIG_DEBUG_PAGEALLOC */
- /* On U3 based machines, we need to reserve the DART area and
- * _NOT_ map it to avoid cache paradoxes as it's remapped non
- * cacheable later on
- */
-
/* create bolted the linear mapping in the hash table */
for_each_memblock(memory, reg) {
base = (unsigned long)__va(reg->base);
@@ -981,6 +975,19 @@ void __init hash__early_init_devtree(void)
void __init hash__early_init_mmu(void)
{
+ /*
+ * We have code in __hash_page_64K() and elsewhere, which assumes it can
+ * do the following:
+ * new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & (H_PAGE_F_SECOND | H_PAGE_F_GIX);
+ *
+ * Where the slot number is between 0-15, and values of 8-15 indicate
+ * the secondary bucket. For that code to work H_PAGE_F_SECOND and
+ * H_PAGE_F_GIX must occupy four contiguous bits in the PTE, and
+ * H_PAGE_F_SECOND must be placed above H_PAGE_F_GIX. Assert that here
+ * with a BUILD_BUG_ON().
+ */
+ BUILD_BUG_ON(H_PAGE_F_SECOND != (1ul << (H_PAGE_F_GIX_SHIFT + 3)));
+
htab_init_page_sizes();
/*
@@ -1120,7 +1127,7 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
copro_flush_all_slbs(mm);
if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
- copy_mm_to_paca(&mm->context);
+ copy_mm_to_paca(mm);
slb_flush_and_rebolt();
}
}
@@ -1192,7 +1199,7 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
{
if (user_region) {
if (psize != get_paca_psize(ea)) {
- copy_mm_to_paca(&mm->context);
+ copy_mm_to_paca(mm);
slb_flush_and_rebolt();
}
} else if (get_paca()->vmalloc_sllp !=
@@ -1855,5 +1862,4 @@ static int __init hash64_debugfs(void)
return 0;
}
machine_device_initcall(pseries, hash64_debugfs);
-
#endif /* CONFIG_DEBUG_FS */
diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c
index 83a8be791e06..bfe4e8526b2d 100644
--- a/arch/powerpc/mm/hugetlbpage-book3e.c
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -148,16 +148,9 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
mm = vma->vm_mm;
-#ifdef CONFIG_PPC_MM_SLICES
- psize = get_slice_psize(mm, ea);
- tsize = mmu_get_tsize(psize);
- shift = mmu_psize_defs[psize].shift;
-#else
psize = vma_mmu_pagesize(vma);
shift = __ilog2(psize);
tsize = shift - 10;
-#endif
-
/*
* We can't be interrupted while we're setting up the MAS
* regusters or after we've confirmed that no tlb exists.
diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c
index 35254a678456..6575b9aabef4 100644
--- a/arch/powerpc/mm/hugetlbpage-radix.c
+++ b/arch/powerpc/mm/hugetlbpage-radix.c
@@ -50,9 +50,12 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
struct hstate *h = hstate_file(file);
struct vm_unmapped_area_info info;
+ if (unlikely(addr > mm->context.addr_limit && addr < TASK_SIZE))
+ mm->context.addr_limit = TASK_SIZE;
+
if (len & ~huge_page_mask(h))
return -EINVAL;
- if (len > TASK_SIZE)
+ if (len > mm->task_size)
return -ENOMEM;
if (flags & MAP_FIXED) {
@@ -64,7 +67,7 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
if (addr) {
addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
+ if (mm->task_size - len >= addr &&
(!vma || addr + len <= vma->vm_start))
return addr;
}
@@ -78,5 +81,9 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
info.high_limit = current->mm->mmap_base;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
info.align_offset = 0;
+
+ if (addr > DEFAULT_MAP_WINDOW)
+ info.high_limit += mm->context.addr_limit - DEFAULT_MAP_WINDOW;
+
return vm_unmapped_area(&info);
}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 8c3389cbcd12..a4f33de4008e 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -753,6 +753,24 @@ static int __init add_huge_page_size(unsigned long long size)
if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
return -EINVAL;
+#ifdef CONFIG_PPC_BOOK3S_64
+ /*
+ * We need to make sure that for different page sizes reported by
+ * firmware we only add hugetlb support for page sizes that can be
+ * supported by linux page table layout.
+ * For now we have
+ * Radix: 2M
+ * Hash: 16M and 16G
+ */
+ if (radix_enabled()) {
+ if (mmu_psize != MMU_PAGE_2M)
+ return -EINVAL;
+ } else {
+ if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G)
+ return -EINVAL;
+ }
+#endif
+
BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
/* Return if huge page size has already been setup */
diff --git a/arch/powerpc/mm/icswx.c b/arch/powerpc/mm/icswx.c
index 915412e4d5ba..1fa794d7d59f 100644
--- a/arch/powerpc/mm/icswx.c
+++ b/arch/powerpc/mm/icswx.c
@@ -186,7 +186,7 @@ static u32 acop_get_inst(struct pt_regs *regs)
}
/**
- * @regs: regsiters at time of interrupt
+ * @regs: registers at time of interrupt
* @address: storage address
* @error_code: Fault code, usually the DSISR or ESR depending on
* processor type
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6aa3b76aa0d6..ec84b31c6c86 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -71,10 +71,6 @@
#if H_PGTABLE_RANGE > USER_VSID_RANGE
#warning Limited user VSID range means pagetable space is wasted
#endif
-
-#if (TASK_SIZE_USER64 < H_PGTABLE_RANGE) && (TASK_SIZE_USER64 < USER_VSID_RANGE)
-#warning TASK_SIZE is smaller than it needs to be.
-#endif
#endif /* CONFIG_PPC_STD_MMU_64 */
phys_addr_t memstart_addr = ~0;
@@ -356,25 +352,48 @@ static void early_check_vec5(void)
unsigned long root, chosen;
int size;
const u8 *vec5;
+ u8 mmu_supported;
root = of_get_flat_dt_root();
chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
- if (chosen == -FDT_ERR_NOTFOUND)
+ if (chosen == -FDT_ERR_NOTFOUND) {
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
return;
+ }
vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
- if (!vec5)
+ if (!vec5) {
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
return;
- if (size <= OV5_INDX(OV5_MMU_RADIX_300) ||
- !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300)))
- /* Hypervisor doesn't support radix */
+ }
+ if (size <= OV5_INDX(OV5_MMU_SUPPORT)) {
cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+ return;
+ }
+
+ /* Check for supported configuration */
+ mmu_supported = vec5[OV5_INDX(OV5_MMU_SUPPORT)] &
+ OV5_FEAT(OV5_MMU_SUPPORT);
+ if (mmu_supported == OV5_FEAT(OV5_MMU_RADIX)) {
+ /* Hypervisor only supports radix - check enabled && GTSE */
+ if (!early_radix_enabled()) {
+ pr_warn("WARNING: Ignoring cmdline option disable_radix\n");
+ }
+ if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
+ OV5_FEAT(OV5_RADIX_GTSE))) {
+ pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
+ }
+ /* 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;
+ }
}
void __init mmu_early_init_devtree(void)
{
/* Disable radix mode based on kernel command line. */
- /* We don't yet have the machinery to do radix as a guest. */
- if (disable_radix || !(mfmsr() & MSR_HV))
+ if (disable_radix)
cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
/*
@@ -383,7 +402,7 @@ void __init mmu_early_init_devtree(void)
* even though the ibm,architecture-vec-5 property created by
* skiboot doesn't have the necessary bits set.
*/
- if (early_radix_enabled() && !(mfmsr() & MSR_HV))
+ if (!(mfmsr() & MSR_HV))
early_check_vec5();
if (early_radix_enabled())
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index a5d9ef59debe..9dbd2a733d6b 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -59,13 +59,14 @@ static inline int mmap_is_legacy(void)
unsigned long arch_mmap_rnd(void)
{
- unsigned long rnd;
+ unsigned long shift, rnd;
- /* 8MB for 32bit, 1GB for 64bit */
+ shift = mmap_rnd_bits;
+#ifdef CONFIG_COMPAT
if (is_32bit_task())
- rnd = get_random_long() % (1<<(23-PAGE_SHIFT));
- else
- rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT));
+ shift = mmap_rnd_compat_bits;
+#endif
+ rnd = get_random_long() % (1ul << shift);
return rnd << PAGE_SHIFT;
}
@@ -79,7 +80,7 @@ static inline unsigned long mmap_base(unsigned long rnd)
else if (gap > MAX_GAP)
gap = MAX_GAP;
- return PAGE_ALIGN(TASK_SIZE - gap - rnd);
+ return PAGE_ALIGN(DEFAULT_MAP_WINDOW - gap - rnd);
}
#ifdef CONFIG_PPC_RADIX_MMU
@@ -97,7 +98,11 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr,
struct vm_area_struct *vma;
struct vm_unmapped_area_info info;
- if (len > TASK_SIZE - mmap_min_addr)
+ if (unlikely(addr > mm->context.addr_limit &&
+ mm->context.addr_limit != TASK_SIZE))
+ mm->context.addr_limit = TASK_SIZE;
+
+ if (len > mm->task_size - mmap_min_addr)
return -ENOMEM;
if (flags & MAP_FIXED)
@@ -106,7 +111,7 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr,
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
+ if (mm->task_size - len >= addr && addr >= mmap_min_addr &&
(!vma || addr + len <= vma->vm_start))
return addr;
}
@@ -114,8 +119,13 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr,
info.flags = 0;
info.length = len;
info.low_limit = mm->mmap_base;
- info.high_limit = TASK_SIZE;
info.align_mask = 0;
+
+ if (unlikely(addr > DEFAULT_MAP_WINDOW))
+ info.high_limit = mm->context.addr_limit;
+ else
+ info.high_limit = DEFAULT_MAP_WINDOW;
+
return vm_unmapped_area(&info);
}
@@ -131,8 +141,12 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
unsigned long addr = addr0;
struct vm_unmapped_area_info info;
+ if (unlikely(addr > mm->context.addr_limit &&
+ mm->context.addr_limit != TASK_SIZE))
+ mm->context.addr_limit = TASK_SIZE;
+
/* requested length too big for entire address space */
- if (len > TASK_SIZE - mmap_min_addr)
+ if (len > mm->task_size - mmap_min_addr)
return -ENOMEM;
if (flags & MAP_FIXED)
@@ -142,7 +156,7 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
+ if (mm->task_size - len >= addr && addr >= mmap_min_addr &&
(!vma || addr + len <= vma->vm_start))
return addr;
}
@@ -152,7 +166,14 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
info.low_limit = max(PAGE_SIZE, mmap_min_addr);
info.high_limit = mm->mmap_base;
info.align_mask = 0;
+
+ if (addr > DEFAULT_MAP_WINDOW)
+ info.high_limit += mm->context.addr_limit - DEFAULT_MAP_WINDOW;
+
addr = vm_unmapped_area(&info);
+ if (!(addr & ~PAGE_MASK))
+ return addr;
+ VM_BUG_ON(addr != -ENOMEM);
/*
* A failed mmap() very likely causes application failure,
@@ -160,15 +181,7 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
* can happen with large stack limits and large mmap()
* allocations.
*/
- if (addr & ~PAGE_MASK) {
- VM_BUG_ON(addr != -ENOMEM);
- info.flags = 0;
- info.low_limit = TASK_UNMAPPED_BASE;
- info.high_limit = TASK_SIZE;
- addr = vm_unmapped_area(&info);
- }
-
- return addr;
+ return radix__arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
}
static void radix__arch_pick_mmap_layout(struct mm_struct *mm,
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 73bf6e14c3aa..c6dca2ae78ef 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -30,17 +30,16 @@
static DEFINE_SPINLOCK(mmu_context_lock);
static DEFINE_IDA(mmu_context_ida);
-int __init_new_context(void)
+static int alloc_context_id(int min_id, int max_id)
{
- int index;
- int err;
+ int index, err;
again:
if (!ida_pre_get(&mmu_context_ida, GFP_KERNEL))
return -ENOMEM;
spin_lock(&mmu_context_lock);
- err = ida_get_new_above(&mmu_context_ida, 1, &index);
+ err = ida_get_new_above(&mmu_context_ida, min_id, &index);
spin_unlock(&mmu_context_lock);
if (err == -EAGAIN)
@@ -48,7 +47,7 @@ again:
else if (err)
return err;
- if (index > MAX_USER_CONTEXT) {
+ if (index > max_id) {
spin_lock(&mmu_context_lock);
ida_remove(&mmu_context_ida, index);
spin_unlock(&mmu_context_lock);
@@ -57,48 +56,105 @@ again:
return index;
}
-EXPORT_SYMBOL_GPL(__init_new_context);
-static int radix__init_new_context(struct mm_struct *mm, int index)
+
+void hash__reserve_context_id(int id)
+{
+ int rc, result = 0;
+
+ do {
+ if (!ida_pre_get(&mmu_context_ida, GFP_KERNEL))
+ break;
+
+ spin_lock(&mmu_context_lock);
+ rc = ida_get_new_above(&mmu_context_ida, id, &result);
+ spin_unlock(&mmu_context_lock);
+ } while (rc == -EAGAIN);
+
+ WARN(result != id, "mmu: Failed to reserve context id %d (rc %d)\n", id, result);
+}
+
+int hash__alloc_context_id(void)
+{
+ unsigned long max;
+
+ if (mmu_has_feature(MMU_FTR_68_BIT_VA))
+ max = MAX_USER_CONTEXT;
+ else
+ max = MAX_USER_CONTEXT_65BIT_VA;
+
+ return alloc_context_id(MIN_USER_CONTEXT, max);
+}
+EXPORT_SYMBOL_GPL(hash__alloc_context_id);
+
+static int hash__init_new_context(struct mm_struct *mm)
+{
+ int index;
+
+ index = hash__alloc_context_id();
+ if (index < 0)
+ return index;
+
+ /*
+ * We do switch_slb() early in fork, even before we setup the
+ * mm->context.addr_limit. Default to max task size so that we copy the
+ * default values to paca which will help us to handle slb miss early.
+ */
+ mm->context.addr_limit = TASK_SIZE_128TB;
+
+ /*
+ * The old code would re-promote on fork, we don't do that when using
+ * slices as it could cause problem promoting slices that have been
+ * forced down to 4K.
+ *
+ * For book3s we have MMU_NO_CONTEXT set to be ~0. Hence check
+ * explicitly against context.id == 0. This ensures that we properly
+ * initialize context slice details for newly allocated mm's (which will
+ * have id == 0) and don't alter context slice inherited via fork (which
+ * will have id != 0).
+ *
+ * We should not be calling init_new_context() on init_mm. Hence a
+ * check against 0 is OK.
+ */
+ if (mm->context.id == 0)
+ slice_set_user_psize(mm, mmu_virtual_psize);
+
+ subpage_prot_init_new_context(mm);
+
+ return index;
+}
+
+static int radix__init_new_context(struct mm_struct *mm)
{
unsigned long rts_field;
+ int index;
+
+ index = alloc_context_id(1, PRTB_ENTRIES - 1);
+ if (index < 0)
+ return index;
/*
* set the process table entry,
*/
rts_field = radix__get_tree_size();
process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE);
- return 0;
+
+ mm->context.npu_context = NULL;
+
+ return index;
}
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
int index;
- index = __init_new_context();
+ if (radix_enabled())
+ index = radix__init_new_context(mm);
+ else
+ index = hash__init_new_context(mm);
+
if (index < 0)
return index;
- if (radix_enabled()) {
- radix__init_new_context(mm, index);
- } else {
-
- /* The old code would re-promote on fork, we don't do that
- * when using slices as it could cause problem promoting slices
- * that have been forced down to 4K
- *
- * For book3s we have MMU_NO_CONTEXT set to be ~0. Hence check
- * explicitly against context.id == 0. This ensures that we
- * properly initialize context slice details for newly allocated
- * mm's (which will have id == 0) and don't alter context slice
- * inherited via fork (which will have id != 0).
- *
- * We should not be calling init_new_context() on init_mm. Hence a
- * check against 0 is ok.
- */
- if (mm->context.id == 0)
- slice_set_user_psize(mm, mmu_virtual_psize);
- subpage_prot_init_new_context(mm);
- }
mm->context.id = index;
#ifdef CONFIG_PPC_ICSWX
mm->context.cop_lockp = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 497130c5c742..e0a2d8e806ed 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -81,7 +81,7 @@ struct page *new_iommu_non_cma_page(struct page *page, unsigned long private,
gfp_t gfp_mask = GFP_USER;
struct page *new_page;
- if (PageHuge(page) || PageTransHuge(page) || PageCompound(page))
+ if (PageCompound(page))
return NULL;
if (PageHighMem(page))
@@ -100,7 +100,7 @@ static int mm_iommu_move_page_from_cma(struct page *page)
LIST_HEAD(cma_migrate_pages);
/* Ignore huge pages for now */
- if (PageHuge(page) || PageTransHuge(page) || PageCompound(page))
+ if (PageCompound(page))
return -EBUSY;
lru_add_drain();
@@ -314,6 +314,25 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
}
EXPORT_SYMBOL_GPL(mm_iommu_lookup);
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
+ unsigned long ua, unsigned long size)
+{
+ struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+ list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list,
+ next) {
+ if ((mem->ua <= ua) &&
+ (ua + size <= mem->ua +
+ (mem->entries << PAGE_SHIFT))) {
+ ret = mem;
+ break;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm);
+
struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
unsigned long ua, unsigned long entries)
{
@@ -345,6 +364,26 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
}
EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
+long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+ unsigned long ua, unsigned long *hpa)
+{
+ const long entry = (ua - mem->ua) >> PAGE_SHIFT;
+ void *va = &mem->hpas[entry];
+ unsigned long *pa;
+
+ if (entry >= mem->entries)
+ return -EFAULT;
+
+ pa = (void *) vmalloc_to_phys(va);
+ if (!pa)
+ return -EFAULT;
+
+ *hpa = *pa | (ua & ~PAGE_MASK);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm);
+
long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
{
if (atomic64_inc_not_zero(&mem->mapped))
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index c491f2c8f2b9..4554d6527682 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -333,11 +333,6 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm)
mm->context.id = MMU_NO_CONTEXT;
mm->context.active = 0;
-
-#ifdef CONFIG_PPC_MM_SLICES
- slice_set_user_psize(mm, mmu_virtual_psize);
-#endif
-
return 0;
}
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9befaee237d6..371792e4418f 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -875,13 +875,6 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
void *nd;
int tnid;
- if (spanned_pages)
- pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
- nid, start_pfn << PAGE_SHIFT,
- (end_pfn << PAGE_SHIFT) - 1);
- else
- pr_info("Initmem setup node %d\n", nid);
-
nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
nd = __va(nd_pa);
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 2a590a98e652..c28165d8970b 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -186,6 +186,10 @@ static void __init radix_init_pgtable(void)
*/
register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
+ asm volatile("ptesync" : : : "memory");
+ asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+ "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
+ asm volatile("eieio; tlbsync; ptesync" : : : "memory");
}
static void __init radix_init_partition_table(void)
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 5e01b2ece1d0..654a0d7ba0e7 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -131,7 +131,7 @@ static void __slb_flush_and_rebolt(void)
"slbmte %2,%3\n"
"isync"
:: "r"(mk_vsid_data(VMALLOC_START, mmu_kernel_ssize, vflags)),
- "r"(mk_esid_data(VMALLOC_START, mmu_kernel_ssize, 1)),
+ "r"(mk_esid_data(VMALLOC_START, mmu_kernel_ssize, VMALLOC_INDEX)),
"r"(ksp_vsid_data),
"r"(ksp_esid_data)
: "memory");
@@ -229,7 +229,7 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
asm volatile("slbie %0" : : "r" (slbie_data));
get_paca()->slb_cache_ptr = 0;
- copy_mm_to_paca(&mm->context);
+ copy_mm_to_paca(mm);
/*
* preload some userspace segments into the SLB.
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index a85e06ea6c20..1519617aab36 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -23,6 +23,48 @@
#include <asm/pgtable.h>
#include <asm/firmware.h>
+/*
+ * This macro generates asm code to compute the VSID scramble
+ * function. Used in slb_allocate() and do_stab_bolted. The function
+ * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
+ *
+ * rt = register containing the proto-VSID and into which the
+ * VSID will be stored
+ * rx = scratch register (clobbered)
+ * rf = flags
+ *
+ * - rt and rx must be different registers
+ * - The answer will end up in the low VSID_BITS bits of rt. The higher
+ * bits may contain other garbage, so you may need to mask the
+ * result.
+ */
+#define ASM_VSID_SCRAMBLE(rt, rx, rf, size) \
+ lis rx,VSID_MULTIPLIER_##size@h; \
+ ori rx,rx,VSID_MULTIPLIER_##size@l; \
+ mulld rt,rt,rx; /* rt = rt * MULTIPLIER */ \
+/* \
+ * powermac get slb fault before feature fixup, so make 65 bit part \
+ * the default part of feature fixup \
+ */ \
+BEGIN_MMU_FTR_SECTION \
+ srdi rx,rt,VSID_BITS_65_##size; \
+ clrldi rt,rt,(64-VSID_BITS_65_##size); \
+ add rt,rt,rx; \
+ addi rx,rt,1; \
+ srdi rx,rx,VSID_BITS_65_##size; \
+ add rt,rt,rx; \
+ rldimi rf,rt,SLB_VSID_SHIFT_##size,(64 - (SLB_VSID_SHIFT_##size + VSID_BITS_65_##size)); \
+MMU_FTR_SECTION_ELSE \
+ srdi rx,rt,VSID_BITS_##size; \
+ clrldi rt,rt,(64-VSID_BITS_##size); \
+ add rt,rt,rx; /* add high and low bits */ \
+ addi rx,rt,1; \
+ srdi rx,rx,VSID_BITS_##size; /* extract 2^VSID_BITS bit */ \
+ add rt,rt,rx; \
+ rldimi rf,rt,SLB_VSID_SHIFT_##size,(64 - (SLB_VSID_SHIFT_##size + VSID_BITS_##size)); \
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_68_BIT_VA)
+
+
/* void slb_allocate_realmode(unsigned long ea);
*
* Create an SLB entry for the given EA (user or kernel).
@@ -45,13 +87,6 @@ _GLOBAL(slb_allocate_realmode)
/* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */
blt cr7,0f /* user or kernel? */
- /* kernel address: proto-VSID = ESID */
- /* WARNING - MAGIC: we don't use the VSID 0xfffffffff, but
- * this code will generate the protoVSID 0xfffffffff for the
- * top segment. That's ok, the scramble below will translate
- * it to VSID 0, which is reserved as a bad VSID - one which
- * will never have any pages in it. */
-
/* Check if hitting the linear mapping or some other kernel space
*/
bne cr7,1f
@@ -63,12 +98,10 @@ _GLOBAL(slb_allocate_realmode)
slb_miss_kernel_load_linear:
li r11,0
/*
- * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+ * context = (ea >> 60) - (0xc - 1)
* r9 = region id.
*/
- addis r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha
- addi r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l
-
+ subi r9,r9,KERNEL_REGION_CONTEXT_OFFSET
BEGIN_FTR_SECTION
b .Lslb_finish_load
@@ -77,9 +110,9 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
1:
#ifdef CONFIG_SPARSEMEM_VMEMMAP
- /* Check virtual memmap region. To be patches at kernel boot */
cmpldi cr0,r9,0xf
bne 1f
+/* Check virtual memmap region. To be patched at kernel boot */
.globl slb_miss_kernel_load_vmemmap
slb_miss_kernel_load_vmemmap:
li r11,0
@@ -102,11 +135,10 @@ slb_miss_kernel_load_io:
li r11,0
6:
/*
- * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+ * context = (ea >> 60) - (0xc - 1)
* r9 = region id.
*/
- addis r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha
- addi r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l
+ subi r9,r9,KERNEL_REGION_CONTEXT_OFFSET
BEGIN_FTR_SECTION
b .Lslb_finish_load
@@ -117,7 +149,13 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
* For userspace addresses, make sure this is region 0.
*/
cmpdi r9, 0
- bne 8f
+ bne- 8f
+ /*
+ * user space make sure we are within the allowed limit
+ */
+ ld r11,PACA_ADDR_LIMIT(r13)
+ cmpld r3,r11
+ bge- 8f
/* when using slices, we extract the psize off the slice bitmaps
* and then we need to get the sllp encoding off the mmu_psize_defs
@@ -189,13 +227,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
*/
.Lslb_finish_load:
rldimi r10,r9,ESID_BITS,0
- ASM_VSID_SCRAMBLE(r10,r9,256M)
- /*
- * bits above VSID_BITS_256M need to be ignored from r10
- * also combine VSID and flags
- */
- rldimi r11,r10,SLB_VSID_SHIFT,(64 - (SLB_VSID_SHIFT + VSID_BITS_256M))
-
+ ASM_VSID_SCRAMBLE(r10,r9,r11,256M)
/* r3 = EA, r11 = VSID data */
/*
* Find a slot, round robin. Previously we tried to find a
@@ -259,12 +291,12 @@ slb_compare_rr_to_size:
.Lslb_finish_load_1T:
srdi r10,r10,(SID_SHIFT_1T - SID_SHIFT) /* get 1T ESID */
rldimi r10,r9,ESID_BITS_1T,0
- ASM_VSID_SCRAMBLE(r10,r9,1T)
+ ASM_VSID_SCRAMBLE(r10,r9,r11,1T)
/*
* bits above VSID_BITS_1T need to be ignored from r10
* also combine VSID and flags
*/
- rldimi r11,r10,SLB_VSID_SHIFT_1T,(64 - (SLB_VSID_SHIFT_1T + VSID_BITS_1T))
+
li r10,MMU_SEGSIZE_1T
rldimi r11,r10,SLB_VSID_SSIZE_SHIFT,0 /* insert segment size */
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 2b27458902ee..966b9fccfa66 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -36,38 +36,29 @@
#include <asm/copro.h>
#include <asm/hugetlb.h>
-/* some sanity checks */
-#if (H_PGTABLE_RANGE >> 43) > SLICE_MASK_SIZE
-#error H_PGTABLE_RANGE exceeds slice_mask high_slices size
-#endif
-
static DEFINE_SPINLOCK(slice_convert_lock);
-
+/*
+ * One bit per slice. We have lower slices which cover 256MB segments
+ * upto 4G range. That gets us 16 low slices. For the rest we track slices
+ * in 1TB size.
