diff options
Diffstat (limited to 'arch/powerpc')
42 files changed, 1227 insertions, 768 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 5ead6a31854b..9faa18c4f3f7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -108,7 +108,6 @@ config PPC select HAVE_ARCH_TRACEHOOK select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG select HAVE_OPROFILE select HAVE_DEBUG_KMEMLEAK @@ -158,6 +157,7 @@ config PPC select ARCH_HAS_DMA_SET_COHERENT_MASK select ARCH_HAS_DEVMEM_IS_ALLOWED select HAVE_ARCH_SECCOMP_FILTER + select ARCH_HAS_UBSAN_SANITIZE_ALL config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig new file mode 100644 index 000000000000..045031048f8d --- /dev/null +++ b/arch/powerpc/configs/powernv_defconfig @@ -0,0 +1,313 @@ +CONFIG_PPC64=y +CONFIG_SMP=y +CONFIG_NR_CPUS=2048 +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_FHANDLE=y +CONFIG_AUDIT=y +CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NUMA_BALANCING=y +CONFIG_CGROUPS=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_USER_NS=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_COMPAT_BRK is not set +CONFIG_PROFILING=y +CONFIG_OPROFILE=y +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_OPAL_PRD=y +# CONFIG_PPC_PSERIES is not set +# CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set +CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y +CONFIG_CPU_IDLE=y +CONFIG_HZ_100=y +CONFIG_BINFMT_MISC=m +CONFIG_PPC_TRANSACTIONAL_MEM=y +CONFIG_HOTPLUG_CPU=y +CONFIG_KEXEC=y +CONFIG_IRQ_ALL_CPUS=y +CONFIG_NUMA=y +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_PPC_64K_PAGES=y +CONFIG_PPC_SUBPAGE_PROT=y +CONFIG_SCHED_SMT=y +CONFIG_PM=y +CONFIG_PCI_MSI=y +CONFIG_HOTPLUG_PCI=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=m +CONFIG_NET_KEY=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_NET_IPIP=y +CONFIG_SYN_COOKIES=y +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +# CONFIG_IPV6 is not set +CONFIG_NETFILTER=y +# CONFIG_NETFILTER_ADVANCED is not set +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_MTD=y +CONFIG_MTD_POWERNV_FLASH=y +CONFIG_PARPORT=m +CONFIG_PARPORT_PC=m +CONFIG_BLK_DEV_FD=m +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=65536 +CONFIG_VIRTIO_BLK=m +CONFIG_IDE=y +CONFIG_BLK_DEV_IDECD=y +CONFIG_BLK_DEV_GENERIC=y +CONFIG_BLK_DEV_AMD74XX=y +CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_ST=y +CONFIG_BLK_DEV_SR=y +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_FC_ATTRS=y +CONFIG_SCSI_SRP_ATTRS=y +CONFIG_SCSI_CXGB3_ISCSI=m +CONFIG_SCSI_CXGB4_ISCSI=m +CONFIG_SCSI_BNX2_ISCSI=m +CONFIG_BE2ISCSI=m +CONFIG_SCSI_MPT2SAS=m +CONFIG_SCSI_SYM53C8XX_2=y +CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 +CONFIG_SCSI_IPR=y +CONFIG_SCSI_QLA_FC=m +CONFIG_SCSI_QLA_ISCSI=m +CONFIG_SCSI_LPFC=m +CONFIG_SCSI_VIRTIO=m +CONFIG_SCSI_DH=y +CONFIG_SCSI_DH_RDAC=m +CONFIG_SCSI_DH_ALUA=m +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +# CONFIG_ATA_SFF is not set +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_MD_LINEAR=y +CONFIG_MD_RAID0=y +CONFIG_MD_RAID1=y +CONFIG_MD_RAID10=m +CONFIG_MD_RAID456=m +CONFIG_MD_MULTIPATH=m +CONFIG_MD_FAULTY=m +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_MIRROR=m +CONFIG_DM_ZERO=m +CONFIG_DM_MULTIPATH=m +CONFIG_DM_MULTIPATH_QL=m +CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_UEVENT=y +CONFIG_BONDING=m +CONFIG_DUMMY=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_VXLAN=m +CONFIG_NETCONSOLE=y +CONFIG_TUN=m +CONFIG_VETH=m +CONFIG_VIRTIO_NET=m +CONFIG_VHOST_NET=m +CONFIG_VORTEX=y +CONFIG_ACENIC=m +CONFIG_ACENIC_OMIT_TIGON_I=y +CONFIG_PCNET32=y +CONFIG_TIGON3=y +CONFIG_BNX2X=m +CONFIG_CHELSIO_T1=m +CONFIG_BE2NET=m +CONFIG_S2IO=m +CONFIG_E100=y +CONFIG_E1000=y +CONFIG_E1000E=y +CONFIG_IXGB=m +CONFIG_IXGBE=m +CONFIG_MLX4_EN=m +CONFIG_MYRI10GE=m +CONFIG_QLGE=m +CONFIG_NETXEN_NIC=m +CONFIG_PPP=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPPOE=m +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +CONFIG_INPUT_EVDEV=m +CONFIG_INPUT_MISC=y +# CONFIG_SERIO_SERPORT is not set +CONFIG_DEVPTS_MULTIPLE_INSTANCES=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_JSM=m +CONFIG_VIRTIO_CONSOLE=m +CONFIG_IPMI_HANDLER=y +CONFIG_IPMI_DEVICE_INTERFACE=y +CONFIG_IPMI_POWERNV=y +CONFIG_RAW_DRIVER=y +CONFIG_MAX_RAW_DEVS=1024 +CONFIG_DRM=y +CONFIG_DRM_AST=y +CONFIG_FIRMWARE_EDID=y +CONFIG_FB_OF=y +CONFIG_FB_MATROX=y +CONFIG_FB_MATROX_MILLENIUM=y +CONFIG_FB_MATROX_MYSTIQUE=y +CONFIG_FB_MATROX_G=y +CONFIG_FB_RADEON=y +CONFIG_FB_IBM_GXT4500=y +CONFIG_LCD_PLATFORM=m +# CONFIG_VGA_CONSOLE is not set +CONFIG_LOGO=y +CONFIG_HID_GYRATION=y +CONFIG_HID_PANTHERLORD=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SUNPLUS=y +CONFIG_USB_HIDDEV=y +CONFIG_USB=y +CONFIG_USB_MON=m +CONFIG_USB_EHCI_HCD=y +# CONFIG_USB_EHCI_HCD_PPC_OF is not set +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_STORAGE=m +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=m +CONFIG_LEDS_POWERNV=m +CONFIG_INFINIBAND=m +CONFIG_INFINIBAND_USER_MAD=m +CONFIG_INFINIBAND_USER_ACCESS=m +CONFIG_INFINIBAND_MTHCA=m +CONFIG_INFINIBAND_CXGB3=m +CONFIG_INFINIBAND_CXGB4=m +CONFIG_MLX4_INFINIBAND=m +CONFIG_INFINIBAND_IPOIB=m +CONFIG_INFINIBAND_IPOIB_CM=y +CONFIG_INFINIBAND_SRP=m +CONFIG_INFINIBAND_ISER=m +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GENERIC=y +CONFIG_VIRTIO_PCI=m +CONFIG_VIRTIO_BALLOON=m +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +CONFIG_REISERFS_FS=y +CONFIG_REISERFS_FS_XATTR=y +CONFIG_REISERFS_FS_POSIX_ACL=y +CONFIG_REISERFS_FS_SECURITY=y +CONFIG_JFS_FS=m +CONFIG_JFS_POSIX_ACL=y +CONFIG_JFS_SECURITY=y +CONFIG_XFS_FS=m +CONFIG_XFS_POSIX_ACL=y +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_NILFS2_FS=m +CONFIG_AUTOFS4_FS=m +CONFIG_FUSE_FS=m +CONFIG_OVERLAY_FS=m +CONFIG_ISO9660_FS=y +CONFIG_UDF_FS=m +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +CONFIG_CRAMFS=m +CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y +CONFIG_PSTORE=y +CONFIG_NFS_FS=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_NFSD=m +CONFIG_NFSD_V3_ACL=y +CONFIG_NFSD_V4=y +CONFIG_CIFS=m +CONFIG_CIFS_XATTR=y +CONFIG_CIFS_POSIX=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_UTF8=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_STACKOVERFLOW=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_LATENCYTOP=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_CODE_PATCHING_SELFTEST=y +CONFIG_FTR_FIXUP_SELFTEST=y +CONFIG_MSI_BITMAP_SELFTEST=y +CONFIG_XMON=y +CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_CCM=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_LZO=m +CONFIG_CRYPTO_DEV_NX=y +CONFIG_VIRTUALIZATION=y +CONFIG_KVM_BOOK3S_64=m +CONFIG_KVM_BOOK3S_64_HV=m diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 55f106ed12bf..ae0751ef8788 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -12,6 +12,24 @@ #define ATOMIC_INIT(i) { (i) } +/* + * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with + * a "bne-" instruction at the end, so an isync is enough as a acquire barrier + * on the platform without lwsync. + */ +#define __atomic_op_acquire(op, args...) \ +({ \ + typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ + __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory"); \ + __ret; \ +}) + +#define __atomic_op_release(op, args...) \ +({ \ + __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory"); \ + op##_relaxed(args); \ +}) + static __inline__ int atomic_read(const atomic_t *v) { int t; @@ -42,27 +60,27 @@ static __inline__ void atomic_##op(int a, atomic_t *v) \ : "cc"); \ } \ -#define ATOMIC_OP_RETURN(op, asm_op) \ -static __inline__ int atomic_##op##_return(int a, atomic_t *v) \ +#define ATOMIC_OP_RETURN_RELAXED(op, asm_op) \ +static inline int atomic_##op##_return_relaxed(int a, atomic_t *v) \ { \ int t; \ \ __asm__ __volatile__( \ - PPC_ATOMIC_ENTRY_BARRIER \ -"1: lwarx %0,0,%2 # atomic_" #op "_return\n" \ - #asm_op " %0,%1,%0\n" \ - PPC405_ERR77(0,%2) \ -" stwcx. %0,0,%2 \n" \ +"1: lwarx %0,0,%3 # atomic_" #op "_return_relaxed\n" \ + #asm_op " %0,%2,%0\n" \ + PPC405_ERR77(0, %3) \ +" stwcx. %0,0,%3\n" \ " bne- 1b\n" \ - PPC_ATOMIC_EXIT_BARRIER \ - : "=&r" (t) \ + : "=&r" (t), "+m" (v->counter) \ : "r" (a), "r" (&v->counter) \ - : "cc", "memory"); \ + : "cc"); \ \ return t; \ } -#define ATOMIC_OPS(op, asm_op) ATOMIC_OP(op, asm_op) ATOMIC_OP_RETURN(op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_OP_RETURN_RELAXED(op, asm_op) ATOMIC_OPS(add, add) ATOMIC_OPS(sub, subf) @@ -71,8 +89,11 @@ ATOMIC_OP(and, and) ATOMIC_OP(or, or) ATOMIC_OP(xor, xor) +#define atomic_add_return_relaxed atomic_add_return_relaxed +#define atomic_sub_return_relaxed atomic_sub_return_relaxed + #undef ATOMIC_OPS -#undef ATOMIC_OP_RETURN +#undef ATOMIC_OP_RETURN_RELAXED #undef ATOMIC_OP #define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) @@ -92,21 +113,19 @@ static __inline__ void atomic_inc(atomic_t *v) : "cc", "xer"); } -static __inline__ int atomic_inc_return(atomic_t *v) +static __inline__ int atomic_inc_return_relaxed(atomic_t *v) { int t; __asm__ __volatile__( - PPC_ATOMIC_ENTRY_BARRIER -"1: lwarx %0,0,%1 # atomic_inc_return\n\ - addic %0,%0,1\n" - PPC405_ERR77(0,%1) -" stwcx. %0,0,%1 \n\ - bne- 1b" - PPC_ATOMIC_EXIT_BARRIER - : "=&r" (t) +"1: lwarx %0,0,%2 # atomic_inc_return_relaxed\n" +" addic %0,%0,1\n" + PPC405_ERR77(0, %2) +" stwcx. %0,0,%2\n" +" bne- 1b" + : "=&r" (t), "+m" (v->counter) : "r" (&v->counter) - : "cc", "xer", "memory"); + : "cc", "xer"); return t; } @@ -136,27 +155,34 @@ static __inline__ void atomic_dec(atomic_t *v) : "cc", "xer"); } -static __inline__ int atomic_dec_return(atomic_t *v) +static __inline__ int atomic_dec_return_relaxed(atomic_t *v) { int t; __asm__ __volatile__( - PPC_ATOMIC_ENTRY_BARRIER -"1: lwarx %0,0,%1 # atomic_dec_return\n\ - addic %0,%0,-1\n" - PPC405_ERR77(0,%1) -" stwcx. %0,0,%1\n\ - bne- 1b" - PPC_ATOMIC_EXIT_BARRIER - : "=&r" (t) +"1: lwarx %0,0,%2 # atomic_dec_return_relaxed\n" +" addic %0,%0,-1\n" + PPC405_ERR77(0, %2) +" stwcx. %0,0,%2\n" +" bne- 1b" + : "=&r" (t), "+m" (v->counter) : "r" (&v->counter) - : "cc", "xer", "memory"); + : "cc", "xer"); return t; } +#define atomic_inc_return_relaxed atomic_inc_return_relaxed +#define atomic_dec_return_relaxed atomic_dec_return_relaxed + #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) +#define atomic_cmpxchg_relaxed(v, o, n) \ + cmpxchg_relaxed(&((v)->counter), (o), (n)) +#define atomic_cmpxchg_acquire(v, o, n) \ + cmpxchg_acquire(&((v)->counter), (o), (n)) + #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) +#define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** * __atomic_add_unless - add unless the number is a given value @@ -285,26 +311,27 @@ static __inline__ void atomic64_##op(long a, atomic64_t *v) \ : "cc"); \ } -#define ATOMIC64_OP_RETURN(op, asm_op) \ -static __inline__ long atomic64_##op##_return(long a, atomic64_t *v) \ +#define ATOMIC64_OP_RETURN_RELAXED(op, asm_op) \ +static inline long \ +atomic64_##op##_return_relaxed(long a, atomic64_t *v) \ { \ long t; \ \ __asm__ __volatile__( \ - PPC_ATOMIC_ENTRY_BARRIER \ -"1: ldarx %0,0,%2 # atomic64_" #op "_return\n" \ - #asm_op " %0,%1,%0\n" \ -" stdcx. %0,0,%2 \n" \ +"1: ldarx %0,0,%3 # atomic64_" #op "_return_relaxed\n" \ + #asm_op " %0,%2,%0\n" \ +" stdcx. %0,0,%3\n" \ " bne- 1b\n" \ - PPC_ATOMIC_EXIT_BARRIER \ - : "=&r" (t) \ + : "=&r" (t), "+m" (v->counter) \ : "r" (a), "r" (&v->counter) \ - : "cc", "memory"); \ + : "cc"); \ \ return t; \ } -#define ATOMIC64_OPS(op, asm_op) ATOMIC64_OP(op, asm_op) ATOMIC64_OP_RETURN(op, asm_op) +#define ATOMIC64_OPS(op, asm_op) \ + ATOMIC64_OP(op, asm_op) \ + ATOMIC64_OP_RETURN_RELAXED(op, asm_op) ATOMIC64_OPS(add, add) ATOMIC64_OPS(sub, subf) @@ -312,8 +339,11 @@ ATOMIC64_OP(and, and) ATOMIC64_OP(or, or) ATOMIC64_OP(xor, xor) -#undef ATOMIC64_OPS -#undef ATOMIC64_OP_RETURN +#define atomic64_add_return_relaxed atomic64_add_return_relaxed +#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed + +#undef ATOPIC64_OPS +#undef ATOMIC64_OP_RETURN_RELAXED #undef ATOMIC64_OP #define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) @@ -332,20 +362,18 @@ static __inline__ void atomic64_inc(atomic64_t *v) : "cc", "xer"); } -static __inline__ long atomic64_inc_return(atomic64_t *v) +static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) { long t; __asm__ __volatile__( - PPC_ATOMIC_ENTRY_BARRIER -"1: ldarx %0,0,%1 # atomic64_inc_return\n\ - addic %0,%0,1\n\ - stdcx. %0,0,%1 \n\ - bne- 1b" - PPC_ATOMIC_EXIT_BARRIER - : "=&r" (t) +"1: ldarx %0,0,%2 # atomic64_inc_return_relaxed\n" +" addic %0,%0,1\n" +" stdcx. %0,0,%2\n" +" bne- 1b" + : "=&r" (t), "+m" (v->counter) : "r" (&v->counter) - : "cc", "xer", "memory"); + : "cc", "xer"); return t; } @@ -374,24 +402,25 @@ static __inline__ void atomic64_dec(atomic64_t *v) : "cc", "xer"); } -static __inline__ long atomic64_dec_return(atomic64_t *v) +static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) { long t; __asm__ __volatile__( - PPC_ATOMIC_ENTRY_BARRIER -"1: ldarx %0,0,%1 # atomic64_dec_return\n\ - addic %0,%0,-1\n\ - stdcx. %0,0,%1\n\ - bne- 1b" - PPC_ATOMIC_EXIT_BARRIER - : "=&r" (t) +"1: ldarx %0,0,%2 # atomic64_dec_return_relaxed\n" +" addic %0,%0,-1\n" +" stdcx. %0,0,%2\n" +" bne- 1b" + : "=&r" (t), "+m" (v->counter) : "r" (&v->counter) - : "cc", "xer", "memory"); + : "cc", "xer"); return t; } +#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed +#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed + #define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) #define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) @@ -420,7 +449,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) } #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) +#define atomic64_cmpxchg_relaxed(v, o, n) \ + cmpxchg_relaxed(&((v)->counter), (o), (n)) +#define atomic64_cmpxchg_acquire(v, o, n) \ + cmpxchg_acquire(&((v)->counter), (o), (n)) + #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) +#define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** * atomic64_add_unless - add unless the number is a given value diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index d1a8d93cccfd..44efe739b6b9 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -5,25 +5,25 @@ #include <linux/compiler.h> #include <asm/synch.h> #include <asm/asm-compat.h> +#include <linux/bug.h> /* * Atomic exchange * - * Changes the memory location '*ptr' to be val and returns + * Changes the memory location '*p' to be val and returns * the previous value stored there. */ + static __always_inline unsigned long -__xchg_u32(volatile void *p, unsigned long val) +__xchg_u32_local(volatile void *p, unsigned long val) { unsigned long prev; __asm__ __volatile__( - PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stwcx. %3,0,%2 \n\ bne- 1b" - PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned int *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -31,42 +31,34 @@ __xchg_u32(volatile void *p, unsigned long val) return prev; } -/* - * Atomic exchange - * - * Changes the memory location '*ptr' to be val and returns - * the previous value stored there. - */ static __always_inline unsigned long -__xchg_u32_local(volatile void *p, unsigned long val) +__xchg_u32_relaxed(u32 *p, unsigned long val) { unsigned long prev; __asm__ __volatile__( -"1: lwarx %0,0,%2 \n" - PPC405_ERR77(0,%2) -" stwcx. %3,0,%2 \n\ - bne- 1b" - : "=&r" (prev), "+m" (*(volatile unsigned int *)p) +"1: lwarx %0,0,%2\n" + PPC405_ERR77(0, %2) +" stwcx. %3,0,%2\n" +" bne- 1b" + : "=&r" (prev), "+m" (*p) : "r" (p), "r" (val) - : "cc", "memory"); + : "cc"); return prev; } #ifdef CONFIG_PPC64 static __always_inline unsigned long -__xchg_u64(volatile void *p, unsigned long val) +__xchg_u64_local(volatile void *p, unsigned long val) { unsigned long prev; __asm__ __volatile__( - PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stdcx. %3,0,%2 \n\ bne- 1b" - PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned long *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -75,64 +67,52 @@ __xchg_u64(volatile void *p, unsigned long val) } static __always_inline unsigned long -__xchg_u64_local(volatile void *p, unsigned long val) +__xchg_u64_relaxed(u64 *p, unsigned long val) { unsigned long prev; __asm__ __volatile__( -"1: ldarx %0,0,%2 \n" - PPC405_ERR77(0,%2) -" stdcx. %3,0,%2 \n\ - bne- 1b" - : "=&r" (prev), "+m" (*(volatile unsigned long *)p) +"1: ldarx %0,0,%2\n" + PPC405_ERR77(0, %2) +" stdcx. %3,0,%2\n" +" bne- 1b" + : "=&r" (prev), "+m" (*p) : "r" (p), "r" (val) - : "cc", "memory"); + : "cc"); return prev; } #endif -/* - * This function doesn't exist, so you'll get a linker error - * if something tries to do an invalid xchg(). - */ -extern void __xchg_called_with_bad_pointer(void); - static __always_inline unsigned long -__xchg(volatile void *ptr, unsigned long x, unsigned int size) +__xchg_local(volatile void *ptr, unsigned long x, unsigned int size) { switch (size) { case 4: - return __xchg_u32(ptr, x); + return __xchg_u32_local(ptr, x); #ifdef CONFIG_PPC64 case 8: - return __xchg_u64(ptr, x); + return __xchg_u64_local(ptr, x); #endif } - __xchg_called_with_bad_pointer(); + BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg"); return x; } static __always_inline unsigned long -__xchg_local(volatile void *ptr, unsigned long x, unsigned int size) +__xchg_relaxed(void *ptr, unsigned long x, unsigned int size) { switch (size) { case 4: - return __xchg_u32_local(ptr, x); + return __xchg_u32_relaxed(ptr, x); #ifdef CONFIG_PPC64 case 8: - return __xchg_u64_local(ptr, x); + return __xchg_u64_relaxed(ptr, x); #endif } - __xchg_called_with_bad_pointer(); + BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local"); return x; } -#define xchg(ptr,x) \ - ({ \ - __typeof__(*(ptr)) _x_ = (x); \ - (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \ - }) - #define xchg_local(ptr,x) \ ({ \ __typeof__(*(ptr)) _x_ = (x); \ @@ -140,6 +120,12 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size) (unsigned long)_x_, sizeof(*(ptr))); \ }) +#define xchg_relaxed(ptr, x) \ +({ \ + __typeof__(*(ptr)) _x_ = (x); \ + (__typeof__(*(ptr))) __xchg_relaxed((ptr), \ + (unsigned long)_x_, sizeof(*(ptr))); \ +}) /* * Compare and exchange - if *p == old, set it to new, * and return the old value of *p. @@ -190,6 +176,56 @@ __cmpxchg_u32_local(volatile unsigned int *p, unsigned long old, return prev; } +static __always_inline unsigned long +__cmpxchg_u32_relaxed(u32 *p, unsigned long old, unsigned long new) +{ + unsigned long prev; + + __asm__ __volatile__ ( +"1: lwarx %0,0,%2 # __cmpxchg_u32_relaxed\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" + PPC405_ERR77(0, %2) +" stwcx. %4,0,%2\n" +" bne- 1b\n" +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc"); + + return prev; +} + +/* + * cmpxchg family don't have order guarantee if cmp part fails, therefore we + * can avoid superfluous barriers if we use assembly code to implement + * cmpxchg() and cmpxchg_acquire(), however we don't do the similar for + * cmpxchg_release() because that will result in putting a barrier in the + * middle of a ll/sc loop, which is probably a bad idea. For example, this + * might cause the conditional store more likely to fail. + */ +static __always_inline unsigned long +__cmpxchg_u32_acquire(u32 *p, unsigned long old, unsigned long new) +{ + unsigned long prev; + + __asm__ __volatile__ ( +"1: lwarx %0,0,%2 # __cmpxchg_u32_acquire\n" +" cmpw 0,%0,%3\n" +" bne- 2f\n" + PPC405_ERR77(0, %2) +" stwcx. %4,0,%2\n" +" bne- 1b\n" + PPC_ACQUIRE_BARRIER + "\n" +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc", "memory"); + + return prev; +} + #ifdef CONFIG_PPC64 static __always_inline unsigned long __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new) @@ -233,11 +269,47 @@ __cmpxchg_u64_local(volatile unsigned long *p, unsigned long old, return prev; } -#endif -/* This function doesn't exist, so you'll get a linker error - if something tries to do an invalid cmpxchg(). */ -extern void __cmpxchg_called_with_bad_pointer(void); +static __always_inline unsigned long +__cmpxchg_u64_relaxed(u64 *p, unsigned long old, unsigned long new) +{ + unsigned long prev; + + __asm__ __volatile__ ( +"1: ldarx %0,0,%2 # __cmpxchg_u64_relaxed\n" +" cmpd 0,%0,%3\n" +" bne- 2f\n" +" stdcx. %4,0,%2\n" +" bne- 1b\n" +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc"); + + return prev; +} + +static __always_inline unsigned long +__cmpxchg_u64_acquire(u64 *p, unsigned long old, unsigned long new) +{ + unsigned long prev; + + __asm__ __volatile__ ( +"1: ldarx %0,0,%2 # __cmpxchg_u64_acquire\n" +" cmpd 0,%0,%3\n" +" bne- 2f\n" +" stdcx. %4,0,%2\n" +" bne- 1b\n" + PPC_ACQUIRE_BARRIER + "\n" +"2:" + : "=&r" (prev), "+m" (*p) + : "r" (p), "r" (old), "r" (new) + : "cc", "memory"); + + return prev; +} +#endif static __always_inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, @@ -251,7 +323,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, return __cmpxchg_u64(ptr, old, new); #endif } - __cmpxchg_called_with_bad_pointer(); + BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg"); return old; } @@ -267,10 +339,41 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new, return __cmpxchg_u64_local(ptr, old, new); #endif } - __cmpxchg_called_with_bad_pointer(); + BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_local"); + return old; +} + +static __always_inline unsigned long +__cmpxchg_relaxed(void *ptr, unsigned long old, unsigned long new, + unsigned int size) +{ + switch (size) { + case 4: + return __cmpxchg_u32_relaxed(ptr, old, new); +#ifdef CONFIG_PPC64 + case 8: + return __cmpxchg_u64_relaxed(ptr, old, new); +#endif + } + BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_relaxed"); return old; } +static __always_inline unsigned long +__cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new, + unsigned int size) +{ + switch (size) { + case 4: + return __cmpxchg_u32_acquire(ptr, old, new); +#ifdef CONFIG_PPC64 + case 8: + return __cmpxchg_u64_acquire(ptr, old, new); +#endif + } + BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_acquire"); + return old; +} #define cmpxchg(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ @@ -288,6 +391,23 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new, (unsigned long)_n_, sizeof(*(ptr))); \ }) +#define cmpxchg_relaxed(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) _o_ = (o); \ + __typeof__(*(ptr)) _n_ = (n); \ + (__typeof__(*(ptr))) __cmpxchg_relaxed((ptr), \ + (unsigned long)_o_, (unsigned long)_n_, \ + sizeof(*(ptr))); \ +}) + +#define cmpxchg_acquire(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) _o_ = (o); \ + __typeof__(*(ptr)) _n_ = (n); \ + (__typeof__(*(ptr))) __cmpxchg_acquire((ptr), \ + (unsigned long)_o_, (unsigned long)_n_, \ + sizeof(*(ptr))); \ +}) #ifdef CONFIG_PPC64 #define cmpxchg64(ptr, o, n) \ ({ \ @@ -299,7 +419,16 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new, BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg_local((ptr), (o), (n)); \ }) -#define cmpxchg64_relaxed cmpxchg64_local +#define cmpxchg64_relaxed(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + cmpxchg_relaxed((ptr), (o), (n)); \ +}) +#define cmpxchg64_acquire(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + cmpxchg_acquire((ptr), (o), (n)); \ +}) #else #include <asm-generic/cmpxchg-local.h> #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index b118072670fb..94ace9b4c4e1 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -171,7 +171,7 @@ enum { #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) -/* Free LONG_ASM_CONST(0x0000001000000000) */ +#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) @@ -196,6 +196,7 @@ enum { #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_SUBCORE LONG_ASM_CONST(0x2000000000000000) #ifndef __ASSEMBLY__ @@ -443,9 +444,19 @@ enum { CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE) #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 | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ + CPU_FTR_MMCRA | CPU_FTR_SMT | \ + CPU_FTR_COHERENT_ICACHE | \ + CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ + CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ + CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ + CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -464,7 +475,7 @@ enum { (CPU_FTRS_POWER4 | 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_PA6T | CPU_FTR_VSX | CPU_FTRS_POWER9) #endif #else enum { @@ -515,7 +526,8 @@ enum { (CPU_FTRS_POWER4 & 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_POWER8_DD1 & ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & \ + CPU_FTRS_POWER9) #endif #else enum { diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 7f522c021dc3..77816acd4fd9 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -125,8 +125,6 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off) #define HAVE_ARCH_DMA_SET_MASK 1 extern int dma_set_mask(struct device *dev, u64 dma_mask); -#include <asm-generic/dma-mapping-common.h> - extern int __dma_set_mask(struct device *dev, u64 dma_mask); extern u64 __dma_get_required_mask(struct device *dev); diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index 493e72f64b35..b4407d0add27 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -191,7 +191,7 @@ struct fadump_crash_info_header { u64 elfcorehdr_addr; u32 crashing_cpu; struct pt_regs regs; - struct cpumask cpu_online_mask; + struct cpumask online_mask; }; /* Crash memory ranges */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 271fefbbe521..9d08d8cbed1a 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -38,8 +38,7 @@ #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS -#define KVM_USER_MEM_SLOTS 32 -#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS +#define KVM_USER_MEM_SLOTS 512 #ifdef CONFIG_KVM_MMIO #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 7352d3f212df..e36dc90c80d0 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -114,6 +114,7 @@ #define POWER7_TLB_SETS 128 /* # sets in POWER7 TLB */ #define POWER8_TLB_SETS 512 /* # sets in POWER8 TLB */ +#define POWER9_TLB_SETS_HASH 256 /* # sets in POWER9 TLB Hash mode */ #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 3d5abfe6ba67..54d46504733d 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -97,6 +97,7 @@ #define MMU_FTRS_POWER6 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE #define MMU_FTRS_POWER7 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE #define MMU_FTRS_POWER8 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE +#define MMU_FTRS_POWER9 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE #define MMU_FTRS_CELL MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ MMU_FTR_CI_LARGE_PAGE #define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 07a99e638449..9d86c6651716 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -248,6 +248,7 @@ extern int opal_elog_init(void); extern void opal_platform_dump_init(void); extern void opal_sys_param_init(void); extern void opal_msglog_init(void); +extern void opal_msglog_sysfs_init(void); extern int opal_async_comp_init(void); extern int opal_sensor_init(void); extern int opal_hmi_handler_init(void); @@ -273,6 +274,8 @@ void opal_free_sg_list(struct opal_sg_list *sg); extern int opal_error_code(int rc); +ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_OPAL_H */ diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 54843ca5fa2b..b0b43f5fbc5f 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -215,11 +215,10 @@ struct pci_dn { #ifdef CONFIG_PCI_IOV u16 vfs_expanded; /* number of VFs IOV BAR expanded */ u16 num_vfs; /* number of VFs enabled*/ - int offset; /* PE# for the first VF PE */ -#define M64_PER_IOV 4 - int m64_per_iov; + int *pe_num_map; /* PE# for the first VF PE or array */ + bool m64_single_mode; /* Use M64 BAR in Single Mode */ #define IODA_INVALID_M64 (-1) - int m64_wins[PCI_SRIOV_NUM_BARS][M64_PER_IOV]; + int (*m64_map)[PCI_SRIOV_NUM_BARS]; #endif /* CONFIG_PCI_IOV */ #endif struct list_head child_list; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index ba336930d448..794f22adf99d 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -136,12 +136,18 @@ endif obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o -# Disable GCOV in odd or sensitive code +# Disable GCOV & sanitizers in odd or sensitive code GCOV_PROFILE_prom_init.o := n +UBSAN_SANITIZE_prom_init.o := n GCOV_PROFILE_ftrace.o := n +UBSAN_SANITIZE_ftrace.o := n GCOV_PROFILE_machine_kexec_64.o := n +UBSAN_SANITIZE_machine_kexec_64.o := n GCOV_PROFILE_machine_kexec_32.o := n +UBSAN_SANITIZE_machine_kexec_32.o := n GCOV_PROFILE_kprobes.o := n +UBSAN_SANITIZE_kprobes.o := n +UBSAN_SANITIZE_vdso.o := n extra-$(CONFIG_PPC_FPU) += fpu.o extra-$(CONFIG_ALTIVEC) += vector.o diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 9c9b7411b28b..5932219f1e79 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -15,6 +15,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/cache.h> +#include <asm/mmu-hash64.h> /* Entry: r3 = crap, r4 = ptr to cputable entry * @@ -83,6 +84,39 @@ _GLOBAL(__restore_cpu_power8) mtlr r11 blr +_GLOBAL(__setup_cpu_power9) + mflr r11 + bl __init_FSCR + bl __init_hvmode_206 + mtlr r11 + beqlr + li r0,0 + mtspr SPRN_LPID,r0 + mfspr r3,SPRN_LPCR + ori r3, r3, LPCR_PECEDH + bl __init_LPCR + bl __init_HFSCR + bl __init_tlb_power9 + mtlr r11 + blr + +_GLOBAL(__restore_cpu_power9) + mflr r11 + bl __init_FSCR + mfmsr r3 + rldicl. r0,r3,4,63 + mtlr r11 + beqlr + li r0,0 + mtspr SPRN_LPID,r0 + mfspr r3,SPRN_LPCR + ori r3, r3, LPCR_PECEDH + bl __init_LPCR + bl __init_HFSCR + bl __init_tlb_power9 + mtlr r11 + blr + __init_hvmode_206: /* Disable CPU_FTR_HVMODE and exit if MSR:HV is not set */ mfmsr r3 @@ -139,7 +173,7 @@ __init_HFSCR: * (invalidate by congruence class). P7 has 128 CCs., P8 has 512. */ __init_tlb_power7: - li r6,128 + li r6,POWER7_TLB_SETS mtctr r6 li r7,0xc00 /* IS field = 0b11 */ ptesync @@ -150,7 +184,18 @@ __init_tlb_power7: 1: blr __init_tlb_power8: - li r6,512 + li r6,POWER8_TLB_SETS + mtctr r6 + li r7,0xc00 /* IS field = 0b11 */ + ptesync +2: tlbiel r7 + addi r7,r7,0x1000 + bdnz 2b + ptesync +1: blr + +__init_tlb_power9: + li r6,POWER9_TLB_SETS_HASH mtctr r6 li r7,0xc00 /* IS field = 0b11 */ ptesync diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 7d80bfdfb15e..be4d73053bed 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -70,9 +70,12 @@ extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power7(void); extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power8(void); +extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); +extern void __restore_cpu_power9(void); extern void __restore_cpu_a2(void); extern void __flush_tlb_power7(unsigned int action); extern void __flush_tlb_power8(unsigned int action); +extern void __flush_tlb_power9(unsigned int action); extern long __machine_check_early_realmode_p7(struct pt_regs *regs); extern long __machine_check_early_realmode_p8(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ @@ -116,6 +119,11 @@ extern void __restore_cpu_e6500(void); #define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ PPC_FEATURE_TRUE_LE | \ PPC_FEATURE_HAS_ALTIVEC_COMP) +#define COMMON_USER_POWER9 COMMON_USER_POWER8 +#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \ + PPC_FEATURE2_ARCH_3_00 | \ + PPC_FEATURE2_HAS_IEEE128) + #ifdef CONFIG_PPC_BOOK3E_64 #define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE) #else @@ -499,6 +507,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, + { /* Power9 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004e0000, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9, + .