From 5df9197edd731a44682444631d68c2384f381bf1 Mon Sep 17 00:00:00 2001 From: Ricardo B. Marliere Date: Tue, 6 Feb 2024 15:05:06 -0300 Subject: workqueue: make wq_subsys const Now that the driver core can properly handle constant struct bus_type, move the wq_subsys variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Suggested-by: Greg Kroah-Hartman Signed-off-by: "Ricardo B. Marliere" Cc: Tejun Heo Link: https://lore.kernel.org/r/20240206-bus_cleanup-workqueue-v1-1-72b10d282d58@marliere.net Signed-off-by: Greg Kroah-Hartman --- kernel/workqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 76e60faed892..f1e062acd091 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6157,7 +6157,7 @@ static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR_NULL, }; -static struct bus_type wq_subsys = { +static const struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; -- cgit v1.2.3 From d6cfd1770f20392d7009ae1fdb04733794514fa9 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Wed, 31 Jan 2024 15:49:33 +0100 Subject: membarrier: riscv: Add full memory barrier in switch_mm() The membarrier system call requires a full memory barrier after storing to rq->curr, before going back to user-space. The barrier is only needed when switching between processes: the barrier is implied by mmdrop() when switching from kernel to userspace, and it's not needed when switching from userspace to kernel. Rely on the feature/mechanism ARCH_HAS_MEMBARRIER_CALLBACKS and on the primitive membarrier_arch_switch_mm(), already adopted by the PowerPC architecture, to insert the required barrier. Fixes: fab957c11efe2f ("RISC-V: Atomic and Locking Code") Signed-off-by: Andrea Parri Reviewed-by: Mathieu Desnoyers Link: https://lore.kernel.org/r/20240131144936.29190-2-parri.andrea@gmail.com Signed-off-by: Palmer Dabbelt --- MAINTAINERS | 2 +- arch/riscv/Kconfig | 1 + arch/riscv/include/asm/membarrier.h | 31 +++++++++++++++++++++++++++++++ arch/riscv/mm/context.c | 2 ++ kernel/sched/core.c | 5 +++-- 5 files changed, 38 insertions(+), 3 deletions(-) create mode 100644 arch/riscv/include/asm/membarrier.h (limited to 'kernel') diff --git a/MAINTAINERS b/MAINTAINERS index 8d1052fa6a69..2450e88d3e2c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14039,7 +14039,7 @@ M: Mathieu Desnoyers M: "Paul E. McKenney" L: linux-kernel@vger.kernel.org S: Supported -F: arch/powerpc/include/asm/membarrier.h +F: arch/*/include/asm/membarrier.h F: include/uapi/linux/membarrier.h F: kernel/sched/membarrier.c diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index bffbd869a068..087abf9e51c6 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -27,6 +27,7 @@ config RISCV select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV + select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_MMIOWB select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API diff --git a/arch/riscv/include/asm/membarrier.h b/arch/riscv/include/asm/membarrier.h new file mode 100644 index 000000000000..6c016ebb5020 --- /dev/null +++ b/arch/riscv/include/asm/membarrier.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_RISCV_MEMBARRIER_H +#define _ASM_RISCV_MEMBARRIER_H + +static inline void membarrier_arch_switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ + /* + * Only need the full barrier when switching between processes. + * Barrier when switching from kernel to userspace is not + * required here, given that it is implied by mmdrop(). Barrier + * when switching from userspace to kernel is not needed after + * store to rq->curr. + */ + if (IS_ENABLED(CONFIG_SMP) && + likely(!(atomic_read(&next->membarrier_state) & + (MEMBARRIER_STATE_PRIVATE_EXPEDITED | + MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev)) + return; + + /* + * The membarrier system call requires a full memory barrier + * after storing to rq->curr, before going back to user-space. + * Matches a full barrier in the proximity of the membarrier + * system call entry. + */ + smp_mb(); +} + +#endif /* _ASM_RISCV_MEMBARRIER_H */ diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index 217fd4de6134..ba8eb3944687 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -323,6 +323,8 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, if (unlikely(prev == next)) return; + membarrier_arch_switch_mm(prev, next, task); + /* * Mark the current MM context as inactive, and the next as * active. This is at least used by the icache flushing diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9116bcc90346..c4ca8085885a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6709,8 +6709,9 @@ static void __sched notrace __schedule(unsigned int sched_mode) * * Here are the schemes providing that barrier on the * various architectures: - * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC. - * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC. + * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC, + * RISC-V. switch_mm() relies on membarrier_arch_switch_mm() + * on PowerPC and on RISC-V. * - finish_lock_switch() for weakly-ordered * architectures where spin_unlock is a full barrier, * - switch_to() for arm64 (weakly-ordered, spin_unlock -- cgit v1.2.3 From a14d11a0f5f4105e0df96811dfa81dc5f79fecba Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Wed, 31 Jan 2024 15:49:34 +0100 Subject: membarrier: Create Documentation/scheduler/membarrier.rst To gather the architecture requirements of the "private/global expedited" membarrier commands. The file will be expanded to integrate further information about the membarrier syscall (as needed/desired in the future). While at it, amend some related inline comments in the membarrier codebase. Suggested-by: Mathieu Desnoyers Signed-off-by: Andrea Parri Reviewed-by: Mathieu Desnoyers Link: https://lore.kernel.org/r/20240131144936.29190-3-parri.andrea@gmail.com Signed-off-by: Palmer Dabbelt --- Documentation/scheduler/index.rst | 1 + Documentation/scheduler/membarrier.rst | 39 ++++++++++++++++++++++++++++++++++ MAINTAINERS | 1 + kernel/sched/core.c | 7 +++++- kernel/sched/membarrier.c | 8 +++---- 5 files changed, 51 insertions(+), 5 deletions(-) create mode 100644 Documentation/scheduler/membarrier.rst (limited to 'kernel') diff --git a/Documentation/scheduler/index.rst b/Documentation/scheduler/index.rst index 3170747226f6..43bd8a145b7a 100644 --- a/Documentation/scheduler/index.rst +++ b/Documentation/scheduler/index.rst @@ -7,6 +7,7 @@ Scheduler completion + membarrier sched-arch sched-bwc sched-deadline diff --git a/Documentation/scheduler/membarrier.rst b/Documentation/scheduler/membarrier.rst new file mode 100644 index 000000000000..2387804b1c63 --- /dev/null +++ b/Documentation/scheduler/membarrier.rst @@ -0,0 +1,39 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================== +membarrier() System Call +======================== + +MEMBARRIER_CMD_{PRIVATE,GLOBAL}_EXPEDITED - Architecture requirements +===================================================================== + +Memory barriers before updating rq->curr +---------------------------------------- + +The commands MEMBARRIER_CMD_PRIVATE_EXPEDITED and MEMBARRIER_CMD_GLOBAL_EXPEDITED +require each architecture to have a full memory barrier after coming from +user-space, before updating rq->curr. This barrier is implied by the sequence +rq_lock(); smp_mb__after_spinlock() in __schedule(). The barrier matches a full +barrier in the proximity of the membarrier system call exit, cf. +membarrier_{private,global}_expedited(). + +Memory barriers after updating rq->curr +--------------------------------------- + +The commands MEMBARRIER_CMD_PRIVATE_EXPEDITED and