whiterose

linux unikernel
Log | Files | Refs | README | LICENSE | git clone https://git.ne02ptzero.me/git/whiterose

commit 8d6973327ee84c2f40dd9efd8928d4a1186c96e2
parent 6d101ba6be2a26a3e1f513b5e293f0fd2b79ec5c
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date:   Thu, 27 Dec 2018 10:43:24 -0800

Merge tag 'powerpc-4.21-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Mitigations for Spectre v2 on some Freescale (NXP) CPUs.

   - A large series adding support for pass-through of Nvidia V100 GPUs
     to guests on Power9.

   - Another large series to enable hardware assistance for TLB table
     walk on MPC8xx CPUs.

   - Some preparatory changes to our DMA code, to make way for further
     cleanups from Christoph.

   - Several fixes for our Transactional Memory handling discovered by
     fuzzing the signal return path.

   - Support for generating our system call table(s) from a text file
     like other architectures.

   - A fix to our page fault handler so that instead of generating a
     WARN_ON_ONCE, user accesses of kernel addresses instead print a
     ratelimited and appropriately scary warning.

   - A cosmetic change to make our unhandled page fault messages more
     similar to other arches and also more compact and informative.

   - Freescale updates from Scott:
       "Highlights include elimination of legacy clock bindings use from
        dts files, an 83xx watchdog handler, fixes to old dts interrupt
        errors, and some minor cleanup."

  And many clean-ups, reworks and minor fixes etc.

  Thanks to: Alexandre Belloni, Alexey Kardashevskiy, Andrew Donnellan,
  Aneesh Kumar K.V, Arnd Bergmann, Benjamin Herrenschmidt, Breno Leitao,
  Christian Lamparter, Christophe Leroy, Christoph Hellwig, Daniel
  Axtens, Darren Stevens, David Gibson, Diana Craciun, Dmitry V. Levin,
  Firoz Khan, Geert Uytterhoeven, Greg Kurz, Gustavo Romero, Hari
  Bathini, Joel Stanley, Kees Cook, Madhavan Srinivasan, Mahesh
  Salgaonkar, Markus Elfring, Mathieu Malaterre, Michal Suchánek, Naveen
  N. Rao, Nick Desaulniers, Oliver O'Halloran, Paul Mackerras, Ram Pai,
  Ravi Bangoria, Rob Herring, Russell Currey, Sabyasachi Gupta, Sam
  Bobroff, Satheesh Rajendran, Scott Wood, Segher Boessenkool, Stephen
  Rothwell, Tang Yuantian, Thiago Jung Bauermann, Yangtao Li, Yuantian
  Tang, Yue Haibing"

* tag 'powerpc-4.21-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (201 commits)
  Revert "powerpc/fsl_pci: simplify fsl_pci_dma_set_mask"
  powerpc/zImage: Also check for stdout-path
  powerpc: Fix HMIs on big-endian with CONFIG_RELOCATABLE=y
  macintosh: Use of_node_name_{eq, prefix} for node name comparisons
  ide: Use of_node_name_eq for node name comparisons
  powerpc: Use of_node_name_eq for node name comparisons
  powerpc/pseries/pmem: Convert to %pOFn instead of device_node.name
  powerpc/mm: Remove very old comment in hash-4k.h
  powerpc/pseries: Fix node leak in update_lmb_associativity_index()
  powerpc/configs/85xx: Enable CONFIG_DEBUG_KERNEL
  powerpc/dts/fsl: Fix dtc-flagged interrupt errors
  clk: qoriq: add more compatibles strings
  powerpc/fsl: Use new clockgen binding
  powerpc/83xx: handle machine check caused by watchdog timer
  powerpc/fsl-rio: fix spelling mistake "reserverd" -> "reserved"
  powerpc/fsl_pci: simplify fsl_pci_dma_set_mask
  arch/powerpc/fsl_rmu: Use dma_zalloc_coherent
  vfio_pci: Add NVIDIA GV100GL [Tesla V100 SXM2] subdriver
  vfio_pci: Allow regions to add own capabilities
  vfio_pci: Allow mapping extra regions
  ...