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, + .flush_tlb = __flush_tlb_power9, + .platform = "power9", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 40e4d4a27663..8c6005cf1583 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -739,7 +739,7 @@ static void *eeh_restore_dev_state(void *data, void *userdata) } /** - * pcibios_set_pcie_slot_reset - Set PCI-E reset state + * pcibios_set_pcie_reset_state - Set PCI-E reset state * @dev: pci device struct * @state: reset state to enter * diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 52c1e273f8cd..650cfb31ea3d 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -400,7 +400,7 @@ static void *eeh_rmv_device(void *data, void *userdata) * support EEH. So we just care about PCI devices for * simplicity here. */ - if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) + if (!dev || (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)) return NULL; /* diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 26d091a1a54c..3cb3b02a13dd 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -415,7 +415,7 @@ void crash_fadump(struct pt_regs *regs, const char *str) else ppc_save_regs(&fdh->regs); - fdh->cpu_online_mask = *cpu_online_mask; + fdh->online_mask = *cpu_online_mask; /* Call ibm,os-term rtas call to trigger firmware assisted dump */ rtas_os_term((char *)str); @@ -646,7 +646,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) } /* Lower 4 bytes of reg_value contains logical cpu id */ cpu = be64_to_cpu(reg_entry->reg_value) & FADUMP_CPU_ID_MASK; - if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { + if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) { SKIP_TO_NEXT_CPU(reg_entry); continue; } diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index e77c3ccf8dcf..dbf098121ce6 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -445,7 +445,11 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code, * Global data */ struct kgdb_arch arch_kgdb_ops = { +#ifdef __LITTLE_ENDIAN__ + .gdb_bpt_instr = {0x08, 0x10, 0x82, 0x7d}, +#else .gdb_bpt_instr = {0x7d, 0x82, 0x10, 0x08}, +#endif }; static int kgdb_not_implemented(struct pt_regs *regs) diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 2c647b1e62e4..ee62b197502d 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -54,8 +54,8 @@ static void flush_tlb_206(unsigned int num_sets, unsigned int action) } /* - * Generic routine to flush TLB on power7. This routine is used as - * flush_tlb hook in cpu_spec for Power7 processor. + * Generic routines to flush TLB on POWER processors. These routines + * are used as flush_tlb hook in the cpu_spec. * * action => TLB_INVAL_SCOPE_GLOBAL: Invalidate all TLBs. * TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID. @@ -65,18 +65,17 @@ void __flush_tlb_power7(unsigned int action) flush_tlb_206(POWER7_TLB_SETS, action); } -/* - * Generic routine to flush TLB on power8. This routine is used as - * flush_tlb hook in cpu_spec for power8 processor. - * - * action => TLB_INVAL_SCOPE_GLOBAL: Invalidate all TLBs. - * TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID. - */ void __flush_tlb_power8(unsigned int action) { flush_tlb_206(POWER8_TLB_SETS, action); } +void __flush_tlb_power9(unsigned int action) +{ + flush_tlb_206(POWER9_TLB_SETS_HASH, action); +} + + /* flush SLBs and reload */ static void flush_and_reload_slb(void) { diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 2e710c15893f..526ac6750e4d 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -187,9 +187,6 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, pci_device_add(dev, bus); - /* Setup MSI caps & disable MSI/MSI-X interrupts */ - pci_msi_setup_pci_dev(dev); - return dev; } EXPORT_SYMBOL(of_create_pci_dev); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index b6becc795bb5..4e5c11d4d19d 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1148,6 +1148,7 @@ void __kprobes program_check_exception(struct pt_regs *regs) goto bail; } if (reason & REASON_TRAP) { + unsigned long bugaddr; /* Debugger is first in line to stop recursive faults in * rcu_lock, notify_die, or atomic_notifier_call_chain */ if (debugger_bpt(regs)) @@ -1158,8 +1159,15 @@ void __kprobes program_check_exception(struct pt_regs *regs) == NOTIFY_STOP) goto bail; + bugaddr = regs->nip; + /* + * Fixup bugaddr for BUG_ON() in real mode + */ + if (!is_kernel_addr(bugaddr) && !(regs->msr & MSR_IR)) + bugaddr += PAGE_OFFSET; + if (!(regs->msr & MSR_PR) && /* not user-mode */ - report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) { + report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) { regs->nip += 4; goto bail; } diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 6abffb7a8cd9..cbabd143acae 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -15,6 +15,7 @@ targets := $(obj-vdso32) vdso32.so vdso32.so.dbg obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) GCOV_PROFILE := n +UBSAN_SANITIZE := n ccflags-y := -shared -fno-common -fno-builtin ccflags-y += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 8c8f2ae43935..c710802b8fb6 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -8,6 +8,7 @@ targets := $(obj-vdso64) vdso64.so vdso64.so.dbg obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) GCOV_PROFILE := n +UBSAN_SANITIZE := n ccflags-y := -shared -fno-common -fno-builtin ccflags-y += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 774a253ca4e1..9bf7031a67ff 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -377,15 +377,12 @@ no_seg_found: static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) { - struct kvmppc_vcpu_book3s *vcpu_book3s; u64 esid, esid_1t; int slb_nr; struct kvmppc_slb *slbe; dprintk("KVM MMU: slbmte(0x%llx, 0x%llx)\n", rs, rb); - vcpu_book3s = to_book3s(vcpu); - esid = GET_ESID(rb); esid_1t = GET_ESID_1T(rb); slb_nr = rb & 0xfff; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index cff207b72c46..baeddb06811d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -833,6 +833,24 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->stat.sum_exits++; + /* + * This can happen if an interrupt occurs in the last stages + * of guest entry or the first stages of guest exit (i.e. after + * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV + * and before setting it to KVM_GUEST_MODE_HOST_HV). + * That can happen due to a bug, or due to a machine check + * occurring at just the wrong time. + */ + if (vcpu->arch.shregs.msr & MSR_HV) { + printk(KERN_EMERG "KVM trap in HV mode!\n"); + printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", + vcpu->arch.trap, kvmppc_get_pc(vcpu), + vcpu->arch.shregs.msr); + kvmppc_dump_regs(vcpu); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->hw.hardware_exit_reason = vcpu->arch.trap; + return RESUME_HOST; + } run->exit_reason = KVM_EXIT_UNKNOWN; run->ready_for_interrupt_injection = 1; switch (vcpu->arch.trap) { diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 3c6badcd53ef..6ee26de9a1de 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* 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, 1, DAWRX_WT + rlwimi r5, r4, 2, DAWRX_WT clrrdi r4, r4, 3 std r4, VCPU_DAWR(r3) std r5, VCPU_DAWRX(r3) @@ -2404,6 +2404,8 @@ machine_check_realmode: * guest as machine check causing guest to crash. */ ld r11, VCPU_MSR(r9) + rldicl. r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */ + bne mc_cont /* if so, exit to host */ andi. r10, r11, MSR_RI /* check for unrecoverable exception */ beq 1f /* Deliver a machine check to guest */ ld r10, VCPU_PC(r9) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6fd2405c7f4a..a3b182dcb823 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: - if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { - r = -ENXIO; - break; - } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ default: @@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ default: diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 856fe6e03c2a..7aa37236bb70 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -127,8 +127,16 @@ static const struct attribute_group *attr_groups[] = { NULL, }; -#define GPCI_MAX_DATA_BYTES \ - (1024 - sizeof(struct hv_get_perf_counter_info_params)) +#define HGPCI_REQ_BUFFER_SIZE 4096 +#define HGPCI_MAX_DATA_BYTES \ + (HGPCI_REQ_BUFFER_SIZE - sizeof(struct hv_get_perf_counter_info_params)) + +DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t)); + +struct hv_gpci_request_buffer { + struct hv_get_perf_counter_info_params params; + uint8_t bytes[HGPCI_MAX_DATA_BYTES]; +} __packed; static unsigned long single_gpci_request(u32 req, u32 starting_index, u16 secondary_index, u8 version_in, u32 offset, u8 length, @@ -137,24 +145,21 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index, unsigned long ret; size_t i; u64 count; + struct hv_gpci_request_buffer *arg; + + arg = (void *)get_cpu_var(hv_gpci_reqb); + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); - struct { - struct hv_get_perf_counter_info_params params; - uint8_t bytes[GPCI_MAX_DATA_BYTES]; - } __packed __aligned(sizeof(uint64_t)) arg = { - .params = { - .counter_request = cpu_to_be32(req), - .starting_index = cpu_to_be32(starting_index), - .secondary_index = cpu_to_be16(secondary_index), - .counter_info_version_in = version_in, - } - }; + arg->params.counter_request = cpu_to_be32(req); + arg->params.starting_index = cpu_to_be32(starting_index); + arg->params.secondary_index = cpu_to_be16(secondary_index); + arg->params.counter_info_version_in = version_in; ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, - virt_to_phys(&arg), sizeof(arg)); + virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); if (ret) { pr_devel("hcall failed: 0x%lx\n", ret); - return ret; + goto out; } /* @@ -163,9 +168,11 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index, */ count = 0; for (i = offset; i < offset + length; i++) - count |= arg.bytes[i] << (i - offset); + count |= arg->bytes[i] << (i - offset); *value = count; +out: + put_cpu_var(hv_gpci_reqb); return ret; } @@ -245,10 +252,10 @@ static int h_gpci_event_init(struct perf_event *event) } /* last byte within the buffer? */ - if ((event_get_offset(event) + length) > GPCI_MAX_DATA_BYTES) { + if ((event_get_offset(event) + length) > HGPCI_MAX_DATA_BYTES) { pr_devel("request outside of buffer: %zu > %zu\n", (size_t)event_get_offset(event) + length, - GPCI_MAX_DATA_BYTES); + HGPCI_MAX_DATA_BYTES); return -EINVAL; } diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 5038fd578e65..2936a0044c04 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1799,9 +1799,9 @@ static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int data struct inode *inode = file_inode(file); int err = filemap_write_and_wait_range(inode->i_mapping, start, end); if (!err) { - mutex_lock(&inode->i_mutex); + inode_lock(inode); err = spufs_mfc_flush(file, NULL); - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); } return err; } diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index ad4840f86be1..dfa863876778 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -163,7 +163,7 @@ static void spufs_prune_dir(struct dentry *dir) { struct dentry *dentry, *tmp; - mutex_lock(&d_inode(dir)->i_mutex); + inode_lock(d_inode(dir)); list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { spin_lock(&dentry->d_lock); if (simple_positive(dentry)) { @@ -180,7 +180,7 @@ static void spufs_prune_dir(struct dentry *dir) } } shrink_dcache_parent(dir); - mutex_unlock(&d_inode(dir)->i_mutex); + inode_unlock(d_inode(dir)); } /* Caller must hold parent->i_mutex */ @@ -225,9 +225,9 @@ static int spufs_dir_close(struct inode *inode, struct file *file) parent = d_inode(dir->d_parent); ctx = SPUFS_I(d_inode(dir))->i_ctx; - mutex_lock_nested(&parent->i_mutex, I_MUTEX_PARENT); + inode_lock_nested(parent, I_MUTEX_PARENT); ret = spufs_rmdir(parent, dir); - mutex_unlock(&parent->i_mutex); + inode_unlock(parent); WARN_ON(ret); return dcache_dir_close(inode, file); @@ -270,7 +270,7 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags, inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; - mutex_lock(&inode->i_mutex); + inode_lock(inode); dget(dentry); inc_nlink(dir); @@ -291,7 +291,7 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags, if (ret) spufs_rmdir(dir, dentry); - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); return ret; } diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index f1516b5ecec9..cd9711e72df6 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -5,7 +5,7 @@ obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o obj-y += opal-kmsg.