Merge tag 'powerpc-4.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
"Notable changes:

- Support for 4PB user address space on 64-bit, opt-in via mmap().

- Removal of POWER4 support, which was accidentally broken in 2016
and no one noticed, and blocked use of some modern instructions.

- Workarounds so that the hypervisor can enable Transactional Memory
on Power9.

- A series to disable the DAWR (Data Address Watchpoint Register) on
Power9.

- More information displayed in the meltdown/spectre_v1/v2 sysfs
files.

- A vpermxor (Power8 Altivec) implementation for the raid6 Q
Syndrome.

- A big series to make the allocation of our pacas (per cpu area),
kernel page tables, and per-cpu stacks NUMA aware when using the
Radix MMU on Power9.

And as usual many fixes, reworks and cleanups.

Thanks to: Aaro Koskinen, Alexandre Belloni, Alexey Kardashevskiy,
Alistair Popple, Andy Shevchenko, Aneesh Kumar K.V, Anshuman Khandual,
Balbir Singh, Benjamin Herrenschmidt, Christophe Leroy, Christophe
Lombard, Cyril Bur, Daniel Axtens, Dave Young, Finn Thain, Frederic
Barrat, Gustavo Romero, Horia Geantă, Jonathan Neuschäfer, Kees Cook,
Larry Finger, Laurent Dufour, Laurent Vivier, Logan Gunthorpe,
Madhavan Srinivasan, Mark Greer, Mark Hairgrove, Markus Elfring,
Mathieu Malaterre, Matt Brown, Matt Evans, Mauricio Faria de Oliveira,
Michael Neuling, Naveen N. Rao, Nicholas Piggin, Paul Mackerras,
Philippe Bergheaud, Ram Pai, Rob Herring, Sam Bobroff, Segher
Boessenkool, Simon Guo, Simon Horman, Stewart Smith, Sukadev
Bhattiprolu, Suraj Jitindar Singh, Thiago Jung Bauermann, Vaibhav
Jain, Vaidyanathan Srinivasan, Vasant Hegde, Wei Yongjun"

* tag 'powerpc-4.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (207 commits)
powerpc/64s/idle: Fix restore of AMOR on POWER9 after deep sleep
powerpc/64s: Fix POWER9 DD2.2 and above in cputable features
powerpc/64s: Fix pkey support in dt_cpu_ftrs, add CPU_FTR_PKEY bit
powerpc/64s: Fix dt_cpu_ftrs to have restore_cpu clear unwanted LPCR bits
Revert "powerpc/64s/idle: POWER9 ESL=0 stop avoid save/restore overhead"
powerpc: iomap.c: introduce io{read|write}64_{lo_hi|hi_lo}
powerpc: io.h: move iomap.h include so that it can use readq/writeq defs
cxl: Fix possible deadlock when processing page faults from cxllib
powerpc/hw_breakpoint: Only disable hw breakpoint if cpu supports it
powerpc/mm/radix: Update command line parsing for disable_radix
powerpc/mm/radix: Parse disable_radix commandline correctly.
powerpc/mm/hugetlb: initialize the pagetable cache correctly for hugetlb
powerpc/mm/radix: Update pte fragment count from 16 to 256 on radix
powerpc/mm/keys: Update documentation and remove unnecessary check
powerpc/64s/idle: POWER9 ESL=0 stop avoid save/restore overhead
powerpc/64s/idle: Consolidate power9_offline_stop()/power9_idle_stop()
powerpc/powernv: Always stop secondaries before reboot/shutdown
powerpc: hard disable irqs in smp_send_stop loop
powerpc: use NMI IPI for smp_send_stop
powerpc/powernv: Fix SMT4 forcing idle code
...

arch/powerpc/Makefile

···
 endif
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
+
 CFLAGS-$(CONFIG_PPC32)	:= -ffixed-r2 $(MULTIPLEWORD)
+CFLAGS-$(CONFIG_PPC32)	+= $(call cc-option,-mno-readonly-in-sdata)
 
 ifeq ($(CONFIG_PPC_BOOK3S_64),y)
-CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power7,-mtune=power4)
-CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=power4
+ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
+CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=power8
+CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power9,-mtune=power8)
+else
+CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power7,$(call cc-option,-mtune=power5))
+CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mcpu=power5,-mcpu=power4)
+endif
 else
 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64
 endif
···
 endif
 
 CFLAGS-$(CONFIG_CELL_CPU) += $(call cc-option,-mcpu=cell)
-CFLAGS-$(CONFIG_POWER4_CPU) += $(call cc-option,-mcpu=power4)
 CFLAGS-$(CONFIG_POWER5_CPU) += $(call cc-option,-mcpu=power5)
 CFLAGS-$(CONFIG_POWER6_CPU) += $(call cc-option,-mcpu=power6)
 CFLAGS-$(CONFIG_POWER7_CPU) += $(call cc-option,-mcpu=power7)
 CFLAGS-$(CONFIG_POWER8_CPU) += $(call cc-option,-mcpu=power8)
+CFLAGS-$(CONFIG_POWER9_CPU) += $(call cc-option,-mcpu=power9)
 
 # Altivec option not allowed with e500mc64 in GCC.
 ifeq ($(CONFIG_ALTIVEC),y)
···
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
+cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= -Wa,-mpower4
 
 KBUILD_AFLAGS += $(cpu-as-y)
 KBUILD_CFLAGS += $(cpu-as-y)

arch/powerpc/boot/dts/acadia.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 	};
 };

arch/powerpc/boot/dts/adder875-redboot.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &console;
+		stdout-path = &console;
 	};
 };

arch/powerpc/boot/dts/adder875-uboot.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &console;
+		stdout-path = &console;
 	};
 };

arch/powerpc/boot/dts/akebono.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &UART0;
+		stdout-path = &UART0;
 	};
 };

arch/powerpc/boot/dts/amigaone.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/pci@80000000/isa@7/serial@3f8";
+		stdout-path = "/pci@80000000/isa@7/serial@3f8";
 	};
 };

arch/powerpc/boot/dts/asp834x-redboot.dts

···
 
 	chosen {
 		bootargs = "console=ttyS0,38400 root=/dev/mtdblock3 rootfstype=jffs2";
-		linux,stdout-path = &serial0;
+		stdout-path = &serial0;
 	};
 
 };

arch/powerpc/boot/dts/bamboo.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 	};
 };

arch/powerpc/boot/dts/c2k.dts

···
 		};
 	};
 	chosen {
-		linux,stdout-path = &MPSC0;
+		stdout-path = &MPSC0;
 	};
 };

arch/powerpc/boot/dts/currituck.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &UART0;
+		stdout-path = &UART0;
 	};
 };

arch/powerpc/boot/dts/digsy_mtc.dts

···
 			};
 
 			rtc@56 {
-				compatible = "mc,rv3029c2";
+				compatible = "microcrystal,rv3029";
 				reg = <0x56>;
 			};
 

arch/powerpc/boot/dts/ebony.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@40000200";
+		stdout-path = "/plb/opb/serial@40000200";
 	};
 };

arch/powerpc/boot/dts/eiger.dts

···
 
 	};
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600200";
+		stdout-path = "/plb/opb/serial@ef600200";
 	};
 
 };

arch/powerpc/boot/dts/ep405.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 	};
 };

arch/powerpc/boot/dts/fsl/mvme7100.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &serial0;
+		stdout-path = &serial0;
 	};
 };
 

arch/powerpc/boot/dts/fsp2.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@b0020000";
+		stdout-path = "/plb/opb/serial@b0020000";
 		bootargs = "console=ttyS0,115200 rw log_buf_len=32768 debug";
 	};
 };

arch/powerpc/boot/dts/holly.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/tsi109@c0000000/serial@7808";
+		stdout-path = "/tsi109@c0000000/serial@7808";
 	};
 };

arch/powerpc/boot/dts/hotfoot.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &UART0;
+		stdout-path = &UART0;
 	};
 };

arch/powerpc/boot/dts/icon.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@f0000200";
+		stdout-path = "/plb/opb/serial@f0000200";
 	};
 };

arch/powerpc/boot/dts/iss4xx-mpic.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@40000200";
+		stdout-path = "/plb/opb/serial@40000200";
 	};
 };

arch/powerpc/boot/dts/iss4xx.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@40000200";
+		stdout-path = "/plb/opb/serial@40000200";
 	};
 };

arch/powerpc/boot/dts/katmai.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@f0000200";
+		stdout-path = "/plb/opb/serial@f0000200";
 	};
 };

arch/powerpc/boot/dts/klondike.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@50001000";
+		stdout-path = "/plb/opb/serial@50001000";
 	};
 };

arch/powerpc/boot/dts/ksi8560.dts

···
 
 
 	chosen {
-		linux,stdout-path = "/soc/cpm/serial@91a00";
+		stdout-path = "/soc/cpm/serial@91a00";
 	};
 };

arch/powerpc/boot/dts/media5200.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &console;
+		stdout-path = &console;
 	};
 
 	cpus {

arch/powerpc/boot/dts/mpc8272ads.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/soc/cpm/serial@11a00";
+		stdout-path = "/soc/cpm/serial@11a00";
 	};
 };

arch/powerpc/boot/dts/mpc866ads.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/soc/cpm/serial@a80";
+		stdout-path = "/soc/cpm/serial@a80";
 	};
 };

arch/powerpc/boot/dts/mpc885ads.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/soc/cpm/serial@a80";
+		stdout-path = "/soc/cpm/serial@a80";
 	};
 };

arch/powerpc/boot/dts/mvme5100.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &serial0;
+		stdout-path = &serial0;
         };
 
 };

arch/powerpc/boot/dts/obs600.dts

···
 		};
 	};
         chosen {
-                linux,stdout-path = "/plb/opb/serial@ef600200";
+                stdout-path = "/plb/opb/serial@ef600200";
         };
 };

arch/powerpc/boot/dts/pq2fads.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/soc/cpm/serial@11a00";
+		stdout-path = "/soc/cpm/serial@11a00";
 	};
 };

arch/powerpc/boot/dts/rainier.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 		bootargs = "console=ttyS0,115200";
 	};
 };

arch/powerpc/boot/dts/redwood.dts

···
 
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600200";
+		stdout-path = "/plb/opb/serial@ef600200";
 	};
 
 };

arch/powerpc/boot/dts/sam440ep.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 	};
 };

arch/powerpc/boot/dts/sequoia.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 		bootargs = "console=ttyS0,115200";
 	};
 };

arch/powerpc/boot/dts/storcenter.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = &serial0;
+		stdout-path = &serial0;
 	};
 };

arch/powerpc/boot/dts/taishan.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@40000300";
+		stdout-path = "/plb/opb/serial@40000300";
 	};
 };

arch/powerpc/boot/dts/virtex440-ml507.dts

···
 	} ;
 	chosen {
 		bootargs = "console=ttyS0 root=/dev/ram";
-		linux,stdout-path = &RS232_Uart_1;
+		stdout-path = &RS232_Uart_1;
 	} ;
 	cpus {
 		#address-cells = <1>;

arch/powerpc/boot/dts/virtex440-ml510.dts

···
 	} ;
 	chosen {
 		bootargs = "console=ttyS0 root=/dev/ram";
-		linux,stdout-path = "/plb@0/serial@83e00000";
+		stdout-path = "/plb@0/serial@83e00000";
 	} ;
 	cpus {
 		#address-cells = <1>;

arch/powerpc/boot/dts/walnut.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 	};
 };

arch/powerpc/boot/dts/warp.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 	};
 };

arch/powerpc/boot/dts/wii.dts

···
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 
 /*
  * This is commented-out for now.
···
 			compatible = "nintendo,hollywood-gpio";
 			reg = <0x0d8000c0 0x40>;
 			gpio-controller;
+			ngpios = <24>;
+
+			gpio-line-names =
+				"POWER", "SHUTDOWN", "FAN", "DC_DC",
+				"DI_SPIN", "SLOT_LED", "EJECT_BTN", "SLOT_IN",
+				"SENSOR_BAR", "DO_EJECT", "EEP_CS", "EEP_CLK",
+				"EEP_MOSI", "EEP_MISO", "AVE_SCL", "AVE_SDA",
+				"DEBUG0", "DEBUG1", "DEBUG2", "DEBUG3",
+				"DEBUG4", "DEBUG5", "DEBUG6", "DEBUG7";
 
 			/*
 			 * This is commented out while a standard binding
···
 			compatible = "nintendo,hollywood-di";
 			reg = <0x0d806000 0x40>;
 			interrupts = <2>;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		/* This is the blue LED in the disk drive slot */
+		drive-slot {
+			label = "wii:blue:drive_slot";
+			gpios = <&GPIO 5 GPIO_ACTIVE_HIGH>;
+			panic-indicator;
 		};
 	};
 };

arch/powerpc/boot/dts/xpedite5200_xmon.dts

···
 
 	/* Needed for dtbImage boot wrapper compatibility */
 	chosen {
-		linux,stdout-path = &serial0;
+		stdout-path = &serial0;
 	};
 };

arch/powerpc/boot/dts/yosemite.dts

···
 	};
 
 	chosen {
-		linux,stdout-path = "/plb/opb/serial@ef600300";
+		stdout-path = "/plb/opb/serial@ef600300";
 	};
 };

arch/powerpc/boot/libfdt_env.h

···
 
 #include "of.h"
 
-typedef u32 uint32_t;
-typedef u64 uint64_t;
 typedef unsigned long uintptr_t;
 
 typedef __be16 fdt16_t;

arch/powerpc/include/asm/asm-prototypes.h

···
 void single_step_exception(struct pt_regs *regs);
 void program_check_exception(struct pt_regs *regs);
 void alignment_exception(struct pt_regs *regs);
+void slb_miss_bad_addr(struct pt_regs *regs);
 void StackOverflow(struct pt_regs *regs);
 void nonrecoverable_exception(struct pt_regs *regs);
 void kernel_fp_unavailable_exception(struct pt_regs *regs);
···
 long sys_swapcontext(struct ucontext __user *old_ctx,
 		    struct ucontext __user *new_ctx,
 		    int ctx_size, int r6, int r7, int r8, struct pt_regs *regs);
+int sys_debug_setcontext(struct ucontext __user *ctx,
+			 int ndbg, struct sig_dbg_op __user *dbg,
+			 int r6, int r7, int r8,
+			 struct pt_regs *regs);
+int
+ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp);
+unsigned long __init early_init(unsigned long dt_ptr);
+void __init machine_init(u64 dt_ptr);
 #endif
+
+long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
+		      u32 len_high, u32 len_low);
 long sys_switch_endian(void);
 notrace unsigned int __check_irq_replay(void);
 void notrace restore_interrupts(void);
···
 /* tracing */
 void _mcount(void);
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
+
+void pnv_power9_force_smt4_catch(void);
+void pnv_power9_force_smt4_release(void);
 
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */

arch/powerpc/include/asm/barrier.h

···
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 
-#ifdef __SUBARCH_HAS_LWSYNC
+/* The sub-arch has lwsync */
+#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
 #    define SMPWMB      LWSYNC
 #else
 #    define SMPWMB      eieio

arch/powerpc/include/asm/book3s/64/hash-4k.h

···
 #define H_PUD_INDEX_SIZE  9
 #define H_PGD_INDEX_SIZE  9
 
+/*
+ * Each context is 512TB. But on 4k we restrict our max TASK size to 64TB
+ * Hence also limit max EA bits to 64TB.
+ */
+#define MAX_EA_BITS_PER_CONTEXT		46
+
 #ifndef __ASSEMBLY__
 #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
 #define H_PMD_TABLE_SIZE	(sizeof(pmd_t) << H_PMD_INDEX_SIZE)
···
 #define H_PAGE_COMBO	0x0
 #define H_PTE_FRAG_NR	0
 #define H_PTE_FRAG_SIZE_SHIFT  0
+
+/* memory key bits, only 8 keys supported */
+#define H_PTE_PKEY_BIT0	0
+#define H_PTE_PKEY_BIT1	0
+#define H_PTE_PKEY_BIT2	_RPAGE_RSV3
+#define H_PTE_PKEY_BIT3	_RPAGE_RSV4
+#define H_PTE_PKEY_BIT4	_RPAGE_RSV5
+
 /*
  * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range()
  */

arch/powerpc/include/asm/book3s/64/hash-64k.h

···
 
 #define H_PTE_INDEX_SIZE  8
 #define H_PMD_INDEX_SIZE  10
-#define H_PUD_INDEX_SIZE  7
+#define H_PUD_INDEX_SIZE  10
 #define H_PGD_INDEX_SIZE  8
+
+/*
+ * Each context is 512TB size. SLB miss for first context/default context
+ * is handled in the hotpath.
+ */
+#define MAX_EA_BITS_PER_CONTEXT		49
 
 /*
  * 64k aligned address free up few of the lower bits of RPN for us
···
 #define H_PAGE_BUSY	_RPAGE_RPN44     /* software: PTE & hash are busy */
 #define H_PAGE_HASHPTE	_RPAGE_RPN43	/* PTE has associated HPTE */
 
+/* memory key bits. */
+#define H_PTE_PKEY_BIT0	_RPAGE_RSV1
+#define H_PTE_PKEY_BIT1	_RPAGE_RSV2
+#define H_PTE_PKEY_BIT2	_RPAGE_RSV3
+#define H_PTE_PKEY_BIT3	_RPAGE_RSV4
+#define H_PTE_PKEY_BIT4	_RPAGE_RSV5
+
 /*
  * We need to differentiate between explicit huge page and THP huge
  * page, since THP huge page also need to track real subpage details
···
 /* PTE flags to conserve for HPTE identification */
 #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | H_PAGE_COMBO)
 /*
- * we support 16 fragments per PTE page of 64K size.
- */
-#define H_PTE_FRAG_NR	16
-/*
  * We use a 2K PTE page fragment and another 2K for storing
  * real_pte_t hash index
+ * 8 bytes per each pte entry and another 8 bytes for storing
+ * slot details.
  */
-#define H_PTE_FRAG_SIZE_SHIFT  12
-#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT)
+#define H_PTE_FRAG_SIZE_SHIFT  (H_PTE_INDEX_SIZE + 3 + 1)
+#define H_PTE_FRAG_NR	(PAGE_SIZE >> H_PTE_FRAG_SIZE_SHIFT)
 
 #ifndef __ASSEMBLY__
 #include <asm/errno.h>

arch/powerpc/include/asm/book3s/64/hash.h

···
 extern void hash__vmemmap_remove_mapping(unsigned long start,
 				     unsigned long page_size);
 
-int hash__create_section_mapping(unsigned long start, unsigned long end);
+int hash__create_section_mapping(unsigned long start, unsigned long end, int nid);
 int hash__remove_section_mapping(unsigned long start, unsigned long end);
 
 #endif /* !__ASSEMBLY__ */

arch/powerpc/include/asm/book3s/64/mmu.h

···
 /* Maximum possible number of NPUs in a system. */
 #define NV_MAX_NPUS 8
 
+/*
+ * One bit per slice. We have lower slices which cover 256MB segments
+ * upto 4G range. That gets us 16 low slices. For the rest we track slices
+ * in 1TB size.
+ */
+struct slice_mask {
+	u64 low_slices;
+	DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
+};
+
 typedef struct {
-	mm_context_id_t id;
+	union {
+		/*
+		 * We use id as the PIDR content for radix. On hash we can use
+		 * more than one id. The extended ids are used when we start
+		 * having address above 512TB. We allocate one extended id
+		 * for each 512TB. The new id is then used with the 49 bit
+		 * EA to build a new VA. We always use ESID_BITS_1T_MASK bits
+		 * from EA and new context ids to build the new VAs.
+		 */
+		mm_context_id_t id;
+		mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE];
+	};
 	u16 user_psize;		/* page size index */
 
 	/* Number of bits in the mm_cpumask */
···
 	struct npu_context *npu_context;
 
 #ifdef CONFIG_PPC_MM_SLICES
-	u64 low_slices_psize;	/* SLB page size encodings */
+	 /* SLB page size encodings*/
+	unsigned char low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE];
 	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
 	unsigned long slb_addr_limit;
+# ifdef CONFIG_PPC_64K_PAGES
+	struct slice_mask mask_64k;
+# endif
+	struct slice_mask mask_4k;
+# ifdef CONFIG_HUGETLB_PAGE
+	struct slice_mask mask_16m;
+	struct slice_mask mask_16g;
+# endif
 #else
 	u16 sllp;		/* SLB page size encoding */
 #endif
···
 #else
 static inline void radix_init_pseries(void) { };
 #endif
+
+static inline int get_ea_context(mm_context_t *ctx, unsigned long ea)
+{
+	int index = ea >> MAX_EA_BITS_PER_CONTEXT;
+
+	if (likely(index < ARRAY_SIZE(ctx->extended_id)))
+		return ctx->extended_id[index];
+
+	/* should never happen */
+	WARN_ON(1);
+	return 0;
+}
+
+static inline unsigned long get_user_vsid(mm_context_t *ctx,
+					  unsigned long ea, int ssize)
+{
+	unsigned long context = get_ea_context(ctx, ea);
+
+	return get_vsid(context, ea, ssize);
+}
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */

arch/powerpc/include/asm/book3s/64/pgalloc.h

···
 
 	pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
 			       pgtable_gfp_flags(mm, GFP_KERNEL));
+	/*
+	 * With hugetlb, we don't clear the second half of the page table.
+	 * If we share the same slab cache with the pmd or pud level table,
+	 * we need to make sure we zero out the full table on alloc.
+	 * With 4K we don't store slot in the second half. Hence we don't
+	 * need to do this for 4k.
+	 */
+#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) && \
+	((H_PGD_INDEX_SIZE == H_PUD_CACHE_INDEX) ||		     \
+	 (H_PGD_INDEX_SIZE == H_PMD_CACHE_INDEX))
 	memset(pgd, 0, PGD_TABLE_SIZE);
-
+#endif
 	return pgd;
 }
 

arch/powerpc/include/asm/book3s/64/pgtable.h

···
 /* Max physical address bit as per radix table */
 #define _RPAGE_PA_MAX		57
 
-#ifdef CONFIG_PPC_MEM_KEYS
-#ifdef CONFIG_PPC_64K_PAGES
-#define H_PTE_PKEY_BIT0	_RPAGE_RSV1
-#define H_PTE_PKEY_BIT1	_RPAGE_RSV2
-#else /* CONFIG_PPC_64K_PAGES */
-#define H_PTE_PKEY_BIT0	0 /* _RPAGE_RSV1 is not available */
-#define H_PTE_PKEY_BIT1	0 /* _RPAGE_RSV2 is not available */
-#endif /* CONFIG_PPC_64K_PAGES */
-#define H_PTE_PKEY_BIT2	_RPAGE_RSV3
-#define H_PTE_PKEY_BIT3	_RPAGE_RSV4
-#define H_PTE_PKEY_BIT4	_RPAGE_RSV5
-#else /*  CONFIG_PPC_MEM_KEYS */
-#define H_PTE_PKEY_BIT0	0
-#define H_PTE_PKEY_BIT1	0
-#define H_PTE_PKEY_BIT2	0
-#define H_PTE_PKEY_BIT3	0
-#define H_PTE_PKEY_BIT4	0
-#endif /*  CONFIG_PPC_MEM_KEYS */
-
 /*
  * Max physical address bit we will use for now.
  *

arch/powerpc/include/asm/book3s/64/radix-4k.h

···
 #define RADIX_PMD_INDEX_SIZE  9  /* 1G huge page */
 #define RADIX_PUD_INDEX_SIZE	 9
 #define RADIX_PGD_INDEX_SIZE  13
+/*
+ * One fragment per per page
+ */
+#define RADIX_PTE_FRAG_SIZE_SHIFT  (RADIX_PTE_INDEX_SIZE + 3)
+#define RADIX_PTE_FRAG_NR	(PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT)
 
 #endif /* _ASM_POWERPC_PGTABLE_RADIX_4K_H */

arch/powerpc/include/asm/book3s/64/radix-64k.h

···
 #define RADIX_PUD_INDEX_SIZE	 9
 #define RADIX_PGD_INDEX_SIZE  13
 
+/*
+ * We use a 256 byte PTE page fragment in radix
+ * 8 bytes per each PTE entry.
+ */
+#define RADIX_PTE_FRAG_SIZE_SHIFT  (RADIX_PTE_INDEX_SIZE + 3)
+#define RADIX_PTE_FRAG_NR	(PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT)
 #endif /* _ASM_POWERPC_PGTABLE_RADIX_64K_H */

arch/powerpc/include/asm/book3s/64/radix.h

···
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int radix__create_section_mapping(unsigned long start, unsigned long end);
+int radix__create_section_mapping(unsigned long start, unsigned long end, int nid);
 int radix__remove_section_mapping(unsigned long start, unsigned long end);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 #endif /* __ASSEMBLY__ */

arch/powerpc/include/asm/book3s/64/slice.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H
+#define _ASM_POWERPC_BOOK3S_64_SLICE_H
+
+#ifdef CONFIG_PPC_MM_SLICES
+
+#define SLICE_LOW_SHIFT		28
+#define SLICE_LOW_TOP		(0x100000000ul)
+#define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
+#define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)
+
+#define SLICE_HIGH_SHIFT	40
+#define SLICE_NUM_HIGH		(H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT)
+#define GET_HIGH_SLICE_INDEX(addr)	((addr) >> SLICE_HIGH_SHIFT)
+
+#else /* CONFIG_PPC_MM_SLICES */
+
+#define get_slice_psize(mm, addr)	((mm)->context.user_psize)
+#define slice_set_user_psize(mm, psize)		\
+do {						\
+	(mm)->context.user_psize = (psize);	\
+	(mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \
+} while (0)
+
+#endif /* CONFIG_PPC_MM_SLICES */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */

arch/powerpc/include/asm/cacheflush.h

···
 #ifdef CONFIG_PPC64
 extern void flush_dcache_range(unsigned long start, unsigned long stop);
 extern void flush_inval_dcache_range(unsigned long start, unsigned long stop);
-extern void flush_dcache_phys_range(unsigned long start, unsigned long stop);
 #endif
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \

arch/powerpc/include/asm/cputable.h

···
 
 /* CPU kernel features */
 
-/* Retain the 32b definitions all use bottom half of word */
+/* Definitions for features that we have on both 32-bit and 64-bit chips */
 #define CPU_FTR_COHERENT_ICACHE		ASM_CONST(0x00000001)
-#define CPU_FTR_L2CR			ASM_CONST(0x00000002)
-#define CPU_FTR_SPEC7450		ASM_CONST(0x00000004)
-#define CPU_FTR_ALTIVEC			ASM_CONST(0x00000008)
-#define CPU_FTR_TAU			ASM_CONST(0x00000010)
-#define CPU_FTR_CAN_DOZE		ASM_CONST(0x00000020)
-#define CPU_FTR_USE_TB			ASM_CONST(0x00000040)
-#define CPU_FTR_L2CSR			ASM_CONST(0x00000080)
-#define CPU_FTR_601			ASM_CONST(0x00000100)
-#define CPU_FTR_DBELL			ASM_CONST(0x00000200)
-#define CPU_FTR_CAN_NAP			ASM_CONST(0x00000400)
-#define CPU_FTR_L3CR			ASM_CONST(0x00000800)
-#define CPU_FTR_L3_DISABLE_NAP		ASM_CONST(0x00001000)
-#define CPU_FTR_NAP_DISABLE_L2_PR	ASM_CONST(0x00002000)
-#define CPU_FTR_DUAL_PLL_750FX		ASM_CONST(0x00004000)
-#define CPU_FTR_NO_DPM			ASM_CONST(0x00008000)
-#define CPU_FTR_476_DD2			ASM_CONST(0x00010000)
-#define CPU_FTR_NEED_COHERENT		ASM_CONST(0x00020000)
-#define CPU_FTR_NO_BTIC			ASM_CONST(0x00040000)
-#define CPU_FTR_DEBUG_LVL_EXC		ASM_CONST(0x00080000)
-#define CPU_FTR_NODSISRALIGN		ASM_CONST(0x00100000)
-#define CPU_FTR_PPC_LE			ASM_CONST(0x00200000)
-#define CPU_FTR_REAL_LE			ASM_CONST(0x00400000)
-#define CPU_FTR_FPU_UNAVAILABLE		ASM_CONST(0x00800000)
-#define CPU_FTR_UNIFIED_ID_CACHE	ASM_CONST(0x01000000)
-#define CPU_FTR_SPE			ASM_CONST(0x02000000)
-#define CPU_FTR_NEED_PAIRED_STWCX	ASM_CONST(0x04000000)
-#define CPU_FTR_LWSYNC			ASM_CONST(0x08000000)
-#define CPU_FTR_NOEXECUTE		ASM_CONST(0x10000000)
-#define CPU_FTR_INDEXED_DCR		ASM_CONST(0x20000000)
-#define CPU_FTR_EMB_HV			ASM_CONST(0x40000000)
+#define CPU_FTR_ALTIVEC			ASM_CONST(0x00000002)
+#define CPU_FTR_DBELL			ASM_CONST(0x00000004)
+#define CPU_FTR_CAN_NAP			ASM_CONST(0x00000008)
+#define CPU_FTR_DEBUG_LVL_EXC		ASM_CONST(0x00000010)
+#define CPU_FTR_NODSISRALIGN		ASM_CONST(0x00000020)
+#define CPU_FTR_FPU_UNAVAILABLE		ASM_CONST(0x00000040)
+#define CPU_FTR_LWSYNC			ASM_CONST(0x00000080)
+#define CPU_FTR_NOEXECUTE		ASM_CONST(0x00000100)
+#define CPU_FTR_EMB_HV			ASM_CONST(0x00000200)
+
+/* Definitions for features that only exist on 32-bit chips */
+#ifdef CONFIG_PPC32
+#define CPU_FTR_601			ASM_CONST(0x00001000)
+#define CPU_FTR_L2CR			ASM_CONST(0x00002000)
+#define CPU_FTR_SPEC7450		ASM_CONST(0x00004000)
+#define CPU_FTR_TAU			ASM_CONST(0x00008000)
+#define CPU_FTR_CAN_DOZE		ASM_CONST(0x00010000)
+#define CPU_FTR_USE_RTC			ASM_CONST(0x00020000)
+#define CPU_FTR_L3CR			ASM_CONST(0x00040000)
+#define CPU_FTR_L3_DISABLE_NAP		ASM_CONST(0x00080000)
+#define CPU_FTR_NAP_DISABLE_L2_PR	ASM_CONST(0x00100000)
+#define CPU_FTR_DUAL_PLL_750FX		ASM_CONST(0x00200000)
+#define CPU_FTR_NO_DPM			ASM_CONST(0x00400000)
+#define CPU_FTR_476_DD2			ASM_CONST(0x00800000)
+#define CPU_FTR_NEED_COHERENT		ASM_CONST(0x01000000)
+#define CPU_FTR_NO_BTIC			ASM_CONST(0x02000000)
+#define CPU_FTR_PPC_LE			ASM_CONST(0x04000000)
+#define CPU_FTR_UNIFIED_ID_CACHE	ASM_CONST(0x08000000)
+#define CPU_FTR_SPE			ASM_CONST(0x10000000)
+#define CPU_FTR_NEED_PAIRED_STWCX	ASM_CONST(0x20000000)
+#define CPU_FTR_INDEXED_DCR		ASM_CONST(0x40000000)
+
+#else	/* CONFIG_PPC32 */
+/* Define these to 0 for the sake of tests in common code */
+#define CPU_FTR_601			(0)
+#define CPU_FTR_PPC_LE			(0)
+#endif
 
 /*
- * Add the 64-bit processor unique features in the top half of the word;
+ * Definitions for the 64-bit processor unique features;
  * on 32-bit, make the names available but defined to be 0.
  */
 #ifdef __powerpc64__
···
 #define LONG_ASM_CONST(x)		0
 #endif
 
-#define CPU_FTR_HVMODE			LONG_ASM_CONST(0x0000000100000000)
-#define CPU_FTR_ARCH_201		LONG_ASM_CONST(0x0000000200000000)
-#define CPU_FTR_ARCH_206		LONG_ASM_CONST(0x0000000400000000)
-#define CPU_FTR_ARCH_207S		LONG_ASM_CONST(0x0000000800000000)
-#define CPU_FTR_ARCH_300		LONG_ASM_CONST(0x0000001000000000)
-#define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000002000000000)
-#define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000004000000000)
-#define CPU_FTR_SMT			LONG_ASM_CONST(0x0000008000000000)
-#define CPU_FTR_PAUSE_ZERO		LONG_ASM_CONST(0x0000010000000000)
-#define CPU_FTR_PURR			LONG_ASM_CONST(0x0000020000000000)
-#define CPU_FTR_CELL_TB_BUG		LONG_ASM_CONST(0x0000040000000000)
-#define CPU_FTR_SPURR			LONG_ASM_CONST(0x0000080000000000)
-#define CPU_FTR_DSCR			LONG_ASM_CONST(0x0000100000000000)
-#define CPU_FTR_VSX			LONG_ASM_CONST(0x0000200000000000)
-#define CPU_FTR_SAO			LONG_ASM_CONST(0x0000400000000000)
-#define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0000800000000000)
-#define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0001000000000000)
-#define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0002000000000000)
-#define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0004000000000000)
-#define CPU_FTR_POPCNTB			LONG_ASM_CONST(0x0008000000000000)
-#define CPU_FTR_POPCNTD			LONG_ASM_CONST(0x0010000000000000)
-#define CPU_FTR_PKEY			LONG_ASM_CONST(0x0020000000000000)
-#define CPU_FTR_VMX_COPY		LONG_ASM_CONST(0x0040000000000000)
-#define CPU_FTR_TM			LONG_ASM_CONST(0x0080000000000000)
-#define CPU_FTR_CFAR			LONG_ASM_CONST(0x0100000000000000)
-#define	CPU_FTR_HAS_PPR			LONG_ASM_CONST(0x0200000000000000)
-#define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
-#define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
-#define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x1000000000000000)
-#define CPU_FTR_P9_TLBIE_BUG		LONG_ASM_CONST(0x2000000000000000)
-#define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x4000000000000000)
-#define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x8000000000000000)
+#define CPU_FTR_REAL_LE			LONG_ASM_CONST(0x0000000000001000)
+#define CPU_FTR_HVMODE			LONG_ASM_CONST(0x0000000000002000)
+#define CPU_FTR_ARCH_206		LONG_ASM_CONST(0x0000000000008000)
+#define CPU_FTR_ARCH_207S		LONG_ASM_CONST(0x0000000000010000)
+#define CPU_FTR_ARCH_300		LONG_ASM_CONST(0x0000000000020000)
+#define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000000000040000)
+#define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000000000080000)
+#define CPU_FTR_SMT			LONG_ASM_CONST(0x0000000000100000)
+#define CPU_FTR_PAUSE_ZERO		LONG_ASM_CONST(0x0000000000200000)
+#define CPU_FTR_PURR			LONG_ASM_CONST(0x0000000000400000)
+#define CPU_FTR_CELL_TB_BUG		LONG_ASM_CONST(0x0000000000800000)
+#define CPU_FTR_SPURR			LONG_ASM_CONST(0x0000000001000000)
+#define CPU_FTR_DSCR			LONG_ASM_CONST(0x0000000002000000)
+#define CPU_FTR_VSX			LONG_ASM_CONST(0x0000000004000000)
+#define CPU_FTR_SAO			LONG_ASM_CONST(0x0000000008000000)
+#define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0000000010000000)
+#define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0000000020000000)
+#define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0000000040000000)
+#define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0000000080000000)
+#define CPU_FTR_POPCNTB			LONG_ASM_CONST(0x0000000100000000)
+#define CPU_FTR_POPCNTD			LONG_ASM_CONST(0x0000000200000000)
+#define CPU_FTR_PKEY			LONG_ASM_CONST(0x0000000400000000)
+#define CPU_FTR_VMX_COPY		LONG_ASM_CONST(0x0000000800000000)
+#define CPU_FTR_TM			LONG_ASM_CONST(0x0000001000000000)
+#define CPU_FTR_CFAR			LONG_ASM_CONST(0x0000002000000000)
+#define	CPU_FTR_HAS_PPR			LONG_ASM_CONST(0x0000004000000000)
+#define CPU_FTR_DAWR			LONG_ASM_CONST(0x0000008000000000)
+#define CPU_FTR_DABRX			LONG_ASM_CONST(0x0000010000000000)
+#define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x0000020000000000)
+#define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x0000040000000000)
+#define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x0000080000000000)
+#define CPU_FTR_P9_TM_HV_ASSIST		LONG_ASM_CONST(0x0000100000000000)
+#define CPU_FTR_P9_TM_XER_SO_BUG	LONG_ASM_CONST(0x0000200000000000)
+#define CPU_FTR_P9_TLBIE_BUG		LONG_ASM_CONST(0x0000400000000000)
 
 #ifndef __ASSEMBLY__
 
···
 #endif
 
 #define CPU_FTRS_PPC601	(CPU_FTR_COMMON | CPU_FTR_601 | \
-	CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE)
-#define CPU_FTRS_603	(CPU_FTR_COMMON | \
-	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
+	CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_USE_RTC)
+#define CPU_FTRS_603	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
-#define CPU_FTRS_604	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | CPU_FTR_PPC_LE)
+#define CPU_FTRS_604	(CPU_FTR_COMMON | CPU_FTR_PPC_LE)
 #define CPU_FTRS_740_NOTAU	(CPU_FTR_COMMON | \
-	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_740	(CPU_FTR_COMMON | \
-	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
 	    CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_PPC_LE)
 #define CPU_FTRS_750	(CPU_FTR_COMMON | \
-	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
 	    CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_PPC_LE)
 #define CPU_FTRS_750CL	(CPU_FTRS_750)
···
 #define CPU_FTRS_750FX	(CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX)
 #define CPU_FTRS_750GX	(CPU_FTRS_750FX)
 #define CPU_FTRS_7400_NOTAU	(CPU_FTR_COMMON | \
-	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
 	    CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7400	(CPU_FTR_COMMON | \
-	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
 	    CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7450_20	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7450_21	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
 	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7450_23	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
+	    CPU_FTR_NEED_PAIRED_STWCX | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
 	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455_1	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
+	    CPU_FTR_NEED_PAIRED_STWCX | \
 	    CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR | \
 	    CPU_FTR_SPEC7450 | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455_20	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
+	    CPU_FTR_NEED_PAIRED_STWCX | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
 	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447_10	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_NO_BTIC | CPU_FTR_PPC_LE | \
 	    CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447A	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7448	(CPU_FTR_COMMON | \
-	    CPU_FTR_USE_TB | \
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
-#define CPU_FTRS_82XX	(CPU_FTR_COMMON | \
-	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB)
+#define CPU_FTRS_82XX	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE)
 #define CPU_FTRS_G2_LE	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
-	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP)
+	    CPU_FTR_MAYBE_CAN_NAP)
 #define CPU_FTRS_E300	(CPU_FTR_MAYBE_CAN_DOZE | \
-	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_COMMON)
 #define CPU_FTRS_E300C2	(CPU_FTR_MAYBE_CAN_DOZE | \
-	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE)
-#define CPU_FTRS_CLASSIC32	(CPU_FTR_COMMON | CPU_FTR_USE_TB)
-#define CPU_FTRS_8XX	(CPU_FTR_USE_TB | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_40X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_44X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_440x6	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \
+#define CPU_FTRS_CLASSIC32	(CPU_FTR_COMMON)
+#define CPU_FTRS_8XX	(CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_40X	(CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_44X	(CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_440x6	(CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_INDEXED_DCR)
 #define CPU_FTRS_47X	(CPU_FTRS_440x6)
-#define CPU_FTRS_E200	(CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \
+#define CPU_FTRS_E200	(CPU_FTR_SPE_COMP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DEBUG_LVL_EXC)
-#define CPU_FTRS_E500	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
+#define CPU_FTRS_E500	(CPU_FTR_MAYBE_CAN_DOZE | \
 	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_E500_2	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
+#define CPU_FTRS_E500_2	(CPU_FTR_MAYBE_CAN_DOZE | \
 	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_E500MC	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
-	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+#define CPU_FTRS_E500MC	(CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
 /*
  * e5500/e6500 erratum A-006958 is a timebase bug that can use the
  * same workaround as CPU_FTR_CELL_TB_BUG.
  */
-#define CPU_FTRS_E5500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
-	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+#define CPU_FTRS_E5500	(CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_CELL_TB_BUG)
-#define CPU_FTRS_E6500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
-	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+#define CPU_FTRS_E6500	(CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_CELL_TB_BUG | CPU_FTR_SMT)
 #define CPU_FTRS_GENERIC_32	(CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
-#define CPU_FTRS_POWER4	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+#define CPU_FTRS_PPC970	(CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
-	    CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS)
-#define CPU_FTRS_PPC970	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_201 | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
 	    CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS | \
 	    CPU_FTR_HVMODE | CPU_FTR_DABRX)
-#define CPU_FTRS_POWER5	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+#define CPU_FTRS_POWER5	(CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_PURR | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_DABRX)
-#define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+#define CPU_FTRS_POWER6 (CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
···
 	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR | \
 	    CPU_FTR_DABRX)
-#define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+#define CPU_FTRS_POWER7 (CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
···
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | \
 	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX | CPU_FTR_PKEY)
-#define CPU_FTRS_POWER8 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+#define CPU_FTRS_POWER8 (CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
···
 	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_PKEY)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
 #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
-#define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+#define CPU_FTRS_POWER9 (CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
···
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
-	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
-	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \
-	    CPU_FTR_PKEY | CPU_FTR_P9_TLBIE_BUG)
+	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
+	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \
+	    CPU_FTR_P9_TLBIE_BUG)
 #define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
 			     (~CPU_FTR_SAO))
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
 #define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1)
-#define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+#define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \
+			       CPU_FTR_P9_TM_HV_ASSIST | \
+			       CPU_FTR_P9_TM_XER_SO_BUG)
+#define CPU_FTRS_CELL	(CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_PAUSE_ZERO  | CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
 	    CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_DABRX)
-#define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+#define CPU_FTRS_PA6T (CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_DABRX)
-#define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
+#define CPU_FTRS_COMPATIBLE	(CPU_FTR_PPCAS_ARCH_V2)
 
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
 #define CPU_FTRS_POSSIBLE	(CPU_FTRS_E6500 | CPU_FTRS_E5500)
 #else
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
 #define CPU_FTRS_POSSIBLE	\
-	    (CPU_FTRS_POWER4 | CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
+	    (CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \
+	     CPU_FTRS_POWER8_DD1 | CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | \
+	     CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \
+	     CPU_FTRS_POWER9_DD2_2)
+#else
+#define CPU_FTRS_POSSIBLE	\
+	    (CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
 	     CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \
 	     CPU_FTRS_POWER8 | CPU_FTRS_POWER8_DD1 | CPU_FTRS_CELL | \
-	     CPU_FTRS_PA6T | CPU_FTR_VSX | CPU_FTRS_POWER9 | \
-	     CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1)
+	     CPU_FTRS_PA6T | CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | \
+	     CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \
+	     CPU_FTRS_POWER9_DD2_2)
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else
 enum {
···
 #ifdef CONFIG_PPC_BOOK3E
 #define CPU_FTRS_ALWAYS		(CPU_FTRS_E6500 & CPU_FTRS_E5500)
 #else
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define CPU_FTRS_ALWAYS \
+	    (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & CPU_FTRS_POWER7 & \
+	     CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & CPU_FTRS_POWER8_DD1 & \
+	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD1 & CPU_FTRS_POWER9_DD2_1)
+#else
 #define CPU_FTRS_ALWAYS		\
-	    (CPU_FTRS_POWER4 & CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
+	    (CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
 	     CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \
 	     CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
 	     CPU_FTRS_POWER8_DD1 & ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & \
-	     CPU_FTRS_POWER9)
+	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD1 & CPU_FTRS_POWER9_DD2_1)
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else
 enum {

arch/powerpc/include/asm/debug.h

···
 
 void set_breakpoint(struct arch_hw_breakpoint *brk);
 void __set_breakpoint(struct arch_hw_breakpoint *brk);
+bool ppc_breakpoint_available(void);
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 extern void do_send_trap(struct pt_regs *regs, unsigned long address,
 			 unsigned long error_code, int brkpt);

arch/powerpc/include/asm/eeh.h

···
 	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
 }
 
+static inline bool eeh_state_active(int state)
+{
+	return (state & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE))
+	== (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+}
+
 typedef void *(*eeh_traverse_func)(void *data, void *flag);
 void eeh_set_pe_aux_size(int size);
 int eeh_phb_pe_create(struct pci_controller *phb);

arch/powerpc/include/asm/eeh_event.h

···
 int eeh_event_init(void);
 int eeh_send_failure_event(struct eeh_pe *pe);
 void eeh_remove_event(struct eeh_pe *pe, bool force);
-void eeh_handle_event(struct eeh_pe *pe);
+void eeh_handle_normal_event(struct eeh_pe *pe);
+void eeh_handle_special_event(void);
 
 #endif /* __KERNEL__ */
 #endif /* ASM_POWERPC_EEH_EVENT_H */

arch/powerpc/include/asm/epapr_hcalls.h

···
 			    unsigned long *out,
 			    unsigned long nr)
 {
-	unsigned long register r0 asm("r0");
-	unsigned long register r3 asm("r3") = in[0];
-	unsigned long register r4 asm("r4") = in[1];
-	unsigned long register r5 asm("r5") = in[2];
-	unsigned long register r6 asm("r6") = in[3];
-	unsigned long register r7 asm("r7") = in[4];
-	unsigned long register r8 asm("r8") = in[5];
-	unsigned long register r9 asm("r9") = in[6];
-	unsigned long register r10 asm("r10") = in[7];
-	unsigned long register r11 asm("r11") = nr;
-	unsigned long register r12 asm("r12");
+	register unsigned long r0 asm("r0");
+	register unsigned long r3 asm("r3") = in[0];
+	register unsigned long r4 asm("r4") = in[1];
+	register unsigned long r5 asm("r5") = in[2];
+	register unsigned long r6 asm("r6") = in[3];
+	register unsigned long r7 asm("r7") = in[4];
+	register unsigned long r8 asm("r8") = in[5];
+	register unsigned long r9 asm("r9") = in[6];
+	register unsigned long r10 asm("r10") = in[7];
+	register unsigned long r11 asm("r11") = nr;
+	register unsigned long r12 asm("r12");
 
 	asm volatile("bl	epapr_hypercall_start"
 		     : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),

arch/powerpc/include/asm/hugetlb.h

···
 
 void flush_dcache_icache_hugepage(struct page *page);
 
-#if defined(CONFIG_PPC_MM_SLICES)
-int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
+int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len);
-#else
+
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
 					 unsigned long len)
 {
+	if (IS_ENABLED(CONFIG_PPC_MM_SLICES) && !radix_enabled())
+		return slice_is_hugepage_only_range(mm, addr, len);
 	return 0;
 }
-#endif
 
 void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
 			    pte_t pte);

arch/powerpc/include/asm/hvcall.h

···
 #define H_P8		-61
 #define H_P9		-62
 #define H_TOO_BIG	-64
+#define H_UNSUPPORTED	-67
 #define H_OVERLAP	-68
 #define H_INTERRUPT	-69
 #define H_BAD_DATA	-70
···
 #define H_CPU_CHAR_L1D_FLUSH_ORI30	(1ull << 61) // IBM bit 2
 #define H_CPU_CHAR_L1D_FLUSH_TRIG2	(1ull << 60) // IBM bit 3
 #define H_CPU_CHAR_L1D_THREAD_PRIV	(1ull << 59) // IBM bit 4
+#define H_CPU_CHAR_BRANCH_HINTS_HONORED	(1ull << 58) // IBM bit 5
+#define H_CPU_CHAR_THREAD_RECONFIG_CTRL	(1ull << 57) // IBM bit 6
+#define H_CPU_CHAR_COUNT_CACHE_DISABLED	(1ull << 56) // IBM bit 7
 
 #define H_CPU_BEHAV_FAVOUR_SECURITY	(1ull << 63) // IBM bit 0
 #define H_CPU_BEHAV_L1D_FLUSH_PR	(1ull << 62) // IBM bit 1

arch/powerpc/include/asm/hw_breakpoint.h

···
 						unsigned long val, void *data);
 int arch_install_hw_breakpoint(struct perf_event *bp);
 void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+void arch_unregister_hw_breakpoint(struct perf_event *bp);
 void hw_breakpoint_pmu_read(struct perf_event *bp);
 extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk);
 
···
 	brk.address = 0;
 	brk.type = 0;
 	brk.len = 0;
-	__set_breakpoint(&brk);
+	if (ppc_breakpoint_available())
+		__set_breakpoint(&brk);
 }
 extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs);
+int hw_breakpoint_handler(struct die_args *args);
 
 #else	/* CONFIG_HAVE_HW_BREAKPOINT */
 static inline void hw_breakpoint_disable(void) { }

arch/powerpc/include/asm/io.h

···
 #include <asm/mmu.h>
 #include <asm/ppc_asm.h>
 
-#include <asm-generic/iomap.h>
-
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #endif
···
 #define writew_relaxed(v, addr)	writew(v, addr)
 #define writel_relaxed(v, addr)	writel(v, addr)
 #define writeq_relaxed(v, addr)	writeq(v, addr)
+
+#include <asm-generic/iomap.h>
 
 #ifdef CONFIG_PPC32
 #define mmiowb()

arch/powerpc/include/asm/irq.h

···
 extern void call_do_softirq(struct thread_info *tp);
 extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
 extern void do_IRQ(struct pt_regs *regs);
+extern void __init init_IRQ(void);
 extern void __do_irq(struct pt_regs *regs);
 
 int irq_choose_cpu(const struct cpumask *mask);

arch/powerpc/include/asm/irq_work.h

···
 {
 	return true;
 }
+extern void arch_irq_work_raise(void);
 
 #endif /* _ASM_POWERPC_IRQ_WORK_H */

arch/powerpc/include/asm/kvm_asm.h

···
 
 /* book3s_hv */
 
+#define BOOK3S_INTERRUPT_HV_SOFTPATCH	0x1500
+
 /*
  * Special trap used to indicate to host that this is a
  * passthrough interrupt that could not be handled

arch/powerpc/include/asm/kvm_book3s.h

···
 			unsigned long mask);
 extern void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr);
 