Diffstat:
MDocumentation/admin-guide/kernel-parameters.txt | 2+-
MDocumentation/devicetree/bindings/clock/qoriq-clock.txt | 6++++++
MDocumentation/powerpc/firmware-assisted-dump.txt | 17++++++++++++++++-
ADocumentation/powerpc/isa-versions.rst | 74++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
March/powerpc/Kconfig | 15++++++---------
March/powerpc/Makefile | 28+++++++++++++++++++++++-----
March/powerpc/boot/dts/bamboo.dts | 4+++-
March/powerpc/boot/dts/fsl/b4420si-pre.dtsi | 4++--
March/powerpc/boot/dts/fsl/b4860si-pre.dtsi | 8++++----
March/powerpc/boot/dts/fsl/b4si-post.dtsi | 15---------------
March/powerpc/boot/dts/fsl/mpc8641_hpcn.dts | 128++++++++++++++++++++++++++++++++++++++++----------------------------------------
March/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts | 128++++++++++++++++++++++++++++++++++++++++----------------------------------------
March/powerpc/boot/dts/fsl/mpc8641si-post.dtsi | 2++
March/powerpc/boot/dts/fsl/p1020rdb-pc.dtsi | 4++--
March/powerpc/boot/dts/fsl/p2041si-post.dtsi | 18------------------
March/powerpc/boot/dts/fsl/p2041si-pre.dtsi | 8++++----
March/powerpc/boot/dts/fsl/p3041si-post.dtsi | 18------------------
March/powerpc/boot/dts/fsl/p3041si-pre.dtsi | 8++++----
March/powerpc/boot/dts/fsl/p4080si-post.dtsi | 70----------------------------------------------------------------------
March/powerpc/boot/dts/fsl/p4080si-pre.dtsi | 16++++++++--------
March/powerpc/boot/dts/fsl/p5020si-pre.dtsi | 4++--
March/powerpc/boot/dts/fsl/p5040si-post.dtsi | 18------------------
March/powerpc/boot/dts/fsl/p5040si-pre.dtsi | 8++++----
March/powerpc/boot/dts/fsl/qoriq-clockgen1.dtsi | 47-----------------------------------------------
March/powerpc/boot/dts/fsl/qoriq-clockgen2.dtsi | 30------------------------------
March/powerpc/boot/dts/fsl/t1023si-post.dtsi | 16----------------
March/powerpc/boot/dts/fsl/t102xsi-pre.dtsi | 4++--
March/powerpc/boot/dts/fsl/t1040si-post.dtsi | 44--------------------------------------------
March/powerpc/boot/dts/fsl/t104xsi-pre.dtsi | 8++++----
March/powerpc/boot/dts/fsl/t2081si-post.dtsi | 22----------------------
March/powerpc/boot/dts/fsl/t208xsi-pre.dtsi | 8++++----
March/powerpc/boot/dts/fsl/t4240si-post.dtsi | 61-------------------------------------------------------------
March/powerpc/boot/dts/fsl/t4240si-pre.dtsi | 24++++++++++++------------
March/powerpc/boot/dts/mpc832x_rdb.dts | 4----
March/powerpc/boot/serial.c | 3++-
March/powerpc/configs/fsl-emb-nonhw.config | 1+
March/powerpc/configs/g5_defconfig | 1-
Aarch/powerpc/configs/guest.config | 13+++++++++++++
March/powerpc/configs/maple_defconfig | 1-
March/powerpc/configs/pmac32_defconfig | 1-
March/powerpc/configs/ppc64_defconfig | 81+++++++++++++++++++++++++++++++++++++++++++------------------------------------
March/powerpc/configs/ppc6xx_defconfig | 1-
March/powerpc/configs/pseries_defconfig | 2--
March/powerpc/include/asm/Kbuild | 4++++
March/powerpc/include/asm/asm-prototypes.h | 1-
March/powerpc/include/asm/book3s/32/hash.h | 1+
March/powerpc/include/asm/book3s/32/mmu-hash.h | 15+++++++++++++++
March/powerpc/include/asm/book3s/32/pgalloc.h | 40++++++++++------------------------------
March/powerpc/include/asm/book3s/32/pgtable.h | 46+++++++++++++++-------------------------------
March/powerpc/include/asm/book3s/64/hash-4k.h | 6+-----
March/powerpc/include/asm/book3s/64/mmu.h | 9+++++++++
March/powerpc/include/asm/book3s/64/pgalloc.h | 6++----
March/powerpc/include/asm/book3s/64/pgtable.h | 2+-
March/powerpc/include/asm/cache.h | 2+-
March/powerpc/include/asm/code-patching.h | 23+++++++++++++++++++++--
March/powerpc/include/asm/cputable.h | 9+++++----
March/powerpc/include/asm/dma-mapping.h | 7-------
March/powerpc/include/asm/fadump.h | 7++++++-
March/powerpc/include/asm/feature-fixups.h | 12++++++++++++
March/powerpc/include/asm/hugetlb.h | 15+++++++--------
March/powerpc/include/asm/io.h | 13++++++++++++-
March/powerpc/include/asm/iommu.h | 17+++++++----------
March/powerpc/include/asm/ipic.h | 1-
Darch/powerpc/include/asm/mmu-44x.h | 153-------------------------------------------------------------------------------
Darch/powerpc/include/asm/mmu-8xx.h | 253-------------------------------------------------------------------------------
March/powerpc/include/asm/mmu.h | 49++++++++++++++++++++++++++++++-------------------
March/powerpc/include/asm/mmu_context.h | 32+++++++++++++++++++++++---------
Rarch/powerpc/include/asm/mmu-40x.h -> arch/powerpc/include/asm/nohash/32/mmu-40x.h | 0
Aarch/powerpc/include/asm/nohash/32/mmu-44x.h | 156+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Aarch/powerpc/include/asm/nohash/32/mmu-8xx.h | 257+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Aarch/powerpc/include/asm/nohash/32/mmu.h | 25+++++++++++++++++++++++++
March/powerpc/include/asm/nohash/32/pgalloc.h | 27++++++++++++---------------
March/powerpc/include/asm/nohash/32/pgtable.h | 15+++++++++++----
March/powerpc/include/asm/nohash/32/pte-40x.h | 2+-
March/powerpc/include/asm/nohash/32/pte-8xx.h | 3---
Aarch/powerpc/include/asm/nohash/64/mmu.h | 12++++++++++++
March/powerpc/include/asm/nohash/64/pgalloc.h | 5+----
Rarch/powerpc/include/asm/mmu-book3e.h -> arch/powerpc/include/asm/nohash/mmu-book3e.h | 0
Aarch/powerpc/include/asm/nohash/mmu.h | 11+++++++++++
March/powerpc/include/asm/nohash/pgtable.h | 4++++
March/powerpc/include/asm/opal.h | 1+
March/powerpc/include/asm/page.h | 18+++---------------
March/powerpc/include/asm/page_32.h | 3++-
March/powerpc/include/asm/pci-bridge.h | 1+
March/powerpc/include/asm/pci.h | 4++++
March/powerpc/include/asm/perf_event.h | 3+++
March/powerpc/include/asm/perf_event_server.h | 2++
March/powerpc/include/asm/pgtable-types.h | 4++++
March/powerpc/include/asm/pgtable.h | 32++++++++++++++++++++++++++++++--
March/powerpc/include/asm/ppc-opcode.h | 1+
March/powerpc/include/asm/ppc_asm.h | 29++++++++++++-----------------
March/powerpc/include/asm/reg.h | 4+++-
March/powerpc/include/asm/setup.h | 7+++++++
March/powerpc/include/asm/sfp-machine.h | 92+++++++++++++++++++++++++------------------------------------------------------
March/powerpc/include/asm/slice.h | 14+++++++++-----
March/powerpc/include/asm/syscall.h | 3+--
Darch/powerpc/include/asm/systbl.h | 396-------------------------------------------------------------------------------
March/powerpc/include/asm/time.h | 2+-
March/powerpc/include/asm/tlb.h | 2+-
March/powerpc/include/asm/uaccess.h | 2+-
March/powerpc/include/asm/unistd.h | 3+--
March/powerpc/include/uapi/asm/Kbuild | 2++
March/powerpc/include/uapi/asm/perf_regs.h | 1+
March/powerpc/include/uapi/asm/unistd.h | 389+------------------------------------------------------------------------------
March/powerpc/kernel/Makefile | 12+-----------
March/powerpc/kernel/btext.c | 16++++------------
March/powerpc/kernel/cacheinfo.c | 2+-
March/powerpc/kernel/cpu_setup_6xx.S | 2+-
March/powerpc/kernel/cpu_setup_fsl_booke.S | 2+-
March/powerpc/kernel/cputable.c | 10++++++----
March/powerpc/kernel/dma-iommu.c | 2--
March/powerpc/kernel/dma-swiotlb.c | 6+-----
March/powerpc/kernel/dma.c | 31+++++++++++++------------------
March/powerpc/kernel/eeh.c | 20++++++++++----------
March/powerpc/kernel/eeh_driver.c | 2+-
March/powerpc/kernel/eeh_event.c | 9+++------
March/powerpc/kernel/entry_32.S | 10+++++-----
March/powerpc/kernel/entry_64.S | 16++++++++++++++--
March/powerpc/kernel/exceptions-64e.S | 26+++++++++++++++++++++++++-
March/powerpc/kernel/exceptions-64s.S | 2+-
March/powerpc/kernel/fadump.c | 154++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------------
March/powerpc/kernel/head_32.S | 20++++++++++++--------
March/powerpc/kernel/head_44x.S | 11+++++------
March/powerpc/kernel/head_8xx.S | 369++++++++++++++++++++++++++++++-------------------------------------------------
March/powerpc/kernel/head_booke.h | 6++++++
March/powerpc/kernel/head_fsl_booke.S | 15+++++++++++++++
March/powerpc/kernel/iommu.c | 69+++++++++++----------------------------------------------------------
March/powerpc/kernel/isa-bridge.c | 3+--
March/powerpc/kernel/legacy_serial.c | 10+++++-----
March/powerpc/kernel/misc_32.S | 4++--
March/powerpc/kernel/nvram_64.c | 1+
March/powerpc/kernel/pci_of_scan.c | 11++++-------
March/powerpc/kernel/pmc.c | 2+-
March/powerpc/kernel/prom.c | 10+++++-----
March/powerpc/kernel/ptrace.c | 54+++++++++++++++++++++++++++++++-----------------------
March/powerpc/kernel/security.c | 29+++++++++++++++++++++++++++--
March/powerpc/kernel/setup-common.c | 7++++---
March/powerpc/kernel/setup_32.c | 6++----
March/powerpc/kernel/signal_32.c | 50++++++++++++++++++++++++++++++++++++++------------
March/powerpc/kernel/signal_64.c | 71++++++++++++++++++++++++++++++++++++++++++++++++++---------------------
Aarch/powerpc/kernel/syscalls/Makefile | 63+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Aarch/powerpc/kernel/syscalls/syscall.tbl | 427+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Aarch/powerpc/kernel/syscalls/syscallhdr.sh | 37+++++++++++++++++++++++++++++++++++++
Aarch/powerpc/kernel/syscalls/syscalltbl.sh | 36++++++++++++++++++++++++++++++++++++
March/powerpc/kernel/sysfs.c | 2+-
March/powerpc/kernel/systbl.S | 40+++++++++++++++++-----------------------
Darch/powerpc/kernel/systbl_chk.c | 60------------------------------------------------------------
March/powerpc/kernel/trace/ftrace.c | 2+-
March/powerpc/kernel/traps.c | 3++-
March/powerpc/kernel/vdso.c | 7+++++--
March/powerpc/kernel/vmlinux.lds.S | 18++++++++++++------
March/powerpc/kvm/book3s_64_vio.c | 18++++++++++--------
March/powerpc/kvm/bookehv_interrupts.S | 4++++
March/powerpc/kvm/e500.h | 2+-
March/powerpc/kvm/e500_emulate.c | 7+++++++
March/powerpc/lib/code-patching.c | 16----------------
March/powerpc/lib/feature-fixups.c | 27+++++++++++++++++++++++++--
March/powerpc/mm/44x_mmu.c | 14+++-----------
March/powerpc/mm/8xx_mmu.c | 10+++-------
March/powerpc/mm/Makefile | 11+++++++----
March/powerpc/mm/dma-noncoherent.c | 15+++++++--------
Aarch/powerpc/mm/dump_bats.c | 173+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
March/powerpc/mm/dump_linuxpagetables-generic.c | 2--
Aarch/powerpc/mm/dump_sr.c | 64++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
March/powerpc/mm/fault.c | 49+++++++++++++++++++++++++++++++++----------------
March/powerpc/mm/hash_low_32.S | 33+++++++++++++++++++--------------
March/powerpc/mm/hugetlbpage.c | 40++++++++++++++++++----------------------
March/powerpc/mm/init-common.c | 56+++++++++++++++++++++++++++++++++++++-------------------
March/powerpc/mm/mem.c | 51+++++++++++++++++++--------------------------------
March/powerpc/mm/mmu_context.c | 10++++++++++
March/powerpc/mm/mmu_context_book3s64.c | 15---------------
March/powerpc/mm/mmu_context_iommu.c | 110++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------------
March/powerpc/mm/mmu_context_nohash.c | 4+---
March/powerpc/mm/mmu_decl.h | 2+-
March/powerpc/mm/numa.c | 2+-
March/powerpc/mm/pgtable-book3s64.c | 88+++----------------------------------------------------------------------------
Aarch/powerpc/mm/pgtable-frag.c | 119+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
March/powerpc/mm/pgtable.c | 26++++++++++++++------------
March/powerpc/mm/pgtable_32.c | 29++++++-----------------------
March/powerpc/mm/pkeys.c | 25++++++++++++++++++-------
March/powerpc/mm/ppc_mmu_32.c | 51+++++++++++++--------------------------------------
March/powerpc/mm/tlb_low_64e.S | 7+++++++
March/powerpc/oprofile/Makefile | 2+-
March/powerpc/oprofile/common.c | 2+-
March/powerpc/perf/core-book3s.c | 39+++++++++++++++++++++++++++++++++------
March/powerpc/perf/imc-pmu.c | 6+++---
March/powerpc/perf/isa207-common.c | 58+++++++++++++++++++++++++++++++++++++++++-----------------
March/powerpc/perf/isa207-common.h | 9+++++++--
March/powerpc/perf/perf_regs.c | 7+++++++
March/powerpc/perf/power9-pmu.c | 22++++++----------------
March/powerpc/platforms/44x/warp.c | 6+++---
March/powerpc/platforms/4xx/ocm.c | 17++++-------------
March/powerpc/platforms/4xx/pci.c | 7++-----
March/powerpc/platforms/512x/Kconfig | 2+-
March/powerpc/platforms/52xx/Kconfig | 2+-
March/powerpc/platforms/52xx/efika.c | 6++----
March/powerpc/platforms/82xx/Kconfig | 4++--
March/powerpc/platforms/83xx/Kconfig | 2+-
March/powerpc/platforms/83xx/misc.c | 17+++++++++++++++++
March/powerpc/platforms/85xx/corenet_generic.c | 10----------
March/powerpc/platforms/85xx/qemu_e500.c | 9---------
March/powerpc/platforms/85xx/t1042rdb_diu.c | 2+-
March/powerpc/platforms/86xx/Kconfig | 2+-
March/powerpc/platforms/86xx/mpc86xx_smp.c | 3+--
March/powerpc/platforms/Kconfig | 8++++----
March/powerpc/platforms/Kconfig.cputype | 21+++++----------------
March/powerpc/platforms/amigaone/Kconfig | 2+-
March/powerpc/platforms/cell/cbe_regs.c | 6+++---
March/powerpc/platforms/cell/setup.c | 5++---
March/powerpc/platforms/cell/spu_callbacks.c | 17+++--------------
March/powerpc/platforms/cell/spu_manage.c | 10++--------
March/powerpc/platforms/chrp/Kconfig | 2+-
March/powerpc/platforms/chrp/pci.c | 4++--
March/powerpc/platforms/chrp/setup.c | 10++--------
March/powerpc/platforms/embedded6xx/Kconfig | 2+-
March/powerpc/platforms/maple/pci.c | 6++----
March/powerpc/platforms/pasemi/dma_lib.c | 4+---
March/powerpc/platforms/pasemi/pci.c | 66++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
March/powerpc/platforms/pasemi/setup.c | 86+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
March/powerpc/platforms/powermac/cache.S | 4++--
March/powerpc/platforms/powermac/feature.c | 14+++++++-------
March/powerpc/platforms/powermac/low_i2c.c | 11+++++------
March/powerpc/platforms/powermac/pci.c | 27+++++++++++----------------
March/powerpc/platforms/powermac/pfunc_base.c | 7+++----
March/powerpc/platforms/powermac/pic.c | 6+++---
March/powerpc/platforms/powermac/setup.c | 10++--------
March/powerpc/platforms/powermac/sleep.S | 4++--
March/powerpc/platforms/powermac/smp.c | 3+--
March/powerpc/platforms/powermac/udbg_adb.c | 2+-
March/powerpc/platforms/powermac/udbg_scc.c | 2+-
March/powerpc/platforms/powernv/eeh-powernv.c | 8++++----
March/powerpc/platforms/powernv/npu-dma.c | 564++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---------------
March/powerpc/platforms/powernv/opal-power.c | 3+--
March/powerpc/platforms/powernv/opal.c | 5++++-
March/powerpc/platforms/powernv/pci-ioda-tce.c | 5+++--
March/powerpc/platforms/powernv/pci-ioda.c | 265+++++++++++++++++++++++++++++++++----------------------------------------------
March/powerpc/platforms/powernv/pci.c | 49++++++++++++++++++++++++++++++++++++++++++++-----
March/powerpc/platforms/powernv/pci.h | 36++++++++----------------------------
March/powerpc/platforms/powernv/vas-debug.c | 28++++------------------------
March/powerpc/platforms/pseries/hotplug-memory.c | 16++++++++--------
March/powerpc/platforms/pseries/iommu.c | 88++++++++++++++++++++++++++++++++++++++++++++++++++++---------------------------
March/powerpc/platforms/pseries/pci.c | 22++++++++++++++++++++++
March/powerpc/platforms/pseries/pmem.c | 8++++----
March/powerpc/platforms/pseries/setup.c | 12++++--------
March/powerpc/platforms/pseries/vio.c | 27++++++++++++---------------
March/powerpc/sysdev/Makefile | 2+-
March/powerpc/sysdev/fsl_rio.h | 2+-
March/powerpc/sysdev/fsl_rmu.c | 4+---
March/powerpc/sysdev/ipic.c | 28----------------------------
March/powerpc/sysdev/scom.c | 4++--
March/powerpc/sysdev/xive/common.c | 2+-
March/powerpc/tools/checkpatch.sh | 1+
March/powerpc/xmon/xmon.c | 33++++++++++++++++++++++-----------
Mdrivers/cpufreq/pmac32-cpufreq.c | 4++--
Mdrivers/cpuidle/cpuidle-pseries.c | 8+++++++-
Mdrivers/crypto/amcc/crypto4xx_core.c | 2+-
Mdrivers/ide/pmac.c | 2+-
Mdrivers/macintosh/ans-lcd.c | 2+-
Mdrivers/macintosh/macio_asic.c | 35++++++++++++++++-------------------
Mdrivers/macintosh/macio_sysfs.c | 18++++++------------
Mdrivers/macintosh/rack-meter.c | 13+++++++------
Mdrivers/macintosh/via-pmu.c | 4++--
Mdrivers/macintosh/windfarm_fcu_controls.c | 14+++++++-------
Mdrivers/macintosh/windfarm_lm87_sensor.c | 4++--
Mdrivers/macintosh/windfarm_smu_controls.c | 4++--
Mdrivers/macintosh/windfarm_smu_sat.c | 9++++-----
Mdrivers/macintosh/windfarm_smu_sensors.c | 15+++++++--------
Mdrivers/misc/cxl/pci.c | 4+---
Mdrivers/misc/cxl/vphb.c | 12------------
Mdrivers/misc/ocxl/afu_irq.c | 1-
Mdrivers/misc/ocxl/config.c | 2+-
Mdrivers/misc/ocxl/link.c | 25+++++++++++++++----------
Mdrivers/vfio/pci/Kconfig | 6++++++
Mdrivers/vfio/pci/Makefile | 1+
Adrivers/vfio/pci/trace.h | 102+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Mdrivers/vfio/pci/vfio_pci.c | 42++++++++++++++++++++++++++++++++++++++++--
Adrivers/vfio/pci/vfio_pci_nvlink2.c | 482+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Mdrivers/vfio/pci/vfio_pci_private.h | 20++++++++++++++++++++
Mdrivers/vfio/vfio_iommu_spapr_tce.c | 74+++++++++++++++++++++++++++++++++++++++++++++-----------------------------
Minclude/linux/mmzone.h | 2+-
Minclude/uapi/linux/vfio.h | 42++++++++++++++++++++++++++++++++++++++++++
Mlib/raid6/Makefile | 15+++++++++++++++
Mlib/test_debug_virtual.c | 1+
Mtools/arch/powerpc/include/uapi/asm/perf_regs.h | 1+
Mtools/perf/arch/powerpc/include/perf_regs.h | 3++-
Mtools/perf/arch/powerpc/util/perf_regs.c | 1+
Mtools/testing/selftests/powerpc/include/utils.h | 10++++++++++
Mtools/testing/selftests/powerpc/ptrace/core-pkey.c | 5+----
Mtools/testing/selftests/powerpc/ptrace/ptrace-gpr.c | 2+-
Mtools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c | 4++--
Mtools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c | 2+-
Mtools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c | 3+--
Mtools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c | 2+-
Mtools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c | 2+-
Mtools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c | 3+--
Mtools/testing/selftests/powerpc/tm/.gitignore | 1+
Mtools/testing/selftests/powerpc/tm/Makefile | 2+-
Atools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c | 46++++++++++++++++++++++++++++++++++++++++++++++
298 files changed, 5095 insertions(+), 3817 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt @@ -2833,7 +2833,7 @@ check bypass). With this option data leaks are possible in the system. - nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 + nospectre_v2 [X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2 (indirect branch prediction) vulnerability. System may allow data leaks with this option, which is equivalent to spectre_v2=off. diff --git a/Documentation/devicetree/bindings/clock/qoriq-clock.txt b/Documentation/devicetree/bindings/clock/qoriq-clock.txt @@ -28,6 +28,12 @@ Required properties: * "fsl,p4080-clockgen" * "fsl,p5020-clockgen" * "fsl,p5040-clockgen" + * "fsl,t1023-clockgen" + * "fsl,t1024-clockgen" + * "fsl,t1040-clockgen" + * "fsl,t1042-clockgen" + * "fsl,t2080-clockgen" + * "fsl,t2081-clockgen" * "fsl,t4240-clockgen" * "fsl,b4420-clockgen" * "fsl,b4860-clockgen" diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.txt @@ -113,7 +113,15 @@ header, is usually reserved at an offset greater than boot memory size (see Fig. 1). This area is *not* released: this region will be kept permanently reserved, so that it can act as a receptacle for a copy of the boot memory content in addition to CPU state -and HPTE region, in the case a crash does occur. +and HPTE region, in the case a crash does occur. Since this reserved +memory area is used only after the system crash, there is no point in +blocking this significant chunk of memory from production kernel. +Hence, the implementation uses the Linux kernel's Contiguous Memory +Allocator (CMA) for memory reservation if CMA is configured for kernel. +With CMA reservation this memory will be available for applications to +use it, while kernel is prevented from using it. With this fadump will +still be able to capture all of the kernel memory and most of the user +space memory except the user pages that were present in CMA region. o Memory Reservation during first kernel @@ -162,6 +170,9 @@ How to enable firmware-assisted dump (fadump): 1. Set config option CONFIG_FA_DUMP=y and build kernel. 2. Boot into linux kernel with 'fadump=on' kernel cmdline option. + By default, fadump reserved memory will be initialized as CMA area. + Alternatively, user can boot linux kernel with 'fadump=nocma' to + prevent fadump to use CMA. 3. Optionally, user can also set 'crashkernel=' kernel cmdline to specify size of the memory to reserve for boot memory dump preservation. @@ -172,6 +183,10 @@ NOTE: 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead 2. If firmware-assisted dump fails to reserve memory then it will fallback to existing kdump mechanism if 'crashkernel=' option is set at kernel cmdline. + 3. if user wants to capture all of user space memory and ok with + reserved memory not available to production system, then + 'fadump=nocma' kernel parameter can be used to fallback to + old behaviour. Sysfs/debugfs files: ------------ diff --git a/Documentation/powerpc/isa-versions.rst b/Documentation/powerpc/isa-versions.rst @@ -0,0 +1,74 @@ +CPU to ISA Version Mapping +========================== + +Mapping of some CPU versions to relevant ISA versions. + +========= ==================== +CPU Architecture version +========= ==================== +Power9 Power ISA v3.0B +Power8 Power ISA v2.07 +Power7 Power ISA v2.06 +Power6 Power ISA v2.05 +PA6T Power ISA v2.04 +Cell PPU - Power ISA v2.02 with some minor exceptions + - Plus Altivec/VMX ~= 2.03 +Power5++ Power ISA v2.04 (no VMX) +Power5+ Power ISA v2.03 +Power5 - PowerPC User Instruction Set Architecture Book I v2.02 + - PowerPC Virtual Environment Architecture Book II v2.02 + - PowerPC Operating Environment Architecture Book III v2.02 +PPC970 - PowerPC User Instruction Set Architecture Book I v2.01 + - PowerPC Virtual Environment Architecture Book II v2.01 + - PowerPC Operating Environment Architecture Book III v2.01 + - Plus Altivec/VMX ~= 2.03 +========= ==================== + + +Key Features +------------ + +========== ================== +CPU VMX (aka. Altivec) +========== ================== +Power9 Yes +Power8 Yes +Power7 Yes +Power6 Yes +PA6T Yes +Cell PPU Yes +Power5++ No +Power5+ No +Power5 No +PPC970 Yes +========== ================== + +========== ==== +CPU VSX +========== ==== +Power9 Yes +Power8 Yes +Power7 Yes +Power6 No +PA6T No +Cell PPU No +Power5++ No +Power5+ No +Power5 No +PPC970 No +========== ==== + +========== ==================== +CPU Transactional Memory +========== ==================== +Power9 Yes (* see transactional_memory.txt) +Power8 Yes +Power7 No +Power6 No +PA6T No +Cell PPU No +Power5++ No +Power5+ No +Power5 No +PPC970 No +========== ==================== diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig @@ -128,6 +128,7 @@ config PPC # # Please keep this list sorted alphabetically. # + select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_SET_COHERENT_MASK select ARCH_HAS_ELF_RANDOMIZE @@ -374,9 +375,9 @@ config PPC_ADV_DEBUG_DAC_RANGE depends on PPC_ADV_DEBUG_REGS && 44x default y -config ZONE_DMA32 +config ZONE_DMA bool - default y if PPC64 + default y if PPC_BOOK3E_64 config PGTABLE_LEVELS int @@ -556,7 +557,7 @@ config RELOCATABLE_TEST config CRASH_DUMP bool "Build a dump capture kernel" - depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP) + depends on PPC64 || PPC_BOOK3S_32 || FSL_BOOKE || (44x && !SMP) select RELOCATABLE if PPC64 || 44x || FSL_BOOKE help Build a kernel suitable for use as a dump capture kernel. @@ -869,10 +870,6 @@ config ISA have an IBM RS/6000 or pSeries machine, say Y. If you have an embedded board, consult your board documentation. -config ZONE_DMA - bool - default y - config GENERIC_ISA_DMA bool depends on ISA_DMA_API @@ -1096,7 +1093,7 @@ config PHYSICAL_START_BOOL config PHYSICAL_START hex "Physical address where the kernel is loaded" if PHYSICAL_START_BOOL - default "0x02000000" if PPC_STD_MMU && CRASH_DUMP && !NONSTATIC_KERNEL + default "0x02000000" if PPC_BOOK3S && CRASH_DUMP && !NONSTATIC_KERNEL default "0x00000000" config PHYSICAL_ALIGN @@ -1146,7 +1143,7 @@ config PIN_TLB_DATA config PIN_TLB_IMMR bool "Pinned TLB for IMMR" - depends on PIN_TLB + depends on PIN_TLB || PPC_EARLY_DEBUG_CPM default y config PIN_TLB_TEXT diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile @@ -30,6 +30,10 @@ endif endif endif +ifdef CONFIG_PPC_BOOK3S_32 +KBUILD_CFLAGS += -mcpu=powerpc +endif + ifeq ($(CROSS_COMPILE),) KBUILD_DEFCONFIG := $(shell uname -m)_defconfig else @@ -152,7 +156,14 @@ endif CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc)) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) -CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 $(MULTIPLEWORD) +# Clang unconditionally reserves r2 on ppc32 and does not support the flag +# https://bugs.llvm.org/show_bug.cgi?id=39555 +CFLAGS-$(CONFIG_PPC32) := $(call cc-option, -ffixed-r2) + +# Clang doesn't support -mmultiple / -mno-multiple +# https://bugs.llvm.org/show_bug.cgi?id=39556 +CFLAGS-$(CONFIG_PPC32) += $(call cc-option, $(MULTIPLEWORD)) + CFLAGS-$(CONFIG_PPC32) += $(call cc-option,-mno-readonly-in-sdata) ifdef CONFIG_PPC_BOOK3S_64 @@ -237,10 +248,6 @@ KBUILD_CFLAGS += $(call cc-option,-fno-dwarf2-cfi-asm) # often slow when they are implemented at all KBUILD_CFLAGS += $(call cc-option,-mno-string) -ifdef CONFIG_6xx -KBUILD_CFLAGS += -mcpu=powerpc -endif - cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 @@ -313,6 +320,14 @@ PHONY += ppc64le_defconfig ppc64le_defconfig: $(call merge_into_defconfig,ppc64_defconfig,le) +PHONY += ppc64le_guest_defconfig +ppc64le_guest_defconfig: + $(call merge_into_defconfig,ppc64_defconfig,le guest) + +PHONY += ppc64_guest_defconfig +ppc64_guest_defconfig: + $(call merge_into_defconfig,ppc64_defconfig,be guest) + PHONY += powernv_be_defconfig powernv_be_defconfig: $(call merge_into_defconfig,powernv_defconfig,be) @@ -398,6 +413,9 @@ archclean: archprepare: checkbin +archheaders: + $(Q)$(MAKE) $(build)=arch/powerpc/kernel/syscalls all + ifdef CONFIG_STACKPROTECTOR prepare: stack_protector_prepare diff --git a/arch/powerpc/boot/dts/bamboo.dts b/arch/powerpc/boot/dts/bamboo.dts @@ -268,8 +268,10 @@ /* Outbound ranges, one memory and one IO, * later cannot be changed. Chip supports a second * IO range but we don't use it for now + * The chip also supports a larger memory range but + * it's not naturally aligned, so our code will break */ - ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x40000000 + ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x20000000 0x02000000 0x00000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00100000 0x01000000 0x00000000 0x00000000 0x00000000 0xe8000000 0x00000000 0x00010000>; diff --git a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi @@ -70,14 +70,14 @@ cpu0: PowerPC,e6500@0 { device_type = "cpu"; reg = <0 1>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; diff --git a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi @@ -75,28 +75,28 @@ cpu0: PowerPC,e6500@0 { device_type = "cpu"; reg = <0 1>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu2: PowerPC,e6500@4 { device_type = "cpu"; reg = <4 5>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu3: PowerPC,e6500@6 { device_type = "cpu"; reg = <6 7>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi @@ -398,21 +398,6 @@ }; /include/ "qoriq-clockgen2.dtsi" - clockgen: global-utilities@e1000 { - compatible = "fsl,b4-clockgen", "fsl,qoriq-clockgen-2.0"; - reg = <0xe1000 0x1000>; - - mux0: mux0@0 { - #clock-cells = <0>; - reg = <0x0 0x4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>; - clock-names = "pll0", "pll0-div2", "pll0-div4", - "pll1", "pll1-div2", "pll1-div4"; - clock-output-names = "cmux0"; - }; - }; rcpm: global-utilities@e2000 { compatible = "fsl,b4-rcpm", "fsl,qoriq-rcpm-2.0"; diff --git a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts b/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts @@ -169,100 +169,100 @@ interrupt-map-mask = <0xff00 0 0 7>; interrupt-map = < /* IDSEL 0x11 func 0 - PCI slot 1 */ - 0x8800 0 0 1 &mpic 2 1 - 0x8800 0 0 2 &mpic 3 1 - 0x8800 0 0 3 &mpic 4 1 - 0x8800 0 0 4 &mpic 1 1 + 0x8800 0 0 1 &mpic 2 1 0 0 + 0x8800 0 0 2 &mpic 3 1 0 0 + 0x8800 0 0 3 &mpic 4 1 0 0 + 0x8800 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 1 - PCI slot 1 */ - 0x8900 0 0 1 &mpic 2 1 - 0x8900 0 0 2 &mpic 3 1 - 0x8900 0 0 3 &mpic 4 1 - 0x8900 0 0 4 &mpic 1 1 + 0x8900 0 0 1 &mpic 2 1 0 0 + 0x8900 0 0 2 &mpic 3 1 0 0 + 0x8900 0 0 3 &mpic 4 1 0 0 + 0x8900 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 2 - PCI slot 1 */ - 0x8a00 0 0 1 &mpic 2 1 - 0x8a00 0 0 2 &mpic 3 1 - 0x8a00 0 0 3 &mpic 4 1 - 0x8a00 0 0 4 &mpic 1 1 + 0x8a00 0 0 1 &mpic 2 1 0 0 + 0x8a00 0 0 2 &mpic 3 1 0 0 + 0x8a00 0 0 3 &mpic 4 1 0 0 + 0x8a00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 3 - PCI slot 1 */ - 0x8b00 0 0 1 &mpic 2 1 - 0x8b00 0 0 2 &mpic 3 1 - 0x8b00 0 0 3 &mpic 4 1 - 0x8b00 0 0 4 &mpic 1 1 + 0x8b00 0 0 1 &mpic 2 1 0 0 + 0x8b00 0 0 2 &mpic 3 1 0 0 + 0x8b00 0 0 3 &mpic 4 1 0 0 + 0x8b00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 4 - PCI slot 1 */ - 0x8c00 0 0 1 &mpic 2 1 - 0x8c00 0 0 2 &mpic 3 1 - 0x8c00 0 0 3 &mpic 4 1 - 0x8c00 0 0 4 &mpic 1 1 + 0x8c00 0 0 1 &mpic 2 1 0 0 + 0x8c00 0 0 2 &mpic 3 1 0 0 + 0x8c00 0 0 3 &mpic 4 1 0 0 + 0x8c00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 5 - PCI slot 1 */ - 0x8d00 0 0 1 &mpic 2 1 - 0x8d00 0 0 2 &mpic 3 1 - 0x8d00 0 0 3 &mpic 4 1 - 0x8d00 0 0 4 &mpic 1 1 + 0x8d00 0 0 1 &mpic 2 1 0 0 + 0x8d00 0 0 2 &mpic 3 1 0 0 + 0x8d00 0 0 3 &mpic 4 1 0 0 + 0x8d00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 6 - PCI slot 1 */ - 0x8e00 0 0 1 &mpic 2 1 - 0x8e00 0 0 2 &mpic 3 1 - 0x8e00 0 0 3 &mpic 4 1 - 0x8e00 0 0 4 &mpic 1 1 + 0x8e00 0 0 1 &mpic 2 1 0 0 + 0x8e00 0 0 2 &mpic 3 1 0 0 + 0x8e00 0 0 3 &mpic 4 1 0 0 + 0x8e00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 7 - PCI slot 1 */ - 0x8f00 0 0 1 &mpic 2 1 - 0x8f00 0 0 2 &mpic 3 1 - 0x8f00 0 0 3 &mpic 4 1 - 0x8f00 0 0 4 &mpic 1 1 + 0x8f00 0 0 1 &mpic 2 1 0 0 + 0x8f00 0 0 2 &mpic 3 1 0 0 + 0x8f00 0 0 3 &mpic 4 1 0 0 + 0x8f00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x12 func 0 - PCI slot 2 */ - 0x9000 0 0 1 &mpic 3 1 - 0x9000 0 0 2 &mpic 4 1 - 0x9000 0 0 3 &mpic 1 1 - 0x9000 0 0 4 &mpic 2 1 + 0x9000 0 0 1 &mpic 3 1 0 0 + 0x9000 0 0 2 &mpic 4 1 0 0 + 0x9000 0 0 3 &mpic 1 1 0 0 + 0x9000 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 1 - PCI slot 2 */ - 0x9100 0 0 1 &mpic 3 1 - 0x9100 0 0 2 &mpic 4 1 - 0x9100 0 0 3 &mpic 1 1 - 0x9100 0 0 4 &mpic 2 1 + 0x9100 0 0 1 &mpic 3 1 0 0 + 0x9100 0 0 2 &mpic 4 1 0 0 + 0x9100 0 0 3 &mpic 1 1 0 0 + 0x9100 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 2 - PCI slot 2 */ - 0x9200 0 0 1 &mpic 3 1 - 0x9200 0 0 2 &mpic 4 1 - 0x9200 0 0 3 &mpic 1 1 - 0x9200 0 0 4 &mpic 2 1 + 0x9200 0 0 1 &mpic 3 1 0 0 + 0x9200 0 0 2 &mpic 4 1 0 0 + 0x9200 0 0 3 &mpic 1 1 0 0 + 0x9200 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 3 - PCI slot 2 */ - 0x9300 0 0 1 &mpic 3 1 - 0x9300 0 0 2 &mpic 4 1 - 0x9300 0 0 3 &mpic 1 1 - 0x9300 0 0 4 &mpic 2 1 + 0x9300 0 0 1 &mpic 3 1 0 0 + 0x9300 0 0 2 &mpic 4 1 0 0 + 0x9300 0 0 3 &mpic 1 1 0 0 + 0x9300 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 4 - PCI slot 2 */ - 0x9400 0 0 1 &mpic 3 1 - 0x9400 0 0 2 &mpic 4 1 - 0x9400 0 0 3 &mpic 1 1 - 0x9400 0 0 4 &mpic 2 1 + 0x9400 0 0 1 &mpic 3 1 0 0 + 0x9400 0 0 2 &mpic 4 1 0 0 + 0x9400 0 0 3 &mpic 1 1 0 0 + 0x9400 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 5 - PCI slot 2 */ - 0x9500 0 0 1 &mpic 3 1 - 0x9500 0 0 2 &mpic 4 1 - 0x9500 0 0 3 &mpic 1 1 - 0x9500 0 0 4 &mpic 2 1 + 0x9500 0 0 1 &mpic 3 1 0 0 + 0x9500 0 0 2 &mpic 4 1 0 0 + 0x9500 0 0 3 &mpic 1 1 0 0 + 0x9500 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 6 - PCI slot 2 */ - 0x9600 0 0 1 &mpic 3 1 - 0x9600 0 0 2 &mpic 4 1 - 0x9600 0 0 3 &mpic 1 1 - 0x9600 0 0 4 &mpic 2 1 + 0x9600 0 0 1 &mpic 3 1 0 0 + 0x9600 0 0 2 &mpic 4 1 0 0 + 0x9600 0 0 3 &mpic 1 1 0 0 + 0x9600 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 7 - PCI slot 2 */ - 0x9700 0 0 1 &mpic 3 1 - 0x9700 0 0 2 &mpic 4 1 - 0x9700 0 0 3 &mpic 1 1 - 0x9700 0 0 4 &mpic 2 1 + 0x9700 0 0 1 &mpic 3 1 0 0 + 0x9700 0 0 2 &mpic 4 1 0 0 + 0x9700 0 0 3 &mpic 1 1 0 0 + 0x9700 0 0 4 &mpic 2 1 0 0 // IDSEL 0x1c USB 0xe000 0 0 1 &i8259 12 2 diff --git a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts b/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts @@ -136,100 +136,100 @@ interrupt-map-mask = <0xff00 0 0 7>; interrupt-map = < /* IDSEL 0x11 func 0 - PCI slot 1 */ - 0x8800 0 0 1 &mpic 2 1 - 0x8800 0 0 2 &mpic 3 1 - 0x8800 0 0 3 &mpic 4 1 - 0x8800 0 0 4 &mpic 1 1 + 0x8800 0 0 1 &mpic 2 1 0 0 + 0x8800 0 0 2 &mpic 3 1 0 0 + 0x8800 0 0 3 &mpic 4 1 0 0 + 0x8800 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 1 - PCI slot 1 */ - 0x8900 0 0 1 &mpic 2 1 - 0x8900 0 0 2 &mpic 3 1 - 0x8900 0 0 3 &mpic 4 1 - 0x8900 0 0 4 &mpic 1 1 + 0x8900 0 0 1 &mpic 2 1 0 0 + 0x8900 0 0 2 &mpic 3 1 0 0 + 0x8900 0 0 3 &mpic 4 1 0 0 + 0x8900 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 2 - PCI slot 1 */ - 0x8a00 0 0 1 &mpic 2 1 - 0x8a00 0 0 2 &mpic 3 1 - 0x8a00 0 0 3 &mpic 4 1 - 0x8a00 0 0 4 &mpic 1 1 + 0x8a00 0 0 1 &mpic 2 1 0 0 + 0x8a00 0 0 2 &mpic 3 1 0 0 + 0x8a00 0 0 3 &mpic 4 1 0 0 + 0x8a00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 3 - PCI slot 1 */ - 0x8b00 0 0 1 &mpic 2 1 - 0x8b00 0 0 2 &mpic 3 1 - 0x8b00 0 0 3 &mpic 4 1 - 0x8b00 0 0 4 &mpic 1 1 + 0x8b00 0 0 1 &mpic 2 1 0 0 + 0x8b00 0 0 2 &mpic 3 1 0 0 + 0x8b00 0 0 3 &mpic 4 1 0 0 + 0x8b00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 4 - PCI slot 1 */ - 0x8c00 0 0 1 &mpic 2 1 - 0x8c00 0 0 2 &mpic 3 1 - 0x8c00 0 0 3 &mpic 4 1 - 0x8c00 0 0 4 &mpic 1 1 + 0x8c00 0 0 1 &mpic 2 1 0 0 + 0x8c00 0 0 2 &mpic 3 1 0 0 + 0x8c00 0 0 3 &mpic 4 1 0 0 + 0x8c00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 5 - PCI slot 1 */ - 0x8d00 0 0 1 &mpic 2 1 - 0x8d00 0 0 2 &mpic 3 1 - 0x8d00 0 0 3 &mpic 4 1 - 0x8d00 0 0 4 &mpic 1 1 + 0x8d00 0 0 1 &mpic 2 1 0 0 + 0x8d00 0 0 2 &mpic 3 1 0 0 + 0x8d00 0 0 3 &mpic 4 1 0 0 + 0x8d00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 6 - PCI slot 1 */ - 0x8e00 0 0 1 &mpic 2 1 - 0x8e00 0 0 2 &mpic 3 1 - 0x8e00 0 0 3 &mpic 4 1 - 0x8e00 0 0 4 &mpic 1 1 + 0x8e00 0 0 1 &mpic 2 1 0 0 + 0x8e00 0 0 2 &mpic 3 1 0 0 + 0x8e00 0 0 3 &mpic 4 1 0 0 + 0x8e00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x11 func 7 - PCI slot 1 */ - 0x8f00 0 0 1 &mpic 2 1 - 0x8f00 0 0 2 &mpic 3 1 - 0x8f00 0 0 3 &mpic 4 1 - 0x8f00 0 0 4 &mpic 1 1 + 0x8f00 0 0 1 &mpic 2 1 0 0 + 0x8f00 0 0 2 &mpic 3 1 0 0 + 0x8f00 0 0 3 &mpic 4 1 0 0 + 0x8f00 0 0 4 &mpic 1 1 0 0 /* IDSEL 0x12 func 0 - PCI slot 2 */ - 0x9000 0 0 1 &mpic 3 1 - 0x9000 0 0 2 &mpic 4 1 - 0x9000 0 0 3 &mpic 1 1 - 0x9000 0 0 4 &mpic 2 1 + 0x9000 0 0 1 &mpic 3 1 0 0 + 0x9000 0 0 2 &mpic 4 1 0 0 + 0x9000 0 0 3 &mpic 1 1 0 0 + 0x9000 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 1 - PCI slot 2 */ - 0x9100 0 0 1 &mpic 3 1 - 0x9100 0 0 2 &mpic 4 1 - 0x9100 0 0 3 &mpic 1 1 - 0x9100 0 0 4 &mpic 2 1 + 0x9100 0 0 1 &mpic 3 1 0 0 + 0x9100 0 0 2 &mpic 4 1 0 0 + 0x9100 0 0 3 &mpic 1 1 0 0 + 0x9100 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 2 - PCI slot 2 */ - 0x9200 0 0 1 &mpic 3 1 - 0x9200 0 0 2 &mpic 4 1 - 0x9200 0 0 3 &mpic 1 1 - 0x9200 0 0 4 &mpic 2 1 + 0x9200 0 0 1 &mpic 3 1 0 0 + 0x9200 0 0 2 &mpic 4 1 0 0 + 0x9200 0 0 3 &mpic 1 1 0 0 + 0x9200 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 3 - PCI slot 2 */ - 0x9300 0 0 1 &mpic 3 1 - 0x9300 0 0 2 &mpic 4 1 - 0x9300 0 0 3 &mpic 1 1 - 0x9300 0 0 4 &mpic 2 1 + 0x9300 0 0 1 &mpic 3 1 0 0 + 0x9300 0 0 2 &mpic 4 1 0 0 + 0x9300 0 0 3 &mpic 1 1 0 0 + 0x9300 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 4 - PCI slot 2 */ - 0x9400 0 0 1 &mpic 3 1 - 0x9400 0 0 2 &mpic 4 1 - 0x9400 0 0 3 &mpic 1 1 - 0x9400 0 0 4 &mpic 2 1 + 0x9400 0 0 1 &mpic 3 1 0 0 + 0x9400 0 0 2 &mpic 4 1 0 0 + 0x9400 0 0 3 &mpic 1 1 0 0 + 0x9400 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 5 - PCI slot 2 */ - 0x9500 0 0 1 &mpic 3 1 - 0x9500 0 0 2 &mpic 4 1 - 0x9500 0 0 3 &mpic 1 1 - 0x9500 0 0 4 &mpic 2 1 + 0x9500 0 0 1 &mpic 3 1 0 0 + 0x9500 0 0 2 &mpic 4 1 0 0 + 0x9500 0 0 3 &mpic 1 1 0 0 + 0x9500 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 6 - PCI slot 2 */ - 0x9600 0 0 1 &mpic 3 1 - 0x9600 0 0 2 &mpic 4 1 - 0x9600 0 0 3 &mpic 1 1 - 0x9600 0 0 4 &mpic 2 1 + 0x9600 0 0 1 &mpic 3 1 0 0 + 0x9600 0 0 2 &mpic 4 1 0 0 + 0x9600 0 0 3 &mpic 1 1 0 0 + 0x9600 0 0 4 &mpic 2 1 0 0 /* IDSEL 0x12 func 7 - PCI slot 2 */ - 0x9700 0 0 1 &mpic 3 1 - 0x9700 0 0 2 &mpic 4 1 - 0x9700 0 0 3 &mpic 1 1 - 0x9700 0 0 4 &mpic 2 1 + 0x9700 0 0 1 &mpic 3 1 0 0 + 0x9700 0 0 2 &mpic 4 1 0 0 + 0x9700 0 0 3 &mpic 1 1 0 0 + 0x9700 0 0 4 &mpic 2 1 0 0 // IDSEL 0x1c USB 0xe000 0 0 1 &i8259 12 2 diff --git a/arch/powerpc/boot/dts/fsl/mpc8641si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8641si-post.dtsi @@ -97,6 +97,7 @@ &pci0 { compatible = "fsl,mpc8641-pcie"; device_type = "pci"; + #interrupt-cells = <1>; #size-cells = <2>; #address-cells = <3>; bus-range = <0x0 0xff>; @@ -123,6 +124,7 @@ &pci1 { compatible = "fsl,mpc8641-pcie"; device_type = "pci"; + #interrupt-cells = <1>; #size-cells = <2>; #address-cells = <3>; bus-range = <0x0 0xff>; diff --git a/arch/powerpc/boot/dts/fsl/p1020rdb-pc.dtsi b/arch/powerpc/boot/dts/fsl/p1020rdb-pc.dtsi @@ -205,13 +205,13 @@ mdio@24000 { phy0: ethernet-phy@0 { interrupt-parent = <&mpic>; - interrupts = <3 1>; + interrupts = <3 1 0 0>; reg = <0x0>; }; phy1: ethernet-phy@1 { interrupt-parent = <&mpic>; - interrupts = <2 1>; + interrupts = <2 1 0 0>; reg = <0x1>; }; diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi @@ -327,24 +327,6 @@ /include/ "qoriq-clockgen1.dtsi" global-utilities@e1000 { compatible = "fsl,p2041-clockgen", "fsl,qoriq-clockgen-1.0"; - - mux2: mux2@40 { - #clock-cells = <0>; - reg = <0x40 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux2"; - }; - - mux3: mux3@60 { - #clock-cells = <0>; - reg = <0x60 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux3"; - }; }; rcpm: global-utilities@e2000 { diff --git a/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi @@ -89,7 +89,7 @@ cpu0: PowerPC,e500mc@0 { device_type = "cpu"; reg = <0>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_0>; fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { @@ -99,7 +99,7 @@ cpu1: PowerPC,e500mc@1 { device_type = "cpu"; reg = <1>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { @@ -109,7 +109,7 @@ cpu2: PowerPC,e500mc@2 { device_type = "cpu"; reg = <2>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_2>; fsl,portid-mapping = <0x20000000>; L2_2: l2-cache { @@ -119,7 +119,7 @@ cpu3: PowerPC,e500mc@3 { device_type = "cpu"; reg = <3>; - clocks = <&mux3>; + clocks = <&clockgen 1 3>; next-level-cache = <&L2_3>; fsl,portid-mapping = <0x10000000>; L2_3: l2-cache { diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi @@ -354,24 +354,6 @@ /include/ "qoriq-clockgen1.dtsi" global-utilities@e1000 { compatible = "fsl,p3041-clockgen", "fsl,qoriq-clockgen-1.0"; - - mux2: mux2@40 { - #clock-cells = <0>; - reg = <0x40 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux2"; - }; - - mux3: mux3@60 { - #clock-cells = <0>; - reg = <0x60 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux3"; - }; }; rcpm: global-utilities@e2000 { diff --git a/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi @@ -90,7 +90,7 @@ cpu0: PowerPC,e500mc@0 { device_type = "cpu"; reg = <0>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_0>; fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { @@ -100,7 +100,7 @@ cpu1: PowerPC,e500mc@1 { device_type = "cpu"; reg = <1>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { @@ -110,7 +110,7 @@ cpu2: PowerPC,e500mc@2 { device_type = "cpu"; reg = <2>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_2>; fsl,portid-mapping = <0x20000000>; L2_2: l2-cache { @@ -120,7 +120,7 @@ cpu3: PowerPC,e500mc@3 { device_type = "cpu"; reg = <3>; - clocks = <&mux3>; + clocks = <&clockgen 1 3>; next-level-cache = <&L2_3>; fsl,portid-mapping = <0x10000000>; L2_3: l2-cache { diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi @@ -374,76 +374,6 @@ /include/ "qoriq-clockgen1.dtsi" global-utilities@e1000 { compatible = "fsl,p4080-clockgen", "fsl,qoriq-clockgen-1.0"; - - pll2: pll2@840 { - #clock-cells = <1>; - reg = <0x840 0x4>; - compatible = "fsl,qoriq-core-pll-1.0"; - clocks = <&sysclk>; - clock-output-names = "pll2", "pll2-div2"; - }; - - pll3: pll3@860 { - #clock-cells = <1>; - reg = <0x860 0x4>; - compatible = "fsl,qoriq-core-pll-1.0"; - clocks = <&sysclk>; - clock-output-names = "pll3", "pll3-div2"; - }; - - mux2: mux2@40 { - #clock-cells = <0>; - reg = <0x40 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux2"; - }; - - mux3: mux3@60 { - #clock-cells = <0>; - reg = <0x60 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux3"; - }; - - mux4: mux4@80 { - #clock-cells = <0>; - reg = <0x80 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll2 0>, <&pll2 1>, <&pll3 0>, <&pll3 1>; - clock-names = "pll2", "pll2-div2", "pll3", "pll3-div2"; - clock-output-names = "cmux4"; - }; - - mux5: mux5@a0 { - #clock-cells = <0>; - reg = <0xa0 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll2 0>, <&pll2 1>, <&pll3 0>, <&pll3 1>; - clock-names = "pll2", "pll2-div2", "pll3", "pll3-div2"; - clock-output-names = "cmux5"; - }; - - mux6: mux6@c0 { - #clock-cells = <0>; - reg = <0xc0 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll2 0>, <&pll2 1>, <&pll3 0>, <&pll3 1>; - clock-names = "pll2", "pll2-div2", "pll3", "pll3-div2"; - clock-output-names = "cmux6"; - }; - - mux7: mux7@e0 { - #clock-cells = <0>; - reg = <0xe0 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll2 0>, <&pll2 1>, <&pll3 0>, <&pll3 1>; - clock-names = "pll2", "pll2-div2", "pll3", "pll3-div2"; - clock-output-names = "cmux7"; - }; }; rcpm: global-utilities@e2000 { diff --git a/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi @@ -94,7 +94,7 @@ cpu0: PowerPC,e500mc@0 { device_type = "cpu"; reg = <0>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_0>; fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { @@ -104,7 +104,7 @@ cpu1: PowerPC,e500mc@1 { device_type = "cpu"; reg = <1>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { @@ -114,7 +114,7 @@ cpu2: PowerPC,e500mc@2 { device_type = "cpu"; reg = <2>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_2>; fsl,portid-mapping = <0x20000000>; L2_2: l2-cache { @@ -124,7 +124,7 @@ cpu3: PowerPC,e500mc@3 { device_type = "cpu"; reg = <3>; - clocks = <&mux3>; + clocks = <&clockgen 1 3>; next-level-cache = <&L2_3>; fsl,portid-mapping = <0x10000000>; L2_3: l2-cache { @@ -134,7 +134,7 @@ cpu4: PowerPC,e500mc@4 { device_type = "cpu"; reg = <4>; - clocks = <&mux4>; + clocks = <&clockgen 1 4>; next-level-cache = <&L2_4>; fsl,portid-mapping = <0x08000000>; L2_4: l2-cache { @@ -144,7 +144,7 @@ cpu5: PowerPC,e500mc@5 { device_type = "cpu"; reg = <5>; - clocks = <&mux5>; + clocks = <&clockgen 1 5>; next-level-cache = <&L2_5>; fsl,portid-mapping = <0x04000000>; L2_5: l2-cache { @@ -154,7 +154,7 @@ cpu6: PowerPC,e500mc@6 { device_type = "cpu"; reg = <6>; - clocks = <&mux6>; + clocks = <&clockgen 1 6>; next-level-cache = <&L2_6>; fsl,portid-mapping = <0x02000000>; L2_6: l2-cache { @@ -164,7 +164,7 @@ cpu7: PowerPC,e500mc@7 { device_type = "cpu"; reg = <7>; - clocks = <&mux7>; + clocks = <&clockgen 1 7>; next-level-cache = <&L2_7>; fsl,portid-mapping = <0x01000000>; L2_7: l2-cache { diff --git a/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi @@ -96,7 +96,7 @@ cpu0: PowerPC,e5500@0 { device_type = "cpu"; reg = <0>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_0>; fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { @@ -106,7 +106,7 @@ cpu1: PowerPC,e5500@1 { device_type = "cpu"; reg = <1>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi @@ -319,24 +319,6 @@ /include/ "qoriq-clockgen1.dtsi" global-utilities@e1000 { compatible = "fsl,p5040-clockgen", "fsl,qoriq-clockgen-1.0"; - - mux2: mux2@40 { - #clock-cells = <0>; - reg = <0x40 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux2"; - }; - - mux3: mux3@60 { - #clock-cells = <0>; - reg = <0x60 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux3"; - }; }; rcpm: global-utilities@e2000 { diff --git a/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi @@ -102,7 +102,7 @@ cpu0: PowerPC,e5500@0 { device_type = "cpu"; reg = <0>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_0>; fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { @@ -112,7 +112,7 @@ cpu1: PowerPC,e5500@1 { device_type = "cpu"; reg = <1>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { @@ -122,7 +122,7 @@ cpu2: PowerPC,e5500@2 { device_type = "cpu"; reg = <2>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_2>; fsl,portid-mapping = <0x20000000>; L2_2: l2-cache { @@ -132,7 +132,7 @@ cpu3: PowerPC,e5500@3 { device_type = "cpu"; reg = <3>; - clocks = <&mux3>; + clocks = <&clockgen 1 3>; next-level-cache = <&L2_3>; fsl,portid-mapping = <0x10000000>; L2_3: l2-cache { diff --git a/arch/powerpc/boot/dts/fsl/qoriq-clockgen1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-clockgen1.dtsi @@ -34,53 +34,6 @@ clockgen: global-utilities@e1000 { compatible = "fsl,qoriq-clockgen-1.0"; - ranges = <0x0 0xe1000 0x1000>; reg = <0xe1000 0x1000>; - clock-frequency = <0>; - #address-cells = <1>; - #size-cells = <1>; #clock-cells = <2>; - - sysclk: sysclk { - #clock-cells = <0>; - compatible = "fsl,qoriq-sysclk-1.0", "fixed-clock"; - clock-output-names = "sysclk"; - }; - pll0: pll0@800 { - #clock-cells = <1>; - reg = <0x800 0x4>; - compatible = "fsl,qoriq-core-pll-1.0"; - clocks = <&sysclk>; - clock-output-names = "pll0", "pll0-div2"; - }; - pll1: pll1@820 { - #clock-cells = <1>; - reg = <0x820 0x4>; - compatible = "fsl,qoriq-core-pll-1.0"; - clocks = <&sysclk>; - clock-output-names = "pll1", "pll1-div2"; - }; - mux0: mux0@0 { - #clock-cells = <0>; - reg = <0x0 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux0"; - }; - mux1: mux1@20 { - #clock-cells = <0>; - reg = <0x20 0x4>; - compatible = "fsl,qoriq-core-mux-1.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>; - clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2"; - clock-output-names = "cmux1"; - }; - platform_pll: platform-pll@c00 { - #clock-cells = <1>; - reg = <0xc00 0x4>; - compatible = "fsl,qoriq-platform-pll-1.0"; - clocks = <&sysclk>; - clock-output-names = "platform-pll", "platform-pll-div2"; - }; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-clockgen2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-clockgen2.dtsi @@ -34,36 +34,6 @@ clockgen: global-utilities@e1000 { compatible = "fsl,qoriq-clockgen-2.0"; - ranges = <0x0 0xe1000 0x1000>; reg = <0xe1000 0x1000>; - #address-cells = <1>; - #size-cells = <1>; #clock-cells = <2>; - - sysclk: sysclk { - #clock-cells = <0>; - compatible = "fsl,qoriq-sysclk-2.0", "fixed-clock"; - clock-output-names = "sysclk"; - }; - pll0: pll0@800 { - #clock-cells = <1>; - reg = <0x800 0x4>; - compatible = "fsl,qoriq-core-pll-2.0"; - clocks = <&sysclk>; - clock-output-names = "pll0", "pll0-div2", "pll0-div4"; - }; - pll1: pll1@820 { - #clock-cells = <1>; - reg = <0x820 0x4>; - compatible = "fsl,qoriq-core-pll-2.0"; - clocks = <&sysclk>; - clock-output-names = "pll1", "pll1-div2", "pll1-div4"; - }; - platform_pll: platform-pll@c00 { - #clock-cells = <1>; - reg = <0xc00 0x4>; - compatible = "fsl,qoriq-platform-pll-2.0"; - clocks = <&sysclk>; - clock-output-names = "platform-pll", "platform-pll-div2"; - }; }; diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi @@ -345,22 +345,6 @@ /include/ "qoriq-clockgen2.dtsi" global-utilities@e1000 { compatible = "fsl,t1023-clockgen", "fsl,qoriq-clockgen-2.0"; - mux0: mux0@0 { - #clock-cells = <0>; - reg = <0x0 4>; - compatible = "fsl,core-mux-clock"; - clocks = <&pll0 0>, <&pll0 1>; - clock-names = "pll0_0", "pll0_1"; - clock-output-names = "cmux0"; - }; - mux1: mux1@20 { - #clock-cells = <0>; - reg = <0x20 4>; - compatible = "fsl,core-mux-clock"; - clocks = <&pll0 0>, <&pll0 1>; - clock-names = "pll0_0", "pll0_1"; - clock-output-names = "cmux1"; - }; }; rcpm: global-utilities@e2000 { diff --git a/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi @@ -74,7 +74,7 @@ cpu0: PowerPC,e5500@0 { device_type = "cpu"; reg = <0>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; #cooling-cells = <2>; L2_1: l2-cache { @@ -84,7 +84,7 @@ cpu1: PowerPC,e5500@1 { device_type = "cpu"; reg = <1>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_2>; #cooling-cells = <2>; L2_2: l2-cache { diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi @@ -425,50 +425,6 @@ /include/ "qoriq-clockgen2.dtsi" global-utilities@e1000 { compatible = "fsl,t1040-clockgen", "fsl,qoriq-clockgen-2.0"; - - mux0: mux0@0 { - #clock-cells = <0>; - reg = <0x0 4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>; - clock-names = "pll0", "pll0-div2", "pll1-div4", - "pll1", "pll1-div2", "pll1-div4"; - clock-output-names = "cmux0"; - }; - - mux1: mux1@20 { - #clock-cells = <0>; - reg = <0x20 4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>; - clock-names = "pll0", "pll0-div2", "pll1-div4", - "pll1", "pll1-div2", "pll1-div4"; - clock-output-names = "cmux1"; - }; - - mux2: mux2@40 { - #clock-cells = <0>; - reg = <0x40 4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>; - clock-names = "pll0", "pll0-div2", "pll1-div4", - "pll1", "pll1-div2", "pll1-div4"; - clock-output-names = "cmux2"; - }; - - mux3: mux3@60 { - #clock-cells = <0>; - reg = <0x60 4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>; - clock-names = "pll0_0", "pll0_1", "pll0_2", - "pll1_0", "pll1_1", "pll1_2"; - clock-output-names = "cmux3"; - }; }; rcpm: global-utilities@e2000 { diff --git a/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi @@ -74,7 +74,7 @@ cpu0: PowerPC,e5500@0 { device_type = "cpu"; reg = <0>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; #cooling-cells = <2>; L2_1: l2-cache { @@ -84,7 +84,7 @@ cpu1: PowerPC,e5500@1 { device_type = "cpu"; reg = <1>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_2>; #cooling-cells = <2>; L2_2: l2-cache { @@ -94,7 +94,7 @@ cpu2: PowerPC,e5500@2 { device_type = "cpu"; reg = <2>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_3>; #cooling-cells = <2>; L2_3: l2-cache { @@ -104,7 +104,7 @@ cpu3: PowerPC,e5500@3 { device_type = "cpu"; reg = <3>; - clocks = <&mux3>; + clocks = <&clockgen 1 3>; next-level-cache = <&L2_4>; #cooling-cells = <2>; L2_4: l2-cache { diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -535,28 +535,6 @@ /include/ "qoriq-clockgen2.dtsi" global-utilities@e1000 { compatible = "fsl,t2080-clockgen", "fsl,qoriq-clockgen-2.0"; - - mux0: mux0@0 { - #clock-cells = <0>; - reg = <0x0 4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>; - clock-names = "pll0", "pll0-div2", "pll0-div4", - "pll1", "pll1-div2", "pll1-div4"; - clock-output-names = "cmux0"; - }; - - mux1: mux1@20 { - #clock-cells = <0>; - reg = <0x20 4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>; - clock-names = "pll0", "pll0-div2", "pll0-div4", - "pll1", "pll1-div2", "pll1-div4"; - clock-output-names = "cmux1"; - }; }; rcpm: global-utilities@e2000 { diff --git a/arch/powerpc/boot/dts/fsl/t208xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t208xsi-pre.dtsi @@ -81,28 +81,28 @@ cpu0: PowerPC,e6500@0 { device_type = "cpu"; reg = <0 1>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu2: PowerPC,e6500@4 { device_type = "cpu"; reg = <4 5>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu3: PowerPC,e6500@6 { device_type = "cpu"; reg = <6 7>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi @@ -950,67 +950,6 @@ /include/ "qoriq-clockgen2.dtsi" global-utilities@e1000 { compatible = "fsl,t4240-clockgen", "fsl,qoriq-clockgen-2.0"; - - pll2: pll2@840 { - #clock-cells = <1>; - reg = <0x840 0x4>; - compatible = "fsl,qoriq-core-pll-2.0"; - clocks = <&sysclk>; - clock-output-names = "pll2", "pll2-div2", "pll2-div4"; - }; - - pll3: pll3@860 { - #clock-cells = <1>; - reg = <0x860 0x4>; - compatible = "fsl,qoriq-core-pll-2.0"; - clocks = <&sysclk>; - clock-output-names = "pll3", "pll3-div2", "pll3-div4"; - }; - - pll4: pll4@880 { - #clock-cells = <1>; - reg = <0x880 0x4>; - compatible = "fsl,qoriq-core-pll-2.0"; - clocks = <&sysclk>; - clock-output-names = "pll4", "pll4-div2", "pll4-div4"; - }; - - mux0: mux0@0 { - #clock-cells = <0>; - reg = <0x0 0x4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>, - <&pll2 0>, <&pll2 1>, <&pll2 2>; - clock-names = "pll0", "pll0-div2", "pll0-div4", - "pll1", "pll1-div2", "pll1-div4", - "pll2", "pll2-div2", "pll2-div4"; - clock-output-names = "cmux0"; - }; - - mux1: mux1@20 { - #clock-cells = <0>; - reg = <0x20 0x4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, - <&pll1 0>, <&pll1 1>, <&pll1 2>, - <&pll2 0>, <&pll2 1>, <&pll2 2>; - clock-names = "pll0", "pll0-div2", "pll0-div4", - "pll1", "pll1-div2", "pll1-div4", - "pll2", "pll2-div2", "pll2-div4"; - clock-output-names = "cmux1"; - }; - - mux2: mux2@40 { - #clock-cells = <0>; - reg = <0x40 0x4>; - compatible = "fsl,qoriq-core-mux-2.0"; - clocks = <&pll3 0>, <&pll3 1>, <&pll3 2>, - <&pll4 0>, <&pll4 1>, <&pll4 2>; - clock-names = "pll3", "pll3-div2", "pll3-div4", - "pll4", "pll4-div2", "pll4-div4"; - clock-output-names = "cmux2"; - }; }; rcpm: global-utilities@e2000 { diff --git a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi @@ -90,84 +90,84 @@ cpu0: PowerPC,e6500@0 { device_type = "cpu"; reg = <0 1>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu2: PowerPC,e6500@4 { device_type = "cpu"; reg = <4 5>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu3: PowerPC,e6500@6 { device_type = "cpu"; reg = <6 7>; - clocks = <&mux0>; + clocks = <&clockgen 1 0>; next-level-cache = <&L2_1>; fsl,portid-mapping = <0x80000000>; }; cpu4: PowerPC,e6500@8 { device_type = "cpu"; reg = <8 9>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_2>; fsl,portid-mapping = <0x40000000>; }; cpu5: PowerPC,e6500@10 { device_type = "cpu"; reg = <10 11>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_2>; fsl,portid-mapping = <0x40000000>; }; cpu6: PowerPC,e6500@12 { device_type = "cpu"; reg = <12 13>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_2>; fsl,portid-mapping = <0x40000000>; }; cpu7: PowerPC,e6500@14 { device_type = "cpu"; reg = <14 15>; - clocks = <&mux1>; + clocks = <&clockgen 1 1>; next-level-cache = <&L2_2>; fsl,portid-mapping = <0x40000000>; }; cpu8: PowerPC,e6500@16 { device_type = "cpu"; reg = <16 17>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_3>; fsl,portid-mapping = <0x20000000>; }; cpu9: PowerPC,e6500@18 { device_type = "cpu"; reg = <18 19>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_3>; fsl,portid-mapping = <0x20000000>; }; cpu10: PowerPC,e6500@20 { device_type = "cpu"; reg = <20 21>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_3>; fsl,portid-mapping = <0x20000000>; }; cpu11: PowerPC,e6500@22 { device_type = "cpu"; reg = <22 23>; - clocks = <&mux2>; + clocks = <&clockgen 1 2>; next-level-cache = <&L2_3>; fsl,portid-mapping = <0x20000000>; }; diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts @@ -311,13 +311,9 @@ compatible = "fsl,ucc-mdio"; phy00:ethernet-phy@0 { - interrupt-parent = <&ipic>; - interrupts = <0>; reg = <0x0>; }; phy04:ethernet-phy@4 { - interrupt-parent = <&ipic>; - interrupts = <0>; reg = <0x4>; }; }; diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c @@ -93,7 +93,8 @@ static void *serial_get_stdout_devp(void) if (devp == NULL) goto err_out; - if (getprop(devp, "linux,stdout-path", path, MAX_PATH_LEN) > 0) { + if (getprop(devp, "linux,stdout-path", path, MAX_PATH_LEN) > 0 || + getprop(devp, "stdout-path", path, MAX_PATH_LEN) > 0) { devp = finddevice(path); if (devp == NULL) goto err_out; diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config @@ -25,6 +25,7 @@ CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_SHIRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEVTMPFS_MOUNT=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig @@ -246,7 +246,6 @@ CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_MUTEXES=y CONFIG_LATENCYTOP=y CONFIG_BOOTX_TEXT=y -CONFIG_PPC_EARLY_DEBUG=y CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y diff --git a/arch/powerpc/configs/guest.config b/arch/powerpc/configs/guest.config @@ -0,0 +1,13 @@ +CONFIG_VIRTIO_BLK=y +CONFIG_VIRTIO_BLK_SCSI=y +CONFIG_SCSI_VIRTIO=y +CONFIG_VIRTIO_NET=y +CONFIG_NET_FAILOVER=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO=y +CONFIG_VIRTIO_PCI=y +CONFIG_KVM_GUEST=y +CONFIG_EPAPR_PARAVIRT=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VHOST_NET=y +CONFIG_VHOST=y diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig @@ -108,7 +108,6 @@ CONFIG_LATENCYTOP=y CONFIG_XMON=y CONFIG_XMON_DEFAULT=y CONFIG_BOOTX_TEXT=y -CONFIG_PPC_EARLY_DEBUG=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig @@ -297,7 +297,6 @@ CONFIG_LATENCYTOP=y CONFIG_XMON=y CONFIG_XMON_DEFAULT=y CONFIG_BOOTX_TEXT=y -CONFIG_PPC_EARLY_DEBUG=y CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_SHA512=m diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig @@ -1,4 +1,3 @@ -CONFIG_PPC64=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_NO_HZ=y @@ -9,21 +8,22 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_LOG_CPU_MAX_BUF_SHIFT=13 +CONFIG_NUMA_BALANCING=y CONFIG_CGROUPS=y +CONFIG_MEMCG=y +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_FREEZER=y CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y CONFIG_BLK_DEV_INITRD=y CONFIG_BPF_SYSCALL=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y -CONFIG_OPROFILE=m -CONFIG_KPROBES=y -CONFIG_JUMP_LABEL=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_PARTITION_ADVANCED=y +CONFIG_PPC64=y +CONFIG_NR_CPUS=2048 CONFIG_PPC_SPLPAR=y CONFIG_DTL=y CONFIG_SCANLOG=m @@ -45,14 +45,11 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_CPU_FREQ_PMAC64=y CONFIG_HZ_100=y -CONFIG_BINFMT_MISC=m CONFIG_PPC_TRANSACTIONAL_MEM=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_CRASH_DUMP=y CONFIG_IRQ_ALL_CPUS=y -CONFIG_KSM=y -CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y CONFIG_HOTPLUG_PCI=y @@ -60,6 +57,23 @@ CONFIG_HOTPLUG_PCI_RPA=m CONFIG_HOTPLUG_PCI_RPA_DLPAR=m CONFIG_PCCARD=y CONFIG_ELECTRA_CF=y +CONFIG_VIRTUALIZATION=y +CONFIG_KVM_BOOK3S_64=m +CONFIG_KVM_BOOK3S_64_HV=m +CONFIG_VHOST_NET=m +CONFIG_OPROFILE=m +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_BINFMT_MISC=m +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -163,7 +177,6 @@ CONFIG_TIGON3=y CONFIG_BNX2X=m CONFIG_CHELSIO_T1=m CONFIG_BE2NET=m -CONFIG_S2IO=m CONFIG_IBMVETH=m CONFIG_EHEA=m CONFIG_E100=y @@ -174,6 +187,7 @@ CONFIG_IXGBE=m CONFIG_I40E=m CONFIG_MLX4_EN=m CONFIG_MYRI10GE=m +CONFIG_S2IO=m CONFIG_PASEMI_MAC=y CONFIG_QLGE=m CONFIG_NETXEN_NIC=m @@ -284,7 +298,7 @@ CONFIG_REISERFS_FS_SECURITY=y CONFIG_JFS_FS=m CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=y -CONFIG_XFS_FS=m +CONFIG_XFS_FS=y CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y @@ -323,25 +337,6 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_STACK_USAGE=y -CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_HARDLOCKUP_DETECTOR=y -CONFIG_DEBUG_MUTEXES=y -CONFIG_LATENCYTOP=y -CONFIG_FTRACE=y -CONFIG_FUNCTION_TRACER=y -CONFIG_FUNCTION_GRAPH_TRACER=y -CONFIG_SCHED_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_CODE_PATCHING_SELFTEST=y -CONFIG_FTR_FIXUP_SELFTEST=y -CONFIG_MSI_BITMAP_SELFTEST=y -CONFIG_XMON=y -CONFIG_BOOTX_TEXT=y -CONFIG_PPC_EARLY_DEBUG=y CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y @@ -364,8 +359,20 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_CRYPTO_DEV_VMX=y -CONFIG_VIRTUALIZATION=y -CONFIG_KVM_BOOK3S_64=m -CONFIG_KVM_BOOK3S_64_HV=m -CONFIG_VHOST_NET=m CONFIG_PRINTK_TIME=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_STACKOVERFLOW=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_DEBUG_MUTEXES=y +CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_CODE_PATCHING_SELFTEST=y +CONFIG_FTR_FIXUP_SELFTEST=y +CONFIG_MSI_BITMAP_SELFTEST=y +CONFIG_XMON=y +CONFIG_BOOTX_TEXT=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig @@ -1155,7 +1155,6 @@ CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_XMON=y CONFIG_BOOTX_TEXT=y -CONFIG_PPC_EARLY_DEBUG=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_NETWORK_XFRM=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig @@ -290,9 +290,7 @@ CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_LATENCYTOP=y -CONFIG_FTRACE=y CONFIG_FUNCTION_TRACER=y -CONFIG_FUNCTION_GRAPH_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_CODE_PATCHING_SELFTEST=y diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild @@ -1,3 +1,7 @@ +generated-y += syscall_table_32.h +generated-y += syscall_table_64.h +generated-y += syscall_table_c32.h +generated-y += syscall_table_spu.h generic-y += div64.h generic-y += export.h generic-y += irq_regs.h diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h @@ -61,7 +61,6 @@ void RunModeException(struct pt_regs *regs); void single_step_exception(struct pt_regs *regs); void program_check_exception(struct pt_regs *regs); void alignment_exception(struct pt_regs *regs); -void slb_miss_bad_addr(struct pt_regs *regs); void StackOverflow(struct pt_regs *regs); void kernel_fp_unavailable_exception(struct pt_regs *regs); void altivec_unavailable_exception(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/book3s/32/hash.h b/arch/powerpc/include/asm/book3s/32/hash.h @@ -26,6 +26,7 @@ #define _PAGE_WRITETHRU 0x040 /* W: cache write-through */ #define _PAGE_DIRTY 0x080 /* C: page changed */ #define _PAGE_ACCESSED 0x100 /* R: page referenced */ +#define _PAGE_EXEC 0x200 /* software: exec allowed */ #define _PAGE_RW 0x400 /* software: user write access allowed */ #define _PAGE_SPECIAL 0x800 /* software: Special page */ diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_ #define _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_ + /* * 32-bit hash table MMU support */ @@ -9,6 +10,8 @@ * BATs */ +#include <asm/page.h> + /* Block size masks */ #define BL_128K 0x000 #define BL_256K 0x001 @@ -34,14 +37,20 @@ #define BAT_PHYS_ADDR(x) ((u32)((x & 0x00000000fffe0000ULL) | \ ((x & 0x0000000e00000000ULL) >> 24) | \ ((x & 0x0000000100000000ULL) >> 30))) +#define PHYS_BAT_ADDR(x) (((u64)(x) & 0x00000000fffe0000ULL) | \ + (((u64)(x) << 24) & 0x0000000e00000000ULL) | \ + (((u64)(x) << 30) & 0x0000000100000000ULL)) #else #define BAT_PHYS_ADDR(x) (x) +#define PHYS_BAT_ADDR(x) ((x) & 0xfffe0000) #endif struct ppc_bat { u32 batu; u32 batl; }; + +typedef pte_t *pgtable_t; #endif /* !