MEMBARRIER_CMD_GLOBAL_EXPEDITED +require each architecture to have a full memory barrier after updating rq->curr, +before returning to user-space. The schemes providing this barrier on the various +architectures are as follows. + + - alpha, arc, arm, hexagon, mips rely on the full barrier implied by + spin_unlock() in finish_lock_switch(). + + - arm64 relies on the full barrier implied by switch_to(). + + - powerpc, riscv, s390, sparc, x86 rely on the full barrier implied by + switch_mm(), if mm is not NULL; they rely on the full barrier implied + by mmdrop(), otherwise. On powerpc and riscv, switch_mm() relies on + membarrier_arch_switch_mm(). + +The barrier matches a full barrier in the proximity of the membarrier system call +entry, cf. membarrier_{private,global}_expedited(). diff --git a/MAINTAINERS b/MAINTAINERS index 2450e88d3e2c..78c835cc69c9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14039,6 +14039,7 @@ M: Mathieu Desnoyers M: "Paul E. McKenney" L: linux-kernel@vger.kernel.org S: Supported +F: Documentation/scheduler/membarrier.rst F: arch/*/include/asm/membarrier.h F: include/uapi/linux/membarrier.h F: kernel/sched/membarrier.c diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c4ca8085885a..a972628e7756 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6638,7 +6638,9 @@ static void __sched notrace __schedule(unsigned int sched_mode) * if (signal_pending_state()) if (p->state & @state) * * Also, the membarrier system call requires a full memory barrier - * after coming from user-space, before storing to rq->curr. + * after coming from user-space, before storing to rq->curr; this + * barrier matches a full barrier in the proximity of the membarrier + * system call exit. */ rq_lock(rq, &rf); smp_mb__after_spinlock(); @@ -6716,6 +6718,9 @@ static void __sched notrace __schedule(unsigned int sched_mode) * architectures where spin_unlock is a full barrier, * - switch_to() for arm64 (weakly-ordered, spin_unlock * is a RELEASE barrier), + * + * The barrier matches a full barrier in the proximity of + * the membarrier system call entry. */ ++*switch_count; diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 2ad881d07752..f3d91628d6b8 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -251,7 +251,7 @@ static int membarrier_global_expedited(void) return 0; /* - * Matches memory barriers around rq->curr modification in + * Matches memory barriers after rq->curr modification in * scheduler. */ smp_mb(); /* system call entry is not a mb. */ @@ -300,7 +300,7 @@ static int membarrier_global_expedited(void) /* * Memory barrier on the caller thread _after_ we finished - * waiting for the last IPI. Matches memory barriers around + * waiting for the last IPI. Matches memory barriers before * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ @@ -339,7 +339,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) return 0; /* - * Matches memory barriers around rq->curr modification in + * Matches memory barriers after rq->curr modification in * scheduler. */ smp_mb(); /* system call entry is not a mb. */ @@ -415,7 +415,7 @@ out: /* * Memory barrier on the caller thread _after_ we finished - * waiting for the last IPI. Matches memory barriers around + * waiting for the last IPI. Matches memory barriers before * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ -- cgit v1.2.3 From 4ff4c745a16c4c151a71863420811e7f406c3ec2 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Wed, 31 Jan 2024 15:49:35 +0100 Subject: locking: Introduce prepare_sync_core_cmd() Introduce an architecture function that architectures can use to set up ("prepare") SYNC_CORE commands. The function will be used by RISC-V to update its "deferred icache- flush" data structures (icache_stale_mask). Architectures defining prepare_sync_core_cmd() static inline need to select ARCH_HAS_PREPARE_SYNC_CORE_CMD. Suggested-by: Mathieu Desnoyers Signed-off-by: Andrea Parri Reviewed-by: Mathieu Desnoyers Link: https://lore.kernel.org/r/20240131144936.29190-4-parri.andrea@gmail.com Signed-off-by: Palmer Dabbelt --- include/linux/sync_core.h | 16 +++++++++++++++- init/Kconfig | 3 +++ kernel/sched/membarrier.c | 1 + 3 files changed, 19 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/sync_core.h b/include/linux/sync_core.h index 013da4b8b327..67bb9794b875 100644 --- a/include/linux/sync_core.h +++ b/include/linux/sync_core.h @@ -17,5 +17,19 @@ static inline void sync_core_before_usermode(void) } #endif -#endif /* _LINUX_SYNC_CORE_H */ +#ifdef CONFIG_ARCH_HAS_PREPARE_SYNC_CORE_CMD +#include +#else +/* + * This is a dummy prepare_sync_core_cmd() implementation that can be used on + * all architectures which provide unconditional core serializing instructions + * in switch_mm(). + * If your architecture doesn't provide such core serializing instructions in + * switch_mm(), you may need to write your own functions. + */ +static inline void prepare_sync_core_cmd(struct mm_struct *mm) +{ +} +#endif +#endif /* _LINUX_SYNC_CORE_H */ diff --git a/init/Kconfig b/init/Kconfig index 8df18f3a9748..c3994b92333d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1970,6 +1970,9 @@ source "kernel/Kconfig.locks" config ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE bool +config ARCH_HAS_PREPARE_SYNC_CORE_CMD + bool + config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE bool diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index f3d91628d6b8..6d1f31b3a967 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -320,6 +320,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY)) return -EPERM; ipi_func = ipi_sync_core; + prepare_sync_core_cmd(mm); } else if (flags == MEMBARRIER_FLAG_RSEQ) { if (!IS_ENABLED(CONFIG_RSEQ)) return -EINVAL; -- cgit v1.2.3 From cd9b29014dc69609489261efe351d0c7709ae8bf Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Wed, 31 Jan 2024 15:49:36 +0100 Subject: membarrier: riscv: Provide core serializing command RISC-V uses xRET instructions on return from interrupt and to go back to user-space; the xRET instruction is not core serializing. Use FENCE.I for providing core serialization as follows: - by calling sync_core_before_usermode() on return from interrupt (cf. ipi_sync_core()), - via switch_mm() and sync_core_before_usermode() (respectively, for uthread->uthread and kthread->uthread transitions) before returning to user-space. On RISC-V, the serialization in switch_mm() is activated by resetting the icache_stale_mask of the mm at prepare_sync_core_cmd(). Suggested-by: Palmer Dabbelt Signed-off-by: Andrea Parri Reviewed-by: Mathieu Desnoyers Link: https://lore.kernel.org/r/20240131144936.29190-5-parri.andrea@gmail.com Signed-off-by: Palmer Dabbelt --- .../sched/membarrier-sync-core/arch-support.txt | 18 +++++++++++++- MAINTAINERS | 1 + arch/riscv/Kconfig | 3 +++ arch/riscv/include/asm/membarrier.h | 19 ++++++++++++++ arch/riscv/include/asm/sync_core.h | 29 ++++++++++++++++++++++ kernel/sched/core.c | 4 +++ kernel/sched/membarrier.c | 4 +++ 7 files changed, 77 insertions(+), 1 deletion(-) create mode 100644 arch/riscv/include/asm/sync_core.h (limited to 'kernel') diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt index d96b778b87ed..7425d2b994a3 100644 --- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt +++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt @@ -10,6 +10,22 @@ # Rely on implicit context synchronization as a result of exception return # when returning from IPI handler, and when returning to user-space. # +# * riscv +# +# riscv uses xRET as return from interrupt and to return to user-space. +# +# Given that xRET is not core serializing, we rely on FENCE.I for providing +# core serialization: +# +# - by calling sync_core_before_usermode() on return from interrupt (cf. +# ipi_sync_core()), +# +# - via switch_mm() and sync_core_before_usermode() (respectively, for +# uthread->uthread and kthread->uthread transitions) before returning +# to user-space. +# +# The serialization in switch_mm() is activated by prepare_sync_core_cmd(). +# # * x86 # # x86-32 uses IRET as return from interrupt, which takes care of the IPI. @@ -43,7 +59,7 @@ | openrisc: | TODO | | parisc: | TODO | | powerpc: | ok | - | riscv: | TODO | + | riscv: | ok | | s390: | ok | | sh: | TODO | | sparc: | TODO | diff --git a/MAINTAINERS b/MAINTAINERS index 78c835cc69c9..cc80968ec355 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14041,6 +14041,7 @@ L: linux-kernel@vger.kernel.org S: Supported F: Documentation/scheduler/membarrier.rst F: arch/*/include/asm/membarrier.h +F: arch/*/include/asm/sync_core.h F: include/uapi/linux/membarrier.h F: kernel/sched/membarrier.c diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 087abf9e51c6..70836381b948 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -28,14 +28,17 @@ config RISCV select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV select ARCH_HAS_MEMBARRIER_CALLBACKS + select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_MMIOWB select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API + select ARCH_HAS_PREPARE_SYNC_CORE_CMD select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_DIRECT_MAP if MMU select ARCH_HAS_SET_MEMORY if MMU select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL + select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN_SANITIZE_ALL diff --git a/arch/riscv/include/asm/membarrier.h b/arch/riscv/include/asm/membarrier.h index 6c016ebb5020..47b240d0d596 100644 --- a/arch/riscv/include/asm/membarrier.h +++ b/arch/riscv/include/asm/membarrier.h @@ -22,6 +22,25 @@ static inline void membarrier_arch_switch_mm(struct mm_struct *prev, /* * The membarrier system call requires a full memory barrier * after storing to rq->curr, before going back to user-space. + * + * This barrier is also needed for the SYNC_CORE command when + * switching between processes; in particular, on a transition + * from a thread belonging to another mm to a thread belonging + * to the mm for which a membarrier SYNC_CORE is done on CPU0: + * + * - [CPU0] sets all bits in the mm icache_stale_mask (in + * prepare_sync_core_cmd()); + * + * - [CPU1] stores to rq->curr (by the scheduler); + * + * - [CPU0] loads rq->curr within membarrier and observes + * cpu_rq(1)->curr->mm != mm, so the IPI is skipped on + * CPU1; this means membarrier relies on switch_mm() to + * issue the sync-core; + * + * - [CPU1] switch_mm() loads icache_stale_mask; if the bit + * is zero, switch_mm() may incorrectly skip the sync-core. + * * Matches a full barrier in the proximity of the membarrier * system call entry. */ diff --git a/arch/riscv/include/asm/sync_core.h b/arch/riscv/include/asm/sync_core.h new file mode 100644 index 000000000000..9153016da8f1 --- /dev/null +++ b/arch/riscv/include/asm/sync_core.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_SYNC_CORE_H +#define _ASM_RISCV_SYNC_CORE_H + +/* + * RISC-V implements return to user-space through an xRET instruction, + * which is not core serializing. + */ +static inline void sync_core_before_usermode(void) +{ + asm volatile ("fence.i" ::: "memory"); +} + +#ifdef CONFIG_SMP +/* + * Ensure the next switch_mm() on every CPU issues a core serializing + * instruction for the given @mm. + */ +static inline void prepare_sync_core_cmd(struct mm_struct *mm) +{ + cpumask_setall(&mm->context.icache_stale_mask); +} +#else +static inline void prepare_sync_core_cmd(struct mm_struct *mm) +{ +} +#endif /* CONFIG_SMP */ + +#endif /* _ASM_RISCV_SYNC_CORE_H */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a972628e7756..e4a87bcf28d4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6721,6 +6721,10 @@ static void __sched notrace __schedule(unsigned int sched_mode) * * The barrier matches a full barrier in the proximity of * the membarrier system call entry. + * + * On RISC-V, this barrier pairing is also needed for the + * SYNC_CORE command when switching between processes, cf. + * the inline comments in membarrier_arch_switch_mm(). */ ++*switch_count; diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 6d1f31b3a967..703e8d80a576 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -342,6 +342,10 @@ static int membarrier_private_expedited(int flags, int cpu_id) /* * Matches memory barriers after rq->curr modification in * scheduler. + * + * On RISC-V, this barrier pairing is also needed for the + * SYNC_CORE command when switching between processes, cf. + * the inline comments in membarrier_arch_switch_mm(). */ smp_mb(); /* system call entry is not a mb. */ -- cgit v1.2.3 From 2444a80c1cc2c4240f60f2162abef3797c1803de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 14 Feb 2024 08:48:28 +0000 Subject: kobject: make uevent_seqnum atomic We will soon no longer acquire uevent_sock_mutex for most kobject_uevent_net_broadcast() calls, and also while calling uevent_net_broadcast(). Make uevent_seqnum an atomic64_t to get its own protection. This fixes a race while reading /sys/kernel/uevent_seqnum. Signed-off-by: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Christian Brauner Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20240214084829.684541-2-edumazet@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 +- kernel/ksysfs.c | 2 +- lib/kobject_uevent.c | 17 +++++++++-------- 3 files changed, 11 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c30affcc43b4..c8219505a79f 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -38,7 +38,7 @@ extern char uevent_helper[]; #endif /* counter to tag the uevent, read only except for the kobject core */ -extern u64 uevent_seqnum; +extern atomic64_t uevent_seqnum; /* * The actions here must match the index to the string array diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 1d4bc493b2f4..32ae7fa74a9c 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -39,7 +39,7 @@ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static ssize_t uevent_seqnum_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sysfs_emit(buf, "%llu\n", (unsigned long long)uevent_seqnum); + return sysfs_emit(buf, "%llu\n", (u64)atomic64_read(&uevent_seqnum)); } KERNEL_ATTR_RO(uevent_seqnum); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index fb9a2f06dd1e..9cb1a7fdaeba 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -30,7 +30,7 @@ #include -u64 uevent_seqnum; +atomic64_t uevent_seqnum; #ifdef CONFIG_UEVENT_HELPER char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH; #endif @@ -44,7 +44,7 @@ struct uevent_sock { static LIST_HEAD(uevent_sock_list); #endif -/* This lock protects uevent_seqnum and uevent_sock_list */ +/* This lock protects uevent_sock_list */ static DEFINE_MUTEX(uevent_sock_mutex); /* the strings here must match the enum in include/linux/kobject.h */ @@ -583,13 +583,13 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, break; } - mutex_lock(&uevent_sock_mutex); /* we will send an event, so request a new sequence number */ - retval = add_uevent_var(env, "SEQNUM=%llu", ++uevent_seqnum); - if (retval) { - mutex_unlock(&uevent_sock_mutex); + retval = add_uevent_var(env, "SEQNUM=%llu", + atomic64_inc_return(&uevent_seqnum)); + if (retval) goto exit; - } + + mutex_lock(&uevent_sock_mutex); retval = kobject_uevent_net_broadcast(kobj, env, action_string, devpath); mutex_unlock(&uevent_sock_mutex); @@ -688,7 +688,8 @@ static int