June 2024 - Linux-stable-mirror

[PATCH 02/15] syscalls: fix compat_sys_io_pgetevents_time64 usage

by Arnd Bergmann

From: Arnd Bergmann <arnd(a)arndb.de> Using sys_io_pgetevents() as the entry point for compat mode tasks works almost correctly, but misses the sign extension for the min_nr and nr arguments. This was addressed on parisc by switching to compat_sys_io_pgetevents_time64() in commit 6431e92fc827 ("parisc: io_pgetevents_time64() needs compat syscall in 32-bit compat mode"), as well as by using more sophisticated system call wrappers on x86 and s390. However, arm64, mips, powerpc, sparc and riscv still have the same bug. Changes all of them over to use compat_sys_io_pgetevents_time64() like parisc already does. This was clearly the intention when the function was originally added, but it got hooked up incorrectly in the tables. Cc: stable(a)vger.kernel.org Fixes: 48166e6ea47d ("y2038: add 64-bit time_t syscalls to all 32-bit architectures") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> --- arch/arm64/include/asm/unistd32.h | 2 +- arch/mips/kernel/syscalls/syscall_n32.tbl | 2 +- arch/mips/kernel/syscalls/syscall_o32.tbl | 2 +- arch/powerpc/kernel/syscalls/syscall.tbl | 2 +- arch/s390/kernel/syscalls/syscall.tbl | 2 +- arch/sparc/kernel/syscalls/syscall.tbl | 2 +- arch/x86/entry/syscalls/syscall_32.tbl | 2 +- include/uapi/asm-generic/unistd.h | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 266b96acc014..1386e8e751f2 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -840,7 +840,7 @@ __SYSCALL(__NR_pselect6_time64, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SYSCALL(__NR_ppoll_time64, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SYSCALL(__NR_io_pgetevents_time64, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SYSCALL(__NR_recvmmsg_time64, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index cc869f5d5693..953f5b7dc723 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -354,7 +354,7 @@ 412 n32 utimensat_time64 sys_utimensat 413 n32 pselect6_time64 compat_sys_pselect6_time64 414 n32 ppoll_time64 compat_sys_ppoll_time64 -416 n32 io_pgetevents_time64 sys_io_pgetevents +416 n32 io_pgetevents_time64 compat_sys_io_pgetevents_time64 417 n32 recvmmsg_time64 compat_sys_recvmmsg_time64 418 n32 mq_timedsend_time64 sys_mq_timedsend 419 n32 mq_timedreceive_time64 sys_mq_timedreceive diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 008ebe60263e..85751c9b9cdb 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -403,7 +403,7 @@ 412 o32 utimensat_time64 sys_utimensat sys_utimensat 413 o32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 o32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 o32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 o32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 o32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 o32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 o32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 3656f1ca7a21..c6b0546b284d 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -502,7 +502,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index bd0fee24ad10..01071182763e 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -418,7 +418,7 @@ 412 32 utimensat_time64 - sys_utimensat 413 32 pselect6_time64 - compat_sys_pselect6_time64 414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - sys_io_pgetevents +416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 - sys_mq_timedsend 419 32 mq_timedreceive_time64 - sys_mq_timedreceive diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index ac6c281ccfe0..b354139b40be 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -461,7 +461,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 7fd1f57ad3d3..d6ebcab1d8b2 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -420,7 +420,7 @@ 412 i386 utimensat_time64 sys_utimensat 413 i386 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 i386 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 i386 io_pgetevents_time64 sys_io_pgetevents +416 i386 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 i386 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 i386 mq_timedsend_time64 sys_mq_timedsend 419 i386 mq_timedreceive_time64 sys_mq_timedreceive diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index d983c48a3b6a..3fdaa573d661 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -737,7 +737,7 @@ __SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 -- 2.39.2

8 months

3
2
0 0

[PATCH 09/15] sh: rework sync_file_range ABI

by Arnd Bergmann

From: Arnd Bergmann <arnd(a)arndb.de> The unusual function calling conventions on superh ended up causing sync_file_range to have the wrong argument order, with the 'flags' argument getting sorted before 'nbytes' by the compiler. In userspace, I found that musl, glibc, uclibc and strace all expect the normal calling conventions with 'nbytes' last, so changing the kernel to match them should make all of those work. In order to be able to also fix libc implementations to work with existing kernels, they need to be able to tell which ABI is used. An easy way to do this is to add yet another system call using the sync_file_range2 ABI that works the same on all architectures. Old user binaries can now work on new kernels, and new binaries can try the new sync_file_range2() to work with new kernels or fall back to the old sync_file_range() version if that doesn't exist. Cc: stable(a)vger.kernel.org Fixes: 75c92acdd5b1 ("sh: Wire up new syscalls.") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> --- arch/sh/kernel/sys_sh32.c | 11 +++++++++++ arch/sh/kernel/syscalls/syscall.tbl | 3 ++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index 9dca568509a5..d5a4f7c697d8 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -59,3 +59,14 @@ asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1, (u64)len0 << 32 | len1, advice); #endif } + +/* + * swap the arguments the way that libc wants it instead of + * moving flags ahead of the 64-bit nbytes argument + */ +SYSCALL_DEFINE6(sh_sync_file_range6, int, fd, SC_ARG64(offset), + SC_ARG64(nbytes), unsigned int, flags) +{ + return ksys_sync_file_range(fd, SC_VAL64(loff_t, offset), + SC_VAL64(loff_t, nbytes), flags); +} diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index bbf83a2db986..c55fd7696d40 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -321,7 +321,7 @@ 311 common set_robust_list sys_set_robust_list 312 common get_robust_list sys_get_robust_list 313 common splice sys_splice -314 common sync_file_range sys_sync_file_range +314 common sync_file_range sys_sh_sync_file_range6 315 common tee sys_tee 316 common vmsplice sys_vmsplice 317 common move_pages sys_move_pages @@ -395,6 +395,7 @@ 385 common pkey_alloc sys_pkey_alloc 386 common pkey_free sys_pkey_free 387 common rseq sys_rseq +388 common sync_file_range2 sys_sync_file_range2 # room for arch specific syscalls 393 common semget sys_semget 394 common semctl sys_semctl -- 2.39.2