__ASSEMBLY__ */ /* @@ -83,6 +92,12 @@ typedef struct { unsigned long vdso_base; } mm_context_t; +/* patch sites */ +extern s32 patch__hash_page_A0, patch__hash_page_A1, patch__hash_page_A2; +extern s32 patch__hash_page_B, patch__hash_page_C; +extern s32 patch__flush_hash_A0, patch__flush_hash_A1, patch__flush_hash_A2; +extern s32 patch__flush_hash_B; + #endif /* !__ASSEMBLY__ */ /* We happily ignore the smaller BATs on 601, we don't actually use diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -25,10 +25,7 @@ extern void __bad_pte(pmd_t *pmd); extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) ({ \ - BUG_ON(!(shift)); \ - pgtable_cache[(shift) - 1]; \ - }) +#define PGT_CACHE(shift) pgtable_cache[shift] static inline pgd_t *pgd_alloc(struct mm_struct *mm) { @@ -50,8 +47,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) #define __pmd_free_tlb(tlb,x,a) do { } while (0) /* #define pgd_populate(mm, pmd, pte) BUG() */ -#ifndef CONFIG_BOOKE - static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *pte) { @@ -61,46 +56,31 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pte_page) { - *pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_PRESENT); -} - -#define pmd_pgtable(pmd) pmd_page(pmd) -#else - -static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, - pte_t *pte) -{ - *pmdp = __pmd((unsigned long)pte | _PMD_PRESENT); -} - -static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, - pgtable_t pte_page) -{ - *pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) | _PMD_PRESENT); + *pmdp = __pmd(__pa(pte_page) | _PMD_PRESENT); } -#define pmd_pgtable(pmd) pmd_page(pmd) -#endif +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr); extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr); +void pte_frag_destroy(void *pte_frag); +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel); +void pte_fragment_free(unsigned long *table, int kernel); static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - free_page((unsigned long)pte); + pte_fragment_free((unsigned long *)pte, 1); } static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) { - pgtable_page_dtor(ptepage); - __free_page(ptepage); + pte_fragment_free((unsigned long *)ptepage, 0); } static inline void pgtable_free(void *table, unsigned index_size) { if (!index_size) { - pgtable_page_dtor(virt_to_page(table)); - free_page((unsigned long)table); + pte_fragment_free((unsigned long *)table, 0); } else { BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE); kmem_cache_free(PGT_CACHE(index_size), table); @@ -138,6 +118,6 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - pgtable_free_tlb(tlb, page_address(table), 0); + pgtable_free_tlb(tlb, table, 0); } #endif /* _ASM_POWERPC_BOOK3S_32_PGALLOC_H */ diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -10,9 +10,9 @@ /* And here we include common definitions */ #define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX 0 +#define _PAGE_KERNEL_ROX (_PAGE_EXEC) #define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW) +#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) #define _PAGE_HPTEFLAGS _PAGE_HASHPTE @@ -66,11 +66,11 @@ static inline bool pte_user(pte_t pte) */ #define PAGE_NONE __pgprot(_PAGE_BASE) #define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) #define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) #define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) @@ -318,7 +318,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, int psize) { unsigned long set = pte_val(entry) & - (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW); + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); pte_update(ptep, 0, set); @@ -328,24 +328,10 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) -/* - * Note that on Book E processors, the pmd contains the kernel virtual - * (lowmem) address of the pte page. The physical address is less useful - * because everything runs with translation enabled (even the TLB miss - * handler). On everything else the pmd contains the physical address - * of the pte page. -- paulus - */ -#ifndef CONFIG_BOOKE #define pmd_page_vaddr(pmd) \ - ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) + ((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) #define pmd_page(pmd) \ pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) -#else -#define pmd_page_vaddr(pmd) \ - ((unsigned long) (pmd_val(pmd) & PAGE_MASK)) -#define pmd_page(pmd) \ - pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT)) -#endif /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) @@ -360,7 +346,8 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define pte_offset_kernel(dir, addr) \ ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr)) #define pte_offset_map(dir, addr) \ - ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr)) + ((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \ + (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr)) #define pte_unmap(pte) kunmap_atomic(pte) /* @@ -384,7 +371,7 @@ static inline int pte_dirty(pte_t pte) { return !!(pte_val(pte) & _PAGE_DIRTY); static inline int pte_young(pte_t pte) { return !!(pte_val(pte) & _PAGE_ACCESSED); } static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIAL); } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } -static inline bool pte_exec(pte_t pte) { return true; } +static inline bool pte_exec(pte_t pte) { return pte_val(pte) & _PAGE_EXEC; } static inline int pte_present(pte_t pte) { @@ -451,7 +438,7 @@ static inline pte_t pte_wrprotect(pte_t pte) static inline pte_t pte_exprotect(pte_t pte) { - return pte; + return __pte(pte_val(pte) & ~_PAGE_EXEC); } static inline pte_t pte_mkclean(pte_t pte) @@ -466,7 +453,7 @@ static inline pte_t pte_mkold(pte_t pte) static inline pte_t pte_mkexec(pte_t pte) { - return pte; + return __pte(pte_val(pte) | _PAGE_EXEC); } static inline pte_t pte_mkpte(pte_t pte) @@ -524,7 +511,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, int percpu) { -#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) +#if defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the * helper pte_update() which does an atomic update. We need to do that * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a @@ -537,7 +524,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, else pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); -#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) +#elif defined(CONFIG_PTE_64BIT) /* Second case is 32-bit with 64-bit PTE. In this case, we * can just store as long as we do the two halves in the right order * with a barrier in between. This is possible because we take care, @@ -560,7 +547,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); -#elif defined(CONFIG_PPC_STD_MMU_32) +#else /* Third case is 32-bit hash table in UP mode, we need to preserve * the _PAGE_HASHPTE bit since we may not have invalidated the previous * translation in the hash yet (done in a subsequent flush_tlb_xxx()) @@ -568,9 +555,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, */ *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) | (pte_val(pte) & ~_PAGE_HASHPTE)); - -#else -#error "Not supported " #endif } diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -1,11 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_BOOK3S_64_HASH_4K_H #define _ASM_POWERPC_BOOK3S_64_HASH_4K_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 - * each entry by assuming that each entry is page aligned. - */ + #define H_PTE_INDEX_SIZE 9 #define H_PMD_INDEX_SIZE 7 #define H_PUD_INDEX_SIZE 9 diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_BOOK3S_64_MMU_H_ #define _ASM_POWERPC_BOOK3S_64_MMU_H_ +#include <asm/page.h> + #ifndef __ASSEMBLY__ /* * Page size definition @@ -24,6 +26,13 @@ struct mmu_psize_def { }; extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; +/* + * For BOOK3s 64 with 4k and 64K linux page size + * we want to use pointers, because the page table + * actually store pfn + */ +typedef pte_t *pgtable_t; + #endif /* __ASSEMBLY__ */ /* 64-bit classic hash table MMU */ diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -37,10 +37,7 @@ extern struct vmemmap_backing *vmemmap_list; #define MAX_PGTABLE_INDEX_SIZE 0xf extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) ({ \ - BUG_ON(!(shift)); \ - pgtable_cache[(shift) - 1]; \ - }) +#define PGT_CACHE(shift) pgtable_cache[shift] extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int); extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long); @@ -50,6 +47,7 @@ extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); #ifdef CONFIG_SMP extern void __tlb_remove_table(void *_table); #endif +void pte_frag_destroy(void *pte_frag); static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1304,7 +1304,7 @@ static inline int pgd_devmap(pgd_t pgd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline const int pud_pfn(pud_t pud) +static inline int pud_pfn(pud_t pud) { /* * Currently all calls to pud_pfn() are gated around a pud_devmap() diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h @@ -71,7 +71,7 @@ extern struct ppc64_caches ppc64_caches; #else #define __read_mostly __attribute__((__section__(".data..read_mostly"))) -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 extern long _get_L2CR(void); extern long _get_L3CR(void); extern void _set_L2CR(unsigned long); diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h @@ -33,14 +33,33 @@ unsigned int create_cond_branch(const unsigned int *addr, int patch_branch(unsigned int *addr, unsigned long target, int flags); int patch_instruction(unsigned int *addr, unsigned int instr); int raw_patch_instruction(unsigned int *addr, unsigned int instr); -int patch_instruction_site(s32 *addr, unsigned int instr); -int patch_branch_site(s32 *site, unsigned long target, int flags); static inline unsigned long patch_site_addr(s32 *site) { return (unsigned long)site + *site; } +static inline int patch_instruction_site(s32 *site, unsigned int instr) +{ + return patch_instruction((unsigned int *)patch_site_addr(site), instr); +} + +static inline int patch_branch_site(s32 *site, unsigned long target, int flags) +{ + return patch_branch((unsigned int *)patch_site_addr(site), target, flags); +} + +static inline int modify_instruction(unsigned int *addr, unsigned int clr, + unsigned int set) +{ + return patch_instruction(addr, (*addr & ~clr) | set); +} + +static inline int modify_instruction_site(s32 *site, unsigned int clr, unsigned int set) +{ + return modify_instruction((unsigned int *)patch_site_addr(site), clr, set); +} + int instr_is_relative_branch(unsigned int instr); int instr_is_relative_link_branch(unsigned int instr); int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr); diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h @@ -44,6 +44,7 @@ extern int machine_check_e500(struct pt_regs *regs); extern int machine_check_e200(struct pt_regs *regs); extern int machine_check_47x(struct pt_regs *regs); int machine_check_8xx(struct pt_regs *regs); +int machine_check_83xx(struct pt_regs *regs); extern void cpu_down_flush_e500v2(void); extern void cpu_down_flush_e500mc(void); @@ -296,7 +297,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTRS_PPC601 (CPU_FTR_COMMON | CPU_FTR_601 | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_USE_RTC) #define CPU_FTRS_603 (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) + CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_604 (CPU_FTR_COMMON | CPU_FTR_PPC_LE) #define CPU_FTRS_740_NOTAU (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \ @@ -367,15 +368,15 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) -#define CPU_FTRS_82XX (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE) +#define CPU_FTRS_82XX (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_G2_LE (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_MAYBE_CAN_NAP) #define CPU_FTRS_E300 (CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_MAYBE_CAN_NAP | \ - CPU_FTR_COMMON) + CPU_FTR_COMMON | CPU_FTR_NOEXECUTE) #define CPU_FTRS_E300C2 (CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_MAYBE_CAN_NAP | \ - CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE) + CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON) #define CPU_FTRS_8XX (CPU_FTR_NOEXECUTE) #define CPU_FTRS_40X (CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h @@ -39,9 +39,6 @@ extern int dma_nommu_mmap_coherent(struct device *dev, * to ensure it is consistent. */ struct device; -extern void *__dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp); -extern void __dma_free_coherent(size_t size, void *vaddr); extern void __dma_sync(void *vaddr, size_t size, int direction); extern void __dma_sync_page(struct page *page, unsigned long offset, size_t size, int direction); @@ -52,8 +49,6 @@ extern unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr); * Cache coherent cores. */ -#define __dma_alloc_coherent(dev, gfp, size, handle) NULL -#define __dma_free_coherent(size, addr) ((void)0) #define __dma_sync(addr, size, rw) ((void)0) #define __dma_sync_page(pg, off, sz, rw) ((void)0) @@ -112,7 +107,5 @@ extern int dma_set_mask(struct device *dev, u64 dma_mask); extern u64 __dma_get_required_mask(struct device *dev); -#define ARCH_HAS_DMA_MMAP_COHERENT - #endif /* __KERNEL__ */ #endif /* _ASM_DMA_MAPPING_H */ diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h @@ -48,6 +48,10 @@ #define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt) +/* Alignement per CMA requirement. */ +#define FADUMP_CMA_ALIGNMENT (PAGE_SIZE << \ + max_t(unsigned long, MAX_ORDER - 1, pageblock_order)) + /* Firmware provided dump sections */ #define FADUMP_CPU_STATE_DATA 0x0001 #define FADUMP_HPTE_REGION 0x0002 @@ -141,6 +145,7 @@ struct fw_dump { unsigned long fadump_supported:1; unsigned long dump_active:1; unsigned long dump_registered:1; + unsigned long nocma:1; }; /* @@ -200,7 +205,7 @@ struct fad_crash_memory_ranges { unsigned long long size; }; -extern int is_fadump_boot_memory_area(u64 addr, ulong size); +extern int is_fadump_memory_area(u64 addr, ulong size); extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data); extern int fadump_reserve_mem(void); diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h @@ -221,6 +221,17 @@ label##3: \ FTR_ENTRY_OFFSET 953b-954b; \ .popsection; +#define START_BTB_FLUSH_SECTION \ +955: \ + +#define END_BTB_FLUSH_SECTION \ +956: \ + .pushsection __btb_flush_fixup,"a"; \ + .align 2; \ +957: \ + FTR_ENTRY_OFFSET 955b-957b; \ + FTR_ENTRY_OFFSET 956b-957b; \ + .popsection; #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -230,6 +241,7 @@ extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; +extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; void apply_feature_fixups(void); void setup_feature_keys(void); diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h @@ -5,8 +5,6 @@ #ifdef CONFIG_HUGETLB_PAGE #include <asm/page.h> -extern struct kmem_cache *hugepte_cache; - #ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/hugetlb.h> @@ -76,7 +74,9 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, unsigned long idx = 0; pte_t *dir = hugepd_page(hpd); -#ifndef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_8xx + idx = (addr & ((1UL << pdshift) - 1)) >> PAGE_SHIFT; +#elif !defined(CONFIG_PPC_FSL_BOOK3E) idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd); #endif @@ -129,15 +129,14 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - pte_t pte; - pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); flush_hugetlb_page(vma, addr); } #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS -extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty); +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty); static inline void arch_clear_hugepage_flags(struct page *page) { diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h @@ -29,12 +29,14 @@ extern struct pci_dev *isa_bridge_pcidev; #include <linux/device.h> #include <linux/compiler.h> +#include <linux/mm.h> #include <asm/page.h> #include <asm/byteorder.h> #include <asm/synch.h> #include <asm/delay.h> #include <asm/mmu.h> #include <asm/ppc_asm.h> +#include <asm/pgtable.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -804,6 +806,8 @@ extern void __iounmap_at(void *ea, unsigned long size); */ static inline unsigned long virt_to_phys(volatile void * address) { + WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && !virt_addr_valid(address)); + return __pa((unsigned long)address); } @@ -827,7 +831,14 @@ static inline void * phys_to_virt(unsigned long address) /* * Change "struct page" to physical address. */ -#define page_to_phys(page) ((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT) +static inline phys_addr_t page_to_phys(struct page *page) +{ + unsigned long pfn = page_to_pfn(page); + + WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && !pfn_valid(pfn)); + + return PFN_PHYS(pfn); +} /* * 32 bits still uses virt_to_bus() for it's implementation of DMA diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h @@ -215,11 +215,12 @@ struct iommu_table_group { extern void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, unsigned long pe_num); -extern int iommu_add_device(struct device *dev); +extern int iommu_add_device(struct iommu_table_group *table_group, + struct device *dev); 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(struct mm_struct *mm, 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, @@ -227,7 +228,8 @@ static inline void iommu_register_group(struct iommu_table_group *table_group, { } -static inline int iommu_add_device(struct device *dev) +static inline int iommu_add_device(struct iommu_table_group *table_group, + struct device *dev) { return 0; } @@ -235,11 +237,6 @@ static inline int iommu_add_device(struct device *dev) static inline void iommu_del_device(struct device *dev) { } - -static inline int __init tce_iommu_bus_notifier_init(void) -{ - return 0; -} #endif /* !CONFIG_IOMMU_API */ int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr); diff --git a/arch/powerpc/include/asm/ipic.h b/arch/powerpc/include/asm/ipic.h @@ -69,7 +69,6 @@ enum ipic_mcp_irq { IPIC_MCP_MU = 7, }; -extern int ipic_set_priority(unsigned int irq, unsigned int priority); extern void ipic_set_highest_priority(unsigned int irq); extern void ipic_set_default_priority(void); extern void ipic_enable_mcp(enum ipic_mcp_irq mcp_irq); diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h @@ -1,153 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_MMU_44X_H_ -#define _ASM_POWERPC_MMU_44X_H_ -/* - * PPC440 support - */ - -#include <asm/asm-const.h> - -#define PPC44x_MMUCR_TID 0x000000ff -#define PPC44x_MMUCR_STS 0x00010000 - -#define PPC44x_TLB_PAGEID 0 -#define PPC44x_TLB_XLAT 1 -#define PPC44x_TLB_ATTRIB 2 - -/* Page identification fields */ -#define PPC44x_TLB_EPN_MASK 0xfffffc00 /* Effective Page Number */ -#define PPC44x_TLB_VALID 0x00000200 /* Valid flag */ -#define PPC44x_TLB_TS 0x00000100 /* Translation address space */ -#define PPC44x_TLB_1K 0x00000000 /* Page sizes */ -#define PPC44x_TLB_4K 0x00000010 -#define PPC44x_TLB_16K 0x00000020 -#define PPC44x_TLB_64K 0x00000030 -#define PPC44x_TLB_256K 0x00000040 -#define PPC44x_TLB_1M 0x00000050 -#define PPC44x_TLB_16M 0x00000070 -#define PPC44x_TLB_256M 0x00000090 - -/* Translation fields */ -#define PPC44x_TLB_RPN_MASK 0xfffffc00 /* Real Page Number */ -#define PPC44x_TLB_ERPN_MASK 0x0000000f - -/* Storage attribute and access control fields */ -#define PPC44x_TLB_ATTR_MASK 0x0000ff80 -#define PPC44x_TLB_U0 0x00008000 /* User 0 */ -#define PPC44x_TLB_U1 0x00004000 /* User 1 */ -#define PPC44x_TLB_U2 0x00002000 /* User 2 */ -#define PPC44x_TLB_U3 0x00001000 /* User 3 */ -#define PPC44x_TLB_W 0x00000800 /* Caching is write-through */ -#define PPC44x_TLB_I 0x00000400 /* Caching is inhibited */ -#define PPC44x_TLB_M 0x00000200 /* Memory is coherent */ -#define PPC44x_TLB_G 0x00000100 /* Memory is guarded */ -#define PPC44x_TLB_E 0x00000080 /* Memory is little endian */ - -#define PPC44x_TLB_PERM_MASK 0x0000003f -#define PPC44x_TLB_UX 0x00000020 /* User execution */ -#define PPC44x_TLB_UW 0x00000010 /* User write */ -#define PPC44x_TLB_UR 0x00000008 /* User read */ -#define PPC44x_TLB_SX 0x00000004 /* Super execution */ -#define PPC44x_TLB_SW 0x00000002 /* Super write */ -#define PPC44x_TLB_SR 0x00000001 /* Super read */ - -/* Number of TLB entries */ -#define PPC44x_TLB_SIZE 64 - -/* 47x bits */ -#define PPC47x_MMUCR_TID 0x0000ffff -#define PPC47x_MMUCR_STS 0x00010000 - -/* Page identification fields */ -#define PPC47x_TLB0_EPN_MASK 0xfffff000 /* Effective Page Number */ -#define PPC47x_TLB0_VALID 0x00000800 /* Valid flag */ -#define PPC47x_TLB0_TS 0x00000400 /* Translation address space */ -#define PPC47x_TLB0_4K 0x00000000 -#define PPC47x_TLB0_16K 0x00000010 -#define PPC47x_TLB0_64K 0x00000030 -#define PPC47x_TLB0_1M 0x00000070 -#define PPC47x_TLB0_16M 0x000000f0 -#define PPC47x_TLB0_256M 0x000001f0 -#define PPC47x_TLB0_1G 0x000003f0 -#define PPC47x_TLB0_BOLTED_R 0x00000008 /* tlbre only */ - -/* Translation fields */ -#define PPC47x_TLB1_RPN_MASK 0xfffff000 /* Real Page Number */ -#define PPC47x_TLB1_ERPN_MASK 0x000003ff - -/* Storage attribute and access control fields */ -#define PPC47x_TLB2_ATTR_MASK 0x0003ff80 -#define PPC47x_TLB2_IL1I 0x00020000 /* Memory is guarded */ -#define PPC47x_TLB2_IL1D 0x00010000 /* Memory is guarded */ -#define PPC47x_TLB2_U0 0x00008000 /* User 0 */ -#define PPC47x_TLB2_U1 0x00004000 /* User 1 */ -#define PPC47x_TLB2_U2 0x00002000 /* User 2 */ -#define PPC47x_TLB2_U3 0x00001000 /* User 3 */ -#define PPC47x_TLB2_W 0x00000800 /* Caching is write-through */ -#define PPC47x_TLB2_I 0x00000400 /* Caching is inhibited */ -#define PPC47x_TLB2_M 0x00000200 /* Memory is coherent */ -#define PPC47x_TLB2_G 0x00000100 /* Memory is guarded */ -#define PPC47x_TLB2_E 0x00000080 /* Memory is little endian */ -#define PPC47x_TLB2_PERM_MASK 0x0000003f -#define PPC47x_TLB2_UX 0x00000020 /* User execution */ -#define PPC47x_TLB2_UW 0x00000010 /* User write */ -#define PPC47x_TLB2_UR 0x00000008 /* User read */ -#define PPC47x_TLB2_SX 0x00000004 /* Super execution */ -#define PPC47x_TLB2_SW 0x00000002 /* Super write */ -#define PPC47x_TLB2_SR 0x00000001 /* Super read */ -#define PPC47x_TLB2_U_RWX (PPC47x_TLB2_UX|PPC47x_TLB2_UW|PPC47x_TLB2_UR) -#define PPC47x_TLB2_S_RWX (PPC47x_TLB2_SX|PPC47x_TLB2_SW|PPC47x_TLB2_SR) -#define PPC47x_TLB2_S_RW (PPC47x_TLB2_SW | PPC47x_TLB2_SR) -#define PPC47x_TLB2_IMG (PPC47x_TLB2_I | PPC47x_TLB2_M | PPC47x_TLB2_G) - -#ifndef __ASSEMBLY__ - -extern unsigned int tlb_44x_hwater; -extern unsigned int tlb_44x_index; - -typedef struct { - unsigned int id; - unsigned int active; - unsigned long vdso_base; -} mm_context_t; - -#endif /* !__ASSEMBLY__ */ - -#ifndef CONFIG_PPC_EARLY_DEBUG_44x -#define PPC44x_EARLY_TLBS 1 -#else -#define PPC44x_EARLY_TLBS 2 -#define PPC44x_EARLY_DEBUG_VIRTADDR (ASM_CONST(0xf0000000) \ - | (ASM_CONST(CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW) & 0xffff)) -#endif - -/* Size of the TLBs used for pinning in lowmem */ -#define PPC_PIN_SIZE (1 << 28) /* 256M */ - -#if defined(CONFIG_PPC_4K_PAGES) -#define PPC44x_TLBE_SIZE PPC44x_TLB_4K -#define PPC47x_TLBE_SIZE PPC47x_TLB0_4K -#define mmu_virtual_psize MMU_PAGE_4K -#elif defined(CONFIG_PPC_16K_PAGES) -#define PPC44x_TLBE_SIZE PPC44x_TLB_16K -#define PPC47x_TLBE_SIZE PPC47x_TLB0_16K -#define mmu_virtual_psize MMU_PAGE_16K -#elif defined(CONFIG_PPC_64K_PAGES) -#define PPC44x_TLBE_SIZE PPC44x_TLB_64K -#define PPC47x_TLBE_SIZE PPC47x_TLB0_64K -#define mmu_virtual_psize MMU_PAGE_64K -#elif defined(CONFIG_PPC_256K_PAGES) -#define PPC44x_TLBE_SIZE PPC44x_TLB_256K -#define mmu_virtual_psize MMU_PAGE_256K -#else -#error "Unsupported PAGE_SIZE" -#endif - -#define mmu_linear_psize MMU_PAGE_256M - -#define PPC44x_PGD_OFF_SHIFT (32 - PGDIR_SHIFT + PGD_T_LOG2) -#define PPC44x_PGD_OFF_MASK_BIT (PGDIR_SHIFT - PGD_T_LOG2) -#define PPC44x_PTE_ADD_SHIFT (32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2) -#define PPC44x_PTE_ADD_MASK_BIT (32 - PTE_T_LOG2 - PTE_SHIFT) - -#endif /* _ASM_POWERPC_MMU_44X_H_ */ diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h @@ -1,253 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_MMU_8XX_H_ -#define _ASM_POWERPC_MMU_8XX_H_ -/* - * PPC8xx support - */ - -/* Control/status registers for the MPC8xx. - * A write operation to these registers causes serialized access. - * During software tablewalk, the registers used perform mask/shift-add - * operations when written/read. A TLB entry is created when the Mx_RPN - * is written, and the contents of several registers are used to - * create the entry. - */ -#define SPRN_MI_CTR 784 /* Instruction TLB control register */ -#define MI_GPM 0x80000000 /* Set domain manager mode */ -#define MI_PPM 0x40000000 /* Set subpage protection */ -#define MI_CIDEF 0x20000000 /* Set cache inhibit when MMU dis */ -#define MI_RSV4I 0x08000000 /* Reserve 4 TLB entries */ -#define MI_PPCS 0x02000000 /* Use MI_RPN prob/priv state */ -#define MI_IDXMASK 0x00001f00 /* TLB index to be loaded */ -#define MI_RESETVAL 0x00000000 /* Value of register at reset */ - -/* These are the Ks and Kp from the PowerPC books. For proper operation, - * Ks = 0, Kp = 1. - */ -#define SPRN_MI_AP 786 -#define MI_Ks 0x80000000 /* Should not be set */ -#define MI_Kp 0x40000000 /* Should always be set */ - -/* - * All pages' PP data bits are set to either 001 or 011 by copying _PAGE_EXEC - * into bit 21 in the ITLBmiss handler (bit 21 is the middle bit), which means - * respectively NA for All or X for Supervisor and no access for User. - * Then we use the APG to say whether accesses are according to Page rules or - * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => No user => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * We define all 16 groups so that all other bits of APG can take any value - */ -#define MI_APG_INIT 0x44444444 - -/* The effective page number register. When read, contains the information - * about the last instruction TLB miss. When MI_RPN is written, bits in - * this register are used to create the TLB entry. - */ -#define SPRN_MI_EPN 787 -#define MI_EPNMASK 0xfffff000 /* Effective page number for entry */ -#define MI_EVALID 0x00000200 /* Entry is valid */ -#define MI_ASIDMASK 0x0000000f /* ASID match value */ - /* Reset value is undefined */ - -/* A "level 1" or "segment" or whatever you want to call it register. - * For the instruction TLB, it contains bits that get loaded into the - * TLB entry when the MI_RPN is written. - */ -#define SPRN_MI_TWC 789 -#define MI_APG 0x000001e0 /* Access protection group (0) */ -#define MI_GUARDED 0x00000010 /* Guarded storage */ -#define MI_PSMASK 0x0000000c /* Mask of page size bits */ -#define MI_PS8MEG 0x0000000c /* 8M page size */ -#define MI_PS512K 0x00000004 /* 512K page size */ -#define MI_PS4K_16K 0x00000000 /* 4K or 16K page size */ -#define MI_SVALID 0x00000001 /* Segment entry is valid */ - /* Reset value is undefined */ - -/* Real page number. Defined by the pte. Writing this register - * causes a TLB entry to be created for the instruction TLB, using - * additional information from the MI_EPN, and MI_TWC registers. - */ -#define SPRN_MI_RPN 790 -#define MI_SPS16K 0x00000008 /* Small page size (0 = 4k, 1 = 16k) */ - -/* Define an RPN value for mapping kernel memory to large virtual - * pages for boot initialization. This has real page number of 0, - * large page size, shared page, cache enabled, and valid. - * Also mark all subpages valid and write access. - */ -#define MI_BOOTINIT 0x000001fd - -#define SPRN_MD_CTR 792 /* Data TLB control register */ -#define MD_GPM 0x80000000 /* Set domain manager mode */ -#define MD_PPM 0x40000000 /* Set subpage protection */ -#define MD_CIDEF 0x20000000 /* Set cache inhibit when MMU dis */ -#define MD_WTDEF 0x10000000 /* Set writethrough when MMU dis */ -#define MD_RSV4I 0x08000000 /* Reserve 4 TLB entries */ -#define MD_TWAM 0x04000000 /* Use 4K page hardware assist */ -#define MD_PPCS 0x02000000 /* Use MI_RPN prob/priv state */ -#define MD_IDXMASK 0x00001f00 /* TLB index to be loaded */ -#define MD_RESETVAL 0x04000000 /* Value of register at reset */ - -#define SPRN_M_CASID 793 /* Address space ID (context) to match */ -#define MC_ASIDMASK 0x0000000f /* Bits used for ASID value */ - - -/* These are the Ks and Kp from the PowerPC books. For proper operation, - * Ks = 0, Kp = 1. - */ -#define SPRN_MD_AP 794 -#define MD_Ks 0x80000000 /* Should not be set */ -#define MD_Kp 0x40000000 /* Should always be set */ - -/* - * All pages' PP data bits are set to either 000 or 011 or 001, which means - * respectively RW for Supervisor and no access for User, or RO for - * Supervisor and no access for user and NA for ALL. - * Then we use the APG to say whether accesses are according to Page rules or - * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => No user => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * We define all 16 groups so that all other bits of APG can take any value - */ -#define MD_APG_INIT 0x44444444 - -/* The effective page number register. When read, contains the information - * about the last instruction TLB miss. When MD_RPN is written, bits in - * this register are used to create the TLB entry. - */ -#define SPRN_MD_EPN 795 -#define MD_EPNMASK 0xfffff000 /* Effective page number for entry */ -#define MD_EVALID 0x00000200 /* Entry is valid */ -#define MD_ASIDMASK 0x0000000f /* ASID match value */ - /* Reset value is undefined */ - -/* The pointer to the base address of the first level page table. - * During a software tablewalk, reading this register provides the address - * of the entry associated with MD_EPN. - */ -#define SPRN_M_TWB 796 -#define M_L1TB 0xfffff000 /* Level 1 table base address */ -#define M_L1INDX 0x00000ffc /* Level 1 index, when read */ - /* Reset value is undefined */ - -/* A "level 1" or "segment" or whatever you want to call it register. - * For the data TLB, it contains bits that get loaded into the TLB entry - * when the MD_RPN is written. It is also provides the hardware assist - * for finding the PTE address during software tablewalk. - */ -#define SPRN_MD_TWC 797 -#define MD_L2TB 0xfffff000 /* Level 2 table base address */ -#define MD_L2INDX 0xfffffe00 /* Level 2 index (*pte), when read */ -#define MD_APG 0x000001e0 /* Access protection group (0) */ -#define MD_GUARDED 0x00000010 /* Guarded storage */ -#define MD_PSMASK 0x0000000c /* Mask of page size bits */ -#define MD_PS8MEG 0x0000000c /* 8M page size */ -#define MD_PS512K 0x00000004 /* 512K page size */ -#define MD_PS4K_16K 0x00000000 /* 4K or 16K page size */ -#define MD_WT 0x00000002 /* Use writethrough page attribute */ -#define MD_SVALID 0x00000001 /* Segment entry is valid */ - /* Reset value is undefined */ - - -/* Real page number. Defined by the pte. Writing this register - * causes a TLB entry to be created for the data TLB, using - * additional information from the MD_EPN, and MD_TWC registers. - */ -#define SPRN_MD_RPN 798 -#define MD_SPS16K 0x00000008 /* Small page size (0 = 4k, 1 = 16k) */ - -/* This is a temporary storage register that could be used to save - * a processor working register during a tablewalk. - */ -#define SPRN_M_TW 799 - -#ifdef CONFIG_PPC_MM_SLICES -#include <asm/nohash/32/slice.h> -#define SLICE_ARRAY_SIZE (1 << (32 - SLICE_LOW_SHIFT - 1)) -#endif - -#ifndef __ASSEMBLY__ -struct slice_mask { - u64 low_slices; - DECLARE_BITMAP(high_slices, 0); -}; - -typedef struct { - unsigned int id; - unsigned int active; - unsigned long vdso_base; -#ifdef CONFIG_PPC_MM_SLICES - u16 user_psize; /* page size index */ - unsigned char low_slices_psize[SLICE_ARRAY_SIZE]; - unsigned char high_slices_psize[0]; - unsigned long slb_addr_limit; - struct slice_mask mask_base_psize; /* 4k or 16k */ -# ifdef CONFIG_HUGETLB_PAGE - struct slice_mask mask_512k; - struct slice_mask mask_8m; -# endif -#endif -} mm_context_t; - -#define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000) -#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE)) - -/* Page size definitions, common between 32 and 64-bit - * - * shift : is the "PAGE_SHIFT" value for that page size - * penc : is the pte encoding mask - * - */ -struct mmu_psize_def { - unsigned int shift; /* number of bits */ - unsigned int enc; /* PTE encoding */ - unsigned int ind; /* Corresponding indirect page size shift */ - unsigned int flags; -#define MMU_PAGE_SIZE_DIRECT 0x1 /* Supported as a direct size */ -#define MMU_PAGE_SIZE_INDIRECT 0x2 /* Supported as an indirect size */ -}; - -extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; - -static inline int shift_to_mmu_psize(unsigned int shift) -{ - int psize; - - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) - if (mmu_psize_defs[psize].shift == shift) - return psize; - return -1; -} - -static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) -{ - if (mmu_psize_defs[mmu_psize].shift) - return mmu_psize_defs[mmu_psize].shift; - BUG(); -} - -/* patch sites */ -extern s32 patch__itlbmiss_linmem_top; -extern s32 patch__dtlbmiss_linmem_top, patch__dtlbmiss_immr_jmp; -extern s32 patch__fixupdar_linmem_top; - -extern s32 patch__itlbmiss_exit_1, patch__itlbmiss_exit_2; -extern s32 patch__dtlbmiss_exit_1, patch__dtlbmiss_exit_2, patch__dtlbmiss_exit_3; -extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf; - -#endif /* !__ASSEMBLY__ */ - -#if defined(CONFIG_PPC_4K_PAGES) -#define mmu_virtual_psize MMU_PAGE_4K -#elif defined(CONFIG_PPC_16K_PAGES) -#define mmu_virtual_psize MMU_PAGE_16K -#else -#error "Unsupported PAGE_SIZE" -#endif - -#define mmu_linear_psize MMU_PAGE_8M - -#endif /* _ASM_POWERPC_MMU_8XX_H_ */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h @@ -48,7 +48,7 @@ #define MMU_FTR_USE_HIGH_BATS ASM_CONST(0x00010000) /* Enable >32-bit physical addresses on 32-bit processor, only used - * by CONFIG_6xx currently as BookE supports that from day 1 + * by CONFIG_PPC_BOOK3S_32 currently as BookE supports that from day 1 */ #define MMU_FTR_BIG_PHYS ASM_CONST(0x00020000) @@ -131,16 +131,37 @@ DECLARE_PER_CPU(int, next_tlbcam_idx); #endif enum { - MMU_FTRS_POSSIBLE = MMU_FTR_HPTE_TABLE | MMU_FTR_TYPE_8xx | - MMU_FTR_TYPE_40x | MMU_FTR_TYPE_44x | MMU_FTR_TYPE_FSL_E | - MMU_FTR_TYPE_47x | MMU_FTR_USE_HIGH_BATS | MMU_FTR_BIG_PHYS | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_USE_TLBILX | - MMU_FTR_LOCK_BCAST_INVAL | MMU_FTR_NEED_DTLB_SW_LRU | + MMU_FTRS_POSSIBLE = +#ifdef CONFIG_PPC_BOOK3S + MMU_FTR_HPTE_TABLE | +#endif +#ifdef CONFIG_PPC_8xx + MMU_FTR_TYPE_8xx | +#endif +#ifdef CONFIG_40x + MMU_FTR_TYPE_40x | +#endif +#ifdef CONFIG_44x + MMU_FTR_TYPE_44x | +#endif +#if defined(CONFIG_E200) || defined(CONFIG_E500) + MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX | +#endif +#ifdef CONFIG_PPC_47x + MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL | +#endif +#ifdef CONFIG_PPC_BOOK3S_32 + MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU | +#endif +#ifdef CONFIG_PPC_BOOK3E_64 MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS | +#endif +#ifdef CONFIG_PPC_BOOK3S_64 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_68_BIT_VA | +#endif #ifdef CONFIG_PPC_RADIX_MMU MMU_FTR_TYPE_RADIX | #endif @@ -338,21 +359,11 @@ static inline void mmu_early_init_devtree(void) { } #endif /* __ASSEMBLY__ */ #endif -#if defined(CONFIG_PPC_STD_MMU_32) +#if defined(CONFIG_PPC_BOOK3S_32) /* 32-bit classic hash table MMU */ #include <asm/book3s/32/mmu-hash.h> -#elif defined(CONFIG_40x) -/* 40x-style software loaded TLB */ -# include <asm/mmu-40x.h> -#elif defined(CONFIG_44x) -/* 44x-style software loaded TLB */ -# include <asm/mmu-44x.h> -#elif defined(CONFIG_PPC_BOOK3E_MMU) -/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */ -# include <asm/mmu-book3e.h> -#elif defined (CONFIG_PPC_8xx) -/* Motorola/Freescale 8xx software loaded TLB */ -# include <asm/mmu-8xx.h> +#elif defined(CONFIG_PPC_MMU_NOHASH) +#include <asm/nohash/mmu.h> #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h @@ -21,9 +21,12 @@ struct mm_iommu_table_group_mem_t; extern int isolate_lru_page(struct page *page); /* from internal.h */ extern bool mm_iommu_preregistered(struct mm_struct *mm); -extern long mm_iommu_get(struct mm_struct *mm, +extern long mm_iommu_new(struct mm_struct *mm, unsigned long ua, unsigned long entries, struct mm_iommu_table_group_mem_t **pmem); +extern long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua, + unsigned long entries, unsigned long dev_hpa, + struct mm_iommu_table_group_mem_t **pmem); extern long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_init(struct mm_struct *mm); @@ -32,15 +35,23 @@ 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, +extern struct mm_iommu_table_group_mem_t *mm_iommu_get(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 int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua); +extern bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa, + unsigned int pageshift, unsigned long *size); 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); +#else +static inline bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa, + unsigned int pageshift, unsigned long *size) +{ + return false; +} #endif extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm); extern void set_context(unsigned long id, pgd_t *pgd); @@ -217,13 +228,7 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, #endif } -static inline int arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) -{ - return 0; -} - -#ifndef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_BOOK3E_64 static inline void arch_exit_mmap(struct mm_struct *mm) { } @@ -247,6 +252,7 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm, #ifdef CONFIG_PPC_MEM_KEYS bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign); +void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm); #else /* CONFIG_PPC_MEM_KEYS */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) @@ -259,6 +265,7 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, #define thread_pkey_regs_save(thread) #define thread_pkey_regs_restore(new_thread, old_thread) #define thread_pkey_regs_init(thread) +#define arch_dup_pkeys(oldmm, mm) static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) { @@ -267,5 +274,12 @@ static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) #endif /* CONFIG_PPC_MEM_KEYS */ +static inline int arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) +{ + arch_dup_pkeys(oldmm, mm); + return 0; +} + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_MMU_CONTEXT_H */ diff --git a/arch/powerpc/include/asm/mmu-40x.h b/arch/powerpc/include/asm/nohash/32/mmu-40x.h diff --git a/arch/powerpc/include/asm/nohash/32/mmu-44x.h b/arch/powerpc/include/asm/nohash/32/mmu-44x.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_MMU_44X_H_ +#define _ASM_POWERPC_MMU_44X_H_ +/* + * PPC440 support + */ + +#include <asm/asm-const.h> + +#define PPC44x_MMUCR_TID 0x000000ff +#define PPC44x_MMUCR_STS 0x00010000 + +#define PPC44x_TLB_PAGEID 0 +#define PPC44x_TLB_XLAT 1 +#define PPC44x_TLB_ATTRIB 2 + +/* Page identification fields */ +#define PPC44x_TLB_EPN_MASK 0xfffffc00 /* Effective Page Number */ +#define PPC44x_TLB_VALID 0x00000200 /* Valid flag */ +#define PPC44x_TLB_TS 0x00000100 /* Translation address space */ +#define PPC44x_TLB_1K 0x00000000 /* Page sizes */ +#define PPC44x_TLB_4K 0x00000010 +#define PPC44x_TLB_16K 0x00000020 +#define PPC44x_TLB_64K 0x00000030 +#define PPC44x_TLB_256K 0x00000040 +#define PPC44x_TLB_1M 0x00000050 +#define PPC44x_TLB_16M 0x00000070 +#define PPC44x_TLB_256M 0x00000090 + +/* Translation fields */ +#define PPC44x_TLB_RPN_MASK 0xfffffc00 /* Real Page Number */ +#define PPC44x_TLB_ERPN_MASK 0x0000000f + +/* Storage attribute and access control fields */ +#define PPC44x_TLB_ATTR_MASK 0x0000ff80 +#define PPC44x_TLB_U0 0x00008000 /* User 0 */ +#define PPC44x_TLB_U1 0x00004000 /* User 1 */ +#define PPC44x_TLB_U2 0x00002000 /* User 2 */ +#define PPC44x_TLB_U3 0x00001000 /* User 3 */ +#define PPC44x_TLB_W 0x00000800 /* Caching is write-through */ +#define PPC44x_TLB_I 0x00000400 /* Caching is inhibited */ +#define PPC44x_TLB_M 0x00000200 /* Memory is coherent */ +#define PPC44x_TLB_G 0x00000100 /* Memory is guarded */ +#define PPC44x_TLB_E 0x00000080 /* Memory is little endian */ + +#define PPC44x_TLB_PERM_MASK 0x0000003f +#define PPC44x_TLB_UX 0x00000020 /* User execution */ +#define PPC44x_TLB_UW 0x00000010 /* User write */ +#define PPC44x_TLB_UR 0x00000008 /* User read */ +#define PPC44x_TLB_SX 0x00000004 /* Super execution */ +#define PPC44x_TLB_SW 0x00000002 /* Super write */ +#define PPC44x_TLB_SR 0x00000001 /* Super read */ + +/* Number of TLB entries */ +#define PPC44x_TLB_SIZE 64 + +/* 47x bits */ +#define PPC47x_MMUCR_TID 0x0000ffff +#define PPC47x_MMUCR_STS 0x00010000 + +/* Page identification fields */ +#define PPC47x_TLB0_EPN_MASK 0xfffff000 /* Effective Page Number */ +#define PPC47x_TLB0_VALID 0x00000800 /* Valid flag */ +#define PPC47x_TLB0_TS 0x00000400 /* Translation address space */ +#define PPC47x_TLB0_4K 0x00000000 +#define PPC47x_TLB0_16K 0x00000010 +#define PPC47x_TLB0_64K 0x00000030 +#define PPC47x_TLB0_1M 0x00000070 +#define PPC47x_TLB0_16M 0x000000f0 +#define PPC47x_TLB0_256M 0x000001f0 +#define PPC47x_TLB0_1G 0x000003f0 +#define PPC47x_TLB0_BOLTED_R 0x00000008 /* tlbre only */ + +/* Translation fields */ +#define PPC47x_TLB1_RPN_MASK 0xfffff000 /* Real Page Number */ +#define PPC47x_TLB1_ERPN_MASK 0x000003ff + +/* Storage attribute and access control fields */ +#define PPC47x_TLB2_ATTR_MASK 0x0003ff80 +#define PPC47x_TLB2_IL1I 0x00020000 /* Memory is guarded */ +#define PPC47x_TLB2_IL1D 0x00010000 /* Memory is guarded */ +#define PPC47x_TLB2_U0 0x00008000 /* User 0 */ +#define PPC47x_TLB2_U1 0x00004000 /* User 1 */ +#define PPC47x_TLB2_U2 0x00002000 /* User 2 */ +#define PPC47x_TLB2_U3 0x00001000 /* User 3 */ +#define PPC47x_TLB2_W 0x00000800 /* Caching is write-through */ +#define PPC47x_TLB2_I 0x00000400 /* Caching is inhibited */ +#define PPC47x_TLB2_M 0x00000200 /* Memory is coherent */ +#define PPC47x_TLB2_G 0x00000100 /* Memory is guarded */ +#define PPC47x_TLB2_E 0x00000080 /* Memory is little endian */ +#define PPC47x_TLB2_PERM_MASK 0x0000003f +#define PPC47x_TLB2_UX 0x00000020 /* User execution */ +#define PPC47x_TLB2_UW 0x00000010 /* User write */ +#define PPC47x_TLB2_UR 0x00000008 /* User read */ +#define PPC47x_TLB2_SX 0x00000004 /* Super execution */ +#define PPC47x_TLB2_SW 0x00000002 /* Super write */ +#define PPC47x_TLB2_SR 0x00000001 /* Super read */ +#define PPC47x_TLB2_U_RWX (PPC47x_TLB2_UX|PPC47x_TLB2_UW|PPC47x_TLB2_UR) +#define PPC47x_TLB2_S_RWX (PPC47x_TLB2_SX|PPC47x_TLB2_SW|PPC47x_TLB2_SR) +#define PPC47x_TLB2_S_RW (PPC47x_TLB2_SW | PPC47x_TLB2_SR) +#define PPC47x_TLB2_IMG (PPC47x_TLB2_I | PPC47x_TLB2_M | PPC47x_TLB2_G) + +#ifndef __ASSEMBLY__ + +extern unsigned int tlb_44x_hwater; +extern unsigned int tlb_44x_index; + +typedef struct { + unsigned int id; + unsigned int active; + unsigned long vdso_base; +} mm_context_t; + +/* patch sites */ +extern s32 patch__tlb_44x_hwater_D, patch__tlb_44x_hwater_I; + +#endif /* !__ASSEMBLY__ */ + +#ifndef CONFIG_PPC_EARLY_DEBUG_44x +#define PPC44x_EARLY_TLBS 1 +#else +#define PPC44x_EARLY_TLBS 2 +#define PPC44x_EARLY_DEBUG_VIRTADDR (ASM_CONST(0xf0000000) \ + | (ASM_CONST(CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW) & 0xffff)) +#endif + +/* Size of the TLBs used for pinning in lowmem */ +#define PPC_PIN_SIZE (1 << 28) /* 256M */ + +#if defined(CONFIG_PPC_4K_PAGES) +#define PPC44x_TLBE_SIZE PPC44x_TLB_4K +#define PPC47x_TLBE_SIZE PPC47x_TLB0_4K +#define mmu_virtual_psize MMU_PAGE_4K +#elif defined(CONFIG_PPC_16K_PAGES) +#define PPC44x_TLBE_SIZE PPC44x_TLB_16K +#define PPC47x_TLBE_SIZE PPC47x_TLB0_16K +#define mmu_virtual_psize MMU_PAGE_16K +#elif defined(CONFIG_PPC_64K_PAGES) +#define PPC44x_TLBE_SIZE PPC44x_TLB_64K +#define PPC47x_TLBE_SIZE PPC47x_TLB0_64K +#define mmu_virtual_psize MMU_PAGE_64K +#elif defined(CONFIG_PPC_256K_PAGES) +#define PPC44x_TLBE_SIZE PPC44x_TLB_256K +#define mmu_virtual_psize MMU_PAGE_256K +#else +#error "Unsupported PAGE_SIZE" +#endif + +#define mmu_linear_psize MMU_PAGE_256M + +#define PPC44x_PGD_OFF_SHIFT (32 - PGDIR_SHIFT + PGD_T_LOG2) +#define PPC44x_PGD_OFF_MASK_BIT (PGDIR_SHIFT - PGD_T_LOG2) +#define PPC44x_PTE_ADD_SHIFT (32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2) +#define PPC44x_PTE_ADD_MASK_BIT (32 - PTE_T_LOG2 - PTE_SHIFT) + +#endif /* _ASM_POWERPC_MMU_44X_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h @@ -0,0 +1,257 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_MMU_8XX_H_ +#define _ASM_POWERPC_MMU_8XX_H_ +/* + * PPC8xx support + */ + +/* Control/status registers for the MPC8xx. + * A write operation to these registers causes serialized access. + * During software tablewalk, the registers used perform mask/shift-add + * operations when written/read. A TLB entry is created when the Mx_RPN + * is written, and the contents of several registers are used to + * create the entry. + */ +#define SPRN_MI_CTR 784 /* Instruction TLB control register */ +#define MI_GPM 0x80000000 /* Set domain manager mode */ +#define MI_PPM 0x40000000 /* Set subpage protection */ +#define MI_CIDEF 0x20000000 /* Set cache inhibit when MMU dis */ +#define MI_RSV4I 0x08000000 /* Reserve 4 TLB entries */ +#define MI_PPCS 0x02000000 /* Use MI_RPN prob/priv state */ +#define MI_IDXMASK 0x00001f00 /* TLB index to be loaded */ +#define MI_RESETVAL 0x00000000 /* Value of register at reset */ + +/* These are the Ks and Kp from the PowerPC books. For proper operation, + * Ks = 0, Kp = 1. + */ +#define SPRN_MI_AP 786 +#define MI_Ks 0x80000000 /* Should not be set */ +#define MI_Kp 0x40000000 /* Should always be set */ + +/* + * All pages' PP data bits are set to either 001 or 011 by copying _PAGE_EXEC + * into bit 21 in the ITLBmiss handler (bit 21 is the middle bit), which means + * respectively NA for All or X for Supervisor and no access for User. + * Then we use the APG to say whether accesses are according to Page rules or + * "all Supervisor" rules (Access to all) + * Therefore, we define 2 APG groups. lsb is _PMD_USER + * 0 => No user => 01 (all accesses performed according to page definition) + * 1 => User => 00 (all accesses performed as supervisor iaw page definition) + * We define all 16 groups so that all other bits of APG can take any value + */ +#define MI_APG_INIT 0x44444444 + +/* The effective page number register. When read, contains the information + * about the last instruction TLB miss. When MI_RPN is written, bits in + * this register are used to create the TLB entry. + */ +#define SPRN_MI_EPN 787 +#define MI_EPNMASK 0xfffff000 /* Effective page number for entry */ +#define MI_EVALID 0x00000200 /* Entry is valid */ +#define MI_ASIDMASK 0x0000000f /* ASID match value */ + /* Reset value is undefined */ + +/* A "level 1" or "segment" or whatever you want to call it register. + * For the instruction TLB, it contains bits that get loaded into the + * TLB entry when the MI_RPN is written. + */ +#define SPRN_MI_TWC 789 +#define MI_APG 0x000001e0 /* Access protection group (0) */ +#define MI_GUARDED 0x00000010 /* Guarded storage */ +#define MI_PSMASK 0x0000000c /* Mask of page size bits */ +#define MI_PS8MEG 0x0000000c /* 8M page size */ +#define MI_PS512K 0x00000004 /* 512K page size */ +#define MI_PS4K_16K 0x00000000 /* 4K or 16K page size */ +#define MI_SVALID 0x00000001 /* Segment entry is valid */ + /* Reset value is undefined */ + +/* Real page number. Defined by the pte. Writing this register + * causes a TLB entry to be created for the instruction TLB, using + * additional information from the MI_EPN, and MI_TWC registers. + */ +#define SPRN_MI_RPN 790 +#define MI_SPS16K 0x00000008 /* Small page size (0 = 4k, 1 = 16k) */ + +/* Define an RPN value for mapping kernel memory to large virtual + * pages for boot initialization. This has real page number of 0, + * large page size, shared page, cache enabled, and valid. + * Also mark all subpages valid and write access. + */ +#define MI_BOOTINIT 0x000001fd + +#define SPRN_MD_CTR 792 /* Data TLB control register */ +#define MD_GPM 0x80000000 /* Set domain manager mode */ +#define MD_PPM 0x40000000 /* Set subpage protection */ +#define MD_CIDEF 0x20000000 /* Set cache inhibit when MMU dis */ +#define MD_WTDEF 0x10000000 /* Set writethrough when MMU dis */ +#define MD_RSV4I 0x08000000 /* Reserve 4 TLB entries */ +#define MD_TWAM 0x04000000 /* Use 4K page hardware assist */ +#define MD_PPCS 0x02000000 /* Use MI_RPN prob/priv state */ +#define MD_IDXMASK 0x00001f00 /* TLB index to be loaded */ +#define MD_RESETVAL 0x04000000 /* Value of register at reset */ + +#define SPRN_M_CASID 793 /* Address space ID (context) to match */ +#define MC_ASIDMASK 0x0000000f /* Bits used for ASID value */ + + +/* These are the Ks and Kp from the PowerPC books. For proper operation, + * Ks = 0, Kp = 1. + */ +#define SPRN_MD_AP 794 +#define MD_Ks 0x80000000 /* Should not be set */ +#define MD_Kp 0x40000000 /* Should always be set */ + +/* + * All pages' PP data bits are set to either 000 or 011 or 001, which means + * respectively RW for Supervisor and no access for User, or RO for + * Supervisor and no access for user and NA for ALL. + * Then we use the APG to say whether accesses are according to Page rules or + * "all Supervisor" rules (Access to all) + * Therefore, we define 2 APG groups. lsb is _PMD_USER + * 0 => No user => 01 (all accesses performed according to page definition) + * 1 => User => 00 (all accesses performed as supervisor iaw page definition) + * We define all 16 groups so that all other bits of APG can take any value + */ +#define MD_APG_INIT 0x44444444 + +/* The effective page number register. When read, contains the information + * about the last instruction TLB miss. When MD_RPN is written, bits in + * this register are used to create the TLB entry. + */ +#define SPRN_MD_EPN 795 +#define MD_EPNMASK 0xfffff000 /* Effective page number for entry */ +#define MD_EVALID 0x00000200 /* Entry is valid */ +#define MD_ASIDMASK 0x0000000f /* ASID match value */ + /* Reset value is undefined */ + +/* The pointer to the base address of the first level page table. + * During a software tablewalk, reading this register provides the address + * of the entry associated with MD_EPN. + */ +#define SPRN_M_TWB 796 +#define M_L1TB 0xfffff000 /* Level 1 table base address */ +#define M_L1INDX 0x00000ffc /* Level 1 index, when read */ + /* Reset value is undefined */ + +/* A "level 1" or "segment" or whatever you want to call it register. + * For the data TLB, it contains bits that get loaded into the TLB entry + * when the MD_RPN is written. It is also provides the hardware assist + * for finding the PTE address during software tablewalk. + */ +#define SPRN_MD_TWC 797 +#define MD_L2TB 0xfffff000 /* Level 2 table base address */ +#define MD_L2INDX 0xfffffe00 /* Level 2 index (*pte), when read */ +#define MD_APG 0x000001e0 /* Access protection group (0) */ +#define MD_GUARDED 0x00000010 /* Guarded storage */ +#define MD_PSMASK 0x0000000c /* Mask of page size bits */ +#define MD_PS8MEG 0x0000000c /* 8M page size */ +#define MD_PS512K 0x00000004 /* 512K page size */ +#define MD_PS4K_16K 0x00000000 /* 4K or 16K page size */ +#define MD_WT 0x00000002 /* Use writethrough page attribute */ +#define MD_SVALID 0x00000001 /* Segment entry is valid */ + /* Reset value is undefined */ + + +/* Real page number. Defined by the pte. Writing this register + * causes a TLB entry to be created for the data TLB, using + * additional information from the MD_EPN, and MD_TWC registers. + */ +#define SPRN_MD_RPN 798 +#define MD_SPS16K 0x00000008 /* Small page size (0 = 4k, 1 = 16k) */ + +/* This is a temporary storage register that could be used to save + * a processor working register during a tablewalk. + */ +#define SPRN_M_TW 799 + +#ifdef CONFIG_PPC_MM_SLICES +#include <asm/nohash/32/slice.h> +#define SLICE_ARRAY_SIZE (1 << (32 - SLICE_LOW_SHIFT - 1)) +#endif + +#ifndef __ASSEMBLY__ +struct slice_mask { + u64 low_slices; + DECLARE_BITMAP(high_slices, 0); +}; + +typedef struct { + unsigned int id; + unsigned int active; + unsigned long vdso_base; +#ifdef CONFIG_PPC_MM_SLICES + u16 user_psize; /* page size index */ + unsigned char low_slices_psize[SLICE_ARRAY_SIZE]; + unsigned char high_slices_psize[0]; + unsigned long slb_addr_limit; + struct slice_mask mask_base_psize; /* 4k or 16k */ +# ifdef CONFIG_HUGETLB_PAGE + struct slice_mask mask_512k; + struct slice_mask mask_8m; +# endif +#endif + void *pte_frag; +} mm_context_t; + +#define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000) +#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE)) + +/* Page size definitions, common between 32 and 64-bit + * + * shift : is the "PAGE_SHIFT" value for that page size + * penc : is the pte encoding mask + * + */ +struct mmu_psize_def { + unsigned int shift; /* number of bits */ + unsigned int enc; /* PTE encoding */ + unsigned int ind; /* Corresponding indirect page size shift */ + unsigned int flags; +#define MMU_PAGE_SIZE_DIRECT 0x1 /* Supported as a direct size */ +#define MMU_PAGE_SIZE_INDIRECT 0x2 /* Supported as an indirect size */ +}; + +extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; + +static inline int shift_to_mmu_psize(unsigned int shift) +{ + int psize; + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) + if (mmu_psize_defs[psize].shift == shift) + return psize; + return -1; +} + +static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) +{ + if (mmu_psize_defs[mmu_psize].shift) + return mmu_psize_defs[mmu_psize].shift; + BUG(); +} + +/* patch sites */ +extern s32 patch__itlbmiss_linmem_top; +extern s32 patch__dtlbmiss_linmem_top, patch__dtlbmiss_immr_jmp; +extern s32 patch__fixupdar_linmem_top; + +extern s32 patch__itlbmiss_exit_1, patch__itlbmiss_exit_2; +extern s32 patch__dtlbmiss_exit_1, patch__dtlbmiss_exit_2, patch__dtlbmiss_exit_3; +extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf; + +#endif /* !__ASSEMBLY__ */ + +#if defined(CONFIG_PPC_4K_PAGES) +#define mmu_virtual_psize MMU_PAGE_4K +#elif defined(CONFIG_PPC_16K_PAGES) +#define mmu_virtual_psize MMU_PAGE_16K +#define PTE_FRAG_NR 4 +#define PTE_FRAG_SIZE_SHIFT 12 +#define PTE_FRAG_SIZE (1UL << 12) +#else +#error "Unsupported PAGE_SIZE" +#endif + +#define mmu_linear_psize MMU_PAGE_8M + +#endif /* _ASM_POWERPC_MMU_8XX_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/mmu.h b/arch/powerpc/include/asm/nohash/32/mmu.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_NOHASH_32_MMU_H_ +#define _ASM_POWERPC_NOHASH_32_MMU_H_ + +#include <asm/page.h> + +#if defined(CONFIG_40x) +/* 40x-style software loaded TLB */ +#include <asm/nohash/32/mmu-40x.h> +#elif defined(CONFIG_44x) +/* 44x-style software loaded TLB */ +#include <asm/nohash/32/mmu-44x.h> +#elif defined(CONFIG_PPC_BOOK3E_MMU) +/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */ +#include <asm/nohash/mmu-book3e.h> +#elif defined (CONFIG_PPC_8xx) +/* Motorola/Freescale 8xx software loaded TLB */ +#include <asm/nohash/32/mmu-8xx.h> +#endif + +#ifndef __ASSEMBLY__ +typedef pte_t *pgtable_t; +#endif + +#endif /* _ASM_POWERPC_NOHASH_32_MMU_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h @@ -25,10 +25,7 @@ extern void __bad_pte(pmd_t *pmd); extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) ({ \ - BUG_ON(!(shift)); \ - pgtable_cache[(shift) - 1]; \ - }) +#define PGT_CACHE(shift) pgtable_cache[shift] static inline pgd_t *pgd_alloc(struct mm_struct *mm) { @@ -61,11 +58,10 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pte_page) { - *pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_USER | - _PMD_PRESENT); + *pmdp = __pmd(__pa(pte_page) | _PMD_USER | _PMD_PRESENT); } -#define pmd_pgtable(pmd) pmd_page(pmd) +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) #else static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, @@ -77,31 +73,32 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pte_page) { - *pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) | _PMD_PRESENT); + *pmdp = __pmd((unsigned long)pte_page | _PMD_PRESENT); } -#define pmd_pgtable(pmd) pmd_page(pmd) +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) #endif extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr); extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr); +void pte_frag_destroy(void *pte_frag); +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel); +void pte_fragment_free(unsigned long *table, int kernel); static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - free_page((unsigned long)pte); + pte_fragment_free((unsigned long *)pte, 1); } static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) { - pgtable_page_dtor(ptepage); - __free_page(ptepage); + pte_fragment_free((unsigned long *)ptepage, 0); } static inline void pgtable_free(void *table, unsigned index_size) { if (!index_size) { - pgtable_page_dtor(virt_to_page(table)); - free_page((unsigned long)table); + pte_fragment_free((unsigned long *)table, 0); } else { BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE); kmem_cache_free(PGT_CACHE(index_size), table); @@ -140,6 +137,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { tlb_flush_pgtable(tlb, address); - pgtable_free_tlb(tlb, page_address(table), 0); + pgtable_free_tlb(tlb, table, 0); } #endif /* _ASM_POWERPC_PGALLOC_32_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -232,7 +232,13 @@ static inline unsigned long pte_update(pte_t *p, : "cc" ); #else /* PTE_ATOMIC_UPDATES */ unsigned long old = pte_val(*p); - *p = __pte((old & ~clr) | set); + unsigned long new = (old & ~clr) | set; + +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) + p->pte = p->pte1 = p->pte2 = p->pte3 = new; +#else + *p = __pte(new); +#endif #endif /* !PTE_ATOMIC_UPDATES */ #ifdef CONFIG_44x @@ -333,12 +339,12 @@ static inline int pte_young(pte_t pte) */ #ifndef CONFIG_BOOKE #define pmd_page_vaddr(pmd) \ - ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) + ((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) #define pmd_page(pmd) \ pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) #else #define pmd_page_vaddr(pmd) \ - ((unsigned long) (pmd_val(pmd) & PAGE_MASK)) + ((unsigned long)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) #define pmd_page(pmd) \ pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT)) #endif @@ -357,7 +363,8 @@ static inline int pte_young(pte_t pte) (pmd_bad(*(dir)) ? NULL : (pte_t *)pmd_page_vaddr(*(dir)) + \ pte_index(addr)) #define pte_offset_map(dir, addr) \ - ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr)) + ((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \ + (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr)) #define pte_unmap(pte) kunmap_atomic(pte) /* diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -33,7 +33,7 @@ * is cleared in the TLB miss handler before the TLB entry is loaded. * - All other bits of the PTE are loaded into TLBLO without * modification, leaving us only the bits 20, 21, 24, 25, 26, 30 for - * software PTE bits. We actually use use bits 21, 24, 25, and + * software PTE bits. We actually use bits 21, 24, 25, and * 30 respectively for the software bits: ACCESSED, DIRTY, RW, and * PRESENT. */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -65,9 +65,6 @@ #define _PTE_NONE_MASK 0 -/* Until my rework is finished, 8xx still needs atomic PTE updates */ -#define PTE_ATOMIC_UPDATES 1 - #ifdef CONFIG_PPC_16K_PAGES #define _PAGE_PSIZE _PAGE_SPS #else diff --git a/arch/powerpc/include/asm/nohash/64/mmu.h b/arch/powerpc/include/asm/nohash/64/mmu.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_NOHASH_64_MMU_H_ +#define _ASM_POWERPC_NOHASH_64_MMU_H_ + +/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */ +#include <asm/nohash/mmu-book3e.h> + +#ifndef __ASSEMBLY__ +typedef struct page *pgtable_t; +#endif + +#endif /* _ASM_POWERPC_NOHASH_64_MMU_H_ */ diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -36,10 +36,7 @@ extern struct vmemmap_backing *vmemmap_list; #define MAX_PGTABLE_INDEX_SIZE 0xf extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) ({ \ - BUG_ON(!(shift)); \ - pgtable_cache[(shift) - 1]; \ - }) +#define PGT_CACHE(shift) pgtable_cache[shift] static inline pgd_t *pgd_alloc(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/nohash/mmu-book3e.h diff --git a/arch/powerpc/include/asm/nohash/mmu.h b/arch/powerpc/include/asm/nohash/mmu.