diff options
88 files changed, 850 insertions, 1084 deletions
diff --git a/Documentation/devicetree/bindings/dma/mv-xor-v2.txt b/Documentation/devicetree/bindings/dma/mv-xor-v2.txt index 217a90eaabe7..9c38bbe7e6d7 100644 --- a/Documentation/devicetree/bindings/dma/mv-xor-v2.txt +++ b/Documentation/devicetree/bindings/dma/mv-xor-v2.txt @@ -11,7 +11,11 @@ Required properties: interrupts. Optional properties: -- clocks: Optional reference to the clock used by the XOR engine. +- clocks: Optional reference to the clocks used by the XOR engine. +- clock-names: mandatory if there is a second clock, in this case the + name must be "core" for the first clock and "reg" for the second + one + Example: @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index eb7f43f23521..0fa71a78ec99 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2307,7 +2307,7 @@ choice it can be used to assist security vulnerability exploitation. This setting can be changed at boot time via the kernel command - line parameter vsyscall=[native|emulate|none]. + line parameter vsyscall=[emulate|none]. On a system with recent enough glibc (2.14 or newer) and no static binaries, you can say None without a performance penalty @@ -2315,15 +2315,6 @@ choice If unsure, select "Emulate". - config LEGACY_VSYSCALL_NATIVE - bool "Native" - help - Actual executable code is located in the fixed vsyscall - address mapping, implementing time() efficiently. Since - this makes the mapping executable, it can be used during - security vulnerability exploitation (traditionally as - ROP gadgets). This configuration is not recommended. - config LEGACY_VSYSCALL_EMULATE bool "Emulate" help diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index e811dd9c5e99..08425c42f8b7 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -363,9 +363,7 @@ ENTRY(entry_INT80_compat) pushq 2*8(%rdi) /* regs->ip */ pushq 1*8(%rdi) /* regs->orig_ax */ - movq (%rdi), %rdi /* restore %rdi */ - - pushq %rdi /* pt_regs->di */ + pushq (%rdi) /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ @@ -406,15 +404,3 @@ ENTRY(entry_INT80_compat) TRACE_IRQS_ON jmp swapgs_restore_regs_and_return_to_usermode END(entry_INT80_compat) - -ENTRY(stub32_clone) - /* - * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr). - * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val). - * - * The native 64-bit kernel's sys_clone() implements the latter, - * so we need to swap arguments here before calling it: - */ - xchg %r8, %rcx - jmp sys_clone -ENDPROC(stub32_clone) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 448ac2161112..2a5e99cff859 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -8,12 +8,12 @@ # 0 i386 restart_syscall sys_restart_syscall 1 i386 exit sys_exit -2 i386 fork sys_fork sys_fork +2 i386 fork sys_fork 3 i386 read sys_read 4 i386 write sys_write 5 i386 open sys_open compat_sys_open 6 i386 close sys_close -7 i386 waitpid sys_waitpid sys32_waitpid +7 i386 waitpid sys_waitpid compat_sys_x86_waitpid 8 i386 creat sys_creat 9 i386 link sys_link 10 i386 unlink sys_unlink @@ -78,7 +78,7 @@ 69 i386 ssetmask sys_ssetmask 70 i386 setreuid sys_setreuid16 71 i386 setregid sys_setregid16 -72 i386 sigsuspend sys_sigsuspend sys_sigsuspend +72 i386 sigsuspend sys_sigsuspend 73 i386 sigpending sys_sigpending compat_sys_sigpending 74 i386 sethostname sys_sethostname 75 i386 setrlimit sys_setrlimit compat_sys_setrlimit @@ -96,7 +96,7 @@ 87 i386 swapon sys_swapon 88 i386 reboot sys_reboot 89 i386 readdir sys_old_readdir compat_sys_old_readdir -90 i386 mmap sys_old_mmap sys32_mmap +90 i386 mmap sys_old_mmap compat_sys_x86_mmap 91 i386 munmap sys_munmap 92 i386 truncate sys_truncate compat_sys_truncate 93 i386 ftruncate sys_ftruncate compat_sys_ftruncate @@ -126,7 +126,7 @@ 117 i386 ipc sys_ipc compat_sys_ipc 118 i386 fsync sys_fsync 119 i386 sigreturn sys_sigreturn sys32_sigreturn -120 i386 clone sys_clone stub32_clone +120 i386 clone sys_clone compat_sys_x86_clone 121 i386 setdomainname sys_setdomainname 122 i386 uname sys_newuname 123 i386 modify_ldt sys_modify_ldt @@ -186,8 +186,8 @@ 177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 i386 rt_sigsuspend sys_rt_sigsuspend -180 i386 pread64 sys_pread64 sys32_pread -181 i386 pwrite64 sys_pwrite64 sys32_pwrite +180 i386 pread64 sys_pread64 compat_sys_x86_pread +181 i386 pwrite64 sys_pwrite64 compat_sys_x86_pwrite 182 i386 chown sys_chown16 183 i386 getcwd sys_getcwd 184 i386 capget sys_capget @@ -196,14 +196,14 @@ 187 i386 sendfile sys_sendfile compat_sys_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork sys_vfork sys_vfork +190 i386 vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff -193 i386 truncate64 sys_truncate64 sys32_truncate64 -194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64 -195 i386 stat64 sys_stat64 sys32_stat64 -196 i386 lstat64 sys_lstat64 sys32_lstat64 -197 i386 fstat64 sys_fstat64 sys32_fstat64 +193 i386 truncate64 sys_truncate64 compat_sys_x86_truncate64 +194 i386 ftruncate64 sys_ftruncate64 compat_sys_x86_ftruncate64 +195 i386 stat64 sys_stat64 compat_sys_x86_stat64 +196 i386 lstat64 sys_lstat64 compat_sys_x86_lstat64 +197 i386 fstat64 sys_fstat64 compat_sys_x86_fstat64 198 i386 lchown32 sys_lchown 199 i386 getuid32 sys_getuid 200 i386 getgid32 sys_getgid @@ -231,7 +231,7 @@ # 222 is unused # 223 is unused 224 i386 gettid sys_gettid -225 i386 readahead sys_readahead sys32_readahead +225 i386 readahead sys_readahead compat_sys_x86_readahead 226 i386 setxattr sys_setxattr 227 i386 lsetxattr sys_lsetxattr 228 i386 fsetxattr sys_fsetxattr @@ -256,7 +256,7 @@ 247 i386 io_getevents sys_io_getevents compat_sys_io_getevents 248 i386 io_submit sys_io_submit compat_sys_io_submit 249 i386 io_cancel sys_io_cancel -250 i386 fadvise64 sys_fadvise64 sys32_fadvise64 +250 i386 fadvise64 sys_fadvise64 compat_sys_x86_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) 252 i386 exit_group sys_exit_group 253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie @@ -278,7 +278,7 @@ 269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 270 i386 tgkill sys_tgkill 271 i386 utimes sys_utimes compat_sys_utimes -272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64 +272 i386 fadvise64_64 sys_fadvise64_64 compat_sys_x86_fadvise64_64 273 i386 vserver 274 i386 mbind sys_mbind 275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy @@ -306,7 +306,7 @@ 297 i386 mknodat sys_mknodat 298 i386 fchownat sys_fchownat 299 i386 futimesat sys_futimesat compat_sys_futimesat -300 i386 fstatat64 sys_fstatat64 sys32_fstatat +300 i386 fstatat64 sys_fstatat64 compat_sys_x86_fstatat 301 i386 unlinkat sys_unlinkat 302 i386 renameat sys_renameat 303 i386 linkat sys_linkat @@ -320,7 +320,7 @@ 311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list 312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list 313 i386 splice sys_splice -314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range +314 i386 sync_file_range sys_sync_file_range compat_sys_x86_sync_file_range 315 i386 tee sys_tee 316 i386 vmsplice sys_vmsplice compat_sys_vmsplice 317 i386 move_pages sys_move_pages compat_sys_move_pages @@ -330,7 +330,7 @@ 321 i386 signalfd sys_signalfd compat_sys_signalfd 322 i386 timerfd_create sys_timerfd_create 323 i386 eventfd sys_eventfd -324 i386 fallocate sys_fallocate sys32_fallocate +324 i386 fallocate sys_fallocate compat_sys_x86_fallocate 325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime 326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime 327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4 diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 577fa8adb785..8560ef68a9d6 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -42,10 +42,8 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = -#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE) - NATIVE; -#elif defined(CONFIG_LEGACY_VSYSCALL_NONE) +static enum { EMULATE, NONE } vsyscall_mode = +#ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #else EMULATE; @@ -56,8 +54,6 @@ static int __init vsyscall_setup(char *str) if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; - else if (!strcmp("native", str)) - vsyscall_mode = NATIVE; else if (!strcmp("none", str)) vsyscall_mode = NONE; else @@ -139,10 +135,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) WARN_ON_ONCE(address != regs->ip); - /* This should be unreachable in NATIVE mode. */ - if (WARN_ON(vsyscall_mode == NATIVE)) - return false; - if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); @@ -370,9 +362,7 @@ void __init map_vsyscall(void) if (vsyscall_mode != NONE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 6d8044ab1060..22ec65bc033a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3606,7 +3606,7 @@ static struct intel_uncore_type skx_uncore_imc = { }; static struct attribute *skx_upi_uncore_formats_attr[] = { - &format_attr_event_ext.attr, + &format_attr_event.attr, &format_attr_umask_ext.attr, &format_attr_edge.attr, &format_attr_inv.attr, diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 96cd33bbfc85..6512498bbef6 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -51,15 +51,14 @@ #define AA(__x) ((unsigned long)(__x)) -asmlinkage long sys32_truncate64(const char __user *filename, - unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename, + unsigned long, offset_low, unsigned long, offset_high) { return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low); } -asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd, + unsigned long, offset_low, unsigned long, offset_high) { return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); } @@ -96,8 +95,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) return 0; } -asmlinkage long sys32_stat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_stat(filename, &stat); @@ -107,8 +106,8 @@ asmlinkage long sys32_stat64(const char __user *filename, return ret; } -asmlinkage long sys32_lstat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_lstat(filename, &stat); @@ -117,7 +116,8 @@ asmlinkage long sys32_lstat64(const char __user *filename, return ret; } -asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_fstat(fd, &stat); @@ -126,8 +126,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) return ret; } -asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag) +COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd, + const char __user *, filename, + struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; @@ -153,7 +154,7 @@ struct mmap_arg_struct32 { unsigned int offset; }; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) +COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) { struct mmap_arg_struct32 a; @@ -167,22 +168,22 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) a.offset>>PAGE_SHIFT); } -asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr, - int options) +COMPAT_SYSCALL_DEFINE3(x86_waitpid, compat_pid_t, pid, unsigned int __user *, + stat_addr, int, options) { return compat_sys_wait4(pid, stat_addr, options, NULL); } /* warning: next two assume little endian */ -asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, - u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); } -asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, - u32 count, u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); @@ -193,8 +194,9 @@ asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, * Some system calls that need sign extended arguments. This could be * done by a generic wrapper. */ -long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, - __u32 len_low, __u32 len_high, int advice) +COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low, + __u32, offset_high, __u32, len_low, __u32, len_high, + int, advice) { return sys_fadvise64_64(fd, (((u64)offset_high)<<32) | offset_low, @@ -202,31 +204,43 @@ long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, advice); } -asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi, - size_t count) +COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo, + unsigned int, off_hi, size_t, count) { return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); } -asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi, - unsigned n_low, unsigned n_hi, int flags) +COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, + unsigned int, off_hi, unsigned int, n_low, + unsigned int, n_hi, int, flags) { return sys_sync_file_range(fd, ((u64)off_hi << 32) | off_low, ((u64)n_hi << 32) | n_low, flags); } -asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi, - size_t len, int advice) +COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo, + unsigned int, offset_hi, size_t, len, int, advice) { return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, len, advice); } -asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo, - unsigned offset_hi, unsigned len_lo, - unsigned len_hi) +COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, + unsigned int, offset_lo, unsigned int, offset_hi, + unsigned int, len_lo, unsigned int, len_hi) { return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, ((u64)len_hi << 32) | len_lo); } + +/* + * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS + */ +COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags, + unsigned long, newsp, int __user *, parent_tidptr, + unsigned long, tls_val, int __user *, child_tidptr) +{ + return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr, + tls_val); +} diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 246f15b4e64c..acfe755562a6 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -174,7 +174,6 @@ enum page_cache_mode { #define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) #define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) #define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) -#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER) #define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) @@ -206,7 +205,6 @@ enum page_cache_mode { #define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) #define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC) #define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) #define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index d6baf23782bc..5c019d23d06b 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -10,6 +10,7 @@ extern struct exception_table_entry __stop___ex_table[]; #if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; +extern char __entry_trampoline_start[], __entry_trampoline_end[]; #endif #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 82c34ee25a65..906794aa034e 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -20,31 +20,43 @@ #include <asm/ia32.h> /* ia32/sys_ia32.c */ -asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long); -asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long); +asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long, + unsigned long); +asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long, + unsigned long); -asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *); -asmlinkage long sys32_fstatat(unsigned int, const char __user *, +asmlinkage long compat_sys_x86_stat64(const char __user *, + struct stat64 __user *); +asmlinkage long compat_sys_x86_lstat64(const char __user *, + struct stat64 __user *); +asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *); +asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *, struct stat64 __user *, int); struct mmap_arg_struct32; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *); +asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *); -asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int); +asmlinkage long compat_sys_x86_waitpid(compat_pid_t, unsigned int __user *, + int); -asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); -asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); +asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32, + u32); +asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32, + u32, u32); -long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int); -long sys32_vm86_warning(void); +asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32, + int); -asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t); -asmlinkage long sys32_sync_file_range(int, unsigned, unsigned, - unsigned, unsigned, int); -asmlinkage long sys32_fadvise64(int, unsigned, unsigned, size_t, int); -asmlinkage long sys32_fallocate(int, int, unsigned, - unsigned, unsigned, unsigned); +asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int, + size_t); +asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int, + unsigned int, unsigned int, + int); +asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int, + size_t, int); +asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int, + unsigned int, unsigned int); +asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *, + unsigned long, int __user *); /* ia32/ia32_signal.c */ asmlinkage long sys32_sigreturn(void); diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 91723461dc1f..435db58a7bad 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -30,6 +30,7 @@ struct mce { __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */ __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ __u64 ppin; /* Protected Processor Inventory Number */ + __u32 microcode;/* Microcode revision */ }; #define MCE_GET_RECORD_LEN _IOR('M', 1, int) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index d19e903214b4..4aa9fd379390 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -144,6 +144,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) { int i; + /* + * We know that the hypervisor lie to us on the microcode version so + * we may as well hope that it is running the correct version. + */ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && c->x86_stepping == spectre_bad_microcodes[i].stepping) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8ff94d1e2dce..466f47301334 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -56,6 +56,9 @@ static DEFINE_MUTEX(mce_log_mutex); +/* sysfs synchronization */ +static DEFINE_MUTEX(mce_sysfs_mutex); + #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -130,6 +133,8 @@ void mce_setup(struct mce *m) if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) rdmsrl(MSR_PPIN, m->ppin); + + m->microcode = boot_cpu_data.microcode; } DEFINE_PER_CPU(struct mce, injectm); @@ -262,7 +267,7 @@ static void __print_mce(struct mce *m) */ pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, - cpu_data(m->extcpu).microcode); + m->microcode); } static void print_mce(struct mce *m) @@ -2086,6 +2091,7 @@ static ssize_t set_ignore_ce(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.ignore_ce ^ !!new) { if (new) { /* disable ce features */ @@ -2098,6 +2104,8 @@ static ssize_t set_ignore_ce(struct device *s, on_each_cpu(mce_enable_ce, (void *)1, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2110,6 +2118,7 @@ static ssize_t set_cmci_disabled(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.cmci_disabled ^ !!new) { if (new) { /* disable cmci */ @@ -2121,6 +2130,8 @@ static ssize_t set_cmci_disabled(struct device *s, on_each_cpu(mce_enable_ce, NULL, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2128,8 +2139,19 @@ static ssize_t store_int_with_restart(struct device *s, struct device_attribute *attr, const char *buf, size_t size) { - ssize_t ret = device_store_int(s, attr, buf, size); + unsigned long old_check_interval = check_interval; + ssize_t ret = device_store_ulong(s, attr, buf, size); + + if (check_interval == old_check_interval) + return ret; + + if (check_interval < 1) + check_interval = 1; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); + return ret; } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index aa1b9a422f2b..70ecbc8099c9 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -22,13 +22,16 @@ #define pr_fmt(fmt) "microcode: " fmt #include <linux/platform_device.h> +#include <linux/stop_machine.h> #include <linux/syscore_ops.h> #include <linux/miscdevice.h> #include <linux/capability.h> #include <linux/firmware.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/mutex.h> #include <linux/cpu.h> +#include <linux/nmi.h> #include <linux/fs.h> #include <linux/mm.h> @@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache); */ static DEFINE_MUTEX(microcode_mutex); +/* + * Serialize late loading so that CPUs get updated one-by-one. + */ +static DEFINE_SPINLOCK(update_lock); + struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu) return ret; } -struct apply_microcode_ctx { - enum ucode_state err; -}; - static void apply_microcode_local(void *arg) { - struct apply_microcode_ctx *ctx = arg; + enum ucode_state *err = arg; - ctx->err = microcode_ops->apply_microcode(smp_processor_id()); + *err = microcode_ops->apply_microcode(smp_processor_id()); } static int apply_microcode_on_target(int cpu) { - struct apply_microcode_ctx ctx = { .err = 0 }; + enum ucode_state err; int ret; - ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1); - if (!ret) - ret = ctx.err; - + ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1); + if (!ret) { + if (err == UCODE_ERROR) + ret = 1; + } return ret; } @@ -489,19 +494,100 @@ static void __exit microcode_dev_exit(void) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; -static enum ucode_state reload_for_cpu(int cpu) +/* + * Late loading dance. Why the heavy-handed stomp_machine effort? + * + * - HT siblings must be idle and not execute other code while the other sibling + * is loading microcode in order to avoid any negative interactions caused by + * the loading. + * + * - In addition, microcode update on the cores must be serialized until this + * requirement can be relaxed in the future. Right now, this is conservative + * and good. + */ +#define SPINUNIT 100 /* 100 nsec */ + +static int check_online_cpus(void) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; + if (num_online_cpus() == num_present_cpus()) + return 0; - if (!uci->valid) - return UCODE_OK; + pr_err("Not all CPUs online, aborting microcode update.\n"); + + return -EINVAL; +} + +static atomic_t late_cpus; + +/* + * Returns: + * < 0 - on error + * 0 - no update done + * 1 - microcode was updated + */ +static int __reload_late(void *info) +{ + unsigned int timeout = NSEC_PER_SEC; + int all_cpus = num_online_cpus(); + int cpu = smp_processor_id(); + enum ucode_state err; + int ret = 0; + + atomic_dec(&late_cpus); + + /* + * Wait for all CPUs to arrive. A load will not be attempted unless all + * CPUs show up. + * */ + while (atomic_read(&late_cpus)) { + if (timeout < SPINUNIT) { + pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n", + atomic_read(&late_cpus)); + return -1; + } - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); - if (ustate != UCODE_OK) - return ustate; + ndelay(SPINUNIT); + timeout -= SPINUNIT; - return apply_microcode_on_target(cpu); + touch_nmi_watchdog(); + } + + spin_lock(&update_lock); + apply_microcode_local(&err); + spin_unlock(&update_lock); + + if (err > UCODE_NFOUND) { + pr_warn("Error reloading microcode on CPU %d\n", cpu); + ret = -1; + } else if (err == UCODE_UPDATED) { + ret = 1; + } + + atomic_inc(&late_cpus); + + while (atomic_read(&late_cpus) != all_cpus) + cpu_relax(); + + return ret; +} + +/* + * Reload microcode late on all CPUs. Wait for a sec until they + * all gather together. + */ +static int microcode_reload_late(void) +{ + int ret; + + atomic_set(&late_cpus, num_online_cpus()); + + ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); + if (ret < 0) + return ret; + else if (ret > 0) + microcode_check(); + + return ret; } static ssize_t reload_store(struct device *dev, @@ -509,10 +595,9 @@ static ssize_t reload_store(struct device *dev, const char *buf, size_t size) { enum ucode_state tmp_ret = UCODE_OK; - bool do_callback = false; + int bsp = boot_cpu_data.cpu_index; unsigned long val; ssize_t ret = 0; - int cpu; ret = kstrtoul(buf, 0, &val); if (ret) @@ -521,29 +606,24 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; - get_online_cpus(); - mutex_lock(µcode_mutex); - for_each_online_cpu(cpu) { - tmp_ret = reload_for_cpu(cpu); - if (tmp_ret > UCODE_NFOUND) { - pr_warn("Error reloading microcode on CPU %d\n", cpu); - - /* set retval for the first encountered reload error */ - if (!ret) - ret = -EINVAL; - } + tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); + if (tmp_ret != UCODE_OK) + return size; - if (tmp_ret == UCODE_UPDATED) - do_callback = true; - } + get_online_cpus(); - if (!ret && do_callback) - microcode_check(); + ret = check_online_cpus(); + if (ret) + goto put; + mutex_lock(µcode_mutex); + ret = microcode_reload_late(); mutex_unlock(µcode_mutex); + +put: put_online_cpus(); - if (!ret) + if (ret >= 0) ret = size; return ret; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 923054a6b760..2aded9db1d42 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) if (!mc) return 0; + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + return UCODE_OK; + } + + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -774,9 +791,9 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) static enum ucode_state apply_microcode_intel(int cpu) { + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; - struct ucode_cpu_info *uci; - struct cpuinfo_x86 *c; static int prev_rev; u32 rev; @@ -784,15 +801,32 @@ static enum ucode_state apply_microcode_intel(int cpu) if (WARN_ON(raw_smp_processor_id() != cpu)) return UCODE_ERROR; - uci = ucode_cpu_info + cpu; - mc = uci->mc; + /* Look for a newer patch in our cache: */ + mc = find_patch(uci); if (!mc) { - /* Look for a newer patch in our cache: */ - mc = find_patch(uci); + mc = uci->mc; if (!mc) return UCODE_NFOUND; } + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + c->microcode = rev; + return UCODE_OK; + } + + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -813,8 +847,6 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } - c = &cpu_data(cpu); - uci->cpu_sig.rev = rev; c->microcode = rev; diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 2f723301eb58..38deafebb21b 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -23,7 +23,7 @@ /* * this changes the io permissions bitmap in the current task. */ -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) +SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) { struct thread_struct *t = ¤t->thread; struct tss_struct *tss; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index bd36f3c33cd0..0715f827607c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler); bool arch_within_kprobe_blacklist(unsigned long addr) { + bool is_in_entry_trampoline_section = false; + +#ifdef CONFIG_X86_64 + is_in_entry_trampoline_section = + (addr >= (unsigned long)__entry_trampoline_start && + addr < (unsigned long)__entry_trampoline_end); +#endif return (addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end) || (addr >= (unsigned long)__entry_text_start && - addr < (unsigned long)__entry_text_end); + addr < (unsigned long)__entry_text_end) || + is_in_entry_trampoline_section; } int __init arch_init_kprobes(void) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9b138a06c1a4..b854ebf5851b 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -118,9 +118,11 @@ SECTIONS #ifdef CONFIG_X86_64 . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_start) = .; _entry_trampoline = .; *(.entry_trampoline) . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_end) = .; ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index ce38f165489b..631507f0c198 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -332,7 +332,7 @@ static void __init pti_clone_user_shared(void) } /* - * Clone the ESPFIX P4D into the user space visinble page table + * Clone the ESPFIX P4D into the user space visible page table */ static void __init pti_setup_espfix64(void) { diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 87855b5123a6..ee62d2d517bf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -266,7 +266,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) struct iov_iter i; ssize_t bw; - iov_iter_bvec(&i, ITER_BVEC, bvec, 1, bvec->bv_len); + iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index e126e4cac2ca..92ec1bbece51 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -262,6 +262,7 @@ static DEFINE_SPINLOCK(minor_lock); static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo); static void blkfront_gather_backend_features(struct blkfront_info *info); +static int negotiate_mq(struct blkfront_info *info); static int get_id_from_freelist(struct blkfront_ring_info *rinfo) { @@ -1774,11 +1775,18 @@ static int talk_to_blkback(struct xenbus_device *dev, unsigned int i, max_page_order; unsigned int ring_page_order; + if (!info) + return -ENODEV; + max_page_order = xenbus_read_unsigned(info->xbdev->otherend, "max-ring-page-order", 0); ring_page_order = min(xen_blkif_max_ring_order, max_page_order); info->nr_ring_pages = 1 << ring_page_order; + err = negotiate_mq(info); + if (err) + goto destroy_blkring; + for (i = 0; i < info->nr_rings; i++) { struct blkfront_ring_info *rinfo = &info->rinfo[i]; @@ -1978,11 +1986,6 @@ static int blkfront_probe(struct xenbus_device *dev, } info->xbdev = dev; - err = negotiate_mq(info); - if (err) { - kfree(info); - return err; - } mutex_init(&info->mutex); info->vdevice = vdevice; @@ -2099,10 +2102,6 @@ static int blkfront_resume(struct xenbus_device *dev) blkif_free(info, info->connected == BLKIF_STATE_CONNECTED); - err = negotiate_mq(info); - if (err) - return err; - err = talk_to_blkback(dev, info); if (!err) blk_mq_update_nr_hw_queues(&info->tag_set, info->nr_rings); diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index b3b4ed9b6874..d2e5382821a4 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -386,6 +386,7 @@ config ATMEL_PIT config ATMEL_ST bool "Atmel ST timer support" if COMPILE_TEST + depends on HAS_IOMEM select TIMER_OF select MFD_SYSCON help diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index f652a0e0f5a2..3548caa9e933 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -163,6 +163,7 @@ struct mv_xor_v2_device { void __iomem *dma_base; void __iomem *glob_base; struct clk *clk; + struct clk *reg_clk; struct tasklet_struct irq_tasklet; struct list_head free_sw_desc; struct dma_device dmadev; @@ -749,13 +750,26 @@ static int mv_xor_v2_probe(struct platform_device *pdev) if (ret) return ret; + xor_dev->reg_clk = devm_clk_get(&pdev->dev, "reg"); + if (PTR_ERR(xor_dev->reg_clk) != -ENOENT) { + if (!IS_ERR(xor_dev->reg_clk)) { + ret = clk_prepare_enable(xor_dev->reg_clk); + if (ret) + return ret; + } else { + return PTR_ERR(xor_dev->reg_clk); + } + } + xor_dev->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { + ret = EPROBE_DEFER; + goto disable_reg_clk; + } if (!IS_ERR(xor_dev->clk)) { ret = clk_prepare_enable(xor_dev->clk); if (ret) - return ret; + goto disable_reg_clk; } ret = platform_msi_domain_alloc_irqs(&pdev->dev, 1, @@ -866,8 +880,9 @@ free_hw_desq: free_msi_irqs: platform_msi_domain_free_irqs(&pdev->dev); disable_clk: - if (!IS_ERR(xor_dev->clk)) - clk_disable_unprepare(xor_dev->clk); + clk_disable_unprepare(xor_dev->clk); +disable_reg_clk: + clk_disable_unprepare(xor_dev->reg_clk); return ret; } diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index e3ff162c03fc..d0cacdb0713e 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -917,7 +917,7 @@ rcar_dmac_chan_prep_sg(struct rcar_dmac_chan *chan, struct scatterlist *sgl, rcar_dmac_chan_configure_desc(chan, desc); - max_chunk_size = (RCAR_DMATCR_MASK + 1) << desc->xfer_shift; + max_chunk_size = RCAR_DMATCR_MASK << desc->xfer_shift; /* * Allocate and fill the transfer chunk descriptors. We own the only diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index e76de57dd617..ebaea8b1594b 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -14,7 +14,6 @@ * GNU General Public License for more details. */ -#include <linux/clk.h> #include <linux/err.h> #include <linux/gpio.h> #include <linux/init.h> @@ -37,10 +36,9 @@ struct gpio_rcar_priv { struct platform_device *pdev; struct gpio_chip gpio_chip; struct irq_chip irq_chip; - struct clk *clk; unsigned int irq_parent; + atomic_t wakeup_path; bool has_both_edge_trigger; - bool needs_clk; }; #define IOINTSEL 0x00 /* General IO/Interrupt Switching Register */ @@ -186,13 +184,10 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on) } } - if (!p->clk) - return 0; - if (on) - clk_enable(p->clk); + atomic_inc(&p->wakeup_path); else - clk_disable(p->clk); + atomic_dec(&p->wakeup_path); return 0; } @@ -330,17 +325,14 @@ static int gpio_rcar_direction_output(struct gpio_chip *chip, unsigned offset, struct gpio_rcar_info { bool has_both_edge_trigger; - bool needs_clk; }; static const struct gpio_rcar_info gpio_rcar_info_gen1 = { .has_both_edge_trigger = false, - .needs_clk = false, }; static const struct gpio_rcar_info gpio_rcar_info_gen2 = { .has_both_edge_trigger = true, - .needs_clk = true, }; static const struct of_device_id gpio_rcar_of_table[] = { @@ -403,7 +395,6 @@ static int gpio_rcar_parse_dt(struct gpio_rcar_priv *p, unsigned int *npins) ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args); *npins = ret == 0 ? args.args[2] : RCAR_MAX_GPIO_PER_BANK; p->has_both_edge_trigger = info->has_both_edge_trigger; - p->needs_clk = info->needs_clk; if (*npins == 0 || *npins > RCAR_MAX_GPIO_PER_BANK) { dev_warn(&p->pdev->dev, @@ -440,16 +431,6 @@ static int gpio_rcar_probe(struct platform_device *pdev) platform_set_drvdata(pdev, p); - p->clk = devm_clk_get(dev, NULL); - if (IS_ERR(p->clk)) { - if (p->needs_clk) { - dev_err(dev, "unable to get clock\n"); - ret = PTR_ERR(p->clk); - goto err0; - } - p->clk = NULL; - } - pm_runtime_enable(dev); irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); @@ -531,11 +512,24 @@ static int gpio_rcar_remove(struct platform_device *pdev) return 0; } +static int __maybe_unused gpio_rcar_suspend(struct device *dev) +{ + struct gpio_rcar_priv *p = dev_get_drvdata(dev); + + if (atomic_read(&p->wakeup_path)) + device_set_wakeup_path(dev); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(gpio_rcar_pm_ops, gpio_rcar_suspend, NULL); + static struct platform_driver gpio_rcar_device_driver = { .probe = gpio_rcar_probe, .remove = gpio_rcar_remove, .driver = { .name = "gpio_rcar", + .pm = &gpio_rcar_pm_ops, .of_match_table = of_match_ptr(gpio_rcar_of_table), } }; diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index a5b4cf030c11..9183d148d644 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -550,18 +550,13 @@ static int addr_resolve(struct sockaddr *src_in, dst_release(dst); } - if (ndev->flags & IFF_LOOPBACK) { - ret = rdma_translate_ip(dst_in, addr); - /* - * Put the loopback device and get the translated - * device instead. - */ + if (ndev) { + if (ndev->flags & IFF_LOOPBACK) + ret = rdma_translate_ip(dst_in, addr); + else + addr->bound_dev_if = ndev->ifindex; dev_put(ndev); - ndev = dev_get_by_index(addr->net, addr->bound_dev_if); - } else { - addr->bound_dev_if = ndev->ifindex; } - dev_put(ndev); return ret; } diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c index bc79ca8215d7..af5ad6a56ae4 100644 --- a/drivers/infiniband/core/cq.c +++ b/drivers/infiniband/core/cq.c @@ -17,6 +17,7 @@ /* # of WCs to poll for with a single call to ib_poll_cq */ #define IB_POLL_BATCH 16 +#define IB_POLL_BATCH_DIRECT 8 /* # of WCs to iterate over before yielding */ #define IB_POLL_BUDGET_IRQ 256 @@ -25,18 +26,18 @@ #define IB_POLL_FLAGS \ (IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS) -static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) +static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs, + int batch) { int i, n, completed = 0; - struct ib_wc *wcs = poll_wc ? : cq->wc; /* * budget might be (-1) if the caller does not * want to bound this call, thus we need unsigned * minimum here. */ - while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH, - budget - completed), wcs)) > 0) { + while ((n = ib_poll_cq(cq, min_t(u32, batch, + budget - completed), wcs)) > 0) { for (i = 0; i < n; i++) { struct ib_wc *wc = &wcs[i]; @@ -48,8 +49,7 @@ static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) completed += n; - if (n != IB_POLL_BATCH || - (budget != -1 && completed >= budget)) + if (n != batch || (budget != -1 && completed >= budget)) break; } @@ -72,9 +72,9 @@ static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) */ int ib_process_cq_direct(struct ib_cq *cq, int budget) { - struct ib_wc wcs[IB_POLL_BATCH]; + struct ib_wc wcs[IB_POLL_BATCH_DIRECT]; - return __ib_process_cq(cq, budget, wcs); + return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT); } EXPORT_SYMBOL(ib_process_cq_direct); @@ -88,7 +88,7 @@ static int ib_poll_handler(struct irq_poll *iop, int budget) struct ib_cq *cq = container_of(iop, struct ib_cq, iop); int completed; - completed = __ib_process_cq(cq, budget, NULL); + completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH); if (completed < budget) { irq_poll_complete(&cq->iop); if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) @@ -108,7 +108,8 @@ static void ib_cq_poll_work(struct work_struct *work) struct ib_cq *cq = container_of(work, struct ib_cq, work); int completed; - completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, NULL); + completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc, + IB_POLL_BATCH); if (completed >= IB_POLL_BUDGET_WORKQUEUE || ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) queue_work(ib_comp_wq, &cq->work); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index e8010e73a1cf..bb065c9449be 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -536,14 +536,14 @@ int ib_register_device(struct ib_device *device, ret = device->query_device(device, &device->attrs, &uhw); if (ret) { pr_warn("Couldn't query the device attributes\n"); - goto cache_cleanup; + goto cg_cleanup; } ret = ib_device_register_sysfs(device, port_callback); if (ret) { pr_warn("Couldn't register device %s with driver model\n", device->name); - goto cache_cleanup; + goto cg_cleanup; } device->reg_state = IB_DEV_REGISTERED; @@ -559,6 +559,8 @@ int ib_register_device(struct ib_device *device, mutex_unlock(&device_mutex); return 0; +cg_cleanup: + ib_device_unregister_rdmacg(device); cache_cleanup: ib_cache_cleanup_one(device); ib_cache_release_one(device); diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 8cf15d4a8ac4..9f029a1ca5ea 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1291,10 +1291,9 @@ int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num, resolved_dev = dev_get_by_index(dev_addr.net, dev_addr.bound_dev_if); - if (resolved_dev->flags & IFF_LOOPBACK) { - dev_put(resolved_dev); - resolved_dev = idev; - dev_hold(resolved_dev); + if (!resolved_dev) { + dev_put(idev); + return -ENODEV; } ndev = ib_get_ndev_from_path(rec); rcu_read_lock(); diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index f015f1bf88c9..3a9d0f5b5881 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1149,6 +1149,9 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file, if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; + if (cmd.qp_state > IB_QPS_ERR) + return -EINVAL; + ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); @@ -1294,6 +1297,9 @@ static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + if (unlikely(cmd.optval > KMALLOC_MAX_SIZE)) + return -EINVAL; + optval = memdup_user((void __user *) (unsigned long) cmd.optval, cmd.optlen); if (IS_ERR(optval)) { diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 643174d949a8..0dd75f449872 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -785,7 +785,7 @@ int bnxt_re_query_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr) return 0; } -static unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) +unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) __acquires(&qp->scq->cq_lock) __acquires(&qp->rcq->cq_lock) { unsigned long flags; @@ -799,8 +799,8 @@ static unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) return flags; } -static void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, - unsigned long flags) +void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, + unsigned long flags) __releases(&qp->scq->cq_lock) __releases(&qp->rcq->cq_lock) { if (qp->rcq != qp->scq) @@ -1606,6 +1606,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, int status; union ib_gid sgid; struct ib_gid_attr sgid_attr; + unsigned int flags; u8 nw_type; qp->qplib_qp.modify_flags = 0; @@ -1634,14 +1635,18 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, dev_dbg(rdev_to_dev(rdev), "Move QP = %p to flush list\n", qp); + flags = bnxt_re_lock_cqs(qp); bnxt_qplib_add_flush_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); } if (!qp->sumem && qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_RESET) { dev_dbg(rdev_to_dev(rdev), "Move QP = %p out of flush list\n", qp); + flags = bnxt_re_lock_cqs(qp); bnxt_qplib_clean_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); } } if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) { @@ -2227,10 +2232,13 @@ static int bnxt_re_build_inv_wqe(struct ib_send_wr *wr, wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV; wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey; + /* Need unconditional fence for local invalidate + * opcode to work as expected. + */ + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + if (wr->send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; - if (wr->send_flags & IB_SEND_FENCE) - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; if (wr->send_flags & IB_SEND_SOLICITED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT; @@ -2251,8 +2259,12 @@ static int bnxt_re_build_reg_wqe(struct ib_reg_wr *wr, wqe->frmr.levels = qplib_frpl->hwq.level + 1; wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR; - if (wr->wr.send_flags & IB_SEND_FENCE) - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + /* Need unconditional fence for reg_mr + * opcode to function as expected. + */ + + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + if (wr->wr.send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index b88a48d43a9d..e62b7c2c7da6 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -222,4 +222,7 @@ struct ib_ucontext *bnxt_re_alloc_ucontext(struct ib_device *ibdev, struct ib_udata *udata); int bnxt_re_dealloc_ucontext(struct ib_ucontext *context); int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma); + +unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp); +void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, unsigned long flags); #endif /* __BNXT_RE_IB_VERBS_H__ */ diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 33a448036c2e..f6e361750466 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -730,6 +730,13 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event, struct bnxt_re_qp *qp) { struct ib_event event; + unsigned int flags; + + if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + flags = bnxt_re_lock_cqs(qp); + bnxt_qplib_add_flush_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); + } memset(&event, 0, sizeof(event)); if (qp->qplib_qp.srq) { @@ -1416,9 +1423,12 @@ static void bnxt_re_task(struct work_struct *work) switch (re_work->event) { case NETDEV_REGISTER: rc = bnxt_re_ib_reg(rdev); - if (rc) + if (rc) { dev_err(rdev_to_dev(rdev), "Failed to register with IB: %#x", rc); + bnxt_re_remove_one(rdev); + bnxt_re_dev_unreg(rdev); + } break; case NETDEV_UP: bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 3ea5b9624f6b..06b42c880fd4 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -88,75 +88,35 @@ static void __bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) } } -void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp, - unsigned long *flags) - __acquires(&qp->scq->hwq.lock) __acquires(&qp->rcq->hwq.lock) +static void bnxt_qplib_acquire_cq_flush_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags) + __acquires(&qp->scq->flush_lock) __acquires(&qp->rcq->flush_lock) { - spin_lock_irqsave(&qp->scq->hwq.lock, *flags); + spin_lock_irqsave(&qp->scq->flush_lock, *flags); if (qp->scq == qp->rcq) - __acquire(&qp->rcq->hwq.lock); + __acquire(&qp->rcq->flush_lock); else - spin_lock(&qp->rcq->hwq.lock); + spin_lock(&qp->rcq->flush_lock); } -void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp, - unsigned long *flags) - __releases(&qp->scq->hwq.lock) __releases(&qp->rcq->hwq.lock) +static void bnxt_qplib_release_cq_flush_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags) + __releases(&qp->scq->flush_lock) __releases(&qp->rcq->flush_lock) { if (qp->scq == qp->rcq) - __release(&qp->rcq->hwq.lock); + __release(&qp->rcq->flush_lock); else - spin_unlock(&qp->rcq->hwq.lock); - spin_unlock_irqrestore(&qp->scq->hwq.lock, *flags); -} - -static struct bnxt_qplib_cq *bnxt_qplib_find_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - if (qp->scq == qp->rcq) - buddy_cq = NULL; - else if (qp->scq == cq) - buddy_cq = qp->rcq; - else - buddy_cq = qp->scq; - return buddy_cq; -} - -static void bnxt_qplib_lock_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) - __acquires(&buddy_cq->hwq.lock) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq); - if (!buddy_cq) - __acquire(&cq->hwq.lock); - else - spin_lock(&buddy_cq->hwq.lock); -} - -static void bnxt_qplib_unlock_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) - __releases(&buddy_cq->hwq.lock) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq); - if (!buddy_cq) - __release(&cq->hwq.lock); - else - spin_unlock(&buddy_cq->hwq.lock); + spin_unlock(&qp->rcq->flush_lock); + spin_unlock_irqrestore(&qp->scq->flush_lock, *flags); } void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) { unsigned long flags; - bnxt_qplib_acquire_cq_locks(qp, &flags); + bnxt_qplib_acquire_cq_flush_locks(qp, &flags); __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + bnxt_qplib_release_cq_flush_locks(qp, &flags); } static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp) @@ -177,7 +137,7 @@ void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp) { unsigned long flags; - bnxt_qplib_acquire_cq_locks(qp, &flags); + bnxt_qplib_acquire_cq_flush_locks(qp, &flags); __clean_cq(qp->scq, (u64)(unsigned