+ */
+struct slice_mask {
+ u64 low_slices;
+ DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
+};
#ifdef DEBUG
int _slice_debug = 1;
static void slice_print_mask(const char *label, struct slice_mask mask)
{
- char *p, buf[16 + 3 + 64 + 1];
- int i;
-
if (!_slice_debug)
return;
- p = buf;
- for (i = 0; i < SLICE_NUM_LOW; i++)
- *(p++) = (mask.low_slices & (1 << i)) ? '1' : '0';
- *(p++) = ' ';
- *(p++) = '-';
- *(p++) = ' ';
- for (i = 0; i < SLICE_NUM_HIGH; i++)
- *(p++) = (mask.high_slices & (1ul << i)) ? '1' : '0';
- *(p++) = 0;
-
- printk(KERN_DEBUG "%s:%s\n", label, buf);
+ pr_devel("%s low_slice: %*pbl\n", label, (int)SLICE_NUM_LOW, &mask.low_slices);
+ pr_devel("%s high_slice: %*pbl\n", label, (int)SLICE_NUM_HIGH, mask.high_slices);
}
-#define slice_dbg(fmt...) do { if (_slice_debug) pr_debug(fmt); } while(0)
+#define slice_dbg(fmt...) do { if (_slice_debug) pr_devel(fmt); } while (0)
#else
@@ -76,25 +67,28 @@ static void slice_print_mask(const char *label, struct slice_mask mask) {}
#endif
-static struct slice_mask slice_range_to_mask(unsigned long start,
- unsigned long len)
+static void slice_range_to_mask(unsigned long start, unsigned long len,
+ struct slice_mask *ret)
{
unsigned long end = start + len - 1;
- struct slice_mask ret = { 0, 0 };
+
+ ret->low_slices = 0;
+ bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
if (start < SLICE_LOW_TOP) {
- unsigned long mend = min(end, SLICE_LOW_TOP);
- unsigned long mstart = min(start, SLICE_LOW_TOP);
+ unsigned long mend = min(end, (SLICE_LOW_TOP - 1));
- ret.low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
- - (1u << GET_LOW_SLICE_INDEX(mstart));
+ ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
+ - (1u << GET_LOW_SLICE_INDEX(start));
}
- if ((start + len) > SLICE_LOW_TOP)
- ret.high_slices = (1ul << (GET_HIGH_SLICE_INDEX(end) + 1))
- - (1ul << GET_HIGH_SLICE_INDEX(start));
+ if ((start + len) > SLICE_LOW_TOP) {
+ unsigned long start_index = GET_HIGH_SLICE_INDEX(start);
+ unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
+ unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;
- return ret;
+ bitmap_set(ret->high_slices, start_index, count);
+ }
}
static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
@@ -128,53 +122,60 @@ static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice)
return !slice_area_is_free(mm, start, end - start);
}
-static struct slice_mask slice_mask_for_free(struct mm_struct *mm)
+static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret)
{
- struct slice_mask ret = { 0, 0 };
unsigned long i;
+ ret->low_slices = 0;
+ bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+
for (i = 0; i < SLICE_NUM_LOW; i++)
if (!slice_low_has_vma(mm, i))
- ret.low_slices |= 1u << i;
+ ret->low_slices |= 1u << i;
if (mm->task_size <= SLICE_LOW_TOP)
- return ret;
+ return;
- for (i = 0; i < SLICE_NUM_HIGH; i++)
+ for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++)
if (!slice_high_has_vma(mm, i))
- ret.high_slices |= 1ul << i;
-
- return ret;
+ __set_bit(i, ret->high_slices);
}
-static struct slice_mask slice_mask_for_size(struct mm_struct *mm, int psize)
+static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret)
{
unsigned char *hpsizes;
int index, mask_index;
- struct slice_mask ret = { 0, 0 };
unsigned long i;
u64 lpsizes;
+ ret->low_slices = 0;
+ bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+
lpsizes = mm->context.low_slices_psize;
for (i = 0; i < SLICE_NUM_LOW; i++)
if (((lpsizes >> (i * 4)) & 0xf) == psize)
- ret.low_slices |= 1u << i;
+ ret->low_slices |= 1u << i;
hpsizes = mm->context.high_slices_psize;
- for (i = 0; i < SLICE_NUM_HIGH; i++) {
+ for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) {
mask_index = i & 0x1;
index = i >> 1;
if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize)
- ret.high_slices |= 1ul << i;
+ __set_bit(i, ret->high_slices);
}
-
- return ret;
}
-static int slice_check_fit(struct slice_mask mask, struct slice_mask available)
+static int slice_check_fit(struct mm_struct *mm,
+ struct slice_mask mask, struct slice_mask available)
{
+ DECLARE_BITMAP(result, SLICE_NUM_HIGH);
+ unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.addr_limit);
+
+ bitmap_and(result, mask.high_slices,
+ available.high_slices, slice_count);
+
return (mask.low_slices & available.low_slices) == mask.low_slices &&
- (mask.high_slices & available.high_slices) == mask.high_slices;
+ bitmap_equal(result, mask.high_slices, slice_count);
}
static void slice_flush_segments(void *parm)
@@ -185,7 +186,7 @@ static void slice_flush_segments(void *parm)
if (mm != current->active_mm)
return;
- copy_mm_to_paca(&current->active_mm->context);
+ copy_mm_to_paca(current->active_mm);
local_irq_save(flags);
slb_flush_and_rebolt();
@@ -218,18 +219,18 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
mm->context.low_slices_psize = lpsizes;
hpsizes = mm->context.high_slices_psize;
- for (i = 0; i < SLICE_NUM_HIGH; i++) {
+ for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) {
mask_index = i & 0x1;
index = i >> 1;
- if (mask.high_slices & (1ul << i))
+ if (test_bit(i, mask.high_slices))
hpsizes[index] = (hpsizes[index] &
~(0xf << (mask_index * 4))) |
(((unsigned long)psize) << (mask_index * 4));
}
slice_dbg(" lsps=%lx, hsps=%lx\n",
- mm->context.low_slices_psize,
- mm->context.high_slices_psize);
+ (unsigned long)mm->context.low_slices_psize,
+ (unsigned long)mm->context.high_slices_psize);
spin_unlock_irqrestore(&slice_convert_lock, flags);
@@ -257,14 +258,14 @@ static bool slice_scan_available(unsigned long addr,
slice = GET_HIGH_SLICE_INDEX(addr);
*boundary_addr = (slice + end) ?
((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
- return !!(available.high_slices & (1ul << slice));
+ return !!test_bit(slice, available.high_slices);
}
}
static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
unsigned long len,
struct slice_mask available,
- int psize)
+ int psize, unsigned long high_limit)
{
int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
unsigned long addr, found, next_end;
@@ -276,7 +277,10 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
info.align_offset = 0;
addr = TASK_UNMAPPED_BASE;
- while (addr < TASK_SIZE) {
+ /*
+ * Check till the allow max value for this mmap request
+ */
+ while (addr < high_limit) {
info.low_limit = addr;
if (!slice_scan_available(addr, available, 1, &addr))
continue;
@@ -288,8 +292,8 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
* Check if we need to reduce the range, or if we can
* extend it to cover the next available slice.
*/
- if (addr >= TASK_SIZE)
- addr = TASK_SIZE;
+ if (addr >= high_limit)
+ addr = high_limit;
else if (slice_scan_available(addr, available, 1, &next_end)) {
addr = next_end;
goto next_slice;
@@ -307,7 +311,7 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
static unsigned long slice_find_area_topdown(struct mm_struct *mm,
unsigned long len,
struct slice_mask available,
- int psize)
+ int psize, unsigned long high_limit)
{
int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
unsigned long addr, found, prev;
@@ -319,6 +323,15 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
info.align_offset = 0;
addr = mm->mmap_base;
+ /*
+ * If we are trying to allocate above DEFAULT_MAP_WINDOW
+ * Add the different to the mmap_base.
+ * Only for that request for which high_limit is above
+ * DEFAULT_MAP_WINDOW we should apply this.
+ */
+ if (high_limit > DEFAULT_MAP_WINDOW)
+ addr += mm->context.addr_limit - DEFAULT_MAP_WINDOW;
+
while (addr > PAGE_SIZE) {
info.high_limit = addr;
if (!slice_scan_available(addr - 1, available, 0, &addr))
@@ -350,29 +363,38 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
* can happen with large stack limits and large mmap()
* allocations.
*/
- return slice_find_area_bottomup(mm, len, available, psize);
+ return slice_find_area_bottomup(mm, len, available, psize, high_limit);
}
static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
struct slice_mask mask, int psize,
- int topdown)
+ int topdown, unsigned long high_limit)
{
if (topdown)
- return slice_find_area_topdown(mm, len, mask, psize);
+ return slice_find_area_topdown(mm, len, mask, psize, high_limit);
else
- return slice_find_area_bottomup(mm, len, mask, psize);
+ return slice_find_area_bottomup(mm, len, mask, psize, high_limit);
}
-#define or_mask(dst, src) do { \
- (dst).low_slices |= (src).low_slices; \
- (dst).high_slices |= (src).high_slices; \
-} while (0)
+static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src)
+{
+ DECLARE_BITMAP(result, SLICE_NUM_HIGH);
+
+ dst->low_slices |= src->low_slices;
+ bitmap_or(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
+ bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+}
-#define andnot_mask(dst, src) do { \
- (dst).low_slices &= ~(src).low_slices; \
- (dst).high_slices &= ~(src).high_slices; \
-} while (0)
+static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src)
+{
+ DECLARE_BITMAP(result, SLICE_NUM_HIGH);
+
+ dst->low_slices &= ~src->low_slices;
+
+ bitmap_andnot(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
+ bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+}
#ifdef CONFIG_PPC_64K_PAGES
#define MMU_PAGE_BASE MMU_PAGE_64K
@@ -384,14 +406,43 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
unsigned long flags, unsigned int psize,
int topdown)
{
- struct slice_mask mask = {0, 0};
+ struct slice_mask mask;
struct slice_mask good_mask;
- struct slice_mask potential_mask = {0,0} /* silence stupid warning */;
- struct slice_mask compat_mask = {0, 0};
+ struct slice_mask potential_mask;
+ struct slice_mask compat_mask;
int fixed = (flags & MAP_FIXED);
int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
struct mm_struct *mm = current->mm;
unsigned long newaddr;
+ unsigned long high_limit;
+
+ /*
+ * Check if we need to expland slice area.
+ */
+ if (unlikely(addr > mm->context.addr_limit &&
+ mm->context.addr_limit != TASK_SIZE)) {
+ mm->context.addr_limit = TASK_SIZE;
+ on_each_cpu(slice_flush_segments, mm, 1);
+ }
+ /*
+ * This mmap request can allocate upt to 512TB
+ */
+ if (addr > DEFAULT_MAP_WINDOW)
+ high_limit = mm->context.addr_limit;
+ else
+ high_limit = DEFAULT_MAP_WINDOW;
+ /*
+ * init different masks
+ */
+ mask.low_slices = 0;
+ bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
+
+ /* silence stupid warning */;
+ potential_mask.low_slices = 0;
+ bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
+
+ compat_mask.low_slices = 0;
+ bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
/* Sanity checks */
BUG_ON(mm->task_size == 0);
@@ -423,7 +474,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
/* First make up a "good" mask of slices that have the right size
* already
*/
- good_mask = slice_mask_for_size(mm, psize);
+ slice_mask_for_size(mm, psize, &good_mask);
slice_print_mask(" good_mask", good_mask);
/*
@@ -448,22 +499,22 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
#ifdef CONFIG_PPC_64K_PAGES
/* If we support combo pages, we can allow 64k pages in 4k slices */
if (psize == MMU_PAGE_64K) {
- compat_mask = slice_mask_for_size(mm, MMU_PAGE_4K);
+ slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask);
if (fixed)
- or_mask(good_mask, compat_mask);
+ slice_or_mask(&good_mask, &compat_mask);
}
#endif
/* First check hint if it's valid or if we have MAP_FIXED */
if (addr != 0 || fixed) {
/* Build a mask for the requested range */
- mask = slice_range_to_mask(addr, len);
+ slice_range_to_mask(addr, len, &mask);
slice_print_mask(" mask", mask);
/* Check if we fit in the good mask. If we do, we just return,
* nothing else to do
*/
- if (slice_check_fit(mask, good_mask)) {
+ if (slice_check_fit(mm, mask, good_mask)) {
slice_dbg(" fits good !\n");
return addr;
}
@@ -471,7 +522,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
/* Now let's see if we can find something in the existing
* slices for that size
*/
- newaddr = slice_find_area(mm, len, good_mask, psize, topdown);
+ newaddr = slice_find_area(mm, len, good_mask,
+ psize, topdown, high_limit);
if (newaddr != -ENOMEM) {
/* Found within the good mask, we don't have to setup,
* we thus return directly
@@ -484,11 +536,11 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
/* We don't fit in the good mask, check what other slices are
* empty and thus can be converted
*/
- potential_mask = slice_mask_for_free(mm);
- or_mask(potential_mask, good_mask);
+ slice_mask_for_free(mm, &potential_mask);
+ slice_or_mask(&potential_mask, &good_mask);
slice_print_mask(" potential", potential_mask);
- if ((addr != 0 || fixed) && slice_check_fit(mask, potential_mask)) {
+ if ((addr != 0 || fixed) && slice_check_fit(mm, mask, potential_mask)) {
slice_dbg(" fits potential !\n");
goto convert;
}
@@ -503,7 +555,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
* anywhere in the good area.
*/
if (addr) {
- addr = slice_find_area(mm, len, good_mask, psize, topdown);
+ addr = slice_find_area(mm, len, good_mask,
+ psize, topdown, high_limit);
if (addr != -ENOMEM) {
slice_dbg(" found area at 0x%lx\n", addr);
return addr;
@@ -513,28 +566,29 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
/* Now let's see if we can find something in the existing slices
* for that size plus free slices
*/
- addr = slice_find_area(mm, len, potential_mask, psize, topdown);
+ addr = slice_find_area(mm, len, potential_mask,
+ psize, topdown, high_limit);
#ifdef CONFIG_PPC_64K_PAGES
if (addr == -ENOMEM && psize == MMU_PAGE_64K) {
/* retry the search with 4k-page slices included */
- or_mask(potential_mask, compat_mask);
- addr = slice_find_area(mm, len, potential_mask, psize,
- topdown);
+ slice_or_mask(&potential_mask, &compat_mask);
+ addr = slice_find_area(mm, len, potential_mask,
+ psize, topdown, high_limit);
}
#endif
if (addr == -ENOMEM)
return -ENOMEM;
- mask = slice_range_to_mask(addr, len);
+ slice_range_to_mask(addr, len, &mask);
slice_dbg(" found potential area at 0x%lx\n", addr);
slice_print_mask(" mask", mask);
convert:
- andnot_mask(mask, good_mask);
- andnot_mask(mask, compat_mask);
- if (mask.low_slices || mask.high_slices) {
+ slice_andnot_mask(&mask, &good_mask);
+ slice_andnot_mask(&mask, &compat_mask);
+ if (mask.low_slices || !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) {
slice_convert(mm, mask, psize);
if (psize > MMU_PAGE_BASE)
on_each_cpu(slice_flush_segments, mm, 1);
@@ -649,8 +703,8 @@ void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
slice_dbg(" lsps=%lx, hsps=%lx\n",
- mm->context.low_slices_psize,
- mm->context.high_slices_psize);
+ (unsigned long)mm->context.low_slices_psize,
+ (unsigned long)mm->context.high_slices_psize);
bail:
spin_unlock_irqrestore(&slice_convert_lock, flags);
@@ -659,9 +713,11 @@ void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
unsigned long len, unsigned int psize)
{
- struct slice_mask mask = slice_range_to_mask(start, len);
+ struct slice_mask mask;
VM_BUG_ON(radix_enabled());
+
+ slice_range_to_mask(start, len, &mask);
slice_convert(mm, mask, psize);
}
@@ -694,14 +750,14 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
if (radix_enabled())
return 0;
- mask = slice_range_to_mask(addr, len);
- available = slice_mask_for_size(mm, psize);
+ slice_range_to_mask(addr, len, &mask);
+ slice_mask_for_size(mm, psize, &available);
#ifdef CONFIG_PPC_64K_PAGES
/* We need to account for 4k slices too */
if (psize == MMU_PAGE_64K) {
struct slice_mask compat_mask;
- compat_mask = slice_mask_for_size(mm, MMU_PAGE_4K);
- or_mask(available, compat_mask);
+ slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask);
+ slice_or_mask(&available, &compat_mask);
}
#endif
@@ -711,6 +767,6 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
slice_print_mask(" mask", mask);
slice_print_mask(" available", available);
#endif
- return !slice_check_fit(mask, available);
+ return !slice_check_fit(mm, mask, available);
}
#endif
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index 94210940112f..e94fbd4c8845 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -197,7 +197,8 @@ long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map)
/* Check parameters */
if ((addr & ~PAGE_MASK) || (len & ~PAGE_MASK) ||
- addr >= TASK_SIZE || len >= TASK_SIZE || addr + len > TASK_SIZE)
+ addr >= mm->task_size || len >= mm->task_size ||
+ addr + len > mm->task_size)
return -EINVAL;
if (is_hugepage_only_range(mm, addr, len))
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 952713d6cf04..02e71402fdd3 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -17,7 +17,6 @@
#include <asm/tlb.h>
#include <asm/tlbflush.h>
-static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
#define RIC_FLUSH_TLB 0
#define RIC_FLUSH_PWC 1
@@ -34,10 +33,8 @@ static inline void __tlbiel_pid(unsigned long pid, int set,
prs = 1; /* process scoped */
r = 1; /* raidx format */
- asm volatile("ptesync": : :"memory");
asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
: : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
- asm volatile("ptesync": : :"memory");
}
/*
@@ -47,9 +44,33 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
{
int set;
- for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
+ asm volatile("ptesync": : :"memory");
+
+ /*
+ * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL,
+ * also flush the entire Page Walk Cache.
+ */
+ __tlbiel_pid(pid, 0, ric);
+
+ if (ric == RIC_FLUSH_ALL)
+ /* For the remaining sets, just flush the TLB */
+ ric = RIC_FLUSH_TLB;
+
+ for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
__tlbiel_pid(pid, set, ric);
- }
+
+ asm volatile("ptesync": : :"memory");
+ asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
+static inline void tlbiel_pwc(unsigned long pid)
+{
+ asm volatile("ptesync": : :"memory");
+
+ /* For PWC flush, we don't look at set number */
+ __tlbiel_pid(pid, 0, RIC_FLUSH_PWC);
+
+ asm volatile("ptesync": : :"memory");
asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
}
@@ -129,12 +150,18 @@ void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
{
unsigned long pid;
struct mm_struct *mm = tlb->mm;
+ /*
+ * If we are doing a full mm flush, we will do a tlb flush
+ * with RIC_FLUSH_ALL later.
+ */
+ if (tlb->fullmm)
+ return;
preempt_disable();
pid = mm->context.id;
if (pid != MMU_NO_CONTEXT)
- _tlbiel_pid(pid, RIC_FLUSH_PWC);
+ tlbiel_pwc(pid);
preempt_enable();
}
@@ -175,15 +202,9 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
if (unlikely(pid == MMU_NO_CONTEXT))
goto no_context;
- if (!mm_is_thread_local(mm)) {
- int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
-
- if (lock_tlbie)
- raw_spin_lock(&native_tlbie_lock);
+ if (!mm_is_thread_local(mm))
_tlbie_pid(pid, RIC_FLUSH_ALL);
- if (lock_tlbie)
- raw_spin_unlock(&native_tlbie_lock);
- } else
+ else
_tlbiel_pid(pid, RIC_FLUSH_ALL);
no_context:
preempt_enable();
@@ -195,22 +216,22 @@ void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
unsigned long pid;
struct mm_struct *mm = tlb->mm;
+ /*
+ * If we are doing a full mm flush, we will do a tlb flush
+ * with RIC_FLUSH_ALL later.
+ */
+ if (tlb->fullmm)
+ return;
preempt_disable();
pid = mm->context.id;
if (unlikely(pid == MMU_NO_CONTEXT))
goto no_context;
- if (!mm_is_thread_local(mm)) {
- int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
-
- if (lock_tlbie)
- raw_spin_lock(&native_tlbie_lock);
+ if (!mm_is_thread_local(mm))
_tlbie_pid(pid, RIC_FLUSH_PWC);
- if (lock_tlbie)
- raw_spin_unlock(&native_tlbie_lock);
- } else
- _tlbiel_pid(pid, RIC_FLUSH_PWC);
+ else
+ tlbiel_pwc(pid);
no_context:
preempt_enable();
}
@@ -226,15 +247,9 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
pid = mm ? mm->context.id : 0;
if (unlikely(pid == MMU_NO_CONTEXT))
goto bail;
- if (!mm_is_thread_local(mm)) {
- int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
-
- if (lock_tlbie)
- raw_spin_lock(&native_tlbie_lock);
+ if (!mm_is_thread_local(mm))
_tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
- if (lock_tlbie)
- raw_spin_unlock(&native_tlbie_lock);
- } else
+ else
_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
bail:
preempt_enable();
@@ -255,13 +270,7 @@ EXPORT_SYMBOL(radix__flush_tlb_page);
void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
-
- if (lock_tlbie)
- raw_spin_lock(&native_tlbie_lock);
_tlbie_pid(0, RIC_FLUSH_ALL);
- if (lock_tlbie)
- raw_spin_unlock(&native_tlbie_lock);
}
EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
@@ -323,7 +332,6 @@ void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
unsigned long addr;
int local = mm_is_thread_local(mm);
unsigned long ap = mmu_get_ap(psize);
- int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
unsigned long page_size = 1UL << mmu_psize_defs[psize].shift;
@@ -344,13 +352,8 @@ void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
if (local)
_tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
- else {
- if (lock_tlbie)
- raw_spin_lock(&native_tlbie_lock);
+ else
_tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
- if (lock_tlbie)
- raw_spin_unlock(&native_tlbie_lock);
- }
}
err_out:
preempt_enable();
@@ -437,7 +440,7 @@ void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
return;
}
- if (old_pte & _PAGE_LARGE)
+ if (old_pte & R_PAGE_LARGE)
radix__flush_tlb_page_psize(mm, address, MMU_PAGE_2M);
else
radix__flush_tlb_page_psize(mm, address, mmu_virtual_psize);
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index ba28fcb98597..bfc4a0869609 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -770,7 +770,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
* avoid going over total available memory just in case...
*/
#ifdef CONFIG_PPC_FSL_BOOK3E
- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+ if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
unsigned long linear_sz;
unsigned int num_cams;
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 595dd718ea87..6c2d4168daec 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -188,6 +188,8 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
sdsync = POWER7P_MMCRA_SDAR_VALID;
else if (ppmu->flags & PPMU_ALT_SIPR)
sdsync = POWER6_MMCRA_SDSYNC;
+ else if (ppmu->flags & PPMU_NO_SIAR)
+ sdsync = MMCRA_SAMPLE_ENABLE;
else
sdsync = MMCRA_SDSYNC;
@@ -2047,6 +2049,14 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
data.br_stack = &cpuhw->bhrb_stack;
}
+ if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
+ ppmu->get_mem_data_src)
+ ppmu->get_mem_data_src(&data.data_src, ppmu->flags, regs);
+
+ if (event->attr.sample_type & PERF_SAMPLE_WEIGHT &&
+ ppmu->get_mem_weight)
+ ppmu->get_mem_weight(&data.weight);
+
if (perf_event_overflow(event, &data, regs))
power_pmu_stop(event, 0);
}
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index e79fb5fb817d..8125160be7bc 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -65,12 +65,41 @@ static bool is_event_valid(u64 event)
return !(event & ~valid_mask);
}
-static u64 mmcra_sdar_mode(u64 event)
+static inline bool is_event_marked(u64 event)
{
- if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
- return p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+ if (event & EVENT_IS_MARKED)
+ return true;
+
+ return false;
+}
- return MMCRA_SDAR_MODE_TLB;
+static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
+{
+ /*
+ * MMCRA[SDAR_MODE] specifices how the SDAR should be updated in
+ * continous sampling mode.
+ *
+ * Incase of Power8:
+ * 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:
+ * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'),
+ * or if group already have any marked events.
+ * Non-Marked events (for DD1):
+ * MMCRA[SDAR_MODE] will be set to 0b01
+ * For rest
+ * MMCRA[SDAR_MODE] will be set from event code.
+ */
+ 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 (!cpu_has_feature(CPU_FTR_POWER9_DD1))
+ *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+ else if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+ *mmcra |= MMCRA_SDAR_MODE_TLB;
+ } else
+ *mmcra |= MMCRA_SDAR_MODE_TLB;
}
static u64 thresh_cmp_val(u64 value)
@@ -119,6 +148,88 @@ static bool is_thresh_cmp_valid(u64 event)
return true;
}
+static inline u64 isa207_find_source(u64 idx, u32 sub_idx)
+{
+ u64 ret = PERF_MEM_NA;
+
+ switch(idx) {
+ case 0:
+ /* Nothing to do */
+ break;
+ case 1:
+ ret = PH(LVL, L1);
+ break;
+ case 2:
+ ret = PH(LVL, L2);
+ break;
+ case 3:
+ ret = PH(LVL, L3);
+ break;
+ case 4:
+ if (sub_idx <= 1)
+ ret = PH(LVL, LOC_RAM);
+ else if (sub_idx > 1 && sub_idx <= 2)
+ ret = PH(LVL, REM_RAM1);
+ else
+ ret = PH(LVL, REM_RAM2);
+ ret |= P(SNOOP, HIT);
+ break;
+ case 5:
+ ret = PH(LVL, REM_CCE1);
+ if ((sub_idx == 0) || (sub_idx == 2) || (sub_idx == 4))
+ ret |= P(SNOOP, HIT);
+ else if ((sub_idx == 1) || (sub_idx == 3) || (sub_idx == 5))
+ ret |= P(SNOOP, HITM);
+ break;
+ case 6:
+ ret = PH(LVL, REM_CCE2);
+ if ((sub_idx == 0) || (sub_idx == 2))
+ ret |= P(SNOOP, HIT);
+ else if ((sub_idx == 1) || (sub_idx == 3))
+ ret |= P(SNOOP, HITM);
+ break;
+ case 7:
+ ret = PM(LVL, L1);
+ break;
+ }
+
+ return ret;
+}
+
+void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
+ struct pt_regs *regs)
+{
+ u64 idx;
+ u32 sub_idx;
+ u64 sier;
+ u64 val;
+
+ /* Skip if no SIER support */
+ if (!(flags & PPMU_HAS_SIER)) {
+ dsrc->val = 0;
+ return;
+ }
+
+ sier = mfspr(SPRN_SIER);
+ val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT;
+ if (val == 1 || val == 2) {
+ idx = (sier & ISA207_SIER_LDST_MASK) >> ISA207_SIER_LDST_SHIFT;
+ sub_idx = (sier & ISA207_SIER_DATA_SRC_MASK) >> ISA207_SIER_DATA_SRC_SHIFT;
+
+ dsrc->val = isa207_find_source(idx, sub_idx);
+ dsrc->val |= (val == 1) ? P(OP, LOAD) : P(OP, STORE);
+ }
+}
+
+void isa207_get_mem_weight(u64 *weight)
+{
+ u64 mmcra = mfspr(SPRN_MMCRA);
+ u64 exp = MMCRA_THR_CTR_EXP(mmcra);
+ u64 mantissa = MMCRA_THR_CTR_MANT(mmcra);
+
+ *weight = mantissa << (2 * exp);
+}
+
int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
{
unsigned int unit, pmc, cache, ebb;
@@ -180,7 +291,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
value |= CNST_L1_QUAL_VAL(cache);
}
- if (event & EVENT_IS_MARKED) {
+ if (is_event_marked(event)) {
mask |= CNST_SAMPLE_MASK;
value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
}
@@ -276,7 +387,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
}
/* In continuous sampling mode, update SDAR on TLB miss */
- mmcra |= mmcra_sdar_mode(event[i]);
+ mmcra_sdar_mode(event[i], &mmcra);
if (event[i] & EVENT_IS_L1) {
cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
@@ -285,7 +396,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
}
- if (event[i] & EVENT_IS_MARKED) {
+ if (is_event_marked(event[i])) {
mmcra |= MMCRA_SAMPLE_ENABLE;
val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index cf9bd8990159..8acbe6e802c7 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -246,7 +246,17 @@
#define MMCRA_THR_CMP_SHIFT 32
#define MMCRA_SDAR_MODE_SHIFT 42
#define MMCRA_SDAR_MODE_TLB (1ull << MMCRA_SDAR_MODE_SHIFT)
+#define MMCRA_SDAR_MODE_NO_UPDATES ~(0x3ull << MMCRA_SDAR_MODE_SHIFT)
#define MMCRA_IFM_SHIFT 30
+#define MMCRA_THR_CTR_MANT_SHIFT 19
+#define MMCRA_THR_CTR_MANT_MASK 0x7Ful
+#define MMCRA_THR_CTR_MANT(v) (((v) >> MMCRA_THR_CTR_MANT_SHIFT) &\
+ MMCRA_THR_CTR_MANT_MASK)
+
+#define MMCRA_THR_CTR_EXP_SHIFT 27
+#define MMCRA_THR_CTR_EXP_MASK 0x7ul
+#define MMCRA_THR_CTR_EXP(v) (((v) >> MMCRA_THR_CTR_EXP_SHIFT) &\
+ MMCRA_THR_CTR_EXP_MASK)
/* MMCR1 Threshold Compare bit constant for power9 */
#define p9_MMCRA_THR_CMP_SHIFT 45
@@ -259,6 +269,19 @@
#define MAX_ALT 2
#define MAX_PMU_COUNTERS 6
+#define ISA207_SIER_TYPE_SHIFT 15
+#define ISA207_SIER_TYPE_MASK (0x7ull << ISA207_SIER_TYPE_SHIFT)
+
+#define ISA207_SIER_LDST_SHIFT 1
+#define ISA207_SIER_LDST_MASK (0x7ull << ISA207_SIER_LDST_SHIFT)
+
+#define ISA207_SIER_DATA_SRC_SHIFT 53
+#define ISA207_SIER_DATA_SRC_MASK (0x7ull << ISA207_SIER_DATA_SRC_SHIFT)
+
+#define P(a, b) PERF_MEM_S(a, b)
+#define PH(a, b) (P(LVL, HIT) | P(a, b))
+#define PM(a, b) (P(LVL, MISS) | P(a, b))
+
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[],
@@ -266,6 +289,8 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[]);
int isa207_get_alternatives(u64 event, u64 alt[],
const unsigned int ev_alt[][MAX_ALT], int size);
-
+void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
+ struct pt_regs *regs);
+void isa207_get_mem_weight(u64 *weight);
#endif
diff --git a/arch/powerpc/perf/power8-events-list.h b/arch/powerpc/perf/power8-events-list.h
index 3a2e6e8ebb92..0f1d184627cc 100644
--- a/arch/powerpc/perf/power8-events-list.h
+++ b/arch/powerpc/perf/power8-events-list.h
@@ -89,3 +89,9 @@ EVENT(PM_MRK_FILT_MATCH, 0x2013c)
EVENT(PM_MRK_FILT_MATCH_ALT, 0x3012e)
/* Alternate event code for PM_LD_MISS_L1 */
EVENT(PM_LD_MISS_L1_ALT, 0x400f0)
+/*
+ * Memory Access Event -- mem_access
+ * Primary PMU event used here is PM_MRK_INST_CMPL, along with
+ * Random Load/Store Facility Sampling (RIS) in Random sampling mode (MMCRA[SM]).