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_NOHASH_MMU_H_ +#define _ASM_POWERPC_NOHASH_MMU_H_ + +#ifdef CONFIG_PPC64 +#include <asm/nohash/64/mmu.h> +#else +#include <asm/nohash/32/mmu.h> +#endif + +#endif /* _ASM_POWERPC_NOHASH_MMU_H_ */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h @@ -209,7 +209,11 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, /* Anything else just stores the PTE normally. That covers all 64-bit * cases, and 32-bit non-hash with 32-bit PTEs. */ +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) + ptep->pte = ptep->pte1 = ptep->pte2 = ptep->pte3 = pte_val(pte); +#else *ptep = pte; +#endif /* * With hardware tablewalk, a sync is needed to ensure that diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h @@ -347,6 +347,7 @@ extern int opal_async_comp_init(void); extern int opal_sensor_init(void); extern int opal_hmi_handler_init(void); extern int opal_event_init(void); +int opal_power_control_init(void); extern int opal_machine_check(struct pt_regs *regs); extern bool opal_mce_check_early_recovery(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h @@ -289,7 +289,7 @@ static inline bool pfn_valid(unsigned long pfn) * page tables at arbitrary addresses, this breaks and will have to change. */ #ifdef CONFIG_PPC64 -#define PD_HUGE 0x8000000000000000 +#define PD_HUGE 0x8000000000000000UL #else #define PD_HUGE 0x80000000 #endif @@ -335,23 +335,11 @@ void arch_free_page(struct page *page, int order); #endif struct vm_area_struct; -#ifdef CONFIG_PPC_BOOK3S_64 -/* - * For BOOK3s 64 with 4k and 64K linux page size - * we want to use pointers, because the page table - * actually store pfn - */ -typedef pte_t *pgtable_t; -#else -#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC64) -typedef pte_t *pgtable_t; -#else -typedef struct page *pgtable_t; -#endif -#endif #include <asm-generic/memory_model.h> #endif /* __ASSEMBLY__ */ #include <asm/slice.h> +#define ARCH_ZONE_DMA_BITS 31 + #endif /* _ASM_POWERPC_PAGE_H */ diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h @@ -22,7 +22,8 @@ #define PTE_FLAGS_OFFSET 0 #endif -#ifdef CONFIG_PPC_256K_PAGES +#if defined(CONFIG_PPC_256K_PAGES) || \ + (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)) #define PTE_SHIFT (PAGE_SHIFT - PTE_T_LOG2 - 2) /* 1/4 of a page */ #else #define PTE_SHIFT (PAGE_SHIFT - PTE_T_LOG2) /* full page */ diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h @@ -129,6 +129,7 @@ struct pci_controller { #endif /* CONFIG_PPC64 */ void *private_data; + struct npu *npu; }; /* These are used for config access before all the PCI probing diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h @@ -129,5 +129,9 @@ extern void pcibios_scan_phb(struct pci_controller *hose); extern struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev); extern struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index); +extern int pnv_npu2_init(struct pci_controller *hose); +extern int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid, + unsigned long msr); +extern int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev); #endif /* __ASM_POWERPC_PCI_H */ diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h @@ -39,4 +39,7 @@ (regs)->gpr[1] = current_stack_pointer(); \ asm volatile("mfmsr %0" : "=r" ((regs)->msr)); \ } while (0) + +/* To support perf_regs sier update */ +extern bool is_sier_available(void); #endif diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h @@ -41,6 +41,8 @@ struct power_pmu { void (*get_mem_data_src)(union perf_mem_data_src *dsrc, u32 flags, struct pt_regs *regs); void (*get_mem_weight)(u64 *weight); + unsigned long group_constraint_mask; + unsigned long group_constraint_val; u64 (*bhrb_filter_map)(u64 branch_sample_type); void (*config_bhrb)(u64 pmu_bhrb_filter); void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h @@ -3,7 +3,11 @@ #define _ASM_POWERPC_PGTABLE_TYPES_H /* PTE level */ +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) +typedef struct { pte_basic_t pte, pte1, pte2, pte3; } pte_t; +#else typedef struct { pte_basic_t pte; } pte_t; +#endif #define __pte(x) ((pte_t) { (x) }) static inline pte_basic_t pte_val(pte_t x) { diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h @@ -66,7 +66,6 @@ extern unsigned long empty_zero_page[]; extern pgd_t swapper_pg_dir[]; -void limit_zone_pfn(enum zone_type zone, unsigned long max_pfn); int dma_pfn_limit_to_zone(u64 pfn_limit); extern void paging_init(void); @@ -101,7 +100,7 @@ extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, /* can we use this in kvm */ unsigned long vmalloc_to_phys(void *vmalloc_addr); -void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); +void pgtable_cache_add(unsigned int shift); void pgtable_cache_init(void); #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32) @@ -110,6 +109,35 @@ void mark_initmem_nx(void); static inline void mark_initmem_nx(void) { } #endif +/* + * When used, PTE_FRAG_NR is defined in subarch pgtable.h + * so we are sure it is included when arriving here. + */ +#ifdef PTE_FRAG_NR +static inline void *pte_frag_get(mm_context_t *ctx) +{ + return ctx->pte_frag; +} + +static inline void pte_frag_set(mm_context_t *ctx, void *p) +{ + ctx->pte_frag = p; +} +#else +#define PTE_FRAG_NR 1 +#define PTE_FRAG_SIZE_SHIFT PAGE_SHIFT +#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) + +static inline void *pte_frag_get(mm_context_t *ctx) +{ + return NULL; +} + +static inline void pte_frag_set(mm_context_t *ctx, void *p) +{ +} +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h @@ -257,6 +257,7 @@ #define PPC_INST_MTSPR_DSCR_USER_MASK 0xfc1ffffe #define PPC_INST_MFVSRD 0x7c000066 #define PPC_INST_MTVSRD 0x7c000166 +#define PPC_INST_SC 0x44000002 #define PPC_INST_SLBFEE 0x7c0007a7 #define PPC_INST_SLBIA 0x7c0003e4 diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h @@ -480,26 +480,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) ori rd,rd,((KERNELBASE>>48)&0xFFFF);\ rotldi rd,rd,48 #else -/* - * On APUS (Amiga PowerPC cpu upgrade board), we don't know the - * physical base address of RAM at compile time. - */ #define toreal(rd) tophys(rd,rd) #define fromreal(rd) tovirt(rd,rd) -#define tophys(rd,rs) \ -0: addis rd,rs,-PAGE_OFFSET@h; \ - .section ".vtop_fixup","aw"; \ - .align 1; \ - .long 0b; \ - .previous - -#define tovirt(rd,rs) \ -0: addis rd,rs,PAGE_OFFSET@h; \ - .section ".ptov_fixup","aw"; \ - .align 1; \ - .long 0b; \ - .previous +#define tophys(rd, rs) addis rd, rs, -PAGE_OFFSET@h +#define tovirt(rd, rs) addis rd, rs, PAGE_OFFSET@h #endif #ifdef CONFIG_PPC_BOOK3S_64 @@ -821,4 +806,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) stringify_in_c(.long (_target) - . ;) \ stringify_in_c(.previous) +#ifdef CONFIG_PPC_FSL_BOOK3E +#define BTB_FLUSH(reg) \ + lis reg,BUCSR_INIT@h; \ + ori reg,reg,BUCSR_INIT@l; \ + mtspr SPRN_BUCSR,reg; \ + isync; +#else +#define BTB_FLUSH(reg) +#endif /* CONFIG_PPC_FSL_BOOK3E */ + #endif /* _ASM_POWERPC_PPC_ASM_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h @@ -582,7 +582,7 @@ #define HID0_POWER9_RADIX __MASK(63 - 8) #define SPRN_HID1 0x3F1 /* Hardware Implementation Register 1 */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 #define HID1_EMCP (1<<31) /* 7450 Machine Check Pin Enable */ #define HID1_DFS (1<<22) /* 7447A Dynamic Frequency Scaling */ #define HID1_PC0 (1<<16) /* 7450 PLL_CFG[0] */ @@ -769,6 +769,8 @@ #define SRR1_PROGTRAP 0x00020000 /* Trap */ #define SRR1_PROGADDR 0x00010000 /* SRR0 contains subsequent addr */ +#define SRR1_MCE_MCP 0x00080000 /* Machine check signal caused interrupt */ + #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */ #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */ #define HSRR1_DENORM 0x00100000 /* Denorm exception */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h @@ -67,6 +67,13 @@ void do_barrier_nospec_fixups_range(bool enable, void *start, void *end); static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; #endif +#ifdef CONFIG_PPC_FSL_BOOK3E +void setup_spectre_v2(void); +#else +static inline void setup_spectre_v2(void) {}; +#endif +void do_btb_flush_fixups(void); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h @@ -213,30 +213,18 @@ * respectively. The result is placed in HIGH_SUM and LOW_SUM. Overflow * (i.e. carry out) is not stored anywhere, and is lost. */ -#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ do { \ if (__builtin_constant_p (bh) && (bh) == 0) \ - __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ - else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0) \ - __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ + __asm__ ("add%I4c %1,%3,%4\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \ + __asm__ ("add%I4c %1,%3,%4\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ else \ - __asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "r" ((USItype)(bh)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ + __asm__ ("add%I5c %1,%4,%5\n\tadde %0,%2,%3" \ + : "=r" (sh), "=&r" (sl) \ + : "%r" (ah), "r" (bh), "%r" (al), "rI" (bl)); \ } while (0) /* sub_ddmmss is used in op-2.h and udivmodti4.c and should be equivalent to @@ -248,44 +236,24 @@ * and LOW_DIFFERENCE. Overflow (i.e. carry out) is not stored anywhere, * and is lost. */ -#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ do { \ if (__builtin_constant_p (ah) && (ah) == 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ - else if (__builtin_constant_p (ah) && (ah) ==~(USItype) 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (ah) && (ah) == ~(USItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ else if (__builtin_constant_p (bh) && (bh) == 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ - else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I3c %1,%4,%3\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ else \ - __asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I4c %1,%5,%4\n\tsubfe %0,%3,%2" \ + : "=r" (sh), "=&r" (sl) \ + : "r" (ah), "r" (bh), "rI" (al), "r" (bl)); \ } while (0) /* asm fragments for mul and div */ @@ -294,13 +262,10 @@ * UWtype integers MULTIPLER and MULTIPLICAND, and generates a two UWtype * word product in HIGH_PROD and LOW_PROD. */ -#define umul_ppmm(ph, pl, m0, m1) \ +#define umul_ppmm(ph, pl, m0, m1) \ do { \ USItype __m0 = (m0), __m1 = (m1); \ - __asm__ ("mulhwu %0,%1,%2" \ - : "=r" ((USItype)(ph)) \ - : "%r" (__m0), \ - "r" (__m1)); \ + __asm__ ("mulhwu %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1)); \ (pl) = __m0 * __m1; \ } while (0) @@ -312,9 +277,10 @@ * significant bit of DENOMINATOR must be 1, then the pre-processor symbol * UDIV_NEEDS_NORMALIZATION is defined to 1. */ -#define udiv_qrnnd(q, r, n1, n0, d) \ +#define udiv_qrnnd(q, r, n1, n0, d) \ do { \ - UWtype __d1, __d0, __q1, __q0, __r1, __r0, __m; \ + UWtype __d1, __d0, __q1, __q0; \ + UWtype __r1, __r0, __m; \ __d1 = __ll_highpart (d); \ __d0 = __ll_lowpart (d); \ \ @@ -325,7 +291,7 @@ if (__r1 < __m) \ { \ __q1--, __r1 += (d); \ - if (__r1 >= (d)) /* we didn't get carry when adding to __r1 */ \ + if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\ if (__r1 < __m) \ __q1--, __r1 += (d); \ } \ diff --git a/arch/powerpc/include/asm/slice.h b/arch/powerpc/include/asm/slice.h @@ -10,6 +10,10 @@ #include <asm/nohash/32/slice.h> #endif +#ifndef __ASSEMBLY__ + +struct mm_struct; + #ifdef CONFIG_PPC_MM_SLICES #ifdef CONFIG_HUGETLB_PAGE @@ -18,10 +22,6 @@ #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -#ifndef __ASSEMBLY__ - -struct mm_struct; - unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, unsigned long flags, unsigned int psize, int topdown); @@ -34,8 +34,12 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start, void slice_init_new_context_exec(struct mm_struct *mm); void slice_setup_new_exec(void); -#endif /* __ASSEMBLY__ */ +#else /* CONFIG_PPC_MM_SLICES */ + +static inline void slice_init_new_context_exec(struct mm_struct *mm) {} #endif /* CONFIG_PPC_MM_SLICES */ +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_POWERPC_SLICE_H */ diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h @@ -18,9 +18,8 @@ #include <linux/thread_info.h> /* ftrace syscalls requires exporting the sys_call_table */ -#ifdef CONFIG_FTRACE_SYSCALLS extern const unsigned long sys_call_table[]; -#endif /* CONFIG_FTRACE_SYSCALLS */ +extern const unsigned long compat_sys_call_table[]; static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h @@ -1,396 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * List of powerpc syscalls. For the meaning of the _SPU suffix see - * arch/powerpc/platforms/cell/spu_callbacks.c - */ - -SYSCALL(restart_syscall) -SYSCALL(exit) -PPC_SYS(fork) -SYSCALL_SPU(read) -SYSCALL_SPU(write) -COMPAT_SYS_SPU(open) -SYSCALL_SPU(close) -SYSCALL_SPU(waitpid) -SYSCALL_SPU(creat) -SYSCALL_SPU(link) -SYSCALL_SPU(unlink) -COMPAT_SYS(execve) -SYSCALL_SPU(chdir) -COMPAT_SYS_SPU(time) -SYSCALL_SPU(mknod) -SYSCALL_SPU(chmod) -SYSCALL_SPU(lchown) -SYSCALL(ni_syscall) -OLDSYS(stat) -COMPAT_SYS_SPU(lseek) -SYSCALL_SPU(getpid) -COMPAT_SYS(mount) -SYSX(sys_ni_syscall,sys_oldumount,sys_oldumount) -SYSCALL_SPU(setuid) -SYSCALL_SPU(getuid) -COMPAT_SYS_SPU(stime) -COMPAT_SYS(ptrace) -SYSCALL_SPU(alarm) -OLDSYS(fstat) -SYSCALL(pause) -COMPAT_SYS(utime) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL_SPU(access) -SYSCALL_SPU(nice) -SYSCALL(ni_syscall) -SYSCALL_SPU(sync) -SYSCALL_SPU(kill) -SYSCALL_SPU(rename) -SYSCALL_SPU(mkdir) -SYSCALL_SPU(rmdir) -SYSCALL_SPU(dup) -SYSCALL_SPU(pipe) -COMPAT_SYS_SPU(times) -SYSCALL(ni_syscall) -SYSCALL_SPU(brk) -SYSCALL_SPU(setgid) -SYSCALL_SPU(getgid) -SYSCALL(signal) -SYSCALL_SPU(geteuid) -SYSCALL_SPU(getegid) -SYSCALL(acct) -SYSCALL(umount) -SYSCALL(ni_syscall) -COMPAT_SYS_SPU(ioctl) -COMPAT_SYS_SPU(fcntl) -SYSCALL(ni_syscall) -SYSCALL_SPU(setpgid) -SYSCALL(ni_syscall) -SYSX(sys_ni_syscall,sys_olduname,sys_olduname) -SYSCALL_SPU(umask) -SYSCALL_SPU(chroot) -COMPAT_SYS(ustat) -SYSCALL_SPU(dup2) -SYSCALL_SPU(getppid) -SYSCALL_SPU(getpgrp) -SYSCALL_SPU(setsid) -SYS32ONLY(sigaction) -SYSCALL_SPU(sgetmask) -SYSCALL_SPU(ssetmask) -SYSCALL_SPU(setreuid) -SYSCALL_SPU(setregid) -#define compat_sys_sigsuspend sys_sigsuspend -SYS32ONLY(sigsuspend) -SYSX(sys_ni_syscall,compat_sys_sigpending,sys_sigpending) -SYSCALL_SPU(sethostname) -COMPAT_SYS_SPU(setrlimit) -SYSX(sys_ni_syscall,compat_sys_old_getrlimit,sys_old_getrlimit) -COMPAT_SYS_SPU(getrusage) -COMPAT_SYS_SPU(gettimeofday) -COMPAT_SYS_SPU(settimeofday) -SYSCALL_SPU(getgroups) -SYSCALL_SPU(setgroups) -SYSX(sys_ni_syscall,sys_ni_syscall,ppc_select) -SYSCALL_SPU(symlink) -OLDSYS(lstat) -SYSCALL_SPU(readlink) -SYSCALL(uselib) -SYSCALL(swapon) -SYSCALL(reboot) -SYSX(sys_ni_syscall,compat_sys_old_readdir,sys_old_readdir) -SYSCALL_SPU(mmap) -SYSCALL_SPU(munmap) -COMPAT_SYS_SPU(truncate) -COMPAT_SYS_SPU(ftruncate) -SYSCALL_SPU(fchmod) -SYSCALL_SPU(fchown) -SYSCALL_SPU(getpriority) -SYSCALL_SPU(setpriority) -SYSCALL(ni_syscall) -COMPAT_SYS(statfs) -COMPAT_SYS(fstatfs) -SYSCALL(ni_syscall) -COMPAT_SYS_SPU(socketcall) -SYSCALL_SPU(syslog) -COMPAT_SYS_SPU(setitimer) -COMPAT_SYS_SPU(getitimer) -COMPAT_SYS_SPU(newstat) -COMPAT_SYS_SPU(newlstat) -COMPAT_SYS_SPU(newfstat) -SYSX(sys_ni_syscall,sys_uname,sys_uname) -SYSCALL(ni_syscall) -SYSCALL_SPU(vhangup) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -COMPAT_SYS_SPU(wait4) -SYSCALL(swapoff) -COMPAT_SYS_SPU(sysinfo) -COMPAT_SYS(ipc) -SYSCALL_SPU(fsync) -SYS32ONLY(sigreturn) -PPC_SYS(clone) -SYSCALL_SPU(setdomainname) -SYSCALL_SPU(newuname) -SYSCALL(ni_syscall) -COMPAT_SYS_SPU(adjtimex) -SYSCALL_SPU(mprotect) -SYSX(sys_ni_syscall,compat_sys_sigprocmask,sys_sigprocmask) -SYSCALL(ni_syscall) -SYSCALL(init_module) -SYSCALL(delete_module) -SYSCALL(ni_syscall) -SYSCALL(quotactl) -SYSCALL_SPU(getpgid) -SYSCALL_SPU(fchdir) -SYSCALL_SPU(bdflush) -SYSCALL_SPU(sysfs) -SYSX_SPU(ppc64_personality,ppc64_personality,sys_personality) -SYSCALL(ni_syscall) -SYSCALL_SPU(setfsuid) -SYSCALL_SPU(setfsgid) -SYSCALL_SPU(llseek) -COMPAT_SYS_SPU(getdents) -COMPAT_SPU_NEW(select) -SYSCALL_SPU(flock) -SYSCALL_SPU(msync) -COMPAT_SYS_SPU(readv) -COMPAT_SYS_SPU(writev) -SYSCALL_SPU(getsid) -SYSCALL_SPU(fdatasync) -COMPAT_SYS(sysctl) -SYSCALL_SPU(mlock) -SYSCALL_SPU(munlock) -SYSCALL_SPU(mlockall) -SYSCALL_SPU(munlockall) -SYSCALL_SPU(sched_setparam) -SYSCALL_SPU(sched_getparam) -SYSCALL_SPU(sched_setscheduler) -SYSCALL_SPU(sched_getscheduler) -SYSCALL_SPU(sched_yield) -SYSCALL_SPU(sched_get_priority_max) -SYSCALL_SPU(sched_get_priority_min) -COMPAT_SYS_SPU(sched_rr_get_interval) -COMPAT_SYS_SPU(nanosleep) -SYSCALL_SPU(mremap) -SYSCALL_SPU(setresuid) -SYSCALL_SPU(getresuid) -SYSCALL(ni_syscall) -SYSCALL_SPU(poll) -SYSCALL(ni_syscall) -SYSCALL_SPU(setresgid) -SYSCALL_SPU(getresgid) -SYSCALL_SPU(prctl) -COMPAT_SYS(rt_sigreturn) -COMPAT_SYS(rt_sigaction) -COMPAT_SYS(rt_sigprocmask) -COMPAT_SYS(rt_sigpending) -COMPAT_SYS(rt_sigtimedwait) -COMPAT_SYS(rt_sigqueueinfo) -COMPAT_SYS(rt_sigsuspend) -COMPAT_SYS_SPU(pread64) -COMPAT_SYS_SPU(pwrite64) -SYSCALL_SPU(chown) -SYSCALL_SPU(getcwd) -SYSCALL_SPU(capget) -SYSCALL_SPU(capset) -COMPAT_SYS(sigaltstack) -SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -PPC_SYS(vfork) -COMPAT_SYS_SPU(getrlimit) -COMPAT_SYS_SPU(readahead) -SYS32ONLY(mmap2) -SYS32ONLY(truncate64) -SYS32ONLY(ftruncate64) -SYSX(sys_ni_syscall,sys_stat64,sys_stat64) -SYSX(sys_ni_syscall,sys_lstat64,sys_lstat64) -SYSX(sys_ni_syscall,sys_fstat64,sys_fstat64) -SYSCALL(pciconfig_read) -SYSCALL(pciconfig_write) -SYSCALL(pciconfig_iobase) -SYSCALL(ni_syscall) -SYSCALL_SPU(getdents64) -SYSCALL_SPU(pivot_root) -SYSX(sys_ni_syscall,compat_sys_fcntl64,sys_fcntl64) -SYSCALL_SPU(madvise) -SYSCALL_SPU(mincore) -SYSCALL_SPU(gettid) -SYSCALL_SPU(tkill) -SYSCALL_SPU(setxattr) -SYSCALL_SPU(lsetxattr) -SYSCALL_SPU(fsetxattr) -SYSCALL_SPU(getxattr) -SYSCALL_SPU(lgetxattr) -SYSCALL_SPU(fgetxattr) -SYSCALL_SPU(listxattr) -SYSCALL_SPU(llistxattr) -SYSCALL_SPU(flistxattr) -SYSCALL_SPU(removexattr) -SYSCALL_SPU(lremovexattr) -SYSCALL_SPU(fremovexattr) -COMPAT_SYS_SPU(futex) -COMPAT_SYS_SPU(sched_setaffinity) -COMPAT_SYS_SPU(sched_getaffinity) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYS32ONLY(sendfile64) -COMPAT_SYS_SPU(io_setup) -SYSCALL_SPU(io_destroy) -COMPAT_SYS_SPU(io_getevents) -COMPAT_SYS_SPU(io_submit) -SYSCALL_SPU(io_cancel) -SYSCALL(set_tid_address) -SYSX_SPU(sys_fadvise64,ppc32_fadvise64,sys_fadvise64) -SYSCALL(exit_group) -COMPAT_SYS(lookup_dcookie) -SYSCALL_SPU(epoll_create) -SYSCALL_SPU(epoll_ctl) -SYSCALL_SPU(epoll_wait) -SYSCALL_SPU(remap_file_pages) -COMPAT_SYS_SPU(timer_create) -COMPAT_SYS_SPU(timer_settime) -COMPAT_SYS_SPU(timer_gettime) -SYSCALL_SPU(timer_getoverrun) -SYSCALL_SPU(timer_delete) -COMPAT_SYS_SPU(clock_settime) -COMPAT_SYS_SPU(clock_gettime) -COMPAT_SYS_SPU(clock_getres) -COMPAT_SYS_SPU(clock_nanosleep) -SYSX(ppc64_swapcontext,ppc32_swapcontext,ppc_swapcontext) -SYSCALL_SPU(tgkill) -COMPAT_SYS_SPU(utimes) -COMPAT_SYS_SPU(statfs64) -COMPAT_SYS_SPU(fstatfs64) -SYSX(sys_ni_syscall,ppc_fadvise64_64,ppc_fadvise64_64) -SYSCALL_SPU(rtas) -OLDSYS(debug_setcontext) -SYSCALL(ni_syscall) -COMPAT_SYS(migrate_pages) -COMPAT_SYS(mbind) -COMPAT_SYS(get_mempolicy) -COMPAT_SYS(set_mempolicy) -COMPAT_SYS(mq_open) -SYSCALL(mq_unlink) -COMPAT_SYS(mq_timedsend) -COMPAT_SYS(mq_timedreceive) -COMPAT_SYS(mq_notify) -COMPAT_SYS(mq_getsetattr) -COMPAT_SYS(kexec_load) -SYSCALL(add_key) -SYSCALL(request_key) -COMPAT_SYS(keyctl) -COMPAT_SYS(waitid) -SYSCALL(ioprio_set) -SYSCALL(ioprio_get) -SYSCALL(inotify_init) -SYSCALL(inotify_add_watch) -SYSCALL(inotify_rm_watch) -SYSCALL(spu_run) -SYSCALL(spu_create) -COMPAT_SYS(pselect6) -COMPAT_SYS(ppoll) -SYSCALL_SPU(unshare) -SYSCALL_SPU(splice) -SYSCALL_SPU(tee) -COMPAT_SYS_SPU(vmsplice) -COMPAT_SYS_SPU(openat) -SYSCALL_SPU(mkdirat) -SYSCALL_SPU(mknodat) -SYSCALL_SPU(fchownat) -COMPAT_SYS_SPU(futimesat) -SYSX_SPU(sys_newfstatat,sys_fstatat64,sys_fstatat64) -SYSCALL_SPU(unlinkat) -SYSCALL_SPU(renameat) -SYSCALL_SPU(linkat) -SYSCALL_SPU(symlinkat) -SYSCALL_SPU(readlinkat) -SYSCALL_SPU(fchmodat) -SYSCALL_SPU(faccessat) -COMPAT_SYS_SPU(get_robust_list) -COMPAT_SYS_SPU(set_robust_list) -COMPAT_SYS_SPU(move_pages) -SYSCALL_SPU(getcpu) -COMPAT_SYS(epoll_pwait) -COMPAT_SYS_SPU(utimensat) -COMPAT_SYS_SPU(signalfd) -SYSCALL_SPU(timerfd_create) -SYSCALL_SPU(eventfd) -COMPAT_SYS_SPU(sync_file_range2) -COMPAT_SYS(fallocate) -SYSCALL(subpage_prot) -COMPAT_SYS_SPU(timerfd_settime) -COMPAT_SYS_SPU(timerfd_gettime) -COMPAT_SYS_SPU(signalfd4) -SYSCALL_SPU(eventfd2) -SYSCALL_SPU(epoll_create1) -SYSCALL_SPU(dup3) -SYSCALL_SPU(pipe2) -SYSCALL(inotify_init1) -SYSCALL_SPU(perf_event_open) -COMPAT_SYS_SPU(preadv) -COMPAT_SYS_SPU(pwritev) -COMPAT_SYS(rt_tgsigqueueinfo) -SYSCALL(fanotify_init) -COMPAT_SYS(fanotify_mark) -SYSCALL_SPU(prlimit64) -SYSCALL_SPU(socket) -SYSCALL_SPU(bind) -SYSCALL_SPU(connect) -SYSCALL_SPU(listen) -SYSCALL_SPU(accept) -SYSCALL_SPU(getsockname) -SYSCALL_SPU(getpeername) -SYSCALL_SPU(socketpair) -SYSCALL_SPU(send) -SYSCALL_SPU(sendto) -COMPAT_SYS_SPU(recv) -COMPAT_SYS_SPU(recvfrom) -SYSCALL_SPU(shutdown) -COMPAT_SYS_SPU(setsockopt) -COMPAT_SYS_SPU(getsockopt) -COMPAT_SYS_SPU(sendmsg) -COMPAT_SYS_SPU(recvmsg) -COMPAT_SYS_SPU(recvmmsg) -SYSCALL_SPU(accept4) -SYSCALL_SPU(name_to_handle_at) -COMPAT_SYS_SPU(open_by_handle_at) -COMPAT_SYS_SPU(clock_adjtime) -SYSCALL_SPU(syncfs) -COMPAT_SYS_SPU(sendmmsg) -SYSCALL_SPU(setns) -COMPAT_SYS(process_vm_readv) -COMPAT_SYS(process_vm_writev) -SYSCALL(finit_module) -SYSCALL(kcmp) /* sys_kcmp */ -SYSCALL_SPU(sched_setattr) -SYSCALL_SPU(sched_getattr) -SYSCALL_SPU(renameat2) -SYSCALL_SPU(seccomp) -SYSCALL_SPU(getrandom) -SYSCALL_SPU(memfd_create) -SYSCALL_SPU(bpf) -COMPAT_SYS(execveat) -PPC64ONLY(switch_endian) -SYSCALL_SPU(userfaultfd) -SYSCALL_SPU(membarrier) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYSCALL(mlock2) -SYSCALL(copy_file_range) -COMPAT_SYS_SPU(preadv2) -COMPAT_SYS_SPU(pwritev2) -SYSCALL(kexec_file_load) -SYSCALL(statx) -SYSCALL(pkey_alloc) -SYSCALL(pkey_free) -SYSCALL(pkey_mprotect) -SYSCALL(rseq) -COMPAT_SYS(io_pgetevents) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h @@ -43,7 +43,7 @@ struct div_result { /* Accessor functions for the timebase (RTC on 601) registers. */ /* If one day CONFIG_POWER is added just define __USE_RTC as 1 */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 #define __USE_RTC() (cpu_has_feature(CPU_FTR_USE_RTC)) #else #define __USE_RTC() 0 diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h @@ -40,7 +40,7 @@ extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address) { -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 if (pte_val(*ptep) & _PAGE_HASHPTE) flush_hash_entry(tlb->mm, ptep, address); #endif diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h @@ -63,7 +63,7 @@ static inline int __access_ok(unsigned long addr, unsigned long size, #endif #define access_ok(type, addr, size) \ - (__chk_user_ptr(addr), \ + (__chk_user_ptr(addr), (void)(type), \ __access_ok((__force unsigned long)(addr), (size), get_fs())) /* diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h @@ -11,8 +11,7 @@ #include <uapi/asm/unistd.h> - -#define NR_syscalls 389 +#define NR_syscalls __NR_syscalls #define __NR__exit __NR_exit diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild @@ -1,6 +1,8 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generated-y += unistd_32.h +generated-y += unistd_64.h generic-y += param.h generic-y += poll.h generic-y += resource.h diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -46,6 +46,7 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_TRAP, PERF_REG_POWERPC_DAR, PERF_REG_POWERPC_DSISR, + PERF_REG_POWERPC_SIER, PERF_REG_POWERPC_MAX, }; #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h @@ -10,395 +10,10 @@ #ifndef _UAPI_ASM_POWERPC_UNISTD_H_ #define _UAPI_ASM_POWERPC_UNISTD_H_ - -#define __NR_restart_syscall 0 -#define __NR_exit 1 -#define __NR_fork 2 -#define __NR_read 3 -#define __NR_write 4 -#define __NR_open 5 -#define __NR_close 6 -#define __NR_waitpid 7 -#define __NR_creat 8 -#define __NR_link 9 -#define __NR_unlink 10 -#define __NR_execve 11 -#define __NR_chdir 12 -#define __NR_time 13 -#define __NR_mknod 14 -#define __NR_chmod 15 -#define __NR_lchown 16 -#define __NR_break 17 -#define __NR_oldstat 18 -#define __NR_lseek 19 -#define __NR_getpid 20 -#define __NR_mount 21 -#define __NR_umount 22 -#define __NR_setuid 23 -#define __NR_getuid 24 -#define __NR_stime 25 -#define __NR_ptrace 26 -#define __NR_alarm 27 -#define __NR_oldfstat 28 -#define __NR_pause 29 -#define __NR_utime 30 -#define __NR_stty 31 -#define __NR_gtty 32 -#define __NR_access 33 -#define __NR_nice 34 -#define __NR_ftime 35 -#define __NR_sync 36 -#define __NR_kill 37 -#define __NR_rename 38 -#define __NR_mkdir 39 -#define __NR_rmdir 40 -#define __NR_dup 41 -#define __NR_pipe 42 -#define __NR_times 43 -#define __NR_prof 44 -#define __NR_brk 45 -#define __NR_setgid 46 -#define __NR_getgid 47 -#define __NR_signal 48 -#define __NR_geteuid 49 -#define __NR_getegid 50 -#define __NR_acct 51 -#define __NR_umount2 52 -#define __NR_lock 53 -#define __NR_ioctl 54 -#define __NR_fcntl 55 -#define __NR_mpx 56 -#define __NR_setpgid 57 -#define __NR_ulimit 58 -#define __NR_oldolduname 59 -#define __NR_umask 60 -#define __NR_chroot 61 -#define __NR_ustat 62 -#define __NR_dup2 63 -#define __NR_getppid 64 -#define __NR_getpgrp 65 -#define __NR_setsid 66 -#define __NR_sigaction 67 -#define __NR_sgetmask 68 -#define __NR_ssetmask 69 -#define __NR_setreuid 70 -#define __NR_setregid 71 -#define __NR_sigsuspend 72 -#define __NR_sigpending 73 -#define __NR_sethostname 74 -#define __NR_setrlimit 75 -#define __NR_getrlimit 76 -#define __NR_getrusage 77 -#define __NR_gettimeofday 78 -#define __NR_settimeofday 79 -#define __NR_getgroups 80 -#define __NR_setgroups 81 -#define __NR_select 82 -#define __NR_symlink 83 -#define __NR_oldlstat 84 -#define __NR_readlink 85 -#define __NR_uselib 86 -#define __NR_swapon 87 -#define __NR_reboot 88 -#define __NR_readdir 89 -#define __NR_mmap 90 -#define __NR_munmap 91 -#define __NR_truncate 92 -#define __NR_ftruncate 93 -#define __NR_fchmod 94 -#define __NR_fchown 95 -#define __NR_getpriority 96 -#define __NR_setpriority 97 -#define __NR_profil 98 -#define __NR_statfs 99 -#define __NR_fstatfs 100 -#define __NR_ioperm 101 -#define __NR_socketcall 102 -#define __NR_syslog 103 -#define __NR_setitimer 104 -#define __NR_getitimer 105 -#define __NR_stat 106 -#define __NR_lstat 107 -#define __NR_fstat 108 -#define __NR_olduname 109 -#define __NR_iopl 110 -#define __NR_vhangup 111 -#define __NR_idle 112 -#define __NR_vm86 113 -#define __NR_wait4 114 -#define __NR_swapoff 115 -#define __NR_sysinfo 116 -#define __NR_ipc 117 -#define __NR_fsync 118 -#define __NR_sigreturn 119 -#define __NR_clone 120 -#define __NR_setdomainname 121 -#define __NR_uname 122 -#define __NR_modify_ldt 123 -#define __NR_adjtimex 124 -#define __NR_mprotect 125 -#define __NR_sigprocmask 126 -#define __NR_create_module 127 -#define __NR_init_module 128 -#define __NR_delete_module 129 -#define __NR_get_kernel_syms 130 -#define __NR_quotactl 131 -#define __NR_getpgid 132 -#define __NR_fchdir 133 -#define __NR_bdflush 134 -#define __NR_sysfs 135 -#define __NR_personality 136 -#define __NR_afs_syscall 137 /* Syscall for Andrew File System */ -#define __NR_setfsuid 138 -#define __NR_setfsgid 139 -#define __NR__llseek 140 -#define __NR_getdents 141 -#define __NR__newselect 142 -#define __NR_flock 143 -#define __NR_msync 144 -#define __NR_readv 145 -#define __NR_writev 146 -#define __NR_getsid 147 -#define __NR_fdatasync 148 -#define __NR__sysctl 149 -#define __NR_mlock 150 -#define __NR_munlock 151 -#define __NR_mlockall 152 -#define __NR_munlockall 153 -#define __NR_sched_setparam 154 -#define __NR_sched_getparam 155 -#define __NR_sched_setscheduler 156 -#define __NR_sched_getscheduler 157 -#define __NR_sched_yield 158 -#define __NR_sched_get_priority_max 159 -#define __NR_sched_get_priority_min 160 -#define __NR_sched_rr_get_interval 161 -#define __NR_nanosleep 162 -#define __NR_mremap 163 -#define __NR_setresuid 164 -#define __NR_getresuid 165 -#define __NR_query_module 166 -#define __NR_poll 167 -#define __NR_nfsservctl 168 -#define __NR_setresgid 169 -#define __NR_getresgid 170 -#define __NR_prctl 171 -#define __NR_rt_sigreturn 172 -#define __NR_rt_sigaction 173 -#define __NR_rt_sigprocmask 174 -#define __NR_rt_sigpending 175 -#define __NR_rt_sigtimedwait 176 -#define __NR_rt_sigqueueinfo 177 -#define __NR_rt_sigsuspend 178 -#define __NR_pread64 179 -#define __NR_pwrite64 180 -#define __NR_chown 181 -#define __NR_getcwd 182 -#define __NR_capget 183 -#define __NR_capset 184 -#define __NR_sigaltstack 185 -#define __NR_sendfile 186 -#define __NR_getpmsg 187 /* some people actually want streams */ -#define __NR_putpmsg 188 /* some people actually want streams */ -#define __NR_vfork 189 -#define __NR_ugetrlimit 190 /* SuS compliant getrlimit */ -#define __NR_readahead 191 -#ifndef __powerpc64__ /* these are 32-bit only */ -#define __NR_mmap2 192 -#define __NR_truncate64 193 -#define __NR_ftruncate64 194 -#define __NR_stat64 195 -#define __NR_lstat64 196 -#define __NR_fstat64 197 -#endif -#define __NR_pciconfig_read 198 -#define __NR_pciconfig_write 199 -#define __NR_pciconfig_iobase 200 -#define __NR_multiplexer 201 -#define __NR_getdents64 202 -#define __NR_pivot_root 203 -#ifndef __powerpc64__ -#define __NR_fcntl64 204 -#endif -#define __NR_madvise 205 -#define __NR_mincore 206 -#define __NR_gettid 207 -#define __NR_tkill 208 -#define __NR_setxattr 209 -#define __NR_lsetxattr 210 -#define __NR_fsetxattr 211 -#define __NR_getxattr 212 -#define __NR_lgetxattr 213 -#define __NR_fgetxattr 214 -#define __NR_listxattr 215 -#define __NR_llistxattr 216 -#define __NR_flistxattr 217 -#define __NR_removexattr 218 -#define __NR_lremovexattr 219 -#define __NR_fremovexattr 220 -#define __NR_futex 221 -#define __NR_sched_setaffinity 222 -#define __NR_sched_getaffinity 223 -/* 224 currently unused */ -#define __NR_tuxcall 225 #ifndef __powerpc64__ -#define __NR_sendfile64 226 -#endif -#define __NR_io_setup 227 -#define __NR_io_destroy 228 -#define __NR_io_getevents 229 -#define __NR_io_submit 230 -#define __NR_io_cancel 231 -#define __NR_set_tid_address 232 -#define __NR_fadvise64 233 -#define __NR_exit_group 234 -#define __NR_lookup_dcookie 235 -#define __NR_epoll_create 236 -#define __NR_epoll_ctl 237 -#define __NR_epoll_wait 238 -#define __NR_remap_file_pages 239 -#define __NR_timer_create 240 -#define __NR_timer_settime 241 -#define __NR_timer_gettime 242 -#define __NR_timer_getoverrun 243 -#define __NR_timer_delete 244 -#define __NR_clock_settime 245 -#define __NR_clock_gettime 246 -#define __NR_clock_getres 247 -#define __NR_clock_nanosleep 248 -#define __NR_swapcontext 249 -#define __NR_tgkill 250 -#define __NR_utimes 251 -#define __NR_statfs64 252 -#define __NR_fstatfs64 253 -#ifndef __powerpc64__ -#define __NR_fadvise64_64 254 -#endif -#define __NR_rtas 255 -#define __NR_sys_debug_setcontext 256 -/* Number 257 is reserved for vserver */ -#define __NR_migrate_pages 258 -#define __NR_mbind 259 -#define __NR_get_mempolicy 260 -#define __NR_set_mempolicy 261 -#define __NR_mq_open 262 -#define __NR_mq_unlink 263 -#define __NR_mq_timedsend 264 -#define __NR_mq_timedreceive 265 -#define __NR_mq_notify 266 -#define __NR_mq_getsetattr 267 -#define __NR_kexec_load 268 -#define __NR_add_key 269 -#define __NR_request_key 270 -#define __NR_keyctl 271 -#define __NR_waitid 272 -#define __NR_ioprio_set 273 -#define __NR_ioprio_get 274 -#define __NR_inotify_init 275 -#define __NR_inotify_add_watch 276 -#define __NR_inotify_rm_watch 277 -#define __NR_spu_run 278 -#define __NR_spu_create 279 -#define __NR_pselect6 280 -#define __NR_ppoll 281 -#define __NR_unshare 282 -#define __NR_splice 283 -#define __NR_tee 284 -#define __NR_vmsplice 285 -#define __NR_openat 286 -#define __NR_mkdirat 287 -#define __NR_mknodat 288 -#define __NR_fchownat 289 -#define __NR_futimesat 290 -#ifdef __powerpc64__ -#define __NR_newfstatat 291 +#include <asm/unistd_32.h> #else -#define __NR_fstatat64 291 +#include <asm/unistd_64.h> #endif -#define __NR_unlinkat 292 -#define __NR_renameat 293 -#define __NR_linkat 294 -#define __NR_symlinkat 295 -#define __NR_readlinkat 296 -#define __NR_fchmodat 297 -#define __NR_faccessat 298 -#define __NR_get_robust_list 299 -#define __NR_set_robust_list 300 -#define __NR_move_pages 301 -#define __NR_getcpu 302 -#define __NR_epoll_pwait 303 -#define __NR_utimensat 304 -#define __NR_signalfd 305 -#define __NR_timerfd_create 306 -#define __NR_eventfd 307 -#define __NR_sync_file_range2 308 -#define __NR_fallocate 309 -#define __NR_subpage_prot 310 -#define __NR_timerfd_settime 311 -#define __NR_timerfd_gettime 312 -#define __NR_signalfd4 313 -#define __NR_eventfd2 314 -#define __NR_epoll_create1 315 -#define __NR_dup3 316 -#define __NR_pipe2 317 -#define __NR_inotify_init1 318 -#define __NR_perf_event_open 319 -#define __NR_preadv 320 -#define __NR_pwritev 321 -#define __NR_rt_tgsigqueueinfo 322 -#define __NR_fanotify_init 323 -#define __NR_fanotify_mark 324 -#define __NR_prlimit64 325 -#define __NR_socket 326 -#define __NR_bind 327 -#define __NR_connect 328 -#define __NR_listen 329 -#define __NR_accept 330 -#define __NR_getsockname 331 -#define __NR_getpeername 332 -#define __NR_socketpair 333 -#define __NR_send 334 -#define __NR_sendto 335 -#define __NR_recv 336 -#define __NR_recvfrom 337 -#define __NR_shutdown 338 -#define __NR_setsockopt 339 -#define __NR_getsockopt 340 -#define __NR_sendmsg 341 -#define __NR_recvmsg 342 -#define __NR_recvmmsg 343 -#define __NR_accept4 344 -#define __NR_name_to_handle_at 345 -#define __NR_open_by_handle_at 346 -#define __NR_clock_adjtime 347 -#define __NR_syncfs 348 -#define __NR_sendmmsg 349 -#define __NR_setns 350 -#define __NR_process_vm_readv 351 -#define __NR_process_vm_writev 352 -#define __NR_finit_module 353 -#define __NR_kcmp 354 -#define __NR_sched_setattr 355 -#define __NR_sched_getattr 356 -#define __NR_renameat2 357 -#define __NR_seccomp 358 -#define __NR_getrandom 359 -#define __NR_memfd_create 360 -#define __NR_bpf 361 -#define __NR_execveat 362 -#define __NR_switch_endian 363 -#define __NR_userfaultfd 364 -#define __NR_membarrier 365 -#define __NR_mlock2 378 -#define __NR_copy_file_range 379 -#define __NR_preadv2 380 -#define __NR_pwritev2 381 -#define __NR_kexec_file_load 382 -#define __NR_statx 383 -#define __NR_pkey_alloc 384 -#define __NR_pkey_free 385 -#define __NR_pkey_mprotect 386 -#define __NR_rseq 387 -#define __NR_io_pgetevents 388 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile @@ -69,7 +69,7 @@ obj-$(CONFIG_FA_DUMP) += fadump.o ifdef CONFIG_PPC32 obj-$(CONFIG_E500) += idle_e500.o endif -obj-$(CONFIG_6xx) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o +obj-$(CONFIG_PPC_BOOK3S_32) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o obj-$(CONFIG_TAU) += tau_6xx.o obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o ifdef CONFIG_FSL_BOOKE @@ -160,16 +160,6 @@ extra-$(CONFIG_ALTIVEC) += vector.o extra-$(CONFIG_PPC64) += entry_64.o extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o -extra-y += systbl_chk.i -$(obj)/systbl.o: systbl_chk - -quiet_cmd_systbl_chk = CALL $< - cmd_systbl_chk = $(CONFIG_SHELL) $< $(obj)/systbl_chk.i - -PHONY += systbl_chk -systbl_chk: $(src)/systbl_chk.sh $(obj)/systbl_chk.i - $(call cmd,systbl_chk) - ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE $(obj)/built-in.a: prom_init_check diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c @@ -232,20 +232,12 @@ static int btext_initialize(struct device_node *np) int __init btext_find_display(int allow_nonstdout) { - const char *name; - struct device_node *np = NULL; + struct device_node *np = of_stdout; int rc = -ENODEV; - name = of_get_property(of_chosen, "linux,stdout-path", NULL); - if (name != NULL) { - np = of_find_node_by_path(name); - if (np != NULL) { - if (strcmp(np->type, "display") != 0) { - printk("boot stdout isn't a display !\n"); - of_node_put(np); - np = NULL; - } - } + if (!of_node_is_type(np, "display")) { + printk("boot stdout isn't a display !\n"); + np = NULL; } if (np) rc = btext_initialize(np); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c @@ -428,7 +428,7 @@ static void link_cache_lists(struct cache *smaller, struct cache *bigger) static void do_subsidiary_caches_debugcheck(struct cache *cache) { WARN_ON_ONCE(cache->level != 1); - WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu")); + WARN_ON_ONCE(!of_node_is_type(cache->ofnode, "cpu")); } static void do_subsidiary_caches(struct cache *cache) diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -326,7 +326,7 @@ _GLOBAL(__save_cpu_setup) lis r5,cpu_state_storage@h ori r5,r5,cpu_state_storage@l - /* Save HID0 (common to all CONFIG_6xx cpus) */ + /* Save HID0 (common to all CONFIG_PPC_BOOK3S_32 cpus) */ mfspr r3,SPRN_HID0 stw r3,CS_HID0(r5) diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -17,7 +17,7 @@ #include <asm/processor.h> #include <asm/cputable.h> #include <asm/ppc_asm.h> -#include <asm/mmu-book3e.h> +#include <asm/nohash/mmu-book3e.h> #include <asm/asm-offsets.h> #include <asm/mpc85xx.h> diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c @@ -1141,6 +1141,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_generic, .platform = "ppc603", }, +#ifdef CONFIG_PPC_83xx { /* e300c1 (a 603e core, plus some) on 83xx */ .pvr_mask = 0x7fff0000, .pvr_value = 0x00830000, @@ -1151,7 +1152,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, + .machine_check = machine_check_83xx, .platform = "ppc603", }, { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */ @@ -1165,7 +1166,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, + .machine_check = machine_check_83xx, .platform = "ppc603", }, { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */ @@ -1179,7 +1180,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, + .machine_check = machine_check_83xx, .num_pmcs = 4, .oprofile_cpu_type = "ppc/e300", .oprofile_type = PPC_OPROFILE_FSL_EMB, @@ -1196,12 +1197,13 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, + .machine_check = machine_check_83xx, .num_pmcs = 4, .oprofile_cpu_type = "ppc/e300", .oprofile_type = PPC_OPROFILE_FSL_EMB, .platform = "ppc603", }, +#endif { /* default match, we assume split I/D cache & TB (non-601)... */ .pvr_mask = 0x00000000, .pvr_value = 0x00000000, diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c @@ -6,7 +6,6 @@ * busses using the iommu infrastructure */ -#include <linux/export.h> #include <asm/iommu.h> /* @@ -123,4 +122,3 @@ struct dma_map_ops dma_iommu_ops = { .get_required_mask = dma_iommu_get_required_mask, .mapping_error = dma_iommu_mapping_error, }; -EXPORT_SYMBOL(dma_iommu_ops); diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c @@ -108,12 +108,8 @@ int __init swiotlb_setup_bus_notifier(void) void __init swiotlb_detect_4g(void) { - if ((memblock_end_of_DRAM() - 1) > 0xffffffff) { + if ((memblock_end_of_DRAM() - 1) > 0xffffffff) ppc_swiotlb_enable = 1; -#ifdef CONFIG_ZONE_DMA32 - limit_zone_pfn(ZONE_DMA32, (1ULL << 32) >> PAGE_SHIFT); -#endif - } } static int __init check_swiotlb_enabled(void) diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c @@ -50,7 +50,8 @@ static int dma_nommu_dma_supported(struct device *dev, u64 mask) return 1; #ifdef CONFIG_FSL_SOC - /* Freescale gets another chance via ZONE_DMA/ZONE_DMA32, however + /* + * Freescale gets another chance via ZONE_DMA, however * that will have to be refined if/when they support iommus */ return 1; @@ -62,18 +63,12 @@ static int dma_nommu_dma_supported(struct device *dev, u64 mask) #endif } +#ifndef CONFIG_NOT_COHERENT_CACHE void *__dma_nommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { void *ret; -#ifdef CONFIG_NOT_COHERENT_CACHE - ret = __dma_alloc_coherent(dev, size, dma_handle, flag); - if (ret == NULL) - return NULL; - *dma_handle += get_dma_offset(dev); - return ret; -#else struct page *page; int node = dev_to_node(dev); #ifdef CONFIG_FSL_SOC @@ -94,13 +89,10 @@ void *__dma_nommu_alloc_coherent(struct device *dev, size_t size, } switch (zone) { +#ifdef CONFIG_ZONE_DMA case ZONE_DMA: flag |= GFP_DMA; break; -#ifdef CONFIG_ZONE_DMA32 - case ZONE_DMA32: - flag |= GFP_DMA32; - break; #endif }; #endif /* CONFIG_FSL_SOC */ @@ -113,19 +105,15 @@ void *__dma_nommu_alloc_coherent(struct device *dev, size_t size, *dma_handle = __pa(ret) + get_dma_offset(dev); return ret; -#endif } void __dma_nommu_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { -#ifdef CONFIG_NOT_COHERENT_CACHE - __dma_free_coherent(size, vaddr); -#else free_pages((unsigned long)vaddr, get_order(size)); -#endif } +#endif /* !CONFIG_NOT_COHERENT_CACHE */ static void *dma_nommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, @@ -210,10 +198,15 @@ static int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl, return nents; } -static void dma_nommu_unmap_sg(struct device *dev, struct scatterlist *sg, +static void dma_nommu_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction, unsigned long attrs) { + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); } static u64 dma_nommu_get_required_mask(struct device *dev) @@ -247,6 +240,8 @@ static inline void dma_nommu_unmap_page(struct device *dev, enum dma_data_direction direction, unsigned long attrs) { + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_sync(bus_to_virt(dma_address), size, direction); } #ifdef CONFIG_NOT_COHERENT_CACHE diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c @@ -1808,10 +1808,10 @@ static int eeh_freeze_dbgfs_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get, - eeh_enable_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(eeh_freeze_dbgfs_ops, eeh_freeze_dbgfs_get, - eeh_freeze_dbgfs_set, "0x%llx\n"); +DEFINE_DEBUGFS_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get, + eeh_enable_dbgfs_set, "0x%llx\n"); +DEFINE_DEBUGFS_ATTRIBUTE(eeh_freeze_dbgfs_ops, eeh_freeze_dbgfs_get, + eeh_freeze_dbgfs_set, "0x%llx\n"); #endif static int __init eeh_init_proc(void) @@ -1819,12 +1819,12 @@ static int __init eeh_init_proc(void) if (machine_is(pseries) || machine_is(powernv)) { proc_create_single("powerpc/eeh", 0, NULL, proc_eeh_show); #ifdef CONFIG_DEBUG_FS - debugfs_create_file("eeh_enable", 0600, - powerpc_debugfs_root, NULL, - &eeh_enable_dbgfs_ops); - debugfs_create_file("eeh_max_freezes", 0600, - powerpc_debugfs_root, NULL, - &eeh_freeze_dbgfs_ops); + debugfs_create_file_unsafe("eeh_enable", 0600, + powerpc_debugfs_root, NULL, + &eeh_enable_dbgfs_ops); + debugfs_create_file_unsafe("eeh_max_freezes", 0600, + powerpc_debugfs_root, NULL, + &eeh_freeze_dbgfs_ops); #endif } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c @@ -60,7 +60,7 @@ static int eeh_result_priority(enum pci_ers_result result) } }; -const char *pci_ers_result_name(enum pci_ers_result result) +static const char *pci_ers_result_name(enum pci_ers_result result) { switch (result) { case PCI_ERS_RESULT_NONE: diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c @@ -35,7 +35,7 @@ */ static DEFINE_SPINLOCK(eeh_eventlist_lock); -static struct semaphore eeh_eventlist_sem; +static DECLARE_COMPLETION(eeh_eventlist_event); static LIST_HEAD(eeh_eventlist); /** @@ -55,7 +55,7 @@ static int eeh_event_handler(void * dummy) struct eeh_pe *pe; while (!kthread_should_stop()) { - if (down_interruptible(&eeh_eventlist_sem)) + if (wait_for_completion_interruptible(&eeh_eventlist_event)) break; /* Fetch EEH event from the queue */ @@ -102,9 +102,6 @@ int eeh_event_init(void) struct task_struct *t; int ret = 0; - /* Initialize semaphore */ - sema_init(&eeh_eventlist_sem, 0); - t = kthread_run(eeh_event_handler, NULL, "eehd"); if (IS_ERR(t)) { ret = PTR_ERR(t); @@ -142,7 +139,7 @@ int eeh_send_failure_event(struct eeh_pe *pe) spin_unlock_irqrestore(&eeh_eventlist_lock, flags); /* For EEH deamon to knick in */ - up(&eeh_eventlist_sem); + complete(&eeh_eventlist_event); return 0; } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S @@ -200,14 +200,14 @@ transfer_to_handler: cmplw r1,r9 /* if r1 <= ksp_limit */ ble- stack_ovf /* then the kernel stack overflowed */ 5: -#if defined(CONFIG_6xx) || defined(CONFIG_E500) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) CURRENT_THREAD_INFO(r9, r1) tophys(r9,r9) /* check local flags */ lwz r12,TI_LOCAL_FLAGS(r9) mtcrf 0x01,r12 bt- 31-TLF_NAPPING,4f bt- 31-TLF_SLEEPING,7f -#endif /* CONFIG_6xx || CONFIG_E500 */ +#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_E500 */ .globl transfer_to_handler_cont transfer_to_handler_cont: 3: @@ -273,7 +273,7 @@ reenable_mmu: /* re-enable mmu so we can */ RFI /* jump to handler, enable MMU */ #endif /* CONFIG_TRACE_IRQFLAGS */ -#if defined (CONFIG_6xx) || defined(CONFIG_E500) +#if defined (CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) 4: rlwinm r12,r12,0,~_TLF_NAPPING stw r12,TI_LOCAL_FLAGS(r9) b power_save_ppc32_restore @@ -612,7 +612,7 @@ ppc_swapcontext: handle_page_fault: stw r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 andis. r0,r5,DSISR_DABRMATCH@h bne- handle_dabr_fault #endif @@ -629,7 +629,7 @@ handle_page_fault: bl bad_page_fault b ret_from_except_full -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 /* We have a data breakpoint exception - handle it */ handle_dabr_fault: SAVE_NVGPRS(r1) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S @@ -54,6 +54,9 @@ SYS_CALL_TABLE: .tc sys_call_table[TC],sys_call_table +COMPAT_SYS_CALL_TABLE: + .tc compat_sys_call_table[TC],compat_sys_call_table + /* This value is used to mark exception frames on the stack. */ exception_marker: .tc ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER @@ -80,6 +83,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) std r0,GPR0(r1) std r10,GPR1(r1) beq 2f /* if from kernel mode */ +#ifdef CONFIG_PPC_FSL_BOOK3E +START_BTB_FLUSH_SECTION + BTB_FLUSH(r10) +END_BTB_FLUSH_SECTION +#endif ACCOUNT_CPU_USER_ENTRY(r13, r10, r11) 2: std r2,GPR2(r1) std r3,GPR3(r1) @@ -173,7 +181,7 @@ system_call: /* label this so stack traces look sane */ ld r11,SYS_CALL_TABLE@toc(2) andis. r10,r10,_TIF_32BIT@h beq 15f - addi r11,r11,8 /* use 32-bit syscall entries */ + ld r11,COMPAT_SYS_CALL_TABLE@toc(2) clrldi r3,r3,32 clrldi r4,r4,32 clrldi r5,r5,32 @@ -181,7 +189,7 @@ system_call: /* label this so stack traces look sane */ clrldi r7,r7,32 clrldi r8,r8,32 15: - slwi r0,r0,4 + slwi r0,r0,3 barrier_nospec_asm /* @@ -286,6 +294,10 @@ BEGIN_FTR_SECTION HMT_MEDIUM_LOW END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + std r8, PACATMSCRATCH(r13) +#endif + ld r13,GPR13(r1) /* only restore r13 if returning to usermode */ ld r2,GPR2(r1) ld r1,GPR1(r1) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S @@ -296,7 +296,8 @@ ret_from_mc_except: andi. r10,r11,MSR_PR; /* save stack pointer */ \ beq 1f; /* branch around if supervisor */ \ ld r1,PACAKSAVE(r13); /* get kernel stack coming from usr */\ -1: cmpdi cr1,r1,0; /* check if SP makes sense */ \ +1: type##_BTB_FLUSH \ + cmpdi cr1,r1,0; /* check if SP makes sense */ \ bge- cr1,exc_##n##_bad_stack;/* bad stack (TODO: out of line) */ \ mfspr r10,SPRN_##type##_SRR0; /* read SRR0 before touching stack */ @@ -328,6 +329,29 @@ ret_from_mc_except: #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 +#ifdef CONFIG_PPC_FSL_BOOK3E +#define GEN_BTB_FLUSH \ + START_BTB_FLUSH_SECTION \ + beq 1f; \ + BTB_FLUSH(r10) \ + 1: \ + END_BTB_FLUSH_SECTION + +#define CRIT_BTB_FLUSH \ + START_BTB_FLUSH_SECTION \ + BTB_FLUSH(r10) \ + END_BTB_FLUSH_SECTION + +#define DBG_BTB_FLUSH CRIT_BTB_FLUSH +#define MC_BTB_FLUSH CRIT_BTB_FLUSH +#define GDBELL_BTB_FLUSH GEN_BTB_FLUSH +#else +#define GEN_BTB_FLUSH +#define CRIT_BTB_FLUSH +#define DBG_BTB_FLUSH +#define GDBELL_BTB_FLUSH +#endif + #define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \ EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n)) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S @@ -1040,7 +1040,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early) EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) EXCEPTION_PROLOG_COMMON_3(0xe60) addi r3,r1,STACK_FRAME_OVERHEAD - BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */ + BRANCH_LINK_TO_FAR(DOTSYM(hmi_exception_realmode)) /* Function call ABI */ cmpdi cr0,r3,0 /* Windup the stack. */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c @@ -35,6 +35,7 @@ #include <linux/kobject.h> #include <linux/sysfs.h> #include <linux/slab.h> +#include <linux/cma.h> #include <asm/debugfs.h> #include <asm/page.h> @@ -46,6 +47,9 @@ static struct fw_dump fw_dump; static struct fadump_mem_struct fdm; static const struct fadump_mem_struct *fdm_active; +#ifdef CONFIG_CMA +static struct cma *fadump_cma; +#endif static DEFINE_MUTEX(fadump_mutex); struct fad_crash_memory_ranges *crash_memory_ranges; @@ -53,6 +57,67 @@ int crash_memory_ranges_size; int crash_mem_ranges; int max_crash_mem_ranges; +#ifdef CONFIG_CMA +/* + * fadump_cma_init() - Initialize CMA area from a fadump reserved memory + * + * This function initializes CMA area from fadump reserved memory. + * The total size of fadump reserved memory covers for boot memory size + * + cpu data size + hpte size and metadata. + * Initialize only the area equivalent to boot memory size for CMA use. + * The reamining portion of fadump reserved memory will be not given + * to CMA and pages for thoes will stay reserved. boot memory size is + * aligned per CMA requirement to satisy cma_init_reserved_mem() call. + * But for some reason even if it fails we still have the memory reservation + * with us and we can still continue doing fadump. + */ +int __init fadump_cma_init(void) +{ + unsigned long long base, size; + int rc; + + if (!fw_dump.fadump_enabled) + return 0; + + /* + * Do not use CMA if user has provided fadump=nocma kernel parameter. + * Return 1 to continue with fadump old behaviour. + */ + if (fw_dump.nocma) + return 1; + + base = fw_dump.reserve_dump_area_start; + size = fw_dump.boot_memory_size; + + if (!size) + return 0; + + rc = cma_init_reserved_mem(base, size, 0, "fadump_cma", &fadump_cma); + if (rc) { + pr_err("Failed to init cma area for firmware-assisted dump,%d\n", rc); + /* + * Though the CMA init has failed we still have memory + * reservation with us. The reserved memory will be + * blocked from production system usage. Hence return 1, + * so that we can continue with fadump. + */ + return 1; + } + + /* + * So we now have successfully initialized cma area for fadump. + */ + pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx " + "bytes of memory reserved for firmware-assisted dump\n", + cma_get_size(fadump_cma), + (unsigned long)cma_get_base(fadump_cma) >> 20, + fw_dump.reserve_dump_area_size); + return 1; +} +#else +static int __init fadump_cma_init(void) { return 1; } +#endif /* CONFIG_CMA */ + /* Scan the Firmware Assisted dump configuration details. */ int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data) @@ -118,13 +183,19 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, /* * If fadump is registered, check if the memory provided - * falls within boot memory area. + * falls within boot memory area and reserved memory area. */ -int is_fadump_boot_memory_area(u64 addr, ulong size) +int is_fadump_memory_area(u64 addr, ulong size) { + u64 d_start = fw_dump.reserve_dump_area_start; + u64 d_end = d_start + fw_dump.reserve_dump_area_size; + if (!fw_dump.dump_registered) return 0; + if (((addr + size) > d_start) && (addr <= d_end)) + return 1; + return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size; } @@ -172,6 +243,35 @@ static int is_boot_memory_area_contiguous(void) return ret; } +/* + * Returns true, if there are no holes in reserved memory area, + * false otherwise. + */ +static bool is_reserved_memory_area_contiguous(void) +{ + struct memblock_region *reg; + unsigned long start, end; + unsigned long d_start = fw_dump.reserve_dump_area_start; + unsigned long d_end = d_start + fw_dump.reserve_dump_area_size; + + for_each_memblock(memory, reg) { + start = max(d_start, (unsigned long)reg->base); + end = min(d_end, (unsigned long)(reg->base + reg->size)); + if (d_start < end) { + /* Memory hole from d_start to start */ + if (start > d_start) + break; + + if (end == d_end) + return true; + + d_start = end + 1; + } + } + + return false; +} + /* Print firmware assisted dump configurations for debugging purpose. */ static void fadump_show_config(void) { @@ -378,8 +478,15 @@ int __init fadump_reserve_mem(void) */ if (fdm_active) fw_dump.boot_memory_size = be64_to_cpu(fdm_active->rmr_region.source_len); - else + else { fw_dump.boot_memory_size = fadump_calculate_reserve_size(); +#ifdef CONFIG_CMA + if (!fw_dump.nocma) + fw_dump.boot_memory_size = + ALIGN(fw_dump.boot_memory_size, + FADUMP_CMA_ALIGNMENT); +#endif + } /* * Calculate the memory boundary. @@ -426,8 +533,9 @@ int __init fadump_reserve_mem(void) fw_dump.fadumphdr_addr = be64_to_cpu(fdm_active->rmr_region.destination_address) + be64_to_cpu(fdm_active->rmr_region.source_len); - pr_debug("fadumphdr_addr = %p\n", - (void *) fw_dump.fadumphdr_addr); + pr_debug("fadumphdr_addr = %pa\n", &fw_dump.fadumphdr_addr); + fw_dump.reserve_dump_area_start = base; + fw_dump.reserve_dump_area_size = size; } else { size = get_fadump_area_size(); @@ -455,10 +563,11 @@ int __init fadump_reserve_mem(void) (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; + fw_dump.reserve_dump_area_start = base; + fw_dump.reserve_dump_area_size = size; + return fadump_cma_init(); + } return 1; } @@ -477,6 +586,10 @@ static int __init early_fadump_param(char *p) fw_dump.fadump_enabled = 1; else if (strncmp(p, "off", 3) == 0) fw_dump.fadump_enabled = 0; + else if (strncmp(p, "nocma", 5) == 0) { + fw_dump.fadump_enabled = 1; + fw_dump.nocma = 1; + } return 0; } @@ -525,8 +638,10 @@ static int register_fw_dump(struct fadump_mem_struct *fdm) break; case -3: if (!is_boot_memory_area_contiguous()) - pr_err("Can't have holes in boot memory area while " - "registering fadump\n"); + pr_err("Can't have holes in boot memory area while registering fadump\n"); + else if (!is_reserved_memory_area_contiguous()) + pr_err("Can't have holes in reserved memory area while" + " registering fadump\n"); printk(KERN_ERR "Failed to register firmware-assisted kernel" " dump. Parameter Error(%d).