8 months

4
5
0 0

[PATCH 14/15] asm-generic: unistd: fix time32 compat syscall handling

by Arnd Bergmann

From: Arnd Bergmann <arnd(a)arndb.de> arch/riscv/ appears to have accidentally enabled the compat time32 syscalls in 64-bit kernels even though the native 32-bit ABI does not expose those. Address this by adding another level of indirection, checking for both the target ABI (32 or 64) and the __ARCH_WANT_TIME32_SYSCALLS macro. The macro arguments are meant to follow the syscall.tbl format, the idea here is that by the end of the series, all other syscalls are changed to the same format to make it possible to move all architectures over to generating the system call table consistently. Only this patch needs to be backported though. Cc: stable(a)vger.kernel.org # v5.19+ Fixes: 7eb6369d7acf ("RISC-V: Add support for rv32 userspace via COMPAT") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> --- include/uapi/asm-generic/unistd.h | 146 +++++++++++++++++++----------- 1 file changed, 94 insertions(+), 52 deletions(-) diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 3fdaa573d661..e47c966557d0 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -16,10 +16,32 @@ #define __SYSCALL(x, y) #endif +#ifndef __SC +#define __SC(_cond, _nr, _sys) __SYSCALL_ ## _cond (_nr, _sys) +#endif + +#ifndef __SCC +#ifdef __SYSCALL_COMPAT +#define __SCC(_cond, _nr, _sys, _comp) __SC(_cond, _nr, _comp) +#else +#define __SCC(_cond, _nr, _sys, _comp) __SC(_cond, _nr, _sys) +#endif +#endif + #if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT) #define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32) +#define __SYSCALL_32(_nr, _sys) __SYSCALL(__NR_ ## _nr, _sys) +#define __SYSCALL_64(_nr, _sys) #else #define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64) +#define __SYSCALL_32(_nr, _sys) +#define __SYSCALL_64(_nr, _sys) __SYSCALL(__NR_ ## _nr, _sys) +#endif + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) +#define __SYSCALL_time32(_nr, _sys) __SYSCALL_32(__NR_ ## _nr, _sys) +#else +#define __SYSCALL_time32(_nr, _sys) #endif #ifdef __SYSCALL_COMPAT @@ -41,7 +63,8 @@ __SYSCALL(__NR_io_cancel, sys_io_cancel) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_io_getevents 4 -__SC_3264(__NR_io_getevents, sys_io_getevents_time32, sys_io_getevents) +__SC(time32, io_getevents, sys_io_getevents_time32) +__SC(64, io_getevents, sys_io_getevents) #endif #define __NR_setxattr 5 @@ -190,9 +213,11 @@ __SYSCALL(__NR3264_sendfile, sys_sendfile64) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_pselect6 72 -__SC_COMP_3264(__NR_pselect6, sys_pselect6_time32, sys_pselect6, compat_sys_pselect6_time32) +__SCC(time32, pselect6, sys_pselect6_time32, compat_sys_pselect6_time32) +__SC(64, pselect6, sys_pselect6) #define __NR_ppoll 73 -__SC_COMP_3264(__NR_ppoll, sys_ppoll_time32, sys_ppoll, compat_sys_ppoll_time32) +__SCC(time32, ppoll, sys_ppoll_time32, compat_sys_ppoll_time32) +__SC(64, ppoll, sys_ppoll) #endif #define __NR_signalfd4 74 @@ -235,16 +260,17 @@ __SYSCALL(__NR_timerfd_create, sys_timerfd_create) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_timerfd_settime 86 -__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \ - sys_timerfd_settime) +__SC(time32, timerfd_settime, sys_timerfd_settime32) +__SC(64, timerfd_settime, sys_timerfd_settime) #define __NR_timerfd_gettime 87 -__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \ - sys_timerfd_gettime) +__SC(time32, timerfd_gettime, sys_timerfd_gettime32) +__SC(64, timerfd_gettime, sys_timerfd_gettime) #endif #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_utimensat 88 -__SC_3264(__NR_utimensat, sys_utimensat_time32, sys_utimensat) +__SC(time32, utimensat, sys_utimensat_time32) +__SC(64, utimensat, sys_utimensat) #endif #define __NR_acct 89 @@ -268,7 +294,8 @@ __SYSCALL(__NR_unshare, sys_unshare) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_futex 98 -__SC_3264(__NR_futex, sys_futex_time32, sys_futex) +__SC(time32, futex, sys_futex_time32) +__SC(64, futex, sys_futex) #endif #define __NR_set_robust_list 99 @@ -280,7 +307,8 @@ __SC_COMP(__NR_get_robust_list, sys_get_robust_list, \ #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_nanosleep 101 -__SC_3264(__NR_nanosleep, sys_nanosleep_time32, sys_nanosleep) +__SC(time32, nanosleep, sys_nanosleep_time32) +__SC(64, nanosleep, sys_nanosleep) #endif #define __NR_getitimer 102 @@ -298,7 +326,8 @@ __SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_timer_gettime 108 -__SC_3264(__NR_timer_gettime, sys_timer_gettime32, sys_timer_gettime) +__SC(time32, timer_gettime, sys_timer_gettime32) +__SC(64, timer_gettime, sys_timer_gettime) #endif #define __NR_timer_getoverrun 109 @@ -306,7 +335,8 @@ __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_timer_settime 110 -__SC_3264(__NR_timer_settime, sys_timer_settime32, sys_timer_settime) +__SC(time32, timer_settime, sys_timer_settime32) +__SC(64, timer_settime, sys_timer_settime) #endif #define __NR_timer_delete 111 @@ -314,14 +344,17 @@ __SYSCALL(__NR_timer_delete, sys_timer_delete) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_clock_settime 112 -__SC_3264(__NR_clock_settime, sys_clock_settime32, sys_clock_settime) +__SC(time32, clock_settime, sys_clock_settime32) +__SC(64, clock_settime, sys_clock_settime) #define __NR_clock_gettime 113 -__SC_3264(__NR_clock_gettime, sys_clock_gettime32, sys_clock_gettime) +__SC(time32, clock_gettime, sys_clock_gettime32) +__SC(64, clock_gettime, sys_clock_gettime) #define __NR_clock_getres 114 -__SC_3264(__NR_clock_getres, sys_clock_getres_time32, sys_clock_getres) +__SC(time32, clock_getres, sys_clock_getres_time32) +__SC(64, clock_getres, sys_clock_getres) #define __NR_clock_nanosleep 115 -__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \ - sys_clock_nanosleep) +__SC(time32, clock_nanosleep, sys_clock_nanosleep_time32) +__SC(64, clock_nanosleep, sys_clock_nanosleep) #endif #define __NR_syslog 116 @@ -351,8 +384,8 @@ __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_sched_rr_get_interval 127 -__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \ - sys_sched_rr_get_interval) +__SC(time32, sched_rr_get_interval, sys_sched_rr_get_interval_time32) +__SC(64, sched_rr_get_interval, sys_sched_rr_get_interval) #endif #define __NR_restart_syscall 128 @@ -376,8 +409,8 @@ __SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_rt_sigtimedwait 137 -__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \ - sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32) +__SCC(time32, rt_sigtimedwait, sys_rt_sigtimedwait_time32, compat_sys_rt_sigtimedwait_time32) +__SC(64, rt_sigtimedwait, sys_rt_sigtimedwait) #endif #define __NR_rt_sigqueueinfo 138 @@ -451,11 +484,14 @@ __SYSCALL(__NR_getcpu, sys_getcpu) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_gettimeofday 169 -__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday) +__SCC(time32, gettimeofday, sys_gettimeofday, compat_sys_gettimeofday) +__SC(64, gettimeofday, sys_gettimeofday) #define __NR_settimeofday 170 -__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday) +__SCC(time32, settimeofday, sys_settimeofday, compat_sys_settimeofday) +__SC(64, settimeofday, sys_settimeofday) #define __NR_adjtimex 171 -__SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex) +__SC(time32, adjtimex, sys_adjtimex_time32) +__SC(64, adjtimex, sys_adjtimex) #endif #define __NR_getpid 172 @@ -481,10 +517,11 @@ __SYSCALL(__NR_mq_unlink, sys_mq_unlink) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_mq_timedsend 182 -__SC_3264(__NR_mq_timedsend, sys_mq_timedsend_time32, sys_mq_timedsend) +__SC(time32, mq_timedsend, sys_mq_timedsend_time32) +__SC(64, mq_timedsend, sys_mq_timedsend) #define __NR_mq_timedreceive 183 -__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \ - sys_mq_timedreceive) +__SC(time32, mq_timedreceive, sys_mq_timedreceive_time32) +__SC(64, mq_timedreceive, sys_mq_timedreceive) #endif #define __NR_mq_notify 184 @@ -506,7 +543,8 @@ __SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_semtimedop 192 -__SC_3264(__NR_semtimedop, sys_semtimedop_time32, sys_semtimedop) +__SC(time32, semtimedop, sys_semtimedop_time32) +__SC(64, semtimedop, sys_semtimedop) #endif #define __NR_semop 193 @@ -618,7 +656,8 @@ __SYSCALL(__NR_accept4, sys_accept4) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_recvmmsg 243 -__SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recvmmsg_time32) +__SCC(time32, recvmmsg, sys_recvmmsg_time32, compat_sys_recvmmsg_time32) +__SC(64, recvmmsg, sys_recvmmsg) #endif /* @@ -629,7 +668,8 @@ __SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recv #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_wait4 260 -__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4) +__SCC(time32, wait4, sys_wait4, compat_sys_wait4) +__SC(64, wait4, sys_wait4) #endif #define __NR_prlimit64 261 @@ -645,7 +685,8 @@ __SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_clock_adjtime 266 -__SC_3264(__NR_clock_adjtime, sys_clock_adjtime32, sys_clock_adjtime) +__SC(time32, clock_adjtime, sys_clock_adjtime32) +__SC(64, clock_adjtime, sys_clock_adjtime) #endif #define __NR_syncfs 267 @@ -701,7 +742,8 @@ __SYSCALL(__NR_statx, sys_statx) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_io_pgetevents 292 -__SC_COMP_3264(__NR_io_pgetevents, sys_io_pgetevents_time32, sys_io_pgetevents, compat_sys_io_pgetevents) +__SCC(time32, io_pgetevents, sys_io_pgetevents_time32, compat_sys_io_pgetevents) +__SC(64, io_pgetevents, sys_io_pgetevents) #endif #define __NR_rseq 293 @@ -713,45 +755,45 @@ __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) #if defined(__SYSCALL_COMPAT) || __BITS_PER_LONG == 32 #define __NR_clock_gettime64 403 -__SYSCALL(__NR_clock_gettime64, sys_clock_gettime) +__SC(32, clock_gettime64, sys_clock_gettime) #define __NR_clock_settime64 404 -__SYSCALL(__NR_clock_settime64, sys_clock_settime) +__SC(32, clock_settime64, sys_clock_settime) #define __NR_clock_adjtime64 405 -__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime) +__SC(32, clock_adjtime64, sys_clock_adjtime) #define __NR_clock_getres_time64 406 -__SYSCALL(__NR_clock_getres_time64, sys_clock_getres) +__SC(32, clock_getres_time64, sys_clock_getres) #define __NR_clock_nanosleep_time64 407 -__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep) +__SC(32, clock_nanosleep_time64, sys_clock_nanosleep) #define __NR_timer_gettime64 408 -__SYSCALL(__NR_timer_gettime64, sys_timer_gettime) +__SC(32, timer_gettime64, sys_timer_gettime) #define __NR_timer_settime64 409 -__SYSCALL(__NR_timer_settime64, sys_timer_settime) +__SC(32, timer_settime64, sys_timer_settime) #define __NR_timerfd_gettime64 410 -__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime) +__SC(32, timerfd_gettime64, sys_timerfd_gettime) #define __NR_timerfd_settime64 411 -__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime) +__SC(32, timerfd_settime64, sys_timerfd_settime) #define __NR_utimensat_time64 412 -__SYSCALL(__NR_utimensat_time64, sys_utimensat) +__SC(32, utimensat_time64, sys_utimensat) #define __NR_pselect6_time64 413 -__SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) +__SCC(32, pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 -__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) +__SCC(32, ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) +__SCC(32, io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 -__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) +__SCC(32, recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 -__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend) +__SC(32, mq_timedsend_time64, sys_mq_timedsend) #define __NR_mq_timedreceive_time64 419 -__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive) +__SC(32, mq_timedreceive_time64, sys_mq_timedreceive) #define __NR_semtimedop_time64 420 -__SYSCALL(__NR_semtimedop_time64, sys_semtimedop) +__SC(32, semtimedop_time64, sys_semtimedop) #define __NR_rt_sigtimedwait_time64 421 -__SC_COMP(__NR_rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64) +__SCC(32, rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64) #define __NR_futex_time64 422 -__SYSCALL(__NR_futex_time64, sys_futex) +__SC(32, futex_time64, sys_futex) #define __NR_sched_rr_get_interval_time64 423 -__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) +__SC(32, sched_rr_get_interval_time64, sys_sched_rr_get_interval) #endif #define __NR_pidfd_send_signal 424 -- 2.39.2