+ */
+EVENT(MEM_ACCESS, 0x10401e0)
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index ce15b19a7962..5463516e369b 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -90,6 +90,7 @@ GENERIC_EVENT_ATTR(branch-instructions, PM_BRU_FIN);
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_access, MEM_ACCESS);
CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1);
CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1);
@@ -120,6 +121,7 @@ static struct attribute *power8_events_attr[] = {
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_ACCESS),
CACHE_EVENT_PTR(PM_LD_MISS_L1),
CACHE_EVENT_PTR(PM_LD_REF_L1),
@@ -325,6 +327,8 @@ static struct power_pmu power8_pmu = {
.bhrb_filter_map = power8_bhrb_filter_map,
.get_constraint = isa207_get_constraint,
.get_alternatives = power8_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,
.n_generic = ARRAY_SIZE(power8_generic_events),
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 7f6582708e06..018f8e90ac35 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -427,6 +427,8 @@ static struct power_pmu power9_pmu = {
.bhrb_filter_map = power9_bhrb_filter_map,
.get_constraint = isa207_get_constraint,
.get_alternatives = power9_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,
.n_generic = ARRAY_SIZE(power9_generic_events),
diff --git a/arch/powerpc/platforms/44x/sam440ep.c b/arch/powerpc/platforms/44x/sam440ep.c
index 688ffeab0699..55fed5e4de14 100644
--- a/arch/powerpc/platforms/44x/sam440ep.c
+++ b/arch/powerpc/platforms/44x/sam440ep.c
@@ -70,7 +70,7 @@ static struct i2c_board_info sam440ep_rtc_info = {
.irq = -1,
};
-static int sam440ep_setup_rtc(void)
+static int __init sam440ep_setup_rtc(void)
{
return i2c_register_board_info(0, &sam440ep_rtc_info, 1);
}
diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig
index b625a2c6f4f2..e4c745981912 100644
--- a/arch/powerpc/platforms/52xx/Kconfig
+++ b/arch/powerpc/platforms/52xx/Kconfig
@@ -33,7 +33,6 @@ config PPC_EFIKA
bool "bPlan Efika 5k2. MPC5200B based computer"
depends on PPC_MPC52xx
select PPC_RTAS
- select RTAS_PROC
select PPC_NATIVE
config PPC_LITE5200
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 078097a0b09d..f51fd35f4618 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -344,6 +344,7 @@ done:
}
struct smp_ops_t smp_85xx_ops = {
+ .cause_nmi_ipi = NULL,
.kick_cpu = smp_85xx_kick_cpu,
.cpu_bootable = smp_generic_cpu_bootable,
#ifdef CONFIG_HOTPLUG_CPU
@@ -461,16 +462,9 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
}
#endif /* CONFIG_KEXEC_CORE */
-static void smp_85xx_basic_setup(int cpu_nr)
-{
- if (cpu_has_feature(CPU_FTR_DBELL))
- doorbell_setup_this_cpu();
-}
-
static void smp_85xx_setup_cpu(int cpu_nr)
{
mpic_setup_this_cpu();
- smp_85xx_basic_setup(cpu_nr);
}
void __init mpc85xx_smp_init(void)
@@ -484,7 +478,7 @@ void __init mpc85xx_smp_init(void)
smp_85xx_ops.setup_cpu = smp_85xx_setup_cpu;
smp_85xx_ops.message_pass = smp_mpic_message_pass;
} else
- smp_85xx_ops.setup_cpu = smp_85xx_basic_setup;
+ smp_85xx_ops.setup_cpu = NULL;
if (cpu_has_feature(CPU_FTR_DBELL)) {
/*
@@ -492,7 +486,7 @@ void __init mpc85xx_smp_init(void)
* smp_muxed_ipi_message_pass
*/
smp_85xx_ops.message_pass = NULL;
- smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
+ smp_85xx_ops.cause_ipi = doorbell_global_ipi;
smp_85xx_ops.probe = NULL;
}
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
index af09baee22cb..020e84a47a32 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
@@ -105,6 +105,7 @@ smp_86xx_setup_cpu(int cpu_nr)
struct smp_ops_t smp_86xx_ops = {
+ .cause_nmi_ipi = NULL,
.message_pass = smp_mpic_message_pass,
.probe = smp_mpic_probe,
.kick_cpu = smp_86xx_kick_cpu,
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 7e3a2ebba29b..33244e3d9375 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -284,6 +284,7 @@ config CPM2
config AXON_RAM
tristate "Axon DDR2 memory device driver"
depends on PPC_IBM_CELL_BLADE && BLOCK
+ select DAX
default m
help
It registers one block device per Axon's DDR2 memory bank found
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 99b0ae8acb78..684e886eaae4 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -279,7 +279,8 @@ config PPC_ICSWX
This option enables kernel support for the PowerPC Initiate
Coprocessor Store Word (icswx) coprocessor instruction on POWER7
- or newer processors.
+ and POWER8 processors. POWER9 uses new copy/paste instructions
+ to invoke the coprocessor.
This option is only useful if you have a processor that supports
the icswx coprocessor instruction. It does not have any effect
@@ -359,7 +360,7 @@ config PPC_BOOK3E_MMU
config PPC_MM_SLICES
bool
- default y if (!PPC_FSL_BOOK3E && PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
+ default y if PPC_STD_MMU_64
default n
config PPC_HAVE_PMU_SUPPORT
@@ -371,9 +372,16 @@ config PPC_PERF_CTRS
help
This enables the powerpc-specific perf_event back-end.
+config FORCE_SMP
+ # Allow platforms to force SMP=y by selecting this
+ bool
+ default n
+ select SMP
+
config SMP
depends on PPC_BOOK3S || PPC_BOOK3E || FSL_BOOKE || PPC_47x
- bool "Symmetric multi-processing support"
+ select GENERIC_IRQ_MIGRATION
+ bool "Symmetric multi-processing support" if !FORCE_SMP
---help---
This enables support for systems with more than one CPU. If you have
a system with only one CPU, say N. If you have a system with more
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 8b55c5f19d4c..8d3ae2cc52bf 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -15,9 +15,9 @@
#include <linux/msi.h>
#include <linux/export.h>
#include <linux/of_platform.h>
-#include <linux/debugfs.h>
#include <linux/slab.h>
+#include <asm/debugfs.h>
#include <asm/dcr.h>
#include <asm/machdep.h>
#include <asm/prom.h>
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index a6bbbaba14a3..871d38479a25 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -211,7 +211,7 @@ void iic_request_IPIs(void)
iic_request_ipi(PPC_MSG_CALL_FUNCTION);
iic_request_ipi(PPC_MSG_RESCHEDULE);
iic_request_ipi(PPC_MSG_TICK_BROADCAST);
- iic_request_ipi(PPC_MSG_DEBUGGER_BREAK);
+ iic_request_ipi(PPC_MSG_NMI_IPI);
}
#endif /* CONFIG_SMP */
diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
index e7d075077cb0..a88944db9fc3 100644
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ b/arch/powerpc/platforms/cell/pervasive.c
@@ -88,11 +88,14 @@ static void cbe_power_save(void)
static int cbe_system_reset_exception(struct pt_regs *regs)
{
switch (regs->msr & SRR1_WAKEMASK) {
- case SRR1_WAKEEE:
- do_IRQ(regs);
- break;
case SRR1_WAKEDEC:
- timer_interrupt(regs);
+ set_dec(1);
+ case SRR1_WAKEEE:
+ /*
+ * Handle these when interrupts get re-enabled and we take
+ * them as regular exceptions. We are in an NMI context
+ * and can't handle these here.
+ */
break;
case SRR1_WAKEMT:
return cbe_sysreset_hack();
diff --git a/arch/powerpc/platforms/chrp/smp.c b/arch/powerpc/platforms/chrp/smp.c
index b6c9a0dcc924..14515040f7cd 100644
--- a/arch/powerpc/platforms/chrp/smp.c
+++ b/arch/powerpc/platforms/chrp/smp.c
@@ -44,6 +44,7 @@ static void smp_chrp_setup_cpu(int cpu_nr)
/* CHRP with openpic */
struct smp_ops_t chrp_smp_ops = {
+ .cause_nmi_ipi = NULL,
.message_pass = smp_mpic_message_pass,
.probe = smp_mpic_probe,
.kick_cpu = smp_chrp_kick_cpu,
diff --git a/arch/powerpc/platforms/pasemi/idle.c b/arch/powerpc/platforms/pasemi/idle.c
index 75b296bc51af..44e0d9226f0a 100644
--- a/arch/powerpc/platforms/pasemi/idle.c
+++ b/arch/powerpc/platforms/pasemi/idle.c
@@ -53,11 +53,14 @@ static int pasemi_system_reset_exception(struct pt_regs *regs)
regs->nip = regs->link;
switch (regs->msr & SRR1_WAKEMASK) {
- case SRR1_WAKEEE:
- do_IRQ(regs);
- break;
case SRR1_WAKEDEC:
- timer_interrupt(regs);
+ set_dec(1);
+ case SRR1_WAKEEE:
+ /*
+ * Handle these when interrupts get re-enabled and we take
+ * them as regular exceptions. We are in an NMI context
+ * and can't handle these here.
+ */
break;
default:
/* do system reset */
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 746ca7321b03..2cd99eb30762 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -172,7 +172,7 @@ static irqreturn_t psurge_ipi_intr(int irq, void *d)
return IRQ_HANDLED;
}
-static void smp_psurge_cause_ipi(int cpu, unsigned long data)
+static void smp_psurge_cause_ipi(int cpu)
{
psurge_set_ipi(cpu);
}
@@ -447,6 +447,7 @@ void __init smp_psurge_give_timebase(void)
struct smp_ops_t psurge_smp_ops = {
.message_pass = NULL, /* Use smp_muxed_ipi_message_pass */
.cause_ipi = smp_psurge_cause_ipi,
+ .cause_nmi_ipi = NULL,
.probe = smp_psurge_probe,
.kick_cpu = smp_psurge_kick_cpu,
.setup_cpu = smp_psurge_setup_cpu,
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 3a07e4dcf97c..6a6f4ef46b9e 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -4,6 +4,7 @@ config PPC_POWERNV
select PPC_NATIVE
select PPC_XICS
select PPC_ICP_NATIVE
+ select PPC_XIVE_NATIVE
select PPC_P7_NAP
select PCI
select PCI_MSI
@@ -19,6 +20,8 @@ config PPC_POWERNV
select CPU_FREQ_GOV_ONDEMAND
select CPU_FREQ_GOV_CONSERVATIVE
select PPC_DOORBELL
+ select MMU_NOTIFIER
+ select FORCE_SMP
default y
config OPAL_PRD
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 6fb5522acd70..d2f19821d71d 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1102,6 +1102,13 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
return -EIO;
}
+ /*
+ * If dealing with the root bus (or the bus underneath the
+ * root port), we reset the bus underneath the root port.
+ *
+ * The cxl driver depends on this behaviour for bi-modal card
+ * switching.
+ */
if (pci_is_root_bus(bus) ||
pci_is_root_bus(bus->parent))
return pnv_eeh_root_reset(hose, option);
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 4ee837e6391a..445f30a2c5ef 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -53,19 +53,6 @@ static int pnv_save_sprs_for_deep_states(void)
uint64_t pir = get_hard_smp_processor_id(cpu);
uint64_t hsprg0_val = (uint64_t)&paca[cpu];
- if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
- /*
- * HSPRG0 is used to store the cpu's pointer to paca.
- * Hence last 3 bits are guaranteed to be 0. Program
- * slw to restore HSPRG0 with 63rd bit set, so that
- * when a thread wakes up at 0x100 we can use this bit
- * to distinguish between fastsleep and deep winkle.
- * This is not necessary with stop/psscr since PLS
- * field of psscr indicates which state we are waking
- * up from.
- */
- hsprg0_val |= 1;
- }
rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
if (rc != 0)
return rc;
@@ -122,9 +109,12 @@ static void pnv_alloc_idle_core_states(void)
for (i = 0; i < nr_cores; i++) {
int first_cpu = i * threads_per_core;
int node = cpu_to_node(first_cpu);
+ size_t paca_ptr_array_size;
core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
*core_idle_state = PNV_CORE_IDLE_THREAD_BITS;
+ paca_ptr_array_size = (threads_per_core *
+ sizeof(struct paca_struct *));
for (j = 0; j < threads_per_core; j++) {
int cpu = first_cpu + j;
@@ -132,6 +122,11 @@ static void pnv_alloc_idle_core_states(void)
paca[cpu].core_idle_state_ptr = core_idle_state;
paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
paca[cpu].thread_mask = 1 << j;
+ if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
+ continue;
+ paca[cpu].thread_sibling_pacas =
+ kmalloc_node(paca_ptr_array_size,
+ GFP_KERNEL, node);
}
}
@@ -147,7 +142,6 @@ u32 pnv_get_supported_cpuidle_states(void)
}
EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
-
static void pnv_fastsleep_workaround_apply(void *info)
{
@@ -241,8 +235,9 @@ static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600,
* The default stop state that will be used by ppc_md.power_save
* function on platforms that support stop instruction.
*/
-u64 pnv_default_stop_val;
-u64 pnv_default_stop_mask;
+static u64 pnv_default_stop_val;
+static u64 pnv_default_stop_mask;
+static bool default_stop_found;
/*
* Used for ppc_md.power_save which needs a function with no parameters
@@ -262,8 +257,42 @@ u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
* psscr value and mask of the deepest stop idle state.
* Used when a cpu is offlined.
*/
-u64 pnv_deepest_stop_psscr_val;
-u64 pnv_deepest_stop_psscr_mask;
+static u64 pnv_deepest_stop_psscr_val;
+static u64 pnv_deepest_stop_psscr_mask;
+static bool deepest_stop_found;
+
+/*
+ * pnv_cpu_offline: A function that puts the CPU into the deepest
+ * available platform idle state on a CPU-Offline.
+ */
+unsigned long pnv_cpu_offline(unsigned int cpu)
+{
+ unsigned long srr1;
+
+ u32 idle_states = pnv_get_supported_cpuidle_states();
+
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && deepest_stop_found) {
+ srr1 = power9_idle_stop(pnv_deepest_stop_psscr_val,
+ pnv_deepest_stop_psscr_mask);
+ } else if (idle_states & OPAL_PM_WINKLE_ENABLED) {
+ srr1 = power7_winkle();
+ } else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
+ (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
+ srr1 = power7_sleep();
+ } else if (idle_states & OPAL_PM_NAP_ENABLED) {
+ srr1 = power7_nap(1);
+ } else {
+ /* This is the fallback method. We emulate snooze */
+ while (!generic_check_cpu_restart(cpu)) {
+ HMT_low();
+ HMT_very_low();
+ }
+ srr1 = 0;
+ HMT_medium();
+ }
+
+ return srr1;
+}
/*
* Power ISA 3.0 idle initialization.
@@ -352,7 +381,6 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
u32 *residency_ns = NULL;
u64 max_residency_ns = 0;
int rc = 0, i;
- bool default_stop_found = false, deepest_stop_found = false;
psscr_val = kcalloc(dt_idle_states, sizeof(*psscr_val), GFP_KERNEL);
psscr_mask = kcalloc(dt_idle_states, sizeof(*psscr_mask), GFP_KERNEL);
@@ -432,21 +460,24 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
}
}
- if (!default_stop_found) {
- pnv_default_stop_val = PSSCR_HV_DEFAULT_VAL;
- pnv_default_stop_mask = PSSCR_HV_DEFAULT_MASK;
- pr_warn("Setting default stop psscr val=0x%016llx,mask=0x%016llx\n",
+ if (unlikely(!default_stop_found)) {
+ pr_warn("cpuidle-powernv: No suitable default stop state found. Disabling platform idle.\n");
+ } else {
+ ppc_md.power_save = power9_idle;
+ pr_info("cpuidle-powernv: Default stop: psscr = 0x%016llx,mask=0x%016llx\n",
pnv_default_stop_val, pnv_default_stop_mask);
}
- if (!deepest_stop_found) {
- pnv_deepest_stop_psscr_val = PSSCR_HV_DEFAULT_VAL;
- pnv_deepest_stop_psscr_mask = PSSCR_HV_DEFAULT_MASK;
- pr_warn("Setting default stop psscr val=0x%016llx,mask=0x%016llx\n",
+ if (unlikely(!deepest_stop_found)) {
+ pr_warn("cpuidle-powernv: No suitable stop state for CPU-Hotplug. Offlined CPUs will busy wait");
+ } else {
+ pr_info("cpuidle-powernv: Deepest stop: psscr = 0x%016llx,mask=0x%016llx\n",
pnv_deepest_stop_psscr_val,
pnv_deepest_stop_psscr_mask);
}
+ pr_info("cpuidle-powernv: Requested Level (RL) value of first deep stop = 0x%llx\n",
+ pnv_first_deep_stop_state);
out:
kfree(psscr_val);
kfree(psscr_mask);
@@ -524,10 +555,30 @@ static int __init pnv_init_idle_states(void)
pnv_alloc_idle_core_states();
+ /*
+ * For each CPU, record its PACA address in each of it's
+ * sibling thread's PACA at the slot corresponding to this
+ * CPU's index in the core.
+ */
+ if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
+ int cpu;
+
+ pr_info("powernv: idle: Saving PACA pointers of all CPUs in their thread sibling PACA\n");
+ for_each_possible_cpu(cpu) {
+ int base_cpu = cpu_first_thread_sibling(cpu);
+ int idx = cpu_thread_in_core(cpu);
+ int i;
+
+ for (i = 0; i < threads_per_core; i++) {
+ int j = base_cpu + i;
+
+ paca[j].thread_sibling_pacas[idx] = &paca[cpu];
+ }
+ }
+ }
+
if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED)
ppc_md.power_save = power7_idle;
- else if (supported_cpuidle_states & OPAL_PM_STOP_INST_FAST)
- ppc_md.power_save = power9_idle;
out:
return 0;
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 1c383f38031d..067defeea691 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -9,11 +9,20 @@
* License as published by the Free Software Foundation.
*/
+#include <linux/slab.h>
+#include <linux/mmu_notifier.h>
+#include <linux/mmu_context.h>
+#include <linux/of.h>
#include <linux/export.h>
#include <linux/pci.h>
#include <linux/memblock.h>
#include <linux/iommu.h>
+#include <asm/tlb.h>
+#include <asm/powernv.h>
+#include <asm/reg.h>
+#include <asm/opal.h>
+#include <asm/io.h>
#include <asm/iommu.h>
#include <asm/pnv-pci.h>
#include <asm/msi_bitmap.h>
@@ -22,6 +31,8 @@
#include "powernv.h"
#include "pci.h"
+#define npu_to_phb(x) container_of(x, struct pnv_phb, npu)
+
/*
* Other types of TCE cache invalidation are not functional in the
* hardware.
@@ -37,6 +48,12 @@ struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev)
struct device_node *dn;
struct pci_dev *gpdev;
+ if (WARN_ON(!npdev))
+ return NULL;
+
+ if (WARN_ON(!npdev->dev.of_node))
+ return NULL;
+
/* Get assoicated PCI device */
dn = of_parse_phandle(npdev->dev.of_node, "ibm,gpu", 0);
if (!dn)
@@ -55,6 +72,12 @@ struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index)
struct device_node *dn;
struct pci_dev *npdev;
+ if (WARN_ON(!gpdev))
+ return NULL;
+
+ if (WARN_ON(!gpdev->dev.of_node))
+ return NULL;
+
/* Get assoicated PCI device */
dn = of_parse_phandle(gpdev->dev.of_node, "ibm,npu", index);
if (!dn)
@@ -180,7 +203,7 @@ long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
pe_err(npe, "Failed to configure TCE table, err %lld\n", rc);
return rc;
}
- pnv_pci_phb3_tce_invalidate_entire(phb, false);
+ pnv_pci_ioda2_tce_invalidate_entire(phb, false);
/* Add the table to the list so its TCE cache will get invalidated */
pnv_pci_link_table_and_group(phb->hose->node, num,
@@ -204,7 +227,7 @@ long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num)
pe_err(npe, "Unmapping failed, ret = %lld\n", rc);
return rc;
}
- pnv_pci_phb3_tce_invalidate_entire(phb, false);
+ pnv_pci_ioda2_tce_invalidate_entire(phb, false);
pnv_pci_unlink_table_and_group(npe->table_group.tables[num],
&npe->table_group);
@@ -270,7 +293,7 @@ static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe)
0 /* bypass base */, top);
if (rc == OPAL_SUCCESS)
- pnv_pci_phb3_tce_invalidate_entire(phb, false);
+ pnv_pci_ioda2_tce_invalidate_entire(phb, false);
return rc;
}
@@ -334,7 +357,7 @@ void pnv_npu_take_ownership(struct pnv_ioda_pe *npe)
pe_err(npe, "Failed to disable bypass, err %lld\n", rc);
return;
}
- pnv_pci_phb3_tce_invalidate_entire(npe->phb, false);
+ pnv_pci_ioda2_tce_invalidate_entire(npe->phb, false);
}
struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe)
@@ -359,3 +382,442 @@ struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe)
return gpe;
}
+
+/* Maximum number of nvlinks per npu */
+#define NV_MAX_LINKS 6
+
+/* Maximum index of npu2 hosts in the system. Always < NV_MAX_NPUS */
+static int max_npu2_index;
+
+struct npu_context {
+ struct mm_struct *mm;
+ struct pci_dev *npdev[NV_MAX_NPUS][NV_MAX_LINKS];
+ struct mmu_notifier mn;
+ struct kref kref;
+
+ /* Callback to stop translation requests on a given GPU */
+ struct npu_context *(*release_cb)(struct npu_context *, void *);
+
+ /*
+ * Private pointer passed to the above callback for usage by
+ * device drivers.
+ */
+ void *priv;
+};
+
+/*
+ * Find a free MMIO ATSD register and mark it in use. Return -ENOSPC
+ * if none are available.
+ */
+static int get_mmio_atsd_reg(struct npu *npu)
+{
+ int i;
+
+ for (i = 0; i < npu->mmio_atsd_count; i++) {
+ if (!test_and_set_bit(i, &npu->mmio_atsd_usage))
+ return i;
+ }
+
+ return -ENOSPC;
+}
+
+static void put_mmio_atsd_reg(struct npu *npu, int reg)
+{
+ clear_bit(reg, &npu->mmio_atsd_usage);
+}
+
+/* MMIO ATSD register offsets */
+#define XTS_ATSD_AVA 1
+#define XTS_ATSD_STAT 2
+
+static int mmio_launch_invalidate(struct npu *npu, unsigned long launch,
+ unsigned long va)
+{
+ int mmio_atsd_reg;
+
+ do {
+ mmio_atsd_reg = get_mmio_atsd_reg(npu);
+ cpu_relax();
+ } while (mmio_atsd_reg < 0);
+
+ __raw_writeq(cpu_to_be64(va),
+ npu->mmio_atsd_regs[mmio_atsd_reg] + XTS_ATSD_AVA);
+ eieio();
+ __raw_writeq(cpu_to_be64(launch), npu->mmio_atsd_regs[mmio_atsd_reg]);
+
+ return mmio_atsd_reg;
+}
+
+static int mmio_invalidate_pid(struct npu *npu, unsigned long pid)
+{
+ unsigned long launch;
+
+ /* IS set to invalidate matching PID */
+ launch = PPC_BIT(12);
+
+ /* PRS set to process-scoped */
+ launch |= PPC_BIT(13);
+
+ /* AP */
+ launch |= (u64) mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17);
+
+ /* PID */
+ launch |= pid << PPC_BITLSHIFT(38);
+
+ /* Invalidating the entire process doesn't use a va */
+ return mmio_launch_invalidate(npu, launch, 0);
+}
+
+static int mmio_invalidate_va(struct npu *npu, unsigned long va,
+ unsigned long pid)
+{
+ unsigned long launch;
+
+ /* IS set to invalidate target VA */
+ launch = 0;
+
+ /* PRS set to process scoped */
+ launch |= PPC_BIT(13);
+
+ /* AP */
+ launch |= (u64) mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17);
+
+ /* PID */
+ launch |= pid << PPC_BITLSHIFT(38);
+
+ return mmio_launch_invalidate(npu, launch, va);
+}
+
+#define mn_to_npu_context(x) container_of(x, struct npu_context, mn)
+
+/*
+ * Invalidate either a single address or an entire PID depending on
+ * the value of va.
+ */
+static void mmio_invalidate(struct npu_context *npu_context, int va,
+ unsigned long address)
+{
+ int i, j, reg;
+ struct npu *npu;
+ struct pnv_phb *nphb;
+ struct pci_dev *npdev;
+ struct {
+ struct npu *npu;
+ int reg;
+ } mmio_atsd_reg[NV_MAX_NPUS];
+ unsigned long pid = npu_context->mm->context.id;
+
+ /*
+ * Loop over all the NPUs this process is active on and launch
+ * an invalidate.
+ */
+ for (i = 0; i <= max_npu2_index; i++) {
+ mmio_atsd_reg[i].reg = -1;
+ for (j = 0; j < NV_MAX_LINKS; j++) {
+ npdev = npu_context->npdev[i][j];
+ if (!npdev)
+ continue;
+
+ nphb = pci_bus_to_host(npdev->bus)->private_data;
+ npu = &nphb->npu;
+ mmio_atsd_reg[i].npu = npu;
+
+ if (va)
+ mmio_atsd_reg[i].reg =
+ mmio_invalidate_va(npu, address, pid);
+ else
+ mmio_atsd_reg[i].reg =
+ mmio_invalidate_pid(npu, pid);
+
+ /*
+ * The NPU hardware forwards the shootdown to all GPUs
+ * so we only have to launch one shootdown per NPU.
+ */
+ break;
+ }
+ }
+
+ /*
+ * Unfortunately the nest mmu does not support flushing specific
+ * addresses so we have to flush the whole mm.
+ */
+ flush_tlb_mm(npu_context->mm);
+
+ /* Wait for all invalidations to complete */
+ for (i = 0; i <= max_npu2_index; i++) {
+ if (mmio_atsd_reg[i].reg < 0)
+ continue;
+
+ /* Wait for completion */
+ npu = mmio_atsd_reg[i].npu;
+ reg = mmio_atsd_reg[i].reg;
+ while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
+ cpu_relax();
+ put_mmio_atsd_reg(npu, reg);
+ }
+}
+
+static void pnv_npu2_mn_release(struct mmu_notifier *mn,
+ struct mm_struct *mm)
+{
+ struct npu_context *npu_context = mn_to_npu_context(mn);
+
+ /* Call into device driver to stop requests to the NMMU */
+ if (npu_context->release_cb)
+ npu_context->release_cb(npu_context, npu_context->priv);
+
+ /*
+ * There should be no more translation requests for this PID, but we
+ * need to ensure any entries for it are removed from the TLB.
+ */
+ mmio_invalidate(npu_context, 0, 0);
+}
+
+static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address,
+ pte_t pte)
+{
+ struct npu_context *npu_context = mn_to_npu_context(mn);
+
+ mmio_invalidate(npu_context, 1, address);
+}
+
+static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ struct npu_context *npu_context = mn_to_npu_context(mn);
+
+ mmio_invalidate(npu_context, 1, address);
+}
+
+static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ struct npu_context *npu_context = mn_to_npu_context(mn);
+ unsigned long address;
+
+ for (address = start; address <= end; address += PAGE_SIZE)
+ mmio_invalidate(npu_context, 1, address);
+}
+
+static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
+ .release = pnv_npu2_mn_release,
+ .change_pte = pnv_npu2_mn_change_pte,
+ .invalidate_page = pnv_npu2_mn_invalidate_page,
+ .invalidate_range = pnv_npu2_mn_invalidate_range,
+};
+
+/*
+ * Call into OPAL to setup the nmmu context for the current task in
+ * the NPU. This must be called to setup the context tables before the
+ * GPU issues ATRs. pdev should be a pointed to PCIe GPU device.
