diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-10-26 14:36:21 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-10-26 14:36:21 -0700 |
| commit | 685f7e4f161425b137056abe35ba8ef7b669d83d (patch) | |
| tree | 550dd1f5dc9e852cfeec26bf5e3ce9dd060c8a33 /arch/powerpc/platforms | |
| parent | c7a2c49ea6c9eebbe44ff2c08b663b2905ee2c13 (diff) | |
| parent | 58cfbac25b1fd2b76f94566aed28a3662b0ff8c6 (diff) | |
| download | blackbird-op-linux-685f7e4f161425b137056abe35ba8ef7b669d83d.tar.gz blackbird-op-linux-685f7e4f161425b137056abe35ba8ef7b669d83d.zip | |
Merge tag 'powerpc-4.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Notable changes:
- A large series to rewrite our SLB miss handling, replacing a lot of
fairly complicated asm with much fewer lines of C.
- Following on from that, we now maintain a cache of SLB entries for
each process and preload them on context switch. Leading to a 27%
speedup for our context switch benchmark on Power9.
- Improvements to our handling of SLB multi-hit errors. We now print
more debug information when they occur, and try to continue running
by flushing the SLB and reloading, rather than treating them as
fatal.
- Enable THP migration on 64-bit Book3S machines (eg. Power7/8/9).
- Add support for physical memory up to 2PB in the linear mapping on
64-bit Book3S. We only support up to 512TB as regular system
memory, otherwise the percpu allocator runs out of vmalloc space.
- Add stack protector support for 32 and 64-bit, with a per-task
canary.
- Add support for PTRACE_SYSEMU and PTRACE_SYSEMU_SINGLESTEP.
- Support recognising "big cores" on Power9, where two SMT4 cores are
presented to us as a single SMT8 core.
- A large series to cleanup some of our ioremap handling and PTE
flags.
- Add a driver for the PAPR SCM (storage class memory) interface,
allowing guests to operate on SCM devices (acked by Dan).
- Changes to our ftrace code to handle very large kernels, where we
need to use a trampoline to get to ftrace_caller().
And many other smaller enhancements and cleanups.
Thanks to: Alan Modra, Alistair Popple, Aneesh Kumar K.V, Anton
Blanchard, Aravinda Prasad, Bartlomiej Zolnierkiewicz, Benjamin
Herrenschmidt, Breno Leitao, Cédric Le Goater, Christophe Leroy,
Christophe Lombard, Dan Carpenter, Daniel Axtens, Finn Thain, Gautham
R. Shenoy, Gustavo Romero, Haren Myneni, Hari Bathini, Jia Hongtao,
Joel Stanley, John Allen, Laurent Dufour, Madhavan Srinivasan, Mahesh
Salgaonkar, Mark Hairgrove, Masahiro Yamada, Michael Bringmann,
Michael Neuling, Michal Suchanek, Murilo Opsfelder Araujo, Nathan
Fontenot, Naveen N. Rao, Nicholas Piggin, Nick Desaulniers, Oliver
O'Halloran, Paul Mackerras, Petr Vorel, Rashmica Gupta, Reza Arbab,
Rob Herring, Sam Bobroff, Samuel Mendoza-Jonas, Scott Wood, Stan
Johnson, Stephen Rothwell, Stewart Smith, Suraj Jitindar Singh, Tyrel
Datwyler, Vaibhav Jain, Vasant Hegde, YueHaibing, zhong jiang"
* tag 'powerpc-4.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (221 commits)
Revert "selftests/powerpc: Fix out-of-tree build errors"
powerpc/msi: Fix compile error on mpc83xx
powerpc: Fix stack protector crashes on CPU hotplug
powerpc/traps: restore recoverability of machine_check interrupts
powerpc/64/module: REL32 relocation range check
powerpc/64s/radix: Fix radix__flush_tlb_collapsed_pmd double flushing pmd
selftests/powerpc: Add a test of wild bctr
powerpc/mm: Fix page table dump to work on Radix
powerpc/mm/radix: Display if mappings are exec or not
powerpc/mm/radix: Simplify split mapping logic
powerpc/mm/radix: Remove the retry in the split mapping logic
powerpc/mm/radix: Fix small page at boundary when splitting
powerpc/mm/radix: Fix overuse of small pages in splitting logic
powerpc/mm/radix: Fix off-by-one in split mapping logic
powerpc/ftrace: Handle large kernel configs
powerpc/mm: Fix WARN_ON with THP NUMA migration
selftests/powerpc: Fix out-of-tree build errors
powerpc/time: no steal_time when CONFIG_PPC_SPLPAR is not selected
powerpc/time: Only set CONFIG_ARCH_HAS_SCALED_CPUTIME on PPC64
powerpc/time: isolate scaled cputime accounting in dedicated functions.
...
Diffstat (limited to 'arch/powerpc/platforms')
51 files changed, 1453 insertions, 652 deletions
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig index 60254a321a91..2a9d66254ffc 100644 --- a/arch/powerpc/platforms/40x/Kconfig +++ b/arch/powerpc/platforms/40x/Kconfig @@ -2,7 +2,6 @@ config ACADIA bool "Acadia" depends on 40x - default n select PPC40x_SIMPLE select 405EZ help @@ -11,7 +10,6 @@ config ACADIA config EP405 bool "EP405/EP405PC" depends on 40x - default n select 405GP select PCI help @@ -20,7 +18,6 @@ config EP405 config HOTFOOT bool "Hotfoot" depends on 40x - default n select PPC40x_SIMPLE select PCI help @@ -29,7 +26,6 @@ config HOTFOOT config KILAUEA bool "Kilauea" depends on 40x - default n select 405EX select PPC40x_SIMPLE select PPC4xx_PCI_EXPRESS @@ -41,7 +37,6 @@ config KILAUEA config MAKALU bool "Makalu" depends on 40x - default n select 405EX select PCI select PPC4xx_PCI_EXPRESS @@ -62,7 +57,6 @@ config WALNUT config XILINX_VIRTEX_GENERIC_BOARD bool "Generic Xilinx Virtex board" depends on 40x - default n select XILINX_VIRTEX_II_PRO select XILINX_VIRTEX_4_FX select XILINX_INTC @@ -80,7 +74,6 @@ config XILINX_VIRTEX_GENERIC_BOARD config OBS600 bool "OpenBlockS 600" depends on 40x - default n select 405EX select PPC40x_SIMPLE help @@ -90,7 +83,6 @@ config OBS600 config PPC40x_SIMPLE bool "Simple PowerPC 40x board support" depends on 40x - default n help This option enables the simple PowerPC 40x platform support. @@ -156,7 +148,6 @@ config IBM405_ERR51 config APM8018X bool "APM8018X" depends on 40x - default n select PPC40x_SIMPLE help This option enables support for the AppliedMicro APM8018X evaluation diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index a6011422b861..f024efd5a4c2 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -2,7 +2,6 @@ config PPC_47x bool "Support for 47x variant" depends on 44x - default n select MPIC help This option enables support for the 47x family of processors and is @@ -11,7 +10,6 @@ config PPC_47x config BAMBOO bool "Bamboo" depends on 44x - default n select PPC44x_SIMPLE select 440EP select PCI @@ -21,7 +19,6 @@ config BAMBOO config BLUESTONE bool "Bluestone" depends on 44x - default n select PPC44x_SIMPLE select APM821xx select PCI_MSI @@ -44,7 +41,6 @@ config EBONY config SAM440EP bool "Sam440ep" depends on 44x - default n select 440EP select PCI help @@ -53,7 +49,6 @@ config SAM440EP config SEQUOIA bool "Sequoia" depends on 44x - default n select PPC44x_SIMPLE select 440EPX help @@ -62,7 +57,6 @@ config SEQUOIA config TAISHAN bool "Taishan" depends on 44x - default n select PPC44x_SIMPLE select 440GX select PCI @@ -73,7 +67,6 @@ config TAISHAN config KATMAI bool "Katmai" depends on 44x - default n select PPC44x_SIMPLE select 440SPe select PCI @@ -86,7 +79,6 @@ config KATMAI config RAINIER bool "Rainier" depends on 44x - default n select PPC44x_SIMPLE select 440GRX select PCI @@ -96,7 +88,6 @@ config RAINIER config WARP bool "PIKA Warp" depends on 44x - default n select 440EP help This option enables support for the PIKA Warp(tm) Appliance. The Warp @@ -109,7 +100,6 @@ config WARP config ARCHES bool "Arches" depends on 44x - default n select PPC44x_SIMPLE select 460EX # Odd since it uses 460GT but the effects are the same select PCI @@ -120,7 +110,6 @@ config ARCHES config CANYONLANDS bool "Canyonlands" depends on 44x - default n select 460EX select PCI select PPC4xx_PCI_EXPRESS @@ -134,7 +123,6 @@ config CANYONLANDS config GLACIER bool "Glacier" depends on 44x - default n select PPC44x_SIMPLE select 460EX # Odd since it uses 460GT but the effects are the same select PCI @@ -147,7 +135,6 @@ config GLACIER config REDWOOD bool "Redwood" depends on 44x - default n select PPC44x_SIMPLE select 460SX select PCI @@ -160,7 +147,6 @@ config REDWOOD config EIGER bool "Eiger" depends on 44x - default n select PPC44x_SIMPLE select 460SX select PCI @@ -172,7 +158,6 @@ config EIGER config YOSEMITE bool "Yosemite" depends on 44x - default n select PPC44x_SIMPLE select 440EP select PCI @@ -182,7 +167,6 @@ config YOSEMITE config ISS4xx bool "ISS 4xx Simulator" depends on (44x || 40x) - default n select 405GP if 40x select 440GP if 44x && !PPC_47x select PPC_FPU @@ -193,7 +177,6 @@ config ISS4xx config CURRITUCK bool "IBM Currituck (476fpe) Support" depends on PPC_47x - default n select SWIOTLB select 476FPE select PPC4xx_PCI_EXPRESS @@ -203,7 +186,6 @@ config CURRITUCK config FSP2 bool "IBM FSP2 (476fpe) Support" depends on PPC_47x - default n select 476FPE select IBM_EMAC_EMAC4 if IBM_EMAC select IBM_EMAC_RGMII if IBM_EMAC @@ -215,7 +197,6 @@ config FSP2 config AKEBONO bool "IBM Akebono (476gtr) Support" depends on PPC_47x - default n select SWIOTLB select 476FPE select PPC4xx_PCI_EXPRESS @@ -241,7 +222,6 @@ config AKEBONO config ICON bool "Icon" depends on 44x - default n select PPC44x_SIMPLE select 440SPe select PCI @@ -252,7 +232,6 @@ config ICON config XILINX_VIRTEX440_GENERIC_BOARD bool "Generic Xilinx Virtex 5 FXT board support" depends on 44x - default n select XILINX_VIRTEX_5_FXT select XILINX_INTC help @@ -280,7 +259,6 @@ config XILINX_ML510 config PPC44x_SIMPLE bool "Simple PowerPC 44x board support" depends on 44x - default n help This option enables the simple PowerPC 44x platform support. diff --git a/arch/powerpc/platforms/44x/fsp2.c b/arch/powerpc/platforms/44x/fsp2.c index 04f0c73a9b4f..7a507f775308 100644 --- a/arch/powerpc/platforms/44x/fsp2.c +++ b/arch/powerpc/platforms/44x/fsp2.c @@ -210,15 +210,15 @@ static void node_irq_request(const char *compat, irq_handler_t errirq_handler) for_each_compatible_node(np, NULL, compat) { irq = irq_of_parse_and_map(np, 0); if (irq == NO_IRQ) { - pr_err("device tree node %s is missing a interrupt", - np->name); + pr_err("device tree node %pOFn is missing a interrupt", + np); return; } rc = request_irq(irq, errirq_handler, 0, np->name, np); if (rc) { - pr_err("fsp_of_probe: request_irq failed: np=%s rc=%d", - np->full_name, rc); + pr_err("fsp_of_probe: request_irq failed: np=%pOF rc=%d", + np, rc); return; } } diff --git a/arch/powerpc/platforms/4xx/ocm.c b/arch/powerpc/platforms/4xx/ocm.c index 69d9f60d9fe5..f5bbd4563342 100644 --- a/arch/powerpc/platforms/4xx/ocm.c +++ b/arch/powerpc/platforms/4xx/ocm.c @@ -113,7 +113,6 @@ static void __init ocm_init_node(int count, struct device_node *node) int len; struct resource rsrc; - int ioflags; ocm = ocm_get_node(count); @@ -179,9 +178,8 @@ static void __init ocm_init_node(int count, struct device_node *node) /* ioremap the non-cached region */ if (ocm->nc.memtotal) { - ioflags = _PAGE_NO_CACHE | _PAGE_GUARDED | _PAGE_EXEC; ocm->nc.virt = __ioremap(ocm->nc.phys, ocm->nc.memtotal, - ioflags); + _PAGE_EXEC | PAGE_KERNEL_NCG); if (!ocm->nc.virt) { printk(KERN_ERR @@ -195,9 +193,8 @@ static void __init ocm_init_node(int count, struct device_node *node) /* ioremap the cached region */ if (ocm->c.memtotal) { - ioflags = _PAGE_EXEC; ocm->c.virt = __ioremap(ocm->c.phys, ocm->c.memtotal, - ioflags); + _PAGE_EXEC | PAGE_KERNEL); if (!ocm->c.virt) { printk(KERN_ERR diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig index 6e04099361b9..1947a88bc69f 100644 --- a/arch/powerpc/platforms/82xx/Kconfig +++ b/arch/powerpc/platforms/82xx/Kconfig @@ -51,7 +51,6 @@ endif config PQ2ADS bool - default n config 8260 bool diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 7e966f4cf19a..fff72425727a 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -216,8 +216,8 @@ static int smp_85xx_start_cpu(int cpu) /* Map the spin table */ if (ioremappable) - spin_table = ioremap_prot(*cpu_rel_addr, - sizeof(struct epapr_spin_table), _PAGE_COHERENT); + spin_table = ioremap_coherent(*cpu_rel_addr, + sizeof(struct epapr_spin_table)); else spin_table = phys_to_virt(*cpu_rel_addr); diff --git a/arch/powerpc/platforms/8xx/machine_check.c b/arch/powerpc/platforms/8xx/machine_check.c index 402016705a39..9944fc303df0 100644 --- a/arch/powerpc/platforms/8xx/machine_check.c +++ b/arch/powerpc/platforms/8xx/machine_check.c @@ -18,9 +18,9 @@ int machine_check_8xx(struct pt_regs *regs) pr_err("Machine check in kernel mode.