\n", rc); @@ -1229,7 +1344,7 @@ static int fadump_unregister_dump(struct fadump_mem_struct *fdm) return 0; } -static int fadump_invalidate_dump(struct fadump_mem_struct *fdm) +static int fadump_invalidate_dump(const struct fadump_mem_struct *fdm) { int rc = 0; unsigned int wait_time; @@ -1260,9 +1375,8 @@ void fadump_cleanup(void) { /* Invalidate the registration only if dump is active. */ if (fw_dump.dump_active) { - init_fadump_mem_struct(&fdm, - be64_to_cpu(fdm_active->cpu_state_data.destination_address)); - fadump_invalidate_dump(&fdm); + /* pass the same memory dump structure provided by platform */ + fadump_invalidate_dump(fdm_active); } else if (fw_dump.dump_registered) { /* Un-register Firmware-assisted dump if it was registered. */ fadump_unregister_dump(&fdm); @@ -1531,17 +1645,7 @@ static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered, 0644, fadump_register_show, fadump_register_store); -static int fadump_region_open(struct inode *inode, struct file *file) -{ - return single_open(file, fadump_region_show, inode->i_private); -} - -static const struct file_operations fadump_region_fops = { - .open = fadump_region_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(fadump_region); static void fadump_init_files(void) { diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S @@ -176,10 +176,10 @@ __after_mmu_off: bl reloc_offset li r24,0 /* cpu# */ bl call_setup_cpu /* Call setup_cpu for this CPU */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 bl reloc_offset bl init_idle_6xx -#endif /* CONFIG_6xx */ +#endif /* CONFIG_PPC_BOOK3S_32 */ /* @@ -393,7 +393,9 @@ DataAccess: bne 1f /* if not, try to put a PTE */ mfspr r4,SPRN_DAR /* into the hash table */ rlwinm r3,r10,32-15,21,21 /* DSISR_STORE -> _PAGE_RW */ +BEGIN_MMU_FTR_SECTION bl hash_page +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) 1: lwz r5,_DSISR(r11) /* get DSISR value */ mfspr r4,SPRN_DAR EXC_XFER_LITE(0x300, handle_page_fault) @@ -408,7 +410,9 @@ InstructionAccess: beq 1f /* if so, try to put a PTE */ li r3,0 /* into the hash table */ mr r4,r12 /* SRR0 is fault address */ +BEGIN_MMU_FTR_SECTION bl hash_page +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) 1: mr r4,r12 andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */ EXC_XFER_LITE(0x400, handle_page_fault) @@ -499,7 +503,7 @@ InstructionTLBMiss: lis r1,PAGE_OFFSET@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2,SPRN_SPRG_THREAD - li r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */ + li r1,_PAGE_USER|_PAGE_PRESENT|_PAGE_EXEC /* low addresses tested as user */ lwz r2,PGDIR(r2) bge- 112f mfspr r2,SPRN_SRR1 /* and MSR_PR bit from SRR1 */ @@ -836,10 +840,10 @@ __secondary_start: lis r3,-KERNELBASE@h mr r4,r24 bl call_setup_cpu /* Call setup_cpu for this CPU */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 lis r3,-KERNELBASE@h bl init_idle_6xx -#endif /* CONFIG_6xx */ +#endif /* CONFIG_PPC_BOOK3S_32 */ /* get current_thread_info and current */ lis r1,secondary_ti@ha @@ -880,14 +884,14 @@ __secondary_start: /* * Those generic dummy functions are kept for CPUs not - * included in CONFIG_6xx + * included in CONFIG_PPC_BOOK3S_32 */ -#if !defined(CONFIG_6xx) +#if !defined(CONFIG_PPC_BOOK3S_32) _ENTRY(__save_cpu_setup) blr _ENTRY(__restore_cpu_setup) blr -#endif /* !defined(CONFIG_6xx) */ +#endif /* !defined(CONFIG_PPC_BOOK3S_32) */ /* diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S @@ -40,6 +40,7 @@ #include <asm/ptrace.h> #include <asm/synch.h> #include <asm/export.h> +#include <asm/code-patching-asm.h> #include "head_booke.h" @@ -382,10 +383,9 @@ interrupt_base: /* Increment, rollover, and store TLB index */ addi r13,r13,1 + patch_site 0f, patch__tlb_44x_hwater_D /* Compare with watermark (instruction gets patched) */ - .globl tlb_44x_patch_hwater_D -tlb_44x_patch_hwater_D: - cmpwi 0,r13,1 /* reserve entries */ +0: cmpwi 0,r13,1 /* reserve entries */ ble 5f li r13,0 5: @@ -478,10 +478,9 @@ tlb_44x_patch_hwater_D: /* Increment, rollover, and store TLB index */ addi r13,r13,1 + patch_site 0f, patch__tlb_44x_hwater_I /* Compare with watermark (instruction gets patched) */ - .globl tlb_44x_patch_hwater_I -tlb_44x_patch_hwater_I: - cmpwi 0,r13,1 /* reserve entries */ +0: cmpwi 0,r13,1 /* reserve entries */ ble 5f li r13,0 5: diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S @@ -106,6 +106,23 @@ turn_on_mmu: mtspr SPRN_SRR0,r0 rfi /* enables MMU */ + +#ifdef CONFIG_PERF_EVENTS + .align 4 + + .globl itlb_miss_counter +itlb_miss_counter: + .space 4 + + .globl dtlb_miss_counter +dtlb_miss_counter: + .space 4 + + .globl instruction_counter +instruction_counter: + .space 4 +#endif + /* * Exception entry code. This code runs with address translation * turned off, i.e. using physical addresses. @@ -149,6 +166,9 @@ turn_on_mmu: li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \ mtmsr r10; \ stw r0,GPR0(r11); \ + lis r10, STACK_FRAME_REGS_MARKER@ha; /* exception frame marker */ \ + addi r10, r10, STACK_FRAME_REGS_MARKER@l; \ + stw r10, 8(r11); \ SAVE_4GPRS(3, r11); \ SAVE_2GPRS(7, r11) @@ -275,7 +295,7 @@ SystemCall: . = 0x1100 /* * For the MPC8xx, this is a software tablewalk to load the instruction - * TLB. The task switch loads the M_TW register with the pointer to the first + * TLB. The task switch loads the M_TWB register with the pointer to the first * level table. * If we discover there is no second level table (value is zero) or if there * is an invalid pte, we load that into the TLB, which causes another fault @@ -285,186 +305,154 @@ SystemCall: */ #ifdef CONFIG_8xx_CPU15 -#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr) \ - addi tmp, addr, PAGE_SIZE; \ - tlbie tmp; \ - addi tmp, addr, -PAGE_SIZE; \ - tlbie tmp +#define INVALIDATE_ADJACENT_PAGES_CPU15(addr) \ + addi addr, addr, PAGE_SIZE; \ + tlbie addr; \ + addi addr, addr, -(PAGE_SIZE << 1); \ + tlbie addr; \ + addi addr, addr, PAGE_SIZE #else -#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr) +#define INVALIDATE_ADJACENT_PAGES_CPU15(addr) #endif InstructionTLBMiss: mtspr SPRN_SPRG_SCRATCH0, r10 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mtspr SPRN_SPRG_SCRATCH1, r11 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mtspr SPRN_SPRG_SCRATCH2, r12 #endif /* If we are faulting a kernel address, we have to use the * kernel page tables. */ mfspr r10, SPRN_SRR0 /* Get effective address of fault */ - INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10) + INVALIDATE_ADJACENT_PAGES_CPU15(r10) + mtspr SPRN_MD_EPN, r10 /* Only modules will cause ITLB Misses as we always * pin the first 8MB of kernel memory */ -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mfcr r12 -#endif #ifdef ITLB_MISS_KERNEL + mfcr r11 #if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT) - andis. r11, r10, 0x8000 /* Address >= 0x80000000 */ + cmpi cr0, r10, 0 /* Address >= 0x80000000 */ #else - rlwinm r11, r10, 16, 0xfff8 - cmpli cr0, r11, PAGE_OFFSET@h + rlwinm r10, r10, 16, 0xfff8 + cmpli cr0, r10, PAGE_OFFSET@h #ifndef CONFIG_PIN_TLB_TEXT /* It is assumed that kernel code fits into the first 8M page */ -0: cmpli cr7, r11, (PAGE_OFFSET + 0x0800000)@h +0: cmpli cr7, r10, (PAGE_OFFSET + 0x0800000)@h patch_site 0b, patch__itlbmiss_linmem_top #endif #endif #endif - mfspr r11, SPRN_M_TW /* Get level 1 table */ + mfspr r10, SPRN_M_TWB /* Get level 1 table */ #ifdef ITLB_MISS_KERNEL #if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT) - beq+ 3f + bge+ 3f #else blt+ 3f #endif #ifndef CONFIG_PIN_TLB_TEXT blt cr7, ITLBMissLinear #endif - lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha + rlwinm r10, r10, 0, 20, 31 + oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha 3: #endif - /* Insert level 1 index */ - rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 - lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ + mtspr SPRN_MI_TWC, r10 /* Set segment attributes */ - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 -#ifdef CONFIG_HUGETLB_PAGE - mtcr r11 - bt- 28, 10f /* bit 28 = Large page (8M) */ - bt- 29, 20f /* bit 29 = Large page (8M or 512k) */ -#endif - rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ + mtspr SPRN_MD_TWC, r10 + mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ -4: -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mtcr r12 +#ifdef ITLB_MISS_KERNEL + mtcr r11 #endif - /* Load the MI_TWC with the attributes for this "segment." */ - mtspr SPRN_MI_TWC, r11 /* Set segment attributes */ - #ifdef CONFIG_SWAP rlwinm r11, r10, 32-5, _PAGE_PRESENT and r11, r11, r10 rlwimi r10, r11, 0, _PAGE_PRESENT #endif - li r11, RPN_PATTERN | 0x200 /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 20 and 23 must be clear. * Software indicator bits 22, 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior * of the MMU. */ - rlwimi r11, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ - rlwimi r10, r11, 0, 0x0ff0 /* Set 22, 24-27, clear 20,23 */ + rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */ + rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ + ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ /* Restore registers */ 0: mfspr r10, SPRN_SPRG_SCRATCH0 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mfspr r11, SPRN_SPRG_SCRATCH1 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mfspr r12, SPRN_SPRG_SCRATCH2 #endif rfi patch_site 0b, patch__itlbmiss_exit_1 #ifdef CONFIG_PERF_EVENTS patch_site 0f, patch__itlbmiss_perf -0: lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha - lwz r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) - addi r11, r11, 1 - stw r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) -#endif +0: lwz r10, (itlb_miss_counter - PAGE_OFFSET)@l(0) + addi r10, r10, 1 + stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0) mfspr r10, SPRN_SPRG_SCRATCH0 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mfspr r11, SPRN_SPRG_SCRATCH1 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mfspr r12, SPRN_SPRG_SCRATCH2 #endif rfi - -#ifdef CONFIG_HUGETLB_PAGE -10: /* 8M pages */ -#ifdef CONFIG_PPC_16K_PAGES - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 - /* Add level 2 base */ - rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 -#else - /* Level 2 base */ - rlwinm r10, r11, 0, ~HUGEPD_SHIFT_MASK #endif - lwz r10, 0(r10) /* Get the pte */ - b 4b -20: /* 512k pages */ - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 - /* Add level 2 base */ - rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 - lwz r10, 0(r10) /* Get the pte */ - b 4b +#ifndef CONFIG_PIN_TLB_TEXT +ITLBMissLinear: + mtcr r11 + /* Set 8M byte page and mark it valid */ + li r11, MI_PS8MEG | MI_SVALID + mtspr SPRN_MI_TWC, r11 + rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */ + ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ + _PAGE_PRESENT + mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ + +0: mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + rfi + patch_site 0b, patch__itlbmiss_exit_2 #endif . = 0x1200 DataStoreTLBMiss: mtspr SPRN_SPRG_SCRATCH0, r10 mtspr SPRN_SPRG_SCRATCH1, r11 - mtspr SPRN_SPRG_SCRATCH2, r12 - mfcr r12 + mfcr r11 /* If we are faulting a kernel address, we have to use the * kernel page tables. */ mfspr r10, SPRN_MD_EPN - rlwinm r11, r10, 16, 0xfff8 - cmpli cr0, r11, PAGE_OFFSET@h - mfspr r11, SPRN_M_TW /* Get level 1 table */ - blt+ 3f - rlwinm r11, r10, 16, 0xfff8 + rlwinm r10, r10, 16, 0xfff8 + cmpli cr0, r10, PAGE_OFFSET@h #ifndef CONFIG_PIN_TLB_IMMR - cmpli cr0, r11, VIRT_IMMR_BASE@h + cmpli cr6, r10, VIRT_IMMR_BASE@h #endif -0: cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h +0: cmpli cr7, r10, (PAGE_OFFSET + 0x1800000)@h patch_site 0b, patch__dtlbmiss_linmem_top + + mfspr r10, SPRN_M_TWB /* Get level 1 table */ + blt+ 3f #ifndef CONFIG_PIN_TLB_IMMR -0: beq- DTLBMissIMMR +0: beq- cr6, DTLBMissIMMR patch_site 0b, patch__dtlbmiss_immr_jmp #endif blt cr7, DTLBMissLinear - lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha + rlwinm r10, r10, 0, 20, 31 + oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha 3: - - /* Insert level 1 index */ - rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 - lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ - - /* We have a pte table, so load fetch the pte from the table. - */ - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 -#ifdef CONFIG_HUGETLB_PAGE mtcr r11 - bt- 28, 10f /* bit 28 = Large page (8M) */ - bt- 29, 20f /* bit 29 = Large page (8M or 512k) */ -#endif - rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ + lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ + + mtspr SPRN_MD_TWC, r11 + mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ -4: - mtcr r12 /* Insert the Guarded flag into the TWC from the Linux PTE. * It is bit 27 of both the Linux PTE and the TWC (at least @@ -503,44 +491,55 @@ DataStoreTLBMiss: 0: mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 rfi patch_site 0b, patch__dtlbmiss_exit_1 #ifdef CONFIG_PERF_EVENTS patch_site 0f, patch__dtlbmiss_perf -0: lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha - lwz r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) - addi r11, r11, 1 - stw r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) -#endif +0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) + addi r10, r10, 1 + stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 rfi - -#ifdef CONFIG_HUGETLB_PAGE -10: /* 8M pages */ - /* Extract level 2 index */ -#ifdef CONFIG_PPC_16K_PAGES - rlwinm r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 - /* Add level 2 base */ - rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 -#else - /* Level 2 base */ - rlwinm r10, r11, 0, ~HUGEPD_SHIFT_MASK #endif - lwz r10, 0(r10) /* Get the pte */ - b 4b -20: /* 512k pages */ - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 - /* Add level 2 base */ - rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 - lwz r10, 0(r10) /* Get the pte */ - b 4b -#endif +DTLBMissIMMR: + mtcr r11 + /* Set 512k byte guarded page and mark it valid */ + li r10, MD_PS512K | MD_GUARDED | MD_SVALID + mtspr SPRN_MD_TWC, r10 + mfspr r10, SPRN_IMMR /* Get current IMMR */ + rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */ + ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ + _PAGE_PRESENT | _PAGE_NO_CACHE + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ + + li r11, RPN_PATTERN + mtspr SPRN_DAR, r11 /* Tag DAR */ + +0: mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + rfi + patch_site 0b, patch__dtlbmiss_exit_2 + +DTLBMissLinear: + mtcr r11 + /* Set 8M byte page and mark it valid */ + li r11, MD_PS8MEG | MD_SVALID + mtspr SPRN_MD_TWC, r11 + rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */ + ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ + _PAGE_PRESENT + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ + + li r11, RPN_PATTERN + mtspr SPRN_DAR, r11 /* Tag DAR */ + +0: mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + rfi + patch_site 0b, patch__dtlbmiss_exit_3 /* This is an instruction TLB error on the MPC8xx. This could be due * to many reasons, such as executing guarded memory or illegal instruction @@ -625,16 +624,13 @@ DataBreakpoint: . = 0x1d00 InstructionBreakpoint: mtspr SPRN_SPRG_SCRATCH0, r10 - mtspr SPRN_SPRG_SCRATCH1, r11 - lis r10, (instruction_counter - PAGE_OFFSET)@ha - lwz r11, (instruction_counter - PAGE_OFFSET)@l(r10) - addi r11, r11, -1 - stw r11, (instruction_counter - PAGE_OFFSET)@l(r10) + lwz r10, (instruction_counter - PAGE_OFFSET)@l(0) + addi r10, r10, -1 + stw r10, (instruction_counter - PAGE_OFFSET)@l(0) lis r10, 0xffff ori r10, r10, 0x01 mtspr SPRN_COUNTA, r10 mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 rfi #else EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE) @@ -644,67 +640,6 @@ InstructionBreakpoint: . = 0x2000 -/* - * Bottom part of DataStoreTLBMiss handlers for IMMR area and linear RAM. - * not enough space in the DataStoreTLBMiss area. - */ -DTLBMissIMMR: - mtcr r12 - /* Set 512k byte guarded page and mark it valid */ - li r10, MD_PS512K | MD_GUARDED | MD_SVALID - mtspr SPRN_MD_TWC, r10 - mfspr r10, SPRN_IMMR /* Get current IMMR */ - rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */ - ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ - _PAGE_PRESENT | _PAGE_NO_CACHE - mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ - - li r11, RPN_PATTERN - mtspr SPRN_DAR, r11 /* Tag DAR */ - -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 - rfi - patch_site 0b, patch__dtlbmiss_exit_2 - -DTLBMissLinear: - mtcr r12 - /* Set 8M byte page and mark it valid */ - li r11, MD_PS8MEG | MD_SVALID - mtspr SPRN_MD_TWC, r11 - rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ - ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ - _PAGE_PRESENT - mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ - - li r11, RPN_PATTERN - mtspr SPRN_DAR, r11 /* Tag DAR */ - -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 - rfi - patch_site 0b, patch__dtlbmiss_exit_3 - -#ifndef CONFIG_PIN_TLB_TEXT -ITLBMissLinear: - mtcr r12 - /* Set 8M byte page and mark it valid */ - li r11, MI_PS8MEG | MI_SVALID - mtspr SPRN_MI_TWC, r11 - rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ - ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ - _PAGE_PRESENT - mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ - -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 - rfi - patch_site 0b, patch__itlbmiss_exit_2 -#endif - /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions * by decoding the registers used by the dcbx instruction and adding them. * DAR is set to the calculated address. @@ -712,12 +647,13 @@ ITLBMissLinear: /* define if you don't want to use self modifying code */ #define NO_SELF_MODIFYING_CODE FixupDAR:/* Entry point for dcbx workaround. */ - mtspr SPRN_SPRG_SCRATCH2, r10 + mtspr SPRN_M_TW, r10 /* fetch instruction from memory. */ mfspr r10, SPRN_SRR0 + mtspr SPRN_MD_EPN, r10 rlwinm r11, r10, 16, 0xfff8 cmpli cr0, r11, PAGE_OFFSET@h - mfspr r11, SPRN_M_TW /* Get level 1 table */ + mfspr r11, SPRN_M_TWB /* Get level 1 table */ blt+ 3f rlwinm r11, r10, 16, 0xfff8 @@ -727,17 +663,17 @@ FixupDAR:/* Entry point for dcbx workaround. */ /* create physical page address from effective address */ tophys(r11, r10) blt- cr7, 201f - lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha - /* Insert level 1 index */ -3: rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 + mfspr r11, SPRN_M_TWB /* Get level 1 table */ + rlwinm r11, r11, 0, 20, 31 + oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha +3: lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + mtspr SPRN_MD_TWC, r11 mtcr r11 + mfspr r11, SPRN_MD_TWC + lwz r11, 0(r11) /* Get the pte */ bt 28,200f /* bit 28 = Large page (8M) */ bt 29,202f /* bit 29 = Large page (8M or 512K) */ - rlwinm r11, r11,0,0,19 /* Extract page descriptor page address */ - /* Insert level 2 index */ - rlwimi r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 - lwz r11, 0(r11) /* Get the pte */ /* concat physical page address(r11) and page offset(r10) */ rlwimi r11, r10, 0, 32 - PAGE_SHIFT, 31 201: lwz r11,0(r11) @@ -756,26 +692,15 @@ FixupDAR:/* Entry point for dcbx workaround. */ beq+ 142f cmpwi cr0, r10, 1964 /* Is icbi? */ beq+ 142f -141: mfspr r10,SPRN_SPRG_SCRATCH2 +141: mfspr r10,SPRN_M_TW b DARFixed /* Nope, go back to normal TLB processing */ - /* concat physical page address(r11) and page offset(r10) */ 200: -#ifdef CONFIG_PPC_16K_PAGES - rlwinm r11, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 - rlwimi r11, r10, 32 - (PAGE_SHIFT_8M - 2), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 -#else - rlwinm r11, r10, 0, ~HUGEPD_SHIFT_MASK -#endif - lwz r11, 0(r11) /* Get the pte */ /* concat physical page address(r11) and page offset(r10) */ rlwimi r11, r10, 0, 32 - PAGE_SHIFT_8M, 31 b 201b 202: - rlwinm r11, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 - rlwimi r11, r10, 32 - (PAGE_SHIFT_512K - 2), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 - lwz r11, 0(r11) /* Get the pte */ /* concat physical page address(r11) and page offset(r10) */ rlwimi r11, r10, 0, 32 - PAGE_SHIFT_512K, 31 b 201b @@ -802,7 +727,7 @@ modified_instr: bne+ 143f subf r10,r0,r10 /* r10=r10-r0, only if reg RA is r0 */ 143: mtdar r10 /* store faulting EA in DAR */ - mfspr r10,SPRN_SPRG_SCRATCH2 + mfspr r10,SPRN_M_TW b DARFixed /* Go back to normal TLB handling */ #else mfctr r10 @@ -856,7 +781,7 @@ modified_instr: mfdar r11 mtctr r11 /* restore ctr reg from DAR */ mtdar r10 /* save fault EA to DAR */ - mfspr r10,SPRN_SPRG_SCRATCH2 + mfspr r10,SPRN_M_TW b DARFixed /* Go back to normal TLB handling */ /* special handling for r10,r11 since these are modified already */ @@ -891,7 +816,7 @@ start_here: lis r6, swapper_pg_dir@ha tophys(r6,r6) - mtspr SPRN_M_TW, r6 + mtspr SPRN_M_TWB, r6 bl early_init /* We have to do this with MMU on */ @@ -1065,17 +990,3 @@ swapper_pg_dir: */ abatron_pteptrs: .space 8 - -#ifdef CONFIG_PERF_EVENTS - .globl itlb_miss_counter -itlb_miss_counter: - .space 4 - - .globl dtlb_miss_counter -dtlb_miss_counter: - .space 4 - - .globl instruction_counter -instruction_counter: - .space 4 -#endif diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h @@ -43,6 +43,9 @@ andi. r11, r11, MSR_PR; /* check whether user or kernel */\ mr r11, r1; \ beq 1f; \ +START_BTB_FLUSH_SECTION \ + BTB_FLUSH(r11) \ +END_BTB_FLUSH_SECTION \ /* if from user, start at top of this thread's kernel stack */ \ lwz r11, THREAD_INFO-THREAD(r10); \ ALLOC_STACK_FRAME(r11, THREAD_SIZE); \ @@ -128,6 +131,9 @@ stw r9,_CCR(r8); /* save CR on stack */\ mfspr r11,exc_level_srr1; /* check whether user or kernel */\ DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \ +START_BTB_FLUSH_SECTION \ + BTB_FLUSH(r10) \ +END_BTB_FLUSH_SECTION \ andi. r11,r11,MSR_PR; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S @@ -453,6 +453,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) DO_KVM BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1 +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION mfspr r10, SPRN_DEAR /* Get faulting address */ /* If we are faulting a kernel address, we have to use the @@ -547,6 +554,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) DO_KVM BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1 +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION + mfspr r10, SPRN_SRR0 /* Get faulting address */ /* If we are faulting a kernel address, we have to use the diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c @@ -47,6 +47,7 @@ #include <asm/fadump.h> #include <asm/vio.h> #include <asm/tce.h> +#include <asm/mmu_context.h> #define DBG(...) @@ -993,15 +994,19 @@ int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa) } 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) +long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, + unsigned long entry, unsigned long *hpa, + enum dma_data_direction *direction) { long ret; + unsigned long size = 0; ret = tbl->it_ops->exchange(tbl, entry, hpa, direction); if (!ret && ((*direction == DMA_FROM_DEVICE) || - (*direction == DMA_BIDIRECTIONAL))) + (*direction == DMA_BIDIRECTIONAL)) && + !mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift, + &size)) SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT)); /* if (unlikely(ret)) @@ -1073,11 +1078,8 @@ void iommu_release_ownership(struct iommu_table *tbl) } EXPORT_SYMBOL_GPL(iommu_release_ownership); -int iommu_add_device(struct device *dev) +int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) { - struct iommu_table *tbl; - struct iommu_table_group_link *tgl; - /* * The sysfs entries should be populated before * binding IOMMU group. If sysfs entries isn't @@ -1093,32 +1095,10 @@ int iommu_add_device(struct device *dev) return -EBUSY; } - tbl = get_iommu_table_base(dev); - if (!tbl) { - pr_debug("%s: Skipping device %s with no tbl\n", - __func__, dev_name(dev)); - return 0; - } - - tgl = list_first_entry_or_null(&tbl->it_group_list, - struct iommu_table_group_link, next); - if (!tgl) { - pr_debug("%s: Skipping device %s with no group\n", - __func__, dev_name(dev)); - return 0; - } pr_debug("%s: Adding %s to iommu group %d\n", - __func__, dev_name(dev), - iommu_group_id(tgl->table_group->group)); - - if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) { - pr_err("%s: Invalid IOMMU page size %lx (%lx) on %s\n", - __func__, IOMMU_PAGE_SIZE(tbl), - PAGE_SIZE, dev_name(dev)); - return -EINVAL; - } + __func__, dev_name(dev), iommu_group_id(table_group->group)); - return iommu_group_add_device(tgl->table_group->group, dev); + return iommu_group_add_device(table_group->group, dev); } EXPORT_SYMBOL_GPL(iommu_add_device); @@ -1138,31 +1118,4 @@ void iommu_del_device(struct device *dev) iommu_group_remove_device(dev); } EXPORT_SYMBOL_GPL(iommu_del_device); - -static int tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - return iommu_add_device(dev); - case BUS_NOTIFY_DEL_DEVICE: - if (dev->iommu_group) - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = tce_iommu_bus_notifier, -}; - -int __init tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} #endif /* CONFIG_IOMMU_API */ diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c @@ -327,8 +327,7 @@ static int isa_bridge_notify(struct notifier_block *nb, unsigned long action, /* Check if we have no ISA device, and this happens to be one, * register it as such if it has an OF device */ - if (!isa_bridge_devnode && devnode && devnode->type && - !strcmp(devnode->type, "isa")) + if (!isa_bridge_devnode && of_node_is_type(devnode, "isa")) isa_bridge_find_late(pdev, devnode); return 0; diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c @@ -192,7 +192,7 @@ static int __init add_legacy_soc_port(struct device_node *np, /* Add port, irq will be dealt with later. We passed a translated * IO port value. It will be fixed up later along with the irq */ - if (tsi && !strcmp(tsi->type, "tsi-bridge")) + if (of_node_is_type(tsi, "tsi-bridge")) return add_legacy_port(np, -1, UPIO_TSI, addr, addr, 0, legacy_port_flags, 0); else @@ -400,8 +400,7 @@ void __init find_legacy_serial_ports(void) /* Next, fill our array with ISA ports */ for_each_node_by_type(np, "serial") { struct device_node *isa = of_get_parent(np); - if (isa && (!strcmp(isa->name, "isa") || - !strcmp(isa->name, "lpc"))) { + if (of_node_name_eq(isa, "isa") || of_node_name_eq(isa, "lpc")) { if (of_device_is_available(np)) { index = add_legacy_isa_port(np, isa); if (index >= 0 && np == stdout) @@ -415,11 +414,12 @@ void __init find_legacy_serial_ports(void) /* Next, try to locate PCI ports */ for (np = NULL; (np = of_find_all_nodes(np));) { struct device_node *pci, *parent = of_get_parent(np); - if (parent && !strcmp(parent->name, "isa")) { + if (of_node_name_eq(parent, "isa")) { of_node_put(parent); continue; } - if (strcmp(np->name, "serial") && strcmp(np->type, "serial")) { + if (!of_node_name_eq(np, "serial") && + !of_node_is_type(np, "serial")) { of_node_put(parent); continue; } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S @@ -153,7 +153,7 @@ _GLOBAL(call_setup_cpu) mtctr r5 bctr -#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_6xx) +#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_PPC_BOOK3S_32) /* This gets called by via-pmu.c to switch the PLL selection * on 750fx CPU. This function should really be moved to some @@ -223,7 +223,7 @@ _GLOBAL(low_choose_7447a_dfs) mtmsr r7 blr -#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_6xx */ +#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */ /* * complement mask on the msr then "or" some values on. diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c @@ -809,6 +809,7 @@ static long dev_nvram_ioctl(struct file *file, unsigned int cmd, #ifdef CONFIG_PPC_PMAC case OBSOLETE_PMAC_NVRAM_GET_OFFSET: printk(KERN_WARNING "nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n"); + /* fall through */ case IOC_NVRAM_GET_OFFSET: { int part, offset; diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c @@ -125,16 +125,13 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, struct pci_bus *bus, int devfn) { struct pci_dev *dev; - const char *type; dev = pci_alloc_dev(bus); if (!dev) return NULL; - type = of_get_property(node, "device_type", NULL); - if (type == NULL) - type = ""; - pr_debug(" create device, devfn: %x, type: %s\n", devfn, type); + pr_debug(" create device, devfn: %x, type: %s\n", devfn, + of_node_get_device_type(node)); dev->dev.of_node = of_node_get(node); dev->dev.parent = bus->bridge; @@ -167,12 +164,12 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, /* Early fixups, before probing the BARs */ pci_fixup_device(pci_fixup_early, dev); - if (!strcmp(type, "pci") || !strcmp(type, "pciex")) { + if (of_node_is_type(node, "pci") || of_node_is_type(node, "pciex")) { /* a PCI-PCI bridge */ dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; dev->rom_base_reg = PCI_ROM_ADDRESS1; set_pcie_hotplug_bridge(dev); - } else if (!strcmp(type, "cardbus")) { + } else if (of_node_is_type(node, "cardbus")) { dev->hdr_type = PCI_HEADER_TYPE_CARDBUS; } else { dev->hdr_type = PCI_HEADER_TYPE_NORMAL; diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c @@ -29,7 +29,7 @@ static void dummy_perf(struct pt_regs *regs) { #if defined(CONFIG_FSL_EMB_PERFMON) mtpmr(PMRN_PMGC0, mfpmr(PMRN_PMGC0) & ~PMGC0_PMIE); -#elif defined(CONFIG_PPC64) || defined(CONFIG_6xx) +#elif defined(CONFIG_PPC64) || defined(CONFIG_PPC_BOOK3S_32) if (cur_cpu_spec->pmc_type == PPC_PMC_IBM) mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~(MMCR0_PMXE|MMCR0_PMAO)); #else diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c @@ -124,12 +124,12 @@ static void __init move_device_tree(void) size = fdt_totalsize(initial_boot_params); if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) || - overlaps_crashkernel(start, size) || - overlaps_initrd(start, size)) { + !memblock_is_memory(start + size - 1) || + overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) { p = __va(memblock_phys_alloc(size, PAGE_SIZE)); memcpy(p, initial_boot_params, size); initial_boot_params = p; - DBG("Moved device tree to 0x%p\n", p); + DBG("Moved device tree to 0x%px\n", p); } DBG("<- move_device_tree\n"); @@ -689,7 +689,7 @@ void __init early_init_devtree(void *params) { phys_addr_t limit; - DBG(" -> early_init_devtree(%p)\n", params); + DBG(" -> early_init_devtree(%px)\n", params); /* Too early to BUG_ON(), do it by hand */ if (!early_init_dt_verify(params)) @@ -749,7 +749,7 @@ void __init early_init_devtree(void *params) memblock_allow_resize(); memblock_dump_all(); - DBG("Phys. mem: %llx\n", memblock_phys_mem_size()); + DBG("Phys. mem: %llx\n", (unsigned long long)memblock_phys_mem_size()); /* We may need to relocate the flat tree, do it now. * FIXME .. and the initrd too? */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c @@ -3263,32 +3263,40 @@ static inline int do_seccomp(struct pt_regs *regs) { return 0; } */ long do_syscall_trace_enter(struct pt_regs *regs) { + u32 flags; + user_exit(); - if (test_thread_flag(TIF_SYSCALL_EMU)) { - /* - * A nonzero return code from tracehook_report_syscall_entry() - * tells us to prevent the syscall execution, but we are not - * going to execute it anyway. - * - * Returning -1 will skip the syscall execution. We want to - * avoid clobbering any register also, thus, not 'gotoing' - * skip label. - */ - if (tracehook_report_syscall_entry(regs)) - ; - return -1; - } + flags = READ_ONCE(current_thread_info()->flags) & + (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE); - /* - * The tracer may decide to abort the syscall, if so tracehook - * will return !0. Note that the tracer may also just change - * regs->gpr[0] to an invalid syscall number, that is handled - * below on the exit path. - */ - if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - goto skip; + if (flags) { + int rc = tracehook_report_syscall_entry(regs); + + if (unlikely(flags & _TIF_SYSCALL_EMU)) { + /* + * A nonzero return code from + * tracehook_report_syscall_entry() tells us to prevent + * the syscall execution, but we are not going to + * execute it anyway. + * + * Returning -1 will skip the syscall execution. We want + * to avoid clobbering any registers, so we don't goto + * the skip label below. + */ + return -1; + } + + if (rc) { + /* + * The tracer decided to abort the syscall. Note that + * the tracer may also just change regs->gpr[0] to an + * invalid syscall number, that is handled below on the + * exit path. + */ + goto skip; + } + } /* Run seccomp after ptrace; allow it to set gpr[3]. */ if (do_seccomp(regs)) diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c @@ -4,6 +4,7 @@ // // Copyright 2018, Michael Ellerman, IBM Corporation. +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/device.h> #include <linux/seq_buf.h> @@ -22,10 +23,14 @@ enum count_cache_flush_type { COUNT_CACHE_FLUSH_SW = 0x2, COUNT_CACHE_FLUSH_HW = 0x4, }; -static enum count_cache_flush_type count_cache_flush_type; +static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; bool barrier_nospec_enabled; static bool no_nospec; +static bool btb_flush_enabled; +#ifdef CONFIG_PPC_FSL_BOOK3E +static bool no_spectrev2; +#endif static void enable_barrier_nospec(bool enable) { @@ -101,6 +106,23 @@ static __init int barrier_nospec_debugfs_init(void) device_initcall(barrier_nospec_debugfs_init); #endif /* CONFIG_DEBUG_FS */ +#ifdef CONFIG_PPC_FSL_BOOK3E +static int __init handle_nospectre_v2(char *p) +{ + no_spectrev2 = true; + + return 0; +} +early_param("nospectre_v2", handle_nospectre_v2); +void setup_spectre_v2(void) +{ + if (no_spectrev2) + do_btb_flush_fixups(); + else + btb_flush_enabled = true; +} +#endif /* CONFIG_PPC_FSL_BOOK3E */ + #ifdef CONFIG_PPC_BOOK3S_64 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { @@ -191,8 +213,11 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) seq_buf_printf(&s, "(hardware accelerated)"); - } else + } else if (btb_flush_enabled) { + seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); + } else { seq_buf_printf(&s, "Vulnerable"); + } seq_buf_printf(&s, "\n"); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c @@ -687,7 +687,7 @@ int check_legacy_ioport(unsigned long base_port) return ret; parent = of_get_parent(np); if (parent) { - if (strcmp(parent->type, "isa") == 0) + if (of_node_is_type(parent, "isa")) ret = 0; of_node_put(parent); } @@ -800,7 +800,7 @@ static __init void print_system_info(void) #ifdef CONFIG_PPC_BOOK3S_64 pr_info("ppc64_pft_size = 0x%llx\n", ppc64_pft_size); #endif -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 pr_info("Hash_size = 0x%lx\n", Hash_size); #endif pr_info("phys_mem_size = 0x%llx\n", @@ -830,7 +830,7 @@ static __init void print_system_info(void) if (htab_hash_mask) pr_info("htab_hash_mask = 0x%lx\n", htab_hash_mask); #endif -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 if (Hash) pr_info("Hash = 0x%p\n", Hash); if (Hash_mask) @@ -974,6 +974,7 @@ void __init setup_arch(char **cmdline_p) ppc_md.setup_arch(); setup_barrier_nospec(); + setup_spectre_v2(); paging_init(); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c @@ -59,7 +59,6 @@ unsigned long ISA_DMA_THRESHOLD; unsigned int DMA_MODE_READ; unsigned int DMA_MODE_WRITE; -EXPORT_SYMBOL(ISA_DMA_THRESHOLD); EXPORT_SYMBOL(DMA_MODE_READ); EXPORT_SYMBOL(DMA_MODE_WRITE); @@ -101,8 +100,7 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) */ notrace void __init machine_init(u64 dt_ptr) { - unsigned int *addr = (unsigned int *)((unsigned long)&patch__memset_nocache + - patch__memset_nocache); + unsigned int *addr = (unsigned int *)patch_site_addr(&patch__memset_nocache); unsigned long insn; /* Configure static keys first, now that we're relocated. */ @@ -240,7 +238,7 @@ void __init exc_lvl_early_init(void) void __init setup_power_save(void) { -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 if (cpu_has_feature(CPU_FTR_CAN_DOZE) || cpu_has_feature(CPU_FTR_CAN_NAP)) ppc_md.power_save = ppc6xx_idle; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c @@ -470,9 +470,9 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, return 1; if (sigret) { - /* Set up the sigreturn trampoline: li r0,sigret; sc */ - if (__put_user(0x38000000UL + sigret, &frame->tramp[0]) - || __put_user(0x44000002UL, &frame->tramp[1])) + /* Set up the sigreturn trampoline: li 0,sigret; sc */ + if (__put_user(PPC_INST_ADDI + sigret, &frame->tramp[0]) + || __put_user(PPC_INST_SC, &frame->tramp[1])) return 1; flush_icache_range((unsigned long) &frame->tramp[0], (unsigned long) &frame->tramp[2]); @@ -619,9 +619,9 @@ static int save_tm_user_regs(struct pt_regs *regs, if (__put_user(msr, &frame->mc_gregs[PT_MSR])) return 1; if (sigret) { - /* Set up the sigreturn trampoline: li r0,sigret; sc */ - if (__put_user(0x38000000UL + sigret, &frame->tramp[0]) - || __put_user(0x44000002UL, &frame->tramp[1])) + /* Set up the sigreturn trampoline: li 0,sigret; sc */ + if (__put_user(PPC_INST_ADDI + sigret, &frame->tramp[0]) + || __put_user(PPC_INST_SC, &frame->tramp[1])) return 1; flush_icache_range((unsigned long) &frame->tramp[0], (unsigned long) &frame->tramp[2]); @@ -848,7 +848,23 @@ static long restore_tm_user_regs(struct pt_regs *regs, /* If TM bits are set to the reserved value, it's an invalid context */ if (MSR_TM_RESV(msr_hi)) return 1; - /* Pull in the MSR TM bits from the user context */ + + /* + * Disabling preemption, since it is unsafe to be preempted + * with MSR[TS] set without recheckpointing. + */ + preempt_disable(); + + /* + * CAUTION: + * After regs->MSR[TS] being updated, make sure that get_user(), + * put_user() or similar functions are *not* called. These + * functions can generate page faults which will cause the process + * to be de-scheduled with MSR[TS] set but without calling + * tm_recheckpoint(). This can cause a bug. + * + * Pull in the MSR TM bits from the user context + */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK); /* Now, recheckpoint. This loads up all of the checkpointed (older) * registers, including FP and V[S]Rs. After recheckpointing, the @@ -873,6 +889,8 @@ static long restore_tm_user_regs(struct pt_regs *regs, } #endif + preempt_enable(); + return 0; } #endif @@ -1140,11 +1158,11 @@ SYSCALL_DEFINE0(rt_sigreturn) { struct rt_sigframe __user *rt_sf; struct pt_regs *regs = current_pt_regs(); + int tm_restore = 0; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM struct ucontext __user *uc_transact; unsigned long msr_hi; unsigned long tmp; - int tm_restore = 0; #endif /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -1192,11 +1210,19 @@ SYSCALL_DEFINE0(rt_sigreturn) goto bad; } } - if (!tm_restore) - /* Fall through, for non-TM restore */ + if (!tm_restore) { + /* + * Unset regs->msr because ucontext MSR TS is not + * set, and recheckpoint was not called. This avoid + * hitting a TM Bad thing at RFID + */ + regs->msr &= ~MSR_TS_MASK; + } + /* Fall through, for non-TM restore */ #endif - if (do_setcontext(&rt_sf->uc, regs, 1)) - goto bad; + if (!tm_restore) + if (do_setcontext(&rt_sf->uc, regs, 1)) + goto bad; /* * It's not clear whether or why it is desirable to save the diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c @@ -467,20 +467,6 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, if (MSR_TM_RESV(msr)) return -EINVAL; - /* pull in MSR TS bits from user context */ - regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); - - /* - * Ensure that TM is enabled in regs->msr before we leave the signal - * handler. It could be the case that (a) user disabled the TM bit - * through the manipulation of the MSR bits in uc_mcontext or (b) the - * TM bit was disabled because a sufficient number of context switches - * happened whilst in the signal handler and load_tm overflowed, - * disabling the TM bit. In either case we can end up with an illegal - * TM state leading to a TM Bad Thing when we return to userspace. - */ - regs->msr |= MSR_TM; - /* pull in MSR LE from user context */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); @@ -572,6 +558,34 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, tm_enable(); /* Make sure the transaction is marked as failed */ tsk->thread.tm_texasr |= TEXASR_FS; + + /* + * Disabling preemption, since it is unsafe to be preempted + * with MSR[TS] set without recheckpointing. + */ + preempt_disable(); + + /* pull in MSR TS bits from user context */ + regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); + + /* + * Ensure that TM is enabled in regs->msr before we leave the signal + * handler. It could be the case that (a) user disabled the TM bit + * through the manipulation of the MSR bits in uc_mcontext or (b) the + * TM bit was disabled because a sufficient number of context switches + * happened whilst in the signal handler and load_tm overflowed, + * disabling the TM bit. In either case we can end up with an illegal + * TM state leading to a TM Bad Thing when we return to userspace. + * + * CAUTION: + * After regs->MSR[TS] being updated, make sure that get_user(), + * put_user() or similar functions are *not* called. These + * functions can generate page faults which will cause the process + * to be de-scheduled with MSR[TS] set but without calling + * tm_recheckpoint(). This can cause a bug. + */ + regs->msr |= MSR_TM; + /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(&tsk->thread); @@ -585,6 +599,8 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, regs->msr |= MSR_VEC; } + preempt_enable(); + return err; } #endif @@ -598,11 +614,12 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp) long err = 0; /* addi r1, r1, __SIGNAL_FRAMESIZE # Pop the dummy stackframe */ - err |= __put_user(0x38210000UL | (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]); + err |= __put_user(PPC_INST_ADDI | __PPC_RT(R1) | __PPC_RA(R1) | + (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]); /* li r0, __NR_[rt_]sigreturn| */ - err |= __put_user(0x38000000UL | (syscall & 0xffff), &tramp[1]); + err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[1]); /* sc */ - err |= __put_user(0x44000002UL, &tramp[2]); + err |= __put_user(PPC_INST_SC, &tramp[2]); /* Minimal traceback info */ for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++) @@ -740,11 +757,23 @@ SYSCALL_DEFINE0(rt_sigreturn) &uc_transact->uc_mcontext)) goto badframe; } - else - /* Fall through, for non-TM restore */ #endif - if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext)) - goto badframe; + /* Fall through, for non-TM restore */ + if (!MSR_TM_ACTIVE(msr)) { + /* + * Unset MSR[TS] on the thread regs since MSR from user + * context does not have MSR active, and recheckpoint was + * not called since restore_tm_sigcontexts() was not called + * also. + * + * If not unsetting it, the code can RFID to userspace with + * MSR[TS] set, but without CPU in the proper state, + * causing a TM bad thing. + */ + current->thread.regs->msr &= ~MSR_TS_MASK; + if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext)) + goto badframe; + } if (restore_altstack(&uc->uc_stack)) goto badframe; diff --git a/arch/powerpc/kernel/syscalls/Makefile b/arch/powerpc/kernel/syscalls/Makefile @@ -0,0 +1,63 @@ +# SPDX-License-Identifier: GPL-2.0 +kapi := arch/$(SRCARCH)/include/generated/asm +uapi := arch/$(SRCARCH)/include/generated/uapi/asm + +_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ + $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') + +syscall := $(srctree)/$(src)/syscall.tbl +syshdr := $(srctree)/$(src)/syscallhdr.sh +systbl := $(srctree)/$(src)/syscalltbl.sh + +quiet_cmd_syshdr = SYSHDR $@ + cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \ + '$(syshdr_abis_$(basetarget))' \ + '$(syshdr_pfx_$(basetarget))' \ + '$(syshdr_offset_$(basetarget))' + +quiet_cmd_systbl = SYSTBL $@ + cmd_systbl = $(CONFIG_SHELL) '$(systbl)' '$<' '$@' \ + '$(systbl_abis_$(basetarget))' \ + '$(systbl_abi_$(basetarget))' \ + '$(systbl_offset_$(basetarget))' + +syshdr_abis_unistd_32 := common,nospu,32 +$(uapi)/unistd_32.h: $(syscall) $(syshdr) + $(call if_changed,syshdr) + +syshdr_abis_unistd_64 := common,nospu,64 +$(uapi)/unistd_64.h: $(syscall) $(syshdr) + $(call if_changed,syshdr) + +systbl_abis_syscall_table_32 := common,nospu,32 +systbl_abi_syscall_table_32 := 32 +$(kapi)/syscall_table_32.h: $(syscall) $(systbl) + $(call if_changed,systbl) + +systbl_abis_syscall_table_64 := common,nospu,64 +systbl_abi_syscall_table_64 := 64 +$(kapi)/syscall_table_64.h: $(syscall) $(systbl) + $(call if_changed,systbl) + +systbl_abis_syscall_table_c32 := common,nospu,32 +systbl_abi_syscall_table_c32 := c32 +$(kapi)/syscall_table_c32.h: $(syscall) $(systbl) + $(call if_changed,systbl) + +systbl_abis_syscall_table_spu := common,spu +systbl_abi_syscall_table_spu := spu +$(kapi)/syscall_table_spu.h: $(syscall) $(systbl) + $(call if_changed,systbl) + +uapisyshdr-y += unistd_32.h unistd_64.h +kapisyshdr-y += syscall_table_32.h \ + syscall_table_64.h \ + syscall_table_c32.h \ + syscall_table_spu.h + +targets += $(uapisyshdr-y) $(kapisyshdr-y) + +PHONY += all +all: $(addprefix $(uapi)/,$(uapisyshdr-y)) +all: $(addprefix $(kapi)/,$(kapisyshdr-y)) + @: diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -0,0 +1,427 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for powerpc +# +# The format is: +# <number> <abi> <name> <entry point> <compat entry point> +# +# The <abi> can be common, spu, nospu, 64, or 32 for this file. +# +0 nospu restart_syscall sys_restart_syscall +1 nospu exit sys_exit +2 nospu fork ppc_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open compat_sys_open +6 common close sys_close +7 common waitpid sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 nospu execve sys_execve compat_sys_execve +12 common chdir sys_chdir +13 common time sys_time compat_sys_time +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown +17 common break sys_ni_syscall +18 32 oldstat sys_stat sys_ni_syscall +18 64 oldstat sys_ni_syscall +18 spu oldstat sys_ni_syscall +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid +21 nospu mount sys_mount compat_sys_mount +22 32 umount sys_oldumount +22 64 umount sys_ni_syscall +22 spu umount sys_ni_syscall +23 common setuid sys_setuid +24 common getuid sys_getuid +25 common stime sys_stime compat_sys_stime +26 nospu ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm +28 32 oldfstat sys_fstat sys_ni_syscall +28 64 oldfstat sys_ni_syscall +28 spu oldfstat sys_ni_syscall +29 nospu pause sys_pause +30 nospu utime sys_utime compat_sys_utime +31 common stty sys_ni_syscall +32 common gtty sys_ni_syscall +33 common access sys_access +34 common nice sys_nice +35 common ftime sys_ni_syscall +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times compat_sys_times +44 common prof sys_ni_syscall +45 common brk sys_brk +46 common setgid sys_setgid +47 common getgid sys_getgid +48 nospu signal sys_signal +49 common geteuid sys_geteuid +50 common getegid sys_getegid +51 nospu acct sys_acct +52 nospu umount2 sys_umount +53 common lock sys_ni_syscall +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +56 common mpx sys_ni_syscall +57 common setpgid sys_setpgid +58 common ulimit sys_ni_syscall +59 32 oldolduname sys_olduname +59 64 oldolduname sys_ni_syscall +59 spu oldolduname sys_ni_syscall +60 common umask sys_umask +61 common chroot sys_chroot +62 nospu ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 32 sigaction sys_sigaction compat_sys_sigaction +67 64 sigaction sys_ni_syscall +67 spu sigaction sys_ni_syscall +68 common sgetmask sys_sgetmask +69 common ssetmask sys_ssetmask +70 common setreuid sys_setreuid +71 common setregid sys_setregid +72 32 sigsuspend sys_sigsuspend +72 64 sigsuspend sys_ni_syscall +72 spu sigsuspend sys_ni_syscall +73 32 sigpending sys_sigpending compat_sys_sigpending +73 64 sigpending sys_ni_syscall +73 spu sigpending sys_ni_syscall +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +76 32 getrlimit sys_old_getrlimit compat_sys_old_getrlimit +76 64 getrlimit sys_ni_syscall +76 spu getrlimit sys_ni_syscall +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 common getgroups sys_getgroups +81 common setgroups sys_setgroups +82 32 select ppc_select sys_ni_syscall +82 64 select sys_ni_syscall +82 spu select sys_ni_syscall +83 common symlink sys_symlink +84 32 oldlstat sys_lstat sys_ni_syscall +84 64 oldlstat sys_ni_syscall +84 spu oldlstat sys_ni_syscall +85 common readlink sys_readlink +86 nospu uselib sys_uselib +87 nospu swapon sys_swapon +88 nospu reboot sys_reboot +89 32 readdir sys_old_readdir compat_sys_old_readdir +89 64 readdir sys_ni_syscall +89 spu readdir sys_ni_syscall +90 common mmap sys_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +98 common profil sys_ni_syscall +99 nospu statfs sys_statfs compat_sys_statfs +100 nospu fstatfs sys_fstatfs compat_sys_fstatfs +101 common ioperm sys_ni_syscall +102 common socketcall sys_socketcall compat_sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common stat sys_newstat compat_sys_newstat +107 common lstat sys_newlstat compat_sys_newlstat +108 common fstat sys_newfstat compat_sys_newfstat +109 32 olduname sys_uname +109 64 olduname sys_ni_syscall +109 spu olduname sys_ni_syscall +110 common iopl sys_ni_syscall +111 common vhangup sys_vhangup +112 common idle sys_ni_syscall +113 common vm86 sys_ni_syscall +114 common wait4 sys_wait4 compat_sys_wait4 +115 nospu swapoff sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +117 nospu ipc sys_ipc compat_sys_ipc +118 common fsync sys_fsync +119 32 sigreturn sys_sigreturn compat_sys_sigreturn +119 64 sigreturn sys_ni_syscall +119 spu sigreturn sys_ni_syscall +120 nospu clone ppc_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +123 common modify_ldt sys_ni_syscall +124 common adjtimex sys_adjtimex compat_sys_adjtimex +125 common mprotect sys_mprotect +126 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask +126 64 sigprocmask sys_ni_syscall +126 spu sigprocmask sys_ni_syscall +127 common create_module sys_ni_syscall +128 nospu init_module sys_init_module +129 nospu delete_module sys_delete_module +130 common get_kernel_syms sys_ni_syscall +131 nospu quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_bdflush +135 common sysfs sys_sysfs +136 32 personality sys_personality ppc64_personality +136 64 personality ppc64_personality +136 spu personality ppc64_personality +137 common afs_syscall sys_ni_syscall +138 common setfsuid sys_setfsuid +139 common setfsgid sys_setfsgid +140 common _llseek sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 common _newselect sys_select compat_sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv compat_sys_readv +146 common writev sys_writev compat_sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 nospu _sysctl sys_sysctl compat_sys_sysctl +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval +162 common nanosleep sys_nanosleep compat_sys_nanosleep +163 common mremap sys_mremap +164 common setresuid sys_setresuid +165 common getresuid sys_getresuid +166 common query_module sys_ni_syscall +167 common poll sys_poll +168 common nfsservctl sys_ni_syscall +169 common setresgid sys_setresgid +170 common getresgid sys_getresgid +171 common prctl sys_prctl +172 nospu rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn +173 nospu rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +174 nospu rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +175 nospu rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +176 nospu rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +179 common pread64 sys_pread64 compat_sys_pread64 +180 common pwrite64 sys_pwrite64 compat_sys_pwrite64 +181 common chown sys_chown +182 common getcwd sys_getcwd +183 common capget sys_capget +184 common capset sys_capset +185 nospu sigaltstack sys_sigaltstack compat_sys_sigaltstack +186 32 sendfile sys_sendfile compat_sys_sendfile +186 64 sendfile sys_sendfile64 +186 spu sendfile sys_sendfile64 +187 common getpmsg sys_ni_syscall +188 common putpmsg sys_ni_syscall +189 nospu vfork ppc_vfork +190 common ugetrlimit sys_getrlimit compat_sys_getrlimit +191 common readahead sys_readahead compat_sys_readahead +192 32 mmap2 sys_mmap2 compat_sys_mmap2 +193 32 truncate64 sys_truncate64 compat_sys_truncate64 +194 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64 +195 32 stat64 sys_stat64 +196 32 lstat64 sys_lstat64 +197 32 fstat64 sys_fstat64 +198 nospu pciconfig_read sys_pciconfig_read +199 nospu pciconfig_write sys_pciconfig_write +200 nospu pciconfig_iobase sys_pciconfig_iobase +201 common multiplexer sys_ni_syscall +202 common getdents64 sys_getdents64 +203 common pivot_root sys_pivot_root +204 32 fcntl64 sys_fcntl64 compat_sys_fcntl64 +205 common madvise sys_madvise +206 common mincore sys_mincore +207 common gettid sys_gettid +208 common tkill sys_tkill +209 common setxattr sys_setxattr +210 common lsetxattr sys_lsetxattr +211 common fsetxattr sys_fsetxattr +212 common getxattr sys_getxattr +213 common lgetxattr sys_lgetxattr +214 common fgetxattr sys_fgetxattr +215 common listxattr sys_listxattr +216 common llistxattr sys_llistxattr +217 common flistxattr sys_flistxattr +218 common removexattr sys_removexattr +219 common lremovexattr sys_lremovexattr +220 common fremovexattr sys_fremovexattr +221 common futex sys_futex compat_sys_futex +222 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +223 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +# 224 unused +225 common tuxcall sys_ni_syscall +226 32 sendfile64 sys_sendfile64 compat_sys_sendfile64 +227 common io_setup sys_io_setup compat_sys_io_setup +228 common io_destroy sys_io_destroy +229 common io_getevents sys_io_getevents compat_sys_io_getevents +230 common io_submit sys_io_submit compat_sys_io_submit +231 common io_cancel sys_io_cancel +232 nospu set_tid_address sys_set_tid_address +233 common fadvise64 sys_fadvise64 ppc32_fadvise64 +234 nospu exit_group sys_exit_group +235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +236 common epoll_create sys_epoll_create +237 common epoll_ctl sys_epoll_ctl +238 common epoll_wait sys_epoll_wait +239 common remap_file_pages sys_remap_file_pages +240 common timer_create sys_timer_create compat_sys_timer_create +241 common timer_settime sys_timer_settime compat_sys_timer_settime +242 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +243 common timer_getoverrun sys_timer_getoverrun +244 common timer_delete sys_timer_delete +245 common clock_settime sys_clock_settime compat_sys_clock_settime +246 common clock_gettime sys_clock_gettime compat_sys_clock_gettime +247 common clock_getres sys_clock_getres compat_sys_clock_getres +248 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +249 32 swapcontext ppc_swapcontext ppc32_swapcontext +249 64 swapcontext ppc64_swapcontext +249 spu swapcontext sys_ni_syscall +250 common tgkill sys_tgkill +251 common utimes sys_utimes compat_sys_utimes +252 common statfs64 sys_statfs64 compat_sys_statfs64 +253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +254 32 fadvise64_64 ppc_fadvise64_64 +254 spu fadvise64_64 sys_ni_syscall +255 common rtas sys_rtas +256 32 sys_debug_setcontext sys_debug_setcontext sys_ni_syscall +256 64 sys_debug_setcontext sys_ni_syscall +256 spu sys_debug_setcontext sys_ni_syscall +# 257 reserved for vserver +258 nospu migrate_pages sys_migrate_pages compat_sys_migrate_pages +259 nospu mbind sys_mbind compat_sys_mbind +260 nospu get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +261 nospu set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +262 nospu mq_open sys_mq_open compat_sys_mq_open +263 nospu mq_unlink sys_mq_unlink +264 nospu mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend +265 nospu mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +266 nospu mq_notify sys_mq_notify compat_sys_mq_notify +267 nospu mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +268 nospu kexec_load sys_kexec_load compat_sys_kexec_load +269 nospu add_key sys_add_key +270 nospu request_key sys_request_key +271 nospu keyctl sys_keyctl compat_sys_keyctl +272 nospu waitid sys_waitid compat_sys_waitid +273 nospu ioprio_set sys_ioprio_set +274 nospu ioprio_get sys_ioprio_get +275 nospu inotify_init sys_inotify_init +276 nospu inotify_add_watch sys_inotify_add_watch +277 nospu inotify_rm_watch sys_inotify_rm_watch +278 nospu spu_run sys_spu_run +279 nospu spu_create sys_spu_create +280 nospu pselect6 sys_pselect6 compat_sys_pselect6 +281 nospu ppoll sys_ppoll compat_sys_ppoll +282 common unshare sys_unshare +283 common splice sys_splice +284 common tee sys_tee +285 common vmsplice sys_vmsplice compat_sys_vmsplice +286 common openat sys_openat compat_sys_openat +287 common mkdirat sys_mkdirat +288 common mknodat sys_mknodat +289 common fchownat sys_fchownat +290 common futimesat sys_futimesat compat_sys_futimesat +291 32 fstatat64 sys_fstatat64 +291 64 newfstatat sys_newfstatat +291 spu newfstatat sys_newfstatat +292 common unlinkat sys_unlinkat +293 common renameat sys_renameat +294 common linkat sys_linkat +295 common symlinkat sys_symlinkat +296 common readlinkat sys_readlinkat +297 common fchmodat sys_fchmodat +298 common faccessat sys_faccessat +299 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +301 common move_pages sys_move_pages compat_sys_move_pages +302 common getcpu sys_getcpu +303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +304 common utimensat sys_utimensat compat_sys_utimensat +305 common signalfd sys_signalfd compat_sys_signalfd +306 common timerfd_create sys_timerfd_create +307 common eventfd sys_eventfd +308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2 +309 nospu fallocate sys_fallocate compat_sys_fallocate +310 nospu subpage_prot sys_subpage_prot +311 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime +312 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +313 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +314 common eventfd2 sys_eventfd2 +315 common epoll_create1 sys_epoll_create1 +316 common dup3 sys_dup3 +317 common pipe2 sys_pipe2 +318 nospu inotify_init1 sys_inotify_init1 +319 common perf_event_open sys_perf_event_open +320 common preadv sys_preadv compat_sys_preadv +321 common pwritev sys_pwritev compat_sys_pwritev +322 nospu rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +323 nospu fanotify_init sys_fanotify_init +324 nospu fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +325 common prlimit64 sys_prlimit64 +326 common socket sys_socket +327 common bind sys_bind +328 common connect sys_connect +329 common listen sys_listen +330 common accept sys_accept +331 common getsockname sys_getsockname +332 common getpeername sys_getpeername +333 common socketpair sys_socketpair +334 common send sys_send +335 common sendto sys_sendto +336 common recv sys_recv compat_sys_recv +337 common recvfrom sys_recvfrom compat_sys_recvfrom +338 common shutdown sys_shutdown +339 common setsockopt sys_setsockopt compat_sys_setsockopt +340 common getsockopt sys_getsockopt compat_sys_getsockopt +341 common sendmsg sys_sendmsg compat_sys_sendmsg +342 common recvmsg sys_recvmsg compat_sys_recvmsg +343 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +344 common accept4 sys_accept4 +345 common name_to_handle_at sys_name_to_handle_at +346 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +347 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +348 common syncfs sys_syncfs +349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +350 common setns sys_setns +351 nospu process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv +352 nospu process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +353 nospu finit_module sys_finit_module +354 nospu kcmp sys_kcmp +355 common sched_setattr sys_sched_setattr +356 common sched_getattr sys_sched_getattr +357 common renameat2 sys_renameat2 +358 common seccomp sys_seccomp +359 common getrandom sys_getrandom +360 common memfd_create sys_memfd_create +361 common bpf sys_bpf +362 nospu execveat sys_execveat compat_sys_execveat +363 32 switch_endian sys_ni_syscall +363 64 switch_endian ppc_switch_endian +363 spu switch_endian sys_ni_syscall +364 common userfaultfd sys_userfaultfd +365 common membarrier sys_membarrier +378 nospu mlock2 sys_mlock2 +379 nospu copy_file_range sys_copy_file_range +380 common preadv2 sys_preadv2 compat_sys_preadv2 +381 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +382 nospu kexec_file_load sys_kexec_file_load +383 nospu statx sys_statx +384 nospu pkey_alloc sys_pkey_alloc +385 nospu pkey_free sys_pkey_free +386 nospu pkey_mprotect sys_pkey_mprotect +387 nospu rseq sys_rseq +388 nospu io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents diff --git a/arch/powerpc/kernel/syscalls/syscallhdr.sh b/arch/powerpc/kernel/syscalls/syscallhdr.sh @@ -0,0 +1,37 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +in="$1" +out="$2" +my_abis=`echo "($3)" | tr ',' '|'` +prefix="$4" +offset="$5" + +fileguard=_UAPI_ASM_POWERPC_`basename "$out" | sed \ + -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \ + -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'` +grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | ( + printf "#ifndef %s\n" "${fileguard}" + printf "#define %s\n" "${fileguard}" + printf "\n" + + nxt=0 + while read nr abi name entry compat ; do + if [ -z "$offset" ]; then + printf "#define __NR_%s%s\t%s\n" \ + "${prefix}" "${name}" "${nr}" + else + printf "#define __NR_%s%s\t(%s + %s)\n" \ + "${prefix}" "${name}" "${offset}" "${nr}" + fi + nxt=$((nr+1)) + done + + printf "\n" + printf "#ifdef __KERNEL__\n" + printf "#define __NR_syscalls\t%s\n" "${nxt}" + printf "#endif\n" + printf "\n" + printf "#endif /* %s */" "${fileguard}" + printf "\n" +) > "$out" diff --git a/arch/powerpc/kernel/syscalls/syscalltbl.sh b/arch/powerpc/kernel/syscalls/syscalltbl.sh @@ -0,0 +1,36 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +in="$1" +out="$2" +my_abis=`echo "($3)" | tr ',' '|'` +my_abi="$4" +offset="$5" + +emit() { + t_nxt="$1" + t_nr="$2" + t_entry="$3" + + while [ $t_nxt -lt $t_nr ]; do + printf "__SYSCALL(%s,sys_ni_syscall, )\n" "${t_nxt}" + t_nxt=$((t_nxt+1)) + done + printf "__SYSCALL(%s,%s, )\n" "${t_nxt}" "${t_entry}" +} + +grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | ( + nxt=0 + if [ -z "$offset" ]; then + offset=0 + fi + + while read nr abi name entry compat ; do + if [ "$my_abi" = "c32" ] && [ ! -z "$compat" ]; then + emit $((nxt+offset)) $((nr+offset)) $compat + else + emit $((nxt+offset)) $((nr+offset)) $entry + fi + nxt=$((nr+1)) + done +) > "$out" diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c @@ -457,7 +457,7 @@ static ssize_t __used \ #define HAS_PPC_PMC_CLASSIC 1 #define HAS_PPC_PMC_IBM 1 #define HAS_PPC_PMC_PA6T 1 -#elif defined(CONFIG_6xx) +#elif defined(CONFIG_PPC_BOOK3S_32) #define HAS_PPC_PMC_CLASSIC 1 #define HAS_PPC_PMC_IBM 1 #define HAS_PPC_PMC_G4 1 diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S @@ -16,28 +16,6 @@ #include <asm/ppc_asm.h> -#ifdef CONFIG_PPC64 -#define SYSCALL(func) .8byte DOTSYM(sys_##func),DOTSYM(sys_##func) -#define COMPAT_SYS(func) .8byte DOTSYM(sys_##func),DOTSYM(compat_sys_##func) -#define PPC_SYS(func) .8byte DOTSYM(ppc_##func),DOTSYM(ppc_##func) -#define OLDSYS(func) .8byte DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall) -#define SYS32ONLY(func) .8byte DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func) -#define PPC64ONLY(func) .8byte DOTSYM(ppc_##func),DOTSYM(sys_ni_syscall) -#define SYSX(f, f3264, f32) .8byte DOTSYM(f),DOTSYM(f3264) -#else -#define SYSCALL(func) .long sys_##func -#define COMPAT_SYS(func) .long sys_##func -#define PPC_SYS(func) .long ppc_##func -#define OLDSYS(func) .long sys_##func -#define SYS32ONLY(func) .long sys_##func -#define PPC64ONLY(func) .long sys_ni_syscall -#define SYSX(f, f3264, f32) .long f32 -#endif -#define SYSCALL_SPU(func) SYSCALL(func) -#define COMPAT_SYS_SPU(func) COMPAT_SYS(func) -#define COMPAT_SPU_NEW(func) COMPAT_SYS(func) -#define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) - .section .rodata,"a" #ifdef CONFIG_PPC64 @@ -46,5 +24,21 @@ .globl sys_call_table sys_call_table: +#ifdef CONFIG_PPC64 +#define __SYSCALL(nr, entry, nargs) .8byte DOTSYM(entry) +#include <asm/syscall_table_64.h> +#undef __SYSCALL +#else +#define __SYSCALL(nr, entry, nargs) .long entry +#include <asm/syscall_table_32.h> +#undef __SYSCALL +#endif -#include <asm/systbl.h> +#ifdef CONFIG_COMPAT +.globl compat_sys_call_table +compat_sys_call_table: +#define compat_sys_sigsuspend sys_sigsuspend +#define __SYSCALL(nr, entry, nargs) .8byte DOTSYM(entry) +#include <asm/syscall_table_c32.h> +#undef __SYSCALL +#endif diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c @@ -1,60 +0,0 @@ -/* - * This file, when run through CPP produces a list of syscall numbers - * in the order of systbl.h. That way we can check for gaps and syscalls - * that are out of order. - * - * Unfortunately, we cannot check for the correct ordering of entries - * using SYSX(). - * - * Copyright © 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 <asm/unistd.h> - -#define SYSCALL(func) __NR_##func -#define COMPAT_SYS(func) __NR_##func -#define PPC_SYS(func) __NR_##func -#ifdef CONFIG_PPC64 -#define OLDSYS(func) -1 -#define SYS32ONLY(func) -1 -#define PPC64ONLY(func) __NR_##func -#else -#define OLDSYS(func) __NR_old##func -#define SYS32ONLY(func) __NR_##func -#define PPC64ONLY(func) -1 -#endif -#define SYSX(f, f3264, f32) -1 - -#define SYSCALL_SPU(func) SYSCALL(func) -#define COMPAT_SYS_SPU(func) COMPAT_SYS(func) -#define COMPAT_SPU_NEW(func) COMPAT_SYS(_new##func) -#define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) - -/* Just insert a marker for ni_syscalls */ -#define __NR_ni_syscall -1 - -/* - * These are the known exceptions. - * Hopefully, there will be no more. - */ -#define __NR_llseek __NR__llseek -#undef __NR_umount -#define __NR_umount __NR_umount2 -#define __NR_old_getrlimit __NR_getrlimit -#define __NR_newstat __NR_stat -#define __NR_newlstat __NR_lstat -#define __NR_newfstat __NR_fstat -#define __NR_newuname __NR_uname -#define __NR_sysctl __NR__sysctl -#define __NR_olddebug_setcontext __NR_sys_debug_setcontext - -/* We call sys_ugetrlimit for syscall number __NR_getrlimit */ -#define getrlimit ugetrlimit - -START_TABLE -#include <asm/systbl.h> -END_TABLE NR_syscalls diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c @@ -107,7 +107,7 @@ static int is_b_op(unsigned int op) static unsigned long find_bl_target(unsigned long ip, unsigned int op) { - static int offset; + int offset; offset = (op & 0x03fffffc); /* make it signed */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c @@ -1434,7 +1434,8 @@ void program_check_exception(struct pt_regs *regs) goto bail; } else { printk(KERN_EMERG "Unexpected TM Bad Thing exception " - "at %lx (msr 0x%lx)\n", regs->nip, regs->msr); + "at %lx (msr 0x%lx) tm_scratch=%llx\n", + regs->nip, regs->msr, get_paca()->tm_scratch); die("Unrecoverable exception", regs, SIGABRT); } } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c @@ -671,15 +671,18 @@ static void __init vdso_setup_syscall_map(void) { unsigned int i; extern unsigned long *sys_call_table; +#ifdef CONFIG_PPC64 + extern unsigned long *compat_sys_call_table; +#endif extern unsigned long sys_ni_syscall; for (i = 0; i < NR_syscalls; i++) { #ifdef CONFIG_PPC64 - if (sys_call_table[i*2] != sys_ni_syscall) + if (sys_call_table[i] != sys_ni_syscall) vdso_data->syscall_map_64[i >> 5] |= 0x80000000UL >> (i & 0x1f); - if (sys_call_table[i*2+1] != sys_ni_syscall) + if (compat_sys_call_table[i] != sys_ni_syscall) vdso_data->syscall_map_32[i >> 5] |= 0x80000000UL >> (i & 0x1f); #else /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S @@ -170,6 +170,14 @@ SECTIONS } #endif /* CONFIG_PPC_BARRIER_NOSPEC */ +#ifdef CONFIG_PPC_FSL_BOOK3E + . = ALIGN(8); + __spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) { + __start__btb_flush_fixup = .; + *(__btb_flush_fixup) + __stop__btb_flush_fixup = .; + } +#endif EXCEPTION_TABLE(0) NOTES :kernel :notes @@ -206,12 +214,6 @@ SECTIONS .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) { INIT_DATA - __vtop_table_begin = .; - KEEP(*(.vtop_fixup)); - __vtop_table_end = .; - __ptov_table_begin = .; - KEEP(*(.ptov_fixup)); - __ptov_table_end = .; } .