+ *
+ * A release callback should be registered to allow a device driver to
+ * be notified that it should not launch any new translation requests
+ * as the final TLB invalidate is about to occur.
+ *
+ * Returns an error if there no contexts are currently available or a
+ * npu_context which should be passed to pnv_npu2_handle_fault().
+ *
+ * mmap_sem must be held in write mode.
+ */
+struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
+ unsigned long flags,
+ struct npu_context *(*cb)(struct npu_context *, void *),
+ void *priv)
+{
+ int rc;
+ u32 nvlink_index;
+ struct device_node *nvlink_dn;
+ struct mm_struct *mm = current->mm;
+ struct pnv_phb *nphb;
+ struct npu *npu;
+ struct npu_context *npu_context;
+
+ /*
+ * At present we don't support GPUs connected to multiple NPUs and I'm
+ * not sure the hardware does either.
+ */
+ struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
+
+ if (!firmware_has_feature(FW_FEATURE_OPAL))
+ return ERR_PTR(-ENODEV);
+
+ if (!npdev)
+ /* No nvlink associated with this GPU device */
+ return ERR_PTR(-ENODEV);
+
+ if (!mm) {
+ /* kernel thread contexts are not supported */
+ return ERR_PTR(-EINVAL);
+ }
+
+ nphb = pci_bus_to_host(npdev->bus)->private_data;
+ npu = &nphb->npu;
+
+ /*
+ * Setup the NPU context table for a particular GPU. These need to be
+ * per-GPU as we need the tables to filter ATSDs when there are no
+ * active contexts on a particular GPU.
+ */
+ rc = opal_npu_init_context(nphb->opal_id, mm->context.id, flags,
+ PCI_DEVID(gpdev->bus->number, gpdev->devfn));
+ if (rc < 0)
+ return ERR_PTR(-ENOSPC);
+
+ /*
+ * We store the npu pci device so we can more easily get at the
+ * associated npus.
+ */
+ npu_context = mm->context.npu_context;
+ if (!npu_context) {
+ npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL);
+ if (!npu_context)
+ return ERR_PTR(-ENOMEM);
+
+ mm->context.npu_context = npu_context;
+ npu_context->mm = mm;
+ npu_context->mn.ops = &nv_nmmu_notifier_ops;
+ __mmu_notifier_register(&npu_context->mn, mm);
+ kref_init(&npu_context->kref);
+ } else {
+ kref_get(&npu_context->kref);
+ }
+
+ npu_context->release_cb = cb;
+ npu_context->priv = priv;
+ nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
+ if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
+ &nvlink_index)))
+ return ERR_PTR(-ENODEV);
+ npu_context->npdev[npu->index][nvlink_index] = npdev;
+
+ return npu_context;
+}
+EXPORT_SYMBOL(pnv_npu2_init_context);
+
+static void pnv_npu2_release_context(struct kref *kref)
+{
+ struct npu_context *npu_context =
+ container_of(kref, struct npu_context, kref);
+
+ npu_context->mm->context.npu_context = NULL;
+ mmu_notifier_unregister(&npu_context->mn,
+ npu_context->mm);
+
+ kfree(npu_context);
+}
+
+void pnv_npu2_destroy_context(struct npu_context *npu_context,
+ struct pci_dev *gpdev)
+{
+ struct pnv_phb *nphb, *phb;
+ struct npu *npu;
+ struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
+ struct device_node *nvlink_dn;
+ u32 nvlink_index;
+
+ if (WARN_ON(!npdev))
+ return;
+
+ if (!firmware_has_feature(FW_FEATURE_OPAL))
+ return;
+
+ nphb = pci_bus_to_host(npdev->bus)->private_data;
+ npu = &nphb->npu;
+ phb = pci_bus_to_host(gpdev->bus)->private_data;
+ nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
+ if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
+ &nvlink_index)))
+ return;
+ npu_context->npdev[npu->index][nvlink_index] = NULL;
+ opal_npu_destroy_context(phb->opal_id, npu_context->mm->context.id,
+ PCI_DEVID(gpdev->bus->number, gpdev->devfn));
+ kref_put(&npu_context->kref, pnv_npu2_release_context);
+}
+EXPORT_SYMBOL(pnv_npu2_destroy_context);
+
+/*
+ * Assumes mmap_sem is held for the contexts associated mm.
+ */
+int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea,
+ unsigned long *flags, unsigned long *status, int count)
+{
+ u64 rc = 0, result = 0;
+ int i, is_write;
+ struct page *page[1];
+
+ /* mmap_sem should be held so the struct_mm must be present */
+ struct mm_struct *mm = context->mm;
+
+ if (!firmware_has_feature(FW_FEATURE_OPAL))
+ return -ENODEV;
+
+ WARN_ON(!rwsem_is_locked(&mm->mmap_sem));
+
+ for (i = 0; i < count; i++) {
+ is_write = flags[i] & NPU2_WRITE;
+ rc = get_user_pages_remote(NULL, mm, ea[i], 1,
+ is_write ? FOLL_WRITE : 0,
+ page, NULL, NULL);
+
+ /*
+ * To support virtualised environments we will have to do an
+ * access to the page to ensure it gets faulted into the
+ * hypervisor. For the moment virtualisation is not supported in
+ * other areas so leave the access out.
+ */
+ if (rc != 1) {
+ status[i] = rc;
+ result = -EFAULT;
+ continue;
+ }
+
+ status[i] = 0;
+ put_page(page[0]);
+ }
+
+ return result;
+}
+EXPORT_SYMBOL(pnv_npu2_handle_fault);
+
+int pnv_npu2_init(struct pnv_phb *phb)
+{
+ unsigned int i;
+ u64 mmio_atsd;
+ struct device_node *dn;
+ struct pci_dev *gpdev;
+ static int npu_index;
+ uint64_t rc = 0;
+
+ for_each_child_of_node(phb->hose->dn, dn) {
+ gpdev = pnv_pci_get_gpu_dev(get_pci_dev(dn));
+ if (gpdev) {
+ rc = opal_npu_map_lpar(phb->opal_id,
+ PCI_DEVID(gpdev->bus->number, gpdev->devfn),
+ 0, 0);
+ if (rc)
+ dev_err(&gpdev->dev,
+ "Error %lld mapping device to LPAR\n",
+ rc);
+ }
+ }
+
+ for (i = 0; !of_property_read_u64_index(phb->hose->dn, "ibm,mmio-atsd",
+ i, &mmio_atsd); i++)
+ phb->npu.mmio_atsd_regs[i] = ioremap(mmio_atsd, 32);
+
+ pr_info("NPU%lld: Found %d MMIO ATSD registers", phb->opal_id, i);
+ phb->npu.mmio_atsd_count = i;
+ phb->npu.mmio_atsd_usage = 0;
+ npu_index++;
+ if (WARN_ON(npu_index >= NV_MAX_NPUS))
+ return -ENOSPC;
+ max_npu2_index = npu_index;
+ phb->npu.index = npu_index;
+
+ return 0;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index a91d7876fae2..6c7ad1d8b32e 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -12,7 +12,6 @@
#include <linux/kernel.h>
#include <linux/of.h>
#include <linux/bug.h>
-#include <linux/debugfs.h>
#include <linux/io.h>
#include <linux/slab.h>
@@ -21,7 +20,7 @@
#include <asm/opal.h>
#include <asm/prom.h>
#include <linux/uaccess.h>
-#include <asm/debug.h>
+#include <asm/debugfs.h>
#include <asm/isa-bridge.h>
static int opal_lpc_chip_id = -1;
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
index 308efd170c27..aa267f120033 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -64,6 +64,10 @@ int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data)
*sensor_data = be32_to_cpu(data);
break;
+ case OPAL_WRONG_STATE:
+ ret = -EIO;
+ break;
+
default:
ret = opal_error_code(ret);
break;
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 6693f75e93d1..f620572f891f 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -39,8 +39,8 @@ opal_tracepoint_refcount:
BEGIN_FTR_SECTION; \
b 1f; \
END_FTR_SECTION(0, 1); \
- ld r12,opal_tracepoint_refcount@toc(r2); \
- cmpdi r12,0; \
+ ld r11,opal_tracepoint_refcount@toc(r2); \
+ cmpdi r11,0; \
bne- LABEL; \
1:
@@ -50,21 +50,13 @@ END_FTR_SECTION(0, 1); \
#define OPAL_BRANCH(LABEL)
#endif
-/* TODO:
- *
- * - Trace irqs in/off (needs saving/restoring all args, argh...)
- * - Get r11 feed up by Dave so I can have better register usage
+/*
+ * DO_OPAL_CALL assumes:
+ * r0 = opal call token
+ * r12 = msr
+ * LR has been saved
*/
-
-#define OPAL_CALL(name, token) \
- _GLOBAL_TOC(name); \
- mfmsr r12; \
- mflr r0; \
- andi. r11,r12,MSR_IR|MSR_DR; \
- std r0,PPC_LR_STKOFF(r1); \
- li r0,token; \
- beq opal_real_call; \
- OPAL_BRANCH(opal_tracepoint_entry) \
+#define DO_OPAL_CALL() \
mfcr r11; \
stw r11,8(r1); \
li r11,0; \
@@ -83,6 +75,18 @@ END_FTR_SECTION(0, 1); \
mtspr SPRN_HSRR0,r12; \
hrfid
+#define OPAL_CALL(name, token) \
+ _GLOBAL_TOC(name); \
+ mfmsr r12; \
+ mflr r0; \
+ andi. r11,r12,MSR_IR|MSR_DR; \
+ std r0,PPC_LR_STKOFF(r1); \
+ li r0,token; \
+ beq opal_real_call; \
+ OPAL_BRANCH(opal_tracepoint_entry) \
+ DO_OPAL_CALL()
+
+
opal_return:
/*
* Fixup endian on OPAL return... we should be able to simplify
@@ -148,26 +152,13 @@ opal_tracepoint_entry:
ld r8,STK_REG(R29)(r1)
ld r9,STK_REG(R30)(r1)
ld r10,STK_REG(R31)(r1)
+
+ /* setup LR so we return via tracepoint_return */
LOAD_REG_ADDR(r11,opal_tracepoint_return)
- mfcr r12
std r11,16(r1)
- stw r12,8(r1)
- li r11,0
+
mfmsr r12
- ori r11,r11,MSR_EE
- std r12,PACASAVEDMSR(r13)
- andc r12,r12,r11
- mtmsrd r12,1
- LOAD_REG_ADDR(r11,opal_return)
- mtlr r11
- li r11,MSR_DR|MSR_IR|MSR_LE
- andc r12,r12,r11
- mtspr SPRN_HSRR1,r12
- LOAD_REG_ADDR(r11,opal)
- ld r12,8(r11)
- ld r2,0(r11)
- mtspr SPRN_HSRR0,r12
- hrfid
+ DO_OPAL_CALL()
opal_tracepoint_return:
std r3,STK_REG(R31)(r1)
@@ -301,3 +292,21 @@ OPAL_CALL(opal_int_eoi, OPAL_INT_EOI);
OPAL_CALL(opal_int_set_mfrr, OPAL_INT_SET_MFRR);
OPAL_CALL(opal_pci_tce_kill, OPAL_PCI_TCE_KILL);
OPAL_CALL(opal_nmmu_set_ptcr, OPAL_NMMU_SET_PTCR);
+OPAL_CALL(opal_xive_reset, OPAL_XIVE_RESET);
+OPAL_CALL(opal_xive_get_irq_info, OPAL_XIVE_GET_IRQ_INFO);
+OPAL_CALL(opal_xive_get_irq_config, OPAL_XIVE_GET_IRQ_CONFIG);
+OPAL_CALL(opal_xive_set_irq_config, OPAL_XIVE_SET_IRQ_CONFIG);
+OPAL_CALL(opal_xive_get_queue_info, OPAL_XIVE_GET_QUEUE_INFO);
+OPAL_CALL(opal_xive_set_queue_info, OPAL_XIVE_SET_QUEUE_INFO);
+OPAL_CALL(opal_xive_donate_page, OPAL_XIVE_DONATE_PAGE);
+OPAL_CALL(opal_xive_alloc_vp_block, OPAL_XIVE_ALLOCATE_VP_BLOCK);
+OPAL_CALL(opal_xive_free_vp_block, OPAL_XIVE_FREE_VP_BLOCK);
+OPAL_CALL(opal_xive_allocate_irq, OPAL_XIVE_ALLOCATE_IRQ);
+OPAL_CALL(opal_xive_free_irq, OPAL_XIVE_FREE_IRQ);
+OPAL_CALL(opal_xive_get_vp_info, OPAL_XIVE_GET_VP_INFO);
+OPAL_CALL(opal_xive_set_vp_info, OPAL_XIVE_SET_VP_INFO);
+OPAL_CALL(opal_xive_sync, OPAL_XIVE_SYNC);
+OPAL_CALL(opal_xive_dump, OPAL_XIVE_DUMP);
+OPAL_CALL(opal_npu_init_context, OPAL_NPU_INIT_CONTEXT);
+OPAL_CALL(opal_npu_destroy_context, OPAL_NPU_DESTROY_CONTEXT);
+OPAL_CALL(opal_npu_map_lpar, OPAL_NPU_MAP_LPAR);
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index d0ac535cf5d7..28651fb25417 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -73,25 +73,32 @@ static int opal_xscom_err_xlate(int64_t rc)
static u64 opal_scom_unmangle(u64 addr)
{
+ u64 tmp;
+
/*
- * XSCOM indirect addresses have the top bit set. Additionally
- * the rest of the top 3 nibbles is always 0.
+ * XSCOM addresses use the top nibble to set indirect mode and
+ * its form. Bits 4-11 are always 0.
*
* Because the debugfs interface uses signed offsets and shifts
* the address left by 3, we basically cannot use the top 4 bits
* of the 64-bit address, and thus cannot use the indirect bit.
*
- * To deal with that, we support the indirect bit being in bit
- * 4 (IBM notation) instead of bit 0 in this API, we do the
- * conversion here. To leave room for further xscom address
- * expansion, we only clear out the top byte
+ * To deal with that, we support the indirect bits being in
+ * bits 4-7 (IBM notation) instead of bit 0-3 in this API, we
+ * do the conversion here.
*
- * For in-kernel use, we also support the real indirect bit, so
- * we test for any of the top 5 bits
+ * For in-kernel use, we don't need to do this mangling. In
+ * kernel won't have bits 4-7 set.
*
+ * So:
+ * debugfs will always set 0-3 = 0 and clear 4-7
+ * kernel will always clear 0-3 = 0 and set 4-7
*/
- if (addr & (0x1full << 59))
- addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+ tmp = addr;
+ tmp &= 0x0f00000000000000;
+ addr &= 0xf0ffffffffffffff;
+ addr |= tmp << 4;
+
return addr;
}
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 86d9fde93c17..59684b4af4d1 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -395,7 +395,6 @@ static int opal_recover_mce(struct pt_regs *regs,
struct machine_check_event *evt)
{
int recovered = 0;
- uint64_t ea = get_mce_fault_addr(evt);
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
@@ -404,26 +403,18 @@ static int opal_recover_mce(struct pt_regs *regs,
} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
/* Platform corrected itself */
recovered = 1;
- } else if (ea && !is_kernel_addr(ea)) {
+ } else if (evt->severity == MCE_SEV_FATAL) {
+ /* Fatal machine check */
+ pr_err("Machine check interrupt is fatal\n");
+ recovered = 0;
+ } else if ((evt->severity == MCE_SEV_ERROR_SYNC) &&
+ (user_mode(regs) && !is_global_init(current))) {
/*
- * Faulting address is not in kernel text. We should be fine.
- * We need to find which process uses this address.
* For now, kill the task if we have received exception when
* in userspace.
*
* TODO: Queue up this address for hwpoisioning later.
*/
- if (user_mode(regs) && !is_global_init(current)) {
- _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
- recovered = 1;
- } else
- recovered = 0;
- } else if (user_mode(regs) && !is_global_init(current) &&
- evt->severity == MCE_SEV_ERROR_SYNC) {
- /*
- * If we have received a synchronous error when in userspace
- * kill the task.
- */
_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
recovered = 1;
}
@@ -444,7 +435,7 @@ int opal_machine_check(struct pt_regs *regs)
evt.version);
return 0;
}
- machine_check_print_event_info(&evt);
+ machine_check_print_event_info(&evt, user_mode(regs));
if (opal_recover_mce(regs, &evt))
return 1;
@@ -604,6 +595,80 @@ static void opal_export_symmap(void)
pr_warn("Error %d creating OPAL symbols file\n", rc);
}
+static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf,
+ loff_t off, size_t count)
+{
+ return memory_read_from_buffer(buf, count, &off, bin_attr->private,
+ bin_attr->size);
+}
+
+/*
+ * opal_export_attrs: creates a sysfs node for each property listed in
+ * the device-tree under /ibm,opal/firmware/exports/
+ * All new sysfs nodes are created under /opal/exports/.
+ * This allows for reserved memory regions (e.g. HDAT) to be read.
+ * The new sysfs nodes are only readable by root.
+ */
+static void opal_export_attrs(void)
+{
+ struct bin_attribute *attr;
+ struct device_node *np;
+ struct property *prop;
+ struct kobject *kobj;
+ u64 vals[2];
+ int rc;
+
+ np = of_find_node_by_path("/ibm,opal/firmware/exports");
+ if (!np)
+ return;
+
+ /* Create new 'exports' directory - /sys/firmware/opal/exports */
+ kobj = kobject_create_and_add("exports", opal_kobj);
+ if (!kobj) {
+ pr_warn("kobject_create_and_add() of exports failed\n");
+ return;
+ }
+
+ for_each_property_of_node(np, prop) {
+ if (!strcmp(prop->name, "name") || !strcmp(prop->name, "phandle"))
+ continue;
+
+ if (of_property_read_u64_array(np, prop->name, &vals[0], 2))
+ continue;
+
+ attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+
+ if (attr == NULL) {
+ pr_warn("Failed kmalloc for bin_attribute!");
+ continue;
+ }
+
+ sysfs_bin_attr_init(attr);
+ attr->attr.name = kstrdup(prop->name, GFP_KERNEL);
+ attr->attr.mode = 0400;
+ attr->read = export_attr_read;
+ attr->private = __va(vals[0]);
+ attr->size = vals[1];
+
+ if (attr->attr.name == NULL) {
+ pr_warn("Failed kstrdup for bin_attribute attr.name");
+ kfree(attr);
+ continue;
+ }
+
+ rc = sysfs_create_bin_file(kobj, attr);
+ if (rc) {
+ pr_warn("Error %d creating OPAL sysfs exports/%s file\n",
+ rc, prop->name);
+ kfree(attr->attr.name);
+ kfree(attr);
+ }
+ }
+
+ of_node_put(np);
+}
+
static void __init opal_dump_region_init(void)
{
void *addr;
@@ -742,6 +807,9 @@ static int __init opal_init(void)
opal_msglog_sysfs_init();
}
+ /* Export all properties */
+ opal_export_attrs();
+
/* Initialize platform devices: IPMI backend, PRD & flash interface */
opal_pdev_init("ibm,opal-ipmi");
opal_pdev_init("ibm,opal-flash");
@@ -899,3 +967,4 @@ EXPORT_SYMBOL_GPL(opal_leds_set_ind);
EXPORT_SYMBOL_GPL(opal_write_oppanel_async);
/* Export this for KVM */
EXPORT_SYMBOL_GPL(opal_int_set_mfrr);
+EXPORT_SYMBOL_GPL(opal_int_eoi);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 6901a06da2f9..283caf1070c9 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -14,7 +14,6 @@
#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/crash_dump.h>
-#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/string.h>
#include <linux/init.h>
@@ -38,7 +37,7 @@
#include <asm/iommu.h>
#include <asm/tce.h>
#include <asm/xics.h>
-#include <asm/debug.h>
+#include <asm/debugfs.h>
#include <asm/firmware.h>
#include <asm/pnv-pci.h>
#include <asm/mmzone.h>
@@ -1262,6 +1261,8 @@ static void pnv_pci_ioda_setup_PEs(void)
/* PE#0 is needed for error reporting */
pnv_ioda_reserve_pe(phb, 0);
pnv_ioda_setup_npu_PEs(hose->bus);
+ if (phb->model == PNV_PHB_MODEL_NPU2)
+ pnv_npu2_init(phb);
}
}
}
@@ -1424,8 +1425,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
iommu_group_put(pe->table_group.group);
BUG_ON(pe->table_group.group);
}
- pnv_pci_ioda2_table_free_pages(tbl);
- iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
+ iommu_tce_table_put(tbl);
}
static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
@@ -1775,17 +1775,20 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
}
static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
- struct pci_bus *bus)
+ struct pci_bus *bus,
+ bool add_to_group)
{
struct pci_dev *dev;
list_for_each_entry(dev, &bus->devices, bus_list) {
set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
set_dma_offset(&dev->dev, pe->tce_bypass_base);
- iommu_add_device(&dev->dev);
+ if (add_to_group)
+ iommu_add_device(&dev->dev);
if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
- pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+ pnv_ioda_setup_bus_dma(pe, dev->subordinate,
+ add_to_group);
}
}
@@ -1857,6 +1860,17 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
return ret;
}
+
+static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
+ unsigned long *hpa, enum dma_data_direction *direction)
+{
+ long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+ if (!ret)
+ pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
+
+ return ret;
+}
#endif
static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
@@ -1871,6 +1885,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
.set = pnv_ioda1_tce_build,
#ifdef CONFIG_IOMMU_API
.exchange = pnv_ioda1_tce_xchg,
+ .exchange_rm = pnv_ioda1_tce_xchg_rm,
#endif
.clear = pnv_ioda1_tce_free,
.get = pnv_tce_get,
@@ -1880,7 +1895,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
#define PHB3_TCE_KILL_INVAL_PE PPC_BIT(1)
#define PHB3_TCE_KILL_INVAL_ONE PPC_BIT(2)
-void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
+static void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
{
__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
const unsigned long val = PHB3_TCE_KILL_INVAL_ALL;
@@ -1945,7 +1960,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
{
struct iommu_table_group_link *tgl;
- list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+ list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) {
struct pnv_ioda_pe *pe = container_of(tgl->table_group,
struct pnv_ioda_pe, table_group);
struct pnv_phb *phb = pe->phb;
@@ -1976,6 +1991,14 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
}
}
+void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
+{
+ if (phb->model == PNV_PHB_MODEL_NPU || phb->model == PNV_PHB_MODEL_PHB3)
+ pnv_pci_phb3_tce_invalidate_entire(phb, rm);
+ else
+ opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL, 0, 0, 0, 0);
+}
+
static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
long npages, unsigned long uaddr,
enum dma_data_direction direction,
@@ -2001,6 +2024,17 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
return ret;
}
+
+static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
+ unsigned long *hpa, enum dma_data_direction *direction)
+{
+ long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+ if (!ret)
+ pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
+
+ return ret;
+}
#endif
static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
@@ -2014,13 +2048,13 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
static void pnv_ioda2_table_free(struct iommu_table *tbl)
{
pnv_pci_ioda2_table_free_pages(tbl);
- iommu_free_table(tbl, "pnv");
}
static struct iommu_table_ops pnv_ioda2_iommu_ops = {
.set = pnv_ioda2_tce_build,
#ifdef CONFIG_IOMMU_API
.exchange = pnv_ioda2_tce_xchg,
+ .exchange_rm = pnv_ioda2_tce_xchg_rm,
#endif
.clear = pnv_ioda2_tce_free,
.get = pnv_tce_get,
@@ -2125,6 +2159,9 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
found:
tbl = pnv_pci_table_alloc(phb->hose->node);
+ if (WARN_ON(!tbl))
+ return;
+
iommu_register_group(&pe->table_group, phb->hose->global_number,
pe->pe_number);
pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
@@ -2191,7 +2228,7 @@ found:
set_iommu_table_base(&pe->pdev->dev, tbl);
iommu_add_device(&pe->pdev->dev);
} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
- pnv_ioda_setup_bus_dma(pe, pe->pbus);
+ pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
return;
fail:
@@ -2200,7 +2237,7 @@ found:
__free_pages(tce_mem, get_order(tce32_segsz * segs));
if (tbl) {
pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
- iommu_free_table(tbl, "pnv");
+ iommu_tce_table_put(tbl);
}
}
@@ -2290,16 +2327,16 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
if (!tbl)
return -ENOMEM;
+ tbl->it_ops = &pnv_ioda2_iommu_ops;
+
ret = pnv_pci_ioda2_table_alloc_pages(nid,
bus_offset, page_shift, window_size,
levels, tbl);
if (ret) {
- iommu_free_table(tbl, "pnv");
+ iommu_tce_table_put(tbl);
return ret;
}
- tbl->it_ops = &pnv_ioda2_iommu_ops;
-
*ptbl = tbl;
return 0;
@@ -2340,7 +2377,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
if (rc) {
pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
rc);
- pnv_ioda2_table_free(tbl);
+ iommu_tce_table_put(tbl);
return rc;
}
@@ -2411,7 +2448,8 @@ static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
tce_table_size /= direct_table_size;
tce_table_size <<= 3;
- tce_table_size = _ALIGN_UP(tce_table_size, direct_table_size);
+ tce_table_size = max_t(unsigned long,
+ tce_table_size, direct_table_size);
}
return bytes;
@@ -2426,7 +2464,9 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
pnv_pci_ioda2_set_bypass(pe, false);
pnv_pci_ioda2_unset_window(&pe->table_group, 0);
- pnv_ioda2_table_free(tbl);
+ if (pe->pbus)
+ pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
+ iommu_tce_table_put(tbl);
}
static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
@@ -2435,6 +2475,8 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
table_group);
pnv_pci_ioda2_setup_default_config(pe);
+ if (pe->pbus)
+ pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
}
static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
@@ -2624,6 +2666,9 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
level_shift = entries_shift + 3;
level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
+ if ((level_shift - 3) * levels + page_shift >= 60)
+ return -EINVAL;
+
/* Allocate TCE table */
addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
levels, tce_table_size, &offset, &total_allocated);
@@ -2725,10 +2770,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
if (rc)
return;
- if (pe->flags & PNV_IODA_PE_DEV)
- iommu_add_device(&pe->pdev->dev);
- else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
- pnv_ioda_setup_bus_dma(pe, pe->pbus);
+ if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
+ pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
}
#ifdef CONFIG_PCI_MSI
@@ -3287,6 +3330,11 @@ static void pnv_pci_setup_bridge(struct pci_bus *bus, unsigned long type)
}
}
+static resource_size_t pnv_pci_default_alignment(void)
+{
+ return PAGE_SIZE;
+}
+
#ifdef CONFIG_PCI_IOV
static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
int resno)
@@ -3396,7 +3444,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
}
free_pages(tbl->it_base, get_order(tbl->it_size << 3));
- iommu_free_table(tbl, "pnv");
+ iommu_tce_table_put(tbl);
}
static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
@@ -3423,7 +3471,7 @@ static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
}
pnv_pci_ioda2_table_free_pages(tbl);
- iommu_free_table(tbl, "pnv");
+ iommu_tce_table_put(tbl);
}
static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,
@@ -3820,6 +3868,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
hose->controller_ops = pnv_pci_ioda_controller_ops;
}
+ ppc_md.pcibios_default_alignment = pnv_pci_default_alignment;
+
#ifdef CONFIG_PCI_IOV
ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index eb835e977e33..935ccb249a8a 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -758,7 +758,7 @@ void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
{
- return *(pnv_tce(tbl, index - tbl->it_offset));
+ return be64_to_cpu(*(pnv_tce(tbl, index - tbl->it_offset)));
}
struct iommu_table *pnv_pci_table_alloc(int nid)
@@ -766,7 +766,11 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
struct iommu_table *tbl;
tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid);
+ if (!tbl)
+ return NULL;
+
INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+ kref_init(&tbl->it_kref);
return tbl;
}
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index e1d3e5526b54..18c8a2fa03b8 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -7,6 +7,9 @@
struct pci_dn;
+/* Maximum possible number of ATSD MMIO registers per NPU */
+#define NV_NMMU_ATSD_REGS 8
+
enum pnv_phb_type {
PNV_PHB_IODA1 = 0,
PNV_PHB_IODA2 = 1,
@@ -174,6 +177,16 @@ struct pnv_phb {
struct OpalIoP7IOCErrorData hub_diag;
} diag;
+ /* Nvlink2 data */
+ struct npu {
+ int index;
+ __be64 *mmio_atsd_regs[NV_NMMU_ATSD_REGS];
+ unsigned int mmio_atsd_count;
+
+ /* Bitmask for MMIO register usage */
+ unsigned long mmio_atsd_usage;
+ } npu;
+
#ifdef CONFIG_CXL_BASE
struct cxl_afu *cxl_afu;
#endif
@@ -229,14 +242,14 @@ extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
/* Nvlink functions */
extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass);
-extern void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
+extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
extern struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe);
extern long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
struct iommu_table *tbl);
extern long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num);
extern void pnv_npu_take_ownership(struct pnv_ioda_pe *npe);
extern void pnv_npu_release_ownership(struct pnv_ioda_pe *npe);
-
+extern int pnv_npu2_init(struct pnv_phb *phb);
/* cxl functions */
extern bool pnv_cxl_enable_device_hook(struct pci_dev *dev);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 613052232475..6dbc0a1da1f6 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -18,8 +18,6 @@ static inline void pnv_pci_shutdown(void) { }
#endif
extern u32 pnv_get_supported_cpuidle_states(void);
-extern u64 pnv_deepest_stop_psscr_val;
-extern u64 pnv_deepest_stop_psscr_mask;
extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c
index 5dcbdea1afac..1a9d84371a4d 100644
--- a/arch/powerpc/platforms/powernv/rng.c
+++ b/arch/powerpc/platforms/powernv/rng.c
@@ -62,7 +62,7 @@ int powernv_get_random_real_mode(unsigned long *v)
rng = raw_cpu_read(powernv_rng);
- *v = rng_whiten(rng, in_rm64(rng->regs_real));
+ *v = rng_whiten(rng, __raw_rm_readq(rng->regs_real));
return 1;
}
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index d50c7d99baaf..2dc7e5fb86c3 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -32,6 +32,7 @@
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/xics.h>
+#include <asm/xive.h>
#include <asm/opal.h>
#include <asm/kexec.h>
#include <asm/smp.h>
@@ -76,7 +77,9 @@ static void __init pnv_init(void)
static void __init pnv_init_IRQ(void)
{
- xics_init();
+ /* Try using a XIVE if available, otherwise use a XICS */
+ if (!xive_native_init())
+ xics_init();
WARN_ON(!ppc_md.get_irq);
}
@@ -95,6 +98,10 @@ static void pnv_show_cpuinfo(struct seq_file *m)
else
seq_printf(m, "firmware\t: BML\n");
of_node_put(root);
+ if (radix_enabled())
+ seq_printf(m, "MMU\t\t: Radix\n");
+ else
+ seq_printf(m, "MMU\t\t: Hash\n");
}
static void pnv_prepare_going_down(void)
@@ -218,10 +225,12 @@ static void pnv_kexec_wait_secondaries_down(void)
static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
{
- xics_kexec_teardown_cpu(secondary);
+ if (xive_enabled())
+ xive_kexec_teardown_cpu(secondary);
+ else
+ xics_kexec_teardown_cpu(secondary);
/* On OPAL, we return all CPUs to firmware */
-
if (!firmware_has_feature(FW_FEATURE_OPAL))
return;
@@ -237,6 +246,10 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
/* Primary waits for the secondaries to have reached OPAL */
pnv_kexec_wait_secondaries_down();
+ /* Switch XIVE back to emulation mode */
+ if (xive_enabled())
+ xive_shutdown();
+
/*
* We might be running as little-endian - now that interrupts
* are disabled, reset the HILE bit to big-endian so we don't
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 8b67e1eefb5c..4aff754b6f2c 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -29,12 +29,14 @@
#include <asm/vdso_datapage.h>
#include <asm/cputhreads.h>
#include <asm/xics.h>
+#include <asm/xive.h>
#include <asm/opal.h>
#include <asm/runlatch.h>
#include <asm/code-patching.h>
#include <asm/dbell.h>
#include <asm/kvm_ppc.h>
#include <asm/ppc-opcode.h>
+#include <asm/cpuidle.h>
#include "powernv.h"
@@ -47,13 +49,10 @@
static void pnv_smp_setup_cpu(int cpu)
{
- if (cpu != boot_cpuid)
+ if (xive_enabled())
+ xive_smp_setup_cpu();
+ else if (cpu != boot_cpuid)
xics_setup_cpu();
-
-#ifdef CONFIG_PPC_DOORBELL
- if (cpu_has_feature(CPU_FTR_DBELL))
- doorbell_setup_this_cpu();
-#endif
}
static int pnv_smp_kick_cpu(int nr)
@@ -132,7 +131,10 @@ static int pnv_smp_cpu_disable(void)
vdso_data->processorCount--;
if (cpu == boot_cpuid)
boot_cpuid = cpumask_any(cpu_online_mask);
- xics_migrate_irqs_away();
+ if (xive_enabled())
+ xive_smp_disable_cpu();
+ else
+ xics_migrate_irqs_away();
return 0;
}
@@ -140,7 +142,6 @@ static void pnv_smp_cpu_kill_self(void)
{
unsigned int cpu;
unsigned long srr1, wmask;
- u32 idle_states;
/* Standard hot unplug procedure */
local_irq_disable();
@@ -155,8 +156,6 @@ static void pnv_smp_cpu_kill_self(void)
if (cpu_has_feature(CPU_FTR_ARCH_207S))
wmask = SRR1_WAKEMASK_P8;
- idle_states = pnv_get_supported_cpuidle_states();
-
/* We don't want to take decrementer interrupts while we are offline,
* so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9)
* enabled as to let IPIs in.