\n"); pr_err("Caused by (from SRR1=%lx): ", reason); if (reason & 0x40000000) - pr_err("Fetch error at address %lx\n", regs->nip); + pr_cont("Fetch error at address %lx\n", regs->nip); else - pr_err("Data access error at address %lx\n", regs->dar); + pr_cont("Data access error at address %lx\n", regs->dar); #ifdef CONFIG_PCI /* the qspan pci read routines can cause machine checks -- Cort diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 14ef17e10ec9..260a56b7602d 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -23,7 +23,6 @@ source "arch/powerpc/platforms/amigaone/Kconfig" config KVM_GUEST bool "KVM Guest support" - default n select EPAPR_PARAVIRT ---help--- This option enables various optimizations for running under the KVM @@ -34,7 +33,6 @@ config KVM_GUEST config EPAPR_PARAVIRT bool "ePAPR para-virtualization support" - default n help Enables ePAPR para-virtualization support for guests. @@ -74,7 +72,6 @@ config PPC_DT_CPU_FTRS config UDBG_RTAS_CONSOLE bool "RTAS based debug console" depends on PPC_RTAS - default n config PPC_SMP_MUXED_IPI bool @@ -86,16 +83,13 @@ config PPC_SMP_MUXED_IPI config IPIC bool - default n config MPIC bool - default n config MPIC_TIMER bool "MPIC Global Timer" depends on MPIC && FSL_SOC - default n help The MPIC global timer is a hardware timer inside the Freescale PIC complying with OpenPIC standard. When the @@ -107,7 +101,6 @@ config MPIC_TIMER config FSL_MPIC_TIMER_WAKEUP tristate "Freescale MPIC global timer wakeup driver" depends on FSL_SOC && MPIC_TIMER && PM - default n help The driver provides a way to wake up the system by MPIC timer. @@ -115,43 +108,35 @@ config FSL_MPIC_TIMER_WAKEUP config PPC_EPAPR_HV_PIC bool - default n select EPAPR_PARAVIRT config MPIC_WEIRD bool - default n config MPIC_MSGR bool "MPIC message register support" depends on MPIC - default n help Enables support for the MPIC message registers. These registers are used for inter-processor communication. config PPC_I8259 bool - default n config U3_DART bool depends on PPC64 - default n config PPC_RTAS bool - default n config RTAS_ERROR_LOGGING bool depends on PPC_RTAS - default n config PPC_RTAS_DAEMON bool depends on PPC_RTAS - default n config RTAS_PROC bool "Proc interface to RTAS" @@ -164,11 +149,9 @@ config RTAS_FLASH config MMIO_NVRAM bool - default n config MPIC_U3_HT_IRQS bool - default n config MPIC_BROKEN_REGREAD bool @@ -187,15 +170,12 @@ config EEH config PPC_MPC106 bool - default n config PPC_970_NAP bool - default n config PPC_P7_NAP bool - default n config PPC_INDIRECT_PIO bool @@ -295,7 +275,6 @@ config CPM2 config FSL_ULI1575 bool - default n select GENERIC_ISA_DMA help Supports for the ULI1575 PCIe south bridge that exists on some diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 6c6a7c72cae4..f4e2c5729374 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 config PPC64 bool "64-bit kernel" - default n select ZLIB_DEFLATE help This option selects whether a 32-bit or a 64-bit kernel @@ -72,6 +71,7 @@ config PPC_BOOK3S_64 select PPC_HAVE_PMU_SUPPORT select SYS_SUPPORTS_HUGETLBFS select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_SUPPORTS_NUMA_BALANCING select IRQ_WORK @@ -368,7 +368,6 @@ config PPC_MM_SLICES bool default y if PPC_BOOK3S_64 default y if PPC_8xx && HUGETLB_PAGE - default n config PPC_HAVE_PMU_SUPPORT bool @@ -382,7 +381,6 @@ config PPC_PERF_CTRS config FORCE_SMP # Allow platforms to force SMP=y by selecting this bool - default n select SMP config SMP @@ -423,7 +421,6 @@ config CHECK_CACHE_COHERENCY config PPC_DOORBELL bool - default n endmenu diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile index e46bb7ea710f..143d4417f6cc 100644 --- a/arch/powerpc/platforms/Makefile +++ b/arch/powerpc/platforms/Makefile @@ -1,7 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror - obj-$(CONFIG_FSL_ULI1575) += fsl_uli1575.o obj-$(CONFIG_PPC_PMAC) += powermac/ diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 9f5958f16923..4b2f114f3116 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_CELL bool - default n config PPC_CELL_COMMON bool @@ -22,7 +21,6 @@ config PPC_CELL_NATIVE select IBM_EMAC_RGMII if IBM_EMAC select IBM_EMAC_ZMII if IBM_EMAC #test only select IBM_EMAC_TAH if IBM_EMAC #test only - default n config PPC_IBM_CELL_BLADE bool "IBM Cell Blade" @@ -54,7 +52,6 @@ config SPU_FS config SPU_BASE bool - default n select PPC_COPRO_BASE config CBE_RAS diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c index 5c409c98cca8..f7e36373f6e0 100644 --- a/arch/powerpc/platforms/cell/spu_manage.c +++ b/arch/powerpc/platforms/cell/spu_manage.c @@ -180,35 +180,22 @@ out: static int __init spu_map_interrupts(struct spu *spu, struct device_node *np) { - struct of_phandle_args oirq; - int ret; int i; for (i=0; i < 3; i++) { - ret = of_irq_parse_one(np, i, &oirq); - if (ret) { - pr_debug("spu_new: failed to get irq %d\n", i); - goto err; - } - ret = -EINVAL; - pr_debug(" irq %d no 0x%x on %pOF\n", i, oirq.args[0], - oirq.np); - spu->irqs[i] = irq_create_of_mapping(&oirq); - if (!spu->irqs[i]) { - pr_debug("spu_new: failed to map it !\n"); + spu->irqs[i] = irq_of_parse_and_map(np, i); + if (!spu->irqs[i]) goto err; - } } return 0; err: - pr_debug("failed to map irq %x for spu %s\n", *oirq.args, - spu->name); + pr_debug("failed to map irq %x for spu %s\n", i, spu->name); for (; i >= 0; i--) { if (spu->irqs[i]) irq_dispose_mapping(spu->irqs[i]); } - return ret; + return -EINVAL; } static int spu_map_resource(struct spu *spu, int nr, @@ -295,8 +282,8 @@ static int __init of_enumerate_spus(int (*fn)(void *data)) for_each_node_by_type(node, "spe") { ret = fn(node); if (ret) { - printk(KERN_WARNING "%s: Error initializing %s\n", - __func__, node->name); + printk(KERN_WARNING "%s: Error initializing %pOFn\n", + __func__, node); of_node_put(node); break; } diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 403523c061ba..ecf703ee3a76 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -112,7 +112,7 @@ static void __iomem *wii_ioremap_hw_regs(char *name, char *compatible) } error = of_address_to_resource(np, 0, &res); if (error) { - pr_err("no valid reg found for %s\n", np->name); + pr_err("no valid reg found for %pOFn\n", np); goto out_put; } diff --git a/arch/powerpc/platforms/maple/Kconfig b/arch/powerpc/platforms/maple/Kconfig index 376d0be36b66..2601fac50354 100644 --- a/arch/powerpc/platforms/maple/Kconfig +++ b/arch/powerpc/platforms/maple/Kconfig @@ -13,7 +13,6 @@ config PPC_MAPLE select PPC_RTAS select MMIO_NVRAM select ATA_NONSTANDARD if ATA - default n help This option enables support for the Maple 970FX Evaluation Board. For more information, refer to <http://www.970eval.com> diff --git a/arch/powerpc/platforms/pasemi/Kconfig b/arch/powerpc/platforms/pasemi/Kconfig index d458a791d35b..98e3bc22bebc 100644 --- a/arch/powerpc/platforms/pasemi/Kconfig +++ b/arch/powerpc/platforms/pasemi/Kconfig @@ -2,7 +2,6 @@ config PPC_PASEMI depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN bool "PA Semi SoC-based platforms" - default n select MPIC select PCI select PPC_UDBG_16550 diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c index c80f72c370ae..53384eb42a76 100644 --- a/arch/powerpc/platforms/pasemi/dma_lib.c +++ b/arch/powerpc/platforms/pasemi/dma_lib.c @@ -576,7 +576,7 @@ int pasemi_dma_init(void) res.start = 0xfd800000; res.end = res.start + 0x1000; } - dma_status = __ioremap(res.start, resource_size(&res), 0); + dma_status = ioremap_cache(res.start, resource_size(&res)); pci_dev_put(iob_pdev); for (i = 0; i < MAX_TXCH; i++) diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index f2839eed0f89..923bfb340433 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -1,9 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS_bootx_init.o += -fPIC +CFLAGS_bootx_init.o += $(call cc-option, -fno-stack-protector) ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code -CFLAGS_REMOVE_bootx_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_bootx_init.o = $(CC_FLAGS_FTRACE) endif obj-y += pic.o setup.o time.o feature.o pci.o \ diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c index f92c1918fb56..f157e3d071f2 100644 --- a/arch/powerpc/platforms/powermac/time.c +++ b/arch/powerpc/platforms/powermac/time.c @@ -45,13 +45,6 @@ #endif /* - * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU - * times wrap in 2040. If we need to handle later times, the read_time functions - * need to be changed to interpret wrapped times as post-2040. - */ -#define RTC_OFFSET 2082844800 - -/* * Calibrate the decrementer frequency with the VIA timer 1. */ #define VIA_TIMER_FREQ_6 4700000 /* time 1 frequency * 6 */ @@ -90,98 +83,6 @@ long __init pmac_time_init(void) return delta; } -#ifdef CONFIG_ADB_CUDA -static time64_t cuda_get_time(void) -{ - struct adb_request req; - time64_t now; - - if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0) - return 0; - while (!req.complete) - cuda_poll(); - if (req.reply_len != 7) - printk(KERN_ERR "cuda_get_time: got %d byte reply\n", - req.reply_len); - now = (u32)((req.reply[3] << 24) + (req.reply[4] << 16) + - (req.reply[5] << 8) + req.reply[6]); - /* it's either after year 2040, or the RTC has gone backwards */ - WARN_ON(now < RTC_OFFSET); - - return now - RTC_OFFSET; -} - -#define cuda_get_rtc_time(tm) rtc_time64_to_tm(cuda_get_time(), (tm)) - -static int cuda_set_rtc_time(struct rtc_time *tm) -{ - u32 nowtime; - struct adb_request req; - - nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET); - if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME, - nowtime >> 24, nowtime >> 16, nowtime >> 8, - nowtime) < 0) - return -ENXIO; - while (!req.complete) - cuda_poll(); - if ((req.reply_len != 3) && (req.reply_len != 7)) - printk(KERN_ERR "cuda_set_rtc_time: got %d byte reply\n", - req.reply_len); - return 0; -} - -#else -#define cuda_get_time() 0 -#define cuda_get_rtc_time(tm) -#define cuda_set_rtc_time(tm) 0 -#endif - -#ifdef CONFIG_ADB_PMU -static time64_t pmu_get_time(void) -{ - struct adb_request req; - time64_t now; - - if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) - return 0; - pmu_wait_complete(&req); - if (req.reply_len != 4) - printk(KERN_ERR "pmu_get_time: got %d byte reply from PMU\n", - req.reply_len); - now = (u32)((req.reply[0] << 24) + (req.reply[1] << 16) + - (req.reply[2] << 8) + req.reply[3]); - - /* it's either after year 2040, or the RTC has gone backwards */ - WARN_ON(now < RTC_OFFSET); - - return now - RTC_OFFSET; -} - -#define pmu_get_rtc_time(tm) rtc_time64_to_tm(pmu_get_time(), (tm)) - -static int pmu_set_rtc_time(struct rtc_time *tm) -{ - u32 nowtime; - struct adb_request req; - - nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET); - if (pmu_request(&req, NULL, 5, PMU_SET_RTC, nowtime >> 24, - nowtime >> 16, nowtime >> 8, nowtime) < 0) - return -ENXIO; - pmu_wait_complete(&req); - if (req.reply_len != 0) - printk(KERN_ERR "pmu_set_rtc_time: %d byte reply from PMU\n", - req.reply_len); - return 0; -} - -#else -#define pmu_get_time() 0 -#define pmu_get_rtc_time(tm) -#define pmu_set_rtc_time(tm) 0 -#endif - #ifdef CONFIG_PMAC_SMU static time64_t smu_get_time(void) { @@ -191,11 +92,6 @@ static time64_t smu_get_time(void) return 0; return rtc_tm_to_time64(&tm); } - -#else -#define smu_get_time() 0 -#define smu_get_rtc_time(tm, spin) -#define smu_set_rtc_time(tm, spin) 0 #endif /* Can't be __init, it's called when suspending and resuming */ @@ -203,12 +99,18 @@ time64_t pmac_get_boot_time(void) { /* Get the time from the RTC, used only at boot time */ switch (sys_ctrler) { +#ifdef CONFIG_ADB_CUDA case SYS_CTRLER_CUDA: return cuda_get_time(); +#endif +#ifdef CONFIG_ADB_PMU case SYS_CTRLER_PMU: return pmu_get_time(); +#endif +#ifdef CONFIG_PMAC_SMU case SYS_CTRLER_SMU: return smu_get_time(); +#endif default: return 0; } @@ -218,15 +120,21 @@ void pmac_get_rtc_time(struct rtc_time *tm) { /* Get the time from the RTC, used only at boot time */ switch (sys_ctrler) { +#ifdef CONFIG_ADB_CUDA case SYS_CTRLER_CUDA: - cuda_get_rtc_time(tm); + rtc_time64_to_tm(cuda_get_time(), tm); break; +#endif +#ifdef CONFIG_ADB_PMU case SYS_CTRLER_PMU: - pmu_get_rtc_time(tm); + rtc_time64_to_tm(pmu_get_time(), tm); break; +#endif +#ifdef CONFIG_PMAC_SMU case SYS_CTRLER_SMU: smu_get_rtc_time(tm, 1); break; +#endif default: ; } @@ -235,12 +143,18 @@ void pmac_get_rtc_time(struct rtc_time *tm) int pmac_set_rtc_time(struct rtc_time *tm) { switch (sys_ctrler) { +#ifdef CONFIG_ADB_CUDA case SYS_CTRLER_CUDA: return cuda_set_rtc_time(tm); +#endif +#ifdef CONFIG_ADB_PMU case SYS_CTRLER_PMU: return pmu_set_rtc_time(tm); +#endif +#ifdef CONFIG_PMAC_SMU case SYS_CTRLER_SMU: return smu_set_rtc_time(tm, 1); +#endif default: return -ENODEV; } diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index f8dc98d3dc01..99083fe992d5 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -15,11 +15,6 @@ config PPC_POWERNV select PPC_SCOM select ARCH_RANDOM select CPU_FREQ - select CPU_FREQ_GOV_PERFORMANCE - select CPU_FREQ_GOV_POWERSAVE - select CPU_FREQ_GOV_USERSPACE - select CPU_FREQ_GOV_ONDEMAND - select CPU_FREQ_GOV_CONSERVATIVE select PPC_DOORBELL select MMU_NOTIFIER select FORCE_SMP @@ -35,7 +30,6 @@ config OPAL_PRD config PPC_MEMTRACE bool "Enable removal of RAM from kernel mappings for tracing" depends on PPC_POWERNV && MEMORY_HOTREMOVE - default n help Enabling this option allows for the removal of memory (RAM) from the kernel mappings to be used for hardware tracing. diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 3c1beae29f2d..abc0be7507c8 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -223,14 +223,6 @@ int pnv_eeh_post_init(void) eeh_probe_devices(); eeh_addr_cache_build(); - if (eeh_has_flag(EEH_POSTPONED_PROBE)) { - eeh_clear_flag(EEH_POSTPONED_PROBE); - if (eeh_enabled()) - pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); - else - pr_info("EEH: No capable adapters found\n"); - } - /* Register OPAL event notifier */ eeh_event_irq = opal_event_request(ilog2(OPAL_EVENT_PCI_ERROR)); if (eeh_event_irq < 0) { @@ -391,12 +383,6 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) return NULL; - /* Skip if we haven't probed yet */ - if (phb->ioda.pe_rmap[config_addr] == IODA_INVALID_PE) { - eeh_add_flag(EEH_POSTPONED_PROBE); - return NULL; - } - /* Initialize eeh device */ edev->class_code = pdn->class_code; edev->mode &= 0xFFFFFF00; @@ -604,7 +590,7 @@ static int pnv_eeh_get_phb_state(struct eeh_pe *pe) EEH_STATE_MMIO_ENABLED | EEH_STATE_DMA_ENABLED); } else if (!