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o -obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o npu-dma.o +obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o obj-$(CONFIG_EEH) += eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 87f47e55aab6..811917219bf1 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -167,42 +167,26 @@ static int pnv_eeh_dbgfs_get(void *data, int offset, u64 *val) return 0; } -static int pnv_eeh_outb_dbgfs_set(void *data, u64 val) -{ - return pnv_eeh_dbgfs_set(data, 0xD10, val); -} - -static int pnv_eeh_outb_dbgfs_get(void *data, u64 *val) -{ - return pnv_eeh_dbgfs_get(data, 0xD10, val); -} - -static int pnv_eeh_inbA_dbgfs_set(void *data, u64 val) -{ - return pnv_eeh_dbgfs_set(data, 0xD90, val); -} - -static int pnv_eeh_inbA_dbgfs_get(void *data, u64 *val) -{ - return pnv_eeh_dbgfs_get(data, 0xD90, val); -} - -static int pnv_eeh_inbB_dbgfs_set(void *data, u64 val) -{ - return pnv_eeh_dbgfs_set(data, 0xE10, val); -} - -static int pnv_eeh_inbB_dbgfs_get(void *data, u64 *val) -{ - return pnv_eeh_dbgfs_get(data, 0xE10, val); -} +#define PNV_EEH_DBGFS_ENTRY(name, reg) \ +static int pnv_eeh_dbgfs_set_##name(void *data, u64 val) \ +{ \ + return pnv_eeh_dbgfs_set(data, reg, val); \ +} \ + \ +static int pnv_eeh_dbgfs_get_##name(void *data, u64 *val) \ +{ \ + return pnv_eeh_dbgfs_get(data, reg, val); \ +} \ + \ +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_dbgfs_ops_##name, \ + pnv_eeh_dbgfs_get_##name, \ + pnv_eeh_dbgfs_set_##name, \ + "0x%llx\n") + +PNV_EEH_DBGFS_ENTRY(outb, 0xD10); +PNV_EEH_DBGFS_ENTRY(inbA, 0xD90); +PNV_EEH_DBGFS_ENTRY(inbB, 0xE10); -DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_outb_dbgfs_ops, pnv_eeh_outb_dbgfs_get, - pnv_eeh_outb_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbA_dbgfs_ops, pnv_eeh_inbA_dbgfs_get, - pnv_eeh_inbA_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbB_dbgfs_ops, pnv_eeh_inbB_dbgfs_get, - pnv_eeh_inbB_dbgfs_set, "0x%llx\n"); #endif /* CONFIG_DEBUG_FS */ /** @@ -268,13 +252,13 @@ static int pnv_eeh_post_init(void) debugfs_create_file("err_injct_outbound", 0600, phb->dbgfs, hose, - &pnv_eeh_outb_dbgfs_ops); + &pnv_eeh_dbgfs_ops_outb); debugfs_create_file("err_injct_inboundA", 0600, phb->dbgfs, hose, - &pnv_eeh_inbA_dbgfs_ops); + &pnv_eeh_dbgfs_ops_inbA); debugfs_create_file("err_injct_inboundB", 0600, phb->dbgfs, hose, - &pnv_eeh_inbB_dbgfs_ops); + &pnv_eeh_dbgfs_ops_inbB); #endif /* CONFIG_DEBUG_FS */ } diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c index 44ed78af1a0d..39d6ff9e5630 100644 --- a/arch/powerpc/platforms/powernv/opal-msglog.c +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -31,26 +31,25 @@ struct memcons { __be32 in_cons; }; -static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, - struct bin_attribute *bin_attr, char *to, - loff_t pos, size_t count) +static struct memcons *opal_memcons = NULL; + +ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count) { - struct memcons *mc = bin_attr->private; const char *conbuf; ssize_t ret; size_t first_read = 0; uint32_t out_pos, avail; - if (!mc) + if (!opal_memcons) return -ENODEV; - out_pos = be32_to_cpu(ACCESS_ONCE(mc->out_pos)); + out_pos = be32_to_cpu(ACCESS_ONCE(opal_memcons->out_pos)); /* Now we've read out_pos, put a barrier in before reading the new * data it points to in conbuf. */ smp_rmb(); - conbuf = phys_to_virt(be64_to_cpu(mc->obuf_phys)); + conbuf = phys_to_virt(be64_to_cpu(opal_memcons->obuf_phys)); /* When the buffer has wrapped, read from the out_pos marker to the end * of the buffer, and then read the remaining data as in the un-wrapped @@ -58,7 +57,7 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, if (out_pos & MEMCONS_OUT_POS_WRAP) { out_pos &= MEMCONS_OUT_POS_MASK; - avail = be32_to_cpu(mc->obuf_size) - out_pos; + avail = be32_to_cpu(opal_memcons->obuf_size) - out_pos; ret = memory_read_from_buffer(to, count, &pos, conbuf + out_pos, avail); @@ -76,7 +75,7 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, } /* Sanity check. The firmware should not do this to us. */ - if (out_pos > be32_to_cpu(mc->obuf_size)) { + if (out_pos > be32_to_cpu(opal_memcons->obuf_size)) { pr_err("OPAL: memory console corruption. Aborting read.\n"); return -EINVAL; } @@ -91,6 +90,13 @@ out: return ret; } +static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *to, + loff_t pos, size_t count) +{ + return opal_msglog_copy(to, pos, count); +} + static struct bin_attribute opal_msglog_attr = { .attr = {.name = "msglog", .mode = 0444}, .read = opal_msglog_read @@ -117,7 +123,15 @@ void __init opal_msglog_init(void) return; } - opal_msglog_attr.private = mc; + opal_memcons = mc; +} + +void __init opal_msglog_sysfs_init(void) +{ + if (!opal_memcons) { + pr_warn("OPAL: message log initialisation failed, not creating sysfs entry\n"); + return; + } if (sysfs_create_bin_file(opal_kobj, &opal_msglog_attr) != 0) pr_warn("OPAL: sysfs file creation failed\n"); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 4e0da5af94a1..0256d0729252 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -724,6 +724,9 @@ static int __init opal_init(void) of_node_put(leds); } + /* Initialise OPAL message log interface */ + opal_msglog_init(); + /* Create "opal" kobject under /sys/firmware */ rc = opal_sysfs_init(); if (rc == 0) { @@ -739,8 +742,8 @@ static int __init opal_init(void) opal_platform_dump_init(); /* Setup system parameters interface */ opal_sys_param_init(); - /* Setup message log interface. */ - opal_msglog_init(); + /* Setup message log sysfs interface. */ + opal_msglog_sysfs_init(); } /* Initialize platform devices: IPMI backend, PRD & flash interface */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index f90dc04395bf..c5baaf3cc4e5 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -872,9 +872,6 @@ static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) if (!res->flags || !res->parent) continue; - if (!pnv_pci_is_mem_pref_64(res->flags)) - continue; - /* * The actual IOV BAR range is determined by the start address * and the actual size for num_vfs VFs BAR. This check is to @@ -903,9 +900,6 @@ static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) if (!res->flags || !res->parent) continue; - if (!pnv_pci_is_mem_pref_64(res->flags)) - continue; - size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); res2 = *res; res->start += size * offset; @@ -1196,29 +1190,36 @@ static void pnv_pci_ioda_setup_PEs(void) } #ifdef CONFIG_PCI_IOV -static int pnv_pci_vf_release_m64(struct pci_dev *pdev) +static int pnv_pci_vf_release_m64(struct pci_dev *pdev, u16 num_vfs) { struct pci_bus *bus; struct pci_controller *hose; struct pnv_phb *phb; struct pci_dn *pdn; int i, j; + int m64_bars; bus = pdev->bus; hose = pci_bus_to_host(bus); phb = hose->private_data; pdn = pci_get_pdn(pdev); + if (pdn->m64_single_mode) + m64_bars = num_vfs; + else + m64_bars = 1; + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) - for (j = 0; j < M64_PER_IOV; j++) { - if (pdn->m64_wins[i][j] == IODA_INVALID_M64) + for (j = 0; j < m64_bars; j++) { + if (pdn->m64_map[j][i] == IODA_INVALID_M64) continue; opal_pci_phb_mmio_enable(phb->opal_id, - OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0); - clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc); - pdn->m64_wins[i][j] = IODA_INVALID_M64; + OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 0); + clear_bit(pdn->m64_map[j][i], &phb->ioda.m64_bar_alloc); + pdn->m64_map[j][i] = IODA_INVALID_M64; } + kfree(pdn->m64_map); return 0; } @@ -1235,8 +1236,7 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) int total_vfs; resource_size_t size, start; int pe_num; - int vf_groups; - int vf_per_group; + int m64_bars; bus = pdev->bus; hose = pci_bus_to_host(bus); @@ -1244,29 +1244,26 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) pdn = pci_get_pdn(pdev); total_vfs = pci_sriov_get_totalvfs(pdev); - /* Initialize the m64_wins to IODA_INVALID_M64 */ - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) - for (j = 0; j < M64_PER_IOV; j++) - pdn->m64_wins[i][j] = IODA_INVALID_M64; + if (pdn->m64_single_mode) + m64_bars = num_vfs; + else + m64_bars = 1; + + pdn->m64_map = kmalloc(sizeof(*pdn->m64_map) * m64_bars, GFP_KERNEL); + if (!pdn->m64_map) + return -ENOMEM; + /* Initialize the m64_map to IODA_INVALID_M64 */ + for (i = 0; i < m64_bars ; i++) + for (j = 0; j < PCI_SRIOV_NUM_BARS; j++) + pdn->m64_map[i][j] = IODA_INVALID_M64; - if (pdn->m64_per_iov == M64_PER_IOV) { - vf_groups = (num_vfs <= M64_PER_IOV) ? num_vfs: M64_PER_IOV; - vf_per_group = (num_vfs <= M64_PER_IOV)? 