diff options
| author | Jonathan Corbet <corbet@lwn.net> | 2018-04-28 01:13:20 +0200 |
|---|---|---|
| committer | Jonathan Corbet <corbet@lwn.net> | 2018-04-28 01:13:20 +0200 |
| commit | ccf2b067948a8f90fc3d7990c57283e7e404d004 (patch) | |
| tree | 298e69b6f3e1eef45ac50ba68abe3dd175c4dc8c /arch | |
| parent | docs/admin-guide/mm: convert plain text cross references to hyperlinks (diff) | |
| parent | Linux 4.17-rc2 (diff) | |
| download | linux-ccf2b067948a8f90fc3d7990c57283e7e404d004.tar.xz linux-ccf2b067948a8f90fc3d7990c57283e7e404d004.zip | |
Merge tag 'v4.17-rc2' into docs-next
Merge -rc2 to pick up the changes to
Documentation/core-api/kernel-api.rst that hit mainline via the
networking tree. In their absence, subsequent patches cannot be
applied.
Diffstat (limited to 'arch')
55 files changed, 1226 insertions, 894 deletions
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index ba964da31a25..1cb2749a72bf 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -366,7 +366,7 @@ void force_signal_inject(int signal, int code, unsigned long address) } /* Force signals we don't understand to SIGKILL */ - if (WARN_ON(signal != SIGKILL || + if (WARN_ON(signal != SIGKILL && siginfo_layout(signal, code) != SIL_FAULT)) { signal = SIGKILL; } diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index dabfc1ecda3d..12145874c02b 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -204,7 +204,7 @@ void __init kasan_init(void) clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); kasan_map_populate(kimg_shadow_start, kimg_shadow_end, - pfn_to_nid(virt_to_pfn(lm_alias(_text)))); + early_pfn_to_nid(virt_to_pfn(lm_alias(_text)))); kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, (void *)mod_shadow_start); @@ -224,7 +224,7 @@ void __init kasan_init(void) kasan_map_populate((unsigned long)kasan_mem_to_shadow(start), (unsigned long)kasan_mem_to_shadow(end), - pfn_to_nid(virt_to_pfn(start))); + early_pfn_to_nid(virt_to_pfn(start))); } /* diff --git a/arch/mips/boot/dts/img/boston.dts b/arch/mips/boot/dts/img/boston.dts index 1bd105428f61..65af3f6ba81c 100644 --- a/arch/mips/boot/dts/img/boston.dts +++ b/arch/mips/boot/dts/img/boston.dts @@ -51,6 +51,8 @@ ranges = <0x02000000 0 0x40000000 0x40000000 0 0x40000000>; + bus-range = <0x00 0xff>; + interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pci0_intc 1>, <0 0 0 2 &pci0_intc 2>, @@ -79,6 +81,8 @@ ranges = <0x02000000 0 0x20000000 0x20000000 0 0x20000000>; + bus-range = <0x00 0xff>; + interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pci1_intc 1>, <0 0 0 2 &pci1_intc 2>, @@ -107,6 +111,8 @@ ranges = <0x02000000 0 0x16000000 0x16000000 0 0x100000>; + bus-range = <0x00 0xff>; + interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pci2_intc 1>, <0 0 0 2 &pci2_intc 2>, diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index 0cbf3af37eca..a7d0b836f2f7 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -307,7 +307,7 @@ static inline void iounmap(const volatile void __iomem *addr) #if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_LOONGSON3_ENHANCEMENT) #define war_io_reorder_wmb() wmb() #else -#define war_io_reorder_wmb() do { } while (0) +#define war_io_reorder_wmb() barrier() #endif #define __BUILD_MEMORY_SINGLE(pfx, bwlq, type, irq) \ @@ -377,6 +377,8 @@ static inline type pfx##read##bwlq(const volatile void __iomem *mem) \ BUG(); \ } \ \ + /* prevent prefetching of coherent DMA data prematurely */ \ + rmb(); \ return pfx##ioswab##bwlq(__mem, __val); \ } diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index b71306947290..06629011a434 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -654,6 +654,13 @@ __clear_user(void __user *addr, __kernel_size_t size) { __kernel_size_t res; +#ifdef CONFIG_CPU_MICROMIPS +/* micromips memset / bzero also clobbers t7 & t8 */ +#define bzero_clobbers "$4", "$5", "$6", __UA_t0, __UA_t1, "$15", "$24", "$31" +#else +#define bzero_clobbers "$4", "$5", "$6", __UA_t0, __UA_t1, "$31" +#endif /* CONFIG_CPU_MICROMIPS */ + if (eva_kernel_access()) { __asm__ __volatile__( "move\t$4, %1\n\t" @@ -663,7 +670,7 @@ __clear_user(void __user *addr, __kernel_size_t size) "move\t%0, $6" : "=r" (res) : "r" (addr), "r" (size) - : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + : bzero_clobbers); } else { might_fault(); __asm__ __volatile__( @@ -674,7 +681,7 @@ __clear_user(void __user *addr, __kernel_size_t size) "move\t%0, $6" : "=r" (res) : "r" (addr), "r" (size) - : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + : bzero_clobbers); } return res; diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index a1456664d6c2..f7327979a8f8 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -219,7 +219,7 @@ 1: PTR_ADDIU a0, 1 /* fill bytewise */ R10KCBARRIER(0(ra)) bne t1, a0, 1b - sb a1, -1(a0) + EX(sb, a1, -1(a0), .Lsmall_fixup\@) 2: jr ra /* done */ move a2, zero @@ -252,13 +252,18 @@ PTR_L t0, TI_TASK($28) andi a2, STORMASK LONG_L t0, THREAD_BUADDR(t0) - LONG_ADDU a2, t1 + LONG_ADDU a2, a0 jr ra LONG_SUBU a2, t0 .Llast_fixup\@: jr ra - andi v1, a2, STORMASK + nop + +.Lsmall_fixup\@: + PTR_SUBU a2, t1, a0 + jr ra + PTR_ADDIU a2, 1 .endm diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index eafd06ab59ef..e5de34d00b1a 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -23,7 +23,7 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PA11) += pci-dma.o obj-$(CONFIG_PCI) += pci.o obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_64BIT) += binfmt_elf32.o sys_parisc32.o signal32.o +obj-$(CONFIG_64BIT) += sys_parisc32.o signal32.o obj-$(CONFIG_STACKTRACE)+= stacktrace.o obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 2d4956e97aa9..ee5a67d57aab 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -807,7 +807,8 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev) eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]); /* PCI Command: 0x4 */ - eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]); + eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1] | + PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); /* Check the PCIe link is ready */ eeh_bridge_check_link(edev); diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 79d005445c6c..e734f6e45abc 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -553,12 +553,12 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE lbz r0,HSTATE_HWTHREAD_STATE(r13) cmpwi r0,KVM_HWTHREAD_IN_KERNEL - beq 1f + beq 0f li r0,KVM_HWTHREAD_IN_KERNEL stb r0,HSTATE_HWTHREAD_STATE(r13) /* Order setting hwthread_state vs. testing hwthread_req */ sync - lbz r0,HSTATE_HWTHREAD_REQ(r13) +0: lbz r0,HSTATE_HWTHREAD_REQ(r13) cmpwi r0,0 beq 1f b kvm_start_guest diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 44c30dd38067..b78f142a4148 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -890,6 +890,17 @@ static void __ref init_fallback_flush(void) return; l1d_size = ppc64_caches.l1d.size; + + /* + * If there is no d-cache-size property in the device tree, l1d_size + * could be zero. That leads to the loop in the asm wrapping around to + * 2^64-1, and then walking off the end of the fallback area and + * eventually causing a page fault which is fatal. Just default to + * something vaguely sane. + */ + if (!l1d_size) + l1d_size = (64 * 1024); + limit = min(ppc64_bolted_size(), ppc64_rma_size); /* diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 35f80ab7cbd8..288fe4f0db4e 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -55,7 +55,7 @@ static int patch_alt_instruction(unsigned int *src, unsigned int *dest, unsigned int *target = (unsigned int *)branch_target(src); /* Branch within the section doesn't need translating */ - if (target < alt_start || target >= alt_end) { + if (target < alt_start || target > alt_end) { instr = translate_branch(dest, src); if (!instr) return 1; diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 9033c8194eda..ccc421503363 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -1093,7 +1093,7 @@ static int show_spu_loadavg(struct seq_file *s, void *private) LOAD_INT(c), LOAD_FRAC(c), count_active_contexts(), atomic_read(&nr_spu_contexts), - idr_get_cursor(&task_active_pid_ns(current)->idr)); + idr_get_cursor(&task_active_pid_ns(current)->idr) - 1); return 0; } diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index d22aeb0b69e1..b48454be5b98 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -389,6 +389,10 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc) if (xive_pool_vps == XIVE_INVALID_VP) return; + /* Check if pool VP already active, if it is, pull it */ + if (in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2) & TM_QW2W2_VP) + in_be64(xive_tima + TM_SPC_PULL_POOL_CTX); + /* Enable the pool VP */ vp = xive_pool_vps + cpu; pr_debug("CPU %d setting up pool VP 0x%x\n", cpu, vp); diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild index 9fdff3fe1a42..e63940bb57cd 100644 --- a/arch/s390/Kbuild +++ b/arch/s390/Kbuild @@ -8,3 +8,4 @@ obj-$(CONFIG_APPLDATA_BASE) += appldata/ obj-y += net/ obj-$(CONFIG_PCI) += pci/ obj-$(CONFIG_NUMA) += numa/ +obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 32a0d5b958bf..199ac3e4da1d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -47,10 +47,6 @@ config PGSTE config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y -config KEXEC - def_bool y - select KEXEC_CORE - config AUDIT_ARCH def_bool y @@ -290,12 +286,12 @@ config MARCH_Z13 older machines. config MARCH_Z14 - bool "IBM z14" + bool "IBM z14 ZR1 and z14" select HAVE_MARCH_Z14_FEATURES help - Select this to enable optimizations for IBM z14 (3906 series). - The kernel will be slightly faster but will not work on older - machines. + Select this to enable optimizations for IBM z14 ZR1 and z14 (3907 + and 3906 series). The kernel will be slightly faster but will not + work on older machines. endchoice @@ -525,6 +521,26 @@ source kernel/Kconfig.preempt source kernel/Kconfig.hz +config KEXEC + def_bool y + select KEXEC_CORE + +config KEXEC_FILE + bool "kexec file based system call" + select KEXEC_CORE + select BUILD_BIN2C + depends on CRYPTO + depends on CRYPTO_SHA256 + depends on CRYPTO_SHA256_S390 + help + Enable the kexec file based system call. In contrast to the normal + kexec system call this system call takes file descriptors for the + kernel and initramfs as arguments. + +config ARCH_HAS_KEXEC_PURGATORY + def_bool y + depends on KEXEC_FILE + config ARCH_RANDOM def_bool y prompt "s390 architectural random number generation API" diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index da9dad35c28e..d1fa37fcce83 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -3,12 +3,6 @@ # Makefile for the linux s390-specific parts of the memory manager. # -COMPILE_VERSION := __linux_compile_version_id__`hostname | \ - tr -c '[0-9A-Za-z]' '_'`__`date | \ - tr -c '[0-9A-Za-z]' '_'`_t - -ccflags-y := -DCOMPILE_VERSION=$(COMPILE_VERSION) -gstabs -I. - targets := image targets += bzImage subdir- := compressed diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore index ae06b9b4c02f..2088cc140629 100644 --- a/arch/s390/boot/compressed/.gitignore +++ b/arch/s390/boot/compressed/.gitignore @@ -1,3 +1,4 @@ sizes.h vmlinux vmlinux.lds +vmlinux.bin.full diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/debug_defconfig index 5af8458951cf..6176fe9795ca 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -24,13 +24,13 @@ CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y -CONFIG_CHECKPOINT_RESTORE=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set @@ -59,10 +59,11 @@ CONFIG_CFQ_GROUP_IOSCHED=y CONFIG_DEFAULT_DEADLINE=y CONFIG_LIVEPATCH=y CONFIG_TUNE_ZEC12=y -CONFIG_NR_CPUS=256 +CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_PREEMPT=y CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -305,7 +306,6 @@ CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_NF_TABLES_BRIDGE=m -CONFIG_NET_SCTPPROBE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -364,11 +364,11 @@ CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y +CONFIG_OPENVSWITCH=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -CONFIG_NET_TCPPROBE=m CONFIG_DEVTMPFS=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 @@ -380,9 +380,9 @@ CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_BLK_DEV_RAM_DAX=y CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_RBD=m +CONFIG_BLK_DEV_NVME=m CONFIG_ENCLOSURE_SERVICES=m CONFIG_GENWQE=m CONFIG_RAID_ATTRS=m @@ -461,6 +461,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -474,6 +475,9 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m +CONFIG_DRM=y +CONFIG_DRM_VIRTIO_GPU=y +CONFIG_FRAMEBUFFER_CONSOLE=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m @@ -482,7 +486,9 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m +CONFIG_VIRTIO_INPUT=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -641,6 +647,8 @@ CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_S390_PTDUMP=y +CONFIG_PERSISTENT_KEYRINGS=y +CONFIG_BIG_KEYS=y CONFIG_ENCRYPTED_KEYS=m CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y @@ -649,17 +657,20 @@ CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_INTEGRITY_SIGNATURE=y +CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y +CONFIG_IMA_DEFAULT_HASH_SHA256=y +CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y -CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_USER=m +# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_GCM=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -707,9 +718,8 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y -CONFIG_ASYMMETRIC_KEY_TYPE=y -CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m -CONFIG_X509_CERTIFICATE_PARSER=m +CONFIG_PKCS7_MESSAGE_PARSER=y +CONFIG_SYSTEM_TRUSTED_KEYRING=y CONFIG_CRC7=m CONFIG_CRC8=m CONFIG_RANDOM32_SELFTEST=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig deleted file mode 100644 index d52eafe57ae8..000000000000 --- a/arch/s390/configs/gcov_defconfig +++ /dev/null @@ -1,661 +0,0 @@ -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -CONFIG_AUDIT=y -CONFIG_NO_HZ_IDLE=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_BSD_PROCESS_ACCT=y -CONFIG_BSD_PROCESS_ACCT_V3=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_NUMA_BALANCING_DEFAULT_ENABLED is not set -CONFIG_MEMCG=y -CONFIG_MEMCG_SWAP=y -CONFIG_BLK_CGROUP=y -CONFIG_CFS_BANDWIDTH=y -CONFIG_RT_GROUP_SCHED=y -CONFIG_CGROUP_PIDS=y -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_HUGETLB=y -CONFIG_CPUSETS=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CGROUP_CPUACCT=y -CONFIG_CGROUP_PERF=y -CONFIG_CHECKPOINT_RESTORE=y -CONFIG_NAMESPACES=y -CONFIG_USER_NS=y -CONFIG_SCHED_AUTOGROUP=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -# CONFIG_SYSFS_SYSCALL is not set -CONFIG_BPF_SYSCALL=y -CONFIG_USERFAULTFD=y -# CONFIG_COMPAT_BRK is not set -CONFIG_PROFILING=y -CONFIG_OPROFILE=m -CONFIG_KPROBES=y -CONFIG_JUMP_LABEL=y -CONFIG_GCOV_KERNEL=y -CONFIG_GCOV_PROFILE_ALL=y -CONFIG_MODULES=y -CONFIG_MODULE_FORCE_LOAD=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_BLK_DEV_INTEGRITY=y -CONFIG_BLK_DEV_THROTTLING=y -CONFIG_BLK_WBT=y -CONFIG_BLK_WBT_SQ=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_IBM_PARTITION=y -CONFIG_BSD_DISKLABEL=y -CONFIG_MINIX_SUBPARTITION=y -CONFIG_SOLARIS_X86_PARTITION=y -CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_CFQ_GROUP_IOSCHED=y -CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_TUNE_ZEC12=y -CONFIG_NR_CPUS=512 -CONFIG_NUMA=y -CONFIG_HZ_100=y -CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTREMOVE=y -CONFIG_KSM=y -CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_CLEANCACHE=y -CONFIG_FRONTSWAP=y -CONFIG_MEM_SOFT_DIRTY=y -CONFIG_ZSWAP=y -CONFIG_ZBUD=m -CONFIG_ZSMALLOC=m -CONFIG_ZSMALLOC_STAT=y -CONFIG_DEFERRED_STRUCT_PAGE_INIT=y -CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_PCI=y -CONFIG_HOTPLUG_PCI=y -CONFIG_HOTPLUG_PCI_S390=y -CONFIG_CHSC_SCH=y -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_PACKET_DIAG=m -CONFIG_UNIX=y -CONFIG_UNIX_DIAG=m -CONFIG_XFRM_USER=m -CONFIG_NET_KEY=m -CONFIG_SMC=m -CONFIG_SMC_DIAG=m -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_ROUTE_MULTIPATH=y -CONFIG_IP_ROUTE_VERBOSE=y -CONFIG_NET_IPIP=m -CONFIG_NET_IPGRE_DEMUX=m -CONFIG_NET_IPGRE=m -CONFIG_NET_IPGRE_BROADCAST=y -CONFIG_IP_MROUTE=y -CONFIG_IP_MROUTE_MULTIPLE_TABLES=y -CONFIG_IP_PIMSM_V1=y -CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y -CONFIG_NET_IPVTI=m -CONFIG_INET_AH=m -CONFIG_INET_ESP=m -CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_MODE_TRANSPORT=m -CONFIG_INET_XFRM_MODE_TUNNEL=m -CONFIG_INET_XFRM_MODE_BEET=m -CONFIG_INET_DIAG=m -CONFIG_INET_UDP_DIAG=m -CONFIG_TCP_CONG_ADVANCED=y -CONFIG_TCP_CONG_HSTCP=m -CONFIG_TCP_CONG_HYBLA=m -CONFIG_TCP_CONG_SCALABLE=m -CONFIG_TCP_CONG_LP=m -CONFIG_TCP_CONG_VENO=m -CONFIG_TCP_CONG_YEAH=m -CONFIG_TCP_CONG_ILLINOIS=m -CONFIG_IPV6_ROUTER_PREF=y -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_MODE_TRANSPORT=m -CONFIG_INET6_XFRM_MODE_TUNNEL=m -CONFIG_INET6_XFRM_MODE_BEET=m -CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m -CONFIG_IPV6_VTI=m -CONFIG_IPV6_SIT=m -CONFIG_IPV6_GRE=m -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_SUBTREES=y -CONFIG_NETFILTER=y -CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_SECMARK=y -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CONNTRACK_TIMEOUT=y -CONFIG_NF_CONNTRACK_TIMESTAMP=y -CONFIG_NF_CONNTRACK_AMANDA=m -CONFIG_NF_CONNTRACK_FTP=m -CONFIG_NF_CONNTRACK_H323=m -CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_NETBIOS_NS=m -CONFIG_NF_CONNTRACK_SNMP=m -CONFIG_NF_CONNTRACK_PPTP=m -CONFIG_NF_CONNTRACK_SANE=m -CONFIG_NF_CONNTRACK_SIP=m -CONFIG_NF_CONNTRACK_TFTP=m -CONFIG_NF_CT_NETLINK=m -CONFIG_NF_CT_NETLINK_TIMEOUT=m -CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_CT=m -CONFIG_NFT_COUNTER=m -CONFIG_NFT_LOG=m -CONFIG_NFT_LIMIT=m -CONFIG_NFT_NAT=m -CONFIG_NFT_COMPAT=m -CONFIG_NFT_HASH=m -CONFIG_NETFILTER_XT_SET=m -CONFIG_NETFILTER_XT_TARGET_AUDIT=m -CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m -CONFIG_NETFILTER_XT_TARGET_CONNMARK=m -CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m -CONFIG_NETFILTER_XT_TARGET_CT=m -CONFIG_NETFILTER_XT_TARGET_DSCP=m -CONFIG_NETFILTER_XT_TARGET_HMARK=m -CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m -CONFIG_NETFILTER_XT_TARGET_LOG=m -CONFIG_NETFILTER_XT_TARGET_MARK=m -CONFIG_NETFILTER_XT_TARGET_NFLOG=m -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_TEE=m -CONFIG_NETFILTER_XT_TARGET_TPROXY=m -CONFIG_NETFILTER_XT_TARGET_TRACE=m -CONFIG_NETFILTER_XT_TARGET_SECMARK=m -CONFIG_NETFILTER_XT_TARGET_TCPMSS=m -CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m -CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m -CONFIG_NETFILTER_XT_MATCH_BPF=m -CONFIG_NETFILTER_XT_MATCH_CLUSTER=m -CONFIG_NETFILTER_XT_MATCH_COMMENT=m -CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m -CONFIG_NETFILTER_XT_MATCH_CONNLABEL=m -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m -CONFIG_NETFILTER_XT_MATCH_CONNMARK=m -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -CONFIG_NETFILTER_XT_MATCH_CPU=m -CONFIG_NETFILTER_XT_MATCH_DCCP=m -CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m -CONFIG_NETFILTER_XT_MATCH_DSCP=m -CONFIG_NETFILTER_XT_MATCH_ESP=m -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m -CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_IPRANGE=m -CONFIG_NETFILTER_XT_MATCH_IPVS=m -CONFIG_NETFILTER_XT_MATCH_LENGTH=m -CONFIG_NETFILTER_XT_MATCH_LIMIT=m -CONFIG_NETFILTER_XT_MATCH_MAC=m -CONFIG_NETFILTER_XT_MATCH_MARK=m -CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -CONFIG_NETFILTER_XT_MATCH_NFACCT=m -CONFIG_NETFILTER_XT_MATCH_OSF=m -CONFIG_NETFILTER_XT_MATCH_OWNER=m -CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m -CONFIG_NETFILTER_XT_MATCH_QUOTA=m -CONFIG_NETFILTER_XT_MATCH_RATEEST=m -CONFIG_NETFILTER_XT_MATCH_REALM=m -CONFIG_NETFILTER_XT_MATCH_RECENT=m -CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NETFILTER_XT_MATCH_STATISTIC=m -CONFIG_NETFILTER_XT_MATCH_STRING=m -CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_TIME=m -CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_IP_SET=m -CONFIG_IP_SET_BITMAP_IP=m -CONFIG_IP_SET_BITMAP_IPMAC=m -CONFIG_IP_SET_BITMAP_PORT=m -CONFIG_IP_SET_HASH_IP=m -CONFIG_IP_SET_HASH_IPPORT=m -CONFIG_IP_SET_HASH_IPPORTIP=m -CONFIG_IP_SET_HASH_IPPORTNET=m -CONFIG_IP_SET_HASH_NETPORTNET=m -CONFIG_IP_SET_HASH_NET=m -CONFIG_IP_SET_HASH_NETNET=m -CONFIG_IP_SET_HASH_NETPORT=m -CONFIG_IP_SET_HASH_NETIFACE=m -CONFIG_IP_SET_LIST_SET=m -CONFIG_IP_VS=m -CONFIG_IP_VS_PROTO_TCP=y -CONFIG_IP_VS_PROTO_UDP=y -CONFIG_IP_VS_PROTO_ESP=y -CONFIG_IP_VS_PROTO_AH=y -CONFIG_IP_VS_RR=m -CONFIG_IP_VS_WRR=m -CONFIG_IP_VS_LC=m -CONFIG_IP_VS_WLC=m -CONFIG_IP_VS_LBLC=m -CONFIG_IP_VS_LBLCR=m -CONFIG_IP_VS_DH=m -CONFIG_IP_VS_SH=m -CONFIG_IP_VS_SED=m -CONFIG_IP_VS_NQ=m -CONFIG_IP_VS_FTP=m -CONFIG_IP_VS_PE_SIP=m -CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_TABLES_IPV4=m -CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NF_TABLES_ARP=m -CONFIG_NFT_CHAIN_NAT_IPV4=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_AH=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_RPFILTER=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_TABLES_IPV6=m -CONFIG_NFT_CHAIN_ROUTE_IPV6=m -CONFIG_NFT_CHAIN_NAT_IPV6=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_AH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_MH=m -CONFIG_IP6_NF_MATCH_RPFILTER=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_RAW=m -CONFIG_IP6_NF_SECURITY=m -CONFIG_IP6_NF_NAT=m -CONFIG_IP6_NF_TARGET_MASQUERADE=m -CONFIG_NF_TABLES_BRIDGE=m -CONFIG_NET_SCTPPROBE=m -CONFIG_RDS=m -CONFIG_RDS_RDMA=m -CONFIG_RDS_TCP=m -CONFIG_L2TP=m -CONFIG_L2TP_DEBUGFS=m -CONFIG_L2TP_V3=y -CONFIG_L2TP_IP=m -CONFIG_L2TP_ETH=m -CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -CONFIG_VLAN_8021Q_GVRP=y -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CBQ=m -CONFIG_NET_SCH_HTB=m -CONFIG_NET_SCH_HFSC=m -CONFIG_NET_SCH_PRIO=m -CONFIG_NET_SCH_MULTIQ=m -CONFIG_NET_SCH_RED=m -CONFIG_NET_SCH_SFB=m -CONFIG_NET_SCH_SFQ=m -CONFIG_NET_SCH_TEQL=m -CONFIG_NET_SCH_TBF=m -CONFIG_NET_SCH_GRED=m -CONFIG_NET_SCH_DSMARK=m -CONFIG_NET_SCH_NETEM=m -CONFIG_NET_SCH_DRR=m -CONFIG_NET_SCH_MQPRIO=m -CONFIG_NET_SCH_CHOKE=m -CONFIG_NET_SCH_QFQ=m -CONFIG_NET_SCH_CODEL=m -CONFIG_NET_SCH_FQ_CODEL=m -CONFIG_NET_SCH_INGRESS=m -CONFIG_NET_SCH_PLUG=m -CONFIG_NET_CLS_BASIC=m -CONFIG_NET_CLS_TCINDEX=m -CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_FW=m -CONFIG_NET_CLS_U32=m -CONFIG_CLS_U32_PERF=y -CONFIG_CLS_U32_MARK=y -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_RSVP6=m -CONFIG_NET_CLS_FLOW=m -CONFIG_NET_CLS_CGROUP=y -CONFIG_NET_CLS_BPF=m -CONFIG_NET_CLS_ACT=y -CONFIG_NET_ACT_POLICE=m -CONFIG_NET_ACT_GACT=m -CONFIG_GACT_PROB=y -CONFIG_NET_ACT_MIRRED=m -CONFIG_NET_ACT_IPT=m -CONFIG_NET_ACT_NAT=m -CONFIG_NET_ACT_PEDIT=m -CONFIG_NET_ACT_SIMP=m -CONFIG_NET_ACT_SKBEDIT=m -CONFIG_NET_ACT_CSUM=m -CONFIG_DNS_RESOLVER=y -CONFIG_NETLINK_DIAG=m -CONFIG_CGROUP_NET_PRIO=y -CONFIG_BPF_JIT=y -CONFIG_NET_PKTGEN=m -CONFIG_NET_TCPPROBE=m -CONFIG_DEVTMPFS=y -CONFIG_DMA_CMA=y -CONFIG_CMA_SIZE_MBYTES=0 -CONFIG_CONNECTOR=y -CONFIG_ZRAM=m -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_BLK_DEV_DRBD=m -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_BLK_DEV_RAM_DAX=y -CONFIG_VIRTIO_BLK=y -CONFIG_ENCLOSURE_SERVICES=m -CONFIG_GENWQE=m -CONFIG_RAID_ATTRS=m -CONFIG_SCSI=y -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m -CONFIG_BLK_DEV_SR=m -CONFIG_CHR_DEV_SG=y -CONFIG_CHR_DEV_SCH=m -CONFIG_SCSI_ENCLOSURE=m -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_LOGGING=y -CONFIG_SCSI_SPI_ATTRS=m -CONFIG_SCSI_FC_ATTRS=y -CONFIG_SCSI_SAS_LIBSAS=m -CONFIG_SCSI_SRP_ATTRS=m -CONFIG_ISCSI_TCP=m -CONFIG_SCSI_DEBUG=m -CONFIG_ZFCP=y -CONFIG_SCSI_VIRTIO=m -CONFIG_SCSI_DH=y -CONFIG_SCSI_DH_RDAC=m -CONFIG_SCSI_DH_HP_SW=m -CONFIG_SCSI_DH_EMC=m -CONFIG_SCSI_DH_ALUA=m -CONFIG_SCSI_OSD_INITIATOR=m -CONFIG_SCSI_OSD_ULD=m -CONFIG_MD=y -CONFIG_BLK_DEV_MD=y -CONFIG_MD_LINEAR=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m -CONFIG_BLK_DEV_DM=m -CONFIG_DM_CRYPT=m -CONFIG_DM_SNAPSHOT=m -CONFIG_DM_THIN_PROVISIONING=m -CONFIG_DM_MIRROR=m -CONFIG_DM_LOG_USERSPACE=m -CONFIG_DM_RAID=m -CONFIG_DM_ZERO=m -CONFIG_DM_MULTIPATH=m -CONFIG_DM_MULTIPATH_QL=m -CONFIG_DM_MULTIPATH_ST=m -CONFIG_DM_DELAY=m -CONFIG_DM_UEVENT=y -CONFIG_DM_FLAKEY=m -CONFIG_DM_VERITY=m -CONFIG_DM_SWITCH=m -CONFIG_NETDEVICES=y -CONFIG_BONDING=m -CONFIG_DUMMY=m -CONFIG_EQUALIZER=m -CONFIG_IFB=m -CONFIG_MACVLAN=m -CONFIG_MACVTAP=m -CONFIG_VXLAN=m -CONFIG_TUN=m -CONFIG_VETH=m -CONFIG_VIRTIO_NET=m -CONFIG_NLMON=m -# CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_VENDOR_CHELSIO is not set -# CONFIG_NET_VENDOR_INTEL is not set -# CONFIG_NET_VENDOR_MARVELL is not set -CONFIG_MLX4_EN=m -CONFIG_MLX5_CORE=m -CONFIG_MLX5_CORE_EN=y -# CONFIG_NET_VENDOR_NATSEMI is not set -CONFIG_PPP=m -CONFIG_PPP_BSDCOMP=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPP_MPPE=m -CONFIG_PPPOE=m -CONFIG_PPTP=m -CONFIG_PPPOL2TP=m -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -CONFIG_LEGACY_PTY_COUNT=0 -CONFIG_HW_RANDOM_VIRTIO=m -CONFIG_RAW_DRIVER=m -CONFIG_HANGCHECK_TIMER=m -CONFIG_TN3270_FS=y -# CONFIG_HWMON is not set -CONFIG_WATCHDOG=y -CONFIG_WATCHDOG_NOWAYOUT=y -CONFIG_SOFT_WATCHDOG=m -CONFIG_DIAG288_WATCHDOG=m -# CONFIG_HID is not set -# CONFIG_USB_SUPPORT is not set -CONFIG_INFINIBAND=m -CONFIG_INFINIBAND_USER_ACCESS=m -CONFIG_MLX4_INFINIBAND=m -CONFIG_MLX5_INFINIBAND=m -CONFIG_VFIO=m -CONFIG_VFIO_PCI=m -CONFIG_VIRTIO_BALLOON=m -CONFIG_EXT4_FS=y -CONFIG_EXT4_FS_POSIX_ACL=y -CONFIG_EXT4_FS_SECURITY=y -CONFIG_EXT4_ENCRYPTION=y -CONFIG_JBD2_DEBUG=y -CONFIG_JFS_FS=m -CONFIG_JFS_POSIX_ACL=y -CONFIG_JFS_SECURITY=y -CONFIG_JFS_STATISTICS=y -CONFIG_XFS_FS=y -CONFIG_XFS_QUOTA=y -CONFIG_XFS_POSIX_ACL=y -CONFIG_XFS_RT=y -CONFIG_GFS2_FS=m -CONFIG_GFS2_FS_LOCKING_DLM=y -CONFIG_OCFS2_FS=m -CONFIG_BTRFS_FS=y -CONFIG_BTRFS_FS_POSIX_ACL=y -CONFIG_NILFS2_FS=m -CONFIG_FS_DAX=y -CONFIG_EXPORTFS_BLOCK_OPS=y -CONFIG_FANOTIFY=y -CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y -CONFIG_QUOTA_NETLINK_INTERFACE=y -CONFIG_QFMT_V1=m -CONFIG_QFMT_V2=m -CONFIG_AUTOFS4_FS=m -CONFIG_FUSE_FS=y -CONFIG_CUSE=m -CONFIG_OVERLAY_FS=m -CONFIG_OVERLAY_FS_REDIRECT_DIR=y -CONFIG_FSCACHE=m -CONFIG_CACHEFILES=m -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_UDF_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_NTFS_FS=m -CONFIG_NTFS_RW=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_TMPFS_POSIX_ACL=y -CONFIG_HUGETLBFS=y -CONFIG_CONFIGFS_FS=m -CONFIG_ECRYPT_FS=m -CONFIG_CRAMFS=m -CONFIG_SQUASHFS=m -CONFIG_SQUASHFS_XATTR=y -CONFIG_SQUASHFS_LZO=y -CONFIG_SQUASHFS_XZ=y -CONFIG_ROMFS_FS=m -CONFIG_NFS_FS=m -CONFIG_NFS_V3_ACL=y -CONFIG_NFS_V4=m -CONFIG_NFS_SWAP=y -CONFIG_NFSD=m -CONFIG_NFSD_V3_ACL=y -CONFIG_NFSD_V4=y -CONFIG_NFSD_V4_SECURITY_LABEL=y -CONFIG_CIFS=m -CONFIG_CIFS_STATS=y -CONFIG_CIFS_STATS2=y -CONFIG_CIFS_WEAK_PW_HASH=y -CONFIG_CIFS_UPCALL=y -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -# CONFIG_CIFS_DEBUG is not set -CONFIG_CIFS_DFS_UPCALL=y -CONFIG_NLS_DEFAULT="utf8" -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_UTF8=m -CONFIG_DLM=m -CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_INFO_DWARF4=y -CONFIG_GDB_SCRIPTS=y -# CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_MEMORY_INIT=y -CONFIG_PANIC_ON_OOPS=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_RCU_CPU_STALL_TIMEOUT=60 -CONFIG_LATENCYTOP=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -CONFIG_HIST_TRIGGERS=y -CONFIG_LKDTM=m -CONFIG_PERCPU_TEST=m -CONFIG_ATOMIC64_SELFTEST=y -CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y -CONFIG_PERSISTENT_KEYRINGS=y -CONFIG_BIG_KEYS=y -CONFIG_ENCRYPTED_KEYS=m -CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y -CONFIG_SECURITY_SELINUX=y -CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 -CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_INTEGRITY_SIGNATURE=y -CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y -CONFIG_IMA=y -CONFIG_IMA_WRITE_POLICY=y -CONFIG_IMA_APPRAISE=y -CONFIG_CRYPTO_DH=m -CONFIG_CRYPTO_ECDH=m -CONFIG_CRYPTO_USER=m -# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set -CONFIG_CRYPTO_PCRYPT=m -CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_MCRYPTD=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_CHACHA20POLY1305=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_KEYWRAP=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_RMD128=m -CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_RMD256=m -CONFIG_CRYPTO_RMD320=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_AES_TI=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAMELLIA=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m -CONFIG_CRYPTO_SEED=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_842=m -CONFIG_CRYPTO_LZ4=m -CONFIG_CRYPTO_LZ4HC=m -CONFIG_CRYPTO_ANSI_CPRNG=m -CONFIG_CRYPTO_USER_API_HASH=m -CONFIG_CRYPTO_USER_API_SKCIPHER=m -CONFIG_CRYPTO_USER_API_RNG=m -CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_ZCRYPT=m -CONFIG_PKEY=m -CONFIG_CRYPTO_PAES_S390=m -CONFIG_CRYPTO_SHA1_S390=m -CONFIG_CRYPTO_SHA256_S390=m -CONFIG_CRYPTO_SHA512_S390=m -CONFIG_CRYPTO_DES_S390=m -CONFIG_CRYPTO_AES_S390=m -CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=y -CONFIG_CRC7=m -CONFIG_CRC8=m -CONFIG_CORDIC=m -CONFIG_CMM=m -CONFIG_APPLDATA_BASE=y -CONFIG_KVM=m -CONFIG_KVM_S390_UCONTROL=y -CONFIG_VHOST_NET=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 20ed149e1137..c105bcc6d7a6 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -25,13 +25,13 @@ CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y -CONFIG_CHECKPOINT_RESTORE=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set @@ -45,6 +45,8 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y @@ -62,6 +64,7 @@ CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -301,7 +304,6 @@ CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_NF_TABLES_BRIDGE=m -CONFIG_NET_SCTPPROBE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -359,11 +361,11 @@ CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y +CONFIG_OPENVSWITCH=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -CONFIG_NET_TCPPROBE=m CONFIG_DEVTMPFS=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 @@ -375,8 +377,9 @@ CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_BLK_DEV_RAM_DAX=y CONFIG_VIRTIO_BLK=y +CONFIG_BLK_DEV_RBD=m +CONFIG_BLK_DEV_NVME=m CONFIG_ENCLOSURE_SERVICES=m CONFIG_GENWQE=m CONFIG_RAID_ATTRS=m @@ -455,6 +458,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -468,6 +472,9 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m +CONFIG_DRM=y +CONFIG_DRM_VIRTIO_GPU=y +CONFIG_FRAMEBUFFER_CONSOLE=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m @@ -476,7 +483,9 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m +CONFIG_VIRTIO_INPUT=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -507,7 +516,6 @@ CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m CONFIG_OVERLAY_FS=m -CONFIG_OVERLAY_FS_REDIRECT_DIR=y CONFIG_FSCACHE=m CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y @@ -592,8 +600,10 @@ CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y +CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_USER=m diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 46a3178d8bc6..f40600eb1762 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -8,6 +8,7 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y +# CONFIG_CPU_ISOLATION is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_CGROUPS=y @@ -23,12 +24,12 @@ CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y -CONFIG_CHECKPOINT_RESTORE=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set @@ -47,6 +48,7 @@ CONFIG_LIVEPATCH=y CONFIG_NR_CPUS=256 CONFIG_NUMA=y CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -129,10 +131,13 @@ CONFIG_EQUALIZER=m CONFIG_TUN=m CONFIG_VIRTIO_NET=y # CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_SOLARFLARE is not set +# CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set +# CONFIG_VT is not set CONFIG_DEVKMEM=y CONFIG_RAW_DRIVER=m CONFIG_VIRTIO_BALLOON=y @@ -177,13 +182,15 @@ CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_FUNCTION_PROFILER=y -CONFIG_KPROBES_SANITY_TEST=y +# CONFIG_RUNTIME_TESTING_MENU is not set CONFIG_S390_PTDUMP=y CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m CONFIG_CRYPTO_CBC=y +CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -213,6 +220,8 @@ CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_SM4=m +CONFIG_CRYPTO_SPECK=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 43bbe63e2992..06b513d192b9 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -320,7 +320,7 @@ static void hypfs_kill_super(struct super_block *sb) if (sb->s_root) hypfs_delete_tree(sb->s_root); - if (sb_info->update_file) + if (sb_info && sb_info->update_file) hypfs_remove(sb_info->update_file); kfree(sb->s_fs_info); sb->s_fs_info = NULL; diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index 1d708a419326..825dd0f7f221 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -46,4 +46,27 @@ static inline void crash_setup_regs(struct pt_regs *newregs, struct pt_regs *oldregs) { } +struct kimage; +struct s390_load_data { + /* Pointer to the kernel buffer. Used to register cmdline etc.. */ + void *kernel_buf; + + /* Total size of loaded segments in memory. Used as an offset. */ + size_t memsz; + + /* Load address of initrd. Used to register INITRD_START in kernel. */ + unsigned long initrd_load_addr; +}; + +int kexec_file_add_purgatory(struct kimage *image, + struct s390_load_data *data); +int kexec_file_add_initrd(struct kimage *image, + struct s390_load_data *data, + char *initrd, unsigned long initrd_len); +int *kexec_file_update_kernel(struct kimage *iamge, + struct s390_load_data *data); + +extern const struct kexec_file_ops s390_kexec_image_ops; +extern const struct kexec_file_ops s390_kexec_elf_ops; + #endif /*_S390_KEXEC_H */ diff --git a/arch/s390/include/asm/purgatory.h b/arch/s390/include/asm/purgatory.h new file mode 100644 index 000000000000..e297bcfc476f --- /dev/null +++ b/arch/s390/include/asm/purgatory.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 2018 + * + * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com> + */ + +#ifndef _S390_PURGATORY_H_ +#define _S390_PURGATORY_H_ +#ifndef __ASSEMBLY__ + +#include <linux/purgatory.h> + +int verify_sha256_digest(void); + +#endif /* __ASSEMBLY__ */ +#endif /* _S390_PURGATORY_H_ */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 124154fdfc97..9c30ebe046f3 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * S390 version - * Copyright IBM Corp. 1999, 2010 + * Copyright IBM Corp. 1999, 2017 */ #ifndef _ASM_S390_SETUP_H #define _ASM_S390_SETUP_H @@ -37,17 +37,31 @@ #define LPP_MAGIC _BITUL(31) #define LPP_PID_MASK _AC(0xffffffff, UL) +/* Offsets to entry points in kernel/head.S */ + +#define STARTUP_NORMAL_OFFSET 0x10000 +#define STARTUP_KDUMP_OFFSET 0x10010 + +/* Offsets to parameters in kernel/head.S */ + +#define IPL_DEVICE_OFFSET 0x10400 +#define INITRD_START_OFFSET 0x10408 +#define INITRD_SIZE_OFFSET 0x10410 +#define OLDMEM_BASE_OFFSET 0x10418 +#define OLDMEM_SIZE_OFFSET 0x10420 +#define COMMAND_LINE_OFFSET 0x10480 + #ifndef __ASSEMBLY__ #include <asm/lowcore.h> #include <asm/types.h> -#define IPL_DEVICE (*(unsigned long *) (0x10400)) -#define INITRD_START (*(unsigned long *) (0x10408)) -#define INITRD_SIZE (*(unsigned long *) (0x10410)) -#define OLDMEM_BASE (*(unsigned long *) (0x10418)) -#define OLDMEM_SIZE (*(unsigned long *) (0x10420)) -#define COMMAND_LINE ((char *) (0x10480)) +#define IPL_DEVICE (*(unsigned long *) (IPL_DEVICE_OFFSET)) +#define INITRD_START (*(unsigned long *) (INITRD_START_OFFSET)) +#define INITRD_SIZE (*(unsigned long *) (INITRD_SIZE_OFFSET)) +#define OLDMEM_BASE (*(unsigned long *) (OLDMEM_BASE_OFFSET)) +#define OLDMEM_SIZE (*(unsigned long *) (OLDMEM_SIZE_OFFSET)) +#define COMMAND_LINE ((char *) (COMMAND_LINE_OFFSET)) extern int memory_end_set; extern unsigned long memory_end; @@ -121,12 +135,12 @@ extern void (*_machine_power_off)(void); #else /* __ASSEMBLY__ */ -#define IPL_DEVICE 0x10400 -#define INITRD_START 0x10408 -#define INITRD_SIZE 0x10410 -#define OLDMEM_BASE 0x10418 -#define OLDMEM_SIZE 0x10420 -#define COMMAND_LINE 0x10480 +#define IPL_DEVICE (IPL_DEVICE_OFFSET) +#define INITRD_START (INITRD_START_OFFSET) +#define INITRD_SIZE (INITRD_SIZE_OFFSET) +#define OLDMEM_BASE (OLDMEM_BASE_OFFSET) +#define OLDMEM_SIZE (OLDMEM_SIZE_OFFSET) +#define COMMAND_LINE (COMMAND_LINE_OFFSET) #endif /* __ASSEMBLY__ */ #endif /* _ASM_S390_SETUP_H */ diff --git a/arch/s390/include/uapi/asm/signal.h b/arch/s390/include/uapi/asm/signal.h index c57f9d28d894..9a14a611ed82 100644 --- a/arch/s390/include/uapi/asm/signal.h +++ b/arch/s390/include/uapi/asm/signal.h @@ -97,22 +97,31 @@ typedef unsigned long sigset_t; #include <asm-generic/signal-defs.h> #ifndef __KERNEL__ -/* Here we must cater to libcs that poke about in kernel headers. */ +/* + * There are two system calls in regard to sigaction, sys_rt_sigaction + * and sys_sigaction. Internally the kernel uses the struct old_sigaction + * for the older sys_sigaction system call, and the kernel version of the + * struct sigaction for the newer sys_rt_sigaction. + * + * The uapi definition for struct sigaction has made a strange distinction + * between 31-bit and 64-bit in the past. For 64-bit the uapi structure + * looks like the kernel struct sigaction, but for 31-bit it used to + * look like the kernel struct old_sigaction. That practically made the + * structure unusable for either system call. To get around this problem + * the glibc always had its own definitions for the sigaction structures. + * + * The current struct sigaction uapi definition below is suitable for the + * sys_rt_sigaction system call only. + */ struct sigaction { union { __sighandler_t _sa_handler; void (*_sa_sigaction)(int, struct siginfo *, void *); } _u; -#ifndef __s390x__ /* lovely */ - sigset_t sa_mask; - unsigned long sa_flags; - void (*sa_restorer)(void); -#else /* __s390x__ */ unsigned long sa_flags; void (*sa_restorer)(void); sigset_t sa_mask; -#endif /* __s390x__ */ }; #define sa_handler _u._sa_handler diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index b06a6f79c1ec..84ea6225efb4 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -82,6 +82,9 @@ obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o +obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o + obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o perf_cpum_sf.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index cfe2c45c5180..eb2a5c0443cd 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -10,6 +10,7 @@ #include <linux/kbuild.h> #include <linux/kvm_host.h> #include <linux/sched.h> +#include <linux/purgatory.h> #include <asm/idle.h> #include <asm/vdso.h> #include <asm/pgtable.h> @@ -204,5 +205,9 @@ int main(void) OFFSET(__GMAP_ASCE, gmap, asce); OFFSET(__SIE_PROG0C, kvm_s390_sie_block, prog0c); OFFSET(__SIE_PROG20, kvm_s390_sie_block, prog20); + /* kexec_sha_region */ + OFFSET(__KEXEC_SHA_REGION_START, kexec_sha_region, start); + OFFSET(__KEXEC_SHA_REGION_LEN, kexec_sha_region, len); + DEFINE(__KEXEC_SHA_REGION_SIZE, sizeof(struct kexec_sha_region)); return 0; } diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index 11e9d8b5c1b0..607c5e9fba3d 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -182,3 +182,4 @@ COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb); COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer); COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags); +COMPAT_SYSCALL_WRAP5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags) diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c new file mode 100644 index 000000000000..5a286b012043 --- /dev/null +++ b/arch/s390/kernel/kexec_elf.