(pe->state & EEH_PE_ISOLATED)) { - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + eeh_pe_mark_isolated(pe); pnv_eeh_get_phb_diag(pe); if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) @@ -706,7 +692,7 @@ static int pnv_eeh_get_pe_state(struct eeh_pe *pe) if (phb->freeze_pe) phb->freeze_pe(phb, pe->addr); - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + eeh_pe_mark_isolated(pe); pnv_eeh_get_phb_diag(pe); if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) @@ -1054,7 +1040,7 @@ static int pnv_eeh_reset_vf_pe(struct eeh_pe *pe, int option) int ret; /* The VF PE should have only one child device */ - edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, list); + edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry); pdn = eeh_dev_to_pdn(edev); if (!pdn) return -ENXIO; @@ -1148,43 +1134,6 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option) } /** - * pnv_eeh_wait_state - Wait for PE state - * @pe: EEH PE - * @max_wait: maximal period in millisecond - * - * Wait for the state of associated PE. It might take some time - * to retrieve the PE's state. - */ -static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait) -{ - int ret; - int mwait; - - while (1) { - ret = pnv_eeh_get_state(pe, &mwait); - - /* - * If the PE's state is temporarily unavailable, - * we have to wait for the specified time. Otherwise, - * the PE's state will be returned immediately. - */ - if (ret != EEH_STATE_UNAVAILABLE) - return ret; - - if (max_wait <= 0) { - pr_warn("%s: Timeout getting PE#%x's state (%d)\n", - __func__, pe->addr, max_wait); - return EEH_STATE_NOT_SUPPORT; - } - - max_wait -= mwait; - msleep(mwait); - } - - return EEH_STATE_NOT_SUPPORT; -} - -/** * pnv_eeh_get_log - Retrieve error log * @pe: EEH PE * @severity: temporary or permanent error log @@ -1611,7 +1560,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe) if ((ret == EEH_NEXT_ERR_FROZEN_PE || ret == EEH_NEXT_ERR_FENCED_PHB) && !((*pe)->state & EEH_PE_ISOLATED)) { - eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + eeh_pe_mark_isolated(*pe); pnv_eeh_get_phb_diag(*pe); if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) @@ -1640,7 +1589,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe) } /* We possibly migrate to another PE */ - eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + eeh_pe_mark_isolated(*pe); } /* @@ -1702,7 +1651,6 @@ static struct eeh_ops pnv_eeh_ops = { .get_pe_addr = pnv_eeh_get_pe_addr, .get_state = pnv_eeh_get_state, .reset = pnv_eeh_reset, - .wait_state = pnv_eeh_wait_state, .get_log = pnv_eeh_get_log, .configure_bridge = pnv_eeh_configure_bridge, .err_inject = pnv_eeh_err_inject, diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index 51dc398ae3f7..a29fdf8a2e56 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -90,17 +90,15 @@ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages) walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE, change_memblock_state); - lock_device_hotplug(); - remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT); - unlock_device_hotplug(); return true; } static u64 memtrace_alloc_node(u32 nid, u64 size) { - u64 start_pfn, end_pfn, nr_pages; + u64 start_pfn, end_pfn, nr_pages, pfn; u64 base_pfn; + u64 bytes = memory_block_size_bytes(); if (!node_spanned_pages(nid)) return 0; @@ -113,8 +111,21 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) end_pfn = round_down(end_pfn - nr_pages, nr_pages); for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) { - if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) + if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) { + /* + * Remove memory in memory block size chunks so that + * iomem resources are always split to the same size and + * we never try to remove memory that spans two iomem + * resources. + */ + lock_device_hotplug(); + end_pfn = base_pfn + nr_pages; + for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) { + remove_memory(nid, pfn << PAGE_SHIFT, bytes); + } + unlock_device_hotplug(); return base_pfn << PAGE_SHIFT; + } } return 0; diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 8006c54a91e3..6f60e0931922 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -17,7 +17,7 @@ #include <linux/pci.h> #include <linux/memblock.h> #include <linux/iommu.h> -#include <linux/debugfs.h> +#include <linux/sizes.h> #include <asm/debugfs.h> #include <asm/tlb.h> @@ -42,14 +42,6 @@ static DEFINE_SPINLOCK(npu_context_lock); /* - * When an address shootdown range exceeds this threshold we invalidate the - * entire TLB on the GPU for the given PID rather than each specific address in - * the range. - */ -static uint64_t atsd_threshold = 2 * 1024 * 1024; -static struct dentry *atsd_threshold_dentry; - -/* * Other types of TCE cache invalidation are not functional in the * hardware. */ @@ -454,79 +446,73 @@ static void put_mmio_atsd_reg(struct npu *npu, int reg) } /* MMIO ATSD register offsets */ -#define XTS_ATSD_AVA 1 -#define XTS_ATSD_STAT 2 - -static void mmio_launch_invalidate(struct mmio_atsd_reg *mmio_atsd_reg, - unsigned long launch, unsigned long va) -{ - struct npu *npu = mmio_atsd_reg->npu; - int reg = mmio_atsd_reg->reg; - - __raw_writeq_be(va, npu->mmio_atsd_regs[reg] + XTS_ATSD_AVA); - eieio(); - __raw_writeq_be(launch, npu->mmio_atsd_regs[reg]); -} +#define XTS_ATSD_LAUNCH 0 +#define XTS_ATSD_AVA 1 +#define XTS_ATSD_STAT 2 -static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], - unsigned long pid, bool flush) +static unsigned long get_atsd_launch_val(unsigned long pid, unsigned long psize) { - int i; - unsigned long launch; - - for (i = 0; i <= max_npu2_index; i++) { - if (mmio_atsd_reg[i].reg < 0) - continue; + unsigned long launch = 0; - /* IS set to invalidate matching PID */ - launch = PPC_BIT(12); - - /* PRS set to process-scoped */ - launch |= PPC_BIT(13); + if (psize == MMU_PAGE_COUNT) { + /* IS set to invalidate entire matching PID */ + launch |= PPC_BIT(12); + } else { + /* AP set to invalidate region of psize */ + launch |= (u64)mmu_get_ap(psize) << PPC_BITLSHIFT(17); + } - /* AP */ - launch |= (u64) - mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17); + /* PRS set to process-scoped */ + launch |= PPC_BIT(13); - /* PID */ - launch |= pid << PPC_BITLSHIFT(38); + /* PID */ + launch |= pid << PPC_BITLSHIFT(38); - /* No flush */ - launch |= !flush << PPC_BITLSHIFT(39); + /* Leave "No flush" (bit 39) 0 so every ATSD performs a flush */ - /* Invalidating the entire process doesn't use a va */ - mmio_launch_invalidate(&mmio_atsd_reg[i], launch, 0); - } + return launch; } -static void mmio_invalidate_va(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], - unsigned long va, unsigned long pid, bool flush) +static void mmio_atsd_regs_write(struct mmio_atsd_reg + mmio_atsd_reg[NV_MAX_NPUS], unsigned long offset, + unsigned long val) { - int i; - unsigned long launch; + struct npu *npu; + int i, reg; for (i = 0; i <= max_npu2_index; i++) { - if (mmio_atsd_reg[i].reg < 0) + reg = mmio_atsd_reg[i].reg; + if (reg < 0) continue; - /* IS set to invalidate target VA */ - launch = 0; + npu = mmio_atsd_reg[i].npu; + __raw_writeq_be(val, npu->mmio_atsd_regs[reg] + offset); + } +} + +static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], + unsigned long pid) +{ + unsigned long launch = get_atsd_launch_val(pid, MMU_PAGE_COUNT); - /* PRS set to process scoped */ - launch |= PPC_BIT(13); + /* Invalidating the entire process doesn't use a va */ + mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_LAUNCH, launch); +} - /* AP */ - launch |= (u64) - mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17); +static void mmio_invalidate_range(struct mmio_atsd_reg + mmio_atsd_reg[NV_MAX_NPUS], unsigned long pid, + unsigned long start, unsigned long psize) +{ + unsigned long launch = get_atsd_launch_val(pid, psize); - /* PID */ - launch |= pid << PPC_BITLSHIFT(38); + /* Write all VAs first */ + mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_AVA, start); - /* No flush */ - launch |= !flush << PPC_BITLSHIFT(39); + /* Issue one barrier for all address writes */ + eieio(); - mmio_launch_invalidate(&mmio_atsd_reg[i], launch, va); - } + /* Launch */ + mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_LAUNCH, launch); } #define mn_to_npu_context(x) container_of(x, struct npu_context, mn) @@ -612,14 +598,36 @@ static void release_atsd_reg(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS]) } /* - * Invalidate either a single address or an entire PID depending on - * the value of va. + * Invalidate a virtual address range */ -static void mmio_invalidate(struct npu_context *npu_context, int va, - unsigned long address, bool flush) +static void mmio_invalidate(struct npu_context *npu_context, + unsigned long start, unsigned long size) { struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS]; unsigned long pid = npu_context->mm->context.id; + unsigned long atsd_start = 0; + unsigned long end = start + size - 1; + int atsd_psize = MMU_PAGE_COUNT; + + /* + * Convert the input range into one of the supported sizes. If the range + * doesn't fit, use the next larger supported size. Invalidation latency + * is high, so over-invalidation is preferred to issuing multiple + * invalidates. + * + * A 4K page size isn't supported by NPU/GPU ATS, so that case is + * ignored. + */ + if (size == SZ_64K) { + atsd_start = start; + atsd_psize = MMU_PAGE_64K; + } else if (ALIGN_DOWN(start, SZ_2M) == ALIGN_DOWN(end, SZ_2M)) { + atsd_start = ALIGN_DOWN(start, SZ_2M); + atsd_psize = MMU_PAGE_2M; + } else if (ALIGN_DOWN(start, SZ_1G) == ALIGN_DOWN(end, SZ_1G)) { + atsd_start = ALIGN_DOWN(start, SZ_1G); + atsd_psize = MMU_PAGE_1G; + } if (npu_context->nmmu_flush) /* @@ -634,23 +642,25 @@ static void mmio_invalidate(struct npu_context *npu_context, int va, * an invalidate. */ acquire_atsd_reg(npu_context, mmio_atsd_reg); - if (va) - mmio_invalidate_va(mmio_atsd_reg, address, pid, flush); + + if (atsd_psize == MMU_PAGE_COUNT) + mmio_invalidate_pid(mmio_atsd_reg, pid); else - mmio_invalidate_pid(mmio_atsd_reg, pid, flush); + mmio_invalidate_range(mmio_atsd_reg, pid, atsd_start, + atsd_psize); mmio_invalidate_wait(mmio_atsd_reg); - if (flush) { - /* - * The GPU requires two flush ATSDs to ensure all entries have - * been flushed. We use PID 0 as it will never be used for a - * process on the GPU. - */ - mmio_invalidate_pid(mmio_atsd_reg, 0, true); - mmio_invalidate_wait(mmio_atsd_reg); - mmio_invalidate_pid(mmio_atsd_reg, 0, true); - mmio_invalidate_wait(mmio_atsd_reg); - } + + /* + * The GPU requires two flush ATSDs to ensure all entries have been + * flushed. We use PID 0 as it will never be used for a process on the + * GPU. + */ + mmio_invalidate_pid(mmio_atsd_reg, 0); + mmio_invalidate_wait(mmio_atsd_reg); + mmio_invalidate_pid(mmio_atsd_reg, 0); + mmio_invalidate_wait(mmio_atsd_reg); + release_atsd_reg(mmio_atsd_reg); } @@ -667,7 +677,7 @@ static void pnv_npu2_mn_release(struct mmu_notifier *mn, * There should be no more translation requests for this PID, but we * need to ensure any entries for it are removed from the TLB. */ - mmio_invalidate(npu_context, 0, 0, true); + mmio_invalidate(npu_context, 0, ~0UL); } static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn, @@ -676,8 +686,7 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn, pte_t pte) { struct npu_context *npu_context = mn_to_npu_context(mn); - - mmio_invalidate(npu_context, 1, address, true); + mmio_invalidate(npu_context, address, PAGE_SIZE); } static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, @@ -685,21 +694,7 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, unsigned long start, unsigned long end) { struct npu_context *npu_context = mn_to_npu_context(mn); - unsigned long address; - - if (end - start > atsd_threshold) { - /* - * Just invalidate the entire PID if the address range is too - * large. - */ - mmio_invalidate(npu_context, 0, 0, true); - } else { - for (address = start; address < end; address += PAGE_SIZE) - mmio_invalidate(npu_context, 1, address, false); - - /* Do the flush only on the final addess == end */ - mmio_invalidate(npu_context, 1, address, true); - } + mmio_invalidate(npu_context, start, end - start); } static const struct mmu_notifier_ops nv_nmmu_notifier_ops = { @@ -962,11 +957,6 @@ int pnv_npu2_init(struct pnv_phb *phb) static int npu_index; uint64_t rc = 0; - if (!atsd_threshold_dentry) { - atsd_threshold_dentry = debugfs_create_x64("atsd_threshold", - 0600, powerpc_debugfs_root, &atsd_threshold); - } - phb->npu.nmmu_flush = of_property_read_bool(phb->hose->dn, "ibm,nmmu-flush"); for_each_child_of_node(phb->hose->dn, dn) { diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c index badb29bde93f..d90ee4fc2c6a 100644 --- a/arch/powerpc/platforms/powernv/opal-powercap.c +++ b/arch/powerpc/platforms/powernv/opal-powercap.c @@ -199,7 +199,7 @@ void __init opal_powercap_init(void) } j = 0; - pcaps[i].pg.name = node->name; + pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node); if (has_min) { powercap_add_attr(min, "powercap-min", &pcaps[i].pattrs[j]); @@ -237,6 +237,7 @@ out_pcaps_pattrs: while (--i >= 0) { kfree(pcaps[i].pattrs); kfree(pcaps[i].pg.attrs); + kfree(pcaps[i].pg.name); } kobject_put(powercap_kobj); out_pcaps: diff --git a/arch/powerpc/platforms/powernv/opal-sensor-groups.c b/arch/powerpc/platforms/powernv/opal-sensor-groups.c index f7d04b6a2d7a..179609220e6f 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor-groups.c +++ b/arch/powerpc/platforms/powernv/opal-sensor-groups.c @@ -214,9 +214,9 @@ void __init opal_sensor_groups_init(void) } if (!of_property_read_u32(node, "ibm,chip-id", &chipid)) - sprintf(sgs[i].name, "%s%d", node->name, chipid); + sprintf(sgs[i].name, "%pOFn%d", node, chipid); else - sprintf(sgs[i].name, "%s", node->name); + sprintf(sgs[i].name, "%pOFn", node); sgs[i].sg.name = sgs[i].name; if (add_attr_group(ops, len, &sgs[i], sgid)) { diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index 9aa87df114fd..916a4b7b1bb5 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -194,7 +194,7 @@ void __init opal_sys_param_init(void) count = of_property_count_strings(sysparam, "param-name"); if (count < 0) { pr_err("SYSPARAM: No string found of property param-name in " - "the node %s\n", sysparam->name); + "the node %pOFn\n", sysparam); goto out_param_buf; } diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 38fe4087484a..a4641515956f 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -535,7 +535,7 @@ static int opal_recover_mce(struct pt_regs *regs, return recovered; } -void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg) +void __noreturn pnv_platform_error_reboot(struct pt_regs *regs, const char *msg) { panic_flush_kmsg_start(); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index adddde023622..14befee4b3f1 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -219,17 +219,41 @@ static void pnv_prepare_going_down(void) static void __noreturn pnv_restart(char *cmd) { - long rc = OPAL_BUSY; + long rc; pnv_prepare_going_down(); - while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { - rc = opal_cec_reboot(); - if (rc == OPAL_BUSY_EVENT) - opal_poll_events(NULL); + do { + if (!cmd) + rc = opal_cec_reboot(); + else if (strcmp(cmd, "full") == 0) + rc = opal_cec_reboot2(OPAL_REBOOT_FULL_IPL, NULL); else + rc = OPAL_UNSUPPORTED; + + if (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + /* Opal is busy wait for some time and retry */ + opal_poll_events(NULL); mdelay(10); - } + + } else if (cmd && rc) { + /* Unknown error while issuing reboot */ + if (rc == OPAL_UNSUPPORTED) + pr_err("Unsupported '%s' reboot.\n", cmd); + else + pr_err("Unable to issue '%s' reboot. Err=%ld\n", + cmd, rc); + pr_info("Forcing a cec-reboot\n"); + cmd = NULL; + rc = OPAL_BUSY; + + } else if (rc != OPAL_SUCCESS) { + /* Unknown error while issuing cec-reboot */ + pr_err("Unable to reboot. Err=%ld\n", rc); + } + + } while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT); + for (;;) opal_poll_events(NULL); } @@ -437,6 +461,16 @@ static unsigned long pnv_get_proc_freq(unsigned int cpu) return ret_freq; } +static long pnv_machine_check_early(struct pt_regs *regs) +{ + long handled = 0; + + if (cur_cpu_spec && cur_cpu_spec->machine_check_early) + handled = cur_cpu_spec->machine_check_early(regs); + + return handled; +} + define_machine(powernv) { .name = "PowerNV", .probe = pnv_probe, @@ -448,6 +482,7 @@ define_machine(powernv) { .machine_shutdown = pnv_shutdown, .power_save = NULL, .calibrate_decr = generic_calibrate_decr, + .machine_check_early = pnv_machine_check_early, #ifdef CONFIG_KEXEC_CORE .kexec_cpu_down = pnv_kexec_cpu_down, #endif diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig index 6f7525555b19..24864b8aaf5d 100644 --- a/arch/powerpc/platforms/ps3/Kconfig +++ b/arch/powerpc/platforms/ps3/Kconfig @@ -49,7 +49,6 @@ config PS3_HTAB_SIZE config PS3_DYNAMIC_DMA depends on PPC_PS3 bool "PS3 Platform dynamic DMA page table management" - default n help This option will enable kernel support to take advantage of the per device dynamic DMA page table management provided by the Cell @@ -89,7 +88,6 @@ config PS3_SYS_MANAGER config PS3_REPOSITORY_WRITE bool "PS3 Repository write support" if PS3_ADVANCED depends on PPC_PS3 - default n help Enables support for writing to the PS3 System Repository. diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c index cdbfc5cfd6f3..f5387ad82279 100644 --- a/arch/powerpc/platforms/ps3/os-area.c +++ b/arch/powerpc/platforms/ps3/os-area.c @@ -664,7 +664,7 @@ static int update_flash_db(void) db_set_64(db, &os_area_db_id_rtc_diff, saved_params.rtc_diff); count = os_area_flash_write(db, sizeof(struct os_area_db), pos); - if (count < sizeof(struct os_area_db)) { + if (count < 0 || count < sizeof(struct os_area_db)) { pr_debug("%s: os_area_flash_write failed %zd\n", __func__, count); error = count < 0 ? count : -EIO; diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index b54850845466..7746c2a3c509 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -215,8 +215,7 @@ static int __init setup_areas(struct spu *spu) goto fail_ioremap; } - spu->local_store = (__force void *)ioremap_prot(spu->local_store_phys, - LS_SIZE, pgprot_val(pgprot_noncached_wc(__pgprot(0)))); + spu->local_store = (__force void *)ioremap_wc(spu->local_store_phys, LS_SIZE); if (!spu->local_store) { pr_debug("%s:%d: ioremap local_store failed\n", diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 0c698fd6d491..2e4bd32154b5 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -28,7 +28,6 @@ config PPC_PSERIES config PPC_SPLPAR depends on PPC_PSERIES bool "Support for shared-processor logical partitions" - default n help Enabling this option will make the kernel run more efficiently on logically-partitioned pSeries systems which use shared @@ -99,7 +98,6 @@ config PPC_SMLPAR bool "Support for shared-memory logical partitions" depends on PPC_PSERIES select LPARCFG - default n help Select this option to enable shared memory partition support. With this option a system running in an LPAR can be given more @@ -140,3 +138,10 @@ config IBMEBUS bool "Support for GX bus based adapters" help Bus device driver for GX bus based adapters. + +config PAPR_SCM + depends on PPC_PSERIES && MEMORY_HOTPLUG + select LIBNVDIMM + tristate "Support for the PAPR Storage Class Memory interface" + help + Enable access to hypervisor provided storage class memory. diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 7e89d5c47068..a43ec843c8e2 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_KEXEC_CORE) += kexec.o obj-$(CONFIG_PSERIES_ENERGY) += pseries_energy.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug-cpu.o -obj-$(CONFIG_MEMORY_HOTPLUG) += hotplug-memory.o +obj-$(CONFIG_MEMORY_HOTPLUG) += hotplug-memory.o pmem.o obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o obj-$(CONFIG_HVCS) += hvcserver.o @@ -24,6 +24,7 @@ obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o obj-$(CONFIG_LPARCFG) += lparcfg.o obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_IBMEBUS) += ibmebus.o +obj-$(CONFIG_PAPR_SCM) += papr_scm.o ifdef CONFIG_PPC_PSERIES obj-$(CONFIG_SUSPEND) += suspend.o diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index a0b20c03f078..7625546caefd 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -32,8 +32,6 @@ static struct workqueue_struct *pseries_hp_wq; struct pseries_hp_work { struct work_struct work; struct pseries_hp_errorlog *errlog; - struct completion *hp_completion; - int *rc; }; struct cc_workarea { @@ -329,7 +327,7 @@ int dlpar_release_drc(u32 drc_index) return 0; } -static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) +int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) { int rc; @@ -357,6 +355,10 @@ static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) case PSERIES_HP_ELOG_RESOURCE_CPU: rc = dlpar_cpu(hp_elog); break; + case PSERIES_HP_ELOG_RESOURCE_PMEM: + rc = dlpar_hp_pmem(hp_elog); + break; + default: pr_warn_ratelimited("Invalid resource (%d) specified\n", hp_elog->resource); @@ -371,20 +373,13 @@ static void pseries_hp_work_fn(struct work_struct *work) struct pseries_hp_work *hp_work = container_of(work, struct pseries_hp_work, work); - if (hp_work->rc) - *(hp_work->rc) = handle_dlpar_errorlog(hp_work->errlog); - else - handle_dlpar_errorlog(hp_work->errlog); - - if (hp_work->hp_completion) - complete(hp_work->hp_completion); + handle_dlpar_errorlog(hp_work->errlog); kfree(hp_work->errlog); kfree((void *)work); } -void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog, - struct completion *hotplug_done, int *rc) +void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog) { struct pseries_hp_work *work; struct pseries_hp_errorlog *hp_errlog_copy; @@ -397,13 +392,9 @@ void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog, if (work) { INIT_WORK((struct work_struct *)work, pseries_hp_work_fn); work->errlog = hp_errlog_copy; - work->hp_completion = hotplug_done; - work->rc = rc; queue_work(pseries_hp_wq, (struct work_struct *)work); } else { - *rc = -ENOMEM; kfree(hp_errlog_copy); - complete(hotplug_done); } } @@ -521,18 +512,15 @@ static int dlpar_parse_id_type(char **cmd, struct pseries_hp_errorlog *hp_elog) static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, const char *buf, size_t count) { - struct pseries_hp_errorlog *hp_elog; - struct completion hotplug_done; + struct pseries_hp_errorlog hp_elog; char *argbuf; char *args; int rc; args = argbuf = kstrdup(buf, GFP_KERNEL); - hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL); - if (!hp_elog || !argbuf) { + if (!argbuf) { pr_info("Could not allocate resources for DLPAR operation\n"); kfree(argbuf); - kfree(hp_elog); return -ENOMEM; } @@ -540,25 +528,22 @@ static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, * Parse out the request from the user, this will be in the form: * <resource> <action> <id_type> <id> */ - rc = dlpar_parse_resource(&args, hp_elog); + rc = dlpar_parse_resource(&args, &hp_elog); if (rc) goto dlpar_store_out; - rc = dlpar_parse_action(&args, hp_elog); + rc = dlpar_parse_action(&args, &hp_elog); if (rc) goto dlpar_store_out; - rc = dlpar_parse_id_type(&args, hp_elog); + rc = dlpar_parse_id_type(&args, &hp_elog); if (rc) goto dlpar_store_out; - init_completion(&hotplug_done); - queue_hotplug_event(hp_elog, &hotplug_done, &rc); - wait_for_completion(&hotplug_done); + rc = handle_dlpar_errorlog(&hp_elog); dlpar_store_out: kfree(argbuf); - kfree(hp_elog); if (rc) pr_err("Could not handle DLPAR request \"%s\"\n", buf); diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 18014cdeb590..ef6595153642 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -149,7 +149,7 @@ static int dtl_start(struct dtl *dtl) /* Register our dtl buffer with the hypervisor. The HV expects the * buffer size to be passed in the second word of the buffer */ - ((u32 *)dtl->buf)[1] = DISPATCH_LOG_BYTES; + ((u32 *)dtl->buf)[1] = cpu_to_be32(DISPATCH_LOG_BYTES); hwcpu = get_hard_smp_processor_id(dtl->cpu); addr = __pa(dtl->buf); @@ -184,7 +184,7 @@ static void dtl_stop(struct dtl *dtl) static u64 dtl_current_index(struct dtl *dtl) { - return lppaca_of(dtl->cpu).dtl_idx; + return be64_to_cpu(lppaca_of(dtl->cpu).dtl_idx); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 823cb27efa8b..c9e5ca4afb26 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -438,7 +438,7 @@ static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) /** * pseries_eeh_get_state - Retrieve PE state * @pe: EEH PE - * @state: return value + * @delay: suggested time to wait if state is unavailable * * Retrieve the state of the specified PE. On RTAS compliant * pseries platform, there already has one dedicated RTAS function @@ -448,7 +448,7 @@ static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) * RTAS calls for the purpose, we need to try the new one and back * to the old one if the new one couldn't work properly. */ -static int pseries_eeh_get_state(struct eeh_pe *pe, int *state) +static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) { int config_addr; int ret; @@ -499,7 +499,8 