8 months

2
1
0 0

[PATCH v2] powerpc: Fix unnecessary copy to 0 when kernel is booted at address 0.

by Jinglin Wen

According to the code logic, when the kernel is loaded to address 0, no copying operation should be performed, but it is currently being done. This patch fixes the issue where the kernel code was incorrectly duplicated to address 0 when booting from address 0. Fixes: b270bebd34e3 ("powerpc/64s: Run at the kernel virtual address earlier in boot") Signed-off-by: Jinglin Wen <jinglin.wen(a)shingroup.cn> Suggested-by: Michael Ellerman <mpe(a)ellerman.id.au> Cc: <stable(a)vger.kernel.org> --- v2: - According to 87le336c6k.fsf(a)mail.lhotse, improve this patch. v1: - 20240617023509.5674-1-jinglin.wen(a)shingroup.cn arch/powerpc/kernel/head_64.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4690c219bfa4..63432a33ec49 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -647,8 +647,9 @@ __after_prom_start: * Note: This process overwrites the OF exception vectors. */ LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET) - mr. r4,r26 /* In some cases the loader may */ - beq 9f /* have already put us at zero */ + mr r4,r26 /* Load the virtual source address into r4 */ + cmpld r3,r4 /* Check if source == dest */ + beq 9f /* If so skip the copy */ li r6,0x100 /* Start offset, the first 0x100 */ /* bytes were copied earlier. */ -- 2.25.1

8 months

2
1
0 0

[PATCHv5 2/4] x86/tdx: Rename tdx_parse_tdinfo() to tdx_setup()

by Kirill A. Shutemov

Rename tdx_parse_tdinfo() to tdx_setup() and move setting NOTIFY_ENABLES there. The function will be extended to adjust TD configuration. Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy(a)linux.intel.com> Reviewed-by: Kai Huang <kai.huang(a)intel.com> Cc: stable(a)vger.kernel.org --- arch/x86/coco/tdx/tdx.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 64717a96a936..08ce488b54d0 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -193,7 +193,7 @@ static void __noreturn tdx_panic(const char *msg) __tdx_hypercall(&args); } -static void tdx_parse_tdinfo(u64 *cc_mask) +static void tdx_setup(u64 *cc_mask) { struct tdx_module_args args = {}; unsigned int gpa_width; @@ -218,6 +218,9 @@ static void tdx_parse_tdinfo(u64 *cc_mask) gpa_width = args.rcx & GENMASK(5, 0); *cc_mask = BIT_ULL(gpa_width - 1); + /* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */ + tdg_vm_wr(TDCS_NOTIFY_ENABLES, 0, -1ULL); + /* * The kernel can not handle #VE's when accessing normal kernel * memory. Ensure that no #VE will be delivered for accesses to @@ -964,11 +967,11 @@ void __init tdx_early_init(void) setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); cc_vendor = CC_VENDOR_INTEL; - tdx_parse_tdinfo(&cc_mask); - cc_set_mask(cc_mask); - /* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */ - tdg_vm_wr(TDCS_NOTIFY_ENABLES, 0, -1ULL); + /* Configure the TD */ + tdx_setup(&cc_mask); + + cc_set_mask(cc_mask); /* * All bits above GPA width are reserved and kernel treats shared bit -- 2.43.0