@@ -184,19 +183,7 @@ static void pnv_smp_cpu_kill_self(void)
kvmppc_set_host_ipi(cpu, 0);
ppc64_runlatch_off();
-
- if (cpu_has_feature(CPU_FTR_ARCH_300)) {
- srr1 = power9_idle_stop(pnv_deepest_stop_psscr_val,
- pnv_deepest_stop_psscr_mask);
- } else if (idle_states & OPAL_PM_WINKLE_ENABLED) {
- srr1 = power7_winkle();
- } else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
- (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
- srr1 = power7_sleep();
- } else {
- srr1 = power7_nap(1);
- }
-
+ srr1 = pnv_cpu_offline(cpu);
ppc64_runlatch_on();
/*
@@ -213,9 +200,12 @@ static void pnv_smp_cpu_kill_self(void)
if (((srr1 & wmask) == SRR1_WAKEEE) ||
((srr1 & wmask) == SRR1_WAKEHVI) ||
(local_paca->irq_happened & PACA_IRQ_EE)) {
- if (cpu_has_feature(CPU_FTR_ARCH_300))
- icp_opal_flush_interrupt();
- else
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (xive_enabled())
+ xive_flush_interrupt();
+ else
+ icp_opal_flush_interrupt();
+ } else
icp_native_flush_interrupt();
} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
@@ -252,10 +242,69 @@ static int pnv_cpu_bootable(unsigned int nr)
return smp_generic_cpu_bootable(nr);
}
+static int pnv_smp_prepare_cpu(int cpu)
+{
+ if (xive_enabled())
+ return xive_smp_prepare_cpu(cpu);
+ return 0;
+}
+
+/* Cause IPI as setup by the interrupt controller (xics or xive) */
+static void (*ic_cause_ipi)(int cpu);
+
+static void pnv_cause_ipi(int cpu)
+{
+ if (doorbell_try_core_ipi(cpu))
+ return;
+
+ ic_cause_ipi(cpu);
+}
+
+static void pnv_p9_dd1_cause_ipi(int cpu)
+{
+ int this_cpu = get_cpu();
+
+ /*
+ * POWER9 DD1 has a global addressed msgsnd, but for now we restrict
+ * IPIs to same core, because it requires additional synchronization
+ * for inter-core doorbells which we do not implement.
+ */
+ if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu)))
+ doorbell_global_ipi(cpu);
+ else
+ ic_cause_ipi(cpu);
+
+ put_cpu();
+}
+
+static void __init pnv_smp_probe(void)
+{
+ if (xive_enabled())
+ xive_smp_probe();
+ else
+ xics_smp_probe();
+
+ if (cpu_has_feature(CPU_FTR_DBELL)) {
+ ic_cause_ipi = smp_ops->cause_ipi;
+ WARN_ON(!ic_cause_ipi);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+ smp_ops->cause_ipi = pnv_p9_dd1_cause_ipi;
+ else
+ smp_ops->cause_ipi = doorbell_global_ipi;
+ } else {
+ smp_ops->cause_ipi = pnv_cause_ipi;
+ }
+ }
+}
+
static struct smp_ops_t pnv_smp_ops = {
- .message_pass = smp_muxed_ipi_message_pass,
- .cause_ipi = NULL, /* Filled at runtime by xics_smp_probe() */
- .probe = xics_smp_probe,
+ .message_pass = NULL, /* Use smp_muxed_ipi_message_pass */
+ .cause_ipi = NULL, /* Filled at runtime by pnv_smp_probe() */
+ .cause_nmi_ipi = NULL,
+ .probe = pnv_smp_probe,
+ .prepare_cpu = pnv_smp_prepare_cpu,
.kick_cpu = pnv_smp_kick_cpu,
.setup_cpu = pnv_smp_setup_cpu,
.cpu_bootable = pnv_cpu_bootable,
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index 60154d08debf..1d1ad5df106f 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -77,7 +77,7 @@ static void __init ps3_smp_probe(void)
BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION != 0);
BUILD_BUG_ON(PPC_MSG_RESCHEDULE != 1);
BUILD_BUG_ON(PPC_MSG_TICK_BROADCAST != 2);
- BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK != 3);
+ BUILD_BUG_ON(PPC_MSG_NMI_IPI != 3);
for (i = 0; i < MSG_COUNT; i++) {
result = ps3_event_receive_port_setup(cpu, &virqs[i]);
@@ -96,7 +96,7 @@ static void __init ps3_smp_probe(void)
ps3_register_ipi_irq(cpu, virqs[i]);
}
- ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
+ ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_NMI_IPI]);
DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
}
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 30ec04f1c67c..913c54e23eea 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -17,9 +17,10 @@ config PPC_PSERIES
select PPC_UDBG_16550
select PPC_NATIVE
select PPC_DOORBELL
- select HOTPLUG_CPU if SMP
+ select HOTPLUG_CPU
select ARCH_RANDOM
select PPC_DOORBELL
+ select FORCE_SMP
default y
config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 193e052fa0dd..bda18d8e1674 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -288,7 +288,6 @@ int dlpar_detach_node(struct device_node *dn)
if (rc)
return rc;
- of_node_put(dn); /* Must decrement the refcount */
return 0;
}
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 6b04e3f0f982..18014cdeb590 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -21,13 +21,12 @@
*/
#include <linux/slab.h>
-#include <linux/debugfs.h>
#include <linux/spinlock.h>
#include <asm/smp.h>
#include <linux/uaccess.h>
#include <asm/firmware.h>
#include <asm/lppaca.h>
-#include <asm/debug.h>
+#include <asm/debugfs.h>
#include <asm/plpar_wrappers.h>
#include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index f02ec3ab428c..957ae347b0b3 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -29,6 +29,16 @@
#include <asm/trace.h>
#include <asm/machdep.h>
+/* For hcall instrumentation. One structure per-hcall, per-CPU */
+struct hcall_stats {
+ unsigned long num_calls; /* number of calls (on this CPU) */
+ unsigned long tb_total; /* total wall time (mftb) of calls. */
+ unsigned long purr_total; /* total cpu time (PURR) of calls. */
+ unsigned long tb_start;
+ unsigned long purr_start;
+};
+#define HCALL_STAT_ARRAY_SIZE ((MAX_HCALL_OPCODE >> 2) + 1)
+
DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats);
/*
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index 99a6bf7f3bcf..b363e439ddb9 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -410,10 +410,7 @@ static ssize_t name_show(struct device *dev,
static ssize_t modalias_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- ssize_t len = of_device_get_modalias(dev, buf, PAGE_SIZE - 2);
- buf[len] = '\n';
- buf[len+1] = 0;
- return len+1;
+ return of_device_modalias(dev, buf, PAGE_SIZE);
}
static struct device_attribute ibmebus_bus_device_attrs[] = {
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 4d757eaa46bf..8374adee27e3 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -74,6 +74,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
goto fail_exit;
INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+ kref_init(&tbl->it_kref);
tgl->table_group = table_group;
list_add_rcu(&tgl->next, &tbl->it_group_list);
@@ -115,7 +116,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
BUG_ON(table_group->group);
}
#endif
- iommu_free_table(tbl, node_name);
+ iommu_tce_table_put(tbl);
kfree(table_group);
}
@@ -550,6 +551,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
static void iommu_table_setparms_lpar(struct pci_controller *phb,
struct device_node *dn,
struct iommu_table *tbl,
+ struct iommu_table_group *table_group,
const __be32 *dma_window)
{
unsigned long offset, size;
@@ -563,6 +565,9 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
tbl->it_type = TCE_PCI;
tbl->it_offset = offset >> tbl->it_page_shift;
tbl->it_size = size >> tbl->it_page_shift;
+
+ table_group->tce32_start = offset;
+ table_group->tce32_size = size;
}
struct iommu_table_ops iommu_table_pseries_ops = {
@@ -651,8 +656,38 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
pr_debug("ISA/IDE, window size is 0x%llx\n", pci->phb->dma_window_size);
}
+#ifdef CONFIG_IOMMU_API
+static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
+ long *tce, enum dma_data_direction *direction)
+{
+ long rc;
+ unsigned long ioba = (unsigned long) index << tbl->it_page_shift;
+ unsigned long flags, oldtce = 0;
+ u64 proto_tce = iommu_direction_to_tce_perm(*direction);
+ unsigned long newtce = *tce | proto_tce;
+
+ spin_lock_irqsave(&tbl->large_pool.lock, flags);
+
+ rc = plpar_tce_get((u64)tbl->it_index, ioba, &oldtce);
+ if (!rc)
+ rc = plpar_tce_put((u64)tbl->it_index, ioba, newtce);
+
+ if (!rc) {
+ *direction = iommu_tce_direction(oldtce);
+ *tce = oldtce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+ }
+
+ spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
+
+ return rc;
+}
+#endif
+
struct iommu_table_ops iommu_table_lpar_multi_ops = {
.set = tce_buildmulti_pSeriesLP,
+#ifdef CONFIG_IOMMU_API
+ .exchange = tce_exchange_pseries,
+#endif
.clear = tce_freemulti_pSeriesLP,
.get = tce_get_pSeriesLP
};
@@ -689,7 +724,8 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
if (!ppci->table_group) {
ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
tbl = ppci->table_group->tables[0];
- iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
+ iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
+ ppci->table_group, dma_window);
tbl->it_ops = &iommu_table_lpar_multi_ops;
iommu_init_table(tbl, ppci->phb->node);
iommu_register_group(ppci->table_group,
@@ -1143,7 +1179,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
if (!pci->table_group) {
pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
tbl = pci->table_group->tables[0];
- iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
+ iommu_table_setparms_lpar(pci->phb, pdn, tbl,
+ pci->table_group, dma_window);
tbl->it_ops = &iommu_table_lpar_multi_ops;
iommu_init_table(tbl, pci->phb->node);
iommu_register_group(pci->table_group,
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 251060cf1713..6541d0b03e4c 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -751,7 +751,9 @@ void __init hpte_init_pseries(void)
mmu_hash_ops.flush_hash_range = pSeries_lpar_flush_hash_range;
mmu_hash_ops.hpte_clear_all = pseries_hpte_clear_all;
mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
- mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
+
+ if (firmware_has_feature(FW_FEATURE_HPT_RESIZE))
+ mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
}
void radix_init_pseries(void)
@@ -956,3 +958,64 @@ int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data)
return rc;
}
+
+static unsigned long vsid_unscramble(unsigned long vsid, int ssize)
+{
+ unsigned long protovsid;
+ unsigned long va_bits = VA_BITS;
+ unsigned long modinv, vsid_modulus;
+ unsigned long max_mod_inv, tmp_modinv;
+
+ if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
+ va_bits = 65;
+
+ if (ssize == MMU_SEGSIZE_256M) {
+ modinv = VSID_MULINV_256M;
+ vsid_modulus = ((1UL << (va_bits - SID_SHIFT)) - 1);
+ } else {
+ modinv = VSID_MULINV_1T;
+ vsid_modulus = ((1UL << (va_bits - SID_SHIFT_1T)) - 1);
+ }
+
+ /*
+ * vsid outside our range.
+ */
+ if (vsid >= vsid_modulus)
+ return 0;
+
+ /*
+ * If modinv is the modular multiplicate inverse of (x % vsid_modulus)
+ * and vsid = (protovsid * x) % vsid_modulus, then we say:
+ * protovsid = (vsid * modinv) % vsid_modulus
+ */
+
+ /* Check if (vsid * modinv) overflow (63 bits) */
+ max_mod_inv = 0x7fffffffffffffffull / vsid;
+ if (modinv < max_mod_inv)
+ return (vsid * modinv) % vsid_modulus;
+
+ tmp_modinv = modinv/max_mod_inv;
+ modinv %= max_mod_inv;
+
+ protovsid = (((vsid * max_mod_inv) % vsid_modulus) * tmp_modinv) % vsid_modulus;
+ protovsid = (protovsid + vsid * modinv) % vsid_modulus;
+
+ return protovsid;
+}
+
+static int __init reserve_vrma_context_id(void)
+{
+ unsigned long protovsid;
+
+ /*
+ * Reserve context ids which map to reserved virtual addresses. For now
+ * we only reserve the context id which maps to the VRMA VSID. We ignore
+ * the addresses in "ibm,adjunct-virtual-addresses" because we don't
+ * enable adjunct support via the "ibm,client-architecture-support"
+ * interface.
+ */
+ protovsid = vsid_unscramble(VRMA_VSID, MMU_SEGSIZE_1T);
+ hash__reserve_context_id(protovsid >> ESID_BITS_1T);
+ return 0;
+}
+machine_device_initcall(pseries, reserve_vrma_context_id);
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 904a677208d1..bb70b26334f0 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -386,6 +386,10 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
}
fwnmi_release_errinfo();
}
+
+ if (smp_handle_nmi_ipi(regs))
+ return 1;
+
return 0; /* need to perform reset */
}
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index b4d362ed03a1..b5d86426e97b 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -87,6 +87,10 @@ static void pSeries_show_cpuinfo(struct seq_file *m)
model = of_get_property(root, "model", NULL);
seq_printf(m, "machine\t\t: CHRP %s\n", model);
of_node_put(root);
+ if (radix_enabled())
+ seq_printf(m, "MMU\t\t: Radix\n");
+ else
+ seq_printf(m, "MMU\t\t: Hash\n");
}
/* Initialize firmware assisted non-maskable interrupts if
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index f6f83aeccaaa..52ca6b311d44 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -55,11 +55,6 @@
*/
static cpumask_var_t of_spin_mask;
-/*
- * If we multiplex IPI mechanisms, store the appropriate XICS IPI mechanism here
- */
-static void (*xics_cause_ipi)(int cpu, unsigned long data);
-
/* Query where a cpu is now. Return codes #defined in plpar_wrappers.h */
int smp_query_cpu_stopped(unsigned int pcpu)
{
@@ -143,8 +138,6 @@ static void smp_setup_cpu(int cpu)
{
if (cpu != boot_cpuid)
xics_setup_cpu();
- if (cpu_has_feature(CPU_FTR_DBELL))
- doorbell_setup_this_cpu();
if (firmware_has_feature(FW_FEATURE_SPLPAR))
vpa_init(cpu);
@@ -187,28 +180,50 @@ static int smp_pSeries_kick_cpu(int nr)
return 0;
}
-/* Only used on systems that support multiple IPI mechanisms */
-static void pSeries_cause_ipi_mux(int cpu, unsigned long data)
+static void smp_pseries_cause_ipi(int cpu)
{
- if (cpumask_test_cpu(cpu, cpu_sibling_mask(smp_processor_id())))
- doorbell_cause_ipi(cpu, data);
- else
- xics_cause_ipi(cpu, data);
+ /* POWER9 should not use this handler */
+ if (doorbell_try_core_ipi(cpu))
+ return;
+
+ icp_ops->cause_ipi(cpu);
+}
+
+static int pseries_cause_nmi_ipi(int cpu)
+{
+ int hwcpu;
+
+ if (cpu == NMI_IPI_ALL_OTHERS) {
+ hwcpu = H_SIGNAL_SYS_RESET_ALL_OTHERS;
+ } else {
+ if (cpu < 0) {
+ WARN_ONCE(true, "incorrect cpu parameter %d", cpu);
+ return 0;
+ }
+
+ hwcpu = get_hard_smp_processor_id(cpu);
+ }
+
+ if (plapr_signal_sys_reset(hwcpu) == H_SUCCESS)
+ return 1;
+
+ return 0;
}
static __init void pSeries_smp_probe(void)
{
xics_smp_probe();
- if (cpu_has_feature(CPU_FTR_DBELL)) {
- xics_cause_ipi = smp_ops->cause_ipi;
- smp_ops->cause_ipi = pSeries_cause_ipi_mux;
- }
+ if (cpu_has_feature(CPU_FTR_DBELL))
+ smp_ops->cause_ipi = smp_pseries_cause_ipi;
+ else
+ smp_ops->cause_ipi = icp_ops->cause_ipi;
}
static struct smp_ops_t pseries_smp_ops = {
.message_pass = NULL, /* Use smp_muxed_ipi_message_pass */
.cause_ipi = NULL, /* Filled at runtime by pSeries_smp_probe() */
+ .cause_nmi_ipi = pseries_cause_nmi_ipi,
.probe = pSeries_smp_probe,
.kick_cpu = smp_pSeries_kick_cpu,
.setup_cpu = smp_setup_cpu,
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 720493932486..28b09fd797ec 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1318,7 +1318,7 @@ static void vio_dev_release(struct device *dev)
struct iommu_table *tbl = get_iommu_table_base(dev);
if (tbl)
- iommu_free_table(tbl, of_node_full_name(dev->of_node));
+ iommu_tce_table_put(tbl);
of_node_put(dev->of_node);
kfree(to_vio_dev(dev));
}
diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S
index f9760ccf4032..3696ea6c4826 100644
--- a/arch/powerpc/purgatory/trampoline.S
+++ b/arch/powerpc/purgatory/trampoline.S
@@ -116,13 +116,13 @@ dt_offset:
.data
.balign 8
-.globl sha256_digest
-sha256_digest:
+.globl purgatory_sha256_digest
+purgatory_sha256_digest:
.skip 32
- .size sha256_digest, . - sha256_digest
+ .size purgatory_sha256_digest, . - purgatory_sha256_digest
.balign 8
-.globl sha_regions
-sha_regions:
+.globl purgatory_sha_regions
+purgatory_sha_regions:
.skip 8 * 2 * 16
- .size sha_regions, . - sha_regions
+ .size purgatory_sha_regions, . - purgatory_sha_regions
diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig
index 52dc165c0efb..caf882e749dc 100644
--- a/arch/powerpc/sysdev/Kconfig
+++ b/arch/powerpc/sysdev/Kconfig
@@ -28,6 +28,7 @@ config PPC_MSI_BITMAP
default y if PPC_POWERNV
source "arch/powerpc/sysdev/xics/Kconfig"
+source "arch/powerpc/sysdev/xive/Kconfig"
config PPC_SCOM
bool
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index a254824719f1..c0ae11d4f62f 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -71,5 +71,6 @@ obj-$(CONFIG_PPC_EARLY_DEBUG_MEMCONS) += udbg_memcons.o
subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
obj-$(CONFIG_PPC_XICS) += xics/
+obj-$(CONFIG_PPC_XIVE) += xive/
obj-$(CONFIG_GE_FPGA) += ge/
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ada29eaed6e2..a7fe5fee744f 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -25,6 +25,7 @@
#include <linux/bio.h>
#include <linux/blkdev.h>
+#include <linux/dax.h>
#include <linux/device.h>
#include <linux/errno.h>
#include <linux/fs.h>
@@ -62,6 +63,7 @@ static int azfs_major, azfs_minor;
struct axon_ram_bank {
struct platform_device *device;
struct gendisk *disk;
+ struct dax_device *dax_dev;
unsigned int irq_id;
unsigned long ph_addr;
unsigned long io_addr;
@@ -137,25 +139,32 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
return BLK_QC_T_NONE;
}
-/**
- * axon_ram_direct_access - direct_access() method for block device
- * @device, @sector, @data: see block_device_operations method
- */
+static const struct block_device_operations axon_ram_devops = {
+ .owner = THIS_MODULE,
+};
+
static long
-axon_ram_direct_access(struct block_device *device, sector_t sector,
- void **kaddr, pfn_t *pfn, long size)
+__axon_ram_direct_access(struct axon_ram_bank *bank, pgoff_t pgoff, long nr_pages,
+ void **kaddr, pfn_t *pfn)
{
- struct axon_ram_bank *bank = device->bd_disk->private_data;
- loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
+ resource_size_t offset = pgoff * PAGE_SIZE;
*kaddr = (void *) bank->io_addr + offset;
*pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV);
- return bank->size - offset;
+ return (bank->size - offset) / PAGE_SIZE;
}
-static const struct block_device_operations axon_ram_devops = {
- .owner = THIS_MODULE,
- .direct_access = axon_ram_direct_access
+static long
+axon_ram_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
+ void **kaddr, pfn_t *pfn)
+{
+ struct axon_ram_bank *bank = dax_get_private(dax_dev);
+
+ return __axon_ram_direct_access(bank, pgoff, nr_pages, kaddr, pfn);
+}
+
+static const struct dax_operations axon_ram_dax_ops = {
+ .direct_access = axon_ram_dax_direct_access,
};
/**
@@ -219,6 +228,7 @@ static int axon_ram_probe(struct platform_device *device)
goto failed;
}
+
bank->disk->major = azfs_major;
bank->disk->first_minor = azfs_minor;
bank->disk->fops = &axon_ram_devops;
@@ -227,6 +237,13 @@ static int axon_ram_probe(struct platform_device *device)
sprintf(bank->disk->disk_name, "%s%d",
AXON_RAM_DEVICE_NAME, axon_ram_bank_id);
+ bank->dax_dev = alloc_dax(bank, bank->disk->disk_name,
+ &axon_ram_dax_ops);
+ if (!bank->dax_dev) {
+ rc = -ENOMEM;
+ goto failed;
+ }
+
bank->disk->queue = blk_alloc_queue(GFP_KERNEL);
if (bank->disk->queue == NULL) {
dev_err(&device->dev, "Cannot register disk queue\n");
@@ -274,8 +291,12 @@ failed:
if (bank->disk->major > 0)
unregister_blkdev(bank->disk->major,
bank->disk->disk_name);
- del_gendisk(bank->disk);
+ if (bank->disk->flags & GENHD_FL_UP)
+ del_gendisk(bank->disk);
+ put_disk(bank->disk);
}
+ kill_dax(bank->dax_dev);
+ put_dax(bank->dax_dev);
device->dev.platform_data = NULL;
if (bank->io_addr != 0)
iounmap((void __iomem *) bank->io_addr);
@@ -298,7 +319,10 @@ axon_ram_remove(struct platform_device *device)
device_remove_file(&device->dev, &dev_attr_ecc);
free_irq(bank->irq_id, device);
+ kill_dax(bank->dax_dev);
+ put_dax(bank->dax_dev);
del_gendisk(bank->disk);
+ put_disk(bank->disk);
iounmap((void __iomem *) bank->io_addr);
kfree(bank);
diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c
index d0e9f178a324..76ea32c1b664 100644
--- a/arch/powerpc/sysdev/scom.c
+++ b/arch/powerpc/sysdev/scom.c
@@ -19,10 +19,9 @@
*/
#include <linux/kernel.h>
-#include <linux/debugfs.h>
#include <linux/slab.h>
#include <linux/export.h>
-#include <asm/debug.h>
+#include <asm/debugfs.h>
#include <asm/prom.h>
#include <asm/scom.h>
#include <linux/uaccess.h>
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index e7fa26c4ff73..bbc839a98c41 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -138,7 +138,7 @@ static void icp_hv_set_cpu_priority(unsigned char cppr)
#ifdef CONFIG_SMP
-static void icp_hv_cause_ipi(int cpu, unsigned long data)
+static void icp_hv_cause_ipi(int cpu)
{
icp_hv_set_qirr(cpu, IPI_PRIORITY);
}
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 8a6a043e239b..2bfb9968d562 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -143,19 +143,9 @@ static unsigned int icp_native_get_irq(void)
#ifdef CONFIG_SMP
-static void icp_native_cause_ipi(int cpu, unsigned long data)
+static void icp_native_cause_ipi(int cpu)
{
kvmppc_set_host_ipi(cpu, 1);
-#ifdef CONFIG_PPC_DOORBELL
- if (cpu_has_feature(CPU_FTR_DBELL)) {
- if (cpumask_test_cpu(cpu, cpu_sibling_mask(get_cpu()))) {
- doorbell_cause_ipi(cpu, data);
- put_cpu();
- return;
- }
- put_cpu();
- }
-#endif
icp_native_set_qirr(cpu, IPI_PRIORITY);
}
@@ -168,15 +158,15 @@ void icp_native_cause_ipi_rm(int cpu)
* Need the physical address of the XICS to be
* previously saved in kvm_hstate in the paca.
