diff options
Diffstat (limited to 'arch/s390')
45 files changed, 436 insertions, 376 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bf680c26a33c..c4145672ca34 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -49,6 +49,13 @@ config KASAN_SHADOW_OFFSET depends on KASAN default 0x1C000000000000 +config CC_HAS_BUILTIN_FFS + def_bool !(CC_IS_GCC && GCC_VERSION < 160000) + help + GCC versions before 16.0.0 generate library calls to ffs() + for __builtin_ffs() even when __has_builtin(__builtin_ffs) + is true. + config CC_ASM_FLAG_OUTPUT_BROKEN def_bool CC_IS_GCC && GCC_VERSION < 140200 help @@ -167,8 +174,6 @@ config S390 select GENERIC_GETTIMEOFDAY select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL - select GENERIC_VDSO_DATA_STORE - select GENERIC_VDSO_TIME_NS select GENERIC_IOREMAP if PCI select HAVE_ALIGNED_STRUCT_PAGE select HAVE_ARCH_AUDITSYSCALL @@ -199,6 +204,7 @@ config S390 select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_GENERIC_TIF_BITS select HAVE_GUP_FAST select HAVE_FENTRY select HAVE_FTRACE_GRAPH_FUNC @@ -547,15 +553,11 @@ config NODES_SHIFT depends on NUMA default "1" -config SCHED_SMT - def_bool n - -config SCHED_MC - def_bool n - config SCHED_TOPOLOGY def_bool y prompt "Topology scheduler support" + select ARCH_SUPPORTS_SCHED_SMT + select ARCH_SUPPORTS_SCHED_MC select SCHED_SMT select SCHED_MC help @@ -710,7 +712,6 @@ menu "Memory setup" config ARCH_SPARSEMEM_ENABLE def_bool y select SPARSEMEM_VMEMMAP_ENABLE - select SPARSEMEM_VMEMMAP config ARCH_SPARSEMEM_DEFAULT def_bool y diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index c0152db285f0..37d5b097ede5 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -10,6 +10,7 @@ #include <linux/printk.h> #include <asm/physmem_info.h> +#include <asm/stacktrace.h> struct vmlinux_info { unsigned long entry; @@ -89,6 +90,13 @@ void __noreturn jump_to_kernel(psw_t *psw); #define boot_info(fmt, ...) boot_printk(KERN_INFO boot_fmt(fmt), ##__VA_ARGS__) #define boot_debug(fmt, ...) boot_printk(KERN_DEBUG boot_fmt(fmt), ##__VA_ARGS__) +#define boot_panic(...) do { \ + boot_emerg(__VA_ARGS__); \ + print_stacktrace(current_frame_address()); \ + boot_emerg(" -- System halted\n"); \ + disabled_wait(); \ +} while (0) + extern struct machine_info machine; extern int boot_console_loglevel; extern bool boot_ignore_loglevel; diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c index 03500b9d9fb9..8d1bc25a6bf4 100644 --- a/arch/s390/boot/decompressor.c +++ b/arch/s390/boot/decompressor.c @@ -68,9 +68,7 @@ static void decompress_error(char *m) { if (bootdebug) boot_rb_dump(); - boot_emerg("Decompression error: %s\n", m); - boot_emerg(" -- System halted\n"); - disabled_wait(); + boot_panic("Decompression error: %s\n", m); } unsigned long mem_safe_offset(void) diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c index 45e3d057cfaa..1f2ca5435838 100644 --- a/arch/s390/boot/physmem_info.c +++ b/arch/s390/boot/physmem_info.c @@ -228,9 +228,7 @@ static void die_oom(unsigned long size, unsigned long align, unsigned long min, boot_emerg("Usable online memory total: %lu Reserved: %lu Free: %lu\n", total_mem, total_reserved_mem, total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0); - print_stacktrace(current_frame_address()); - boot_emerg(" -- System halted\n"); - disabled_wait(); + boot_panic("Oom\n"); } static void _physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 93684a775716..3fbd25b9498f 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -44,13 +44,6 @@ u64 __bootdata_preserved(clock_comparator_max) = -1UL; u64 __bootdata_preserved(stfle_fac_list[16]); struct oldmem_data __bootdata_preserved(oldmem_data); -void error(char *x) -{ - boot_emerg("%s\n", x); - boot_emerg(" -- System halted\n"); - disabled_wait(); -} - static char sysinfo_page[PAGE_SIZE] __aligned(PAGE_SIZE); static void detect_machine_type(void) @@ -220,10 +213,10 @@ static void rescue_initrd(unsigned long min, unsigned long max) static void copy_bootdata(void) { if (__boot_data_end - __boot_data_start != vmlinux.bootdata_size) - error(".boot.data section size mismatch"); + boot_panic(".boot.data section size mismatch\n"); memcpy((void *)vmlinux.bootdata_off, __boot_data_start, vmlinux.bootdata_size); if (__boot_data_preserved_end - __boot_data_preserved_start != vmlinux.bootdata_preserved_size) - error(".boot.preserved.data section size mismatch"); + boot_panic(".boot.preserved.data section size mismatch\n"); memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size); } @@ -237,7 +230,7 @@ static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, for (reloc = (int *)__vmlinux_relocs_64_start; reloc < (int *)__vmlinux_relocs_64_end; reloc++) { loc = (long)*reloc + phys_offset; if (loc < min_addr || loc > max_addr) - error("64-bit relocation outside of kernel!\n"); + boot_panic("64-bit relocation outside of kernel!\n"); *(u64 *)loc += offset; } } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 1d073acd05a7..cea3de4dce8c 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -530,6 +530,9 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l lowcore_address + sizeof(struct lowcore), POPULATE_LOWCORE); for_each_physmem_usable_range(i, &start, &end) { + /* Do not map lowcore with identity mapping */ + if (!start) + start = sizeof(struct lowcore); pgtable_populate((unsigned long)__identity_va(start), (unsigned long)__identity_va(end), POPULATE_IDENTITY); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 6b33429f1c4d..b31c1df90257 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -5,6 +5,7 @@ CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_POSIX_AUX_CLOCKS=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_BPF_JIT_ALWAYS_ON=y @@ -19,6 +20,7 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +CONFIG_SCHED_PROXY_EXEC=y CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y @@ -42,6 +44,7 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y +CONFIG_CRASH_DM_CRYPT=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 @@ -105,6 +108,7 @@ CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y +CONFIG_ZONE_DEVICE=y CONFIG_PERCPU_STATS=y CONFIG_GUP_TEST=y CONFIG_ANON_VMA_NAME=y @@ -114,10 +118,17 @@ CONFIG_PACKET=y CONFIG_PACKET_DIAG=m CONFIG_UNIX=y CONFIG_UNIX_DIAG=m +CONFIG_TLS=m +CONFIG_TLS_DEVICE=y +CONFIG_TLS_TOE=y CONFIG_XFRM_USER=m CONFIG_NET_KEY=m +CONFIG_XDP_SOCKETS=y +CONFIG_XDP_SOCKETS_DIAG=m +CONFIG_DIBS=y +CONFIG_DIBS_LO=y +CONFIG_SMC=m CONFIG_SMC_DIAG=m -CONFIG_SMC_LO=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -223,17 +234,19 @@ 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_HL=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_NAT=m CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m CONFIG_NETFILTER_XT_TARGET_REDIRECT=m +CONFIG_NETFILTER_XT_TARGET_MASQUERADE=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 @@ -248,6 +261,7 @@ 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 @@ -318,16 +332,8 @@ 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_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m CONFIG_IP6_NF_IPTABLES=m @@ -340,15 +346,9 @@ 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_IP_SCTP=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -383,6 +383,7 @@ CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m CONFIG_NET_SCH_ETS=m +CONFIG_NET_SCH_DUALPI2=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_ROUTE4=m CONFIG_NET_CLS_FW=m @@ -504,6 +505,7 @@ CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m +CONFIG_OVPN=m CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m @@ -547,6 +549,7 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +CONFIG_MLX5_SF=y # CONFIG_NET_VENDOR_META is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set @@ -641,6 +644,7 @@ CONFIG_VP_VDPA=m CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m CONFIG_VHOST_VDPA=m +CONFIG_DEV_DAX=m CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -662,9 +666,7 @@ CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_BTRFS_DEBUG=y CONFIG_BTRFS_ASSERT=y CONFIG_NILFS2_FS=m -CONFIG_BCACHEFS_FS=y -CONFIG_BCACHEFS_QUOTA=y -CONFIG_BCACHEFS_POSIX_ACL=y +CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y CONFIG_FS_VERITY=y @@ -755,6 +757,8 @@ CONFIG_HARDENED_USERCOPY=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_SELFTESTS=y +CONFIG_CRYPTO_SELFTESTS_FULL=y +CONFIG_CRYPTO_NULL=y CONFIG_CRYPTO_PCRYPT=m CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_BENCHMARK=m @@ -762,7 +766,6 @@ CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECDSA=m CONFIG_CRYPTO_ECRDSA=m -CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_ARIA=m @@ -783,7 +786,6 @@ CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_MD4=m @@ -822,6 +824,7 @@ CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CRYPTO_KRB5=m CONFIG_CRYPTO_KRB5_SELFTESTS=y CONFIG_CORDIC=m +CONFIG_TRACE_MMIO_ACCESS=y CONFIG_RANDOM32_SELFTEST=y CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index b75eb2775850..161dad7ef211 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -4,6 +4,7 @@ CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_POSIX_AUX_CLOCKS=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_BPF_JIT_ALWAYS_ON=y @@ -17,6 +18,7 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +CONFIG_SCHED_PROXY_EXEC=y CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y @@ -40,11 +42,12 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y +CONFIG_CRASH_DM_CRYPT=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y -CONFIG_HZ_100=y +CONFIG_HZ_1000=y CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y @@ -97,6 +100,7 @@ CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y +CONFIG_ZONE_DEVICE=y CONFIG_PERCPU_STATS=y CONFIG_ANON_VMA_NAME=y CONFIG_USERFAULTFD=y @@ -105,10 +109,17 @@ CONFIG_PACKET=y CONFIG_PACKET_DIAG=m CONFIG_UNIX=y CONFIG_UNIX_DIAG=m +CONFIG_TLS=m +CONFIG_TLS_DEVICE=y +CONFIG_TLS_TOE=y CONFIG_XFRM_USER=m CONFIG_NET_KEY=m +CONFIG_XDP_SOCKETS=y +CONFIG_XDP_SOCKETS_DIAG=m +CONFIG_DIBS=y +CONFIG_DIBS_LO=y +CONFIG_SMC=m CONFIG_SMC_DIAG=m -CONFIG_SMC_LO=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -214,17 +225,19 @@ 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_HL=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_NAT=m CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m CONFIG_NETFILTER_XT_TARGET_REDIRECT=m +CONFIG_NETFILTER_XT_TARGET_MASQUERADE=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 @@ -239,6 +252,7 @@ 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 @@ -309,16 +323,8 @@ 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_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m CONFIG_IP6_NF_IPTABLES=m @@ -331,15 +337,9 @@ 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_IP_SCTP=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -373,6 +373,7 @@ CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m CONFIG_NET_SCH_ETS=m +CONFIG_NET_SCH_DUALPI2=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_ROUTE4=m CONFIG_NET_CLS_FW=m @@ -494,6 +495,7 @@ CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m +CONFIG_OVPN=m CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m @@ -537,6 +539,7 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +CONFIG_MLX5_SF=y # CONFIG_NET_VENDOR_META is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set @@ -631,6 +634,7 @@ CONFIG_VP_VDPA=m CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m CONFIG_VHOST_VDPA=m +CONFIG_DEV_DAX=m CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -649,9 +653,7 @@ CONFIG_OCFS2_FS=m CONFIG_BTRFS_FS=y CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m -CONFIG_BCACHEFS_FS=m -CONFIG_BCACHEFS_QUOTA=y -CONFIG_BCACHEFS_POSIX_ACL=y +CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y CONFIG_FS_VERITY=y @@ -683,7 +685,6 @@ CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_INODE64=y CONFIG_TMPFS_QUOTA=y CONFIG_HUGETLBFS=y -CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m @@ -741,6 +742,7 @@ CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_SELFTESTS=y +CONFIG_CRYPTO_NULL=y CONFIG_CRYPTO_PCRYPT=m CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_BENCHMARK=m @@ -748,7 +750,6 @@ CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECDSA=m CONFIG_CRYPTO_ECRDSA=m -CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_ARIA=m @@ -769,7 +770,6 @@ CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_MD4=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 8163c1702720..ed0b137353ad 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -1,5 +1,6 @@ CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_POSIX_AUX_CLOCKS=y CONFIG_BPF_SYSCALL=y # CONFIG_CPU_ISOLATION is not set # CONFIG_UTS_NS is not set @@ -11,7 +12,7 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_KEXEC=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=2 -CONFIG_HZ_100=y +CONFIG_HZ_1000=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set # CONFIG_AP is not set diff --git a/arch/s390/crypto/sha.h b/arch/s390/crypto/sha.h index cadb4b13622a..b9cd9572dd35 100644 --- a/arch/s390/crypto/sha.h +++ b/arch/s390/crypto/sha.h @@ -10,14 +10,15 @@ #ifndef _CRYPTO_ARCH_S390_SHA_H #define _CRYPTO_ARCH_S390_SHA_H +#include <crypto/hash.h> #include <crypto/sha2.h> #include <crypto/sha3.h> +#include <linux/build_bug.h> #include <linux/types.h> /* must be big enough for the largest SHA variant */ #define CPACF_MAX_PARMBLOCK_SIZE SHA3_STATE_SIZE #define SHA_MAX_BLOCK_SIZE SHA3_224_BLOCK_SIZE -#define S390_SHA_CTX_SIZE sizeof(struct s390_sha_ctx) struct s390_sha_ctx { u64 count; /* message length in bytes */ @@ -42,4 +43,9 @@ int s390_sha_update_blocks(struct shash_desc *desc, const u8 *data, int s390_sha_finup(struct shash_desc *desc, const u8 *src, unsigned int len, u8 *out); +static inline void __check_s390_sha_ctx_size(void) +{ + BUILD_BUG_ON(S390_SHA_CTX_SIZE != sizeof(struct s390_sha_ctx)); +} + #endif diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 5d9effb0867c..41a0d2066fa0 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -6,6 +6,7 @@ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> */ +#include <linux/security.h> #include <linux/slab.h> #include "hypfs.h" @@ -66,23 +67,27 @@ static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) long rc; mutex_lock(&df->lock); - if (df->unlocked_ioctl) - rc = df->unlocked_ioctl(file, cmd, arg); - else - rc = -ENOTTY; + rc = df->unlocked_ioctl(file, cmd, arg); mutex_unlock(&df->lock); return rc; } -static const struct file_operations dbfs_ops = { +static const struct file_operations dbfs_ops_ioctl = { .read = dbfs_read, .unlocked_ioctl = dbfs_ioctl, }; +static const struct file_operations dbfs_ops = { + .read = dbfs_read, +}; + void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df) { - df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df, - &dbfs_ops); + const struct file_operations *fops = &dbfs_ops; + + if (df->unlocked_ioctl && !security_locked_down(LOCKDOWN_DEBUGFS)) + fops = &dbfs_ops_ioctl; + df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df, fops); mutex_init(&df->lock); } diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index a5ca0a947691..ec945fb60c02 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -122,6 +122,8 @@ static inline bool test_bit_inv(unsigned long nr, return test_bit(nr ^ (BITS_PER_LONG - 1), ptr); } +#ifndef CONFIG_CC_HAS_BUILTIN_FFS + /** * __flogr - find leftmost one * @word - The word to search @@ -130,11 +132,12 @@ static inline bool test_bit_inv(unsigned long nr, * where the most significant bit has bit number 0. * If no bit is set this function returns 64. */ -static inline unsigned char __flogr(unsigned long word) +static __always_inline __attribute_const__ unsigned long __flogr(unsigned long word) { - if (__builtin_constant_p(word)) { - unsigned long bit = 0; + unsigned long bit; + if (__builtin_constant_p(word)) { + bit = 0; if (!word) return 64; if (!