From 35f3f8504c3b60a1ae5576e178b27fc0ddd6157d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 10 May 2021 16:12:42 +0300 Subject: spi: Switch to signed types for *_native_cs SPI controller fields While fixing undefined behaviour the commit f60d7270c8a3 ("spi: Avoid undefined behaviour when counting unused native CSs") missed the case when all CSs are GPIOs and thus unused_native_cs will be evaluated to -1 in unsigned representation. This will falsely trigger a condition in the spi_get_gpio_descs(). Switch to signed types for *_native_cs SPI controller fields to fix above. Fixes: f60d7270c8a3 ("spi: Avoid undefined behaviour when counting unused native CSs") Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210510131242.49455-1-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 360a3bc767ca..74239d65c7fd 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -644,8 +644,8 @@ struct spi_controller { int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; - u8 unused_native_cs; - u8 max_native_cs; + s8 unused_native_cs; + s8 max_native_cs; /* statistics */ struct spi_statistics statistics; -- cgit From add0b32ef9146a8559a60aed54c37692a5f9d34f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 30 Apr 2021 17:06:01 -0500 Subject: siginfo: Move si_trapno inside the union inside _si_fault It turns out that linux uses si_trapno very sparingly, and as such it can be considered extra information for a very narrow selection of signals, rather than information that is present with every fault reported in siginfo. As such move si_trapno inside the union inside of _si_fault. This results in no change in placement, and makes it eaiser to extend _si_fault in the future as this reduces the number of special cases. In particular with si_trapno included in the union it is no longer a concern that the union must be pointer aligned on most architectures because the union follows immediately after si_addr which is a pointer. This change results in a difference in siginfo field placement on sparc and alpha for the fields si_addr_lsb, si_lower, si_upper, si_pkey, and si_perf. These architectures do not implement the signals that would use si_addr_lsb, si_lower, si_upper, si_pkey, and si_perf. Further these architecture have not yet implemented the userspace that would use si_perf. The point of this change is in fact to correct these placement issues before sparc or alpha grow userspace that cares. This change was discussed[1] and the agreement is that this change is currently safe. [1]: https://lkml.kernel.org/r/CAK8P3a0+uKYwL1NhY6Hvtieghba2hKYGD6hcKx5n8=4Gtt+pHA@mail.gmail.com Acked-by: Marco Elver v1: https://lkml.kernel.org/r/m1tunns7yf.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210505141101.11519-5-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20210517195748.8880-1-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- arch/x86/kernel/signal_compat.c | 3 +++ include/linux/compat.h | 5 ++--- include/uapi/asm-generic/siginfo.h | 7 ++----- kernel/signal.c | 1 + 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index 0e5d0a7e203b..a9fcabd8a5e5 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -127,6 +127,9 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C); + BUILD_BUG_ON(offsetof(siginfo_t, si_trapno) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_trapno) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10); diff --git a/include/linux/compat.h b/include/linux/compat.h index f0d2dd35d408..6af7bef15e94 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -214,12 +214,11 @@ typedef struct compat_siginfo { /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGTRAP, SIGEMT */ struct { compat_uptr_t _addr; /* faulting insn/memory ref. */ -#ifdef __ARCH_SI_TRAPNO - int _trapno; /* TRAP # which caused the signal */ -#endif #define __COMPAT_ADDR_BND_PKEY_PAD (__alignof__(compat_uptr_t) < sizeof(short) ? \ sizeof(short) : __alignof__(compat_uptr_t)) union { + /* used on alpha and sparc */ + int _trapno; /* TRAP # which caused the signal */ /* * used when si_code=BUS_MCEERR_AR or * used when si_code=BUS_MCEERR_AO diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 03d6f6d2c1fe..e663bf117b46 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -63,9 +63,6 @@ union __sifields { /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGTRAP, SIGEMT */ struct { void __user *_addr; /* faulting insn/memory ref. */ -#ifdef __ARCH_SI_TRAPNO - int _trapno; /* TRAP # which caused the signal */ -#endif #ifdef __ia64__ int _imm; /* immediate value for "break" */ unsigned int _flags; /* see ia64 si_flags */ @@ -75,6 +72,8 @@ union __sifields { #define __ADDR_BND_PKEY_PAD (__alignof__(void *) < sizeof(short) ? \ sizeof(short) : __alignof__(void *)) union { + /* used on alpha and sparc */ + int _trapno; /* TRAP # which caused the signal */ /* * used when si_code=BUS_MCEERR_AR or * used when si_code=BUS_MCEERR_AO @@ -150,9 +149,7 @@ typedef struct siginfo { #define si_int _sifields._rt._sigval.sival_int #define si_ptr _sifields._rt._sigval.sival_ptr #define si_addr _sifields._sigfault._addr -#ifdef __ARCH_SI_TRAPNO #define si_trapno _sifields._sigfault._trapno -#endif #define si_addr_lsb _sifields._sigfault._addr_lsb #define si_lower _sifields._sigfault._addr_bnd._lower #define si_upper _sifields._sigfault._addr_bnd._upper diff --git a/kernel/signal.c b/kernel/signal.c index c3017aa8024a..65888aec65a0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -4607,6 +4607,7 @@ static inline void siginfo_buildtime_checks(void) /* sigfault */ CHECK_OFFSET(si_addr); + CHECK_OFFSET(si_trapno); CHECK_OFFSET(si_addr_lsb); CHECK_OFFSET(si_lower); CHECK_OFFSET(si_upper); -- cgit From 9abcabe3111811aeae0f3a14e159b14248631875 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 30 Apr 2021 17:29:36 -0500 Subject: signal: Implement SIL_FAULT_TRAPNO Now that si_trapno is part of the union in _si_fault and available on all architectures, add SIL_FAULT_TRAPNO and update siginfo_layout to return SIL_FAULT_TRAPNO when the code assumes si_trapno is valid. There is room for future changes to reduce when si_trapno is valid but this is all that is needed to make si_trapno and the other members of the the union in _sigfault mutually exclusive. Update the code that uses siginfo_layout to deal with SIL_FAULT_TRAPNO and have the same code ignore si_trapno in in all other cases. v1: https://lkml.kernel.org/r/m1o8dvs7s7.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210505141101.11519-6-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20210517195748.8880-2-ebiederm@xmission.com Reviewed-by: Marco Elver Signed-off-by: "Eric W. Biederman" --- fs/signalfd.c | 8 +++----- include/linux/signal.h | 1 + kernel/signal.c | 34 ++++++++++++---------------------- 3 files changed, 16 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/signalfd.c b/fs/signalfd.c index 040a1142915f..e87e59581653 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -123,15 +123,13 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, */ case SIL_FAULT: new.ssi_addr = (long) kinfo->si_addr; -#ifdef __ARCH_SI_TRAPNO + break; + case SIL_FAULT_TRAPNO: + new.ssi_addr = (long) kinfo->si_addr; new.ssi_trapno = kinfo->si_trapno; -#endif break; case SIL_FAULT_MCEERR: new.ssi_addr = (long) kinfo->si_addr; -#ifdef __ARCH_SI_TRAPNO - new.ssi_trapno = kinfo->si_trapno; -#endif new.ssi_addr_lsb = (short) kinfo->si_addr_lsb; break; case SIL_PERF_EVENT: diff --git a/include/linux/signal.h b/include/linux/signal.h index 1e98548d7cf6..5160fd45e5ca 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -40,6 +40,7 @@ enum siginfo_layout { SIL_TIMER, SIL_POLL, SIL_FAULT, + SIL_FAULT_TRAPNO, SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, diff --git a/kernel/signal.c b/kernel/signal.c index 