*/
- unsigned long xics_phys;
+ void __iomem *xics_phys;
/*
* Just like the cause_ipi functions, it is required to
- * include a full barrier (out8 includes a sync) before
- * causing the IPI.
+ * include a full barrier before causing the IPI.
*/
xics_phys = paca[cpu].kvm_hstate.xics_phys;
- out_rm8((u8 *)(xics_phys + XICS_MFRR), IPI_PRIORITY);
+ mb();
+ __raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
}
#endif
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index f9670eabfcfa..c71d2ea42627 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -91,6 +91,16 @@ static unsigned int icp_opal_get_irq(void)
static void icp_opal_set_cpu_priority(unsigned char cppr)
{
+ /*
+ * Here be dragons. The caller has asked to allow only IPI's and not
+ * external interrupts. But OPAL XIVE doesn't support that. So instead
+ * of allowing no interrupts allow all. That's still not right, but
+ * currently the only caller who does this is xics_migrate_irqs_away()
+ * and it works in that case.
+ */
+ if (cppr >= DEFAULT_PRIORITY)
+ cppr = LOWEST_PRIORITY;
+
xics_set_base_cppr(cppr);
opal_int_set_cppr(cppr);
iosync();
@@ -116,7 +126,7 @@ static void icp_opal_eoi(struct irq_data *d)
#ifdef CONFIG_SMP
-static void icp_opal_cause_ipi(int cpu, unsigned long data)
+static void icp_opal_cause_ipi(int cpu)
{
int hw_cpu = get_hard_smp_processor_id(cpu);
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 69d858e51ac7..ffe138b8b9dc 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -20,6 +20,7 @@
#include <linux/of.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <linux/delay.h>
#include <asm/prom.h>
#include <asm/io.h>
@@ -142,11 +143,11 @@ static void xics_request_ipi(void)
void __init xics_smp_probe(void)
{
- /* Setup cause_ipi callback based on which ICP is used */
- smp_ops->cause_ipi = icp_ops->cause_ipi;
-
/* Register all the IPIs */
xics_request_ipi();
+
+ /* Setup cause_ipi callback based on which ICP is used */
+ smp_ops->cause_ipi = icp_ops->cause_ipi;
}
#endif /* CONFIG_SMP */
@@ -198,9 +199,6 @@ void xics_migrate_irqs_away(void)
/* Remove ourselves from the global interrupt queue */
xics_set_cpu_giq(xics_default_distrib_server, 0);
- /* Allow IPIs again... */
- icp_ops->set_priority(DEFAULT_PRIORITY);
-
for_each_irq_desc(virq, desc) {
struct irq_chip *chip;
long server;
@@ -255,6 +253,19 @@ void xics_migrate_irqs_away(void)
unlock:
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
+
+ /* Allow "sufficient" time to drop any inflight IRQ's */
+ mdelay(5);
+
+ /*
+ * Allow IPIs again. This is done at the very end, after migrating all
+ * interrupts, the expectation is that we'll only get woken up by an IPI
+ * interrupt beyond this point, but leave externals masked just to be
+ * safe. If we're using icp-opal this may actually allow all
+ * interrupts anyway, but that should be OK.
+ */
+ icp_ops->set_priority(DEFAULT_PRIORITY);
+
}
#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/powerpc/sysdev/xive/Kconfig b/arch/powerpc/sysdev/xive/Kconfig
new file mode 100644
index 000000000000..12ccd7373d2f
--- /dev/null
+++ b/arch/powerpc/sysdev/xive/Kconfig
@@ -0,0 +1,11 @@
+config PPC_XIVE
+ bool
+ default n
+ select PPC_SMP_MUXED_IPI
+ select HARDIRQS_SW_RESEND
+
+config PPC_XIVE_NATIVE
+ bool
+ default n
+ select PPC_XIVE
+ depends on PPC_POWERNV
diff --git a/arch/powerpc/sysdev/xive/Makefile b/arch/powerpc/sysdev/xive/Makefile
new file mode 100644
index 000000000000..3fab303fc169
--- /dev/null
+++ b/arch/powerpc/sysdev/xive/Makefile
@@ -0,0 +1,4 @@
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
+obj-y += common.o
+obj-$(CONFIG_PPC_XIVE_NATIVE) += native.o
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
new file mode 100644
index 000000000000..913825086b8d
--- /dev/null
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -0,0 +1,1432 @@
+/*
+ * Copyright 2016,2017 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "xive: " fmt
+
+#include <linux/types.h>
+#include <linux/threads.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/debugfs.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/msi.h>
+
+#include <asm/prom.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/machdep.h>
+#include <asm/irq.h>
+#include <asm/errno.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/xmon.h>
+
+#include "xive-internal.h"
+
+#undef DEBUG_FLUSH
+#undef DEBUG_ALL
+
+#ifdef DEBUG_ALL
+#define DBG_VERBOSE(fmt...) pr_devel(fmt)
+#else
+#define DBG_VERBOSE(fmt...) do { } while(0)
+#endif
+
+bool __xive_enabled;
+EXPORT_SYMBOL_GPL(__xive_enabled);
+bool xive_cmdline_disabled;
+
+/* We use only one priority for now */
+static u8 xive_irq_priority;
+
+/* TIMA exported to KVM */
+void __iomem *xive_tima;
+EXPORT_SYMBOL_GPL(xive_tima);
+u32 xive_tima_offset;
+
+/* Backend ops */
+static const struct xive_ops *xive_ops;
+
+/* Our global interrupt domain */
+static struct irq_domain *xive_irq_domain;
+
+#ifdef CONFIG_SMP
+/* The IPIs all use the same logical irq number */
+static u32 xive_ipi_irq;
+#endif
+
+/* Xive state for each CPU */
+static DEFINE_PER_CPU(struct xive_cpu *, xive_cpu);
+
+/*
+ * A "disabled" interrupt should never fire, to catch problems
+ * we set its logical number to this
+ */
+#define XIVE_BAD_IRQ 0x7fffffff
+#define XIVE_MAX_IRQ (XIVE_BAD_IRQ - 1)
+
+/* An invalid CPU target */
+#define XIVE_INVALID_TARGET (-1)
+
+/*
+ * Read the next entry in a queue, return its content if it's valid
+ * or 0 if there is no new entry.
+ *
+ * The queue pointer is moved forward unless "just_peek" is set
+ */
+static u32 xive_read_eq(struct xive_q *q, bool just_peek)
+{
+ u32 cur;
+
+ if (!q->qpage)
+ return 0;
+ cur = be32_to_cpup(q->qpage + q->idx);
+
+ /* Check valid bit (31) vs current toggle polarity */
+ if ((cur >> 31) == q->toggle)
+ return 0;
+
+ /* If consuming from the queue ... */
+ if (!just_peek) {
+ /* Next entry */
+ q->idx = (q->idx + 1) & q->msk;
+
+ /* Wrap around: flip valid toggle */
+ if (q->idx == 0)
+ q->toggle ^= 1;
+ }
+ /* Mask out the valid bit (31) */
+ return cur & 0x7fffffff;
+}
+
+/*
+ * Scans all the queue that may have interrupts in them
+ * (based on "pending_prio") in priority order until an
+ * interrupt is found or all the queues are empty.
+ *
+ * Then updates the CPPR (Current Processor Priority
+ * Register) based on the most favored interrupt found
+ * (0xff if none) and return what was found (0 if none).
+ *
+ * If just_peek is set, return the most favored pending
+ * interrupt if any but don't update the queue pointers.
+ *
+ * Note: This function can operate generically on any number
+ * of queues (up to 8). The current implementation of the XIVE
+ * driver only uses a single queue however.
+ *
+ * Note2: This will also "flush" "the pending_count" of a queue
+ * into the "count" when that queue is observed to be empty.
+ * This is used to keep track of the amount of interrupts
+ * targetting a queue. When an interrupt is moved away from
+ * a queue, we only decrement that queue count once the queue
+ * has been observed empty to avoid races.
+ */
+static u32 xive_scan_interrupts(struct xive_cpu *xc, bool just_peek)
+{
+ u32 irq = 0;
+ u8 prio;
+
+ /* Find highest pending priority */
+ while (xc->pending_prio != 0) {
+ struct xive_q *q;
+
+ prio = ffs(xc->pending_prio) - 1;
+ DBG_VERBOSE("scan_irq: trying prio %d\n", prio);
+
+ /* Try to fetch */
+ irq = xive_read_eq(&xc->queue[prio], just_peek);
+
+ /* Found something ? That's it */
+ if (irq)
+ break;
+
+ /* Clear pending bits */
+ xc->pending_prio &= ~(1 << prio);
+
+ /*
+ * Check if the queue count needs adjusting due to
+ * interrupts being moved away. See description of
+ * xive_dec_target_count()
+ */
+ q = &xc->queue[prio];
+ if (atomic_read(&q->pending_count)) {
+ int p = atomic_xchg(&q->pending_count, 0);
+ if (p) {
+ WARN_ON(p > atomic_read(&q->count));
+ atomic_sub(p, &q->count);
+ }
+ }
+ }
+
+ /* If nothing was found, set CPPR to 0xff */
+ if (irq == 0)
+ prio = 0xff;
+
+ /* Update HW CPPR to match if necessary */
+ if (prio != xc->cppr) {
+ DBG_VERBOSE("scan_irq: adjusting CPPR to %d\n", prio);
+ xc->cppr = prio;
+ out_8(xive_tima + xive_tima_offset + TM_CPPR, prio);
+ }
+
+ return irq;
+}
+
+/*
+ * This is used to perform the magic loads from an ESB
+ * described in xive.h
+ */
+static u8 xive_poke_esb(struct xive_irq_data *xd, u32 offset)
+{
+ u64 val;
+
+ /* Handle HW errata */
+ if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG)
+ offset |= offset << 4;
+
+ val = in_be64(xd->eoi_mmio + offset);
+
+ return (u8)val;
+}
+
+#ifdef CONFIG_XMON
+static void xive_dump_eq(const char *name, struct xive_q *q)
+{
+ u32 i0, i1, idx;
+
+ if (!q->qpage)
+ return;
+ idx = q->idx;
+ i0 = be32_to_cpup(q->qpage + idx);
+ idx = (idx + 1) & q->msk;
+ i1 = be32_to_cpup(q->qpage + idx);
+ xmon_printf(" %s Q T=%d %08x %08x ...\n", name,
+ q->toggle, i0, i1);
+}
+
+void xmon_xive_do_dump(int cpu)
+{
+ struct xive_cpu *xc = per_cpu(xive_cpu, cpu);
+
+ xmon_printf("XIVE state for CPU %d:\n", cpu);
+ xmon_printf(" pp=%02x cppr=%02x\n", xc->pending_prio, xc->cppr);
+ xive_dump_eq("IRQ", &xc->queue[xive_irq_priority]);
+#ifdef CONFIG_SMP
+ {
+ u64 val = xive_poke_esb(&xc->ipi_data, XIVE_ESB_GET);
+ xmon_printf(" IPI state: %x:%c%c\n", xc->hw_ipi,
+ val & XIVE_ESB_VAL_P ? 'P' : 'p',
+ val & XIVE_ESB_VAL_P ? 'Q' : 'q');
+ }
+#endif
+}
+#endif /* CONFIG_XMON */
+
+static unsigned int xive_get_irq(void)
+{
+ struct xive_cpu *xc = __this_cpu_read(xive_cpu);
+ u32 irq;
+
+ /*
+ * This can be called either as a result of a HW interrupt or
+ * as a "replay" because EOI decided there was still something
+ * in one of the queues.
+ *
+ * First we perform an ACK cycle in order to update our mask
+ * of pending priorities. This will also have the effect of
+ * updating the CPPR to the most favored pending interrupts.
+ *
+ * In the future, if we have a way to differenciate a first
+ * entry (on HW interrupt) from a replay triggered by EOI,
+ * we could skip this on replays unless we soft-mask tells us
+ * that a new HW interrupt occurred.
+ */
+ xive_ops->update_pending(xc);
+
+ DBG_VERBOSE("get_irq: pending=%02x\n", xc->pending_prio);
+
+ /* Scan our queue(s) for interrupts */
+ irq = xive_scan_interrupts(xc, false);
+
+ DBG_VERBOSE("get_irq: got irq 0x%x, new pending=0x%02x\n",
+ irq, xc->pending_prio);
+
+ /* Return pending interrupt if any */
+ if (irq == XIVE_BAD_IRQ)
+ return 0;
+ return irq;
+}
+
+/*
+ * After EOI'ing an interrupt, we need to re-check the queue
+ * to see if another interrupt is pending since multiple
+ * interrupts can coalesce into a single notification to the
+ * CPU.
+ *
+ * If we find that there is indeed more in there, we call
+ * force_external_irq_replay() to make Linux synthetize an
+ * external interrupt on the next call to local_irq_restore().
+ */
+static void xive_do_queue_eoi(struct xive_cpu *xc)
+{
+ if (xive_scan_interrupts(xc, true) != 0) {
+ DBG_VERBOSE("eoi: pending=0x%02x\n", xc->pending_prio);
+ force_external_irq_replay();
+ }
+}
+
+/*
+ * EOI an interrupt at the source. There are several methods
+ * to do this depending on the HW version and source type
+ */
+void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd)
+{
+ /* If the XIVE supports the new "store EOI facility, use it */
+ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
+ out_be64(xd->eoi_mmio, 0);
+ else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) {
+ /*
+ * The FW told us to call it. This happens for some
+ * interrupt sources that need additional HW whacking
+ * beyond the ESB manipulation. For example LPC interrupts
+ * on P9 DD1.0 need a latch to be clared in the LPC bridge
+ * itself. The Firmware will take care of it.
+ */
+ if (WARN_ON_ONCE(!xive_ops->eoi))
+ return;
+ xive_ops->eoi(hw_irq);
+ } else {
+ u8 eoi_val;
+
+ /*
+ * Otherwise for EOI, we use the special MMIO that does
+ * a clear of both P and Q and returns the old Q,
+ * except for LSIs where we use the "EOI cycle" special
+ * load.
+ *
+ * This allows us to then do a re-trigger if Q was set
+ * rather than synthesizing an interrupt in software
+ *
+ * For LSIs, using the HW EOI cycle works around a problem
+ * on P9 DD1 PHBs where the other ESB accesses don't work
+ * properly.
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_LSI)
+ in_be64(xd->eoi_mmio);
+ else {
+ eoi_val = xive_poke_esb(xd, XIVE_ESB_SET_PQ_00);
+ DBG_VERBOSE("eoi_val=%x\n", offset, eoi_val);
+
+ /* Re-trigger if needed */
+ if ((eoi_val & XIVE_ESB_VAL_Q) && xd->trig_mmio)
+ out_be64(xd->trig_mmio, 0);
+ }
+ }
+}
+
+/* irq_chip eoi callback */
+static void xive_irq_eoi(struct irq_data *d)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ struct xive_cpu *xc = __this_cpu_read(xive_cpu);
+
+ DBG_VERBOSE("eoi_irq: irq=%d [0x%lx] pending=%02x\n",
+ d->irq, irqd_to_hwirq(d), xc->pending_prio);
+
+ /*
+ * EOI the source if it hasn't been disabled and hasn't
+ * been passed-through to a KVM guest
+ */
+ if (!irqd_irq_disabled(d) && !irqd_is_forwarded_to_vcpu(d))
+ xive_do_source_eoi(irqd_to_hwirq(d), xd);
+
+ /*
+ * Clear saved_p to indicate that it's no longer occupying
+ * a queue slot on the target queue
+ */
+ xd->saved_p = false;
+
+ /* Check for more work in the queue */
+ xive_do_queue_eoi(xc);
+}
+
+/*
+ * Helper used to mask and unmask an interrupt source. This
+ * is only called for normal interrupts that do not require
+ * masking/unmasking via firmware.
+ */
+static void xive_do_source_set_mask(struct xive_irq_data *xd,
+ bool mask)
+{
+ u64 val;
+
+ /*
+ * If the interrupt had P set, it may be in a queue.
+ *
+ * We need to make sure we don't re-enable it until it
+ * has been fetched from that queue and EOId. We keep
+ * a copy of that P state and use it to restore the
+ * ESB accordingly on unmask.
+ */
+ if (mask) {
+ val = xive_poke_esb(xd, XIVE_ESB_SET_PQ_01);
+ xd->saved_p = !!(val & XIVE_ESB_VAL_P);
+ } else if (xd->saved_p)
+ xive_poke_esb(xd, XIVE_ESB_SET_PQ_10);
+ else
+ xive_poke_esb(xd, XIVE_ESB_SET_PQ_00);
+}
+
+/*
+ * Try to chose "cpu" as a new interrupt target. Increments
+ * the queue accounting for that target if it's not already
+ * full.
+ */
+static bool xive_try_pick_target(int cpu)
+{
+ struct xive_cpu *xc = per_cpu(xive_cpu, cpu);
+ struct xive_q *q = &xc->queue[xive_irq_priority];
+ int max;
+
+ /*
+ * Calculate max number of interrupts in that queue.
+ *
+ * We leave a gap of 1 just in case...
+ */
+ max = (q->msk + 1) - 1;
+ return !!atomic_add_unless(&q->count, 1, max);
+}
+
+/*
+ * Un-account an interrupt for a target CPU. We don't directly
+ * decrement q->count since the interrupt might still be present
+ * in the queue.
+ *
+ * Instead increment a separate counter "pending_count" which
+ * will be substracted from "count" later when that CPU observes
+ * the queue to be empty.
+ */
+static void xive_dec_target_count(int cpu)
+{
+ struct xive_cpu *xc = per_cpu(xive_cpu, cpu);
+ struct xive_q *q = &xc->queue[xive_irq_priority];
+
+ if (unlikely(WARN_ON(cpu < 0 || !xc))) {
+ pr_err("%s: cpu=%d xc=%p\n", __func__, cpu, xc);
+ return;
+ }
+
+ /*
+ * We increment the "pending count" which will be used
+ * to decrement the target queue count whenever it's next
+ * processed and found empty. This ensure that we don't
+ * decrement while we still have the interrupt there
+ * occupying a slot.
+ */
+ atomic_inc(&q->pending_count);
+}
+
+/* Find a tentative CPU target in a CPU mask */
+static int xive_find_target_in_mask(const struct cpumask *mask,
+ unsigned int fuzz)
+{
+ int cpu, first, num, i;
+
+ /* Pick up a starting point CPU in the mask based on fuzz */
+ num = cpumask_weight(mask);
+ first = fuzz % num;
+
+ /* Locate it */
+ cpu = cpumask_first(mask);
+ for (i = 0; i < first && cpu < nr_cpu_ids; i++)
+ cpu = cpumask_next(cpu, mask);
+
+ /* Sanity check */
+ if (WARN_ON(cpu >= nr_cpu_ids))
+ cpu = cpumask_first(cpu_online_mask);
+
+ /* Remember first one to handle wrap-around */
+ first = cpu;
+
+ /*
+ * Now go through the entire mask until we find a valid
+ * target.
+ */
+ for (;;) {
+ /*
+ * We re-check online as the fallback case passes us
+ * an untested affinity mask
+ */
+ if (cpu_online(cpu) && xive_try_pick_target(cpu))
+ return cpu;
+ cpu = cpumask_next(cpu, mask);
+ if (cpu == first)
+ break;
+ /* Wrap around */
+ if (cpu >= nr_cpu_ids)
+ cpu = cpumask_first(mask);
+ }
+ return -1;
+}
+
+/*
+ * Pick a target CPU for an interrupt. This is done at
+ * startup or if the affinity is changed in a way that
+ * invalidates the current target.
+ */
+static int xive_pick_irq_target(struct irq_data *d,
+ const struct cpumask *affinity)
+{
+ static unsigned int fuzz;
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ cpumask_var_t mask;
+ int cpu = -1;
+
+ /*
+ * If we have chip IDs, first we try to build a mask of
+ * CPUs matching the CPU and find a target in there
+ */
+ if (xd->src_chip != XIVE_INVALID_CHIP_ID &&
+ zalloc_cpumask_var(&mask, GFP_ATOMIC)) {
+ /* Build a mask of matching chip IDs */
+ for_each_cpu_and(cpu, affinity, cpu_online_mask) {
+ struct xive_cpu *xc = per_cpu(xive_cpu, cpu);
+ if (xc->chip_id == xd->src_chip)
+ cpumask_set_cpu(cpu, mask);
+ }
+ /* Try to find a target */
+ if (cpumask_empty(mask))
+ cpu = -1;
+ else
+ cpu = xive_find_target_in_mask(mask, fuzz++);
+ free_cpumask_var(mask);
+ if (cpu >= 0)
+ return cpu;
+ fuzz--;
+ }
+
+ /* No chip IDs, fallback to using the affinity mask */
+ return xive_find_target_in_mask(affinity, fuzz++);
+}
+
+static unsigned int xive_irq_startup(struct irq_data *d)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ int target, rc;
+
+ pr_devel("xive_irq_startup: irq %d [0x%x] data @%p\n",
+ d->irq, hw_irq, d);
+
+#ifdef CONFIG_PCI_MSI
+ /*
+ * The generic MSI code returns with the interrupt disabled on the
+ * card, using the MSI mask bits. Firmware doesn't appear to unmask
+ * at that level, so we do it here by hand.
+ */
+ if (irq_data_get_msi_desc(d))
+ pci_msi_unmask_irq(d);
+#endif
+
+ /* Pick a target */
+ target = xive_pick_irq_target(d, irq_data_get_affinity_mask(d));
+ if (target == XIVE_INVALID_TARGET) {
+ /* Try again breaking affinity */
+ target = xive_pick_irq_target(d, cpu_online_mask);
+ if (target == XIVE_INVALID_TARGET)
+ return -ENXIO;
+ pr_warn("irq %d started with broken affinity\n", d->irq);
+ }
+
+ /* Sanity check */
+ if (WARN_ON(target == XIVE_INVALID_TARGET ||
+ target >= nr_cpu_ids))
+ target = smp_processor_id();
+
+ xd->target = target;
+
+ /*
+ * Configure the logical number to be the Linux IRQ number
+ * and set the target queue
+ */
+ rc = xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(target),
+ xive_irq_priority, d->irq);
+ if (rc)
+ return rc;
+
+ /* Unmask the ESB */
+ xive_do_source_set_mask(xd, false);
+
+ return 0;
+}
+
+static void xive_irq_shutdown(struct irq_data *d)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+
+ pr_devel("xive_irq_shutdown: irq %d [0x%x] data @%p\n",
+ d->irq, hw_irq, d);
+
+ if (WARN_ON(xd->target == XIVE_INVALID_TARGET))
+ return;
+
+ /* Mask the interrupt at the source */
+ xive_do_source_set_mask(xd, true);
+
+ /*
+ * The above may have set saved_p. We clear it otherwise it
+ * will prevent re-enabling later on. It is ok to forget the
+ * fact that the interrupt might be in a queue because we are
+ * accounting that already in xive_dec_target_count() and will
+ * be re-routing it to a new queue with proper accounting when
+ * it's started up again
+ */
+ xd->saved_p = false;
+
+ /*
+ * Mask the interrupt in HW in the IVT/EAS and set the number
+ * to be the "bad" IRQ number
+ */
+ xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(xd->target),
+ 0xff, XIVE_BAD_IRQ);
+
+ xive_dec_target_count(xd->target);
+ xd->target = XIVE_INVALID_TARGET;
+}
+
+static void xive_irq_unmask(struct irq_data *d)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+
+ pr_devel("xive_irq_unmask: irq %d data @%p\n", d->irq, xd);
+
+ /*
+ * This is a workaround for PCI LSI problems on P9, for
+ * these, we call FW to set the mask. The problems might
+ * be fixed by P9 DD2.0, if that is the case, firmware
+ * will no longer set that flag.
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_MASK_FW) {
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(xd->target),
+ xive_irq_priority, d->irq);
+ return;
+ }
+
+ xive_do_source_set_mask(xd, false);
+}
+
+static void xive_irq_mask(struct irq_data *d)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+
+ pr_devel("xive_irq_mask: irq %d data @%p\n", d->irq, xd);
+
+ /*
+ * This is a workaround for PCI LSI problems on P9, for
+ * these, we call OPAL to set the mask. The problems might
+ * be fixed by P9 DD2.0, if that is the case, firmware
+ * will no longer set that flag.
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_MASK_FW) {
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(xd->target),
+ 0xff, d->irq);
+ return;
+ }
+
+ xive_do_source_set_mask(xd, true);
+}
+
+static int xive_irq_set_affinity(struct irq_data *d,
+ const struct cpumask *cpumask,
+ bool force)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ u32 target, old_target;
+ int rc = 0;
+
+ pr_devel("xive_irq_set_affinity: irq %d\n", d->irq);
+
+ /* Is this valid ? */
+ if (cpumask_any_and(cpumask, cpu_online_mask) >= nr_cpu_ids)
+ return -EINVAL;
+
+ /*
+ * If existing target is already in the new mask, and is
+ * online then do nothing.
+ */
+ if (xd->target != XIVE_INVALID_TARGET &&
+ cpu_online(xd->target) &&
+ cpumask_test_cpu(xd->target, cpumask))
+ return IRQ_SET_MASK_OK;
+
+ /* Pick a new target */
+ target = xive_pick_irq_target(d, cpumask);
+
+ /* No target found */
+ if (target == XIVE_INVALID_TARGET)
+ return -ENXIO;
+
+ /* Sanity check */
+ if (WARN_ON(target >= nr_cpu_ids))
+ target = smp_processor_id();
+
+ old_target = xd->target;
+
+ /*
+ * Only configure the irq if it's not currently passed-through to
+ * a KVM guest
+ */
+ if (!irqd_is_forwarded_to_vcpu(d))
+ rc = xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(target),
+ xive_irq_priority, d->irq);
+ if (rc < 0) {
+ pr_err("Error %d reconfiguring irq %d\n", rc, d->irq);
+ return rc;
+ }
+
+ pr_devel(" target: 0x%x\n", target);
+ xd->target = target;
+
+ /* Give up previous target */
+ if (old_target != XIVE_INVALID_TARGET)
+ xive_dec_target_count(old_target);
+
+ return IRQ_SET_MASK_OK;
+}
+
+static int xive_irq_set_type(struct irq_data *d, unsigned int flow_type)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+
+ /*
+ * We only support these. This has really no effect other than setting
+ * the corresponding descriptor bits mind you but those will in turn
+ * affect the resend function when re-enabling an edge interrupt.
+ *
+ * Set set the default to edge as explained in map().
+ */
+ if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE)
+ flow_type = IRQ_TYPE_EDGE_RISING;
+
+ if (flow_type != IRQ_TYPE_EDGE_RISING &&
+ flow_type != IRQ_TYPE_LEVEL_LOW)
+ return -EINVAL;
+
+ irqd_set_trigger_type(d, flow_type);
+
+ /*
+ * Double check it matches what the FW thinks
+ *
+ * NOTE: We don't know yet if the PAPR interface will provide
+ * the LSI vs MSI information apart from the device-tree so
+ * this check might have to move into an optional backend call
+ * that is specific to the native backend
+ */
+ if ((flow_type == IRQ_TYPE_LEVEL_LOW) !=
+ !!(xd->flags & XIVE_IRQ_FLAG_LSI)) {
+ pr_warn("Interrupt %d (HW 0x%x) type mismatch, Linux says %s, FW says %s\n",
+ d->irq, (u32)irqd_to_hwirq(d),
+ (flow_type == IRQ_TYPE_LEVEL_LOW) ? "Level" : "Edge",
+ (xd->flags & XIVE_IRQ_FLAG_LSI) ? "Level" : "Edge");
+ }
+
+ return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+static int xive_irq_retrigger(struct irq_data *d)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+
+ /* This should be only for MSIs */
+ if (WARN_ON(xd->flags & XIVE_IRQ_FLAG_LSI))
+ return 0;
+
+ /*
+ * To perform a retrigger, we first set the PQ bits to
+ * 11, then perform an EOI.