(word & 0xffffffff00000000UL)) { @@ -163,86 +166,49 @@ static inline unsigned char __flogr(unsigned long word) } return bit; } else { - union register_pair rp; + union register_pair rp __uninitialized; rp.even = word; - asm volatile( - " flogr %[rp],%[rp]\n" - : [rp] "+d" (rp.pair) : : "cc"); - return rp.even; + asm("flogr %[rp],%[rp]" + : [rp] "+d" (rp.pair) : : "cc"); + bit = rp.even; + /* + * The result of the flogr instruction is a value in the range + * of 0..64. Let the compiler know that the AND operation can + * be optimized away. + */ + __assume(bit <= 64); + return bit & 127; } } /** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static inline unsigned long __ffs(unsigned long word) -{ - return __flogr(-word & word) ^ (BITS_PER_LONG - 1); -} - -/** * ffs - find first bit set * @word: the word to search * * This is defined the same way as the libc and * compiler builtin ffs routines (man ffs). */ -static inline int ffs(int word) +static __always_inline __flatten __attribute_const__ int ffs(int word) { - unsigned long mask = 2 * BITS_PER_LONG - 1; unsigned int val = (unsigned int)word; - return (1 + (__flogr(-val & val) ^ (BITS_PER_LONG - 1))) & mask; -} - -/** - * __fls - find last (most-significant) set bit in a long word - * @word: the word to search - * - * Undefined if no set bit exists, so code should check against 0 first. - */ -static inline unsigned long __fls(unsigned long word) -{ - return __flogr(word) ^ (BITS_PER_LONG - 1); + return BITS_PER_LONG - __flogr(-val & val); } -/** - * fls64 - find last set bit in a 64-bit word - * @word: the word to search - * - * This is defined in a similar way as the libc and compiler builtin - * ffsll, but returns the position of the most significant set bit. - * - * fls64(value) returns 0 if value is 0 or the position of the last - * set bit if value is nonzero. The last (most significant) bit is - * at position 64. - */ -static inline int fls64(unsigned long word) -{ - unsigned long mask = 2 * BITS_PER_LONG - 1; +#else /* CONFIG_CC_HAS_BUILTIN_FFS */ - return (1 + (__flogr(word) ^ (BITS_PER_LONG - 1))) & mask; -} +#include <asm-generic/bitops/builtin-ffs.h> -/** - * fls - find last (most-significant) bit set - * @word: the word to search - * - * This is defined the same way as ffs. - * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. - */ -static inline int fls(unsigned int word) -{ - return fls64(word); -} +#endif /* CONFIG_CC_HAS_BUILTIN_FFS */ +#include <asm-generic/bitops/builtin-__ffs.h> +#include <asm-generic/bitops/ffz.h> +#include <asm-generic/bitops/builtin-__fls.h> +#include <asm-generic/bitops/builtin-fls.h> +#include <asm-generic/bitops/fls64.h> #include <asm/arch_hweight.h> #include <asm-generic/bitops/const_hweight.h> -#include <asm-generic/bitops/ffz.h> #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 931fcc413598..69131736daaa 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -39,7 +39,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_arch_1, &folio->flags); + clear_bit(PG_arch_1, &folio->flags.f); } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index f870d09515cc..95d15416c39d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -356,7 +356,7 @@ struct kvm_s390_float_interrupt { int counters[FIRQ_MAX_COUNT]; struct kvm_s390_mchk_info mchk; struct kvm_s390_ext_info srv_signal; - int next_rr_cpu; + int last_sleep_cpu; struct mutex ais_lock; u8 simm; u8 nimm; diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index e5f57cfe1d45..025c6dcbf893 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -16,11 +16,11 @@ #define ZPCI_PCI_ST_FUNC_NOT_AVAIL 40 #define ZPCI_PCI_ST_ALREADY_IN_RQ_STATE 44 -/* Load/Store return codes */ -#define ZPCI_PCI_LS_OK 0 -#define ZPCI_PCI_LS_ERR 1 -#define ZPCI_PCI_LS_BUSY 2 -#define ZPCI_PCI_LS_INVAL_HANDLE 3 +/* PCI instruction condition codes */ +#define ZPCI_CC_OK 0 +#define ZPCI_CC_ERR 1 +#define ZPCI_CC_BUSY 2 +#define ZPCI_CC_INVAL_HANDLE 3 /* Load/Store address space identifiers */ #define ZPCI_PCIAS_MEMIO_0 0 diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 5345398df653..a16e65072371 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -19,12 +19,16 @@ #define CRST_ALLOC_ORDER 2 -unsigned long *crst_table_alloc(struct mm_struct *); +unsigned long *crst_table_alloc_noprof(struct mm_struct *); +#define crst_table_alloc(...) alloc_hooks(crst_table_alloc_noprof(__VA_ARGS__)) void crst_table_free(struct mm_struct *, unsigned long *); -unsigned long *page_table_alloc(struct mm_struct *); -struct ptdesc *page_table_alloc_pgste(struct mm_struct *mm); +unsigned long *page_table_alloc_noprof(struct mm_struct *); +#define page_table_alloc(...) alloc_hooks(page_table_alloc_noprof(__VA_ARGS__)) void page_table_free(struct mm_struct *, unsigned long *); + +struct ptdesc *page_table_alloc_pgste_noprof(struct mm_struct *mm); +#define page_table_alloc_pgste(...) alloc_hooks(page_table_alloc_pgste_noprof(__VA_ARGS__)) void page_table_free_pgste(struct ptdesc *ptdesc); static inline void crst_table_init(unsigned long *crst, unsigned long entry) @@ -48,9 +52,9 @@ static inline unsigned long check_asce_limit(struct mm_struct *mm, unsigned long return addr; } -static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) +static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long address) { - unsigned long *table = crst_table_alloc(mm); + unsigned long *table = crst_table_alloc_noprof(mm); if (!table) return NULL; @@ -59,6 +63,7 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) return (p4d_t *) table; } +#define p4d_alloc_one(...) alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__)) static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { @@ -69,9 +74,9 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) crst_table_free(mm, (unsigned long *) p4d); } -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) +static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long address) { - unsigned long *table = crst_table_alloc(mm); + unsigned long *table = crst_table_alloc_noprof(mm); if (!table) return NULL; @@ -80,6 +85,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) return (pud_t *) table; } +#define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__)) static inline void pud_free(struct mm_struct *mm, pud_t *pud) { @@ -90,9 +96,9 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) crst_table_free(mm, (unsigned long *) pud); } -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) +static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long vmaddr) { - unsigned long *table = crst_table_alloc(mm); + unsigned long *table = crst_table_alloc_noprof(mm); if (!table) return NULL; @@ -103,6 +109,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) } return (pmd_t *) table; } +#define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__)) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { @@ -127,9 +134,9 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) set_pud(pud, __pud(_REGION3_ENTRY | __pa(pmd))); } -static inline pgd_t *pgd_alloc(struct mm_struct *mm) +static inline pgd_t *pgd_alloc_noprof(struct mm_struct *mm) { - unsigned long *table = crst_table_alloc(mm); + unsigned long *table = crst_table_alloc_noprof(mm); if (!table) return NULL; @@ -137,6 +144,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) return (pgd_t *) table; } +#define pgd_alloc(...) alloc_hooks(pgd_alloc_noprof(__VA_ARGS__)) static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index c1a7a92f0575..b7100c6a4054 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -2055,4 +2055,26 @@ static inline unsigned long gmap_pgste_get_pgt_addr(unsigned long *pgt) return res; } +static inline pgste_t pgste_get_lock(pte_t *ptep) +{ + unsigned long value = 0; +#ifdef CONFIG_PGSTE + unsigned long *ptr = (unsigned long *)(ptep + PTRS_PER_PTE); + + do { + value = __atomic64_or_barrier(PGSTE_PCL_BIT, ptr); + } while (value & PGSTE_PCL_BIT); + value |= PGSTE_PCL_BIT; +#endif + return __pgste(value); +} + +static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste) +{ +#ifdef CONFIG_PGSTE + barrier(); + WRITE_ONCE(*(unsigned long *)(ptep + PTRS_PER_PTE), pgste_val(pgste) & ~PGSTE_PCL_BIT); +#endif +} + #endif /* _S390_PAGE_H */ diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index f6ed2c8192c8..7878e9bfbf07 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -56,49 +56,31 @@ void arch_setup_new_exec(void); /* * thread information flags bit numbers + * + * Tell the generic TIF infrastructure which special bits s390 supports */ -#define TIF_NOTIFY_RESUME 0 /* callback before returning to user */ -#define TIF_SIGPENDING 1 /* signal pending */ -#define TIF_NEED_RESCHED 2 /* rescheduling necessary */ -#define TIF_NEED_RESCHED_LAZY 3 /* lazy rescheduling needed */ -#define TIF_UPROBE 4 /* breakpointed or single-stepping */ -#define TIF_PATCH_PENDING 5 /* pending live patching update */ -#define TIF_ASCE_PRIMARY 6 /* primary asce is kernel asce */ -#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ -#define TIF_GUARDED_STORAGE 8 /* load guarded storage control block */ -#define TIF_ISOLATE_BP_GUEST 9 /* Run KVM guests with isolated BP */ -#define TIF_PER_TRAP 10 /* Need to handle PER trap on exit to usermode */ -#define TIF_31BIT 16 /* 32bit process */ -#define TIF_MEMDIE 17 /* is terminating due to OOM killer */ -#define TIF_RESTORE_SIGMASK 18 /* restore signal mask in do_signal() */ -#define TIF_SINGLE_STEP 19 /* This task is single stepped */ -#define TIF_BLOCK_STEP 20 /* This task is block stepped */ -#define TIF_UPROBE_SINGLESTEP 21 /* This task is uprobe single stepped */ -#define TIF_SYSCALL_TRACE 24 /* syscall trace active */ -#define TIF_SYSCALL_AUDIT 25 /* syscall auditing active */ -#define TIF_SECCOMP 26 /* secure computing */ -#define TIF_SYSCALL_TRACEPOINT 27 /* syscall tracepoint instrumentation */ +#define HAVE_TIF_NEED_RESCHED_LAZY +#define HAVE_TIF_RESTORE_SIGMASK + +#include <asm-generic/thread_info_tif.h> + +/* Architecture specific bits */ +#define TIF_ASCE_PRIMARY 16 /* primary asce is kernel asce */ +#define TIF_GUARDED_STORAGE 17 /* load guarded storage control block */ +#define TIF_ISOLATE_BP_GUEST 18 /* Run KVM guests with isolated BP */ +#define TIF_PER_TRAP 19 /* Need to handle PER trap on exit to usermode */ +#define TIF_31BIT 20 /* 32bit process */ +#define TIF_SINGLE_STEP 21 /* This task is single stepped */ +#define TIF_BLOCK_STEP 22 /* This task is block stepped */ +#define TIF_UPROBE_SINGLESTEP 23 /* This task is uprobe single stepped */ -#define _TIF_NOTIFY_RESUME BIT(TIF_NOTIFY_RESUME) -#define _TIF_SIGPENDING BIT(TIF_SIGPENDING) -#define _TIF_NEED_RESCHED BIT(TIF_NEED_RESCHED) -#define _TIF_NEED_RESCHED_LAZY BIT(TIF_NEED_RESCHED_LAZY) -#define _TIF_UPROBE BIT(TIF_UPROBE) -#define _TIF_PATCH_PENDING BIT(TIF_PATCH_PENDING) #define _TIF_ASCE_PRIMARY BIT(TIF_ASCE_PRIMARY) -#define _TIF_NOTIFY_SIGNAL BIT(TIF_NOTIFY_SIGNAL) #define _TIF_GUARDED_STORAGE BIT(TIF_GUARDED_STORAGE) #define _TIF_ISOLATE_BP_GUEST BIT(TIF_ISOLATE_BP_GUEST) #define _TIF_PER_TRAP BIT(TIF_PER_TRAP) #define _TIF_31BIT BIT(TIF_31BIT) -#define _TIF_MEMDIE BIT(TIF_MEMDIE) -#define _TIF_RESTORE_SIGMASK BIT(TIF_RESTORE_SIGMASK) #define _TIF_SINGLE_STEP BIT(TIF_SINGLE_STEP) #define _TIF_BLOCK_STEP BIT(TIF_BLOCK_STEP) #define _TIF_UPROBE_SINGLESTEP BIT(TIF_UPROBE_SINGLESTEP) -#define _TIF_SYSCALL_TRACE BIT(TIF_SYSCALL_TRACE) -#define _TIF_SYSCALL_AUDIT BIT(TIF_SYSCALL_AUDIT) -#define _TIF_SECCOMP BIT(TIF_SECCOMP) -#define _TIF_SYSCALL_TRACEPOINT BIT(TIF_SYSCALL_TRACEPOINT) #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 95ecad9c7d7d..a8915663e917 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -4,6 +4,7 @@ * This code generates raw asm output which is post-processed to extract * and format the required data. */ +#define COMPILE_OFFSETS #include <linux/kbuild.h> #include <linux/sched.h> diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index c62100dc62c8..6a26f202441d 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1416,18 +1416,12 @@ static inline char *debug_get_user_string(const char __user *user_buf, { char *buffer; - buffer = kmalloc(user_len + 1, GFP_KERNEL); - if (!buffer) - return ERR_PTR(-ENOMEM); - if (copy_from_user(buffer, user_buf, user_len) != 0) { - kfree(buffer); - return ERR_PTR(-EFAULT); - } + buffer = memdup_user_nul(user_buf, user_len); + if (IS_ERR(buffer)) + return buffer; /* got the string, now strip linefeed. */ if (buffer[user_len - 1] == '\n') buffer[user_len - 1] = 0; - else - buffer[user_len] = 0; return buffer; } diff --git a/arch/s390/kernel/diag/diag324.c b/arch/s390/kernel/diag/diag324.c index 7fa4c0b7eb6c..f0a8b4841fb9 100644 --- a/arch/s390/kernel/diag/diag324.c +++ b/arch/s390/kernel/diag/diag324.c @@ -116,7 +116,7 @@ static void pibwork_handler(struct work_struct *work) mutex_lock(&pibmutex); timedout = ktime_add_ns(data->expire, PIBWORK_DELAY); if (ktime_before(ktime_get(), timedout)) { - mod_delayed_work(system_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY)); + mod_delayed_work(system_percpu_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY)); goto out; } vfree(data->pib); @@ -174,7 +174,7 @@ long diag324_pibbuf(unsigned long arg) pib_update(data); data->sequence++; data->expire = ktime_add_ns(ktime_get(), tod_to_ns(data->pib->intv)); - mod_delayed_work(system_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY)); + mod_delayed_work(system_percpu_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY)); first = false; } rc = data->rc; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 9adfbdd377dc..544e5403dd91 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -21,6 +21,7 @@ #include <linux/kernel.h> #include <asm/asm-extable.h> #include <linux/memblock.h> +#include <linux/kasan.h> #include <asm/access-regs.h> #include <asm/asm-offsets.h> #include <asm/machine.h> @@ -65,7 +66,7 @@ static void __init kasan_early_init(void) { #ifdef CONFIG_KASAN init_task.kasan_depth = 0; - pr_info("KernelAddressSanitizer initialized\n"); + kasan_init_generic(); #endif } diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c index