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) { @@ -308,6 +310,10 @@ SECTIONS #ifdef CONFIG_PPC32 .data : AT(ADDR(.data) - LOAD_OFFSET) { DATA_DATA +#ifdef CONFIG_UBSAN + *(.data..Lubsan_data*) + *(.data..Lubsan_type*) +#endif *(.data.rel*) *(SDATA_MAIN) *(.sdata2) diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c @@ -397,12 +397,13 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, return H_SUCCESS; } -static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry) +static void kvmppc_clear_tce(struct mm_struct *mm, 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); + iommu_tce_xchg(mm, tbl, entry, &hpa, &dir); } static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, @@ -433,7 +434,7 @@ static long kvmppc_tce_iommu_do_unmap(struct kvm *kvm, unsigned long hpa = 0; long ret; - if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir))) + if (WARN_ON_ONCE(iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir))) return H_TOO_HARD; if (dir == DMA_NONE) @@ -441,7 +442,7 @@ static long kvmppc_tce_iommu_do_unmap(struct kvm *kvm, ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry); if (ret != H_SUCCESS) - iommu_tce_xchg(tbl, entry, &hpa, &dir); + iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir); return ret; } @@ -487,7 +488,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (mm_iommu_mapped_inc(mem)) return H_TOO_HARD; - ret = iommu_tce_xchg(tbl, entry, &hpa, &dir); + ret = iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir); if (WARN_ON_ONCE(ret)) { mm_iommu_mapped_dec(mem); return H_TOO_HARD; @@ -566,7 +567,7 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, entry, ua, dir); if (ret != H_SUCCESS) { - kvmppc_clear_tce(stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); goto unlock_exit; } } @@ -655,7 +656,8 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_clear_tce(stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, + entry); goto unlock_exit; } } @@ -704,7 +706,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, return ret; WARN_ON_ONCE(1); - kvmppc_clear_tce(stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); } } diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S @@ -75,6 +75,10 @@ PPC_LL r1, VCPU_HOST_STACK(r4) PPC_LL r2, HOST_R2(r1) +START_BTB_FLUSH_SECTION + BTB_FLUSH(r10) +END_BTB_FLUSH_SECTION + mfspr r10, SPRN_PID lwz r8, VCPU_HOST_PID(r4) PPC_LL r11, VCPU_SHARED(r4) diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h @@ -20,7 +20,7 @@ #define KVM_E500_H #include <linux/kvm_host.h> -#include <asm/mmu-book3e.h> +#include <asm/nohash/mmu-book3e.h> #include <asm/tlb.h> #include <asm/cputhreads.h> diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c @@ -277,6 +277,13 @@ int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_va vcpu->arch.pwrmgtcr0 = spr_val; break; + case SPRN_BUCSR: + /* + * If we are here, it means that we have already flushed the + * branch predictor, so just return to guest. + */ + break; + /* extra exceptions */ #ifdef CONFIG_SPE_POSSIBLE case SPRN_IVOR32: diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c @@ -204,22 +204,6 @@ int patch_branch(unsigned int *addr, unsigned long target, int flags) return patch_instruction(addr, create_branch(addr, target, flags)); } -int patch_branch_site(s32 *site, unsigned long target, int flags) -{ - unsigned int *addr; - - addr = (unsigned int *)((unsigned long)site + *site); - return patch_instruction(addr, create_branch(addr, target, flags)); -} - -int patch_instruction_site(s32 *site, unsigned int instr) -{ - unsigned int *addr; - - addr = (unsigned int *)((unsigned long)site + *site); - return patch_instruction(addr, instr); -} - bool is_offset_in_branch_range(long offset) { /* diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c @@ -118,7 +118,7 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) } #ifdef CONFIG_PPC_BOOK3S_64 -void do_stf_entry_barrier_fixups(enum stf_barrier_type types) +static void do_stf_entry_barrier_fixups(enum stf_barrier_type types) { unsigned int instrs[3], *dest; long *start, *end; @@ -168,7 +168,7 @@ void do_stf_entry_barrier_fixups(enum stf_barrier_type types) : "unknown"); } -void do_stf_exit_barrier_fixups(enum stf_barrier_type types) +static void do_stf_exit_barrier_fixups(enum stf_barrier_type types) { unsigned int instrs[6], *dest; long *start, *end; @@ -347,6 +347,29 @@ void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_ printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); } + +static void patch_btb_flush_section(long *curr) +{ + unsigned int *start, *end; + + start = (void *)curr + *curr; + end = (void *)curr + *(curr + 1); + for (; start < end; start++) { + pr_devel("patching dest %lx\n", (unsigned long)start); + patch_instruction(start, PPC_INST_NOP); + } +} + +void do_btb_flush_fixups(void) +{ + long *start, *end; + + start = PTRRELOC(&__start__btb_flush_fixup); + end = PTRRELOC(&__stop__btb_flush_fixup); + + for (; start < end; start += 2) + patch_btb_flush_section(start); +} #endif /* CONFIG_PPC_FSL_BOOK3E */ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c @@ -29,6 +29,7 @@ #include <asm/mmu.h> #include <asm/page.h> #include <asm/cacheflush.h> +#include <asm/code-patching.h> #include "mmu_decl.h" @@ -43,22 +44,13 @@ unsigned long tlb_47x_boltmap[1024/8]; static void ppc44x_update_tlb_hwater(void) { - extern unsigned int tlb_44x_patch_hwater_D[]; - extern unsigned int tlb_44x_patch_hwater_I[]; - /* The TLB miss handlers hard codes the watermark in a cmpli * instruction to improve performances rather than loading it * from the global variable. Thus, we patch the instructions * in the 2 TLB miss handlers when updating the value */ - tlb_44x_patch_hwater_D[0] = (tlb_44x_patch_hwater_D[0] & 0xffff0000) | - tlb_44x_hwater; - flush_icache_range((unsigned long)&tlb_44x_patch_hwater_D[0], - (unsigned long)&tlb_44x_patch_hwater_D[1]); - tlb_44x_patch_hwater_I[0] = (tlb_44x_patch_hwater_I[0] & 0xffff0000) | - tlb_44x_hwater; - flush_icache_range((unsigned long)&tlb_44x_patch_hwater_I[0], - (unsigned long)&tlb_44x_patch_hwater_I[1]); + modify_instruction_site(&patch__tlb_44x_hwater_D, 0xffff, tlb_44x_hwater); + modify_instruction_site(&patch__tlb_44x_hwater_I, 0xffff, tlb_44x_hwater); } /* diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c @@ -100,11 +100,7 @@ static void __init mmu_mapin_immr(void) static void __init mmu_patch_cmp_limit(s32 *site, unsigned long mapped) { - unsigned int instr = *(unsigned int *)patch_site_addr(site); - - instr &= 0xffff0000; - instr |= (unsigned long)__va(mapped) >> 16; - patch_instruction_site(site, instr); + modify_instruction_site(site, 0xffff, (unsigned long)__va(mapped) >> 16); } unsigned long __init mmu_mapin_ram(unsigned long top) @@ -175,12 +171,12 @@ void set_context(unsigned long id, pgd_t *pgd) *(ptr + 1) = pgd; #endif - /* Register M_TW will contain base address of level 1 table minus the + /* Register M_TWB will contain base address of level 1 table minus the * lower part of the kernel PGDIR base address, so that all accesses to * level 1 table are done relative to lower part of kernel PGDIR base * address. */ - mtspr(SPRN_M_TW, __pa(pgd) - offset); + mtspr(SPRN_M_TWB, __pa(pgd) - offset); /* Update context */ mtspr(SPRN_M_CASID, id - 1); diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile @@ -15,10 +15,13 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(BITS)e.o hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o -obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb.o $(hash64-y) mmu_context_book3s64.o pgtable-book3s64.o +obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb.o \ + $(hash64-y) mmu_context_book3s64.o \ + pgtable-book3s64.o pgtable-frag.o +obj-$(CONFIG_PPC32) += pgtable-frag.o obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o -obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o -obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(BITS).o +obj-$(CONFIG_PPC_BOOK3S_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o +obj-$(CONFIG_PPC_BOOK3S) += tlb_hash$(BITS).o ifdef CONFIG_PPC_BOOK3S_64 obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o @@ -47,7 +50,7 @@ ifdef CONFIG_PPC_PTDUMP obj-$(CONFIG_4xx) += dump_linuxpagetables-generic.o obj-$(CONFIG_PPC_8xx) += dump_linuxpagetables-8xx.o obj-$(CONFIG_PPC_BOOK3E_MMU) += dump_linuxpagetables-generic.o -obj-$(CONFIG_PPC_BOOK3S_32) += dump_linuxpagetables-generic.o +obj-$(CONFIG_PPC_BOOK3S_32) += dump_linuxpagetables-generic.o dump_bats.o dump_sr.o obj-$(CONFIG_PPC_BOOK3S_64) += dump_linuxpagetables-book3s64.o endif obj-$(CONFIG_PPC_HTDUMP) += dump_hashpagetable.o diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c @@ -29,7 +29,7 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/highmem.h> -#include <linux/dma-mapping.h> +#include <linux/dma-direct.h> #include <linux/export.h> #include <asm/tlbflush.h> @@ -151,8 +151,8 @@ static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsi * Allocate DMA-coherent memory space and return both the kernel remapped * virtual and bus address for that space. */ -void * -__dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp) +void *__dma_nommu_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { struct page *page; struct ppc_vm_region *c; @@ -223,7 +223,7 @@ __dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t /* * Set the "dma handle" */ - *handle = page_to_phys(page); + *dma_handle = phys_to_dma(dev, page_to_phys(page)); do { SetPageReserved(page); @@ -249,12 +249,12 @@ __dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t no_page: return NULL; } -EXPORT_SYMBOL(__dma_alloc_coherent); /* * free a page as defined by the above mapping. */ -void __dma_free_coherent(size_t size, void *vaddr) +void __dma_nommu_free_coherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, unsigned long attrs) { struct ppc_vm_region *c; unsigned long flags, addr; @@ -309,7 +309,6 @@ void __dma_free_coherent(size_t size, void *vaddr) __func__, vaddr); dump_stack(); } -EXPORT_SYMBOL(__dma_free_coherent); /* * make an area consistent. @@ -401,7 +400,7 @@ EXPORT_SYMBOL(__dma_sync_page); /* * Return the PFN for a given cpu virtual address returned by - * __dma_alloc_coherent. This is used by dma_mmap_coherent() + * __dma_nommu_alloc_coherent. This is used by dma_mmap_coherent() */ unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr) { diff --git a/arch/powerpc/mm/dump_bats.c b/arch/powerpc/mm/dump_bats.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018, Christophe Leroy CS S.I. + * <christophe.leroy@c-s.fr> + * + * This dumps the content of BATS + */ + +#include <asm/debugfs.h> +#include <asm/pgtable.h> +#include <asm/cpu_has_feature.h> + +static char *pp_601(int k, int pp) +{ + if (pp == 0) + return k ? "NA" : "RWX"; + if (pp == 1) + return k ? "ROX" : "RWX"; + if (pp == 2) + return k ? "RWX" : "RWX"; + return k ? "ROX" : "ROX"; +} + +static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper) +{ + u32 blpi = upper & 0xfffe0000; + u32 k = (upper >> 2) & 3; + u32 pp = upper & 3; + phys_addr_t pbn = PHYS_BAT_ADDR(lower); + u32 bsm = lower & 0x3ff; + u32 size = (bsm + 1) << 17; + + seq_printf(m, "%d: ", idx); + if (!(lower & 0x40)) { + seq_puts(m, " -\n"); + return; + } + + seq_printf(m, "0x%08x-0x%08x ", blpi, blpi + size - 1); +#ifdef CONFIG_PHYS_64BIT + seq_printf(m, "0x%016llx ", pbn); +#else + seq_printf(m, "0x%08x ", pbn); +#endif + + seq_printf(m, "Kernel %s User %s", pp_601(k & 2, pp), pp_601(k & 1, pp)); + + if (lower & _PAGE_WRITETHRU) + seq_puts(m, "write through "); + if (lower & _PAGE_NO_CACHE) + seq_puts(m, "no cache "); + if (lower & _PAGE_COHERENT) + seq_puts(m, "coherent "); + seq_puts(m, "\n"); +} + +#define BAT_SHOW_601(_m, _n, _l, _u) bat_show_601(_m, _n, mfspr(_l), mfspr(_u)) + +static int bats_show_601(struct seq_file *m, void *v) +{ + seq_puts(m, "---[ Block Address Translation ]---\n"); + + BAT_SHOW_601(m, 0, SPRN_IBAT0L, SPRN_IBAT0U); + BAT_SHOW_601(m, 1, SPRN_IBAT1L, SPRN_IBAT1U); + BAT_SHOW_601(m, 2, SPRN_IBAT2L, SPRN_IBAT2U); + BAT_SHOW_601(m, 3, SPRN_IBAT3L, SPRN_IBAT3U); + + return 0; +} + +static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool is_d) +{ + u32 bepi = upper & 0xfffe0000; + u32 bl = (upper >> 2) & 0x7ff; + u32 k = upper & 3; + phys_addr_t brpn = PHYS_BAT_ADDR(lower); + u32 size = (bl + 1) << 17; + + seq_printf(m, "%d: ", idx); + if (k == 0) { + seq_puts(m, " -\n"); + return; + } + + seq_printf(m, "0x%08x-0x%08x ", bepi, bepi + size - 1); +#ifdef CONFIG_PHYS_64BIT + seq_printf(m, "0x%016llx ", brpn); +#else + seq_printf(m, "0x%08x ", brpn); +#endif + + if (k == 1) + seq_puts(m, "User "); + else if (k == 2) + seq_puts(m, "Kernel "); + else + seq_puts(m, "Kernel/User "); + + if (lower & BPP_RX) + seq_puts(m, is_d ? "RO " : "EXEC "); + else if (lower & BPP_RW) + seq_puts(m, is_d ? "RW " : "EXEC "); + else + seq_puts(m, is_d ? "NA " : "NX "); + + if (lower & _PAGE_WRITETHRU) + seq_puts(m, "write through "); + if (lower & _PAGE_NO_CACHE) + seq_puts(m, "no cache "); + if (lower & _PAGE_COHERENT) + seq_puts(m, "coherent "); + if (lower & _PAGE_GUARDED) + seq_puts(m, "guarded "); + seq_puts(m, "\n"); +} + +#define BAT_SHOW_603(_m, _n, _l, _u, _d) bat_show_603(_m, _n, mfspr(_l), mfspr(_u), _d) + +static int bats_show_603(struct seq_file *m, void *v) +{ + seq_puts(m, "---[ Instruction Block Address Translation ]---\n"); + + BAT_SHOW_603(m, 0, SPRN_IBAT0L, SPRN_IBAT0U, false); + BAT_SHOW_603(m, 1, SPRN_IBAT1L, SPRN_IBAT1U, false); + BAT_SHOW_603(m, 2, SPRN_IBAT2L, SPRN_IBAT2U, false); + BAT_SHOW_603(m, 3, SPRN_IBAT3L, SPRN_IBAT3U, false); + if (mmu_has_feature(MMU_FTR_USE_HIGH_BATS)) { + BAT_SHOW_603(m, 4, SPRN_IBAT4L, SPRN_IBAT4U, false); + BAT_SHOW_603(m, 5, SPRN_IBAT5L, SPRN_IBAT5U, false); + BAT_SHOW_603(m, 6, SPRN_IBAT6L, SPRN_IBAT6U, false); + BAT_SHOW_603(m, 7, SPRN_IBAT7L, SPRN_IBAT7U, false); + } + + seq_puts(m, "\n---[ Data Block Address Translation ]---\n"); + + BAT_SHOW_603(m, 0, SPRN_DBAT0L, SPRN_DBAT0U, true); + BAT_SHOW_603(m, 1, SPRN_DBAT1L, SPRN_DBAT1U, true); + BAT_SHOW_603(m, 2, SPRN_DBAT2L, SPRN_DBAT2U, true); + BAT_SHOW_603(m, 3, SPRN_DBAT3L, SPRN_DBAT3U, true); + if (mmu_has_feature(MMU_FTR_USE_HIGH_BATS)) { + BAT_SHOW_603(m, 4, SPRN_DBAT4L, SPRN_DBAT4U, true); + BAT_SHOW_603(m, 5, SPRN_DBAT5L, SPRN_DBAT5U, true); + BAT_SHOW_603(m, 6, SPRN_DBAT6L, SPRN_DBAT6U, true); + BAT_SHOW_603(m, 7, SPRN_DBAT7L, SPRN_DBAT7U, true); + } + + return 0; +} + +static int bats_open(struct inode *inode, struct file *file) +{ + if (cpu_has_feature(CPU_FTR_601)) + return single_open(file, bats_show_601, NULL); + + return single_open(file, bats_show_603, NULL); +} + +static const struct file_operations bats_fops = { + .open = bats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init bats_init(void) +{ + struct dentry *debugfs_file; + + debugfs_file = debugfs_create_file("block_address_translation", 0400, + powerpc_debugfs_root, NULL, &bats_fops); + return debugfs_file ? 0 : -ENOMEM; +} +device_initcall(bats_init); diff --git a/arch/powerpc/mm/dump_linuxpagetables-generic.c b/arch/powerpc/mm/dump_linuxpagetables-generic.c @@ -21,13 +21,11 @@ static const struct flag_info flag_array[] = { .set = "rw", .clear = "r ", }, { -#ifndef CONFIG_PPC_BOOK3S_32 .mask = _PAGE_EXEC, .val = _PAGE_EXEC, .set = " X ", .clear = " ", }, { -#endif .mask = _PAGE_PRESENT, .val = _PAGE_PRESENT, .set = "present", diff --git a/arch/powerpc/mm/dump_sr.c b/arch/powerpc/mm/dump_sr.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018, Christophe Leroy CS S.I. + * <christophe.leroy@c-s.fr> + * + * This dumps the content of Segment Registers + */ + +#include <asm/debugfs.h> + +static void seg_show(struct seq_file *m, int i) +{ + u32 val = mfsrin(i << 28); + + seq_printf(m, "0x%01x0000000-0x%01xfffffff ", i, i); + seq_printf(m, "Kern key %d ", (val >> 30) & 1); + seq_printf(m, "User key %d ", (val >> 29) & 1); + if (val & 0x80000000) { + seq_printf(m, "Device 0x%03x", (val >> 20) & 0x1ff); + seq_printf(m, "-0x%05x", val & 0xfffff); + } else { + if (val & 0x10000000) + seq_puts(m, "No Exec "); + seq_printf(m, "VSID 0x%06x", val & 0xffffff); + } + seq_puts(m, "\n"); +} + +static int sr_show(struct seq_file *m, void *v) +{ + int i; + + seq_puts(m, "---[ User Segments ]---\n"); + for (i = 0; i < TASK_SIZE >> 28; i++) + seg_show(m, i); + + seq_puts(m, "\n---[ Kernel Segments ]---\n"); + for (; i < 16; i++) + seg_show(m, i); + + return 0; +} + +static int sr_open(struct inode *inode, struct file *file) +{ + return single_open(file, sr_show, NULL); +} + +static const struct file_operations sr_fops = { + .open = sr_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init sr_init(void) +{ + struct dentry *debugfs_file; + + debugfs_file = debugfs_create_file("segment_registers", 0400, + powerpc_debugfs_root, NULL, &sr_fops); + return debugfs_file ? 0 : -ENOMEM; +} +device_initcall(sr_init); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c @@ -226,7 +226,9 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, static bool bad_kernel_fault(bool is_exec, unsigned long error_code, unsigned long address) { - if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT))) { + /* NX faults set DSISR_PROTFAULT on the 8xx, DSISR_NOEXEC_OR_G on others */ + if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT | + DSISR_PROTFAULT))) { printk_ratelimited(KERN_CRIT "kernel tried to execute" " exec-protected page (%lx) -" "exploit attempt? (uid: %d)\n", @@ -341,10 +343,21 @@ static inline void cmo_account_page_fault(void) static inline void cmo_account_page_fault(void) { } #endif /* CONFIG_PPC_SMLPAR */ -#ifdef CONFIG_PPC_STD_MMU -static void sanity_check_fault(bool is_write, unsigned long error_code) +#ifdef CONFIG_PPC_BOOK3S +static void sanity_check_fault(bool is_write, bool is_user, + unsigned long error_code, unsigned long address) { /* + * Userspace trying to access kernel address, we get PROTFAULT for that. + */ + if (is_user && address >= TASK_SIZE) { + pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n", + current->comm, current->pid, address, + from_kuid(&init_user_ns, current_uid())); + return; + } + + /* * For hash translation mode, we should never get a * PROTFAULT. Any update to pte to reduce access will result in us * removing the hash page table entry, thus resulting in a DSISR_NOHPTE @@ -373,12 +386,15 @@ static void sanity_check_fault(bool is_write, unsigned long error_code) * For radix, we can get prot fault for autonuma case, because radix * page table will have them marked noaccess for user. */ - if (!radix_enabled() && !is_write) - WARN_ON_ONCE(error_code & DSISR_PROTFAULT); + if (radix_enabled() || is_write) + return; + + WARN_ON_ONCE(error_code & DSISR_PROTFAULT); } #else -static void sanity_check_fault(bool is_write, unsigned long error_code) { } -#endif /* CONFIG_PPC_STD_MMU */ +static void sanity_check_fault(bool is_write, bool is_user, + unsigned long error_code, unsigned long address) { } +#endif /* CONFIG_PPC_BOOK3S */ /* * Define the correct "is_write" bit in error_code based @@ -435,7 +451,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address, } /* Additional sanity check(s) */ - sanity_check_fault(is_write, error_code); + sanity_check_fault(is_write, is_user, error_code, address); /* * The kernel should never take an execute fault nor should it @@ -637,21 +653,22 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) case 0x300: case 0x380: case 0xe00: - printk(KERN_ALERT "Unable to handle kernel paging request for " - "data at address 0x%08lx\n", regs->dar); + pr_alert("BUG: %s at 0x%08lx\n", + regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" : + "Unable to handle kernel data access", regs->dar); break; case 0x400: case 0x480: - printk(KERN_ALERT "Unable to handle kernel paging request for " - "instruction fetch\n"); + pr_alert("BUG: Unable to handle kernel instruction fetch%s", + regs->nip < PAGE_SIZE ? " (NULL pointer?)\n" : "\n"); break; case 0x600: - printk(KERN_ALERT "Unable to handle kernel paging request for " - "unaligned access at address 0x%08lx\n", regs->dar); + pr_alert("BUG: Unable to handle kernel unaligned access at 0x%08lx\n", + regs->dar); break; default: - printk(KERN_ALERT "Unable to handle kernel paging request for " - "unknown fault\n"); + pr_alert("BUG: Unable to handle unknown paging fault at 0x%08lx\n", + regs->dar); break; } printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n", diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S @@ -28,6 +28,7 @@ #include <asm/asm-offsets.h> #include <asm/export.h> #include <asm/feature-fixups.h> +#include <asm/code-patching-asm.h> #ifdef CONFIG_SMP .section .bss @@ -337,11 +338,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) rlwimi r5,r4,10,26,31 /* put in API (abbrev page index) */ SET_V(r5) /* set V (valid) bit */ + patch_site 0f, patch__hash_page_A0 + patch_site 1f, patch__hash_page_A1 + patch_site 2f, patch__hash_page_A2 /* Get the address of the primary PTE group in the hash table (r3) */ -_GLOBAL(hash_page_patch_A) - addis r0,r7,Hash_base@h /* base address of hash table */ - rlwimi r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */ - rlwinm r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */ +0: addis r0,r7,Hash_base@h /* base address of hash table */ +1: rlwimi r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */ +2: rlwinm r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */ xor r3,r3,r0 /* make primary hash */ li r0,8 /* PTEs/group */ @@ -366,10 +369,10 @@ _GLOBAL(hash_page_patch_A) bdnzf 2,1b /* loop while ctr != 0 && !cr0.eq */ beq+ found_slot + patch_site 0f, patch__hash_page_B /* Search the secondary PTEG for a matching PTE */ ori r5,r5,PTE_H /* set H (secondary hash) bit */ -_GLOBAL(hash_page_patch_B) - xoris r4,r3,Hash_msk>>16 /* compute secondary hash */ +0: xoris r4,r3,Hash_msk>>16 /* compute secondary hash */ xori r4,r4,(-PTEG_SIZE & 0xffff) addi r4,r4,-HPTE_SIZE mtctr r0 @@ -393,10 +396,10 @@ _GLOBAL(hash_page_patch_B) addi r6,r6,1 stw r6,primary_pteg_full@l(r4) + patch_site 0f, patch__hash_page_C /* Search the secondary PTEG for an empty slot */ ori r5,r5,PTE_H /* set H (secondary hash) bit */ -_GLOBAL(hash_page_patch_C) - xoris r4,r3,Hash_msk>>16 /* compute secondary hash */ +0: xoris r4,r3,Hash_msk>>16 /* compute secondary hash */ xori r4,r4,(-PTEG_SIZE & 0xffff) addi r4,r4,-HPTE_SIZE mtctr r0 @@ -577,11 +580,13 @@ _GLOBAL(flush_hash_pages) stwcx. r8,0,r5 /* update the pte */ bne- 33b + patch_site 0f, patch__flush_hash_A0 + patch_site 1f, patch__flush_hash_A1 + patch_site 2f, patch__flush_hash_A2 /* Get the address of the primary PTE group in the hash table (r3) */ -_GLOBAL(flush_hash_patch_A) - addis r8,r7,Hash_base@h /* base address of hash table */ - rlwimi r8,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */ - rlwinm r0,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */ +0: addis r8,r7,Hash_base@h /* base address of hash table */ +1: rlwimi r8,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */ +2: rlwinm r0,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */ xor r8,r0,r8 /* make primary hash */ /* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */ @@ -593,11 +598,11 @@ _GLOBAL(flush_hash_patch_A) bdnzf 2,1b /* loop while ctr != 0 && !cr0.eq */ beq+ 3f + patch_site 0f, patch__flush_hash_B /* Search the secondary PTEG for a matching PTE */ ori r11,r11,PTE_H /* set H (secondary hash) bit */ li r0,8 /* PTEs/group */ -_GLOBAL(flush_hash_patch_B) - xoris r12,r8,Hash_msk>>16 /* compute secondary hash */ +0: xoris r12,r8,Hash_msk>>16 /* compute secondary hash */ xori r12,r12,(-PTEG_SIZE & 0xffff) addi r12,r12,-HPTE_SIZE mtctr r0 diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c @@ -42,6 +42,8 @@ EXPORT_SYMBOL(HPAGE_SHIFT); #define hugepd_none(hpd) (hpd_val(hpd) == 0) +#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_t)) - __builtin_ffs(sizeof(void *))) + pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { /* @@ -61,14 +63,17 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, int num_hugepd; if (pshift >= pdshift) { - cachep = hugepte_cache; + cachep = PGT_CACHE(PTE_T_ORDER); num_hugepd = 1 << (pshift - pdshift); + } else if (IS_ENABLED(CONFIG_PPC_8xx)) { + cachep = PGT_CACHE(PTE_INDEX_SIZE); + num_hugepd = 1; } else { cachep = PGT_CACHE(pdshift - pshift); num_hugepd = 1; } - new = kmem_cache_zalloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); @@ -264,7 +269,7 @@ static void hugepd_free_rcu_callback(struct rcu_head *head) unsigned int i; for (i = 0; i < batch->index; i++) - kmem_cache_free(hugepte_cache, batch->ptes[i]); + kmem_cache_free(PGT_CACHE(PTE_T_ORDER), batch->ptes[i]); free_page((unsigned long)batch); } @@ -277,7 +282,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) if (atomic_read(&tlb->mm->mm_users) < 2 || mm_is_thread_local(tlb->mm)) { - kmem_cache_free(hugepte_cache, hugepte); + kmem_cache_free(PGT_CACHE(PTE_T_ORDER), hugepte); put_cpu_var(hugepd_freelist_cur); return; } @@ -329,6 +334,9 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_free_tlb(tlb, hugepte, + get_hugepd_cache_index(PTE_INDEX_SIZE)); else pgtable_free_tlb(tlb, hugepte, get_hugepd_cache_index(pdshift - shift)); @@ -652,7 +660,6 @@ static int __init hugepage_setup_sz(char *str) } __setup("hugepagesz=", hugepage_setup_sz); -struct kmem_cache *hugepte_cache; static int __init hugetlbpage_init(void) { int psize; @@ -699,24 +706,13 @@ static int __init hugetlbpage_init(void) * if we have pdshift and shift value same, we don't * use pgt cache for hugepd. */ - if (pdshift > shift) - pgtable_cache_add(pdshift - shift, NULL); + if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_cache_add(PTE_INDEX_SIZE); + else if (pdshift > shift) + pgtable_cache_add(pdshift - shift); #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) - else if (!hugepte_cache) { - /* - * Create a kmem cache for hugeptes. The bottom bits in - * the pte have size information encoded in them, so - * align them to allow this - */ - hugepte_cache = kmem_cache_create("hugepte-cache", - sizeof(pte_t), - HUGEPD_SHIFT_MASK + 1, - 0, NULL); - if (hugepte_cache == NULL) - panic("%s: Unable to create kmem cache " - "for hugeptes\n", __func__); - - } + else + pgtable_cache_add(PTE_T_ORDER); #endif } diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c @@ -25,22 +25,40 @@ #include <asm/pgalloc.h> #include <asm/pgtable.h> -static void pgd_ctor(void *addr) -{ - memset(addr, 0, PGD_TABLE_SIZE); +#define CTOR(shift) static void ctor_##shift(void *addr) \ +{ \ + memset(addr, 0, sizeof(void *) << (shift)); \ } -static void pud_ctor(void *addr) -{ - memset(addr, 0, PUD_TABLE_SIZE); -} +CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7); +CTOR(8); CTOR(9); CTOR(10); CTOR(11); CTOR(12); CTOR(13); CTOR(14); CTOR(15); -static void pmd_ctor(void *addr) +static inline void (*ctor(int shift))(void *) { - memset(addr, 0, PMD_TABLE_SIZE); + BUILD_BUG_ON(MAX_PGTABLE_INDEX_SIZE != 15); + + switch (shift) { + case 0: return ctor_0; + case 1: return ctor_1; + case 2: return ctor_2; + case 3: return ctor_3; + case 4: return ctor_4; + case 5: return ctor_5; + case 6: return ctor_6; + case 7: return ctor_7; + case 8: return ctor_8; + case 9: return ctor_9; + case 10: return ctor_10; + case 11: return ctor_11; + case 12: return ctor_12; + case 13: return ctor_13; + case 14: return ctor_14; + case 15: return ctor_15; + } + return NULL; } -struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE]; +struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE + 1]; EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */ /* @@ -50,7 +68,7 @@ EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */ * everything else. Caches created by this function are used for all * the higher level pagetables, and for hugepage pagetables. */ -void pgtable_cache_add(unsigned shift, void (*ctor)(void *)) +void pgtable_cache_add(unsigned int shift) { char *name; unsigned long table_size = sizeof(void *) << shift; @@ -71,19 +89,19 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *)) * moment, gcc doesn't seem to recognize is_power_of_2 as a * constant expression, so so much for that. */ BUG_ON(!is_power_of_2(minalign)); - BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE)); + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); if (PGT_CACHE(shift)) return; /* Already have a cache of this size */ align = max_t(unsigned long, align, minalign); name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift); - new = kmem_cache_create(name, table_size, align, 0, ctor); + new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); if (!new) panic("Could not allocate pgtable cache for order %d", shift); kfree(name); - pgtable_cache[shift - 1] = new; + pgtable_cache[shift] = new; pr_debug("Allocated pgtable cache for order %d\n", shift); } @@ -91,15 +109,15 @@ EXPORT_SYMBOL_GPL(pgtable_cache_add); /* used by kvm_hv module */ void pgtable_cache_init(void) { - pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor); + pgtable_cache_add(PGD_INDEX_SIZE); - if (PMD_CACHE_INDEX && !PGT_CACHE(PMD_CACHE_INDEX)) - pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor); + if (PMD_CACHE_INDEX) + pgtable_cache_add(PMD_CACHE_INDEX); /* * In all current configs, when the PUD index exists it's the * same size as either the pgd or pmd index except with THP enabled * on book3s 64 */ - if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX)) - pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor); + if (PUD_CACHE_INDEX) + pgtable_cache_add(PUD_CACHE_INDEX); } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c @@ -246,35 +246,19 @@ static int __init mark_nonram_nosave(void) } #endif -static bool zone_limits_final; - /* - * The memory zones past TOP_ZONE are managed by generic mm code. - * These should be set to zero since that's what every other - * architecture does. + * Zones usage: + * + * We setup ZONE_DMA to be 31-bits on all platforms and ZONE_NORMAL to be + * everything else. GFP_DMA32 page allocations automatically fall back to + * ZONE_DMA. + * + * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to + * inform the generic DMA mapping code. 32-bit only devices (if not handled + * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get + * otherwise served by ZONE_DMA. */ -static unsigned long max_zone_pfns[MAX_NR_ZONES] = { - [0 ... TOP_ZONE ] = ~0UL, - [TOP_ZONE + 1 ... MAX_NR_ZONES - 1] = 0 -}; - -/* - * Restrict the specified zone and all more restrictive zones - * to be below the specified pfn. May not be called after - * paging_init(). - */ -void __init limit_zone_pfn(enum zone_type zone, unsigned long pfn_limit) -{ - int i; - - if (WARN_ON(zone_limits_final)) - return; - - for (i = zone; i >= 0; i--) { - if (max_zone_pfns[i] > pfn_limit) - max_zone_pfns[i] = pfn_limit; - } -} +static unsigned long max_zone_pfns[MAX_NR_ZONES]; /* * Find the least restrictive zone that is entirely below the @@ -324,11 +308,14 @@ void __init paging_init(void) printk(KERN_DEBUG "Memory hole size: %ldMB\n", (long int)((top_of_ram - total_ram) >> 20)); +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = min(max_low_pfn, 0x7fffffffUL >> PAGE_SHIFT); +#endif + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM - limit_zone_pfn(ZONE_NORMAL, lowmem_end_addr >> PAGE_SHIFT); + max_zone_pfns[ZONE_HIGHMEM] = max_pfn; #endif - limit_zone_pfn(TOP_ZONE, top_of_ram >> PAGE_SHIFT); - zone_limits_final = true; + free_area_init_nodes(max_zone_pfns); mark_nonram_nosave(); @@ -503,7 +490,7 @@ EXPORT_SYMBOL(flush_icache_user_range); void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { -#ifdef CONFIG_PPC_STD_MMU +#ifdef CONFIG_PPC_BOOK3S /* * We don't need to worry about _PAGE_PRESENT here because we are * called with either mm->page_table_lock held or ptl lock held @@ -541,7 +528,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, } hash_preload(vma->vm_mm, address, is_exec, trap); -#endif /* CONFIG_PPC_STD_MMU */ +#endif /* CONFIG_PPC_BOOK3S */ #if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \ && defined(CONFIG_HUGETLB_PAGE) if (is_vm_hugetlb_page(vma)) diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c @@ -15,6 +15,7 @@ #include <linux/sched/mm.h> #include <asm/mmu_context.h> +#include <asm/pgalloc.h> #if defined(CONFIG_PPC32) static inline void switch_mm_pgdir(struct task_struct *tsk, @@ -97,3 +98,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, switch_mmu_context(prev, next, tsk); } +#ifdef CONFIG_PPC32 +void arch_exit_mmap(struct mm_struct *mm) +{ + void *frag = pte_frag_get(&mm->context); + + if (frag) + pte_frag_destroy(frag); +} +#endif diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c @@ -164,21 +164,6 @@ static void destroy_contexts(mm_context_t *ctx) } } -static void pte_frag_destroy(void *pte_frag) -{ - int count; - struct page *page; - - page = virt_to_page(pte_frag); - /* drop all the pending references */ - count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; - /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_page_dtor(page); - __free_page(page); - } -} - static void pmd_frag_destroy(void *pmd_frag) { int count; diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c @@ -36,6 +36,8 @@ struct mm_iommu_table_group_mem_t { u64 ua; /* userspace address */ u64 entries; /* number of entries in hpas[] */ u64 *hpas; /* vmalloc'ed */ +#define MM_IOMMU_TABLE_INVALID_HPA ((uint64_t)-1) + u64 dev_hpa; /* Device memory base address */ }; static long mm_iommu_adjust_locked_vm(struct mm_struct *mm, @@ -126,7 +128,8 @@ static int mm_iommu_move_page_from_cma(struct page *page) return 0; } -long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, +static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, + unsigned long entries, unsigned long dev_hpa, struct mm_iommu_table_group_mem_t **pmem) { struct mm_iommu_table_group_mem_t *mem; @@ -140,12 +143,6 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) { - if ((mem->ua == ua) && (mem->entries == entries)) { - ++mem->used; - *pmem = mem; - goto unlock_exit; - } - /* Overlap? */ if ((mem->ua < (ua + (entries << PAGE_SHIFT))) && (ua < (mem->ua + @@ -156,11 +153,13 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, } - ret = mm_iommu_adjust_locked_vm(mm, entries, true); - if (ret) - goto unlock_exit; + if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) { + ret = mm_iommu_adjust_locked_vm(mm, entries, true); + if (ret) + goto unlock_exit; - locked_entries = entries; + locked_entries = entries; + } mem = kzalloc(sizeof(*mem), GFP_KERNEL); if (!mem) { @@ -168,6 +167,13 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, goto unlock_exit; } + if (dev_hpa != MM_IOMMU_TABLE_INVALID_HPA) { + mem->pageshift = __ffs(dev_hpa | (entries << PAGE_SHIFT)); + mem->dev_hpa = dev_hpa; + goto good_exit; + } + mem->dev_hpa = MM_IOMMU_TABLE_INVALID_HPA; + /* * For a starting point for a maximum page size calculation * we use @ua and @entries natural alignment to allow IOMMU pages @@ -236,6 +242,7 @@ populate: mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; } +good_exit: atomic64_set(&mem->mapped, 1); mem->used = 1; mem->ua = ua; @@ -252,13 +259,31 @@ unlock_exit: return ret; } -EXPORT_SYMBOL_GPL(mm_iommu_get); + +long mm_iommu_new(struct mm_struct *mm, unsigned long ua, unsigned long entries, + struct mm_iommu_table_group_mem_t **pmem) +{ + return mm_iommu_do_alloc(mm, ua, entries, MM_IOMMU_TABLE_INVALID_HPA, + pmem); +} +EXPORT_SYMBOL_GPL(mm_iommu_new); + +long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua, + unsigned long entries, unsigned long dev_hpa, + struct mm_iommu_table_group_mem_t **pmem) +{ + return mm_iommu_do_alloc(mm, ua, entries, dev_hpa, pmem); +} +EXPORT_SYMBOL_GPL(mm_iommu_newdev); static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem) { long i; struct page *page = NULL; + if (!mem->hpas) + return; + for (i = 0; i < mem->entries; ++i) { if (!mem->hpas[i]) continue; @@ -300,6 +325,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem) long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem) { long ret = 0; + unsigned long entries, dev_hpa; mutex_lock(&mem_list_mutex); @@ -321,9 +347,12 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem) } /* @mapped became 0 so now mappings are disabled, release the region */ + entries = mem->entries; + dev_hpa = mem->dev_hpa; mm_iommu_release(mem); - mm_iommu_adjust_locked_vm(mm, mem->entries, false); + if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) + mm_iommu_adjust_locked_vm(mm, entries, false); unlock_exit: mutex_unlock(&mem_list_mutex); @@ -368,27 +397,32 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm, return ret; } -struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, +struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries) { struct mm_iommu_table_group_mem_t *mem, *ret = NULL; + mutex_lock(&mem_list_mutex); + list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) { if ((mem->ua == ua) && (mem->entries == entries)) { ret = mem; + ++mem->used; break; } } + mutex_unlock(&mem_list_mutex); + return ret; } -EXPORT_SYMBOL_GPL(mm_iommu_find); +EXPORT_SYMBOL_GPL(mm_iommu_get); long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; - u64 *va = &mem->hpas[entry]; + u64 *va; if (entry >= mem->entries) return -EFAULT; @@ -396,6 +430,12 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (pageshift > mem->pageshift) return -EFAULT; + if (!mem->hpas) { + *hpa = mem->dev_hpa + (ua - mem->ua); + return 0; + } + + va = &mem->hpas[entry]; *hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; @@ -406,7 +446,6 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; - void *va = &mem->hpas[entry]; unsigned long *pa; if (entry >= mem->entries) @@ -415,7 +454,12 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (pageshift > mem->pageshift) return -EFAULT; - pa = (void *) vmalloc_to_phys(va); + if (!mem->hpas) { + *hpa = mem->dev_hpa + (ua - mem->ua); + return 0; + } + + pa = (void *) vmalloc_to_phys(&mem->hpas[entry]); if (!pa) return -EFAULT; @@ -435,6 +479,9 @@ extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua) if (!mem) return; + if (mem->dev_hpa != MM_IOMMU_TABLE_INVALID_HPA) + return; + entry = (ua - mem->ua) >> PAGE_SHIFT; va = &mem->hpas[entry]; @@ -445,6 +492,33 @@ extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua) *pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY; } +bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa, + unsigned int pageshift, unsigned long *size) +{ + struct mm_iommu_table_group_mem_t *mem; + unsigned long end; + + list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) { + if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) + continue; + + end = mem->dev_hpa + (mem->entries << PAGE_SHIFT); + if ((mem->dev_hpa <= hpa) && (hpa < end)) { + /* + * Since the IOMMU page size might be bigger than + * PAGE_SIZE, the amount of preregistered memory + * starting from @hpa might be smaller than 1<<pageshift + * and the caller needs to distinguish this situation. + */ + *size = min(1UL << pageshift, end - hpa); + return true; + } + } + + return false; +} +EXPORT_SYMBOL_GPL(mm_iommu_is_devmem); + 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 @@ -372,7 +372,6 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm) { pr_hard("initing context for mm @%p\n", mm); -#ifdef CONFIG_PPC_MM_SLICES /* * We have MMU_NO_CONTEXT set to be ~0. Hence check * explicitly against context.id == 0. This ensures that we properly @@ -382,9 +381,9 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm) */ if (mm->context.id == 0) slice_init_new_context_exec(mm); -#endif mm->context.id = MMU_NO_CONTEXT; mm->context.active = 0; + pte_frag_set(&mm->context, NULL); return 0; } @@ -487,4 +486,3 @@ void __init mmu_context_init(void) next_context = FIRST_CONTEXT; nr_free_contexts = LAST_CONTEXT - FIRST_CONTEXT + 1; } - diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h @@ -155,7 +155,7 @@ struct tlbcam { }; #endif -#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx) /* 6xx have BATS */ /* FSL_BOOKE have TLBCAM */ /* 8xx have LTLB */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c @@ -1475,7 +1475,7 @@ static int dt_update_callback(struct notifier_block *nb, switch (action) { case OF_RECONFIG_UPDATE_PROPERTY: - if (!of_prop_cmp(update->dn->type, "cpu") && + if (of_node_is_type(update->dn, "cpu") && !of_prop_cmp(update->prop->name, "ibm,associativity")) { u32 core_id; of_property_read_u32(update->dn, "reg", &core_id); diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c @@ -244,6 +244,9 @@ static pmd_t *get_pmd_from_cache(struct mm_struct *mm) { void *pmd_frag, *ret; + if (PMD_FRAG_NR == 1) + return NULL; + spin_lock(&mm->page_table_lock); ret = mm->context.pmd_frag; if (ret) { @@ -322,91 +325,6 @@ void pmd_fragment_free(unsigned long *pmd) } } -static pte_t *get_pte_from_cache(struct mm_struct *mm) -{ - void *pte_frag, *ret; - - spin_lock(&mm->page_table_lock); - ret = mm->context.pte_frag; - if (ret) { - pte_frag = ret + PTE_FRAG_SIZE; - /* - * If we have taken up all the fragments mark PTE page NULL - */ - if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) - pte_frag = NULL; - mm->context.pte_frag = pte_frag; - } - spin_unlock(&mm->page_table_lock); - return (pte_t *)ret; -} - -static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) -{ - void *ret = NULL; - struct page *page; - - if (!kernel) { - page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); - if (!page) - return NULL; - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - } else { - page = alloc_page(PGALLOC_GFP); - if (!page) - return NULL; - } - - atomic_set(&page->pt_frag_refcount, 1); - - ret = page_address(page); - /* - * if we support only one fragment just return the - * allocated page. - */ - if (PTE_FRAG_NR == 1) - return ret; - spin_lock(&mm->page_table_lock); - /* - * If we find pgtable_page set, we return - * the allocated page with single fragement - * count. - */ - if (likely(!mm->context.pte_frag)) { - atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); - mm->context.pte_frag = ret + PTE_FRAG_SIZE; - } - spin_unlock(&mm->page_table_lock); - - return (pte_t *)ret; -} - -pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) -{ - pte_t *pte; - - pte = get_pte_from_cache(mm); - if (pte) - return pte; - - return __alloc_for_ptecache(mm, kernel); -} - -void pte_fragment_free(unsigned long *table, int kernel) -{ - struct page *page = virt_to_page(table); - - BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); - if (atomic_dec_and_test(&page->pt_frag_refcount)) { - if (!kernel) - pgtable_page_dtor(page); - __free_page(page); - } -} - static inline void pgtable_free(void *table, int index) { switch (index) { diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Handling Page Tables through page fragments + * + */ + +#include <linux/kernel.h> +#include <linux/gfp.h> +#include <linux/mm.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> +#include <linux/hugetlb.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm/tlb.h> + +void pte_frag_destroy(void *pte_frag) +{ + int count; + struct page *page; + + page = virt_to_page(pte_frag); + /* drop all the pending references */ + count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; + /* We allow PTE_FRAG_NR fragments from a PTE page */ + if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { + pgtable_page_dtor(page); + __free_page(page); + } +} + +static pte_t *get_pte_from_cache(struct mm_struct *mm) +{ + void *pte_frag, *ret; + + if (PTE_FRAG_NR == 1) + return NULL; + + spin_lock(&mm->page_table_lock); + ret = pte_frag_get(&mm->context); + if (ret) { + pte_frag = ret + PTE_FRAG_SIZE; + /* + * If we have taken up all the fragments mark PTE page NULL + */ + if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) + pte_frag = NULL; + pte_frag_set(&mm->context, pte_frag); + } + spin_unlock(&mm->page_table_lock); + return (pte_t *)ret; +} + +static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) +{ + void *ret = NULL; + struct page *page; + + if (!kernel) { + page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); + if (!page) + return NULL; + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } + } else { + page = alloc_page(PGALLOC_GFP); + if (!page) + return NULL; + } + + atomic_set(&page->pt_frag_refcount, 1); + + ret = page_address(page); + /* + * if we support only one fragment just return the + * allocated page. + */ + if (PTE_FRAG_NR == 1) + return ret; + spin_lock(&mm->page_table_lock); + /* + * If we find pgtable_page set, we return + * the allocated page with single fragement + * count. + */ + if (likely(!pte_frag_get(&mm->context))) { + atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); + pte_frag_set(&mm->context, ret + PTE_FRAG_SIZE); + } + spin_unlock(&mm->page_table_lock); + + return (pte_t *)ret; +} + +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) +{ + pte_t *pte; + + pte = get_pte_from_cache(mm); + if (pte) + return pte; + + return __alloc_for_ptecache(mm, kernel); +} + +void pte_fragment_free(unsigned long *table, int kernel) +{ + struct page *page = virt_to_page(table); + + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { + if (!kernel) + pgtable_page_dtor(page); + __free_page(page); + } +} diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c @@ -74,7 +74,7 @@ static struct page *maybe_pte_to_page(pte_t pte) * support falls into the same category. */ -static pte_t set_pte_filter(pte_t pte) +static pte_t set_pte_filter_hash(pte_t pte) { if (radix_enabled()) return pte; @@ -93,14 +93,12 @@ static pte_t set_pte_filter(pte_t pte) return pte; } -static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, - int dirty) -{ - return pte; -} - #else /* CONFIG_PPC_BOOK3S */ +static pte_t set_pte_filter_hash(pte_t pte) { return pte; } + +#endif /* CONFIG_PPC_BOOK3S */ + /* Embedded type MMU with HW exec support. This is a bit more complicated * as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so * instead we "filter out" the exec permission for non clean pages. @@ -109,6 +107,9 @@ static pte_t set_pte_filter(pte_t pte) { struct page *pg; + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return set_pte_filter_hash(pte); + /* No exec permission in the first place, move on */ if (!pte_exec(pte) || !pte_looks_normal(pte)) return pte; @@ -138,6 +139,9 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, { struct page *pg; + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return pte; + /* So here, we only care about exec faults, as we use them * to recover lost _PAGE_EXEC and perform I$/D$ coherency * if necessary. Also if _PAGE_EXEC is already set, same deal, @@ -172,8 +176,6 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, return pte_mkexec(pte); } -#endif /* CONFIG_PPC_BOOK3S */ - /* * set_pte stores a linux PTE into the linux page table. */ @@ -221,9 +223,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, } #ifdef CONFIG_HUGETLB_PAGE -extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) { #ifdef HUGETLB_NEED_PRELOAD /* diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c @@ -45,32 +45,15 @@ extern char etext[], _stext[], _sinittext[], _einittext[]; __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte; + if (!slab_is_available()) + return memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE); - if (slab_is_available()) { - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - } else { - pte = __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); - if (pte) - clear_page(pte); - } - return pte; + return (pte_t *)pte_fragment_alloc(mm, address, 1); } pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *ptepage; - - gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT; - - ptepage = alloc_pages(flags, 0); - if (!ptepage) - return NULL; - if (!pgtable_page_ctor(ptepage)) { - __free_page(ptepage); - return NULL; - } - return ptepage; + return (pgtable_t)pte_fragment_alloc(mm, address, 0); } void __iomem * @@ -160,7 +143,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call * Don't allow anybody to remap normal RAM that we're using. * mem_init() sets high_memory so only do the check after that. */ - if (slab_is_available() && (p < virt_to_phys(high_memory)) && + if (slab_is_available() && p <= virt_to_phys(high_memory - 1) && page_is_ram(__phys_to_pfn(p))) { printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n", (unsigned long long)p, __builtin_return_address(0)); @@ -260,7 +243,7 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top) ktext = ((char *)v >= _stext && (char *)v < etext) || ((char *)v >= _sinittext && (char *)v < _einittext); map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL); -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 if (ktext) hash_preload(&init_mm, v, false, 0x300); #endif diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c @@ -6,20 +6,21 @@ */ #include <asm/mman.h> +#include <asm/mmu_context.h> #include <asm/setup.h> #include <linux/pkeys.h> #include <linux/of_device.h> DEFINE_STATIC_KEY_TRUE(pkey_disabled); -bool pkey_execute_disable_supported; int pkeys_total; /* Total pkeys as per device tree */ -bool pkeys_devtree_defined; /* pkey property exported by device tree */ u32 initial_allocation_mask; /* Bits set for the initially allocated keys */ u32 reserved_allocation_mask; /* Bits set for reserved keys */ -u64 pkey_amr_mask; /* Bits in AMR not to be touched */ -u64 pkey_iamr_mask; /* Bits in AMR not to be touched */ -u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */ -int execute_only_key = 2; +static bool pkey_execute_disable_supported; +static bool pkeys_devtree_defined; /* property exported by device tree */ +static u64 pkey_amr_mask; /* Bits in AMR not to be touched */ +static u64 pkey_iamr_mask; /* Bits in AMR not to be touched */ +static u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */ +static int execute_only_key = 2; #define AMR_BITS_PER_PKEY 2 #define AMR_RD_BIT 0x1UL @@ -57,7 +58,7 @@ static inline bool pkey_mmu_enabled(void) return cpu_has_feature(CPU_FTR_PKEY); } -int pkey_initialize(void) +static int pkey_initialize(void) { int os_reserved, i; @@ -414,3 +415,13 @@ bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, return pkey_access_permitted(vma_pkey(vma), write, execute); } + +void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) +{ + if (static_branch_likely(&pkey_disabled)) + return; + + /* Duplicate the oldmm pkey state in mm: */ + mm_pkey_allocation_map(mm) = mm_pkey_allocation_map(oldmm); + mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; +} diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c @@ -31,6 +31,7 @@ #include <asm/prom.h> #include <asm/mmu.h> #include <asm/machdep.h> +#include <asm/code-patching.h> #include "mmu_decl.h" @@ -52,7 +53,7 @@ struct batrange { /* stores address ranges mapped by BATs */ phys_addr_t v_block_mapped(unsigned long va) { int b; - for (b = 0; b < 4; ++b) + for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b) if (va >= bat_addrs[b].start && va < bat_addrs[b].limit) return bat_addrs[b].phys + (va - bat_addrs[b].start); return 0; @@ -64,7 +65,7 @@ phys_addr_t v_block_mapped(unsigned long va) unsigned long p_block_mapped(phys_addr_t pa) { int b; - for (b = 0; b < 4; ++b) + for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b) if (pa >= bat_addrs[b].phys && pa < (bat_addrs[b].limit-bat_addrs[b].start) +bat_addrs[b].phys) @@ -182,22 +183,8 @@ void __init MMU_init_hw(void) unsigned int hmask, mb, mb2; unsigned int n_hpteg, lg_n_hpteg; - extern unsigned int hash_page_patch_A[]; - extern unsigned int hash_page_patch_B[], hash_page_patch_C[]; - extern unsigned int hash_page[]; - extern unsigned int flush_hash_patch_A[], flush_hash_patch_B[]; - - if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) { - /* - * Put a blr (procedure return) instruction at the - * start of hash_page, since we can still get DSI - * exceptions on a 603. - */ - hash_page[0] = 0x4e800020; - flush_icache_range((unsigned long) &hash_page[0], - (unsigned long) &hash_page[1]); + if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) return; - } if ( ppc_md.progress ) ppc_md.progress("hash:enter", 0x105); @@ -244,31 +231,19 @@ void __init MMU_init_hw(void) if (lg_n_hpteg > 16) mb2 = 16 - LG_HPTEG_SIZE; - hash_page_patch_A[0] = (hash_page_patch_A[0] & ~0xffff) - | ((unsigned int)(Hash) >> 16); - hash_page_patch_A[1] = (hash_page_patch_A[1] & ~0x7c0) | (mb << 6); - hash_page_patch_A[2] = (hash_page_patch_A[2] & ~0x7c0) | (mb2 << 6); - hash_page_patch_B[0] = (hash_page_patch_B[0] & ~0xffff) | hmask; - hash_page_patch_C[0] = (hash_page_patch_C[0] & ~0xffff) | hmask; - - /* - * Ensure that the locations we've patched have been written - * out from the data cache and invalidated in the instruction - * cache, on those machines with split caches. - */ - flush_icache_range((unsigned long) &hash_page_patch_A[0], - (unsigned long) &hash_page_patch_C[1]); + modify_instruction_site(&patch__hash_page_A0, 0xffff, (unsigned int)Hash >> 16); + modify_instruction_site(&patch__hash_page_A1, 0x7c0, mb << 6); + modify_instruction_site(&patch__hash_page_A2, 0x7c0, mb2 << 6); + modify_instruction_site(&patch__hash_page_B, 0xffff, hmask); + modify_instruction_site(&patch__hash_page_C, 0xffff, hmask); /* * Patch up the instructions in hashtable.S:flush_hash_page */ - flush_hash_patch_A[0] = (flush_hash_patch_A[0] & ~0xffff) - | ((unsigned int)(Hash) >> 16); - flush_hash_patch_A[1] = (flush_hash_patch_A[1] & ~0x7c0) | (mb << 6); - flush_hash_patch_A[2] = (flush_hash_patch_A[2] & ~0x7c0) | (mb2 << 6); - flush_hash_patch_B[0] = (flush_hash_patch_B[0] & ~0xffff) | hmask; - flush_icache_range((unsigned long) &flush_hash_patch_A[0], - (unsigned long) &flush_hash_patch_B[1]); + modify_instruction_site(&patch__flush_hash_A0, 0xffff, (unsigned int)Hash >> 16); + modify_instruction_site(&patch__flush_hash_A1, 0x7c0, mb << 6); + modify_instruction_site(&patch__flush_hash_A2, 0x7c0, mb2 << 6); + modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask); if ( ppc_md.progress ) ppc_md.progress("hash:done", 0x205); } diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S @@ -70,6 +70,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) std r15,EX_TLB_R15(r12) std r10,EX_TLB_CR(r12) #ifdef CONFIG_PPC_FSL_BOOK3E +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION std r7,EX_TLB_R7(r12) #endif TLB_MISS_PROLOG_STATS diff --git a/arch/powerpc/oprofile/Makefile b/arch/powerpc/oprofile/Makefile @@ -16,4 +16,4 @@ oprofile-$(CONFIG_OPROFILE_CELL) += op_model_cell.o \ cell/spu_task_sync.o oprofile-$(CONFIG_PPC_BOOK3S_64) += op_model_power4.o op_model_pa6t.o oprofile-$(CONFIG_FSL_EMB_PERFMON) += op_model_fsl_emb.o -oprofile-$(CONFIG_6xx) += op_model_7450.o +oprofile-$(CONFIG_PPC_BOOK3S_32) += op_model_7450.o diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c @@ -212,7 +212,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) model = &op_model_pa6t; break; #endif -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 case PPC_OPROFILE_G4: model = &op_model_7450; break; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c @@ -10,6 +10,7 @@ */ #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/sched/clock.h> #include <linux/perf_event.h> #include <linux/percpu.h> #include <linux/hardirq.h> @@ -130,6 +131,14 @@ static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {} static void pmao_restore_workaround(bool ebb) { } #endif /* CONFIG_PPC32 */ +bool is_sier_available(void) +{ + if (ppmu->flags & PPMU_HAS_SIER) + return true; + + return false; +} + static bool regs_use_siar(struct pt_regs *regs) { /* @@ -864,6 +873,8 @@ static int power_check_constraints(struct cpu_hw_events *cpuhw, int i, j; unsigned long addf = ppmu->add_fields; unsigned long tadd = ppmu->test_adder; + unsigned long grp_mask = ppmu->group_constraint_mask; + unsigned long grp_val = ppmu->group_constraint_val; if (n_ev > ppmu->n_counter) return -1; @@ -884,15 +895,23 @@ static int power_check_constraints(struct cpu_hw_events *cpuhw, for (i = 0; i < n_ev; ++i) { nv = (value | cpuhw->avalues[i][0]) + (value & cpuhw->avalues[i][0] & addf); - if ((((nv + tadd) ^ value) & mask) != 0 || - (((nv + tadd) ^ cpuhw->avalues[i][0]) & - cpuhw->amasks[i][0]) != 0) + + if (((((nv + tadd) ^ value) & mask) & (~grp_mask)) != 0) + break; + + if (((((nv + tadd) ^ cpuhw->avalues[i][0]) & cpuhw->amasks[i][0]) + & (~grp_mask)) != 0) break; + value = nv; mask |= cpuhw->amasks[i][0]; } - if (i == n_ev) - return 0; /* all OK */ + if (i == n_ev) { + if ((value & mask & grp_mask) != (mask & grp_val)) + return -1; + else + return 0; /* all OK */ + } /* doesn't work, gather alternatives... */ if (!ppmu->get_alternatives) @@ -2148,7 +2167,7 @@ static bool pmc_overflow(unsigned long val) /* * Performance monitor interrupt stuff */ -static void perf_event_interrupt(struct pt_regs *regs) +static void __perf_event_interrupt(struct pt_regs *regs) { int i, j; struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); @@ -2232,6 +2251,14 @@ static void perf_event_interrupt(struct pt_regs *regs) irq_exit(); } +static void perf_event_interrupt(struct pt_regs *regs) +{ + u64 start_clock = sched_clock(); + + __perf_event_interrupt(regs); + perf_sample_event_took(sched_clock() - start_clock); +} + static int power_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c @@ -28,13 +28,13 @@ static DEFINE_MUTEX(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; -struct imc_pmu_ref *nest_imc_refc; +static struct imc_pmu_ref *nest_imc_refc; static int nest_pmus; /* Core IMC data structures and variables */ static cpumask_t core_imc_cpumask; -struct imc_pmu_ref *core_imc_refc; +static struct imc_pmu_ref *core_imc_refc; static struct imc_pmu *core_imc_pmu; /* Thread IMC data structures and variables */ @@ -43,7 +43,7 @@ static DEFINE_PER_CPU(u64 *, thread_imc_mem); static struct imc_pmu *thread_imc_pmu; static int thread_imc_mem_size; -struct imc_pmu *imc_event_to_pmu(struct perf_event *event) +static struct imc_pmu *imc_event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct imc_pmu, pmu); } diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c @@ -148,6 +148,14 @@ static bool is_thresh_cmp_valid(u64 event) return true; } +static unsigned int dc_ic_rld_quad_l1_sel(u64 event) +{ + unsigned int cache; + + cache = (event >> EVENT_CACHE_SEL_SHIFT) & MMCR1_DC_IC_QUAL_MASK; + return cache; +} + static inline u64 isa207_find_source(u64 idx, u32 sub_idx) { u64 ret = PERF_MEM_NA; @@ -226,8 +234,13 @@ 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); + u64 sier = mfspr(SPRN_SIER); + u64 val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT; - *weight = mantissa << (2 * exp); + if (val == 0 || val == 7) + *weight = 0; + else + *weight = mantissa << (2 * exp); } int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) @@ -274,19 +287,27 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) } if (unit >= 6 && unit <= 9) { - /* - * L2/L3 events contain a cache selector field, which is - * supposed to be programmed into MMCRC. However MMCRC is only - * HV writable, and there is no API for guest kernels to modify - * it. The solution is for the hypervisor to initialise the - * field to zeroes, and for us to only ever allow events that - * have a cache selector of zero. The bank selector (bit 3) is - * irrelevant, as long as the rest of the value is 0. - */ - if (cache & 0x7) + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + mask |= CNST_CACHE_GROUP_MASK; + value |= CNST_CACHE_GROUP_VAL(event & 0xff); + + mask |= CNST_CACHE_PMC4_MASK; + if (pmc == 4) + value |= CNST_CACHE_PMC4_VAL; + } else if (cache & 0x7) { + /* + * L2/L3 events contain a cache selector field, which is + * supposed to be programmed into MMCRC. However MMCRC is only + * HV writable, and there is no API for guest kernels to modify + * it. The solution is for the hypervisor to initialise the + * field to zeroes, and for us to only ever allow events that + * have a cache selector of zero. The bank selector (bit 3) is + * irrelevant, as long as the rest of the value is 0. + */ return -1; + } - } else if (event & EVENT_IS_L1) { + } else if (cpu_has_feature(CPU_FTR_ARCH_300) || (event & EVENT_IS_L1)) { mask |= CNST_L1_QUAL_MASK; value |= CNST_L1_QUAL_VAL(cache); } @@ -389,11 +410,14 @@ int isa207_compute_mmcr(u64 event[], int n_ev, /* In continuous sampling mode, update SDAR on TLB miss */ mmcra_sdar_mode(event[i], &mmcra); - if (event[i] & EVENT_IS_L1) { - cache = event[i] >> EVENT_CACHE_SEL_SHIFT; - mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT; - cache >>= 1; - mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT; + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + cache = dc_ic_rld_quad_l1_sel(event[i]); + mmcr1 |= (cache) << MMCR1_DC_IC_QUAL_SHIFT; + } else { + if (event[i] & EVENT_IS_L1) { + cache = dc_ic_rld_quad_l1_sel(event[i]); + mmcr1 |= (cache) << MMCR1_DC_IC_QUAL_SHIFT; + } } if (is_event_marked(event[i])) { diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h @@ -134,6 +134,11 @@ #define CNST_SAMPLE_VAL(v) (((v) & EVENT_SAMPLE_MASK) << 16) #define CNST_SAMPLE_MASK CNST_SAMPLE_VAL(EVENT_SAMPLE_MASK) +#define CNST_CACHE_GROUP_VAL(v) (((v) & 0xffull) << 55) +#define CNST_CACHE_GROUP_MASK CNST_CACHE_GROUP_VAL(0xff) +#define CNST_CACHE_PMC4_VAL (1ull << 54) +#define CNST_CACHE_PMC4_MASK CNST_CACHE_PMC4_VAL + /* * For NC we are counting up to 4 events. This requires three bits, and we need * the fifth event to overflow and set the 4th bit. To achieve that we bias the @@ -163,8 +168,8 @@ #define MMCR1_COMBINE_SHIFT(pmc) (35 - ((pmc) - 1)) #define MMCR1_PMCSEL_SHIFT(pmc) (24 - (((pmc) - 1)) * 8) #define MMCR1_FAB_SHIFT 36 -#define MMCR1_DC_QUAL_SHIFT 47 -#define MMCR1_IC_QUAL_SHIFT 46 +#define MMCR1_DC_IC_QUAL_MASK 0x3 +#define MMCR1_DC_IC_QUAL_SHIFT 46 /* MMCR1 Combine bits macro for power9 */ #define p9_MMCR1_COMBINE_SHIFT(pmc) (38 - ((pmc - 1) * 2)) diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c @@ -69,6 +69,7 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_TRAP, trap), PT_REGS_OFFSET(PERF_REG_POWERPC_DAR, dar), PT_REGS_OFFSET(PERF_REG_POWERPC_DSISR, dsisr), + PT_REGS_OFFSET(PERF_REG_POWERPC_SIER, dar), }; u64 perf_reg_value(struct pt_regs *regs, int idx) @@ -76,6 +77,12 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX)) return 0; + if (idx == PERF_REG_POWERPC_SIER && + (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) || + IS_ENABLED(CONFIG_PPC32) || + !is_sier_available())) + return 0; + return regs_get_register(regs, pt_regs_offset[idx]); } diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c @@ -63,16 +63,8 @@ * MMCRA[9:11] = thresh_cmp[0:2] * MMCRA[12:18] = thresh_cmp[3:9] * - * if unit == 6 or unit == 7 - * MMCRC[53:55] = cache_sel[1:3] (L2EVENT_SEL) - * else if unit == 8 or unit == 9: - * if cache_sel[0] == 0: # L3 bank - * MMCRC[47:49] = cache_sel[1:3] (L3EVENT_SEL0) - * else if cache_sel[0] == 1: - * MMCRC[50:51] = cache_sel[2:3] (L3EVENT_SEL1) - * else if cache_sel[1]: # L1 event - * MMCR1[16] = cache_sel[2] - * MMCR1[17] = cache_sel[3] + * MMCR1[16] = cache_sel[2] + * MMCR1[17] = cache_sel[3] * * if mark: * MMCRA[63] = 1 (SAMPLE_ENABLE) @@ -179,8 +171,6 @@ CACHE_EVENT_ATTR(L1-icache-prefetches, PM_IC_PREF_WRITE); CACHE_EVENT_ATTR(LLC-load-misses, PM_DATA_FROM_L3MISS); CACHE_EVENT_ATTR(LLC-loads, PM_DATA_FROM_L3); CACHE_EVENT_ATTR(LLC-prefetches, PM_L3_PREF_ALL); -CACHE_EVENT_ATTR(LLC-store-misses, PM_L2_ST_MISS); -CACHE_EVENT_ATTR(LLC-stores, PM_L2_ST); CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL); CACHE_EVENT_ATTR(branch-loads, PM_BR_CMPL); CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS); @@ -205,8 +195,6 @@ static struct attribute *power9_events_attr[] = { CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS), CACHE_EVENT_PTR(PM_DATA_FROM_L3), CACHE_EVENT_PTR(PM_L3_PREF_ALL), - CACHE_EVENT_PTR(PM_L2_ST_MISS), - CACHE_EVENT_PTR(PM_L2_ST), CACHE_EVENT_PTR(PM_BR_MPRED_CMPL), CACHE_EVENT_PTR(PM_BR_CMPL), CACHE_EVENT_PTR(PM_DTLB_MISS), @@ -354,8 +342,8 @@ static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [ C(RESULT_MISS) ] = PM_DATA_FROM_L3MISS, }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = PM_L2_ST, - [ C(RESULT_MISS) ] = PM_L2_ST_MISS, + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, }, [ C(OP_PREFETCH) ] = { [ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL, @@ -427,6 +415,8 @@ static struct power_pmu power9_pmu = { .n_counter = MAX_PMU_COUNTERS, .add_fields = ISA207_ADD_FIELDS, .test_adder = ISA207_TEST_ADDER, + .group_constraint_mask = CNST_CACHE_PMC4_MASK, + .group_constraint_val = CNST_CACHE_PMC4_VAL, .compute_mmcr = isa207_compute_mmcr, .config_bhrb = power9_config_bhrb, .bhrb_filter_map = power9_bhrb_filter_map, diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c @@ -47,7 +47,7 @@ static int __init warp_probe(void) if (!of_machine_is_compatible("pika,warp")) return 0; - /* For __dma_alloc_coherent */ + /* For __dma_nommu_alloc_coherent */ ISA_DMA_THRESHOLD = ~0L; return 1; @@ -179,9 +179,9 @@ static int pika_setup_leds(void) } for_each_child_of_node(np, child) - if (strcmp(child->name, "green") == 0) + if (of_node_name_eq(child, "green")) green_led = of_get_gpio(child, 0); - else if (strcmp(child->name, "red") == 0) + else if (of_node_name_eq(child, "red")) red_led = of_get_gpio(child, 0); of_node_put(np); diff --git a/arch/powerpc/platforms/4xx/ocm.c b/arch/powerpc/platforms/4xx/ocm.c @@ -223,8 +223,6 @@ static void __init ocm_init_node(int count, struct device_node *node) INIT_LIST_HEAD(&ocm->c.list); ocm->ready = 1; - - return; } static int ocm_debugfs_show(struct seq_file *m, void *v) @@ -242,9 +240,7 @@ static int ocm_debugfs_show(struct seq_file *m, void *v) seq_printf(m, "PhysAddr : 0x%llx\n", ocm->phys); seq_printf(m, "MemTotal : %d Bytes\n", ocm->memtotal); seq_printf(m, "MemTotal(NC) : %d Bytes\n", ocm->nc.memtotal); - seq_printf(m, "MemTotal(C) : %d Bytes\n", ocm->c.memtotal); - - seq_printf(m, "\n"); + seq_printf(m, "MemTotal(C) : %d Bytes\n\n", ocm->c.memtotal); seq_printf(m, "NC.PhysAddr : 0x%llx\n", ocm->nc.phys); seq_printf(m, "NC.VirtAddr : 0x%p\n", ocm->nc.virt); @@ -256,9 +252,7 @@ static int ocm_debugfs_show(struct seq_file *m, void *v) blk->size, blk->owner); } - seq_printf(m, "\n"); - - seq_printf(m, "C.PhysAddr : 0x%llx\n", ocm->c.phys); + seq_printf(m, "\nC.PhysAddr : 0x%llx\n", ocm->c.phys); seq_printf(m, "C.VirtAddr : 0x%p\n", ocm->c.virt); seq_printf(m, "C.MemTotal : %d Bytes\n", ocm->c.memtotal); seq_printf(m, "C.MemFree : %d Bytes\n", ocm->c.memfree); @@ -268,7 +262,7 @@ static int ocm_debugfs_show(struct seq_file *m, void *v) blk->size, blk->owner); } - seq_printf(m, "\n"); + seq_putc(m, '\n'); } return 0; @@ -338,7 +332,6 @@ void *ppc4xx_ocm_alloc(phys_addr_t *phys, int size, int align, ocm_blk = kzalloc(sizeof(*ocm_blk), GFP_KERNEL); if (!ocm_blk) { - printk(KERN_ERR "PPC4XX OCM: could not allocate ocm block"); rh_free(ocm_reg->rh, offset); break; } @@ -392,10 +385,8 @@ static int __init ppc4xx_ocm_init(void) return 0; ocm_nodes = kzalloc((count * sizeof(struct ocm_info)), GFP_KERNEL); - if (!ocm_nodes) { - printk(KERN_ERR "PPC4XX OCM: failed to allocate OCM nodes!