+extern int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu);
+extern int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu);
+extern void kvmhv_emulate_tm_rollback(struct kvm_vcpu *vcpu);
+
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);
 extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);

arch/powerpc/include/asm/kvm_book3s_64.h

···
 			set_bit_le(i, map);
 }
 
+static inline u64 sanitize_msr(u64 msr)
+{
+	msr &= ~MSR_HV;
+	msr |= MSR_ME;
+	return msr;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline void copy_from_checkpoint(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.cr  = vcpu->arch.cr_tm;
+	vcpu->arch.xer = vcpu->arch.xer_tm;
+	vcpu->arch.lr  = vcpu->arch.lr_tm;
+	vcpu->arch.ctr = vcpu->arch.ctr_tm;
+	vcpu->arch.amr = vcpu->arch.amr_tm;
+	vcpu->arch.ppr = vcpu->arch.ppr_tm;
+	vcpu->arch.dscr = vcpu->arch.dscr_tm;
+	vcpu->arch.tar = vcpu->arch.tar_tm;
+	memcpy(vcpu->arch.gpr, vcpu->arch.gpr_tm,
+	       sizeof(vcpu->arch.gpr));
+	vcpu->arch.fp  = vcpu->arch.fp_tm;
+	vcpu->arch.vr  = vcpu->arch.vr_tm;
+	vcpu->arch.vrsave = vcpu->arch.vrsave_tm;
+}
+
+static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.cr_tm  = vcpu->arch.cr;
+	vcpu->arch.xer_tm = vcpu->arch.xer;
+	vcpu->arch.lr_tm  = vcpu->arch.lr;
+	vcpu->arch.ctr_tm = vcpu->arch.ctr;
+	vcpu->arch.amr_tm = vcpu->arch.amr;
+	vcpu->arch.ppr_tm = vcpu->arch.ppr;
+	vcpu->arch.dscr_tm = vcpu->arch.dscr;
+	vcpu->arch.tar_tm = vcpu->arch.tar;
+	memcpy(vcpu->arch.gpr_tm, vcpu->arch.gpr,
+	       sizeof(vcpu->arch.gpr));
+	vcpu->arch.fp_tm  = vcpu->arch.fp;
+	vcpu->arch.vr_tm  = vcpu->arch.vr;
+	vcpu->arch.vrsave_tm = vcpu->arch.vrsave;
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */

arch/powerpc/include/asm/kvm_book3s_asm.h

···
 	u8 host_ipi;
 	u8 ptid;		/* thread number within subcore when split */
 	u8 tid;			/* thread number within whole core */
+	u8 fake_suspend;
 	struct kvm_vcpu *kvm_vcpu;
 	struct kvmppc_vcore *kvm_vcore;
 	void __iomem *xics_phys;

arch/powerpc/include/asm/kvm_host.h

···
 	u64 tfhar;
 	u64 texasr;
 	u64 tfiar;
+	u64 orig_texasr;
 
 	u32 cr_tm;
 	u64 xer_tm;

arch/powerpc/include/asm/kvm_ppc.h

···
 extern void kvm_cma_reserve(void) __init;
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {
-	paca[cpu].kvm_hstate.xics_phys = (void __iomem *)addr;
+	paca_ptrs[cpu]->kvm_hstate.xics_phys = (void __iomem *)addr;
 }
 
 static inline void kvmppc_set_xive_tima(int cpu,
 					unsigned long phys_addr,
 					void __iomem *virt_addr)
 {
-	paca[cpu].kvm_hstate.xive_tima_phys = (void __iomem *)phys_addr;
-	paca[cpu].kvm_hstate.xive_tima_virt = virt_addr;
+	paca_ptrs[cpu]->kvm_hstate.xive_tima_phys = (void __iomem *)phys_addr;
+	paca_ptrs[cpu]->kvm_hstate.xive_tima_virt = virt_addr;
 }
 
 static inline u32 kvmppc_get_xics_latch(void)
···
 
 static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
 {
-	paca[cpu].kvm_hstate.host_ipi = host_ipi;
+	paca_ptrs[cpu]->kvm_hstate.host_ipi = host_ipi;
 }
 
 static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)

arch/powerpc/include/asm/lppaca.h

···
 #include <linux/threads.h>
 #include <asm/types.h>
 #include <asm/mmu.h>
+#include <asm/firmware.h>
 
 /*
- * We only have to have statically allocated lppaca structs on
- * legacy iSeries, which supports at most 64 cpus.
- */
-#define NR_LPPACAS	1
-
-/*
- * The Hypervisor barfs if the lppaca crosses a page boundary.  A 1k
- * alignment is sufficient to prevent this
+ * The lppaca is the "virtual processor area" registered with the hypervisor,
+ * H_REGISTER_VPA etc.
+ *
+ * According to PAPR, the structure is 640 bytes long, must be L1 cache line
+ * aligned, and must not cross a 4kB boundary. Its size field must be at
+ * least 640 bytes (but may be more).
+ *
+ * Pre-v4.14 KVM hypervisors reject the VPA if its size field is smaller than
+ * 1kB, so we dynamically allocate 1kB and advertise size as 1kB, but keep
+ * this structure as the canonical 640 byte size.
  */
 struct lppaca {
 	/* cacheline 1 contains read-only data */
···
 
 	__be32	page_ins;		/* CMO Hint - # page ins by OS */
 	u8	reserved11[148];
-	volatile __be64 dtl_idx;		/* Dispatch Trace Log head index */
+	volatile __be64 dtl_idx;	/* Dispatch Trace Log head index */
 	u8	reserved12[96];
-} __attribute__((__aligned__(0x400)));
+} ____cacheline_aligned;
 
-extern struct lppaca lppaca[];
-
-#define lppaca_of(cpu)	(*paca[cpu].lppaca_ptr)
+#define lppaca_of(cpu)	(*paca_ptrs[cpu]->lppaca_ptr)
 
 /*
  * We are using a non architected field to determine if a partition is
···
 
 static inline bool lppaca_shared_proc(struct lppaca *l)
 {
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return false;
 	return !!(l->__old_status & LPPACA_OLD_SHARED_PROC);
 }
 

arch/powerpc/include/asm/mmu-8xx.h

···
 #define M_APG2		0x00000040
 #define M_APG3		0x00000060
 
+#ifdef CONFIG_PPC_MM_SLICES
+#include <asm/nohash/32/slice.h>
+#define SLICE_ARRAY_SIZE	(1 << (32 - SLICE_LOW_SHIFT - 1))
+#endif
+
 #ifndef __ASSEMBLY__
+struct slice_mask {
+	u64 low_slices;
+	DECLARE_BITMAP(high_slices, 0);
+};
+
 typedef struct {
 	unsigned int id;
 	unsigned int active;
 	unsigned long vdso_base;
+#ifdef CONFIG_PPC_MM_SLICES
+	u16 user_psize;		/* page size index */
+	unsigned char low_slices_psize[SLICE_ARRAY_SIZE];
+	unsigned char high_slices_psize[0];
+	unsigned long slb_addr_limit;
+	struct slice_mask mask_base_psize; /* 4k or 16k */
+# ifdef CONFIG_HUGETLB_PAGE
+	struct slice_mask mask_512k;
+	struct slice_mask mask_8m;
+# endif
+#endif
 } mm_context_t;
 
 #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)

arch/powerpc/include/asm/mmu.h

···
 /* MMU feature bit sets for various CPUs */
 #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2	\
 	MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2
-#define MMU_FTRS_POWER4		MMU_FTRS_DEFAULT_HPTE_ARCH_V2
-#define MMU_FTRS_PPC970		MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA
-#define MMU_FTRS_POWER5		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
+#define MMU_FTRS_POWER		MMU_FTRS_DEFAULT_HPTE_ARCH_V2
+#define MMU_FTRS_PPC970		MMU_FTRS_POWER | MMU_FTR_TLBIE_CROP_VA
+#define MMU_FTRS_POWER5		MMU_FTRS_POWER | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_POWER6		MMU_FTRS_POWER5 | MMU_FTR_KERNEL_RO | MMU_FTR_68_BIT_VA
 #define MMU_FTRS_POWER7		MMU_FTRS_POWER6
 #define MMU_FTRS_POWER8		MMU_FTRS_POWER6

arch/powerpc/include/asm/mmu_context.h

···
 extern void hash__reserve_context_id(int id);
 extern void __destroy_context(int context_id);
 static inline void mmu_context_init(void) { }
+
+static inline int alloc_extended_context(struct mm_struct *mm,
+					 unsigned long ea)
+{
+	int context_id;
+
+	int index = ea >> MAX_EA_BITS_PER_CONTEXT;
+
+	context_id = hash__alloc_context_id();
+	if (context_id < 0)
+		return context_id;
+
+	VM_WARN_ON(mm->context.extended_id[index]);
+	mm->context.extended_id[index] = context_id;
+	return context_id;
+}
+
+static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
+{
+	int context_id;
+
+	context_id = get_ea_context(&mm->context, ea);
+	if (!context_id)
+		return true;
+	return false;
+}
+
 #else
 extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next,
 			       struct task_struct *tsk);
 extern unsigned long __init_new_context(void);
 extern void __destroy_context(unsigned long context_id);
 extern void mmu_context_init(void);
+static inline int alloc_extended_context(struct mm_struct *mm,
+					 unsigned long ea)
+{
+	/* non book3s_64 should never find this called */
+	WARN_ON(1);
+	return -ENOMEM;
+}
+
+static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
+{
+	return false;
+}
 #endif
 
 #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)

arch/powerpc/include/asm/nohash/32/slice.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_NOHASH_32_SLICE_H
+#define _ASM_POWERPC_NOHASH_32_SLICE_H
+
+#ifdef CONFIG_PPC_MM_SLICES
+
+#define SLICE_LOW_SHIFT		26	/* 64 slices */
+#define SLICE_LOW_TOP		(0x100000000ull)
+#define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
+#define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)
+
+#define SLICE_HIGH_SHIFT	0
+#define SLICE_NUM_HIGH		0ul
+#define GET_HIGH_SLICE_INDEX(addr)	(addr & 0)
+
+#endif /* CONFIG_PPC_MM_SLICES */
+
+#endif /* _ASM_POWERPC_NOHASH_32_SLICE_H */

arch/powerpc/include/asm/nohash/64/slice.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_NOHASH_64_SLICE_H
+#define _ASM_POWERPC_NOHASH_64_SLICE_H
+
+#ifdef CONFIG_PPC_64K_PAGES
+#define get_slice_psize(mm, addr)	MMU_PAGE_64K
+#else /* CONFIG_PPC_64K_PAGES */
+#define get_slice_psize(mm, addr)	MMU_PAGE_4K
+#endif /* !CONFIG_PPC_64K_PAGES */
+#define slice_set_user_psize(mm, psize)	do { BUG(); } while (0)
+
+#endif /* _ASM_POWERPC_NOHASH_64_SLICE_H */

arch/powerpc/include/asm/opal-api.h

···
 #define OPAL_NPU_SPA_SETUP			159
 #define OPAL_NPU_SPA_CLEAR_CACHE		160
 #define OPAL_NPU_TL_SET				161
-#define OPAL_LAST				161
+#define OPAL_PCI_GET_PBCQ_TUNNEL_BAR		164
+#define OPAL_PCI_SET_PBCQ_TUNNEL_BAR		165
+#define OPAL_LAST				165
 
 /* Device tree flags */
 

arch/powerpc/include/asm/opal.h

···
 int64_t opal_slw_set_reg(uint64_t cpu_pir, uint64_t sprn, uint64_t val);
 int64_t opal_config_cpu_idle_state(uint64_t state, uint64_t flag);
 int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number);
+int64_t opal_pci_get_pbcq_tunnel_bar(uint64_t phb_id, uint64_t *addr);
+int64_t opal_pci_set_pbcq_tunnel_bar(uint64_t phb_id, uint64_t addr);
 int64_t opal_ipmi_send(uint64_t interface, struct opal_ipmi_msg *msg,
 		uint64_t msg_len);
 int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg,
···
 extern unsigned long opal_get_boot_time(void);
 extern void opal_nvram_init(void);
 extern void opal_flash_update_init(void);
-extern void opal_flash_term_callback(void);
+extern void opal_flash_update_print_message(void);
 extern int opal_elog_init(void);
 extern void opal_platform_dump_init(void);
 extern void opal_sys_param_init(void);

arch/powerpc/include/asm/paca.h

···
 #include <asm/accounting.h>
 #include <asm/hmi.h>
 #include <asm/cpuidle.h>
+#include <asm/atomic.h>
 
 register struct paca_struct *local_paca asm("r13");
 
···
 #define get_paca()	local_paca
 #endif
 
+#ifdef CONFIG_PPC_PSERIES
 #define get_lppaca()	(get_paca()->lppaca_ptr)
+#endif
+
 #define get_slb_shadow()	(get_paca()->slb_shadow_ptr)
 
 struct task_struct;
···
  * processor.
  */
 struct paca_struct {
-#ifdef CONFIG_PPC_BOOK3S
+#ifdef CONFIG_PPC_PSERIES
 	/*
 	 * Because hw_cpu_id, unlike other paca fields, is accessed
 	 * routinely from other CPUs (from the IRQ code), we stick to
···
 	 */
 
 	struct lppaca *lppaca_ptr;	/* Pointer to LpPaca for PLIC */
-#endif /* CONFIG_PPC_BOOK3S */
+#endif /* CONFIG_PPC_PSERIES */
+
 	/*
 	 * MAGIC: the spinlock functions in arch/powerpc/lib/locks.c 
 	 * load lock_token and paca_index with a single lwz
···
 #ifdef CONFIG_PPC_BOOK3S
 	mm_context_id_t mm_ctx_id;
 #ifdef CONFIG_PPC_MM_SLICES
-	u64 mm_ctx_low_slices_psize;
+	unsigned char mm_ctx_low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE];
 	unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE];
 	unsigned long mm_ctx_slb_addr_limit;
 #else
···
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
 	u16 trap_save;			/* Used when bad stack is encountered */
 	u8 irq_soft_mask;		/* mask for irq soft masking */
+	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 irq_happened;		/* irq happened while soft-disabled */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
 	u8 nap_state_lost;		/* NV GPR values lost in power7_idle */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	u8 pmcregs_in_use;		/* pseries puts this in lppaca */
+#endif
 	u64 sprg_vdso;			/* Saved user-visible sprg */
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	u64 tm_scratch;                 /* TM scratch area for reclaim */
···
 	u8 thread_mask;
 	/* Mask to denote subcore sibling threads */
 	u8 subcore_sibling_mask;
+	/* Flag to request this thread not to stop */
+	atomic_t dont_stop;
 	/*
 	 * Pointer to an array which contains pointer
 	 * to the sibling threads' paca.
···
 	void *rfi_flush_fallback_area;
 	u64 l1d_flush_size;
 #endif
-};
+} ____cacheline_aligned;
 
 extern void copy_mm_to_paca(struct mm_struct *mm);
-extern struct paca_struct *paca;
+extern struct paca_struct **paca_ptrs;
 extern void initialise_paca(struct paca_struct *new_paca, int cpu);
 extern void setup_paca(struct paca_struct *new_paca);
-extern void allocate_pacas(void);
+extern void allocate_paca_ptrs(void);
+extern void allocate_paca(int cpu);
 extern void free_unused_pacas(void);
 
 #else /* CONFIG_PPC64 */
 
-static inline void allocate_pacas(void) { };
+static inline void allocate_paca_ptrs(void) { };
+static inline void allocate_paca(int cpu) { };
 static inline void free_unused_pacas(void) { };
 
 #endif /* CONFIG_PPC64 */

arch/powerpc/include/asm/page.h

···
 
 #ifdef CONFIG_FLATMEM
 #define ARCH_PFN_OFFSET		((unsigned long)(MEMORY_START >> PAGE_SHIFT))
-#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && (pfn) < max_mapnr)
+#ifndef __ASSEMBLY__
+extern unsigned long max_mapnr;
+static inline bool pfn_valid(unsigned long pfn)
+{
+	unsigned long min_pfn = ARCH_PFN_OFFSET;
+
+	return pfn >= min_pfn && pfn < max_mapnr;
+}
+#endif
 #endif
 
 #define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
···
 
 #include <asm-generic/memory_model.h>
 #endif /* __ASSEMBLY__ */
+#include <asm/slice.h>
 
 #endif /* _ASM_POWERPC_PAGE_H */

arch/powerpc/include/asm/page_64.h

···
 
 #endif /* __ASSEMBLY__ */
 
-#ifdef CONFIG_PPC_MM_SLICES
-
-#define SLICE_LOW_SHIFT		28
-#define SLICE_HIGH_SHIFT	40
-
-#define SLICE_LOW_TOP		(0x100000000ul)
-#define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
-#define SLICE_NUM_HIGH		(H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT)
-
-#define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)
-#define GET_HIGH_SLICE_INDEX(addr)	((addr) >> SLICE_HIGH_SHIFT)
-
-#ifndef __ASSEMBLY__
-struct mm_struct;
-
-extern unsigned long slice_get_unmapped_area(unsigned long addr,
-					     unsigned long len,
-					     unsigned long flags,
-					     unsigned int psize,
-					     int topdown);
-
-extern unsigned int get_slice_psize(struct mm_struct *mm,
-				    unsigned long addr);
-
-extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize);
-extern void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
-				  unsigned long len, unsigned int psize);
-
-#endif /* __ASSEMBLY__ */
-#else
-#define slice_init()
-#ifdef CONFIG_PPC_BOOK3S_64
-#define get_slice_psize(mm, addr)	((mm)->context.user_psize)
-#define slice_set_user_psize(mm, psize)		\
-do {						\
-	(mm)->context.user_psize = (psize);	\
-	(mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \
-} while (0)
-#else /* !CONFIG_PPC_BOOK3S_64 */
-#ifdef CONFIG_PPC_64K_PAGES
-#define get_slice_psize(mm, addr)	MMU_PAGE_64K
-#else /* CONFIG_PPC_64K_PAGES */
-#define get_slice_psize(mm, addr)	MMU_PAGE_4K
-#endif /* !CONFIG_PPC_64K_PAGES */
-#define slice_set_user_psize(mm, psize)	do { BUG(); } while(0)
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-#define slice_set_range_psize(mm, start, len, psize)	\
-	slice_set_user_psize((mm), (psize))
-#endif /* CONFIG_PPC_MM_SLICES */
-
-#ifdef CONFIG_HUGETLB_PAGE
-
-#ifdef CONFIG_PPC_MM_SLICES
-#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-#endif
-
-#endif /* !CONFIG_HUGETLB_PAGE */
-
 #define VM_DATA_DEFAULT_FLAGS \
 	(is_32bit_task() ? \
 	 VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64)

arch/powerpc/include/asm/perf_event_server.h

···
 			       [PERF_COUNT_HW_CACHE_OP_MAX]
 			       [PERF_COUNT_HW_CACHE_RESULT_MAX];
 
+	int		n_blacklist_ev;
+	int 		*blacklist_ev;
 	/* BHRB entries in the PMU */
 	int		bhrb_nr;
 };

arch/powerpc/include/asm/plpar_wrappers.h

···
 #ifndef _ASM_POWERPC_PLPAR_WRAPPERS_H
 #define _ASM_POWERPC_PLPAR_WRAPPERS_H
 
+#ifdef CONFIG_PPC_PSERIES
+
 #include <linux/string.h>
 #include <linux/irqflags.h>
 
 #include <asm/hvcall.h>
 #include <asm/paca.h>
 #include <asm/page.h>
-
-/* Get state of physical CPU from query_cpu_stopped */
-int smp_query_cpu_stopped(unsigned int pcpu);
-#define QCSS_STOPPED 0
-#define QCSS_STOPPING 1
-#define QCSS_NOT_STOPPED 2
-#define QCSS_HARDWARE_ERROR -1
-#define QCSS_HARDWARE_BUSY -2
 
 static inline long poll_pending(void)
 {
···
 	return plpar_set_mode(1, H_SET_MODE_RESOURCE_LE, 0, 0);
 }
 
-static inline long plapr_set_ciabr(unsigned long ciabr)
+static inline long plpar_set_ciabr(unsigned long ciabr)
 {
 	return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_CIABR, ciabr, 0);
 }
 
-static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long dawrx0)
+static inline long plpar_set_watchpoint0(unsigned long dawr0, unsigned long dawrx0)
 {
 	return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR, dawr0, dawrx0);
 }
 
-static inline long plapr_signal_sys_reset(long cpu)
+static inline long plpar_signal_sys_reset(long cpu)
 {
 	return plpar_hcall_norets(H_SIGNAL_SYS_RESET, cpu);
 }
···
 
 	return rc;
 }
+
+#else /* !CONFIG_PPC_PSERIES */
+
+static inline long plpar_set_ciabr(unsigned long ciabr)
+{
+	return 0;
+}
+#endif /* CONFIG_PPC_PSERIES */
 
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */

arch/powerpc/include/asm/pmc.h

···
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/lppaca.h>
+#include <asm/firmware.h>
 
 static inline void ppc_set_pmu_inuse(int inuse)
 {
-	get_lppaca()->pmcregs_in_use = inuse;
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
+#ifdef CONFIG_PPC_PSERIES
+		get_lppaca()->pmcregs_in_use = inuse;
+#endif
+	} else {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		get_paca()->pmcregs_in_use = inuse;
+#endif
+	}
+#endif
 }
 
 extern void power4_enable_pmcs(void);

arch/powerpc/include/asm/pnv-pci.h

···
 extern int pnv_pci_set_p2p(struct pci_dev *initiator, struct pci_dev *target,
 			   u64 desc);
 
+extern int pnv_pci_enable_tunnel(struct pci_dev *dev, uint64_t *asnind);
+extern int pnv_pci_disable_tunnel(struct pci_dev *dev);
+extern int pnv_pci_set_tunnel_bar(struct pci_dev *dev, uint64_t addr,
+				  int enable);
+extern int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid,
+				      u32 *pid, u32 *tid);
 int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode);
 int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
 			   unsigned int virq);

arch/powerpc/include/asm/powernv.h

···
 }
 
 static inline void pnv_tm_init(void) { }
+static inline void pnv_power9_force_smt4(void) { }
 #endif
 
 #endif /* _ASM_POWERNV_H */

arch/powerpc/include/asm/ppc-opcode.h

···
 #define PPC_INST_MSGSYNC		0x7c0006ec
 #define PPC_INST_MSGSNDP		0x7c00011c
 #define PPC_INST_MSGCLRP		0x7c00015c
+#define PPC_INST_MTMSRD			0x7c000164
 #define PPC_INST_MTTMR			0x7c0003dc
 #define PPC_INST_NOP			0x60000000
 #define PPC_INST_PASTE			0x7c20070d
···
 #define PPC_INST_POPCNTB_MASK		0xfc0007fe
 #define PPC_INST_POPCNTD		0x7c0003f4
 #define PPC_INST_POPCNTW		0x7c0002f4
+#define PPC_INST_RFEBB			0x4c000124
 #define PPC_INST_RFCI			0x4c000066
 #define PPC_INST_RFDI			0x4c00004e
+#define PPC_INST_RFID			0x4c000024
 #define PPC_INST_RFMCI			0x4c00004c
 #define PPC_INST_MFSPR			0x7c0002a6
 #define PPC_INST_MFSPR_DSCR		0x7c1102a6
···
 #define PPC_INST_TLBSRX_DOT		0x7c0006a5
 #define PPC_INST_VPMSUMW		0x10000488
 #define PPC_INST_VPMSUMD		0x100004c8
+#define PPC_INST_VPERMXOR		0x1000002d
 #define PPC_INST_XXLOR			0xf0000490
 #define PPC_INST_XXSWAPD		0xf0000250
 #define PPC_INST_XVCPSGNDP		0xf0000780
 #define PPC_INST_TRECHKPT		0x7c0007dd
 #define PPC_INST_TRECLAIM		0x7c00075d
 #define PPC_INST_TABORT			0x7c00071d
+#define PPC_INST_TSR			0x7c0005dd
 
 #define PPC_INST_NAP			0x4c000364
 #define PPC_INST_SLEEP			0x4c0003a4
···
 					       VSX_XX3((t), a, a))
 #define XVCPSGNDP(t, a, b)	stringify_in_c(.long (PPC_INST_XVCPSGNDP | \
 					       VSX_XX3((t), (a), (b))))
+
+#define VPERMXOR(vrt, vra, vrb, vrc)				\
+	stringify_in_c(.long (PPC_INST_VPERMXOR |		\
+			      ___PPC_RT(vrt) | ___PPC_RA(vra) | \
+			      ___PPC_RB(vrb) | (((vrc) & 0x1f) << 6)))
 
 #define PPC_NAP			stringify_in_c(.long PPC_INST_NAP)
 #define PPC_SLEEP		stringify_in_c(.long PPC_INST_SLEEP)

arch/powerpc/include/asm/ppc_asm.h

···
 
 /* The following stops all load and store data streams associated with stream
  * ID (ie. streams created explicitly).  The embedded and server mnemonics for
- * dcbt are different so we use machine "power4" here explicitly.
+ * dcbt are different so this must only be used for server.
  */
-#define DCBT_STOP_ALL_STREAM_IDS(scratch)	\
-.machine push ;					\
-.machine "power4" ;				\
-       lis     scratch,0x60000000@h;		\
-       dcbt    0,scratch,0b01010;		\
-.machine pop
+#define DCBT_BOOK3S_STOP_ALL_STREAM_IDS(scratch)	\
+       lis     scratch,0x60000000@h;			\
+       dcbt    0,scratch,0b01010
 
 /*
  * toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them

arch/powerpc/include/asm/processor.h

···
 #define TASK_SIZE_64TB  (0x0000400000000000UL)
 #define TASK_SIZE_128TB (0x0000800000000000UL)
 #define TASK_SIZE_512TB (0x0002000000000000UL)
+#define TASK_SIZE_1PB   (0x0004000000000000UL)
+#define TASK_SIZE_2PB   (0x0008000000000000UL)
+/*
+ * With 52 bits in the address we can support
+ * upto 4PB of range.
+ */
+#define TASK_SIZE_4PB   (0x0010000000000000UL)
 
 /*
  * For now 512TB is only supported with book3s and 64K linux page size.
···
 /*
  * Max value currently used:
  */
-#define TASK_SIZE_USER64		TASK_SIZE_512TB
+#define TASK_SIZE_USER64		TASK_SIZE_4PB
 #define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
+#define TASK_CONTEXT_SIZE		TASK_SIZE_512TB
 #else
 #define TASK_SIZE_USER64		TASK_SIZE_64TB
 #define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_64TB
+/*
+ * We don't need to allocate extended context ids for 4K page size, because
+ * we limit the max effective address on this config to 64TB.
+ */
+#define TASK_CONTEXT_SIZE		TASK_SIZE_64TB
 #endif
 
 /*
···
 extern unsigned long power7_idle_insn(unsigned long type); /* PNV_THREAD_NAP/etc*/
 extern void power7_idle_type(unsigned long type);
 extern unsigned long power9_idle_stop(unsigned long psscr_val);
+extern unsigned long power9_offline_stop(unsigned long psscr_val);
 extern void power9_idle_type(unsigned long stop_psscr_val,
 			      unsigned long stop_psscr_mask);
 

arch/powerpc/include/asm/reg.h

···
 #define PSSCR_SD		0x00400000 /* Status Disable */
 #define PSSCR_PLS	0xf000000000000000 /* Power-saving Level Status */
 #define PSSCR_GUEST_VIS	0xf0000000000003ff /* Guest-visible PSSCR fields */
+#define PSSCR_FAKE_SUSPEND	0x00000400 /* Fake-suspend bit (P9 DD2.2) */
+#define PSSCR_FAKE_SUSPEND_LG	10	   /* Fake-suspend bit position */
 
 /* Floating Point Status and Control Register (FPSCR) Fields */
 #define FPSCR_FX	0x80000000	/* FPU exception summary */
···
 #define SPRN_TFIAR	0x81	/* Transaction Failure Inst Addr   */
 #define SPRN_TEXASR	0x82	/* Transaction EXception & Summary */
 #define SPRN_TEXASRU	0x83	/* ''	   ''	   ''	 Upper 32  */
+#define   TEXASR_ABORT	__MASK(63-31) /* terminated by tabort or treclaim */
+#define   TEXASR_SUSP	__MASK(63-32) /* tx failed in suspended state */
+#define   TEXASR_HV	__MASK(63-34) /* MSR[HV] when failure occurred */
+#define   TEXASR_PR	__MASK(63-35) /* MSR[PR] when failure occurred */
 #define   TEXASR_FS	__MASK(63-36) /* TEXASR Failure Summary */
+#define   TEXASR_EXACT	__MASK(63-37) /* TFIAR value is exact */
 #define SPRN_TFHAR	0x80	/* Transaction Failure Handler Addr */
 #define SPRN_TIDR	144	/* Thread ID register */
 #define SPRN_CTRLF	0x088

arch/powerpc/include/asm/security_features.h

···
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Security related feature bit definitions.
+ *
+ * Copyright 2018, Michael Ellerman, IBM Corporation.
+ */
+
+#ifndef _ASM_POWERPC_SECURITY_FEATURES_H
+#define _ASM_POWERPC_SECURITY_FEATURES_H
+
+
+extern unsigned long powerpc_security_features;
+extern bool rfi_flush;
+
+static inline void security_ftr_set(unsigned long feature)
+{
+	powerpc_security_features |= feature;
+}
+
+static inline void security_ftr_clear(unsigned long feature)
+{
+	powerpc_security_features &= ~feature;
+}
+
+static inline bool security_ftr_enabled(unsigned long feature)
+{
+	return !!(powerpc_security_features & feature);
+}
+
+
+// Features indicating support for Spectre/Meltdown mitigations
+
+// The L1-D cache can be flushed with ori r30,r30,0
+#define SEC_FTR_L1D_FLUSH_ORI30		0x0000000000000001ull
+
+// The L1-D cache can be flushed with mtspr 882,r0 (aka SPRN_TRIG2)
+#define SEC_FTR_L1D_FLUSH_TRIG2		0x0000000000000002ull
+
+// ori r31,r31,0 acts as a speculation barrier
+#define SEC_FTR_SPEC_BAR_ORI31		0x0000000000000004ull
+
+// Speculation past bctr is disabled
+#define SEC_FTR_BCCTRL_SERIALISED	0x0000000000000008ull
+
+// Entries in L1-D are private to a SMT thread
+#define SEC_FTR_L1D_THREAD_PRIV		0x0000000000000010ull
+
+// Indirect branch prediction cache disabled
+#define SEC_FTR_COUNT_CACHE_DISABLED	0x0000000000000020ull
+
+
+// Features indicating need for Spectre/Meltdown mitigations
+
+// The L1-D cache should be flushed on MSR[HV] 1->0 transition (hypervisor to guest)
+#define SEC_FTR_L1D_FLUSH_HV		0x0000000000000040ull
+
+// The L1-D cache should be flushed on MSR[PR] 0->1 transition (kernel to userspace)
+#define SEC_FTR_L1D_FLUSH_PR		0x0000000000000080ull
+
+// A speculation barrier should be used for bounds checks (Spectre variant 1)
+#define SEC_FTR_BNDS_CHK_SPEC_BAR	0x0000000000000100ull
+
+// Firmware configuration indicates user favours security over performance
+#define SEC_FTR_FAVOUR_SECURITY		0x0000000000000200ull
+
+
+// Features enabled by default
+#define SEC_FTR_DEFAULT \
+	(SEC_FTR_L1D_FLUSH_HV | \
+	 SEC_FTR_L1D_FLUSH_PR | \
+	 SEC_FTR_BNDS_CHK_SPEC_BAR | \
+	 SEC_FTR_FAVOUR_SECURITY)
+
+#endif /* _ASM_POWERPC_SECURITY_FEATURES_H */

arch/powerpc/include/asm/setup.h

···
 #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
 
 void check_for_initrd(void);
+void mem_topology_setup(void);
 void initmem_init(void);
 void setup_panic(void);
 #define ARCH_PANIC_TIMEOUT 180
···
 	L1D_FLUSH_MTTRIG	= 0x8,
 };
 
-void __init setup_rfi_flush(enum l1d_flush_type, bool enable);
+void setup_rfi_flush(enum l1d_flush_type, bool enable);
 void do_rfi_flush_fixups(enum l1d_flush_type types);
 
 #endif /* !__ASSEMBLY__ */

arch/powerpc/include/asm/slice.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_SLICE_H
+#define _ASM_POWERPC_SLICE_H
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#include <asm/book3s/64/slice.h>
+#elif defined(CONFIG_PPC64)
+#include <asm/nohash/64/slice.h>
+#elif defined(CONFIG_PPC_MMU_NOHASH)
+#include <asm/nohash/32/slice.h>
+#endif
+
+#ifdef CONFIG_PPC_MM_SLICES
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+
+#ifndef __ASSEMBLY__
+
+struct mm_struct;
+
+unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
+				      unsigned long flags, unsigned int psize,
+				      int topdown);
+
+unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr);
+
+void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
+			   unsigned long len, unsigned int psize);
+
+void slice_init_new_context_exec(struct mm_struct *mm);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_PPC_MM_SLICES */
+
+#endif /* _ASM_POWERPC_SLICE_H */

arch/powerpc/include/asm/smp.h

···
 
 extern int boot_cpuid;
 extern int spinning_secondaries;
+extern u32 *cpu_to_phys_id;
 
 extern void cpu_die(void);
 extern int cpu_to_chip_id(int cpu);
···
 #ifdef CONFIG_PPC64
 static inline int get_hard_smp_processor_id(int cpu)
 {
-	return paca[cpu].hw_cpu_id;
+	return paca_ptrs[cpu]->hw_cpu_id;
 }
 
 static inline void set_hard_smp_processor_id(int cpu, int phys)
 {
-	paca[cpu].hw_cpu_id = phys;
+	paca_ptrs[cpu]->hw_cpu_id = phys;
 }
 #else
 /* 32-bit */

arch/powerpc/include/asm/sparsemem.h

···
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end);
+extern int create_section_mapping(unsigned long start, unsigned long end, int nid);
 extern int remove_section_mapping(unsigned long start, unsigned long end);
 
 #ifdef CONFIG_PPC_BOOK3S_64

arch/powerpc/include/asm/spinlock.h

···
 #define vcpu_is_preempted vcpu_is_preempted
 static inline bool vcpu_is_preempted(int cpu)
 {
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return false;
 	return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
 }
 #endif

arch/powerpc/include/asm/switch_to.h

···
 	msr_check_and_clear(MSR_FP);
 }
 #else
-static inline void __giveup_fpu(struct task_struct *t) { }
 static inline void save_fpu(struct task_struct *t) { }
 static inline void flush_fp_to_thread(struct task_struct *t) { }
 #endif

arch/powerpc/include/asm/synch.h

···
 #include <linux/stringify.h>
 #include <asm/feature-fixups.h>
 
-#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
-#define __SUBARCH_HAS_LWSYNC
-#endif
-
 #ifndef __ASSEMBLY__
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,

arch/powerpc/include/asm/thread_info.h

···
 	return (struct thread_info *)val;
 }
 
+extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #endif /* __ASSEMBLY__ */
 
 /*

arch/powerpc/include/asm/time.h

···
 extern void tick_broadcast_ipi_handler(void);
 
 extern void generic_calibrate_decr(void);
+extern void hdec_interrupt(struct pt_regs *regs);
 
 /* Some sane defaults: 125 MHz timebase, 1GHz processor */
 extern unsigned long ppc_proc_freq;
···
 /* Accessor functions for the timebase (RTC on 601) registers. */
 /* If one day CONFIG_POWER is added just define __USE_RTC as 1 */
 #ifdef CONFIG_6xx
-#define __USE_RTC()	(!cpu_has_feature(CPU_FTR_USE_TB))
+#define __USE_RTC()	(cpu_has_feature(CPU_FTR_USE_RTC))
 #else
 #define __USE_RTC()	0
 #endif
···
 DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array);
 
 extern void secondary_cpu_time_init(void);
+extern void __init time_init(void);
 
 DECLARE_PER_CPU(u64, decrementers_next_tb);
 

arch/powerpc/include/asm/uaccess.h

···
 
 #else
 
-#define __access_ok(addr, size, segment)	\
-	(((addr) <= (segment).seg) &&		\
-	 (((size) == 0) || (((size) - 1) <= ((segment).seg - (addr)))))
+static inline int __access_ok(unsigned long addr, unsigned long size,
+			mm_segment_t seg)
+{
+	if (addr > seg.seg)
+		return 0;
+	return (size == 0 || size - 1 <= seg.seg - addr);
+}
 
 #endif
 

arch/powerpc/kernel/Makefile

···
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o security.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/

arch/powerpc/kernel/asm-offsets.c

···
 	OFFSET(PACA_EXMC, paca_struct, exmc);
 	OFFSET(PACA_EXSLB, paca_struct, exslb);
 	OFFSET(PACA_EXNMI, paca_struct, exnmi);
+#ifdef CONFIG_PPC_PSERIES
 	OFFSET(PACALPPACAPTR, paca_struct, lppaca_ptr);
+#endif
 	OFFSET(PACA_SLBSHADOWPTR, paca_struct, slb_shadow_ptr);
 	OFFSET(SLBSHADOW_STACKVSID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid);
 	OFFSET(SLBSHADOW_STACKESID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid);
 	OFFSET(SLBSHADOW_SAVEAREA, slb_shadow, save_area);
 	OFFSET(LPPACA_PMCINUSE, lppaca, pmcregs_in_use);
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	OFFSET(PACA_PMCINUSE, paca_struct, pmcregs_in_use);
+#endif
 	OFFSET(LPPACA_DTLIDX, lppaca, dtl_idx);
 	OFFSET(LPPACA_YIELDCOUNT, lppaca, yield_count);
 	OFFSET(PACA_DTL_RIDX, paca_struct, dtl_ridx);
···
 	OFFSET(VCPU_TFHAR, kvm_vcpu, arch.tfhar);
 	OFFSET(VCPU_TFIAR, kvm_vcpu, arch.tfiar);
 	OFFSET(VCPU_TEXASR, kvm_vcpu, arch.texasr);
+	OFFSET(VCPU_ORIG_TEXASR, kvm_vcpu, arch.orig_texasr);
 	OFFSET(VCPU_GPR_TM, kvm_vcpu, arch.gpr_tm);
 	OFFSET(VCPU_FPRS_TM, kvm_vcpu, arch.fp_tm.fpr);
 	OFFSET(VCPU_VRS_TM, kvm_vcpu, arch.vr_tm.vr);
···
 	HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
 	HSTATE_FIELD(HSTATE_PTID, ptid);
 	HSTATE_FIELD(HSTATE_TID, tid);
+	HSTATE_FIELD(HSTATE_FAKE_SUSPEND, fake_suspend);
 	HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]);
 	HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]);
 	HSTATE_FIELD(HSTATE_MMCRA, host_mmcr[2]);
···
 	OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask);
 	OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas);
 	OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr);
+	OFFSET(PACA_DONT_STOP, paca_struct, dont_stop);
 #define STOP_SPR(x, f)	OFFSET(x, paca_struct, stop_sprs.f)
 	STOP_SPR(STOP_PID, pid);
 	STOP_SPR(STOP_LDBAR, ldbar);

arch/powerpc/kernel/cpu_setup_6xx.S

···
 	beq	1f
 END_FTR_SECTION_IFSET(CPU_FTR_L3CR)
 	lwz	r6,CPU_SPEC_FEATURES(r4)
-	andi.	r0,r6,CPU_FTR_L3_DISABLE_NAP
+	andis.	r0,r6,CPU_FTR_L3_DISABLE_NAP@h
 	beq	1f
 	li	r7,CPU_FTR_CAN_NAP
 	andc	r6,r6,r7

arch/powerpc/kernel/cpu_setup_fsl_booke.S

···
 	 * the feature on the primary core, avoid doing it on the
 	 * secondary core.
 	 */
-	andis.	r6, r3, CPU_FTR_EMB_HV@h
+	andi.	r6, r3, CPU_FTR_EMB_HV
 	beq	2f
 	rlwinm	r3, r3, 0, ~CPU_FTR_EMB_HV
 	stw	r3, CPU_SPEC_FEATURES(r4)

arch/powerpc/kernel/cputable.c

···
 
 static struct cpu_spec __initdata cpu_specs[] = {
 #ifdef CONFIG_PPC_BOOK3S_64
-	{	/* Power4 */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x00350000,
-		.cpu_name		= "POWER4 (gp)",
-		.cpu_features		= CPU_FTRS_POWER4,
-		.cpu_user_features	= COMMON_USER_POWER4,
-		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
-		.icache_bsize		= 128,
-		.dcache_bsize		= 128,
-		.num_pmcs		= 8,
-		.pmc_type		= PPC_PMC_IBM,
-		.oprofile_cpu_type	= "ppc64/power4",
-		.oprofile_type		= PPC_OPROFILE_POWER4,
-		.platform		= "power4",
-	},
-	{	/* Power4+ */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x00380000,
-		.cpu_name		= "POWER4+ (gq)",
-		.cpu_features		= CPU_FTRS_POWER4,
-		.cpu_user_features	= COMMON_USER_POWER4,
-		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
-		.icache_bsize		= 128,
-		.dcache_bsize		= 128,
-		.num_pmcs		= 8,
-		.pmc_type		= PPC_PMC_IBM,
-		.oprofile_cpu_type	= "ppc64/power4",
-		.oprofile_type		= PPC_OPROFILE_POWER4,
-		.platform		= "power4",
-	},
 	{	/* PPC970 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00390000,
···
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
-	{	/* Power9 DD 2.1 or later (see DD2.0 above) */
+	{	/* Power9 DD 2.1 */
+		.pvr_mask		= 0xffffefff,
+		.pvr_value		= 0x004e0201,
+		.cpu_name		= "POWER9 (raw)",
+		.cpu_features		= CPU_FTRS_POWER9_DD2_1,
+		.cpu_user_features	= COMMON_USER_POWER9,
+		.cpu_user_features2	= COMMON_USER2_POWER9,
+		.mmu_features		= MMU_FTRS_POWER9,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power9",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power9,
+		.cpu_restore		= __restore_cpu_power9,
+		.machine_check_early	= __machine_check_early_realmode_p9,
+		.platform		= "power9",
+	},
+	{	/* Power9 DD2.2 or later */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x004e0000,
 		.cpu_name		= "POWER9 (raw)",
-		.cpu_features		= CPU_FTRS_POWER9_DD2_1,
+		.cpu_features		= CPU_FTRS_POWER9_DD2_2,
 		.cpu_user_features	= COMMON_USER_POWER9,
 		.cpu_user_features2	= COMMON_USER2_POWER9,
 		.mmu_features		= MMU_FTRS_POWER9,
···
 	{	/* default match */
 		.pvr_mask		= 0x00000000,
 		.pvr_value		= 0x00000000,
-		.cpu_name		= "POWER4 (compatible)",
+		.cpu_name		= "POWER5 (compatible)",
 		.cpu_features		= CPU_FTRS_COMPATIBLE,
 		.cpu_user_features	= COMMON_USER_PPC64,
-		.mmu_features		= MMU_FTRS_DEFAULT_HPTE_ARCH_V2,
+		.mmu_features		= MMU_FTRS_POWER,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
 		.pmc_type		= PPC_PMC_IBM,
-		.platform		= "power4",
+		.platform		= "power5",
 	}
 #endif	/* CONFIG_PPC_BOOK3S_64 */
 

arch/powerpc/kernel/crash.c

···
 		if (i == cpu)
 			continue;
 
-		while (paca[i].kexec_state < KEXEC_STATE_REAL_MODE) {
+		while (paca_ptrs[i]->kexec_state < KEXEC_STATE_REAL_MODE) {
 			barrier();
 			if (!cpu_possible(i) || !cpu_online(i) || (msecs <= 0))
 				break;

arch/powerpc/kernel/dt_cpu_ftrs.c

···
 };
 
 #define CPU_FTRS_BASE \
-	   (CPU_FTR_USE_TB | \
-	    CPU_FTR_LWSYNC | \
+	   (CPU_FTR_LWSYNC | \
 	    CPU_FTR_FPU_UNAVAILABLE |\
 	    CPU_FTR_NODSISRALIGN |\
 	    CPU_FTR_NOEXECUTE |\
···
 
 static struct {
 	u64	lpcr;
+	u64	lpcr_clear;
 	u64	hfscr;
 	u64	fscr;
 } system_registers;
···
 
 static void __restore_cpu_cpufeatures(void)
 {
+	u64 lpcr;
+
 	/*
 	 * LPCR is restored by the power on engine already. It can be changed
 	 * after early init e.g., by radix enable, and we have no unified API
···
 	 * The best we can do to accommodate secondary boot and idle restore
 	 * for now is "or" LPCR with existing.
 	 */
-
-	mtspr(SPRN_LPCR, system_registers.lpcr | mfspr(SPRN_LPCR));
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |= system_registers.lpcr;
+	lpcr &= ~system_registers.lpcr_clear;
+	mtspr(SPRN_LPCR, lpcr);
 	if (hv_mode) {
 		mtspr(SPRN_LPID, 0);
 		mtspr(SPRN_HFSCR, system_registers.hfscr);
···
 {
 	u64 lpcr;
 
+	system_registers.lpcr_clear |= (LPCR_ISL | LPCR_UPRT | LPCR_HR);
 	lpcr = mfspr(SPRN_LPCR);
-	lpcr &= ~LPCR_ISL;
+	lpcr &= ~(LPCR_ISL | LPCR_UPRT | LPCR_HR);
 	mtspr(SPRN_LPCR, lpcr);
 
 	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
···
 	{"virtual-page-class-key-protection", feat_enable, 0},
 	{"transactional-memory", feat_enable_tm, CPU_FTR_TM},
 	{"transactional-memory-v3", feat_enable_tm, 0},
+	{"tm-suspend-hypervisor-assist", feat_enable, CPU_FTR_P9_TM_HV_ASSIST},
+	{"tm-suspend-xer-so-bug", feat_enable, CPU_FTR_P9_TM_XER_SO_BUG},
 	{"idle-nap", feat_enable_idle_nap, 0},
 	{"alignment-interrupt-dsisr", feat_enable_align_dsisr, 0},
 	{"idle-stop", feat_enable_idle_stop, 0},
···
 	 */
 	if ((version & 0xffffff00) == 0x004e0100)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
+	else if ((version & 0xffffefff) == 0x004e0200)
+		; /* DD2.0 has no feature flag */
 	else if ((version & 0xffffefff) == 0x004e0201)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+	else if ((version & 0xffffefff) == 0x004e0202) {
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
+		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+	} else /* DD2.1 and up have DD2_1 */
+		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
 
-	if ((version & 0xffff0000) == 0x004e0000)
+	if ((version & 0xffff0000) == 0x004e0000) {
+		cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG;
+	}
+
+	/*
+	 * PKEY was not in the initial base or feature node
+	 * specification, but it should become optional in the next
+	 * cpu feature version sequence.
+	 */
+	cur_cpu_spec->cpu_features |= CPU_FTR_PKEY;
 }
 
 static void __init cpufeatures_setup_finished(void)

arch/powerpc/kernel/eeh.c

···
 	/* Check PHB state */
 	ret = eeh_ops->get_state(phb_pe, NULL);
 	if ((ret < 0) ||
-	    (ret == EEH_STATE_NOT_SUPPORT) ||
-	    (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
-	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
+	    (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) {
 		ret = 0;
 		goto out;
 	}
···
 int eeh_dev_check_failure(struct eeh_dev *edev)
 {
 	int ret;
-	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	unsigned long flags;
 	struct device_node *dn;
 	struct pci_dev *dev;
···
 	 * state, PE is in good state.
 	 */
 	if ((ret < 0) ||
-	    (ret == EEH_STATE_NOT_SUPPORT) ||
-	    ((ret & active_flags) == active_flags)) {
+	    (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) {
 		eeh_stats.false_positives++;
 		pe->false_positives++;
 		rc = 0;
···
 
 		/* Frozen parent PE ? */
 		ret = eeh_ops->get_state(parent_pe, NULL);
-		if (ret > 0 &&
-		    (ret & active_flags) != active_flags)
+		if (ret > 0 && !eeh_state_active(ret))
 			pe = parent_pe;
 
 		/* Next parent level */
···
  */
 int eeh_pe_reset_full(struct eeh_pe *pe)
 {
-	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	int reset_state = (EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
 	int type = EEH_RESET_HOT;
 	unsigned int freset = 0;
···
 
 		/* Wait until the PE is in a functioning state */
 		state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if ((state & active_flags) == active_flags)
+		if (eeh_state_active(state))
 			break;
 
 		if (state < 0) {
···
 	struct eeh_dev *edev, *tmp;
 	struct pci_dev *pdev;
 	struct pci_device_id *id;
-	int flags, ret;
+	int ret;
 
 	/* Check PE state */
-	flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	ret = eeh_ops->get_state(pe, NULL);
 	if (ret < 0 || ret == EEH_STATE_NOT_SUPPORT)
 		return 0;
 
 	/* Unfrozen PE, nothing to do */
-	if ((ret & flags) == flags)
+	if (eeh_state_active(ret))
 		return 0;
 
 	/* Frozen PE, check if it needs PE level reset */

arch/powerpc/kernel/eeh_cache.c

···
  * @addr: mmio (PIO) phys address or i/o port number
  *
  * Given an mmio phys address, or a port number, find a pci device
- * that implements this address.  Be sure to pci_dev_put the device
- * when finished.  I/O port numbers are assumed to be offset
+ * that implements this address.  I/O port numbers are assumed to be offset
  * from zero (that is, they do *not* have pci_io_addr added in).
  * It is safe to call this function within an interrupt.
  */

arch/powerpc/kernel/eeh_driver.c

···
 
 	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
 		return NULL;
+
+	device_lock(&dev->dev);
 	dev->error_state = pci_channel_io_frozen;
 
 	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
+	if (!driver) goto out_no_dev;
 
 	eeh_disable_irq(dev);
 
 	if (!driver->err_handler ||
-	    !driver->err_handler->error_detected) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
+	    !driver->err_handler->error_detected)
+		goto out;
 
 	rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
 
···
 	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
 
 	edev->in_error = true;
-	eeh_pcid_put(dev);
 	pci_uevent_ers(dev, PCI_ERS_RESULT_NONE);
+
+out:
+	eeh_pcid_put(dev);
+out_no_dev:
+	device_unlock(&dev->dev);
 	return NULL;
 }
 
···
 	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
 		return NULL;
 
+	device_lock(&dev->dev);
 	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
+	if (!driver) goto out_no_dev;
 
 	if (!driver->err_handler ||
 	    !driver->err_handler->mmio_enabled ||
-	    (edev->mode & EEH_DEV_NO_HANDLER)) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
+	    (edev->mode & EEH_DEV_NO_HANDLER))
+		goto out;
 
 	rc = driver->err_handler->mmio_enabled(dev);
 
···
 	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
 	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
 
+out:
 	eeh_pcid_put(dev);
+out_no_dev:
+	device_unlock(&dev->dev);
 	return NULL;
 }
 
···
 
 	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
 		return NULL;
+
+	device_lock(&dev->dev);
 	dev->error_state = pci_channel_io_normal;
 
 	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
+	if (!driver) goto out_no_dev;
 
 	eeh_enable_irq(dev);
 
 	if (!driver->err_handler ||
 	    !driver->err_handler->slot_reset ||
 	    (edev->mode & EEH_DEV_NO_HANDLER) ||
-	    (!edev->in_error)) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
+	    (!edev->in_error))
+		goto out;
 
 	rc = driver->err_handler->slot_reset(dev);
 	if ((*res == PCI_ERS_RESULT_NONE) ||
···
 	if (*res == PCI_ERS_RESULT_DISCONNECT &&
 	     rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
 