e7b66d046e8d..2507bc3f7757 100644 --- a/arch/s390/kernel/hiperdispatch.c +++ b/arch/s390/kernel/hiperdispatch.c @@ -191,7 +191,7 @@ int hd_enable_hiperdispatch(void) return 0; if (hd_online_cores <= hd_entitled_cores) return 0; - mod_delayed_work(system_wq, &hd_capacity_work, HD_DELAY_INTERVAL * hd_delay_factor); + mod_delayed_work(system_dfl_wq, &hd_capacity_work, HD_DELAY_INTERVAL * hd_delay_factor); hd_update_capacities(); return 1; } diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c index 4d364de43799..143e34a4eca5 100644 --- a/arch/s390/kernel/kexec_elf.c +++ b/arch/s390/kernel/kexec_elf.c @@ -16,7 +16,7 @@ static int kexec_file_add_kernel_elf(struct kimage *image, struct s390_load_data *data) { - struct kexec_buf buf; + struct kexec_buf buf = {}; const Elf_Ehdr *ehdr; const Elf_Phdr *phdr; Elf_Addr entry; diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c index a32ce8bea745..9a439175723c 100644 --- a/arch/s390/kernel/kexec_image.c +++ b/arch/s390/kernel/kexec_image.c @@ -16,7 +16,7 @@ static int kexec_file_add_kernel_image(struct kimage *image, struct s390_load_data *data) { - struct kexec_buf buf; + struct kexec_buf buf = {}; buf.image = image; diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index c2bac14dd668..a36d7311c668 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -129,7 +129,7 @@ static int kexec_file_update_purgatory(struct kimage *image, static int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data) { - struct kexec_buf buf; + struct kexec_buf buf = {}; int ret; buf.image = image; @@ -152,7 +152,7 @@ static int kexec_file_add_purgatory(struct kimage *image, static int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data) { - struct kexec_buf buf; + struct kexec_buf buf = {}; int ret; buf.image = image; @@ -184,7 +184,7 @@ static int kexec_file_add_ipl_report(struct kimage *image, { __u32 *lc_ipl_parmblock_ptr; unsigned int len, ncerts; - struct kexec_buf buf; + struct kexec_buf buf = {}; unsigned long addr; void *ptr, *end; int ret; diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 4d09954ebf49..04457d88e589 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -760,8 +760,6 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) break; case PERF_TYPE_HARDWARE: - if (is_sampling_event(event)) /* No sampling support */ - return -ENOENT; ev = attr->config; if (!attr->exclude_user && attr->exclude_kernel) { /* @@ -859,6 +857,8 @@ static int cpumf_pmu_event_init(struct perf_event *event) unsigned int type = event->attr.type; int err = -ENOENT; + if (is_sampling_event(event)) /* No sampling support */ + return err; if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW) err = __hw_perf_event_init(event, type); else if (event->pmu->type == type) diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index f373a1009c45..9455f213dc20 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -285,10 +285,10 @@ static int paicrypt_event_init(struct perf_event *event) /* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */ if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type) return -ENOENT; - /* PAI crypto event must be in valid range */ + /* PAI crypto event must be in valid range, try others if not */ if (a->config < PAI_CRYPTO_BASE || a->config > PAI_CRYPTO_BASE + paicrypt_cnt) - return -EINVAL; + return -ENOENT; /* Allow only CRYPTO_ALL for sampling */ if (a->sample_period && a->config != PAI_CRYPTO_BASE) return -EINVAL; diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index d827473e7f87..7b32935273ce 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -265,7 +265,7 @@ static int paiext_event_valid(struct perf_event *event) event->hw.config_base = offsetof(struct paiext_cb, acc); return 0; } - return -EINVAL; + return -ENOENT; } /* Might be called on different CPU than the one the event is intended for. */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index f55f09cda6f8..b107dbca4ed7 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -106,7 +106,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { - unsigned long clone_flags = args->flags; + u64 clone_flags = args->flags; unsigned long new_stackp = args->stack; unsigned long tls = args->tls; struct fake_frame diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 46569b8e47dd..1594c80e9bc4 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -509,33 +509,27 @@ int topology_cpu_init(struct cpu *cpu) return rc; } -static const struct cpumask *cpu_thread_mask(int cpu) -{ - return &cpu_topology[cpu].thread_mask; -} - - const struct cpumask *cpu_coregroup_mask(int cpu) { return &cpu_topology[cpu].core_mask; } -static const struct cpumask *cpu_book_mask(int cpu) +static const struct cpumask *tl_book_mask(struct sched_domain_topology_level *tl, int cpu) { return &cpu_topology[cpu].book_mask; } -static const struct cpumask *cpu_drawer_mask(int cpu) +static const struct cpumask *tl_drawer_mask(struct sched_domain_topology_level *tl, int cpu) { return &cpu_topology[cpu].drawer_mask; } static struct sched_domain_topology_level s390_topology[] = { - SDTL_INIT(cpu_thread_mask, cpu_smt_flags, SMT), - SDTL_INIT(cpu_coregroup_mask, cpu_core_flags, MC), - SDTL_INIT(cpu_book_mask, NULL, BOOK), - SDTL_INIT(cpu_drawer_mask, NULL, DRAWER), - SDTL_INIT(cpu_cpu_mask, NULL, PKG), + SDTL_INIT(tl_smt_mask, cpu_smt_flags, SMT), + SDTL_INIT(tl_mc_mask, cpu_core_flags, MC), + SDTL_INIT(tl_book_mask, NULL, BOOK), + SDTL_INIT(tl_drawer_mask, NULL, DRAWER), + SDTL_INIT(tl_pkg_mask, NULL, PKG), { NULL, }, }; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 47f574cd1728..93b2a01bae40 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -144,7 +144,7 @@ int uv_destroy_folio(struct folio *folio) folio_get(folio); rc = uv_destroy(folio_to_phys(folio)); if (!rc) - clear_bit(PG_arch_1, &folio->flags); + clear_bit(PG_arch_1, &folio->flags.f); folio_put(folio); return rc; } @@ -193,7 +193,7 @@ int uv_convert_from_secure_folio(struct folio *folio) folio_get(folio); rc = uv_convert_from_secure(folio_to_phys(folio)); if (!rc) - clear_bit(PG_arch_1, &folio->flags); + clear_bit(PG_arch_1, &folio->flags.f); folio_put(folio); return rc; } @@ -289,7 +289,7 @@ static int __make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) expected = expected_folio_refs(folio) + 1; if (!folio_ref_freeze(folio, expected)) return -EBUSY; - set_bit(PG_arch_1, &folio->flags); + set_bit(PG_arch_1, &folio->flags.f); /* * If the UVC does not succeed or fail immediately, we don't want to * loop for long, or we might get stall notifications. @@ -483,18 +483,18 @@ int arch_make_folio_accessible(struct folio *folio) * convert_to_secure. * As secure pages are never large folios, both variants can co-exists. */ - if (!test_bit(PG_arch_1, &folio->flags)) + if (!test_bit(PG_arch_1, &folio->flags.f)) return 0; rc = uv_pin_shared(folio_to_phys(folio)); if (!rc) { - clear_bit(PG_arch_1, &folio->flags); + clear_bit(PG_arch_1, &folio->flags.f); return 0; } rc = uv_convert_from_secure(folio_to_phys(folio)); if (!rc) { - clear_bit(PG_arch_1, &folio->flags); + clear_bit(PG_arch_1, &folio->flags.f); return 0; } diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 1c606dfa595d..feecf1a6ddb4 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -209,6 +209,11 @@ SECTIONS . = ALIGN(PAGE_SIZE); _end = . ; + /* Debugging sections. */ + STABS_DEBUG + DWARF_DEBUG + ELF_DETAILS + /* * uncompressed image info used by the decompressor * it should match struct vmlinux_info @@ -239,11 +244,6 @@ SECTIONS #endif } :NONE - /* Debugging sections. */ - STABS_DEBUG - DWARF_DEBUG - ELF_DETAILS - /* * Make sure that the .got.plt is either completely empty or it * contains only the three reserved double words. diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 2a92a8b9e4c2..c62a868cf2b6 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1323,6 +1323,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: kvm_vcpu_srcu_read_unlock(vcpu); + vcpu->kvm->arch.float_int.last_sleep_cpu = vcpu->vcpu_idx; kvm_vcpu_halt(vcpu); vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); @@ -1949,18 +1950,15 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) if (!online_vcpus) return; - /* find idle VCPUs first, then round robin */ - sigcpu = find_first_bit(kvm->arch.idle_mask, online_vcpus); - if (sigcpu == online_vcpus) { - do { - sigcpu = kvm->arch.float_int.next_rr_cpu++; - kvm->arch.float_int.next_rr_cpu %= online_vcpus; - /* avoid endless loops if all vcpus are stopped */ - if (nr_tries++ >= online_vcpus) - return; - } while (is_vcpu_stopped(kvm_get_vcpu(kvm, sigcpu))); + for (sigcpu = kvm->arch.float_int.last_sleep_cpu; ; sigcpu++) { + sigcpu %= online_vcpus; + dst_vcpu = kvm_get_vcpu(kvm, sigcpu); + if (!is_vcpu_stopped(dst_vcpu)) + break; + /* avoid endless loops if all vcpus are stopped */ + if (nr_tries++ >= online_vcpus) + return; } - dst_vcpu = kvm_get_vcpu(kvm, sigcpu); /* make the VCPU drop out of the SIE, or wake it up if sleeping */ switch (type) { @@ -2778,12 +2776,19 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap) static struct page *get_map_page(struct kvm *kvm, u64 uaddr) { + struct mm_struct *mm = kvm->mm; struct page *page = NULL; + int locked = 1; + + if (mmget_not_zero(mm)) { + mmap_read_lock(mm); + get_user_pages_remote(mm, uaddr, 1, FOLL_WRITE, + &page, &locked); + if (locked) + mmap_read_unlock(mm); + mmput(mm); + } - mmap_read_lock(kvm->mm); - get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE, - &page, NULL); - mmap_read_unlock(kvm->mm); return page; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bf6fa8b9ca73..6d51aa5f66be 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4864,12 +4864,12 @@ static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu) * @vcpu: the vCPU whose gmap is to be fixed up * @gfn: the guest frame number used for memslots (including fake memslots) * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps - * @flags: FOLL_* flags + * @foll: FOLL_* flags * * Return: 0 on success, < 0 in case of error. * Context: The mm lock must not be held before calling. May sleep. */ -int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags) +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int foll) { struct kvm_memory_slot *slot; unsigned int fault_flags; @@ -4883,13 +4883,13 @@ int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, u if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return vcpu_post_run_addressing_exception(vcpu); - fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; + fault_flags = foll & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; if (vcpu->arch.gmap->pfault_enabled) - flags |= FOLL_NOWAIT; + foll |= FOLL_NOWAIT; vmaddr = __gfn_to_hva_memslot(slot, gfn); try_again: - pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page); + pfn = __kvm_faultin_pfn(slot, gfn, foll, &writable, &page); /* Access outside memory, inject addressing exception */ if (is_noslot_pfn(pfn)) @@ -4905,7 +4905,7 @@ try_again: return 0; vcpu->stat.pfault_sync++; /* Could not setup async pfault, try again synchronously */ - flags &= ~FOLL_NOWAIT; + foll &= ~FOLL_NOWAIT; goto try_again; } /* Any other error */ @@ -4925,7 +4925,7 @@ try_again: return rc; } -static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags) +static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int foll) { unsigned long gaddr_tmp; gfn_t gfn; @@ -4950,18 +4950,18 @@ static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, un } gfn = gpa_to_gfn(gaddr_tmp); } - return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags); + return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, foll); } static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) { - unsigned int flags = 0; + unsigned int foll = 0; unsigned long gaddr; int rc; gaddr = current->thread.gmap_teid.addr * PAGE_SIZE; if (kvm_s390_cur_gmap_fault_is_write()) - flags = FAULT_FLAG_WRITE; + foll = FOLL_WRITE; switch (current->thread.gmap_int_code & PGM_INT_CODE_MASK) { case 0: @@ -5003,7 +5003,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) send_sig(SIGSEGV, current, 0); if (rc != -ENXIO) break; - flags = FAULT_FLAG_WRITE; + foll = FOLL_WRITE; fallthrough; case PGM_PROTECTION: case PGM_SEGMENT_TRANSLATION: @@ -5013,7 +5013,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) case PGM_REGION_SECOND_TRANS: case PGM_REGION_THIRD_TRANS: kvm_s390_assert_primary_as(vcpu); - return vcpu_dat_fault_handler(vcpu, gaddr, flags); + return vcpu_dat_fault_handler(vcpu, gaddr, foll); default: KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx", current->thread.gmap_int_code, current->thread.gmap_teid.val); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 25ede8354514..6ba5a0305e25 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -624,6 +624,17 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) int cc, ret; u16 dummy; + /* Add the notifier only once. No races because we hold kvm->lock */ + if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) { + /* The notifier will be unregistered when the VM is destroyed */ + kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops; + ret = mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm); + if (ret) { + kvm->arch.pv.mmu_notifier.ops = NULL; + return ret; + } + } + ret = kvm_s390_pv_alloc_vm(kvm); if (ret) return ret; @@ -659,11 +670,6 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; - /* Add the notifier only once. No races because we hold kvm->lock */ - if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) { - kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops; - mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm); - } return 0; } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index c7defe4ed1f6..8ff6bba107e8 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2272,7 +2272,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, start = pmd_val(*pmd) & HPAGE_MASK; end = start + HPAGE_SIZE; __storage_key_init_range(start, end); - set_bit(PG_arch_1, &folio->flags); + set_bit(PG_arch_1, &folio->flags.f); cond_resched(); return 0; } diff --git a/arch/s390/mm/gmap_helpers.c b/arch/s390/mm/gmap_helpers.c index b63f427e7289..d4c3c36855e2 100644 --- a/arch/s390/mm/gmap_helpers.c +++ b/arch/s390/mm/gmap_helpers.c @@ -15,6 +15,7 @@ #include <linux/pagewalk.h> #include <linux/ksm.h> #include <asm/gmap_helpers.h> +#include <asm/pgtable.h> /** * ptep_zap_swap_entry() - discard a swap entry. @@ -47,6 +48,7 @@ void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr) { struct vm_area_struct *vma; spinlock_t *ptl; + pgste_t pgste; pte_t *ptep; mmap_assert_locked(mm); @@ -60,8 +62,16 @@ void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr) ptep = get_locked_pte(mm, vmaddr, &ptl); if (unlikely(!ptep)) return; - if (pte_swap(*ptep)) + if (pte_swap(*ptep)) { + preempt_disable(); + pgste = pgste_get_lock(ptep); + ptep_zap_swap_entry(mm, pte_to_swp_entry(*ptep)); + pte_clear(mm, vmaddr, ptep); + + pgste_set_unlock(ptep, pgste); + preempt_enable(); + } pte_unmap_unlock(ptep, ptl); } EXPORT_SYMBOL_GPL(gmap_helper_zap_one_page); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index