65888aec65a0..597594ee72de 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1194,6 +1194,7 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info) case SIL_TIMER: case SIL_POLL: case SIL_FAULT: + case SIL_FAULT_TRAPNO: case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: @@ -2527,6 +2528,7 @@ static void hide_si_addr_tag_bits(struct ksignal *ksig) { switch (siginfo_layout(ksig->sig, ksig->info.si_code)) { case SIL_FAULT: + case SIL_FAULT_TRAPNO: case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: @@ -3214,6 +3216,10 @@ enum siginfo_layout siginfo_layout(unsigned sig, int si_code) #endif else if ((sig == SIGTRAP) && (si_code == TRAP_PERF)) layout = SIL_PERF_EVENT; +#ifdef __ARCH_SI_TRAPNO + else if (layout == SIL_FAULT) + layout = SIL_FAULT_TRAPNO; +#endif } else if (si_code <= NSIGPOLL) layout = SIL_POLL; @@ -3317,30 +3323,22 @@ void copy_siginfo_to_external32(struct compat_siginfo *to, break; case SIL_FAULT: to->si_addr = ptr_to_compat(from->si_addr); -#ifdef __ARCH_SI_TRAPNO + break; + case SIL_FAULT_TRAPNO: + to->si_addr = ptr_to_compat(from->si_addr); to->si_trapno = from->si_trapno; -#endif break; case SIL_FAULT_MCEERR: to->si_addr = ptr_to_compat(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: to->si_addr = ptr_to_compat(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_lower = ptr_to_compat(from->si_lower); to->si_upper = ptr_to_compat(from->si_upper); break; case SIL_FAULT_PKUERR: to->si_addr = ptr_to_compat(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_pkey = from->si_pkey; break; case SIL_PERF_EVENT: @@ -3401,30 +3399,22 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, break; case SIL_FAULT: to->si_addr = compat_ptr(from->si_addr); -#ifdef __ARCH_SI_TRAPNO + break; + case SIL_FAULT_TRAPNO: + to->si_addr = compat_ptr(from->si_addr); to->si_trapno = from->si_trapno; -#endif break; case SIL_FAULT_MCEERR: to->si_addr = compat_ptr(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: to->si_addr = compat_ptr(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_lower = compat_ptr(from->si_lower); to->si_upper = compat_ptr(from->si_upper); break; case SIL_FAULT_PKUERR: to->si_addr = compat_ptr(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_pkey = from->si_pkey; break; case SIL_PERF_EVENT: -- cgit From af5eeab7e8e8c2f0fad10e4ab8cc8092012a2d5b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 2 May 2021 14:27:24 -0500 Subject: signal: Factor force_sig_perf out of perf_sigtrap Separate filling in siginfo for TRAP_PERF from deciding that siginal needs to be sent. There are enough little details that need to be correct when properly filling in siginfo_t that it is easy to make mistakes if filling in the siginfo_t is in the same function with other logic. So factor out force_sig_perf to reduce the cognative load of on reviewers, maintainers and implementors. v1: https://lkml.kernel.org/r/m17dkjqqxz.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210505141101.11519-10-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20210517195748.8880-3-ebiederm@xmission.com Reviewed-by: Marco Elver Acked-by: Peter Zijlstra (Intel) Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 1 + kernel/events/core.c | 11 ++--------- kernel/signal.c | 13 +++++++++++++ 3 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3f6a0fcaa10c..7f4278fa21fe 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -326,6 +326,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); +int force_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); diff --git a/kernel/events/core.c b/kernel/events/core.c index 928b166d888e..48ea8863183b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6394,8 +6394,6 @@ void perf_event_wakeup(struct perf_event *event) static void perf_sigtrap(struct perf_event *event) { - struct kernel_siginfo info; - /* * We'd expect this to only occur if the irq_work is delayed and either * ctx->task or current has changed in the meantime. This can be the @@ -6410,13 +6408,8 @@ static void perf_sigtrap(struct perf_event *event) if (current->flags & PF_EXITING) return; - clear_siginfo(&info); - info.si_signo = SIGTRAP; - info.si_code = TRAP_PERF; - info.si_errno = event->attr.type; - info.si_perf = event->attr.sig_data; - info.si_addr = (void __user *)event->pending_addr; - force_sig_info(&info); + force_sig_perf((void __user *)event->pending_addr, + event->attr.type, event->attr.sig_data); } static void perf_pending_event_disable(struct perf_event *event) diff --git a/kernel/signal.c b/kernel/signal.c index 597594ee72de..3a18d13c39b2 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1763,6 +1763,19 @@ int force_sig_pkuerr(void __user *addr, u32 pkey) } #endif +int force_sig_perf(void __user *addr, u32 type, u64 sig_data) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = SIGTRAP; + info.si_errno = type; + info.si_code = TRAP_PERF; + info.si_addr = addr; + info.si_perf = sig_data; + return force_sig_info(&info); +} + /* For the crazy architectures that include trap information in * the errno field, instead of an actual errno value. */ -- cgit From 0683b53197b55343a166f1507086823030809a19 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 2 May 2021 17:28:31 -0500 Subject: signal: Deliver all of the siginfo perf data in _perf Don't abuse si_errno and deliver all of the perf data in _perf member of siginfo_t. Note: The data field in the perf data structures in a u64 to allow a pointer to be encoded without needed to implement a 32bit and 64bit version of the same structure. There already exists a 32bit and 64bit versions siginfo_t, and the 32bit version can not include a 64bit member as it only has 32bit alignment. So unsigned long is used in siginfo_t instead of a u64 as unsigned long can encode a pointer on all architectures linux supports. v1: https://lkml.kernel.org/r/m11rarqqx2.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210503203814.25487-10-ebiederm@xmission.com v3: https://lkml.kernel.org/r/20210505141101.11519-11-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20210517195748.8880-4-ebiederm@xmission.com Reviewed-by: Marco Elver Signed-off-by: "Eric W. Biederman" --- arch/m68k/kernel/signal.c | 3 ++- arch/x86/kernel/signal_compat.c | 6 ++++-- fs/signalfd.c | 3 ++- include/linux/compat.h | 5 ++++- include/uapi/asm-generic/siginfo.h | 8 ++++++-- include/uapi/linux/perf_event.h | 2 +- include/uapi/linux/signalfd.h | 4 ++-- kernel/signal.c | 21 +++++++++++++-------- .../testing/selftests/perf_events/sigtrap_threads.c | 14 +++++++------- 9 files changed, 41 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index a4b7ee1df211..8f215e79e70e 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -623,7 +623,8 @@ static inline void siginfo_build_tests(void) BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x12); /* _sigfault._perf */ - BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x14); /* _sigpoll */ BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x0c); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index a9fcabd8a5e5..06743ec054d2 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -141,8 +141,10 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14); - BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14); CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); diff --git a/fs/signalfd.c b/fs/signalfd.c index e87e59581653..373df2f12415 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -134,7 +134,8 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, break; case SIL_PERF_EVENT: new.ssi_addr = (long) kinfo->si_addr; - new.ssi_perf = kinfo->si_perf; + new.ssi_perf_type = kinfo->si_perf_type; + new.ssi_perf_data = kinfo->si_perf_data; break; case SIL_CHLD: new.ssi_pid = kinfo->si_pid; diff --git a/include/linux/compat.h b/include/linux/compat.h index 