+out:
 	eeh_pcid_put(dev);
+out_no_dev:
+	device_unlock(&dev->dev);
 	return NULL;
 }
 
···
 
 	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
 		return NULL;
+
+	device_lock(&dev->dev);
 	dev->error_state = pci_channel_io_normal;
 
 	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
+	if (!driver) goto out_no_dev;
 
 	was_in_error = edev->in_error;
 	edev->in_error = false;
···
 	    !driver->err_handler->resume ||
 	    (edev->mode & EEH_DEV_NO_HANDLER) || !was_in_error) {
 		edev->mode &= ~EEH_DEV_NO_HANDLER;
-		eeh_pcid_put(dev);
-		return NULL;
+		goto out;
 	}
 
 	driver->err_handler->resume(dev);
 
-	eeh_pcid_put(dev);
 	pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED);
+out:
+	eeh_pcid_put(dev);
 #ifdef CONFIG_PCI_IOV
 	if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev))
 		eeh_ops->notify_resume(eeh_dev_to_pdn(edev));
 #endif
+out_no_dev:
+	device_unlock(&dev->dev);
 	return NULL;
 }
 
···
 
 	if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
 		return NULL;
+
+	device_lock(&dev->dev);
 	dev->error_state = pci_channel_io_perm_failure;
 
 	driver = eeh_pcid_get(dev);
-	if (!driver) return NULL;
+	if (!driver) goto out_no_dev;
 
 	eeh_disable_irq(dev);
 
 	if (!driver->err_handler ||
-	    !driver->err_handler->error_detected) {
-		eeh_pcid_put(dev);
-		return NULL;
-	}
+	    !driver->err_handler->error_detected)
+		goto out;
 
 	driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
 
-	eeh_pcid_put(dev);
 	pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
+out:
+	eeh_pcid_put(dev);
+out_no_dev:
+	device_unlock(&dev->dev);
 	return NULL;
 }
 
···
 
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
+ * @driver_eeh_aware: Does the device's driver provide EEH support?
  * @pe: EEH PE
  * @bus: PCI bus corresponding to the isolcated slot
+ * @rmv_data: Optional, list to record removed devices
  *
  * This routine must be called to do reset on the indicated PE.
  * During the reset, udev might be invoked because those affected
  * PCI devices will be removed and then added.
  */
 static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
-				struct eeh_rmv_data *rmv_data)
+			    struct eeh_rmv_data *rmv_data,
+			    bool driver_eeh_aware)
 {
-	struct pci_bus *frozen_bus = eeh_pe_bus_get(pe);
 	time64_t tstamp;
 	int cnt, rc;
 	struct eeh_dev *edev;
···
 	 * into pci_hp_add_devices().
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
-	if (bus) {
-		if (pe->type & EEH_PE_VF) {
-			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
-		} else {
-			pci_lock_rescan_remove();
-			pci_hp_remove_devices(bus);
-			pci_unlock_rescan_remove();
-		}
-	} else if (frozen_bus) {
+	if (driver_eeh_aware || (pe->type & EEH_PE_VF)) {
 		eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
+	} else {
+		pci_lock_rescan_remove();
+		pci_hp_remove_devices(bus);
+		pci_unlock_rescan_remove();
 	}
 
 	/*
···
 	 * the device up before the scripts have taken it down,
 	 * potentially weird things happen.
 	 */
-	if (bus) {
-		pr_info("EEH: Sleep 5s ahead of complete hotplug\n");
+	if (!driver_eeh_aware || rmv_data->removed) {
+		pr_info("EEH: Sleep 5s ahead of %s hotplug\n",
+			(driver_eeh_aware ? "partial" : "complete"));
 		ssleep(5);
 
 		/*
···
 		if (pe->type & EEH_PE_VF) {
 			eeh_add_virt_device(edev, NULL);
 		} else {
-			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
+			if (!driver_eeh_aware)
+				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 			pci_hp_add_devices(bus);
 		}
-	} else if (frozen_bus && rmv_data->removed) {
-		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
-		ssleep(5);
-
-		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
-		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
-		if (pe->type & EEH_PE_VF)
-			eeh_add_virt_device(edev, NULL);
-		else
-			pci_hp_add_devices(frozen_bus);
 	}
 	eeh_pe_state_clear(pe, EEH_PE_KEEP);
 
···
 
 /**
  * eeh_handle_normal_event - Handle EEH events on a specific PE
- * @pe: EEH PE
+ * @pe: EEH PE - which should not be used after we return, as it may
+ * have been invalidated.
  *
  * Attempts to recover the given PE.  If recovery fails or the PE has failed
  * too many times, remove the PE.
  *
- * Returns true if @pe should no longer be used, else false.
+ * While PHB detects address or data parity errors on particular PCI
+ * slot, the associated PE will be frozen. Besides, DMA's occurring
+ * to wild addresses (which usually happen due to bugs in device
+ * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
+ * #PERR or other misc PCI-related errors also can trigger EEH errors.
+ *
+ * Recovery process consists of unplugging the device driver (which
+ * generated hotplug events to userspace), then issuing a PCI #RST to
+ * the device, then reconfiguring the PCI config space for all bridges
+ * & devices under this slot, and then finally restarting the device
+ * drivers (which cause a second set of hotplug events to go out to
+ * userspace).
  */
-static bool eeh_handle_normal_event(struct eeh_pe *pe)
+void eeh_handle_normal_event(struct eeh_pe *pe)
 {
-	struct pci_bus *frozen_bus;
+	struct pci_bus *bus;
 	struct eeh_dev *edev, *tmp;
 	int rc = 0;
 	enum pci_ers_result result = PCI_ERS_RESULT_NONE;
 	struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.edev_list), 0};
 
-	frozen_bus = eeh_pe_bus_get(pe);
-	if (!frozen_bus) {
+	bus = eeh_pe_bus_get(pe);
+	if (!bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
-		return false;
+		return;
 	}
+
+	eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
 
 	eeh_pe_update_time_stamp(pe);
 	pe->freeze_count++;
···
 	 */
 	if (result == PCI_ERS_RESULT_NONE) {
 		pr_info("EEH: Reset with hotplug activity\n");
-		rc = eeh_reset_device(pe, frozen_bus, NULL);
+		rc = eeh_reset_device(pe, bus, NULL, false);
 		if (rc) {
 			pr_warn("%s: Unable to reset, err=%d\n",
 				__func__, rc);
···
 	/* If any device called out for a reset, then reset the slot */
 	if (result == PCI_ERS_RESULT_NEED_RESET) {
 		pr_info("EEH: Reset without hotplug activity\n");
-		rc = eeh_reset_device(pe, NULL, &rmv_data);
+		rc = eeh_reset_device(pe, bus, &rmv_data, true);
 		if (rc) {
 			pr_warn("%s: Cannot reset, err=%d\n",
 				__func__, rc);
···
 	pr_info("EEH: Notify device driver to resume\n");
 	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
 
-	return false;
+	goto final;
 
 hard_fail:
 	/*
···
 	 * all removed devices correctly to avoid access
 	 * the their PCI config any more.
 	 */
-	if (frozen_bus) {
-		if (pe->type & EEH_PE_VF) {
-			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
-			eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
-		} else {
-			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
-			eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+	if (pe->type & EEH_PE_VF) {
+		eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
+		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+	} else {
+		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
+		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
-			pci_lock_rescan_remove();
-			pci_hp_remove_devices(frozen_bus);
-			pci_unlock_rescan_remove();
-
-			/* The passed PE should no longer be used */
-			return true;
-		}
+		pci_lock_rescan_remove();
+		pci_hp_remove_devices(bus);
+		pci_unlock_rescan_remove();
+		/* The passed PE should no longer be used */
+		return;
 	}
-	return false;
+final:
+	eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 }
 
 /**
···
  * specific PE.  Iterates through possible failures and handles them as
  * necessary.
  */
-static void eeh_handle_special_event(void)
+void eeh_handle_special_event(void)
 {
 	struct eeh_pe *pe, *phb_pe;
 	struct pci_bus *bus;
···
 		 */
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
-			/*
-			 * eeh_handle_normal_event() can make the PE stale if it
-			 * determines that the PE cannot possibly be recovered.
-			 * Don't modify the PE state if that's the case.
-			 */
-			if (eeh_handle_normal_event(pe))
-				continue;
-
-			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+			eeh_handle_normal_event(pe);
 		} else {
 			pci_lock_rescan_remove();
 			list_for_each_entry(hose, &hose_list, list_node) {
···
 		if (rc == EEH_NEXT_ERR_DEAD_IOC)
 			break;
 	} while (rc != EEH_NEXT_ERR_NONE);
-}
-
-/**
- * eeh_handle_event - Reset a PCI device after hard lockup.
- * @pe: EEH PE
- *
- * While PHB detects address or data parity errors on particular PCI
- * slot, the associated PE will be frozen. Besides, DMA's occurring
- * to wild addresses (which usually happen due to bugs in device
- * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
- * #PERR or other misc PCI-related errors also can trigger EEH errors.
- *
- * Recovery process consists of unplugging the device driver (which
- * generated hotplug events to userspace), then issuing a PCI #RST to
- * the device, then reconfiguring the PCI config space for all bridges
- * & devices under this slot, and then finally restarting the device
- * drivers (which cause a second set of hotplug events to go out to
- * userspace).
- */
-void eeh_handle_event(struct eeh_pe *pe)
-{
-	if (pe)
-		eeh_handle_normal_event(pe);
-	else
-		eeh_handle_special_event();
 }

arch/powerpc/kernel/eeh_event.c

···
 		/* We might have event without binding PE */
 		pe = event->pe;
 		if (pe) {
-			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
 			if (pe->type & EEH_PE_PHB)
 				pr_info("EEH: Detected error on PHB#%x\n",
 					 pe->phb->global_number);
···
 				pr_info("EEH: Detected PCI bus error on "
 					"PHB#%x-PE#%x\n",
 					pe->phb->global_number, pe->addr);
-			eeh_handle_event(pe);
-			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+			eeh_handle_normal_event(pe);
 		} else {
-			eeh_handle_event(NULL);
+			eeh_handle_special_event();
 		}
 
 		kfree(event);

arch/powerpc/kernel/entry_64.S

···
 /* Cancel all explict user streams as they will have no use after context
  * switch and will stop the HW from creating streams itself
  */
-	DCBT_STOP_ALL_STREAM_IDS(r6)
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6)
 #endif
 
 	addi	r6,r4,-THREAD	/* Convert THREAD to 'current' */

arch/powerpc/kernel/exceptions-64s.S

···
 	b	pnv_powersave_wakeup
 #endif
 
+/*
+ * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does
+ * the right thing. We do not want to reconcile because that goes
+ * through irq tracing which we don't want in NMI.
+ *
+ * Save PACAIRQHAPPENED because some code will do a hard disable
+ * (e.g., xmon). So we want to restore this back to where it was
+ * when we return. DAR is unused in the stack, so save it there.
+ */
+#define ADD_RECONCILE_NMI						\
+	li	r10,IRQS_ALL_DISABLED;					\
+	stb	r10,PACAIRQSOFTMASK(r13);				\
+	lbz	r10,PACAIRQHAPPENED(r13);				\
+	std	r10,_DAR(r1)
+
 EXC_COMMON_BEGIN(system_reset_common)
 	/*
 	 * Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able
···
 	subi	r1,r1,INT_FRAME_SIZE
 	EXCEPTION_COMMON_NORET_STACK(PACA_EXNMI, 0x100,
 			system_reset, system_reset_exception,
-			ADD_NVGPRS;ADD_RECONCILE)
+			ADD_NVGPRS;ADD_RECONCILE_NMI)
+
+	/* This (and MCE) can be simplified with mtmsrd L=1 */
+	/* Clear MSR_RI before setting SRR0 and SRR1. */
+	li	r0,MSR_RI
+	mfmsr	r9
+	andc	r9,r9,r0
+	mtmsrd	r9,1
 
 	/*
-	 * The stack is no longer in use, decrement in_nmi.
+	 * MSR_RI is clear, now we can decrement paca->in_nmi.
 	 */
 	lhz	r10,PACA_IN_NMI(r13)
 	subi	r10,r10,1
 	sth	r10,PACA_IN_NMI(r13)
 
-	b	ret_from_except
+	/*
+	 * Restore soft mask settings.
+	 */
+	ld	r10,_DAR(r1)
+	stb	r10,PACAIRQHAPPENED(r13)
+	ld	r10,SOFTE(r1)
+	stb	r10,PACAIRQSOFTMASK(r13)
+
+	/*
+	 * Keep below code in synch with MACHINE_CHECK_HANDLER_WINDUP.
+	 * Should share common bits...
+	 */
+
+	/* Move original SRR0 and SRR1 into the respective regs */
+	ld	r9,_MSR(r1)
+	mtspr	SPRN_SRR1,r9
+	ld	r3,_NIP(r1)
+	mtspr	SPRN_SRR0,r3
+	ld	r9,_CTR(r1)
+	mtctr	r9
+	ld	r9,_XER(r1)
+	mtxer	r9
+	ld	r9,_LINK(r1)
+	mtlr	r9
+	REST_GPR(0, r1)
+	REST_8GPRS(2, r1)
+	REST_GPR(10, r1)
+	ld	r11,_CCR(r1)
+	mtcr	r11
+	REST_GPR(11, r1)
+	REST_2GPRS(12, r1)
+	/* restore original r1. */
+	ld	r1,GPR1(r1)
+	RFI_TO_USER_OR_KERNEL
 
 #ifdef CONFIG_PPC_PSERIES
 /*
···
 	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
 	mtlr	r10
 
-	beq-	8f		/* if bad address, make full stack frame */
+	/*
+	 * Large address, check whether we have to allocate new contexts.
+	 */
+	beq-	8f
 
 	bne-	cr5,2f		/* if unrecoverable exception, oops */
 
···
 
 	bne	cr4,1f		/* returning to kernel */
 
-.machine	push
-.machine	"power4"
 	mtcrf	0x80,r9
 	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
 	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
 	mtcrf	0x02,r9		/* I/D indication is in cr6 */
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
-.machine	pop
 
 	RESTORE_CTR(r9, PACA_EXSLB)
 	RESTORE_PPR_PACA(PACA_EXSLB, r9)
···
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 1:
-.machine	push
-.machine	"power4"
 	mtcrf	0x80,r9
 	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
 	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
 	mtcrf	0x02,r9		/* I/D indication is in cr6 */
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
-.machine	pop
 
 	RESTORE_CTR(r9, PACA_EXSLB)
 	RESTORE_PPR_PACA(PACA_EXSLB, r9)
···
 	mr	r3,r12
 	mfspr	r11,SPRN_SRR0
 	mfspr	r12,SPRN_SRR1
-	LOAD_HANDLER(r10,bad_addr_slb)
+	LOAD_HANDLER(r10, large_addr_slb)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
···
 	bl	unrecoverable_exception
 	b	1b
 
-EXC_COMMON_BEGIN(bad_addr_slb)
+EXC_COMMON_BEGIN(large_addr_slb)
 	EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB)
 	RECONCILE_IRQ_STATE(r10, r11)
 	ld	r3, PACA_EXSLB+EX_DAR(r13)
···
 	std	r10, _TRAP(r1)
 2:	bl	save_nvgprs
 	addi	r3, r1, STACK_FRAME_OVERHEAD
-	bl	slb_miss_bad_addr
+	bl	slb_miss_large_addr
 	b	ret_from_except
 
 EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
···
 	bne+	denorm_assist
 #endif
 
-	KVMTEST_PR(0x1500)
+	KVMTEST_HV(0x1500)
 	EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV)
 EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100)
 
···
 EXC_VIRT_NONE(0x5500, 0x100)
 #endif
 
-TRAMP_KVM_SKIP(PACA_EXGEN, 0x1500)
+TRAMP_KVM_HV(PACA_EXGEN, 0x1500)
 
 #ifdef CONFIG_PPC_DENORMALISATION
 TRAMP_REAL_BEGIN(denorm_assist)
···
 	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
 	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
 	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
 
 	/* order ld/st prior to dcbt stop all streams with flushing */
 	sync
···
 	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
 	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
 	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
 
 	/* order ld/st prior to dcbt stop all streams with flushing */
 	sync

arch/powerpc/kernel/head_64.S

···
 	 * physical cpu id in r24, we need to search the pacas to find
 	 * which logical id maps to our physical one.
 	 */
-	LOAD_REG_ADDR(r13, paca)	/* Load paca pointer		 */
-	ld	r13,0(r13)		/* Get base vaddr of paca array	 */
 #ifndef CONFIG_SMP
-	addi	r13,r13,PACA_SIZE	/* know r13 if used accidentally */
 	b	kexec_wait		/* wait for next kernel if !SMP	 */
 #else
+	LOAD_REG_ADDR(r8, paca_ptrs)	/* Load paca_ptrs pointe	 */
+	ld	r8,0(r8)		/* Get base vaddr of array	 */
 	LOAD_REG_ADDR(r7, nr_cpu_ids)	/* Load nr_cpu_ids address       */
 	lwz	r7,0(r7)		/* also the max paca allocated 	 */
 	li	r5,0			/* logical cpu id                */
-1:	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
+1:
+	sldi	r9,r5,3			/* get paca_ptrs[] index from cpu id */
+	ldx	r13,r9,r8		/* r13 = paca_ptrs[cpu id]       */
+	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
 	cmpw	r6,r24			/* Compare to our id             */
 	beq	2f
-	addi	r13,r13,PACA_SIZE	/* Loop to next PACA on miss     */
 	addi	r5,r5,1
 	cmpw	r5,r7			/* Check if more pacas exist     */
 	blt	1b
···
 	mtmsrd	r3			/* RI on */
 
 	/* Set up a paca value for this processor. */
-	LOAD_REG_ADDR(r4,paca)		/* Load paca pointer		*/
-	ld	r4,0(r4)		/* Get base vaddr of paca array	*/
-	mulli	r13,r24,PACA_SIZE	/* Calculate vaddr of right paca */
-	add	r13,r13,r4		/* for this processor.		*/
+	LOAD_REG_ADDR(r4,paca_ptrs)	/* Load paca pointer		*/
+	ld	r4,0(r4)		/* Get base vaddr of paca_ptrs array */
+	sldi	r5,r24,3		/* get paca_ptrs[] index from cpu id */
+	ldx	r13,r5,r4		/* r13 = paca_ptrs[cpu id]       */
 	SET_PACA(r13)			/* Save vaddr of paca in an SPRG*/
 
 	/* Mark interrupts soft and hard disabled (they might be enabled

arch/powerpc/kernel/hw_breakpoint.c

···
 #include <asm/hw_breakpoint.h>
 #include <asm/processor.h>
 #include <asm/sstep.h>
+#include <asm/debug.h>
 #include <linux/uaccess.h>
 
 /*
···
 	 * HW_BREAKPOINT_ALIGN by rounding off to the lower address, the
 	 * 'symbolsize' should satisfy the check below.
 	 */
+	if (!ppc_breakpoint_available())
+		return -ENODEV;
 	length_max = 8; /* DABR */
 	if (cpu_has_feature(CPU_FTR_DAWR)) {
 		length_max = 512 ; /* 64 doublewords */

arch/powerpc/kernel/idle_book3s.S

···
  * r3 - PSSCR value corresponding to the requested stop state.
  */
 power_enter_stop:
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/* Tell KVM we're entering idle */
-	li	r4,KVM_HWTHREAD_IN_IDLE
-	/* DO THIS IN REAL MODE!  See comment above. */
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
 /*
  * Check if we are executing the lite variant with ESL=EC=0
  */
···
 	bne	 .Lhandle_esl_ec_set
 	PPC_STOP
 	li	r3,0  /* Since we didn't lose state, return 0 */
+	std	r3, PACA_REQ_PSSCR(r13)
 
 	/*
 	 * pnv_wakeup_noloss() expects r12 to contain the SRR1 value so
···
 /*
  * Entered with MSR[EE]=0 and no soft-masked interrupts pending.
  * r3 contains desired PSSCR register value.
+ *
+ * Offline (CPU unplug) case also must notify KVM that the CPU is
+ * idle.
  */
+_GLOBAL(power9_offline_stop)
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/*
+	 * Tell KVM we're entering idle.
+	 * This does not have to be done in real mode because the P9 MMU
+	 * is independent per-thread. Some steppings share radix/hash mode
+	 * between threads, but in that case KVM has a barrier sync in real
+	 * mode before and after switching between radix and hash.
+	 */
+	li	r4,KVM_HWTHREAD_IN_IDLE
+	stb	r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
+	/* fall through */
+
 _GLOBAL(power9_idle_stop)
 	std	r3, PACA_REQ_PSSCR(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+BEGIN_FTR_SECTION
+	sync
+	lwz	r5, PACA_DONT_STOP(r13)
+	cmpwi	r5, 0
+	bne	1f
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
+#endif
 	mtspr 	SPRN_PSSCR,r3
 	LOAD_REG_ADDR(r4,power_enter_stop)
 	b	pnv_powersave_common
 	/* No return */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+1:
+	/*
+	 * We get here when TM / thread reconfiguration bug workaround
+	 * code wants to get the CPU into SMT4 mode, and therefore
+	 * we are being asked not to stop.
+	 */
+	li	r3, 0
+	std	r3, PACA_REQ_PSSCR(r13)
+	blr		/* return 0 for wakeup cause / SRR1 value */
+#endif
 
 /*
  * On waking up from stop 0,1,2 with ESL=1 on POWER9 DD1,
···
 	mr	r3,r12
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	lbz	r0,HSTATE_HWTHREAD_STATE(r13)
+	cmpwi	r0,KVM_HWTHREAD_IN_KERNEL
+	beq	1f
 	li	r0,KVM_HWTHREAD_IN_KERNEL
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 	/* Order setting hwthread_state vs. testing hwthread_req */
···
 	mfspr	r5, SPRN_PSSCR
 	rldicl  r5,r5,4,60
 ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_POWER9_DD1, 71)
+	li	r0, 0		/* clear requested_psscr to say we're awake */
+	std	r0, PACA_REQ_PSSCR(r13)
 	cmpd	cr4,r5,r4
 	bge	cr4,pnv_wakeup_tb_loss /* returns to caller */
 
···
 	mtspr	SPRN_PTCR,r4
 	ld	r4,_RPR(r1)
 	mtspr	SPRN_RPR,r4
+	ld	r4,_AMOR(r1)
+	mtspr	SPRN_AMOR,r4
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	ld	r4,_TSCR(r1)

arch/powerpc/kernel/iomap.c

···
 {
 	return readq(addr);
 }
+u64 ioread64_lo_hi(void __iomem *addr)
+{
+	return readq(addr);
+}
+u64 ioread64_hi_lo(void __iomem *addr)
+{
+	return readq(addr);
+}
 u64 ioread64be(void __iomem *addr)
 {
 	return readq_be(addr);
 }
+u64 ioread64be_lo_hi(void __iomem *addr)
+{
+	return readq_be(addr);
+}
+u64 ioread64be_hi_lo(void __iomem *addr)
+{
+	return readq_be(addr);
+}
 EXPORT_SYMBOL(ioread64);
+EXPORT_SYMBOL(ioread64_lo_hi);
+EXPORT_SYMBOL(ioread64_hi_lo);
 EXPORT_SYMBOL(ioread64be);
+EXPORT_SYMBOL(ioread64be_lo_hi);
+EXPORT_SYMBOL(ioread64be_hi_lo);
 #endif /* __powerpc64__ */
 
 void iowrite8(u8 val, void __iomem *addr)
···
 {
 	writeq(val, addr);
 }
+void iowrite64_lo_hi(u64 val, void __iomem *addr)
+{
+	writeq(val, addr);
+}
+void iowrite64_hi_lo(u64 val, void __iomem *addr)
+{
+	writeq(val, addr);
+}
 void iowrite64be(u64 val, void __iomem *addr)
 {
 	writeq_be(val, addr);
 }
+void iowrite64be_lo_hi(u64 val, void __iomem *addr)
+{
+	writeq_be(val, addr);
+}
+void iowrite64be_hi_lo(u64 val, void __iomem *addr)
+{
+	writeq_be(val, addr);
+}
 EXPORT_SYMBOL(iowrite64);
+EXPORT_SYMBOL(iowrite64_lo_hi);
+EXPORT_SYMBOL(iowrite64_hi_lo);
 EXPORT_SYMBOL(iowrite64be);
+EXPORT_SYMBOL(iowrite64be_lo_hi);
+EXPORT_SYMBOL(iowrite64be_hi_lo);
 #endif /* __powerpc64__ */
 
 /*

arch/powerpc/kernel/kprobes.c

···
 	}
 
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-	regs->nip = orig_ret_address;
+
 	/*
-	 * Make LR point to the orig_ret_address.
-	 * When the 'nop' inside the kretprobe_trampoline
-	 * is optimized, we can do a 'blr' after executing the
-	 * detour buffer code.
+	 * We get here through one of two paths:
+	 * 1. by taking a trap -> kprobe_handler() -> here
+	 * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here
+	 *
+	 * When going back through (1), we need regs->nip to be setup properly
+	 * as it is used to determine the return address from the trap.
+	 * For (2), since nip is not honoured with optprobes, we instead setup
+	 * the link register properly so that the subsequent 'blr' in
+	 * kretprobe_trampoline jumps back to the right instruction.
+	 *
+	 * For nip, we should set the address to the previous instruction since
+	 * we end up emulating it in kprobe_handler(), which increments the nip
+	 * again.
 	 */
+	regs->nip = orig_ret_address - 4;
 	regs->link = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
 	}
-	/*
-	 * By returning a non-zero value, we are telling
-	 * kprobe_handler() that we don't want the post_handler
-	 * to run (and have re-enabled preemption)
-	 */
-	return 1;
+
+	return 0;
 }
 NOKPROBE_SYMBOL(trampoline_probe_handler);
 

arch/powerpc/kernel/machine_kexec_64.c

···
 	 * are correctly onlined.  If somehow we start a CPU on boot with RTAS
 	 * start-cpu, but somehow that CPU doesn't write callin_cpu_map[] in
 	 * time, the boot CPU will timeout.  If it does eventually execute
-	 * stuff, the secondary will start up (paca[].cpu_start was written) and
-	 * get into a peculiar state.  If the platform supports
-	 * smp_ops->take_timebase(), the secondary CPU will probably be spinning
-	 * in there.  If not (i.e. pseries), the secondary will continue on and
-	 * try to online itself/idle/etc. If it survives that, we need to find
-	 * these possible-but-not-online-but-should-be CPUs and chaperone them
-	 * into kexec_smp_wait().
+	 * stuff, the secondary will start up (paca_ptrs[]->cpu_start was
+	 * written) and get into a peculiar state.
+	 * If the platform supports smp_ops->take_timebase(), the secondary CPU
+	 * will probably be spinning in there.  If not (i.e. pseries), the
+	 * secondary will continue on and try to online itself/idle/etc. If it
+	 * survives that, we need to find these
+	 * possible-but-not-online-but-should-be CPUs and chaperone them into
+	 * kexec_smp_wait().
 	 */
 	for_each_online_cpu(i) {
 		if (i == my_cpu)
 			continue;
 
-		while (paca[i].kexec_state < wait_state) {
+		while (paca_ptrs[i]->kexec_state < wait_state) {
 			barrier();
 			if (i != notified) {
 				printk(KERN_INFO "kexec: waiting for cpu %d "
 				       "(physical %d) to enter %i state\n",
-				       i, paca[i].hw_cpu_id, wait_state);
+				       i, paca_ptrs[i]->hw_cpu_id, wait_state);
 				notified = i;
 			}
 		}
···
 	kexec_stack.thread_info.cpu = current_thread_info()->cpu;
 
 	/* We need a static PACA, too; copy this CPU's PACA over and switch to
-	 * it.  Also poison per_cpu_offset to catch anyone using non-static
-	 * data.
+	 * it. Also poison per_cpu_offset and NULL lppaca to catch anyone using
+	 * non-static data.
 	 */
 	memcpy(&kexec_paca, get_paca(), sizeof(struct paca_struct));
 	kexec_paca.data_offset = 0xedeaddeadeeeeeeeUL;
-	paca = (struct paca_struct *)RELOC_HIDE(&kexec_paca, 0) -
-		kexec_paca.paca_index;
+#ifdef CONFIG_PPC_PSERIES
+	kexec_paca.lppaca_ptr = NULL;
+#endif
+	paca_ptrs[kexec_paca.paca_index] = &kexec_paca;
+
 	setup_paca(&kexec_paca);
 
-	/* XXX: If anyone does 'dynamic lppacas' this will also need to be
-	 * switched to a static version!
+	/*
+	 * The lppaca should be unregistered at this point so the HV won't
+	 * touch it. In the case of a crash, none of the lppacas are
+	 * unregistered so there is not much we can do about it here.
 	 */
+
 	/*
 	 * On Book3S, the copy must happen with the MMU off if we are either
 	 * using Radix page tables or we are not in an LPAR since we can

arch/powerpc/kernel/machine_kexec_file_64.c

···
 
 	/* We don't support crash kernels yet. */
 	if (image->type == KEXEC_TYPE_CRASH)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) {
 		fops = kexec_file_loaders[i];

arch/powerpc/kernel/misc_64.S

···
 	blr
 EXPORT_SYMBOL(flush_dcache_range)
 
-/*
- * Like above, but works on non-mapped physical addresses.
- * Use only for non-LPAR setups ! It also assumes real mode
- * is cacheable. Used for flushing out the DART before using
- * it as uncacheable memory 
- *
- * flush_dcache_phys_range(unsigned long start, unsigned long stop)
- *
- *    flush all bytes from start to stop-1 inclusive
- */
-_GLOBAL(flush_dcache_phys_range)
- 	ld	r10,PPC64_CACHES@toc(r2)
-	lwz	r7,DCACHEL1BLOCKSIZE(r10)	/* Get dcache block size */
-	addi	r5,r7,-1
-	andc	r6,r3,r5		/* round low to line bdy */
-	subf	r8,r6,r4		/* compute length */
-	add	r8,r8,r5		/* ensure we get enough */
-	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)	/* Get log-2 of dcache block size */
-	srw.	r8,r8,r9		/* compute line count */
-	beqlr				/* nothing to do? */
-	mfmsr	r5			/* Disable MMU Data Relocation */
-	ori	r0,r5,MSR_DR
-	xori	r0,r0,MSR_DR
-	sync
-	mtmsr	r0
-	sync
-	isync
-	mtctr	r8
-0:	dcbst	0,r6
-	add	r6,r6,r7
-	bdnz	0b
-	sync
-	isync
-	mtmsr	r5			/* Re-enable MMU Data Relocation */
-	sync
-	isync
-	blr
-
 _GLOBAL(flush_inval_dcache_range)
  	ld	r10,PPC64_CACHES@toc(r2)
 	lwz	r7,DCACHEL1BLOCKSIZE(r10)	/* Get dcache block size */

arch/powerpc/kernel/nvram_64.c

···
 
 	tmp_index = part->index;
 
-	rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info),
-				&tmp_index);
+	rc = ppc_md.nvram_write((char *)&info, sizeof(info), &tmp_index);
 	if (rc <= 0) {
 		pr_err("%s: Failed nvram_write (%d)\n", __func__, rc);
 		return rc;
···
 	tmp_index = part->index;
 
 	if (part->os_partition) {
-		rc = ppc_md.nvram_read((char *)&info,
-					sizeof(struct err_log_info),
-					&tmp_index);
+		rc = ppc_md.nvram_read((char *)&info, sizeof(info), &tmp_index);
 		if (rc <= 0) {
 			pr_err("%s: Failed nvram_read (%d)\n", __func__, rc);
 			return rc;
···
 			       "detected: 0-length partition\n");
 			goto out;
 		}
-		tmp_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL);
+		tmp_part = kmalloc(sizeof(*tmp_part), GFP_KERNEL);
 		err = -ENOMEM;
 		if (!tmp_part) {
 			printk(KERN_ERR "nvram_scan_partitions: kmalloc failed\n");

arch/powerpc/kernel/paca.c

···
 
 #include "setup.h"
 
-#ifdef CONFIG_PPC_BOOK3S
+#ifndef CONFIG_SMP
+#define boot_cpuid 0
+#endif
+
+static void *__init alloc_paca_data(unsigned long size, unsigned long align,
+				unsigned long limit, int cpu)
+{
+	unsigned long pa;
+	int nid;
+
+	/*
+	 * boot_cpuid paca is allocated very early before cpu_to_node is up.
+	 * Set bottom-up mode, because the boot CPU should be on node-0,
+	 * which will put its paca in the right place.
+	 */
+	if (cpu == boot_cpuid) {
+		nid = -1;
+		memblock_set_bottom_up(true);
+	} else {
+		nid = early_cpu_to_node(cpu);
+	}
+
+	pa = memblock_alloc_base_nid(size, align, limit, nid, MEMBLOCK_NONE);
+	if (!pa) {
+		pa = memblock_alloc_base(size, align, limit);
+		if (!pa)
+			panic("cannot allocate paca data");
+	}
+
+	if (cpu == boot_cpuid)
+		memblock_set_bottom_up(false);
+
+	return __va(pa);
+}
+
+#ifdef CONFIG_PPC_PSERIES
 
 /*
- * The structure which the hypervisor knows about - this structure
- * should not cross a page boundary.  The vpa_init/register_vpa call
- * is now known to fail if the lppaca structure crosses a page
- * boundary.  The lppaca is also used on POWER5 pSeries boxes.
- * The lppaca is 640 bytes long, and cannot readily
- * change since the hypervisor knows its layout, so a 1kB alignment
- * will suffice to ensure that it doesn't cross a page boundary.
+ * See asm/lppaca.h for more detail.
+ *
+ * lppaca structures must must be 1kB in size, L1 cache line aligned,
+ * and not cross 4kB boundary. A 1kB size and 1kB alignment will satisfy
+ * these requirements.
  */
-struct lppaca lppaca[] = {
-	[0 ... (NR_LPPACAS-1)] = {
+static inline void init_lppaca(struct lppaca *lppaca)
+{
+	BUILD_BUG_ON(sizeof(struct lppaca) != 640);
+
+	*lppaca = (struct lppaca) {
 		.desc = cpu_to_be32(0xd397d781),	/* "LpPa" */
-		.size = cpu_to_be16(sizeof(struct lppaca)),
+		.size = cpu_to_be16(0x400),
 		.fpregs_in_use = 1,
 		.slb_count = cpu_to_be16(64),
 		.vmxregs_in_use = 0,
-		.page_ins = 0,
-	},
+		.page_ins = 0, };
 };
 
-static struct lppaca *extra_lppacas;
-static long __initdata lppaca_size;
-
-static void __init allocate_lppacas(int nr_cpus, unsigned long limit)
-{
-	if (nr_cpus <= NR_LPPACAS)
-		return;
-
-	lppaca_size = PAGE_ALIGN(sizeof(struct lppaca) *
-				 (nr_cpus - NR_LPPACAS));
-	extra_lppacas = __va(memblock_alloc_base(lppaca_size,
-						 PAGE_SIZE, limit));
-}
-
-static struct lppaca * __init new_lppaca(int cpu)
+static struct lppaca * __init new_lppaca(int cpu, unsigned long limit)
 {
 	struct lppaca *lp;
+	size_t size = 0x400;
 
-	if (cpu < NR_LPPACAS)
-		return &lppaca[cpu];
+	BUILD_BUG_ON(size < sizeof(struct lppaca));
 
-	lp = extra_lppacas + (cpu - NR_LPPACAS);
-	*lp = lppaca[0];
+	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+		return NULL;
+
+	lp = alloc_paca_data(size, 0x400, limit, cpu);
+	init_lppaca(lp);
 
 	return lp;
 }
-
-static void __init free_lppacas(void)
-{
-	long new_size = 0, nr;
-
-	if (!lppaca_size)
-		return;
-	nr = num_possible_cpus() - NR_LPPACAS;
-	if (nr > 0)
-		new_size = PAGE_ALIGN(nr * sizeof(struct lppaca));
-	if (new_size >= lppaca_size)
-		return;
-
-	memblock_free(__pa(extra_lppacas) + new_size, lppaca_size - new_size);
-	lppaca_size = new_size;
-}
-
-#else
-
-static inline void allocate_lppacas(int nr_cpus, unsigned long limit) { }
-static inline void free_lppacas(void) { }
-
 #endif /* CONFIG_PPC_BOOK3S */
 
 #ifdef CONFIG_PPC_BOOK3S_64
 
 /*
- * 3 persistent SLBs are registered here.  The buffer will be zero
+ * 3 persistent SLBs are allocated here.  The buffer will be zero
  * initially, hence will all be invaild until we actually write them.
  *
  * If you make the number of persistent SLB entries dynamic, please also
  * update PR KVM to flush and restore them accordingly.
  */
-static struct slb_shadow * __initdata slb_shadow;
-
-static void __init allocate_slb_shadows(int nr_cpus, int limit)
-{
-	int size = PAGE_ALIGN(sizeof(struct slb_shadow) * nr_cpus);
-
-	if (early_radix_enabled())
-		return;
-
-	slb_shadow = __va(memblock_alloc_base(size, PAGE_SIZE, limit));
-	memset(slb_shadow, 0, size);
-}
-
-static struct slb_shadow * __init init_slb_shadow(int cpu)
+static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit)
 {
 	struct slb_shadow *s;
 
-	if (early_radix_enabled())
-		return NULL;
+	if (cpu != boot_cpuid) {
+		/*
+		 * Boot CPU comes here before early_radix_enabled
+		 * is parsed (e.g., for disable_radix). So allocate
+		 * always and this will be fixed up in free_unused_pacas.
+		 */
+		if (early_radix_enabled())
+			return NULL;
+	}
 
-	s = &slb_shadow[cpu];
-
-	/*
-	 * When we come through here to initialise boot_paca, the slb_shadow
-	 * buffers are not allocated yet. That's OK, we'll get one later in
-	 * boot, but make sure we don't corrupt memory at 0.
-	 */
-	if (!slb_shadow)
-		return NULL;
+	s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu);
+	memset(s, 0, sizeof(*s));
 
 	s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
 	s->buffer_length = cpu_to_be32(sizeof(*s));
 
 	return s;
 }
-
-#else /* !CONFIG_PPC_BOOK3S_64 */
-
-static void __init allocate_slb_shadows(int nr_cpus, int limit) { }
 
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
···
  * processors.  The processor VPD array needs one entry per physical
  * processor (not thread).
  */
-struct paca_struct *paca;
-EXPORT_SYMBOL(paca);
+struct paca_struct **paca_ptrs __read_mostly;
+EXPORT_SYMBOL(paca_ptrs);
 
 void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 {
-#ifdef CONFIG_PPC_BOOK3S
-	new_paca->lppaca_ptr = new_lppaca(cpu);
-#else
+#ifdef CONFIG_PPC_PSERIES
+	new_paca->lppaca_ptr = NULL;
+#endif
+#ifdef CONFIG_PPC_BOOK3E
 	new_paca->kernel_pgd = swapper_pg_dir;
 #endif
 	new_paca->lock_token = 0x8000;
···
 	new_paca->__current = &init_task;
 	new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL;
 #ifdef CONFIG_PPC_BOOK3S_64
-	new_paca->slb_shadow_ptr = init_slb_shadow(cpu);
+	new_paca->slb_shadow_ptr = NULL;
 #endif
 
 #ifdef CONFIG_PPC_BOOK3E
···
 
 }
 
-static int __initdata paca_size;
+static int __initdata paca_nr_cpu_ids;
+static int __initdata paca_ptrs_size;
+static int __initdata paca_struct_size;
 
-void __init allocate_pacas(void)
+void __init allocate_paca_ptrs(void)
+{
+	paca_nr_cpu_ids = nr_cpu_ids;
+
+	paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
+	paca_ptrs = __va(memblock_alloc(paca_ptrs_size, 0));
+	memset(paca_ptrs, 0x88, paca_ptrs_size);
+}
+
+void __init allocate_paca(int cpu)
 {
 	u64 limit;
-	int cpu;
+	struct paca_struct *paca;
+
+	BUG_ON(cpu >= paca_nr_cpu_ids);
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	/*
···
 	limit = ppc64_rma_size;
 #endif
 
-	paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
+	paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES,
+				limit, cpu);
+	paca_ptrs[cpu] = paca;
+	memset(paca, 0, sizeof(struct paca_struct));
 
-	paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit));
-	memset(paca, 0, paca_size);
-
-	printk(KERN_DEBUG "Allocated %u bytes for %u pacas at %p\n",
-		paca_size, nr_cpu_ids, paca);
-
-	allocate_lppacas(nr_cpu_ids, limit);
-
-	allocate_slb_shadows(nr_cpu_ids, limit);
-
-	/* Can't use for_each_*_cpu, as they aren't functional yet */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
-		initialise_paca(&paca[cpu], cpu);
+	initialise_paca(paca, cpu);
+#ifdef CONFIG_PPC_PSERIES
+	paca->lppaca_ptr = new_lppaca(cpu, limit);
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
+#endif
+	paca_struct_size += sizeof(struct paca_struct);
 }
 
 void __init free_unused_pacas(void)
 {
-	int new_size;
+	int new_ptrs_size;
 
-	new_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
+	new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
+	if (new_ptrs_size < paca_ptrs_size)
+		memblock_free(__pa(paca_ptrs) + new_ptrs_size,
+					paca_ptrs_size - new_ptrs_size);
 
-	if (new_size >= paca_size)
-		return;
+	paca_nr_cpu_ids = nr_cpu_ids;
+	paca_ptrs_size = new_ptrs_size;
 
-	memblock_free(__pa(paca) + new_size, paca_size - new_size);
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (early_radix_enabled()) {
+		/* Ugly fixup, see new_slb_shadow() */
+		memblock_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr),
+				sizeof(struct slb_shadow));
+		paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL;
+	}
+#endif
 
-	printk(KERN_DEBUG "Freed %u bytes for unused pacas\n",
-		paca_size - new_size);
-
-	paca_size = new_size;
-
-	free_lppacas();
+	printk(KERN_DEBUG "Allocated %u bytes for %u pacas\n",
+			paca_ptrs_size + paca_struct_size, nr_cpu_ids);
 }
 
 void copy_mm_to_paca(struct mm_struct *mm)
···
 #ifdef CONFIG_PPC_MM_SLICES
 	VM_BUG_ON(!mm->context.slb_addr_limit);
 	get_paca()->mm_ctx_slb_addr_limit = mm->context.slb_addr_limit;
-	get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize;
+	memcpy(&get_paca()->mm_ctx_low_slices_psize,
+	       &context->low_slices_psize, sizeof(context->low_slices_psize));
 	memcpy(&get_paca()->mm_ctx_high_slices_psize,
 	       &context->high_slices_psize, TASK_SLICE_ARRAY_SZ(mm));
 #else /* CONFIG_PPC_MM_SLICES */

arch/powerpc/kernel/process.c

···
 EXPORT_SYMBOL(__msr_check_and_clear);
 
 #ifdef CONFIG_PPC_FPU
-void __giveup_fpu(struct task_struct *tsk)
+static void __giveup_fpu(struct task_struct *tsk)
 {
 	unsigned long msr;
 
···
 	regs->msr = msr;
 }
 
-void save_all(struct task_struct *tsk)
+static void save_all(struct task_struct *tsk)
 {
 	unsigned long usermsr;
 
···
 {
 	thread->hw_brk.address = 0;
 	thread->hw_brk.type = 0;
-	set_breakpoint(&thread->hw_brk);
+	if (ppc_breakpoint_available())
+		set_breakpoint(&thread->hw_brk);
 }
 #endif /* !CONFIG_HAVE_HW_BREAKPOINT */
 #endif	/* CONFIG_PPC_ADV_DEBUG_REGS */
···
 	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
 
 	if (cpu_has_feature(CPU_FTR_DAWR))
+		// Power8 or later
 		set_dawr(brk);
-	else
+	else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		// Power7 or earlier
 		set_dabr(brk);
+	else
+		// Shouldn't happen due to higher level checks
+		WARN_ON_ONCE(1);
 }
 
 void set_breakpoint(struct arch_hw_breakpoint *brk)
···
 	__set_breakpoint(brk);
 	preempt_enable();
 }
+
+/* Check if we have DAWR or DABR hardware */
+bool ppc_breakpoint_available(void)
+{
+	if (cpu_has_feature(CPU_FTR_DAWR))
+		return true; /* POWER8 DAWR */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		return false; /* POWER9 with DAWR disabled */
+	/* DABR: Everything but POWER8 and POWER9 */
+	return true;
+}
+EXPORT_SYMBOL_GPL(ppc_breakpoint_available);
 
 #ifdef CONFIG_PPC64
 DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array);

arch/powerpc/kernel/prom.c

···
 
 static void __init check_cpu_feature_properties(unsigned long node)
 {
-	unsigned long i;
+	int i;
 	struct feature_property *fp = feature_properties;
 	const __be32 *prop;
 
-	for (i = 0; i < ARRAY_SIZE(feature_properties); ++i, ++fp) {
+	for (i = 0; i < (int)ARRAY_SIZE(feature_properties); ++i, ++fp) {
 		prop = of_get_flat_dt_prop(node, fp->name, NULL);
 		if (prop && be32_to_cpup(prop) >= fp->min_value) {
 			cur_cpu_spec->cpu_features |= fp->cpu_feature;
···
 	DBG("boot cpu: logical %d physical %d\n", found,
 	    be32_to_cpu(intserv[found_thread]));
 	boot_cpuid = found;
-	set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread]));
 
 	/*
 	 * PAPR defines "logical" PVR values for cpus that
···
 		cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
 	else if (!dt_cpu_ftrs_in_use())
 		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+	allocate_paca(boot_cpuid);
 #endif
+	set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread]));
 
 	return 0;
 }
···
 	 * FIXME .. and the initrd too? */
 	move_device_tree();
 
-	allocate_pacas();
+	allocate_paca_ptrs();
 
 	DBG("Scanning CPUs ...\n");
 
···
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * Early firmware scanning must use this rather than
+	 * get_hard_smp_processor_id because we don't have pacas allocated
+	 * until memory topology is discovered.
+	 */
+	if (cpu_to_phys_id != NULL)
+		return (int)phys_id == cpu_to_phys_id[cpu];
+#endif
+
 	return (int)phys_id == get_hard_smp_processor_id(cpu);
 }

arch/powerpc/kernel/prom_init.c

···
 static unsigned long __initdata prom_tce_alloc_end;
 #endif
 
-static bool __initdata prom_radix_disable;
+static bool prom_radix_disable __initdata = !IS_ENABLED(CONFIG_PPC_RADIX_MMU_DEFAULT);
 
 struct platform_support {
 	bool hash_mmu;
···
 
 	opt = strstr(prom_cmd_line, "disable_radix");
 	if (opt) {
-		prom_debug("Radix disabled from cmdline\n");
-		prom_radix_disable = true;
+		opt += 13;
+		if (*opt && *opt == '=') {
+			bool val;
+
+			if (kstrtobool(++opt, &val))
+				prom_radix_disable = false;
+			else
+				prom_radix_disable = val;
+		} else
+			prom_radix_disable = true;
 	}
+	if (prom_radix_disable)
+		prom_debug("Radix disabled from cmdline\n");
 }
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
···
 		}
 	}
 
-	if (supported.radix_mmu && supported.radix_gtse) {
+	if (supported.radix_mmu && supported.radix_gtse &&
+	    IS_ENABLED(CONFIG_PPC_RADIX_MMU)) {
 		/* Radix preferred - but we require GTSE for now */
 		prom_debug("Asking for radix with GTSE\n");
 		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
···
 		 * size to 4 MB.  This is enough to map 2GB of PCI DMA space.
 		 * By doing this, we avoid the pitfalls of trying to DMA to
 		 * MMIO space and the DMA alias hole.
-		 *
-		 * On POWER4, firmware sets the TCE region by assuming
-		 * each TCE table is 8MB. Using this memory for anything
-		 * else will impact performance, so we always allocate 8MB.
-		 * Anton
 		 */
-		if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p))
-			minsize = 8UL << 20;
-		else
-			minsize = 4UL << 20;
+		minsize = 4UL << 20;
 
 		/* Align to the greater of the align or size */
 		align = max(minalign, minsize);

arch/powerpc/kernel/prom_init_check.sh

···
 WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush
 _end enter_prom memcpy memset reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
-strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224
+strcmp strcpy strlcpy strlen strncmp strstr kstrtobool logo_linux_clut224
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
 __prom_init_toc_start __prom_init_toc_end btext_setup_display TOC."
 

arch/powerpc/kernel/ptrace.c

···
 #include <asm/switch_to.h>
 #include <asm/tm.h>
 #include <asm/asm-prototypes.h>
+#include <asm/debug.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
···
 	struct perf_event_attr attr;
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 #ifndef CONFIG_PPC_ADV_DEBUG_REGS
+	bool set_bp = true;
 	struct arch_hw_breakpoint hw_brk;
 #endif
 
···
 	hw_brk.address = data & (~HW_BRK_TYPE_DABR);
 	hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL;
 	hw_brk.len = 8;
+	set_bp = (data) && (hw_brk.type & HW_BRK_TYPE_RDWR);
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	bp = thread->ptrace_bps[0];
-	if ((!data) || !(hw_brk.type & HW_BRK_TYPE_RDWR)) {
+	if (!set_bp) {
 		if (bp) {
 			unregister_hw_breakpoint(bp);
 			thread->ptrace_bps[0] = NULL;
···
 		return PTR_ERR(bp);
 	}
 
+#else /* !CONFIG_HAVE_HW_BREAKPOINT */
+	if (set_bp && (!ppc_breakpoint_available()))
+		return -ENODEV;
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 	task->thread.hw_brk = hw_brk;
 #else /* CONFIG_PPC_ADV_DEBUG_REGS */
···
 	if (child->thread.hw_brk.address)
 		return -ENOSPC;
 
+	if (!ppc_breakpoint_available())
+		return -ENODEV;
+
 	child->thread.hw_brk = brk;
 
 	return 1;
···
 #endif
 #else /* !CONFIG_PPC_ADV_DEBUG_REGS */
 		dbginfo.num_instruction_bps = 0;
-		dbginfo.num_data_bps = 1;
+		if (ppc_breakpoint_available())
+			dbginfo.num_data_bps = 1;
+		else
+			dbginfo.num_data_bps = 0;
 		dbginfo.num_condition_regs = 0;
 #ifdef CONFIG_PPC64
 		dbginfo.data_bp_alignment = 8;

arch/powerpc/kernel/security.c

···
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Security related flags and so on.
+//
+// Copyright 2018, Michael Ellerman, IBM Corporation.
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/seq_buf.h>
+
+#include <asm/security_features.h>
+
+
+unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	bool thread_priv;
+
+	thread_priv = security_ftr_enabled(SEC_FTR_L1D_THREAD_PRIV);
+
+	if (rfi_flush || thread_priv) {
+		struct seq_buf s;
+		seq_buf_init(&s, buf, PAGE_SIZE - 1);
+
+		seq_buf_printf(&s, "Mitigation: ");
+
+		if (rfi_flush)
+			seq_buf_printf(&s, "RFI Flush");
+
+		if (rfi_flush && thread_priv)
+			seq_buf_printf(&s, ", ");
+
+		if (thread_priv)
+			seq_buf_printf(&s, "L1D private per thread");
+
+		seq_buf_printf(&s, "\n");
+
+		return s.len;
+	}
+
+	if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) &&
+	    !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR))
+		return sprintf(buf, "Not affected\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	if (!security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR))
+		return sprintf(buf, "Not affected\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	bool bcs, ccd, ori;
+	struct seq_buf s;
+
+	seq_buf_init(&s, buf, PAGE_SIZE - 1);
+
+	bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED);
+	ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED);
+	ori = security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31);
+
+	if (bcs || ccd) {
+		seq_buf_printf(&s, "Mitigation: ");
+
+		if (bcs)
+			seq_buf_printf(&s, "Indirect branch serialisation (kernel only)");
+
+		if (bcs && ccd)
+			seq_buf_printf(&s, ", ");
+
+		if (ccd)
+			seq_buf_printf(&s, "Indirect branch cache disabled");
+	} else
+		seq_buf_printf(&s, "Vulnerable");
+
+	if (ori)
+		seq_buf_printf(&s, ", ori31 speculation barrier enabled");
+
+	seq_buf_printf(&s, "\n");
+
+	return s.len;
+}

arch/powerpc/kernel/setup-common.c

···
 }
 
 
+u32 *cpu_to_phys_id = NULL;
+
 /**
  * setup_cpu_maps - initialize the following cpu maps:
  *                  cpu_possible_mask
···
 
 	DBG("smp_setup_cpu_maps()\n");
 
+	cpu_to_phys_id = __va(memblock_alloc(nr_cpu_ids * sizeof(u32),
+							__alignof__(u32)));
+	memset(cpu_to_phys_id, 0, nr_cpu_ids * sizeof(u32));
+
 	for_each_node_by_type(dn, "cpu") {
 		const __be32 *intserv;
 		__be32 cpu_be;
···
 			intserv = of_get_property(dn, "reg", &len);
 			if (!intserv) {
 				cpu_be = cpu_to_be32(cpu);
+				/* XXX: what is this? uninitialized?? */
 				intserv = &cpu_be;	/* assume logical == phys */
 				len = 4;
 			}
···
 						"enable-method", "spin-table");
 
 			set_cpu_present(cpu, avail);
-			set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
 			set_cpu_possible(cpu, true);
+			cpu_to_phys_id[cpu] = be32_to_cpu(intserv[j]);
 			cpu++;
 		}
 
···
 	pr_info("-----------------------------------------------------\n");
 }
 
+#ifdef CONFIG_SMP
+static void smp_setup_pacas(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			continue;
+		allocate_paca(cpu);
+		set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]);
+	}
+
+	memblock_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32));
+	cpu_to_phys_id = NULL;
+}
+#endif
+
 /*
  * Called into from start_kernel this initializes memblock, which is used
  * to manage page allocation until mem_init is called.
···
 	/* Check the SMT related command line arguments (ppc64). */
 	check_smt_enabled();
 
-	/* On BookE, setup per-core TLB data structures. */
-	setup_tlb_core_data();
+	/* Parse memory topology */
+	mem_topology_setup();
 
 	/*
 	 * Release secondary cpus out of their spinloops at 0x60 now that
···
 	 * so smp_release_cpus() does nothing for them.
 	 */
 #ifdef CONFIG_SMP
+	smp_setup_pacas();
+
+	/* On BookE, setup per-core TLB data structures. */
+	setup_tlb_core_data();
+
 	smp_release_cpus();
 #endif
 
···
 #ifdef CONFIG_PPC64
 	if (!radix_enabled())
 		init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
+#elif defined(CONFIG_PPC_8xx)
+	init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW;
 #else
 #error	"context.addr_limit not initialized."
 #endif

arch/powerpc/kernel/setup.h

···
 #endif
 
 #ifdef CONFIG_PPC64
-void record_spr_defaults(void);
-#else
-static inline void record_spr_defaults(void) { };
-#endif
-
-#ifdef CONFIG_PPC64
 u64 ppc64_bolted_size(void);
+
+/* Default SPR values from firmware/kexec */
+extern unsigned long spr_default_dscr;
 #endif
 
 /*

arch/powerpc/kernel/setup_32.c

···
 #include <asm/udbg.h>
 #include <asm/code-patching.h>
 #include <asm/cpu_has_feature.h>
+#include <asm/asm-prototypes.h>
 
 #define DBG(fmt...)
 