\n"); + if (!ocm_nodes) return -ENOMEM; - } ocm_count = count; count = 0; diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c @@ -1399,7 +1399,6 @@ static void __init ppc_476fpe_pciex_check_link(struct ppc4xx_pciex_port *port) printk(KERN_WARNING "PCIE%d: Link up failed\n", port->index); iounmap(mbase); - return; } static struct ppc4xx_pciex_hwops ppc_476fpe_pcie_hwops __initdata = @@ -2081,7 +2080,6 @@ static void __init ppc4xx_probe_pciex_bridge(struct device_node *np) const u32 *pval; int portno; unsigned int dcrs; - const char *val; /* First, proceed to core initialization as we assume there's * only one PCIe core in the system @@ -2127,10 +2125,9 @@ static void __init ppc4xx_probe_pciex_bridge(struct device_node *np) * Resulting from this setup this PCIe port will be configured * as root-complex or as endpoint. */ - val = of_get_property(port->node, "device_type", NULL); - if (!strcmp(val, "pci-endpoint")) { + if (of_node_is_type(port->node, "pci-endpoint")) { port->endpoint = 1; - } else if (!strcmp(val, "pci")) { + } else if (of_node_is_type(port->node, "pci")) { port->endpoint = 0; } else { printk(KERN_ERR "PCIE: missing or incorrect device_type for %pOF\n", diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_MPC512x bool "512x-based boards" - depends on 6xx + depends on PPC_BOOK3S_32 select COMMON_CLK select FSL_SOC select IPIC diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_MPC52xx bool "52xx-based boards" - depends on 6xx + depends on PPC_BOOK3S_32 select COMMON_CLK select PPC_PCI_CHOICE diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c @@ -82,11 +82,9 @@ static void __init efika_pcisetup(void) return; } - for (pcictrl = NULL;;) { - pcictrl = of_get_next_child(root, pcictrl); - if ((pcictrl == NULL) || (strcmp(pcictrl->name, "pci") == 0)) + for_each_child_of_node(root, pcictrl) + if (of_node_name_eq(pcictrl, "pci")) break; - } of_node_put(root); diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 menuconfig PPC_82xx bool "82xx-based boards (PQ II)" - depends on 6xx + depends on PPC_BOOK3S_32 if PPC_82xx @@ -54,7 +54,7 @@ config PQ2ADS config 8260 bool - depends on 6xx + depends on PPC_BOOK3S_32 select CPM2 help The MPC8260 is a typical embedded CPU made by Freescale. Selecting diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 menuconfig PPC_83xx bool "83xx-based boards" - depends on 6xx + depends on PPC_BOOK3S_32 select PPC_UDBG_16550 select PPC_PCI_CHOICE select FSL_PCI if PCI diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c @@ -14,6 +14,7 @@ #include <linux/of_platform.h> #include <linux/pci.h> +#include <asm/debug.h> #include <asm/io.h> #include <asm/hw_irq.h> #include <asm/ipic.h> @@ -150,3 +151,19 @@ void __init mpc83xx_setup_arch(void) mpc83xx_setup_pci(); } + +int machine_check_83xx(struct pt_regs *regs) +{ + u32 mask = 1 << (31 - IPIC_MCP_WDT); + + if (!(regs->msr & SRR1_MCE_MCP) || !(ipic_get_mcp_status() & mask)) + return machine_check_generic(regs); + ipic_clear_mcp_status(mask); + + if (debugger_fault_handler(regs)) + return 1; + + die("Watchdog NMI Reset", regs, 0); + + return 1; +} diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -68,16 +68,6 @@ void __init corenet_gen_setup_arch(void) swiotlb_detect_4g(); -#if defined(CONFIG_FSL_PCI) && defined(CONFIG_ZONE_DMA32) - /* - * Inbound windows don't cover the full lower 4 GiB - * due to conflicts with PCICSRBAR and outbound windows, - * so limit the DMA32 zone to 2 GiB, to allow consistent - * allocations to succeed. - */ - limit_zone_pfn(ZONE_DMA32, 1UL << (31 - PAGE_SHIFT)); -#endif - pr_info("%s board\n", ppc_md.name); mpc85xx_qe_init(); diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -45,15 +45,6 @@ static void __init qemu_e500_setup_arch(void) fsl_pci_assign_primary(); swiotlb_detect_4g(); -#if defined(CONFIG_FSL_PCI) && defined(CONFIG_ZONE_DMA32) - /* - * Inbound windows don't cover the full lower 4 GiB - * due to conflicts with PCICSRBAR and outbound windows, - * so limit the DMA32 zone to 2 GiB, to allow consistent - * allocations to succeed. - */ - limit_zone_pfn(ZONE_DMA32, 1UL << (31 - PAGE_SHIFT)); -#endif mpc85xx_smp_init(); } diff --git a/arch/powerpc/platforms/85xx/t1042rdb_diu.c b/arch/powerpc/platforms/85xx/t1042rdb_diu.c @@ -39,7 +39,7 @@ struct device_node *cpld_node; */ static void t1042rdb_set_monitor_port(enum fsl_diu_monitor_port port) { - static void __iomem *cpld_base; + void __iomem *cpld_base; cpld_base = of_iomap(cpld_node, 0); if (!cpld_base) { diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig @@ -2,7 +2,7 @@ config PPC_86xx menuconfig PPC_86xx bool "86xx-based boards" - depends on 6xx + depends on PPC_BOOK3S_32 select FSL_SOC select ALTIVEC help diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c @@ -86,8 +86,7 @@ smp_86xx_kick_cpu(int nr) mdelay(1); /* Restore the exception vector */ - *vector = save_vector; - flush_icache_range((unsigned long) vector, (unsigned long) vector + 4); + patch_instruction(vector, save_vector); local_irq_restore(flags); diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig @@ -40,7 +40,7 @@ config EPAPR_PARAVIRT config PPC_NATIVE bool - depends on 6xx || PPC64 + depends on PPC_BOOK3S_32 || PPC64 help Support for running natively on the hardware, i.e. without a hypervisor. This option is not user-selectable but should @@ -48,7 +48,7 @@ config PPC_NATIVE config PPC_OF_BOOT_TRAMPOLINE bool "Support booting from Open Firmware or yaboot" - depends on 6xx || PPC64 + depends on PPC_BOOK3S_32 || PPC64 default y help Support from booting from Open Firmware or yaboot using an @@ -197,7 +197,7 @@ endmenu config PPC601_SYNC_FIX bool "Workarounds for PPC601 bugs" - depends on 6xx && PPC_PMAC + depends on PPC_BOOK3S_32 && PPC_PMAC help Some versions of the PPC601 (the first PowerPC chip) have bugs which mean that extra synchronization instructions are required near @@ -211,7 +211,7 @@ config PPC601_SYNC_FIX config TAU bool "On-chip CPU temperature sensor support" - depends on 6xx + depends on PPC_BOOK3S_32 help G3 and G4 processors have an on-chip temperature sensor called the 'Thermal Assist Unit (TAU)', which, in theory, can measure the on-die diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype @@ -24,6 +24,7 @@ choice config PPC_BOOK3S_32 bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx" select PPC_FPU + select PPC_HAVE_PMU_SUPPORT config PPC_85xx bool "Freescale 85xx" @@ -179,11 +180,6 @@ config PPC_BOOK3E def_bool y depends on PPC_BOOK3E_64 -config 6xx - def_bool y - depends on PPC32 && PPC_BOOK3S - select PPC_HAVE_PMU_SUPPORT - config E500 select FSL_EMB_PERFMON select PPC_FSL_BOOK3E @@ -266,7 +262,7 @@ config PHYS_64BIT config ALTIVEC bool "AltiVec Support" - depends on 6xx || PPC_BOOK3S_64 || (PPC_E500MC && PPC64) + depends on PPC_BOOK3S_32 || PPC_BOOK3S_64 || (PPC_E500MC && PPC64) ---help--- This option enables kernel support for the Altivec extensions to the PowerPC processor. The kernel currently supports saving and restoring @@ -316,14 +312,6 @@ config SPE If in doubt, say Y here. -config PPC_STD_MMU - def_bool y - depends on PPC_BOOK3S - -config PPC_STD_MMU_32 - def_bool y - depends on PPC_STD_MMU && PPC32 - config ARCH_ENABLE_SPLIT_PMD_PTLOCK def_bool y depends on PPC_BOOK3S_64 @@ -358,7 +346,7 @@ config ARCH_ENABLE_HUGEPAGE_MIGRATION config PPC_MMU_NOHASH def_bool y - depends on !PPC_STD_MMU + depends on !PPC_BOOK3S config PPC_BOOK3E_MMU def_bool y @@ -412,7 +400,8 @@ config NR_CPUS config NOT_COHERENT_CACHE bool - depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || GAMECUBE_COMMON + depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \ + GAMECUBE_COMMON || AMIGAONE default n if PPC_47x default y diff --git a/arch/powerpc/platforms/amigaone/Kconfig b/arch/powerpc/platforms/amigaone/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config AMIGAONE bool "Eyetech AmigaOne/MAI Teron" - depends on 6xx && BROKEN_ON_SMP + depends on PPC_BOOK3S_32 && BROKEN_ON_SMP select PPC_I8259 select PPC_INDIRECT_PCI select PPC_UDBG_16550 diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c @@ -53,7 +53,7 @@ static struct cbe_regs_map *cbe_find_map(struct device_node *np) int i; struct device_node *tmp_np; - if (strcasecmp(np->type, "spe")) { + if (!of_node_is_type(np, "spe")) { for (i = 0; i < cbe_regs_map_count; i++) if (cbe_regs_maps[i].cpu_node == np || cbe_regs_maps[i].be_node == np) @@ -70,8 +70,8 @@ static struct cbe_regs_map *cbe_find_map(struct device_node *np) tmp_np = tmp_np->parent; /* on a correct devicetree we wont get up to root */ BUG_ON(!tmp_np); - } while (strcasecmp(tmp_np->type, "cpu") && - strcasecmp(tmp_np->type, "be")); + } while (!of_node_is_type(tmp_np, "cpu") || + !of_node_is_type(tmp_np, "be")); np->data = cbe_find_map(tmp_np); diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c @@ -131,7 +131,7 @@ static int cell_setup_phb(struct pci_controller *phb) np = phb->dn; model = of_get_property(np, "model", NULL); - if (model == NULL || strcmp(np->name, "pci")) + if (model == NULL || !of_node_name_eq(np, "pci")) return 0; /* Setup workarounds for spider */ @@ -168,8 +168,7 @@ static int __init cell_publish_devices(void) * platform devices for the PCI host bridges */ for_each_child_of_node(root, np) { - if (np->type == NULL || (strcmp(np->type, "pci") != 0 && - strcmp(np->type, "pciex") != 0)) + if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "pciex")) continue; of_platform_device_create(np, NULL, NULL); } diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -34,20 +34,9 @@ */ static void *spu_syscall_table[] = { -#define SYSCALL(func) sys_ni_syscall, -#define COMPAT_SYS(func) sys_ni_syscall, -#define PPC_SYS(func) sys_ni_syscall, -#define OLDSYS(func) sys_ni_syscall, -#define SYS32ONLY(func) sys_ni_syscall, -#define PPC64ONLY(func) sys_ni_syscall, -#define SYSX(f, f3264, f32) sys_ni_syscall, - -#define SYSCALL_SPU(func) sys_##func, -#define COMPAT_SYS_SPU(func) sys_##func, -#define COMPAT_SPU_NEW(func) sys_##func, -#define SYSX_SPU(f, f3264, f32) f, - -#include <asm/systbl.h> +#define __SYSCALL(nr, entry, nargs) entry, +#include <asm/syscall_table_spu.h> +#undef __SYSCALL }; long spu_sys_callback(struct spu_syscall_block *s) diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c @@ -458,7 +458,6 @@ static void init_affinity_node(int cbe) struct device_node *vic_dn, *last_spu_dn; phandle avoid_ph; const phandle *vic_handles; - const char *name; int lenp, i, added; last_spu = list_first_entry(&cbe_spu_info[cbe].spus, struct spu, @@ -480,12 +479,7 @@ static void init_affinity_node(int cbe) if (!vic_dn) continue; - /* a neighbour might be spe, mic-tm, or bif0 */ - name = of_get_property(vic_dn, "name", NULL); - if (!name) - continue; - - if (strcmp(name, "spe") == 0) { + if (of_node_name_eq(vic_dn, "spe") ) { spu = devnode_spu(cbe, vic_dn); avoid_ph = last_spu_dn->phandle; } else { @@ -498,7 +492,7 @@ static void init_affinity_node(int cbe) spu = neighbour_spu(cbe, vic_dn, last_spu_dn); if (!spu) continue; - if (!strcmp(name, "mic-tm")) { + if (of_node_name_eq(vic_dn, "mic-tm")) { last_spu->has_mem_affinity = 1; spu->has_mem_affinity = 1; } diff --git a/arch/powerpc/platforms/chrp/Kconfig b/arch/powerpc/platforms/chrp/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_CHRP bool "Common Hardware Reference Platform (CHRP) based machines" - depends on 6xx + depends on PPC_BOOK3S_32 select HAVE_PCSPKR_PLATFORM select MPIC select PPC_I8259 diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c @@ -230,8 +230,8 @@ chrp_find_bridges(void) else if (strncmp(machine, "Pegasos", 7) == 0) is_pegasos = 1; } - for (dev = root->child; dev != NULL; dev = dev->sibling) { - if (dev->type == NULL || strcmp(dev->type, "pci") != 0) + for_each_child_of_node(root, dev) { + if (!of_node_is_type(dev, "pci")) continue; ++index; /* The GG2 bridge on the LongTrail doesn't have an address */ diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c @@ -280,20 +280,14 @@ static __init void chrp_init(void) node = of_find_node_by_path(property); if (!node) return; - property = of_get_property(node, "device_type", NULL); - if (!property) - goto out_put; - if (strcmp(property, "serial")) + if (!of_node_is_type(node, "serial")) goto out_put; /* * The 9pin connector is either /failsafe * or /pci@80000000/isa@C/serial@i2F8 * The optional graphics card has also type 'serial' in VGA mode. */ - property = of_get_property(node, "name", NULL); - if (!property) - goto out_put; - if (!strcmp(property, "failsafe") || !strcmp(property, "serial")) + if (of_node_name_eq(node, "failsafe") || of_node_name_eq(node, "serial")) add_preferred_console("ttyS", 0, NULL); out_put: of_node_put(node); diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config EMBEDDED6xx bool "Embedded 6xx/7xx/7xxx-based boards" - depends on 6xx && BROKEN_ON_SMP + depends on PPC_BOOK3S_32 && BROKEN_ON_SMP config LINKSTATION bool "Linkstation / Kurobox(HG) from Buffalo" diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c @@ -604,10 +604,8 @@ void __init maple_pci_init(void) printk(KERN_CRIT "maple_find_bridges: can't find root of device tree\n"); return; } - for (np = NULL; (np = of_get_next_child(root, np)) != NULL;) { - if (!np->type) - continue; - if (strcmp(np->type, "pci") && strcmp(np->type, "ht")) + for_each_child_of_node(root, np) { + if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "ht")) continue; if ((of_device_is_compatible(np, "u4-pcie") || of_device_is_compatible(np, "u3-agp")) && diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c @@ -255,15 +255,13 @@ int pasemi_dma_alloc_ring(struct pasemi_dmachan *chan, int ring_size) chan->ring_size = ring_size; - chan->ring_virt = dma_alloc_coherent(&dma_pdev->dev, + chan->ring_virt = dma_zalloc_coherent(&dma_pdev->dev, ring_size * sizeof(u64), &chan->ring_dma, GFP_KERNEL); if (!chan->ring_virt) return -ENOMEM; - memset(chan->ring_virt, 0, ring_size * sizeof(u64)); - return 0; } EXPORT_SYMBOL(pasemi_dma_alloc_ring); diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c @@ -27,6 +27,7 @@ #include <linux/pci.h> #include <asm/pci-bridge.h> +#include <asm/isa-bridge.h> #include <asm/machdep.h> #include <asm/ppc-pci.h> @@ -108,6 +109,61 @@ static int workaround_5945(struct pci_bus *bus, unsigned int devfn, return 1; } +#ifdef CONFIG_PPC_PASEMI_NEMO +#define PXP_ERR_CFG_REG 0x4 +#define PXP_IGNORE_PCIE_ERRORS 0x800 +#define SB600_BUS 5 + +static void sb600_set_flag(int bus) +{ + static void __iomem *iob_mapbase = NULL; + struct resource res; + struct device_node *dn; + int err; + + if (iob_mapbase == NULL) { + dn = of_find_compatible_node(NULL, "isa", "pasemi,1682m-iob"); + if (!dn) { + pr_crit("NEMO SB600 missing iob node\n"); + return; + } + + err = of_address_to_resource(dn, 0, &res); + of_node_put(dn); + + if (err) { + pr_crit("NEMO SB600 missing resource\n"); + return; + } + + pr_info("NEMO SB600 IOB base %08llx\n",res.start); + + iob_mapbase = ioremap(res.start + 0x100, 0x94); + } + + if (iob_mapbase != NULL) { + if (bus == SB600_BUS) { + /* + * This is the SB600's bus, tell the PCI-e root port + * to allow non-zero devices to enumerate. + */ + out_le32(iob_mapbase + PXP_ERR_CFG_REG, in_le32(iob_mapbase + PXP_ERR_CFG_REG) | PXP_IGNORE_PCIE_ERRORS); + } else { + /* + * Only scan device 0 on other busses + */ + out_le32(iob_mapbase + PXP_ERR_CFG_REG, in_le32(iob_mapbase + PXP_ERR_CFG_REG) & ~PXP_IGNORE_PCIE_ERRORS); + } + } +} + +#else + +static void sb600_set_flag(int bus) +{ +} +#endif + static int pa_pxp_read_config(struct pci_bus *bus, unsigned int devfn, int offset, int len, u32 *val) { @@ -126,6 +182,8 @@ static int pa_pxp_read_config(struct pci_bus *bus, unsigned int devfn, addr = pa_pxp_cfg_addr(hose, bus->number, devfn, offset); + sb600_set_flag(bus->number); + /* * Note: the caller has already checked that offset is * suitably aligned and that len is 1, 2 or 4. @@ -160,6 +218,8 @@ static int pa_pxp_write_config(struct pci_bus *bus, unsigned int devfn, addr = pa_pxp_cfg_addr(hose, bus->number, devfn, offset); + sb600_set_flag(bus->number); + /* * Note: the caller has already checked that offset is * suitably aligned and that len is 1, 2 or 4. @@ -210,6 +270,12 @@ static int __init pas_add_bridge(struct device_node *dev) /* Interpret the "ranges" property */ pci_process_bridge_OF_ranges(hose, dev, 1); + /* + * Scan for an isa bridge. This is needed to find the SB600 on the nemo + * and does nothing on machines without one. + */ + isa_bridge_find_early(hose); + return 0; } diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c @@ -34,6 +34,7 @@ #include <asm/prom.h> #include <asm/iommu.h> #include <asm/machdep.h> +#include <asm/i8259.h> #include <asm/mpic.h> #include <asm/smp.h> #include <asm/time.h> @@ -72,6 +73,40 @@ static void __noreturn pas_restart(char *cmd) out_le32(reset_reg, 0x6000000); } +#ifdef CONFIG_PPC_PASEMI_NEMO +void pas_shutdown(void) +{ + /* Set the PLD bit that makes the SB600 think the power button is being pressed */ + void __iomem *pld_map = ioremap(0xf5000000,4096); + while (1) + out_8(pld_map+7,0x01); +} + +/* RTC platform device structure as is not in device tree */ +static struct resource rtc_resource[] = {{ + .name = "rtc", + .start = 0x70, + .end = 0x71, + .flags = IORESOURCE_IO, +}, { + .name = "rtc", + .start = 8, + .end = 8, + .flags = IORESOURCE_IRQ, +}}; + +static inline void nemo_init_rtc(void) +{ + platform_device_register_simple("rtc_cmos", -1, rtc_resource, 2); +} + +#else + +static inline void nemo_init_rtc(void) +{ +} +#endif + #ifdef CONFIG_SMP static arch_spinlock_t timebase_lock; static unsigned long timebase; @@ -183,6 +218,42 @@ static int __init pas_setup_mce_regs(void) } machine_device_initcall(pasemi, pas_setup_mce_regs); +#ifdef CONFIG_PPC_PASEMI_NEMO +static void sb600_8259_cascade(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned int cascade_irq = i8259_irq(); + + if (cascade_irq) + generic_handle_irq(cascade_irq); + + chip->irq_eoi(&desc->irq_data); +} + +static void nemo_init_IRQ(struct mpic *mpic) +{ + struct device_node *np; + int gpio_virq; + /* Connect the SB600's legacy i8259 controller */ + np = of_find_node_by_path("/pxp@0,e0000000"); + i8259_init(np, 0); + of_node_put(np); + + gpio_virq = irq_create_mapping(NULL, 3); + irq_set_irq_type(gpio_virq, IRQ_TYPE_LEVEL_HIGH); + irq_set_chained_handler(gpio_virq, sb600_8259_cascade); + mpic_unmask_irq(irq_get_irq_data(gpio_virq)); + + irq_set_default_host(mpic->irqhost); +} + +#else + +static inline void nemo_init_IRQ(struct mpic *mpic) +{ +} +#endif + static __init void pas_init_IRQ(void) { struct device_node *np; @@ -243,6 +314,8 @@ static __init void pas_init_IRQ(void) mpic_unmask_irq(irq_get_irq_data(nmi_virq)); } + nemo_init_IRQ(mpic); + of_node_put(mpic_node); of_node_put(root); } @@ -404,6 +477,8 @@ static int __init pasemi_publish_devices(void) /* Publish OF platform devices for SDC and other non-PCI devices */ of_platform_bus_probe(NULL, pasemi_bus_ids, NULL); + nemo_init_rtc(); + return 0; } machine_device_initcall(pasemi, pasemi_publish_devices); @@ -418,6 +493,17 @@ static int __init pas_probe(void) !of_machine_is_compatible("pasemi,pwrficient")) return 0; +#ifdef CONFIG_PPC_PASEMI_NEMO + /* + * Check for the Nemo motherboard here, if we are running on one + * change the machine definition to fit + */ + if (of_machine_is_compatible("pasemi,nemo")) { + pm_power_off = pas_shutdown; + ppc_md.name = "A-EON Amigaone X1000"; + } +#endif + iommu_init_early_pasemi(); return 1; diff --git a/arch/powerpc/platforms/powermac/cache.S b/arch/powerpc/platforms/powermac/cache.S @@ -28,7 +28,7 @@ */ _GLOBAL(flush_disable_caches) -#ifndef CONFIG_6xx +#ifndef CONFIG_PPC_BOOK3S_32 blr #else BEGIN_FTR_SECTION @@ -356,4 +356,4 @@ END_FTR_SECTION_IFSET(CPU_FTR_L3CR) mtmsr r11 /* restore DR and EE */ isync blr -#endif /* CONFIG_6xx */ +#endif /* CONFIG_PPC_BOOK3S_32 */ diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c @@ -51,7 +51,7 @@ #define DBG(fmt...) #endif -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 extern int powersave_lowspeed; #endif @@ -173,9 +173,9 @@ static long ohare_htw_scc_enable(struct device_node *node, long param, macio = macio_find(node, 0); if (!macio) return -ENODEV; - if (!strcmp(node->name, "ch-a")) + if (of_node_name_eq(node, "ch-a")) chan_mask = MACIO_FLAG_SCCA_ON; - else if (!strcmp(node->name, "ch-b")) + else if (of_node_name_eq(node, "ch-b")) chan_mask = MACIO_FLAG_SCCB_ON; else return -ENODEV; @@ -610,9 +610,9 @@ static long core99_scc_enable(struct device_node *node, long param, long value) macio = macio_find(node, 0); if (!macio) return -ENODEV; - if (!strcmp(node->name, "ch-a")) + if (of_node_name_eq(node, "ch-a")) chan_mask = MACIO_FLAG_SCCA_ON; - else if (!strcmp(node->name, "ch-b")) + else if (of_node_name_eq(node, "ch-b")) chan_mask = MACIO_FLAG_SCCB_ON; else return -ENODEV; @@ -1392,8 +1392,7 @@ static long g5_mpic_enable(struct device_node *node, long param, long value) if (parent == NULL) return 0; - is_u3 = strcmp(parent->name, "u3") == 0 || - strcmp(parent->name, "u4") == 0; + is_u3 = of_node_name_eq(parent, "u3") || of_node_name_eq(parent, "u4"); of_node_put(parent); if (!is_u3) return 0; @@ -1471,6 +1470,7 @@ static long g5_i2s_enable(struct device_node *node, long param, long value) case 2: if (macio->type == macio_shasta) break; + /* fall through */ default: return -ENODEV; } diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c @@ -617,7 +617,7 @@ static void __init kw_i2c_probe(void) * but not for now */ child = of_get_next_child(np, NULL); - multibus = !child || strcmp(child->name, "i2c-bus"); + multibus = !of_node_name_eq(child, "i2c-bus"); of_node_put(child); /* For a multibus setup, we get the bus count based on the @@ -917,10 +917,9 @@ static void __init smu_i2c_probe(void) * type as older device trees mix i2c busses and other things * at the same level */ - for (busnode = NULL; - (busnode = of_get_next_child(controller, busnode)) != NULL;) { - if (strcmp(busnode->type, "i2c") && - strcmp(busnode->type, "i2c-bus")) + for_each_child_of_node(controller, busnode) { + if (!of_node_is_type(busnode, "i2c") && + !of_node_is_type(busnode, "i2c-bus")) continue; reg = of_get_property(busnode, "reg", NULL); if (reg == NULL) @@ -1206,7 +1205,7 @@ static void pmac_i2c_devscan(void (*callback)(struct device_node *dev, if (bus != pmac_i2c_find_bus(np)) continue; for (p = whitelist; p->name != NULL; p++) { - if (strcmp(np->name, p->name)) + if (!of_node_name_eq(np, p->name)) continue; if (p->compatible && !of_device_is_compatible(np, p->compatible)) diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c @@ -501,9 +501,7 @@ static void __init init_p2pbridge(void) /* XXX it would be better here to identify the specific PCI-PCI bridge chip we have. */ p2pbridge = of_find_node_by_name(NULL, "pci-bridge"); - if (p2pbridge == NULL - || p2pbridge->parent == NULL - || strcmp(p2pbridge->parent->name, "pci") != 0) + if (p2pbridge == NULL || !of_node_name_eq(p2pbridge->parent, "pci")) goto done; if (pci_device_from_OF_node(p2pbridge, &bus, &devfn) < 0) { DBG("Can't find PCI infos for PCI<->PCI bridge\n"); @@ -828,14 +826,14 @@ static int __init pmac_add_bridge(struct device_node *dev) if (of_device_is_compatible(dev, "uni-north")) { primary = setup_uninorth(hose, &rsrc); disp_name = "UniNorth"; - } else if (strcmp(dev->name, "pci") == 0) { + } else if (of_node_name_eq(dev, "pci")) { /* XXX assume this is a mpc106 (grackle) */ setup_grackle(hose); disp_name = "Grackle (MPC106)"; - } else if (strcmp(dev->name, "bandit") == 0) { + } else if (of_node_name_eq(dev, "bandit")) { setup_bandit(hose, &rsrc); disp_name = "Bandit"; - } else if (strcmp(dev->name, "chaos") == 0) { + } else if (of_node_name_eq(dev, "chaos")) { setup_chaos(hose, &rsrc); disp_name = "Chaos"; primary = 0; @@ -914,16 +912,14 @@ void __init pmac_pci_init(void) "of device tree\n"); return; } - for (np = NULL; (np = of_get_next_child(root, np)) != NULL;) { - if (np->name == NULL) - continue; - if (strcmp(np->name, "bandit") == 0 - || strcmp(np->name, "chaos") == 0 - || strcmp(np->name, "pci") == 0) { + for_each_child_of_node(root, np) { + if (of_node_name_eq(np, "bandit") + || of_node_name_eq(np, "chaos") + || of_node_name_eq(np, "pci")) { if (pmac_add_bridge(np) == 0) of_node_get(np); } - if (strcmp(np->name, "ht") == 0) { + if (of_node_name_eq(np, "ht")) { of_node_get(np); ht = np; } @@ -983,7 +979,7 @@ static bool pmac_pci_enable_device_hook(struct pci_dev *dev) /* Firewire & GMAC were disabled after PCI probe, the driver is * claiming them, we must re-enable them now. */ - if (uninorth_child && !strcmp(node->name, "firewire") && + if (uninorth_child && of_node_name_eq(node, "firewire") && (of_device_is_compatible(node, "pci106b,18") || of_device_is_compatible(node, "pci106b,30") || of_device_is_compatible(node, "pci11c1,5811"))) { @@ -991,7 +987,7 @@ static bool pmac_pci_enable_device_hook(struct pci_dev *dev) pmac_call_feature(PMAC_FTR_1394_ENABLE, node, 0, 1); updatecfg = 1; } - if (uninorth_child && !strcmp(node->name, "ethernet") && + if (uninorth_child && of_node_name_eq(node, "ethernet") && of_device_is_compatible(node, "gmac")) { pmac_call_feature(PMAC_FTR_GMAC_ENABLE, node, 0, 1); updatecfg = 1; @@ -1262,4 +1258,3 @@ struct pci_controller_ops pmac_pci_controller_ops = { .enable_device_hook = pmac_pci_enable_device_hook, #endif }; - diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c @@ -101,9 +101,8 @@ static void macio_gpio_init_one(struct macio_chip *macio) * Find the "gpio" parent node */ - for (gparent = NULL; - (gparent = of_get_next_child(macio->of_node, gparent)) != NULL;) - if (strcmp(gparent->name, "gpio") == 0) + for_each_child_of_node(macio->of_node, gparent) + if (of_node_name_eq(gparent, "gpio")) break; if (gparent == NULL) return; @@ -313,7 +312,7 @@ static void uninorth_install_pfunc(void) * Install handlers for the hwclock child if any */ for (np = NULL; (np = of_get_next_child(uninorth_node, np)) != NULL;) - if (strcmp(np->name, "hw-clock") == 0) { + if (of_node_name_eq(np, "hw-clock")) { unin_hwclock = np; break; } diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c @@ -417,7 +417,7 @@ int of_irq_parse_oldworld(struct device_node *device, int index, if (ints != NULL) break; device = device->parent; - if (device && strcmp(device->type, "pci") != 0) + if (!of_node_is_type(device, "pci")) break; } if (ints == NULL) @@ -553,13 +553,13 @@ void __init pmac_pic_init(void) for_each_node_with_property(np, "interrupt-controller") { /* Skip /chosen/interrupt-controller */ - if (strcmp(np->name, "chosen") == 0) + if (of_node_name_eq(np, "chosen")) continue; /* It seems like at least one person wants * to use BootX on a machine with an AppleKiwi * controller which happens to pretend to be an * interrupt controller too. */ - if (strcmp(np->name, "AppleKiwi") == 0) + if (of_node_name_eq(np, "AppleKiwi")) continue; /* I think we found one ! */ of_irq_dflt_pic = np; diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c @@ -560,15 +560,9 @@ static int __init check_pmac_serial_console(void) } pr_debug("stdout is %pOF\n", prom_stdout); - name = of_get_property(prom_stdout, "name", NULL); - if (!name) { - pr_debug(" stdout package has no name !\n"); - goto not_found; - } - - if (strcmp(name, "ch-a") == 0) + if (of_node_name_eq(prom_stdout, "ch-a")) offset = 0; - else if (strcmp(name, "ch-b") == 0) + else if (of_node_name_eq(prom_stdout, "ch-b")) offset = 1; else goto not_found; diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S @@ -56,7 +56,7 @@ * vector that will be called by the ROM on wakeup */ _GLOBAL(low_sleep_handler) -#ifndef CONFIG_6xx +#ifndef CONFIG_PPC_BOOK3S_32 blr #else mflr r0 @@ -394,5 +394,5 @@ sleep_storage: .long 0 .balign L1_CACHE_BYTES, 0 -#endif /* CONFIG_6xx */ +#endif /* CONFIG_PPC_BOOK3S_32 */ .section .text diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c @@ -832,8 +832,7 @@ static int smp_core99_kick_cpu(int nr) mdelay(1); /* Restore our exception vector */ - *vector = save_vector; - flush_icache_range((unsigned long) vector, (unsigned long) vector + 4); + patch_instruction(vector, save_vector); local_irq_restore(flags); if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu done", 0x347); diff --git a/arch/powerpc/platforms/powermac/udbg_adb.c b/arch/powerpc/platforms/powermac/udbg_adb.c @@ -194,7 +194,7 @@ int __init udbg_adb_init(int force_btext) */ for_each_node_by_name(np, "keyboard") { struct device_node *parent = of_get_parent(np); - int found = (parent && strcmp(parent->type, "adb") == 0); + int found = of_node_is_type(parent, "adb"); of_node_put(parent); if (found) break; diff --git a/arch/powerpc/platforms/powermac/udbg_scc.c b/arch/powerpc/platforms/powermac/udbg_scc.c @@ -87,7 +87,7 @@ void udbg_scc_init(int force_scc) for (ch = NULL; (ch = of_get_next_child(escc, ch)) != NULL;) { if (ch == stdout) ch_def = of_node_get(ch); - if (strcmp(ch->name, "ch-a") == 0) + if (of_node_name_eq(ch, "ch-a")) ch_a = of_node_get(ch); } if (ch_def == NULL && !force_scc) diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -564,8 +564,8 @@ static void pnv_eeh_get_phb_diag(struct eeh_pe *pe) static int pnv_eeh_get_phb_state(struct eeh_pe *pe) { struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; s64 rc; int result = 0; @@ -603,8 +603,8 @@ static int pnv_eeh_get_phb_state(struct eeh_pe *pe) static int pnv_eeh_get_pe_state(struct eeh_pe *pe) { struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; s64 rc; int result; diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c @@ -9,32 +9,19 @@ * 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 <linux/sizes.h> #include <asm/debugfs.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> #include <asm/opal.h> -#include "powernv.h" #include "pci.h" -#define npu_to_phb(x) container_of(x, struct pnv_phb, npu) - /* * spinlock to protect initialisation of an npu_context for a particular * mm_struct. @@ -133,15 +120,25 @@ static struct pnv_ioda_pe *get_gpu_pci_dev_and_pe(struct pnv_ioda_pe *npe, return pe; } -long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num, +static long pnv_npu_unset_window(struct iommu_table_group *table_group, + int num); + +static long pnv_npu_set_window(struct iommu_table_group *table_group, int num, struct iommu_table *tbl) { + struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe, + table_group); struct pnv_phb *phb = npe->phb; int64_t rc; const unsigned long size = tbl->it_indirect_levels ? tbl->it_level_size : tbl->it_size; const __u64 start_addr = tbl->it_offset << tbl->it_page_shift; const __u64 win_size = tbl->it_size << tbl->it_page_shift; + int num2 = (num == 0) ? 1 : 0; + + /* NPU has just one TVE so if there is another table, remove it first */ + if (npe->table_group.tables[num2]) + pnv_npu_unset_window(&npe->table_group, num2); pe_info(npe, "Setting up window %llx..%llx pg=%lx\n", start_addr, start_addr + win_size - 1, @@ -167,11 +164,16 @@ long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num, return 0; } -long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num) +static long pnv_npu_unset_window(struct iommu_table_group *table_group, int num) { + struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe, + table_group); struct pnv_phb *phb = npe->phb; int64_t rc; + if (!npe->table_group.tables[num]) + return 0; + pe_info(npe, "Removing DMA window\n"); rc = opal_pci_map_pe_dma_window(phb->opal_id, npe->pe_number, @@ -210,7 +212,8 @@ static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe) if (!gpe) return; - rc = pnv_npu_set_window(npe, 0, gpe->table_group.tables[0]); + rc = pnv_npu_set_window(&npe->table_group, 0, + gpe->table_group.tables[0]); /* * NVLink devices use the same TCE table configuration as @@ -235,7 +238,7 @@ static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe) if (phb->type != PNV_PHB_NPU_NVLINK || !npe->pdev) return -EINVAL; - rc = pnv_npu_unset_window(npe, 0); + rc = pnv_npu_unset_window(&npe->table_group, 0); if (rc != OPAL_SUCCESS) return rc; @@ -288,11 +291,15 @@ void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass) } } +#ifdef CONFIG_IOMMU_API /* Switch ownership from platform code to external user (e.g. VFIO) */ -void pnv_npu_take_ownership(struct pnv_ioda_pe *npe) +static void pnv_npu_take_ownership(struct iommu_table_group *table_group) { + struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe, + table_group); struct pnv_phb *phb = npe->phb; int64_t rc; + struct pci_dev *gpdev = NULL; /* * Note: NPU has just a single TVE in the hardware which means that @@ -301,7 +308,7 @@ void pnv_npu_take_ownership(struct pnv_ioda_pe *npe) * if it was enabled at the moment of ownership change. */ if (npe->table_group.tables[0]) { - pnv_npu_unset_window(npe, 0); + pnv_npu_unset_window(&npe->table_group, 0); return; } @@ -314,30 +321,315 @@ void pnv_npu_take_ownership(struct pnv_ioda_pe *npe) return; } pnv_pci_ioda2_tce_invalidate_entire(npe->phb, false); + + get_gpu_pci_dev_and_pe(npe, &gpdev); + if (gpdev) + pnv_npu2_unmap_lpar_dev(gpdev); } -struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe) +static void pnv_npu_release_ownership(struct iommu_table_group *table_group) { - struct pnv_phb *phb = npe->phb; - struct pci_bus *pbus = phb->hose->bus; - struct pci_dev *npdev, *gpdev = NULL, *gptmp; - struct pnv_ioda_pe *gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); + struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe, + table_group); + struct pci_dev *gpdev = NULL; + + get_gpu_pci_dev_and_pe(npe, &gpdev); + if (gpdev) + pnv_npu2_map_lpar_dev(gpdev, 0, MSR_DR | MSR_PR | MSR_HV); +} + +static struct iommu_table_group_ops pnv_pci_npu_ops = { + .set_window = pnv_npu_set_window, + .unset_window = pnv_npu_unset_window, + .take_ownership = pnv_npu_take_ownership, + .release_ownership = pnv_npu_release_ownership, +}; +#endif /* !CONFIG_IOMMU_API */ + +/* + * NPU2 ATS + */ +/* Maximum possible number of ATSD MMIO registers per NPU */ +#define NV_NMMU_ATSD_REGS 8 +#define NV_NPU_MAX_PE_NUM 16 + +/* + * A compound NPU IOMMU group which might consist of 1 GPU + 2xNPUs (POWER8) or + * up to 3 x (GPU + 2xNPUs) (POWER9). + */ +struct npu_comp { + struct iommu_table_group table_group; + int pe_num; + struct pnv_ioda_pe *pe[NV_NPU_MAX_PE_NUM]; +}; + +/* An NPU descriptor, valid for POWER9 only */ +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; + + /* Do we need to explicitly flush the nest mmu? */ + bool nmmu_flush; + + struct npu_comp npucomp; +}; + +#ifdef CONFIG_IOMMU_API +static long pnv_npu_peers_create_table_userspace( + struct iommu_table_group *table_group, + int num, __u32 page_shift, __u64 window_size, __u32 levels, + struct iommu_table **ptbl) +{ + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + if (!npucomp->pe_num || !npucomp->pe[0] || + !npucomp->pe[0]->table_group.ops || + !npucomp->pe[0]->table_group.ops->create_table) + return -EFAULT; + + return npucomp->pe[0]->table_group.ops->create_table( + &npucomp->pe[0]->table_group, num, page_shift, + window_size, levels, ptbl); +} + +static long pnv_npu_peers_set_window(struct iommu_table_group *table_group, + int num, struct iommu_table *tbl) +{ + int i, j; + long ret = 0; + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + for (i = 0; i < npucomp->pe_num; ++i) { + struct pnv_ioda_pe *pe = npucomp->pe[i]; + + if (!pe->table_group.ops->set_window) + continue; + + ret = pe->table_group.ops->set_window(&pe->table_group, + num, tbl); + if (ret) + break; + } + + if (ret) { + for (j = 0; j < i; ++j) { + struct pnv_ioda_pe *pe = npucomp->pe[j]; + + if (!pe->table_group.ops->unset_window) + continue; + + ret = pe->table_group.ops->unset_window( + &pe->table_group, num); + if (ret) + break; + } + } else { + table_group->tables[num] = iommu_tce_table_get(tbl); + } + + return ret; +} - if (!gpe || !gpdev) +static long pnv_npu_peers_unset_window(struct iommu_table_group *table_group, + int num) +{ + int i, j; + long ret = 0; + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + for (i = 0; i < npucomp->pe_num; ++i) { + struct pnv_ioda_pe *pe = npucomp->pe[i]; + + WARN_ON(npucomp->table_group.tables[num] != + table_group->tables[num]); + if (!npucomp->table_group.tables[num]) + continue; + + if (!pe->table_group.ops->unset_window) + continue; + + ret = pe->table_group.ops->unset_window(&pe->table_group, num); + if (ret) + break; + } + + if (ret) { + for (j = 0; j < i; ++j) { + struct pnv_ioda_pe *pe = npucomp->pe[j]; + + if (!npucomp->table_group.tables[num]) + continue; + + if (!pe->table_group.ops->set_window) + continue; + + ret = pe->table_group.ops->set_window(&pe->table_group, + num, table_group->tables[num]); + if (ret) + break; + } + } else if (table_group->tables[num]) { + iommu_tce_table_put(table_group->tables[num]); + table_group->tables[num] = NULL; + } + + return ret; +} + +static void pnv_npu_peers_take_ownership(struct iommu_table_group *table_group) +{ + int i; + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + for (i = 0; i < npucomp->pe_num; ++i) { + struct pnv_ioda_pe *pe = npucomp->pe[i]; + + if (!pe->table_group.ops->take_ownership) + continue; + pe->table_group.ops->take_ownership(&pe->table_group); + } +} + +static void pnv_npu_peers_release_ownership( + struct iommu_table_group *table_group) +{ + int i; + struct npu_comp *npucomp = container_of(table_group, struct npu_comp, + table_group); + + for (i = 0; i < npucomp->pe_num; ++i) { + struct pnv_ioda_pe *pe = npucomp->pe[i]; + + if (!pe->table_group.ops->release_ownership) + continue; + pe->table_group.ops->release_ownership(&pe->table_group); + } +} + +static struct iommu_table_group_ops pnv_npu_peers_ops = { + .get_table_size = pnv_pci_ioda2_get_table_size, + .create_table = pnv_npu_peers_create_table_userspace, + .set_window = pnv_npu_peers_set_window, + .unset_window = pnv_npu_peers_unset_window, + .take_ownership = pnv_npu_peers_take_ownership, + .release_ownership = pnv_npu_peers_release_ownership, +}; + +static void pnv_comp_attach_table_group(struct npu_comp *npucomp, + struct pnv_ioda_pe *pe) +{ + if (WARN_ON(npucomp->pe_num == NV_NPU_MAX_PE_NUM)) + return; + + npucomp->pe[npucomp->pe_num] = pe; + ++npucomp->pe_num; +} + +struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe) +{ + struct iommu_table_group *table_group; + struct npu_comp *npucomp; + struct pci_dev *gpdev = NULL; + struct pci_controller *hose; + struct pci_dev *npdev = NULL; + + list_for_each_entry(gpdev, &pe->pbus->devices, bus_list) { + npdev = pnv_pci_get_npu_dev(gpdev, 0); + if (npdev) + break; + } + + if (!npdev) + /* It is not an NPU attached device, skip */ + return NULL; + + hose = pci_bus_to_host(npdev->bus); + + if (hose->npu) { + table_group = &hose->npu->npucomp.table_group; + + if (!table_group->group) { + table_group->ops = &pnv_npu_peers_ops; + iommu_register_group(table_group, + hose->global_number, + pe->pe_number); + } + } else { + /* Create a group for 1 GPU and attached NPUs for POWER8 */ + pe->npucomp = kzalloc(sizeof(pe->npucomp), GFP_KERNEL); + table_group = &pe->npucomp->table_group; + table_group->ops = &pnv_npu_peers_ops; + iommu_register_group(table_group, hose->global_number, + pe->pe_number); + } + + /* Steal capabilities from a GPU PE */ + table_group->max_dynamic_windows_supported = + pe->table_group.max_dynamic_windows_supported; + table_group->tce32_start = pe->table_group.tce32_start; + table_group->tce32_size = pe->table_group.tce32_size; + table_group->max_levels = pe->table_group.max_levels; + if (!table_group->pgsizes) + table_group->pgsizes = pe->table_group.pgsizes; + + npucomp = container_of(table_group, struct npu_comp, table_group); + pnv_comp_attach_table_group(npucomp, pe); + + return table_group; +} + +struct iommu_table_group *pnv_npu_compound_attach(struct pnv_ioda_pe *pe) +{ + struct iommu_table_group *table_group; + struct npu_comp *npucomp; + struct pci_dev *gpdev = NULL; + struct pci_dev *npdev; + struct pnv_ioda_pe *gpe = get_gpu_pci_dev_and_pe(pe, &gpdev); + + WARN_ON(!(pe->flags & PNV_IODA_PE_DEV)); + if (!gpe) return NULL; - list_for_each_entry(npdev, &pbus->devices, bus_list) { - gptmp = pnv_pci_get_gpu_dev(npdev); + /* + * IODA2 bridges get this set up from pci_controller_ops::setup_bridge + * but NPU bridges do not have this hook defined so we do it here. + * We do not setup other table group parameters as they won't be used + * anyway - NVLink bridges are subordinate PEs. + */ + pe->table_group.ops = &pnv_pci_npu_ops; + + table_group = iommu_group_get_iommudata( + iommu_group_get(&gpdev->dev)); + + /* + * On P9 NPU PHB and PCI PHB support different page sizes, + * keep only matching. We expect here that NVLink bridge PE pgsizes is + * initialized by the caller. + */ + table_group->pgsizes &= pe->table_group.pgsizes; + npucomp = container_of(table_group, struct npu_comp, table_group); + pnv_comp_attach_table_group(npucomp, pe); + + list_for_each_entry(npdev, &pe->phb->hose->bus->devices, bus_list) { + struct pci_dev *gpdevtmp = pnv_pci_get_gpu_dev(npdev); - if (gptmp != gpdev) + if (gpdevtmp != gpdev) continue; - pe_info(gpe, "Attached NPU %s\n", dev_name(&npdev->dev)); - iommu_group_add_device(gpe->table_group.group, &npdev->dev); + iommu_add_device(table_group, &npdev->dev); } - return gpe; + return table_group; } +#endif /* CONFIG_IOMMU_API */ /* Maximum number of nvlinks per npu */ #define NV_MAX_LINKS 6 @@ -490,7 +782,6 @@ static void acquire_atsd_reg(struct npu_context *npu_context, int i, j; struct npu *npu; struct pci_dev *npdev; - struct pnv_phb *nphb; for (i = 0; i <= max_npu2_index; i++) { mmio_atsd_reg[i].reg = -1; @@ -505,8 +796,10 @@ static void acquire_atsd_reg(struct npu_context *npu_context, if (!npdev) continue; - nphb = pci_bus_to_host(npdev->bus)->private_data; - npu = &nphb->npu; + npu = pci_bus_to_host(npdev->bus)->npu; + if (!npu) + continue; + mmio_atsd_reg[i].npu = npu; mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu); while (mmio_atsd_reg[i].reg < 0) { @@ -671,9 +964,9 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, 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; + struct pci_controller *hose; /* * At present we don't support GPUs connected to multiple NPUs and I'm @@ -681,13 +974,14 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, */ 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); + /* We only support DR/PR/HV in pnv_npu2_map_lpar_dev() */ + if (flags & ~(MSR_DR | MSR_PR | MSR_HV)) + return ERR_PTR(-EINVAL); + 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))) @@ -701,20 +995,10 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, 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. It is safe for these to be - * called concurrently with destroy as the OPAL call takes appropriate - * locks and refcounts on init/destroy. - */ - 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); + hose = pci_bus_to_host(npdev->bus); + npu = hose->npu; + if (!npu) + return ERR_PTR(-ENODEV); /* * We store the npu pci device so we can more easily get at the @@ -726,9 +1010,6 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, if (npu_context->release_cb != cb || npu_context->priv != priv) { spin_unlock(&npu_context_lock); - opal_npu_destroy_context(nphb->opal_id, mm->context.id, - PCI_DEVID(gpdev->bus->number, - gpdev->devfn)); return ERR_PTR(-EINVAL); } @@ -754,9 +1035,6 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, if (rc) { kfree(npu_context); - opal_npu_destroy_context(nphb->opal_id, mm->context.id, - PCI_DEVID(gpdev->bus->number, - gpdev->devfn)); return ERR_PTR(rc); } @@ -776,7 +1054,7 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, */ WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], npdev); - if (!nphb->npu.nmmu_flush) { + if (!npu->nmmu_flush) { /* * If we're not explicitly flushing ourselves we need to mark * the thread for global flushes @@ -809,27 +1087,24 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context, struct pci_dev *gpdev) { int removed; - struct pnv_phb *nphb; struct npu *npu; struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); struct device_node *nvlink_dn; u32 nvlink_index; + struct pci_controller *hose; if (WARN_ON(!npdev)) return; - if (!firmware_has_feature(FW_FEATURE_OPAL)) + hose = pci_bus_to_host(npdev->bus); + npu = hose->npu; + if (!npu) return; - - nphb = pci_bus_to_host(npdev->bus)->private_data; - npu = &nphb->npu; 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; WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL); - opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id, - PCI_DEVID(gpdev->bus->number, gpdev->devfn)); spin_lock(&npu_context_lock); removed = kref_put(&npu_context->kref, pnv_npu2_release_context); spin_unlock(&npu_context_lock); @@ -857,13 +1132,12 @@ int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, u64 rc = 0, result = 0; int i, is_write; struct page *page[1]; + const char __user *u; + char c; /* 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++) { @@ -872,18 +1146,17 @@ int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, 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; } + /* Make sure partition scoped tree gets a pte */ + u = page_address(page[0]); + if (__get_user(c, u)) + result = -EFAULT; + status[i] = 0; put_page(page[0]); } @@ -892,42 +1165,127 @@ int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, } EXPORT_SYMBOL(pnv_npu2_handle_fault); -int pnv_npu2_init(struct pnv_phb *phb) +int pnv_npu2_init(struct pci_controller *hose) { unsigned int i; u64 mmio_atsd; - struct device_node *dn; - struct pci_dev *gpdev; static int npu_index; - uint64_t rc = 0; - - phb->npu.nmmu_flush = - of_property_read_bool(phb->hose->dn, "ibm,nmmu-flush"); - 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); - } - } + struct npu *npu; + int ret; + + npu = kzalloc(sizeof(*npu), GFP_KERNEL); + if (!npu) + return -ENOMEM; - 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); + npu->nmmu_flush = of_property_read_bool(hose->dn, "ibm,nmmu-flush"); - 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; + for (i = 0; i < ARRAY_SIZE(npu->mmio_atsd_regs) && + !of_property_read_u64_index(hose->dn, "ibm,mmio-atsd", + i, &mmio_atsd); i++) + npu->mmio_atsd_regs[i] = ioremap(mmio_atsd, 32); + + pr_info("NPU%d: Found %d MMIO ATSD registers", hose->global_number, i); + npu->mmio_atsd_count = i; + npu->mmio_atsd_usage = 0; npu_index++; - if (WARN_ON(npu_index >= NV_MAX_NPUS)) - return -ENOSPC; + if (WARN_ON(npu_index >= NV_MAX_NPUS)) { + ret = -ENOSPC; + goto fail_exit; + } max_npu2_index = npu_index; - phb->npu.index = npu_index; + npu->index = npu_index; + hose->npu = npu; + + return 0; + +fail_exit: + for (i = 0; i < npu->mmio_atsd_count; ++i) + iounmap(npu->mmio_atsd_regs[i]); + + kfree(npu); + + return ret; +} + +int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid, + unsigned long msr) +{ + int ret; + struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); + struct pci_controller *hose; + struct pnv_phb *nphb; + + if (!npdev) + return -ENODEV; + + hose = pci_bus_to_host(npdev->bus); + nphb = hose->private_data; + + dev_dbg(&gpdev->dev, "Map LPAR opalid=%llu lparid=%u\n", + nphb->opal_id, lparid); + /* + * Currently we only support radix and non-zero LPCR only makes sense + * for hash tables so skiboot expects the LPCR parameter to be a zero. + */ + ret = opal_npu_map_lpar(nphb->opal_id, + PCI_DEVID(gpdev->bus->number, gpdev->devfn), lparid, + 0 /* LPCR bits */); + if (ret) { + dev_err(&gpdev->dev, "Error %d mapping device to LPAR\n", ret); + return ret; + } + + dev_dbg(&gpdev->dev, "init context opalid=%llu msr=%lx\n", + nphb->opal_id, msr); + ret = opal_npu_init_context(nphb->opal_id, 0/*__unused*/, msr, + PCI_DEVID(gpdev->bus->number, gpdev->devfn)); + if (ret < 0) + dev_err(&gpdev->dev, "Failed to init context: %d\n", ret); + else + ret = 0; return 0; } +EXPORT_SYMBOL_GPL(pnv_npu2_map_lpar_dev); + +void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr) +{ + struct pci_dev *gpdev; + + list_for_each_entry(gpdev, &gpe->pbus->devices, bus_list) + pnv_npu2_map_lpar_dev(gpdev, 0, msr); +} + +int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev) +{ + int ret; + struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); + struct pci_controller *hose; + struct pnv_phb *nphb; + + if (!npdev) + return -ENODEV; + + hose = pci_bus_to_host(npdev->bus); + nphb = hose->private_data; + + dev_dbg(&gpdev->dev, "destroy context opalid=%llu\n", + nphb->opal_id); + ret = opal_npu_destroy_context(nphb->opal_id, 0/*__unused*/, + PCI_DEVID(gpdev->bus->number, gpdev->devfn)); + if (ret < 0) { + dev_err(&gpdev->dev, "Failed to destroy context: %d\n", ret); + return ret; + } + + /* Set LPID to 0 anyway, just to be safe */ + dev_dbg(&gpdev->dev, "Map LPAR opalid=%llu lparid=0\n", nphb->opal_id); + ret = opal_npu_map_lpar(nphb->opal_id, + PCI_DEVID(gpdev->bus->number, gpdev->devfn), 0 /*LPID*/, + 0 /* LPCR bits */); + if (ret) + dev_err(&gpdev->dev, "Error %d mapping device to LPAR\n", ret); + + return ret; +} +EXPORT_SYMBOL_GPL(pnv_npu2_unmap_lpar_dev); diff --git a/arch/powerpc/platforms/powernv/opal-power.c b/arch/powerpc/platforms/powernv/opal-power.c @@ -138,7 +138,7 @@ static struct notifier_block opal_power_control_nb = { .priority = 0, }; -static int __init opal_power_control_init(void) +int __init opal_power_control_init(void) { int ret, supported = 0; struct device_node *np; @@ -176,4 +176,3 @@ static int __init opal_power_control_init(void) return 0; } -machine_subsys_initcall(powernv, opal_power_control_init); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c @@ -877,7 +877,7 @@ static int __init opal_init(void) consoles = of_find_node_by_path("/ibm,opal/consoles"); if (consoles) { for_each_child_of_node(consoles, np) { - if (strcmp(np->name, "serial")) + if (!of_node_name_eq(np, "serial")) continue; of_platform_device_create(np, NULL, NULL); } @@ -960,6 +960,9 @@ static int __init opal_init(void) /* Initialise OPAL sensor groups */ opal_sensor_groups_init(); + /* Initialise OPAL Power control interface */ + opal_power_control_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -299,7 +299,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, if (alloc_userspace_copy) { offset = 0; uas = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, - levels, tce_table_size, &offset, + tmplevels, tce_table_size, &offset, &total_allocated_uas); if (!uas) goto free_tces_exit; @@ -368,6 +368,7 @@ void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, found = false; for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { if (table_group->tables[i] == tbl) { + iommu_tce_table_put(tbl); table_group->tables[i] = NULL; found = true; break; @@ -393,7 +394,7 @@ long pnv_pci_link_table_and_group(int node, int num, tgl->table_group = table_group; list_add_rcu(&tgl->next, &tbl->it_group_list); - table_group->tables[num] = tbl; + table_group->tables[num] = iommu_tce_table_get(tbl); return 0; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -190,7 +190,8 @@ static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe) unsigned int pe_num = pe->pe_number; WARN_ON(pe->pdev); - + WARN_ON(pe->npucomp); /* NPUs are not supposed to be freed */ + kfree(pe->npucomp); memset(pe, 0, sizeof(struct pnv_ioda_pe)); clear_bit(pe_num, phb->ioda.pe_alloc); } @@ -517,8 +518,6 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) phb->init_m64 = pnv_ioda1_init_m64; else phb->init_m64 = pnv_ioda2_init_m64; - phb->reserve_m64_pe = pnv_ioda_reserve_m64_pe; - phb->pick_m64_pe = pnv_ioda_pick_m64_pe; } static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no) @@ -604,8 +603,8 @@ static int pnv_ioda_unfreeze_pe(struct pnv_phb *phb, int pe_no, int opt) static int pnv_ioda_get_pe_state(struct pnv_phb *phb, int pe_no) { struct pnv_ioda_pe *slave, *pe; - u8 fstate, state; - __be16 pcierr; + u8 fstate = 0, state; + __be16 pcierr = 0; s64 rc; /* Sanity check on PE number */ @@ -663,10 +662,6 @@ static int pnv_ioda_get_pe_state(struct pnv_phb *phb, int pe_no) return state; } -/* Currently those 2 are only used when MSIs are enabled, this will change - * but in the meantime, we need to protect them to avoid warnings - */ -#ifdef CONFIG_PCI_MSI struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); @@ -679,7 +674,6 @@ struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) return NULL; return &phb->ioda.pe_array[pdn->pe_number]; } -#endif /* CONFIG_PCI_MSI */ static int pnv_ioda_set_one_peltv(struct pnv_phb *phb, struct pnv_ioda_pe *parent, @@ -1160,8 +1154,8 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all) pe = &phb->ioda.pe_array[phb->ioda.root_pe_idx]; /* Check if PE is determined by M64 */ - if (!pe && phb->pick_m64_pe) - pe = phb->pick_m64_pe(bus, all); + if (!pe) + pe = pnv_ioda_pick_m64_pe(bus, all); /* The PE number isn't pinned by M64 */ if (!pe) @@ -1273,19 +1267,20 @@ static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus) static void pnv_pci_ioda_setup_PEs(void) { - struct pci_controller *hose, *tmp; + struct pci_controller *hose; struct pnv_phb *phb; struct pci_bus *bus; struct pci_dev *pdev; + struct pnv_ioda_pe *pe; - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + list_for_each_entry(hose, &hose_list, list_node) { phb = hose->private_data; if (phb->type == PNV_PHB_NPU_NVLINK) { /* 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); + WARN_ON_ONCE(pnv_npu2_init(hose)); } if (phb->type == PNV_PHB_NPU_OCAPI) { bus = hose->bus; @@ -1293,6 +1288,14 @@ static void pnv_pci_ioda_setup_PEs(void) pnv_ioda_setup_dev_PE(pdev); } } + list_for_each_entry(hose, &hose_list, list_node) { + phb = hose->private_data; + if (phb->type != PNV_PHB_IODA2) + continue; + + list_for_each_entry(pe, &phb->ioda.pe_list, list) + pnv_npu2_map_lpar(pe, MSR_DR | MSR_PR | MSR_HV); + } } #ifdef CONFIG_PCI_IOV @@ -1531,6 +1534,11 @@ void pnv_pci_sriov_disable(struct pci_dev *pdev) static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe); +#ifdef CONFIG_IOMMU_API +static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe, + struct iommu_table_group *table_group, struct pci_bus *bus); + +#endif static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) { struct pci_bus *bus; @@ -1584,6 +1592,9 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) mutex_unlock(&phb->ioda.pe_list_mutex); pnv_pci_ioda2_setup_dma_pe(phb, pe); +#ifdef CONFIG_IOMMU_API + pnv_ioda_setup_bus_iommu_group(pe, &pe->table_group, NULL); +#endif } } @@ -1923,21 +1934,16 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev) return mask; } -static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, - struct pci_bus *bus, - bool add_to_group) +static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) { struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { set_iommu_table_base(&dev->dev, pe->table_group.tables[0]); set_dma_offset(&dev->dev, pe->tce_bypass_base); - 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, - add_to_group); + pnv_ioda_setup_bus_dma(pe, dev->subordinate); } } @@ -2366,16 +2372,8 @@ found: pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift; iommu_init_table(tbl, phb->hose->node); - if (pe->flags & PNV_IODA_PE_DEV) { - /* - * Setting table base here only for carrying iommu_group - * further down to let iommu_add_device() do the job. - * pnv_pci_ioda_dma_dev_setup will override it later anyway. - */ - 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, true); + if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) + pnv_ioda_setup_bus_dma(pe, pe->pbus); return; fail: @@ -2527,14 +2525,6 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) if (!pnv_iommu_bypass_disabled) pnv_pci_ioda2_set_bypass(pe, true); - /* - * Setting table base here only for carrying iommu_group - * further down to let iommu_add_device() do the job. - * pnv_pci_ioda_dma_dev_setup will override it later anyway. - */ - if (pe->flags & PNV_IODA_PE_DEV) - set_iommu_table_base(&pe->pdev->dev, tbl); - return 0; } @@ -2565,7 +2555,7 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group, #endif #ifdef CONFIG_IOMMU_API -static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, +unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, __u64 window_size, __u32 levels) { unsigned long bytes = 0; @@ -2616,7 +2606,7 @@ 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); if (pe->pbus) - pnv_ioda_setup_bus_dma(pe, pe->pbus, false); + pnv_ioda_setup_bus_dma(pe, pe->pbus); iommu_tce_table_put(tbl); } @@ -2627,7 +2617,7 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) pnv_pci_ioda2_setup_default_config(pe); if (pe->pbus) - pnv_ioda_setup_bus_dma(pe, pe->pbus, false); + pnv_ioda_setup_bus_dma(pe, pe->pbus); } static struct iommu_table_group_ops pnv_pci_ioda2_ops = { @@ -2639,131 +2629,100 @@ static struct iommu_table_group_ops pnv_pci_ioda2_ops = { .release_ownership = pnv_ioda2_release_ownership, }; -static int gpe_table_group_to_npe_cb(struct device *dev, void *opaque) +static void pnv_ioda_setup_bus_iommu_group_add_devices(struct pnv_ioda_pe *pe, + struct iommu_table_group *table_group, + struct pci_bus *bus) { - struct pci_controller *hose; - struct pnv_phb *phb; - struct pnv_ioda_pe **ptmppe = opaque; - struct pci_dev *pdev = container_of(dev, struct pci_dev, dev); - struct pci_dn *pdn = pci_get_pdn(pdev); - - if (!pdn || pdn->pe_number == IODA_INVALID_PE) - return 0; - - hose = pci_bus_to_host(pdev->bus); - phb = hose->private_data; - if (phb->type != PNV_PHB_NPU_NVLINK) - return 0; + struct pci_dev *dev; - *ptmppe = &phb->ioda.pe_array[pdn->pe_number]; + list_for_each_entry(dev, &bus->devices, bus_list) { + iommu_add_device(table_group, &dev->dev); - return 1; + if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) + pnv_ioda_setup_bus_iommu_group_add_devices(pe, + table_group, dev->subordinate); + } } -/* - * This returns PE of associated NPU. - * This assumes that NPU is in the same IOMMU group with GPU and there is - * no other PEs. - */ -static struct pnv_ioda_pe *gpe_table_group_to_npe( - struct iommu_table_group *table_group) +static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe, + struct iommu_table_group *table_group, struct pci_bus *bus) { - struct pnv_ioda_pe *npe = NULL; - int ret = iommu_group_for_each_dev(table_group->group, &npe, - gpe_table_group_to_npe_cb); - BUG_ON(!ret || !npe); + if (pe->flags & PNV_IODA_PE_DEV) + iommu_add_device(table_group, &pe->pdev->dev); - return npe; + if ((pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) || bus) + pnv_ioda_setup_bus_iommu_group_add_devices(pe, table_group, + bus); } -static long pnv_pci_ioda2_npu_set_window(struct iommu_table_group *table_group, - int num, struct iommu_table *tbl) -{ - struct pnv_ioda_pe *npe = gpe_table_group_to_npe(table_group); - int num2 = (num == 0) ? 