long)qp); qp->sq.hwq.prod = 0; qp->sq.hwq.cons = 0; @@ -186,7 +146,7 @@ void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp) qp->rq.hwq.cons = 0; __bnxt_qplib_del_flush_qp(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + bnxt_qplib_release_cq_flush_locks(qp, &flags); } static void bnxt_qpn_cqn_sched_task(struct work_struct *work) @@ -2107,9 +2067,6 @@ void bnxt_qplib_mark_qp_error(void *qp_handle) /* Must block new posting of SQ and RQ */ qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; bnxt_qplib_cancel_phantom_processing(qp); - - /* Add qp to flush list of the CQ */ - __bnxt_qplib_add_flush_qp(qp); } /* Note: SQE is valid from sw_sq_cons up to cqe_sq_cons (exclusive) @@ -2285,9 +2242,9 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, sw_sq_cons, cqe->wr_id, cqe->status); cqe++; (*budget)--; - bnxt_qplib_lock_buddy_cq(qp, cq); bnxt_qplib_mark_qp_error(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + /* Add qp to flush list of the CQ */ + bnxt_qplib_add_flush_qp(qp); } else { if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) { /* Before we complete, do WA 9060 */ @@ -2403,9 +2360,7 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } @@ -2489,9 +2444,7 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } done: @@ -2501,11 +2454,9 @@ done: bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq) { struct cq_base *hw_cqe, **hw_cqe_ptr; - unsigned long flags; u32 sw_cons, raw_cons; bool rc = true; - spin_lock_irqsave(&cq->hwq.lock, flags); raw_cons = cq->hwq.cons; sw_cons = HWQ_CMP(raw_cons, &cq->hwq); hw_cqe_ptr = (struct cq_base **)cq->hwq.pbl_ptr; @@ -2513,7 +2464,6 @@ bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq) /* Check for Valid bit. If the CQE is valid, return false */ rc = !CQE_CMP_VALID(hw_cqe, raw_cons, cq->hwq.max_elements); - spin_unlock_irqrestore(&cq->hwq.lock, flags); return rc; } @@ -2602,9 +2552,7 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } @@ -2719,9 +2667,7 @@ do_rq: */ /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); done: return rc; } @@ -2750,7 +2696,7 @@ int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq, u32 budget = num_cqes; unsigned long flags; - spin_lock_irqsave(&cq->hwq.lock, flags); + spin_lock_irqsave(&cq->flush_lock, flags); list_for_each_entry(qp, &cq->sqf_head, sq_flush) { dev_dbg(&cq->hwq.pdev->dev, "QPLIB: FP: Flushing SQ QP= %p", @@ -2764,7 +2710,7 @@ int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq, qp); __flush_rq(&qp->rq, qp, &cqe, &budget); } - spin_unlock_irqrestore(&cq->hwq.lock, flags); + spin_unlock_irqrestore(&cq->flush_lock, flags); return num_cqes - budget; } @@ -2773,11 +2719,9 @@ int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe, int num_cqes, struct bnxt_qplib_qp **lib_qp) { struct cq_base *hw_cqe, **hw_cqe_ptr; - unsigned long flags; u32 sw_cons, raw_cons; int budget, rc = 0; - spin_lock_irqsave(&cq->hwq.lock, flags); raw_cons = cq->hwq.cons; budget = num_cqes; @@ -2853,20 +2797,15 @@ int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe, bnxt_qplib_arm_cq(cq, DBR_DBR_TYPE_CQ); } exit: - spin_unlock_irqrestore(&cq->hwq.lock, flags); return num_cqes - budget; } void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type) { - unsigned long flags; - - spin_lock_irqsave(&cq->hwq.lock, flags); if (arm_type) bnxt_qplib_arm_cq(cq, arm_type); /* Using cq->arm_state variable to track whether to issue cq handler */ atomic_set(&cq->arm_state, 1); - spin_unlock_irqrestore(&cq->hwq.lock, flags); } void bnxt_qplib_flush_cqn_wq(struct bnxt_qplib_qp *qp) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index ca0a2ffa3509..ade9f13c0fd1 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -389,6 +389,18 @@ struct bnxt_qplib_cq { struct list_head sqf_head, rqf_head; atomic_t arm_state; spinlock_t compl_lock; /* synch CQ handlers */ +/* Locking Notes: + * QP can move to error state from modify_qp, async error event or error + * CQE as part of poll_cq. When QP is moved to error state, it gets added + * to two flush lists, one each for SQ and RQ. + * Each flush list is protected by qplib_cq->flush_lock. Both scq and rcq + * flush_locks should be acquired when QP is moved to error. The control path + * operations(modify_qp and async error events) are synchronized with poll_cq + * using upper level CQ locks (bnxt_re_cq->cq_lock) of both SCQ and RCQ. + * The qplib_cq->flush_lock is required to synchronize two instances of poll_cq + * of the same QP while manipulating the flush list. + */ + spinlock_t flush_lock; /* QP flush management */ }; #define BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE sizeof(struct xrrq_irrq) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 8329ec6a7946..80027a494730 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -305,9 +305,8 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, err_event->res_err_state_reason); if (!qp) break; - bnxt_qplib_acquire_cq_locks(qp, &flags); bnxt_qplib_mark_qp_error(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + rcfw->aeq_handler(rcfw, qp_event, qp); break; default: /* Command Response */ @@ -460,7 +459,11 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, int rc; RCFW_CMD_PREP(req, INITIALIZE_FW, cmd_flags); - + /* Supply (log-base-2-of-host-page-size - base-page-shift) + * to bono to adjust the doorbell page sizes. + */ + req.log2_dbr_pg_size = cpu_to_le16(PAGE_SHIFT - + RCFW_DBR_BASE_PAGE_SHIFT); /* * VFs need not setup the HW context area, PF * shall setup this area for VF. Skipping the diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 6bee6e3636ea..c7cce2e4185e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -49,6 +49,7 @@ #define RCFW_COMM_SIZE 0x104 #define RCFW_DBR_PCI_BAR_REGION 2 +#define RCFW_DBR_BASE_PAGE_SHIFT 12 #define RCFW_CMD_PREP(req, CMD, cmd_flags) \ do { \ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 03057983341f..ee98e5efef84 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -139,7 +139,8 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_pkey = le32_to_cpu(sb->max_pkeys); attr->max_inline_data = le32_to_cpu(sb->max_inline_data); - attr->l2_db_size = (sb->l2_db_space_size + 1) * PAGE_SIZE; + attr->l2_db_size = (sb->l2_db_space_size + 1) * + (0x01 << RCFW_DBR_BASE_PAGE_SHIFT); attr->max_sgid = le32_to_cpu(sb->max_gid); bnxt_qplib_query_version(rcfw, attr->fw_ver); diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h index 2d7ea096a247..3e5a4f760d0e 100644 --- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h +++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h @@ -1761,7 +1761,30 @@ struct cmdq_initialize_fw { #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_2M (0x3UL << 4) #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8M (0x4UL << 4) #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_1G (0x5UL << 4) - __le16 reserved16; + /* This value is (log-base-2-of-DBR-page-size - 12). + * 0 for 4KB. HW supported values are enumerated below. + */ + __le16 log2_dbr_pg_size; + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_SFT 0 + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4K 0x0UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8K 0x1UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16K 0x2UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32K 0x3UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64K 0x4UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128K 0x5UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_256K 0x6UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_512K 0x7UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_1M 0x8UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_2M 0x9UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4M 0xaUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8M 0xbUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16M 0xcUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32M 0xdUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64M 0xeUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M 0xfUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_LAST \ + CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M __le64 qpc_page_dir; __le64 mrw_page_dir; __le64 srq_page_dir; diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 9a566ee3ceff..82adc0d1d30e 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -601,6 +601,7 @@ static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct wc->dlid_path_bits = 0; if (is_eth) { + wc->slid = 0; wc->vlan_id = be16_to_cpu(hdr->tun.sl_vid); memcpy(&(wc->smac[0]), (char *)&hdr->tun.mac_31_0, 4); memcpy(&(wc->smac[4]), (char *)&hdr->tun.slid_mac_47_32, 2); @@ -851,7 +852,6 @@ repoll: } } - wc->slid = be16_to_cpu(cqe->rlid); g_mlpath_rqpn = be32_to_cpu(cqe->g_mlpath_rqpn); wc->src_qp = g_mlpath_rqpn & 0xffffff; wc->dlid_path_bits = (g_mlpath_rqpn >> 24) & 0x7f; @@ -860,6 +860,7 @@ repoll: wc->wc_flags |= mlx4_ib_ipoib_csum_ok(cqe->status, cqe->checksum) ? IB_WC_IP_CSUM_OK : 0; if (is_eth) { + wc->slid = 0; wc->sl = be16_to_cpu(cqe->sl_vid) >> 13; if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_CVLAN_PRESENT_MASK) { @@ -871,6 +872,7 @@ repoll: memcpy(wc->smac, cqe->smac, ETH_ALEN); wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC); } else { + wc->slid = be16_to_cpu(cqe->rlid); wc->sl = be16_to_cpu(cqe->sl_vid) >> 12; wc->vlan_id = 0xffff; } diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 8d2ee9322f2e..5a0e4fc4785a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -219,8 +219,6 @@ static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids, gid_tbl[i].version = 2; if (!ipv6_addr_v4mapped((struct in6_addr *)&gids[i].gid)) gid_tbl[i].type = 1; - else - memset(&gid_tbl[i].gid, 0, 12); } } @@ -366,8 +364,13 @@ static int mlx4_ib_del_gid(struct ib_device *device, if (!gids) { ret = -ENOMEM; } else { - for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) - memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid)); + for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) { + memcpy(&gids[i].gid, + &port_gid_table->gids[i].gid, + sizeof(union ib_gid)); + gids[i].gid_type = + port_gid_table->gids[i].gid_type; + } } } spin_unlock_bh(&iboe->lock); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 5b974fb97611..15457c9569a7 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -226,7 +226,6 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, wc->ex.invalidate_rkey = be32_to_cpu(cqe->imm_inval_pkey); break; } - wc->slid = be16_to_cpu(cqe->slid); wc->src_qp = be32_to_cpu(cqe->flags_rqpn) & 0xffffff; wc->dlid_path_bits = cqe->ml_path; g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; @@ -241,10 +240,12 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, } if (ll != IB_LINK_LAYER_ETHERNET) { + wc->slid = be16_to_cpu(cqe->slid); wc->sl = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0xf; return; } + wc->slid = 0; vlan_present = cqe->l4_l3_hdr_type & 0x1; roce_packet_type = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0x3; if (vlan_present) { @@ -1177,7 +1178,12 @@ static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (ucmd.reserved0 || ucmd.reserved1) return -EINVAL; - umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size, + /* check multiplication overflow */ + if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <= entries - 1) + return -EINVAL; + + umem = ib_umem_get(context, ucmd.buf_addr, + (size_t)ucmd.cqe_size * entries, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(umem)) { err = PTR_ERR(umem); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 4236c8086820..033b6af90de9 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -245,12 +245,16 @@ struct mlx5_core_dev *mlx5_ib_get_native_port_mdev(struct mlx5_ib_dev *ibdev, struct mlx5_ib_multiport_info *mpi; struct mlx5_ib_port *port; + if (!mlx5_core_mp_enabled(ibdev->mdev) || + ll != IB_LINK_LAYER_ETHERNET) { + if (native_port_num) + *native_port_num = ib_port_num; + return ibdev->mdev; + } + if (native_port_num) *native_port_num = 1; - if (!mlx5_core_mp_enabled(ibdev->mdev) || ll != IB_LINK_LAYER_ETHERNET) - return ibdev->mdev; - port = &ibdev->port[ib_port_num - 1]; if (!port) return NULL; @@ -3263,7 +3267,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work) struct mlx5_ib_dev *ibdev; struct ib_event ibev; bool fatal = false; - u8 port = 0; + u8 port = (u8)work->param; if (mlx5_core_is_mp_slave(work->dev)) { ibdev = mlx5_ib_get_ibdev_from_mpi(work->context); @@ -3283,8 +3287,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work) case MLX5_DEV_EVENT_PORT_UP: case MLX5_DEV_EVENT_PORT_DOWN: case MLX5_DEV_EVENT_PORT_INITIALIZED: - port = (u8)work->param; - /* In RoCE, port up/down events are handled in * mlx5_netdev_event(). */ @@ -3298,24 +3300,19 @@ static void mlx5_ib_handle_event(struct work_struct *_work) case MLX5_DEV_EVENT_LID_CHANGE: ibev.event = IB_EVENT_LID_CHANGE; - port = (u8)work->param; break; case MLX5_DEV_EVENT_PKEY_CHANGE: ibev.event = IB_EVENT_PKEY_CHANGE; - port = (u8)work->param; - schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work); break; case MLX5_DEV_EVENT_GUID_CHANGE: ibev.event = IB_EVENT_GID_CHANGE; - port = (u8)work->param; break; case MLX5_DEV_EVENT_CLIENT_REREG: ibev.event = IB_EVENT_CLIENT_REREGISTER; - port = (u8)work->param; break; case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT: schedule_work(&ibdev->delay_drop.delay_drop_work); @@ -3327,7 +3324,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work) ibev.device = &ibdev->ib_dev; ibev.element.port_num = port; - if (port < 1 || port > ibdev->num_ports) { + if (!rdma_is_port_valid(&ibdev->ib_dev, port)) { mlx5_ib_warn(ibdev, "warning: event on port %d\n", port); goto out; } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 556e015678de..1961c6a45437 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1816,7 +1816,6 @@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr, mr->ibmr.iova = sg_dma_address(sg) + sg_offset; mr->ibmr.length = 0; - mr->ndescs = sg_nents; for_each_sg(sgl, sg, sg_nents, i) { if (unlikely(i >= mr->max_descs)) @@ -1828,6 +1827,7 @@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr, sg_offset = 0; } + mr->ndescs = i; if (sg_offset_p) *sg_offset_p = sg_offset; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 39d24bf694a8..36197fbac63a 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1584,6 +1584,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 uidx = MLX5_IB_DEFAULT_UIDX; struct mlx5_ib_create_qp ucmd; struct mlx5_ib_qp_base *base; + int mlx5_st; void *qpc; u32 *in; int err; @@ -1592,6 +1593,10 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); + mlx5_st = to_mlx5_st(init_attr->qp_type); + if (mlx5_st < 0) + return -EINVAL; + if (init_attr->rwq_ind_tbl) { if (!udata) return -ENOSYS; @@ -1753,7 +1758,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); - MLX5_SET(qpc, qpc, st, to_mlx5_st(init_attr->qp_type)); + MLX5_SET(qpc, qpc, st, mlx5_st); MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); if (init_attr->qp_type != MLX5_IB_QPT_REG_UMR) @@ -3095,8 +3100,10 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, goto out; if (mlx5_cur >= MLX5_QP_NUM_STATE || mlx5_new >= MLX5_QP_NUM_STATE || - !optab[mlx5_cur][mlx5_new]) + !optab[mlx5_cur][mlx5_new]) { + err = -EINVAL; goto out; + } op = optab[mlx5_cur][mlx5_new]; optpar = ib_mask_to_mlx5_opt(attr_mask); diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 