8 months

1
0
0 0

[PATCHv5 1/4] x86/tdx: Introduce wrappers to read and write TD metadata

by Kirill A. Shutemov

The TDG_VM_WR TDCALL is used to ask the TDX module to change some TD-specific VM configuration. There is currently only one user in the kernel of this TDCALL leaf. More will be added shortly. Refactor to make way for more users of TDG_VM_WR who will need to modify other TD configuration values. Add a wrapper for the TDG_VM_RD TDCALL that requests TD-specific metadata from the TDX module. There are currently no users for TDG_VM_RD. Mark it as __maybe_unused until the first user appears. This is preparation for enumeration and enabling optional TD features. Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Reviewed-by: Kai Huang <kai.huang(a)intel.com> Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy(a)linux.intel.com> Cc: stable(a)vger.kernel.org --- arch/x86/coco/tdx/tdx.c | 32 ++++++++++++++++++++++++++----- arch/x86/include/asm/shared/tdx.h | 1 + 2 files changed, 28 insertions(+), 5 deletions(-) diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 078e2bac2553..64717a96a936 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -77,6 +77,32 @@ static inline void tdcall(u64 fn, struct tdx_module_args *args) panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); } +/* Read TD-scoped metadata */ +static inline u64 __maybe_unused tdg_vm_rd(u64 field, u64 *value) +{ + struct tdx_module_args args = { + .rdx = field, + }; + u64 ret; + + ret = __tdcall_ret(TDG_VM_RD, &args); + *value = args.r8; + + return ret; +} + +/* Write TD-scoped metadata */ +static inline u64 tdg_vm_wr(u64 field, u64 value, u64 mask) +{ + struct tdx_module_args args = { + .rdx = field, + .r8 = value, + .r9 = mask, + }; + + return __tdcall(TDG_VM_WR, &args); +} + /** * tdx_mcall_get_report0() - Wrapper to get TDREPORT0 (a.k.a. TDREPORT * subtype 0) using TDG.MR.REPORT TDCALL. @@ -924,10 +950,6 @@ static void tdx_kexec_finish(void) void __init tdx_early_init(void) { - struct tdx_module_args args = { - .rdx = TDCS_NOTIFY_ENABLES, - .r9 = -1ULL, - }; u64 cc_mask; u32 eax, sig[3]; @@ -946,7 +968,7 @@ void __init tdx_early_init(void) cc_set_mask(cc_mask); /* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */ - tdcall(TDG_VM_WR, &args); + tdg_vm_wr(TDCS_NOTIFY_ENABLES, 0, -1ULL); /* * All bits above GPA width are reserved and kernel treats shared bit diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index fdfd41511b02..7e12cfa28bec 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -16,6 +16,7 @@ #define TDG_VP_VEINFO_GET 3 #define TDG_MR_REPORT 4 #define TDG_MEM_PAGE_ACCEPT 6 +#define TDG_VM_RD 7 #define TDG_VM_WR 8 /* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */ -- 2.43.0

8 months

1
0
0 0

[PATCH v2 2/5] mei: vsc: Enhance SPI transfer of IVSC rom

by Wentong Wu

Constructing the SPI transfer command as per the specific request. Fixes: 566f5ca97680 ("mei: Add transport driver for IVSC device") Cc: stable(a)vger.kernel.org # for 6.8+ Signed-off-by: Wentong Wu <wentong.wu(a)intel.com> Tested-by: Jason Chen <jason.z.chen(a)intel.com> --- drivers/misc/mei/vsc-tp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c index 5f3195636e53..fed156919fda 100644 --- a/drivers/misc/mei/vsc-tp.c +++ b/drivers/misc/mei/vsc-tp.c @@ -331,7 +331,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len) return ret; } - ret = vsc_tp_dev_xfer(tp, tp->tx_buf, tp->rx_buf, len); + ret = vsc_tp_dev_xfer(tp, tp->tx_buf, ibuf ? tp->rx_buf : ibuf, len); if (ret) return ret; -- 2.34.1