···
 }
 
 /* Checks "l2cr=xxxx" command-line option */
-int __init ppc_setup_l2cr(char *str)
+static int __init ppc_setup_l2cr(char *str)
 {
 	if (cpu_has_feature(CPU_FTR_L2CR)) {
 		unsigned long val = simple_strtoul(str, NULL, 0);
···
 __setup("l2cr=", ppc_setup_l2cr);
 
 /* Checks "l3cr=xxxx" command-line option */
-int __init ppc_setup_l3cr(char *str)
+static int __init ppc_setup_l3cr(char *str)
 {
 	if (cpu_has_feature(CPU_FTR_L3CR)) {
 		unsigned long val = simple_strtoul(str, NULL, 0);
···
 
 #endif /* CONFIG_NVRAM */
 
-int __init ppc_init(void)
+static int __init ppc_init(void)
 {
 	/* clear the progress line */
 	if (ppc_md.progress)
···
 	}
 	return 0;
 }
-
 arch_initcall(ppc_init);
 
 void __init irqstack_early_init(void)

arch/powerpc/kernel/setup_64.c

···
 		if (cpu_first_thread_sibling(boot_cpuid) == first)
 			first = boot_cpuid;
 
-		paca[cpu].tcd_ptr = &paca[first].tcd;
+		paca_ptrs[cpu]->tcd_ptr = &paca_ptrs[first]->tcd;
 
 		/*
 		 * If we have threads, we need either tlbsrx.
···
 	get_paca()->kernel_msr = MSR_KERNEL;
 }
 
+unsigned long spr_default_dscr = 0;
+
+void __init record_spr_defaults(void)
+{
+	if (early_cpu_has_feature(CPU_FTR_DSCR))
+		spr_default_dscr = mfspr(SPRN_DSCR);
+}
+
 /*
  * Early initialization entry point. This is called by head.S
  * with MMU translation disabled. We rely on the "feature" of
···
 	early_init_devtree(__va(dt_ptr));
 
 	/* Now we know the logical id of our boot cpu, setup the paca. */
-	setup_paca(&paca[boot_cpuid]);
+	if (boot_cpuid != 0) {
+		/* Poison paca_ptrs[0] again if it's not the boot cpu */
+		memset(&paca_ptrs[0], 0x88, sizeof(paca_ptrs[0]));
+	}
+	setup_paca(paca_ptrs[boot_cpuid]);
 	fixup_boot_paca();
 
 	/*
···
 #endif
 }
 
+static void *__init alloc_stack(unsigned long limit, int cpu)
+{
+	unsigned long pa;
+
+	pa = memblock_alloc_base_nid(THREAD_SIZE, THREAD_SIZE, limit,
+					early_cpu_to_node(cpu), MEMBLOCK_NONE);
+	if (!pa) {
+		pa = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
+		if (!pa)
+			panic("cannot allocate stacks");
+	}
+
+	return __va(pa);
+}
+
 void __init irqstack_early_init(void)
 {
 	u64 limit = ppc64_bolted_size();
···
 	 * accessed in realmode.
 	 */
 	for_each_possible_cpu(i) {
-		softirq_ctx[i] = (struct thread_info *)
-			__va(memblock_alloc_base(THREAD_SIZE,
-					    THREAD_SIZE, limit));
-		hardirq_ctx[i] = (struct thread_info *)
-			__va(memblock_alloc_base(THREAD_SIZE,
-					    THREAD_SIZE, limit));
+		softirq_ctx[i] = alloc_stack(limit, i);
+		hardirq_ctx[i] = alloc_stack(limit, i);
 	}
 }
 
···
 void __init exc_lvl_early_init(void)
 {
 	unsigned int i;
-	unsigned long sp;
 
 	for_each_possible_cpu(i) {
-		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
-		critirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].crit_kstack = __va(sp + THREAD_SIZE);
+		void *sp;
 
-		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
-		dbgirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].dbg_kstack = __va(sp + THREAD_SIZE);
+		sp = alloc_stack(ULONG_MAX, i);
+		critirq_ctx[i] = sp;
+		paca_ptrs[i]->crit_kstack = sp + THREAD_SIZE;
 
-		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
-		mcheckirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].mc_kstack = __va(sp + THREAD_SIZE);
+		sp = alloc_stack(ULONG_MAX, i);
+		dbgirq_ctx[i] = sp;
+		paca_ptrs[i]->dbg_kstack = sp + THREAD_SIZE;
+
+		sp = alloc_stack(ULONG_MAX, i);
+		mcheckirq_ctx[i] = sp;
+		paca_ptrs[i]->mc_kstack = sp + THREAD_SIZE;
 	}
 
 	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
···
 
 	for_each_possible_cpu(i) {
 		struct thread_info *ti;
-		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+
+		ti = alloc_stack(limit, i);
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
-		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+		ti = alloc_stack(limit, i);
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
-		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+		ti = alloc_stack(limit, i);
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}
 }
···
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
                 __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
-		paca[cpu].data_offset = __per_cpu_offset[cpu];
+		paca_ptrs[cpu]->data_offset = __per_cpu_offset[cpu];
 	}
 }
 #endif
···
 
 void rfi_flush_enable(bool enable)
 {
-	if (rfi_flush == enable)
-		return;
-
 	if (enable) {
 		do_rfi_flush_fixups(enabled_flush_types);
 		on_each_cpu(do_nothing, NULL, 1);
···
 	u64 l1d_size, limit;
 	int cpu;
 
+	/* Only allocate the fallback flush area once (at boot time). */
+	if (l1d_flush_fallback_area)
+		return;
+
 	l1d_size = ppc64_caches.l1d.size;
 	limit = min(ppc64_bolted_size(), ppc64_rma_size);
 
···
 	memset(l1d_flush_fallback_area, 0, l1d_size * 2);
 
 	for_each_possible_cpu(cpu) {
-		paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
-		paca[cpu].l1d_flush_size = l1d_size;
+		struct paca_struct *paca = paca_ptrs[cpu];
+		paca->rfi_flush_fallback_area = l1d_flush_fallback_area;
+		paca->l1d_flush_size = l1d_size;
 	}
 }
 
-void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
+void setup_rfi_flush(enum l1d_flush_type types, bool enable)
 {
 	if (types & L1D_FLUSH_FALLBACK) {
-		pr_info("rfi-flush: Using fallback displacement flush\n");
+		pr_info("rfi-flush: fallback displacement flush available\n");
 		init_fallback_flush();
 	}
 
 	if (types & L1D_FLUSH_ORI)
-		pr_info("rfi-flush: Using ori type flush\n");
+		pr_info("rfi-flush: ori type flush available\n");
 
 	if (types & L1D_FLUSH_MTTRIG)
-		pr_info("rfi-flush: Using mttrig type flush\n");
+		pr_info("rfi-flush: mttrig type flush available\n");
 
 	enabled_flush_types = types;
 
···
 #ifdef CONFIG_DEBUG_FS
 static int rfi_flush_set(void *data, u64 val)
 {
+	bool enable;
+
 	if (val == 1)
-		rfi_flush_enable(true);
+		enable = true;
 	else if (val == 0)
-		rfi_flush_enable(false);
+		enable = false;
 	else
 		return -EINVAL;
+
+	/* Only do anything if we're changing state */
+	if (enable != rfi_flush)
+		rfi_flush_enable(enable);
 
 	return 0;
 }
···
 }
 device_initcall(rfi_flush_debugfs_init);
 #endif
-
-ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	if (rfi_flush)
-		return sprintf(buf, "Mitigation: RFI Flush\n");
-
-	return sprintf(buf, "Vulnerable\n");
-}
 #endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/kernel/signal.h

···
 
 #else /* CONFIG_PPC64 */
 
+extern long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
+		     struct pt_regs *regs);
+extern long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
+		       struct pt_regs *regs);
+
 static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 				     struct task_struct *tsk)
 {

arch/powerpc/kernel/signal_32.c

···
 		     struct ucontext __user *new_ctx,
 		     int ctx_size, int r6, int r7, int r8, struct pt_regs *regs)
 {
-	unsigned char tmp;
+	unsigned char tmp __maybe_unused;
 	int ctx_has_vsx_region = 0;
 
 #ifdef CONFIG_PPC64
···
 {
 	struct sig_dbg_op op;
 	int i;
-	unsigned char tmp;
+	unsigned char tmp __maybe_unused;
 	unsigned long new_msr = regs->msr;
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	unsigned long new_dbcr0 = current->thread.debug.dbcr0;

arch/powerpc/kernel/smp.c

···
 	 * cpu_start field to become non-zero After we set cpu_start,
 	 * the processor will continue on to secondary_start
 	 */
-	if (!paca[nr].cpu_start) {
-		paca[nr].cpu_start = 1;
+	if (!paca_ptrs[nr]->cpu_start) {
+		paca_ptrs[nr]->cpu_start = 1;
 		smp_mb();
 		return 0;
 	}
···
 }
 #endif
 
+#ifdef CONFIG_NMI_IPI
+static void stop_this_cpu(struct pt_regs *regs)
+#else
 static void stop_this_cpu(void *dummy)
+#endif
 {
 	/* Remove this CPU */
 	set_cpu_online(smp_processor_id(), false);
 
-	local_irq_disable();
+	hard_irq_disable();
+	spin_begin();
 	while (1)
-		;
+		spin_cpu_relax();
 }
 
 void smp_send_stop(void)
 {
+#ifdef CONFIG_NMI_IPI
+	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000);
+#else
 	smp_call_function(stop_this_cpu, NULL, 0);
+#endif
 }
 
 struct thread_info *current_set[NR_CPUS];
···
 {
 	BUG_ON(smp_processor_id() != boot_cpuid);
 #ifdef CONFIG_PPC64
-	paca[boot_cpuid].__current = current;
+	paca_ptrs[boot_cpuid]->__current = current;
 #endif
 	set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
 	current_set[boot_cpuid] = task_thread_info(current);
···
 	struct thread_info *ti = task_thread_info(idle);
 
 #ifdef CONFIG_PPC64
-	paca[cpu].__current = idle;
-	paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+	paca_ptrs[cpu]->__current = idle;
+	paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
 #endif
 	ti->cpu = cpu;
 	secondary_ti = current_set[cpu] = ti;

arch/powerpc/kernel/sysfs.c

···
 #include <asm/firmware.h>
 
 #include "cacheinfo.h"
+#include "setup.h"
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
···
 
 static void sysfs_create_dscr_default(void)
 {
-	int err = 0;
-	if (cpu_has_feature(CPU_FTR_DSCR))
-		err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
-}
-
-void __init record_spr_defaults(void)
-{
-	int cpu;
-
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
-		dscr_default = mfspr(SPRN_DSCR);
-		for (cpu = 0; cpu < nr_cpu_ids; cpu++)
-			paca[cpu].dscr_default = dscr_default;
+		int err = 0;
+		int cpu;
+
+		dscr_default = spr_default_dscr;
+		for_each_possible_cpu(cpu)
+			paca_ptrs[cpu]->dscr_default = dscr_default;
+
+		err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
 	}
 }
+
 #endif /* CONFIG_PPC64 */
 
 #ifdef HAS_PPC_PMC_PA6T

arch/powerpc/kernel/time.c

···
 
 static inline u64 calculate_stolen_time(u64 stop_tb)
 {
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return 0;
+
 	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
 		return scan_dispatch_log(stop_tb);
 
···
 static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm)
 {
 	ppc_md.get_rtc_time(tm);
-	return rtc_valid_tm(tm);
+	return 0;
 }
 
 static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm)

arch/powerpc/kernel/traps.c

···
 	}
 	raw_local_irq_restore(flags);
 
+	/*
+	 * system_reset_excption handles debugger, crash dump, panic, for 0x100
+	 */
+	if (TRAP(regs) == 0x100)
+		return;
+
 	crash_fadump(regs, "die oops");
 
 	if (kexec_should_crash(current))
···
 {
 	unsigned long flags;
 
-	if (debugger(regs))
-		return;
+	/*
+	 * system_reset_excption handles debugger, crash dump, panic, for 0x100
+	 */
+	if (TRAP(regs) != 0x100) {
+		if (debugger(regs))
+			return;
+	}
 
 	flags = oops_begin(regs);
 	if (__die(str, regs, err))
···
 /* single-step stuff */
 #define single_stepping(regs)	(current->thread.debug.dbcr0 & DBCR0_IC)
 #define clear_single_step(regs)	(current->thread.debug.dbcr0 &= ~DBCR0_IC)
-
+#define clear_br_trace(regs)	do {} while(0)
 #else
 /* On non-4xx, the reason for the machine check or program
    exception is in the MSR. */
···
 
 #define single_stepping(regs)	((regs)->msr & MSR_SE)
 #define clear_single_step(regs)	((regs)->msr &= ~MSR_SE)
+#define clear_br_trace(regs)	((regs)->msr &= ~MSR_BE)
 #endif
 
 #if defined(CONFIG_E500)
···
 	enum ctx_state prev_state = exception_enter();
 
 	clear_single_step(regs);
+	clear_br_trace(regs);
 
 	if (kprobe_post_handler(regs))
 		return;
···
 		bad_page_fault(regs, regs->dar, sig);
 
 bail:
-	exception_exit(prev_state);
-}
-
-void slb_miss_bad_addr(struct pt_regs *regs)
-{
-	enum ctx_state prev_state = exception_enter();
-
-	if (user_mode(regs))
-		_exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
-	else
-		bad_page_fault(regs, regs->dar, SIGSEGV);
-
 	exception_exit(prev_state);
 }
 

arch/powerpc/kernel/vdso.c

···
 		CPU_FTR_COHERENT_ICACHE, CPU_FTR_COHERENT_ICACHE,
 		"__kernel_sync_dicache", "__kernel_sync_dicache_p5"
 	},
+#ifdef CONFIG_PPC32
 	{
-		CPU_FTR_USE_TB, 0,
+		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
 		"__kernel_gettimeofday", NULL
 	},
 	{
-		CPU_FTR_USE_TB, 0,
+		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
 		"__kernel_clock_gettime", NULL
 	},
 	{
-		CPU_FTR_USE_TB, 0,
+		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
 		"__kernel_clock_getres", NULL
 	},
 	{
-		CPU_FTR_USE_TB, 0,
+		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
 		"__kernel_get_tbfreq", NULL
 	},
 	{
-		CPU_FTR_USE_TB, 0,
+		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
 		"__kernel_time", NULL
 	},
+#endif
 };
 
 /*

arch/powerpc/kvm/Makefile

···
 	book3s_64_mmu_hv.o \
 	book3s_64_mmu_radix.o
 
+kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
+	book3s_hv_tm.o
+
 kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
 	book3s_hv_rm_xics.o book3s_hv_rm_xive.o
+
+kvm-book3s_64-builtin-tm-objs-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
+	book3s_hv_tm_builtin.o
 
 ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
···
 	book3s_hv_rm_mmu.o \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
+	$(kvm-book3s_64-builtin-tm-objs-y) \
 	$(kvm-book3s_64-builtin-xics-objs-y)
 endif
 

arch/powerpc/kvm/book3s_hv.c

···
 #include <asm/reg.h>
 #include <asm/ppc-opcode.h>
 #include <asm/asm-prototypes.h>
+#include <asm/debug.h>
 #include <asm/disassemble.h>
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
···
 
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (cpu >= 0 && cpu < nr_cpu_ids) {
-		if (paca[cpu].kvm_hstate.xics_phys) {
+		if (paca_ptrs[cpu]->kvm_hstate.xics_phys) {
 			xics_wake_cpu(cpu);
 			return true;
 		}
···
 		 * use 640 bytes of the structure though, so we should accept
 		 * clients that set a size of 640.
 		 */
-		if (len < 640)
+		BUILD_BUG_ON(sizeof(struct lppaca) != 640);
+		if (len < sizeof(struct lppaca))
 			break;
 		vpap = &tvcpu->arch.vpa;
 		err = 0;
···
 		return H_SUCCESS;
 	case H_SET_MODE_RESOURCE_SET_DAWR:
 		if (!kvmppc_power8_compatible(vcpu))
+			return H_P2;
+		if (!ppc_breakpoint_available())
 			return H_P2;
 		if (mflags)
 			return H_UNSUPPORTED_FLAG_START;
···
 			r = RESUME_GUEST;
 		}
 		break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+		/*
+		 * This occurs for various TM-related instructions that
+		 * we need to emulate on POWER9 DD2.2.  We have already
+		 * handled the cases where the guest was in real-suspend
+		 * mode and was transitioning to transactional state.
+		 */
+		r = kvmhv_p9_tm_emulation(vcpu);
+		break;
+#endif
+
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		r = RESUME_PASSTHROUGH;
 		break;
···
 	 * turn off the HFSCR bit, which causes those instructions to trap.
 	 */
 	vcpu->arch.hfscr = mfspr(SPRN_HFSCR);
-	if (!cpu_has_feature(CPU_FTR_TM))
+	if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+		vcpu->arch.hfscr |= HFSCR_TM;
+	else if (!cpu_has_feature(CPU_FTR_TM_COMP))
 		vcpu->arch.hfscr &= ~HFSCR_TM;
 	if (cpu_has_feature(CPU_FTR_ARCH_300))
 		vcpu->arch.hfscr &= ~HFSCR_MSGP;
···
 	struct paca_struct *tpaca;
 	long timeout = 10000;
 
-	tpaca = &paca[cpu];
+	tpaca = paca_ptrs[cpu];
 
 	/* Ensure the thread won't go into the kernel if it wakes */
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
···
 {
 	struct paca_struct *tpaca;
 
-	tpaca = &paca[cpu];
+	tpaca = paca_ptrs[cpu];
 	tpaca->kvm_hstate.hwthread_req = 0;
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
 	tpaca->kvm_hstate.kvm_vcore = NULL;
···
 		vcpu->arch.thread_cpu = cpu;
 		cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest);
 	}
-	tpaca = &paca[cpu];
+	tpaca = paca_ptrs[cpu];
 	tpaca->kvm_hstate.kvm_vcpu = vcpu;
 	tpaca->kvm_hstate.ptid = cpu - vc->pcpu;
+	tpaca->kvm_hstate.fake_suspend = 0;
 	/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
 	smp_wmb();
 	tpaca->kvm_hstate.kvm_vcore = vc;
···
 		 * for any threads that still have a non-NULL vcore ptr.
 		 */
 		for (i = 1; i < n_threads; ++i)
-			if (paca[cpu + i].kvm_hstate.kvm_vcore)
+			if (paca_ptrs[cpu + i]->kvm_hstate.kvm_vcore)
 				break;
 		if (i == n_threads) {
 			HMT_medium();
···
 	}
 	HMT_medium();
 	for (i = 1; i < n_threads; ++i)
-		if (paca[cpu + i].kvm_hstate.kvm_vcore)
+		if (paca_ptrs[cpu + i]->kvm_hstate.kvm_vcore)
 			pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
 }
 
···
 	}
 
 	for (thr = 0; thr < controlled_threads; ++thr) {
-		paca[pcpu + thr].kvm_hstate.tid = thr;
-		paca[pcpu + thr].kvm_hstate.napping = 0;
-		paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip;
+		struct paca_struct *paca = paca_ptrs[pcpu + thr];
+
+		paca->kvm_hstate.tid = thr;
+		paca->kvm_hstate.napping = 0;
+		paca->kvm_hstate.kvm_split_mode = sip;
 	}
 
 	/* Initiate micro-threading (split-core) on POWER8 if required */
···
 	} else if (hpt_on_radix) {
 		/* Wait for all threads to have seen final sync */
 		for (thr = 1; thr < controlled_threads; ++thr) {
-			while (paca[pcpu + thr].kvm_hstate.kvm_split_mode) {
+			struct paca_struct *paca = paca_ptrs[pcpu + thr];
+
+			while (paca->kvm_hstate.kvm_split_mode) {
 				HMT_low();
 				barrier();
 			}
···
 		int node = cpu_to_node(first_cpu);
 
 		/* Ignore if it is already allocated. */
-		if (paca[first_cpu].sibling_subcore_state)
+		if (paca_ptrs[first_cpu]->sibling_subcore_state)
 			continue;
 
 		sibling_subcore_state =
···
 		for (j = 0; j < threads_per_core; j++) {
 			int cpu = first_cpu + j;
 
-			paca[cpu].sibling_subcore_state = sibling_subcore_state;
+			paca_ptrs[cpu]->sibling_subcore_state =
+						sibling_subcore_state;
 		}
 	}
 	return 0;
···
 
 	/*
 	 * We need a way of accessing the XICS interrupt controller,
-	 * either directly, via paca[cpu].kvm_hstate.xics_phys, or
+	 * either directly, via paca_ptrs[cpu]->kvm_hstate.xics_phys, or
 	 * indirectly, via OPAL.
 	 */
 #ifdef CONFIG_SMP

arch/powerpc/kvm/book3s_hv_builtin.c

···
 	    return;
 
 	/* Else poke the target with an IPI */
-	xics_phys = paca[cpu].kvm_hstate.xics_phys;
+	xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys;
 	if (xics_phys)
 		__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
 	else

arch/powerpc/kvm/book3s_hv_interrupts.S

···
 	li	r5, 0
 	mtspr	SPRN_MMCRA, r5
 	isync
-	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
-	lbz	r5, LPPACA_PMCINUSE(r3)
+	lbz	r5, PACA_PMCINUSE(r13)	/* is the host using the PMU? */
 	cmpwi	r5, 0
 	beq	31f			/* skip if not */
 	mfspr	r5, SPRN_MMCR1

arch/powerpc/kvm/book3s_hv_rmhandlers.S

···
 	mtspr	SPRN_SPRG_VDSO_WRITE,r3
 
 	/* Reload the host's PMU registers */
-	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
-	lbz	r4, LPPACA_PMCINUSE(r3)
+	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
 	cmpwi	r4, 0
 	beq	23f			/* skip if not */
 BEGIN_FTR_SECTION
···
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Branch around the call if both CPU_FTR_TM and
+ * CPU_FTR_P9_TM_HV_ASSIST are off.
+ */
 BEGIN_FTR_SECTION
+	b	91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
 	 */
 	bl	kvmppc_restore_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
 #endif
 
 	/* Load guest PMU registers */
···
 	ld	r6, VCPU_DAWRX(r4)
 	ld	r7, VCPU_CIABR(r4)
 	ld	r8, VCPU_TAR(r4)
+	/*
+	 * Handle broken DAWR case by not writing it. This means we
+	 * can still store the DAWR register for migration.
+	 */
+BEGIN_FTR_SECTION
 	mtspr	SPRN_DAWR, r5
 	mtspr	SPRN_DAWRX, r6
+END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
 	mtspr	SPRN_CIABR, r7
 	mtspr	SPRN_TAR, r8
 	ld	r5, VCPU_IC(r4)
···
 	mtspr	SPRN_ACOP, r6
 	mtspr	SPRN_CSIGR, r7
 	mtspr	SPRN_TACR, r8
+	nop
 FTR_SECTION_ELSE
 	/* POWER9-only registers */
 	ld	r5, VCPU_TID(r4)
 	ld	r6, VCPU_PSSCR(r4)
+	lbz	r8, HSTATE_FAKE_SUSPEND(r13)
 	oris	r6, r6, PSSCR_EC@h	/* This makes stop trap to HV */
+	rldimi	r6, r8, PSSCR_FAKE_SUSPEND_LG, 63 - PSSCR_FAKE_SUSPEND_LG
 	ld	r7, VCPU_HFSCR(r4)
 	mtspr	SPRN_TIDR, r5
 	mtspr	SPRN_PSSCR, r6
···
 	std	r3, VCPU_CTR(r9)
 	std	r4, VCPU_XER(r9)
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* For softpatch interrupt, go off and do TM instruction emulation */
+	cmpwi	r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
+	beq	kvmppc_tm_emul
+#endif
+
 	/* If this is a page table miss then see if it's theirs or ours */
 	cmpwi	r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
 	beq	kvmppc_hdsi
···
 	bl	kvmppc_save_fp
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Branch around the call if both CPU_FTR_TM and
+ * CPU_FTR_P9_TM_HV_ASSIST are off.
+ */
 BEGIN_FTR_SECTION
+	b	91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
 	 */
 	bl	kvmppc_save_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
 #endif
 
 	/* Increment yield count if they have a VPA */
···
 	ld	r6, STACK_SLOT_DAWR(r1)
 	ld	r7, STACK_SLOT_DAWRX(r1)
 	mtspr	SPRN_CIABR, r5
+	/*
+	 * If the DAWR doesn't work, it's ok to write these here as
+	 * this value should always be zero
+	*/
 	mtspr	SPRN_DAWR, r6
 	mtspr	SPRN_DAWRX, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
···
 	addi	r1, r1, SFS
 	mtlr	r0
 	blr
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Softpatch interrupt for transactional memory emulation cases
+ * on POWER9 DD2.2.  This is early in the guest exit path - we
+ * haven't saved registers or done a treclaim yet.
+ */
+kvmppc_tm_emul:
+	/* Save instruction image in HEIR */
+	mfspr	r3, SPRN_HEIR
+	stw	r3, VCPU_HEIR(r9)
+
+	/*
+	 * The cases we want to handle here are those where the guest
+	 * is in real suspend mode and is trying to transition to
+	 * transactional mode.
+	 */
+	lbz	r0, HSTATE_FAKE_SUSPEND(r13)
+	cmpwi	r0, 0		/* keep exiting guest if in fake suspend */
+	bne	guest_exit_cont
+	rldicl	r3, r11, 64 - MSR_TS_S_LG, 62
+	cmpwi	r3, 1		/* or if not in suspend state */
+	bne	guest_exit_cont
+
+	/* Call C code to do the emulation */
+	mr	r3, r9
+	bl	kvmhv_p9_tm_emulation_early
+	nop
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	li	r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
+	cmpwi	r3, 0
+	beq	guest_exit_cont		/* continue exiting if not handled */
+	ld	r10, VCPU_PC(r9)
+	ld	r11, VCPU_MSR(r9)
+	b	fast_interrupt_c_return	/* go back to guest if handled */
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
 /*
  * Check whether an HDSI is an HPTE not found fault or something else.
···
 	li	r3,0
 	blr
 
+2:
+BEGIN_FTR_SECTION
+	/* POWER9 with disabled DAWR */
+	li	r3, H_HARDWARE
+	blr
+END_FTR_SECTION_IFCLR(CPU_FTR_DAWR)
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
-2:	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
+	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
 	rlwimi	r5, r4, 2, DAWRX_WT
 	clrrdi	r4, r4, 3
 	std	r4, VCPU_DAWR(r3)
···
 	bl	kvmppc_save_fp
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Branch around the call if both CPU_FTR_TM and
+ * CPU_FTR_P9_TM_HV_ASSIST are off.
+ */
 BEGIN_FTR_SECTION
+	b	91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
 	 */
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	bl	kvmppc_save_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
 #endif
 
 	/*
···
 #endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Branch around the call if both CPU_FTR_TM and
+ * CPU_FTR_P9_TM_HV_ASSIST are off.
+ */
 BEGIN_FTR_SECTION
+	b	91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
 	 */
 	bl	kvmppc_restore_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
 #endif
 
 	/* load up FP state */
···
 kvmppc_save_tm:
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -PPC_MIN_STKFRM(r1)
 
 	/* Turn on TM. */
 	mfmsr	r8
···
 	std	r1, HSTATE_HOST_R1(r13)
 	li	r3, TM_CAUSE_KVM_RESCHED
 
+BEGIN_FTR_SECTION
+	lbz	r0, HSTATE_FAKE_SUSPEND(r13) /* Were we fake suspended? */
+	cmpwi	r0, 0
+	beq	3f
+	rldicl. r8, r8, 64 - MSR_TS_S_LG, 62 /* Did we actually hrfid? */
+	beq	4f
+BEGIN_FTR_SECTION_NESTED(96)
+	bl	pnv_power9_force_smt4_catch
+END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
+	nop
+	b	6f
+3:
+	/* Emulation of the treclaim instruction needs TEXASR before treclaim */
+	mfspr	r6, SPRN_TEXASR
+	std	r6, VCPU_ORIG_TEXASR(r9)
+6:
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
+
 	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
 	li	r5, 0
 	mtmsrd	r5, 1
···
 	SET_SCRATCH0(r13)
 	GET_PACA(r13)
 	std	r9, PACATMSCRATCH(r13)
+
+	/* If doing TM emulation on POWER9 DD2.2, check for fake suspend mode */
+BEGIN_FTR_SECTION
+	lbz	r9, HSTATE_FAKE_SUSPEND(r13)
+	cmpwi	r9, 0
+	beq	2f
+	/*
+	 * We were in fake suspend, so we are not going to save the
+	 * register state as the guest checkpointed state (since
+	 * we already have it), therefore we can now use any volatile GPR.
+	 */
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+	HMT_MEDIUM
+	ld	r6, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r6
+BEGIN_FTR_SECTION_NESTED(96)
+	bl	pnv_power9_force_smt4_release
+END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
+	nop
+
+4:
+	mfspr	r3, SPRN_PSSCR
+	/* PSSCR_FAKE_SUSPEND is a write-only bit, but clear it anyway */
+	li	r0, PSSCR_FAKE_SUSPEND
+	andc	r3, r3, r0
+	mtspr	SPRN_PSSCR, r3
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	/* Don't save TEXASR, use value from last exit in real suspend state */
+	b	11f
+2:
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
+
 	ld	r9, HSTATE_KVM_VCPU(r13)
 
 	/* Get a few more GPRs free. */
···
 	 * change these outside of a transaction, so they must always be
 	 * context switched.
 	 */
+	mfspr	r7, SPRN_TEXASR
+	std	r7, VCPU_TEXASR(r9)
+11:
 	mfspr	r5, SPRN_TFHAR
 	mfspr	r6, SPRN_TFIAR
-	mfspr	r7, SPRN_TEXASR
 	std	r5, VCPU_TFHAR(r9)
 	std	r6, VCPU_TFIAR(r9)
-	std	r7, VCPU_TEXASR(r9)
 
+	addi	r1, r1, PPC_MIN_STKFRM
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr
···
 	mtspr	SPRN_TFIAR, r6
 	mtspr	SPRN_TEXASR, r7
 
+	li	r0, 0
+	stb	r0, HSTATE_FAKE_SUSPEND(r13)
 	ld	r5, VCPU_MSR(r4)
 	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
 	beqlr		/* TM not active in guest */
···
 	 */
 	oris	r7, r7, (TEXASR_FS)@h
 	mtspr	SPRN_TEXASR, r7
+
+	/*
+	 * If we are doing TM emulation for the guest on a POWER9 DD2,
+	 * then we don't actually do a trechkpt -- we either set up
+	 * fake-suspend mode, or emulate a TM rollback.
+	 */
+BEGIN_FTR_SECTION
+	b	.Ldo_tm_fake_load
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
 
 	/*
 	 * We need to load up the checkpointed state for the guest.
···
 	/* Set the MSR RI since we have our registers back. */
 	li	r5, MSR_RI
 	mtmsrd	r5, 1
-
+9:
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr
+
+.Ldo_tm_fake_load:
+	cmpwi	r5, 1		/* check for suspended state */
+	bgt	10f
+	stb	r5, HSTATE_FAKE_SUSPEND(r13)
+	b	9b		/* and return */
+10:	stdu	r1, -PPC_MIN_STKFRM(r1)
+	/* guest is in transactional state, so simulate rollback */
+	mr	r3, r4
+	bl	kvmhv_emulate_tm_rollback
+	nop
+	ld      r4, HSTATE_KVM_VCPU(r13) /* our vcpu pointer has been trashed */
+	addi	r1, r1, PPC_MIN_STKFRM
+	b	9b
 #endif
 
 /*

arch/powerpc/kvm/book3s_hv_tm.c

···
+/*
+ * Copyright 2017 Paul Mackerras, IBM Corp. <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_book3s_64.h>
+#include <asm/reg.h>
+#include <asm/ppc-opcode.h>
+
+static void emulate_tx_failure(struct kvm_vcpu *vcpu, u64 failure_cause)
+{
+	u64 texasr, tfiar;
+	u64 msr = vcpu->arch.shregs.msr;
+
+	tfiar = vcpu->arch.pc & ~0x3ull;
+	texasr = (failure_cause << 56) | TEXASR_ABORT | TEXASR_FS | TEXASR_EXACT;
+	if (MSR_TM_SUSPENDED(vcpu->arch.shregs.msr))
+		texasr |= TEXASR_SUSP;
+	if (msr & MSR_PR) {
+		texasr |= TEXASR_PR;
+		tfiar |= 1;
+	}
+	vcpu->arch.tfiar = tfiar;
+	/* Preserve ROT and TL fields of existing TEXASR */
+	vcpu->arch.texasr = (vcpu->arch.texasr & 0x3ffffff) | texasr;
+}
+
+/*
+ * This gets called on a softpatch interrupt on POWER9 DD2.2 processors.
+ * We expect to find a TM-related instruction to be emulated.  The
+ * instruction image is in vcpu->arch.emul_inst.  If the guest was in
+ * TM suspended or transactional state, the checkpointed state has been
+ * reclaimed and is in the vcpu struct.  The CPU is in virtual mode in
+ * host context.
+ */
+int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
+{
+	u32 instr = vcpu->arch.emul_inst;
+	u64 msr = vcpu->arch.shregs.msr;
+	u64 newmsr, bescr;
+	int ra, rs;
+
+	switch (instr & 0xfc0007ff) {
+	case PPC_INST_RFID:
+		/* XXX do we need to check for PR=0 here? */
+		newmsr = vcpu->arch.shregs.srr1;
+		/* should only get here for Sx -> T1 transition */
+		WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+			       MSR_TM_TRANSACTIONAL(newmsr) &&
+			       (newmsr & MSR_TM)));
+		newmsr = sanitize_msr(newmsr);
+		vcpu->arch.shregs.msr = newmsr;
+		vcpu->arch.cfar = vcpu->arch.pc - 4;
+		vcpu->arch.pc = vcpu->arch.shregs.srr0;
+		return RESUME_GUEST;
+
+	case PPC_INST_RFEBB:
+		if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) {
+			/* generate an illegal instruction interrupt */
+			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+			return RESUME_GUEST;
+		}
+		/* check EBB facility is available */
+		if (!(vcpu->arch.hfscr & HFSCR_EBB)) {
+			/* generate an illegal instruction interrupt */
+			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+			return RESUME_GUEST;
+		}
+		if ((msr & MSR_PR) && !(vcpu->arch.fscr & FSCR_EBB)) {
+			/* generate a facility unavailable interrupt */
+			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+				((u64)FSCR_EBB_LG << 56);
+			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
+			return RESUME_GUEST;
+		}
+		bescr = vcpu->arch.bescr;
+		/* expect to see a S->T transition requested */
+		WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+			       ((bescr >> 30) & 3) == 2));
+		bescr &= ~BESCR_GE;
+		if (instr & (1 << 11))
+			bescr |= BESCR_GE;
+		vcpu->arch.bescr = bescr;
+		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+		vcpu->arch.shregs.msr = msr;
+		vcpu->arch.cfar = vcpu->arch.pc - 4;
+		vcpu->arch.pc = vcpu->arch.ebbrr;
+		return RESUME_GUEST;
+
+	case PPC_INST_MTMSRD:
+		/* XXX do we need to check for PR=0 here? */
+		rs = (instr >> 21) & 0x1f;
+		newmsr = kvmppc_get_gpr(vcpu, rs);
+		/* check this is a Sx -> T1 transition */
+		WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+			       MSR_TM_TRANSACTIONAL(newmsr) &&
+			       (newmsr & MSR_TM)));
+		/* mtmsrd doesn't change LE */
+		newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
+		newmsr = sanitize_msr(newmsr);
+		vcpu->arch.shregs.msr = newmsr;
+		return RESUME_GUEST;
+
+	case PPC_INST_TSR:
+		/* check for PR=1 and arch 2.06 bit set in PCR */
+		if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) {
+			/* generate an illegal instruction interrupt */
+			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+			return RESUME_GUEST;
+		}
+		/* check for TM disabled in the HFSCR or MSR */
+		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+			/* generate an illegal instruction interrupt */
+			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+			return RESUME_GUEST;
+		}
+		if (!(msr & MSR_TM)) {
+			/* generate a facility unavailable interrupt */
+			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+				((u64)FSCR_TM_LG << 56);
+			kvmppc_book3s_queue_irqprio(vcpu,
+						BOOK3S_INTERRUPT_FAC_UNAVAIL);
+			return RESUME_GUEST;
+		}
+		/* Set CR0 to indicate previous transactional state */
+		vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+		/* L=1 => tresume, L=0 => tsuspend */
+		if (instr & (1 << 21)) {
+			if (MSR_TM_SUSPENDED(msr))
+				msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+		} else {
+			if (MSR_TM_TRANSACTIONAL(msr))
+				msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
+		}
+		vcpu->arch.shregs.msr = msr;
+		return RESUME_GUEST;
+
+	case PPC_INST_TRECLAIM:
+		/* check for TM disabled in the HFSCR or MSR */
+		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+			/* generate an illegal instruction interrupt */
+			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+			return RESUME_GUEST;
+		}
+		if (!(msr & MSR_TM)) {
+			/* generate a facility unavailable interrupt */
+			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+				((u64)FSCR_TM_LG << 56);
+			kvmppc_book3s_queue_irqprio(vcpu,
+						BOOK3S_INTERRUPT_FAC_UNAVAIL);
+			return RESUME_GUEST;
+		}
+		/* If no transaction active, generate TM bad thing */
+		if (!MSR_TM_ACTIVE(msr)) {
+			kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+			return RESUME_GUEST;
+		}
+		/* If failure was not previously recorded, recompute TEXASR */
+		if (!(vcpu->arch.orig_texasr & TEXASR_FS)) {
+			ra = (instr >> 16) & 0x1f;
+			if (ra)
+				ra = kvmppc_get_gpr(vcpu, ra) & 0xff;
+			emulate_tx_failure(vcpu, ra);
+		}
+
+		copy_from_checkpoint(vcpu);
+
+		/* Set CR0 to indicate previous transactional state */
+		vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+		return RESUME_GUEST;
+
+	case PPC_INST_TRECHKPT:
+		/* XXX do we need to check for PR=0 here? */
+		/* check for TM disabled in the HFSCR or MSR */
+		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+			/* generate an illegal instruction interrupt */
+			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+			return RESUME_GUEST;
+		}
+		if (!(msr & MSR_TM)) {
+			/* generate a facility unavailable interrupt */
+			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+				((u64)FSCR_TM_LG << 56);
+			kvmppc_book3s_queue_irqprio(vcpu,
+						BOOK3S_INTERRUPT_FAC_UNAVAIL);
+			return RESUME_GUEST;
+		}
+		/* If transaction active or TEXASR[FS] = 0, bad thing */
+		if (MSR_TM_ACTIVE(msr) || !(vcpu->arch.texasr & TEXASR_FS)) {
+			kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+			return RESUME_GUEST;
+		}
+
+		copy_to_checkpoint(vcpu);
+
+		/* Set CR0 to indicate previous transactional state */
+		vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+		vcpu->arch.shregs.msr = msr | MSR_TS_S;
+		return RESUME_GUEST;
+	}
+
+	/* What should we do here? We didn't recognize the instruction */
+	WARN_ON_ONCE(1);
+	return RESUME_GUEST;
+}

arch/powerpc/kvm/book3s_hv_tm_builtin.c

···
+/*
+ * Copyright 2017 Paul Mackerras, IBM Corp. <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_book3s_64.h>
+#include <asm/reg.h>
+#include <asm/ppc-opcode.h>
+
+/*
+ * This handles the cases where the guest is in real suspend mode
+ * and we want to get back to the guest without dooming the transaction.
+ * The caller has checked that the guest is in real-suspend mode
+ * (MSR[TS] = S and the fake-suspend flag is not set).
+ */
+int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
+{
+	u32 instr = vcpu->arch.emul_inst;
+	u64 newmsr, msr, bescr;
+	int rs;
+
+	switch (instr & 0xfc0007ff) {
+	case PPC_INST_RFID:
+		/* XXX do we need to check for PR=0 here? */
+		newmsr = vcpu->arch.shregs.srr1;
+		/* should only get here for Sx -> T1 transition */
+		if (!(MSR_TM_TRANSACTIONAL(newmsr) && (newmsr & MSR_TM)))
+			return 0;
+		newmsr = sanitize_msr(newmsr);
+		vcpu->arch.shregs.msr = newmsr;
+		vcpu->arch.cfar = vcpu->arch.pc - 4;
+		vcpu->arch.pc = vcpu->arch.shregs.srr0;
+		return 1;
+
+	case PPC_INST_RFEBB:
+		/* check for PR=1 and arch 2.06 bit set in PCR */
+		msr = vcpu->arch.shregs.msr;
+		if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206))
+			return 0;
+		/* check EBB facility is available */
+		if (!(vcpu->arch.hfscr & HFSCR_EBB) ||
+		    ((msr & MSR_PR) && !(mfspr(SPRN_FSCR) & FSCR_EBB)))
+			return 0;
+		bescr = mfspr(SPRN_BESCR);
+		/* expect to see a S->T transition requested */
+		if (((bescr >> 30) & 3) != 2)
+			return 0;
+		bescr &= ~BESCR_GE;
+		if (instr & (1 << 11))
+			bescr |= BESCR_GE;
+		mtspr(SPRN_BESCR, bescr);
+		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+		vcpu->arch.shregs.msr = msr;
+		vcpu->arch.cfar = vcpu->arch.pc - 4;
+		vcpu->arch.pc = mfspr(SPRN_EBBRR);
+		return 1;
+
+	case PPC_INST_MTMSRD:
+		/* XXX do we need to check for PR=0 here? */
+		rs = (instr >> 21) & 0x1f;
+		newmsr = kvmppc_get_gpr(vcpu, rs);
+		msr = vcpu->arch.shregs.msr;
+		/* check this is a Sx -> T1 transition */
+		if (!(MSR_TM_TRANSACTIONAL(newmsr) && (newmsr & MSR_TM)))
+			return 0;
+		/* mtmsrd doesn't change LE */
+		newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
+		newmsr = sanitize_msr(newmsr);
+		vcpu->arch.shregs.msr = newmsr;
+		return 1;
+
+	case PPC_INST_TSR:
+		/* we know the MSR has the TS field = S (0b01) here */
+		msr = vcpu->arch.shregs.msr;
+		/* check for PR=1 and arch 2.06 bit set in PCR */
+		if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206))
+			return 0;
+		/* check for TM disabled in the HFSCR or MSR */
+		if (!(vcpu->arch.hfscr & HFSCR_TM) || !(msr & MSR_TM))
+			return 0;
+		/* L=1 => tresume => set TS to T (0b10) */
+		if (instr & (1 << 21))
+			vcpu->arch.shregs.msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+		/* Set CR0 to 0b0010 */
+		vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0x20000000;
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * This is called when we are returning to a guest in TM transactional
+ * state.  We roll the guest state back to the checkpointed state.
+ */
+void kvmhv_emulate_tm_rollback(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.shregs.msr &= ~MSR_TS_MASK;	/* go to N state */
+	vcpu->arch.pc = vcpu->arch.tfhar;
+	copy_from_checkpoint(vcpu);
+	vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0xa0000000;
+}

arch/powerpc/kvm/emulate.c

···
 #ifdef CONFIG_PPC_BOOK3S
 	/* mtdec lowers the interrupt line when positive. */
 	kvmppc_core_dequeue_dec(vcpu);
-
-	/* POWER4+ triggers a dec interrupt if the value is < 0 */
-	if (vcpu->arch.dec & 0x80000000) {
-		kvmppc_core_queue_dec(vcpu);
-		return;
-	}
 #endif
 
 #ifdef CONFIG_BOOKE

arch/powerpc/kvm/powerpc.c

···
 		r = hv_enabled;
 		break;
 #endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	case KVM_CAP_PPC_HTM:
 		r = hv_enabled &&
-		    (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM_COMP);
+		    (!!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
+		     cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST));
 		break;
+#endif
 	default:
 		r = 0;
 		break;

arch/powerpc/lib/Makefile

···
 extra-$(CONFIG_PPC64)	+= crtsavres.o
 endif
 
+obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
+			       memcpy_power7.o
+
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \
-	   memcpy_64.o memcmp_64.o pmem.o
+	   string_64.o memcpy_64.o memcmp_64.o pmem.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o

arch/powerpc/lib/copypage_64.S

···
 BEGIN_FTR_SECTION
 	lis	r5,PAGE_SIZE@h
 FTR_SECTION_ELSE
+#ifdef CONFIG_PPC_BOOK3S_64
 	b	copypage_power7
+#endif
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 	ori	r5,r5,PAGE_SIZE@l
 BEGIN_FTR_SECTION

arch/powerpc/lib/copypage_power7.S

···
 	lis	r8,0x8000	/* GO=1 */
 	clrldi	r8,r8,32
 
-.machine push
-.machine "power4"
 	/* setup read stream 0  */
 	dcbt	0,r4,0b01000  	/* addr from */
 	dcbt	0,r7,0b01010   /* length and depth from */
···
 	dcbtst	0,r10,0b01010  /* length and depth to */
 	eieio
 	dcbt	0,r8,0b01010	/* all streams GO */
-.machine pop
 