478b7317b80a..26dc374787f7 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -458,8 +458,7 @@ qedr_addr6_resolve(struct qedr_dev *dev, } return -EINVAL; } - neigh = dst_neigh_lookup(dst, &dst_in); - + neigh = dst_neigh_lookup(dst, &fl6.daddr); if (neigh) { rcu_read_lock(); if (neigh->nud_state & NUD_VALID) { @@ -494,10 +493,14 @@ int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) qp = idr_find(&dev->qpidr, conn_param->qpn); - laddr = (struct sockaddr_in *)&cm_id->local_addr; - raddr = (struct sockaddr_in *)&cm_id->remote_addr; - laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr; - raddr6 = (struct sockaddr_in6 *)&cm_id->remote_addr; + laddr = (struct sockaddr_in *)&cm_id->m_local_addr; + raddr = (struct sockaddr_in *)&cm_id->m_remote_addr; + laddr6 = (struct sockaddr_in6 *)&cm_id->m_local_addr; + raddr6 = (struct sockaddr_in6 *)&cm_id->m_remote_addr; + + DP_DEBUG(dev, QEDR_MSG_IWARP, "MAPPED %d %d\n", + ntohs(((struct sockaddr_in *)&cm_id->remote_addr)->sin_port), + ntohs(raddr->sin_port)); DP_DEBUG(dev, QEDR_MSG_IWARP, "Connect source address: %pISpc, remote address: %pISpc\n", @@ -599,8 +602,8 @@ int qedr_iw_create_listen(struct iw_cm_id *cm_id, int backlog) int rc; int i; - laddr = (struct sockaddr_in *)&cm_id->local_addr; - laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr; + laddr = (struct sockaddr_in *)&cm_id->m_local_addr; + laddr6 = (struct sockaddr_in6 *)&cm_id->m_local_addr; DP_DEBUG(dev, QEDR_MSG_IWARP, "Create Listener address: %pISpc\n", &cm_id->local_addr); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 53f00dbf313f..875b17272d65 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -3034,6 +3034,11 @@ static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, switch (wr->opcode) { case IB_WR_SEND_WITH_IMM: + if (unlikely(rdma_protocol_iwarp(&dev->ibdev, 1))) { + rc = -EINVAL; + *bad_wr = wr; + break; + } wqe->req_type = RDMA_SQ_REQ_TYPE_SEND_WITH_IMM; swqe = (struct rdma_sq_send_wqe_1st *)wqe; swqe->wqe_size = 2; @@ -3075,6 +3080,11 @@ static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, break; case IB_WR_RDMA_WRITE_WITH_IMM: + if (unlikely(rdma_protocol_iwarp(&dev->ibdev, 1))) { + rc = -EINVAL; + *bad_wr = wr; + break; + } wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_WR_WITH_IMM; rwqe = (struct rdma_sq_rdma_wqe_1st *)wqe; @@ -3724,7 +3734,7 @@ int qedr_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) { struct qedr_dev *dev = get_qedr_dev(ibcq->device); struct qedr_cq *cq = get_qedr_cq(ibcq); - union rdma_cqe *cqe = cq->latest_cqe; + union rdma_cqe *cqe; u32 old_cons, new_cons; unsigned long flags; int update = 0; @@ -3741,6 +3751,7 @@ int qedr_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) return qedr_gsi_poll_cq(ibcq, num_entries, wc); spin_lock_irqsave(&cq->cq_lock, flags); + cqe = cq->latest_cqe; old_cons = qed_chain_get_cons_idx_u32(&cq->pbl); while (num_entries && is_valid_cqe(cq, cqe)) { struct qedr_qp *qp; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 4d1d8dfb2d2a..f2273143b3cb 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -963,6 +963,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, uint32_t rtime = cpu_to_le32(get_seconds()); struct uuid_entry *u; char buf[BDEVNAME_SIZE]; + struct cached_dev *exist_dc, *t; bdevname(dc->bdev, buf); @@ -987,6 +988,16 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, return -EINVAL; } + /* Check whether already attached */ + list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) { + if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) { + pr_err("Tried to attach %s but duplicate UUID already attached", + buf); + + return -EINVAL; + } + } + u = uuid_find(c, dc->sb.uuid); if (u && @@ -1204,7 +1215,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page, return; err: - pr_notice("error opening %s: %s", bdevname(bdev, name), err); + pr_notice("error %s: %s", bdevname(bdev, name), err); bcache_device_stop(&dc->disk); } @@ -1883,6 +1894,8 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, const char *err = NULL; /* must be set for any error case */ int ret = 0; + bdevname(bdev, name); + memcpy(&ca->sb, sb, sizeof(struct cache_sb)); ca->bdev = bdev; ca->bdev->bd_holder = ca; @@ -1891,11 +1904,12 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, bio_first_bvec_all(&ca->sb_bio)->bv_page = sb_page; get_page(sb_page); - if (blk_queue_discard(bdev_get_queue(ca->bdev))) + if (blk_queue_discard(bdev_get_queue(bdev))) ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); if (ret != 0) { + blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); if (ret == -ENOMEM) err = "cache_alloc(): -ENOMEM"; else @@ -1918,14 +1932,14 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, goto out; } - pr_info("registered cache device %s", bdevname(bdev, name)); + pr_info("registered cache device %s", name); out: kobject_put(&ca->kobj); err: if (err) - pr_notice("error opening %s: %s", bdevname(bdev, name), err); + pr_notice("error %s: %s", name, err); return ret; } @@ -2014,6 +2028,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (err) goto err_close; + err = "failed to register device"; if (SB_IS_BDEV(sb)) { struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL); if (!dc) @@ -2028,7 +2043,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, goto err_close; if (register_cache(sb, sb_page, bdev, ca) != 0) - goto err_close; + goto err; } out: if (sb_page) @@ -2041,7 +2056,7 @@ out: err_close: blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); err: - pr_info("error opening %s: %s", path, err); + pr_info("error %s: %s", path, err); ret = -EINVAL; goto out; } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 414c9af54ded..aa2032fa80d4 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -386,9 +386,6 @@ static void __cache_size_refresh(void) static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, enum data_mode *data_mode) { - unsigned noio_flag; - void *ptr; - if (c->block_size <= DM_BUFIO_BLOCK_SIZE_SLAB_LIMIT) { *data_mode = DATA_MODE_SLAB; return kmem_cache_alloc(DM_BUFIO_CACHE(c), gfp_mask); @@ -412,16 +409,15 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, * all allocations done by this process (including pagetables) are done * as if GFP_NOIO was specified. */ + if (gfp_mask & __GFP_NORETRY) { + unsigned noio_flag = memalloc_noio_save(); + void *ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); - if (gfp_mask & __GFP_NORETRY) - noio_flag = memalloc_noio_save(); - - ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); - - if (gfp_mask & __GFP_NORETRY) memalloc_noio_restore(noio_flag); + return ptr; + } - return ptr; + return __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); } /* diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 7d3e572072f5..3fde9e9faddd 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -22,6 +22,7 @@ #include <linux/time.h> #include <linux/workqueue.h> #include <linux/delay.h> +#include <scsi/scsi_device.h> #include <scsi/scsi_dh.h> #include <linux/atomic.h> #include <linux/blk-mq.h> @@ -211,25 +212,13 @@ static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m) else m->queue_mode = DM_TYPE_REQUEST_BASED; - } else if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) { + } else if (m->queue_mode == DM_TYPE_BIO_BASED) { INIT_WORK(&m->process_queued_bios, process_queued_bios); - - if (m->queue_mode == DM_TYPE_BIO_BASED) { - /* - * bio-based doesn't support any direct scsi_dh management; - * it just discovers if a scsi_dh is attached. - */ - set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags); - } - } - - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) { - set_bit(MPATHF_QUEUE_IO, &m->flags); - atomic_set(&m->pg_init_in_progress, 0); - atomic_set(&m->pg_init_count, 0); - m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT; - init_waitqueue_head(&m->pg_init_wait); + /* + * bio-based doesn't support any direct scsi_dh management; + * it just discovers if a scsi_dh is attached. + */ + set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags); } dm_table_set_type(ti->table, m->queue_mode); @@ -337,14 +326,12 @@ static void __switch_pg(struct multipath *m, struct priority_group *pg) { m->current_pg = pg; - if (m->queue_mode == DM_TYPE_NVME_BIO_BASED) - return; - /* Must we initialise the PG first, and queue I/O till it's ready? */ if (m->hw_handler_name) { set_bit(MPATHF_PG_INIT_REQUIRED, &m->flags); set_bit(MPATHF_QUEUE_IO, &m->flags); } else { + /* FIXME: not needed if no scsi_dh is attached */ clear_bit(MPATHF_PG_INIT_REQUIRED, &m->flags); clear_bit(MPATHF_QUEUE_IO, &m->flags); } @@ -385,8 +372,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes) unsigned bypassed = 1; if (!atomic_read(&m->nr_valid_paths)) { - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) - clear_bit(MPATHF_QUEUE_IO, &m->flags); + clear_bit(MPATHF_QUEUE_IO, &m->flags); goto failed; } @@ -599,7 +585,7 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio) return pgpath; } -static struct pgpath *__map_bio_nvme(struct multipath *m, struct bio *bio) +static struct pgpath *__map_bio_fast(struct multipath *m, struct bio *bio) { struct pgpath *pgpath; unsigned long flags; @@ -634,8 +620,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, { struct pgpath *pgpath; - if (m->queue_mode == DM_TYPE_NVME_BIO_BASED) - pgpath = __map_bio_nvme(m, bio); + if (!m->hw_handler_name) + pgpath = __map_bio_fast(m, bio); else pgpath = __map_bio(m, bio); @@ -675,8 +661,7 @@ static void process_queued_io_list(struct multipath *m) { if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED) dm_mq_kick_requeue_list(dm_table_get_md(m->ti->table)); - else if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) + else if (m->queue_mode == DM_TYPE_BIO_BASED) queue_work(kmultipathd, &m->process_queued_bios); } @@ -838,6 +823,16 @@ retain: */ kfree(m->hw_handler_name); m->hw_handler_name = attached_handler_name; + + /* + * Init fields that are only used when a scsi_dh is attached + */ + if (!test_and_set_bit(MPATHF_QUEUE_IO, &m->flags)) { + atomic_set(&m->pg_init_in_progress, 0); + atomic_set(&m->pg_init_count, 0); + m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT; + init_waitqueue_head(&m->pg_init_wait); + } } } @@ -873,6 +868,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps int r; struct pgpath *p; struct multipath *m = ti->private; + struct scsi_device *sdev; /* we need at least a path arg */ if (as->argc < 1) { @@ -891,7 +887,9 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps goto bad; } - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) { + sdev = scsi_device_from_queue(bdev_get_queue(p->path.dev->bdev)); + if (sdev) { + put_device(&sdev->sdev_gendev); INIT_DELAYED_WORK(&p->activate_path, activate_path_work); r = setup_scsi_dh(p->path.dev->bdev, m, &ti->error); if (r) { @@ -1001,8 +999,7 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m) if (!hw_argc) return 0; - if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) { + if (m->queue_mode == DM_TYPE_BIO_BASED) { dm_consume_args(as, hw_argc); DMERR("bio-based multipath doesn't allow hardware handler args"); return 0; @@ -1091,8 +1088,6 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) if (!strcasecmp(queue_mode_name, "bio")) m->queue_mode = DM_TYPE_BIO_BASED; - else if (!strcasecmp(queue_mode_name, "nvme")) - m->queue_mode = DM_TYPE_NVME_BIO_BASED; else if (!strcasecmp(queue_mode_name, "rq")) m->queue_mode = DM_TYPE_REQUEST_BASED; else if (!strcasecmp(queue_mode_name, "mq")) @@ -1193,7 +1188,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->num_discard_bios = 1; ti->num_write_same_bios = 1; ti->num_write_zeroes_bios = 1; - if (m->queue_mode == DM_TYPE_BIO_BASED || m->queue_mode == DM_TYPE_NVME_BIO_BASED) + if (m->queue_mode == DM_TYPE_BIO_BASED) ti->per_io_data_size = multipath_per_bio_data_size(); else ti->per_io_data_size = sizeof(struct dm_mpath_io); @@ -1730,9 +1725,6 @@ static void multipath_status(struct dm_target *ti, status_type_t type, case DM_TYPE_BIO_BASED: DMEMIT("queue_mode bio "); break; - case DM_TYPE_NVME_BIO_BASED: - DMEMIT("queue_mode nvme "); - break; case DM_TYPE_MQ_REQUEST_BASED: DMEMIT("queue_mode mq "); break; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 7ef469e902c6..c1d1034ff7b7 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3408,9 +3408,10 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); } else { - if (test_bit(MD_RECOVERY_NEEDED, &recovery) || - test_bit(MD_RECOVERY_RESHAPE, &recovery) || - test_bit(MD_RECOVERY_RUNNING, &recovery)) + if (!test_bit(MD_RECOVERY_INTR, &recovery) && + (test_bit(MD_RECOVERY_NEEDED, &recovery) || + test_bit(MD_RECOVERY_RESHAPE, &recovery) || + test_bit(MD_RECOVERY_RUNNING, &recovery))) r = mddev->curr_resync_completed; else r = mddev->recovery_cp; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 5fe7ec356c33..7eb3e2a3c07d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -942,17 +942,12 @@ static int dm_table_determine_type(struct dm_table *t) if (t->type != DM_TYPE_NONE) { /* target already set the table's type */ - if (t->type == DM_TYPE_BIO_BASED) - return 0; - else if (t->type == DM_TYPE_NVME_BIO_BASED) { - if (!dm_table_does_not_support_partial_completion(t)) { - DMERR("nvme bio-based is only possible with devices" - " that don't support partial completion"); - return -EINVAL; - } - /* Fallthru, also verify all devices are blk-mq */ + if (t->type == DM_TYPE_BIO_BASED) { + /* possibly upgrade to a variant of bio-based */ + goto verify_bio_based; } BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED); + BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED); goto verify_rq_based; } @@ -985,6 +980,7 @@ static int dm_table_determine_type(struct dm_table *t) } if (bio_based) { +verify_bio_based: /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; if (dm_table_supports_dax(t) || @@ -1755,7 +1751,7 @@ static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev char b[BDEVNAME_SIZE]; /* For now, NVMe devices are the only devices of this class */ - return (strncmp(bdevname(dev->bdev, b), "nvme", 3) == 0); + return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0); } static bool dm_table_does_not_support_partial_completion(struct dm_table *t) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 68136806d365..45328d8b2859 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -458,9 +458,11 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } -static int dm_grab_bdev_for_ioctl(struct mapped_device *md, - struct block_device **bdev, - fmode_t *mode) +static char *_dm_claim_ptr = "I belong to device-mapper"; + +static int dm_get_bdev_for_ioctl(struct mapped_device *md, + struct block_device **bdev, + fmode_t *mode) { struct dm_target *tgt; struct dm_table *map; @@ -490,6 +492,10 @@ retry: goto out; bdgrab(*bdev); + r = blkdev_get(*bdev, *mode, _dm_claim_ptr); + if (r < 0) + goto out; + dm_put_live_table(md, srcu_idx); return r; @@ -508,7 +514,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, struct mapped_device *md = bdev->bd_disk->private_data; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -528,7 +534,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, r = __blkdev_driver_ioctl(bdev, mode, cmd, arg); out: - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -708,14 +714,13 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU) static int open_table_device(struct table_device *td, dev_t dev, struct mapped_device *md) { - static char *_claim_ptr = "I belong to device-mapper"; struct block_device *bdev; int r; BUG_ON(td->dm_dev.bdev); - bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _claim_ptr); + bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _dm_claim_ptr); if (IS_ERR(bdev)) return PTR_ERR(bdev); @@ -3011,7 +3016,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3021,7 +3026,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3032,7 +3037,7 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type) fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3042,7 +3047,7 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type) else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3054,7 +3059,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3064,7 +3069,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3075,7 +3080,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key) fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3085,7 +3090,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key) else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 21d29f7936f6..d39b0b7011b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -124,7 +124,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) trigger_cmd_completions(dev); } - mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0); + mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 1); mlx5_core_err(dev, "end\n"); unlock: diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 817e5e2766da..7aeca5db7916 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3033,7 +3033,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns->disk->disk_name); nvme_mpath_add_disk(ns->head); - nvme_mpath_add_disk_links(ns); return; out_unlink_ns: mutex_lock(&ctrl->subsys->lock); @@ -3053,7 +3052,6 @@ static void nvme_ns_remove(struct nvme_ns *ns) return; if (ns->disk && ns->disk->flags & GENHD_FL_UP) { - nvme_mpath_remove_disk_links(ns); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, &nvme_ns_id_attr_group); if (ns->ndev) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index a1c58e35075e..8f0f34d06d46 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -650,6 +650,11 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, ret = -EINVAL; goto out; } + if (opts->discovery_nqn) { + pr_debug("Ignoring nr_io_queues value for discovery controller\n"); + break; + } + opts->nr_io_queues = min_t(unsigned int, num_online_cpus(), token); break; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 7f51f8414b97..1dc1387b7134 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1206,7 +1206,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, sizeof(struct fcnvme_lsdesc_cr_assoc_cmd)); assoc_rqst->assoc_cmd.ersp_ratio = cpu_to_be16(ersp_ratio); - assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize); + assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize - 1); /* Linux supports only Dynamic controllers */ assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff); uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id); @@ -1321,7 +1321,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, sizeof(struct fcnvme_lsdesc_cr_conn_cmd)); conn_rqst->connect_cmd.ersp_ratio = cpu_to_be16(ersp_ratio); conn_rqst->connect_cmd.qid = cpu_to_be16(queue->qnum); - conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize); + conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize - 1); lsop->queue = queue; lsreq->rqstaddr = conn_rqst; @@ -2481,11 +2481,11 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl) goto out_free_tag_set; } - ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_cleanup_blk_queue; - ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_delete_hw_queues; @@ -2532,11 +2532,11 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl) if (ret) goto out_free_io_queues; - ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_free_io_queues; - ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_delete_hw_queues; @@ -2632,13 +2632,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) nvme_fc_init_queue(ctrl, 0); ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0, - NVME_AQ_BLK_MQ_DEPTH); + NVME_AQ_DEPTH); if (ret) goto out_free_queue; ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0], - NVME_AQ_BLK_MQ_DEPTH, - (NVME_AQ_BLK_MQ_DEPTH / 4)); + NVME_AQ_DEPTH, (NVME_AQ_DEPTH / 4)); if (ret) goto out_delete_hw_queue; @@ -2666,7 +2665,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) } ctrl->ctrl.sqsize = - min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap) + 1, ctrl->ctrl.sqsize); + min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize); ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap); if (ret) @@ -2699,6 +2698,14 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) opts->queue_size = ctrl->ctrl.maxcmd; } + if (opts->queue_size > ctrl->ctrl.sqsize + 1) { + /* warn if sqsize is lower than queue_size */ + dev_warn(ctrl->ctrl.device, + "queue_size %zu > ctrl sqsize %u, clamping down\n", + opts->queue_size, ctrl->ctrl.sqsize + 1); + opts->queue_size = ctrl->ctrl.sqsize + 1; + } + ret = nvme_fc_init_aen_ops(ctrl); if (ret) goto out_term_aen_ops; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index b7e5c6db4d92..060f69e03427 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -210,25 +210,6 @@ void nvme_mpath_add_disk(struct nvme_ns_head *head) mutex_unlock(&head->subsys->lock); } -void nvme_mpath_add_disk_links(struct nvme_ns *ns) -{ - struct kobject *slave_disk_kobj, *holder_disk_kobj; - - if (!ns->head->disk) - return; - - slave_disk_kobj = &disk_to_dev(ns->disk)->kobj; - if (sysfs_create_link(ns->head->disk->slave_dir, slave_disk_kobj, - kobject_name(slave_disk_kobj))) - return; - - holder_disk_kobj = &disk_to_dev(ns->head->disk)->kobj; - if (sysfs_create_link(ns->disk->part0.holder_dir, holder_disk_kobj, - kobject_name(holder_disk_kobj))) - sysfs_remove_link(ns->head->disk->slave_dir, - kobject_name(slave_disk_kobj)); -} - void nvme_mpath_remove_disk(struct nvme_ns_head *head) { if (!head->disk) @@ -243,14 +224,3 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) blk_cleanup_queue(head->disk->queue); put_disk(head->disk); } - -void nvme_mpath_remove_disk_links(struct nvme_ns *ns) -{ - if (!ns->head->disk) - return; - - sysfs_remove_link(ns->disk->part0.holder_dir, - kobject_name(&disk_to_dev(ns->head->disk)->kobj)); - sysfs_remove_link(ns->head->disk->slave_dir, - kobject_name(&disk_to_dev(ns->disk)->kobj)); -} diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 0521e4707d1c..d733b14ede9d 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -410,9 +410,7 @@ bool nvme_req_needs_failover(struct request *req, blk_status_t error); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_disk(struct nvme_ns_head *head); -void nvme_mpath_add_disk_links(struct nvme_ns *ns); void nvme_mpath_remove_disk(struct nvme_ns_head *head); -void nvme_mpath_remove_disk_links(struct nvme_ns *ns); static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) { @@ -454,12 +452,6 @@ static inline void nvme_mpath_add_disk(struct nvme_ns_head *head) static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) { } -static inline void nvme_mpath_add_disk_links(struct nvme_ns *ns) -{ -} -static inline void nvme_mpath_remove_disk_links(struct nvme_ns *ns) -{ -} static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) { } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 5933a5c732e8..b6f43b738f03 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1153,12 +1153,6 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) if (!(csts & NVME_CSTS_CFS) && !nssro) return false; - /* If PCI error recovery process is happening, we cannot reset or - * the recovery mechanism will surely fail. - */ - if (pci_channel_offline(to_pci_dev(dev->dev))) - return false; - return true; } @@ -1189,6 +1183,13 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) struct nvme_command cmd; u32 csts = readl(dev->bar + NVME_REG_CSTS); + /* If PCI error recovery process is happening, we cannot reset or + * the recovery mechanism will surely fail. + */ + mb(); + if (pci_channel_offline(to_pci_dev(dev->dev))) + return BLK_EH_RESET_TIMER; + /* * Reset immediately if the controller is failed */ @@ -1913,7 +1914,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) int result, nr_io_queues; unsigned long size; - nr_io_queues = num_present_cpus(); + nr_io_queues = num_possible_cpus(); result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues); if (result < 0) return result; diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 9a8f96465cdc..d10ffe51da24 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -105,31 +105,44 @@ config ASUS_LAPTOP If you have an ACPI-compatible ASUS laptop, say Y or M here. +# +# If the DELL_SMBIOS_SMM feature is enabled, the DELL_SMBIOS driver +# becomes dependent on the DCDBAS driver. The "depends" line prevents a +# configuration where DELL_SMBIOS=y while DCDBAS=m. +# config DELL_SMBIOS - tristate + tristate "Dell SMBIOS driver" + depends on DCDBAS || DCDBAS=n + ---help--- + This provides support for the Dell SMBIOS calling interface. + If you have a Dell computer you should enable this option. + + Be sure to select at least one backend for it to work properly. config DELL_SMBIOS_WMI - tristate "Dell SMBIOS calling interface (WMI implementation)" + bool "Dell SMBIOS driver WMI backend" + default y depends on ACPI_WMI select DELL_WMI_DESCRIPTOR - select DELL_SMBIOS + depends on DELL_SMBIOS ---help--- This provides an implementation for the Dell SMBIOS calling interface communicated over ACPI-WMI. - If you have a Dell computer from >2007 you should say Y or M here. + If you have a Dell computer from >2007 you should say Y here. If you aren't sure and this module doesn't work for your computer it just won't load. config DELL_SMBIOS_SMM - tristate "Dell SMBIOS calling interface (SMM implementation)" + bool "Dell SMBIOS driver SMM backend" + default y depends on DCDBAS - select DELL_SMBIOS + depends on DELL_SMBIOS ---help--- This provides an implementation for the Dell SMBIOS calling interface communicated over SMI/SMM. - If you have a Dell computer from <=2017 you should say Y or M here. + If you have a Dell computer from <=2017 you should say Y here. If you aren't sure and this module doesn't work for your computer it just won't load. diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index c388608ad2a3..2ba6cb795338 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -13,8 +13,9 @@ obj-$(CONFIG_MSI_LAPTOP) += msi-laptop.o obj-$(CONFIG_ACPI_CMPC) += classmate-laptop.o obj-$(CONFIG_COMPAL_LAPTOP) += compal-laptop.o obj-$(CONFIG_DELL_SMBIOS) += dell-smbios.o -obj-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o -obj-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o +dell-smbios-objs := dell-smbios-base.o +dell-smbios-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o +dell-smbios-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o obj-$(CONFIG_DELL_LAPTOP) += dell-laptop.o obj-$(CONFIG_DELL_WMI) += dell-wmi.o obj-$(CONFIG_DELL_WMI_DESCRIPTOR) += dell-wmi-descriptor.o diff --git a/drivers/platform/x86/dell-smbios.c b/drivers/platform/x86/dell-smbios-base.c index 8541cde4cb7d..5bcf8a18f785 100644 --- a/drivers/platform/x86/dell-smbios.c +++ b/drivers/platform/x86/dell-smbios-base.c @@ -36,7 +36,7 @@ static DEFINE_MUTEX(smbios_mutex); struct smbios_device { struct list_head list; struct device *device; - int (*call_fn)(struct calling_interface_buffer *); + int (*call_fn)(struct calling_interface_buffer *arg); }; struct smbios_call { @@ -352,8 +352,10 @@ static void __init parse_da_table(const struct dmi_header *dm) struct calling_interface_structure *table = container_of(dm, struct calling_interface_structure, header); - /* 4 bytes of table header, plus 7 bytes of Dell header, plus at least - 6 bytes of entry */ + /* + * 4 bytes of table header, plus 7 bytes of Dell header + * plus at least 6 bytes of entry + */ if (dm->length < 17) return; @@ -554,7 +556,7 @@ static void free_group(struct platform_device *pdev) static int __init dell_smbios_init(void) { const struct dmi_device *valid; - int ret; + int ret, wmi, smm; valid = dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Dell System", NULL); if (!valid) { @@ -589,8 +591,24 @@ static int __init dell_smbios_init(void) if (ret) goto fail_create_group; + /* register backends */ + wmi = init_dell_smbios_wmi(); + if (wmi) + pr_debug("Failed to initialize WMI backend: %d\n", wmi); + smm = init_dell_smbios_smm(); + if (smm) + pr_debug("Failed to initialize SMM backend: %d\n", smm); + if (wmi && smm) { + pr_err("No SMBIOS backends available (wmi: %d, smm: %d)\n", + wmi, smm); + goto fail_sysfs; + } + return 0; +fail_sysfs: + free_group(platform_device); + fail_create_group: platform_device_del(platform_device); @@ -607,6 +625,8 @@ fail_platform_driver: static void __exit dell_smbios_exit(void) { + exit_dell_smbios_wmi(); + exit_dell_smbios_smm(); mutex_lock(&smbios_mutex); if (platform_device) { free_group(platform_device); @@ -623,5 +643,6 @@ module_exit(dell_smbios_exit); MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); MODULE_DESCRIPTION("Common functions for kernel modules using Dell SMBIOS"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios-smm.c b/drivers/platform/x86/dell-smbios-smm.c index 89f65c4651a0..e9e9da556318 100644 --- a/drivers/platform/x86/dell-smbios-smm.c +++ b/drivers/platform/x86/dell-smbios-smm.c @@ -58,7 +58,7 @@ static const struct dmi_system_id dell_device_table[] __initconst = { }; MODULE_DEVICE_TABLE(dmi, dell_device_table); -static void __init parse_da_table(const struct dmi_header *dm) +static void parse_da_table(const struct dmi_header *dm) { struct calling_interface_structure *table = container_of(dm, struct calling_interface_structure, header); @@ -73,7 +73,7 @@ static void __init parse_da_table(const struct dmi_header *dm) da_command_code = table->cmdIOCode; } -static void __init find_cmd_address(const struct dmi_header *dm, void *dummy) +static void find_cmd_address(const struct dmi_header *dm, void *dummy) { switch (dm->type) { case 0xda: /* Calling interface */ @@ -128,7 +128,7 @@ static bool test_wsmt_enabled(void) return false; } -static int __init dell_smbios_smm_init(void) +int init_dell_smbios_smm(void) { int ret; /* @@ -176,7 +176,7 @@ fail_platform_device_alloc: return ret; } -static void __exit dell_smbios_smm_exit(void) +void exit_dell_smbios_smm(void) { if (platform_device) { dell_smbios_unregister_device(&platform_device->dev); @@ -184,13 +184,3 @@ static void __exit dell_smbios_smm_exit(void) free_page((unsigned long)buffer); } } - -subsys_initcall(dell_smbios_smm_init); -module_exit(dell_smbios_smm_exit); - -MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); -MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); -MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); -MODULE_DESCRIPTION("Dell SMBIOS communications over SMI"); -MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios-wmi.c b/drivers/platform/x86/dell-smbios-wmi.c index 609557aa5868..fbefedb1c172 100644 --- a/drivers/platform/x86/dell-smbios-wmi.c +++ b/drivers/platform/x86/dell-smbios-wmi.c @@ -228,7 +228,7 @@ static const struct wmi_device_id dell_smbios_wmi_id_table[] = { { }, }; -static void __init parse_b1_table(const struct dmi_header *dm) +static void parse_b1_table(const struct dmi_header *dm) { struct misc_bios_flags_structure *flags = container_of(dm, struct misc_bios_flags_structure, header); @@ -242,7 +242,7 @@ static void __init parse_b1_table(const struct dmi_header *dm) wmi_supported = 1; } -static void __init find_b1(const struct dmi_header *dm, void *dummy) +static void find_b1(const struct dmi_header *dm, void *dummy) { switch (dm->type) { case 0xb1: /* misc bios flags */ @@ -261,7 +261,7 @@ static struct wmi_driver dell_smbios_wmi_driver = { .filter_callback = dell_smbios_wmi_filter, }; -static int __init init_dell_smbios_wmi(void) +int init_dell_smbios_wmi(void) { dmi_walk(find_b1, NULL); @@ -271,15 +271,9 @@ static int __init init_dell_smbios_wmi(void) return wmi_driver_register(&dell_smbios_wmi_driver); } -static void __exit exit_dell_smbios_wmi(void) +void exit_dell_smbios_wmi(void) { wmi_driver_unregister(&dell_smbios_wmi_driver); } -module_init(init_dell_smbios_wmi); -module_exit(exit_dell_smbios_wmi); - MODULE_ALIAS("wmi:" DELL_WMI_SMBIOS_GUID); -MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); -MODULE_DESCRIPTION("Dell SMBIOS communications over WMI"); -MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios.h b/drivers/platform/x86/dell-smbios.h index 138d478d9adc..d8adaf959740 100644 --- a/drivers/platform/x86/dell-smbios.h +++ b/drivers/platform/x86/dell-smbios.h @@ -75,4 +75,29 @@ int dell_laptop_register_notifier(struct notifier_block *nb); int dell_laptop_unregister_notifier(struct notifier_block *nb); void dell_laptop_call_notifier(unsigned long action, void *data); -#endif +/* for the supported backends */ +#ifdef CONFIG_DELL_SMBIOS_WMI +int init_dell_smbios_wmi(void); +void exit_dell_smbios_wmi(void); +#else /* CONFIG_DELL_SMBIOS_WMI */ +static inline int init_dell_smbios_wmi(void) +{ + return -ENODEV; +} +static inline void exit_dell_smbios_wmi(void) +{} +#endif /* CONFIG_DELL_SMBIOS_WMI */ + +#ifdef CONFIG_DELL_SMBIOS_SMM +int init_dell_smbios_smm(void); +void exit_dell_smbios_smm(void); +#else /* CONFIG_DELL_SMBIOS_SMM */ +static inline int init_dell_smbios_smm(void) +{ + return -ENODEV; +} +static inline void exit_dell_smbios_smm(void) +{} +#endif /* CONFIG_DELL_SMBIOS_SMM */ + +#endif /* _DELL_SMBIOS_H_ */ diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c index e0678c14480f..3a33c5344bd5 100644 --- a/drivers/watchdog/f71808e_wdt.c +++ b/drivers/watchdog/f71808e_wdt.c @@ -566,7 +566,8 @@ static ssize_t watchdog_write(struct file *file, const char __user *buf, char c; if (get_user(c, buf + i)) return -EFAULT; - expect_close = (c == 'V'); + if (c == 'V') + expect_close = true; } /* Properly order writes across fork()ed processes */ diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index f1f00dfc0e68..b0a158073abd 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -28,16 +28,7 @@ #include <linux/types.h> #include <linux/uaccess.h> #include <linux/watchdog.h> -#ifdef CONFIG_HPWDT_NMI_DECODING -#include <linux/dmi.h> -#include <linux/spinlock.h> -#include <linux/nmi.h> -#include <linux/kdebug.h> -#include <linux/notifier.h> -#include <asm/set_memory.h> -#endif /* CONFIG_HPWDT_NMI_DECODING */ #include <asm/nmi.h> -#include <asm/frame.h> #define HPWDT_VERSION "1.4.0" #define SECS_TO_TICKS(secs) ((secs) * 1000 / 128) @@ -48,6 +39,9 @@ static unsigned int soft_margin = DEFAULT_MARGIN; /* in seconds */ static unsigned int reload; /* the computed soft_margin */ static bool nowayout = WATCHDOG_NOWAYOUT; +#ifdef CONFIG_HPWDT_NMI_DECODING +static unsigned int allow_kdump = 1; +#endif static char expect_release; static unsigned long hpwdt_is_open; @@ -63,373 +57,6 @@ static const struct pci_device_id hpwdt_devices[] = { }; MODULE_DEVICE_TABLE(pci, hpwdt_devices); -#ifdef CONFIG_HPWDT_NMI_DECODING -#define PCI_BIOS32_SD_VALUE 0x5F32335F /* "_32_" */ -#define CRU_BIOS_SIGNATURE_VALUE 0x55524324 -#define PCI_BIOS32_PARAGRAPH_LEN 16 -#define PCI_ROM_BASE1 0x000F0000 -#define ROM_SIZE 0x10000 - -struct bios32_service_dir { - u32 signature; - u32 entry_point; - u8 revision; - u8 length; - u8 checksum; - u8 reserved[5]; -}; - -/* type 212 */ -struct smbios_cru64_info { - u8 type; - u8 byte_length; - u16 handle; - u32 signature; - u64 physical_address; - u32 double_length; - u32 double_offset; -}; -#define SMBIOS_CRU64_INFORMATION 212 - -/* type 219 */ -struct smbios_proliant_info { - u8 type; - u8 byte_length; - u16 handle; - u32 power_features; - u32 omega_features; - u32 reserved; - u32 misc_features; -}; -#define SMBIOS_ICRU_INFORMATION 219 - - -struct cmn_registers { - union { - struct { - u8 ral; - u8 rah; - u16 rea2; - }; - u32 reax; - } u1; - union { - struct { - u8 rbl; - u8 rbh; - u8 reb2l; - u8 reb2h; - }; - u32 rebx; - } u2; - union { - struct { - u8 rcl; - u8 rch; - u16 rec2; - }; - u32 recx; - } u3; - union { - struct { - u8 rdl; - u8 rdh; - u16 red2; - }; - u32 redx; - } u4; - - u32 resi; - u32 redi; - u16 rds; - u16 res; - u32 reflags; -} __attribute__((packed)); - -static unsigned int hpwdt_nmi_decoding; -static unsigned int allow_kdump = 1; -static unsigned int is_icru; -static unsigned int is_uefi; -static DEFINE_SPINLOCK(rom_lock); -static void *cru_rom_addr; -static struct cmn_registers cmn_regs; - -extern asmlinkage void asminline_call(struct cmn_registers *pi86Regs, - unsigned long *pRomEntry); - -#ifdef CONFIG_X86_32 -/* --32 Bit Bios------------------------------------------------------------ */ - -#define HPWDT_ARCH 32 - -asm(".text \n\t" - ".align 4 \n\t" - ".globl asminline_call \n" - "asminline_call: \n\t" - "pushl %ebp \n\t" - "movl %esp, %ebp \n\t" - "pusha \n\t" - "pushf \n\t" - "push %es \n\t" - "push %ds \n\t" - "pop %es \n\t" - "movl 8(%ebp),%eax \n\t" - "movl 4(%eax),%ebx \n\t" - "movl 8(%eax),%ecx \n\t" - "movl 12(%eax),%edx \n\t" - "movl 16(%eax),%esi \n\t" - "movl 20(%eax),%edi \n\t" - "movl (%eax),%eax \n\t" - "push %cs \n\t" - "call *12(%ebp) \n\t" - "pushf \n\t" - "pushl %eax \n\t" - "movl 8(%ebp),%eax \n\t" - "movl %ebx,4(%eax) \n\t" - "movl %ecx,8(%eax) \n\t" - "movl %edx,12(%eax) \n\t" - "movl %esi,16(%eax) \n\t" - "movl %edi,20(%eax) \n\t" - "movw %ds,24(%eax) \n\t" - "movw %es,26(%eax) \n\t" - "popl %ebx \n\t" - "movl %ebx,(%eax) \n\t" - "popl %ebx \n\t" - "movl %ebx,28(%eax) \n\t" - "pop %es \n\t" - "popf \n\t" - "popa \n\t" - "leave \n\t" - "ret \n\t" - ".previous"); - - -/* - * cru_detect - * - * Routine Description: - * This function uses the 32-bit BIOS Service Directory record to - * search for a $CRU record. - * - * Return Value: - * 0 : SUCCESS - * <0 : FAILURE - */ -static int cru_detect(unsigned long map_entry, - unsigned long map_offset) -{ - void *bios32_map; - unsigned long *bios32_entrypoint; - unsigned long cru_physical_address; - unsigned long cru_length; - unsigned long physical_bios_base = 0; - unsigned long physical_bios_offset = 0; - int retval = -ENODEV; - - bios32_map = ioremap(map_entry, (2 * PAGE_SIZE)); - - if (bios32_map == NULL) - return -ENODEV; - - bios32_entrypoint = bios32_map + map_offset; - - cmn_regs.u1.reax = CRU_BIOS_SIGNATURE_VALUE; - - set_memory_x((unsigned long)bios32_map, 2); - asminline_call(&cmn_regs, bios32_entrypoint); - - if (cmn_regs.u1.ral != 0) { - pr_warn("Call succeeded but with an error: 0x%x\n", - cmn_regs.u1.ral); - } else { - physical_bios_base = cmn_regs.u2.rebx; - physical_bios_offset = cmn_regs.u4.redx; - cru_length = cmn_regs.u3.recx; - cru_physical_address = - physical_bios_base + physical_bios_offset; - - /* If the values look OK, then map it in. */ - if ((physical_bios_base + physical_bios_offset)) { - cru_rom_addr = - ioremap(cru_physical_address, cru_length); - if (cru_rom_addr) { - set_memory_x((unsigned long)cru_rom_addr & PAGE_MASK, - (cru_length + PAGE_SIZE - 1) >> PAGE_SHIFT); - retval = 0; - } - } - - pr_debug("CRU Base Address: 0x%lx\n", physical_bios_base); - pr_debug("CRU Offset Address: 0x%lx\n", physical_bios_offset); - pr_debug("CRU Length: 0x%lx\n", cru_length); - pr_debug("CRU Mapped Address: %p\n", &cru_rom_addr); - } - iounmap(bios32_map); - return retval; -} - -/* - * bios_checksum - */ -static int bios_checksum(const char __iomem *ptr, int len) -{ - char sum = 0; - int i; - - /* - * calculate checksum of size bytes. This should add up - * to zero if we have a valid header. - */ - for (i = 0; i < len; i++) - sum += ptr[i]; - - return ((sum == 0) && (len > 0)); -} - -/* - * bios32_present - * - * Routine Description: - * This function finds the 32-bit BIOS Service Directory - * - * Return Value: - * 0 : SUCCESS - * <0 : FAILURE - */ -static int bios32_present(const char __iomem *p) -{ - struct bios32_service_dir *bios_32_ptr; - int length; - unsigned long map_entry, map_offset; - - bios_32_ptr = (struct bios32_service_dir *) p; - - /* - * Search for signature by checking equal to the swizzled value - * instead of calling another routine to perform a strcmp. - */ - if (bios_32_ptr->signature == PCI_BIOS32_SD_VALUE) { - length = bios_32_ptr->length * PCI_BIOS32_PARAGRAPH_LEN; - if (bios_checksum(p, length)) { - /* - * According to the spec, we're looking for the - * first 4KB-aligned address below the entrypoint - * listed in the header. The Service Directory code - * is guaranteed to occupy no more than 2 4KB pages. - */ - map_entry = bios_32_ptr->entry_point & ~(PAGE_SIZE - 1); - map_offset = bios_32_ptr->entry_point - map_entry; - - return cru_detect(map_entry, map_offset); - } - } - return -ENODEV; -} - -static int detect_cru_service(void) -{ - char __iomem *p, *q; - int rc = -1; - - /* - * Search from 0x0f0000 through 0x0fffff, inclusive. - */ - p = ioremap(PCI_ROM_BASE1, ROM_SIZE); - if (p == NULL) - return -ENOMEM; - - for (q = p; q < p + ROM_SIZE; q += 16) { - rc = bios32_present(q); - if (!rc) - break; - } - iounmap(p); - return rc; -} -/* ------------------------------------------------------------------------- */ -#endif /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_64 -/* --64 Bit Bios------------------------------------------------------------ */ - -#define HPWDT_ARCH 64 - -asm(".text \n\t" - ".align 4 \n\t" - ".globl asminline_call \n\t" - ".type asminline_call, @function \n\t" - "asminline_call: \n\t" - FRAME_BEGIN - "pushq %rax \n\t" - "pushq %rbx \n\t" - "pushq %rdx \n\t" - "pushq %r12 \n\t" - "pushq %r9 \n\t" - "movq %rsi, %r12 \n\t" - "movq %rdi, %r9 \n\t" - "movl 4(%r9),%ebx \n\t" - "movl 8(%r9),%ecx \n\t" - "movl 12(%r9),%edx \n\t" - "movl 16(%r9),%esi \n\t" - "movl 20(%r9),%edi \n\t" - "movl (%r9),%eax \n\t" - "call *%r12 \n\t" - "pushfq \n\t" - "popq %r12 \n\t" - "movl %eax, (%r9) \n\t" - "movl %ebx, 4(%r9) \n\t" - "movl %ecx, 8(%r9) \n\t" - "movl %edx, 12(%r9) \n\t" - "movl %esi, 16(%r9) \n\t" - "movl %edi, 20(%r9) \n\t" - "movq %r12, %rax \n\t" - "movl %eax, 28(%r9) \n\t" - "popq %r9 \n\t" - "popq %r12 \n\t" - "popq %rdx \n\t" - "popq %rbx \n\t" - "popq %rax \n\t" - FRAME_END - "ret \n\t" - ".previous"); - -/* - * dmi_find_cru - * - * Routine Description: - * This function checks whether or not a SMBIOS/DMI record is - * the 64bit CRU info or not - */ -static void dmi_find_cru(const struct dmi_header *dm, void *dummy) -{ - struct smbios_cru64_info *smbios_cru64_ptr; - unsigned long cru_physical_address; - - if (dm->type == SMBIOS_CRU64_INFORMATION) { - smbios_cru64_ptr = (struct smbios_cru64_info *) dm; - if (smbios_cru64_ptr->signature == CRU_BIOS_SIGNATURE_VALUE) { - cru_physical_address = - smbios_cru64_ptr->physical_address + - smbios_cru64_ptr->double_offset; - cru_rom_addr = ioremap(cru_physical_address, - smbios_cru64_ptr->double_length); - set_memory_x((unsigned long)cru_rom_addr & PAGE_MASK, - smbios_cru64_ptr->double_length >> PAGE_SHIFT); - } - } -} - -static int detect_cru_service(void) -{ - cru_rom_addr = NULL; - - dmi_walk(dmi_find_cru, NULL); - - /* if cru_rom_addr has been set then we found a CRU service */ - return ((cru_rom_addr != NULL) ? 0 : -ENODEV); -} -/* ------------------------------------------------------------------------- */ -#endif /* CONFIG_X86_64 */ -#endif /* CONFIG_HPWDT_NMI_DECODING */ /* * Watchdog operations @@ -486,30 +113,12 @@ static int hpwdt_my_nmi(void) */ static int hpwdt_pretimeout(unsigned int ulReason, struct pt_regs *regs) { - unsigned long rom_pl; - static int die_nmi_called; - - if (!hpwdt_nmi_decoding) - return NMI_DONE; - if ((ulReason == NMI_UNKNOWN) && !hpwdt_my_nmi()) return NMI_DONE; - spin_lock_irqsave(&rom_lock, rom_pl); - if (!die_nmi_called && !is_icru && !is_uefi) - asminline_call(&cmn_regs, cru_rom_addr); - die_nmi_called = 1; - spin_unlock_irqrestore(&rom_lock, rom_pl); - if (allow_kdump) hpwdt_stop(); - if (!is_icru && !is_uefi) { - if (cmn_regs.u1.ral == 0) { - nmi_panic(regs, "An NMI occurred, but unable to determine source.\n"); - return NMI_HANDLED; - } - } nmi_panic(regs, "An NMI occurred. Depending on your system the reason " "for the NMI is logged in any one of the following " "resources:\n" @@ -675,84 +284,11 @@ static struct miscdevice hpwdt_miscdev = { * Init & Exit */ -#ifdef CONFIG_HPWDT_NMI_DECODING -#ifdef CONFIG_X86_LOCAL_APIC -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ - /* - * If nmi_watchdog is turned off then we can turn on - * our nmi decoding capability. - */ - hpwdt_nmi_decoding = 1; -} -#else -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ - dev_warn(&dev->dev, "NMI decoding is disabled. " - "Your kernel does not support a NMI Watchdog.\n"); -} -#endif /* CONFIG_X86_LOCAL_APIC */ - -/* - * dmi_find_icru - * - * Routine Description: - * This function checks whether or not we are on an iCRU-based server. - * This check is independent of architecture and needs to be made for - * any ProLiant system. - */ -static void dmi_find_icru(const struct dmi_header *dm, void *dummy) -{ - struct smbios_proliant_info *smbios_proliant_ptr; - - if (dm->type == SMBIOS_ICRU_INFORMATION) { - smbios_proliant_ptr = (struct smbios_proliant_info *) dm; - if (smbios_proliant_ptr->misc_features & 0x01) - is_icru = 1; - if (smbios_proliant_ptr->misc_features & 0x1400) - is_uefi = 1; - } -} static int hpwdt_init_nmi_decoding(struct pci_dev *dev) { +#ifdef CONFIG_HPWDT_NMI_DECODING int retval; - - /* - * On typical CRU-based systems we need to map that service in - * the BIOS. For 32 bit Operating Systems we need to go through - * the 32 Bit BIOS Service Directory. For 64 bit Operating - * Systems we get that service through SMBIOS. - * - * On systems that support the new iCRU service all we need to - * do is call dmi_walk to get the supported flag value and skip - * the old cru detect code. - */ - dmi_walk(dmi_find_icru, NULL); - if (!is_icru && !is_uefi) { - - /* - * We need to map the ROM to get the CRU service. - * For 32 bit Operating Systems we need to go through the 32 Bit - * BIOS Service Directory - * For 64 bit Operating Systems we get that service through SMBIOS. - */ - retval = detect_cru_service(); - if (retval < 0) { - dev_warn(&dev->dev, - "Unable to detect the %d Bit CRU Service.\n", - HPWDT_ARCH); - return retval; - } - - /* - * We know this is the only CRU call we need to make so lets keep as - * few instructions as possible once the NMI comes in. - */ - cmn_regs.u1.rah = 0x0D; - cmn_regs.u1.ral = 0x02; - } - /* * Only one function can register for NMI_UNKNOWN */ @@ -780,45 +316,26 @@ error: dev_warn(&dev->dev, "Unable to register a die notifier (err=%d).