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ELF loader for kexec_file_load system call. + * + * Copyright IBM Corp. 2018 + * + * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com> + */ + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <asm/setup.h> + +static int kexec_file_add_elf_kernel(struct kimage *image, + struct s390_load_data *data, + char *kernel, unsigned long kernel_len) +{ + struct kexec_buf buf; + const Elf_Ehdr *ehdr; + const Elf_Phdr *phdr; + int i, ret; + + ehdr = (Elf_Ehdr *)kernel; + buf.image = image; + + phdr = (void *)ehdr + ehdr->e_phoff; + for (i = 0; i < ehdr->e_phnum; i++, phdr++) { + if (phdr->p_type != PT_LOAD) + continue; + + buf.buffer = kernel + phdr->p_offset; + buf.bufsz = phdr->p_filesz; + + buf.mem = ALIGN(phdr->p_paddr, phdr->p_align); + buf.memsz = phdr->p_memsz; + + if (phdr->p_paddr == 0) { + data->kernel_buf = buf.buffer; + data->memsz += STARTUP_NORMAL_OFFSET; + + buf.buffer += STARTUP_NORMAL_OFFSET; + buf.bufsz -= STARTUP_NORMAL_OFFSET; + + buf.mem += STARTUP_NORMAL_OFFSET; + buf.memsz -= STARTUP_NORMAL_OFFSET; + } + + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + + ret = kexec_add_buffer(&buf); + if (ret) + return ret; + + data->memsz += buf.memsz; + } + + return 0; +} + +static void *s390_elf_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + struct s390_load_data data = {0}; + const Elf_Ehdr *ehdr; + const Elf_Phdr *phdr; + size_t size; + int i, ret; + + /* image->fobs->probe already checked for valid ELF magic number. */ + ehdr = (Elf_Ehdr *)kernel; + + if (ehdr->e_type != ET_EXEC || + ehdr->e_ident[EI_CLASS] != ELFCLASS64 || + !elf_check_arch(ehdr)) + return ERR_PTR(-EINVAL); + + if (!ehdr->e_phnum || ehdr->e_phentsize != sizeof(Elf_Phdr)) + return ERR_PTR(-EINVAL); + + size = ehdr->e_ehsize + ehdr->e_phoff; + size += ehdr->e_phentsize * ehdr->e_phnum; + if (size > kernel_len) + return ERR_PTR(-EINVAL); + + phdr = (void *)ehdr + ehdr->e_phoff; + size = ALIGN(size, phdr->p_align); + for (i = 0; i < ehdr->e_phnum; i++, phdr++) { + if (phdr->p_type == PT_INTERP) + return ERR_PTR(-EINVAL); + + if (phdr->p_offset > kernel_len) + return ERR_PTR(-EINVAL); + + size += ALIGN(phdr->p_filesz, phdr->p_align); + } + + if (size > kernel_len) + return ERR_PTR(-EINVAL); + + ret = kexec_file_add_elf_kernel(image, &data, kernel, kernel_len); + if (ret) + return ERR_PTR(ret); + + if (!data.memsz) + return ERR_PTR(-EINVAL); + + if (initrd) { + ret = kexec_file_add_initrd(image, &data, initrd, initrd_len); + if (ret) + return ERR_PTR(ret); + } + + ret = kexec_file_add_purgatory(image, &data); + if (ret) + return ERR_PTR(ret); + + return kexec_file_update_kernel(image, &data); +} + +static int s390_elf_probe(const char *buf, unsigned long len) +{ + const Elf_Ehdr *ehdr; + + if (len < sizeof(Elf_Ehdr)) + return -ENOEXEC; + + ehdr = (Elf_Ehdr *)buf; + + /* Only check the ELF magic number here and do proper validity check + * in the loader. Any check here that fails would send the erroneous + * ELF file to the image loader that does not care what it gets. + * (Most likely) causing behavior not intended by the user. + */ + if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0) + return -ENOEXEC; + + return 0; +} + +const struct kexec_file_ops s390_kexec_elf_ops = { + .probe = s390_elf_probe, + .load = s390_elf_load, +}; diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c new file mode 100644 index 000000000000..3800852595e8 --- /dev/null +++ b/arch/s390/kernel/kexec_image.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Image loader for kexec_file_load system call. + * + * Copyright IBM Corp. 2018 + * + * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com> + */ + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <asm/setup.h> + +static int kexec_file_add_image_kernel(struct kimage *image, + struct s390_load_data *data, + char *kernel, unsigned long kernel_len) +{ + struct kexec_buf buf; + int ret; + + buf.image = image; + + buf.buffer = kernel + STARTUP_NORMAL_OFFSET; + buf.bufsz = kernel_len - STARTUP_NORMAL_OFFSET; + + buf.mem = STARTUP_NORMAL_OFFSET; + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + buf.memsz = buf.bufsz; + + ret = kexec_add_buffer(&buf); + + data->kernel_buf = kernel; + data->memsz += buf.memsz + STARTUP_NORMAL_OFFSET; + + return ret; +} + +static void *s390_image_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + struct s390_load_data data = {0}; + int ret; + + ret = kexec_file_add_image_kernel(image, &data, kernel, kernel_len); + if (ret) + return ERR_PTR(ret); + + if (initrd) { + ret = kexec_file_add_initrd(image, &data, initrd, initrd_len); + if (ret) + return ERR_PTR(ret); + } + + ret = kexec_file_add_purgatory(image, &data); + if (ret) + return ERR_PTR(ret); + + return kexec_file_update_kernel(image, &data); +} + +static int s390_image_probe(const char *buf, unsigned long len) +{ + /* Can't reliably tell if an image is valid. Therefore give the + * user whatever he wants. + */ + return 0; +} + +const struct kexec_file_ops s390_kexec_image_ops = { + .probe = s390_image_probe, + .load = s390_image_load, +}; diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c new file mode 100644 index 000000000000..f413f57f8d20 --- /dev/null +++ b/arch/s390/kernel/machine_kexec_file.c @@ -0,0 +1,245 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * s390 code for kexec_file_load system call + * + * Copyright IBM Corp. 2018 + * + * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com> + */ + +#include <linux/elf.h> +#include <linux/kexec.h> +#include <asm/setup.h> + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &s390_kexec_elf_ops, + &s390_kexec_image_ops, + NULL, +}; + +int *kexec_file_update_kernel(struct kimage *image, + struct s390_load_data *data) +{ + unsigned long *loc; + + if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE) + return ERR_PTR(-EINVAL); + + if (image->cmdline_buf_len) + memcpy(data->kernel_buf + COMMAND_LINE_OFFSET, + image->cmdline_buf, image->cmdline_buf_len); + + if (image->type == KEXEC_TYPE_CRASH) { + loc = (unsigned long *)(data->kernel_buf + OLDMEM_BASE_OFFSET); + *loc = crashk_res.start; + + loc = (unsigned long *)(data->kernel_buf + OLDMEM_SIZE_OFFSET); + *loc = crashk_res.end - crashk_res.start + 1; + } + + if (image->initrd_buf) { + loc = (unsigned long *)(data->kernel_buf + INITRD_START_OFFSET); + *loc = data->initrd_load_addr; + + loc = (unsigned long *)(data->kernel_buf + INITRD_SIZE_OFFSET); + *loc = image->initrd_buf_len; + } + + return NULL; +} + +static int kexec_file_update_purgatory(struct kimage *image) +{ + u64 entry, type; + int ret; + + if (image->type == KEXEC_TYPE_CRASH) { + entry = STARTUP_KDUMP_OFFSET; + type = KEXEC_TYPE_CRASH; + } else { + entry = STARTUP_NORMAL_OFFSET; + type = KEXEC_TYPE_DEFAULT; + } + + ret = kexec_purgatory_get_set_symbol(image, "kernel_entry", &entry, + sizeof(entry), false); + if (ret) + return ret; + + ret = kexec_purgatory_get_set_symbol(image, "kernel_type", &type, + sizeof(type), false); + if (ret) + return ret; + + if (image->type == KEXEC_TYPE_CRASH) { + u64 crash_size; + + ret = kexec_purgatory_get_set_symbol(image, "crash_start", + &crashk_res.start, + sizeof(crashk_res.start), + false); + if (ret) + return ret; + + crash_size = crashk_res.end - crashk_res.start + 1; + ret = kexec_purgatory_get_set_symbol(image, "crash_size", + &crash_size, + sizeof(crash_size), + false); + } + return ret; +} + +int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data) +{ + struct kexec_buf buf; + int ret; + + buf.image = image; + + data->memsz = ALIGN(data->memsz, PAGE_SIZE); + buf.mem = data->memsz; + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + + ret = kexec_load_purgatory(image, &buf); + if (ret) + return ret; + + ret = kexec_file_update_purgatory(image); + return ret; +} + +int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data, + char *initrd, unsigned long initrd_len) +{ + struct kexec_buf buf; + int ret; + + buf.image = image; + + buf.buffer = initrd; + buf.bufsz = initrd_len; + + data->memsz = ALIGN(data->memsz, PAGE_SIZE); + buf.mem = data->memsz; + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + buf.memsz = buf.bufsz; + + data->initrd_load_addr = buf.mem; + data->memsz += buf.memsz; + + ret = kexec_add_buffer(&buf); + return ret; +} + +/* + * The kernel is loaded to a fixed location. Turn off kexec_locate_mem_hole + * and provide kbuf->mem by hand. + */ +int arch_kexec_walk_mem(struct kexec_buf *kbuf, + int (*func)(struct resource *, void *)) +{ + return 1; +} + +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab) +{ + Elf_Rela *relas; + int i; + + relas = (void *)pi->ehdr + relsec->sh_offset; + + for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) { + const Elf_Sym *sym; /* symbol to relocate */ + unsigned long addr; /* final location after relocation */ + unsigned long val; /* relocated symbol value */ + void *loc; /* tmp location to modify */ + + sym = (void *)pi->ehdr + symtab->sh_offset; + sym += ELF64_R_SYM(relas[i].r_info); + + if (sym->st_shndx == SHN_UNDEF) + return -ENOEXEC; + + if (sym->st_shndx == SHN_COMMON) + return -ENOEXEC; + + if (sym->st_shndx >= pi->ehdr->e_shnum && + sym->st_shndx != SHN_ABS) + return -ENOEXEC; + + loc = pi->purgatory_buf; + loc += section->sh_offset; + loc += relas[i].r_offset; + + val = sym->st_value; + if (sym->st_shndx != SHN_ABS) + val += pi->sechdrs[sym->st_shndx].sh_addr; + val += relas[i].r_addend; + + addr = section->sh_addr + relas[i].r_offset; + + switch (ELF64_R_TYPE(relas[i].r_info)) { + case R_390_8: /* Direct 8 bit. */ + *(u8 *)loc = val; + break; + case R_390_12: /* Direct 12 bit. */ + *(u16 *)loc &= 0xf000; + *(u16 *)loc |= val & 0xfff; + break; + case R_390_16: /* Direct 16 bit. */ + *(u16 *)loc = val; + break; + case R_390_20: /* Direct 20 bit. */ + *(u32 *)loc &= 0xf00000ff; + *(u32 *)loc |= (val & 0xfff) << 16; /* DL */ + *(u32 *)loc |= (val & 0xff000) >> 4; /* DH */ + break; + case R_390_32: /* Direct 32 bit. */ + *(u32 *)loc = val; + break; + case R_390_64: /* Direct 64 bit. */ + *(u64 *)loc = val; + break; + case R_390_PC16: /* PC relative 16 bit. */ + *(u16 *)loc = (val - addr); + break; + case R_390_PC16DBL: /* PC relative 16 bit shifted by 1. */ + *(u16 *)loc = (val - addr) >> 1; + break; + case R_390_PC32DBL: /* PC relative 32 bit shifted by 1. */ + *(u32 *)loc = (val - addr) >> 1; + break; + case R_390_PC32: /* PC relative 32 bit. */ + *(u32 *)loc = (val - addr); + break; + case R_390_PC64: /* PC relative 64 bit. */ + *(u64 *)loc = (val - addr); + break; + default: + break; + } + } + return 0; +} + +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + /* A kernel