 #ifdef CONFIG_ALTIVEC
 	mflr	r0

arch/powerpc/lib/copyuser_64.S

···
 
 	.align	7
 _GLOBAL_TOC(__copy_tofrom_user)
+#ifdef CONFIG_PPC_BOOK3S_64
 BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
 	b	__copy_tofrom_user_power7
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
+#endif
 _GLOBAL(__copy_tofrom_user_base)
 	/* first check for a whole page copy on a page boundary */
 	cmpldi	cr1,r5,16

arch/powerpc/lib/copyuser_power7.S

···
 	lis	r8,0x8000	/* GO=1 */
 	clrldi	r8,r8,32
 
-.machine push
-.machine "power4"
 	/* setup read stream 0 */
 	dcbt	0,r6,0b01000   /* addr from */
 	dcbt	0,r7,0b01010   /* length and depth from */
···
 	dcbtst	0,r10,0b01010  /* length and depth to */
 	eieio
 	dcbt	0,r8,0b01010	/* all streams GO */
-.machine pop
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
 

arch/powerpc/lib/feature-fixups.c

···
 		patch_instruction(dest + 2, instrs[2]);
 	}
 
-	printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i);
+	printk(KERN_DEBUG "rfi-flush: patched %d locations (%s flush)\n", i,
+		(types == L1D_FLUSH_NONE)       ? "no" :
+		(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
+		(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
+							? "ori+mttrig type"
+							: "ori type" :
+		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
+						: "unknown");
 }
 #endif /* CONFIG_PPC_BOOK3S_64 */
 

arch/powerpc/lib/memcpy_64.S

···
 	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* save destination pointer for return value */
 #endif
 FTR_SECTION_ELSE
+#ifdef CONFIG_PPC_BOOK3S_64
 #ifndef SELFTEST
 	b	memcpy_power7
+#endif
 #endif
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 #ifdef __LITTLE_ENDIAN__

arch/powerpc/lib/memcpy_power7.S

···
 	lis	r8,0x8000	/* GO=1 */
 	clrldi	r8,r8,32
 
-.machine push
-.machine "power4"
 	dcbt	0,r6,0b01000
 	dcbt	0,r7,0b01010
 	dcbtst	0,r9,0b01000
 	dcbtst	0,r10,0b01010
 	eieio
 	dcbt	0,r8,0b01010	/* GO */
-.machine pop
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
 

arch/powerpc/lib/sstep.c

···
  * Copy from userspace to a buffer, using the largest possible
  * aligned accesses, up to sizeof(long).
  */
-static int nokprobe_inline copy_mem_in(u8 *dest, unsigned long ea, int nb,
+static nokprobe_inline int copy_mem_in(u8 *dest, unsigned long ea, int nb,
 				       struct pt_regs *regs)
 {
 	int err = 0;
···
  * Copy from a buffer to userspace, using the largest possible
  * aligned accesses, up to sizeof(long).
  */
-static int nokprobe_inline copy_mem_out(u8 *dest, unsigned long ea, int nb,
+static nokprobe_inline int copy_mem_out(u8 *dest, unsigned long ea, int nb,
 					struct pt_regs *regs)
 {
 	int err = 0;

arch/powerpc/mm/8xx_mmu.c

···
 	mtspr(SPRN_M_TW, __pa(pgd) - offset);
 
 	/* Update context */
-	mtspr(SPRN_M_CASID, id);
+	mtspr(SPRN_M_CASID, id - 1);
 	/* sync */
 	mb();
 }

arch/powerpc/mm/copro_fault.c

···
 			return 1;
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
-		vsid = get_vsid(mm->context.id, ea, ssize);
+		vsid = get_user_vsid(&mm->context, ea, ssize);
 		vsidkey = SLB_VSID_USER;
 		break;
 	case VMALLOC_REGION_ID:

arch/powerpc/mm/fault.c

···
 
 	if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
 		return true;
-
+	/*
+	 * We should ideally do the vma pkey access check here. But in the
+	 * fault path, handle_mm_fault() also does the same check. To avoid
+	 * these multiple checks, we skip it here and handle access error due
+	 * to pkeys later.
+	 */
 	return false;
 }
 
···
 
 #ifdef CONFIG_PPC_MEM_KEYS
 	/*
-	 * if the HPTE is not hashed, hardware will not detect
-	 * a key fault. Lets check if we failed because of a
-	 * software detected key fault.
+	 * we skipped checking for access error due to key earlier.
+	 * Check that using handle_mm_fault error return.
 	 */
 	if (unlikely(fault & VM_FAULT_SIGSEGV) &&
-		!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
-			is_exec, 0)) {
-		/*
-		 * The PGD-PDT...PMD-PTE tree may not have been fully setup.
-		 * Hence we cannot walk the tree to locate the PTE, to locate
-		 * the key. Hence let's use vma_pkey() to get the key; instead
-		 * of get_mm_addr_key().
-		 */
+		!arch_vma_access_permitted(vma, is_write, is_exec, 0)) {
+
 		int pkey = vma_pkey(vma);
 
-		if (likely(pkey)) {
-			up_read(&mm->mmap_sem);
-			return bad_key_fault_exception(regs, address, pkey);
-		}
+		up_read(&mm->mmap_sem);
+		return bad_key_fault_exception(regs, address, pkey);
 	}
 #endif /* CONFIG_PPC_MEM_KEYS */
 

arch/powerpc/mm/hash_native_64.c

···
 	local_irq_restore(flags);
 }
 
-static int native_register_proc_table(unsigned long base, unsigned long page_size,
-				      unsigned long table_size)
-{
-	unsigned long patb1 = base << 25; /* VSID */
-
-	patb1 |= (page_size << 5);  /* sllp */
-	patb1 |= table_size;
-
-	partition_tb->patb1 = cpu_to_be64(patb1);
-	return 0;
-}
-
 void __init hpte_init_native(void)
 {
 	mmu_hash_ops.hpte_invalidate	= native_hpte_invalidate;
···
 	mmu_hash_ops.hpte_clear_all	= native_hpte_clear;
 	mmu_hash_ops.flush_hash_range = native_flush_hash_range;
 	mmu_hash_ops.hugepage_invalidate   = native_hugepage_invalidate;
-
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		register_process_table = native_register_proc_table;
 }

arch/powerpc/mm/hash_utils_64.c

···
  * is provided by the firmware.
  */
 
-/* Pre-POWER4 CPUs (4k pages only)
+/*
+ * Fallback (4k pages only)
  */
-static struct mmu_psize_def mmu_psize_defaults_old[] = {
+static struct mmu_psize_def mmu_psize_defaults[] = {
 	[MMU_PAGE_4K] = {
 		.shift	= 12,
 		.sllp	= 0,
···
 	mmu_psize_set_default_penc();
 
 	/* Default to 4K pages only */
-	memcpy(mmu_psize_defs, mmu_psize_defaults_old,
-	       sizeof(mmu_psize_defaults_old));
+	memcpy(mmu_psize_defs, mmu_psize_defaults,
+	       sizeof(mmu_psize_defaults));
 
 	/*
 	 * Try to find the available page sizes in the device-tree
···
 	}
 }
 
-int hash__create_section_mapping(unsigned long start, unsigned long end)
+int hash__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	int rc = htab_bolt_mapping(start, end, __pa(start),
 				   pgprot_val(PAGE_KERNEL), mmu_linear_psize,
···
 		/* Using a hypervisor which owns the htab */
 		htab_address = NULL;
 		_SDR1 = 0; 
+		/*
+		 * On POWER9, we need to do a H_REGISTER_PROC_TBL hcall
+		 * to inform the hypervisor that we wish to use the HPT.
+		 */
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			register_process_table(0, 0, 0);
 #ifdef CONFIG_FA_DUMP
 		/*
 		 * If firmware assisted dump is active firmware preserves
···
 #ifdef CONFIG_PPC_MM_SLICES
 static unsigned int get_paca_psize(unsigned long addr)
 {
-	u64 lpsizes;
-	unsigned char *hpsizes;
+	unsigned char *psizes;
 	unsigned long index, mask_index;
 
 	if (addr < SLICE_LOW_TOP) {
-		lpsizes = get_paca()->mm_ctx_low_slices_psize;
+		psizes = get_paca()->mm_ctx_low_slices_psize;
 		index = GET_LOW_SLICE_INDEX(addr);
-		return (lpsizes >> (index * 4)) & 0xF;
+	} else {
+		psizes = get_paca()->mm_ctx_high_slices_psize;
+		index = GET_HIGH_SLICE_INDEX(addr);
 	}
-	hpsizes = get_paca()->mm_ctx_high_slices_psize;
-	index = GET_HIGH_SLICE_INDEX(addr);
 	mask_index = index & 0x1;
-	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF;
+	return (psizes[index >> 1] >> (mask_index * 4)) & 0xF;
 }
 
 #else
···
 		}
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
-		vsid = get_vsid(mm->context.id, ea, ssize);
+		vsid = get_user_vsid(&mm->context, ea, ssize);
 		break;
 	case VMALLOC_REGION_ID:
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
···
 
 	/* Get VSID */
 	ssize = user_segment_size(ea);
-	vsid = get_vsid(mm->context.id, ea, ssize);
+	vsid = get_user_vsid(&mm->context, ea, ssize);
 	if (!vsid)
 		return;
 	/*

arch/powerpc/mm/hugetlbpage.c

···
 #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 #define HUGEPD_PGD_SHIFT PGDIR_SHIFT
 #define HUGEPD_PUD_SHIFT PUD_SHIFT
-#else
-#define HUGEPD_PGD_SHIFT PUD_SHIFT
-#define HUGEPD_PUD_SHIFT PMD_SHIFT
 #endif
 
 /*
···
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
+#ifdef CONFIG_PPC_RADIX_MMU
 	if (radix_enabled())
 		return radix__hugetlb_get_unmapped_area(file, addr, len,
 						       pgoff, flags);
+#endif
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
 }
 #endif
···
 unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 {
 #ifdef CONFIG_PPC_MM_SLICES
-	unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
 	/* With radix we don't use slice, so derive it from vma*/
-	if (!radix_enabled())
+	if (!radix_enabled()) {
+		unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
+
 		return 1UL << mmu_psize_to_shift(psize);
+	}
 #endif
 	return vma_kernel_pagesize(vma);
 }
···
 
 		shift = mmu_psize_to_shift(psize);
 
-		if (add_huge_page_size(1ULL << shift) < 0)
+#ifdef CONFIG_PPC_BOOK3S_64
+		if (shift > PGDIR_SHIFT)
 			continue;
-
+		else if (shift > PUD_SHIFT)
+			pdshift = PGDIR_SHIFT;
+		else if (shift > PMD_SHIFT)
+			pdshift = PUD_SHIFT;
+		else
+			pdshift = PMD_SHIFT;
+#else
 		if (shift < HUGEPD_PUD_SHIFT)
 			pdshift = PMD_SHIFT;
 		else if (shift < HUGEPD_PGD_SHIFT)
 			pdshift = PUD_SHIFT;
 		else
 			pdshift = PGDIR_SHIFT;
+#endif
+
+		if (add_huge_page_size(1ULL << shift) < 0)
+			continue;
 		/*
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.

arch/powerpc/mm/init_32.c

···
 int __map_without_bats;
 int __map_without_ltlbs;
 
-/*
- * This tells the system to allow ioremapping memory marked as reserved.
- */
-int __allow_ioremap_reserved;
-
 /* max amount of low RAM to map in */
 unsigned long __max_low_memory = MAX_LOW_MEM;
 
 /*
  * Check for command-line options that affect what MMU_init will do.
  */
-void __init MMU_setup(void)
+static void __init MMU_setup(void)
 {
 	/* Check for nobats option (used in mapin_ram). */
 	if (strstr(boot_command_line, "nobats")) {

arch/powerpc/mm/init_64.c

···
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3S_64
-#if H_PGTABLE_RANGE > USER_VSID_RANGE
-#warning Limited user VSID range means pagetable space is wasted
-#endif
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
 phys_addr_t memstart_addr = ~0;
 EXPORT_SYMBOL_GPL(memstart_addr);
 phys_addr_t kernstart_addr;
···
 {
 	bool val;
 
-	if (strlen(p) == 0)
+	if (!p)
 		val = true;
 	else if (kstrtobool(p, &val))
 		return -EINVAL;

arch/powerpc/mm/mem.c

···
 
 int page_is_ram(unsigned long pfn)
 {
-#ifndef CONFIG_PPC64	/* XXX for now */
-	return pfn < max_pfn;
-#else
-	unsigned long paddr = (pfn << PAGE_SHIFT);
-	struct memblock_region *reg;
-
-	for_each_memblock(memory, reg)
-		if (paddr >= reg->base && paddr < (reg->base + reg->size))
-			return 1;
-	return 0;
-#endif
+	return memblock_is_memory(__pfn_to_phys(pfn));
 }
 
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
···
 }
 #endif
 
-int __weak create_section_mapping(unsigned long start, unsigned long end)
+int __weak create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	return -ENODEV;
 }
···
 	return -ENODEV;
 }
 
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int __meminit arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 		bool want_memblock)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
···
 	resize_hpt_for_hotplug(memblock_phys_mem_size());
 
 	start = (unsigned long)__va(start);
-	rc = create_section_mapping(start, start + size);
+	rc = create_section_mapping(start, start + size, nid);
 	if (rc) {
 		pr_warn("Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
 			start, start + size, rc);
···
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+int __meminit arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
···
 EXPORT_SYMBOL_GPL(walk_system_ram_range);
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-void __init initmem_init(void)
+void __init mem_topology_setup(void)
 {
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
···
 	 * memblock_regions
 	 */
 	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
+}
 
+void __init initmem_init(void)
+{
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
 	sparse_init();

arch/powerpc/mm/mmu_context_book3s64.c

···
 		return index;
 
 	/*
-	 * In the case of exec, use the default limit,
-	 * otherwise inherit it from the mm we are duplicating.
-	 */
-	if (!mm->context.slb_addr_limit)
-		mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
-
-	/*
 	 * The old code would re-promote on fork, we don't do that when using
 	 * slices as it could cause problem promoting slices that have been
 	 * forced down to 4K.
···
 	 * check against 0 is OK.
 	 */
 	if (mm->context.id == 0)
-		slice_set_user_psize(mm, mmu_virtual_psize);
+		slice_init_new_context_exec(mm);
 
 	subpage_prot_init_new_context(mm);
 
···
 }
 EXPORT_SYMBOL_GPL(__destroy_context);
 
+static void destroy_contexts(mm_context_t *ctx)
+{
+	int index, context_id;
+
+	spin_lock(&mmu_context_lock);
+	for (index = 0; index < ARRAY_SIZE(ctx->extended_id); index++) {
+		context_id = ctx->extended_id[index];
+		if (context_id)
+			ida_remove(&mmu_context_ida, context_id);
+	}
+	spin_unlock(&mmu_context_lock);
+}
+
 #ifdef CONFIG_PPC_64K_PAGES
 static void destroy_pagetable_page(struct mm_struct *mm)
 {
···
 	else
 		subpage_prot_free(mm);
 	destroy_pagetable_page(mm);
-	__destroy_context(mm->context.id);
+	destroy_contexts(&mm->context);
 	mm->context.id = MMU_NO_CONTEXT;
 }
 

arch/powerpc/mm/mmu_context_nohash.c

···
 {
 	pr_hard("initing context for mm @%p\n", mm);
 
+#ifdef	CONFIG_PPC_MM_SLICES
+	/*
+	 * We have MMU_NO_CONTEXT set to be ~0. Hence check
+	 * explicitly against context.id == 0. This ensures that we properly
+	 * initialize context slice details for newly allocated mm's (which will
+	 * have id == 0) and don't alter context slice inherited via fork (which
+	 * will have id != 0).
+	 */
+	if (mm->context.id == 0)
+		slice_init_new_context_exec(mm);
+#endif
 	mm->context.id = MMU_NO_CONTEXT;
 	mm->context.active = 0;
 	return 0;
···
 	 *      -- BenH
 	 */
 	if (mmu_has_feature(MMU_FTR_TYPE_8xx)) {
-		first_context = 0;
-		last_context = 15;
+		first_context = 1;
+		last_context = 16;
 		no_selective_tlbil = true;
 	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
 		first_context = 1;

arch/powerpc/mm/mmu_decl.h

···
 		   unsigned int size, pgprot_t prot);
 
 extern int __map_without_bats;
-extern int __allow_ioremap_reserved;
 extern unsigned int rtas_data, rtas_size;
 
 struct hash_pte;

arch/powerpc/mm/numa.c

···
 	of_node_put(rtas);
 }
 
-void __init initmem_init(void)
+void __init mem_topology_setup(void)
 {
-	int nid, cpu;
-
-	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	max_pfn = max_low_pfn;
+	int cpu;
 
 	if (parse_numa_properties())
 		setup_nonnuma();
-
-	memblock_dump_all();
 
 	/*
 	 * Modify the set of possible NUMA nodes to reflect information
···
 
 	find_possible_nodes();
 
+	setup_node_to_cpumask_map();
+
+	reset_numa_cpu_lookup_table();
+
+	for_each_present_cpu(cpu)
+		numa_setup_cpu(cpu);
+}
+
+void __init initmem_init(void)
+{
+	int nid;
+
+	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
+	max_pfn = max_low_pfn;
+
+	memblock_dump_all();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
 
···
 
 	sparse_init();
 
-	setup_node_to_cpumask_map();
-
-	reset_numa_cpu_lookup_table();
-
 	/*
 	 * We need the numa_cpu_lookup_table to be accurate for all CPUs,
 	 * even before we online them, so that we can use cpu_to_{node,mem}
···
 	 */
 	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "powerpc/numa:prepare",
 				  ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
-	for_each_present_cpu(cpu)
-		numa_setup_cpu(cpu);
 }
 
 static int __init early_numa(char *p)
···
 	for_each_possible_cpu(cpu) {
 		int i;
 		u8 *counts = vphn_cpu_change_counts[cpu];
-		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+		volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
 
 		for (i = 0; i < distance_ref_points_depth; i++)
 			counts[i] = hypervisor_counts[i];
···
 	for_each_possible_cpu(cpu) {
 		int i, changed = 0;
 		u8 *counts = vphn_cpu_change_counts[cpu];
-		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+		volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
 
 		for (i = 0; i < distance_ref_points_depth; i++) {
 			if (hypervisor_counts[i] != counts[i]) {

arch/powerpc/mm/pgtable-book3s64.c

···
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int create_section_mapping(unsigned long start, unsigned long end)
+int __meminit create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	if (radix_enabled())
-		return radix__create_section_mapping(start, end);
+		return radix__create_section_mapping(start, end, nid);
 
-	return hash__create_section_mapping(start, end);
+	return hash__create_section_mapping(start, end, nid);
 }
 
-int remove_section_mapping(unsigned long start, unsigned long end)
+int __meminit remove_section_mapping(unsigned long start, unsigned long end)
 {
 	if (radix_enabled())
 		return radix__remove_section_mapping(start, end);

arch/powerpc/mm/pgtable-hash64.c

···
 #define CREATE_TRACE_POINTS
 #include <trace/events/thp.h>
 
+#if H_PGTABLE_RANGE > (USER_VSID_RANGE * (TASK_SIZE_USER64 / TASK_CONTEXT_SIZE))
+#warning Limited user VSID range means pagetable space is wasted
+#endif
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * vmemmap is the starting address of the virtual address space where
···
 
 	if (!is_kernel_addr(addr)) {
 		ssize = user_segment_size(addr);
-		vsid = get_vsid(mm->context.id, addr, ssize);
+		vsid = get_user_vsid(&mm->context, addr, ssize);
 		WARN_ON(vsid == 0);
 	} else {
 		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);

arch/powerpc/mm/pgtable-radix.c

···
 	return 0;
 }
 
-static __ref void *early_alloc_pgtable(unsigned long size)
+static __ref void *early_alloc_pgtable(unsigned long size, int nid,
+			unsigned long region_start, unsigned long region_end)
 {
+	unsigned long pa = 0;
 	void *pt;
 
-	pt = __va(memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE));
+	if (region_start || region_end) /* has region hint */
+		pa = memblock_alloc_range(size, size, region_start, region_end,
+						MEMBLOCK_NONE);
+	else if (nid != -1) /* has node hint */
+		pa = memblock_alloc_base_nid(size, size,
+						MEMBLOCK_ALLOC_ANYWHERE,
+						nid, MEMBLOCK_NONE);
+
+	if (!pa)
+		pa = memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE);
+
+	BUG_ON(!pa);
+
+	pt = __va(pa);
 	memset(pt, 0, size);
 
 	return pt;
 }
 
-int radix__map_kernel_page(unsigned long ea, unsigned long pa,
+static int early_map_kernel_page(unsigned long ea, unsigned long pa,
 			  pgprot_t flags,
-			  unsigned int map_page_size)
+			  unsigned int map_page_size,
+			  int nid,
+			  unsigned long region_start, unsigned long region_end)
 {
+	unsigned long pfn = pa >> PAGE_SHIFT;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	pgdp = pgd_offset_k(ea);
+	if (pgd_none(*pgdp)) {
+		pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid,
+						region_start, region_end);
+		pgd_populate(&init_mm, pgdp, pudp);
+	}
+	pudp = pud_offset(pgdp, ea);
+	if (map_page_size == PUD_SIZE) {
+		ptep = (pte_t *)pudp;
+		goto set_the_pte;
+	}
+	if (pud_none(*pudp)) {
+		pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid,
+						region_start, region_end);
+		pud_populate(&init_mm, pudp, pmdp);
+	}
+	pmdp = pmd_offset(pudp, ea);
+	if (map_page_size == PMD_SIZE) {
+		ptep = pmdp_ptep(pmdp);
+		goto set_the_pte;
+	}
+	if (!pmd_present(*pmdp)) {
+		ptep = early_alloc_pgtable(PAGE_SIZE, nid,
+						region_start, region_end);
+		pmd_populate_kernel(&init_mm, pmdp, ptep);
+	}
+	ptep = pte_offset_kernel(pmdp, ea);
+
+set_the_pte:
+	set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
+	smp_wmb();
+	return 0;
+}
+
+/*
+ * nid, region_start, and region_end are hints to try to place the page
+ * table memory in the same node or region.
+ */
+static int __map_kernel_page(unsigned long ea, unsigned long pa,
+			  pgprot_t flags,
+			  unsigned int map_page_size,
+			  int nid,
+			  unsigned long region_start, unsigned long region_end)
+{
+	unsigned long pfn = pa >> PAGE_SHIFT;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
···
 	 * Make sure task size is correct as per the max adddr
 	 */
 	BUILD_BUG_ON(TASK_SIZE_USER64 > RADIX_PGTABLE_RANGE);
-	if (slab_is_available()) {
-		pgdp = pgd_offset_k(ea);
-		pudp = pud_alloc(&init_mm, pgdp, ea);
-		if (!pudp)
-			return -ENOMEM;
-		if (map_page_size == PUD_SIZE) {
-			ptep = (pte_t *)pudp;
-			goto set_the_pte;
-		}
-		pmdp = pmd_alloc(&init_mm, pudp, ea);
-		if (!pmdp)
-			return -ENOMEM;
-		if (map_page_size == PMD_SIZE) {
-			ptep = pmdp_ptep(pmdp);
-			goto set_the_pte;
-		}
-		ptep = pte_alloc_kernel(pmdp, ea);
-		if (!ptep)
-			return -ENOMEM;
-	} else {
-		pgdp = pgd_offset_k(ea);
-		if (pgd_none(*pgdp)) {
-			pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
-			BUG_ON(pudp == NULL);
-			pgd_populate(&init_mm, pgdp, pudp);
-		}
-		pudp = pud_offset(pgdp, ea);
-		if (map_page_size == PUD_SIZE) {
-			ptep = (pte_t *)pudp;
-			goto set_the_pte;
-		}
-		if (pud_none(*pudp)) {
-			pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
-			BUG_ON(pmdp == NULL);
-			pud_populate(&init_mm, pudp, pmdp);
-		}
-		pmdp = pmd_offset(pudp, ea);
-		if (map_page_size == PMD_SIZE) {
-			ptep = pmdp_ptep(pmdp);
-			goto set_the_pte;
-		}
-		if (!pmd_present(*pmdp)) {
-			ptep = early_alloc_pgtable(PAGE_SIZE);
-			BUG_ON(ptep == NULL);
-			pmd_populate_kernel(&init_mm, pmdp, ptep);
-		}
-		ptep = pte_offset_kernel(pmdp, ea);
+
+	if (unlikely(!slab_is_available()))
+		return early_map_kernel_page(ea, pa, flags, map_page_size,
+						nid, region_start, region_end);
+
+	/*
+	 * Should make page table allocation functions be able to take a
+	 * node, so we can place kernel page tables on the right nodes after
+	 * boot.
+	 */
+	pgdp = pgd_offset_k(ea);
+	pudp = pud_alloc(&init_mm, pgdp, ea);
+	if (!pudp)
+		return -ENOMEM;
+	if (map_page_size == PUD_SIZE) {
+		ptep = (pte_t *)pudp;
+		goto set_the_pte;
 	}
+	pmdp = pmd_alloc(&init_mm, pudp, ea);
+	if (!pmdp)
+		return -ENOMEM;
+	if (map_page_size == PMD_SIZE) {
+		ptep = pmdp_ptep(pmdp);
+		goto set_the_pte;
+	}
+	ptep = pte_alloc_kernel(pmdp, ea);
+	if (!ptep)
+		return -ENOMEM;
 
 set_the_pte:
-	set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, flags));
+	set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
 	smp_wmb();
 	return 0;
+}
+
+int radix__map_kernel_page(unsigned long ea, unsigned long pa,
+			  pgprot_t flags,
+			  unsigned int map_page_size)
+{
+	return __map_kernel_page(ea, pa, flags, map_page_size, -1, 0, 0);
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
···
 }
 
 static int __meminit create_physical_mapping(unsigned long start,
-					     unsigned long end)
+					     unsigned long end,
+					     int nid)
 {
 	unsigned long vaddr, addr, mapping_size = 0;
 	pgprot_t prot;
···
 		else
 			prot = PAGE_KERNEL;
 
-		rc = radix__map_kernel_page(vaddr, addr, prot, mapping_size);
+		rc = __map_kernel_page(vaddr, addr, prot, mapping_size, nid, start, end);
 		if (rc)
 			return rc;
 	}
···
 	return 0;
 }
 
-static void __init radix_init_pgtable(void)
+void __init radix_init_pgtable(void)
 {
 	unsigned long rts_field;
 	struct memblock_region *reg;
···
 	/*
 	 * Create the linear mapping, using standard page size for now
 	 */
-	for_each_memblock(memory, reg)
+	for_each_memblock(memory, reg) {
+		/*
+		 * The memblock allocator  is up at this point, so the
+		 * page tables will be allocated within the range. No
+		 * need or a node (which we don't have yet).
+		 */
 		WARN_ON(create_physical_mapping(reg->base,
-						reg->base + reg->size));
+						reg->base + reg->size,
+						-1));
+	}
 
 	/* Find out how many PID bits are supported */
 	if (cpu_has_feature(CPU_FTR_HVMODE)) {
···
 	 * host.
 	 */
 	BUG_ON(PRTB_SIZE_SHIFT > 36);
-	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
+	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT, -1, 0, 0);
 	/*
 	 * Fill in the process table.
 	 */
···
 #ifdef CONFIG_PCI
 	pci_io_base = ISA_IO_BASE;
 #endif
-
-	/*
-	 * For now radix also use the same frag size
-	 */
-	__pte_frag_nr = H_PTE_FRAG_NR;
-	__pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT;
+	__pte_frag_nr = RADIX_PTE_FRAG_NR;
+	__pte_frag_size_shift = RADIX_PTE_FRAG_SIZE_SHIFT;
 
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		radix_init_native();
···
 	unsigned long aligned_end;
 };
 
-static int stop_machine_change_mapping(void *data)
+static int __meminit stop_machine_change_mapping(void *data)
 {
 	struct change_mapping_params *params =
 			(struct change_mapping_params *)data;
···
 
 	spin_unlock(&init_mm.page_table_lock);
 	pte_clear(&init_mm, params->aligned_start, params->pte);
-	create_physical_mapping(params->aligned_start, params->start);
-	create_physical_mapping(params->end, params->aligned_end);
+	create_physical_mapping(params->aligned_start, params->start, -1);
+	create_physical_mapping(params->end, params->aligned_end, -1);
 	spin_lock(&init_mm.page_table_lock);
 	return 0;
 }
···
 /*
  * clear the pte and potentially split the mapping helper
  */
-static void split_kernel_mapping(unsigned long addr, unsigned long end,
+static void __meminit split_kernel_mapping(unsigned long addr, unsigned long end,
 				unsigned long size, pte_t *pte)
 {
 	unsigned long mask = ~(size - 1);
···
 	}
 }
 
-static void remove_pagetable(unsigned long start, unsigned long end)
+static void __meminit remove_pagetable(unsigned long start, unsigned long end)
 {
 	unsigned long addr, next;
 	pud_t *pud_base;
···
 	radix__flush_tlb_kernel_range(start, end);
 }
 
-int __ref radix__create_section_mapping(unsigned long start, unsigned long end)
+int __meminit radix__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
-	return create_physical_mapping(start, end);
+	return create_physical_mapping(start, end, nid);
 }
 
-int radix__remove_section_mapping(unsigned long start, unsigned long end)
+int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
 {
 	remove_pagetable(start, end);
 	return 0;
···
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
+static int __map_kernel_page_nid(unsigned long ea, unsigned long pa,
+				 pgprot_t flags, unsigned int map_page_size,
+				 int nid)
+{
+	return __map_kernel_page(ea, pa, flags, map_page_size, nid, 0, 0);
+}
+
 int __meminit radix__vmemmap_create_mapping(unsigned long start,
 				      unsigned long page_size,
 				      unsigned long phys)
 {
 	/* Create a PTE encoding */
 	unsigned long flags = _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_KERNEL_RW;
+	int nid = early_pfn_to_nid(phys >> PAGE_SHIFT);
+	int ret;
 
-	BUG_ON(radix__map_kernel_page(start, phys, __pgprot(flags), page_size));
+	ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid);
+	BUG_ON(ret);
+
 	return 0;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size)
+void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size)
 {
 	remove_pagetable(start, start + page_size);
 }

arch/powerpc/mm/pgtable_32.c

···
 	 * mem_init() sets high_memory so only do the check after that.
 	 */
 	if (slab_is_available() && (p < virt_to_phys(high_memory)) &&
-	    !(__allow_ioremap_reserved && memblock_is_region_reserved(p, size))) {
+	    page_is_ram(__phys_to_pfn(p))) {
 		printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n",
 		       (unsigned long long)p, __builtin_return_address(0));
 		return NULL;

arch/powerpc/mm/pgtable_64.c

···
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3S_64
-#if TASK_SIZE_USER64 > (1UL << (ESID_BITS + SID_SHIFT))
-#error TASK_SIZE_USER64 exceeds user VSID range
-#endif
-#endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
 /*

arch/powerpc/mm/pkeys.c

···
 #else
 	os_reserved = 0;
 #endif
+	initial_allocation_mask = ~0x0;
+	pkey_amr_uamor_mask = ~0x0ul;
+	pkey_iamr_mask = ~0x0ul;
 	/*
-	 * Bits are in LE format. NOTE: 1, 0 are reserved.
+	 * key 0, 1 are reserved.
 	 * key 0 is the default key, which allows read/write/execute.
 	 * key 1 is recommended not to be used. PowerISA(3.0) page 1015,
 	 * programming note.
 	 */
-	initial_allocation_mask = ~0x0;
-
-	/* register mask is in BE format */
-	pkey_amr_uamor_mask = ~0x0ul;
-	pkey_iamr_mask = ~0x0ul;
-
 	for (i = 2; i < (pkeys_total - os_reserved); i++) {
 		initial_allocation_mask &= ~(0x1 << i);
 		pkey_amr_uamor_mask &= ~(0x3ul << pkeyshift(i));
···
 	if (static_branch_likely(&pkey_disabled))
 		return;
 
-	write_amr(read_amr() & pkey_amr_uamor_mask);
-	write_iamr(read_iamr() & pkey_iamr_mask);
-	write_uamor(read_uamor() & pkey_amr_uamor_mask);
+	thread->amr = read_amr() & pkey_amr_uamor_mask;
+	thread->iamr = read_iamr() & pkey_iamr_mask;
+	thread->uamor = read_uamor() & pkey_amr_uamor_mask;
 }
 
 static inline bool pkey_allows_readwrite(int pkey)

arch/powerpc/mm/slb.c

···
 #include <asm/cacheflush.h>
 #include <asm/smp.h>
 #include <linux/compiler.h>
+#include <linux/context_tracking.h>
 #include <linux/mm_types.h>
 
 #include <asm/udbg.h>
···
 				     mmu_kernel_ssize, lflags, KSTACK_INDEX);
 
 	asm volatile("isync":::"memory");
+}
+
+static void insert_slb_entry(unsigned long vsid, unsigned long ea,
+			     int bpsize, int ssize)
+{
+	unsigned long flags, vsid_data, esid_data;
+	enum slb_index index;
+	int slb_cache_index;
+
+	/*
+	 * We are irq disabled, hence should be safe to access PACA.
+	 */
+	index = get_paca()->stab_rr;
+
+	/*
+	 * simple round-robin replacement of slb starting at SLB_NUM_BOLTED.
+	 */
+	if (index < (mmu_slb_size - 1))
+		index++;
+	else
+		index = SLB_NUM_BOLTED;
+
+	get_paca()->stab_rr = index;
+
+	flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
+	vsid_data = (vsid << slb_vsid_shift(ssize)) | flags |
+		    ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
+	esid_data = mk_esid_data(ea, ssize, index);
+
+	asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data)
+		     : "memory");
+
+	/*
+	 * Now update slb cache entries
+	 */
+	slb_cache_index = get_paca()->slb_cache_ptr;
+	if (slb_cache_index < SLB_CACHE_ENTRIES) {
+		/*
+		 * We have space in slb cache for optimized switch_slb().
+		 * Top 36 bits from esid_data as per ISA
+		 */
+		get_paca()->slb_cache[slb_cache_index++] = esid_data >> 28;
+		get_paca()->slb_cache_ptr++;
+	} else {
+		/*
+		 * Our cache is full and the current cache content strictly
+		 * doesn't indicate the active SLB conents. Bump the ptr
+		 * so that switch_slb() will ignore the cache.
+		 */
+		get_paca()->slb_cache_ptr = SLB_CACHE_ENTRIES + 1;
+	}
+}
+
+static void handle_multi_context_slb_miss(int context_id, unsigned long ea)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long vsid;
+	int bpsize;
+
+	/*
+	 * We are always above 1TB, hence use high user segment size.
+	 */
+	vsid = get_vsid(context_id, ea, mmu_highuser_ssize);
+	bpsize = get_slice_psize(mm, ea);
+	insert_slb_entry(vsid, ea, bpsize, mmu_highuser_ssize);
+}
+
+void slb_miss_large_addr(struct pt_regs *regs)
+{
+	enum ctx_state prev_state = exception_enter();
+	unsigned long ea = regs->dar;
+	int context;
+
+	if (REGION_ID(ea) != USER_REGION_ID)
+		goto slb_bad_addr;
+
+	/*
+	 * Are we beyound what the page table layout supports ?
+	 */
+	if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
+		goto slb_bad_addr;
+
+	/* Lower address should have been handled by asm code */
+	if (ea < (1UL << MAX_EA_BITS_PER_CONTEXT))
+		goto slb_bad_addr;
+
+	/*
+	 * consider this as bad access if we take a SLB miss
+	 * on an address above addr limit.
+	 */
+	if (ea >= current->mm->context.slb_addr_limit)
+		goto slb_bad_addr;
+
+	context = get_ea_context(&current->mm->context, ea);
+	if (!context)
+		goto slb_bad_addr;
+
+	handle_multi_context_slb_miss(context, ea);
+	exception_exit(prev_state);
+	return;
+
+slb_bad_addr:
+	if (user_mode(regs))
+		_exception(SIGSEGV, regs, SEGV_BNDERR, ea);
+	else
+		bad_page_fault(regs, ea, SIGSEGV);
+	exception_exit(prev_state);
 }

arch/powerpc/mm/slb_low.S

···
  */
 _GLOBAL(slb_allocate)
 	/*
-	 * check for bad kernel/user address
-	 * (ea & ~REGION_MASK) >= PGTABLE_RANGE
+	 * Check if the address falls within the range of the first context, or
+	 * if we may need to handle multi context. For the first context we
+	 * allocate the slb entry via the fast path below. For large address we
+	 * branch out to C-code and see if additional contexts have been
+	 * allocated.
+	 * The test here is:
+	 *   (ea & ~REGION_MASK) >= (1ull << MAX_EA_BITS_PER_CONTEXT)
 	 */
-	rldicr. r9,r3,4,(63 - H_PGTABLE_EADDR_SIZE - 4)
+	rldicr. r9,r3,4,(63 - MAX_EA_BITS_PER_CONTEXT - 4)
 	bne-	8f
 
 	srdi	r9,r3,60		/* get region */
···
 5:
 	/*
 	 * Handle lpsizes
-	 * r9 is get_paca()->context.low_slices_psize, r11 is index
+	 * r9 is get_paca()->context.low_slices_psize[index], r11 is mask_index
 	 */
-	ld	r9,PACALOWSLICESPSIZE(r13)
-	mr	r11,r10
+	srdi    r11,r10,1 /* index */
+	addi	r9,r11,PACALOWSLICESPSIZE
+	lbzx	r9,r13,r9		/* r9 is lpsizes[r11] */
+	rldicl	r11,r10,0,63		/* r11 = r10 & 0x1 */
 6:
 	sldi	r11,r11,2  /* index * 4 */
 	/* Extract the psize and multiply to get an array offset */

arch/powerpc/mm/slice.c

···
 #include <asm/hugetlb.h>
 
 static DEFINE_SPINLOCK(slice_convert_lock);
-/*
- * One bit per slice. We have lower slices which cover 256MB segments
- * upto 4G range. That gets us 16 low slices. For the rest we track slices
- * in 1TB size.
- */
-struct slice_mask {
-	u64 low_slices;
-	DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
-};
 
 #ifdef DEBUG
 int _slice_debug = 1;
 
-static void slice_print_mask(const char *label, struct slice_mask mask)
+static void slice_print_mask(const char *label, const struct slice_mask *mask)
 {
 	if (!_slice_debug)
 		return;
-	pr_devel("%s low_slice: %*pbl\n", label, (int)SLICE_NUM_LOW, &mask.low_slices);
-	pr_devel("%s high_slice: %*pbl\n", label, (int)SLICE_NUM_HIGH, mask.high_slices);
+	pr_devel("%s low_slice: %*pbl\n", label,
+			(int)SLICE_NUM_LOW, &mask->low_slices);
+	pr_devel("%s high_slice: %*pbl\n", label,
+			(int)SLICE_NUM_HIGH, mask->high_slices);
 }
 
 #define slice_dbg(fmt...) do { if (_slice_debug) pr_devel(fmt); } while (0)
 
 #else
 
-static void slice_print_mask(const char *label, struct slice_mask mask) {}
+static void slice_print_mask(const char *label, const struct slice_mask *mask) {}
 #define slice_dbg(fmt...)
 
 #endif
···
 	unsigned long end = start + len - 1;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	if (SLICE_NUM_HIGH)
+		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	if (start < SLICE_LOW_TOP) {
-		unsigned long mend = min(end, (SLICE_LOW_TOP - 1));
+		unsigned long mend = min(end,
+					 (unsigned long)(SLICE_LOW_TOP - 1));
 
 		ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
 			- (1u << GET_LOW_SLICE_INDEX(start));
···
 	unsigned long start = slice << SLICE_HIGH_SHIFT;
 	unsigned long end = start + (1ul << SLICE_HIGH_SHIFT);
 
+#ifdef CONFIG_PPC64
 	/* Hack, so that each addresses is controlled by exactly one
 	 * of the high or low area bitmaps, the first high area starts
 	 * at 4GB, not 0 */
 	if (start == 0)
 		start = SLICE_LOW_TOP;
+#endif
 
 	return !slice_area_is_free(mm, start, end - start);
 }
···
 	unsigned long i;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	if (SLICE_NUM_HIGH)
+		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	for (i = 0; i < SLICE_NUM_LOW; i++)
 		if (!slice_low_has_vma(mm, i))
···
 			__set_bit(i, ret->high_slices);
 }
 
-static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret,
-				unsigned long high_limit)
+#ifdef CONFIG_PPC_BOOK3S_64
+static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
 {
-	unsigned char *hpsizes;
-	int index, mask_index;
-	unsigned long i;
-	u64 lpsizes;
-
-	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
-
-	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (((lpsizes >> (i * 4)) & 0xf) == psize)
-			ret->low_slices |= 1u << i;
-
-	if (high_limit <= SLICE_LOW_TOP)
-		return;
-
-	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < GET_HIGH_SLICE_INDEX(high_limit); i++) {
-		mask_index = i & 0x1;
-		index = i >> 1;
-		if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize)
-			__set_bit(i, ret->high_slices);
-	}
+#ifdef CONFIG_PPC_64K_PAGES
+	if (psize == MMU_PAGE_64K)
+		return &mm->context.mask_64k;
+#endif
+	if (psize == MMU_PAGE_4K)
+		return &mm->context.mask_4k;
+#ifdef CONFIG_HUGETLB_PAGE
+	if (psize == MMU_PAGE_16M)
+		return &mm->context.mask_16m;
+	if (psize == MMU_PAGE_16G)
+		return &mm->context.mask_16g;
+#endif
+	BUG();
 }
-
-static int slice_check_fit(struct mm_struct *mm,
-			   struct slice_mask mask, struct slice_mask available)
+#elif defined(CONFIG_PPC_8xx)
+static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-	/*
-	 * Make sure we just do bit compare only to the max
-	 * addr limit and not the full bit map size.
-	 */
-	unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
+	if (psize == mmu_virtual_psize)
+		return &mm->context.mask_base_psize;
+#ifdef CONFIG_HUGETLB_PAGE
+	if (psize == MMU_PAGE_512K)
+		return &mm->context.mask_512k;
+	if (psize == MMU_PAGE_8M)
+		return &mm->context.mask_8m;
+#endif
+	BUG();
+}
+#else
+#error "Must define the slice masks for page sizes supported by the platform"
+#endif
 
-	bitmap_and(result, mask.high_slices,
-		   available.high_slices, slice_count);
+static bool slice_check_range_fits(struct mm_struct *mm,
+			   const struct slice_mask *available,
+			   unsigned long start, unsigned long len)
+{
+	unsigned long end = start + len - 1;
+	u64 low_slices = 0;
 
-	return (mask.low_slices & available.low_slices) == mask.low_slices &&
-		bitmap_equal(result, mask.high_slices, slice_count);
+	if (start < SLICE_LOW_TOP) {
+		unsigned long mend = min(end,
+					 (unsigned long)(SLICE_LOW_TOP - 1));
+
+		low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
+				- (1u << GET_LOW_SLICE_INDEX(start));
+	}
+	if ((low_slices & available->low_slices) != low_slices)
+		return false;
+
+	if (SLICE_NUM_HIGH && ((start + len) > SLICE_LOW_TOP)) {
+		unsigned long start_index = GET_HIGH_SLICE_INDEX(start);
+		unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
+		unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;
+		unsigned long i;
+
+		for (i = start_index; i < start_index + count; i++) {
+			if (!test_bit(i, available->high_slices))
+				return false;
+		}
+	}
+
+	return true;
 }
 
 static void slice_flush_segments(void *parm)
 {
+#ifdef CONFIG_PPC64
 	struct mm_struct *mm = parm;
 	unsigned long flags;
 
···
 	local_irq_save(flags);
 	slb_flush_and_rebolt();
 	local_irq_restore(flags);
+#endif
 }
 
-static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psize)
+static void slice_convert(struct mm_struct *mm,
+				const struct slice_mask *mask, int psize)
 {
 	int index, mask_index;
 	/* Write the new slice psize bits */
-	unsigned char *hpsizes;
-	u64 lpsizes;
+	unsigned char *hpsizes, *lpsizes;
+	struct slice_mask *psize_mask, *old_mask;
 	unsigned long i, flags;
+	int old_psize;
 
 	slice_dbg("slice_convert(mm=%p, psize=%d)\n", mm, psize);
 	slice_print_mask(" mask", mask);
+
+	psize_mask = slice_mask_for_size(mm, psize);
 
 	/* We need to use a spinlock here to protect against
 	 * concurrent 64k -> 4k demotion ...
···
 	spin_lock_irqsave(&slice_convert_lock, flags);
 
 	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (mask.low_slices & (1u << i))
-			lpsizes = (lpsizes & ~(0xful << (i * 4))) |
-				(((unsigned long)psize) << (i * 4));
+	for (i = 0; i < SLICE_NUM_LOW; i++) {
+		if (!(mask->low_slices & (1u << i)))
+			continue;
 
-	/* Assign the value back */
-	mm->context.low_slices_psize = lpsizes;
+		mask_index = i & 0x1;
+		index = i >> 1;
+
+		/* Update the slice_mask */
+		old_psize = (lpsizes[index] >> (mask_index * 4)) & 0xf;
+		old_mask = slice_mask_for_size(mm, old_psize);
+		old_mask->low_slices &= ~(1u << i);
+		psize_mask->low_slices |= 1u << i;
+
+		/* Update the sizes array */
+		lpsizes[index] = (lpsizes[index] & ~(0xf << (mask_index * 4))) |
+				(((unsigned long)psize) << (mask_index * 4));
+	}
 
 	hpsizes = mm->context.high_slices_psize;
 	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++) {
+		if (!test_bit(i, mask->high_slices))
+			continue;
+
 		mask_index = i & 0x1;
 		index = i >> 1;
-		if (test_bit(i, mask.high_slices))
-			hpsizes[index] = (hpsizes[index] &
-					  ~(0xf << (mask_index * 4))) |
+
+		/* Update the slice_mask */
+		old_psize = (hpsizes[index] >> (mask_index * 4)) & 0xf;
+		old_mask = slice_mask_for_size(mm, old_psize);
+		__clear_bit(i, old_mask->high_slices);
+		__set_bit(i, psize_mask->high_slices);
+
+		/* Update the sizes array */
+		hpsizes[index] = (hpsizes[index] & ~(0xf << (mask_index * 4))) |
 				(((unsigned long)psize) << (mask_index * 4));
 	}
 
···
  * 'available' slice_mark.
  */
 static bool slice_scan_available(unsigned long addr,
-				 struct slice_mask available,
-				 int end,
-				 unsigned long *boundary_addr)
+				 const struct slice_mask *available,
+				 int end, unsigned long *boundary_addr)
 {
 	unsigned long slice;
 	if (addr < SLICE_LOW_TOP) {
 		slice = GET_LOW_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) << SLICE_LOW_SHIFT;
-		return !!(available.low_slices & (1u << slice));
+		return !!(available->low_slices & (1u << slice));
 	} else {
 		slice = GET_HIGH_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) ?
 			((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
-		return !!test_bit(slice, available.high_slices);
+		return !!test_bit(slice, available->high_slices);
 	}
 }
 
 static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
 					      unsigned long len,
-					      struct slice_mask available,
+					      const struct slice_mask *available,
 					      int psize, unsigned long high_limit)
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
···
 
 static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 					     unsigned long len,
-					     struct slice_mask available,
+					     const struct slice_mask *available,
 					     int psize, unsigned long high_limit)
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
···
 
 
 static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
-				     struct slice_mask mask, int psize,
+				     const struct slice_mask *mask, int psize,
 				     int topdown, unsigned long high_limit)
 {
 	if (topdown)
···
 		return slice_find_area_bottomup(mm, len, mask, psize, high_limit);
 }
 
-static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src)
+static inline void slice_copy_mask(struct slice_mask *dst,
+					const struct slice_mask *src)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-
-	dst->low_slices |= src->low_slices;
-	bitmap_or(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
-	bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+	dst->low_slices = src->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_copy(dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
 }
 
-static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src)
+static inline void slice_or_mask(struct slice_mask *dst,
+					const struct slice_mask *src1,
+					const struct slice_mask *src2)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
+	dst->low_slices = src1->low_slices | src2->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_or(dst->high_slices, src1->high_slices, src2->high_slices, SLICE_NUM_HIGH);
+}
 
-	dst->low_slices &= ~src->low_slices;
-
-	bitmap_andnot(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
-	bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+static inline void slice_andnot_mask(struct slice_mask *dst,
+					const struct slice_mask *src1,
+					const struct slice_mask *src2)
+{
+	dst->low_slices = src1->low_slices & ~src2->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_andnot(dst->high_slices, src1->high_slices, src2->high_slices, SLICE_NUM_HIGH);
 }
 
 #ifdef CONFIG_PPC_64K_PAGES
···
 				      unsigned long flags, unsigned int psize,
 				      int topdown)
 {
-	struct slice_mask mask;
 	struct slice_mask good_mask;
 	struct slice_mask potential_mask;
-	struct slice_mask compat_mask;
+	const struct slice_mask *maskp;
+	const struct slice_mask *compat_maskp = NULL;
 	int fixed = (flags & MAP_FIXED);
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 	unsigned long page_size = 1UL << pshift;
···
 	}
 
 	if (high_limit > mm->context.slb_addr_limit) {
+		/*
+		 * Increasing the slb_addr_limit does not require
+		 * slice mask cache to be recalculated because it should
+		 * be already initialised beyond the old address limit.
+		 */
 		mm->context.slb_addr_limit = high_limit;
+
 		on_each_cpu(slice_flush_segments, mm, 1);
 	}
-
-	/*
-	 * init different masks
-	 */
-	mask.low_slices = 0;
-	bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
-
-	/* silence stupid warning */;
-	potential_mask.low_slices = 0;
-	bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
-
-	compat_mask.low_slices = 0;
-	bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
 
 	/* Sanity checks */
 	BUG_ON(mm->task_size == 0);
···
 	/* First make up a "good" mask of slices that have the right size
 	 * already
 	 */
-	slice_mask_for_size(mm, psize, &good_mask, high_limit);
-	slice_print_mask(" good_mask", good_mask);
+	maskp = slice_mask_for_size(mm, psize);
 
 	/*
 	 * Here "good" means slices that are already the right page size,
···
 	 *	search in good | compat | free, found => convert free.
 	 */
 
-#ifdef CONFIG_PPC_64K_PAGES
-	/* If we support combo pages, we can allow 64k pages in 4k slices */
-	if (psize == MMU_PAGE_64K) {
-		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
+	/*
+	 * If we support combo pages, we can allow 64k pages in 4k slices
+	 * The mask copies could be avoided in most cases here if we had
+	 * a pointer to good mask for the next code to use.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && psize == MMU_PAGE_64K) {
+		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
 		if (fixed)
-			slice_or_mask(&good_mask, &compat_mask);
+			slice_or_mask(&good_mask, maskp, compat_maskp);
+		else
+			slice_copy_mask(&good_mask, maskp);
+	} else {
+		slice_copy_mask(&good_mask, maskp);
 	}
-#endif
+
+	slice_print_mask(" good_mask", &good_mask);
+	if (compat_maskp)
+		slice_print_mask(" compat_mask", compat_maskp);
 
 	/* First check hint if it's valid or if we have MAP_FIXED */
 	if (addr != 0 || fixed) {
-		/* Build a mask for the requested range */
-		slice_range_to_mask(addr, len, &mask);
-		slice_print_mask(" mask", mask);
-
 		/* Check if we fit in the good mask. If we do, we just return,
 		 * nothing else to do
 		 */
-		if (slice_check_fit(mm, mask, good_mask)) {
+		if (slice_check_range_fits(mm, &good_mask, addr, len)) {
 			slice_dbg(" fits good !\n");
-			return addr;
+			newaddr = addr;
+			goto return_addr;
 		}
 	} else {
 		/* Now let's see if we can find something in the existing
 		 * slices for that size
 		 */
-		newaddr = slice_find_area(mm, len, good_mask,
+		newaddr = slice_find_area(mm, len, &good_mask,
 					  psize, topdown, high_limit);
 		if (newaddr != -ENOMEM) {
 			/* Found within the good mask, we don't have to setup,
 			 * we thus return directly
 			 */
 			slice_dbg(" found area at 0x%lx\n", newaddr);
-			return newaddr;
+			goto return_addr;
 		}
 	}
 	/*
···
 	 * empty and thus can be converted
 	 */
 	slice_mask_for_free(mm, &potential_mask, high_limit);
-	slice_or_mask(&potential_mask, &good_mask);
-	slice_print_mask(" potential", potential_mask);
+	slice_or_mask(&potential_mask, &potential_mask, &good_mask);
+	slice_print_mask(" potential", &potential_mask);
 