6af7bef15e94..a27fffaae121 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -236,7 +236,10 @@ typedef struct compat_siginfo { u32 _pkey; } _addr_pkey; /* used when si_code=TRAP_PERF */ - compat_ulong_t _perf; + struct { + compat_ulong_t _data; + u32 _type; + } _perf; }; } _sigfault; diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index e663bf117b46..5a3c221f4c9d 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -91,7 +91,10 @@ union __sifields { __u32 _pkey; } _addr_pkey; /* used when si_code=TRAP_PERF */ - unsigned long _perf; + struct { + unsigned long _data; + __u32 _type; + } _perf; }; } _sigfault; @@ -154,7 +157,8 @@ typedef struct siginfo { #define si_lower _sifields._sigfault._addr_bnd._lower #define si_upper _sifields._sigfault._addr_bnd._upper #define si_pkey _sifields._sigfault._addr_pkey._pkey -#define si_perf _sifields._sigfault._perf +#define si_perf_data _sifields._sigfault._perf._data +#define si_perf_type _sifields._sigfault._perf._type #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #define si_call_addr _sifields._sigsys._call_addr diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index e54e639248c8..7b14753b3d38 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -464,7 +464,7 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via - * siginfo_t::si_perf, e.g. to permit user to identify the event. + * siginfo_t::si_perf_data, e.g. to permit user to identify the event. */ __u64 sig_data; }; diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h index 7e333042c7e3..e78dddf433fc 100644 --- a/include/uapi/linux/signalfd.h +++ b/include/uapi/linux/signalfd.h @@ -39,8 +39,8 @@ struct signalfd_siginfo { __s32 ssi_syscall; __u64 ssi_call_addr; __u32 ssi_arch; - __u32 __pad3; - __u64 ssi_perf; + __u32 ssi_perf_type; + __u64 ssi_perf_data; /* * Pad strcture to 128 bytes. Remember to update the diff --git a/kernel/signal.c b/kernel/signal.c index 3a18d13c39b2..dca53515ae3f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1768,11 +1768,13 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data) struct kernel_siginfo info; clear_siginfo(&info); - info.si_signo = SIGTRAP; - info.si_errno = type; - info.si_code = TRAP_PERF; - info.si_addr = addr; - info.si_perf = sig_data; + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_PERF; + info.si_addr = addr; + info.si_perf_data = sig_data; + info.si_perf_type = type; + return force_sig_info(&info); } @@ -3356,7 +3358,8 @@ void copy_siginfo_to_external32(struct compat_siginfo *to, break; case SIL_PERF_EVENT: to->si_addr = ptr_to_compat(from->si_addr); - to->si_perf = from->si_perf; + to->si_perf_data = from->si_perf_data; + to->si_perf_type = from->si_perf_type; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -3432,7 +3435,8 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, break; case SIL_PERF_EVENT: to->si_addr = compat_ptr(from->si_addr); - to->si_perf = from->si_perf; + to->si_perf_data = from->si_perf_data; + to->si_perf_type = from->si_perf_type; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -4615,7 +4619,8 @@ static inline void siginfo_buildtime_checks(void) CHECK_OFFSET(si_lower); CHECK_OFFSET(si_upper); CHECK_OFFSET(si_pkey); - CHECK_OFFSET(si_perf); + CHECK_OFFSET(si_perf_data); + CHECK_OFFSET(si_perf_type); /* sigpoll */ CHECK_OFFSET(si_band); diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c index 78ddf5e11625..8e83cf91513a 100644 --- a/tools/testing/selftests/perf_events/sigtrap_threads.c +++ b/tools/testing/selftests/perf_events/sigtrap_threads.c @@ -43,7 +43,7 @@ static struct { siginfo_t first_siginfo; /* First observed siginfo_t. */ } ctx; -/* Unique value to check si_perf is correctly set from perf_event_attr::sig_data. */ +/* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */ #define TEST_SIG_DATA(addr) (~(unsigned long)(addr)) static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr) @@ -164,8 +164,8 @@ TEST_F(sigtrap_threads, enable_event) EXPECT_EQ(ctx.signal_count, NUM_THREADS); EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); - EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -183,8 +183,8 @@ TEST_F(sigtrap_threads, modify_and_enable_event) EXPECT_EQ(ctx.signal_count, NUM_THREADS); EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); - EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -203,8 +203,8 @@ TEST_F(sigtrap_threads, signal_stress) EXPECT_EQ(ctx.signal_count, NUM_THREADS * ctx.iterate_on); EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); - EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); } TEST_HARNESS_MAIN -- cgit From 3410fbcd47dc6479af4309febf760ccaa5efb472 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 12 May 2021 13:52:27 +0300 Subject: {net, RDMA}/mlx5: Fix override of log_max_qp by other device mlx5_core_dev holds pointer to static profile, hence when the log_max_qp of the profile is override by some device, then it effect all other mlx5 devices that share the same profile. Fix it by having a profile instance for every mlx5 device. Fixes: 883371c453b9 ("net/mlx5: Check FW limitations on log_max_qp before setting it") Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/mr.c | 4 +-- drivers/net/ethernet/mellanox/mlx5/core/main.c | 11 +++---- include/linux/mlx5/driver.h | 44 +++++++++++++------------- 3 files changed, 29 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 4388afeff251..9662cd39c7ff 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -743,10 +743,10 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) ent->xlt = (1 << ent->order) * sizeof(struct mlx5_mtt) / MLX5_IB_UMR_OCTOWORD; ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT; - if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) && + if ((dev->mdev->profile.mask & MLX5_PROF_MASK_MR_CACHE) && !dev->is_rep && mlx5_core_is_pf(dev->mdev) && mlx5_ib_can_load_pas_with_umr(dev, 0)) - ent->limit = dev->mdev->profile->mr_cache[i].limit; + ent->limit = dev->mdev->profile.mr_cache[i].limit; else ent->limit = 0; spin_lock_irq(&ent->lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c114365eb126..a1d67bd7fb43 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -503,7 +503,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) { - struct mlx5_profile *prof = dev->profile; + struct mlx5_profile *prof = &dev->profile; void *set_hca_cap; int err; @@ -524,11 +524,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) to_fw_pkey_sz(dev, 128)); /* Check log_max_qp from HCA caps to set in current profile */ - if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) { + if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) { mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n", - profile[prof_sel].log_max_qp, + prof->log_max_qp, MLX5_CAP_GEN_MAX(dev, log_max_qp)); - profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); + prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); } if (prof->mask & MLX5_PROF_MASK_QP_SIZE) MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp, @@ -1381,8 +1381,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) struct mlx5_priv *priv = &dev->priv; int err; - dev->profile = &profile[profile_idx]; - + memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile)); INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); mutex_init(&dev->intf_state_mutex); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8e8d7e90616..020a8f7fdbdd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -703,6 +703,27 @@ struct mlx5_hv_vhca; #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) +enum { + MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, + MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, +}; + +enum { + MR_CACHE_LAST_STD_ENTRY = 20, + MLX5_IMR_MTT_CACHE_ENTRY, + MLX5_IMR_KSM_CACHE_ENTRY, + MAX_MR_CACHE_ENTRIES +}; + +struct