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state) break; case 5: if (rets[2]) { - if (state) *state = rets[2]; + if (delay) + *delay = rets[2]; result = EEH_STATE_UNAVAILABLE; } else { result = EEH_STATE_NOT_SUPPORT; @@ -554,64 +555,6 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option) } /** - * pseries_eeh_wait_state - Wait for PE state - * @pe: EEH PE - * @max_wait: maximal period in millisecond - * - * Wait for the state of associated PE. It might take some time - * to retrieve the PE's state. - */ -static int pseries_eeh_wait_state(struct eeh_pe *pe, int max_wait) -{ - int ret; - int mwait; - - /* - * According to PAPR, the state of PE might be temporarily - * unavailable. Under the circumstance, we have to wait - * for indicated time determined by firmware. The maximal - * wait time is 5 minutes, which is acquired from the original - * EEH implementation. Also, the original implementation - * also defined the minimal wait time as 1 second. - */ -#define EEH_STATE_MIN_WAIT_TIME (1000) -#define EEH_STATE_MAX_WAIT_TIME (300 * 1000) - - while (1) { - ret = pseries_eeh_get_state(pe, &mwait); - - /* - * If the PE's state is temporarily unavailable, - * we have to wait for the specified time. Otherwise, - * the PE's state will be returned immediately. - */ - if (ret != EEH_STATE_UNAVAILABLE) - return ret; - - if (max_wait <= 0) { - pr_warn("%s: Timeout when getting PE's state (%d)\n", - __func__, max_wait); - return EEH_STATE_NOT_SUPPORT; - } - - if (mwait <= 0) { - pr_warn("%s: Firmware returned bad wait value %d\n", - __func__, mwait); - mwait = EEH_STATE_MIN_WAIT_TIME; - } else if (mwait > EEH_STATE_MAX_WAIT_TIME) { - pr_warn("%s: Firmware returned too long wait value %d\n", - __func__, mwait); - mwait = EEH_STATE_MAX_WAIT_TIME; - } - - max_wait -= mwait; - msleep(mwait); - } - - return EEH_STATE_NOT_SUPPORT; -} - -/** * pseries_eeh_get_log - Retrieve error log * @pe: EEH PE * @severity: temporary or permanent error log @@ -849,7 +792,6 @@ static struct eeh_ops pseries_eeh_ops = { .get_pe_addr = pseries_eeh_get_pe_addr, .get_state = pseries_eeh_get_state, .reset = pseries_eeh_reset, - .wait_state = pseries_eeh_wait_state, .get_log = pseries_eeh_get_log, .configure_bridge = pseries_eeh_configure_bridge, .err_inject = NULL, diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c index 6eeb0d4bab61..446ef104fb3a 100644 --- a/arch/powerpc/platforms/pseries/event_sources.c +++ b/arch/powerpc/platforms/pseries/event_sources.c @@ -16,7 +16,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <asm/prom.h> +#include <linux/interrupt.h> +#include <linux/of_irq.h> #include "pseries.h" @@ -24,34 +25,19 @@ void request_event_sources_irqs(struct device_node *np, irq_handler_t handler, const char *name) { - int i, index, count = 0; - struct of_phandle_args oirq; - unsigned int virqs[16]; + int i, virq, rc; - /* First try to do a proper OF tree parsing */ - for (index = 0; of_irq_parse_one(np, index, &oirq) == 0; - index++) { - if (count > 15) - break; - virqs[count] = irq_create_of_mapping(&oirq); - if (!virqs[count]) { - pr_err("event-sources: Unable to allocate " - "interrupt number for %pOF\n", - np); - WARN_ON(1); - } else { - count++; - } - } + for (i = 0; i < 16; i++) { + virq = of_irq_get(np, i); + if (virq < 0) + return; + if (WARN(!virq, "event-sources: Unable to allocate " + "interrupt number for %pOF\n", np)) + continue; - /* Now request them */ - for (i = 0; i < count; i++) { - if (request_irq(virqs[i], handler, 0, name, NULL)) { - pr_err("event-sources: Unable to request interrupt " - "%d for %pOF\n", virqs[i], np); - WARN_ON(1); + rc = request_irq(virq, handler, 0, name, NULL); + if (WARN(rc, "event-sources: Unable to request interrupt %d for %pOF\n", + virq, np)) return; - } } } - diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index a3bbeb43689e..608ecad0178f 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -65,6 +65,8 @@ hypertas_fw_features_table[] = { {FW_FEATURE_SET_MODE, "hcall-set-mode"}, {FW_FEATURE_BEST_ENERGY, "hcall-best-energy-1*"}, {FW_FEATURE_HPT_RESIZE, "hcall-hpt-resize"}, + {FW_FEATURE_BLOCK_REMOVE, "hcall-block-remove"}, + {FW_FEATURE_PAPR_SCM, "hcall-scm"}, }; /* Build up the firmware features bitmask using the contents of diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 6ef77caf7bcf..2f8e62163602 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -287,7 +287,7 @@ static int pseries_add_processor(struct device_node *np) if (cpumask_empty(tmp)) { printk(KERN_ERR "Unable to find space in cpu_present_mask for" - " processor %s with %d thread(s)\n", np->name, + " processor %pOFn with %d thread(s)\n", np, nthreads); goto out_unlock; } @@ -481,8 +481,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index) if (rc) { saved_rc = rc; - pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n", - dn->name, rc, drc_index); + pr_warn("Failed to attach node %pOFn, rc: %d, drc index: %x\n", + dn, rc, drc_index); rc = dlpar_release_drc(drc_index); if (!rc) @@ -494,8 +494,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index) rc = dlpar_online_cpu(dn); if (rc) { saved_rc = rc; - pr_warn("Failed to online cpu %s, rc: %d, drc index: %x\n", - dn->name, rc, drc_index); + pr_warn("Failed to online cpu %pOFn, rc: %d, drc index: %x\n", + dn, rc, drc_index); rc = dlpar_detach_node(dn); if (!rc) @@ -504,7 +504,7 @@ static ssize_t dlpar_cpu_add(u32 drc_index) return saved_rc; } - pr_debug("Successfully added CPU %s, drc index: %x\n", dn->name, + pr_debug("Successfully added CPU %pOFn, drc index: %x\n", dn, drc_index); return rc; } @@ -570,19 +570,19 @@ static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index) { int rc; - pr_debug("Attempting to remove CPU %s, drc index: %x\n", - dn->name, drc_index); + pr_debug("Attempting to remove CPU %pOFn, drc index: %x\n", + dn, drc_index); rc = dlpar_offline_cpu(dn); if (rc) { - pr_warn("Failed to offline CPU %s, rc: %d\n", dn->name, rc); + pr_warn("Failed to offline CPU %pOFn, rc: %d\n", dn, rc); return -EINVAL; } rc = dlpar_release_drc(drc_index); if (rc) { - pr_warn("Failed to release drc (%x) for CPU %s, rc: %d\n", - drc_index, dn->name, rc); + pr_warn("Failed to release drc (%x) for CPU %pOFn, rc: %d\n", + drc_index, dn, rc); dlpar_online_cpu(dn); return rc; } @@ -591,7 +591,7 @@ static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index) if (rc) { int saved_rc = rc; - pr_warn("Failed to detach CPU %s, rc: %d", dn->name, rc); + pr_warn("Failed to detach CPU %pOFn, rc: %d", dn, rc); rc = dlpar_acquire_drc(drc_index); if (!rc) @@ -662,8 +662,8 @@ static int find_dlpar_cpus_to_remove(u32 *cpu_drcs, int cpus_to_remove) rc = of_property_read_u32(dn, "ibm,my-drc-index", &cpu_drcs[cpus_found - 1]); if (rc) { - pr_warn("Error occurred getting drc-index for %s\n", - dn->name); + pr_warn("Error occurred getting drc-index for %pOFn\n", + dn); of_node_put(dn); return -1; } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index c1578f54c626..2b796da822c2 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -101,11 +101,12 @@ static struct property *dlpar_clone_property(struct property *prop, return new_prop; } -static u32 find_aa_index(struct device_node *dr_node, - struct property *ala_prop, const u32 *lmb_assoc) +static bool find_aa_index(struct device_node *dr_node, + struct property *ala_prop, + const u32 *lmb_assoc, u32 *aa_index) { - u32 *assoc_arrays; - u32 aa_index; + u32 *assoc_arrays, new_prop_size; + struct property *new_prop; int aa_arrays, aa_array_entries, aa_array_sz; int i, index; @@ -121,54 +122,48 @@ static u32 find_aa_index(struct device_node *dr_node, aa_array_entries = be32_to_cpu(assoc_arrays[1]); aa_array_sz = aa_array_entries * sizeof(u32); - aa_index = -1; for (i = 0; i < aa_arrays; i++) { index = (i * aa_array_entries) + 2; if (memcmp(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz)) continue; - aa_index = i; - break; + *aa_index = i; + return true; } - if (aa_index == -1) { - struct property *new_prop; - u32 new_prop_size; - - new_prop_size = ala_prop->length + aa_array_sz; - new_prop = dlpar_clone_property(ala_prop, new_prop_size); - if (!new_prop) - return -1; - - assoc_arrays = new_prop->value; + new_prop_size = ala_prop->length + aa_array_sz; + new_prop = dlpar_clone_property(ala_prop, new_prop_size); + if (!new_prop) + return false; - /* increment the number of entries in the lookup array */ - assoc_arrays[0] = cpu_to_be32(aa_arrays + 1); + assoc_arrays = new_prop->value; - /* copy the new associativity into the lookup array */ - index = aa_arrays * aa_array_entries + 2; - memcpy(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz); + /* increment the number of entries in the lookup array */ + assoc_arrays[0] = cpu_to_be32(aa_arrays + 1); - of_update_property(dr_node, new_prop); + /* copy the new associativity into the lookup array */ + index = aa_arrays * aa_array_entries + 2; + memcpy(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz); - /* - * The associativity lookup array index for this lmb is - * number of entries - 1 since we added its associativity - * to the end of the lookup array. - */ - aa_index = be32_to_cpu(assoc_arrays[0]) - 1; - } + of_update_property(dr_node, new_prop); - return aa_index; + /* + * The associativity lookup array index for this lmb is + * number of entries - 1 since we added its associativity + * to the end of the lookup array. + */ + *aa_index = be32_to_cpu(assoc_arrays[0]) - 1; + return true; } -static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb) +static int update_lmb_associativity_index(struct drmem_lmb *lmb) { struct device_node *parent, *lmb_node, *dr_node; struct property *ala_prop; const u32 *lmb_assoc; u32 aa_index; + bool found; parent = of_find_node_by_path("/"); if (!parent) @@ -200,46 +195,17 @@ static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb) return -ENODEV; } - aa_index = find_aa_index(dr_node, ala_prop, lmb_assoc); + found = find_aa_index(dr_node, ala_prop, lmb_assoc, &aa_index); dlpar_free_cc_nodes(lmb_node); - return aa_index; -} -static int dlpar_add_device_tree_lmb(struct drmem_lmb *lmb) -{ - int rc, aa_index; - - lmb->flags |= DRCONF_MEM_ASSIGNED; - - aa_index = lookup_lmb_associativity_index(lmb); - if (aa_index < 0) { - pr_err("Couldn't find associativity index for drc index %x\n", - lmb->drc_index); - return aa_index; + if (!found) { + pr_err("Could not find LMB associativity\n"); + return -1; } lmb->aa_index = aa_index; - - rtas_hp_event = true; - rc = drmem_update_dt(); - rtas_hp_event = false; - - return rc; -} - -static int dlpar_remove_device_tree_lmb(struct drmem_lmb *lmb) -{ - int rc; - - lmb->flags &= ~DRCONF_MEM_ASSIGNED; - lmb->aa_index = 0xffffffff; - - rtas_hp_event = true; - rc = drmem_update_dt(); - rtas_hp_event = false; - - return rc; + return 0; } static struct memory_block *lmb_to_memblock(struct drmem_lmb *lmb) @@ -428,7 +394,9 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb) /* Update memory regions for memory remove */ memblock_remove(lmb->base_addr, block_sz); - dlpar_remove_device_tree_lmb(lmb); + invalidate_lmb_associativity_index(lmb); + lmb->flags &= ~DRCONF_MEM_ASSIGNED; + return 0; } @@ -688,10 +656,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) if (lmb->flags & DRCONF_MEM_ASSIGNED) return -EINVAL; - rc = dlpar_add_device_tree_lmb(lmb); + rc = update_lmb_associativity_index(lmb); if (rc) { - pr_err("Couldn't update device tree for drc index %x\n", - lmb->drc_index); dlpar_release_drc(lmb->drc_index); return rc; } @@ -704,14 +670,14 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) /* Add the memory */ rc = add_memory(nid, lmb->base_addr, block_sz); if (rc) { - dlpar_remove_device_tree_lmb(lmb); + invalidate_lmb_associativity_index(lmb); return rc; } rc = dlpar_online_lmb(lmb); if (rc) { remove_memory(nid, lmb->base_addr, block_sz); - dlpar_remove_device_tree_lmb(lmb); + invalidate_lmb_associativity_index(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; } @@ -958,6 +924,12 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) break; } + if (!rc) { + rtas_hp_event = true; + rc = drmem_update_dt(); + rtas_hp_event = false; + } + unlock_device_hotplug(); return rc; } diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index c7c1140c13b6..5b4a56131904 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -404,7 +404,7 @@ static ssize_t name_show(struct device *dev, struct platform_device *ofdev; ofdev = to_platform_device(dev); - return sprintf(buf, "%s\n", ofdev->dev.of_node->name); + return sprintf(buf, "%pOFn\n", ofdev->dev.of_node); } static DEVICE_ATTR_RO(name); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index d3992ced0782..32d4452973e7 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -48,6 +48,7 @@ #include <asm/kexec.h> #include <asm/fadump.h> #include <asm/asm-prototypes.h> +#include <asm/debugfs.h> #include "pseries.h" @@ -417,6 +418,79 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, BUG_ON(lpar_rc != H_SUCCESS); } + +/* + * As