-	if ((addr != 0 || fixed) && slice_check_fit(mm, mask, potential_mask)) {
-		slice_dbg(" fits potential !\n");
-		goto convert;
+	if (addr != 0 || fixed) {
+		if (slice_check_range_fits(mm, &potential_mask, addr, len)) {
+			slice_dbg(" fits potential !\n");
+			newaddr = addr;
+			goto convert;
+		}
 	}
 
 	/* If we have MAP_FIXED and failed the above steps, then error out */
···
 	 * anywhere in the good area.
 	 */
 	if (addr) {
-		addr = slice_find_area(mm, len, good_mask,
-				       psize, topdown, high_limit);
-		if (addr != -ENOMEM) {
-			slice_dbg(" found area at 0x%lx\n", addr);
-			return addr;
+		newaddr = slice_find_area(mm, len, &good_mask,
+					  psize, topdown, high_limit);
+		if (newaddr != -ENOMEM) {
+			slice_dbg(" found area at 0x%lx\n", newaddr);
+			goto return_addr;
 		}
 	}
 
 	/* Now let's see if we can find something in the existing slices
 	 * for that size plus free slices
 	 */
-	addr = slice_find_area(mm, len, potential_mask,
-			       psize, topdown, high_limit);
+	newaddr = slice_find_area(mm, len, &potential_mask,
+				  psize, topdown, high_limit);
 
 #ifdef CONFIG_PPC_64K_PAGES
-	if (addr == -ENOMEM && psize == MMU_PAGE_64K) {
+	if (newaddr == -ENOMEM && psize == MMU_PAGE_64K) {
 		/* retry the search with 4k-page slices included */
-		slice_or_mask(&potential_mask, &compat_mask);
-		addr = slice_find_area(mm, len, potential_mask,
-				       psize, topdown, high_limit);
+		slice_or_mask(&potential_mask, &potential_mask, compat_maskp);
+		newaddr = slice_find_area(mm, len, &potential_mask,
+					  psize, topdown, high_limit);
 	}
 #endif
 
-	if (addr == -ENOMEM)
+	if (newaddr == -ENOMEM)
 		return -ENOMEM;
 
-	slice_range_to_mask(addr, len, &mask);
-	slice_dbg(" found potential area at 0x%lx\n", addr);
-	slice_print_mask(" mask", mask);
+	slice_range_to_mask(newaddr, len, &potential_mask);
+	slice_dbg(" found potential area at 0x%lx\n", newaddr);
+	slice_print_mask(" mask", &potential_mask);
 
  convert:
-	slice_andnot_mask(&mask, &good_mask);
-	slice_andnot_mask(&mask, &compat_mask);
-	if (mask.low_slices || !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) {
-		slice_convert(mm, mask, psize);
+	/*
+	 * Try to allocate the context before we do slice convert
+	 * so that we handle the context allocation failure gracefully.
+	 */
+	if (need_extra_context(mm, newaddr)) {
+		if (alloc_extended_context(mm, newaddr) < 0)
+			return -ENOMEM;
+	}
+
+	slice_andnot_mask(&potential_mask, &potential_mask, &good_mask);
+	if (compat_maskp && !fixed)
+		slice_andnot_mask(&potential_mask, &potential_mask, compat_maskp);
+	if (potential_mask.low_slices ||
+		(SLICE_NUM_HIGH &&
+		 !bitmap_empty(potential_mask.high_slices, SLICE_NUM_HIGH))) {
+		slice_convert(mm, &potential_mask, psize);
 		if (psize > MMU_PAGE_BASE)
 			on_each_cpu(slice_flush_segments, mm, 1);
 	}
-	return addr;
+	return newaddr;
 
+return_addr:
+	if (need_extra_context(mm, newaddr)) {
+		if (alloc_extended_context(mm, newaddr) < 0)
+			return -ENOMEM;
+	}
+	return newaddr;
 }
 EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
 
···
 
 unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
 {
-	unsigned char *hpsizes;
+	unsigned char *psizes;
 	int index, mask_index;
 
-	/*
-	 * Radix doesn't use slice, but can get enabled along with MMU_SLICE
-	 */
-	if (radix_enabled()) {
-#ifdef CONFIG_PPC_64K_PAGES
-		return MMU_PAGE_64K;
-#else
-		return MMU_PAGE_4K;
-#endif
-	}
+	VM_BUG_ON(radix_enabled());
+
 	if (addr < SLICE_LOW_TOP) {
-		u64 lpsizes;
-		lpsizes = mm->context.low_slices_psize;
+		psizes = mm->context.low_slices_psize;
 		index = GET_LOW_SLICE_INDEX(addr);
-		return (lpsizes >> (index * 4)) & 0xf;
+	} else {
+		psizes = mm->context.high_slices_psize;
+		index = GET_HIGH_SLICE_INDEX(addr);
 	}
-	hpsizes = mm->context.high_slices_psize;
-	index = GET_HIGH_SLICE_INDEX(addr);
 	mask_index = index & 0x1;
-	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xf;
+	return (psizes[index >> 1] >> (mask_index * 4)) & 0xf;
 }
 EXPORT_SYMBOL_GPL(get_slice_psize);
 
-/*
- * This is called by hash_page when it needs to do a lazy conversion of
- * an address space from real 64K pages to combo 4K pages (typically
- * when hitting a non cacheable mapping on a processor or hypervisor
- * that won't allow them for 64K pages).
- *
- * This is also called in init_new_context() to change back the user
- * psize from whatever the parent context had it set to
- * N.B. This may be called before mm->context.id has been set.
- *
- * This function will only change the content of the {low,high)_slice_psize
- * masks, it will not flush SLBs as this shall be handled lazily by the
- * caller.
- */
-void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
+void slice_init_new_context_exec(struct mm_struct *mm)
 {
-	int index, mask_index;
-	unsigned char *hpsizes;
-	unsigned long flags, lpsizes;
-	unsigned int old_psize;
-	int i;
+	unsigned char *hpsizes, *lpsizes;
+	struct slice_mask *mask;
+	unsigned int psize = mmu_virtual_psize;
 
-	slice_dbg("slice_set_user_psize(mm=%p, psize=%d)\n", mm, psize);
+	slice_dbg("slice_init_new_context_exec(mm=%p)\n", mm);
 
-	VM_BUG_ON(radix_enabled());
-	spin_lock_irqsave(&slice_convert_lock, flags);
-
-	old_psize = mm->context.user_psize;
-	slice_dbg(" old_psize=%d\n", old_psize);
-	if (old_psize == psize)
-		goto bail;
+	/*
+	 * In the case of exec, use the default limit. In the
+	 * case of fork it is just inherited from the mm being
+	 * duplicated.
+	 */
+#ifdef CONFIG_PPC64
+	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
+#else
+	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW;
+#endif
 
 	mm->context.user_psize = psize;
-	wmb();
 
+	/*
+	 * Set all slice psizes to the default.
+	 */
 	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (((lpsizes >> (i * 4)) & 0xf) == old_psize)
-			lpsizes = (lpsizes & ~(0xful << (i * 4))) |
-				(((unsigned long)psize) << (i * 4));
-	/* Assign the value back */
-	mm->context.low_slices_psize = lpsizes;
+	memset(lpsizes, (psize << 4) | psize, SLICE_NUM_LOW >> 1);
 
 	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < SLICE_NUM_HIGH; i++) {
-		mask_index = i & 0x1;
-		index = i >> 1;
-		if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == old_psize)
-			hpsizes[index] = (hpsizes[index] &
-					  ~(0xf << (mask_index * 4))) |
-				(((unsigned long)psize) << (mask_index * 4));
-	}
+	memset(hpsizes, (psize << 4) | psize, SLICE_NUM_HIGH >> 1);
 
-
-
-
-	slice_dbg(" lsps=%lx, hsps=%lx\n",
-		  (unsigned long)mm->context.low_slices_psize,
-		  (unsigned long)mm->context.high_slices_psize);
-
- bail:
-	spin_unlock_irqrestore(&slice_convert_lock, flags);
+	/*
+	 * Slice mask cache starts zeroed, fill the default size cache.
+	 */
+	mask = slice_mask_for_size(mm, psize);
+	mask->low_slices = ~0UL;
+	if (SLICE_NUM_HIGH)
+		bitmap_fill(mask->high_slices, SLICE_NUM_HIGH);
 }
 
 void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
···
 	VM_BUG_ON(radix_enabled());
 
 	slice_range_to_mask(start, len, &mask);
-	slice_convert(mm, mask, psize);
+	slice_convert(mm, &mask, psize);
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
···
  * for now as we only use slices with hugetlbfs enabled. This should
  * be fixed as the generic code gets fixed.
  */
-int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
+int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len)
 {
-	struct slice_mask mask, available;
+	const struct slice_mask *maskp;
 	unsigned int psize = mm->context.user_psize;
-	unsigned long high_limit = mm->context.slb_addr_limit;
 
-	if (radix_enabled())
-		return 0;
+	VM_BUG_ON(radix_enabled());
 
-	slice_range_to_mask(addr, len, &mask);
-	slice_mask_for_size(mm, psize, &available, high_limit);
+	maskp = slice_mask_for_size(mm, psize);
 #ifdef CONFIG_PPC_64K_PAGES
 	/* We need to account for 4k slices too */
 	if (psize == MMU_PAGE_64K) {
-		struct slice_mask compat_mask;
-		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
-		slice_or_mask(&available, &compat_mask);
+		const struct slice_mask *compat_maskp;
+		struct slice_mask available;
+
+		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
+		slice_or_mask(&available, maskp, compat_maskp);
+		return !slice_check_range_fits(mm, &available, addr, len);
 	}
 #endif
 
-#if 0 /* too verbose */
-	slice_dbg("is_hugepage_only_range(mm=%p, addr=%lx, len=%lx)\n",
-		 mm, addr, len);
-	slice_print_mask(" mask", mask);
-	slice_print_mask(" available", available);
-#endif
-	return !slice_check_fit(mm, mask, available);
+	return !slice_check_range_fits(mm, maskp, addr, len);
 }
 #endif

arch/powerpc/mm/tlb-radix.c

···
 	rb |= set << PPC_BITLSHIFT(51);
 	rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
···
 	rb = PPC_BIT(53); /* IS = 1 */
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
···
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
···
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
···
 
 	rb = 0x3 << PPC_BITLSHIFT(53); /* IS = 3 */
 	prs = 0; /* partition scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 	rs = 1 & ((1UL << 32) - 1); /* any LPID value to flush guest mappings */
 
 	asm volatile("ptesync": : :"memory");
···
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
 {
-	unsigned int pid = mm->context.id;
+	unsigned long pid = mm->context.id;
 
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		return;
···
 		for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
 			if (sib == cpu)
 				continue;
-			if (paca[sib].kvm_hstate.kvm_vcpu)
+			if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
 				flush = true;
 		}
 		if (flush)

arch/powerpc/mm/tlb_hash64.c

···
 	/* Build full vaddr */
 	if (!is_kernel_addr(addr)) {
 		ssize = user_segment_size(addr);
-		vsid = get_vsid(mm->context.id, addr, ssize);
+		vsid = get_user_vsid(&mm->context, addr, ssize);
 	} else {
 		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
 		ssize = mmu_kernel_ssize;

arch/powerpc/oprofile/cell/spu_task_sync.c

···
 	/* Create cached_info and set spu_info[spu->number] to point to it.
 	 * spu->number is a system-wide value, not a per-node value.
 	 */
-	info = kzalloc(sizeof(struct cached_info), GFP_KERNEL);
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
 		printk(KERN_ERR "SPU_PROF: "
 		       "%s, line %d: create vma_map failed\n",

arch/powerpc/oprofile/cell/vma_map.c

···
 	    unsigned int size, unsigned int offset, unsigned int guard_ptr,
 	    unsigned int guard_val)
 {
-	struct vma_to_fileoffset_map *new =
-		kzalloc(sizeof(struct vma_to_fileoffset_map), GFP_KERNEL);
+	struct vma_to_fileoffset_map *new = kzalloc(sizeof(*new), GFP_KERNEL);
+
 	if (!new) {
 		printk(KERN_ERR "SPU_PROF: %s, line %d: malloc failed\n",
 		       __func__, __LINE__);

arch/powerpc/perf/Makefile

···
 obj-$(CONFIG_PERF_EVENTS)	+= callchain.o perf_regs.o
 
 obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o bhrb.o
-obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
+obj64-$(CONFIG_PPC_PERF_CTRS)	+= ppc970-pmu.o power5-pmu.o \
 				   power5+-pmu.o power6-pmu.o power7-pmu.o \
 				   isa207-common.o power8-pmu.o power9-pmu.o
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o

arch/powerpc/perf/core-book3s.c

···
 
 	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
 		*addrp = mfspr(SPRN_SDAR);
+
+	if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) &&
+		is_kernel_addr(mfspr(SPRN_SDAR)))
+		*addrp = 0;
 }
 
 static bool regs_sihv(struct pt_regs *regs)
···
 
 			if (!addr)
 				/* invalid entry */
+				continue;
+
+			/*
+			 * BHRB rolling buffer could very much contain the kernel
+			 * addresses at this point. Check the privileges before
+			 * exporting it to userspace (avoid exposure of regions
+			 * where we could have speculative execution)
+			 */
+			if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) &&
+				is_kernel_addr(addr))
 				continue;
 
 			/* Branches are read most recent first (ie. mfbhrb 0 is
···
 		 */
 		write_mmcr0(cpuhw, val);
 		mb();
+		isync();
 
 		/*
 		 * Disable instruction sampling if it was enabled
···
 			mtspr(SPRN_MMCRA,
 			      cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
 			mb();
+			isync();
 		}
 
 		cpuhw->disabled = 1;
 		cpuhw->n_added = 0;
 
 		ebb_switch_out(mmcr0);
+
+#ifdef CONFIG_PPC64
+		/*
+		 * These are readable by userspace, may contain kernel
+		 * addresses and are not switched by context switch, so clear
+		 * them now to avoid leaking anything to userspace in general
+		 * including to another process.
+		 */
+		if (ppmu->flags & PPMU_ARCH_207S) {
+			mtspr(SPRN_SDAR, 0);
+			mtspr(SPRN_SIAR, 0);
+		}
+#endif
 	}
 
 	local_irq_restore(flags);
···
 	return 0;
 }
 
+static bool is_event_blacklisted(u64 ev)
+{
+	int i;
+
+	for (i=0; i < ppmu->n_blacklist_ev; i++) {
+		if (ppmu->blacklist_ev[i] == ev)
+			return true;
+	}
+
+	return false;
+}
+
 static int power_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
···
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
 			return -EOPNOTSUPP;
+
+		if (ppmu->blacklist_ev && is_event_blacklisted(ev))
+			return -EINVAL;
 		ev = ppmu->generic_events[ev];
 		break;
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
 			return err;
+
+		if (ppmu->blacklist_ev && is_event_blacklisted(ev))
+			return -EINVAL;
 		break;
 	case PERF_TYPE_RAW:
 		ev = event->attr.config;
+
+		if (ppmu->blacklist_ev && is_event_blacklisted(ev))
+			return -EINVAL;
 		break;
 	default:
 		return -ENOENT;

arch/powerpc/perf/power4-pmu.c

···
-/*
- * Performance counter support for POWER4 (GP) and POWER4+ (GQ) processors.
- *
- * Copyright 2009 Paul Mackerras, IBM Corporation.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#include <linux/kernel.h>
-#include <linux/perf_event.h>
-#include <linux/string.h>
-#include <asm/reg.h>
-#include <asm/cputable.h>
-
-/*
- * Bits in event code for POWER4
- */
-#define PM_PMC_SH	12	/* PMC number (1-based) for direct events */
-#define PM_PMC_MSK	0xf
-#define PM_UNIT_SH	8	/* TTMMUX number and setting - unit select */
-#define PM_UNIT_MSK	0xf
-#define PM_LOWER_SH	6
-#define PM_LOWER_MSK	1
-#define PM_LOWER_MSKS	0x40
-#define PM_BYTE_SH	4	/* Byte number of event bus to use */
-#define PM_BYTE_MSK	3
-#define PM_PMCSEL_MSK	7
-
-/*
- * Unit code values
- */
-#define PM_FPU		1
-#define PM_ISU1		2
-#define PM_IFU		3
-#define PM_IDU0		4
-#define PM_ISU1_ALT	6
-#define PM_ISU2		7
-#define PM_IFU_ALT	8
-#define PM_LSU0		9
-#define PM_LSU1		0xc
-#define PM_GPS		0xf
-
-/*
- * Bits in MMCR0 for POWER4
- */
-#define MMCR0_PMC1SEL_SH	8
-#define MMCR0_PMC2SEL_SH	1
-#define MMCR_PMCSEL_MSK		0x1f
-
-/*
- * Bits in MMCR1 for POWER4
- */
-#define MMCR1_TTM0SEL_SH	62
-#define MMCR1_TTC0SEL_SH	61
-#define MMCR1_TTM1SEL_SH	59
-#define MMCR1_TTC1SEL_SH	58
-#define MMCR1_TTM2SEL_SH	56
-#define MMCR1_TTC2SEL_SH	55
-#define MMCR1_TTM3SEL_SH	53
-#define MMCR1_TTC3SEL_SH	52
-#define MMCR1_TTMSEL_MSK	3
-#define MMCR1_TD_CP_DBG0SEL_SH	50
-#define MMCR1_TD_CP_DBG1SEL_SH	48
-#define MMCR1_TD_CP_DBG2SEL_SH	46
-#define MMCR1_TD_CP_DBG3SEL_SH	44
-#define MMCR1_DEBUG0SEL_SH	43
-#define MMCR1_DEBUG1SEL_SH	42
-#define MMCR1_DEBUG2SEL_SH	41
-#define MMCR1_DEBUG3SEL_SH	40
-#define MMCR1_PMC1_ADDER_SEL_SH	39
-#define MMCR1_PMC2_ADDER_SEL_SH	38
-#define MMCR1_PMC6_ADDER_SEL_SH	37
-#define MMCR1_PMC5_ADDER_SEL_SH	36
-#define MMCR1_PMC8_ADDER_SEL_SH	35
-#define MMCR1_PMC7_ADDER_SEL_SH	34
-#define MMCR1_PMC3_ADDER_SEL_SH	33
-#define MMCR1_PMC4_ADDER_SEL_SH	32
-#define MMCR1_PMC3SEL_SH	27
-#define MMCR1_PMC4SEL_SH	22
-#define MMCR1_PMC5SEL_SH	17
-#define MMCR1_PMC6SEL_SH	12
-#define MMCR1_PMC7SEL_SH	7
-#define MMCR1_PMC8SEL_SH	2	/* note bit 0 is in MMCRA for GP */
-
-static short mmcr1_adder_bits[8] = {
-	MMCR1_PMC1_ADDER_SEL_SH,
-	MMCR1_PMC2_ADDER_SEL_SH,
-	MMCR1_PMC3_ADDER_SEL_SH,
-	MMCR1_PMC4_ADDER_SEL_SH,
-	MMCR1_PMC5_ADDER_SEL_SH,
-	MMCR1_PMC6_ADDER_SEL_SH,
-	MMCR1_PMC7_ADDER_SEL_SH,
-	MMCR1_PMC8_ADDER_SEL_SH
-};
-
-/*
- * Bits in MMCRA
- */
-#define MMCRA_PMC8SEL0_SH	17	/* PMC8SEL bit 0 for GP */
-
-/*
- * Layout of constraint bits:
- * 6666555555555544444444443333333333222222222211111111110000000000
- * 3210987654321098765432109876543210987654321098765432109876543210
- *        |[  >[  >[   >|||[  >[  ><  ><  ><  ><  ><><><><><><><><>
- *        | UC1 UC2 UC3 ||| PS1 PS2 B0  B1  B2  B3 P1P2P3P4P5P6P7P8
- * 	  \SMPL	        ||\TTC3SEL
- * 		        |\TTC_IFU_SEL
- * 		        \TTM2SEL0
- *
- * SMPL - SAMPLE_ENABLE constraint
- *     56: SAMPLE_ENABLE value 0x0100_0000_0000_0000
- *
- * UC1 - unit constraint 1: can't have all three of FPU/ISU1/IDU0|ISU2
- *     55: UC1 error 0x0080_0000_0000_0000
- *     54: FPU events needed 0x0040_0000_0000_0000
- *     53: ISU1 events needed 0x0020_0000_0000_0000
- *     52: IDU0|ISU2 events needed 0x0010_0000_0000_0000
- *
- * UC2 - unit constraint 2: can't have all three of FPU/IFU/LSU0
- *     51: UC2 error 0x0008_0000_0000_0000
- *     50: FPU events needed 0x0004_0000_0000_0000
- *     49: IFU events needed 0x0002_0000_0000_0000
- *     48: LSU0 events needed 0x0001_0000_0000_0000
- *
- * UC3 - unit constraint 3: can't have all four of LSU0/IFU/IDU0|ISU2/ISU1
- *     47: UC3 error 0x8000_0000_0000
- *     46: LSU0 events needed 0x4000_0000_0000
- *     45: IFU events needed 0x2000_0000_0000
- *     44: IDU0|ISU2 events needed 0x1000_0000_0000
- *     43: ISU1 events needed 0x0800_0000_0000
- *
- * TTM2SEL0
- *     42: 0 = IDU0 events needed
- *     	   1 = ISU2 events needed 0x0400_0000_0000
- *
- * TTC_IFU_SEL
- *     41: 0 = IFU.U events needed
- *     	   1 = IFU.L events needed 0x0200_0000_0000
- *
- * TTC3SEL
- *     40: 0 = LSU1.U events needed
- *     	   1 = LSU1.L events needed 0x0100_0000_0000
- *
- * PS1
- *     39: PS1 error 0x0080_0000_0000
- *     36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000
- *
- * PS2
- *     35: PS2 error 0x0008_0000_0000
- *     32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000
- *
- * B0
- *     28-31: Byte 0 event source 0xf000_0000
- *     	   1 = FPU
- * 	   2 = ISU1
- * 	   3 = IFU
- * 	   4 = IDU0
- * 	   7 = ISU2
- * 	   9 = LSU0
- * 	   c = LSU1
- * 	   f = GPS
- *
- * B1, B2, B3
- *     24-27, 20-23, 16-19: Byte 1, 2, 3 event sources
- *
- * P8
- *     15: P8 error 0x8000
- *     14-15: Count of events needing PMC8
- *
- * P1..P7
- *     0-13: Count of events needing PMC1..PMC7
- *
- * Note: this doesn't allow events using IFU.U to be combined with events
- * using IFU.L, though that is feasible (using TTM0 and TTM2).  However
- * there are no listed events for IFU.L (they are debug events not
- * verified for performance monitoring) so this shouldn't cause a
- * problem.
- */
-
-static struct unitinfo {
-	unsigned long	value, mask;
-	int		unit;
-	int		lowerbit;
-} p4_unitinfo[16] = {
-	[PM_FPU]  = { 0x44000000000000ul, 0x88000000000000ul, PM_FPU, 0 },
-	[PM_ISU1] = { 0x20080000000000ul, 0x88000000000000ul, PM_ISU1, 0 },
-	[PM_ISU1_ALT] =
-		    { 0x20080000000000ul, 0x88000000000000ul, PM_ISU1, 0 },
-	[PM_IFU]  = { 0x02200000000000ul, 0x08820000000000ul, PM_IFU, 41 },
-	[PM_IFU_ALT] =
-		    { 0x02200000000000ul, 0x08820000000000ul, PM_IFU, 41 },
-	[PM_IDU0] = { 0x10100000000000ul, 0x80840000000000ul, PM_IDU0, 1 },
-	[PM_ISU2] = { 0x10140000000000ul, 0x80840000000000ul, PM_ISU2, 0 },
-	[PM_LSU0] = { 0x01400000000000ul, 0x08800000000000ul, PM_LSU0, 0 },
-	[PM_LSU1] = { 0x00000000000000ul, 0x00010000000000ul, PM_LSU1, 40 },
-	[PM_GPS]  = { 0x00000000000000ul, 0x00000000000000ul, PM_GPS, 0 }
-};
-
-static unsigned char direct_marked_event[8] = {
-	(1<<2) | (1<<3),	/* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */
-	(1<<3) | (1<<5),	/* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */
-	(1<<3),			/* PMC3: PM_MRK_ST_CMPL_INT */
-	(1<<4) | (1<<5),	/* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */
-	(1<<4) | (1<<5),	/* PMC5: PM_MRK_GRP_TIMEO */
-	(1<<3) | (1<<4) | (1<<5),
-		/* PMC6: PM_MRK_ST_GPS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */
-	(1<<4) | (1<<5),	/* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */
-	(1<<4),			/* PMC8: PM_MRK_LSU_FIN */
-};
-
-/*
- * Returns 1 if event counts things relating to marked instructions
- * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
- */
-static int p4_marked_instr_event(u64 event)
-{
-	int pmc, psel, unit, byte, bit;
-	unsigned int mask;
-
-	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
-	psel = event & PM_PMCSEL_MSK;
-	if (pmc) {
-		if (direct_marked_event[pmc - 1] & (1 << psel))
-			return 1;
-		if (psel == 0)		/* add events */
-			bit = (pmc <= 4)? pmc - 1: 8 - pmc;
-		else if (psel == 6)	/* decode events */
-			bit = 4;
-		else
-			return 0;
-	} else
-		bit = psel;
-
-	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
-	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
-	mask = 0;
-	switch (unit) {
-	case PM_LSU1:
-		if (event & PM_LOWER_MSKS)
-			mask = 1 << 28;		/* byte 7 bit 4 */
-		else
-			mask = 6 << 24;		/* byte 3 bits 1 and 2 */
-		break;
-	case PM_LSU0:
-		/* byte 3, bit 3; byte 2 bits 0,2,3,4,5; byte 1 */
-		mask = 0x083dff00;
-	}
-	return (mask >> (byte * 8 + bit)) & 1;
-}
-
-static int p4_get_constraint(u64 event, unsigned long *maskp,
-			     unsigned long *valp)
-{
-	int pmc, byte, unit, lower, sh;
-	unsigned long mask = 0, value = 0;
-	int grp = -1;
-
-	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
-	if (pmc) {
-		if (pmc > 8)
-			return -1;
-		sh = (pmc - 1) * 2;
-		mask |= 2 << sh;
-		value |= 1 << sh;
-		grp = ((pmc - 1) >> 1) & 1;
-	}
-	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
-	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
-	if (unit) {
-		lower = (event >> PM_LOWER_SH) & PM_LOWER_MSK;
-
-		/*
-		 * Bus events on bytes 0 and 2 can be counted
-		 * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8.
-		 */
-		if (!pmc)
-			grp = byte & 1;
-
-		if (!p4_unitinfo[unit].unit)
-			return -1;
-		mask  |= p4_unitinfo[unit].mask;
-		value |= p4_unitinfo[unit].value;
-		sh = p4_unitinfo[unit].lowerbit;
-		if (sh > 1)
-			value |= (unsigned long)lower << sh;
-		else if (lower != sh)
-			return -1;
-		unit = p4_unitinfo[unit].unit;
-
-		/* Set byte lane select field */
-		mask  |= 0xfULL << (28 - 4 * byte);
-		value |= (unsigned long)unit << (28 - 4 * byte);
-	}
-	if (grp == 0) {
-		/* increment PMC1/2/5/6 field */
-		mask  |= 0x8000000000ull;
-		value |= 0x1000000000ull;
-	} else {
-		/* increment PMC3/4/7/8 field */
-		mask  |= 0x800000000ull;
-		value |= 0x100000000ull;
-	}
-
-	/* Marked instruction events need sample_enable set */
-	if (p4_marked_instr_event(event)) {
-		mask  |= 1ull << 56;
-		value |= 1ull << 56;
-	}
-
-	/* PMCSEL=6 decode events on byte 2 need sample_enable clear */
-	if (pmc && (event & PM_PMCSEL_MSK) == 6 && byte == 2)
-		mask  |= 1ull << 56;
-
-	*maskp = mask;
-	*valp = value;
-	return 0;
-}
-
-static unsigned int ppc_inst_cmpl[] = {
-	0x1001, 0x4001, 0x6001, 0x7001, 0x8001
-};
-
-static int p4_get_alternatives(u64 event, unsigned int flags, u64 alt[])
-{
-	int i, j, na;
-
-	alt[0] = event;
-	na = 1;
-
-	/* 2 possibilities for PM_GRP_DISP_REJECT */
-	if (event == 0x8003 || event == 0x0224) {
-		alt[1] = event ^ (0x8003 ^ 0x0224);
-		return 2;
-	}
-
-	/* 2 possibilities for PM_ST_MISS_L1 */
-	if (event == 0x0c13 || event == 0x0c23) {
-		alt[1] = event ^ (0x0c13 ^ 0x0c23);
-		return 2;
-	}
-
-	/* several possibilities for PM_INST_CMPL */
-	for (i = 0; i < ARRAY_SIZE(ppc_inst_cmpl); ++i) {
-		if (event == ppc_inst_cmpl[i]) {
-			for (j = 0; j < ARRAY_SIZE(ppc_inst_cmpl); ++j)
-				if (j != i)
-					alt[na++] = ppc_inst_cmpl[j];
-			break;
-		}
-	}
-
-	return na;
-}
-
-static int p4_compute_mmcr(u64 event[], int n_ev,
-			   unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
-{
-	unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0;
-	unsigned int pmc, unit, byte, psel, lower;
-	unsigned int ttm, grp;
-	unsigned int pmc_inuse = 0;
-	unsigned int pmc_grp_use[2];
-	unsigned char busbyte[4];
-	unsigned char unituse[16];
-	unsigned int unitlower = 0;
-	int i;
-
-	if (n_ev > 8)
-		return -1;
-
-	/* First pass to count resource use */
-	pmc_grp_use[0] = pmc_grp_use[1] = 0;
-	memset(busbyte, 0, sizeof(busbyte));
-	memset(unituse, 0, sizeof(unituse));
-	for (i = 0; i < n_ev; ++i) {
-		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
-		if (pmc) {
-			if (pmc_inuse & (1 << (pmc - 1)))
-				return -1;
-			pmc_inuse |= 1 << (pmc - 1);
-			/* count 1/2/5/6 vs 3/4/7/8 use */
-			++pmc_grp_use[((pmc - 1) >> 1) & 1];
-		}
-		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
-		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
-		lower = (event[i] >> PM_LOWER_SH) & PM_LOWER_MSK;
-		if (unit) {
-			if (!pmc)
-				++pmc_grp_use[byte & 1];
-			if (unit == 6 || unit == 8)
-				/* map alt ISU1/IFU codes: 6->2, 8->3 */
-				unit = (unit >> 1) - 1;
-			if (busbyte[byte] && busbyte[byte] != unit)
-				return -1;
-			busbyte[byte] = unit;
-			lower <<= unit;
-			if (unituse[unit] && lower != (unitlower & lower))
-				return -1;
-			unituse[unit] = 1;
-			unitlower |= lower;
-		}
-	}
-	if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4)
-		return -1;
-
-	/*
-	 * Assign resources and set multiplexer selects.
-	 *
-	 * Units 1,2,3 are on TTM0, 4,6,7 on TTM1, 8,10 on TTM2.
-	 * Each TTMx can only select one unit, but since
-	 * units 2 and 6 are both ISU1, and 3 and 8 are both IFU,
-	 * we have some choices.
-	 */
-	if (unituse[2] & (unituse[1] | (unituse[3] & unituse[9]))) {
-		unituse[6] = 1;		/* Move 2 to 6 */
-		unituse[2] = 0;
-	}
-	if (unituse[3] & (unituse[1] | unituse[2])) {
-		unituse[8] = 1;		/* Move 3 to 8 */
-		unituse[3] = 0;
-		unitlower = (unitlower & ~8) | ((unitlower & 8) << 5);
-	}
-	/* Check only one unit per TTMx */
-	if (unituse[1] + unituse[2] + unituse[3] > 1 ||
-	    unituse[4] + unituse[6] + unituse[7] > 1 ||
-	    unituse[8] + unituse[9] > 1 ||
-	    (unituse[5] | unituse[10] | unituse[11] |
-	     unituse[13] | unituse[14]))
-		return -1;
-
-	/* Set TTMxSEL fields.  Note, units 1-3 => TTM0SEL codes 0-2 */
-	mmcr1 |= (unsigned long)(unituse[3] * 2 + unituse[2])
-		<< MMCR1_TTM0SEL_SH;
-	mmcr1 |= (unsigned long)(unituse[7] * 3 + unituse[6] * 2)
-		<< MMCR1_TTM1SEL_SH;
-	mmcr1 |= (unsigned long)unituse[9] << MMCR1_TTM2SEL_SH;
-
-	/* Set TTCxSEL fields. */
-	if (unitlower & 0xe)
-		mmcr1 |= 1ull << MMCR1_TTC0SEL_SH;
-	if (unitlower & 0xf0)
-		mmcr1 |= 1ull << MMCR1_TTC1SEL_SH;
-	if (unitlower & 0xf00)
-		mmcr1 |= 1ull << MMCR1_TTC2SEL_SH;
-	if (unitlower & 0x7000)
-		mmcr1 |= 1ull << MMCR1_TTC3SEL_SH;
-
-	/* Set byte lane select fields. */
-	for (byte = 0; byte < 4; ++byte) {
-		unit = busbyte[byte];
-		if (!unit)
-			continue;
-		if (unit == 0xf) {
-			/* special case for GPS */
-			mmcr1 |= 1ull << (MMCR1_DEBUG0SEL_SH - byte);
-		} else {
-			if (!unituse[unit])
-				ttm = unit - 1;		/* 2->1, 3->2 */
-			else
-				ttm = unit >> 2;
-			mmcr1 |= (unsigned long)ttm
-				<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
-		}
-	}
-
-	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
-	for (i = 0; i < n_ev; ++i) {
-		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
-		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
-		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
-		psel = event[i] & PM_PMCSEL_MSK;
-		if (!pmc) {
-			/* Bus event or 00xxx direct event (off or cycles) */
-			if (unit)
-				psel |= 0x10 | ((byte & 2) << 2);
-			for (pmc = 0; pmc < 8; ++pmc) {
-				if (pmc_inuse & (1 << pmc))
-					continue;
-				grp = (pmc >> 1) & 1;
-				if (unit) {
-					if (grp == (byte & 1))
-						break;
-				} else if (pmc_grp_use[grp] < 4) {
-					++pmc_grp_use[grp];
-					break;
-				}
-			}
-			pmc_inuse |= 1 << pmc;
-		} else {
-			/* Direct event */
-			--pmc;
-			if (psel == 0 && (byte & 2))
-				/* add events on higher-numbered bus */
-				mmcr1 |= 1ull << mmcr1_adder_bits[pmc];
-			else if (psel == 6 && byte == 3)
-				/* seem to need to set sample_enable here */
-				mmcra |= MMCRA_SAMPLE_ENABLE;
-			psel |= 8;
-		}
-		if (pmc <= 1)
-			mmcr0 |= psel << (MMCR0_PMC1SEL_SH - 7 * pmc);
-		else
-			mmcr1 |= psel << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
-		if (pmc == 7)	/* PMC8 */
-			mmcra |= (psel & 1) << MMCRA_PMC8SEL0_SH;
-		hwc[i] = pmc;
-		if (p4_marked_instr_event(event[i]))
-			mmcra |= MMCRA_SAMPLE_ENABLE;
-	}
-
-	if (pmc_inuse & 1)
-		mmcr0 |= MMCR0_PMC1CE;
-	if (pmc_inuse & 0xfe)
-		mmcr0 |= MMCR0_PMCjCE;
-
-	mmcra |= 0x2000;	/* mark only one IOP per PPC instruction */
-
-	/* Return MMCRx values */
-	mmcr[0] = mmcr0;
-	mmcr[1] = mmcr1;
-	mmcr[2] = mmcra;
-	return 0;
-}
-
-static void p4_disable_pmc(unsigned int pmc, unsigned long mmcr[])
-{
-	/*
-	 * Setting the PMCxSEL field to 0 disables PMC x.
-	 * (Note that pmc is 0-based here, not 1-based.)
-	 */
-	if (pmc <= 1) {
-		mmcr[0] &= ~(0x1fUL << (MMCR0_PMC1SEL_SH - 7 * pmc));
-	} else {
-		mmcr[1] &= ~(0x1fUL << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)));
-		if (pmc == 7)
-			mmcr[2] &= ~(1UL << MMCRA_PMC8SEL0_SH);
-	}
-}
-
-static int p4_generic_events[] = {
-	[PERF_COUNT_HW_CPU_CYCLES]		= 7,
-	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x1001,
-	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x8c10, /* PM_LD_REF_L1 */
-	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3c10, /* PM_LD_MISS_L1 */
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x330,  /* PM_BR_ISSUED */
-	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x331,  /* PM_BR_MPRED_CR */
-};
-
-#define C(x)	PERF_COUNT_HW_CACHE_##x
-
-/*
- * Table of generalized cache-related events.
- * 0 means not supported, -1 means nonsensical, other values
- * are event codes.
- */
-static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
-	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	0x8c10,		0x3c10	},
-		[C(OP_WRITE)] = {	0x7c10,		0xc13	},
-		[C(OP_PREFETCH)] = {	0xc35,		0	},
-	},
-	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	0,		0	},
-		[C(OP_WRITE)] = {	-1,		-1	},
-		[C(OP_PREFETCH)] = {	0,		0	},
-	},
-	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	0,		0	},
-		[C(OP_WRITE)] = {	0,		0	},
-		[C(OP_PREFETCH)] = {	0xc34,		0	},
-	},
-	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	0,		0x904	},
-		[C(OP_WRITE)] = {	-1,		-1	},
-		[C(OP_PREFETCH)] = {	-1,		-1	},
-	},
-	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	0,		0x900	},
-		[C(OP_WRITE)] = {	-1,		-1	},
-		[C(OP_PREFETCH)] = {	-1,		-1	},
-	},
-	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	0x330,		0x331	},
-		[C(OP_WRITE)] = {	-1,		-1	},
-		[C(OP_PREFETCH)] = {	-1,		-1	},
-	},
-	[C(NODE)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	-1,		-1	},
-		[C(OP_WRITE)] = {	-1,		-1	},
-		[C(OP_PREFETCH)] = {	-1,		-1	},
-	},
-};
-
-static struct power_pmu power4_pmu = {
-	.name			= "POWER4/4+",
-	.n_counter		= 8,
-	.max_alternatives	= 5,
-	.add_fields		= 0x0000001100005555ul,
-	.test_adder		= 0x0011083300000000ul,
-	.compute_mmcr		= p4_compute_mmcr,
-	.get_constraint		= p4_get_constraint,
-	.get_alternatives	= p4_get_alternatives,
-	.disable_pmc		= p4_disable_pmc,
-	.n_generic		= ARRAY_SIZE(p4_generic_events),
-	.generic_events		= p4_generic_events,
-	.cache_events		= &power4_cache_events,
-	.flags			= PPMU_NO_SIPR | PPMU_NO_CONT_SAMPLING,
-};
-
-static int __init init_power4_pmu(void)
-{
-	if (!cur_cpu_spec->oprofile_cpu_type ||
-	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power4"))
-		return -ENODEV;
-
-	return register_power_pmu(&power4_pmu);
-}
-
-early_initcall(init_power4_pmu);

arch/powerpc/perf/power9-events-list.h

···
 EVENT(PM_BR_2PATH,				0x20036)
 /* ALternate branch event that are not strongly biased */
 EVENT(PM_BR_2PATH_ALT,				0x40036)
+
+/* Blacklisted events */
+EVENT(PM_MRK_ST_DONE_L2,			0x10134)
+EVENT(PM_RADIX_PWC_L1_HIT,			0x1f056)
+EVENT(PM_FLOP_CMPL,				0x100f4)
+EVENT(PM_MRK_NTF_FIN,				0x20112)
+EVENT(PM_RADIX_PWC_L2_HIT,			0x2d024)
+EVENT(PM_IFETCH_THROTTLE,			0x3405e)
+EVENT(PM_MRK_L2_TM_ST_ABORT_SISTER,		0x3e15c)
+EVENT(PM_RADIX_PWC_L3_HIT,			0x3f056)
+EVENT(PM_RUN_CYC_SMT2_MODE,			0x3006c)
+EVENT(PM_TM_TX_PASS_RUN_INST,			0x4e014)
+EVENT(PM_DISP_HELD_SYNC_HOLD,			0x4003c)
+EVENT(PM_DTLB_MISS_16G,				0x1c058)
+EVENT(PM_DERAT_MISS_2M,				0x1c05a)
+EVENT(PM_DTLB_MISS_2M,				0x1c05c)
+EVENT(PM_MRK_DTLB_MISS_1G,			0x1d15c)
+EVENT(PM_DTLB_MISS_4K,				0x2c056)
+EVENT(PM_DERAT_MISS_1G,				0x2c05a)
+EVENT(PM_MRK_DERAT_MISS_2M,			0x2d152)
+EVENT(PM_MRK_DTLB_MISS_4K,			0x2d156)
+EVENT(PM_MRK_DTLB_MISS_16G,			0x2d15e)
+EVENT(PM_DTLB_MISS_64K,				0x3c056)
+EVENT(PM_MRK_DERAT_MISS_1G,			0x3d152)
+EVENT(PM_MRK_DTLB_MISS_64K,			0x3d156)
+EVENT(PM_DTLB_MISS_16M,				0x4c056)
+EVENT(PM_DTLB_MISS_1G,				0x4c05a)
+EVENT(PM_MRK_DTLB_MISS_16M,			0x4c15e)

arch/powerpc/perf/power9-pmu.c

···
 #define POWER9_MMCRA_IFM2		0x0000000080000000UL
 #define POWER9_MMCRA_IFM3		0x00000000C0000000UL
 
+/* Nasty Power9 specific hack */
+#define PVR_POWER9_CUMULUS		0x00002000
+
 /* PowerISA v2.07 format attribute structure*/
 extern struct attribute_group isa207_pmu_format_group;
+
+int p9_dd21_bl_ev[] = {
+	PM_MRK_ST_DONE_L2,
+	PM_RADIX_PWC_L1_HIT,
+	PM_FLOP_CMPL,
+	PM_MRK_NTF_FIN,
+	PM_RADIX_PWC_L2_HIT,
+	PM_IFETCH_THROTTLE,
+	PM_MRK_L2_TM_ST_ABORT_SISTER,
+	PM_RADIX_PWC_L3_HIT,
+	PM_RUN_CYC_SMT2_MODE,
+	PM_TM_TX_PASS_RUN_INST,
+	PM_DISP_HELD_SYNC_HOLD,
+};
+
+int p9_dd22_bl_ev[] = {
+	PM_DTLB_MISS_16G,
+	PM_DERAT_MISS_2M,
+	PM_DTLB_MISS_2M,
+	PM_MRK_DTLB_MISS_1G,
+	PM_DTLB_MISS_4K,
+	PM_DERAT_MISS_1G,
+	PM_MRK_DERAT_MISS_2M,
+	PM_MRK_DTLB_MISS_4K,
+	PM_MRK_DTLB_MISS_16G,
+	PM_DTLB_MISS_64K,
+	PM_MRK_DERAT_MISS_1G,
+	PM_MRK_DTLB_MISS_64K,
+	PM_DISP_HELD_SYNC_HOLD,
+	PM_DTLB_MISS_16M,
+	PM_DTLB_MISS_1G,
+	PM_MRK_DTLB_MISS_16M,
+};
 
 /* Table of alternatives, sorted by column 0 */
 static const unsigned int power9_event_alternatives[][MAX_ALT] = {
···
 static int __init init_power9_pmu(void)
 {
 	int rc = 0;
+	unsigned int pvr = mfspr(SPRN_PVR);
 
 	/* Comes from cpu_specs[] */
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power9"))
 		return -ENODEV;
+
+	/* Blacklist events */
+	if (!(pvr & PVR_POWER9_CUMULUS)) {
+		if ((PVR_CFG(pvr) == 2) && (PVR_MIN(pvr) == 1)) {
+			power9_pmu.blacklist_ev = p9_dd21_bl_ev;
+			power9_pmu.n_blacklist_ev = ARRAY_SIZE(p9_dd21_bl_ev);
+		} else if ((PVR_CFG(pvr) == 2) && (PVR_MIN(pvr) == 2)) {
+			power9_pmu.blacklist_ev = p9_dd22_bl_ev;
+			power9_pmu.n_blacklist_ev = ARRAY_SIZE(p9_dd22_bl_ev);
+		}
+	}
 
 	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
 		/*

arch/powerpc/platforms/4xx/msi.c

···
 
 	dev_dbg(&dev->dev, "PCIE-MSI: Setting up MSI support...\n");
 
-	msi = kzalloc(sizeof(struct ppc4xx_msi), GFP_KERNEL);
+	msi = kzalloc(sizeof(*msi), GFP_KERNEL);
 	if (!msi) {
 		dev_err(&dev->dev, "No memory for MSI structure\n");
 		return -ENOMEM;
···
 	if (!msi_irqs)
 		return -ENODEV;
 
-	if (ppc4xx_setup_pcieh_hw(dev, res, msi))
+	err = ppc4xx_setup_pcieh_hw(dev, res, msi);
+	if (err)
 		goto error_out;
 
 	err = ppc4xx_msi_init_allocator(dev, msi);

arch/powerpc/platforms/4xx/ocm.c

···
 		if (IS_ERR_VALUE(offset))
 			continue;
 
-		ocm_blk = kzalloc(sizeof(struct ocm_block), GFP_KERNEL);
+		ocm_blk = kzalloc(sizeof(*ocm_blk), GFP_KERNEL);
 		if (!ocm_blk) {
 			printk(KERN_ERR "PPC4XX OCM: could not allocate ocm block");
 			rh_free(ocm_reg->rh, offset);

arch/powerpc/platforms/85xx/smp.c

···
 	for (i = 0; i < 500; i++) {
 		if (is_cpu_dead(cpu)) {
 #ifdef CONFIG_PPC64
-			paca[cpu].cpu_start = 0;
+			paca_ptrs[cpu]->cpu_start = 0;
 #endif
 			return;
 		}
···
 		return ret;
 
 done:
-	paca[nr].cpu_start = 1;
+	paca_ptrs[nr]->cpu_start = 1;
 	generic_set_cpu_up(nr);
 
 	return ret;
···
 	}
 
 	if (disable_threadbit) {
-		while (paca[disable_cpu].kexec_state < KEXEC_STATE_REAL_MODE) {
+		while (paca_ptrs[disable_cpu]->kexec_state < KEXEC_STATE_REAL_MODE) {
 			barrier();
 			now = mftb();
 			if (!notified && now - start > 1000000) {
 				pr_info("%s/%d: waiting for cpu %d to enter KEXEC_STATE_REAL_MODE (%d)\n",
 					__func__, smp_processor_id(),
 					disable_cpu,
-					paca[disable_cpu].kexec_state);
+					paca_ptrs[disable_cpu]->kexec_state);
 				notified = true;
 			}
 		}

arch/powerpc/platforms/8xx/m8xx_setup.c

···
 
 static void cpm_cascade(struct irq_desc *desc)
 {
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	int cascade_irq = cpm_get_irq();
-
-	if (cascade_irq >= 0)
-		generic_handle_irq(cascade_irq);
-
-	chip->irq_eoi(&desc->irq_data);
+	generic_handle_irq(cpm_get_irq());
 }
 
 /* Initialize the internal interrupt controllers.  The number of

arch/powerpc/platforms/Kconfig.cputype

···
 	help
 	  There are two families of 64 bit PowerPC chips supported.
 	  The most common ones are the desktop and server CPUs
-	  (POWER4, POWER5, 970, POWER5+, POWER6, POWER7, POWER8 ...)
+	  (POWER5, 970, POWER5+, POWER6, POWER7, POWER8, POWER9 ...)
 