mlx5_profile { + u64 mask; + u8 log_max_qp; + struct { + int size; + int limit; + } mr_cache[MAX_MR_CACHE_ENTRIES]; +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -731,7 +752,7 @@ struct mlx5_core_dev { struct mutex intf_state_mutex; unsigned long intf_state; struct mlx5_priv priv; - struct mlx5_profile *profile; + struct mlx5_profile profile; u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_dm *dm; @@ -1083,18 +1104,6 @@ static inline u8 mlx5_mkey_variant(u32 mkey) return mkey & 0xff; } -enum { - MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, - MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, -}; - -enum { - MR_CACHE_LAST_STD_ENTRY = 20, - MLX5_IMR_MTT_CACHE_ENTRY, - MLX5_IMR_KSM_CACHE_ENTRY, - MAX_MR_CACHE_ENTRIES -}; - /* Async-atomic event notifier used by mlx5 core to forward FW * evetns recived from event queue to mlx5 consumers. * Optimise event queue dipatching. @@ -1148,15 +1157,6 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, struct ib_device *device, struct rdma_netdev_alloc_params *params); -struct mlx5_profile { - u64 mask; - u8 log_max_qp; - struct { - int size; - int limit; - } mr_cache[MAX_MR_CACHE_ENTRIES]; -}; - enum { MLX5_PCI_DEV_IS_VF = 1 << 0, }; -- cgit From 7c9f131f366ab414691907fa0407124ea2b2f3bc Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 22 Apr 2021 15:48:10 +0300 Subject: {net,vdpa}/mlx5: Configure interface MAC into mpfs L2 table net/mlx5: Expose MPFS configuration API MPFS is the multi physical function switch that bridges traffic between the physical port and any physical functions associated with it. The driver is required to add or remove MAC entries to properly forward incoming traffic to the correct physical function. We export the API to control MPFS so that other drivers, such as mlx5_vdpa are able to add MAC addresses of their network interfaces. The MAC address of the vdpa interface must be configured into the MPFS L2 address. Failing to do so could cause, in some NIC configurations, failure to forward packets to the vdpa network device instance. Fix this by adding calls to update the MPFS table. CC: CC: CC: Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices") Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c | 3 +++ drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h | 5 +---- drivers/vdpa/mlx5/net/mlx5_vnet.c | 19 ++++++++++++++++++- include/linux/mlx5/mpfs.h | 18 ++++++++++++++++++ 6 files changed, 42 insertions(+), 5 deletions(-) create mode 100644 include/linux/mlx5/mpfs.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 0d571a0c76d9..0b75fab41ae8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -35,6 +35,7 @@ #include #include #include +#include #include "en.h" #include "en_rep.h" #include "lib/mpfs.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 570f2280823c..b88705a3a1a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -35,6 +35,7 @@ #include #include #include +#include #include "esw/acl/lgcy.h" #include "esw/legacy.h" #include "mlx5_core.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index fd8449ff9e17..839a01da110f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include "mlx5_core.h" #include "lib/mpfs.h" @@ -175,6 +176,7 @@ out: mutex_unlock(&mpfs->lock); return err; } +EXPORT_SYMBOL(mlx5_mpfs_add_mac); int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { @@ -206,3 +208,4 @@ unlock: mutex_unlock(&mpfs->lock); return err; } +EXPORT_SYMBOL(mlx5_mpfs_del_mac); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h index 4a7b2c3203a7..4a293542a7aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h @@ -84,12 +84,9 @@ struct l2addr_node { #ifdef CONFIG_MLX5_MPFS int mlx5_mpfs_init(struct mlx5_core_dev *dev); void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev); -int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); -int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); #else /* #ifndef CONFIG_MLX5_MPFS */ static inline int mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; } static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {} -static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } -static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } #endif + #endif diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 189e4385df40..dda5dc6f7737 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "mlx5_vdpa.h" MODULE_AUTHOR("Eli Cohen "); @@ -1859,11 +1860,16 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb static void mlx5_vdpa_free(struct vdpa_device *vdev) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_core_dev *pfmdev; struct mlx5_vdpa_net *ndev; ndev = to_mlx5_vdpa_ndev(mvdev); free_resources(ndev); + if (!is_zero_ether_addr(ndev->config.mac)) { + pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev)); + mlx5_mpfs_del_mac(pfmdev, ndev->config.mac); + } mlx5_vdpa_free_resources(&ndev->mvdev); mutex_destroy(&ndev->reslock); } @@ -1990,6 +1996,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) { struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev); struct virtio_net_config *config; + struct mlx5_core_dev *pfmdev; struct mlx5_vdpa_dev *mvdev; struct mlx5_vdpa_net *ndev; struct mlx5_core_dev *mdev; @@ -2023,10 +2030,17 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) if (err) goto err_mtu; + if (!is_zero_ether_addr(config->mac)) { + pfmdev = pci_get_drvdata(pci_physfn(mdev->pdev)); + err = mlx5_mpfs_add_mac(pfmdev, config->mac); + if (err) + goto err_mtu; + } + mvdev->vdev.dma_dev = mdev->device; err = mlx5_vdpa_alloc_resources(&ndev->mvdev); if (err) - goto err_mtu; + goto err_mpfs; err = alloc_resources(ndev); if (err) @@ -2044,6 +2058,9 @@ err_reg: free_resources(ndev); err_res: mlx5_vdpa_free_resources(&ndev->mvdev); +err_mpfs: + if (!is_zero_ether_addr(config->mac)) + mlx5_mpfs_del_mac(pfmdev, config->mac); err_mtu: mutex_destroy(&ndev->reslock); put_device(&mvdev->vdev.dev); diff --git a/include/linux/mlx5/mpfs.h b/include/linux/mlx5/mpfs.h new file mode 100644 index 000000000000..bf700c8d5516 --- /dev/null +++ b/include/linux/mlx5/mpfs.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + * Copyright (c) 2021 Mellanox Technologies Ltd. + */ + +#ifndef _MLX5_MPFS_ +#define _MLX5_MPFS_ + +struct mlx5_core_dev; + +#ifdef CONFIG_MLX5_MPFS +int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); +int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); +#else /* #ifndef CONFIG_MLX5_MPFS */ +static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +#endif + +#endif -- cgit From ba6e1d8422bd476ad79da409639a773c02f0cbad Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 May 2021 22:04:36 +0200 Subject: platform/surface: aggregator: avoid clang -Wconstant-conversion warning Clang complains about the assignment of SSAM_ANY_IID to ssam_device_uid->instance: drivers/platform/surface/surface_aggregator_registry.c:478:25: error: implicit conversion from 'int' to '__u8' (aka 'unsigned char') changes value from 65535 to 255 [-Werror,-Wconstant-conversion] { SSAM_VDEV(HUB, 0x02, SSAM_ANY_IID, 0x00) }, ~ ^~~~~~~~~~~~ include/linux/surface_aggregator/device.h:71:23: note: expanded from macro 'SSAM_ANY_IID' #define SSAM_ANY_IID 0xffff ^~~~~~ include/linux/surface_aggregator/device.h:126:63: note: expanded from macro 'SSAM_VDEV' SSAM_DEVICE(SSAM_DOMAIN_VIRTUAL, SSAM_VIRTUAL_TC_##cat, tid, iid, fun) ^~~ include/linux/surface_aggregator/device.h:102:41: note: expanded from macro 'SSAM_DEVICE' .instance = ((iid) != SSAM_ANY_IID) ? (iid) : 0, \ ^~~ The assignment doesn't actually happen, but clang checks the type limits before checking whether this assignment is reached. Replace the ?: operator with a __builtin_choose_expr() invocation that avoids the warning for the untaken part. Fixes: eb0e90a82098 ("platform/surface: aggregator: Add dedicated bus and device type") Cc: platform-driver-x86@vger.kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Nathan Chancellor Reviewed-by: Maximilian Luz Link: https://lore.kernel.org/r/20210514200453.1542978-1-arnd@kernel.org Signed-off-by: Hans de Goede --- include/linux/surface_aggregator/device.