+ */
+ xive_poke_esb(xd, XIVE_ESB_SET_PQ_11);
+
+ /*
+ * Note: We pass "0" to the hw_irq argument in order to
+ * avoid calling into the backend EOI code which we don't
+ * want to do in the case of a re-trigger. Backends typically
+ * only do EOI for LSIs anyway.
+ */
+ xive_do_source_eoi(0, xd);
+
+ return 1;
+}
+
+static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ int rc;
+ u8 pq;
+
+ /*
+ * We only support this on interrupts that do not require
+ * firmware calls for masking and unmasking
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_MASK_FW)
+ return -EIO;
+
+ /*
+ * This is called by KVM with state non-NULL for enabling
+ * pass-through or NULL for disabling it
+ */
+ if (state) {
+ irqd_set_forwarded_to_vcpu(d);
+
+ /* Set it to PQ=10 state to prevent further sends */
+ pq = xive_poke_esb(xd, XIVE_ESB_SET_PQ_10);
+
+ /* No target ? nothing to do */
+ if (xd->target == XIVE_INVALID_TARGET) {
+ /*
+ * An untargetted interrupt should have been
+ * also masked at the source
+ */
+ WARN_ON(pq & 2);
+
+ return 0;
+ }
+
+ /*
+ * If P was set, adjust state to PQ=11 to indicate
+ * that a resend is needed for the interrupt to reach
+ * the guest. Also remember the value of P.
+ *
+ * This also tells us that it's in flight to a host queue
+ * or has already been fetched but hasn't been EOIed yet
+ * by the host. This it's potentially using up a host
+ * queue slot. This is important to know because as long
+ * as this is the case, we must not hard-unmask it when
+ * "returning" that interrupt to the host.
+ *
+ * This saved_p is cleared by the host EOI, when we know
+ * for sure the queue slot is no longer in use.
+ */
+ if (pq & 2) {
+ pq = xive_poke_esb(xd, XIVE_ESB_SET_PQ_11);
+ xd->saved_p = true;
+
+ /*
+ * Sync the XIVE source HW to ensure the interrupt
+ * has gone through the EAS before we change its
+ * target to the guest. That should guarantee us
+ * that we *will* eventually get an EOI for it on
+ * the host. Otherwise there would be a small window
+ * for P to be seen here but the interrupt going
+ * to the guest queue.
+ */
+ if (xive_ops->sync_source)
+ xive_ops->sync_source(hw_irq);
+ } else
+ xd->saved_p = false;
+ } else {
+ irqd_clr_forwarded_to_vcpu(d);
+
+ /* No host target ? hard mask and return */
+ if (xd->target == XIVE_INVALID_TARGET) {
+ xive_do_source_set_mask(xd, true);
+ return 0;
+ }
+
+ /*
+ * Sync the XIVE source HW to ensure the interrupt
+ * has gone through the EAS before we change its
+ * target to the host.
+ */
+ if (xive_ops->sync_source)
+ xive_ops->sync_source(hw_irq);
+
+ /*
+ * By convention we are called with the interrupt in
+ * a PQ=10 or PQ=11 state, ie, it won't fire and will
+ * have latched in Q whether there's a pending HW
+ * interrupt or not.
+ *
+ * First reconfigure the target.
+ */
+ rc = xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(xd->target),
+ xive_irq_priority, d->irq);
+ if (rc)
+ return rc;
+
+ /*
+ * Then if saved_p is not set, effectively re-enable the
+ * interrupt with an EOI. If it is set, we know there is
+ * still a message in a host queue somewhere that will be
+ * EOId eventually.
+ *
+ * Note: We don't check irqd_irq_disabled(). Effectively,
+ * we *will* let the irq get through even if masked if the
+ * HW is still firing it in order to deal with the whole
+ * saved_p business properly. If the interrupt triggers
+ * while masked, the generic code will re-mask it anyway.
+ */
+ if (!xd->saved_p)
+ xive_do_source_eoi(hw_irq, xd);
+
+ }
+ return 0;
+}
+
+static struct irq_chip xive_irq_chip = {
+ .name = "XIVE-IRQ",
+ .irq_startup = xive_irq_startup,
+ .irq_shutdown = xive_irq_shutdown,
+ .irq_eoi = xive_irq_eoi,
+ .irq_mask = xive_irq_mask,
+ .irq_unmask = xive_irq_unmask,
+ .irq_set_affinity = xive_irq_set_affinity,
+ .irq_set_type = xive_irq_set_type,
+ .irq_retrigger = xive_irq_retrigger,
+ .irq_set_vcpu_affinity = xive_irq_set_vcpu_affinity,
+};
+
+bool is_xive_irq(struct irq_chip *chip)
+{
+ return chip == &xive_irq_chip;
+}
+EXPORT_SYMBOL_GPL(is_xive_irq);
+
+void xive_cleanup_irq_data(struct xive_irq_data *xd)
+{
+ if (xd->eoi_mmio) {
+ iounmap(xd->eoi_mmio);
+ if (xd->eoi_mmio == xd->trig_mmio)
+ xd->trig_mmio = NULL;
+ xd->eoi_mmio = NULL;
+ }
+ if (xd->trig_mmio) {
+ iounmap(xd->trig_mmio);
+ xd->trig_mmio = NULL;
+ }
+}
+EXPORT_SYMBOL_GPL(xive_cleanup_irq_data);
+
+static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw)
+{
+ struct xive_irq_data *xd;
+ int rc;
+
+ xd = kzalloc(sizeof(struct xive_irq_data), GFP_KERNEL);
+ if (!xd)
+ return -ENOMEM;
+ rc = xive_ops->populate_irq_data(hw, xd);
+ if (rc) {
+ kfree(xd);
+ return rc;
+ }
+ xd->target = XIVE_INVALID_TARGET;
+ irq_set_handler_data(virq, xd);
+
+ return 0;
+}
+
+static void xive_irq_free_data(unsigned int virq)
+{
+ struct xive_irq_data *xd = irq_get_handler_data(virq);
+
+ if (!xd)
+ return;
+ irq_set_handler_data(virq, NULL);
+ xive_cleanup_irq_data(xd);
+ kfree(xd);
+}
+
+#ifdef CONFIG_SMP
+
+static void xive_cause_ipi(int cpu)
+{
+ struct xive_cpu *xc;
+ struct xive_irq_data *xd;
+
+ xc = per_cpu(xive_cpu, cpu);
+
+ DBG_VERBOSE("IPI CPU %d -> %d (HW IRQ 0x%x)\n",
+ smp_processor_id(), cpu, xc->hw_ipi);
+
+ xd = &xc->ipi_data;
+ if (WARN_ON(!xd->trig_mmio))
+ return;
+ out_be64(xd->trig_mmio, 0);
+}
+
+static irqreturn_t xive_muxed_ipi_action(int irq, void *dev_id)
+{
+ return smp_ipi_demux();
+}
+
+static void xive_ipi_eoi(struct irq_data *d)
+{
+ struct xive_cpu *xc = __this_cpu_read(xive_cpu);
+
+ /* Handle possible race with unplug and drop stale IPIs */
+ if (!xc)
+ return;
+ xive_do_source_eoi(xc->hw_ipi, &xc->ipi_data);
+ xive_do_queue_eoi(xc);
+}
+
+static void xive_ipi_do_nothing(struct irq_data *d)
+{
+ /*
+ * Nothing to do, we never mask/unmask IPIs, but the callback
+ * has to exist for the struct irq_chip.
+ */
+}
+
+static struct irq_chip xive_ipi_chip = {
+ .name = "XIVE-IPI",
+ .irq_eoi = xive_ipi_eoi,
+ .irq_mask = xive_ipi_do_nothing,
+ .irq_unmask = xive_ipi_do_nothing,
+};
+
+static void __init xive_request_ipi(void)
+{
+ unsigned int virq;
+
+ /*
+ * Initialization failed, move on, we might manage to
+ * reach the point where we display our errors before
+ * the system falls appart
+ */
+ if (!xive_irq_domain)
+ return;
+
+ /* Initialize it */
+ virq = irq_create_mapping(xive_irq_domain, 0);
+ xive_ipi_irq = virq;
+
+ WARN_ON(request_irq(virq, xive_muxed_ipi_action,
+ IRQF_PERCPU | IRQF_NO_THREAD, "IPI", NULL));
+}
+
+static int xive_setup_cpu_ipi(unsigned int cpu)
+{
+ struct xive_cpu *xc;
+ int rc;
+
+ pr_debug("Setting up IPI for CPU %d\n", cpu);
+
+ xc = per_cpu(xive_cpu, cpu);
+
+ /* Check if we are already setup */
+ if (xc->hw_ipi != 0)
+ return 0;
+
+ /* Grab an IPI from the backend, this will populate xc->hw_ipi */
+ if (xive_ops->get_ipi(cpu, xc))
+ return -EIO;
+
+ /*
+ * Populate the IRQ data in the xive_cpu structure and
+ * configure the HW / enable the IPIs.
+ */
+ rc = xive_ops->populate_irq_data(xc->hw_ipi, &xc->ipi_data);
+ if (rc) {
+ pr_err("Failed to populate IPI data on CPU %d\n", cpu);
+ return -EIO;
+ }
+ rc = xive_ops->configure_irq(xc->hw_ipi,
+ get_hard_smp_processor_id(cpu),
+ xive_irq_priority, xive_ipi_irq);
+ if (rc) {
+ pr_err("Failed to map IPI CPU %d\n", cpu);
+ return -EIO;
+ }
+ pr_devel("CPU %d HW IPI %x, virq %d, trig_mmio=%p\n", cpu,
+ xc->hw_ipi, xive_ipi_irq, xc->ipi_data.trig_mmio);
+
+ /* Unmask it */
+ xive_do_source_set_mask(&xc->ipi_data, false);
+
+ return 0;
+}
+
+static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc)
+{
+ /* Disable the IPI and free the IRQ data */
+
+ /* Already cleaned up ? */
+ if (xc->hw_ipi == 0)
+ return;
+
+ /* Mask the IPI */
+ xive_do_source_set_mask(&xc->ipi_data, true);
+
+ /*
+ * Note: We don't call xive_cleanup_irq_data() to free
+ * the mappings as this is called from an IPI on kexec
+ * which is not a safe environment to call iounmap()
+ */
+
+ /* Deconfigure/mask in the backend */
+ xive_ops->configure_irq(xc->hw_ipi, hard_smp_processor_id(),
+ 0xff, xive_ipi_irq);
+
+ /* Free the IPIs in the backend */
+ xive_ops->put_ipi(cpu, xc);
+}
+
+void __init xive_smp_probe(void)
+{
+ smp_ops->cause_ipi = xive_cause_ipi;
+
+ /* Register the IPI */
+ xive_request_ipi();
+
+ /* Allocate and setup IPI for the boot CPU */
+ xive_setup_cpu_ipi(smp_processor_id());
+}
+
+#endif /* CONFIG_SMP */
+
+static int xive_irq_domain_map(struct irq_domain *h, unsigned int virq,
+ irq_hw_number_t hw)
+{
+ int rc;
+
+ /*
+ * Mark interrupts as edge sensitive by default so that resend
+ * actually works. Will fix that up below if needed.
+ */
+ irq_clear_status_flags(virq, IRQ_LEVEL);
+
+#ifdef CONFIG_SMP
+ /* IPIs are special and come up with HW number 0 */
+ if (hw == 0) {
+ /*
+ * IPIs are marked per-cpu. We use separate HW interrupts under
+ * the hood but associated with the same "linux" interrupt
+ */
+ irq_set_chip_and_handler(virq, &xive_ipi_chip,
+ handle_percpu_irq);
+ return 0;
+ }
+#endif
+
+ rc = xive_irq_alloc_data(virq, hw);
+ if (rc)
+ return rc;
+
+ irq_set_chip_and_handler(virq, &xive_irq_chip, handle_fasteoi_irq);
+
+ return 0;
+}
+
+static void xive_irq_domain_unmap(struct irq_domain *d, unsigned int virq)
+{
+ struct irq_data *data = irq_get_irq_data(virq);
+ unsigned int hw_irq;
+
+ /* XXX Assign BAD number */
+ if (!data)
+ return;
+ hw_irq = (unsigned int)irqd_to_hwirq(data);
+ if (hw_irq)
+ xive_irq_free_data(virq);
+}
+
+static int xive_irq_domain_xlate(struct irq_domain *h, struct device_node *ct,
+ const u32 *intspec, unsigned int intsize,
+ irq_hw_number_t *out_hwirq, unsigned int *out_flags)
+
+{
+ *out_hwirq = intspec[0];
+
+ /*
+ * If intsize is at least 2, we look for the type in the second cell,
+ * we assume the LSB indicates a level interrupt.
+ */
+ if (intsize > 1) {
+ if (intspec[1] & 1)
+ *out_flags = IRQ_TYPE_LEVEL_LOW;
+ else
+ *out_flags = IRQ_TYPE_EDGE_RISING;
+ } else
+ *out_flags = IRQ_TYPE_LEVEL_LOW;
+
+ return 0;
+}
+
+static int xive_irq_domain_match(struct irq_domain *h, struct device_node *node,
+ enum irq_domain_bus_token bus_token)
+{
+ return xive_ops->match(node);
+}
+
+static const struct irq_domain_ops xive_irq_domain_ops = {
+ .match = xive_irq_domain_match,
+ .map = xive_irq_domain_map,
+ .unmap = xive_irq_domain_unmap,
+ .xlate = xive_irq_domain_xlate,
+};
+
+static void __init xive_init_host(void)
+{
+ xive_irq_domain = irq_domain_add_nomap(NULL, XIVE_MAX_IRQ,
+ &xive_irq_domain_ops, NULL);
+ if (WARN_ON(xive_irq_domain == NULL))
+ return;
+ irq_set_default_host(xive_irq_domain);
+}
+
+static void xive_cleanup_cpu_queues(unsigned int cpu, struct xive_cpu *xc)
+{
+ if (xc->queue[xive_irq_priority].qpage)
+ xive_ops->cleanup_queue(cpu, xc, xive_irq_priority);
+}
+
+static int xive_setup_cpu_queues(unsigned int cpu, struct xive_cpu *xc)
+{
+ int rc = 0;
+
+ /* We setup 1 queues for now with a 64k page */
+ if (!xc->queue[xive_irq_priority].qpage)
+ rc = xive_ops->setup_queue(cpu, xc, xive_irq_priority);
+
+ return rc;
+}
+
+static int xive_prepare_cpu(unsigned int cpu)
+{
+ struct xive_cpu *xc;
+
+ xc = per_cpu(xive_cpu, cpu);
+ if (!xc) {
+ struct device_node *np;
+
+ xc = kzalloc_node(sizeof(struct xive_cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!xc)
+ return -ENOMEM;
+ np = of_get_cpu_node(cpu, NULL);
+ if (np)
+ xc->chip_id = of_get_ibm_chip_id(np);
+ of_node_put(np);
+
+ per_cpu(xive_cpu, cpu) = xc;
+ }
+
+ /* Setup EQs if not already */
+ return xive_setup_cpu_queues(cpu, xc);
+}
+
+static void xive_setup_cpu(void)
+{
+ struct xive_cpu *xc = __this_cpu_read(xive_cpu);
+
+ /* Debug: Dump the TM state */
+ pr_devel("CPU %d [HW 0x%02x] VT=%02x\n",
+ smp_processor_id(), hard_smp_processor_id(),
+ in_8(xive_tima + xive_tima_offset + TM_WORD2));
+
+ /* The backend might have additional things to do */
+ if (xive_ops->setup_cpu)
+ xive_ops->setup_cpu(smp_processor_id(), xc);
+
+ /* Set CPPR to 0xff to enable flow of interrupts */
+ xc->cppr = 0xff;
+ out_8(xive_tima + xive_tima_offset + TM_CPPR, 0xff);
+}
+
+#ifdef CONFIG_SMP
+void xive_smp_setup_cpu(void)
+{
+ pr_devel("SMP setup CPU %d\n", smp_processor_id());
+
+ /* This will have already been done on the boot CPU */
+ if (smp_processor_id() != boot_cpuid)
+ xive_setup_cpu();
+
+}
+
+int xive_smp_prepare_cpu(unsigned int cpu)
+{
+ int rc;
+
+ /* Allocate per-CPU data and queues */
+ rc = xive_prepare_cpu(cpu);
+ if (rc)
+ return rc;
+
+ /* Allocate and setup IPI for the new CPU */
+ return xive_setup_cpu_ipi(cpu);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void xive_flush_cpu_queue(unsigned int cpu, struct xive_cpu *xc)
+{
+ u32 irq;
+
+ /* We assume local irqs are disabled */
+ WARN_ON(!irqs_disabled());
+
+ /* Check what's already in the CPU queue */
+ while ((irq = xive_scan_interrupts(xc, false)) != 0) {
+ /*
+ * We need to re-route that interrupt to its new destination.
+ * First get and lock the descriptor
+ */
+ struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_data *d = irq_desc_get_irq_data(desc);
+ struct xive_irq_data *xd;
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+
+ /*
+ * Ignore anything that isn't a XIVE irq and ignore
+ * IPIs, so can just be dropped.
+ */
+ if (d->domain != xive_irq_domain || hw_irq == 0)
+ continue;
+
+ /*
+ * The IRQ should have already been re-routed, it's just a
+ * stale in the old queue, so re-trigger it in order to make
+ * it reach is new destination.
+ */
+#ifdef DEBUG_FLUSH
+ pr_info("CPU %d: Got irq %d while offline, re-sending...\n",
+ cpu, irq);
+#endif
+ raw_spin_lock(&desc->lock);
+ xd = irq_desc_get_handler_data(desc);
+
+ /*
+ * For LSIs, we EOI, this will cause a resend if it's
+ * still asserted. Otherwise do an MSI retrigger.
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_LSI)
+ xive_do_source_eoi(irqd_to_hwirq(d), xd);
+ else
+ xive_irq_retrigger(d);
+
+ raw_spin_unlock(&desc->lock);
+ }
+}
+
+void xive_smp_disable_cpu(void)
+{
+ struct xive_cpu *xc = __this_cpu_read(xive_cpu);
+ unsigned int cpu = smp_processor_id();
+
+ /* Migrate interrupts away from the CPU */
+ irq_migrate_all_off_this_cpu();
+
+ /* Set CPPR to 0 to disable flow of interrupts */
+ xc->cppr = 0;
+ out_8(xive_tima + xive_tima_offset + TM_CPPR, 0);
+
+ /* Flush everything still in the queue */
+ xive_flush_cpu_queue(cpu, xc);
+
+ /* Re-enable CPPR */
+ xc->cppr = 0xff;
+ out_8(xive_tima + xive_tima_offset + TM_CPPR, 0xff);
+}
+
+void xive_flush_interrupt(void)
+{
+ struct xive_cpu *xc = __this_cpu_read(xive_cpu);
+ unsigned int cpu = smp_processor_id();
+
+ /* Called if an interrupt occurs while the CPU is hot unplugged */
+ xive_flush_cpu_queue(cpu, xc);
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+#endif /* CONFIG_SMP */
+
+void xive_kexec_teardown_cpu(int secondary)
+{
+ struct xive_cpu *xc = __this_cpu_read(xive_cpu);
+ unsigned int cpu = smp_processor_id();
+
+ /* Set CPPR to 0 to disable flow of interrupts */
+ xc->cppr = 0;
+ out_8(xive_tima + xive_tima_offset + TM_CPPR, 0);
+
+ /* Backend cleanup if any */
+ if (xive_ops->teardown_cpu)
+ xive_ops->teardown_cpu(cpu, xc);
+
+#ifdef CONFIG_SMP
+ /* Get rid of IPI */
+ xive_cleanup_cpu_ipi(cpu, xc);
+#endif
+
+ /* Disable and free the queues */
+ xive_cleanup_cpu_queues(cpu, xc);
+}
+
+void xive_shutdown(void)
+{
+ xive_ops->shutdown();
+}
+
+bool xive_core_init(const struct xive_ops *ops, void __iomem *area, u32 offset,
+ u8 max_prio)
+{
+ xive_tima = area;
+ xive_tima_offset = offset;
+ xive_ops = ops;
+ xive_irq_priority = max_prio;
+
+ ppc_md.get_irq = xive_get_irq;
+ __xive_enabled = true;
+
+ pr_devel("Initializing host..\n");
+ xive_init_host();
+
+ pr_devel("Initializing boot CPU..\n");
+
+ /* Allocate per-CPU data and queues */
+ xive_prepare_cpu(smp_processor_id());
+
+ /* Get ready for interrupts */
+ xive_setup_cpu();
+
+ pr_info("Interrupt handling intialized with %s backend\n",
+ xive_ops->name);
+ pr_info("Using priority %d for all interrupts\n", max_prio);
+
+ return true;
+}
+
+static int __init xive_off(char *arg)
+{
+ xive_cmdline_disabled = true;
+ return 0;
+}
+__setup("xive=off", xive_off);
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
new file mode 100644
index 000000000000..ab9ecce61ee5
--- /dev/null
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -0,0 +1,716 @@
+/*
+ * Copyright 2016,2017 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "xive: " fmt
+
+#include <linux/types.h>
+#include <linux/irq.h>
+#include <linux/debugfs.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/cpumask.h>
+#include <linux/mm.h>
+
+#include <asm/prom.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/errno.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/opal.h>
+#include <asm/kvm_ppc.h>
+
+#include "xive-internal.h"
+
+
+static u32 xive_provision_size;
+static u32 *xive_provision_chips;
+static u32 xive_provision_chip_count;
+static u32 xive_queue_shift;
+static u32 xive_pool_vps = XIVE_INVALID_VP;
+static struct kmem_cache *xive_provision_cache;
+
+int xive_native_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
+{
+ __be64 flags, eoi_page, trig_page;
+ __be32 esb_shift, src_chip;
+ u64 opal_flags;
+ s64 rc;
+
+ memset(data, 0, sizeof(*data));
+
+ rc = opal_xive_get_irq_info(hw_irq, &flags, &eoi_page, &trig_page,
+ &esb_shift, &src_chip);
+ if (rc) {
+ pr_err("opal_xive_get_irq_info(0x%x) returned %lld\n",
+ hw_irq, rc);
+ return -EINVAL;
+ }
+
+ opal_flags = be64_to_cpu(flags);
+ if (opal_flags & OPAL_XIVE_IRQ_STORE_EOI)
+ data->flags |= XIVE_IRQ_FLAG_STORE_EOI;
+ if (opal_flags & OPAL_XIVE_IRQ_LSI)
+ data->flags |= XIVE_IRQ_FLAG_LSI;
+ if (opal_flags & OPAL_XIVE_IRQ_SHIFT_BUG)
+ data->flags |= XIVE_IRQ_FLAG_SHIFT_BUG;
+ if (opal_flags & OPAL_XIVE_IRQ_MASK_VIA_FW)
+ data->flags |= XIVE_IRQ_FLAG_MASK_FW;
+ if (opal_flags & OPAL_XIVE_IRQ_EOI_VIA_FW)
+ data->flags |= XIVE_IRQ_FLAG_EOI_FW;
+ data->eoi_page = be64_to_cpu(eoi_page);
+ data->trig_page = be64_to_cpu(trig_page);
+ data->esb_shift = be32_to_cpu(esb_shift);
+ data->src_chip = be32_to_cpu(src_chip);
+
+ data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift);
+ if (!data->eoi_mmio) {
+ pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq);
+ return -ENOMEM;
+ }
+
+ if (!data->trig_page)
+ return 0;
+ if (data->trig_page == data->eoi_page) {
+ data->trig_mmio = data->eoi_mmio;
+ return 0;
+ }
+
+ data->trig_mmio = ioremap(data->trig_page, 1u << data->esb_shift);
+ if (!data->trig_mmio) {
+ pr_err("Failed to map trigger page for irq 0x%x\n", hw_irq);
+ return -ENOMEM;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_populate_irq_data);
+
+int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq)
+{
+ s64 rc;
+
+ for (;;) {
+ rc = opal_xive_set_irq_config(hw_irq, target, prio, sw_irq);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ return rc == 0 ? 0 : -ENXIO;
+}
+EXPORT_SYMBOL_GPL(xive_native_configure_irq);
+
+
+/* This can be called multiple time to change a queue configuration */
+int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
+ __be32 *qpage, u32 order, bool can_escalate)
+{
+ s64 rc = 0;
+ __be64 qeoi_page_be;
+ __be32 esc_irq_be;
+ u64 flags, qpage_phys;
+
+ /* If there's an actual queue page, clean it */
+ if (order) {
+ if (WARN_ON(!qpage))
+ return -EINVAL;
+ qpage_phys = __pa(qpage);
+ } else
+ qpage_phys = 0;
+
+ /* Initialize the rest of the fields */
+ q->msk = order ? ((1u << (order - 2)) - 1) : 0;
+ q->idx = 0;
+ q->toggle = 0;
+
+ rc = opal_xive_get_queue_info(vp_id, prio, NULL, NULL,
+ &qeoi_page_be,
+ &esc_irq_be,
+ NULL);
+ if (rc) {
+ pr_err("Error %lld getting queue info prio %d\n", rc, prio);
+ rc = -EIO;
+ goto fail;
+ }
+ q->eoi_phys = be64_to_cpu(qeoi_page_be);
+
+ /* Default flags */
+ flags = OPAL_XIVE_EQ_ALWAYS_NOTIFY | OPAL_XIVE_EQ_ENABLED;
+
+ /* Escalation needed ? */
+ if (can_escalate) {
+ q->esc_irq = be32_to_cpu(esc_irq_be);
+ flags |= OPAL_XIVE_EQ_ESCALATE;
+ }
+
+ /* Configure and enable the queue in HW */
+ for (;;) {
+ rc = opal_xive_set_queue_info(vp_id, prio, qpage_phys, order, flags);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ if (rc) {
+ pr_err("Error %lld setting queue for prio %d\n", rc, prio);
+ rc = -EIO;
+ } else {
+ /*
+ * KVM code requires all of the above to be visible before
+ * q->qpage is set due to how it manages IPI EOIs
+ */
+ wmb();
+ q->qpage = qpage;
+ }
+fail:
+ return rc;
+}
+EXPORT_SYMBOL_GPL(xive_native_configure_queue);
+
+static void __xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio)
+{
+ s64 rc;
+
+ /* Disable the queue in HW */
+ for (;;) {
+ rc = opal_xive_set_queue_info(vp_id, prio, 0, 0, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ if (rc)
+ pr_err("Error %lld disabling queue for prio %d\n", rc, prio);
+}
+
+void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio)
+{
+ __xive_native_disable_queue(vp_id, q, prio);
+}
+EXPORT_SYMBOL_GPL(xive_native_disable_queue);
+
+static int xive_native_setup_queue(unsigned int cpu, struct xive_cpu *xc, u8 prio)
+{
+ struct xive_q *q = &xc->queue[prio];
+ unsigned int alloc_order;
+ struct page *pages;
+ __be32 *qpage;
+
+ alloc_order = (xive_queue_shift > PAGE_SHIFT) ?
+ (xive_queue_shift - PAGE_SHIFT) : 0;
+ pages = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, alloc_order);
+ if (!pages)
+ return -ENOMEM;
+ qpage = (__be32 *)page_address(pages);
+ memset(qpage, 0, 1 << xive_queue_shift);
+ return xive_native_configure_queue(get_hard_smp_processor_id(cpu),
+ q, prio, qpage, xive_queue_shift, false);
+}
+
+static void xive_native_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, u8 prio)
+{
+ struct xive_q *q = &xc->queue[prio];
+ unsigned int alloc_order;
+
+ /*
+ * We use the variant with no iounmap as this is called on exec
+ * from an IPI and iounmap isn't safe
+ */
+ __xive_native_disable_queue(get_hard_smp_processor_id(cpu), q, prio);
+ alloc_order = (xive_queue_shift > PAGE_SHIFT) ?