 	  The other are the "embedded" processors compliant with the
 	  "Book 3E" variant of the architecture
···
 choice
 	prompt "CPU selection"
 	depends on PPC64
-	default POWER8_CPU if CPU_LITTLE_ENDIAN
 	default GENERIC_CPU
 	help
 	  This will create a kernel which is optimised for a particular CPU.
···
 	  If unsure, select Generic.
 
 config GENERIC_CPU
-	bool "Generic"
+	bool "Generic (POWER4 and above)"
 	depends on !CPU_LITTLE_ENDIAN
+
+config GENERIC_CPU
+	bool "Generic (POWER8 and above)"
+	depends on CPU_LITTLE_ENDIAN
+	select ARCH_HAS_FAST_MULTIPLIER
 
 config CELL_CPU
 	bool "Cell Broadband Engine"
-	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
-
-config POWER4_CPU
-	bool "POWER4"
 	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
 
 config POWER5_CPU
···
 
 config POWER8_CPU
 	bool "POWER8"
+	depends on PPC_BOOK3S_64
+	select ARCH_HAS_FAST_MULTIPLIER
+
+config POWER9_CPU
+	bool "POWER9"
 	depends on PPC_BOOK3S_64
 	select ARCH_HAS_FAST_MULTIPLIER
 
···
 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

arch/powerpc/platforms/cell/axon_msi.c

···
 
 	pr_devel("axon_msi: setting up dn %pOF\n", dn);
 
-	msic = kzalloc(sizeof(struct axon_msic), GFP_KERNEL);
+	msic = kzalloc(sizeof(*msic), GFP_KERNEL);
 	if (!msic) {
 		printk(KERN_ERR "axon_msi: couldn't allocate msic for %pOF\n",
 		       dn);

arch/powerpc/platforms/cell/smp.c

···
 	pcpu = get_hard_smp_processor_id(lcpu);
 
 	/* Fixup atomic count: it exited inside IRQ handler. */
-	task_thread_info(paca[lcpu].__current)->preempt_count	= 0;
+	task_thread_info(paca_ptrs[lcpu]->__current)->preempt_count	= 0;
 
 	/*
 	 * If the RTAS start-cpu token does not exist then presume the
···
 	 * cpu_start field to become non-zero After we set cpu_start,
 	 * the processor will continue on to secondary_start
 	 */
-	paca[nr].cpu_start = 1;
+	paca_ptrs[nr]->cpu_start = 1;
 
 	return 0;
 }

arch/powerpc/platforms/cell/spider-pci.c

···
 	pr_debug("SPIDERPCI-IOWA:Bus initialize for spider(%pOF)\n",
 		 np);
 
-	priv = kzalloc(sizeof(struct spiderpci_iowa_private), GFP_KERNEL);
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		pr_err("SPIDERPCI-IOWA:"
 		       "Can't allocate struct spiderpci_iowa_private");

arch/powerpc/platforms/cell/spufs/lscsa_alloc.c

···
 	struct spu_lscsa *lscsa;
 	unsigned char *p;
 
-	lscsa = vzalloc(sizeof(struct spu_lscsa));
+	lscsa = vzalloc(sizeof(*lscsa));
 	if (!lscsa)
 		return -ENOMEM;
 	csa->lscsa = lscsa;

arch/powerpc/platforms/embedded6xx/flipper-pic.c

···
 	out_be32(io_base + FLIPPER_ICR, 0xffffffff);
 }
 
-struct irq_domain * __init flipper_pic_init(struct device_node *np)
+static struct irq_domain * __init flipper_pic_init(struct device_node *np)
 {
 	struct device_node *pi;
 	struct irq_domain *irq_domain = NULL;

arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c

···
 /*
  * Transmits a character.
  */
-void ug_udbg_putc(char ch)
+static void ug_udbg_putc(char ch)
 {
 	ug_putc(ch);
 }

arch/powerpc/platforms/embedded6xx/wii.c

···
 #define HW_GPIO_BASE(idx)	(idx * 0x20)
 #define HW_GPIO_OUT(idx)	(HW_GPIO_BASE(idx) + 0)
 #define HW_GPIO_DIR(idx)	(HW_GPIO_BASE(idx) + 4)
+#define HW_GPIO_OWNER		(HW_GPIO_BASE(1) + 0x1c)
 
 #define HW_GPIO_SHUTDOWN	(1<<1)
 #define HW_GPIO_SLOT_LED	(1<<5)
···
 	BUG_ON(memblock.memory.cnt != 2);
 	BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base));
 
-	/* trim unaligned tail */
-	memblock_remove(ALIGN(p[1].base + p[1].size, PAGE_SIZE),
-			(phys_addr_t)ULLONG_MAX);
-
-	/* determine hole, add & reserve them */
+	/* determine hole */
 	wii_hole_start = ALIGN(p[0].base + p[0].size, PAGE_SIZE);
 	wii_hole_size = p[1].base - wii_hole_start;
-	memblock_add(wii_hole_start, wii_hole_size);
-	memblock_reserve(wii_hole_start, wii_hole_size);
-
-	BUG_ON(memblock.memory.cnt != 1);
-	__memblock_dump_all();
-
-	/* allow ioremapping the address space in the hole */
-	__allow_ioremap_reserved = 1;
 }
 
 unsigned long __init wii_mmu_mapin_mem2(unsigned long top)
···
 	local_irq_disable();
 
 	if (hw_gpio) {
+		/*
+		 * set the owner of the shutdown pin to ARM, because it is
+		 * accessed through the registers for the ARM, below
+		 */
+		clrbits32(hw_gpio + HW_GPIO_OWNER, HW_GPIO_SHUTDOWN);
+
 		/* make sure that the poweroff GPIO is configured as output */
 		setbits32(hw_gpio + HW_GPIO_DIR(1), HW_GPIO_SHUTDOWN);
 
···
 	if (!machine_is(wii))
 		return 0;
 
-	of_platform_bus_probe(NULL, wii_of_bus, NULL);
+	of_platform_populate(NULL, wii_of_bus, NULL, NULL);
 	return 0;
 }
 device_initcall(wii_device_probe);

arch/powerpc/platforms/powermac/low_i2c.c

···
 	const u32		*psteps, *prate, *addrp;
 	u32			steps;
 
-	host = kzalloc(sizeof(struct pmac_i2c_host_kw), GFP_KERNEL);
+	host = kzalloc(sizeof(*host), GFP_KERNEL);
 	if (host == NULL) {
 		printk(KERN_ERR "low_i2c: Can't allocate host for %pOF\n",
 		       np);

arch/powerpc/platforms/powermac/pfunc_core.c

···
 
 	while (length >= 12) {
 		/* Allocate a structure */
-		func = kzalloc(sizeof(struct pmf_function), GFP_KERNEL);
+		func = kzalloc(sizeof(*func), GFP_KERNEL);
 		if (func == NULL)
 			goto bail;
 		kref_init(&func->ref);
···
 		return -EBUSY;
 	}
 
-	dev = kzalloc(sizeof(struct pmf_device), GFP_KERNEL);
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (dev == NULL) {
 		DBG("pmf: no memory !\n");
 		return -ENOMEM;

arch/powerpc/platforms/powernv/Makefile

···
 obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
 obj-$(CONFIG_PPC_MEMTRACE)	+= memtrace.o
 obj-$(CONFIG_PPC_VAS)	+= vas.o vas-window.o vas-debug.o
-obj-$(CONFIG_PPC_FTW)	+= nx-ftw.o
 obj-$(CONFIG_OCXL_BASE)	+= ocxl.o

arch/powerpc/platforms/powernv/eeh-powernv.c

···
 	dev_pe = dev_pe->parent;
 	while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) {
 		int ret;
-		int active_flags = (EEH_STATE_MMIO_ACTIVE |
-				    EEH_STATE_DMA_ACTIVE);
-
 		ret = eeh_ops->get_state(dev_pe, NULL);
-		if (ret <= 0 || (ret & active_flags) == active_flags) {
+		if (ret <= 0 || eeh_state_active(ret)) {
 			dev_pe = dev_pe->parent;
 			continue;
 		}
···
 	struct eeh_pe *phb_pe, *parent_pe;
 	__be64 frozen_pe_no;
 	__be16 err_type, severity;
-	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	long rc;
 	int state, ret = EEH_NEXT_ERR_NONE;
 
···
 
 				/* Frozen parent PE ? */
 				state = eeh_ops->get_state(parent_pe, NULL);
-				if (state > 0 &&
-				    (state & active_flags) != active_flags)
+				if (state > 0 && !eeh_state_active(state))
 					*pe = parent_pe;
 
 				/* Next parent level */

arch/powerpc/platforms/powernv/idle.c

···
 #include <asm/code-patching.h>
 #include <asm/smp.h>
 #include <asm/runlatch.h>
+#include <asm/dbell.h>
 
 #include "powernv.h"
 #include "subcore.h"
···
 
 	for_each_possible_cpu(cpu) {
 		uint64_t pir = get_hard_smp_processor_id(cpu);
-		uint64_t hsprg0_val = (uint64_t)&paca[cpu];
+		uint64_t hsprg0_val = (uint64_t)paca_ptrs[cpu];
 
 		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
 		if (rc != 0)
···
 		for (j = 0; j < threads_per_core; j++) {
 			int cpu = first_cpu + j;
 
-			paca[cpu].core_idle_state_ptr = core_idle_state;
-			paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
-			paca[cpu].thread_mask = 1 << j;
+			paca_ptrs[cpu]->core_idle_state_ptr = core_idle_state;
+			paca_ptrs[cpu]->thread_idle_state = PNV_THREAD_RUNNING;
+			paca_ptrs[cpu]->thread_mask = 1 << j;
 			if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
 				continue;
-			paca[cpu].thread_sibling_pacas =
+			paca_ptrs[cpu]->thread_sibling_pacas =
 				kmalloc_node(paca_ptr_array_size,
 					     GFP_KERNEL, node);
 		}
···
 	power9_idle_type(pnv_default_stop_val, pnv_default_stop_mask);
 }
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+/*
+ * This is used in working around bugs in thread reconfiguration
+ * on POWER9 (at least up to Nimbus DD2.2) relating to transactional
+ * memory and the way that XER[SO] is checkpointed.
+ * This function forces the core into SMT4 in order by asking
+ * all other threads not to stop, and sending a message to any
+ * that are in a stop state.
+ * Must be called with preemption disabled.
+ */
+void pnv_power9_force_smt4_catch(void)
+{
+	int cpu, cpu0, thr;
+	int awake_threads = 1;		/* this thread is awake */
+	int poke_threads = 0;
+	int need_awake = threads_per_core;
+
+	cpu = smp_processor_id();
+	cpu0 = cpu & ~(threads_per_core - 1);
+	for (thr = 0; thr < threads_per_core; ++thr) {
+		if (cpu != cpu0 + thr)
+			atomic_inc(&paca_ptrs[cpu0+thr]->dont_stop);
+	}
+	/* order setting dont_stop vs testing requested_psscr */
+	mb();
+	for (thr = 0; thr < threads_per_core; ++thr) {
+		if (!paca_ptrs[cpu0+thr]->requested_psscr)
+			++awake_threads;
+		else
+			poke_threads |= (1 << thr);
+	}
+
+	/* If at least 3 threads are awake, the core is in SMT4 already */
+	if (awake_threads < need_awake) {
+		/* We have to wake some threads; we'll use msgsnd */
+		for (thr = 0; thr < threads_per_core; ++thr) {
+			if (poke_threads & (1 << thr)) {
+				ppc_msgsnd_sync();
+				ppc_msgsnd(PPC_DBELL_MSGTYPE, 0,
+					   paca_ptrs[cpu0+thr]->hw_cpu_id);
+			}
+		}
+		/* now spin until at least 3 threads are awake */
+		do {
+			for (thr = 0; thr < threads_per_core; ++thr) {
+				if ((poke_threads & (1 << thr)) &&
+				    !paca_ptrs[cpu0+thr]->requested_psscr) {
+					++awake_threads;
+					poke_threads &= ~(1 << thr);
+				}
+			}
+		} while (awake_threads < need_awake);
+	}
+}
+EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_catch);
+
+void pnv_power9_force_smt4_release(void)
+{
+	int cpu, cpu0, thr;
+
+	cpu = smp_processor_id();
+	cpu0 = cpu & ~(threads_per_core - 1);
+
+	/* clear all the dont_stop flags */
+	for (thr = 0; thr < threads_per_core; ++thr) {
+		if (cpu != cpu0 + thr)
+			atomic_dec(&paca_ptrs[cpu0+thr]->dont_stop);
+	}
+}
+EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_release);
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
+
 #ifdef CONFIG_HOTPLUG_CPU
 static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
 {
···
 		psscr = mfspr(SPRN_PSSCR);
 		psscr = (psscr & ~pnv_deepest_stop_psscr_mask) |
 						pnv_deepest_stop_psscr_val;
-		srr1 = power9_idle_stop(psscr);
+		srr1 = power9_offline_stop(psscr);
 
 	} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
 		   (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
···
 			for (i = 0; i < threads_per_core; i++) {
 				int j = base_cpu + i;
 
-				paca[j].thread_sibling_pacas[idx] = &paca[cpu];
+				paca_ptrs[j]->thread_sibling_pacas[idx] =
+					paca_ptrs[cpu];
 			}
 		}
 	}

arch/powerpc/platforms/powernv/npu-dma.c

···
 	void *priv;
 };
 
+struct mmio_atsd_reg {
+	struct npu *npu;
+	int reg;
+};
+
 /*
  * Find a free MMIO ATSD register and mark it in use. Return -ENOSPC
  * if none are available.
···
 	int i;
 
 	for (i = 0; i < npu->mmio_atsd_count; i++) {
-		if (!test_and_set_bit(i, &npu->mmio_atsd_usage))
+		if (!test_and_set_bit_lock(i, &npu->mmio_atsd_usage))
 			return i;
 	}
 
···
 
 static void put_mmio_atsd_reg(struct npu *npu, int reg)
 {
-	clear_bit(reg, &npu->mmio_atsd_usage);
+	clear_bit_unlock(reg, &npu->mmio_atsd_usage);
 }
 
 /* MMIO ATSD register offsets */
 #define XTS_ATSD_AVA  1
 #define XTS_ATSD_STAT 2
 
-static int mmio_launch_invalidate(struct npu *npu, unsigned long launch,
-				unsigned long va)
+static void mmio_launch_invalidate(struct mmio_atsd_reg *mmio_atsd_reg,
+				unsigned long launch, unsigned long va)
 {
-	int mmio_atsd_reg;
-
-	do {
-		mmio_atsd_reg = get_mmio_atsd_reg(npu);
-		cpu_relax();
-	} while (mmio_atsd_reg < 0);
+	struct npu *npu = mmio_atsd_reg->npu;
+	int reg = mmio_atsd_reg->reg;
 
 	__raw_writeq(cpu_to_be64(va),
-		npu->mmio_atsd_regs[mmio_atsd_reg] + XTS_ATSD_AVA);
+		npu->mmio_atsd_regs[reg] + XTS_ATSD_AVA);
 	eieio();
-	__raw_writeq(cpu_to_be64(launch), npu->mmio_atsd_regs[mmio_atsd_reg]);
-
-	return mmio_atsd_reg;
+	__raw_writeq(cpu_to_be64(launch), npu->mmio_atsd_regs[reg]);
 }
 
-static int mmio_invalidate_pid(struct npu *npu, unsigned long pid, bool flush)
+static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS],
+				unsigned long pid, bool flush)
 {
+	int i;
 	unsigned long launch;
 
-	/* IS set to invalidate matching PID */
-	launch = PPC_BIT(12);
+	for (i = 0; i <= max_npu2_index; i++) {
+		if (mmio_atsd_reg[i].reg < 0)
+			continue;
 
-	/* PRS set to process-scoped */
-	launch |= PPC_BIT(13);
+		/* IS set to invalidate matching PID */
+		launch = PPC_BIT(12);
 
-	/* 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);
+		/* AP */
+		launch |= (u64)
+			mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17);
 
-	/* No flush */
-	launch |= !flush << PPC_BITLSHIFT(39);
+		/* PID */
+		launch |= pid << PPC_BITLSHIFT(38);
 
-	/* Invalidating the entire process doesn't use a va */
-	return mmio_launch_invalidate(npu, launch, 0);
+		/* No flush */
+		launch |= !flush << PPC_BITLSHIFT(39);
+
+		/* Invalidating the entire process doesn't use a va */
+		mmio_launch_invalidate(&mmio_atsd_reg[i], launch, 0);
+	}
 }
 
-static int mmio_invalidate_va(struct npu *npu, unsigned long va,
-			unsigned long pid, bool flush)
+static void mmio_invalidate_va(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS],
+			unsigned long va, unsigned long pid, bool flush)
 {
+	int i;
 	unsigned long launch;
 
-	/* IS set to invalidate target VA */
-	launch = 0;
+	for (i = 0; i <= max_npu2_index; i++) {
+		if (mmio_atsd_reg[i].reg < 0)
+			continue;
 
-	/* PRS set to process scoped */
-	launch |= PPC_BIT(13);
+		/* IS set to invalidate target VA */
+		launch = 0;
 
-	/* 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);
+		/* AP */
+		launch |= (u64)
+			mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17);
 
-	/* No flush */
-	launch |= !flush << PPC_BITLSHIFT(39);
+		/* PID */
+		launch |= pid << PPC_BITLSHIFT(38);
 
-	return mmio_launch_invalidate(npu, launch, va);
+		/* No flush */
+		launch |= !flush << PPC_BITLSHIFT(39);
+
+		mmio_launch_invalidate(&mmio_atsd_reg[i], launch, va);
+	}
 }
 
 #define mn_to_npu_context(x) container_of(x, struct npu_context, mn)
 
-struct mmio_atsd_reg {
-	struct npu *npu;
-	int reg;
-};
-
 static void mmio_invalidate_wait(
-	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], bool flush)
+	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
 {
 	struct npu *npu;
 	int i, reg;
···
 		reg = mmio_atsd_reg[i].reg;
 		while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
 			cpu_relax();
+	}
+}
 
-		put_mmio_atsd_reg(npu, reg);
+/*
+ * Acquires all the address translation shootdown (ATSD) registers required to
+ * launch an ATSD on all links this npu_context is active on.
+ */
+static void acquire_atsd_reg(struct npu_context *npu_context,
+			struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
+{
+	int i, j;
+	struct npu *npu;
+	struct pci_dev *npdev;
+	struct pnv_phb *nphb;
 
+	for (i = 0; i <= max_npu2_index; i++) {
+		mmio_atsd_reg[i].reg = -1;
+		for (j = 0; j < NV_MAX_LINKS; j++) {
+			/*
+			 * There are no ordering requirements with respect to
+			 * the setup of struct npu_context, but to ensure
+			 * consistent behaviour we need to ensure npdev[][] is
+			 * only read once.
+			 */
+			npdev = READ_ONCE(npu_context->npdev[i][j]);
+			if (!npdev)
+				continue;
+
+			nphb = pci_bus_to_host(npdev->bus)->private_data;
+			npu = &nphb->npu;
+			mmio_atsd_reg[i].npu = npu;
+			mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu);
+			while (mmio_atsd_reg[i].reg < 0) {
+				mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu);
+				cpu_relax();
+			}
+			break;
+		}
+	}
+}
+
+/*
+ * Release previously acquired ATSD registers. To avoid deadlocks the registers
+ * must be released in the same order they were acquired above in
+ * acquire_atsd_reg.
+ */
+static void release_atsd_reg(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
+{
+	int i;
+
+	for (i = 0; i <= max_npu2_index; i++) {
 		/*
-		 * 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.
+		 * We can't rely on npu_context->npdev[][] being the same here
+		 * as when acquire_atsd_reg() was called, hence we use the
+		 * values stored in mmio_atsd_reg during the acquire phase
+		 * rather than re-reading npdev[][].
 		 */
-		if (flush)
-			mmio_invalidate_pid(npu, 0, true);
+		if (mmio_atsd_reg[i].reg < 0)
+			continue;
+
+		put_mmio_atsd_reg(mmio_atsd_reg[i].npu, mmio_atsd_reg[i].reg);
 	}
 }
 
···
 static void mmio_invalidate(struct npu_context *npu_context, int va,
 			unsigned long address, bool flush)
 {
-	int i, j;
-	struct npu *npu;
-	struct pnv_phb *nphb;
-	struct pci_dev *npdev;
 	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS];
 	unsigned long pid = npu_context->mm->context.id;
 
···
 	 * Loop over all the NPUs this process is active on and launch
 	 * an invalidate.
 	 */
-	for (i = 0; i <= max_npu2_index; i++) {
-		mmio_atsd_reg[i].reg = -1;
-		for (j = 0; j < NV_MAX_LINKS; j++) {
-			npdev = npu_context->npdev[i][j];
-			if (!npdev)
-				continue;
+	acquire_atsd_reg(npu_context, mmio_atsd_reg);
+	if (va)
+		mmio_invalidate_va(mmio_atsd_reg, address, pid, flush);
+	else
+		mmio_invalidate_pid(mmio_atsd_reg, pid, flush);
 
-			nphb = pci_bus_to_host(npdev->bus)->private_data;
-			npu = &nphb->npu;
-			mmio_atsd_reg[i].npu = npu;
-
-			if (va)
-				mmio_atsd_reg[i].reg =
-					mmio_invalidate_va(npu, address, pid,
-							flush);
-			else
-				mmio_atsd_reg[i].reg =
-					mmio_invalidate_pid(npu, pid, flush);
-
-			/*
-			 * The NPU hardware forwards the shootdown to all GPUs
-			 * so we only have to launch one shootdown per NPU.
-			 */
-			break;
-		}
+	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);
 	}
-
-	mmio_invalidate_wait(mmio_atsd_reg, flush);
-	if (flush)
-		/* Wait for the flush to complete */
-		mmio_invalidate_wait(mmio_atsd_reg, false);
+	release_atsd_reg(mmio_atsd_reg);
 }
 
 static void pnv_npu2_mn_release(struct mmu_notifier *mn,
···
 		/* No nvlink associated with this GPU device */
 		return ERR_PTR(-ENODEV);
 
+	nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
+	if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
+							&nvlink_index)))
+		return ERR_PTR(-ENODEV);
+
 	if (!mm || mm->context.id == 0) {
 		/*
 		 * Kernel thread contexts are not supported and context id 0 is
···
 	 */
 	npu_context = mm->context.npu_context;
 	if (!npu_context) {
+		rc = -ENOMEM;
 		npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL);
-		if (!npu_context)
-			return ERR_PTR(-ENOMEM);
+		if (npu_context) {
+			kref_init(&npu_context->kref);
+			npu_context->mm = mm;
+			npu_context->mn.ops = &nv_nmmu_notifier_ops;
+			rc = __mmu_notifier_register(&npu_context->mn, mm);
+		}
+
+		if (rc) {
+			kfree(npu_context);
+			opal_npu_destroy_context(nphb->opal_id, mm->context.id,
+					PCI_DEVID(gpdev->bus->number,
+						gpdev->devfn));
+			return ERR_PTR(rc);
+		}
 
 		mm->context.npu_context = npu_context;
-		npu_context->mm = mm;
-		npu_context->mn.ops = &nv_nmmu_notifier_ops;
-		__mmu_notifier_register(&npu_context->mn, mm);
-		kref_init(&npu_context->kref);
 	} else {
-		kref_get(&npu_context->kref);
+		WARN_ON(!kref_get_unless_zero(&npu_context->kref));
 	}
 
 	npu_context->release_cb = cb;
 	npu_context->priv = priv;
-	nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
-	if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
-							&nvlink_index)))
-		return ERR_PTR(-ENODEV);
-	npu_context->npdev[npu->index][nvlink_index] = npdev;
+
+	/*
+	 * npdev is a pci_dev pointer setup by the PCI code. We assign it to
+	 * npdev[][] to indicate to the mmu notifiers that an invalidation
+	 * should also be sent over this nvlink. The notifiers don't use any
+	 * other fields in npu_context, so we just need to ensure that when they
+	 * deference npu_context->npdev[][] it is either a valid pointer or
+	 * NULL.
+	 */
+	WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], npdev);
 
 	if (!nphb->npu.nmmu_flush) {
 		/*
···
 	if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
 							&nvlink_index)))
 		return;
-	npu_context->npdev[npu->index][nvlink_index] = NULL;
+	WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL);
 	opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
 				PCI_DEVID(gpdev->bus->number, gpdev->devfn));
 	kref_put(&npu_context->kref, pnv_npu2_release_context);

arch/powerpc/platforms/powernv/opal-flash.c

···
 	return rc;
 }
 
-/* Return CPUs to OPAL before starting FW update */
-static void flash_return_cpu(void *info)
-{
-	int cpu = smp_processor_id();
-
-	if (!cpu_online(cpu))
-		return;
-
-	/* Disable IRQ */
-	hard_irq_disable();
-
-	/* Return the CPU to OPAL */
-	opal_return_cpu();
-}
-
 /* This gets called just before system reboots */
-void opal_flash_term_callback(void)
+void opal_flash_update_print_message(void)
 {
-	struct cpumask mask;
-
 	if (update_flash_data.status != FLASH_IMG_READY)
 		return;
 
···
 
 	/* Small delay to help getting the above message out */
 	msleep(500);
-
-	/* Return secondary CPUs to firmware */
-	cpumask_copy(&mask, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), &mask);
-	if (!cpumask_empty(&mask))
-		smp_call_function_many(&mask,
-				       flash_return_cpu, NULL, false);
-	/* Hard disable interrupts */
-	hard_irq_disable();
 }
 
 /*
···
 	void *addr;
 	int size;
 
-	if (count < sizeof(struct image_header_t)) {
+	if (count < sizeof(image_header)) {
 		pr_warn("FLASH: Invalid candidate image\n");
 		return -EINVAL;
 	}
 
-	memcpy(&image_header, (void *)buffer, sizeof(struct image_header_t));
+	memcpy(&image_header, (void *)buffer, sizeof(image_header));
 	image_data.size = be32_to_cpu(image_header.size);
 	pr_debug("FLASH: Candidate image size = %u\n", image_data.size);
 

arch/powerpc/platforms/powernv/opal-hmi.c

···
 		pr_err("HMI: out of memory, Opal message event not handled\n");
 		return -ENOMEM;
 	}
-	memcpy(&msg_node->hmi_evt, hmi_evt, sizeof(struct OpalHMIEvent));
+	memcpy(&msg_node->hmi_evt, hmi_evt, sizeof(*hmi_evt));
 
 	spin_lock_irqsave(&opal_hmi_evt_lock, flags);
 	list_add(&msg_node->list, &opal_hmi_evt_list);

arch/powerpc/platforms/powernv/opal-imc.c

···
 	if (nr_chips <= 0)
 		return -ENODEV;
 
-	base_addr_arr = kcalloc(nr_chips, sizeof(u64), GFP_KERNEL);
+	base_addr_arr = kcalloc(nr_chips, sizeof(*base_addr_arr), GFP_KERNEL);
 	if (!base_addr_arr)
 		return -ENOMEM;
 
-	chipid_arr = kcalloc(nr_chips, sizeof(u32), GFP_KERNEL);
+	chipid_arr = kcalloc(nr_chips, sizeof(*chipid_arr), GFP_KERNEL);
 	if (!chipid_arr)
 		return -ENOMEM;
 
···
 								nr_chips))
 		goto error;
 
-	pmu_ptr->mem_info = kcalloc(nr_chips, sizeof(struct imc_mem_info),
-								GFP_KERNEL);
+	pmu_ptr->mem_info = kcalloc(nr_chips, sizeof(*pmu_ptr->mem_info),
+				    GFP_KERNEL);
 	if (!pmu_ptr->mem_info)
 		goto error;
 
···
 	u32 offset;
 
 	/* memory for pmu */
-	pmu_ptr = kzalloc(sizeof(struct imc_pmu), GFP_KERNEL);
+	pmu_ptr = kzalloc(sizeof(*pmu_ptr), GFP_KERNEL);
 	if (!pmu_ptr)
 		return -ENOMEM;
 

arch/powerpc/platforms/powernv/opal-memory-errors.c

···
 		       "handled\n");
 		return -ENOMEM;
 	}
-	memcpy(&msg_node->msg, msg, sizeof(struct opal_msg));
+	memcpy(&msg_node->msg, msg, sizeof(msg_node->msg));
 
 	spin_lock_irqsave(&opal_mem_err_lock, flags);
 	list_add(&msg_node->list, &opal_memory_err_list);

arch/powerpc/platforms/powernv/opal-nvram.c

···
 		if (rc == OPAL_BUSY_EVENT)
 			opal_poll_events(NULL);
 	}
+
+	if (rc)
+		return -EIO;
+
 	*index += count;
 	return count;
 }

arch/powerpc/platforms/powernv/opal-psr.c

···
 		return;
 	}
 
-	psr_attrs = kcalloc(of_get_child_count(psr), sizeof(struct psr_attr),
+	psr_attrs = kcalloc(of_get_child_count(psr), sizeof(*psr_attrs),
 			    GFP_KERNEL);
 	if (!psr_attrs)
 		return;

arch/powerpc/platforms/powernv/opal-sensor-groups.c

···
 		if (!nr_attrs)
 			continue;
 
-		sgs[i].sgattrs = kcalloc(nr_attrs, sizeof(struct sg_attr),
+		sgs[i].sgattrs = kcalloc(nr_attrs, sizeof(*sgs[i].sgattrs),
 					 GFP_KERNEL);
 		if (!sgs[i].sgattrs)
 			goto out_sgs_sgattrs;
 
 		sgs[i].sg.attrs = kcalloc(nr_attrs + 1,
-					  sizeof(struct attribute *),
+					  sizeof(*sgs[i].sg.attrs),
 					  GFP_KERNEL);
 
 		if (!sgs[i].sg.attrs) {

arch/powerpc/platforms/powernv/opal-wrappers.S

···
 OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
 OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
 OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
+OPAL_CALL(opal_pci_get_pbcq_tunnel_bar,		OPAL_PCI_GET_PBCQ_TUNNEL_BAR);
+OPAL_CALL(opal_pci_set_pbcq_tunnel_bar,		OPAL_PCI_SET_PBCQ_TUNNEL_BAR);

arch/powerpc/platforms/powernv/opal-xscom.c

···
 			__func__, dev);
 		return SCOM_MAP_INVALID;
 	}
-	m = kmalloc(sizeof(struct opal_scom_map), GFP_KERNEL);
+	m = kmalloc(sizeof(*m), GFP_KERNEL);
 	if (!m)
 		return NULL;
 	m->chip = be32_to_cpup(gcid);

arch/powerpc/platforms/powernv/opal.c

···
 	 *    opal to trigger checkstop explicitly for error analysis.
 	 *    The FSP PRD component would have already got notified
 	 *    about this error through other channels.
+	 * 4. We are running on a newer skiboot that by default does
+	 *    not cause a checkstop, drops us back to the kernel to
+	 *    extract context and state at the time of the error.
 	 */
 
-	ppc_md.restart(NULL);
+	panic(msg);
 }
 
 int opal_machine_check(struct pt_regs *regs)

arch/powerpc/platforms/powernv/pci-cxl.c

···
 
 #include "pci.h"
 
-struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-
-	return of_node_get(hose->dn);
-}
-EXPORT_SYMBOL(pnv_pci_get_phb_node);
-
 int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);

arch/powerpc/platforms/powernv/pci-ioda.c

···
 static long pnv_pci_ioda2_npu_set_window(struct iommu_table_group *table_group,
 		int num, struct iommu_table *tbl)
 {
+	struct pnv_ioda_pe *npe = gpe_table_group_to_npe(table_group);
+	int num2 = (num == 0) ? 1 : 0;
 	long ret = pnv_pci_ioda2_set_window(table_group, num, tbl);
 
 	if (ret)
 		return ret;
 
-	ret = pnv_npu_set_window(gpe_table_group_to_npe(table_group), num, tbl);
-	if (ret)
+	if (table_group->tables[num2])
+		pnv_npu_unset_window(npe, num2);
+
+	ret = pnv_npu_set_window(npe, num, tbl);
+	if (ret) {
 		pnv_pci_ioda2_unset_window(table_group, num);
+		if (table_group->tables[num2])
+			pnv_npu_set_window(npe, num2,
+					table_group->tables[num2]);
+	}
 
 	return ret;
 }
···
 		struct iommu_table_group *table_group,
 		int num)
 {
+	struct pnv_ioda_pe *npe = gpe_table_group_to_npe(table_group);
+	int num2 = (num == 0) ? 1 : 0;
 	long ret = pnv_pci_ioda2_unset_window(table_group, num);
 
 	if (ret)
 		return ret;
 
-	return pnv_npu_unset_window(gpe_table_group_to_npe(table_group), num);
+	if (!npe->table_group.tables[num])
+		return 0;
+
+	ret = pnv_npu_unset_window(npe, num);
+	if (ret)
+		return ret;
+
+	if (table_group->tables[num2])
+		ret = pnv_npu_set_window(npe, num2, table_group->tables[num2]);
+
+	return ret;
 }
 
 static void pnv_ioda2_npu_take_ownership(struct iommu_table_group *table_group)
···
 	phb_id = be64_to_cpup(prop64);
 	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
 
-	phb = memblock_virt_alloc(sizeof(struct pnv_phb), 0);
+	phb = memblock_virt_alloc(sizeof(*phb), 0);
 
 	/* Allocate PCI controller */
 	phb->hose = hose = pcibios_alloc_controller(np);

arch/powerpc/platforms/powernv/pci.c

···
 #include <linux/io.h>
 #include <linux/msi.h>
 #include <linux/iommu.h>
+#include <linux/sched/mm.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
···
 #include "pci.h"
 
 static DEFINE_MUTEX(p2p_mutex);
+static DEFINE_MUTEX(tunnel_mutex);
 
 int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
 {
···
 	return rc;
 }
 EXPORT_SYMBOL_GPL(pnv_pci_set_p2p);
+
+struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+	return of_node_get(hose->dn);
+}
+EXPORT_SYMBOL(pnv_pci_get_phb_node);
+
+int pnv_pci_enable_tunnel(struct pci_dev *dev, u64 *asnind)
+{
+	struct device_node *np;
+	const __be32 *prop;
+	struct pnv_ioda_pe *pe;
+	uint16_t window_id;
+	int rc;
+
+	if (!radix_enabled())
+		return -ENXIO;
+
+	if (!(np = pnv_pci_get_phb_node(dev)))
+		return -ENXIO;
+
+	prop = of_get_property(np, "ibm,phb-indications", NULL);
+	of_node_put(np);
+
+	if (!prop || !prop[1])
+		return -ENXIO;
+
+	*asnind = (u64)be32_to_cpu(prop[1]);
+	pe = pnv_ioda_get_pe(dev);
+	if (!pe)
+		return -ENODEV;
+
+	/* Increase real window size to accept as_notify messages. */
+	window_id = (pe->pe_number << 1 ) + 1;
+	rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, pe->pe_number,
+					     window_id, pe->tce_bypass_base,
+					     (uint64_t)1 << 48);
+	return opal_error_code(rc);
+}
+EXPORT_SYMBOL_GPL(pnv_pci_enable_tunnel);
+
+int pnv_pci_disable_tunnel(struct pci_dev *dev)
+{
+	struct pnv_ioda_pe *pe;
+
+	pe = pnv_ioda_get_pe(dev);
+	if (!pe)
+		return -ENODEV;
+
+	/* Restore default real window size. */
+	pnv_pci_ioda2_set_bypass(pe, true);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_disable_tunnel);
+
+int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable)
+{
+	__be64 val;
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+	u64 tunnel_bar;
+	int rc;
+
+	if (!opal_check_token(OPAL_PCI_GET_PBCQ_TUNNEL_BAR))
+		return -ENXIO;
+	if (!opal_check_token(OPAL_PCI_SET_PBCQ_TUNNEL_BAR))
+		return -ENXIO;
+
+	hose = pci_bus_to_host(dev->bus);
+	phb = hose->private_data;
+
+	mutex_lock(&tunnel_mutex);
+	rc = opal_pci_get_pbcq_tunnel_bar(phb->opal_id, &val);
+	if (rc != OPAL_SUCCESS) {
+		rc = -EIO;
+		goto out;
+	}
+	tunnel_bar = be64_to_cpu(val);
+	if (enable) {
+		/*
+		* Only one device per PHB can use atomics.
+		* Our policy is first-come, first-served.
+		*/
+		if (tunnel_bar) {
+			if (tunnel_bar != addr)
+				rc = -EBUSY;
+			else
+				rc = 0;	/* Setting same address twice is ok */
+			goto out;
+		}
+	} else {
+		/*
+		* The device that owns atomics and wants to release
+		* them must pass the same address with enable == 0.
+		*/
+		if (tunnel_bar != addr) {
+			rc = -EPERM;
+			goto out;
+		}
+		addr = 0x0ULL;
+	}
+	rc = opal_pci_set_pbcq_tunnel_bar(phb->opal_id, addr);
+	rc = opal_error_code(rc);
+out:
+	mutex_unlock(&tunnel_mutex);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_set_tunnel_bar);
+
+#ifdef CONFIG_PPC64	/* for thread.tidr */
+int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid, u32 *pid,
+			       u32 *tid)
+{
+	struct mm_struct *mm = NULL;
+
+	if (task == NULL)
+		return -EINVAL;
+
+	mm = get_task_mm(task);
+	if (mm == NULL)
+		return -EINVAL;
+
+	*pid = mm->context.id;
+	mmput(mm);
+
+	*tid = task->thread.tidr;
+	*lpid = mfspr(SPRN_LPID);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_get_as_notify_info);
+#endif
 
 void pnv_pci_shutdown(void)
 {

arch/powerpc/platforms/powernv/setup.c

···
 #include <asm/smp.h>
 #include <asm/tm.h>
 #include <asm/setup.h>
+#include <asm/security_features.h>
 
 #include "powernv.h"
+
+
+static bool fw_feature_is(const char *state, const char *name,
+			  struct device_node *fw_features)
+{
+	struct device_node *np;
+	bool rc = false;
+
+	np = of_get_child_by_name(fw_features, name);
+	if (np) {
+		rc = of_property_read_bool(np, state);
+		of_node_put(np);
+	}
+
+	return rc;
+}
+
+static void init_fw_feat_flags(struct device_node *np)
+{
+	if (fw_feature_is("enabled", "inst-spec-barrier-ori31,31,0", np))
+		security_ftr_set(SEC_FTR_SPEC_BAR_ORI31);
+
+	if (fw_feature_is("enabled", "fw-bcctrl-serialized", np))
+		security_ftr_set(SEC_FTR_BCCTRL_SERIALISED);
+
+	if (fw_feature_is("enabled", "inst-l1d-flush-ori30,30,0", np))
+		security_ftr_set(SEC_FTR_L1D_FLUSH_ORI30);
+
+	if (fw_feature_is("enabled", "inst-l1d-flush-trig2", np))
+		security_ftr_set(SEC_FTR_L1D_FLUSH_TRIG2);
+
+	if (fw_feature_is("enabled", "fw-l1d-thread-split", np))
+		security_ftr_set(SEC_FTR_L1D_THREAD_PRIV);
+
+	if (fw_feature_is("enabled", "fw-count-cache-disabled", np))
+		security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED);
+
+	/*
+	 * The features below are enabled by default, so we instead look to see
+	 * if firmware has *disabled* them, and clear them if so.
+	 */
+	if (fw_feature_is("disabled", "speculation-policy-favor-security", np))
+		security_ftr_clear(SEC_FTR_FAVOUR_SECURITY);
+
+	if (fw_feature_is("disabled", "needs-l1d-flush-msr-pr-0-to-1", np))
+		security_ftr_clear(SEC_FTR_L1D_FLUSH_PR);
+
+	if (fw_feature_is("disabled", "needs-l1d-flush-msr-hv-1-to-0", np))
+		security_ftr_clear(SEC_FTR_L1D_FLUSH_HV);
+
+	if (fw_feature_is("disabled", "needs-spec-barrier-for-bound-checks", np))
+		security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR);
+}
 
 static void pnv_setup_rfi_flush(void)
 {
 	struct device_node *np, *fw_features;
 	enum l1d_flush_type type;
-	int enable;
+	bool enable;
 
 	/* Default to fallback in case fw-features are not available */
 	type = L1D_FLUSH_FALLBACK;
-	enable = 1;
 
 	np = of_find_node_by_name(NULL, "ibm,opal");
 	fw_features = of_get_child_by_name(np, "fw-features");
 	of_node_put(np);
 
 	if (fw_features) {
-		np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2");
-		if (np && of_property_read_bool(np, "enabled"))
+		init_fw_feat_flags(fw_features);
+		of_node_put(fw_features);
+
+		if (security_ftr_enabled(SEC_FTR_L1D_FLUSH_TRIG2))
 			type = L1D_FLUSH_MTTRIG;
 
-		of_node_put(np);
-
-		np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0");
-		if (np && of_property_read_bool(np, "enabled"))
+		if (security_ftr_enabled(SEC_FTR_L1D_FLUSH_ORI30))
 			type = L1D_FLUSH_ORI;
-
-		of_node_put(np);
-
-		/* Enable unless firmware says NOT to */
-		enable = 2;
-		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0");
-		if (np && of_property_read_bool(np, "disabled"))
-			enable--;
-
-		of_node_put(np);
-
-		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1");
-		if (np && of_property_read_bool(np, "disabled"))
-			enable--;
-
-		np = of_get_child_by_name(fw_features, "speculation-policy-favor-security");
-		if (np && of_property_read_bool(np, "disabled"))
-			enable = 0;
-
-		of_node_put(np);
-		of_node_put(fw_features);
 	}
 
-	setup_rfi_flush(type, enable > 0);
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
+		 (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR)   || \
+		  security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV));
+
+	setup_rfi_flush(type, enable);
 }
 
 static void __init pnv_setup_arch(void)
···
 	 */
 	opal_event_shutdown();
 
-	/* Soft disable interrupts */
-	local_irq_disable();
+	/* Print flash update message if one is scheduled. */
+	opal_flash_update_print_message();
 
-	/*
-	 * Return secondary CPUs to firwmare if a flash update
-	 * is pending otherwise we will get all sort of error
-	 * messages about CPU being stuck etc.. This will also
-	 * have the side effect of hard disabling interrupts so
-	 * past this point, the kernel is effectively dead.
-	 */
-	opal_flash_term_callback();
+	smp_send_stop();
+
+	hard_irq_disable();
 }
 
 static void  __noreturn pnv_restart(char *cmd)
···
 			if (i != notified) {
 				printk(KERN_INFO "kexec: waiting for cpu %d "
 				       "(physical %d) to enter OPAL\n",
-				       i, paca[i].hw_cpu_id);
+				       i, paca_ptrs[i]->hw_cpu_id);
 				notified = i;
 			}
 
···
 			if (timeout-- == 0) {
 				printk(KERN_ERR "kexec: timed out waiting for "
 				       "cpu %d (physical %d) to enter OPAL\n",
-				       i, paca[i].hw_cpu_id);
+				       i, paca_ptrs[i]->hw_cpu_id);
 				break;
 			}
 		}

arch/powerpc/platforms/powernv/smp.c

···
 	 * If we already started or OPAL is not supported, we just
 	 * kick the CPU via the PACA
 	 */
-	if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPAL))
+	if (paca_ptrs[nr]->cpu_start || !firmware_has_feature(FW_FEATURE_OPAL))
 		goto kick;
 
 	/*

arch/powerpc/platforms/powernv/subcore.c

···
 		int offset = (tid / threads_per_subcore) * threads_per_subcore;
 		int mask = sibling_mask_first_cpu << offset;
 
-		paca[cpu].subcore_sibling_mask = mask;
+		paca_ptrs[cpu]->subcore_sibling_mask = mask;
 
 	}
 }

arch/powerpc/platforms/powernv/vas-debug.c

···
 
 	return;
 
-free_name:
-	kfree(window->dbgname);
-	window->dbgname = NULL;
-
 remove_dir:
 	debugfs_remove_recursive(window->dbgdir);
 	window->dbgdir = NULL;
+
+free_name:
+	kfree(window->dbgname);
+	window->dbgname = NULL;
 }
 
 void vas_instance_init_dbgdir(struct vas_instance *vinst)
 {
 	struct dentry *d;
 
+	vas_init_dbgdir();
 	if (!vas_debugfs)
 		return;
 
···
 	vinst->dbgdir = NULL;
 }
 
+/*
+ * Set up the "root" VAS debugfs dir. Return if we already set it up
+ * (or failed to) in an earlier instance of VAS.
+ */
 void vas_init_dbgdir(void)
 {
+	static bool first_time = true;
+
+	if (!first_time)
+		return;
+
+	first_time = false;
 	vas_debugfs = debugfs_create_dir("vas", NULL);
 	if (IS_ERR(vas_debugfs))
 		vas_debugfs = NULL;

arch/powerpc/platforms/powernv/vas-trace.h

···
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM	vas
+
+#if !defined(_VAS_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#define _VAS_TRACE_H
+#include <linux/tracepoint.h>
+#include <linux/sched.h>
+#include <asm/vas.h>
+
+TRACE_EVENT(	vas_rx_win_open,
+
+		TP_PROTO(struct task_struct *tsk,
+			 int vasid,
+			 int cop,
+			 struct vas_rx_win_attr *rxattr),
+
+		TP_ARGS(tsk, vasid, cop, rxattr),
+
+		TP_STRUCT__entry(
+			__field(struct task_struct *, tsk)
+			__field(int, pid)
+			__field(int, cop)
+			__field(int, vasid)
+			__field(struct vas_rx_win_attr *, rxattr)
+			__field(int, lnotify_lpid)
+			__field(int, lnotify_pid)
+			__field(int, lnotify_tid)
+		),
+
+		TP_fast_assign(
+			__entry->pid = tsk->pid;
+			__entry->vasid = vasid;
+			__entry->cop = cop;
+			__entry->lnotify_lpid = rxattr->lnotify_lpid;
+			__entry->lnotify_pid = rxattr->lnotify_pid;
+			__entry->lnotify_tid = rxattr->lnotify_tid;
+		),
+
+		TP_printk("pid=%d, vasid=%d, cop=%d, lpid=%d, pid=%d, tid=%d",
+			__entry->pid, __entry->vasid, __entry->cop,
+			__entry->lnotify_lpid, __entry->lnotify_pid,
+			__entry->lnotify_tid)
+);
+
+TRACE_EVENT(	vas_tx_win_open,
+
+		TP_PROTO(struct task_struct *tsk,
+			 int vasid,
+			 int cop,
+			 struct vas_tx_win_attr *txattr),
+
+		TP_ARGS(tsk, vasid, cop, txattr),
+
+		TP_STRUCT__entry(
+			__field(struct task_struct *, tsk)
+			__field(int, pid)
+			__field(int, cop)
+			__field(int, vasid)
+			__field(struct vas_tx_win_attr *, txattr)
+			__field(int, lpid)
+			__field(int, pidr)
+		),
+
+		TP_fast_assign(
+			__entry->pid = tsk->pid;
+			__entry->vasid = vasid;
+			__entry->cop = cop;
+			__entry->lpid = txattr->lpid;
+			__entry->pidr = txattr->pidr;
+		),
+
+		TP_printk("pid=%d, vasid=%d, cop=%d, lpid=%d, pidr=%d",
+			__entry->pid, __entry->vasid, __entry->cop,
+			__entry->lpid, __entry->pidr)
+);
+
+TRACE_EVENT(	vas_paste_crb,
+
+		TP_PROTO(struct task_struct *tsk,
+			struct vas_window *win),
+
+		TP_ARGS(tsk, win),
+
+		TP_STRUCT__entry(
+			__field(struct task_struct *, tsk)
+			__field(struct vas_window *, win)
+			__field(int, pid)
+			__field(int, vasid)
+			__field(int, winid)
+			__field(unsigned long, paste_kaddr)
+		),
+
+		TP_fast_assign(
+			__entry->pid = tsk->pid;
+			__entry->vasid = win->vinst->vas_id;
+			__entry->winid = win->winid;
+			__entry->paste_kaddr = (unsigned long)win->paste_kaddr
+		),
+
+		TP_printk("pid=%d, vasid=%d, winid=%d, paste_kaddr=0x%016lx\n",
+			__entry->pid, __entry->vasid, __entry->winid,
+			__entry->paste_kaddr)
+);
+
+#endif /* _VAS_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../arch/powerpc/platforms/powernv
+#define TRACE_INCLUDE_FILE vas-trace
+#include <trace/define_trace.h>

arch/powerpc/platforms/powernv/vas-window.c

···
 #include "vas.h"
 #include "copy-paste.h"
 
+#define CREATE_TRACE_POINTS
+#include "vas-trace.h"
+
 /*
  * Compute the paste address region for the window @window using the
  * ->paste_base_addr and ->paste_win_id_shift we got from device tree.
···
 	struct vas_winctx winctx;
 	struct vas_instance *vinst;
 
+	trace_vas_rx_win_open(current, vasid, cop, rxattr);
+
 	if (!rx_win_args_valid(cop, rxattr))
 		return ERR_PTR(-EINVAL);
 
···
 	struct vas_winctx winctx;
 	struct vas_instance *vinst;
 
+	trace_vas_tx_win_open(current, vasid, cop, attr);
+
 	if (!tx_win_args_valid(cop, attr))
 		return ERR_PTR(-EINVAL);
 
···
 	int rc;
 	void *addr;
 	uint64_t val;
+
+	trace_vas_paste_crb(current, txwin);
 
 	/*
 	 * Only NX windows are supported for now and hardware assumes

arch/powerpc/platforms/powernv/vas.c

···
 	int found = 0;
 	struct device_node *dn;
 
-	vas_init_dbgdir();
-
 	platform_driver_register(&vas_driver);
 
 	for_each_compatible_node(dn, NULL, "ibm,vas") {
···
 		found++;
 	}
 
-	if (!found)
+	if (!found) {
+		platform_driver_unregister(&vas_driver);
 		return -ENODEV;
+	}
 
 	pr_devel("Found %d instances\n", found);
 

arch/powerpc/platforms/ps3/mm.c

···
 	int result;
 	struct dma_chunk *c;
 
-	c = kzalloc(sizeof(struct dma_chunk), GFP_ATOMIC);
-
+	c = kzalloc(sizeof(*c), GFP_ATOMIC);
 	if (!c) {
 		result = -ENOMEM;
 		goto fail_alloc;
···
 
 	DBG(KERN_ERR "%s: phy=%#lx, lpar%#lx, len=%#lx\n", __func__,
 	    phys_addr, ps3_mm_phys_to_lpar(phys_addr), len);
-	c = kzalloc(sizeof(struct dma_chunk), GFP_ATOMIC);
-
+	c = kzalloc(sizeof(*c), GFP_ATOMIC);
 	if (!c) {
 		result = -ENOMEM;
 		goto fail_alloc;

arch/powerpc/platforms/pseries/hotplug-cpu.c

···
 	 * done here.  Change isolate state to Isolate and
 	 * change allocation-state to Unusable.
 	 */
-	paca[cpu].cpu_start = 0;
+	paca_ptrs[cpu]->cpu_start = 0;
 }
 
 /*

arch/powerpc/platforms/pseries/kexec.c

···
 
 void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 {
-	/* Don't risk a hypervisor call if we're crashing */
+	/*
+	 * Don't risk a hypervisor call if we're crashing
+	 * XXX: Why? The hypervisor is not crashing. It might be better
+	 * to at least attempt unregister to avoid the hypervisor stepping
+	 * on our memory.
+	 */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR) && !crash_shutdown) {
 		int ret;
 		int cpu = smp_processor_id();

arch/powerpc/platforms/pseries/lpar.c

···
 	 * reports that.  All SPLPAR support SLB shadow buffer.
 	 */
 	if (!radix_enabled() && firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		addr = __pa(paca[cpu].slb_shadow_ptr);
+		addr = __pa(paca_ptrs[cpu]->slb_shadow_ptr);
 		ret = register_slb_shadow(hwcpu, addr);
 		if (ret)
 			pr_err("WARNING: SLB shadow buffer registration for "
···
 	/*
 	 * Register dispatch trace log, if one has been allocated.
 	 */
-	pp = &paca[cpu];
+	pp = paca_ptrs[cpu];
 	dtl = pp->dispatch_log;
 	if (dtl) {
 		pp->dtl_ridx = 0;
···
 
 	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
-	pr_devel("    update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...",
-		 want_v, slot, flags, psize);
-
 	flags = (newpp & 7) | H_AVPN;
 	if (mmu_has_feature(MMU_FTR_KERNEL_RO))
 		/* Move pp0 into bit 8 (IBM 55) */
 		flags |= (newpp & HPTE_R_PP0) >> 55;
+
+	pr_devel("    update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...",
+		 want_v, slot, flags, psize);
 
 	lpar_rc = plpar_pte_protect(flags, slot, want_v);
 
···
 	return 0;
 }
 
-/* Actually only used for radix, so far */
 static int pseries_lpar_register_process_table(unsigned long base,
 			unsigned long page_size, unsigned long table_size)
 {
 	long rc;
-	unsigned long flags = PROC_TABLE_NEW;
+	unsigned long flags = 0;
 
+	if (table_size)
+		flags |= PROC_TABLE_NEW;
 	if (radix_enabled())
 		flags |= PROC_TABLE_RADIX | PROC_TABLE_GTSE;
+	else
+		flags |= PROC_TABLE_HPT_SLB;
 	for (;;) {
 		rc = plpar_hcall_norets(H_REGISTER_PROC_TBL, flags, base,
 					page_size, table_size);
···
 	mmu_hash_ops.flush_hash_range	 = pSeries_lpar_flush_hash_range;
 	mmu_hash_ops.hpte_clear_all      = pseries_hpte_clear_all;
 	mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
+	register_process_table		 = pseries_lpar_register_process_table;
 
 	if (firmware_has_feature(FW_FEATURE_HPT_RESIZE))
 		mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;

arch/powerpc/platforms/pseries/mobility.c

···
 		printk(KERN_ERR "Post-mobility device tree update "
 			"failed: %d\n", rc);
 