8 months

3
2
0 0

FAILED: patch "[PATCH] mm: fix race between __split_huge_pmd_locked() and GUP-fast" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 3a5a8d343e1cf96eb9971b17cbd4b832ab19b8e7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024061319-skater-sculptor-905f@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: 3a5a8d343e1c ("mm: fix race between __split_huge_pmd_locked() and GUP-fast") 4f83145721f3 ("mm: avoid unnecessary flush on change_huge_pmd()") c9fe66560bf2 ("mm/mprotect: do not flush when not required architecturally") 4a18419f71cd ("mm/mprotect: use mmu_gather") e346e6688c4a ("mm: thp: skip make PMD PROT_NONE if THP migration is not supported") f0953a1bbaca ("mm: fix typos in comments") e2db1a9aa381 ("kasan, mm: optimize kmalloc poisoning") 928501344fc6 ("kasan, mm: don't save alloc stacks twice") 2b8305260fb3 ("kfence, kasan: make KFENCE compatible with KASAN") 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure") 41139aa4c3a3 ("mm/filemap: add mapping_seek_hole_data") a1ba9da8f0f9 ("mm/hugetlb.c: fix unnecessary address expansion of pmd sharing") 611806b4bf8d ("kasan: fix bug detection via ksize for HW_TAGS mode") 027b37b552f3 ("kasan: move _RET_IP_ to inline wrappers") 573a48092313 ("kasan: add match-all tag tests") f00748bfa024 ("kasan: prefix global functions with kasan_") dbf53f7597be ("mm/mprotect.c: optimize error detection in do_mprotect_pkey()") 96667f8a4382 ("mm: Close race in generic_access_phys") 97593cad003c ("kasan: sanitize objects when metadata doesn't fit") 1ef3133bd3b8 ("kasan: simplify assign_tag and set_tag calls") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 3a5a8d343e1cf96eb9971b17cbd4b832ab19b8e7 Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Wed, 1 May 2024 15:33:10 +0100 Subject: [PATCH] mm: fix race between __split_huge_pmd_locked() and GUP-fast __split_huge_pmd_locked() can be called for a present THP, devmap or (non-present) migration entry. It calls pmdp_invalidate() unconditionally on the pmdp and only determines if it is present or not based on the returned old pmd. This is a problem for the migration entry case because pmd_mkinvalid(), called by pmdp_invalidate() must only be called for a present pmd. On arm64 at least, pmd_mkinvalid() will mark the pmd such that any future call to pmd_present() will return true. And therefore any lockless pgtable walker could see the migration entry pmd in this state and start interpretting the fields as if it were present, leading to BadThings (TM). GUP-fast appears to be one such lockless pgtable walker. x86 does not suffer the above problem, but instead pmd_mkinvalid() will corrupt the offset field of the swap entry within the swap pte. See link below for discussion of that problem. Fix all of this by only calling pmdp_invalidate() for a present pmd. And for good measure let's add a warning to all implementations of pmdp_invalidate[_ad](). I've manually reviewed all other pmdp_invalidate[_ad]() call sites and believe all others to be conformant. This is a theoretical bug found during code review. I don't have any test case to trigger it in practice. Link: https://lkml.kernel.org/r/20240501143310.1381675-1-ryan.roberts@arm.com Link: https://lore.kernel.org/all/0dd7827a-6334-439a-8fd0-43c98e6af22b@arm.com/ Fixes: 84c3fc4e9c56 ("mm: thp: check pmd migration entry in common path") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Zi Yan <ziy(a)nvidia.com> Reviewed-by: Anshuman Khandual <anshuman.khandual(a)arm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Andreas Larsson <andreas(a)gaisler.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Aneesh Kumar K.V <aneesh.kumar(a)kernel.org> Cc: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Christian Borntraeger <borntraeger(a)linux.ibm.com> Cc: Christophe Leroy <christophe.leroy(a)csgroup.eu> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Jonathan Corbet <corbet(a)lwn.net> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Naveen N. Rao <naveen.n.rao(a)linux.ibm.com> Cc: Nicholas Piggin <npiggin(a)gmail.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Sven Schnelle <svens(a)linux.ibm.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Will Deacon <will(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst index 2466d3363af7..ad50ca6f495e 100644 --- a/Documentation/mm/arch_pgtable_helpers.rst +++ b/Documentation/mm/arch_pgtable_helpers.rst @@ -140,7 +140,8 @@ PMD Page Table Helpers +---------------------------+--------------------------------------------------+ | pmd_swp_clear_soft_dirty | Clears a soft dirty swapped PMD | +---------------------------+--------------------------------------------------+ -| pmd_mkinvalid | Invalidates a mapped PMD [1] | +| pmd_mkinvalid | Invalidates a present PMD; do not call for | +| | non-present PMD [1] | +---------------------------+--------------------------------------------------+ | pmd_set_huge | Creates a PMD huge mapping | +---------------------------+--------------------------------------------------+ @@ -196,7 +197,8 @@ PUD Page Table Helpers +---------------------------+--------------------------------------------------+ | pud_mkdevmap | Creates a ZONE_DEVICE mapped PUD | +---------------------------+--------------------------------------------------+ -| pud_mkinvalid | Invalidates a mapped PUD [1] | +| pud_mkinvalid | Invalidates a present PUD; do not call for | +| | non-present PUD [1] | +---------------------------+--------------------------------------------------+ | pud_set_huge | Creates a PUD huge mapping | +---------------------------+--------------------------------------------------+ diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 83823db3488b..2975ea0841ba 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -170,6 +170,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { unsigned long old_pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return __pmd(old_pmd); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 2cb2a2e7b34b..558902edbfec 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1769,8 +1769,10 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, static inline pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); + pmd_t pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); return pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd); } diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 19642f7ffb52..8648a50afe88 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -249,6 +249,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { pmd_t old, entry; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID); old = pmdp_establish(vma, address, pmdp, entry); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 94767c82fc0d..93e54ba91fbf 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -631,6 +631,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 08e4f3343bcd..ccdcff73284a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2430,32 +2430,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, return __split_huge_zero_page_pmd(vma, haddr, pmd); } - /* - * Up to this point the pmd is present and huge and userland has the - * whole access to the hugepage during the split (which happens in - * place). If we overwrite the pmd with the not-huge version pointing - * to the pte here (which of course we could if all CPUs were bug - * free), userland could trigger a small page size TLB miss on the - * small sized TLB while the hugepage TLB entry is still established in - * the huge TLB. Some CPU doesn't like that. - * See http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum - * 383 on page 105. Intel should be safe but is also warns that it's - * only safe if the permission and cache attributes of the two entries - * loaded in the two TLB is identical (which should be the case here). - * But it is generally safer to never allow small and huge TLB entries - * for the same virtual address to be loaded simultaneously. So instead - * of doing "pmd_populate(); flush_pmd_tlb_range();" we first mark the - * current pmd notpresent (atomically because here the pmd_trans_huge - * must remain set at all times on the pmd until the split is complete - * for this pmd), then we flush the SMP TLB and finally we write the - * non-huge version of the pmd entry with pmd_populate. - */ - old_pmd = pmdp_invalidate(vma, haddr, pmd); - - pmd_migration = is_pmd_migration_entry(old_pmd); + pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) { swp_entry_t entry; + old_pmd = *pmd; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); @@ -2466,6 +2445,30 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { + /* + * Up to this point the pmd is present and huge and userland has + * the whole access to the hugepage during the split (which + * happens in place). If we overwrite the pmd with the not-huge + * version pointing to the pte here (which of course we could if + * all CPUs were bug free), userland could trigger a small page + * size TLB miss on the small sized TLB while the hugepage TLB + * entry is still established in the huge TLB. Some CPU doesn't + * like that. See + * http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum + * 383 on page 105. Intel should be safe but is also warns that + * it's only safe if the permission and cache attributes of the + * two entries loaded in the two TLB is identical (which should + * be the case here). But it is generally safer to never allow + * small and huge TLB entries for the same virtual address to be + * loaded simultaneously. So instead of doing "pmd_populate(); + * flush_pmd_tlb_range();" we first mark the current pmd + * notpresent (atomically because here the pmd_trans_huge must + * remain set at all times on the pmd until the split is + * complete for this pmd), then we flush the SMP TLB and finally + * we write the non-huge version of the pmd entry with + * pmd_populate. + */ + old_pmd = pmdp_invalidate(vma, haddr, pmd); page = pmd_page(old_pmd); folio = page_folio(page); if (pmd_dirty(old_pmd)) { diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4fcd959dcc4d..a78a4adf711a 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -198,6 +198,7 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return old; @@ -208,6 +209,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); return pmdp_invalidate(vma, address, pmdp); } #endif