defined in the PAPR's section 14.5.4.1.8 + * The control mask doesn't include the returned reference and change bit from + * the processed PTE. + */ +#define HBLKR_AVPN 0x0100000000000000UL +#define HBLKR_CTRL_MASK 0xf800000000000000UL +#define HBLKR_CTRL_SUCCESS 0x8000000000000000UL +#define HBLKR_CTRL_ERRNOTFOUND 0x8800000000000000UL +#define HBLKR_CTRL_ERRBUSY 0xa000000000000000UL + +/** + * H_BLOCK_REMOVE caller. + * @idx should point to the latest @param entry set with a PTEX. + * If PTE cannot be processed because another CPUs has already locked that + * group, those entries are put back in @param starting at index 1. + * If entries has to be retried and @retry_busy is set to true, these entries + * are retried until success. If @retry_busy is set to false, the returned + * is the number of entries yet to process. + */ +static unsigned long call_block_remove(unsigned long idx, unsigned long *param, + bool retry_busy) +{ + unsigned long i, rc, new_idx; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + + if (idx < 2) { + pr_warn("Unexpected empty call to H_BLOCK_REMOVE"); + return 0; + } +again: + new_idx = 0; + if (idx > PLPAR_HCALL9_BUFSIZE) { + pr_err("Too many PTEs (%lu) for H_BLOCK_REMOVE", idx); + idx = PLPAR_HCALL9_BUFSIZE; + } else if (idx < PLPAR_HCALL9_BUFSIZE) + param[idx] = HBR_END; + + rc = plpar_hcall9(H_BLOCK_REMOVE, retbuf, + param[0], /* AVA */ + param[1], param[2], param[3], param[4], /* TS0-7 */ + param[5], param[6], param[7], param[8]); + if (rc == H_SUCCESS) + return 0; + + BUG_ON(rc != H_PARTIAL); + + /* Check that the unprocessed entries were 'not found' or 'busy' */ + for (i = 0; i < idx-1; i++) { + unsigned long ctrl = retbuf[i] & HBLKR_CTRL_MASK; + + if (ctrl == HBLKR_CTRL_ERRBUSY) { + param[++new_idx] = param[i+1]; + continue; + } + + BUG_ON(ctrl != HBLKR_CTRL_SUCCESS + && ctrl != HBLKR_CTRL_ERRNOTFOUND); + } + + /* + * If there were entries found busy, retry these entries if requested, + * of if all the entries have to be retried. + */ + if (new_idx && (retry_busy || new_idx == (PLPAR_HCALL9_BUFSIZE-1))) { + idx = new_idx + 1; + goto again; + } + + return new_idx; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need @@ -424,17 +498,57 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, */ #define PPC64_HUGE_HPTE_BATCH 12 -static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot, - unsigned long *vpn, int count, - int psize, int ssize) +static void hugepage_block_invalidate(unsigned long *slot, unsigned long *vpn, + int count, int psize, int ssize) { unsigned long param[PLPAR_HCALL9_BUFSIZE]; - int i = 0, pix = 0, rc; - unsigned long flags = 0; - int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + unsigned long shift, current_vpgb, vpgb; + int i, pix = 0; - if (lock_tlbie) - spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags); + shift = mmu_psize_defs[psize].shift; + + for (i = 0; i < count; i++) { + /* + * Shifting 3 bits more on the right to get a + * 8 pages aligned virtual addresse. + */ + vpgb = (vpn[i] >> (shift - VPN_SHIFT + 3)); + if (!pix || vpgb != current_vpgb) { + /* + * Need to start a new 8 pages block, flush + * the current one if needed. + */ + if (pix) + (void)call_block_remove(pix, param, true); + current_vpgb = vpgb; + param[0] = hpte_encode_avpn(vpn[i], psize, ssize); + pix = 1; + } + + param[pix++] = HBR_REQUEST | HBLKR_AVPN | slot[i]; + if (pix == PLPAR_HCALL9_BUFSIZE) { + pix = call_block_remove(pix, param, false); + /* + * pix = 0 means that all the entries were + * removed, we can start a new block. + * Otherwise, this means that there are entries + * to retry, and pix points to latest one, so + * we should increment it and try to continue + * the same block. + */ + if (pix) + pix++; + } + } + if (pix) + (void)call_block_remove(pix, param, true); +} + +static void hugepage_bulk_invalidate(unsigned long *slot, unsigned long *vpn, + int count, int psize, int ssize) +{ + unsigned long param[PLPAR_HCALL9_BUFSIZE]; + int i = 0, pix = 0, rc; for (i = 0; i < count; i++) { @@ -462,6 +576,23 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot, param[6], param[7]); BUG_ON(rc != H_SUCCESS); } +} + +static inline void __pSeries_lpar_hugepage_invalidate(unsigned long *slot, + unsigned long *vpn, + int count, int psize, + int ssize) +{ + unsigned long flags = 0; + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + + if (lock_tlbie) + spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags); + + if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) + hugepage_block_invalidate(slot, vpn, count, psize, ssize); + else + hugepage_bulk_invalidate(slot, vpn, count, psize, ssize); if (lock_tlbie) spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags); @@ -546,6 +677,86 @@ static int pSeries_lpar_hpte_removebolted(unsigned long ea, return 0; } + +static inline unsigned long compute_slot(real_pte_t pte, + unsigned long vpn, + unsigned long index, + unsigned long shift, + int ssize) +{ + unsigned long slot, hash, hidx; + + hash = hpt_hash(vpn, shift, ssize); + hidx = __rpte_to_hidx(pte, index); + if (hidx & _PTEIDX_SECONDARY) + hash = ~hash; + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += hidx & _PTEIDX_GROUP_IX; + return slot; +} + +/** + * The hcall H_BLOCK_REMOVE implies that the virtual pages to processed are + * "all within the same naturally aligned 8 page virtual address block". + */ +static void do_block_remove(unsigned long number, struct ppc64_tlb_batch *batch, + unsigned long *param) +{ + unsigned long vpn; + unsigned long i, pix = 0; + unsigned long index, shift, slot, current_vpgb, vpgb; + real_pte_t pte; + int psize, ssize; + + psize = batch->psize; + ssize = batch->ssize; + + for (i = 0; i < number; i++) { + vpn = batch->vpn[i]; + pte = batch->pte[i]; + pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) { + /* + * Shifting 3 bits more on the right to get a + * 8 pages aligned virtual addresse. + */ + vpgb = (vpn >> (shift - VPN_SHIFT + 3)); + if (!pix || vpgb != current_vpgb) { + /* + * Need to start a new 8 pages block, flush + * the current one if needed. + */ + if (pix) + (void)call_block_remove(pix, param, + true); + current_vpgb = vpgb; + param[0] = hpte_encode_avpn(vpn, psize, + ssize); + pix = 1; + } + + slot = compute_slot(pte, vpn, index, shift, ssize); + param[pix++] = HBR_REQUEST | HBLKR_AVPN | slot; + + if (pix == PLPAR_HCALL9_BUFSIZE) { + pix = call_block_remove(pix, param, false); + /* + * pix = 0 means that all the entries were + * removed, we can start a new block. + * Otherwise, this means that there are entries + * to retry, and pix points to latest one, so + * we should increment it and try to continue + * the same block. + */ + if (pix) + pix++; + } + } pte_iterate_hashed_end(); + } + + if (pix) + (void)call_block_remove(pix, param, true); +} + /* * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie * lock. @@ -558,13 +769,18 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch); int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); unsigned long param[PLPAR_HCALL9_BUFSIZE]; - unsigned long hash, index, shift, hidx, slot; + unsigned long index, shift, slot; real_pte_t pte; int psize, ssize; if (lock_tlbie) spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags); + if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) { + do_block_remove(number, batch, param); + goto out; + } + psize = batch->psize; ssize = batch->ssize; pix = 0; @@ -572,12 +788,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) vpn = batch->vpn[i]; pte = batch->pte[i]; pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) { - hash = hpt_hash(vpn, shift, ssize); - hidx = __rpte_to_hidx(pte, index); - if (hidx & _PTEIDX_SECONDARY) - hash = ~hash; - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - slot += hidx & _PTEIDX_GROUP_IX; + slot = compute_slot(pte, vpn, index, shift, ssize); if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) { /* * lpar doesn't use the passed actual page size @@ -608,6 +819,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) BUG_ON(rc != H_SUCCESS); } +out: if (lock_tlbie) spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags); } @@ -1028,3 +1240,56 @@ static int __init reserve_vrma_context_id(void) return 0; } machine_device_initcall(pseries, reserve_vrma_context_id); + +#ifdef CONFIG_DEBUG_FS +/* debugfs file interface for vpa data */ +static ssize_t vpa_file_read(struct file *filp, char __user *buf, size_t len, + loff_t *pos) +{ + int cpu = (long)filp->private_data; + struct lppaca *lppaca = &lppaca_of(cpu); + + return simple_read_from_buffer(buf, len, pos, lppaca, + sizeof(struct lppaca)); +} + +static const struct file_operations vpa_fops = { + .open = simple_open, + .read = vpa_file_read, + .llseek = default_llseek, +}; + +static int __init vpa_debugfs_init(void) +{ + char name[16]; + long i; + static struct dentry *vpa_dir; + + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return 0; + + vpa_dir = debugfs_create_dir("vpa", powerpc_debugfs_root); + if (!vpa_dir) { + pr_warn("%s: can't create vpa root dir\n", __func__); + return -ENOMEM; + } + + /* set up the per-cpu vpa file*/ + for_each_possible_cpu(i) { + struct dentry *d; + + sprintf(name, "cpu-%ld", i); + + d = debugfs_create_file(name, 0400, vpa_dir, (void *)i, + &vpa_fops); + if (!d) { + pr_warn("%s: can't create per-cpu vpa file\n", + __func__); + return -ENOMEM; + } + } + + return 0; +} +machine_arch_initcall(pseries, vpa_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 7c872dc01bdb..8bd590af488a 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -585,8 +585,7 @@ static ssize_t update_mpp(u64 *entitlement, u8 *weight) static ssize_t lparcfg_write(struct file *file, const char __user * buf, size_t count, loff_t * off) { - int kbuf_sz = 64; - char kbuf[kbuf_sz]; + char kbuf[64]; char *tmp; u64 new_entitled, *new_entitled_ptr = &new_entitled; u8 new_weight, *new_weight_ptr = &new_weight; @@ -595,7 +594,7 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf, if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return -EINVAL; - if (count > kbuf_sz) + if (count > sizeof(kbuf)) return -EINVAL; if (copy_from_user(kbuf, buf, count)) diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index f0e30dc94988..88925f8ca8a0 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -242,7 +242,7 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index) static void prrn_update_node(__be32 phandle) { - struct pseries_hp_errorlog *hp_elog; + struct pseries_hp_errorlog hp_elog; struct device_node *dn; /* @@ -255,18 +255,12 @@ static void prrn_update_node(__be32 phandle) return; } - hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL); - if(!hp_elog) - return; - - hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM; - hp_elog->action = PSERIES_HP_ELOG_ACTION_READD; - hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX; - hp_elog->_drc_u.drc_index = phandle; - - queue_hotplug_event(hp_elog, NULL, NULL); + hp_elog.resource = PSERIES_HP_ELOG_RESOURCE_MEM; + hp_elog.action = PSERIES_HP_ELOG_ACTION_READD; + hp_elog.id_type = PSERIES_HP_ELOG_ID_DRC_INDEX; + hp_elog._drc_u.drc_index = phandle; - kfree(hp_elog); + handle_dlpar_errorlog(&hp_elog); } int pseries_devicetree_update(s32 scope) @@ -366,6 +360,8 @@ static ssize_t migration_store(struct class *class, if (rc) return rc; + stop_topology_update(); + do { rc = rtas_ibm_suspend_me(streamid); if (rc == -EAGAIN) @@ -376,6 +372,9 @@ static ssize_t migration_store(struct class *class, return rc; post_mobility_fixup(); + + start_topology_update(); + return count; } diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index b7496948129e..8011b4129e3a 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -203,7 +203,8 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) /* Get the top level device in the PE */ edev = pdn_to_eeh_dev(PCI_DN(dn)); if (edev->pe) - edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, list); + edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, + entry); dn = pci_device_to_OF_node(edev->pdev); if (!dn) return NULL; diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c new file mode 100644 index 000000000000..ee9372b65ca5 --- /dev/null +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define pr_fmt(fmt) "papr-scm: " fmt + +#include <linux/of.