e88c02c9e642..72e8fa136af5 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -155,7 +155,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) paddr = rste & PMD_MASK; } - if (!test_and_set_bit(PG_arch_1, &folio->flags)) + if (!test_and_set_bit(PG_arch_1, &folio->flags.f)) __storage_key_init_range(paddr, paddr + size); } diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 40a526d28184..197c1d9497a7 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -27,7 +27,7 @@ static unsigned long stack_maxrandom_size(void) return STACK_RND_MASK << PAGE_SHIFT; } -static inline int mmap_is_legacy(struct rlimit *rlim_stack) +static inline int mmap_is_legacy(const struct rlimit *rlim_stack) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; @@ -47,7 +47,7 @@ static unsigned long mmap_base_legacy(unsigned long rnd) } static inline unsigned long mmap_base(unsigned long rnd, - struct rlimit *rlim_stack) + const struct rlimit *rlim_stack) { unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_maxrandom_size() + stack_guard_gap; @@ -169,7 +169,7 @@ check_asce_limit: * This function, called very early during the creation of a new * process VM image, sets up which VM layout function to use: */ -void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) +void arch_pick_mmap_layout(struct mm_struct *mm, const struct rlimit *rlim_stack) { unsigned long random_factor = 0UL; @@ -182,10 +182,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) */ if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = mmap_base_legacy(random_factor); - clear_bit(MMF_TOPDOWN, &mm->flags); + mm_flags_clear(MMF_TOPDOWN, mm); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); - set_bit(MMF_TOPDOWN, &mm->flags); + mm_flags_set(MMF_TOPDOWN, mm); } } diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index d2f6f1f6d2fc..76d92069799f 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -14,14 +14,18 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> -unsigned long *crst_table_alloc(struct mm_struct *mm) +unsigned long *crst_table_alloc_noprof(struct mm_struct *mm) { - struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, CRST_ALLOC_ORDER); + gfp_t gfp = GFP_KERNEL_ACCOUNT; + struct ptdesc *ptdesc; unsigned long *table; + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; + ptdesc = pagetable_alloc_noprof(gfp, CRST_ALLOC_ORDER); if (!ptdesc) return NULL; - table = ptdesc_to_virt(ptdesc); + table = ptdesc_address(ptdesc); __arch_set_page_dat(table, 1UL << CRST_ALLOC_ORDER); return table; } @@ -112,14 +116,14 @@ err_p4d: #ifdef CONFIG_PGSTE -struct ptdesc *page_table_alloc_pgste(struct mm_struct *mm) +struct ptdesc *page_table_alloc_pgste_noprof(struct mm_struct *mm) { struct ptdesc *ptdesc; u64 *table; - ptdesc = pagetable_alloc(GFP_KERNEL, 0); + ptdesc = pagetable_alloc_noprof(GFP_KERNEL_ACCOUNT, 0); if (ptdesc) { - table = (u64 *)ptdesc_to_virt(ptdesc); + table = (u64 *)ptdesc_address(ptdesc); __arch_set_page_dat(table, 1); memset64(table, _PAGE_INVALID, PTRS_PER_PTE); memset64(table + PTRS_PER_PTE, 0, PTRS_PER_PTE); @@ -134,19 +138,22 @@ void page_table_free_pgste(struct ptdesc *ptdesc) #endif /* CONFIG_PGSTE */ -unsigned long *page_table_alloc(struct mm_struct *mm) +unsigned long *page_table_alloc_noprof(struct mm_struct *mm) { + gfp_t gfp = GFP_KERNEL_ACCOUNT; struct ptdesc *ptdesc; unsigned long *table; - ptdesc = pagetable_alloc(GFP_KERNEL, 0); + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; + ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } - table = ptdesc_to_virt(ptdesc); + table = ptdesc_address(ptdesc); __arch_set_page_dat(table, 1); memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE); memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 60688be4e876..0fde20bbc50b 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -24,6 +24,7 @@ #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/page-states.h> +#include <asm/pgtable.h> #include <asm/machine.h> pgprot_t pgprot_writecombine(pgprot_t prot) @@ -115,28 +116,6 @@ static inline pte_t ptep_flush_lazy(struct mm_struct *mm, return old; } -static inline pgste_t pgste_get_lock(pte_t *ptep) -{ - unsigned long value = 0; -#ifdef CONFIG_PGSTE - unsigned long *ptr = (unsigned long *)(ptep + PTRS_PER_PTE); - - do { - value = __atomic64_or_barrier(PGSTE_PCL_BIT, ptr); - } while (value & PGSTE_PCL_BIT); - value |= PGSTE_PCL_BIT; -#endif - return __pgste(value); -} - -static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste) -{ -#ifdef CONFIG_PGSTE - barrier(); - WRITE_ONCE(*(unsigned long *)(ptep + PTRS_PER_PTE), pgste_val(pgste) & ~PGSTE_PCL_BIT); -#endif -} - static inline pgste_t pgste_get(pte_t *ptep) { unsigned long pgste = 0; @@ -335,7 +314,6 @@ pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, int nodat; struct mm_struct *mm = vma->vm_mm; - preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT); old = ptep_flush_lazy(mm, addr, ptep, nodat); @@ -360,7 +338,6 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, } else { set_pte(ptep, pte); } - preempt_enable(); } static inline void pmdp_idte_local(struct mm_struct *mm, diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile index 8cab6deb0403..9275cf63192a 100644 --- a/arch/s390/net/Makefile +++ b/arch/s390/net/Makefile @@ -2,5 +2,5 @@ # # Arch-specific network modules # -obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o +obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o obj-$(CONFIG_HAVE_PNETID) += pnet.o diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index bb17efe29d65..cf461d76e9da 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -675,20 +675,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, struct bpf_prog *fp) } while (0) /* - * Call r1 either directly or via __s390_indirect_jump_r1 thunk - */ -static void call_r1(struct bpf_jit *jit) -{ - if (nospec_uses_trampoline()) - /* brasl %r14,__s390_indirect_jump_r1 */ - EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, - __s390_indirect_jump_r1); - else - /* basr %r14,%r1 */ - EMIT2(0x0d00, REG_14, REG_1); -} - -/* * Function epilogue */ static void bpf_jit_epilogue(struct bpf_jit *jit) @@ -1790,20 +1776,21 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, REG_SET_SEEN(BPF_REG_5); jit->seen |= SEEN_FUNC; + /* * Copy the tail call counter to where the callee expects it. - * - * Note 1: The callee can increment the tail call counter, but - * we do not load it back, since the x86 JIT does not do this - * either. - * - * Note 2: We assume that the verifier does not let us call the - * main program, which clears the tail call counter on entry. */ - /* mvc tail_call_cnt(4,%r15),frame_off+tail_call_cnt(%r15) */ - _EMIT6(0xd203f000 | offsetof(struct prog_frame, tail_call_cnt), - 0xf000 | (jit->frame_off + - offsetof(struct prog_frame, tail_call_cnt))); + + if (insn->src_reg == BPF_PSEUDO_CALL) + /* + * mvc tail_call_cnt(4,%r15), + * frame_off+tail_call_cnt(%r15) + */ + _EMIT6(0xd203f000 | offsetof(struct prog_frame, + tail_call_cnt), + 0xf000 | (jit->frame_off + + offsetof(struct prog_frame, + tail_call_cnt))); /* Sign-extend the kfunc arguments. */ if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { @@ -1819,12 +1806,38 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, } } - /* lgrl %w1,func */ - EMIT6_PCREL_RILB(0xc4080000, REG_W1, _EMIT_CONST_U64(func)); - /* %r1() */ - call_r1(jit); - /* lgr %b0,%r2: load return value into %b0 */ - EMIT4(0xb9040000, BPF_REG_0, REG_2); + if ((void *)func == arch_bpf_timed_may_goto) { + /* + * arch_bpf_timed_may_goto() has a special ABI: the + * parameters are in BPF_REG_AX and BPF_REG_10; the + * return value is in BPF_REG_AX; and all GPRs except + * REG_W0, REG_W1, and BPF_REG_AX are callee-saved. + */ + + /* brasl %r0,func */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_0, (void *)func); + } else { + /* brasl %r14,func */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, (void *)func); + /* lgr %b0,%r2: load return value into %b0 */ + EMIT4(0xb9040000, BPF_REG_0, REG_2); + } + + /* + * Copy the potentially updated tail call counter back. + */ + + if (insn->src_reg == BPF_PSEUDO_CALL) + /* + * mvc frame_off+tail_call_cnt(%r15), + * tail_call_cnt(4,%r15) + */ + _EMIT6(0xd203f000 | (jit->frame_off + + offsetof(struct prog_frame, + tail_call_cnt)), + 0xf000 | offsetof(struct prog_frame, + tail_call_cnt)); + break; } case BPF_JMP | BPF_TAIL_CALL: { @@ -2517,14 +2530,12 @@ static int invoke_bpf_prog(struct bpf_tramp_jit *tjit, * goto skip; */ - /* %r1 = __bpf_prog_enter */ - load_imm64(jit, REG_1, (u64)bpf_trampoline_enter(p)); /* %r2 = p */ load_imm64(jit, REG_2, (u64)p); /* la %r3,run_ctx_off(%r15) */ EMIT4_DISP(0x41000000, REG_3, REG_15, tjit->run_ctx_off); - /* %r1() */ - call_r1(jit); + /* brasl %r14,__bpf_prog_enter */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, bpf_trampoline_enter(p)); /* ltgr %r7,%r2 */ EMIT4(0xb9020000, REG_7, REG_2); /* brcl 8,skip */ @@ -2535,15 +2546,13 @@ static int invoke_bpf_prog(struct bpf_tramp_jit *tjit, * retval = bpf_func(args, p->insnsi); */ - /* %r1 = p->bpf_func */ - load_imm64(jit, REG_1, (u64)p->bpf_func); /* la %r2,bpf_args_off(%r15) */ EMIT4_DISP(0x41000000, REG_2, REG_15, tjit->bpf_args_off); /* %r3 = p->insnsi */ if (!p->jited) load_imm64(jit, REG_3, (u64)p->insnsi); - /* %r1() */ - call_r1(jit); + /* brasl %r14,p->bpf_func */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, p->bpf_func); /* stg %r2,retval_off(%r15) */ if (save_ret) { if (sign_extend(jit, REG_2, m->ret_size, m->ret_flags)) @@ -2560,16 +2569,14 @@ static int invoke_bpf_prog(struct bpf_tramp_jit *tjit, * __bpf_prog_exit(p, start, &run_ctx); */ - /* %r1 = __bpf_prog_exit */ - load_imm64(jit, REG_1, (u64)bpf_trampoline_exit(p)); /* %r2 = p */ load_imm64(jit, REG_2, (u64)p); /* lgr %r3,%r7 */ EMIT4(0xb9040000, REG_3, REG_7); /* la %r4,run_ctx_off(%r15) */ EMIT4_DISP(0x41000000, REG_4, REG_15, tjit->run_ctx_off); - /* %r1() */ - call_r1(jit); + /* brasl %r14,__bpf_prog_exit */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, bpf_trampoline_exit(p)); return 0; } @@ -2729,9 +2736,6 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, /* lgr %r8,%r0 */ EMIT4(0xb9040000, REG_8, REG_0); - } else { - /* %r8 = func_addr + S390X_PATCH_SIZE */ - load_imm64(jit, REG_8, (u64)func_addr + S390X_PATCH_SIZE); } /* @@ -2757,12 +2761,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, * __bpf_tramp_enter(im); */ - /* %r1 = __bpf_tramp_enter */ - load_imm64(jit, REG_1, (u64)__bpf_tramp_enter); /* %r2 = im */ load_imm64(jit, REG_2, (u64)im); - /* %r1() */ - call_r1(jit); + /* brasl %r14,__bpf_tramp_enter */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, __bpf_tramp_enter); } for (i = 0; i < fentry->nr_links; i++) @@ -2815,13 +2817,25 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, /* mvc tail_call_cnt(4,%r15),tccnt_off(%r15) */ _EMIT6(0xd203f000 | offsetof(struct prog_frame, tail_call_cnt), 0xf000 | tjit->tccnt_off); - /* lgr %r1,%r8 */ - EMIT4(0xb9040000, REG_1, REG_8); - /* %r1() */ - call_r1(jit); + if (flags & BPF_TRAMP_F_ORIG_STACK) { + if (nospec_uses_trampoline()) + /* brasl %r14,__s390_indirect_jump_r8 */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, + __s390_indirect_jump_r8); + else + /* basr %r14,%r8 */ + EMIT2(0x0d00, REG_14, REG_8); + } else { + /* brasl %r14,func_addr+S390X_PATCH_SIZE */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, + func_addr + S390X_PATCH_SIZE); + } /* stg %r2,retval_off(%r15) */ EMIT6_DISP_LH(0xe3000000, 0x0024, REG_2, REG_0, REG_15, tjit->retval_off); + /* mvc tccnt_off(%r15),tail_call_cnt(4,%r15) */ + _EMIT6(0xd203f000 | tjit->tccnt_off, + 0xf000 | offsetof(struct prog_frame, tail_call_cnt)); im->ip_after_call = jit->prg_buf + jit->prg; @@ -2846,12 +2860,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, * __bpf_tramp_exit(im); */ - /* %r1 = __bpf_tramp_exit */ - load_imm64(jit, REG_1, (u64)__bpf_tramp_exit); /* %r2 = im */ load_imm64(jit, REG_2, (u64)im); - /* %r1() */ - call_r1(jit); + /* brasl %r14,__bpf_tramp_exit */ + EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, __bpf_tramp_exit); } /* lmg %r2,%rN,reg_args_off(%r15) */ @@ -2860,7 +2872,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, REG_2 + (nr_reg_args - 1), REG_15, tjit->reg_args_off); /* lgr %r1,%r8 */ - if (!(flags & BPF_TRAMP_F_SKIP_FRAME)) + if (!(flags & BPF_TRAMP_F_SKIP_FRAME) && + (flags & BPF_TRAMP_F_ORIG_STACK)) EMIT4(0xb9040000, REG_1, REG_8); /* lmg %r7,%r8,r7_r8_off(%r15) */ EMIT6_DISP_LH(0xeb000000, 0x0004, REG_7, REG_8, REG_15, @@ -2879,9 +2892,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, EMIT4_IMM(0xa70b0000, REG_15, tjit->stack_size); if (flags & BPF_TRAMP_F_SKIP_FRAME) EMIT_JUMP_REG(14); - else + else if (flags & BPF_TRAMP_F_ORIG_STACK) EMIT_JUMP_REG(1); - + else + /* brcl 0xf,func_addr+S390X_PATCH_SIZE */ + EMIT6_PCREL_RILC_PTR(0xc0040000, 0xf, + func_addr + S390X_PATCH_SIZE); return 0; } @@ -2951,6 +2967,11 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) case BPF_STX | BPF_ATOMIC | BPF_DW: if (bpf_atomic_is_load_store(insn)) return false; + break; + case BPF_LDX | BPF_MEMSX | BPF_B: + case BPF_LDX | BPF_MEMSX | BPF_H: + case BPF_LDX | BPF_MEMSX | BPF_W: + return false; } return true; } @@ -2989,3 +3010,8 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *, u64, u64, u64), prev_addr = addr; } } + +bool bpf_jit_supports_timed_may_goto(void) +{ + return true; +} diff --git a/arch/s390/net/bpf_timed_may_goto.S b/arch/s390/net/bpf_timed_may_goto.S new file mode 100644 index 000000000000..06f567a460d7 --- /dev/null +++ b/arch/s390/net/bpf_timed_may_goto.S @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/export.h> +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/nospec-insn.h> + +#define R2_OFF 0 +#define R5_OFF (R2_OFF + (5 - 2 + 1) * 8) +#define R14_OFF (R5_OFF + 8) +#define RETADDR_OFF (R14_OFF + 8) +#define R15_OFF (RETADDR_OFF + 8) +#define BACKCHAIN_OFF (R15_OFF + 8) +#define FRAME_SIZE (BACKCHAIN_OFF + 8) +#define FRAME_OFF (STACK_FRAME_OVERHEAD - FRAME_SIZE) +#if (FRAME_OFF + BACKCHAIN_OFF) != __SF_BACKCHAIN +#error Stack frame layout calculation is broken +#endif + + GEN_BR_THUNK %r1 + +SYM_FUNC_START(arch_bpf_timed_may_goto) + /* + * This function has a special ABI: the parameters are in %r12 and + * %r13; the return value is in %r12; all GPRs except %r0, %r1, and + * %r12 are callee-saved; and the return address is in %r0. + */ + stmg %r2,%r5,FRAME_OFF+R2_OFF(%r15) + stg %r14,FRAME_OFF+R14_OFF(%r15) + stg %r0,FRAME_OFF+RETADDR_OFF(%r15) + stg %r15,FRAME_OFF+R15_OFF(%r15) + lgr %r1,%r15 + lay %r15,-FRAME_SIZE(%r15) + stg %r1,__SF_BACKCHAIN(%r15) + + lay %r2,0(%r12,%r13) + brasl %r14,bpf_check_timed_may_goto + lgr %r12,%r2 + + lg %r15,FRAME_SIZE+FRAME_OFF+R15_OFF(%r15) + lmg %r2,%r5,FRAME_OFF+R2_OFF(%r15) + lg %r14,FRAME_OFF+R14_OFF(%r15) + lg %r1,FRAME_OFF+RETADDR_OFF(%r15) + BR_EX %r1 +SYM_FUNC_END(arch_bpf_timed_may_goto) |