8 months

2
1
0 0

[PATCH net v3] net: usb: ax88179_178a: improve link status logs

by Jose Ignacio Tornos Martinez

Avoid spurious link status logs that may ultimately be wrong; for example, if the link is set to down with the cable plugged, then the cable is unplugged and after this the link is set to up, the last new log that is appearing is incorrectly telling that the link is up. In order to avoid errors, show link status logs after link_reset processing, and in order to avoid spurious as much as possible, only show the link loss when some link status change is detected. cc: stable(a)vger.kernel.org Fixes: e2ca90c276e1 ("ax88179_178a: ASIX AX88179_178A USB 3.0/2.0 to gigabit ethernet adapter driver") Signed-off-by: Jose Ignacio Tornos Martinez <jtornosm(a)redhat.com> --- v3: - Add net as target tree in the subject. - Use constant string instead of variable because no other value is possible. v2: https://lore.kernel.org/netdev/20240618115054.101577-1-jtornosm@redhat.com/ - Fix the nits v1: https://lore.kernel.org/netdev/20240617103405.654567-1-jtornosm@redhat.com/ drivers/net/usb/ax88179_178a.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index c2fb736f78b2..b034ef8a73ea 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -326,7 +326,8 @@ static void ax88179_status(struct usbnet *dev, struct urb *urb) if (netif_carrier_ok(dev->net) != link) { usbnet_link_change(dev, link, 1); - netdev_info(dev->net, "ax88179 - Link status is: %d\n", link); + if (!link) + netdev_info(dev->net, "ax88179 - Link status is: 0\n"); } } @@ -1542,6 +1543,7 @@ static int ax88179_link_reset(struct usbnet *dev) GMII_PHY_PHYSR, 2, &tmp16); if (!(tmp16 & GMII_PHY_PHYSR_LINK)) { + netdev_info(dev->net, "ax88179 - Link status is: 0\n"); return 0; } else if (GMII_PHY_PHYSR_GIGA == (tmp16 & GMII_PHY_PHYSR_SMASK)) { mode |= AX_MEDIUM_GIGAMODE | AX_MEDIUM_EN_125MHZ; @@ -1579,6 +1581,8 @@ static int ax88179_link_reset(struct usbnet *dev) netif_carrier_on(dev->net); + netdev_info(dev->net, "ax88179 - Link status is: 1\n"); + return 0; } -- 2.45.1