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index 4441ad667c3f..6ff9c58b3e17 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -98,9 +98,9 @@ struct ssam_device_uid { | (((fun) != SSAM_ANY_FUN) ? SSAM_MATCH_FUNCTION : 0), \ .domain = d, \ .category = cat, \ - .target = ((tid) != SSAM_ANY_TID) ? (tid) : 0, \ - .instance = ((iid) != SSAM_ANY_IID) ? (iid) : 0, \ - .function = ((fun) != SSAM_ANY_FUN) ? (fun) : 0 \ + .target = __builtin_choose_expr((tid) != SSAM_ANY_TID, (tid), 0), \ + .instance = __builtin_choose_expr((iid) != SSAM_ANY_IID, (iid), 0), \ + .function = __builtin_choose_expr((fun) != SSAM_ANY_FUN, (fun), 0) /** * SSAM_VDEV() - Initialize a &struct ssam_device_id as virtual device with -- cgit From 6c60ff048ca1e0739f39aa25996543c6e662a46c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 14 May 2021 15:18:41 +0200 Subject: block: prevent block device lookups at the beginning of del_gendisk As an artifact of how gendisk lookup used to work in earlier kernels, GENHD_FL_UP is only cleared very late in del_gendisk, and a global lock is used to prevent opens from succeeding while del_gendisk is tearing down the gendisk. Switch to clearing the flag early and under bd_mutex so that callers can use bd_mutex to stabilize the flag, which removes the need for the global mutex. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20210514131842.1600568-2-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 11 +---------- fs/block_dev.c | 15 +++++---------- include/linux/genhd.h | 2 -- 3 files changed, 6 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 39ca97b0edc6..9f8cb7beaad1 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -29,8 +29,6 @@ static struct kobject *block_depr; -DECLARE_RWSEM(bdev_lookup_sem); - /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) static DEFINE_IDA(ext_devt_ida); @@ -609,13 +607,8 @@ void del_gendisk(struct gendisk *disk) blk_integrity_del(disk); disk_del_events(disk); - /* - * Block lookups of the disk until all bdevs are unhashed and the - * disk is marked as dead (GENHD_FL_UP cleared). - */ - down_write(&bdev_lookup_sem); - mutex_lock(&disk->part0->bd_mutex); + disk->flags &= ~GENHD_FL_UP; blk_drop_partitions(disk); mutex_unlock(&disk->part0->bd_mutex); @@ -629,8 +622,6 @@ void del_gendisk(struct gendisk *disk) remove_inode_hash(disk->part0->bd_inode); set_capacity(disk, 0); - disk->flags &= ~GENHD_FL_UP; - up_write(&bdev_lookup_sem); if (!(disk->flags & GENHD_FL_HIDDEN)) { sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); diff --git a/fs/block_dev.c b/fs/block_dev.c index eb265d72fce8..580bae995b87 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1298,6 +1298,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) struct gendisk *disk = bdev->bd_disk; int ret = 0; + if (!(disk->flags & GENHD_FL_UP)) + return -ENXIO; + if (!bdev->bd_openers) { if (!bdev_is_partition(bdev)) { ret = 0; @@ -1332,8 +1335,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) whole->bd_part_count++; mutex_unlock(&whole->bd_mutex); - if (!(disk->flags & GENHD_FL_UP) || - !bdev_nr_sectors(bdev)) { + if (!bdev_nr_sectors(bdev)) { __blkdev_put(whole, mode, 1); bdput(whole); return -ENXIO; @@ -1364,16 +1366,12 @@ struct block_device *blkdev_get_no_open(dev_t dev) struct block_device *bdev; struct gendisk *disk; - down_read(&bdev_lookup_sem); bdev = bdget(dev); if (!bdev) { - up_read(&bdev_lookup_sem); blk_request_module(dev); - down_read(&bdev_lookup_sem); - bdev = bdget(dev); if (!bdev) - goto unlock; + return NULL; } disk = bdev->bd_disk; @@ -1383,14 +1381,11 @@ struct block_device *blkdev_get_no_open(dev_t dev) goto put_disk; if (!try_module_get(bdev->bd_disk->fops->owner)) goto put_disk; - up_read(&bdev_lookup_sem); return bdev; put_disk: put_disk(disk); bdput: bdput(bdev); -unlock: - up_read(&bdev_lookup_sem); return NULL; } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7e9660ea967d..6fc26f7bdf71 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -306,8 +306,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ -extern struct rw_semaphore bdev_lookup_sem; - dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK -- cgit From 80dd33cf72d1ab4f0af303f1fa242c6d6c8d328f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 14 May 2021 14:10:15 +0200 Subject: drivers: base: Fix device link removal When device_link_free() drops references to the supplier and consumer devices of the device link going away and the reference being dropped turns out to be the last one for any of those device objects, its ->release callback will be invoked and it may sleep which goes against the SRCU callback execution requirements. To address this issue, make the device link removal code carry out the device_link_free() actions preceded by SRCU synchronization from a separate work item (the "long" workqueue is used for that, because it does not matter when the device link memory is released and it may take time to get to that point) instead of using SRCU callbacks. While at it, make the code work analogously when SRCU is not enabled to reduce the differences between the SRCU and non-SRCU cases. Fixes: 843e600b8a2b ("driver core: Fix sleeping in invalid context during device link deletion") Cc: stable Reported-by: chenxiang (M) Tested-by: chenxiang (M) Reviewed-by: Saravana Kannan Signed-off-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/5722787.lOV4Wx5bFT@kreacher Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 37 +++++++++++++++++++++++-------------- include/linux/device.h | 6 ++---- 2 files changed, 25 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 628e33939aca..61c19641e1d0 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -194,6 +194,11 @@ int device_links_read_lock_held(void) { return srcu_read_lock_held(&device_links_srcu); } + +static void device_link_synchronize_removal(void) +{ + synchronize_srcu(&device_links_srcu); +} #else /* !CONFIG_SRCU */ static DECLARE_RWSEM(device_links_lock); @@ -224,6 +229,10 @@ int device_links_read_lock_held(void) return lockdep_is_held(&device_links_lock); } #endif + +static inline void device_link_synchronize_removal(void) +{ +} #endif /* !CONFIG_SRCU */ static bool device_is_ancestor(struct device *dev, struct device *target) @@ -445,8 +454,13 @@ static struct attribute *devlink_attrs[] = { }; ATTRIBUTE_GROUPS(devlink); -static void device_link_free(struct device_link *link) +static void device_link_release_fn(struct work_struct *work) { + struct device_link *link = container_of(work, struct device_link, rm_work); + + /* Ensure that all references to the link object have been dropped. */ + device_link_synchronize_removal(); + while (refcount_dec_not_one(&link->rpm_active)) pm_runtime_put(link->supplier); @@ -455,24 +469,19 @@ static void device_link_free(struct device_link *link) kfree(link); } -#ifdef CONFIG_SRCU -static void __device_link_free_srcu(struct rcu_head *rhead) -{ - device_link_free(container_of(rhead, struct device_link, rcu_head)); -} - static void devlink_dev_release(struct device *dev) { struct device_link *link = to_devlink(dev); - call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu); -} -#else -static void devlink_dev_release(struct device *dev) -{ - device_link_free(to_devlink(dev)); + INIT_WORK(&link->rm_work, device_link_release_fn); + /* + * It may take a while to complete this work because of the SRCU + * synchronization in device_link_release_fn() and if the consumer or + * supplier devices get deleted when it runs, so put it into