\n", retval); - if (cru_rom_addr) - iounmap(cru_rom_addr); return retval; +#endif /* CONFIG_HPWDT_NMI_DECODING */ + return 0; } static void hpwdt_exit_nmi_decoding(void) { +#ifdef CONFIG_HPWDT_NMI_DECODING unregister_nmi_handler(NMI_UNKNOWN, "hpwdt"); unregister_nmi_handler(NMI_SERR, "hpwdt"); unregister_nmi_handler(NMI_IO_CHECK, "hpwdt"); - if (cru_rom_addr) - iounmap(cru_rom_addr); -} -#else /* !CONFIG_HPWDT_NMI_DECODING */ -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ -} - -static int hpwdt_init_nmi_decoding(struct pci_dev *dev) -{ - return 0; +#endif } -static void hpwdt_exit_nmi_decoding(void) -{ -} -#endif /* CONFIG_HPWDT_NMI_DECODING */ - static int hpwdt_init_one(struct pci_dev *dev, const struct pci_device_id *ent) { int retval; /* - * Check if we can do NMI decoding or not - */ - hpwdt_check_nmi_decoding(dev); - - /* * First let's find out if we are on an iLO2+ server. We will * not run on a legacy ASM box. * So we only support the G5 ProLiant servers and higher. @@ -922,6 +439,6 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" #ifdef CONFIG_HPWDT_NMI_DECODING module_param(allow_kdump, int, 0); MODULE_PARM_DESC(allow_kdump, "Start a kernel dump after NMI occurs"); -#endif /* !CONFIG_HPWDT_NMI_DECODING */ +#endif /* CONFIG_HPWDT_NMI_DECODING */ module_pci_driver(hpwdt_driver); diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c index 316c2eb122d2..e8bd9887c566 100644 --- a/drivers/watchdog/sbsa_gwdt.c +++ b/drivers/watchdog/sbsa_gwdt.c @@ -50,6 +50,7 @@ */ #include <linux/io.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/moduleparam.h> @@ -159,7 +160,7 @@ static unsigned int sbsa_gwdt_get_timeleft(struct watchdog_device *wdd) !(readl(gwdt->control_base + SBSA_GWDT_WCS) & SBSA_GWDT_WCS_WS0)) timeleft += readl(gwdt->control_base + SBSA_GWDT_WOR); - timeleft += readq(gwdt->control_base + SBSA_GWDT_WCV) - + timeleft += lo_hi_readq(gwdt->control_base + SBSA_GWDT_WCV) - arch_counter_get_cntvct(); do_div(timeleft, gwdt->clk); diff --git a/kernel/events/core.c b/kernel/events/core.c index 96db9ae5d5af..4b838470fac4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2246,7 +2246,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, struct perf_event_context *task_ctx, enum event_type_t event_type) { - enum event_type_t ctx_event_type = event_type & EVENT_ALL; + enum event_type_t ctx_event_type; bool cpu_event = !!(event_type & EVENT_CPU); /* @@ -2256,6 +2256,8 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, if (event_type & EVENT_PINNED) event_type |= EVENT_FLEXIBLE; + ctx_event_type = event_type & EVENT_ALL; + perf_pmu_disable(cpuctx->ctx.pmu); if (task_ctx) task_ctx_sched_out(cpuctx, task_ctx, event_type); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 65cc0cb984e6..940633c63254 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1616,11 +1616,12 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) { DEFINE_WAKE_Q(wake_q); + unsigned long flags; bool postunlock; - raw_spin_lock_irq(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); postunlock = __rt_mutex_futex_unlock(lock, &wake_q); - raw_spin_unlock_irq(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); if (postunlock) rt_mutex_postunlock(&wake_q); diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 5589bae34af6..a6f538b31ad6 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -297,11 +297,11 @@ cmd_dt_S_dtb= \ echo '\#include <asm-generic/vmlinux.lds.h>'; \ echo '.section .dtb.init.rodata,"a"'; \ echo '.balign STRUCT_ALIGNMENT'; \ - echo '.global __dtb_$(*F)_begin'; \ - echo '__dtb_$(*F)_begin:'; \ + echo '.global __dtb_$(subst -,_,$(*F))_begin'; \ + echo '__dtb_$(subst -,_,$(*F))_begin:'; \ echo '.incbin "$<" '; \ - echo '__dtb_$(*F)_end:'; \ - echo '.global __dtb_$(*F)_end'; \ + echo '__dtb_$(subst -,_,$(*F))_end:'; \ + echo '.global __dtb_$(subst -,_,$(*F))_end'; \ echo '.balign STRUCT_ALIGNMENT'; \ ) > $@ diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index fa3d39b6f23b..449b68c4c90c 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -93,14 +93,6 @@ * (Note: it'd be easy to port over the complete mkdep state machine, * but I don't think the added complexity is worth it) */ -/* - * Note 2: if somebody writes HELLO_CONFIG_BOOM in a file, it will depend onto - * CONFIG_BOOM. This could seem a bug (not too hard to fix), but please do not - * fix it! Some UserModeLinux files (look at arch/um/) call CONFIG_BOOM as - * UML_CONFIG_BOOM, to avoid conflicts with /usr/include/linux/autoconf.h, - * through arch/um/include/uml-config.h; this fixdep "bug" makes sure that - * those files will have correct dependencies. - */ #include <sys/types.h> #include <sys/stat.h> @@ -233,8 +225,13 @@ static int str_ends_with(const char *s, int slen, const char *sub) static void parse_config_file(const char *p) { const char *q, *r; + const char *start = p; while ((p = strstr(p, "CONFIG_"))) { + if (p > start && (isalnum(p[-1]) || p[-1] == '_')) { + p += 7; + continue; + } p += 7; q = p; while (*q && (isalnum(*q) || *q == '_')) @@ -286,8 +283,6 @@ static int is_ignored_file(const char *s, int len) { return str_ends_with(s, len, "include/generated/autoconf.h") || str_ends_with(s, len, "include/generated/autoksyms.h") || - str_ends_with(s, len, "arch/um/include/uml-config.h") || - str_ends_with(s, len, "include/linux/kconfig.h") || str_ends_with(s, len, ".ver"); } diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter index 94b664817ad9..d84a5674e95e 100755 --- a/scripts/bloat-o-meter +++ b/scripts/bloat-o-meter @@ -15,7 +15,7 @@ signal(SIGPIPE, SIG_DFL) if len(sys.argv) < 3: sys.stderr.write("usage: %s [option] file1 file2\n" % sys.argv[0]) sys.stderr.write("The options are:\n") - sys.stderr.write("-c cateogrize output based on symbole type\n") + sys.stderr.write("-c categorize output based on symbol type\n") sys.stderr.write("-d Show delta of Data Section\n") sys.stderr.write("-t Show delta of text Section\n") sys.exit(-1) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 0dfe4d3f74e2..f41079da38c5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -213,6 +213,7 @@ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 0fb5ef939732..7b26d4b0b052 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt { #define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 #define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 #define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) +#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) /* * Extension capability list. @@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_AIS_MIGRATION 150 #define KVM_CAP_PPC_GET_CPU_CHAR 151 #define KVM_CAP_S390_BPB 152 +#define KVM_CAP_GET_MSR_FEATURES 153 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 46c1d239cc1b..92b6a2c21631 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1116,42 +1116,29 @@ static int read_unwind_hints(struct objtool_file *file) static int read_retpoline_hints(struct objtool_file *file) { - struct section *sec, *relasec; + struct section *sec; struct instruction *insn; struct rela *rela; - int i; - sec = find_section_by_name(file->elf, ".discard.retpoline_safe"); + sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); if (!sec) return 0; - relasec = sec->rela; - if (!relasec) { - WARN("missing .rela.discard.retpoline_safe section"); - return -1; - } - - if (sec->len % sizeof(unsigned long)) { - WARN("retpoline_safe size mismatch: %d %ld", sec->len, sizeof(unsigned long)); - return -1; - } - - for (i = 0; i < sec->len / sizeof(unsigned long); i++) { - rela = find_rela_by_dest(sec, i * sizeof(unsigned long)); - if (!rela) { - WARN("can't find rela for retpoline_safe[%d]", i); + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); return -1; } insn = find_insn(file, rela->sym->sec, rela->addend); if (!insn) { - WARN("can't find insn for retpoline_safe[%d]", i); + WARN("bad .discard.retpoline_safe entry"); return -1; } if (insn->type != INSN_JUMP_DYNAMIC && insn->type != INSN_CALL_DYNAMIC) { - WARN_FUNC("retpoline_safe hint not a indirect jump/call", + WARN_FUNC("retpoline_safe hint not an indirect jump/call", insn->sec, insn->offset); return -1; } diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt index 954ea9e21236..cf9f4040ea5c 100644 --- a/tools/perf/Documentation/perf-kallsyms.txt +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -8,7 +8,7 @@ perf-kallsyms - Searches running kernel for symbols SYNOPSIS -------- [verse] -'perf kallsyms <options> symbol_name[,symbol_name...]' +'perf kallsyms' [<options>] symbol_name[,symbol_name...] DESCRIPTION ----------- diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index bf4ca749d1ac..a217623fec2e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -881,6 +881,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } } + /* + * If we have just single event and are sending data + * through pipe, we need to force the ids allocation, + * because we synthesize event name through the pipe + * and need the id for that. + */ + if (data->is_pipe && rec->evlist->nr_entries == 1) + rec->opts.sample_id = true; + if (record__open(rec) != 0) { err = -1; goto out_child; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 98bf9d32f222..54a4c152edb3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -917,7 +917,7 @@ static void print_metric_csv(void *ctx, char buf[64], *vals, *ends; if (unit == NULL || fmt == NULL) { - fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep); + fprintf(out, "%s%s", csv_sep, csv_sep); return; } snprintf(buf, sizeof(buf), fmt, val); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b7c823ba8374..35ac016fcb98 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -991,7 +991,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top, evlist__for_each_entry(evlist, counter) counter->attr.write_backward = false; opts->overwrite = false; - ui__warning("fall back to non-overwrite mode\n"); + pr_debug2("fall back to non-overwrite mode\n"); return 1; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index cfe46236a5e5..57b9b342d533 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -61,6 +61,7 @@ struct record_opts { bool tail_synthesize; bool overwrite; bool ignore_missing_thread; + bool sample_id; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 286427975112..fbf927cf775d 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -327,7 +327,32 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) if (!disasm_line__is_valid_jump(cursor, sym)) return; + /* + * This first was seen with a gcc function, _cpp_lex_token, that + * has the usual jumps: + * + * │1159e6c: ↓ jne 115aa32 <_cpp_lex_token@@Base+0xf92> + * + * I.e. jumps to a label inside that function (_cpp_lex_token), and + * those works, but also this kind: + * + * │1159e8b: ↓ jne c469be <cpp_named_operator2name@@Base+0xa72> + * + * I.e. jumps to another function, outside _cpp_lex_token, which + * are not being correctly handled generating as a side effect references + * to ab->offset[] entries that are set to NULL, so to make this code + * more robust, check that here. + * + * A proper fix for will be put in place, looking at the function + * name right after the '<' token and probably treating this like a + * 'call' instruction. + */ target = ab->offsets[cursor->ops.target.offset]; + if (target == NULL) { + ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n", + cursor->ops.target.offset); + return; + } bcursor = browser_line(&cursor->al); btarget = browser_line(target); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 9faf3b5367db..6470ea2aa25e 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -60,6 +60,12 @@ #include "sane_ctype.h" #include "symbol/kallsyms.h" +static bool auxtrace__dont_decode(struct perf_session *session) +{ + return !session->itrace_synth_opts || + session->itrace_synth_opts->dont_decode; +} + int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, struct auxtrace_mmap_params *mp, void *userpg, int fd) @@ -762,6 +768,9 @@ int auxtrace_queues__process_index(struct auxtrace_queues *queues, size_t i; int err; + if (auxtrace__dont_decode(session)) + return 0; + list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) { for (i = 0; i < auxtrace_index->nr; i++) { ent = &auxtrace_index->entries[i]; @@ -892,12 +901,6 @@ out_free: return err; } -static bool auxtrace__dont_decode(struct perf_session *session) -{ - return !session->itrace_synth_opts || - session->itrace_synth_opts->dont_decode; -} - int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_session *session) diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 1e97937b03a9..6f09e4962dad 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -137,6 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, struct perf_evsel *evsel; bool use_sample_identifier = false; bool use_comm_exec; + bool sample_id = opts->sample_id; /* * Set the evsel leader links before we configure attributes, @@ -163,8 +164,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, * match the id. */ use_sample_identifier = perf_can_sample_identifier(); - evlist__for_each_entry(evlist, evsel) - perf_evsel__set_sample_id(evsel, use_sample_identifier); + sample_id = true; } else if (evlist->nr_entries > 1) { struct perf_evsel *first = perf_evlist__first(evlist); @@ -174,6 +174,10 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, use_sample_identifier = perf_can_sample_identifier(); break; } + sample_id = true; + } + + if (sample_id) { evlist__for_each_entry(evlist, evsel) perf_evsel__set_sample_id(evsel, use_sample_identifier); } diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h index 370138e7e35c..88223bc7c82b 100644 --- a/tools/perf/util/trigger.h +++ b/tools/perf/util/trigger.h @@ -12,7 +12,7 @@ * States and transits: * * - * OFF--(on)--> READY --(hit)--> HIT + * OFF--> ON --> READY --(hit)--> HIT * ^ | * | (ready) * | | @@ -27,8 +27,9 @@ struct trigger { volatile enum { TRIGGER_ERROR = -2, TRIGGER_OFF = -1, - TRIGGER_READY = 0, - TRIGGER_HIT = 1, + TRIGGER_ON = 0, + TRIGGER_READY = 1, + TRIGGER_HIT = 2, } state; const char *name; }; @@ -50,7 +51,7 @@ static inline bool trigger_is_error(struct trigger *t) static inline void trigger_on(struct trigger *t) { TRIGGER_WARN_ONCE(t, TRIGGER_OFF); - t->state = TRIGGER_READY; + t->state = TRIGGER_ON; } static inline void trigger_ready(struct trigger *t) diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index be81621446f0..0b4f1cc2291c 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -450,7 +450,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) num_vsyscall_traps++; } -static int test_native_vsyscall(void) +static int test_emulation(void) { time_t tmp; bool is_native; @@ -458,7 +458,7 @@ static int test_native_vsyscall(void) if (!vtime) return 0; - printf("[RUN]\tchecking for native vsyscall\n"); + printf("[RUN]\tchecking that vsyscalls are emulated\n"); sethandler(SIGTRAP, sigtrap, 0); set_eflags(get_eflags() | X86_EFLAGS_TF); vtime(&tmp); @@ -474,11 +474,12 @@ static int test_native_vsyscall(void) */ is_native = (num_vsyscall_traps > 1); - printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n", + printf("[%s]\tvsyscalls are %s (%d instructions in vsyscall page)\n", + (is_native ? "FAIL" : "OK"), (is_native ? "native" : "emulated"), (int)num_vsyscall_traps); - return 0; + return is_native; } #endif @@ -498,7 +499,7 @@ int main(int argc, char **argv) nerrs += test_vsys_r(); #ifdef __x86_64__ - nerrs += test_native_vsyscall(); + nerrs += test_emulation(); #endif return nerrs ? 1 : 0; |