+	/* Possibly switch to a new RFI flush type */
+	pseries_setup_rfi_flush();
+
 	return;
 }
 

arch/powerpc/platforms/pseries/pseries.h

···
 
 #ifdef CONFIG_SMP
 extern void smp_init_pseries(void);
+
+/* Get state of physical CPU from query_cpu_stopped */
+int smp_query_cpu_stopped(unsigned int pcpu);
+#define QCSS_STOPPED 0
+#define QCSS_STOPPING 1
+#define QCSS_NOT_STOPPED 2
+#define QCSS_HARDWARE_ERROR -1
+#define QCSS_HARDWARE_BUSY -2
 #else
 static inline void smp_init_pseries(void) { };
 #endif
···
 }
 
 int dlpar_workqueue_init(void);
+
+void pseries_setup_rfi_flush(void);
 
 #endif /* _PSERIES_PSERIES_H */

arch/powerpc/platforms/pseries/setup.c

···
 #include <asm/plpar_wrappers.h>
 #include <asm/kexec.h>
 #include <asm/isa-bridge.h>
+#include <asm/security_features.h>
 
 #include "pseries.h"
 
···
 		return 0;
 
 	for_each_possible_cpu(cpu) {
-		pp = &paca[cpu];
+		pp = paca_ptrs[cpu];
 		dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
 		if (!dtl) {
 			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
···
 	of_pci_check_probe_only();
 }
 
-static void pseries_setup_rfi_flush(void)
+static void init_cpu_char_feature_flags(struct h_cpu_char_result *result)
+{
+	/*
+	 * The features below are disabled by default, so we instead look to see
+	 * if firmware has *enabled* them, and set them if so.
+	 */
+	if (result->character & H_CPU_CHAR_SPEC_BAR_ORI31)
+		security_ftr_set(SEC_FTR_SPEC_BAR_ORI31);
+
+	if (result->character & H_CPU_CHAR_BCCTRL_SERIALISED)
+		security_ftr_set(SEC_FTR_BCCTRL_SERIALISED);
+
+	if (result->character & H_CPU_CHAR_L1D_FLUSH_ORI30)
+		security_ftr_set(SEC_FTR_L1D_FLUSH_ORI30);
+
+	if (result->character & H_CPU_CHAR_L1D_FLUSH_TRIG2)
+		security_ftr_set(SEC_FTR_L1D_FLUSH_TRIG2);
+
+	if (result->character & H_CPU_CHAR_L1D_THREAD_PRIV)
+		security_ftr_set(SEC_FTR_L1D_THREAD_PRIV);
+
+	if (result->character & H_CPU_CHAR_COUNT_CACHE_DISABLED)
+		security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED);
+
+	/*
+	 * The features below are enabled by default, so we instead look to see
+	 * if firmware has *disabled* them, and clear them if so.
+	 */
+	if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY))
+		security_ftr_clear(SEC_FTR_FAVOUR_SECURITY);
+
+	if (!(result->behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
+		security_ftr_clear(SEC_FTR_L1D_FLUSH_PR);
+
+	if (!(result->behaviour & H_CPU_BEHAV_BNDS_CHK_SPEC_BAR))
+		security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR);
+}
+
+void pseries_setup_rfi_flush(void)
 {
 	struct h_cpu_char_result result;
 	enum l1d_flush_type types;
 	bool enable;
 	long rc;
 
-	/* Enable by default */
-	enable = true;
+	/*
+	 * Set features to the defaults assumed by init_cpu_char_feature_flags()
+	 * so it can set/clear again any features that might have changed after
+	 * migration, and in case the hypercall fails and it is not even called.
+	 */
+	powerpc_security_features = SEC_FTR_DEFAULT;
 
 	rc = plpar_get_cpu_characteristics(&result);
-	if (rc == H_SUCCESS) {
-		types = L1D_FLUSH_NONE;
+	if (rc == H_SUCCESS)
+		init_cpu_char_feature_flags(&result);
 
-		if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2)
-			types |= L1D_FLUSH_MTTRIG;
-		if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30)
-			types |= L1D_FLUSH_ORI;
+	/*
+	 * We're the guest so this doesn't apply to us, clear it to simplify
+	 * handling of it elsewhere.
+	 */
+	security_ftr_clear(SEC_FTR_L1D_FLUSH_HV);
 
-		/* Use fallback if nothing set in hcall */
-		if (types == L1D_FLUSH_NONE)
-			types = L1D_FLUSH_FALLBACK;
+	types = L1D_FLUSH_FALLBACK;
 
-		if ((!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) ||
-		    (!(result.behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)))
-			enable = false;
-	} else {
-		/* Default to fallback if case hcall is not available */
-		types = L1D_FLUSH_FALLBACK;
-	}
+	if (security_ftr_enabled(SEC_FTR_L1D_FLUSH_TRIG2))
+		types |= L1D_FLUSH_MTTRIG;
+
+	if (security_ftr_enabled(SEC_FTR_L1D_FLUSH_ORI30))
+		types |= L1D_FLUSH_ORI;
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR);
 
 	setup_rfi_flush(types, enable);
 }
···
 	/* PAPR says we can't set HYP */
 	dawrx &= ~DAWRX_HYP;
 
-	return  plapr_set_watchpoint0(dawr, dawrx);
+	return  plpar_set_watchpoint0(dawr, dawrx);
 }
 
 #define CMO_CHARACTERISTICS_TOKEN 44

arch/powerpc/platforms/pseries/smp.c

···
 	}
 
 	/* Fixup atomic count: it exited inside IRQ handler. */
-	task_thread_info(paca[lcpu].__current)->preempt_count	= 0;
+	task_thread_info(paca_ptrs[lcpu]->__current)->preempt_count	= 0;
 #ifdef CONFIG_HOTPLUG_CPU
 	if (get_cpu_current_state(lcpu) == CPU_STATE_INACTIVE)
 		goto out;
···
 	 * cpu_start field to become non-zero After we set cpu_start,
 	 * the processor will continue on to secondary_start
 	 */
-	paca[nr].cpu_start = 1;
+	paca_ptrs[nr]->cpu_start = 1;
 #ifdef CONFIG_HOTPLUG_CPU
 	set_preferred_offline_state(nr, CPU_STATE_ONLINE);
 
···
 		hwcpu = get_hard_smp_processor_id(cpu);
 	}
 
-	if (plapr_signal_sys_reset(hwcpu) == H_SUCCESS)
+	if (plpar_signal_sys_reset(hwcpu) == H_SUCCESS)
 		return 1;
 
 	return 0;

arch/powerpc/sysdev/mpic.c

···
 	int i;
 	u32 mask = 0;
 
-	for (i = 0; i < min(32, NR_CPUS); ++i, cpumask >>= 1)
+	for (i = 0; i < min(32, NR_CPUS) && cpu_possible(i); ++i, cpumask >>= 1)
 		mask |= (cpumask & 1) << get_hard_smp_processor_id(i);
 	return mask;
 }

arch/powerpc/sysdev/xics/icp-native.c

···
 	 * Just like the cause_ipi functions, it is required to
 	 * include a full barrier before causing the IPI.
 	 */
-	xics_phys = paca[cpu].kvm_hstate.xics_phys;
+	xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys;
 	mb();
 	__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
 }

arch/powerpc/sysdev/xive/common.c

···
 		u64 val = xive_esb_read(&xc->ipi_data, XIVE_ESB_GET);
 		xmon_printf("  IPI state: %x:%c%c\n", xc->hw_ipi,
 			val & XIVE_ESB_VAL_P ? 'P' : 'p',
-			val & XIVE_ESB_VAL_P ? 'Q' : 'q');
+			val & XIVE_ESB_VAL_Q ? 'Q' : 'q');
 	}
 #endif
 }

arch/powerpc/xmon/xmon.c

···
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
+#include <asm/plpar_wrappers.h>
 #include <asm/cputable.h>
 #include <asm/rtas.h>
 #include <asm/sstep.h>
···
 #ifdef CONFIG_PPC64
 #include <asm/hvcall.h>
 #include <asm/paca.h>
-#endif
-
-#if defined(CONFIG_PPC_SPLPAR)
-#include <asm/plpar_wrappers.h>
-#else
-static inline long plapr_set_ciabr(unsigned long ciabr) {return 0; };
 #endif
 
 #include "nonstdio.h"
···
 		mtspr(SPRN_CIABR, ciabr);
 		return;
 	}
-	plapr_set_ciabr(ciabr);
+	plpar_set_ciabr(ciabr);
 }
 
 /**
···
 	return 1;
 }
 
+/* Force enable xmon if not already enabled */
+static inline void force_enable_xmon(void)
+{
+	/* Enable xmon hooks if needed */
+	if (!xmon_on) {
+		printf("xmon: Enabling debugger hooks\n");
+		xmon_on = 1;
+	}
+}
+
 static char *breakpoint_help_string =
     "Breakpoint command usage:\n"
     "b                show breakpoints\n"
···
 	static const char badaddr[] = "Only kernel addresses are permitted for breakpoints\n";
 	int mode;
 	case 'd':	/* bd - hardware data breakpoint */
+		if (!ppc_breakpoint_available()) {
+			printf("Hardware data breakpoint not supported on this cpu\n");
+			break;
+		}
 		mode = 7;
 		cmd = inchar();
 		if (cmd == 'r')
···
 			dabr.address &= ~HW_BRK_TYPE_DABR;
 			dabr.enabled = mode | BP_DABR;
 		}
+
+		force_enable_xmon();
 		break;
 
 	case 'i':	/* bi - hardware instr breakpoint */
···
 		if (bp != NULL) {
 			bp->enabled |= BP_CIABR;
 			iabr = bp;
+			force_enable_xmon();
 		}
 		break;
 #endif
···
 		if (!check_bp_loc(a))
 			break;
 		bp = new_breakpoint(a);
-		if (bp != NULL)
+		if (bp != NULL) {
 			bp->enabled |= BP_TRAP;
+			force_enable_xmon();
+		}
 		break;
 	}
 }
···
 	catch_memory_errors = 1;
 	sync();
 
-	p = &paca[cpu];
+	p = paca_ptrs[cpu];
 
 	printf("paca for cpu 0x%x @ %px:\n", cpu, p);
 
···
 #endif /* CONFIG_MAGIC_SYSRQ */
 
 #ifdef CONFIG_DEBUG_FS
+static void clear_all_bpt(void)
+{
+	int i;
+
+	/* clear/unpatch all breakpoints */
+	remove_bpts();
+	remove_cpu_bpts();
+
+	/* Disable all breakpoints */
+	for (i = 0; i < NBPTS; ++i)
+		bpts[i].enabled = 0;
+
+	/* Clear any data or iabr breakpoints */
+	if (iabr || dabr.enabled) {
+		iabr = NULL;
+		dabr.enabled = 0;
+	}
+
+	printf("xmon: All breakpoints cleared\n");
+}
+
 static int xmon_dbgfs_set(void *data, u64 val)
 {
 	xmon_on = !!val;
 	xmon_init(xmon_on);
 
+	/* make sure all breakpoints removed when disabling */
+	if (!xmon_on)
+		clear_all_bpt();
 	return 0;
 }
 

drivers/macintosh/adb-iop.c

···
 static int adb_iop_reset_bus(void);
 
 struct adb_driver adb_iop_driver = {
-	"ISM IOP",
-	adb_iop_probe,
-	adb_iop_init,
-	adb_iop_send_request,
-	adb_iop_autopoll,
-	adb_iop_poll,
-	adb_iop_reset_bus
+	.name         = "ISM IOP",
+	.probe        = adb_iop_probe,
+	.init         = adb_iop_init,
+	.send_request = adb_iop_send_request,
+	.autopoll     = adb_iop_autopoll,
+	.poll         = adb_iop_poll,
+	.reset_bus    = adb_iop_reset_bus
 };
 
 static void adb_iop_end_req(struct adb_request *req, int state)

drivers/macintosh/ans-lcd.c

···
 
 module_init(anslcd_init);
 module_exit(anslcd_exit);
+MODULE_LICENSE("GPL v2");

drivers/macintosh/macio-adb.c

···
 static int macio_adb_reset_bus(void);
 
 struct adb_driver macio_adb_driver = {
-	"MACIO",
-	macio_probe,
-	macio_init,
-	macio_send_request,
-	/*macio_write,*/
-	macio_adb_autopoll,
-	macio_adb_poll,
-	macio_adb_reset_bus
+	.name         = "MACIO",
+	.probe        = macio_probe,
+	.init         = macio_init,
+	.send_request = macio_send_request,
+	.autopoll     = macio_adb_autopoll,
+	.poll         = macio_adb_poll,
+	.reset_bus    = macio_adb_reset_bus,
 };
 
 int macio_probe(void)

drivers/macintosh/rack-meter.c

···
 		DBDMA_DO_STOP(rm->dma_regs);
 		return;
 	}
-	memset(rdma->buf1, 0, ARRAY_SIZE(rdma->buf1));
-	memset(rdma->buf2, 0, ARRAY_SIZE(rdma->buf2));
+	memset(rdma->buf1, 0, sizeof(rdma->buf1));
+	memset(rdma->buf2, 0, sizeof(rdma->buf2));
 
 	rm->dma_buf_v->mark = 0;
 
···
 	}
 
 	/* Create and initialize our instance data */
-	rm = kzalloc(sizeof(struct rackmeter), GFP_KERNEL);
+	rm = kzalloc(sizeof(*rm), GFP_KERNEL);
 	if (rm == NULL) {
 		printk(KERN_ERR "rackmeter: failed to allocate memory !\n");
 		rc = -ENOMEM;

drivers/macintosh/via-macii.c

···
 static int macii_reset_bus(void);
 
 struct adb_driver via_macii_driver = {
-	"Mac II",
-	macii_probe,
-	macii_init,
-	macii_send_request,
-	macii_autopoll,
-	macii_poll,
-	macii_reset_bus
+	.name         = "Mac II",
+	.probe        = macii_probe,
+	.init         = macii_init,
+	.send_request = macii_send_request,
+	.autopoll     = macii_autopoll,
+	.poll         = macii_poll,
+	.reset_bus    = macii_reset_bus,
 };
 
 static enum macii_state {

drivers/macintosh/via-pmu.c

···
 static const struct file_operations pmu_options_proc_fops;
 
 #ifdef CONFIG_ADB
-struct adb_driver via_pmu_driver = {
-	"PMU",
-	pmu_probe,
-	pmu_init,
-	pmu_send_request,
-	pmu_adb_autopoll,
-	pmu_poll_adb,
-	pmu_adb_reset_bus
+const struct adb_driver via_pmu_driver = {
+	.name         = "PMU",
+	.probe        = pmu_probe,
+	.init         = pmu_init,
+	.send_request = pmu_send_request,
+	.autopoll     = pmu_adb_autopoll,
+	.poll         = pmu_poll_adb,
+	.reset_bus    = pmu_adb_reset_bus,
 };
 #endif /* CONFIG_ADB */
 

drivers/macintosh/via-pmu68k.c

···
 static void pmu_set_brightness(int level);
 
 struct adb_driver via_pmu_driver = {
-	"68K PMU",
-	pmu_probe,
-	pmu_init,
-	pmu_send_request,
-	pmu_autopoll,
-	pmu_poll,
-	pmu_reset_bus
+	.name         = "68K PMU",
+	.probe        = pmu_probe,
+	.init         = pmu_init,
+	.send_request = pmu_send_request,
+	.autopoll     = pmu_autopoll,
+	.poll         = pmu_poll,
+	.reset_bus    = pmu_reset_bus,
 };
 
 /*

drivers/misc/cxl/cxl.h

···
 #define CXL_PSL_TFC_An_AE (1ull << (63-30)) /* Restart PSL with address error */
 #define CXL_PSL_TFC_An_R  (1ull << (63-31)) /* Restart PSL transaction */
 
+/****** CXL_PSL_DEBUG *****************************************************/
+#define CXL_PSL_DEBUG_CDC  (1ull << (63-27)) /* Coherent Data cache support */
+
 /****** CXL_XSL9_IERAT_ERAT - CAIA 2 **********************************/
 #define CXL_XSL9_IERAT_MLPID    (1ull << (63-0))  /* Match LPID */
 #define CXL_XSL9_IERAT_MPID     (1ull << (63-1))  /* Match PID */
···
 	irq_hw_number_t err_hwirq;
 	unsigned int err_virq;
 	u64 ps_off;
+	bool no_data_cache; /* set if no data cache on the card */
 	const struct cxl_service_layer_ops *sl_ops;
 };
 
···
 int cxl_calc_capp_routing(struct pci_dev *dev, u64 *chipid,
 			  u32 *phb_index, u64 *capp_unit_id);
 int cxl_slot_is_switched(struct pci_dev *dev);
-int cxl_get_xsl9_dsnctl(u64 capp_unit_id, u64 *reg);
+int cxl_get_xsl9_dsnctl(struct pci_dev *dev, u64 capp_unit_id, u64 *reg);
 u64 cxl_calculate_sr(bool master, bool kernel, bool real_mode, bool p9);
 
 void cxl_native_irq_dump_regs_psl9(struct cxl_context *ctx);

drivers/misc/cxl/cxllib.c

···
 	if (rc)
 		return rc;
 
-	rc = cxl_get_xsl9_dsnctl(capp_unit_id, &cfg->dsnctl);
+	rc = cxl_get_xsl9_dsnctl(dev, capp_unit_id, &cfg->dsnctl);
 	if (rc)
 		return rc;
 	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
···
 }
 EXPORT_SYMBOL_GPL(cxllib_get_PE_attributes);
 
-int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags)
+static int get_vma_info(struct mm_struct *mm, u64 addr,
+			u64 *vma_start, u64 *vma_end,
+			unsigned long *page_size)
 {
-	int rc;
-	u64 dar;
 	struct vm_area_struct *vma = NULL;
-	unsigned long page_size;
-
-	if (mm == NULL)
-		return -EFAULT;
+	int rc = 0;
 
 	down_read(&mm->mmap_sem);
 
 	vma = find_vma(mm, addr);
 	if (!vma) {
-		pr_err("Can't find vma for addr %016llx\n", addr);
 		rc = -EFAULT;
 		goto out;
 	}
-	/* get the size of the pages allocated */
-	page_size = vma_kernel_pagesize(vma);
-
-	for (dar = (addr & ~(page_size - 1)); dar < (addr + size); dar += page_size) {
-		if (dar < vma->vm_start || dar >= vma->vm_end) {
-			vma = find_vma(mm, addr);
-			if (!vma) {
-				pr_err("Can't find vma for addr %016llx\n", addr);
-				rc = -EFAULT;
-				goto out;
-			}
-			/* get the size of the pages allocated */
-			page_size = vma_kernel_pagesize(vma);
-		}
-
-		rc = cxl_handle_mm_fault(mm, flags, dar);
-		if (rc) {
-			pr_err("cxl_handle_mm_fault failed %d", rc);
-			rc = -EFAULT;
-			goto out;
-		}
-	}
-	rc = 0;
+	*page_size = vma_kernel_pagesize(vma);
+	*vma_start = vma->vm_start;
+	*vma_end = vma->vm_end;
 out:
 	up_read(&mm->mmap_sem);
 	return rc;
+}
+
+int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags)
+{
+	int rc;
+	u64 dar, vma_start, vma_end;
+	unsigned long page_size;
+
+	if (mm == NULL)
+		return -EFAULT;
+
+	/*
+	 * The buffer we have to process can extend over several pages
+	 * and may also cover several VMAs.
+	 * We iterate over all the pages. The page size could vary
+	 * between VMAs.
+	 */
+	rc = get_vma_info(mm, addr, &vma_start, &vma_end, &page_size);
+	if (rc)
+		return rc;
+
+	for (dar = (addr & ~(page_size - 1)); dar < (addr + size);
+	     dar += page_size) {
+		if (dar < vma_start || dar >= vma_end) {
+			/*
+			 * We don't hold the mm->mmap_sem semaphore
+			 * while iterating, since the semaphore is
+			 * required by one of the lower-level page
+			 * fault processing functions and it could
+			 * create a deadlock.
+			 *
+			 * It means the VMAs can be altered between 2
+			 * loop iterations and we could theoretically
+			 * miss a page (however unlikely). But that's
+			 * not really a problem, as the driver will
+			 * retry access, get another page fault on the
+			 * missing page and call us again.
+			 */
+			rc = get_vma_info(mm, dar, &vma_start, &vma_end,
+					&page_size);
+			if (rc)
+				return rc;
+		}
+
+		rc = cxl_handle_mm_fault(mm, flags, dar);
+		if (rc)
+			return -EFAULT;
+	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(cxllib_handle_fault);

drivers/misc/cxl/native.c

···
 	u64 reg;
 	unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
 
-	pr_devel("Flushing data cache\n");
+	/*
+	 * Do a datacache flush only if datacache is available.
+	 * In case of PSL9D datacache absent hence flush operation.
+	 * would timeout.
+	 */
+	if (adapter->native->no_data_cache) {
+		pr_devel("No PSL data cache. Ignoring cache flush req.\n");
+		return 0;
+	}
 
+	pr_devel("Flushing data cache\n");
 	reg = cxl_p1_read(adapter, CXL_PSL_Control);
 	reg |= CXL_PSL_Control_Fr;
 	cxl_p1_write(adapter, CXL_PSL_Control, reg);

drivers/misc/cxl/pci.c

···
 	return 0;
 }
 
-int cxl_get_xsl9_dsnctl(u64 capp_unit_id, u64 *reg)
+static DEFINE_MUTEX(indications_mutex);
+
+static int get_phb_indications(struct pci_dev *dev, u64 *capiind, u64 *asnind,
+			       u64 *nbwind)
+{
+	static u64 nbw, asn, capi = 0;
+	struct device_node *np;
+	const __be32 *prop;
+
+	mutex_lock(&indications_mutex);
+	if (!capi) {
+		if (!(np = pnv_pci_get_phb_node(dev))) {
+			mutex_unlock(&indications_mutex);
+			return -ENODEV;
+		}
+
+		prop = of_get_property(np, "ibm,phb-indications", NULL);
+		if (!prop) {
+			nbw = 0x0300UL; /* legacy values */
+			asn = 0x0400UL;
+			capi = 0x0200UL;
+		} else {
+			nbw = (u64)be32_to_cpu(prop[2]);
+			asn = (u64)be32_to_cpu(prop[1]);
+			capi = (u64)be32_to_cpu(prop[0]);
+		}
+		of_node_put(np);
+	}
+	*capiind = capi;
+	*asnind = asn;
+	*nbwind = nbw;
+	mutex_unlock(&indications_mutex);
+	return 0;
+}
+
+int cxl_get_xsl9_dsnctl(struct pci_dev *dev, u64 capp_unit_id, u64 *reg)
 {
 	u64 xsl_dsnctl;
+	u64 capiind, asnind, nbwind;
 
 	/*
 	 * CAPI Identifier bits [0:7]
 	 * bit 61:60 MSI bits --> 0
 	 * bit 59 TVT selector --> 0
 	 */
+	if (get_phb_indications(dev, &capiind, &asnind, &nbwind))
+		return -ENODEV;
 
 	/*
 	 * Tell XSL where to route data to.
 	 * The field chipid should match the PHB CAPI_CMPM register
 	 */
-	xsl_dsnctl = ((u64)0x2 << (63-7)); /* Bit 57 */
+	xsl_dsnctl = (capiind << (63-15)); /* Bit 57 */
 	xsl_dsnctl |= (capp_unit_id << (63-15));
 
 	/* nMMU_ID Defaults to: b’000001001’*/
···
 		 * nbwind=0x03, bits [57:58], must include capi indicator.
 		 * Not supported on P9 DD1.
 		 */
-		xsl_dsnctl |= ((u64)0x03 << (63-47));
+		xsl_dsnctl |= (nbwind << (63-55));
 
 		/*
 		 * Upper 16b address bits of ASB_Notify messages sent to the
 		 * system. Need to match the PHB’s ASN Compare/Mask Register.
 		 * Not supported on P9 DD1.
 		 */
-		xsl_dsnctl |= ((u64)0x04 << (63-55));
+		xsl_dsnctl |= asnind;
 	}
 
 	*reg = xsl_dsnctl;
···
 	u64 chipid;
 	u32 phb_index;
 	u64 capp_unit_id;
+	u64 psl_debug;
 	int rc;
 
 	rc = cxl_calc_capp_routing(dev, &chipid, &phb_index, &capp_unit_id);
 	if (rc)
 		return rc;
 
-	rc = cxl_get_xsl9_dsnctl(capp_unit_id, &xsl_dsnctl);
+	rc = cxl_get_xsl9_dsnctl(dev, capp_unit_id, &xsl_dsnctl);
 	if (rc)
 		return rc;
 
···
 	if (cxl_is_power9_dd1()) {
 		/* Disabling deadlock counter CAR */
 		cxl_p1_write(adapter, CXL_PSL9_GP_CT, 0x0020000000000001ULL);
-	} else
-		cxl_p1_write(adapter, CXL_PSL9_DEBUG, 0x4000000000000000ULL);
+		/* Enable NORST */
+		cxl_p1_write(adapter, CXL_PSL9_DEBUG, 0x8000000000000000ULL);
+	} else {
+		/* Enable NORST and DD2 features */
+		cxl_p1_write(adapter, CXL_PSL9_DEBUG, 0xC000000000000000ULL);
+	}
+
+	/*
+	 * Check if PSL has data-cache. We need to flush adapter datacache
+	 * when as its about to be removed.
+	 */
+	psl_debug = cxl_p1_read(adapter, CXL_PSL9_DEBUG);
+	if (psl_debug & CXL_PSL_DEBUG_CDC) {
+		dev_dbg(&dev->dev, "No data-cache present\n");
+		adapter->native->no_data_cache = true;
+	}
 
 	return 0;
 }
···
 /* For the PSL this is a multiple for 0 < n <= 7: */
 #define PSL_2048_250MHZ_CYCLES 1
 
-static void write_timebase_ctrl_psl9(struct cxl *adapter)
-{
-	cxl_p1_write(adapter, CXL_PSL9_TB_CTLSTAT,
-		     TBSYNC_CNT(2 * PSL_2048_250MHZ_CYCLES));
-}
-
 static void write_timebase_ctrl_psl8(struct cxl *adapter)
 {
 	cxl_p1_write(adapter, CXL_PSL_TB_CTLSTAT,
···
 
 static void cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
 {
-	u64 psl_tb;
-	int delta;
-	unsigned int retry = 0;
 	struct device_node *np;
 
 	adapter->psl_timebase_synced = false;
···
 	 * Setup PSL Timebase Control and Status register
 	 * with the recommended Timebase Sync Count value
 	 */
-	adapter->native->sl_ops->write_timebase_ctrl(adapter);
+	if (adapter->native->sl_ops->write_timebase_ctrl)
+		adapter->native->sl_ops->write_timebase_ctrl(adapter);
 
 	/* Enable PSL Timebase */
 	cxl_p1_write(adapter, CXL_PSL_Control, 0x0000000000000000);
 	cxl_p1_write(adapter, CXL_PSL_Control, CXL_PSL_Control_tb);
 
-	/* Wait until CORE TB and PSL TB difference <= 16usecs */
-	do {
-		msleep(1);
-		if (retry++ > 5) {
-			dev_info(&dev->dev, "PSL timebase can't synchronize\n");
-			return;
-		}
-		psl_tb = adapter->native->sl_ops->timebase_read(adapter);
-		delta = mftb() - psl_tb;
-		if (delta < 0)
-			delta = -delta;
-	} while (tb_to_ns(delta) > 16000);
-
-	adapter->psl_timebase_synced = true;
 	return;
 }
 
···
 
 	/*
 	 * The adapter is about to be reset, so ignore errors.
-	 * Not supported on P9 DD1
 	 */
-	if ((cxl_is_power8()) || (!(cxl_is_power9_dd1())))
-		cxl_data_cache_flush(adapter);
+	cxl_data_cache_flush(adapter);
 
 	/* pcie_warm_reset requests a fundamental pci reset which includes a
 	 * PERST assert/deassert.  PERST triggers a loading of the image
···
 	.psl_irq_dump_registers = cxl_native_irq_dump_regs_psl9,
 	.err_irq_dump_registers = cxl_native_err_irq_dump_regs_psl9,
 	.debugfs_stop_trace = cxl_stop_trace_psl9,
-	.write_timebase_ctrl = write_timebase_ctrl_psl9,
 	.timebase_read = timebase_read_psl9,
 	.capi_mode = OPAL_PHB_CAPI_MODE_CAPI,
 	.needs_reset_before_disable = true,
···
 
 	/*
 	 * Flush adapter datacache as its about to be removed.
-	 * Not supported on P9 DD1.
 	 */
-	if ((cxl_is_power8()) || (!(cxl_is_power9_dd1())))
-		cxl_data_cache_flush(adapter);
+	cxl_data_cache_flush(adapter);
 
 	cxl_deconfigure_adapter(adapter);
 

drivers/misc/cxl/sysfs.c

···
 					char *buf)
 {
 	struct cxl *adapter = to_cxl_adapter(device);
+	u64 psl_tb, delta;
 
+	/* Recompute the status only in native mode */
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		psl_tb = adapter->native->sl_ops->timebase_read(adapter);
+		delta = abs(mftb() - psl_tb);
+
+		/* CORE TB and PSL TB difference <= 16usecs ? */
+		adapter->psl_timebase_synced = (tb_to_ns(delta) < 16000) ? true : false;
+		pr_devel("PSL timebase %s - delta: 0x%016llx\n",
+			 (tb_to_ns(delta) < 16000) ? "synchronized" :
+			 "not synchronized", tb_to_ns(delta));
+	}
 	return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_timebase_synced);
 }
 

drivers/pci/hotplug/pnv_php.c

···
 		return;
 
 	php_slot->state = PNV_PHP_STATE_OFFLINE;
-	pnv_php_put_slot(php_slot);
 	pci_hp_deregister(&php_slot->slot);
+	pnv_php_put_slot(php_slot);
 }
 
 static void pnv_php_unregister(struct device_node *dn)

include/linux/memblock.h

···
 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 					phys_addr_t start, phys_addr_t end,
 					ulong flags);
+phys_addr_t memblock_alloc_base_nid(phys_addr_t size,
+					phys_addr_t align, phys_addr_t max_addr,
+					int nid, ulong flags);
 phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
 				phys_addr_t max_addr);
 phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,

include/linux/raid/pq.h

···
 extern const struct raid6_calls raid6_avx512x2;
 extern const struct raid6_calls raid6_avx512x4;
 extern const struct raid6_calls raid6_s390vx8;
+extern const struct raid6_calls raid6_vpermxor1;
+extern const struct raid6_calls raid6_vpermxor2;
+extern const struct raid6_calls raid6_vpermxor4;
+extern const struct raid6_calls raid6_vpermxor8;
 
 struct raid6_recov_calls {
 	void (*data2)(int, size_t, int, int, void **);

lib/raid6/.gitignore

···
 tables.c
 neon?.c
 s390vx?.c
+vpermxor*.c

lib/raid6/Makefile

···
 		   int8.o int16.o int32.o
 
 raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o avx512.o recov_avx512.o
-raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
+raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o \
+                              vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
 raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
 raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
 
···
 targets += altivec8.c
 $(obj)/altivec8.c:   UNROLL := 8
 $(obj)/altivec8.c:   $(src)/altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_vpermxor1.o += $(altivec_flags)
+targets += vpermxor1.c
+$(obj)/vpermxor1.c: UNROLL := 1
+$(obj)/vpermxor1.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_vpermxor2.o += $(altivec_flags)
+targets += vpermxor2.c
+$(obj)/vpermxor2.c: UNROLL := 2
+$(obj)/vpermxor2.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_vpermxor4.o += $(altivec_flags)
+targets += vpermxor4.c
+$(obj)/vpermxor4.c: UNROLL := 4
+$(obj)/vpermxor4.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_vpermxor8.o += $(altivec_flags)
+targets += vpermxor8.c
+$(obj)/vpermxor8.c: UNROLL := 8
+$(obj)/vpermxor8.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
 
 CFLAGS_neon1.o += $(NEON_FLAGS)

lib/raid6/algos.c

···
 	&raid6_altivec2,
 	&raid6_altivec4,
 	&raid6_altivec8,
+	&raid6_vpermxor1,
+	&raid6_vpermxor2,
+	&raid6_vpermxor4,
+	&raid6_vpermxor8,
 #endif
 #if defined(CONFIG_S390)
 	&raid6_s390vx8,

lib/raid6/altivec.uc

···
 
 #include <linux/raid/pq.h>
 
+#ifdef CONFIG_ALTIVEC
+
 #include <altivec.h>
 #ifdef __KERNEL__
 # include <asm/cputable.h>
 # include <asm/switch_to.h>
+#endif /* __KERNEL__ */
 
 /*
  * This is the C data type to use.  We use a vector of

lib/raid6/test/Makefile

···
         CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1
 else
         HAS_ALTIVEC := $(shell printf '\#include <altivec.h>\nvector int a;\n' |\
-                         gcc -c -x c - >&/dev/null && \
-                         rm ./-.o && echo yes)
+                         gcc -c -x c - >/dev/null && rm ./-.o && echo yes)
         ifeq ($(HAS_ALTIVEC),yes)
-                OBJS += altivec1.o altivec2.o altivec4.o altivec8.o
+                CFLAGS += -I../../../arch/powerpc/include
+                CFLAGS += -DCONFIG_ALTIVEC
+                OBJS += altivec1.o altivec2.o altivec4.o altivec8.o \
+                        vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
         endif
 endif
 
···
 altivec8.c: altivec.uc ../unroll.awk
 	$(AWK) ../unroll.awk -vN=8 < altivec.uc > $@
 
+vpermxor1.c: vpermxor.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=1 < vpermxor.uc > $@
+
+vpermxor2.c: vpermxor.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=2 < vpermxor.uc > $@
+
+vpermxor4.c: vpermxor.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=4 < vpermxor.uc > $@
+
+vpermxor8.c: vpermxor.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=8 < vpermxor.uc > $@
+
 int1.c: int.uc ../unroll.awk
 	$(AWK) ../unroll.awk -vN=1 < int.uc > $@
 
···
 	./mktables > tables.c
 
 clean:
-	rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test
+	rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c vpermxor*.c neon*.c tables.c raid6test
 
 spotless: clean
 	rm -f *~

lib/raid6/vpermxor.uc

···
+/*
+ * Copyright 2017, Matt Brown, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * vpermxor$#.c
+ *
+ * Based on H. Peter Anvin's paper - The mathematics of RAID-6
+ *
+ * $#-way unrolled portable integer math RAID-6 instruction set
+ * This file is postprocessed using unroll.awk
+ *
+ * vpermxor$#.c makes use of the vpermxor instruction to optimise the RAID6 Q
+ * syndrome calculations.
+ * This can be run on systems which have both Altivec and vpermxor instruction.
+ *
+ * This instruction was introduced in POWER8 - ISA v2.07.
+ */
+
+#include <linux/raid/pq.h>
+#ifdef CONFIG_ALTIVEC
+
+#include <altivec.h>
+#ifdef __KERNEL__
+#include <asm/cputable.h>
+#include <asm/ppc-opcode.h>
+#include <asm/switch_to.h>
+#endif
+
+typedef vector unsigned char unative_t;
+#define NSIZE sizeof(unative_t)
+
+static const vector unsigned char gf_low = {0x1e, 0x1c, 0x1a, 0x18, 0x16, 0x14,
+					    0x12, 0x10, 0x0e, 0x0c, 0x0a, 0x08,
+					    0x06, 0x04, 0x02,0x00};
+static const vector unsigned char gf_high = {0xfd, 0xdd, 0xbd, 0x9d, 0x7d, 0x5d,
+					     0x3d, 0x1d, 0xe0, 0xc0, 0xa0, 0x80,
+					     0x60, 0x40, 0x20, 0x00};
+
+static void noinline raid6_vpermxor$#_gen_syndrome_real(int disks, size_t bytes,
+							void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+	unative_t wp$$, wq$$, wd$$;
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	for (d = 0; d < bytes; d += NSIZE*$#) {
+		wp$$ = wq$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE];
+
+		for (z = z0-1; z>=0; z--) {
+			wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE];
+			/* P syndrome */
+			wp$$ = vec_xor(wp$$, wd$$);
+
+			/* Q syndrome */
+			asm(VPERMXOR(%0,%1,%2,%3):"=v"(wq$$):"v"(gf_high), "v"(gf_low), "v"(wq$$));
+			wq$$ = vec_xor(wq$$, wd$$);
+		}
+		*(unative_t *)&p[d+NSIZE*$$] = wp$$;
+		*(unative_t *)&q[d+NSIZE*$$] = wq$$;
+	}
+}
+
+static void raid6_vpermxor$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+
+	raid6_vpermxor$#_gen_syndrome_real(disks, bytes, ptrs);
+
+	disable_kernel_altivec();
+	preempt_enable();
+}
+
+int raid6_have_altivec_vpermxor(void);
+#if $# == 1
+int raid6_have_altivec_vpermxor(void)
+{
+	/* Check if arch has both altivec and the vpermxor instructions */
+# ifdef __KERNEL__
+	return (cpu_has_feature(CPU_FTR_ALTIVEC_COMP) &&
+		cpu_has_feature(CPU_FTR_ARCH_207S));
+# else
+	return 1;
+#endif
+
+}
+#endif
+
+const struct raid6_calls raid6_vpermxor$# = {
+	raid6_vpermxor$#_gen_syndrome,
+	NULL,
+	raid6_have_altivec_vpermxor,
+	"vpermxor$#",
+	0
+};
+#endif

mm/memblock.c

···
 					flags);
 }
 
-static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
+phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t max_addr,
 					int nid, ulong flags)
 {

tools/testing/selftests/powerpc/benchmarks/.gitignore

···
 gettimeofday
 context_switch
+fork
+exec_target
 mmap_bench
 futex_bench
 null_syscall

tools/testing/selftests/powerpc/benchmarks/Makefile

···
 # SPDX-License-Identifier: GPL-2.0
-TEST_GEN_PROGS := gettimeofday context_switch mmap_bench futex_bench null_syscall
+TEST_GEN_PROGS := gettimeofday context_switch fork mmap_bench futex_bench null_syscall
+TEST_GEN_FILES := exec_target
 
 CFLAGS += -O2
 
···
 $(OUTPUT)/context_switch: ../utils.c
 $(OUTPUT)/context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec
 $(OUTPUT)/context_switch: LDLIBS += -lpthread
+
+$(OUTPUT)/fork: LDLIBS += -lpthread
+
+$(OUTPUT)/exec_target: CFLAGS += -static -nostartfiles

tools/testing/selftests/powerpc/benchmarks/exec_target.c

···
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Part of fork context switch microbenchmark.
+ *
+ * Copyright 2018, Anton Blanchard, IBM Corp.
+ */
+
+void _exit(int);
+void _start(void)
+{
+	_exit(0);
+}

tools/testing/selftests/powerpc/benchmarks/fork.c

···
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Context switch microbenchmark.
+ *
+ * Copyright 2018, Anton Blanchard, IBM Corp.
+ */
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <errno.h>
+#include <getopt.h>
+#include <limits.h>
+#include <linux/futex.h>
+#include <pthread.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/shm.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+static unsigned int timeout = 30;
+
+static void set_cpu(int cpu)
+{
+	cpu_set_t cpuset;
+
+	if (cpu == -1)
+		return;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset)) {
+		perror("sched_setaffinity");
+		exit(1);
+	}
+}
+
+static void start_process_on(void *(*fn)(void *), void *arg, int cpu)
+{
+	int pid;
+
+	pid = fork();
+	if (pid == -1) {
+		perror("fork");
+		exit(1);
+	}
+
+	if (pid)
+		return;
+
+	set_cpu(cpu);
+
+	fn(arg);
+
+	exit(0);
+}
+
+static int cpu;
+static int do_fork = 0;
+static int do_vfork = 0;
+static int do_exec = 0;
+static char *exec_file;
+static int exec_target = 0;
+static unsigned long iterations;
+static unsigned long iterations_prev;
+
+static void run_exec(void)
+{
+	char *const argv[] = { "./exec_target", NULL };
+
+	if (execve("./exec_target", argv, NULL) == -1) {
+		perror("execve");
+		exit(1);
+	}
+}
+
+static void bench_fork(void)
+{
+	while (1) {
+		pid_t pid = fork();
+		if (pid == -1) {
+			perror("fork");
+			exit(1);
+		}
+		if (pid == 0) {
+			if (do_exec)
+				run_exec();
+			_exit(0);
+		}
+		pid = waitpid(pid, NULL, 0);
+		if (pid == -1) {
+			perror("waitpid");
+			exit(1);
+		}
+		iterations++;
+	}
+}
+
+static void bench_vfork(void)
+{
+	while (1) {
+		pid_t pid = vfork();
+		if (pid == -1) {
+			perror("fork");
+			exit(1);
+		}
+		if (pid == 0) {
+			if (do_exec)
+				run_exec();
+			_exit(0);
+		}
+		pid = waitpid(pid, NULL, 0);
+		if (pid == -1) {
+			perror("waitpid");
+			exit(1);
+		}
+		iterations++;
+	}
+}
+
+static void *null_fn(void *arg)
+{
+	pthread_exit(NULL);
+}
+
+static void bench_thread(void)
+{
+	pthread_t tid;
+	cpu_set_t cpuset;
+	pthread_attr_t attr;
+	int rc;
+
+	rc = pthread_attr_init(&attr);
+	if (rc) {
+		errno = rc;
+		perror("pthread_attr_init");
+		exit(1);
+	}
+
+	if (cpu != -1) {
+		CPU_ZERO(&cpuset);
+		CPU_SET(cpu, &cpuset);
+
+		rc = pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+		if (rc) {
+			errno = rc;
+			perror("pthread_attr_setaffinity_np");
+			exit(1);
+		}
+	}
+
+	while (1) {
+		rc = pthread_create(&tid, &attr, null_fn, NULL);
+		if (rc) {
+			errno = rc;
+			perror("pthread_create");
+			exit(1);
+		}
+		rc = pthread_join(tid, NULL);
+		if (rc) {
+			errno = rc;
+			perror("pthread_join");
+			exit(1);
+		}
+		iterations++;
+	}
+}
+
+static void sigalrm_handler(int junk)
+{
+	unsigned long i = iterations;
+
+	printf("%ld\n", i - iterations_prev);
+	iterations_prev = i;
+
+	if (--timeout == 0)
+		kill(0, SIGUSR1);
+
+	alarm(1);
+}
+
+static void sigusr1_handler(int junk)
+{
+	exit(0);
+}
+
+static void *bench_proc(void *arg)
+{
+	signal(SIGALRM, sigalrm_handler);
+	alarm(1);
+
+	if (do_fork)
+		bench_fork();
+	else if (do_vfork)
+		bench_vfork();
+	else
+		bench_thread();
+
+	return NULL;
+}
+
+static struct option options[] = {
+	{ "fork", no_argument, &do_fork, 1 },
+	{ "vfork", no_argument, &do_vfork, 1 },
+	{ "exec", no_argument, &do_exec, 1 },
+	{ "timeout", required_argument, 0, 's' },
+	{ "exec-target", no_argument, &exec_target, 1 },
+	{ NULL },
+};
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: fork <options> CPU\n\n");
+	fprintf(stderr, "\t\t--fork\tUse fork() (default threads)\n");
+	fprintf(stderr, "\t\t--vfork\tUse vfork() (default threads)\n");
+	fprintf(stderr, "\t\t--exec\tAlso exec() (default no exec)\n");
+	fprintf(stderr, "\t\t--timeout=X\tDuration in seconds to run (default 30)\n");
+	fprintf(stderr, "\t\t--exec-target\tInternal option for exec workload\n");
+}
+
+int main(int argc, char *argv[])
+{
+	signed char c;
+
+	while (1) {
+		int option_index = 0;
+
+		c = getopt_long(argc, argv, "", options, &option_index);
+
+		if (c == -1)
+			break;
+
+		switch (c) {
+		case 0:
+			if (options[option_index].flag != 0)
+				break;
+
+			usage();
+			exit(1);
+			break;
+
+		case 's':
+			timeout = atoi(optarg);
+			break;
+
+		default:
+			usage();
+			exit(1);
+		}
+	}
+
+	if (do_fork && do_vfork) {
+		usage();
+		exit(1);
+	}
+	if (do_exec && !do_fork && !do_vfork) {
+		usage();
+		exit(1);
+	}
+
+	if (do_exec) {
+		char *dirname = strdup(argv[0]);
+		int i;
+		i = strlen(dirname) - 1;
+		while (i) {
+			if (dirname[i] == '/') {
+				dirname[i] = '\0';
+				if (chdir(dirname) == -1) {
+					perror("chdir");
+					exit(1);
+				}
+				break;
+			}
+			i--;
+		}
+	}
+
+	if (exec_target) {
+		exit(0);
+	}
+
+	if (((argc - optind) != 1)) {
+		cpu = -1;
+	} else {
+		cpu = atoi(argv[optind++]);
+	}
+
+	if (do_exec)
+		exec_file = argv[0];
+
+	set_cpu(cpu);
+
+	printf("Using ");
+	if (do_fork)
+		printf("fork");
+	else if (do_vfork)
+		printf("vfork");
+	else
+		printf("clone");
+
+	if (do_exec)
+		printf(" + exec");
+
+	printf(" on cpu %d\n", cpu);
+
+	/* Create a new process group so we can signal everyone for exit */
+	setpgid(getpid(), getpid());
+
+	signal(SIGUSR1, sigusr1_handler);
+
+	start_process_on(bench_proc, NULL, cpu);
+
+	while (1)
+		sleep(3600);
+
+	return 0;
+}

tools/testing/selftests/powerpc/copyloops/Makefile

···
 CFLAGS += -D SELFTEST
 CFLAGS += -maltivec
 
-# Use our CFLAGS for the implicit .S rule
-ASFLAGS = $(CFLAGS)
+# Use our CFLAGS for the implicit .S rule & set the asm machine type
+ASFLAGS = $(CFLAGS) -Wa,-mpower4
 
 TEST_GEN_PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7
 EXTRA_SOURCES := validate.c ../harness.c

tools/testing/selftests/powerpc/tm/Makefile

···
 
 TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
 	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable tm-trap \
-	$(SIGNAL_CONTEXT_CHK_TESTS)
+	$(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn
 
 include ../../lib.mk
 

tools/testing/selftests/powerpc/tm/tm-sigreturn.c

···
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2015, Laurent Dufour, IBM Corp.
+ *
+ * Test the kernel's signal returning code to check reclaim is done if the
+ * sigreturn() is called while in a transaction (suspended since active is
+ * already dropped trough the system call path).
+ *
+ * The kernel must discard the transaction when entering sigreturn, since
+ * restoring the potential TM SPRS from the signal frame is requiring to not be
+ * in a transaction.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "tm.h"
+#include "utils.h"
+
+
+void handler(int sig)
+{
+	uint64_t ret;
+
+	asm __volatile__(
+		"li             3,1             ;"
+		"tbegin.                        ;"
+		"beq            1f              ;"
+		"li             3,0             ;"
+		"tsuspend.                      ;"
+		"1:                             ;"
+		"std%X[ret]     3, %[ret]       ;"
+		: [ret] "=m"(ret)
+		:
+		: "memory", "3", "cr0");
+
+	if (ret)
+		exit(1);
+
+	/*
+	 * We return from the signal handle while in a suspended transaction
+	 */
+}
+
+
+int tm_sigreturn(void)
+{
+	struct sigaction sa;
+	uint64_t ret = 0;
+
+	SKIP_IF(!have_htm());
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = handler;
+	sigemptyset(&sa.sa_mask);
+
+	if (sigaction(SIGSEGV, &sa, NULL))
+		exit(1);
+
+	asm __volatile__(
+		"tbegin.                        ;"
+		"beq            1f              ;"
+		"li             3,0             ;"
+		"std            3,0(3)          ;" /* trigger SEGV */
+		"li             3,1             ;"
+		"std%X[ret]     3,%[ret]        ;"
+		"tend.                          ;"
+		"b              2f              ;"
+		"1:                             ;"
+		"li             3,2             ;"
+		"std%X[ret]     3,%[ret]        ;"
+		"2:                             ;"
+		: [ret] "=m"(ret)
+		:
+		: "memory", "3", "cr0");
+
+	if (ret != 2)
+		exit(1);
+
+	exit(0);
+}
+
+int main(void)
+{
+	return test_harness(tm_sigreturn, "tm_sigreturn");
+}

tools/testing/selftests/powerpc/tm/tm-unavailable.c

···
 	return ((condition_reg >> 28) & 0xa) == 0xa;
 }
 
-void *ping(void *input)
+void *tm_una_ping(void *input)
 {
 
 	/*
···
 }
 
 /* Thread to force context switch */
-void *pong(void *not_used)
+void *tm_una_pong(void *not_used)
 {
 	/* Wait thread get its name "pong". */
 	if (DEBUG)
···
 	do {
 		int rc;
 
-		/* Bind 'ping' to CPU 0, as specified in 'attr'. */
-		rc = pthread_create(&t0, attr, ping, (void *) &flags);
+		/* Bind to CPU 0, as specified in 'attr'. */
+		rc = pthread_create(&t0, attr, tm_una_ping, (void *) &flags);
 		if (rc)
 			pr_err(rc, "pthread_create()");
-		rc = pthread_setname_np(t0, "ping");
+		rc = pthread_setname_np(t0, "tm_una_ping");
 		if (rc)
 			pr_warn(rc, "pthread_setname_np");
 		rc = pthread_join(t0, &ret_value);
···
 	}
 }
 
-int main(int argc, char **argv)
+int tm_unavailable_test(void)
 {
 	int rc, exception; /* FP = 0, VEC = 1, VSX = 2 */
 	pthread_t t1;
 	pthread_attr_t attr;
 	cpu_set_t cpuset;
+
+	SKIP_IF(!have_htm());
 
 	/* Set only CPU 0 in the mask. Both threads will be bound to CPU 0. */
 	CPU_ZERO(&cpuset);
···
 	if (rc)
 		pr_err(rc, "pthread_attr_setaffinity_np()");
 
-	rc = pthread_create(&t1, &attr /* Bind 'pong' to CPU 0 */, pong, NULL);
+	rc = pthread_create(&t1, &attr /* Bind to CPU 0 */, tm_una_pong, NULL);
 	if (rc)
 		pr_err(rc, "pthread_create()");
 
 	/* Name it for systemtap convenience */
-	rc = pthread_setname_np(t1, "pong");
+	rc = pthread_setname_np(t1, "tm_una_pong");
 	if (rc)
 		pr_warn(rc, "pthread_create()");
 
···
 		printf("result: success\n");
 		exit(0);
 	}
+}
+
+int main(int argc, char **argv)
+{
+	test_harness_set_timeout(220);
+	return test_harness(tm_unavailable_test, "tm_unavailable_test");
 }