8 months

3
2
0 0

FAILED: patch "[PATCH] mm: fix race between __split_huge_pmd_locked() and GUP-fast" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 3a5a8d343e1cf96eb9971b17cbd4b832ab19b8e7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024061316-brook-imaging-a202@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 3a5a8d343e1c ("mm: fix race between __split_huge_pmd_locked() and GUP-fast") 4f83145721f3 ("mm: avoid unnecessary flush on change_huge_pmd()") c9fe66560bf2 ("mm/mprotect: do not flush when not required architecturally") 4a18419f71cd ("mm/mprotect: use mmu_gather") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 3a5a8d343e1cf96eb9971b17cbd4b832ab19b8e7 Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Wed, 1 May 2024 15:33:10 +0100 Subject: [PATCH] mm: fix race between __split_huge_pmd_locked() and GUP-fast __split_huge_pmd_locked() can be called for a present THP, devmap or (non-present) migration entry. It calls pmdp_invalidate() unconditionally on the pmdp and only determines if it is present or not based on the returned old pmd. This is a problem for the migration entry case because pmd_mkinvalid(), called by pmdp_invalidate() must only be called for a present pmd. On arm64 at least, pmd_mkinvalid() will mark the pmd such that any future call to pmd_present() will return true. And therefore any lockless pgtable walker could see the migration entry pmd in this state and start interpretting the fields as if it were present, leading to BadThings (TM). GUP-fast appears to be one such lockless pgtable walker. x86 does not suffer the above problem, but instead pmd_mkinvalid() will corrupt the offset field of the swap entry within the swap pte. See link below for discussion of that problem. Fix all of this by only calling pmdp_invalidate() for a present pmd. And for good measure let's add a warning to all implementations of pmdp_invalidate[_ad](). I've manually reviewed all other pmdp_invalidate[_ad]() call sites and believe all others to be conformant. This is a theoretical bug found during code review. I don't have any test case to trigger it in practice. Link: https://lkml.kernel.org/r/20240501143310.1381675-1-ryan.roberts@arm.com Link: https://lore.kernel.org/all/0dd7827a-6334-439a-8fd0-43c98e6af22b@arm.com/ Fixes: 84c3fc4e9c56 ("mm: thp: check pmd migration entry in common path") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Zi Yan <ziy(a)nvidia.com> Reviewed-by: Anshuman Khandual <anshuman.khandual(a)arm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Andreas Larsson <andreas(a)gaisler.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Aneesh Kumar K.V <aneesh.kumar(a)kernel.org> Cc: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Christian Borntraeger <borntraeger(a)linux.ibm.com> Cc: Christophe Leroy <christophe.leroy(a)csgroup.eu> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Jonathan Corbet <corbet(a)lwn.net> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Naveen N. Rao <naveen.n.rao(a)linux.ibm.com> Cc: Nicholas Piggin <npiggin(a)gmail.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Sven Schnelle <svens(a)linux.ibm.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Will Deacon <will(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst index 2466d3363af7..ad50ca6f495e 100644 --- a/Documentation/mm/arch_pgtable_helpers.rst +++ b/Documentation/mm/arch_pgtable_helpers.rst @@ -140,7 +140,8 @@ PMD Page Table Helpers +---------------------------+--------------------------------------------------+ | pmd_swp_clear_soft_dirty | Clears a soft dirty swapped PMD | +---------------------------+--------------------------------------------------+ -| pmd_mkinvalid | Invalidates a mapped PMD [1] | +| pmd_mkinvalid | Invalidates a present PMD; do not call for | +| | non-present PMD [1] | +---------------------------+--------------------------------------------------+ | pmd_set_huge | Creates a PMD huge mapping | +---------------------------+--------------------------------------------------+ @@ -196,7 +197,8 @@ PUD Page Table Helpers +---------------------------+--------------------------------------------------+ | pud_mkdevmap | Creates a ZONE_DEVICE mapped PUD | +---------------------------+--------------------------------------------------+ -| pud_mkinvalid | Invalidates a mapped PUD [1] | +| pud_mkinvalid | Invalidates a present PUD; do not call for | +| | non-present PUD [1] | +---------------------------+--------------------------------------------------+ | pud_set_huge | Creates a PUD huge mapping | +---------------------------+--------------------------------------------------+ diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 83823db3488b..2975ea0841ba 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -170,6 +170,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { unsigned long old_pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return __pmd(old_pmd); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 2cb2a2e7b34b..558902edbfec 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1769,8 +1769,10 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, static inline pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); + pmd_t pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); return pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd); } diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 19642f7ffb52..8648a50afe88 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -249,6 +249,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { pmd_t old, entry; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID); old = pmdp_establish(vma, address, pmdp, entry); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 94767c82fc0d..93e54ba91fbf 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -631,6 +631,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 08e4f3343bcd..ccdcff73284a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2430,32 +2430,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, return __split_huge_zero_page_pmd(vma, haddr, pmd); } - /* - * Up to this point the pmd is present and huge and userland has the - * whole access to the hugepage during the split (which happens in - * place). If we overwrite the pmd with the not-huge version pointing - * to the pte here (which of course we could if all CPUs were bug - * free), userland could trigger a small page size TLB miss on the - * small sized TLB while the hugepage TLB entry is still established in - * the huge TLB. Some CPU doesn't like that. - * See http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum - * 383 on page 105. Intel should be safe but is also warns that it's - * only safe if the permission and cache attributes of the two entries - * loaded in the two TLB is identical (which should be the case here). - * But it is generally safer to never allow small and huge TLB entries - * for the same virtual address to be loaded simultaneously. So instead - * of doing "pmd_populate(); flush_pmd_tlb_range();" we first mark the - * current pmd notpresent (atomically because here the pmd_trans_huge - * must remain set at all times on the pmd until the split is complete - * for this pmd), then we flush the SMP TLB and finally we write the - * non-huge version of the pmd entry with pmd_populate. - */ - old_pmd = pmdp_invalidate(vma, haddr, pmd); - - pmd_migration = is_pmd_migration_entry(old_pmd); + pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) { swp_entry_t entry; + old_pmd = *pmd; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); @@ -2466,6 +2445,30 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { + /* + * Up to this point the pmd is present and huge and userland has + * the whole access to the hugepage during the split (which + * happens in place). If we overwrite the pmd with the not-huge + * version pointing to the pte here (which of course we could if + * all CPUs were bug free), userland could trigger a small page + * size TLB miss on the small sized TLB while the hugepage TLB + * entry is still established in the huge TLB. Some CPU doesn't + * like that. See + * http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum + * 383 on page 105. Intel should be safe but is also warns that + * it's only safe if the permission and cache attributes of the + * two entries loaded in the two TLB is identical (which should + * be the case here). But it is generally safer to never allow + * small and huge TLB entries for the same virtual address to be + * loaded simultaneously. So instead of doing "pmd_populate(); + * flush_pmd_tlb_range();" we first mark the current pmd + * notpresent (atomically because here the pmd_trans_huge must + * remain set at all times on the pmd until the split is + * complete for this pmd), then we flush the SMP TLB and finally + * we write the non-huge version of the pmd entry with + * pmd_populate. + */ + old_pmd = pmdp_invalidate(vma, haddr, pmd); page = pmd_page(old_pmd); folio = page_folio(page); if (pmd_dirty(old_pmd)) { diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4fcd959dcc4d..a78a4adf711a 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -198,6 +198,7 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return old; @@ -208,6 +209,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); return pmdp_invalidate(vma, address, pmdp); } #endif

8 months

3
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2024