1: - roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; - } else { - vf_groups = 1; - vf_per_group = 1; - } for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { res = &pdev->resource[i + PCI_IOV_RESOURCES]; if (!res->flags || !res->parent) continue; - if (!pnv_pci_is_mem_pref_64(res->flags)) - continue; - - for (j = 0; j < vf_groups; j++) { + for (j = 0; j < m64_bars; j++) { do { win = find_next_zero_bit(&phb->ioda.m64_bar_alloc, phb->ioda.m64_bar_idx + 1, 0); @@ -1275,12 +1272,11 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) goto m64_failed; } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc)); - pdn->m64_wins[i][j] = win; + pdn->m64_map[j][i] = win; - if (pdn->m64_per_iov == M64_PER_IOV) { + if (pdn->m64_single_mode) { size = pci_iov_resource_size(pdev, PCI_IOV_RESOURCES + i); - size = size * vf_per_group; start = res->start + size * j; } else { size = resource_size(res); @@ -1288,16 +1284,16 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) } /* Map the M64 here */ - if (pdn->m64_per_iov == M64_PER_IOV) { - pe_num = pdn->offset + j; + if (pdn->m64_single_mode) { + pe_num = pdn->pe_num_map[j]; rc = opal_pci_map_pe_mmio_window(phb->opal_id, pe_num, OPAL_M64_WINDOW_TYPE, - pdn->m64_wins[i][j], 0); + pdn->m64_map[j][i], 0); } rc = opal_pci_set_phb_mem_window(phb->opal_id, OPAL_M64_WINDOW_TYPE, - pdn->m64_wins[i][j], + pdn->m64_map[j][i], start, 0, /* unused */ size); @@ -1309,12 +1305,12 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) goto m64_failed; } - if (pdn->m64_per_iov == M64_PER_IOV) + if (pdn->m64_single_mode) rc = opal_pci_phb_mmio_enable(phb->opal_id, - OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2); + OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 2); else rc = opal_pci_phb_mmio_enable(phb->opal_id, - OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 1); + OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 1); if (rc != OPAL_SUCCESS) { dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n", @@ -1326,7 +1322,7 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) return 0; m64_failed: - pnv_pci_vf_release_m64(pdev); + pnv_pci_vf_release_m64(pdev, num_vfs); return -EBUSY; } @@ -1353,15 +1349,13 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe iommu_free_table(tbl, of_node_full_name(dev->dev.of_node)); } -static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs) +static void pnv_ioda_release_vf_PE(struct pci_dev *pdev) { struct pci_bus *bus; struct pci_controller *hose; struct pnv_phb *phb; struct pnv_ioda_pe *pe, *pe_n; struct pci_dn *pdn; - u16 vf_index; - int64_t rc; bus = pdev->bus; hose = pci_bus_to_host(bus); @@ -1371,35 +1365,6 @@ static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs) if (!pdev->is_physfn) return; - if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) { - int vf_group; - int vf_per_group; - int vf_index1; - - vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; - - for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) - for (vf_index = vf_group * vf_per_group; - vf_index < (vf_group + 1) * vf_per_group && - vf_index < num_vfs; - vf_index++) - for (vf_index1 = vf_group * vf_per_group; - vf_index1 < (vf_group + 1) * vf_per_group && - vf_index1 < num_vfs; - vf_index1++){ - - rc = opal_pci_set_peltv(phb->opal_id, - pdn->offset + vf_index, - pdn->offset + vf_index1, - OPAL_REMOVE_PE_FROM_DOMAIN); - - if (rc) - dev_warn(&pdev->dev, "%s: Failed to unlink same group PE#%d(%lld)\n", - __func__, - pdn->offset + vf_index1, rc); - } - } - list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) { if (pe->parent_dev != pdev) continue; @@ -1424,7 +1389,7 @@ void pnv_pci_sriov_disable(struct pci_dev *pdev) struct pnv_phb *phb; struct pci_dn *pdn; struct pci_sriov *iov; - u16 num_vfs; + u16 num_vfs, i; bus = pdev->bus; hose = pci_bus_to_host(bus); @@ -1434,18 +1399,25 @@ void pnv_pci_sriov_disable(struct pci_dev *pdev) num_vfs = pdn->num_vfs; /* Release VF PEs */ - pnv_ioda_release_vf_PE(pdev, num_vfs); + pnv_ioda_release_vf_PE(pdev); if (phb->type == PNV_PHB_IODA2) { - if (pdn->m64_per_iov == 1) - pnv_pci_vf_resource_shift(pdev, -pdn->offset); + if (!pdn->m64_single_mode) + pnv_pci_vf_resource_shift(pdev, -*pdn->pe_num_map); /* Release M64 windows */ - pnv_pci_vf_release_m64(pdev); + pnv_pci_vf_release_m64(pdev, num_vfs); /* Release PE numbers */ - bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs); - pdn->offset = 0; + if (pdn->m64_single_mode) { + for (i = 0; i < num_vfs; i++) { + if (pdn->pe_num_map[i] != IODA_INVALID_PE) + pnv_ioda_free_pe(phb, pdn->pe_num_map[i]); + } + } else + bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs); + /* Releasing pe_num_map */ + kfree(pdn->pe_num_map); } } @@ -1460,7 +1432,6 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) int pe_num; u16 vf_index; struct pci_dn *pdn; - int64_t rc; bus = pdev->bus; hose = pci_bus_to_host(bus); @@ -1472,7 +1443,10 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) /* Reserve PE for each VF */ for (vf_index = 0; vf_index < num_vfs; vf_index++) { - pe_num = pdn->offset + vf_index; + if (pdn->m64_single_mode) + pe_num = pdn->pe_num_map[vf_index]; + else + pe_num = *pdn->pe_num_map + vf_index; pe = &phb->ioda.pe_array[pe_num]; pe->pe_number = pe_num; @@ -1505,37 +1479,6 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) pnv_pci_ioda2_setup_dma_pe(phb, pe); } - - if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) { - int vf_group; - int vf_per_group; - int vf_index1; - - vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; - - for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) { - for (vf_index = vf_group * vf_per_group; - vf_index < (vf_group + 1) * vf_per_group && - vf_index < num_vfs; - vf_index++) { - for (vf_index1 = vf_group * vf_per_group; - vf_index1 < (vf_group + 1) * vf_per_group && - vf_index1 < num_vfs; - vf_index1++) { - - rc = opal_pci_set_peltv(phb->opal_id, - pdn->offset + vf_index, - pdn->offset + vf_index1, - OPAL_ADD_PE_TO_DOMAIN); - - if (rc) - dev_warn(&pdev->dev, "%s: Failed to link same group PE#%d(%lld)\n", - __func__, - pdn->offset + vf_index1, rc); - } - } - } - } } int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) @@ -1545,6 +1488,7 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) struct pnv_phb *phb; struct pci_dn *pdn; int ret; + u16 i; bus = pdev->bus; hose = pci_bus_to_host(bus); @@ -1552,20 +1496,59 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) pdn = pci_get_pdn(pdev); if (phb->type == PNV_PHB_IODA2) { + if (!pdn->vfs_expanded) { + dev_info(&pdev->dev, "don't support this SRIOV device" + " with non 64bit-prefetchable IOV BAR\n"); + return -ENOSPC; + } + + /* + * When M64 BARs functions in Single PE mode, the number of VFs + * could be enabled must be less than the number of M64 BARs. + */ + if (pdn->m64_single_mode && num_vfs > phb->ioda.m64_bar_idx) { + dev_info(&pdev->dev, "Not enough M64 BAR for VFs\n"); + return -EBUSY; + } + + /* Allocating pe_num_map */ + if (pdn->m64_single_mode) + pdn->pe_num_map = kmalloc(sizeof(*pdn->pe_num_map) * num_vfs, + GFP_KERNEL); + else + pdn->pe_num_map = kmalloc(sizeof(*pdn->pe_num_map), GFP_KERNEL); + + if (!pdn->pe_num_map) + return -ENOMEM; + + if (pdn->m64_single_mode) + for (i = 0; i < num_vfs; i++) + pdn->pe_num_map[i] = IODA_INVALID_PE; + /* Calculate available PE for required VFs */ - mutex_lock(&phb->ioda.pe_alloc_mutex); - pdn->offset = bitmap_find_next_zero_area( - phb->ioda.pe_alloc, phb->ioda.total_pe, - 0, num_vfs, 0); - if (pdn->offset >= phb->ioda.total_pe) { + if (pdn->m64_single_mode) { + for (i = 0; i < num_vfs; i++) { + pdn->pe_num_map[i] = pnv_ioda_alloc_pe(phb); + if (pdn->pe_num_map[i] == IODA_INVALID_PE) { + ret = -EBUSY; + goto m64_failed; + } + } + } else { + mutex_lock(&phb->ioda.pe_alloc_mutex); + *pdn->pe_num_map = bitmap_find_next_zero_area( + phb->ioda.pe_alloc, phb->ioda.total_pe, + 0, num_vfs, 0); + if (*pdn->pe_num_map >= phb->ioda.total_pe) { + mutex_unlock(&phb->ioda.pe_alloc_mutex); + dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs); + kfree(pdn->pe_num_map); + return -EBUSY; + } + bitmap_set(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs); mutex_unlock(&phb->ioda.pe_alloc_mutex); - dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs); - pdn->offset = 0; - return -EBUSY; } - bitmap_set(phb->ioda.pe_alloc, pdn->offset, num_vfs); pdn->num_vfs = num_vfs; - mutex_unlock(&phb->ioda.pe_alloc_mutex); /* Assign M64 window accordingly */ ret = pnv_pci_vf_assign_m64(pdev, num_vfs); @@ -1579,8 +1562,8 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) * the IOV BAR according to the PE# allocated to the VFs. * Otherwise, the PE# for the VF will conflict with others. */ - if (pdn->m64_per_iov == 1) { - ret = pnv_pci_vf_resource_shift(pdev, pdn->offset); + if (!pdn->m64_single_mode) { + ret = pnv_pci_vf_resource_shift(pdev, *pdn->pe_num_map); if (ret) goto m64_failed; } @@ -1592,8 +1575,16 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) return 0; m64_failed: - bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs); - pdn->offset = 0; + if (pdn->m64_single_mode) { + for (i = 0; i < num_vfs; i++) { + if (pdn->pe_num_map[i] != IODA_INVALID_PE) + pnv_ioda_free_pe(phb, pdn->pe_num_map[i]); + } + } else + bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs); + + /* Releasing pe_num_map */ + kfree(pdn->pe_num_map); return ret; } @@ -1612,8 +1603,7 @@ int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) /* Allocate PCI data */ add_dev_pci_data(pdev); - pnv_pci_sriov_enable(pdev, num_vfs); - return 0; + return pnv_pci_sriov_enable(pdev, num_vfs); } #endif /* CONFIG_PCI_IOV */ @@ -2851,45 +2841,58 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } #ifdef CONFIG_PCI_IOV static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) { - struct pci_controller *hose; - struct pnv_phb *phb; + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + const resource_size_t gate = phb->ioda.m64_segsize >> 2; struct resource *res; int i; - resource_size_t size; + resource_size_t size, total_vf_bar_sz; struct pci_dn *pdn; int mul, total_vfs; if (!pdev->is_physfn || pdev->is_added) return; - hose = pci_bus_to_host(pdev->bus); - phb = hose->private_data; - pdn = pci_get_pdn(pdev); pdn->vfs_expanded = 0; + pdn->m64_single_mode = false; total_vfs = pci_sriov_get_totalvfs(pdev); - pdn->m64_per_iov = 1; mul = phb->ioda.total_pe; + total_vf_bar_sz = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { res = &pdev->resource[i + PCI_IOV_RESOURCES]; if (!res->flags || res->parent) continue; if (!pnv_pci_is_mem_pref_64(res->flags)) { - dev_warn(&pdev->dev, " non M64 VF BAR%d: %pR\n", + dev_warn(&pdev->dev, "Don't support SR-IOV with" + " non M64 VF BAR%d: %pR. \n", i, res); - continue; + goto truncate_iov; } - size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + total_vf_bar_sz += pci_iov_resource_size(pdev, + i + PCI_IOV_RESOURCES); - /* bigger than 64M */ - if (size > (1 << 26)) { - dev_info(&pdev->dev, "PowerNV: VF BAR%d: %pR IOV size is bigger than 64M, roundup power2\n", - i, res); - pdn->m64_per_iov = M64_PER_IOV; + /* + * If bigger than quarter of M64 segment size, just round up + * power of two. + * + * Generally, one M64 BAR maps one IOV BAR. To avoid conflict + * with other devices, IOV BAR size is expanded to be + * (total_pe * VF_BAR_size). When VF_BAR_size is half of M64 + * segment size , the expanded size would equal to half of the + * whole M64 space size, which will exhaust the M64 Space and + * limit the system flexibility. This is a design decision to + * set the boundary to quarter of the M64 segment size. + */ + if (total_vf_bar_sz > gate) { mul = roundup_pow_of_two(total_vfs); + dev_info(&pdev->dev, + "VF BAR Total IOV size %llx > %llx, roundup to %d VFs\n", + total_vf_bar_sz, gate, mul); + pdn->m64_single_mode = true; break; } } @@ -2898,20 +2901,31 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) res = &pdev->resource[i + PCI_IOV_RESOURCES]; if (!res->flags || res->parent) continue; - if (!pnv_pci_is_mem_pref_64(res->flags)) { - dev_warn(&pdev->dev, "Skipping expanding VF BAR%d: %pR\n", - i, res); - continue; - } - dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res); size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + /* + * On PHB3, the minimum size alignment of M64 BAR in single + * mode is 32MB. + */ + if (pdn->m64_single_mode && (size < SZ_32M)) + goto truncate_iov; + dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res); res->end = res->start + size * mul - 1; dev_dbg(&pdev->dev, " %pR\n", res); dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)", i, res, mul); } pdn->vfs_expanded = mul; + + return; + +truncate_iov: + /* To save MMIO space, IOV BAR is truncated. */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + res->flags = 0; + res->end = res->start - 1; + } } #endif /* CONFIG_PCI_IOV */ @@ -3125,18 +3139,35 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, int resno) { + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; struct pci_dn *pdn = pci_get_pdn(pdev); - resource_size_t align, iov_align; - - iov_align = resource_size(&pdev->resource[resno]); - if (iov_align) - return iov_align; + resource_size_t align; + /* + * On PowerNV platform, IOV BAR is mapped by M64 BAR to enable the + * SR-IOV. While from hardware perspective, the range mapped by M64 + * BAR should be size aligned. + * + * When IOV BAR is mapped with M64 BAR in Single PE mode, the extra + * powernv-specific hardware restriction is gone. But if just use the + * VF BAR size as the alignment, PF BAR / VF BAR may be allocated with + * in one segment of M64 #15, which introduces the PE conflict between + * PF and VF. Based on this, the minimum alignment of an IOV BAR is + * m64_segsize. + * + * This function returns the total IOV BAR size if M64 BAR is in + * Shared PE mode or just VF BAR size if not. + * If the M64 BAR is in Single PE mode, return the VF BAR size or + * M64 segment size if IOV BAR size is less. + */ align = pci_iov_resource_size(pdev, resno); - if (pdn->vfs_expanded) - return pdn->vfs_expanded * align; + if (!pdn->vfs_expanded) + return align; + if (pdn->m64_single_mode) + return max(align, (resource_size_t)phb->ioda.m64_segsize); - return align; + return pdn->vfs_expanded * align; } #endif /* CONFIG_PCI_IOV */ diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c deleted file mode 100644 index f2bdfea3b68d..000000000000 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ /dev/null @@ -1,271 +0,0 @@ -/* - * Support PCI/PCIe on PowerNV platforms - * - * Currently supports only P5IOC2 - * - * Copyright 2011 Benjamin Herrenschmidt, 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. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/delay.h> -#include <linux/string.h> -#include <linux/init.h> -#include <linux/bootmem.h> -#include <linux/irq.h> -#include <linux/io.h> -#include <linux/msi.h> - -#include <asm/sections.h> -#include <asm/io.h> -#include <asm/prom.h> -#include <asm/pci-bridge.h> -#include <asm/machdep.h> -#include <asm/msi_bitmap.h> -#include <asm/ppc-pci.h> -#include <asm/opal.h> -#include <asm/iommu.h> -#include <asm/tce.h> - -#include "powernv.h" -#include "pci.h" - -/* For now, use a fixed amount of TCE memory for each p5ioc2 - * hub, 16M will do - */ -#define P5IOC2_TCE_MEMORY 0x01000000 - -#ifdef CONFIG_PCI_MSI -static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int virq, - unsigned int is_64, struct msi_msg *msg) -{ - if (WARN_ON(!is_64)) - return -ENXIO; - msg->data = hwirq - phb->msi_base; - msg->address_hi = 0x10000000; - msg->address_lo = 0; - - return 0; -} - -static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) -{ - unsigned int count; - const __be32 *prop = of_get_property(phb->hose->dn, - "ibm,opal-msi-ranges", NULL); - if (!prop) - return; - - /* Don't do MSI's on p5ioc2 PCI-X are they are not properly - * verified in HW - */ - if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix")) - return; - phb->msi_base = be32_to_cpup(prop); - count = be32_to_cpup(prop + 1); - if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { - pr_err("PCI %d: Failed to allocate MSI bitmap !\n", - phb->hose->global_number); - return; - } - phb->msi_setup = pnv_pci_p5ioc2_msi_setup; - phb->msi32_support = 0; - pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - count, phb->msi_base); -} -#else -static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { } -#endif /* CONFIG_PCI_MSI */ - -static struct iommu_table_ops pnv_p5ioc2_iommu_ops = { - .set = pnv_tce_build, -#ifdef CONFIG_IOMMU_API - .exchange = pnv_tce_xchg, -#endif - .clear = pnv_tce_free, - .get = pnv_tce_get, -}; - -static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb, - struct pci_dev *pdev) -{ - struct iommu_table *tbl = phb->p5ioc2.table_group.tables[0]; - - if (!tbl->it_map) { - tbl->it_ops = &pnv_p5ioc2_iommu_ops; - iommu_init_table(tbl, phb->hose->node); - iommu_register_group(&phb->p5ioc2.table_group, - pci_domain_nr(phb->hose->bus), phb->opal_id); - INIT_LIST_HEAD_RCU(&tbl->it_group_list); - pnv_pci_link_table_and_group(phb->hose->node, 0, - tbl, &phb->p5ioc2.table_group); - } - - set_iommu_table_base(&pdev->dev, tbl); - iommu_add_device(&pdev->dev); -} - -static const struct pci_controller_ops pnv_pci_p5ioc2_controller_ops = { - .dma_dev_setup = pnv_pci_dma_dev_setup, -#ifdef CONFIG_PCI_MSI - .setup_msi_irqs = pnv_setup_msi_irqs, - .teardown_msi_irqs = pnv_teardown_msi_irqs, -#endif -}; - -static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, - void *tce_mem, u64 tce_size) -{ - struct pnv_phb *phb; - const __be64 *prop64; - u64 phb_id; - int64_t rc; - static int primary = 1; - struct iommu_table_group *table_group; - struct iommu_table *tbl; - - pr_info(" Initializing p5ioc2 PHB %s\n", np->full_name); - - prop64 = of_get_property(np, "ibm,opal-phbid", NULL); - if (!prop64) { - pr_err(" Missing \"ibm,opal-phbid\" property !\n"); - return; - } - phb_id = be64_to_cpup(prop64); - pr_devel(" PHB-ID : 0x%016llx\n", phb_id); - pr_devel(" TCE AT : 0x%016lx\n", __pa(tce_mem)); - pr_devel(" TCE SZ : 0x%016llx\n", tce_size); - - rc = opal_pci_set_phb_tce_memory(phb_id, __pa(tce_mem), tce_size); - if (rc != OPAL_SUCCESS) { - pr_err(" Failed to set TCE memory, OPAL error %lld\n", rc); - return; - } - - phb = memblock_virt_alloc(sizeof(struct pnv_phb), 0); - phb->hose = pcibios_alloc_controller(np); - if (!phb->hose) { - pr_err(" Failed to allocate PCI controller\n"); - return; - } - - spin_lock_init(&phb->lock); - phb->hose->first_busno = 0; - phb->hose->last_busno = 0xff; - phb->hose->private_data = phb; - phb->hose->controller_ops = pnv_pci_p5ioc2_controller_ops; - phb->hub_id = hub_id; - phb->opal_id = phb_id; - phb->type = PNV_PHB_P5IOC2; - phb->model = PNV_PHB_MODEL_P5IOC2; - - phb->regs = of_iomap(np, 0); - - if (phb->regs == NULL) - pr_err(" Failed to map registers !\n"); - else { - pr_devel(" P_BUID = 0x%08x\n", in_be32(phb->regs + 0x100)); - pr_devel(" P_IOSZ = 0x%08x\n", in_be32(phb->regs + 0x1b0)); - pr_devel(" P_IO_ST = 0x%08x\n", in_be32(phb->regs + 0x1e0)); - pr_devel(" P_MEM1_H = 0x%08x\n", in_be32(phb->regs + 0x1a0)); - pr_devel(" P_MEM1_L = 0x%08x\n", in_be32(phb->regs + 0x190)); - pr_devel(" P_MSZ1_L = 0x%08x\n", in_be32(phb->regs + 0x1c0)); - pr_devel(" P_MEM_ST = 0x%08x\n", in_be32(phb->regs + 0x1d0)); - pr_devel(" P_MEM2_H = 0x%08x\n", in_be32(phb->regs + 0x2c0)); - pr_devel(" P_MEM2_L = 0x%08x\n", in_be32(phb->regs + 0x2b0)); - pr_devel(" P_MSZ2_H = 0x%08x\n", in_be32(phb->regs + 0x2d0)); - pr_devel(" P_MSZ2_L = 0x%08x\n", in_be32(phb->regs + 0x2e0)); - } - - /* Interpret the "ranges" property */ - /* This also maps the I/O region and sets isa_io/mem_base */ - pci_process_bridge_OF_ranges(phb->hose, np, primary); - primary = 0; - - phb->hose->ops = &pnv_pci_ops; - - /* Setup MSI support */ - pnv_pci_init_p5ioc2_msis(phb); - - /* Setup TCEs */ - phb->dma_dev_setup = pnv_pci_p5ioc2_dma_dev_setup; - pnv_pci_setup_iommu_table(&phb->p5ioc2.iommu_table, - tce_mem, tce_size, 0, - IOMMU_PAGE_SHIFT_4K); - /* - * We do not allocate iommu_table as we do not support - * hotplug or SRIOV on P5IOC2 and therefore iommu_free_table() - * should not be called for phb->p5ioc2.table_group.tables[0] ever. - */ - tbl = phb->p5ioc2.table_group.tables[0] = &phb->p5ioc2.iommu_table; - table_group = &phb->p5ioc2.table_group; - table_group->tce32_start = tbl->it_offset << tbl->it_page_shift; - table_group->tce32_size = tbl->it_size << tbl->it_page_shift; -} - -void __init pnv_pci_init_p5ioc2_hub(struct device_node *np) -{ - struct device_node *phbn; - const __be64 *prop64; - u64 hub_id; - void *tce_mem; - uint64_t tce_per_phb; - int64_t rc; - int phb_count = 0; - - pr_info("Probing p5ioc2 IO-Hub %s\n", np->full_name); - - prop64 = of_get_property(np, "ibm,opal-hubid", NULL); - if (!prop64) { - pr_err(" Missing \"ibm,opal-hubid\" property !