the "long" + * workqueue. + */ + queue_work(system_long_wq, &link->rm_work); } -#endif static struct class devlink_class = { .name = "devlink", diff --git a/include/linux/device.h b/include/linux/device.h index 38a2071cf776..f1a00040fa53 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -570,7 +570,7 @@ struct device { * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. - * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. + * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { @@ -583,9 +583,7 @@ struct device_link { u32 flags; refcount_t rpm_active; struct kref kref; -#ifdef CONFIG_SRCU - struct rcu_head rcu_head; -#endif + struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; -- cgit From f747e6667ebb2ffb8133486c9cd19800d72b0d98 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Sat, 22 May 2021 17:42:02 -0700 Subject: linux/bits.h: fix compilation error with GENMASK GENMASK() has an input check which uses __builtin_choose_expr() to enable a compile time sanity check of its inputs if they are known at compile time. However, it turns out that __builtin_constant_p() does not always return a compile time constant [0]. It was thought this problem was fixed with gcc 4.9 [1], but apparently this is not the case [2]. Switch to use __is_constexpr() instead which always returns a compile time constant, regardless of its inputs. Link: https://lore.kernel.org/lkml/42b4342b-aefc-a16a-0d43-9f9c0d63ba7a@rasmusvillemoes.dk [0] Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=19449 [1] Link: https://lore.kernel.org/lkml/1ac7bbc2-45d9-26ed-0b33-bf382b8d858b@I-love.SAKURA.ne.jp [2] Link: https://lkml.kernel.org/r/20210511203716.117010-1-rikard.falkeborn@gmail.com Signed-off-by: Rikard Falkeborn Reported-by: Tetsuo Handa Acked-by: Arnd Bergmann Reviewed-by: Andy Shevchenko Cc: Ard Biesheuvel Cc: Yury Norov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bits.h | 2 +- include/linux/const.h | 8 ++++++++ include/linux/minmax.h | 10 ++-------- tools/include/linux/bits.h | 2 +- tools/include/linux/const.h | 8 ++++++++ 5 files changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bits.h b/include/linux/bits.h index 7f475d59a097..87d112650dfb 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -22,7 +22,7 @@ #include #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __builtin_constant_p((l) > (h)), (l) > (h), 0))) + __is_constexpr((l) > (h)), (l) > (h), 0))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, diff --git a/include/linux/const.h b/include/linux/const.h index 81b8aae5a855..435ddd72d2c4 100644 --- a/include/linux/const.h +++ b/include/linux/const.h @@ -3,4 +3,12 @@ #include +/* + * This returns a constant expression while determining if an argument is + * a constant expression, most importantly without evaluating the argument. + * Glory to Martin Uecker + */ +#define __is_constexpr(x) \ + (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) + #endif /* _LINUX_CONST_H */ diff --git a/include/linux/minmax.h b/include/linux/minmax.h index c0f57b0c64d9..5433c08fcc68 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -2,6 +2,8 @@ #ifndef _LINUX_MINMAX_H #define _LINUX_MINMAX_H +#include + /* * min()/max()/clamp() macros must accomplish three things: * @@ -17,14 +19,6 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* - * This returns a constant expression while determining if an argument is - * a constant expression, most importantly without evaluating the argument. - * Glory to Martin Uecker - */ -#define __is_constexpr(x) \ - (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) - #define __no_side_effects(x, y) \ (__is_constexpr(x) && __is_constexpr(y)) diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 7f475d59a097..87d112650dfb 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -22,7 +22,7 @@ #include #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __builtin_constant_p((l) > (h)), (l) > (h), 0))) + __is_constexpr((l) > (h)), (l) > (h), 0))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h index 81b8aae5a855..435ddd72d2c4 100644 --- a/tools/include/linux/const.h +++ b/tools/include/linux/const.h @@ -3,4 +3,12 @@ #include +/* + * This returns a constant expression while determining if an argument is + * a constant expression, most importantly without evaluating the argument. + * Glory to Martin Uecker + */ +#define __is_constexpr(x) \ + (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) + #endif /* _LINUX_CONST_H */ -- cgit From 08b2b6fdf6b26032f025084ce2893924a0cdb4a2 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Mon, 24 May 2021 16:29:43 +0800 Subject: cgroup: fix spelling mistakes Fix some spelling mistakes in comments: hierarhcy ==> hierarchy automtically ==> automatically overriden ==> overridden In absense of .. or ==> In absence of .. and assocaited ==> associated taget ==> target initate ==> initiate succeded ==> succeeded curremt ==> current udpated ==> updated Signed-off-by: Zhen Lei Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 6 +++--- include/linux/cgroup.h | 2 +- kernel/cgroup/cgroup-v1.c | 2 +- kernel/cgroup/cgroup.c | 8 ++++---- kernel/cgroup/cpuset.c | 2 +- kernel/cgroup/rdma.c | 2 +- kernel/cgroup/rstat.c | 2 +- 7 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 559ee05f86b2..fb8f6d2cd104 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -232,7 +232,7 @@ struct css_set { struct list_head task_iters; /* - * On the default hierarhcy, ->subsys[ssid] may point to a css + * On the default hierarchy, ->subsys[ssid] may point to a css * attached to an ancestor instead of the cgroup this css_set is * associated with. The following node is anchored at * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to @@ -668,7 +668,7 @@ struct cgroup_subsys { */ bool threaded:1; - /* the following two fields are initialized automtically during boot */ + /* the following two fields are initialized automatically during boot */ int id; const char *name; @@ -757,7 +757,7 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. * On boot, sock_cgroup_data records the cgroup that the sock was created * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overriden to carry prioidx and/or + * net_cls starts being used, the area is overridden to carry prioidx and/or * classid. The two modes are distinguished by whether the lowest bit is * set. Clear bit indicates cgroup pointer while set bit prioidx and * classid. diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4f2f79de083e..6bc9c76680b2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -32,7 +32,7 @@ struct kernel_clone_args; #ifdef CONFIG_CGROUPS /* - * All weight knobs on the default hierarhcy should use the following min, + * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 391aa570369b..8190b6bfc978 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1001,7 +1001,7 @@ static int check_cgroupfs_options(struct fs_context *fc) ctx->subsys_mask &= enabled; /* - * In absense of 'none', 'name=' or subsystem name options, + * In absence of 'none', 'name=' and subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e7a9a2998245..21ecc6ee6a6d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -468,7 +468,7 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, * @cgrp: the cgroup of interest * @ss: the subsystem of interest * - * Find and get @cgrp's css assocaited with @ss. If the css doesn't exist + * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, @@ -1633,7 +1633,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) /** * css_clear_dir - remove subsys files in a cgroup directory - * @css: taget css + * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { @@ -5350,7 +5350,7 @@ out_unlock: /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to - * initate destruction and put the css ref from