1 : 0; - long ret = pnv_pci_ioda2_set_window(table_group, num, tbl); - - if (ret) - return ret; - - if (table_group->tables[num2]) - pnv_npu_unset_window(npe, num2); - - ret = pnv_npu_set_window(npe, num, tbl); - if (ret) { - pnv_pci_ioda2_unset_window(table_group, num); - if (table_group->tables[num2]) - pnv_npu_set_window(npe, num2, - table_group->tables[num2]); - } - - return ret; -} +static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb); -static long pnv_pci_ioda2_npu_unset_window( - struct iommu_table_group *table_group, - int num) +static void pnv_pci_ioda_setup_iommu_api(void) { - struct pnv_ioda_pe *npe = gpe_table_group_to_npe(table_group); - int num2 = (num == 0) ? 1 : 0; - long ret = pnv_pci_ioda2_unset_window(table_group, num); - - if (ret) - return ret; - - if (!npe->table_group.tables[num]) - return 0; - - ret = pnv_npu_unset_window(npe, num); - if (ret) - return ret; - - if (table_group->tables[num2]) - ret = pnv_npu_set_window(npe, num2, table_group->tables[num2]); - - return ret; -} + struct pci_controller *hose; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe; -static void pnv_ioda2_npu_take_ownership(struct iommu_table_group *table_group) -{ /* - * Detach NPU first as pnv_ioda2_take_ownership() will destroy - * the iommu_table if 32bit DMA is enabled. + * There are 4 types of PEs: + * - PNV_IODA_PE_BUS: a downstream port with an adapter, + * created from pnv_pci_setup_bridge(); + * - PNV_IODA_PE_BUS_ALL: a PCI-PCIX bridge with devices behind it, + * created from pnv_pci_setup_bridge(); + * - PNV_IODA_PE_VF: a SRIOV virtual function, + * created from pnv_pcibios_sriov_enable(); + * - PNV_IODA_PE_DEV: an NPU or OCAPI device, + * created from pnv_pci_ioda_fixup(). + * + * Normally a PE is represented by an IOMMU group, however for + * devices with side channels the groups need to be more strict. */ - pnv_npu_take_ownership(gpe_table_group_to_npe(table_group)); - pnv_ioda2_take_ownership(table_group); -} + list_for_each_entry(hose, &hose_list, list_node) { + phb = hose->private_data; -static struct iommu_table_group_ops pnv_pci_ioda2_npu_ops = { - .get_table_size = pnv_pci_ioda2_get_table_size, - .create_table = pnv_pci_ioda2_create_table_userspace, - .set_window = pnv_pci_ioda2_npu_set_window, - .unset_window = pnv_pci_ioda2_npu_unset_window, - .take_ownership = pnv_ioda2_npu_take_ownership, - .release_ownership = pnv_ioda2_release_ownership, -}; + if (phb->type == PNV_PHB_NPU_NVLINK) + continue; -static void pnv_pci_ioda_setup_iommu_api(void) -{ - struct pci_controller *hose, *tmp; - struct pnv_phb *phb; - struct pnv_ioda_pe *pe, *gpe; + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + struct iommu_table_group *table_group; + + table_group = pnv_try_setup_npu_table_group(pe); + if (!table_group) { + if (!pnv_pci_ioda_pe_dma_weight(pe)) + continue; + + table_group = &pe->table_group; + iommu_register_group(&pe->table_group, + pe->phb->hose->global_number, + pe->pe_number); + } + pnv_ioda_setup_bus_iommu_group(pe, table_group, + pe->pbus); + } + } /* * Now we have all PHBs discovered, time to add NPU devices to * the corresponding IOMMU groups. */ - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + list_for_each_entry(hose, &hose_list, list_node) { + unsigned long pgsizes; + phb = hose->private_data; if (phb->type != PNV_PHB_NPU_NVLINK) continue; + pgsizes = pnv_ioda_parse_tce_sizes(phb); list_for_each_entry(pe, &phb->ioda.pe_list, list) { - gpe = pnv_pci_npu_setup_iommu(pe); - if (gpe) - gpe->table_group.ops = &pnv_pci_ioda2_npu_ops; + /* + * IODA2 bridges get this set up from + * pci_controller_ops::setup_bridge but NPU bridges + * do not have this hook defined so we do it here. + */ + pe->table_group.pgsizes = pgsizes; + pnv_npu_compound_attach(pe); } } } @@ -2810,9 +2769,6 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, /* TVE #1 is selected by PCI address bit 59 */ pe->tce_bypass_base = 1ull << 59; - iommu_register_group(&pe->table_group, phb->hose->global_number, - pe->pe_number); - /* The PE will reserve all possible 32-bits space */ pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n", phb->ioda.m32_pci_base); @@ -2833,10 +2789,9 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, return; if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) - pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + pnv_ioda_setup_bus_dma(pe, pe->pbus); } -#ifdef CONFIG_PCI_MSI int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq) { struct pnv_phb *phb = container_of(chip, struct pnv_phb, @@ -2982,9 +2937,6 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", count, phb->msi_base); } -#else -static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } -#endif /* CONFIG_PCI_MSI */ #ifdef CONFIG_PCI_IOV static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) @@ -3402,8 +3354,7 @@ static void pnv_pci_setup_bridge(struct pci_bus *bus, unsigned long type) return; /* Reserve PEs according to used M64 resources */ - if (phb->reserve_m64_pe) - phb->reserve_m64_pe(bus, NULL, all); + pnv_ioda_reserve_m64_pe(bus, NULL, all); /* * Assign PE. We might run here because of partial hotplug. @@ -3687,6 +3638,15 @@ static void pnv_pci_release_device(struct pci_dev *pdev) pnv_ioda_release_pe(pe); } +static void pnv_npu_disable_device(struct pci_dev *pdev) +{ + struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); + struct eeh_pe *eehpe = edev ? edev->pe : NULL; + + if (eehpe && eeh_ops && eeh_ops->reset) + eeh_ops->reset(eehpe, EEH_RESET_HOT); +} + static void pnv_pci_ioda_shutdown(struct pci_controller *hose) { struct pnv_phb *phb = hose->private_data; @@ -3698,10 +3658,8 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, .dma_bus_setup = pnv_pci_dma_bus_setup, -#ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, -#endif .enable_device_hook = pnv_pci_enable_device_hook, .release_device = pnv_pci_release_device, .window_alignment = pnv_pci_window_alignment, @@ -3722,15 +3680,14 @@ static int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask) static const struct pci_controller_ops pnv_npu_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, -#ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, -#endif .enable_device_hook = pnv_pci_enable_device_hook, .window_alignment = pnv_pci_window_alignment, .reset_secondary_bus = pnv_pci_reset_secondary_bus, .dma_set_mask = pnv_npu_dma_set_mask, .shutdown = pnv_pci_ioda_shutdown, + .disable_device = pnv_npu_disable_device, }; static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = { diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c @@ -160,7 +160,6 @@ exit: } EXPORT_SYMBOL_GPL(pnv_pci_set_power_state); -#ifdef CONFIG_PCI_MSI int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); @@ -229,7 +228,6 @@ void pnv_teardown_msi_irqs(struct pci_dev *pdev) msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, 1); } } -#endif /* CONFIG_PCI_MSI */ /* Nicely print the contents of the PE State Tables (PEST). */ static void pnv_pci_dump_pest(__be64 pestA[], __be64 pestB[], int pest_size) @@ -602,8 +600,8 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) static void pnv_pci_config_check_eeh(struct pci_dn *pdn) { struct pnv_phb *phb = pdn->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; unsigned int pe_no; s64 rc; @@ -1127,4 +1125,45 @@ void __init pnv_pci_init(void) set_pci_dma_ops(&dma_iommu_ops); } -machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init); +static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + struct pci_dev *pdev; + struct pci_dn *pdn; + struct pnv_ioda_pe *pe; + struct pci_controller *hose; + struct pnv_phb *phb; + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + pdev = to_pci_dev(dev); + pdn = pci_get_pdn(pdev); + hose = pci_bus_to_host(pdev->bus); + phb = hose->private_data; + + WARN_ON_ONCE(!phb); + if (!pdn || pdn->pe_number == IODA_INVALID_PE || !phb) + return 0; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + iommu_add_device(&pe->table_group, dev); + return 0; + case BUS_NOTIFY_DEL_DEVICE: + iommu_del_device(dev); + return 0; + default: + return 0; + } +} + +static struct notifier_block pnv_tce_iommu_bus_nb = { + .notifier_call = pnv_tce_iommu_bus_notifier, +}; + +static int __init pnv_tce_iommu_bus_notifier_init(void) +{ + bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb); + return 0; +} +machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h @@ -8,9 +8,6 @@ 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, @@ -65,6 +62,7 @@ struct pnv_ioda_pe { /* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */ struct iommu_table_group table_group; + struct npu_comp *npucomp; /* 64-bit TCE bypass region */ bool tce_bypass_enabled; @@ -106,20 +104,14 @@ struct pnv_phb { struct dentry *dbgfs; #endif -#ifdef CONFIG_PCI_MSI unsigned int msi_base; unsigned int msi32_support; struct msi_bitmap msi_bmp; -#endif int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev, unsigned int hwirq, unsigned int virq, unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); - void (*fixup_phb)(struct pci_controller *hose); int (*init_m64)(struct pnv_phb *phb); - void (*reserve_m64_pe)(struct pci_bus *bus, - unsigned long *pe_bitmap, bool all); - struct pnv_ioda_pe *(*pick_m64_pe)(struct pci_bus *bus, bool all); int (*get_pe_state)(struct pnv_phb *phb, int pe_no); void (*freeze_pe)(struct pnv_phb *phb, int pe_no); int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt); @@ -180,19 +172,6 @@ struct pnv_phb { unsigned int diag_data_size; u8 *diag_data; - /* 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; - - /* Do we need to explicitly flush the nest mmu? */ - bool nmmu_flush; - } npu; - int p2p_target_count; }; @@ -210,6 +189,7 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_init_npu_phb(struct device_node *np); extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np); +extern void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr); extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); @@ -220,6 +200,8 @@ extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev); extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq); extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable); +extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, + __u64 window_size, __u32 levels); extern int pnv_eeh_post_init(void); extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, @@ -235,12 +217,10 @@ extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass); 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); +extern struct iommu_table_group *pnv_try_setup_npu_table_group( + struct pnv_ioda_pe *pe); +extern struct iommu_table_group *pnv_npu_compound_attach( + struct pnv_ioda_pe *pe); /* pci-ioda-tce.c */ #define POWERNV_IOMMU_DEFAULT_LEVELS 1 diff --git a/arch/powerpc/platforms/powernv/vas-debug.c b/arch/powerpc/platforms/powernv/vas-debug.c @@ -30,7 +30,7 @@ static char *cop_to_str(int cop) } } -static int info_dbg_show(struct seq_file *s, void *private) +static int info_show(struct seq_file *s, void *private) { struct vas_window *window = s->private; @@ -49,17 +49,7 @@ unlock: return 0; } -static int info_dbg_open(struct inode *inode, struct file *file) -{ - return single_open(file, info_dbg_show, inode->i_private); -} - -static const struct file_operations info_fops = { - .open = info_dbg_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(info); static inline void print_reg(struct seq_file *s, struct vas_window *win, char *name, u32 reg) @@ -67,7 +57,7 @@ static inline void print_reg(struct seq_file *s, struct vas_window *win, seq_printf(s, "0x%016llx %s\n", read_hvwc_reg(win, name, reg), name); } -static int hvwc_dbg_show(struct seq_file *s, void *private) +static int hvwc_show(struct seq_file *s, void *private) { struct vas_window *window = s->private; @@ -115,17 +105,7 @@ unlock: return 0; } -static int hvwc_dbg_open(struct inode *inode, struct file *file) -{ - return single_open(file, hvwc_dbg_show, inode->i_private); -} - -static const struct file_operations hvwc_fops = { - .open = hvwc_dbg_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(hvwc); void vas_window_free_dbgdir(struct vas_window *window) { diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -197,6 +197,7 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb) found = find_aa_index(dr_node, ala_prop, lmb_assoc, &aa_index); + of_node_put(dr_node); dlpar_free_cc_nodes(lmb_node); if (!found) { @@ -313,7 +314,6 @@ out: static int pseries_remove_mem_node(struct device_node *np) { - const char *type; const __be32 *regs; unsigned long base; unsigned int lmb_size; @@ -322,8 +322,7 @@ static int pseries_remove_mem_node(struct device_node *np) /* * Check to see if we are actually removing memory */ - type = of_get_property(np, "device_type", NULL); - if (type == NULL || strcmp(type, "memory") != 0) + if (!of_node_is_type(np, "memory")) return 0; /* @@ -355,8 +354,11 @@ static bool lmb_is_removable(struct drmem_lmb *lmb) phys_addr = lmb->base_addr; #ifdef CONFIG_FA_DUMP - /* Don't hot-remove memory that falls in fadump boot memory area */ - if (is_fadump_boot_memory_area(phys_addr, block_sz)) + /* + * Don't hot-remove memory that falls in fadump boot memory area + * and memory that is reserved for capturing old kernel memory. + */ + if (is_fadump_memory_area(phys_addr, block_sz)) return false; #endif @@ -936,7 +938,6 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) static int pseries_add_mem_node(struct device_node *np) { - const char *type; const __be32 *regs; unsigned long base; unsigned int lmb_size; @@ -945,8 +946,7 @@ static int pseries_add_mem_node(struct device_node *np) /* * Check to see if we are actually adding memory */ - type = of_get_property(np, "device_type", NULL); - if (type == NULL || strcmp(type, "memory") != 0) + if (!of_node_is_type(np, "memory")) return 0; /* diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c @@ -57,7 +57,6 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) { struct iommu_table_group *table_group; struct iommu_table *tbl; - struct iommu_table_group_link *tgl; table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL, node); @@ -68,22 +67,13 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) if (!tbl) goto free_group; - tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL, - node); - if (!tgl) - goto free_table; - 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); table_group->tables[0] = tbl; return table_group; -free_table: - kfree(tbl); free_group: kfree(table_group); return NULL; @@ -93,23 +83,12 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group, const char *node_name) { struct iommu_table *tbl; -#ifdef CONFIG_IOMMU_API - struct iommu_table_group_link *tgl; -#endif if (!table_group) return; tbl = table_group->tables[0]; #ifdef CONFIG_IOMMU_API - tgl = list_first_entry_or_null(&tbl->it_group_list, - struct iommu_table_group_link, next); - - WARN_ON_ONCE(!tgl); - if (tgl) { - list_del_rcu(&tgl->next); - kfree(tgl); - } if (table_group->group) { iommu_group_put(table_group->group); BUG_ON(table_group->group); @@ -645,7 +624,6 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) iommu_table_setparms(pci->phb, dn, tbl); tbl->it_ops = &iommu_table_pseries_ops; iommu_init_table(tbl, pci->phb->node); - iommu_register_group(pci->table_group, pci_domain_nr(bus), 0); /* Divide the rest (1.75GB) among the children */ pci->phb->dma_window_size = 0x80000000ul; @@ -756,10 +734,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) iommu_table_setparms(phb, dn, tbl); tbl->it_ops = &iommu_table_pseries_ops; iommu_init_table(tbl, phb->node); - iommu_register_group(PCI_DN(dn)->table_group, - pci_domain_nr(phb->bus), 0); set_iommu_table_base(&dev->dev, tbl); - iommu_add_device(&dev->dev); return; } @@ -770,11 +745,10 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) while (dn && PCI_DN(dn) && PCI_DN(dn)->table_group == NULL) dn = dn->parent; - if (dn && PCI_DN(dn)) { + if (dn && PCI_DN(dn)) set_iommu_table_base(&dev->dev, PCI_DN(dn)->table_group->tables[0]); - iommu_add_device(&dev->dev); - } else + else printk(KERN_WARNING "iommu: Device %s has no iommu table\n", pci_name(dev)); } @@ -964,6 +938,37 @@ struct failed_ddw_pdn { static LIST_HEAD(failed_ddw_pdn_list); +static phys_addr_t ddw_memory_hotplug_max(void) +{ + phys_addr_t max_addr = memory_hotplug_max(); + struct device_node *memory; + + for_each_node_by_type(memory, "memory") { + unsigned long start, size; + int ranges, n_mem_addr_cells, n_mem_size_cells, len; + const __be32 *memcell_buf; + + memcell_buf = of_get_property(memory, "reg", &len); + if (!memcell_buf || len <= 0) + continue; + + n_mem_addr_cells = of_n_addr_cells(memory); + n_mem_size_cells = of_n_size_cells(memory); + + /* ranges in cell */ + ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells); + + start = of_read_number(memcell_buf, n_mem_addr_cells); + memcell_buf += n_mem_addr_cells; + size = of_read_number(memcell_buf, n_mem_size_cells); + memcell_buf += n_mem_size_cells; + + max_addr = max_t(phys_addr_t, max_addr, start + size); + } + + return max_addr; +} + /* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, @@ -1053,7 +1058,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) } /* verify the window * number of ptes will map the partition */ /* check largest block * page size > max memory hotplug addr */ - max_addr = memory_hotplug_max(); + max_addr = ddw_memory_hotplug_max(); if (query.largest_available_block < (max_addr >> page_shift)) { dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u " "%llu-sized pages\n", max_addr, query.largest_available_block, @@ -1190,7 +1195,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) } set_iommu_table_base(&dev->dev, pci->table_group->tables[0]); - iommu_add_device(&dev->dev); + iommu_add_device(pci->table_group, &dev->dev); } static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) @@ -1395,4 +1400,27 @@ static int __init disable_multitce(char *str) __setup("multitce=", disable_multitce); +static int tce_iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + + switch (action) { + case BUS_NOTIFY_DEL_DEVICE: + iommu_del_device(dev); + return 0; + default: + return 0; + } +} + +static struct notifier_block tce_iommu_bus_nb = { + .notifier_call = tce_iommu_bus_notifier, +}; + +static int __init tce_iommu_bus_notifier_init(void) +{ + bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); + return 0; +} machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c @@ -29,6 +29,7 @@ #include <asm/pci-bridge.h> #include <asm/prom.h> #include <asm/ppc-pci.h> +#include <asm/pci.h> #include "pseries.h" #if 0 @@ -237,6 +238,8 @@ static void __init pSeries_request_regions(void) void __init pSeries_final_fixup(void) { + struct pci_controller *hose; + pSeries_request_regions(); eeh_probe_devices(); @@ -246,6 +249,25 @@ void __init pSeries_final_fixup(void) ppc_md.pcibios_sriov_enable = pseries_pcibios_sriov_enable; ppc_md.pcibios_sriov_disable = pseries_pcibios_sriov_disable; #endif + list_for_each_entry(hose, &hose_list, list_node) { + struct device_node *dn = hose->dn, *nvdn; + + while (1) { + dn = of_find_all_nodes(dn); + if (!dn) + break; + nvdn = of_parse_phandle(dn, "ibm,nvlink", 0); + if (!nvdn) + continue; + if (!of_device_is_compatible(nvdn, "ibm,npu-link")) + continue; + if (!of_device_is_compatible(nvdn->parent, + "ibm,power9-npu")) + continue; + WARN_ON_ONCE(pnv_npu2_init(hose)); + break; + } + } } /* diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c @@ -52,8 +52,8 @@ static ssize_t pmem_drc_add_node(u32 drc_index) /* NB: The of reconfig notifier creates platform device from the node */ rc = dlpar_attach_node(dn, pmem_node); if (rc) { - pr_err("Failed to attach node %s, rc: %d, drc index: %x\n", - dn->name, rc, drc_index); + pr_err("Failed to attach node %pOF, rc: %d, drc index: %x\n", + dn, rc, drc_index); if (dlpar_release_drc(drc_index)) dlpar_free_cc_nodes(dn); @@ -93,8 +93,8 @@ static ssize_t pmem_drc_remove_node(u32 drc_index) rc = dlpar_release_drc(drc_index); if (rc) { - pr_err("Failed to release drc (%x) for CPU %s, rc: %d\n", - drc_index, dn->name, rc); + pr_err("Failed to release drc (%x) for CPU %pOFn, rc: %d\n", + drc_index, dn, rc); dlpar_attach_node(dn, pmem_node); return rc; } diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c @@ -190,7 +190,7 @@ static void __init pseries_setup_i8259_cascade(void) of_node_put(old); if (np == NULL) break; - if (strcmp(np->name, "pci") != 0) + if (!of_node_name_eq(np, "pci")) continue; addrp = of_get_property(np, "8259-interrupt-acknowledge", NULL); if (addrp == NULL) @@ -469,8 +469,8 @@ static void __init find_and_init_phbs(void) struct device_node *root = of_find_node_by_path("/"); for_each_child_of_node(root, node) { - if (node->type == NULL || (strcmp(node->type, "pci") != 0 && - strcmp(node->type, "pciex") != 0)) + if (!of_node_is_type(node, "pci") && + !of_node_is_type(node, "pciex")) continue; phb = pcibios_alloc_controller(node); @@ -978,11 +978,7 @@ static void pseries_power_off(void) static int __init pSeries_probe(void) { - const char *dtype = of_get_property(of_root, "device_type", NULL); - - if (dtype == NULL) - return 0; - if (strcmp(dtype, "chrp")) + if (!of_node_is_type(of_root, "chrp")) return 0; /* Cell blades firmware claims to be chrp while it's not. Until this diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c @@ -1356,9 +1356,9 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) */ parent_node = of_get_parent(of_node); if (parent_node) { - if (!strcmp(parent_node->type, "ibm,platform-facilities")) + if (of_node_is_type(parent_node, "ibm,platform-facilities")) family = PFO; - else if (!strcmp(parent_node->type, "vdevice")) + else if (of_node_is_type(parent_node, "vdevice")) family = VDEVICE; else { pr_warn("%s: parent(%pOF) of %pOFn not recognized.\n", @@ -1395,9 +1395,8 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) if (viodev->family == VDEVICE) { unsigned int unit_address; - if (of_node->type != NULL) - viodev->type = of_node->type; - else { + viodev->type = of_node_get_device_type(of_node); + if (!viodev->type) { pr_warn("%s: node %pOFn is missing the 'device_type' " "property.\n", __func__, of_node); goto out; @@ -1672,32 +1671,30 @@ struct vio_dev *vio_find_node(struct device_node *vnode) { char kobj_name[20]; struct device_node *vnode_parent; - const char *dev_type; vnode_parent = of_get_parent(vnode); if (!vnode_parent) return NULL; - dev_type = of_get_property(vnode_parent, "device_type", NULL); - of_node_put(vnode_parent); - if (!dev_type) - return NULL; - /* construct the kobject name from the device node */ - if (!strcmp(dev_type, "vdevice")) { + if (of_node_is_type(vnode_parent, "vdevice")) { const __be32 *prop; prop = of_get_property(vnode, "reg", NULL); if (!prop) - return NULL; + goto out; snprintf(kobj_name, sizeof(kobj_name), "%x", (uint32_t)of_read_number(prop, 1)); - } else if (!strcmp(dev_type, "ibm,platform-facilities")) + } else if (of_node_is_type(vnode_parent, "ibm,platform-facilities")) snprintf(kobj_name, sizeof(kobj_name), "%pOFn", vnode); else - return NULL; + goto out; + of_node_put(vnode_parent); return vio_find_name(kobj_name); +out: + of_node_put(vnode_parent); + return NULL; } EXPORT_SYMBOL(vio_find_node); diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile @@ -48,7 +48,7 @@ obj-$(CONFIG_PPC_MPC512x) += mpc5xxx_clocks.o obj-$(CONFIG_PPC_MPC52xx) += mpc5xxx_clocks.o ifdef CONFIG_SUSPEND -obj-$(CONFIG_6xx) += 6xx-suspend.o +obj-$(CONFIG_PPC_BOOK3S_32) += 6xx-suspend.o endif obj-$(CONFIG_PPC_SCOM) += scom.o diff --git a/arch/powerpc/sysdev/fsl_rio.h b/arch/powerpc/sysdev/fsl_rio.h @@ -41,7 +41,7 @@ #define DOORBELL_ROWAR_PCI 0x02000000 /* PCI window */ #define DOORBELL_ROWAR_NREAD 0x00040000 /* NREAD */ #define DOORBELL_ROWAR_MAINTRD 0x00070000 /* maintenance read */ -#define DOORBELL_ROWAR_RES 0x00002000 /* wrtpy: reserverd */ +#define DOORBELL_ROWAR_RES 0x00002000 /* wrtpy: reserved */ #define DOORBELL_ROWAR_MAINTWD 0x00007000 #define DOORBELL_ROWAR_SIZE 0x0000000b /* window size is 4k */ diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c @@ -756,15 +756,13 @@ fsl_open_outb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entries) } /* Initialize outbound message descriptor ring */ - rmu->msg_tx_ring.virt = dma_alloc_coherent(priv->dev, + rmu->msg_tx_ring.virt = dma_zalloc_coherent(priv->dev, rmu->msg_tx_ring.size * RIO_MSG_DESC_SIZE, &rmu->msg_tx_ring.phys, GFP_KERNEL); if (!rmu->msg_tx_ring.virt) { rc = -ENOMEM; goto out_dma; } - memset(rmu->msg_tx_ring.virt, 0, - rmu->msg_tx_ring.size * RIO_MSG_DESC_SIZE); rmu->msg_tx_ring.tx_slot = 0; /* Point dequeue/enqueue pointers at first entry in ring */ diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c @@ -771,34 +771,6 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags) return ipic; } -int ipic_set_priority(unsigned int virq, unsigned int priority) -{ - struct ipic *ipic = ipic_from_irq(virq); - unsigned int src = virq_to_hw(virq); - u32 temp; - - if (priority > 7) - return -EINVAL; - if (src > 127) - return -EINVAL; - if (ipic_info[src].prio == 0) - return -EINVAL; - - temp = ipic_read(ipic->regs, ipic_info[src].prio); - - if (priority < 4) { - temp &= ~(0x7 << (20 + (3 - priority) * 3)); - temp |= ipic_info[src].prio_mask << (20 + (3 - priority) * 3); - } else { - temp &= ~(0x7 << (4 + (7 - priority) * 3)); - temp |= ipic_info[src].prio_mask << (4 + (7 - priority) * 3); - } - - ipic_write(ipic->regs, ipic_info[src].prio, temp); - - return 0; -} - void ipic_set_highest_priority(unsigned int virq) { struct ipic *ipic = ipic_from_irq(virq); diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c @@ -60,7 +60,7 @@ scom_map_t scom_map_device(struct device_node *dev, int index) parent = scom_find_parent(dev); if (parent == NULL) - return 0; + return NULL; /* * We support "scom-reg" properties for adding scom registers @@ -83,7 +83,7 @@ scom_map_t scom_map_device(struct device_node *dev, int index) size >>= 2; if (index >= (size / (2*cells))) - return 0; + return NULL; reg = of_read_number(&prop[index * cells * 2], cells); cnt = of_read_number(&prop[index * cells * 2 + cells], cells); diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c @@ -309,7 +309,7 @@ static void xive_do_queue_eoi(struct xive_cpu *xc) * 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) +static 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) diff --git a/arch/powerpc/tools/checkpatch.sh b/arch/powerpc/tools/checkpatch.sh @@ -19,4 +19,5 @@ exec $script_base/../../../scripts/checkpatch.pl \ --ignore GLOBAL_INITIALISERS \ --ignore LINE_SPACING \ --ignore MULTIPLE_ASSIGNMENTS \ + --ignore DT_SPLIT_BINDING_PATCH \ $@ diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c @@ -75,6 +75,9 @@ static int xmon_gate; #define xmon_owner 0 #endif /* CONFIG_SMP */ +#ifdef CONFIG_PPC_PSERIES +static int set_indicator_token = RTAS_UNKNOWN_SERVICE; +#endif static unsigned long in_xmon __read_mostly = 0; static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT); @@ -273,7 +276,7 @@ Commands:\n\ X exit monitor and don't recover\n" #if defined(CONFIG_PPC64) && !defined(CONFIG_PPC_BOOK3E) " u dump segment table or SLB\n" -#elif defined(CONFIG_PPC_STD_MMU_32) +#elif defined(CONFIG_PPC_BOOK3S_32) " u dump segment registers\n" #elif defined(CONFIG_44x) || defined(CONFIG_PPC_BOOK3E) " u dump TLB\n" @@ -358,7 +361,6 @@ static inline void disable_surveillance(void) #ifdef CONFIG_PPC_PSERIES /* Since this can't be a module, args should end up below 4GB. */ static struct rtas_args args; - int token; /* * At this point we have got all the cpus we can into @@ -367,11 +369,11 @@ static inline void disable_surveillance(void) * If we did try to take rtas.lock there would be a * real possibility of deadlock. */ - token = rtas_token("set-indicator"); - if (token == RTAS_UNKNOWN_SERVICE) + if (set_indicator_token == RTAS_UNKNOWN_SERVICE) return; - rtas_call_unlocked(&args, token, 3, 1, NULL, SURVEILLANCE_TOKEN, 0, 0); + rtas_call_unlocked(&args, set_indicator_token, 3, 1, NULL, + SURVEILLANCE_TOKEN, 0, 0); #endif /* CONFIG_PPC_PSERIES */ } @@ -1058,7 +1060,7 @@ cmds(struct pt_regs *excp) case 'P': show_tasks(); break; -#ifdef CONFIG_PPC_STD_MMU +#ifdef CONFIG_PPC_BOOK3S case 'u': dump_segments(); break; @@ -2793,7 +2795,7 @@ print_address(unsigned long addr) xmon_print_symbol(addr, "\t# ", ""); } -void +static void dump_log_buf(void) { struct kmsg_dumper dumper = { .active = 1 }; @@ -2994,13 +2996,13 @@ static void show_task(struct task_struct *tsk) printf("%px %016lx %6d %6d %c %2d %s\n", tsk, tsk->thread.ksp, - tsk->pid, tsk->parent->pid, + tsk->pid, rcu_dereference(tsk->parent)->pid, state, task_thread_info(tsk)->cpu, tsk->comm); } #ifdef CONFIG_PPC_BOOK3S_64 -void format_pte(void *ptep, unsigned long pte) +static void format_pte(void *ptep, unsigned long pte) { pte_t entry = __pte(pte); @@ -3495,14 +3497,14 @@ void dump_segments(void) } #endif -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 void dump_segments(void) { int i; printf("sr0-15 ="); for (i = 0; i < 16; ++i) - printf(" %x", mfsrin(i)); + printf(" %x", mfsrin(i << 28)); printf("\n"); } #endif @@ -3688,6 +3690,14 @@ static void xmon_init(int enable) __debugger_iabr_match = xmon_iabr_match; __debugger_break_match = xmon_break_match; __debugger_fault_handler = xmon_fault_handler; + +#ifdef CONFIG_PPC_PSERIES + /* + * Get the token here to avoid trying to get a lock + * during the crash, causing a deadlock. + */ + set_indicator_token = rtas_token("set-indicator"); +#endif } else { __debugger = NULL; __debugger_ipi = NULL; @@ -4033,6 +4043,7 @@ static int do_spu_cmd(void) subcmd = inchar(); if (isxdigit(subcmd) || subcmd == '\n') termch = subcmd; + /* fall through */ case 'f': scanhex(&num); if (num >= XMON_NUM_SPUS || !spu_info[num].spu) { diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c @@ -128,7 +128,7 @@ static int cpu_750fx_cpu_speed(int low_speed) mtspr(SPRN_HID2, hid2); } } -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 low_choose_750fx_pll(low_speed); #endif if (low_speed == 1) { @@ -166,7 +166,7 @@ static int dfs_set_cpu_speed(int low_speed) } /* set frequency */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 low_choose_7447a_dfs(low_speed); #endif udelay(100); diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c @@ -247,7 +247,13 @@ static int pseries_idle_probe(void) return -ENODEV; if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - if (lppaca_shared_proc(get_lppaca())) { + /* + * Use local_paca instead of get_lppaca() since + * preemption is not disabled, and it is not required in + * fact, since lppaca_ptr does not need to be the value + * associated to the current CPU, it can be from any CPU. + */ + if (lppaca_shared_proc(local_paca->lppaca_ptr)) { cpuidle_state_table = shared_states; max_idle_state = ARRAY_SIZE(shared_states); } else { diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c @@ -596,7 +596,7 @@ static void crypto4xx_aead_done(struct crypto4xx_device *dev, pd->pd_ctl_len.bf.pkt_len, dst); } else { - __dma_sync_page(sg_page(dst), dst->offset, dst->length, + dma_unmap_page(dev->core_dev->device, pd->dest, dst->length, DMA_FROM_DEVICE); } diff --git a/drivers/ide/pmac.c b/drivers/ide/pmac.c @@ -1046,7 +1046,7 @@ static int pmac_ide_setup_device(pmac_ide_hwif_t *pmif, struct ide_hw *hw) d.port_ops = &pmac_ide_ata4_port_ops; d.udma_mask = ATA_UDMA5; } else if (of_device_is_compatible(np, "keylargo-ata")) { - if (strcmp(np->name, "ata-4") == 0) { + if (of_node_name_eq(np, "ata-4")) { pmif->kind = controller_kl_ata4; d.port_ops = &pmac_ide_ata4_port_ops; d.udma_mask = ATA_UDMA4; diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c @@ -160,7 +160,7 @@ anslcd_init(void) struct device_node* node; node = of_find_node_by_name(NULL, "lcd"); - if (!node || !node->parent || strcmp(node->parent->name, "gc")) { + if (!node || !of_node_name_eq(node->parent, "gc")) { of_node_put(node); return -ENODEV; } diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c @@ -190,11 +190,11 @@ static int macio_resource_quirks(struct device_node *np, struct resource *res, return 0; /* Grand Central has too large resource 0 on some machines */ - if (index == 0 && !strcmp(np->name, "gc")) + if (index == 0 && of_node_name_eq(np, "gc")) res->end = res->start + 0x1ffff; /* Airport has bogus resource 2 */ - if (index >= 2 && !strcmp(np->name, "radio")) + if (index >= 2 && of_node_name_eq(np, "radio")) return 1; #ifndef CONFIG_PPC64 @@ -207,21 +207,21 @@ static int macio_resource_quirks(struct device_node *np, struct resource *res, * level of hierarchy, but I don't really feel the need * for it */ - if (!strcmp(np->name, "escc")) + if (of_node_name_eq(np, "escc")) return 1; /* ESCC has bogus resources >= 3 */ - if (index >= 3 && !(strcmp(np->name, "ch-a") && - strcmp(np->name, "ch-b"))) + if (index >= 3 && (of_node_name_eq(np, "ch-a") || + of_node_name_eq(np, "ch-b"))) return 1; /* Media bay has too many resources, keep only first one */ - if (index > 0 && !strcmp(np->name, "media-bay")) + if (index > 0 && of_node_name_eq(np, "media-bay")) return 1; /* Some older IDE resources have bogus sizes */ - if (!(strcmp(np->name, "IDE") && strcmp(np->name, "ATA") && - strcmp(np->type, "ide") && strcmp(np->type, "ata"))) { + if (of_node_name_eq(np, "IDE") || of_node_name_eq(np, "ATA") || + of_node_is_type(np, "ide") || of_node_is_type(np, "ata")) { if (index == 0 && (res->end - res->start) > 0xfff) res->end = res->start + 0xfff; if (index == 1 && (res->end - res->start) > 0xff) @@ -260,7 +260,7 @@ static void macio_add_missing_resources(struct macio_dev *dev) irq_base = 64; /* Fix SCC */ - if (strcmp(np->name, "ch-a") == 0) { + if (of_node_name_eq(np, "ch-a")) { macio_create_fixup_irq(dev, 0, 15 + irq_base); macio_create_fixup_irq(dev, 1, 4 + irq_base); macio_create_fixup_irq(dev, 2, 5 + irq_base); @@ -268,18 +268,18 @@ static void macio_add_missing_resources(struct macio_dev *dev) } /* Fix media-bay */ - if (strcmp(np->name, "media-bay") == 0) { + if (of_node_name_eq(np, "media-bay")) { macio_create_fixup_irq(dev, 0, 29 + irq_base); printk(KERN_INFO "macio: fixed media-bay irq on gatwick\n"); } /* Fix left media bay childs */ - if (dev->media_bay != NULL && strcmp(np->name, "floppy") == 0) { + if (dev->media_bay != NULL && of_node_name_eq(np, "floppy")) { macio_create_fixup_irq(dev, 0, 19 + irq_base); macio_create_fixup_irq(dev, 1, 1 + irq_base); printk(KERN_INFO "macio: fixed left floppy irqs\n"); } - if (dev->media_bay != NULL && strcasecmp(np->name, "ata4") == 0) { + if (dev->media_bay != NULL && of_node_name_eq(np, "ata4")) { macio_create_fixup_irq(dev, 0, 14 + irq_base); macio_create_fixup_irq(dev, 0, 3 + irq_base); printk(KERN_INFO "macio: fixed left ide irqs\n"); @@ -438,11 +438,8 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, static int macio_skip_device(struct device_node *np) { - if (strncmp(np->name, "battery", 7) == 0) - return 1; - if (strncmp(np->name, "escc-legacy", 11) == 0) - return 1; - return 0; + return of_node_name_prefix(np, "battery") || + of_node_name_prefix(np, "escc-legacy"); } /** @@ -489,9 +486,9 @@ static void macio_pci_add_devices(struct macio_chip *chip) root_res); if (mdev == NULL) of_node_put(np); - else if (strncmp(np->name, "media-bay", 9) == 0) + else if (of_node_name_prefix(np, "media-bay")) mbdev = mdev; - else if (strncmp(np->name, "escc", 4) == 0) + else if (of_node_name_prefix(np, "escc")) sdev = mdev; } diff --git a/drivers/macintosh/macio_sysfs.c b/drivers/macintosh/macio_sysfs.c @@ -3,17 +3,6 @@ #include <linux/stat.h> #include <asm/macio.h> - -#define macio_config_of_attr(field, format_string) \ -static ssize_t \ -field##_show (struct device *dev, struct device_attribute *attr, \ - char *buf) \ -{ \ - struct macio_dev *mdev = to_macio_device (dev); \ - return sprintf (buf, format_string, mdev->ofdev.dev.of_node->field); \ -} \ -static DEVICE_ATTR_RO(field); - static ssize_t compatible_show (struct device *dev, struct device_attribute *attr, char *buf) { @@ -65,7 +54,12 @@ static ssize_t name_show(struct device *dev, } static DEVICE_ATTR_RO(name); -macio_config_of_attr (type, "%s\n"); +static ssize_t type_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%s\n", of_node_get_device_type(dev->of_node)); +} +static DEVICE_ATTR_RO(type); static struct attribute *macio_dev_attrs[] = { &dev_attr_name.attr, diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c @@ -376,18 +376,19 @@ static int rackmeter_probe(struct macio_dev* mdev, pr_debug("rackmeter_probe()\n"); /* Get i2s-a node */ - while ((i2s = of_get_next_child(mdev->ofdev.dev.of_node, i2s)) != NULL) - if (strcmp(i2s->name, "i2s-a") == 0) - break; + for_each_child_of_node(mdev->ofdev.dev.of_node, i2s) + if (of_node_name_eq(i2s, "i2s-a")) + break; + if (i2s == NULL) { pr_debug(" i2s-a child not found\n"); goto bail; } /* Get lightshow or virtual sound */ - while ((np = of_get_next_child(i2s, np)) != NULL) { - if (strcmp(np->name, "lightshow") == 0) + for_each_child_of_node(i2s, np) { + if (of_node_name_eq(np, "lightshow")) break; - if ((strcmp(np->name, "sound") == 0) && + if (of_node_name_eq(np, "sound") && of_get_property(np, "virtual", NULL) != NULL) break; } diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c @@ -318,8 +318,8 @@ int __init find_via_pmu(void) PMU_INT_ADB | PMU_INT_TICK; - if (vias->parent->name && ((strcmp(vias->parent->name, "ohare") == 0) - || of_device_is_compatible(vias->parent, "ohare"))) + if (of_node_name_eq(vias->parent, "ohare") || + of_device_is_compatible(vias->parent, "ohare")) pmu_kind = PMU_OHARE_BASED; else if (of_device_is_compatible(vias->parent, "paddington")) pmu_kind = PMU_PADDINGTON_BASED; diff --git a/drivers/macintosh/windfarm_fcu_controls.c b/drivers/macintosh/windfarm_fcu_controls.c @@ -425,25 +425,25 @@ static void wf_fcu_lookup_fans(struct wf_fcu_priv *pv) { "CPU B 2", "cpu-fan-b-1", }, { "CPU B 3", "cpu-fan-c-1", }, }; - struct device_node *np = NULL, *fcu = pv->i2c->dev.of_node; + struct device_node *np, *fcu = pv->i2c->dev.of_node; int i; DBG("Looking up FCU controls in device-tree...\n"); - while ((np = of_get_next_child(fcu, np)) != NULL) { + for_each_child_of_node(fcu, np) { int id, type = -1; const char *loc; const char *name; const u32 *reg; - DBG(" control: %s, type: %s\n", np->name, np->type); + DBG(" control: %pOFn, type: %s\n", np, of_node_get_device_type(np)); /* Detect control type */ - if (!strcmp(np->type, "fan-rpm-control") || - !strcmp(np->type, "fan-rpm")) + if (of_node_is_type(np, "fan-rpm-control") || + of_node_is_type(np, "fan-rpm")) type = FCU_FAN_RPM; - if (!strcmp(np->type, "fan-pwm-control") || - !strcmp(np->type, "fan-pwm")) + if (of_node_is_type(np, "fan-pwm-control") || + of_node_is_type(np, "fan-pwm")) type = FCU_FAN_PWM; /* Only care about fans for now */ if (type == -1) diff --git a/drivers/macintosh/windfarm_lm87_sensor.c b/drivers/macintosh/windfarm_lm87_sensor.c @@ -110,8 +110,8 @@ static int wf_lm87_probe(struct i2c_client *client, * the Xserve G5 has several lm87's. However, for now we only * care about the internal temperature sensor */ - while ((np = of_get_next_child(client->dev.of_node, np)) != NULL) { - if (strcmp(np->name, "int-temp")) + for_each_child_of_node(client->dev.of_node, np) { + if (!of_node_name_eq(np, "int-temp")) continue; loc = of_get_property(np, "location", NULL); if (!loc) diff --git a/drivers/macintosh/windfarm_smu_controls.c b/drivers/macintosh/windfarm_smu_controls.c @@ -267,7 +267,7 @@ static int __init smu_controls_init(void) /* Look for RPM fans */ for (fans = NULL; (fans = of_get_next_child(smu, fans)) != NULL;) - if (!strcmp(fans->name, "rpm-fans") || + if (of_node_name_eq(fans, "rpm-fans") || of_device_is_compatible(fans, "smu-rpm-fans")) break; for (fan = NULL; @@ -287,7 +287,7 @@ static int __init smu_controls_init(void) /* Look for PWM fans */ for (fans = NULL; (fans = of_get_next_child(smu, fans)) != NULL;) - if (!strcmp(fans->name, "pwm-fans")) + if (of_node_name_eq(fans, "pwm-fans")) break; for (fan = NULL; fans && (fan = of_get_next_child(fans, fan)) != NULL;) { diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c @@ -197,7 +197,7 @@ static int wf_sat_probe(struct i2c_client *client, struct wf_sat *sat; struct wf_sat_sensor *sens; const u32 *reg; - const char *loc, *type; + const char *loc; u8 chip, core; struct device_node *child; int shift, cpu, index; @@ -220,7 +220,6 @@ static int wf_sat_probe(struct i2c_client *client, child = NULL; while ((child = of_get_next_child(dev, child)) != NULL) { reg = of_get_property(child, "reg", NULL); - type = of_get_property(child, "device_type", NULL); loc = of_get_property(child, "location", NULL); if (reg == NULL || loc == NULL) continue; @@ -249,15 +248,15 @@ static int wf_sat_probe(struct i2c_client *client, continue; } - if (strcmp(type, "voltage-sensor") == 0) { + if (of_node_is_type(child, "voltage-sensor")) { name = "cpu-voltage"; shift = 4; vsens[core] = index; - } else if (strcmp(type, "current-sensor") == 0) { + } else if (of_node_is_type(child, "current-sensor")) { name = "cpu-current"; shift = 8; isens[core] = index; - } else if (strcmp(type, "temp-sensor") == 0) { + } else if (of_node_is_type(child, "temp-sensor")) { name = "cpu-temp"; shift = 10; } else diff --git a/drivers/macintosh/windfarm_smu_sensors.c b/drivers/macintosh/windfarm_smu_sensors.c @@ -197,15 +197,14 @@ static const struct wf_sensor_ops smu_slotspow_ops = { static struct smu_ad_sensor *smu_ads_create(struct device_node *node) { struct smu_ad_sensor *ads; - const char *c, *l; + const char *l; const u32 *v; ads = kmalloc(sizeof(struct smu_ad_sensor), GFP_KERNEL); if (ads == NULL) return NULL; - c = of_get_property(node, "device_type", NULL); l = of_get_property(node, "location", NULL); - if (c == NULL || l == NULL) + if (l == NULL) goto fail; /* We currently pick the sensors based on the OF name and location @@ -215,7 +214,7 @@ static struct smu_ad_sensor *smu_ads_create(struct device_node *node) * the names and locations consistents so I'll stick with the names * and locations for now. */ - if (!strcmp(c, "temp-sensor") && + if (of_node_is_type(node, "temp-sensor") && !strcmp(l, "CPU T-Diode")) { ads->sens.ops = &smu_cputemp_ops; ads->sens.name = "cpu-temp"; @@ -224,7 +223,7 @@ static struct smu_ad_sensor *smu_ads_create(struct device_node *node) SMU_SDB_CPUDIODE_ID); goto fail; } - } else if (!strcmp(c, "current-sensor") && + } else if (of_node_is_type(node, "current-sensor") && !strcmp(l, "CPU Current")) { ads->sens.ops = &smu_cpuamp_ops; ads->sens.name = "cpu-current"; @@ -233,7 +232,7 @@ static struct smu_ad_sensor *smu_ads_create(struct device_node *node) SMU_SDB_CPUVCP_ID); goto fail; } - } else if (!strcmp(c, "voltage-sensor") && + } else if (of_node_is_type(node, "voltage-sensor") && !strcmp(l, "CPU Voltage")) { ads->sens.ops = &smu_cpuvolt_ops; ads->sens.name = "cpu-voltage"; @@ -242,7 +241,7 @@ static struct smu_ad_sensor *smu_ads_create(struct device_node *node) SMU_SDB_CPUVCP_ID); goto fail; } - } else if (!strcmp(c, "power-sensor") && + } else if (of_node_is_type(node, "power-sensor") && !strcmp(l, "Slots Power")) { ads->sens.ops = &smu_slotspow_ops; ads->sens.name = "slots-power"; @@ -425,7 +424,7 @@ static int __init smu_sensors_init(void) /* Look for sensors subdir */ for (sensors = NULL; (sensors = of_get_next_child(smu, sensors)) != NULL;) - if (!strcmp(sensors->name, "sensors")) + if (of_node_name_eq(sensors, "sensors")) break; of_node_put(smu); diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c @@ -1718,7 +1718,6 @@ int cxl_slot_is_switched(struct pci_dev *dev) { struct device_node *np; int depth = 0; - const __be32 *prop; if (!(np = pci_device_to_OF_node(dev))) { pr_err("cxl: np = NULL\n"); @@ -1727,8 +1726,7 @@ int cxl_slot_is_switched(struct pci_dev *dev) of_node_get(np); while (np) { np = of_get_next_parent(np); - prop = of_get_property(np, "device_type", NULL); - if (!prop || strcmp((char *)prop, "pciex")) + if (!of_node_is_type(np, "pciex")) break; depth++; } diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c @@ -11,17 +11,6 @@ #include <misc/cxl.h> #include "cxl.h" -static int cxl_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) -{ - if (dma_mask < DMA_BIT_MASK(64)) { - pr_info("%s only 64bit DMA supported on CXL", __func__); - return -EIO; - } - - *(pdev->dev.dma_mask) = dma_mask; - return 0; -} - static int cxl_pci_probe_mode(struct pci_bus *bus) { return PCI_PROBE_NORMAL; @@ -220,7 +209,6 @@ static struct pci_controller_ops cxl_pci_controller_ops = .reset_secondary_bus = cxl_pci_reset_secondary_bus, .setup_msi_irqs = cxl_setup_msi_irqs, .teardown_msi_irqs = cxl_teardown_msi_irqs, - .dma_set_mask = cxl_dma_set_mask, }; int cxl_pci_vphb_add(struct cxl_afu *afu) diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c @@ -2,7 +2,6 @@ // Copyright 2017 IBM Corp. #include <linux/interrupt.h> #include <linux/eventfd.h> -#include <asm/pnv-ocxl.h> #include "ocxl_internal.h" #include "trace.h" diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c @@ -318,7 +318,7 @@ static int read_afu_name(struct pci_dev *dev, struct ocxl_fn_config *fn, if (rc) return rc; ptr = (u32 *) &afu->name[i]; - *ptr = val; + *ptr = le32_to_cpu((__force __le32) val); } afu->name[OCXL_AFU_NAME_SZ - 1] = '\0'; /* play safe */ return 0; diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c @@ -273,9 +273,9 @@ static int setup_xsl_irq(struct pci_dev *dev, struct link *link) spa->irq_name = kasprintf(GFP_KERNEL, "ocxl-xsl-%x-%x-%x", link->domain, link->bus, link->dev); if (!spa->irq_name) { - unmap_irq_registers(spa); dev_err(&dev->dev, "Can't allocate name for xsl interrupt\n"); - return -ENOMEM; + rc = -ENOMEM; + goto err_xsl; } /* * At some point, we'll need to look into allowing a higher @@ -283,11 +283,10 @@ static int setup_xsl_irq(struct pci_dev *dev, struct link *link) */ spa->virq = irq_create_mapping(NULL, hwirq); if (!spa->virq) { - kfree(spa->irq_name); - unmap_irq_registers(spa); dev_err(&dev->dev, "irq_create_mapping failed for translation interrupt\n"); - return -EINVAL; + rc = -EINVAL; + goto err_name; } dev_dbg(&dev->dev, "hwirq %d mapped to virq %d\n", hwirq, spa->virq); @@ -295,15 +294,21 @@ static int setup_xsl_irq(struct pci_dev *dev, struct link *link) rc = request_irq(spa->virq, xsl_fault_handler, 0, spa->irq_name, link); if (rc) { - irq_dispose_mapping(spa->virq); - kfree(spa->irq_name); - unmap_irq_registers(spa); dev_err(&dev->dev, "request_irq failed for translation interrupt: %d\n", rc); - return -EINVAL; + rc = -EINVAL; + goto err_mapping; } return 0; + +err_mapping: + irq_dispose_mapping(spa->virq); +err_name: + kfree(spa->irq_name); +err_xsl: + unmap_irq_registers(spa); + return rc; } static void release_xsl_irq(struct link *link) @@ -566,7 +571,7 @@ int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid) mutex_lock(&spa->spa_lock); - pe->tid = tid; + pe->tid = cpu_to_be32(tid); /* * The barrier makes sure the PE is updated diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig @@ -38,3 +38,9 @@ config VFIO_PCI_IGD and LPC bridge config space. To enable Intel IGD assignment through vfio-pci, say Y. + +config VFIO_PCI_NVLINK2 + def_bool y + depends on VFIO_PCI && PPC_POWERNV + help + VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile @@ -1,5 +1,6 @@ vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o +vfio-pci-$(CONFIG_VFIO_PCI_NVLINK2) += vfio_pci_nvlink2.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o diff --git a/drivers/vfio/pci/trace.h b/drivers/vfio/pci/trace.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * VFIO PCI mmap/mmap_fault tracepoints + * + * Copyright (C) 2018 IBM Corp. All rights reserved. + * Author: Alexey Kardashevskiy <aik@ozlabs.ru> + * + * 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. + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vfio_pci + +#if !defined(_TRACE_VFIO_PCI_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_VFIO_PCI_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(vfio_pci_nvgpu_mmap_fault, + TP_PROTO(struct pci_dev *pdev, unsigned long hpa, unsigned long ua, + vm_fault_t ret), + TP_ARGS(pdev, hpa, ua, ret), + + TP_STRUCT__entry( + __field(const char *, name) + __field(unsigned long, hpa) + __field(unsigned long, ua) + __field(int, ret) + ), + + TP_fast_assign( + __entry->name = dev_name(&pdev->dev), + __entry->hpa = hpa; + __entry->ua = ua; + __entry->ret = ret; + ), + + TP_printk("%s: %lx -> %lx ret=%d", __entry->name, __entry->hpa, + __entry->ua, __entry->ret) +); + +TRACE_EVENT(vfio_pci_nvgpu_mmap, + TP_PROTO(struct pci_dev *pdev, unsigned long hpa, unsigned long ua, + unsigned long size, int ret), + TP_ARGS(pdev, hpa, ua, size, ret), + + TP_STRUCT__entry( + __field(const char *, name) + __field(unsigned long, hpa) + __field(unsigned long, ua) + __field(unsigned long, size) + __field(int, ret) + ), + + TP_fast_assign( + __entry->name = dev_name(&pdev->dev), + __entry->hpa = hpa; + __entry->ua = ua; + __entry->size = size; + __entry->ret = ret; + ), + + TP_printk("%s: %lx -> %lx size=%lx ret=%d", __entry->name, __entry->hpa, + __entry->ua, __entry->size, __entry->ret) +); + +TRACE_EVENT(vfio_pci_npu2_mmap, + TP_PROTO(struct pci_dev *pdev, unsigned long hpa, unsigned long ua, + unsigned long size, int ret), + TP_ARGS(pdev, hpa, ua, size, ret), + + TP_STRUCT__entry( + __field(const char *, name) + __field(unsigned long, hpa) + __field(unsigned long, ua) + __field(unsigned long, size) + __field(int, ret) + ), + + TP_fast_assign( + __entry->name = dev_name(&pdev->dev), + __entry->hpa = hpa; + __entry->ua = ua; + __entry->size = size; + __entry->ret = ret; + ), + + TP_printk("%s: %lx -> %lx size=%lx ret=%d", __entry->name, __entry->hpa, + __entry->ua, __entry->size, __entry->ret) +); + +#endif /* _TRACE_VFIO_PCI_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c @@ -289,14 +289,37 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev) if (ret) { dev_warn(&vdev->pdev->dev, "Failed to setup Intel IGD regions\n"); - vfio_pci_disable(vdev); - return ret; + goto disable_exit; + } + } + + if (pdev->vendor == PCI_VENDOR_ID_NVIDIA && + IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) { + ret = vfio_pci_nvdia_v100_nvlink2_init(vdev); + if (ret && ret != -ENODEV) { + dev_warn(&vdev->pdev->dev, + "Failed to setup NVIDIA NV2 RAM region\n"); + goto disable_exit; + } + } + + if (pdev->vendor == PCI_VENDOR_ID_IBM && + IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) { + ret = vfio_pci_ibm_npu2_init(vdev); + if (ret && ret != -ENODEV) { + dev_warn(&vdev->pdev->dev, + "Failed to setup NVIDIA NV2 ATSD region\n"); + goto disable_exit; } } vfio_pci_probe_mmaps(vdev); return 0; + +disable_exit: + vfio_pci_disable(vdev); + return ret; } static void vfio_pci_disable(struct vfio_pci_device *vdev) @@ -750,6 +773,12 @@ static long vfio_pci_ioctl(void *device_data, if (ret) return ret; + if (vdev->region[i].ops->add_capability) { + ret = vdev->region[i].ops->add_capability(vdev, + &vdev->region[i], &caps); + if (ret) + return ret; + } } } @@ -1117,6 +1146,15 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) return -EINVAL; if ((vma->vm_flags & VM_SHARED) == 0) return -EINVAL; + if (index >= VFIO_PCI_NUM_REGIONS) { + int regnum = index - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_region *region = vdev->region + regnum; + + if (region && region->ops && region->ops->mmap && + (region->flags & VFIO_REGION_INFO_FLAG_MMAP)) + return region->ops->mmap(vdev, region, vma); + return -EINVAL; + } if (index >= VFIO_PCI_ROM_REGION_INDEX) return -EINVAL; if (!vdev->bar_mmap_supported[index]) diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c @@ -0,0 +1,482 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * VFIO PCI NVIDIA Whitherspoon GPU support a.k.a. NVLink2. + * + * Copyright (C) 2018 IBM Corp. All rights reserved. + * Author: Alexey Kardashevskiy <aik@ozlabs.ru> + * + * 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. + * + * Register an on-GPU RAM region for cacheable access. + * + * Derived from original vfio_pci_igd.c: + * Copyright (C) 2016 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson <alex.williamson@redhat.com> + */ + +#include <linux/io.h> +#include <linux/pci.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> +#include <linux/sched/mm.h> +#include <linux/mmu_context.h> +#include <asm/kvm_ppc.h> +#include "vfio_pci_private.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" + +EXPORT_TRACEPOINT_SYMBOL_GPL(vfio_pci_nvgpu_mmap_fault); +EXPORT_TRACEPOINT_SYMBOL_GPL(vfio_pci_nvgpu_mmap); +EXPORT_TRACEPOINT_SYMBOL_GPL(vfio_pci_npu2_mmap); + +struct vfio_pci_nvgpu_data { + unsigned long gpu_hpa; /* GPU RAM physical address */ + unsigned long gpu_tgt; /* TGT address of corresponding GPU RAM */ + unsigned long useraddr; /* GPU RAM userspace address */ + unsigned long size; /* Size of the GPU RAM window (usually 128GB) */ + struct mm_struct *mm; + struct mm_iommu_table_group_mem_t *mem; /* Pre-registered RAM descr. */ + struct pci_dev *gpdev; + struct notifier_block group_notifier; +}; + +static size_t vfio_pci_nvgpu_rw(struct vfio_pci_device *vdev, + char __user *buf, size_t count, loff_t *ppos, bool iswrite) +{ + unsigned int i = VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_nvgpu_data *data = vdev->region[i].data; + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + loff_t posaligned = pos & PAGE_MASK, posoff = pos & ~PAGE_MASK; + size_t sizealigned; + void __iomem *ptr; + + if (pos >= vdev->region[i].size) + return -EINVAL; + + count = min(count, (size_t)(vdev->region[i].size - pos)); + + /* + * We map only a bit of GPU RAM for a short time instead of mapping it + * for the guest lifetime as: + * + * 1) we do not know GPU RAM size, only aperture which is 4-8 times + * bigger than actual RAM size (16/32GB RAM vs. 128GB aperture); + * 2) mapping GPU RAM allows CPU to prefetch and if this happens + * before NVLink bridge is reset (which fences GPU RAM), + * hardware management interrupts (HMI) might happen, this + * will freeze NVLink bridge. + * + * This is not fast path anyway. + */ + sizealigned = _ALIGN_UP(posoff + count, PAGE_SIZE); + ptr = ioremap_cache(data->gpu_hpa + posaligned, sizealigned); + if (!ptr) + return -EFAULT; + + if (iswrite) { + if (copy_from_user(ptr + posoff, buf, count)) + count = -EFAULT; + else + *ppos += count; + } else { + if (copy_to_user(buf, ptr + posoff, count)) + count = -EFAULT; + else + *ppos += count; + } + + iounmap(ptr); + + return count; +} + +static void vfio_pci_nvgpu_release(struct vfio_pci_device *vdev, + struct vfio_pci_region *region) +{ + struct vfio_pci_nvgpu_data *data = region->data; + long ret; + + /* If there were any mappings at all... */ + if (data->mm) { + ret = mm_iommu_put(data->mm, data->mem); + WARN_ON(ret); + + mmdrop(data->mm); + } + + vfio_unregister_notifier(&data->gpdev->dev, VFIO_GROUP_NOTIFY, + &data->group_notifier); + + pnv_npu2_unmap_lpar_dev(data->gpdev); + + kfree(data); +} + +static vm_fault_t vfio_pci_nvgpu_mmap_fault(struct vm_fault *vmf) +{ + vm_fault_t ret; + struct vm_area_struct *vma = vmf->vma; + struct vfio_pci_region *region = vma->vm_private_data; + struct vfio_pci_nvgpu_data *data = region->data; + unsigned long vmf_off = (vmf->address - vma->vm_start) >> PAGE_SHIFT; + unsigned long nv2pg = data->gpu_hpa >> PAGE_SHIFT; + unsigned long vm_pgoff = vma->vm_pgoff & + ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); + unsigned long pfn = nv2pg + vm_pgoff + vmf_off; + + ret = vmf_insert_pfn(vma, vmf->address, pfn); + trace_vfio_pci_nvgpu_mmap_fault(data->gpdev, pfn << PAGE_SHIFT, + vmf->address, ret); + + return ret; +} + +static const struct vm_operations_struct vfio_pci_nvgpu_mmap_vmops = { + .fault = vfio_pci_nvgpu_mmap_fault, +}; + +static int vfio_pci_nvgpu_mmap(struct vfio_pci_device *vdev, + struct vfio_pci_region *region, struct vm_area_struct *vma) +{ + int ret; + struct vfio_pci_nvgpu_data *data = region->data; + + if (data->useraddr) + return -EPERM; + + if (vma->vm_end - vma->vm_start > data->size) + return -EINVAL; + + vma->vm_private_data = region; + vma->vm_flags |= VM_PFNMAP; + vma->vm_ops = &vfio_pci_nvgpu_mmap_vmops; + + /* + * Calling mm_iommu_newdev() here once as the region is not + * registered yet and therefore right initialization will happen now. + * Other places will use mm_iommu_find() which returns + * registered @mem and does not go gup(). + */ + data->useraddr = vma->vm_start; + data->mm = current->mm; + + atomic_inc(&data->mm->mm_count); + ret = (int) mm_iommu_newdev(data->mm, data->useraddr, + (vma->vm_end - vma->vm_start) >> PAGE_SHIFT, + data->gpu_hpa, &data->mem); + + trace_vfio_pci_nvgpu_mmap(vdev->pdev, data->gpu_hpa, data->useraddr, + vma->vm_end - vma->vm_start, ret); + + return ret; +} + +static int vfio_pci_nvgpu_add_capability(struct vfio_pci_device *vdev, + struct vfio_pci_region *region, struct vfio_info_cap *caps) +{ + struct vfio_pci_nvgpu_data *data = region->data; + struct vfio_region_info_cap_nvlink2_ssatgt cap = { 0 }; + + cap.header.id = VFIO_REGION_INFO_CAP_NVLINK2_SSATGT; + cap.header.version = 1; + cap.tgt = data->gpu_tgt; + + return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); +} + +static const struct vfio_pci_regops vfio_pci_nvgpu_regops = { + .rw = vfio_pci_nvgpu_rw, + .release = vfio_pci_nvgpu_release, + .mmap = vfio_pci_nvgpu_mmap, + .add_capability = vfio_pci_nvgpu_add_capability, +}; + +static int vfio_pci_nvgpu_group_notifier(struct notifier_block *nb, + unsigned long action, void *opaque) +{ + struct kvm *kvm = opaque; + struct vfio_pci_nvgpu_data *data = container_of(nb, + struct vfio_pci_nvgpu_data, + group_notifier); + + if (action == VFIO_GROUP_NOTIFY_SET_KVM && kvm && + pnv_npu2_map_lpar_dev(data->gpdev, + kvm->arch.lpid, MSR_DR | MSR_PR)) + return NOTIFY_BAD; + + return NOTIFY_OK; +} + +int vfio_pci_nvdia_v100_nvlink2_init(struct vfio_pci_device *vdev) +{ + int ret; + u64 reg[2]; + u64 tgt = 0; + struct device_node *npu_node, *mem_node; + struct pci_dev *npu_dev; + struct vfio_pci_nvgpu_data *data; + uint32_t mem_phandle = 0; + unsigned long events = VFIO_GROUP_NOTIFY_SET_KVM; + + /* + * PCI config space does not tell us about NVLink presense but + * platform does, use this. + */ + npu_dev = pnv_pci_get_npu_dev(vdev->pdev, 0); + if (!npu_dev) + return -ENODEV; + + npu_node = pci_device_to_OF_node(npu_dev); + if (!npu_node) + return -EINVAL; + + if (of_property_read_u32(npu_node, "memory-region", &mem_phandle)) + return -EINVAL; + + mem_node = of_find_node_by_phandle(mem_phandle); + if (!mem_node) + return -EINVAL; + + if (of_property_read_variable_u64_array(mem_node, "reg", reg, + ARRAY_SIZE(reg), ARRAY_SIZE(reg)) != + ARRAY_SIZE(reg)) + return -EINVAL; + + if (of_property_read_u64(npu_node, "ibm,device-tgt-addr", &tgt)) { + dev_warn(&vdev->pdev->dev, "No ibm,device-tgt-addr found\n"); + return -EFAULT; + } + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->gpu_hpa = reg[0]; + data->gpu_tgt = tgt; + data->size = reg[1]; + + dev_dbg(&vdev->pdev->dev, "%lx..%lx\n", data->gpu_hpa, + data->gpu_hpa + data->size - 1); + + data->gpdev = vdev->pdev; + data->group_notifier.notifier_call = vfio_pci_nvgpu_group_notifier; + + ret = vfio_register_notifier(&data->gpdev->dev, VFIO_GROUP_NOTIFY, + &events, &data->group_notifier); + if (ret) + goto free_exit; + + /* + * We have just set KVM, we do not need the listener anymore. + * Also, keeping it registered means that if more than one GPU is + * assigned, we will get several similar notifiers notifying about + * the same device again which does not help with anything. + */ + vfio_unregister_notifier(&data->gpdev->dev, VFIO_GROUP_NOTIFY, + &data->group_notifier); + + ret = vfio_pci_register_dev_region(vdev, + PCI_VENDOR_ID_NVIDIA | VFIO_REGION_TYPE_PCI_VENDOR_TYPE, + VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM, + &vfio_pci_nvgpu_regops, + data->size, + VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE | + VFIO_REGION_INFO_FLAG_MMAP, + data); + if (ret) + goto free_exit; + + return 0; +free_exit: + kfree(data); + + return ret; +} + +/* + * IBM NPU2 bridge + */ +struct vfio_pci_npu2_data { + void *base; /* ATSD register virtual address, for emulated access */ + unsigned long mmio_atsd; /* ATSD physical address */ + unsigned long gpu_tgt; /* TGT address of corresponding GPU RAM */ + unsigned int link_speed; /* The link speed from DT's ibm,nvlink-speed */ +}; + +static size_t vfio_pci_npu2_rw(struct vfio_pci_device *vdev, + char __user *buf, size_t count, loff_t *ppos, bool iswrite) +{ + unsigned int i = VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_npu2_data *data = vdev->region[i].data; + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + + if (pos >= vdev->region[i].size) + return -EINVAL; + + count = min(count, (size_t)(vdev->region[i].size - pos)); + + if (iswrite) { + if (copy_from_user(data->base + pos, buf, count))