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/ioport.h> +#include <linux/slab.h> +#include <linux/ndctl.h> +#include <linux/sched.h> +#include <linux/libnvdimm.h> +#include <linux/platform_device.h> + +#include <asm/plpar_wrappers.h> + +#define BIND_ANY_ADDR (~0ul) + +#define PAPR_SCM_DIMM_CMD_MASK \ + ((1ul << ND_CMD_GET_CONFIG_SIZE) | \ + (1ul << ND_CMD_GET_CONFIG_DATA) | \ + (1ul << ND_CMD_SET_CONFIG_DATA)) + +struct papr_scm_priv { + struct platform_device *pdev; + struct device_node *dn; + uint32_t drc_index; + uint64_t blocks; + uint64_t block_size; + int metadata_size; + + uint64_t bound_addr; + + struct nvdimm_bus_descriptor bus_desc; + struct nvdimm_bus *bus; + struct nvdimm *nvdimm; + struct resource res; + struct nd_region *region; + struct nd_interleave_set nd_set; +}; + +static int drc_pmem_bind(struct papr_scm_priv *p) +{ + unsigned long ret[PLPAR_HCALL_BUFSIZE]; + uint64_t rc, token; + + /* + * When the hypervisor cannot map all the requested memory in a single + * hcall it returns H_BUSY and we call again with the token until + * we get H_SUCCESS. Aborting the retry loop before getting H_SUCCESS + * leave the system in an undefined state, so we wait. + */ + token = 0; + + do { + rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0, + p->blocks, BIND_ANY_ADDR, token); + token = be64_to_cpu(ret[0]); + cond_resched(); + } while (rc == H_BUSY); + + if (rc) { + dev_err(&p->pdev->dev, "bind err: %lld\n", rc); + return -ENXIO; + } + + p->bound_addr = be64_to_cpu(ret[1]); + + dev_dbg(&p->pdev->dev, "bound drc %x to %pR\n", p->drc_index, &p->res); + + return 0; +} + +static int drc_pmem_unbind(struct papr_scm_priv *p) +{ + unsigned long ret[PLPAR_HCALL_BUFSIZE]; + uint64_t rc, token; + + token = 0; + + /* NB: unbind has the same retry requirements mentioned above */ + do { + rc = plpar_hcall(H_SCM_UNBIND_MEM, ret, p->drc_index, + p->bound_addr, p->blocks, token); + token = be64_to_cpu(ret); + cond_resched(); + } while (rc == H_BUSY); + + if (rc) + dev_err(&p->pdev->dev, "unbind error: %lld\n", rc); + + return !!rc; +} + +static int papr_scm_meta_get(struct papr_scm_priv *p, + struct nd_cmd_get_config_data_hdr *hdr) +{ + unsigned long data[PLPAR_HCALL_BUFSIZE]; + int64_t ret; + + if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1) + return -EINVAL; + + ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index, + hdr->in_offset, 1); + + if (ret == H_PARAMETER) /* bad DRC index */ + return -ENODEV; + if (ret) + return -EINVAL; /* other invalid parameter */ + + hdr->out_buf[0] = data[0] & 0xff; + + return 0; +} + +static int papr_scm_meta_set(struct papr_scm_priv *p, + struct nd_cmd_set_config_hdr *hdr) +{ + int64_t ret; + + if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1) + return -EINVAL; + + ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, + p->drc_index, hdr->in_offset, hdr->in_buf[0], 1); + + if (ret == H_PARAMETER) /* bad DRC index */ + return -ENODEV; + if (ret) + return -EINVAL; /* other invalid parameter */ + + return 0; +} + +int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, + unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc) +{ + struct nd_cmd_get_config_size *get_size_hdr; + struct papr_scm_priv *p; + + /* Only dimm-specific calls are supported atm */ + if (!nvdimm) + return -EINVAL; + + p = nvdimm_provider_data(nvdimm); + + switch (cmd) { + case ND_CMD_GET_CONFIG_SIZE: + get_size_hdr = buf; + + get_size_hdr->status = 0; + get_size_hdr->max_xfer = 1; + get_size_hdr->config_size = p->metadata_size; + *cmd_rc = 0; + break; + + case ND_CMD_GET_CONFIG_DATA: + *cmd_rc = papr_scm_meta_get(p, buf); + break; + + case ND_CMD_SET_CONFIG_DATA: + *cmd_rc = papr_scm_meta_set(p, buf); + break; + + default: + return -EINVAL; + } + + dev_dbg(&p->pdev->dev, "returned with cmd_rc = %d\n", *cmd_rc); + + return 0; +} + +static const struct attribute_group *region_attr_groups[] = { + &nd_region_attribute_group, + &nd_device_attribute_group, + &nd_mapping_attribute_group, + &nd_numa_attribute_group, + NULL, +}; + +static const struct attribute_group *bus_attr_groups[] = { + &nvdimm_bus_attribute_group, + NULL, +}; + +static const struct attribute_group *papr_scm_dimm_groups[] = { + &nvdimm_attribute_group, + &nd_device_attribute_group, + NULL, +}; + +static int papr_scm_nvdimm_init(struct papr_scm_priv *p) +{ + struct device *dev = &p->pdev->dev; + struct nd_mapping_desc mapping; + struct nd_region_desc ndr_desc; + unsigned long dimm_flags; + + p->bus_desc.ndctl = papr_scm_ndctl; + p->bus_desc.module = THIS_MODULE; + p->bus_desc.of_node = p->pdev->dev.of_node; + p->bus_desc.attr_groups = bus_attr_groups; + p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL); + + if (!p->bus_desc.provider_name) + return -ENOMEM; + + p->bus = nvdimm_bus_register(NULL, &p->bus_desc); + if (!p->bus) { + dev_err(dev, "Error creating nvdimm bus %pOF\n", p->dn); + return -ENXIO; + } + + dimm_flags = 0; + set_bit(NDD_ALIASING, &dimm_flags); + + p->nvdimm = nvdimm_create(p->bus, p, papr_scm_dimm_groups, + dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL); + if (!p->nvdimm) { + dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn); + goto err; + } + + /* now add the region */ + + memset(&mapping, 0, sizeof(mapping)); + mapping.nvdimm = p->nvdimm; + mapping.start = 0; + mapping.size = p->blocks * p->block_size; // XXX: potential overflow? + + memset(&ndr_desc, 0, sizeof(ndr_desc)); + ndr_desc.attr_groups = region_attr_groups; + ndr_desc.numa_node = dev_to_node(&p->pdev->dev); + ndr_desc.res = &p->res; + ndr_desc.of_node = p->dn; + ndr_desc.provider_data = p; + ndr_desc.mapping = &mapping; + ndr_desc.num_mappings = 1; + ndr_desc.nd_set = &p->nd_set; + set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags); + + p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc); + if (!p->region) { + dev_err(dev, "Error registering region %pR from %pOF\n", + ndr_desc.res, p->dn); + goto err; + } + + return 0; + +err: nvdimm_bus_unregister(p->bus); + kfree(p->bus_desc.provider_name); + return -ENXIO; +} + +static int papr_scm_probe(struct platform_device *pdev) +{ + uint32_t drc_index, metadata_size, unit_cap[2]; + struct device_node *dn = pdev->dev.of_node; + struct papr_scm_priv *p; + int rc; + + /* check we have all the required DT properties */ + if (of_property_read_u32(dn, "ibm,my-drc-index", &drc_index)) { + dev_err(&pdev->dev, "%pOF: missing drc-index!\n", dn); + return -ENODEV; + } + + if (of_property_read_u32_array(dn, "ibm,unit-capacity", unit_cap, 2)) { + dev_err(&pdev->dev, "%pOF: missing unit-capacity!\n", dn); + return -ENODEV; + } + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + + /* optional DT properties */ + of_property_read_u32(dn, "ibm,metadata-size", &metadata_size); + + p->dn = dn; + p->drc_index = drc_index; + p->block_size = unit_cap[0]; + p->blocks = unit_cap[1]; + + /* might be zero */ + p->metadata_size = metadata_size; + p->pdev = pdev; + + /* request the hypervisor to bind this region to somewhere in memory */ + rc = drc_pmem_bind(p); + if (rc) + goto err; + + /* setup the resource for the newly bound range */ + p->res.start = p->bound_addr; + p->res.end = p->bound_addr + p->blocks * p->block_size; + p->res.name = pdev->name; + p->res.flags = IORESOURCE_MEM; + + rc = papr_scm_nvdimm_init(p); + if (rc) + goto err2; + + platform_set_drvdata(pdev, p); + + return 0; + +err2: drc_pmem_unbind(p); +err: kfree(p); + return rc; +} + +static int papr_scm_remove(struct platform_device *pdev) +{ + struct papr_scm_priv *p = platform_get_drvdata(pdev); + + nvdimm_bus_unregister(p->bus); + drc_pmem_unbind(p); + kfree(p); + + return 0; +} + +static const struct of_device_id papr_scm_match[] = { + { .compatible = "ibm,pmemory" }, + { }, +}; + +static struct platform_driver papr_scm_driver = { + .probe = papr_scm_probe, + .remove = papr_scm_remove, + .driver = { + .name = "papr_scm", + .owner = THIS_MODULE, + .of_match_table = papr_scm_match, + }, +}; + +module_platform_driver(papr_scm_driver); +MODULE_DEVICE_TABLE(of, papr_scm_match); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("IBM Corporation"); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index eab96637d6cf..41d8a4d1d02e 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -239,6 +239,7 @@ void __init pSeries_final_fixup(void) { pSeries_request_regions(); + eeh_probe_devices(); eeh_addr_cache_build(); #ifdef CONFIG_PCI_IOV diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c new file mode 100644 index 000000000000..a27f40eb57b1 --- /dev/null +++ b/arch/powerpc/platforms/pseries/pmem.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Handles hot and cold plug of persistent memory regions on pseries. + */ + +#define pr_fmt(fmt) "pseries-pmem: " fmt + +#include <linux/kernel.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/sched.h> /* for idle_task_exit */ +#include <linux/sched/hotplug.h> +#include <linux/cpu.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/slab.h> +#include <asm/prom.h> +#include <asm/rtas.h> +#include <asm/firmware.h> +#include <asm/machdep.h> +#include <asm/vdso_datapage.h> +#include <asm/plpar_wrappers.h> +#include <asm/topology.h> + +#include "pseries.h" +#include "offline_states.h" + +static struct device_node *pmem_node; + +static ssize_t pmem_drc_add_node(u32 drc_index) +{ + struct device_node *dn; + int rc; + + pr_debug("Attempting to add pmem node, drc index: %x\n", drc_index); + + rc = dlpar_acquire_drc(drc_index); + if (rc) { + pr_err("Failed to acquire DRC, rc: %d, drc index: %x\n", + rc, drc_index); + return -EINVAL; + } + + dn = dlpar_configure_connector(cpu_to_be32(drc_index), pmem_node); + if (!dn) { + pr_err("configure-connector failed for drc %x\n", drc_index); + dlpar_release_drc(drc_index); + return -EINVAL; + } + + /* 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); + + if (dlpar_release_drc(drc_index)) + dlpar_free_cc_nodes(dn); + + return rc; + } + + pr_info("Successfully added %pOF, drc index: %x\n", dn, drc_index); + + return 0; +} + +static ssize_t pmem_drc_remove_node(u32 drc_index) +{ + struct device_node *dn; + uint32_t index; + int rc; + + for_each_child_of_node(pmem_node, dn) { + if (of_property_read_u32(dn, "ibm,my-drc-index", &index)) + continue; + if (index == drc_index) + break; + } + + if (!dn) { + pr_err("Attempting to remove unused DRC index %x\n", drc_index); + return -ENODEV; + } + + pr_debug("Attempting to remove %pOF, drc index: %x\n", dn, drc_index); + + /* * NB: tears down the ibm,pmemory device as a side-effect */ + rc = dlpar_detach_node(dn); + if (rc) + return rc; + + 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); + dlpar_attach_node(dn, pmem_node); + return rc; + } + + pr_info("Successfully removed PMEM with drc index: %x\n", drc_index); + + return 0; +} + +int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog) +{ + u32 count, drc_index; + int rc; + + /* slim chance, but we might get a hotplug event while booting */ + if (!pmem_node) + pmem_node = of_find_node_by_type(NULL, "ibm,persistent-memory"); + if (!pmem_node) { + pr_err("Hotplug event for a pmem device, but none exists\n"); + return -ENODEV; + } + + if (hp_elog->id_type != PSERIES_HP_ELOG_ID_DRC_INDEX) { + pr_err("Unsupported hotplug event type %d\n", + hp_elog->id_type); + return -EINVAL; + } + + count = hp_elog->_drc_u.drc_count; + drc_index = hp_elog->_drc_u.drc_index; + + lock_device_hotplug(); + + if (hp_elog->action == PSERIES_HP_ELOG_ACTION_ADD) { + rc = pmem_drc_add_node(drc_index); + } else if (hp_elog->action == PSERIES_HP_ELOG_ACTION_REMOVE) { + rc = pmem_drc_remove_node(drc_index); + } else { + pr_err("Unsupported hotplug action (%d)\n", hp_elog->action); + rc = -EINVAL; + } + + unlock_device_hotplug(); + return rc; +} + +const struct of_device_id drc_pmem_match[] = { + { .type = "ibm,persistent-memory", }, + {} +}; + +static int pseries_pmem_init(void) +{ + pmem_node = of_find_node_by_type(NULL, "ibm,persistent-memory"); + if (!pmem_node) + return 0; + + /* + * The generic OF bus probe/populate handles creating platform devices + * from the child (ibm,pmemory) nodes. The generic code registers an of + * reconfig notifier to handle the hot-add/remove cases too. + */ + of_platform_bus_probe(pmem_node, drc_pmem_match, NULL); + + return 0; +} +machine_arch_initcall(pseries, pseries_pmem_init); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 60db2ee511fb..7dee8c5d3363 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -24,6 +24,7 @@ struct pt_regs; extern int pSeries_system_reset_exception(struct pt_regs *regs); extern int pSeries_machine_check_exception(struct pt_regs *regs); +extern long pseries_machine_check_realmode(struct pt_regs *regs); #ifdef CONFIG_SMP extern void smp_init_pseries(void); @@ -59,15 +60,21 @@ extern int dlpar_detach_node(struct device_node *); extern int dlpar_acquire_drc(u32 drc_index); extern int dlpar_release_drc(u32 drc_index); -void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog, - struct completion *hotplug_done, int *rc); +void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog); +int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_errlog); + #ifdef CONFIG_MEMORY_HOTPLUG int dlpar_memory(struct pseries_hp_errorlog *hp_elog); +int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog); #else static inline int dlpar_memory(struct pseries_hp_errorlog *hp_elog) { return -EOPNOTSUPP; } +static inline int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} #endif #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 851ce326874a..d97d52772789 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -27,6 +27,7 @@ #include <asm/machdep.h> #include <asm/rtas.h> #include <asm/firmware.h> +#include <asm/mce.h> #include "pseries.h" @@ -50,6 +51,101 @@ static irqreturn_t ras_hotplug_interrupt(int irq, void *dev_id); static irqreturn_t ras_epow_interrupt(int irq, void *dev_id); static irqreturn_t ras_error_interrupt(int irq, void *dev_id); +/* RTAS pseries MCE errorlog section. */ +struct pseries_mc_errorlog { + __be32 fru_id; + __be32 proc_id; + u8 error_type; + /* + * sub_err_type (1 byte). Bit fields depends on error_type + * + * MSB0 + * | + * V + * 01234567 + * XXXXXXXX + * + * For error_type == MC_ERROR_TYPE_UE + * XXXXXXXX + * X 1: Permanent or Transient UE. + * X 1: Effective address provided. + * X 1: Logical address provided. + * XX 2: Reserved. + * XXX 3: Type of UE error. + * + * For error_type != MC_ERROR_TYPE_UE + * XXXXXXXX + * X 1: Effective address provided. + * XXXXX 5: Reserved. + * XX 2: Type of SLB/ERAT/TLB error. + */ + u8 sub_err_type; + u8 reserved_1[6]; + __be64 effective_address; + __be64 logical_address; +} __packed; + +/* RTAS pseries MCE error types */ +#define MC_ERROR_TYPE_UE 0x00 +#define MC_ERROR_TYPE_SLB 0x01 +#define MC_ERROR_TYPE_ERAT 0x02 +#define MC_ERROR_TYPE_TLB 0x04 +#define MC_ERROR_TYPE_D_CACHE 0x05 +#define MC_ERROR_TYPE_I_CACHE 0x07 + +/* RTAS pseries MCE error sub types */ +#define MC_ERROR_UE_INDETERMINATE 0 +#define MC_ERROR_UE_IFETCH 1 +#define MC_ERROR_UE_PAGE_TABLE_WALK_IFETCH 2 +#define MC_ERROR_UE_LOAD_STORE 3 +#define MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE 4 + +#define MC_ERROR_SLB_PARITY 0 +#define MC_ERROR_SLB_MULTIHIT 1 +#define MC_ERROR_SLB_INDETERMINATE 2 + +#define MC_ERROR_ERAT_PARITY 1 +#define MC_ERROR_ERAT_MULTIHIT 2 +#define MC_ERROR_ERAT_INDETERMINATE 3 + +#define MC_ERROR_TLB_PARITY 1 +#define MC_ERROR_TLB_MULTIHIT 2 +#define MC_ERROR_TLB_INDETERMINATE 3 + +static inline u8 rtas_mc_error_sub_type(const struct pseries_mc_errorlog *mlog) +{ + switch (mlog->error_type) { + case MC_ERROR_TYPE_UE: + return (mlog->sub_err_type & 0x07); + case MC_ERROR_TYPE_SLB: + case MC_ERROR_TYPE_ERAT: + case MC_ERROR_TYPE_TLB: + return (mlog->sub_err_type & 0x03); + default: + return 0; + } +} + +static +inline u64 rtas_mc_get_effective_addr(const struct pseries_mc_errorlog *mlog) +{ + __be64 addr = 0; + + switch (mlog->error_type) { + case MC_ERROR_TYPE_UE: + if (mlog->sub_err_type & 0x40) + addr = mlog->effective_address; + break; + case MC_ERROR_TYPE_SLB: + case MC_ERROR_TYPE_ERAT: + case MC_ERROR_TYPE_TLB: + if (mlog->sub_err_type & 0x80) + addr = mlog->effective_address; + default: + break; + } + return be64_to_cpu(addr); +} /* * Enable the hotplug interrupt late because processing them may touch other @@ -237,8 +333,9 @@ static irqreturn_t ras_hotplug_interrupt(int irq, void *dev_id) * hotplug events on the ras_log_buf to be handled by rtas_errd. */ if (hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_MEM || - hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_CPU) - queue_hotplug_event(hp_elog, NULL, NULL); + hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_CPU || + hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_PMEM) + queue_hotplug_event(hp_elog); else log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, 0); @@ -427,6 +524,188 @@ int pSeries_system_reset_exception(struct pt_regs *regs) return 0; /* need to perform reset */ } +#define VAL_TO_STRING(ar, val) \ + (((val) < ARRAY_SIZE(ar)) ? ar[(val)] : "Unknown") + +static void pseries_print_mce_info(struct pt_regs *regs, + struct rtas_error_log *errp) +{ + const char *level, *sevstr; + struct pseries_errorlog *pseries_log; + struct pseries_mc_errorlog *mce_log; + u8 error_type, err_sub_type; + u64 addr; + u8 initiator = rtas_error_initiator(errp); + int disposition = rtas_error_disposition(errp); + + static const char * const initiators[] = { + "Unknown", + "CPU", + "PCI", + "ISA", + "Memory", + "Power Mgmt", + }; + static const char * const mc_err_types[] = { + "UE", + "SLB", + "ERAT", + "TLB", + "D-Cache", + "Unknown", + "I-Cache", + }; + static const char * const mc_ue_types[] = { + "Indeterminate", + "Instruction fetch", + "Page table walk ifetch", + "Load/Store", + "Page table walk Load/Store", + }; + + /* SLB sub errors valid values are 0x0, 0x1, 0x2 */ + static const char * const mc_slb_types[] = { + "Parity", + "Multihit", + "Indeterminate", + }; + + /* TLB and ERAT sub errors valid values are 0x1, 0x2, 0x3 */ + static const char * const mc_soft_types[] = { + "Unknown", + "Parity", + "Multihit", + "Indeterminate", + }; + + if (!rtas_error_extended(errp)) { + pr_err("Machine check interrupt: Missing extended error log\n"); + return; + } + + pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); + if (pseries_log == NULL) + return; + + mce_log = (struct pseries_mc_errorlog *)pseries_log->data; + + error_type = mce_log->error_type; + err_sub_type = rtas_mc_error_sub_type(mce_log); + + switch (rtas_error_severity(errp)) { + case RTAS_SEVERITY_NO_ERROR: + level = KERN_INFO; + sevstr = "Harmless"; + break; + case RTAS_SEVERITY_WARNING: + level = KERN_WARNING; + sevstr = ""; + break; + case RTAS_SEVERITY_ERROR: + case RTAS_SEVERITY_ERROR_SYNC: + level = KERN_ERR; + sevstr = "Severe"; + break; + case RTAS_SEVERITY_FATAL: + default: + level = KERN_ERR; + sevstr = "Fatal"; + break; + } + +#ifdef CONFIG_PPC_BOOK3S_64 + /* Display faulty slb contents for SLB errors. */ + if (error_type == MC_ERROR_TYPE_SLB) + slb_dump_contents(local_paca->mce_faulty_slbs); +#endif + + printk("%s%s Machine check interrupt [%s]\n", level, sevstr, + disposition == RTAS_DISP_FULLY_RECOVERED ? + "Recovered" : "Not recovered"); + if (user_mode(regs)) { + printk("%s NIP: [%016lx] PID: %d Comm: %s\n", level, + regs->nip, current->pid, current->comm); + } else { + printk("%s NIP [%016lx]: %pS\n", level, regs->nip, + (void *)regs->nip); + } + printk("%s Initiator: %s\n", level, + VAL_TO_STRING(initiators, initiator)); + + switch (error_type) { + case MC_ERROR_TYPE_UE: + printk("%s Error type: %s [%s]\n", level, + VAL_TO_STRING(mc_err_types, error_type), + VAL_TO_STRING(mc_ue_types, err_sub_type)); + break; + case MC_ERROR_TYPE_SLB: + printk("%s Error type: %s [%s]\n", level, + VAL_TO_STRING(mc_err_types, error_type), + VAL_TO_STRING(mc_slb_types, err_sub_type)); + break; + case MC_ERROR_TYPE_ERAT: + case MC_ERROR_TYPE_TLB: + printk("%s Error type: %s [%s]\n", level, + VAL_TO_STRING(mc_err_types, error_type), + VAL_TO_STRING(mc_soft_types, err_sub_type)); + break; + default: + printk("%s Error type: %s\n", level, + VAL_TO_STRING(mc_err_types, error_type)); + break; + } + + addr = rtas_mc_get_effective_addr(mce_log); + if (addr) + printk("%s Effective address: %016llx\n", level, addr); +} + +static int mce_handle_error(struct rtas_error_log *errp) +{ + struct pseries_errorlog *pseries_log; + struct pseries_mc_errorlog *mce_log; + int disposition = rtas_error_disposition(errp); + u8 error_type; + + if (!rtas_error_extended(errp)) + goto out; + + pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); + if (pseries_log == NULL) + goto out; + + mce_log = (struct pseries_mc_errorlog *)pseries_log->data; + error_type = mce_log->error_type; + +#ifdef CONFIG_PPC_BOOK3S_64 + if (disposition == RTAS_DISP_NOT_RECOVERED) { + switch (error_type) { + case MC_ERROR_TYPE_SLB: + case MC_ERROR_TYPE_ERAT: + /* + * Store the old slb content in paca before flushing. + * Print this when we go to virtual mode. + * There are chances that we may hit MCE again if there + * is a parity error on the SLB entry we trying to read + * for saving. Hence limit the slb saving to single + * level of recursion. + */ + if (local_paca->in_mce == 1) + slb_save_contents(local_paca->mce_faulty_slbs); + flush_and_reload_slb(); + disposition = RTAS_DISP_FULLY_RECOVERED; + rtas_set_disposition_recovered(errp); + break; + default: + break; + } + } +#endif + +out: + return disposition; +} + /* * Process MCE rtas errlog event. */ @@ -452,8 +731,11 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) int recovered = 0; int disposition = rtas_error_disposition(err); + pseries_print_mce_info(regs, err); + if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ + pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n"); recovered = 0; } else if (disposition == RTAS_DISP_FULLY_RECOVERED) { @@ -503,11 +785,31 @@ int pSeries_machine_check_exception(struct pt_regs *regs) struct rtas_error_log *errp; if (fwnmi_active) { - errp = fwnmi_get_errinfo(regs); fwnmi_release_errinfo(); + errp = fwnmi_get_errlog(); if (errp && recover_mce(regs, errp)) return 1; } return 0; } + +long pseries_machine_check_realmode(struct pt_regs *regs) +{ + struct rtas_error_log *errp; + int disposition; + + if (fwnmi_active) { + errp = fwnmi_get_errinfo(regs); + /* + * Call to fwnmi_release_errinfo() in real mode causes kernel + * to panic. Hence we will call it as soon as we go into + * virtual mode. + */ + disposition = mce_handle_error(errp); + if (disposition == RTAS_DISP_FULLY_RECOVERED) + return 1; + } + + return 0; +} diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index ba1791fd3234..0f553dcfa548 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -107,6 +107,10 @@ static void __init fwnmi_init(void) u8 *mce_data_buf; unsigned int i; int nr_cpus = num_possible_cpus(); +#ifdef CONFIG_PPC_BOOK3S_64 + struct slb_entry *slb_ptr; + size_t size; +#endif int ibm_nmi_register = rtas_token("ibm,nmi-register"); if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE) @@ -132,6 +136,15 @@ static void __init fwnmi_init(void) paca_ptrs[i]->mce_data_buf = mce_data_buf + (RTAS_ERROR_LOG_MAX * i); } + +#ifdef CONFIG_PPC_BOOK3S_64 + /* Allocate per cpu slb area to save old slb contents during MCE */ + size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus; + slb_ptr = __va(memblock_alloc_base(size, sizeof(struct slb_entry), + ppc64_rma_size)); + for_each_possible_cpu(i) + paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i); +#endif } static void pseries_8259_cascade(struct irq_desc *desc) @@ -1017,6 +1030,7 @@ define_machine(pseries) { .calibrate_decr = generic_calibrate_decr, .progress = rtas_progress, .system_reset_exception = pSeries_system_reset_exception, + .machine_check_early = pseries_machine_check_realmode, .machine_check_exception = pSeries_machine_check_exception, #ifdef CONFIG_KEXEC_CORE .machine_kexec = pSeries_machine_kexec, diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 49e04ec19238..88f1ad1d6309 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1349,7 +1349,6 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) struct device_node *parent_node; const __be32 *prop; enum vio_dev_family family; - const char *of_node_name = of_node->name ? of_node->name : "<unknown>"; /* * Determine if this node is a under the /vdevice node or under the @@ -1362,24 +1361,24 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) else if (!strcmp(parent_node->type, "vdevice")) family = VDEVICE; else { - pr_warn("%s: parent(%pOF) of %s not recognized.\n", + pr_warn("%s: parent(%pOF) of %pOFn not recognized.\n", __func__, parent_node, - of_node_name); + of_node); of_node_put(parent_node); return NULL; } of_node_put(parent_node); } else { - pr_warn("%s: could not determine the parent of node %s.\n", - __func__, of_node_name); + pr_warn("%s: could not determine the parent of node %pOFn.\n", + __func__, of_node); return NULL; } if (family == PFO) { if (of_get_property(of_node, "interrupt-controller", NULL)) { - pr_debug("%s: Skipping the interrupt controller %s.\n", - __func__, of_node_name); + pr_debug("%s: Skipping the interrupt controller %pOFn.\n", + __func__, of_node); return NULL; } } @@ -1399,15 +1398,15 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) if (of_node->type != NULL) viodev->type = of_node->type; else { - pr_warn("%s: node %s is missing the 'device_type' " - "property.\n", __func__, of_node_name); + pr_warn("%s: node %pOFn is missing the 'device_type' " + "property.\n", __func__, of_node); goto out; } prop = of_get_property(of_node, "reg", NULL); if (prop == NULL) { - pr_warn("%s: node %s missing 'reg'\n", - __func__, of_node_name); + pr_warn("%s: node %pOFn missing 'reg'\n", + __func__, of_node); goto out; } unit_address = of_read_number(prop, 1); @@ -1422,8 +1421,8 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) if (prop != NULL) viodev->resource_id = of_read_number(prop, 1); - dev_set_name(&viodev->dev, "%s", of_node_name); - viodev->type = of_node_name; + dev_set_name(&viodev->dev, "%pOFn", of_node); + viodev->type = dev_name(&viodev->dev); viodev->irq = 0; } @@ -1694,7 +1693,7 @@ struct vio_dev *vio_find_node(struct device_node *vnode) snprintf(kobj_name, sizeof(kobj_name), "%x", (uint32_t)of_read_number(prop, 1)); } else if (!strcmp(dev_type, "ibm,platform-facilities")) - snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name); + snprintf(kobj_name, sizeof(kobj_name), "%pOFn", vnode); else return NULL; |