kill_css(). + * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { @@ -6052,7 +6052,7 @@ out_revert: * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* - * cgroup_can_fork() succeded and cleans up references we took to + * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a945504c0ae7..adb5190c4429 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3376,7 +3376,7 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) } /** - * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed + * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c index ae042c347c64..3135406608c7 100644 --- a/kernel/cgroup/rdma.c +++ b/kernel/cgroup/rdma.c @@ -244,7 +244,7 @@ EXPORT_SYMBOL(rdmacg_uncharge); * This function follows charging resource in hierarchical way. * It will fail if the charge would cause the new value to exceed the * hierarchical limit. - * Returns 0 if the charge succeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. + * Returns 0 if the charge succeeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. * Returns pointer to rdmacg for this resource when charging is successful. * * Charger needs to account resources on two criteria. diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 3a3fd2993a65..cee265cb535c 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -75,7 +75,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) * @root: root of the tree to traversal * @cpu: target cpu * - * Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts + * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. -- cgit From 1cb61759d40716643281b8e0f8c7afebc8699249 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 21 May 2021 09:26:10 +0200 Subject: init: verify that function is initcall_t at compile-time In the spirit of making it hard to misuse an interface, add a compile-time assertion in the CONFIG_HAVE_ARCH_PREL32_RELOCATIONS case to verify the initcall function matches initcall_t, because the inline asm bypasses any type-checking the compiler would otherwise do. This will help developers catch incorrect API use in all configurations. A recent example of this is: https://lkml.kernel.org/r/20210514140015.2944744-1-arnd@kernel.org Signed-off-by: Marco Elver Reviewed-by: Miguel Ojeda Reviewed-by: Nathan Chancellor Tested-by: Nathan Chancellor Reviewed-by: Sami Tolvanen Tested-by: Paul E. McKenney Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210521072610.2880286-1-elver@google.com --- include/linux/init.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 045ad1650ed1..d82b4b2e1d25 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -242,7 +242,8 @@ extern bool initcall_debug; asm(".section \"" __sec "\", \"a\" \n" \ __stringify(__name) ": \n" \ ".long " __stringify(__stub) " - . \n" \ - ".previous \n"); + ".previous \n"); \ + static_assert(__same_type(initcall_t, &fn)); #else #define ____define_initcall(fn, __unused, __name, __sec) \ static initcall_t __name __used \ -- cgit From e86be3a04bc4aeaf12f93af35f08f8d4385bcd98 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 25 May 2021 18:43:38 -0400 Subject: SUNRPC: More fixes for backlog congestion Ensure that we fix the XPRT_CONGESTED starvation issue for RDMA as well as socket based transports. Ensure we always initialise the request after waking up from the backlog list. Fixes: e877a88d1f06 ("SUNRPC in case of backlog, hand free slots directly to waiting task") Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ net/sunrpc/xprt.c | 58 ++++++++++++++++++++--------------------- net/sunrpc/xprtrdma/transport.c | 12 ++++----- net/sunrpc/xprtrdma/verbs.c | 18 ++++++++++--- net/sunrpc/xprtrdma/xprt_rdma.h | 1 + 5 files changed, 52 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d81fe8b364d0..61b622e334ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -368,6 +368,8 @@ struct rpc_xprt * xprt_alloc(struct net *net, size_t size, unsigned int num_prealloc, unsigned int max_req); void xprt_free(struct rpc_xprt *); +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task); +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req); static inline int xprt_enable_swap(struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 5b3981fd3783..3509a7f139b9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1607,11 +1607,18 @@ xprt_transmit(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } -static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) +static void xprt_complete_request_init(struct rpc_task *task) +{ + if (task->tk_rqstp) + xprt_request_init(task); +} + +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) { set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); + rpc_sleep_on(&xprt->backlog, task, xprt_complete_request_init); } +EXPORT_SYMBOL_GPL(xprt_add_backlog); static bool __xprt_set_rq(struct rpc_task *task, void *data) { @@ -1619,14 +1626,13 @@ static bool __xprt_set_rq(struct rpc_task *task, void *data) if (task->tk_rqstp == NULL) { memset(req, 0, sizeof(*req)); /* mark unused */ - task->tk_status = -EAGAIN; task->tk_rqstp = req; return true; } return false; } -static bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) { if (rpc_wake_up_first(&xprt->backlog, __xprt_set_rq, req) == NULL) { clear_bit(XPRT_CONGESTED, &xprt->state); @@ -1634,6 +1640,7 @@ static bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) } return true; } +EXPORT_SYMBOL_GPL(xprt_wake_up_backlog); static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task) { @@ -1643,7 +1650,7 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task goto out; spin_lock(&xprt->reserve_lock); if (test_bit(XPRT_CONGESTED, &xprt->state)) { - rpc_sleep_on(&xprt->backlog, task, NULL); + xprt_add_backlog(xprt, task); ret = true; } spin_unlock(&xprt->reserve_lock); @@ -1812,10 +1819,6 @@ xprt_request_init(struct rpc_task *task) struct rpc_xprt *xprt = task->tk_xprt; struct rpc_rqst *req = task->tk_rqstp; - if (req->rq_task) - /* Already initialized */ - return; - req->rq_task = task; req->rq_xprt = xprt; req->rq_buffer = NULL; @@ -1876,10 +1879,8 @@ void xprt_retry_reserve(struct rpc_task *task) struct rpc_xprt *xprt = task->tk_xprt; task->tk_status = 0; - if (task->tk_rqstp != NULL) { - xprt_request_init(task); + if (task->tk_rqstp != NULL) return; - } task->tk_status = -EAGAIN; xprt_do_reserve(xprt, task); @@ -1904,24 +1905,21 @@ void xprt_release(struct rpc_task *task) } xprt = req->rq_xprt; - if (xprt) { - xprt_request_dequeue_xprt(task); - spin_lock(&xprt->transport_lock); - xprt->ops->release_xprt(xprt, task); - if (xprt->ops->release_request) - xprt->ops->release_request(task); - xprt_schedule_autodisconnect(xprt); - spin_unlock(&xprt->transport_lock); - if (req->rq_buffer) - xprt->ops->buf_free(task); - xdr_free_bvec(&req->rq_rcv_buf); - xdr_free_bvec(&req->rq_snd_buf); - if (req->rq_cred != NULL) - put_rpccred(req->rq_cred); - if (req->rq_release_snd_buf) - req->rq_release_snd_buf(req); - } else - xprt = task->tk_xprt; + xprt_request_dequeue_xprt(task); + spin_lock(&xprt->transport_lock); + xprt->ops->release_xprt(xprt, task); + if (xprt->ops->release_request) + xprt->ops->release_request(task); + xprt_schedule_autodisconnect(xprt); + spin_unlock(&xprt->transport_lock); + if (req->rq_buffer) + xprt->ops->buf_free(task); + xdr_free_bvec(&req->rq_rcv_buf); + xdr_free_bvec(&req->rq_snd_buf); + if (req->rq_cred != NULL) + put_rpccred(req->rq_cred); + if (req->rq_release_snd_buf) + req->rq_release_snd_buf(req); task->tk_rqstp = NULL; if (likely(!bc_prealloc(req))) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 09953597d055..19a49d26b1e4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -520,9 +520,8 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) return; out_sleep: - set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); task->tk_status = -EAGAIN; + xprt_add_backlog(xprt, task); } /** @@ -537,10 +536,11 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst) struct rpcrdma_xprt *r_xprt = container_of(xprt, struct rpcrdma_xprt, rx_xprt); - memset(rqst, 0, sizeof(*rqst)); - rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); - if (unlikely(!rpc_wake_up_next(&xprt->backlog))) - clear_bit(XPRT_CONGESTED, &xprt->state); + rpcrdma_reply_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + if (!xprt_wake_up_backlog(xprt, rqst)) { + memset(rqst, 0, sizeof(*rqst)); + rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + } } static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt, diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 1e965a380896..649c23518ec0 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1200,6 +1200,20 @@ rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt) return mr; } +/** + * rpcrdma_reply_put - Put reply buffers back into pool + * @buffers: buffer pool + * @req: object to return + * + */ +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + if (req->rl_reply) { + rpcrdma_rep_put(buffers, req->rl_reply); + req->rl_reply = NULL; + } +} + /** * rpcrdma_buffer_get - Get a request buffer * @buffers: Buffer pool from which to obtain a buffer @@ -1228,9 +1242,7 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) */ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) { - if (req->rl_reply) - rpcrdma_rep_put(buffers, req->rl_reply); - req->rl_reply = NULL; + rpcrdma_reply_put(buffers, req); spin_lock(&buffers->rb_lock); list_add(&req->rl_list, &buffers->rb_send_bufs); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 436ad7312614..5d231d94e944 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -479,6 +479,7 @@ struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep); +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size, gfp_t flags); -- cgit From 62f3415db237b8d2aa9a804ff84ce2efa87df179 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 26 May 2021 11:46:17 -0700 Subject: net: phy: Document phydev::dev_flags bits allocation Document the phydev::dev_flags bit allocation to allow bits 15:0 to define PHY driver specific behavior, bits 23:16 to be reserved for now, and bits 31:24 to hold generic PHY driver flags. Signed-off-by: Florian Fainelli Reviewed-by: Russell King (Oracle) Link: https://lore.kernel.org/r/20210526184617.3105012-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 60d2b26026a2..852743f07e3e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -496,6 +496,11 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. + * Bits [15:0] are free to use by the PHY driver to communicate + * driver specific behavior. + * Bits [23:16] are currently reserved for future use. + * Bits [31:24] are reserved for defining generic + * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY -- cgit From 6bd5b743686243dae7351d5dcceeb7f171201bb4 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 18 May 2021 05:00:31 -0700 Subject: KVM: PPC: exit halt polling on need_resched() This is inspired by commit 262de4102c7bb8 (kvm: exit halt polling on need_resched() as well). Due to PPC implements an arch specific halt polling logic, we have to the need_resched() check there as well. This patch adds a helper function that can be shared between book3s and generic halt-polling loops. Reviewed-by: David Matlack Reviewed-by: Venkatesh Srinivas Cc: Ben Segall Cc: Venkatesh Srinivas Cc: Jim Mattson Cc: David Matlack Cc: Paul Mackerras Cc: Suraj Jitindar Singh Signed-off-by: Wanpeng Li Message-Id: <1621339235-11131-1-git-send-email-wanpengli@tencent.com> [Make the function inline. - Paolo] Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/book3s_hv.c | 2 +- include/linux/kvm_host.h | 6 ++++++ virt/kvm/kvm_main.c | 3 +-- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 28a80d240b76..7360350e66ff 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3936,7 +3936,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) break; } cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2f34487e21f2..5d4b96b36ec0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -265,6 +266,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) return !!map->hva; } +static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) +{ + return single_task_running() && !need_resched() && ktime_before(cur, stop); +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6b4feb92dc79..5f40725144f5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2973,8 +2973,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) goto out; } poll_end = cur = ktime_get(); - } while (single_task_running() && !need_resched() && - ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); } prepare_to_rcuwait(&vcpu->wait); -- cgit From 084071d5e9226add45a6031928bf10e6afc855fd Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 25 May 2021 10:41:17 -0300 Subject: KVM: rename KVM_REQ_PENDING_TIMER to KVM_REQ_UNBLOCK KVM_REQ_UNBLOCK will be used to exit a vcpu from its inner vcpu halt emulation loop. Rename KVM_REQ_PENDING_TIMER to KVM_REQ_UNBLOCK, switch PowerPC to arch specific request bit. Signed-off-by: Marcelo Tosatti Message-Id: <20210525134321.303768132@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/vcpu-requests.rst | 8 +++++--- arch/powerpc/include/asm/kvm_host.h | 1 + arch/x86/kvm/lapic.c | 2 +- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 2 ++ 6 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index 5feb3706a7ae..af1b37441e0a 100644 --- a/Documentation/virt/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst @@ -118,10 +118,12 @@ KVM_REQ_MMU_RELOAD necessary to inform each VCPU to completely refresh the tables. This request is used for that. -KVM_REQ_PENDING_TIMER +KVM_REQ_UNBLOCK - This request may be made from a timer handler run on the host on behalf - of a VCPU. It informs the VCPU thread to inject a timer interrupt. + This request informs the vCPU to exit kvm_vcpu_block. It is used for + example from timer handlers that run on the host on behalf of a vCPU, + or in order to update the interrupt routing and ensure that assigned + devices will wake up the vCPU. KVM_REQ_UNHALT diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1e83359f286b..7f2e90db2050 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -51,6 +51,7 @@ /* PPC-specific vcpu->requests bit members */ #define KVM_REQ_WATCHDOG KVM_ARCH_REQ(0) #define KVM_REQ_EPR_EXIT KVM_ARCH_REQ(1) +#define KVM_REQ_PENDING_TIMER KVM_ARCH_REQ(2) #include diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5d91f2367c31..8120e8614b92 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1669,7 +1669,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) } atomic_inc(&apic->lapic_timer.pending); - kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_make_request(KVM_REQ_UNBLOCK, vcpu); if (from_timer_fn) kvm_vcpu_kick(vcpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 98538b1cb453..fe464b66898f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9501,7 +9501,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (r <= 0) break; - kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5d4b96b36ec0..76102efbf079 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -147,7 +147,7 @@ static inline bool is_error_page(struct page *page) */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_PENDING_TIMER 2 +#define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 #define KVM_REQUEST_ARCH_BASE 8 diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5f40725144f5..37a2d500a148 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2929,6 +2929,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) goto out; if (signal_pending(current)) goto out; + if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) + goto out; ret = 0; out: -- cgit