uevent_net_broadcast(struct sock *usk, struct sk_buff *skb, int ret; /* bump and prepare sequence number */ - ret = snprintf(buf, sizeof(buf), "SEQNUM=%llu", ++uevent_seqnum); + ret = snprintf(buf, sizeof(buf), "SEQNUM=%llu", + atomic64_inc_return(&uevent_seqnum)); if (ret < 0 || (size_t)ret >= sizeof(buf)) return -ENOMEM; ret++; -- cgit v1.2.3 From d2d5cba5d92c4ed23caa86228a1bc31b07e90fe9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 15 Feb 2024 23:15:01 +0900 Subject: kbuild: remove EXPERT and !COMPILE_TEST guarding from TRIM_UNUSED_KSYMS This reverts the following two commits: - a555bdd0c58c ("Kbuild: enable TRIM_UNUSED_KSYMS again, with some guarding") - 5cf0fd591f2e ("Kbuild: disable TRIM_UNUSED_KSYMS option") Commit 5e9e95cc9148 ("kbuild: implement CONFIG_TRIM_UNUSED_KSYMS without recursion") solved the build time issue. Signed-off-by: Masahiro Yamada --- kernel/module/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 0ea1b2970a23..c3ced519e14b 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -362,8 +362,7 @@ config MODPROBE_PATH userspace can still load modules explicitly). config TRIM_UNUSED_KSYMS - bool "Trim unused exported kernel symbols" if EXPERT - depends on !COMPILE_TEST + bool "Trim unused exported kernel symbols" help The kernel and some modules make many symbols available for other modules to use via EXPORT_SYMBOL() and variants. Depending -- cgit v1.2.3 From 801410b26a0e8b8a16f7915b2b55c9528b69ca87 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 4 Mar 2024 13:43:49 -0800 Subject: serial: Lock console when calling into driver before registration During the handoff from earlycon to the real console driver, we have two separate drivers operating on the same device concurrently. In the case of the 8250 driver these concurrent accesses cause problems due to the driver's use of banked registers, controlled by LCR.DLAB. It is possible for the setup(), config_port(), pm() and set_mctrl() callbacks to set DLAB, which can cause the earlycon code that intends to access TX to instead access DLL, leading to missed output and corruption on the serial line due to unintended modifications to the baud rate. In particular, for setup() we have: univ8250_console_setup() -> serial8250_console_setup() -> uart_set_options() -> serial8250_set_termios() -> serial8250_do_set_termios() -> serial8250_do_set_divisor() For config_port() we have: serial8250_config_port() -> autoconfig() For pm() we have: serial8250_pm() -> serial8250_do_pm() -> serial8250_set_sleep() For set_mctrl() we have (for some devices): serial8250_set_mctrl() -> omap8250_set_mctrl() -> __omap8250_set_mctrl() To avoid such problems, let's make it so that the console is locked during pre-registration calls to these callbacks, which will prevent the earlycon driver from running concurrently. Remove the partial solution to this problem in the 8250 driver that locked the console only during autoconfig_irq(), as this would result in a deadlock with the new approach. The console continues to be locked during autoconfig_irq() because it can only be called through uart_configure_port(). Although this patch introduces more locking than strictly necessary (and in particular it also locks during the call to rs485_config() which is not affected by this issue as far as I can tell), it follows the principle that it is the responsibility of the generic console code to manage the earlycon handoff by ensuring that earlycon and real console driver code cannot run concurrently, and not the individual drivers. Signed-off-by: Peter Collingbourne Reviewed-by: John Ogness Link: https://linux-review.googlesource.com/id/I7cf8124dcebf8618e6b2ee543fa5b25532de55d8 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240304214350.501253-1-pcc@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 6 ------ drivers/tty/serial/serial_core.c | 12 ++++++++++++ kernel/printk/printk.c | 21 ++++++++++++++++++--- 3 files changed, 30 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 336a0bd4d172..fc9dd5d45295 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1325,9 +1325,6 @@ static void autoconfig_irq(struct uart_8250_port *up) inb_p(ICP); } - if (uart_console(port)) - console_lock(); - /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); @@ -1367,9 +1364,6 @@ static void autoconfig_irq(struct uart_8250_port *up) if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); - if (uart_console(port)) - console_unlock(); - port->irq = (irq > 0) ? irq : 0; } diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index d6a58a9e072a..ff85ebd3a007 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2608,7 +2608,12 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); port->ops->config_port(port, flags); + if (uart_console(port)) + console_unlock(); } if (port->type != PORT_UNKNOWN) { @@ -2616,6 +2621,10 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_report_port(drv, port); + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); + /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); @@ -2632,6 +2641,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_rs485_config(port); + if (uart_console(port)) + console_unlock(); + /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index f2444b581e16..89f2aa2e1172 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3263,6 +3263,21 @@ static int __init keep_bootcon_setup(char *str) early_param("keep_bootcon", keep_bootcon_setup); +static int console_call_setup(struct console *newcon, char *options) +{ + int err; + + if (!newcon->setup) + return 0; + + /* Synchronize with possible boot console. */ + console_lock(); + err = newcon->setup(newcon, options); + console_unlock(); + + return err; +} + /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected @@ -3298,8 +3313,8 @@ static int try_enable_preferred_console(struct console *newcon, if (_braille_register_console(newcon, c)) return 0; - if (newcon->setup && - (err = newcon->setup(newcon, c->options)) != 0) + err = console_call_setup(newcon, c->options); + if (err) return err; } newcon->flags |= CON_ENABLED; @@ -3325,7 +3340,7 @@ static void try_enable_default_console(struct console *newcon) if (newcon->index < 0) newcon->index = 0; - if (newcon->setup && newcon->setup(newcon, NULL) != 0) + if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; -- cgit v1.2.3 From 6b6ca096115e5b7a85e8313f4e68a72d52db91b3 Mon Sep 17 00:00:00 2001 From: Ricardo B. Marliere Date: Tue, 5 Mar 2024 15:22:28 -0300 Subject: rtc: class: make rtc_class constant Since commit 43a7206b0963 ("driver core: class: make class_register() take a const *"), the driver core allows for struct class to be in read-only memory, so move the rtc_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Ricardo B. Marliere Link: https://lore.kernel.org/r/20240305-class_cleanup-abelloni-v1-1-944c026137c8@marliere.net Signed-off-by: Alexandre Belloni --- drivers/rtc/class.c | 21 +++++++++++++-------- drivers/rtc/interface.c | 2 +- include/linux/rtc.h | 2 +- kernel/power/suspend_test.c | 2 +- kernel/time/alarmtimer.c | 2 +- 5 files changed, 17 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 921ee1827974..e31fa0ad127e 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -21,7 +21,6 @@ #include "rtc-core.h" static DEFINE_IDA(rtc_ida); -struct class *rtc_class; static void rtc_device_release(struct device *dev) { @@ -199,6 +198,11 @@ static SIMPLE_DEV_PM_OPS(rtc_class_dev_pm_ops, rtc_suspend, rtc_resume); #define RTC_CLASS_DEV_PM_OPS NULL #endif +const struct class rtc_class = { + .name = "rtc", + .pm = RTC_CLASS_DEV_PM_OPS, +}; + /* Ensure the caller will set the id before releasing the device */ static struct rtc_device *rtc_allocate_device(void) { @@ -220,7 +224,7 @@ static struct rtc_device *rtc_allocate_device(void) rtc->irq_freq = 1; rtc->max_user_freq = 64; - rtc->dev.class = rtc_class; + rtc->dev.class = &rtc_class; rtc->dev.groups = rtc_get_dev_attribute_groups(); rtc->dev.release = rtc_device_release; @@ -475,13 +479,14 @@ EXPORT_SYMBOL_GPL(devm_rtc_device_register); static int __init rtc_init(void) { - rtc_class = class_create("rtc"); - if (IS_ERR(rtc_class)) { - pr_err("couldn't create class\n"); - return PTR_ERR(rtc_class); - } - rtc_class->pm = RTC_CLASS_DEV_PM_OPS; + int err; + + err = class_register(&rtc_class); + if (err) + return err; + rtc_dev_init(); + return 0; } subsys_initcall(rtc_init); diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 1b63111cdda2..5faafb4aa55c 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -696,7 +696,7 @@ struct rtc_device *rtc_class_open(const char *name) struct device *dev; struct rtc_device *rtc = NULL; - dev = class_find_device_by_name(rtc_class, name); + dev = class_find_device_by_name(&rtc_class, name); if (dev) rtc = to_rtc_device(dev); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 5f8e438a0312..3f4d315aaec9 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -42,7 +42,7 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) #include #include -extern struct class *rtc_class; +extern const struct class rtc_class; /* * For these RTC methods the device parameter is the physical device diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index b663a97f5867..d4856ec61570 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -201,7 +201,7 @@ static int __init test_suspend(void) } /* RTCs have initialized by now too ... can we use one? */ - dev = class_find_device(rtc_class, NULL, NULL, has_wakealarm); + dev = class_find_device(&rtc_class, NULL, NULL, has_wakealarm); if (dev) { rtc = rtc_class_open(dev_name(dev)); put_device(dev); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 4657cb8e8b1f..5abfa4390673 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -134,7 +134,7 @@ static struct class_interface alarmtimer_rtc_interface = { static int alarmtimer_rtc_interface_setup(void) { - alarmtimer_rtc_interface.class = rtc_class; + alarmtimer_rtc_interface.class = &rtc_class; return class_interface_register(&alarmtimer_rtc_interface); } static void alarmtimer_rtc_interface_remove(void) -- cgit v1.2.3 From fb13b11d53875e28e7fbf0c26b288e4ea676aa9f Mon Sep 17 00:00:00 2001 From: André Rösti Date: Mon, 11 Mar 2024 21:17:04 +0000 Subject: entry: Respect changes to system call number by trace_sys_enter() When a probe is registered at the trace_sys_enter() tracepoint, and that probe changes the system call number, the old system call still gets executed. This worked correctly until commit b6ec41346103 ("core/entry: Report syscall correctly for trace and audit"), which removed the re-evaluation of the syscall number after the trace point. Restore the original semantics by re-evaluating the system call number after trace_sys_enter(). The performance impact of this re-evaluation is minimal because it only takes place when a trace point is active, and compared to the actual trace point overhead the read from a cache hot variable is negligible. Fixes: b6ec41346103 ("core/entry: Report syscall correctly for trace and audit") Signed-off-by: André Rösti Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240311211704.7262-1-an.roesti@gmail.com --- kernel/entry/common.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 88cb3c88aaa5..90843cc38588 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -57,8 +57,14 @@ long syscall_trace_enter(struct pt_regs *regs, long syscall, /* Either of the above might have changed the syscall number */ syscall = syscall_get_nr(current, regs); - if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) + if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) { trace_sys_enter(regs, syscall); + /* + * Probes or BPF hooks in the tracepoint may have changed the + * system call number as well. + */ + syscall = syscall_get_nr(current, regs); + } syscall_enter_audit(regs, syscall); -- cgit v1.2.3 From 04867a7a33324c9c562ee7949dbcaab7aaad1fb4 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Mar 2024 15:28:24 +0000 Subject: swiotlb: Fix double-allocation of slots due to broken alignment handling Commit bbb73a103fbb ("swiotlb: fix a braino in the alignment check fix"), which was a fix for commit 0eee5ae10256 ("swiotlb: fix slot alignment checks"), causes a functional regression with vsock in a virtual machine using bouncing via a restricted DMA SWIOTLB pool. When virtio allocates the virtqueues for the vsock device using dma_alloc_coherent(), the SWIOTLB search can return page-unaligned allocations if 'area->index' was left unaligned by a previous allocation from the buffer: # Final address in brackets is the SWIOTLB address returned to the caller | virtio-pci 0000:00:07.0: orig_addr 0x0 alloc_size 0x2000, iotlb_align_mask 0x800 stride 0x2: got slot 1645-1649/7168 (0x98326800) | virtio-pci 0000:00:07.0: orig_addr 0x0 alloc_size 0x2000, iotlb_align_mask 0x800 stride 0x2: got slot 1649-1653/7168 (0x98328800) | virtio-pci 0000:00:07.0: orig_addr 0x0 alloc_size 0x2000, iotlb_align_mask 0x800 stride 0x2: got slot 1653-1657/7168 (0x9832a800) This ends badly (typically buffer corruption and/or a hang) because swiotlb_alloc() is expecting a page-aligned allocation and so blindly returns a pointer to the 'struct page' corresponding to the allocation, therefore double-allocating the first half (2KiB slot) of the 4KiB page. Fix the problem by treating the allocation alignment separately to any additional alignment requirements from the device, using the maximum of the two as the stride to search the buffer slots and taking care to ensure a minimum of page-alignment for buffers larger than a page. This also resolves swiotlb allocation failures occuring due to the inclusion of ~PAGE_MASK in 'iotlb_align_mask' for large allocations and resulting in alignment requirements exceeding swiotlb_max_mapping_size(). Fixes: bbb73a103fbb ("swiotlb: fix a braino in the alignment check fix") Fixes: 0eee5ae10256 ("swiotlb: fix slot alignment checks") Signed-off-by: Will Deacon Reviewed-by: Michael Kelley Reviewed-by: Petr Tesarik Tested-by: Nicolin Chen Tested-by: Michael Kelley Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 77974cea3e69..980a7ec70418 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1004,7 +1004,7 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool phys_to_dma_unencrypted(dev, pool->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); unsigned int iotlb_align_mask = - dma_get_min_align_mask(dev) | alloc_align_mask; + dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1); unsigned int nslots = nr_slots(alloc_size), stride; unsigned int offset = swiotlb_align_offset(dev, orig_addr); unsigned int index, slots_checked, count = 0, i; @@ -1016,18 +1016,17 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool BUG_ON(area_index >= pool->nareas); /* - * For allocations of PAGE_SIZE or larger only look for page aligned - * allocations. + * For mappings with an alignment requirement don't bother looping to + * unaligned slots once we found an aligned one. */ - if (alloc_size >= PAGE_SIZE) - iotlb_align_mask |= ~PAGE_MASK; - iotlb_align_mask &= ~(IO_TLB_SIZE - 1); + stride = get_max_slots(max(alloc_align_mask, iotlb_align_mask)); /* - * For mappings with an alignment requirement don't bother looping to - * unaligned slots once we found an aligned one. + * For allocations of PAGE_SIZE or larger only look