\n"); - return; - } - hub_id = be64_to_cpup(prop64); - pr_info(" HUB-ID : 0x%016llx\n", hub_id); - - /* Count child PHBs and calculate TCE space per PHB */ - for_each_child_of_node(np, phbn) { - if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") || - of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) - phb_count++; - } - - if (phb_count <= 0) { - pr_info(" No PHBs for Hub %s\n", np->full_name); - return; - } - - tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count); - pr_info(" Allocating %lld MB of TCE memory per PHB\n", - tce_per_phb >> 20); - - /* Currently allocate 16M of TCE memory for every Hub - * - * XXX TODO: Make it chip local if possible - */ - tce_mem = memblock_virt_alloc(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY); - pr_debug(" TCE : 0x%016lx..0x%016lx\n", - __pa(tce_mem), __pa(tce_mem) + P5IOC2_TCE_MEMORY - 1); - rc = opal_pci_set_hub_tce_memory(hub_id, __pa(tce_mem), - P5IOC2_TCE_MEMORY); - if (rc != OPAL_SUCCESS) { - pr_err(" Failed to allocate TCE memory, OPAL error %lld\n", rc); - return; - } - - /* Initialize PHBs */ - for_each_child_of_node(np, phbn) { - if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") || - of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) { - pnv_pci_init_p5ioc2_phb(phbn, hub_id, - tce_mem, tce_per_phb); - tce_mem += tce_per_phb; - } - } -} diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b1ef84a6c9d1..73c8dc2a353f 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -380,10 +380,7 @@ static void pnv_pci_config_check_eeh(struct pci_dn *pdn) */ pe_no = pdn->pe_number; if (pe_no == IODA_INVALID_PE) { - if (phb->type == PNV_PHB_P5IOC2) - pe_no = 0; - else - pe_no = phb->ioda.reserved_pe; + pe_no = phb->ioda.reserved_pe; } /* @@ -805,7 +802,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk); void __init pnv_pci_init(void) { struct device_node *np; - bool found_ioda = false; pci_add_flags(PCI_CAN_SKIP_ISA_ALIGN); @@ -813,20 +809,11 @@ void __init pnv_pci_init(void) if (!firmware_has_feature(FW_FEATURE_OPAL)) return; - /* Look for IODA IO-Hubs. We don't support mixing IODA - * and p5ioc2 due to the need to change some global - * probing flags - */ + /* Look for IODA IO-Hubs. */ for_each_compatible_node(np, NULL, "ibm,ioda-hub") { pnv_pci_init_ioda_hub(np); - found_ioda = true; } - /* Look for p5ioc2 IO-Hubs */ - if (!found_ioda) - for_each_compatible_node(np, NULL, "ibm,p5ioc2") - pnv_pci_init_p5ioc2_hub(np); - /* Look for ioda2 built-in PHB3's */ for_each_compatible_node(np, NULL, "ibm,ioda2-phb") pnv_pci_init_ioda2_phb(np); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 00691a9b99af..3f814f382b2e 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -4,16 +4,14 @@ struct pci_dn; enum pnv_phb_type { - PNV_PHB_P5IOC2 = 0, - PNV_PHB_IODA1 = 1, - PNV_PHB_IODA2 = 2, - PNV_PHB_NPU = 3, + PNV_PHB_IODA1 = 0, + PNV_PHB_IODA2 = 1, + PNV_PHB_NPU = 2, }; /* Precise PHB model for error management */ enum pnv_phb_model { PNV_PHB_MODEL_UNKNOWN, - PNV_PHB_MODEL_P5IOC2, PNV_PHB_MODEL_P7IOC, PNV_PHB_MODEL_PHB3, PNV_PHB_MODEL_NPU, @@ -121,81 +119,74 @@ struct pnv_phb { void (*freeze_pe)(struct pnv_phb *phb, int pe_no); int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt); - union { - struct { - struct iommu_table iommu_table; - struct iommu_table_group table_group; - } p5ioc2; - - struct { - /* Global bridge info */ - unsigned int total_pe; - unsigned int reserved_pe; - - /* 32-bit MMIO window */ - unsigned int m32_size; - unsigned int m32_segsize; - unsigned int m32_pci_base; - - /* 64-bit MMIO window */ - unsigned int m64_bar_idx; - unsigned long m64_size; - unsigned long m64_segsize; - unsigned long m64_base; - unsigned long m64_bar_alloc; - - /* IO ports */ - unsigned int io_size; - unsigned int io_segsize; - unsigned int io_pci_base; - - /* PE allocation bitmap */ - unsigned long *pe_alloc; - /* PE allocation mutex */ - struct mutex pe_alloc_mutex; - - /* M32 & IO segment maps */ - unsigned int *m32_segmap; - unsigned int *io_segmap; - struct pnv_ioda_pe *pe_array; - - /* IRQ chip */ - int irq_chip_init; - struct irq_chip irq_chip; - - /* Sorted list of used PE's based - * on the sequence of creation - */ - struct list_head pe_list; - struct mutex pe_list_mutex; - - /* Reverse map of PEs, will have to extend if - * we are to support more than 256 PEs, indexed - * bus { bus, devfn } - */ - unsigned char pe_rmap[0x10000]; - - /* 32-bit TCE tables allocation */ - unsigned long tce32_count; - - /* Total "weight" for the sake of DMA resources - * allocation - */ - unsigned int dma_weight; - unsigned int dma_pe_count; - - /* Sorted list of used PE's, sorted at - * boot for resource allocation purposes - */ - struct list_head pe_dma_list; - - /* TCE cache invalidate registers (physical and - * remapped) - */ - phys_addr_t tce_inval_reg_phys; - __be64 __iomem *tce_inval_reg; - } ioda; - }; + struct { + /* Global bridge info */ + unsigned int total_pe; + unsigned int reserved_pe; + + /* 32-bit MMIO window */ + unsigned int m32_size; + unsigned int m32_segsize; + unsigned int m32_pci_base; + + /* 64-bit MMIO window */ + unsigned int m64_bar_idx; + unsigned long m64_size; + unsigned long m64_segsize; + unsigned long m64_base; + unsigned long m64_bar_alloc; + + /* IO ports */ + unsigned int io_size; + unsigned int io_segsize; + unsigned int io_pci_base; + + /* PE allocation bitmap */ + unsigned long *pe_alloc; + /* PE allocation mutex */ + struct mutex pe_alloc_mutex; + + /* M32 & IO segment maps */ + unsigned int *m32_segmap; + unsigned int *io_segmap; + struct pnv_ioda_pe *pe_array; + + /* IRQ chip */ + int irq_chip_init; + struct irq_chip irq_chip; + + /* Sorted list of used PE's based + * on the sequence of creation + */ + struct list_head pe_list; + struct mutex pe_list_mutex; + + /* Reverse map of PEs, will have to extend if + * we are to support more than 256 PEs, indexed + * bus { bus, devfn } + */ + unsigned char pe_rmap[0x10000]; + + /* 32-bit TCE tables allocation */ + unsigned long tce32_count; + + /* Total "weight" for the sake of DMA resources + * allocation + */ + unsigned int dma_weight; + unsigned int dma_pe_count; + + /* Sorted list of used PE's, sorted at + * boot for resource allocation purposes + */ + struct list_head pe_dma_list; + + /* TCE cache invalidate registers (physical and + * remapped) + */ + phys_addr_t tce_inval_reg_phys; + __be64 __iomem *tce_inval_reg; + } ioda; /* PHB and hub status structure */ union { @@ -232,7 +223,6 @@ extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, void *tce_mem, u64 tce_size, u64 dma_offset, unsigned page_shift); -extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_init_npu_phb(struct device_node *np); diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c index 503a73f59359..0babef11136f 100644 --- a/arch/powerpc/platforms/powernv/subcore.c +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -407,7 +407,7 @@ static DEVICE_ATTR(subcores_per_core, 0644, static int subcore_init(void) { - if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + if (!cpu_has_feature(CPU_FTR_SUBCORE)) return 0; /* diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 1278788d96e3..436062dbb6e2 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -3,6 +3,7 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror GCOV_PROFILE := n +UBSAN_SANITIZE := n ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 07a8508cb7fa..942796fa4767 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -47,6 +47,9 @@ #include <asm/debug.h> #include <asm/hw_breakpoint.h> +#include <asm/opal.h> +#include <asm/firmware.h> + #ifdef CONFIG_PPC64 #include <asm/hvcall.h> #include <asm/paca.h> @@ -119,6 +122,16 @@ static void dump(void); static void prdump(unsigned long, long); static int ppc_inst_dump(unsigned long, long, int); static void dump_log_buf(void); + +#ifdef CONFIG_PPC_POWERNV +static void dump_opal_msglog(void); +#else +static inline void dump_opal_msglog(void) +{ + printf("Machine is not running OPAL firmware.\n"); +} +#endif + static void backtrace(struct pt_regs *); static void excprint(struct pt_regs *); static void prregs(struct pt_regs *); @@ -150,6 +163,7 @@ static int cpu_cmd(void); static void csum(void); static void bootcmds(void); static void proccall(void); +static void show_tasks(void); void dump_segments(void); static void symbol_lookup(void); static void xmon_show_stack(unsigned long sp, unsigned long lr, @@ -202,6 +216,10 @@ Commands:\n\ df dump float values\n\ dd dump double values\n\ dl dump the kernel log buffer\n" +#ifdef CONFIG_PPC_POWERNV + "\ + do dump the OPAL message log\n" +#endif #ifdef CONFIG_PPC64 "\ dp[#] dump paca for current cpu, or cpu #\n\ @@ -221,6 +239,7 @@ Commands:\n\ mz zero a block of memory\n\ mi show information about memory allocation\n\ p call a procedure\n\ + P list processes/tasks\n\ r print registers\n\ s single step\n" #ifdef CONFIG_SPU_BASE @@ -233,7 +252,7 @@ Commands:\n\ " S print special registers\n\ t print backtrace\n\ x exit monitor and recover\n\ - X exit monitor and dont recover\n" + X exit monitor and don't recover\n" #if defined(CONFIG_PPC64) && !defined(CONFIG_PPC_BOOK3E) " u dump segment table or SLB\n" #elif defined(CONFIG_PPC_STD_MMU_32) @@ -950,6 +969,9 @@ cmds(struct pt_regs *excp) case 'p': proccall(); break; + case 'P': + show_tasks(); + break; #ifdef CONFIG_PPC_STD_MMU case 'u': dump_segments(); @@ -2253,6 +2275,8 @@ dump(void) last_cmd = "di\n"; } else if (c == 'l') { dump_log_buf(); + } else if (c == 'o') { + dump_opal_msglog(); } else if (c == 'r') { scanhex(&ndump); if (ndump == 0) @@ -2395,6 +2419,45 @@ dump_log_buf(void) catch_memory_errors = 0; } +#ifdef CONFIG_PPC_POWERNV +static void dump_opal_msglog(void) +{ + unsigned char buf[128]; + ssize_t res; + loff_t pos = 0; + + if (!firmware_has_feature(FW_FEATURE_OPAL)) { + printf("Machine is not running OPAL firmware.\n"); + return; + } + + if (setjmp(bus_error_jmp) != 0) { + printf("Error dumping OPAL msglog!\n"); + return; + } + + catch_memory_errors = 1; + sync(); + + xmon_start_pagination(); + while ((res = opal_msglog_copy(buf, pos, sizeof(buf) - 1))) { + if (res < 0) { + printf("Error dumping OPAL msglog! Error: %zd\n", res); + break; + } + buf[res] = '\0'; + printf("%s", buf); + pos += res; + } + xmon_end_pagination(); + + sync(); + /* wait a little while to see if we get a machine check */ + __delay(200); + catch_memory_errors = 0; +} +#endif + /* * Memory operations - move, set, print differences */ @@ -2508,6 +2571,61 @@ memzcan(void) printf("%.8x\n", a - mskip); } +static void show_task(struct task_struct *tsk) +{ + char state; + + /* + * Cloned from kdb_task_state_char(), which is not entirely + * appropriate for calling from xmon. This could be moved + * to a common, generic, routine used by both. + */ + state = (tsk->state == 0) ? 'R' : + (tsk->state < 0) ? 'U' : + (tsk->state & TASK_UNINTERRUPTIBLE) ? 'D' : + (tsk->state & TASK_STOPPED) ? 'T' : + (tsk->state & TASK_TRACED) ? 'C' : + (tsk->exit_state & EXIT_ZOMBIE) ? 'Z' : + (tsk->exit_state & EXIT_DEAD) ? 'E' : + (tsk->state & TASK_INTERRUPTIBLE) ? 'S' : '?'; + + printf("%p %016lx %6d %6d %c %2d %s\n", tsk, + tsk->thread.ksp, + tsk->pid, tsk->parent->pid, + state, task_thread_info(tsk)->cpu, + tsk->comm); +} + +static void show_tasks(void) +{ + unsigned long tskv; + struct task_struct *tsk = NULL; + + printf(" task_struct ->thread.ksp PID PPID S P CMD\n"); + + if (scanhex(&tskv)) + tsk = (struct task_struct *)tskv; + + if (setjmp(bus_error_jmp) != 0) { + catch_memory_errors = 0; + printf("*** Error dumping task %p\n", tsk); + return; + } + + catch_memory_errors = 1; + sync(); + + if (tsk) + show_task(tsk); + else + for_each_process(tsk) + show_task(tsk); + + sync(); + __delay(200); + catch_memory_errors = 0; +} + static void proccall(void) { unsigned long args[8]; |