must be at least large enough to contain head.S. During + * load memory in head.S will be accessed, e.g. to register the next + * command line. If the next kernel were smaller the current kernel + * will panic at load. + * + * 0x11000 = sizeof(head.S) + */ + if (buf_len < 0x11000) + return -ENOEXEC; + + return kexec_image_probe_default(image, buf, buf_len); +} diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index f236ce8757e8..46d49a11663f 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #include <linux/device.h> +#include <linux/cpu.h> #include <asm/nospec-branch.h> static int __init nobp_setup_early(char *str) diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c index c5bc3f209652..5ee27dc9a10c 100644 --- a/arch/s390/kernel/perf_cpum_cf_events.c +++ b/arch/s390/kernel/perf_cpum_cf_events.c @@ -583,6 +583,7 @@ __init const struct attribute_group **cpumf_cf_event_group(void) model = cpumcf_z13_pmu_event_attr; break; case 0x3906: + case 0x3907: model = cpumcf_z14_pmu_event_attr; break; default: diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index fc3b4aa185cc..d82a9ec64ea9 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -821,6 +821,7 @@ static int __init setup_hwcaps(void) strcpy(elf_platform, "z13"); break; case 0x3906: + case 0x3907: strcpy(elf_platform, "z14"); break; } diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index b38d48464368..8b210ead7956 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -388,3 +388,4 @@ 378 common s390_guarded_storage sys_s390_guarded_storage compat_sys_s390_guarded_storage 379 common statx sys_statx compat_sys_statx 380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi +381 common kexec_file_load sys_kexec_file_load compat_sys_kexec_file_load diff --git a/arch/s390/purgatory/.gitignore b/arch/s390/purgatory/.gitignore new file mode 100644 index 000000000000..e9e66f178a6d --- /dev/null +++ b/arch/s390/purgatory/.gitignore @@ -0,0 +1,2 @@ +kexec-purgatory.c +purgatory.ro diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile new file mode 100644 index 000000000000..e9525bc1b4a6 --- /dev/null +++ b/arch/s390/purgatory/Makefile @@ -0,0 +1,37 @@ +# SPDX-License-Identifier: GPL-2.0 + +OBJECT_FILES_NON_STANDARD := y + +purgatory-y := head.o purgatory.o string.o sha256.o mem.o + +targets += $(purgatory-y) purgatory.ro kexec-purgatory.c +PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) + +$(obj)/sha256.o: $(srctree)/lib/sha256.c + $(call if_changed_rule,cc_o_c) + +$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S + $(call if_changed_rule,as_o_S) + +$(obj)/string.o: $(srctree)/arch/s390/lib/string.c + $(call if_changed_rule,cc_o_c) + +LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib +LDFLAGS_purgatory.ro += -z nodefaultlib +KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes +KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare +KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding +KBUILD_CFLAGS += -c -MD -Os -m64 +KBUILD_CFLAGS += $(call cc-option,-fno-PIE) + +$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE + $(call if_changed,ld) + +CMD_BIN2C = $(objtree)/scripts/basic/bin2c +quiet_cmd_bin2c = BIN2C $@ + cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@ + +$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE + $(call if_changed,bin2c) + +obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += kexec-purgatory.o diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S new file mode 100644 index 000000000000..660c96a05a9b --- /dev/null +++ b/arch/s390/purgatory/head.S @@ -0,0 +1,279 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Purgatory setup code + * + * Copyright IBM Corp. 2018 + * + * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com> + */ + +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/page.h> +#include <asm/sigp.h> + +/* The purgatory is the code running between two kernels. It's main purpose + * is to verify that the next kernel was not corrupted after load and to + * start it. + * + * If the next kernel is a crash kernel there are some peculiarities to + * consider: + * + * First the purgatory is called twice. Once only to verify the + * sha digest. So if the crash kernel got corrupted the old kernel can try + * to trigger a stand-alone dumper. And once to actually load the crash kernel. + * + * Second the purgatory also has to swap the crash memory region with its + * destination at address 0. As the purgatory is part of crash memory this + * requires some finesse. The tactic here is that the purgatory first copies + * itself to the end of the destination and then swaps the rest of the + * memory running from there. + */ + +#define bufsz purgatory_end-stack + +.macro MEMCPY dst,src,len + lgr %r0,\dst + lgr %r1,\len + lgr %r2,\src + lgr %r3,\len + +20: mvcle %r0,%r2,0 + jo 20b +.endm + +.macro MEMSWAP dst,src,buf,len +10: cghi \len,bufsz + jh 11f + lgr %r4,\len + j 12f +11: lghi %r4,bufsz + +12: MEMCPY \buf,\dst,%r4 + MEMCPY \dst,\src,%r4 + MEMCPY \src,\buf,%r4 + + agr \dst,%r4 + agr \src,%r4 + sgr \len,%r4 + + cghi \len,0 + jh 10b +.endm + +.macro START_NEXT_KERNEL base + lg %r4,kernel_entry-\base(%r13) + lg %r5,load_psw_mask-\base(%r13) + ogr %r4,%r5 + stg %r4,0(%r0) + + xgr %r0,%r0 + diag %r0,%r0,0x308 +.endm + +.text +.align PAGE_SIZE +ENTRY(purgatory_start) + /* The purgatory might be called after a diag308 so better set + * architecture and addressing mode. + */ + lhi %r1,1 + sigp %r1,%r0,SIGP_SET_ARCHITECTURE + sam64 + + larl %r5,gprregs + stmg %r6,%r15,0(%r5) + + basr %r13,0 +.base_crash: + + /* Setup stack */ + larl %r15,purgatory_end + aghi %r15,-160 + + /* If the next kernel is KEXEC_TYPE_CRASH the purgatory is called + * directly with a flag passed in %r2 whether the purgatory shall do + * checksum verification only (%r2 = 0 -> verification only). + * + * Check now and preserve over C function call by storing in + * %r10 whith + * 1 -> checksum verification only + * 0 -> load new kernel + */ + lghi %r10,0 + lg %r11,kernel_type-.base_crash(%r13) + cghi %r11,1 /* KEXEC_TYPE_CRASH */ + jne .do_checksum_verification + cghi %r2,0 /* checksum verification only */ + jne .do_checksum_verification + lghi %r10,1 + +.do_checksum_verification: + brasl %r14,verify_sha256_digest + + cghi %r10,1 /* checksum verification only */ + je .return_old_kernel + cghi %r2,0 /* checksum match */ + jne .disabled_wait + + /* If the next kernel is a crash kernel the purgatory has to swap + * the mem regions first. + */ + cghi %r11,1 /* KEXEC_TYPE_CRASH */ + je .start_crash_kernel + + /* start normal kernel */ + START_NEXT_KERNEL .base_crash + +.return_old_kernel: + lmg %r6,%r15,gprregs-.base_crash(%r13) + br %r14 + +.disabled_wait: + lpswe disabled_wait_psw-.base_crash(%r13) + +.start_crash_kernel: + /* Location of purgatory_start in crash memory */ + lgr %r8,%r13 + aghi %r8,-(.base_crash-purgatory_start) + + /* Destination for this code i.e. end of memory to be swapped. */ + lg %r9,crash_size-.base_crash(%r13) + aghi %r9,-(purgatory_end-purgatory_start) + + /* Destination in crash memory, i.e. same as r9 but in crash memory. */ + lg %r10,crash_start-.base_crash(%r13) + agr %r10,%r9 + + /* Buffer location (in crash memory) and size. As the purgatory is + * behind the point of no return it can re-use the stack as buffer. + */ + lghi %r11,bufsz + larl %r12,stack + + MEMCPY %r12,%r9,%r11 /* dst -> (crash) buf */ + MEMCPY %r9,%r8,%r11 /* self -> dst */ + + /* Jump to new location. */ + lgr %r7,%r9 + aghi %r7,.jump_to_dst-purgatory_start + br %r7 + +.jump_to_dst: + basr %r13,0 +.base_dst: + + /* clear buffer */ + MEMCPY %r12,%r10,%r11 /* (crash) buf -> (crash) dst */ + + /* Load new buffer location after jump */ + larl %r7,stack + aghi %r10,stack-purgatory_start + MEMCPY %r10,%r7,%r11 /* (new) buf -> (crash) buf */ + + /* Now the code is set up to run from its designated location. Start + * swapping the rest of crash memory now. + * + * The registers will be used as follow: + * + * %r0-%r4 reserved for macros defined above + * %r5-%r6 tmp registers + * %r7 pointer to current struct sha region + * %r8 index to iterate over all sha regions + * %r9 pointer in crash memory + * %r10 pointer in old kernel + * %r11 total size (still) to be moved + * %r12 pointer to buffer + */ + lgr %r12,%r7 + lgr %r11,%r9 + lghi %r10,0 + lg %r9,crash_start-.base_dst(%r13) + lghi %r8,16 /* KEXEC_SEGMENTS_MAX */ + larl %r7,purgatory_sha_regions + + j .loop_first + + /* Loop over all purgatory_sha_regions. */ +.loop_next: + aghi %r8,-1 + cghi %r8,0 + je .loop_out + + aghi %r7,__KEXEC_SHA_REGION_SIZE + +.loop_first: + lg %r5,__KEXEC_SHA_REGION_START(%r7) + cghi %r5,0 + je .loop_next + + /* Copy [end last sha region, start current sha region) */ + /* Note: kexec_sha_region->start points in crash memory */ + sgr %r5,%r9 + MEMCPY %r9,%r10,%r5 + + agr %r9,%r5 + agr %r10,%r5 + sgr %r11,%r5 + + /* Swap sha region */ + lg %r6,__KEXEC_SHA_REGION_LEN(%r7) + MEMSWAP %r9,%r10,%r12,%r6 + sg %r11,__KEXEC_SHA_REGION_LEN(%r7) + j .loop_next + +.loop_out: + /* Copy rest of crash memory */ + MEMCPY %r9,%r10,%r11 + + /* start crash kernel */ + START_NEXT_KERNEL .base_dst + + +load_psw_mask: + .long 0x00080000,0x80000000 + + .align 8 +disabled_wait_psw: + .quad 0x0002000180000000 + .quad 0x0000000000000000 + .do_checksum_verification + +gprregs: + .rept 10 + .quad 0 + .endr + +purgatory_sha256_digest: + .global purgatory_sha256_digest + .rept 32 /* SHA256_DIGEST_SIZE */ + .byte 0 + .endr + +purgatory_sha_regions: + .global purgatory_sha_regions + .rept 16 * __KEXEC_SHA_REGION_SIZE /* KEXEC_SEGMENTS_MAX */ + .byte 0 + .endr + +kernel_entry: + .global kernel_entry + .quad 0 + +kernel_type: + .global kernel_type + .quad 0 + +crash_start: + .global crash_start + .quad 0 + +crash_size: + .global crash_size + .quad 0 + + .align PAGE_SIZE +stack: + /* The buffer to move this code must be as big as the code. */ + .skip stack-purgatory_start + .align PAGE_SIZE +purgatory_end: diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c new file mode 100644 index 000000000000..4e2beb3c29b7 --- /dev/null +++ b/arch/s390/purgatory/purgatory.