+ (xive_queue_shift - PAGE_SHIFT) : 0;
+ free_pages((unsigned long)q->qpage, alloc_order);
+ q->qpage = NULL;
+}
+
+static bool xive_native_match(struct device_node *node)
+{
+ return of_device_is_compatible(node, "ibm,opal-xive-vc");
+}
+
+#ifdef CONFIG_SMP
+static int xive_native_get_ipi(unsigned int cpu, struct xive_cpu *xc)
+{
+ struct device_node *np;
+ unsigned int chip_id;
+ s64 irq;
+
+ /* Find the chip ID */
+ np = of_get_cpu_node(cpu, NULL);
+ if (np) {
+ if (of_property_read_u32(np, "ibm,chip-id", &chip_id) < 0)
+ chip_id = 0;
+ }
+
+ /* Allocate an IPI and populate info about it */
+ for (;;) {
+ irq = opal_xive_allocate_irq(chip_id);
+ if (irq == OPAL_BUSY) {
+ msleep(1);
+ continue;
+ }
+ if (irq < 0) {
+ pr_err("Failed to allocate IPI on CPU %d\n", cpu);
+ return -ENXIO;
+ }
+ xc->hw_ipi = irq;
+ break;
+ }
+ return 0;
+}
+#endif /* CONFIG_SMP */
+
+u32 xive_native_alloc_irq(void)
+{
+ s64 rc;
+
+ for (;;) {
+ rc = opal_xive_allocate_irq(OPAL_XIVE_ANY_CHIP);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ if (rc < 0)
+ return 0;
+ return rc;
+}
+EXPORT_SYMBOL_GPL(xive_native_alloc_irq);
+
+void xive_native_free_irq(u32 irq)
+{
+ for (;;) {
+ s64 rc = opal_xive_free_irq(irq);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+}
+EXPORT_SYMBOL_GPL(xive_native_free_irq);
+
+#ifdef CONFIG_SMP
+static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc)
+{
+ s64 rc;
+
+ /* Free the IPI */
+ if (!xc->hw_ipi)
+ return;
+ for (;;) {
+ rc = opal_xive_free_irq(xc->hw_ipi);
+ if (rc == OPAL_BUSY) {
+ msleep(1);
+ continue;
+ }
+ xc->hw_ipi = 0;
+ break;
+ }
+}
+#endif /* CONFIG_SMP */
+
+static void xive_native_shutdown(void)
+{
+ /* Switch the XIVE to emulation mode */
+ opal_xive_reset(OPAL_XIVE_MODE_EMU);
+}
+
+/*
+ * Perform an "ack" cycle on the current thread, thus
+ * grabbing the pending active priorities and updating
+ * the CPPR to the most favored one.
+ */
+static void xive_native_update_pending(struct xive_cpu *xc)
+{
+ u8 he, cppr;
+ u16 ack;
+
+ /* Perform the acknowledge hypervisor to register cycle */
+ ack = be16_to_cpu(__raw_readw(xive_tima + TM_SPC_ACK_HV_REG));
+
+ /* Synchronize subsequent queue accesses */
+ mb();
+
+ /*
+ * Grab the CPPR and the "HE" field which indicates the source
+ * of the hypervisor interrupt (if any)
+ */
+ cppr = ack & 0xff;
+ he = GETFIELD(TM_QW3_NSR_HE, (ack >> 8));
+ switch(he) {
+ case TM_QW3_NSR_HE_NONE: /* Nothing to see here */
+ break;
+ case TM_QW3_NSR_HE_PHYS: /* Physical thread interrupt */
+ if (cppr == 0xff)
+ return;
+ /* Mark the priority pending */
+ xc->pending_prio |= 1 << cppr;
+
+ /*
+ * A new interrupt should never have a CPPR less favored
+ * than our current one.
+ */
+ if (cppr >= xc->cppr)
+ pr_err("CPU %d odd ack CPPR, got %d at %d\n",
+ smp_processor_id(), cppr, xc->cppr);
+
+ /* Update our idea of what the CPPR is */
+ xc->cppr = cppr;
+ break;
+ case TM_QW3_NSR_HE_POOL: /* HV Pool interrupt (unused) */
+ case TM_QW3_NSR_HE_LSI: /* Legacy FW LSI (unused) */
+ pr_err("CPU %d got unexpected interrupt type HE=%d\n",
+ smp_processor_id(), he);
+ return;
+ }
+}
+
+static void xive_native_eoi(u32 hw_irq)
+{
+ /*
+ * Not normally used except if specific interrupts need
+ * a workaround on EOI.
+ */
+ opal_int_eoi(hw_irq);
+}
+
+static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
+{
+ s64 rc;
+ u32 vp;
+ __be64 vp_cam_be;
+ u64 vp_cam;
+
+ if (xive_pool_vps == XIVE_INVALID_VP)
+ return;
+
+ /* Enable the pool VP */
+ vp = xive_pool_vps + cpu;
+ pr_debug("CPU %d setting up pool VP 0x%x\n", cpu, vp);
+ for (;;) {
+ rc = opal_xive_set_vp_info(vp, OPAL_XIVE_VP_ENABLED, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ if (rc) {
+ pr_err("Failed to enable pool VP on CPU %d\n", cpu);
+ return;
+ }
+
+ /* Grab it's CAM value */
+ rc = opal_xive_get_vp_info(vp, NULL, &vp_cam_be, NULL, NULL);
+ if (rc) {
+ pr_err("Failed to get pool VP info CPU %d\n", cpu);
+ return;
+ }
+ vp_cam = be64_to_cpu(vp_cam_be);
+
+ pr_debug("VP CAM = %llx\n", vp_cam);
+
+ /* Push it on the CPU (set LSMFB to 0xff to skip backlog scan) */
+ pr_debug("(Old HW value: %08x)\n",
+ in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2));
+ out_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD0, 0xff);
+ out_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2,
+ TM_QW2W2_VP | vp_cam);
+ pr_debug("(New HW value: %08x)\n",
+ in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2));
+}
+
+static void xive_native_teardown_cpu(unsigned int cpu, struct xive_cpu *xc)
+{
+ s64 rc;
+ u32 vp;
+
+ if (xive_pool_vps == XIVE_INVALID_VP)
+ return;
+
+ /* Pull the pool VP from the CPU */
+ in_be64(xive_tima + TM_SPC_PULL_POOL_CTX);
+
+ /* Disable it */
+ vp = xive_pool_vps + cpu;
+ for (;;) {
+ rc = opal_xive_set_vp_info(vp, 0, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+}
+
+void xive_native_sync_source(u32 hw_irq)
+{
+ opal_xive_sync(XIVE_SYNC_EAS, hw_irq);
+}
+EXPORT_SYMBOL_GPL(xive_native_sync_source);
+
+static const struct xive_ops xive_native_ops = {
+ .populate_irq_data = xive_native_populate_irq_data,
+ .configure_irq = xive_native_configure_irq,
+ .setup_queue = xive_native_setup_queue,
+ .cleanup_queue = xive_native_cleanup_queue,
+ .match = xive_native_match,
+ .shutdown = xive_native_shutdown,
+ .update_pending = xive_native_update_pending,
+ .eoi = xive_native_eoi,
+ .setup_cpu = xive_native_setup_cpu,
+ .teardown_cpu = xive_native_teardown_cpu,
+ .sync_source = xive_native_sync_source,
+#ifdef CONFIG_SMP
+ .get_ipi = xive_native_get_ipi,
+ .put_ipi = xive_native_put_ipi,
+#endif /* CONFIG_SMP */
+ .name = "native",
+};
+
+static bool xive_parse_provisioning(struct device_node *np)
+{
+ int rc;
+
+ if (of_property_read_u32(np, "ibm,xive-provision-page-size",
+ &xive_provision_size) < 0)
+ return true;
+ rc = of_property_count_elems_of_size(np, "ibm,xive-provision-chips", 4);
+ if (rc < 0) {
+ pr_err("Error %d getting provision chips array\n", rc);
+ return false;
+ }
+ xive_provision_chip_count = rc;
+ if (rc == 0)
+ return true;
+
+ xive_provision_chips = kzalloc(4 * xive_provision_chip_count,
+ GFP_KERNEL);
+ if (WARN_ON(!xive_provision_chips))
+ return false;
+
+ rc = of_property_read_u32_array(np, "ibm,xive-provision-chips",
+ xive_provision_chips,
+ xive_provision_chip_count);
+ if (rc < 0) {
+ pr_err("Error %d reading provision chips array\n", rc);
+ return false;
+ }
+
+ xive_provision_cache = kmem_cache_create("xive-provision",
+ xive_provision_size,
+ xive_provision_size,
+ 0, NULL);
+ if (!xive_provision_cache) {
+ pr_err("Failed to allocate provision cache\n");
+ return false;
+ }
+ return true;
+}
+
+static void xive_native_setup_pools(void)
+{
+ /* Allocate a pool big enough */
+ pr_debug("XIVE: Allocating VP block for pool size %d\n", nr_cpu_ids);
+
+ xive_pool_vps = xive_native_alloc_vp_block(nr_cpu_ids);
+ if (WARN_ON(xive_pool_vps == XIVE_INVALID_VP))
+ pr_err("XIVE: Failed to allocate pool VP, KVM might not function\n");
+
+ pr_debug("XIVE: Pool VPs allocated at 0x%x for %d max CPUs\n",
+ xive_pool_vps, nr_cpu_ids);
+}
+
+u32 xive_native_default_eq_shift(void)
+{
+ return xive_queue_shift;
+}
+EXPORT_SYMBOL_GPL(xive_native_default_eq_shift);
+
+bool xive_native_init(void)
+{
+ struct device_node *np;
+ struct resource r;
+ void __iomem *tima;
+ struct property *prop;
+ u8 max_prio = 7;
+ const __be32 *p;
+ u32 val, cpu;
+ s64 rc;
+
+ if (xive_cmdline_disabled)
+ return false;
+
+ pr_devel("xive_native_init()\n");
+ np = of_find_compatible_node(NULL, NULL, "ibm,opal-xive-pe");
+ if (!np) {
+ pr_devel("not found !\n");
+ return false;
+ }
+ pr_devel("Found %s\n", np->full_name);
+
+ /* Resource 1 is HV window */
+ if (of_address_to_resource(np, 1, &r)) {
+ pr_err("Failed to get thread mgmnt area resource\n");
+ return false;
+ }
+ tima = ioremap(r.start, resource_size(&r));
+ if (!tima) {
+ pr_err("Failed to map thread mgmnt area\n");
+ return false;
+ }
+
+ /* Read number of priorities */
+ if (of_property_read_u32(np, "ibm,xive-#priorities", &val) == 0)
+ max_prio = val - 1;
+
+ /* Iterate the EQ sizes and pick one */
+ of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, p, val) {
+ xive_queue_shift = val;
+ if (val == PAGE_SHIFT)
+ break;
+ }
+
+ /* Configure Thread Management areas for KVM */
+ for_each_possible_cpu(cpu)
+ kvmppc_set_xive_tima(cpu, r.start, tima);
+
+ /* Grab size of provisionning pages */
+ xive_parse_provisioning(np);
+
+ /* Switch the XIVE to exploitation mode */
+ rc = opal_xive_reset(OPAL_XIVE_MODE_EXPL);
+ if (rc) {
+ pr_err("Switch to exploitation mode failed with error %lld\n", rc);
+ return false;
+ }
+
+ /* Setup some dummy HV pool VPs */
+ xive_native_setup_pools();
+
+ /* Initialize XIVE core with our backend */
+ if (!xive_core_init(&xive_native_ops, tima, TM_QW3_HV_PHYS,
+ max_prio)) {
+ opal_xive_reset(OPAL_XIVE_MODE_EMU);
+ return false;
+ }
+ pr_info("Using %dkB queues\n", 1 << (xive_queue_shift - 10));
+ return true;
+}
+
+static bool xive_native_provision_pages(void)
+{
+ u32 i;
+ void *p;
+
+ for (i = 0; i < xive_provision_chip_count; i++) {
+ u32 chip = xive_provision_chips[i];
+
+ /*
+ * XXX TODO: Try to make the allocation local to the node where
+ * the chip resides.
+ */
+ p = kmem_cache_alloc(xive_provision_cache, GFP_KERNEL);
+ if (!p) {
+ pr_err("Failed to allocate provisioning page\n");
+ return false;
+ }
+ opal_xive_donate_page(chip, __pa(p));
+ }
+ return true;
+}
+
+u32 xive_native_alloc_vp_block(u32 max_vcpus)
+{
+ s64 rc;
+ u32 order;
+
+ order = fls(max_vcpus) - 1;
+ if (max_vcpus > (1 << order))
+ order++;
+
+ pr_info("VP block alloc, for max VCPUs %d use order %d\n",
+ max_vcpus, order);
+
+ for (;;) {
+ rc = opal_xive_alloc_vp_block(order);
+ switch (rc) {
+ case OPAL_BUSY:
+ msleep(1);
+ break;
+ case OPAL_XIVE_PROVISIONING:
+ if (!xive_native_provision_pages())
+ return XIVE_INVALID_VP;
+ break;
+ default:
+ if (rc < 0) {
+ pr_err("OPAL failed to allocate VCPUs order %d, err %lld\n",
+ order, rc);
+ return XIVE_INVALID_VP;
+ }
+ return rc;
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(xive_native_alloc_vp_block);
+
+void xive_native_free_vp_block(u32 vp_base)
+{
+ s64 rc;
+
+ if (vp_base == XIVE_INVALID_VP)
+ return;
+
+ rc = opal_xive_free_vp_block(vp_base);
+ if (rc < 0)
+ pr_warn("OPAL error %lld freeing VP block\n", rc);
+}
+EXPORT_SYMBOL_GPL(xive_native_free_vp_block);
+
+int xive_native_enable_vp(u32 vp_id)
+{
+ s64 rc;
+
+ for (;;) {
+ rc = opal_xive_set_vp_info(vp_id, OPAL_XIVE_VP_ENABLED, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ return rc ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_enable_vp);
+
+int xive_native_disable_vp(u32 vp_id)
+{
+ s64 rc;
+
+ for (;;) {
+ rc = opal_xive_set_vp_info(vp_id, 0, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ return rc ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_disable_vp);
+
+int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id)
+{
+ __be64 vp_cam_be;
+ __be32 vp_chip_id_be;
+ s64 rc;
+
+ rc = opal_xive_get_vp_info(vp_id, NULL, &vp_cam_be, NULL, &vp_chip_id_be);
+ if (rc)
+ return -EIO;
+ *out_cam_id = be64_to_cpu(vp_cam_be) & 0xffffffffu;
+ *out_chip_id = be32_to_cpu(vp_chip_id_be);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_vp_info);
diff --git a/arch/powerpc/sysdev/xive/xive-internal.h b/arch/powerpc/sysdev/xive/xive-internal.h
new file mode 100644
index 000000000000..d07ef2d29caf
--- /dev/null
+++ b/arch/powerpc/sysdev/xive/xive-internal.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright 2016,2017 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef __XIVE_INTERNAL_H
+#define __XIVE_INTERNAL_H
+
+/* Each CPU carry one of these with various per-CPU state */
+struct xive_cpu {
+#ifdef CONFIG_SMP
+ /* HW irq number and data of IPI */
+ u32 hw_ipi;
+ struct xive_irq_data ipi_data;
+#endif /* CONFIG_SMP */
+
+ int chip_id;
+
+ /* Queue datas. Only one is populated */
+#define XIVE_MAX_QUEUES 8
+ struct xive_q queue[XIVE_MAX_QUEUES];
+
+ /*
+ * Pending mask. Each bit corresponds to a priority that
+ * potentially has pending interrupts.
+ */
+ u8 pending_prio;
+
+ /* Cache of HW CPPR */
+ u8 cppr;
+};
+
+/* Backend ops */
+struct xive_ops {
+ int (*populate_irq_data)(u32 hw_irq, struct xive_irq_data *data);
+ int (*configure_irq)(u32 hw_irq, u32 target, u8 prio, u32 sw_irq);
+ int (*setup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio);
+ void (*cleanup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio);
+ void (*setup_cpu)(unsigned int cpu, struct xive_cpu *xc);
+ void (*teardown_cpu)(unsigned int cpu, struct xive_cpu *xc);
+ bool (*match)(struct device_node *np);
+ void (*shutdown)(void);
+
+ void (*update_pending)(struct xive_cpu *xc);
+ void (*eoi)(u32 hw_irq);
+ void (*sync_source)(u32 hw_irq);
+#ifdef CONFIG_SMP
+ int (*get_ipi)(unsigned int cpu, struct xive_cpu *xc);
+ void (*put_ipi)(unsigned int cpu, struct xive_cpu *xc);
+#endif
+ const char *name;
+};
+
+bool xive_core_init(const struct xive_ops *ops, void __iomem *area, u32 offset,
+ u8 max_prio);
+
+extern bool xive_cmdline_disabled;
+
+#endif /* __XIVE_INTERNAL_H */
diff --git a/arch/powerpc/scripts/gcc-check-mprofile-kernel.sh b/arch/powerpc/tools/gcc-check-mprofile-kernel.sh
index c658d8cf760b..c658d8cf760b 100755
--- a/arch/powerpc/scripts/gcc-check-mprofile-kernel.sh
+++ b/arch/powerpc/tools/gcc-check-mprofile-kernel.sh
diff --git a/arch/powerpc/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh
index ec2d5c835170..ec2d5c835170 100755
--- a/arch/powerpc/relocs_check.sh
+++ b/arch/powerpc/tools/relocs_check.sh
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 16321ad9e70c..f11f65634aab 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -29,7 +29,9 @@
#include <linux/nmi.h>
#include <linux/ctype.h>
+#include <asm/debugfs.h>
#include <asm/ptrace.h>
+#include <asm/smp.h>
#include <asm/string.h>
#include <asm/prom.h>
#include <asm/machdep.h>
@@ -48,7 +50,7 @@
#include <asm/reg.h>
#include <asm/debug.h>
#include <asm/hw_breakpoint.h>
-
+#include <asm/xive.h>
#include <asm/opal.h>
#include <asm/firmware.h>
@@ -76,6 +78,7 @@ static int xmon_gate;
#endif /* CONFIG_SMP */
static unsigned long in_xmon __read_mostly = 0;
+static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT);
static unsigned long adrs;
static int size = 1;
@@ -184,8 +187,6 @@ static void dump_tlb_44x(void);
static void dump_tlb_book3e(void);
#endif
-static int xmon_no_auto_backtrace;
-
#ifdef CONFIG_PPC64
#define REG "%.16lx"
#else
@@ -232,7 +233,13 @@ Commands:\n\
"\
dr dump stream of raw bytes\n\
dt dump the tracing buffers (uses printk)\n\
- e print exception information\n\
+"
+#ifdef CONFIG_PPC_POWERNV
+" dx# dump xive on CPU #\n\
+ dxi# dump xive irq state #\n\
+ dxa dump xive on all CPUs\n"
+#endif
+" e print exception information\n\
f flush cache\n\
la lookup symbol+offset of specified address\n\
ls lookup address of specified symbol\n\
@@ -411,7 +418,22 @@ int cpus_are_in_xmon(void)
{
return !cpumask_empty(&cpus_in_xmon);
}
-#endif
+
+static bool wait_for_other_cpus(int ncpus)
+{
+ unsigned long timeout;
+
+ /* We wait for 2s, which is a metric "little while" */
+ for (timeout = 20000; timeout != 0; --timeout) {
+ if (cpumask_weight(&cpus_in_xmon) >= ncpus)
+ return true;
+ udelay(100);
+ barrier();
+ }
+
+ return false;
+}
+#endif /* CONFIG_SMP */
static inline int unrecoverable_excp(struct pt_regs *regs)
{
@@ -433,7 +455,6 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
#ifdef CONFIG_SMP
int cpu;
int secondary;
- unsigned long timeout;
#endif
local_irq_save(flags);
@@ -520,13 +541,17 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
xmon_owner = cpu;
mb();
if (ncpus > 1) {
- smp_send_debugger_break();
- /* wait for other cpus to come in */
- for (timeout = 100000000; timeout != 0; --timeout) {
- if (cpumask_weight(&cpus_in_xmon) >= ncpus)
- break;
- barrier();
- }
+ /*
+ * A system reset (trap == 0x100) can be triggered on
+ * all CPUs, so when we come in via 0x100 try waiting
+ * for the other CPUs to come in before we send the
+ * debugger break (IPI). This is similar to
+ * crash_kexec_secondary().
+ */
+ if (TRAP(regs) != 0x100 || !wait_for_other_cpus(ncpus))
+ smp_send_debugger_break();
+
+ wait_for_other_cpus(ncpus);
}
remove_bpts();
disable_surveillance();
@@ -884,10 +909,7 @@ cmds(struct pt_regs *excp)
last_cmd = NULL;
xmon_regs = excp;
- if (!xmon_no_auto_backtrace) {
- xmon_no_auto_backtrace = 1;
- xmon_show_stack(excp->gpr[1], excp->link, excp->nip);
- }
+ xmon_show_stack(excp->gpr[1], excp->link, excp->nip);
for(;;) {
#ifdef CONFIG_SMP
@@ -1347,9 +1369,19 @@ const char *getvecname(unsigned long vec)
case 0x100: ret = "(System Reset)"; break;
case 0x200: ret = "(Machine Check)"; break;
case 0x300: ret = "(Data Access)"; break;
- case 0x380: ret = "(Data SLB Access)"; break;
+ case 0x380:
+ if (radix_enabled())
+ ret = "(Data Access Out of Range)";
+ else
+ ret = "(Data SLB Access)";
+ break;
case 0x400: ret = "(Instruction Access)"; break;
- case 0x480: ret = "(Instruction SLB Access)"; break;
+ case 0x480:
+ if (radix_enabled())
+ ret = "(Instruction Access Out of Range)";
+ else
+ ret = "(Instruction SLB Access)";
+ break;
case 0x500: ret = "(Hardware Interrupt)"; break;
case 0x600: ret = "(Alignment)"; break;
case 0x700: ret = "(Program Check)"; break;
@@ -2231,7 +2263,9 @@ static void dump_one_paca(int cpu)
DUMP(p, kernel_msr, "lx");
DUMP(p, emergency_sp, "p");
#ifdef CONFIG_PPC_BOOK3S_64
+ DUMP(p, nmi_emergency_sp, "p");
DUMP(p, mc_emergency_sp, "p");
+ DUMP(p, in_nmi, "x");
DUMP(p, in_mce, "x");
DUMP(p, hmi_event_available, "x");
#endif
@@ -2338,6 +2372,81 @@ static void dump_pacas(void)
}
#endif
+#ifdef CONFIG_PPC_POWERNV
+static void dump_one_xive(int cpu)
+{
+ unsigned int hwid = get_hard_smp_processor_id(cpu);
+
+ opal_xive_dump(XIVE_DUMP_TM_HYP, hwid);
+ opal_xive_dump(XIVE_DUMP_TM_POOL, hwid);
+ opal_xive_dump(XIVE_DUMP_TM_OS, hwid);
+ opal_xive_dump(XIVE_DUMP_TM_USER, hwid);
+ opal_xive_dump(XIVE_DUMP_VP, hwid);
+ opal_xive_dump(XIVE_DUMP_EMU_STATE, hwid);
+
+ if (setjmp(bus_error_jmp) != 0) {
+ catch_memory_errors = 0;
+ printf("*** Error dumping xive on cpu %d\n", cpu);
+ return;
+ }
+
+ catch_memory_errors = 1;
+ sync();
+ xmon_xive_do_dump(cpu);
+ sync();
+ __delay(200);
+ catch_memory_errors = 0;
+}
+
+static void dump_all_xives(void)
+{
+ int cpu;
+
+ if (num_possible_cpus() == 0) {
+ printf("No possible cpus, use 'dx #' to dump individual cpus\n");
+ return;
+ }
+
+ for_each_possible_cpu(cpu)
+ dump_one_xive(cpu);
+}
+
+static void dump_one_xive_irq(u32 num)
+{
+ s64 rc;
+ __be64 vp;
+ u8 prio;
+ __be32 lirq;
+
+ rc = opal_xive_get_irq_config(num, &vp, &prio, &lirq);
+ xmon_printf("IRQ 0x%x config: vp=0x%llx prio=%d lirq=0x%x (rc=%lld)\n",
+ num, be64_to_cpu(vp), prio, be32_to_cpu(lirq), rc);
+}
+
+static void dump_xives(void)
+{
+ unsigned long num;
+ int c;
+
+ c = inchar();
+ if (c == 'a') {
+ dump_all_xives();
+ return;
+ } else if (c == 'i') {
+ if (scanhex(&num))
+ dump_one_xive_irq(num);
+ return;
+ }
+
+ termch = c; /* Put c back, it wasn't 'a' */
+
+ if (scanhex(&num))
+ dump_one_xive(num);
+ else
+ dump_one_xive(xmon_owner);
+}
+#endif /* CONFIG_PPC_POWERNV */
+
static void dump_by_size(unsigned long addr, long count, int size)
{
unsigned char temp[16];
@@ -2386,6 +2495,14 @@ dump(void)
return;
}
#endif
+#ifdef CONFIG_PPC_POWERNV
+ if (c == 'x') {
+ xmon_start_pagination();
+ dump_xives();
+ xmon_end_pagination();
+ return;
+ }
+#endif
if (c == '\n')
termch = c;
@@ -3070,23 +3187,28 @@ void dump_segments(void)
for (i = 0; i < mmu_slb_size; i++) {
asm volatile("slbmfee %0,%1" : "=r" (esid) : "r" (i));
asm volatile("slbmfev %0,%1" : "=r" (vsid) : "r" (i));
- if (esid || vsid) {
- printf("%02d %016lx %016lx", i, esid, vsid);
- if (esid & SLB_ESID_V) {
- llp = vsid & SLB_VSID_LLP;
- if (vsid & SLB_VSID_B_1T) {
- printf(" 1T ESID=%9lx VSID=%13lx LLP:%3lx \n",
- GET_ESID_1T(esid),
- (vsid & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T,
- llp);
- } else {
- printf(" 256M ESID=%9lx VSID=%13lx LLP:%3lx \n",
- GET_ESID(esid),
- (vsid & ~SLB_VSID_B) >> SLB_VSID_SHIFT,
- llp);
- }
- } else
- printf("\n");
+
+ if (!esid && !vsid)
+ continue;
+
+ printf("%02d %016lx %016lx", i, esid, vsid);
+
+ if (!(esid & SLB_ESID_V)) {
+ printf("\n");
+ continue;
+ }
+
+ llp = vsid & SLB_VSID_LLP;
+ if (vsid & SLB_VSID_B_1T) {
+ printf(" 1T ESID=%9lx VSID=%13lx LLP:%3lx \n",
+ GET_ESID_1T(esid),
+ (vsid & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T,
+ llp);
+ } else {
+ printf(" 256M ESID=%9lx VSID=%13lx LLP:%3lx \n",
+ GET_ESID(esid),
+ (vsid & ~SLB_VSID_B) >> SLB_VSID_SHIFT,
+ llp);
}
}
}
@@ -3302,6 +3424,8 @@ static void sysrq_handle_xmon(int key)
/* ensure xmon is enabled */
xmon_init(1);
debugger(get_irq_regs());
+ if (!xmon_on)
+ xmon_init(0);
}
static struct sysrq_key_op sysrq_xmon_op = {
@@ -3315,10 +3439,37 @@ static int __init setup_xmon_sysrq(void)
register_sysrq_key('x', &sysrq_xmon_op);
return 0;
}
-__initcall(setup_xmon_sysrq);
+device_initcall(setup_xmon_sysrq);
#endif /* CONFIG_MAGIC_SYSRQ */
-static int __initdata xmon_early, xmon_off;
+#ifdef CONFIG_DEBUG_FS
+static int xmon_dbgfs_set(void *data, u64 val)
+{
+ xmon_on = !!val;
+ xmon_init(xmon_on);
+
+ return 0;
+}
+
+static int xmon_dbgfs_get(void *data, u64 *val)
+{
+ *val = xmon_on;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(xmon_dbgfs_ops, xmon_dbgfs_get,
+ xmon_dbgfs_set, "%llu\n");
+
+static int __init setup_xmon_dbgfs(void)
+{
+ debugfs_create_file("xmon", 0600, powerpc_debugfs_root, NULL,
+ &xmon_dbgfs_ops);
+ return 0;
+}
+device_initcall(setup_xmon_dbgfs);
+#endif /* CONFIG_DEBUG_FS */
+
+static int xmon_early __initdata;
static int __init early_parse_xmon(char *p)
{
@@ -3326,12 +3477,12 @@ static int __init early_parse_xmon(char *p)
/* just "xmon" is equivalent to "xmon=early" */
xmon_init(1);
xmon_early = 1;
- } else if (strncmp(p, "on", 2) == 0)
+ xmon_on = 1;
+ } else if (strncmp(p, "on", 2) == 0) {
xmon_init(1);
- else if (strncmp(p, "off", 3) == 0)
- xmon_off = 1;
- else if (strncmp(p, "nobt", 4) == 0)
- xmon_no_auto_backtrace = 1;
+ xmon_on = 1;
+ } else if (strncmp(p, "off", 3) == 0)
+ xmon_on = 0;
else
return 1;
@@ -3341,10 +3492,8 @@ early_param("xmon", early_parse_xmon);
void __init xmon_setup(void)
{
-#ifdef CONFIG_XMON_DEFAULT
- if (!xmon_off)
+ if (xmon_on)
xmon_init(1);
-#endif
if (xmon_early)
debugger(NULL);
}