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Purgatory code running between two kernels. + * + * Copyright IBM Corp. 2018 + * + * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com> + */ + +#include <linux/kexec.h> +#include <linux/sha256.h> +#include <linux/string.h> +#include <asm/purgatory.h> + +struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX]; +u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE]; + +u64 kernel_entry; +u64 kernel_type; + +u64 crash_start; +u64 crash_size; + +int verify_sha256_digest(void) +{ + struct kexec_sha_region *ptr, *end; + u8 digest[SHA256_DIGEST_SIZE]; + struct sha256_state sctx; + + sha256_init(&sctx); + end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions); + + for (ptr = purgatory_sha_regions; ptr < end; ptr++) + sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len); + + sha256_final(&sctx, digest); + + if (memcmp(digest, purgatory_sha256_digest, sizeof(digest))) + return 1; + + return 0; +} diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index c98b943e58b4..77076a102e34 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3028,10 +3028,27 @@ static struct intel_uncore_type bdx_uncore_cbox = { .format_group = &hswep_uncore_cbox_format_group, }; +static struct intel_uncore_type bdx_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &hswep_uncore_sbox_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + +#define BDX_MSR_UNCORE_SBOX 3 + static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, &hswep_uncore_pcu, + &bdx_uncore_sbox, NULL, }; @@ -3043,10 +3060,25 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { void bdx_uncore_cpu_init(void) { + int pkg = topology_phys_to_logical_pkg(0); + if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; uncore_msr_uncores = bdx_msr_uncores; + /* BDX-DE doesn't have SBOX */ + if (boot_cpu_data.x86_model == 86) { + uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; + /* Detect systems with no SBOXes */ + } else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) { + struct pci_dev *pdev; + u32 capid4; + + pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]; + pci_read_config_dword(pdev, 0x94, &capid4); + if (((capid4 >> 6) & 0x3) == 0) + bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; + } hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints; } @@ -3264,6 +3296,11 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), }, + { /* PCU.3 (for Capability registers) */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + HSWEP_PCI_PCU_3), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 386a6900e206..219faaec51df 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -136,7 +136,6 @@ #endif #ifndef __ASSEMBLY__ -#ifndef __BPF__ /* * This output constraint should be used for any inline asm which has a "call" * instruction. Otherwise the asm may be inserted before the frame pointer @@ -146,6 +145,5 @@ register unsigned long current_stack_pointer asm(_ASM_SP); #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) #endif -#endif #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 949c977bc4c9..c25775fad4ed 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1013,6 +1013,7 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); + u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4fa4206029e3..21a114914ba4 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -749,13 +749,11 @@ enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, extern void enable_sep_cpu(void); extern int sysenter_setup(void); -extern void early_trap_init(void); void early_trap_pf_init(void); /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; -extern void cpu_set_gdt(int); extern void switch_to_new_gdt(int); extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index dde444f932c1..3b20607d581b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -215,6 +215,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) apic_id = processor->local_apic_id; enabled = processor->lapic_flags & ACPI_MADT_ENABLED; + /* Ignore invalid ID */ + if (apic_id == 0xffffffff) + return 0; + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 3182908b7e6c..7326078eaa7a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -398,11 +398,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * little bit simple */ efi_map_sz = efi_get_runtime_map_size(); - efi_map_sz = ALIGN(efi_map_sz, 16); params_cmdline_sz = sizeof(struct boot_params) + cmdline_len + MAX_ELFCOREHDR_STR_LEN; params_cmdline_sz = ALIGN(params_cmdline_sz, 16); - kbuf.bufsz = params_cmdline_sz + efi_map_sz + + kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) + sizeof(struct setup_data) + sizeof(struct efi_setup_data); @@ -410,7 +409,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, if (!params) return ERR_PTR(-ENOMEM); efi_map_offset = params_cmdline_sz; - efi_setup_data_offset = efi_map_offset + efi_map_sz; + efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16); /* Copy setup header onto bootparams. Documentation/x86/boot.txt */ setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index d41d896481b8..c9b14020f4dd 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -166,7 +166,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) */ pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL); /* Filter out unsuppored __PAGE_KERNEL* bits: */ - pgprot_val(pte_prot) |= __supported_pte_mask; + pgprot_val(pte_prot) &= __supported_pte_mask; pte = pfn_pte(pfn, pte_prot); set_pte_at(mm, va, ptep, pte); pte_unmap_unlock(ptep, ptl); diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c deleted file mode 100644 index ac7ea3a8242f..000000000000 --- a/arch/x86/kernel/pci-nommu.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Fallback functions when the main IOMMU code is not compiled in. This - code is roughly equivalent to i386. */ -#include <linux/dma-direct.h> -#include <linux/scatterlist.h> -#include <linux/string.h> -#include <linux/gfp.h> -#include <linux/pci.h> -#include <linux/mm.h> - -#include <asm/processor.h> -#include <asm/iommu.h> -#include <asm/dma.h> - -#define NOMMU_MAPPING_ERROR 0 - -static int -check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) -{ - if (hwdev && !dma_capable(hwdev, bus, size)) { - if (*hwdev->dma_mask >= DMA_BIT_MASK(32)) - printk(KERN_ERR - "nommu_%s: overflow %Lx+%zu of device mask %Lx\n", - name, (long long)bus, size, - (long long)*hwdev->dma_mask); - return 0; - } - return 1; -} - -static dma_addr_t nommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset; - WARN_ON(size == 0); - if (!check_addr("map_single", dev, bus, size)) - return NOMMU_MAPPING_ERROR; - return bus; -} - -/* Map a set of buffers described by scatterlist in streaming - * mode for DMA. This is the scatter-gather version of the - * above pci_map_single interface. Here the scatter gather list - * elements are each tagged with the appropriate dma address - * and length. They are obtained via sg_dma_{address,length}(SG). - * - * NOTE: An implementation may be able to use a smaller number of - * DMA address/length pairs than there are SG table elements. - * (for example via virtual mapping capabilities) - * The routine returns the number of addr/length pairs actually - * used, at most nents. - * - * Device ownership issues as mentioned above for pci_map_single are - * the same here. - */ -static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s; - int i; - - WARN_ON(nents == 0 || sg[0].length == 0); - - for_each_sg(sg, s, nents, i) { - BUG_ON(!sg_page(s)); - s->dma_address = sg_phys(s); - if (!check_addr("map_sg", hwdev, s->dma_address, s->length)) - return 0; - s->dma_length = s->length; - } - return nents; -} - -static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return dma_addr == NOMMU_MAPPING_ERROR; -} - -const struct dma_map_ops nommu_dma_ops = { - .alloc = dma_generic_alloc_coherent, - .free = dma_generic_free_coherent, - .map_sg = nommu_map_sg, - .map_page = nommu_map_page, - .is_phys = 1, - .mapping_error = nommu_mapping_error, - .dma_supported = x86_dma_supported, -}; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ff99e2b6fc54..45175b81dd5b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,6 +77,8 @@ #include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -390,15 +392,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } +/* + * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs. + * + * These are Intel CPUs that enumerate an LLC that is shared by + * multiple NUMA nodes. The LLC on these systems is shared for + * off-package data access but private to the NUMA node (half + * of the package) for on-package access. + * + * CPUID (the source of the information about the LLC) can only + * enumerate the cache as being shared *or* unshared, but not + * this particular configuration. The CPU in this case enumerates + * the cache to be shared across the entire package (spanning both + * NUMA nodes). + */ + +static const struct x86_cpu_id snc_cpu[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X }, + {} +}; + static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) - return topology_sane(c, o, "llc"); + /* Do not match if we do not have a valid APICID for cpu: */ + if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID) + return false; - return false; + /* Do not match if LLC id does not match: */ + if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2)) + return false; + + /* + * Allow the SNC topology without warning. Return of false + * means 'c' does not share the LLC of 'o'. This will be + * reflected to userspace. + */ + if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu)) + return false; + + return topology_sane(c, o, "llc"); } /* @@ -456,7 +490,8 @@ static struct sched_domain_topology_level x86_topology[] = { /* * Set if a package/die has multiple NUMA nodes inside. - * AMD Magny-Cours and Intel Cluster-on-Die have this. + * AMD Magny-Cours, Intel Cluster-on-Die, and Intel + * Sub-NUMA Clustering have this. */ static bool x86_has_numa_in_package; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index ef32297ff17e..91e6da48cbb6 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -317,7 +317,7 @@ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2) hpet2 -= hpet1; tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); do_div(tmp, 1000000); - do_div(deltatsc, tmp); + deltatsc = div64_u64(deltatsc, tmp); return (unsigned long) deltatsc; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b58787daf9f8..1fc05e428aba 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1423,12 +1423,23 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } +static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_guest_mode(vcpu)) + return svm->nested.hsave->control.tsc_offset; + + return vcpu->arch.tsc_offset; +} + static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); u64 g_tsc_offset = 0; if (is_guest_mode(vcpu)) { + /* Write L1's TSC offset. */ g_tsc_offset = svm->vmcb->control.tsc_offset - svm->nested.hsave->control.tsc_offset; svm->nested.hsave->control.tsc_offset = offset; @@ -3322,6 +3333,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) /* Restore the original control entries */ copy_vmcb_control_area(vmcb, hsave); + svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset; kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); @@ -3482,10 +3494,12 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, /* We don't want to see VMMCALLs from a nested guest */ clr_intercept(svm, INTERCEPT_VMMCALL); + svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset; + svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset; + svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext; svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; - svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; @@ -4035,12 +4049,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) struct vcpu_svm *svm = to_svm(vcpu); switch (msr_info->index) { - case MSR_IA32_TSC: { - msr_info->data = svm->vmcb->control.tsc_offset + - kvm_scale_tsc(vcpu, rdtsc()); - - break; - } case MSR_STAR: msr_info->data = svm->vmcb->save.star; break; @@ -4193,9 +4201,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->vmcb->save.g_pat = data; mark_dirty(svm->vmcb, VMCB_NPT); break; - case MSR_IA32_TSC: - kvm_write_tsc(vcpu, msr); - break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) @@ -5265,9 +5270,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, } if (!ret && svm) { - trace_kvm_pi_irte_update(svm->vcpu.vcpu_id, - host_irq, e->gsi, - vcpu_info.vector, + trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id, + e->gsi, vcpu_info.vector, vcpu_info.pi_desc_addr, set); } @@ -7102,6 +7106,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .has_wbinvd_exit = svm_has_wbinvd_exit, + .read_l1_tsc_offset = svm_read_l1_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index aafcc9881e88..aa66ccd6ed6c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2880,18 +2880,15 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx_update_msr_bitmap(&vmx->vcpu); } -/* - * reads and returns guest's timestamp counter "register" - * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset - * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3 - */ -static u64 guest_read_tsc(struct kvm_vcpu *vcpu) +static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) { - u64 host_tsc, tsc_offset; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - host_tsc = rdtsc(); - tsc_offset = vmcs_read64(TSC_OFFSET); - return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset; + if (is_guest_mode(vcpu) && + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + return vcpu->arch.tsc_offset - vmcs12->tsc_offset; + + return vcpu->arch.tsc_offset; } /* @@ -3524,9 +3521,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); - case MSR_IA32_TSC: - msr_info->data = guest_read_tsc(vcpu); - break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && @@ -3646,9 +3640,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vmcs_write64(GUEST_BNDCFGS, data); break; - case MSR_IA32_TSC: - kvm_write_tsc(vcpu, msr_info); - break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && @@ -10608,6 +10599,16 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, return true; } +static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && + !page_address_valid(vcpu, vmcs12->apic_access_addr)) + return -EINVAL; + else + return 0; +} + static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -11176,11 +11177,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); } - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) - vmcs_write64(TSC_OFFSET, - vcpu->arch.tsc_offset + vmcs12->tsc_offset); - else - vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -11299,6 +11297,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_apic_access_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; @@ -11420,6 +11421,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); u32 msr_entry_idx; u32 exit_qual; + int r; enter_guest_mode(vcpu); @@ -11429,26 +11431,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); - if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { - leave_guest_mode(vcpu); - vmx_switch_vmcs(vcpu, &vmx->vmcs01); - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, exit_qual); - return 1; - } + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + vcpu->arch.tsc_offset += vmcs12->tsc_offset; + + r = EXIT_REASON_INVALID_STATE; + if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) + goto fail; nested_get_vmcs12_pages(vcpu, vmcs12); + r = EXIT_REASON_MSR_LOAD_FAIL; msr_entry_idx = nested_vmx_load_msr(vcpu, vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count); - if (msr_entry_idx) { - leave_guest_mode(vcpu); - vmx_switch_vmcs(vcpu, &vmx->vmcs01); - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx); - return 1; - } + if (msr_entry_idx) + goto fail; /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point @@ -11457,6 +11454,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) * the success flag) when L2 exits (see nested_vmx_vmexit()). */ return 0; + +fail: + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + vcpu->arch.tsc_offset -= vmcs12->tsc_offset; + leave_guest_mode(vcpu); + vmx_switch_vmcs(vcpu, &vmx->vmcs01); + nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual); + return 1; } /* @@ -12028,6 +12033,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, leave_guest_mode(vcpu); + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + vcpu->arch.tsc_offset -= vmcs12->tsc_offset; + if (likely(!vmx->fail)) { if (exit_reason == -1) sync_vmcs12(vcpu, vmcs12); @@ -12224,10 +12232,16 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift, static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 tscl = rdtsc(); - u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl); - u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; + struct vcpu_vmx *vmx; + u64 tscl, guest_tscl, delta_tsc; + + if (kvm_mwait_in_guest(vcpu->kvm)) + return -EOPNOTSUPP; + + vmx = to_vmx(vcpu); + tscl = rdtsc(); + guest_tscl = kvm_read_l1_tsc(vcpu, tscl); + delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; /* Convert to host delta tsc if tsc scaling is enabled */ if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && @@ -12533,7 +12547,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); vcpu_info.vector = irq.vector; - trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi, + trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi, vcpu_info.vector, vcpu_info.pi_desc_addr, set); if (set) @@ -12712,6 +12726,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, + .read_l1_tsc_offset = vmx_read_l1_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b2ff74b12ec4..51ecd381793b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1490,7 +1490,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) { - u64 curr_offset = vcpu->arch.tsc_offset; + u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } @@ -1532,7 +1532,9 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc); + u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + + return tsc_offset + kvm_scale_tsc(vcpu, host_tsc); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); @@ -2362,6 +2364,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.smbase = data; break; + case MSR_IA32_TSC: + kvm_write_tsc(vcpu, msr_info); + break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) return 1; @@ -2605,6 +2610,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; + case MSR_IA32_TSC: + msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; + break; case MSR_MTRRcap: case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); @@ -2819,7 +2827,8 @@ out: static inline bool kvm_can_mwait_in_guest(void) { return boot_cpu_has(X86_FEATURE_MWAIT) && - !boot_cpu_has_bug(X86_BUG_MONITOR); + !boot_cpu_has_bug(X86_BUG_MONITOR) && + boot_cpu_has(X86_FEATURE_ARAT); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 62a7e9f65dec..cc7ff5957194 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/sched.h> #include <linux/seq_file.h> +#include <linux/highmem.h> #include <asm/pgtable.h> @@ -334,16 +335,16 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, pgprotval_t eff_in, unsigned long P) { int i; - pte_t *start; + pte_t *pte; pgprotval_t prot, eff; - start = (pte_t *)pmd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PTE; i++) { - prot = pte_flags(*start); - eff = effective_prot(eff_in, prot); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); + pte = pte_offset_map(&addr, st->current_address); + prot = pte_flags(*pte); + eff = effective_prot(eff_in, prot); note_page(m, st, __pgprot(prot), eff, 5); - start++; + pte_unmap(pte); } } #ifdef CONFIG_KASAN diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 48b14b534897..ccf4a49bb065 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -98,7 +98,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) set_pgd(pgd + pgd_index(restore_jump_address), new_pgd); } else { /* No p4d for 4-level paging: point the pgd to the pud page table */ - pgd_t new_pgd = __pgd(__pa(p4d) | pgprot_val(pgtable_prot)); + pgd_t new_pgd = __pgd(__pa(pud) | pgprot_val(pgtable_prot)); set_pgd(pgd + pgd_index(restore_jump_address), new_pgd); } |