for page aligned + * allocations. */ - stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1; + if (alloc_size >= PAGE_SIZE) + stride = umax(stride, PAGE_SHIFT - IO_TLB_SHIFT + 1); spin_lock_irqsave(&area->lock, flags); if (unlikely(nslots > pool->area_nslabs - area->used)) @@ -1037,11 +1036,14 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool index = area->index; for (slots_checked = 0; slots_checked < pool->area_nslabs; ) { + phys_addr_t tlb_addr; + slot_index = slot_base + index; + tlb_addr = slot_addr(tbl_dma_addr, slot_index); - if (orig_addr && - (slot_addr(tbl_dma_addr, slot_index) & - iotlb_align_mask) != (orig_addr & iotlb_align_mask)) { + if ((tlb_addr & alloc_align_mask) || + (orig_addr && (tlb_addr & iotlb_align_mask) != + (orig_addr & iotlb_align_mask))) { index = wrap_area_index(pool, index + 1); slots_checked++; continue; -- cgit v1.2.3 From 823353b7cf0ea9dfb09f5181d5fb2825d727200b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Mar 2024 15:28:25 +0000 Subject: swiotlb: Enforce page alignment in swiotlb_alloc() When allocating pages from a restricted DMA pool in swiotlb_alloc(), the buffer address is blindly converted to a 'struct page *' that is returned to the caller. In the unlikely event of an allocation bug, page-unaligned addresses are not detected and slots can silently be double-allocated. Add a simple check of the buffer alignment in swiotlb_alloc() to make debugging a little easier if something has gone wonky. Signed-off-by: Will Deacon Reviewed-by: Michael Kelley Reviewed-by: Petr Tesarik Tested-by: Nicolin Chen Tested-by: Michael Kelley Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 980a7ec70418..88114433f1e6 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1689,6 +1689,12 @@ struct page *swiotlb_alloc(struct device *dev, size_t size) return NULL; tlb_addr = slot_addr(pool->start, index); + if (unlikely(!PAGE_ALIGNED(tlb_addr))) { + dev_WARN_ONCE(dev, 1, "Cannot allocate pages from non page-aligned swiotlb addr 0x%pa.\n", + &tlb_addr); + swiotlb_release_slots(dev, tlb_addr); + return NULL; + } return pfn_to_page(PFN_DOWN(tlb_addr)); } -- cgit v1.2.3 From cbf53074a528191df82b4dba1e3d21191102255e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Mar 2024 15:28:26 +0000 Subject: swiotlb: Honour dma_alloc_coherent() alignment in swiotlb_alloc() core-api/dma-api-howto.rst states the following properties of dma_alloc_coherent(): | The CPU virtual address and the DMA address are both guaranteed to | be aligned to the smallest PAGE_SIZE order which is greater than or | equal to the requested size. However, swiotlb_alloc() passes zero for the 'alloc_align_mask' parameter of swiotlb_find_slots() and so this property is not upheld. Instead, allocations larger than a page are aligned to PAGE_SIZE, Calculate the mask corresponding to the page order suitable for holding the allocation and pass that to swiotlb_find_slots(). Fixes: e81e99bacc9f ("swiotlb: Support aligned swiotlb buffers") Signed-off-by: Will Deacon Reviewed-by: Michael Kelley Reviewed-by: Petr Tesarik Tested-by: Nicolin Chen Tested-by: Michael Kelley Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 88114433f1e6..a3645a9ae68e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1679,12 +1679,14 @@ struct page *swiotlb_alloc(struct device *dev, size_t size) struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; phys_addr_t tlb_addr; + unsigned int align; int index; if (!mem) return NULL; - index = swiotlb_find_slots(dev, 0, size, 0, &pool); + align = (1 << (get_order(size) + PAGE_SHIFT)) - 1; + index = swiotlb_find_slots(dev, 0, size, align, &pool); if (index == -1) return NULL; -- cgit v1.2.3 From 51b30ecb73b481d5fac6ccf2ecb4a309c9ee3310 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Mar 2024 15:28:27 +0000 Subject: swiotlb: Fix alignment checks when both allocation and DMA masks are present Nicolin reports that swiotlb buffer allocations fail for an NVME device behind an IOMMU using 64KiB pages. This is because we end up with a minimum allocation alignment of 64KiB (for the IOMMU to map the buffer safely) but a minimum DMA alignment mask corresponding to a 4KiB NVME page (i.e. preserving the 4KiB page offset from the original allocation). If the original address is not 4KiB-aligned, the allocation will fail because swiotlb_search_pool_area() erroneously compares these unmasked bits with the 64KiB-aligned candidate allocation. Tweak swiotlb_search_pool_area() so that the DMA alignment mask is reduced based on the required alignment of the allocation. Fixes: 82612d66d51d ("iommu: Allow the dma-iommu api to use bounce buffers") Link: https://lore.kernel.org/r/cover.1707851466.git.nicolinc@nvidia.com Reported-by: Nicolin Chen Signed-off-by: Will Deacon Reviewed-by: Michael Kelley Tested-by: Nicolin Chen Tested-by: Michael Kelley Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index a3645a9ae68e..f212943e51ca 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1003,8 +1003,7 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, pool->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); - unsigned int iotlb_align_mask = - dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1); + unsigned int iotlb_align_mask = dma_get_min_align_mask(dev); unsigned int nslots = nr_slots(alloc_size), stride; unsigned int offset = swiotlb_align_offset(dev, orig_addr); unsigned int index, slots_checked, count = 0, i; @@ -1015,6 +1014,14 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool BUG_ON(!nslots); BUG_ON(area_index >= pool->nareas); + /* + * Ensure that the allocation is at least slot-aligned and update + * 'iotlb_align_mask' to ignore bits that will be preserved when + * offsetting into the allocation. + */ + alloc_align_mask |= (IO_TLB_SIZE - 1); + iotlb_align_mask &= ~alloc_align_mask; + /* * For mappings with an alignment requirement don't bother looping to * unaligned slots once we found an aligned one. -- cgit v1.2.3 From 14cebf689a78e8a1c041138af221ef6eac6bc7da Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Mar 2024 15:28:29 +0000 Subject: swiotlb: Reinstate page-alignment for mappings >= PAGE_SIZE For swiotlb allocations >= PAGE_SIZE, the slab search historically adjusted the stride to avoid checking unaligned slots. This had the side-effect of aligning large mapping requests to PAGE_SIZE, but that was broken by 0eee5ae10256 ("swiotlb: fix slot alignment checks"). Since this alignment could be relied upon drivers, reinstate PAGE_SIZE alignment for swiotlb mappings >= PAGE_SIZE. Reported-by: Michael Kelley Signed-off-by: Will Deacon Reviewed-by: Robin Murphy Reviewed-by: Petr Tesarik Tested-by: Nicolin Chen Tested-by: Michael Kelley Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index f212943e51ca..86fe172b5958 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1014,6 +1014,17 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool BUG_ON(!nslots); BUG_ON(area_index >= pool->nareas); + /* + * Historically, swiotlb allocations >= PAGE_SIZE were guaranteed to be + * page-aligned in the absence of any other alignment requirements. + * 'alloc_align_mask' was later introduced to specify the alignment + * explicitly, however this is passed as zero for streaming mappings + * and so we preserve the old behaviour there in case any drivers are + * relying on it. + */ + if (!alloc_align_mask && !iotlb_align_mask && alloc_size >= PAGE_SIZE) + alloc_align_mask = PAGE_SIZE - 1; + /* * Ensure that the allocation is at least slot-aligned and update * 'iotlb_align_mask' to ignore bits that will be preserved when @@ -1028,13 +1039,6 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool */ stride = get_max_slots(max(alloc_align_mask, iotlb_align_mask)); - /* - * For allocations of PAGE_SIZE or larger only look for page aligned - * allocations. - */ - if (alloc_size >= PAGE_SIZE) - stride = umax(stride, PAGE_SHIFT - IO_TLB_SHIFT + 1); - spin_lock_irqsave(&area->lock, flags); if (unlikely(nslots > pool->area_nslabs - area->used)) goto not_found; -- cgit v1.2.3 From 3acec69a94eaaf3d7ebb043e1db45cc26f58a847 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Fri, 8 Mar 2024 12:32:03 +0000 Subject: PM: EM: Force device drivers to provide power in uW The EM only supports power in uW. Make sure that it is not possible to register some downstream driver which doesn't provide power in uW. The only exception is artificial EM, but that EM is ignored by the rest of kernel frameworks (thermal, powercap, etc). Reported-by: PoShao Chen Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel') diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index b686ac0345bd..9e1c9aa399ea 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -612,6 +612,17 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, else if (cb->get_cost) flags |= EM_PERF_DOMAIN_ARTIFICIAL; + /* + * EM only supports uW (exception is artificial EM). + * Therefore, check and force the drivers to provide + * power in uW. + */ + if (!microwatts && !(flags & EM_PERF_DOMAIN_ARTIFICIAL)) { + dev_err(dev, "EM: only supports uW power values\n"); + ret = -EINVAL; + goto unlock; + } + ret = em_create_pd(dev, nr_states, cb, cpus, flags); if (ret) goto unlock; -- cgit v1.2.3 From 44d79142ede8162fd67bf8ca4ddbda1fbcfa94f1 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Thu, 14 Mar 2024 17:49:31 +0000 Subject: bpf: Temporarily disable atomic operations in BPF arena Currently, the x86 JIT handling PROBE_MEM32 tagged accesses is not equipped to handle atomic accesses into PTR_TO_ARENA, as no PROBE_MEM32 tagging is performed and no handling is enabled for them. This will lead to unsafety as the offset into arena will dereferenced directly without turning it into a base + offset access into the arena region. Since the changes to the x86 JIT will be fairly involved, for now, temporarily disallow use of PTR_TO_ARENA as the destination operand for atomics until support is added to the JIT backend. Fixes: 2fe99eb0ccf2 ("bpf: Add x86-64 JIT support for PROBE_MEM32 pseudo instructions.") Reported-by: Kumar Kartikeya Dwivedi Signed-off-by: Puranjay Mohan Acked-by: Kumar Kartikeya Dwivedi Message-ID: <20240314174931.98702-1-puranjay12@gmail.com> Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 63749ad5ac6b..1dd3b99d1bb9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5682,6 +5682,13 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_FLOW_KEYS; } +static bool is_arena_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = reg_state(env, regno); + + return reg->type == PTR_TO_ARENA; +} + static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { #ifdef CONFIG_NET [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], @@ -7019,7 +7026,8 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg) || is_flow_key_reg(env, insn->dst_reg) || - is_sk_reg(env, insn->dst_reg)) { + is_sk_reg(env, insn->dst_reg) || + is_arena_reg(env, insn->dst_reg)) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str(env, reg_state(env, insn->dst_reg)->type)); -- cgit v1.2.3 From 8076972468584d4a21dab9aa50e388b3ea9ad8c7 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 26 Feb 2024 13:07:24 +0106 Subject: printk: Update @console_may_schedule in console_trylock_spinning() console_trylock_spinning() may takeover the console lock from a schedulable context. Update @console_may_schedule to make sure it reflects a trylock acquire. Reported-by: Mukesh Ojha Closes: https://lore.kernel.org/lkml/20240222090538.23017-1-quic_mojha@quicinc.com Fixes: dbdda842fe96 ("printk: Add console owner and waiter logic to load balance console writes") Signed-off-by: John Ogness Reviewed-by: Mukesh Ojha Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/875xybmo2z.fsf@jogness.linutronix.de Signed-off-by: Petr Mladek --- kernel/printk/printk.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b06f63e276c1..612c73333848 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2009,6 +2009,12 @@ static int console_trylock_spinning(void) */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); + /* + * Update @console_may_schedule for trylock because the previous + * owner may have been schedulable. + */ + console_may_schedule = 0; + return 1; } -- cgit v1.2.3 From ee498a38f3177d9ee0213839d3a05b94272aa48c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Mar 2024 19:18:31 -0700 Subject: bpf: Clarify bpf_arena comments. Clarify two bpf_arena comments, use existing SZ_4G #define, improve page_cnt check. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20240315021834.62988-2-alexei.starovoitov@gmail.com --- kernel/bpf/arena.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 86571e760dd6..343c3456c8dd 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -38,7 +38,7 @@ /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ #define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8) -#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ) +#define KERN_VM_SZ (SZ_4G + GUARD_SZ) struct bpf_arena { struct bpf_map map; @@ -110,7 +110,7 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr) return ERR_PTR(-EINVAL); vm_range = (u64)attr->max_entries * PAGE_SIZE; - if (vm_range > (1ull << 32)) + if (vm_range > SZ_4G) return ERR_PTR(-E2BIG); if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32)) @@ -301,7 +301,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad if (pgoff) return -EINVAL; - if (len > (1ull << 32)) + if (len > SZ_4G) return -E2BIG; /* if user_vm_start was specified at arena creation time */ @@ -322,7 +322,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad if (WARN_ON_ONCE(arena->user_vm_start)) /* checks at map creation time should prevent this */ return -EFAULT; - return round_up(ret, 1ull << 32); + return round_up(ret, SZ_4G); } static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) @@ -346,7 +346,7 @@ static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) return -EBUSY; /* Earlier checks should prevent this */ - if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff)) + if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > SZ_4G || vma->vm_pgoff)) return -EFAULT; if (remember_vma(arena, vma)) @@ -420,7 +420,7 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt if (uaddr & ~PAGE_MASK) return 0; pgoff = compute_pgoff(arena, uaddr); - if (pgoff + page_cnt > page_cnt_max) + if (pgoff > page_cnt_max - page_cnt) /* requested address will be outside of user VMA */ return 0; } @@ -447,7 +447,13 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt goto out; uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE); - /* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */ + /* Earlier checks made sure that uaddr32 + page_cnt * PAGE_SIZE - 1 + * will not overflow 32-bit. Lower 32-bit need to represent + * contiguous user address range. + * Map these pages at kern_vm_start base. + * kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE - 1 can overflow + * lower 32-bit and it's ok. + */ ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32, kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages); if (ret) { @@ -510,6 +516,11 @@ static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt) if (!page) continue; if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */ + /* Optimization for the common case of page_cnt==1: + * If page wasn't mapped into some user vma there + * is no need to call zap_pages which is slow. When + * page_cnt is big it's faster to do the batched zap. + */ zap_pages(arena, full_uaddr, 1); vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE); __free_page(page); -- cgit v1.2.3 From 0b18c852cc6fb8284ac0ab97e3e840974a6a8a64 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Tue, 20 Feb 2024 09:06:14 -0500 Subject: tracing: Have saved_cmdlines arrays all in one allocation The saved_cmdlines have three arrays for mapping PIDs to COMMs: - map_pid_to_cmdline[] - map_cmdline_to_pid[] - saved_cmdlines The map_pid_to_cmdline[] is PID_MAX_DEFAULT in size and holds the index into the other arrays. The map_cmdline_to_pid[] is a mapping back to the full pid as it can be larger than PID_MAX_DEFAULT. And the saved_cmdlines[] just holds the COMMs associated to the pids. Currently the map_pid_to_cmdline[] and saved_cmdlines[] are allocated together (in reality the saved_cmdlines is just in the memory of the rounding of the allocation of the structure as it is always allocated in powers of two). The map_cmdline_to_pid[] array is allocated separately. Since the rounding to a power of two is rather large (it allows for 8000 elements in saved_cmdlines), also include the map_cmdline_to_pid[] array. (This drops it to 6000 by default, which is still plenty for most use cases). This saves even more memory as the map_cmdline_to_pid[] array doesn't need to be allocated. Link: https://lore.kernel.org/linux-trace-kernel/20240212174011.068211d9@gandalf.local.home/ Link: https://lore.kernel.org/linux-trace-kernel/20240220140703.182330529@goodmis.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Tim Chen Cc: Vincent Donnefort Cc: Sven Schnelle Cc: Mete Durlu Fixes: 44dc5c41b5b1 ("tracing: Fix wasted memory in saved_cmdlines logic") Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ab4c1a1fbda8..70202e60a60a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2346,6 +2346,10 @@ struct saved_cmdlines_buffer { }; static struct saved_cmdlines_buffer *savedcmd; +/* Holds the size of a cmdline and pid element */ +#define SAVED_CMDLINE_MAP_ELEMENT_SIZE(s) \ + (TASK_COMM_LEN + sizeof((s)->map_cmdline_to_pid[0])) + static inline char *get_saved_cmdlines(int idx) { return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; @@ -2360,7 +2364,6 @@ static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) { int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); - kfree(s->map_cmdline_to_pid); kmemleak_free(s); free_pages((unsigned long)s, order); } @@ -2373,7 +2376,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) int order; /* Figure out how much is needed to hold the given number of cmdlines */ - orig_size = sizeof(*s) + val * TASK_COMM_LEN; + orig_size = sizeof(*s) + val * SAVED_CMDLINE_MAP_ELEMENT_SIZE(s); order = get_order(orig_size); size = 1 << (order + PAGE_SHIFT); page = alloc_pages(GFP_KERNEL, order); @@ -2385,16 +2388,11 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) memset(s, 0, sizeof(*s)); /* Round up to actual allocation */ - val = (size - sizeof(*s)) / TASK_COMM_LEN; + val = (size - sizeof(*s)) / SAVED_CMDLINE_MAP_ELEMENT_SIZE(s); s->cmdline_num = val; - s->map_cmdline_to_pid = kmalloc_array(val, - sizeof(*s->map_cmdline_to_pid), - GFP_KERNEL); - if (!s->map_cmdline_to_pid) { - free_saved_cmdlines_buffer(s); - return NULL; - } + /* Place map_cmdline_to_pid array right after saved_cmdlines */ + s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN]; s->cmdline_idx = 0; memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, -- cgit v1.2.3 From e85d471c2be5d3d4dadee1110db316f352daaf0b Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Tue, 20 Feb 2024 09:06:15 -0500 Subject: tracing: Move open coded processing of tgid_map into helper function In preparation of moving the saved_cmdlines logic out of trace.c and into trace_sched_switch.c, replace the open coded manipulation of tgid_map in set_tracer_flag() into a helper function trace_alloc_tgid_map() so that it can be easily moved into trace_sched_switch.c without changing existing functions in trace.c. No functional changes. Link: https://lore.kernel.org/linux-trace-kernel/20240220140703.338116216@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Tim Chen Cc: Vincent Donnefort Cc: Sven Schnelle Cc: Mete Durlu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 38 +++++++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 70202e60a60a..d3e630dd36f8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5453,10 +5453,31 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) return 0; } -int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) +static int trace_alloc_tgid_map(void) { int *map; + if (tgid_map) + return 0; + + tgid_map_max = pid_max; + map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map), + GFP_KERNEL); + if (!map) + return -ENOMEM; + + /* + * Pairs with smp_load_acquire() in + * trace_find_tgid_ptr() to ensure that if it observes + * the tgid_map we just allocated then it also observes + * the corresponding tgid_map_max value. + */ + smp_store_release(&tgid_map, map); + return 0; +} + +int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) +{ if ((mask == TRACE_ITER_RECORD_TGID) || (mask == TRACE_ITER_RECORD_CMD)) lockdep_assert_held(&event_mutex); @@ -5479,20 +5500,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) trace_event_enable_cmd_record(enabled); if (mask == TRACE_ITER_RECORD_TGID) { - if (!tgid_map) { - tgid_map_max = pid_max; - map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map), - GFP_KERNEL); - - /* - * Pairs with smp_load_acquire() in - * trace_find_tgid_ptr() to ensure that if it observes - * the tgid_map we just allocated then it also observes - * the corresponding tgid_map_max value. - */ - smp_store_release(&tgid_map, map); - } - if (!tgid_map) { + if (trace_alloc_tgid_map() < 0) { tr->trace_flags &= ~TRACE_ITER_RECORD_TGID; return -ENOMEM; } -- cgit v1.2.3 From 2cc621fd2e9b8494df06de459c14738cf76add91 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Tue, 20 Feb 2024 09:06:16 -0500 Subject: tracing: Move saved_cmdline code into trace_sched_switch.c The code that handles saved_cmdlines is split between the trace.c file and the trace_sched_switch.c. There's some history to this. The trace_sched_switch.c was originally created to handle the sched_switch tracer that was deprecated due to sched_switch trace event making it obsolete. But that file did not get deleted as it had some code to help with saved_cmdlines. But trace.c has grown tremendously since then. Just move all the saved_cmdlines code into trace_sched_switch.c as that's the only reason that file still exists, and trace.c has gotten too big. No functional changes. Link: https://lore.kernel.org/linux-trace-kernel/20240220140703.497966629@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Tim Chen Cc: Vincent Donnefort Cc: Sven Schnelle Cc: Mete Durlu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 515 +------------------------------------- kernel/trace/trace.h | 10 + kernel/trace/trace_sched_switch.c | 515 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 528 insertions(+), 512 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d3e630dd36f8..1e5f80cda39a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -39,7 +39,6 @@ #include #include #include -#include #include #include #include @@ -105,7 +104,7 @@ dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) * tracing is active, only save the comm when a trace event * occurred. */ -static DEFINE_PER_CPU(bool, trace_taskinfo_save); +DEFINE_PER_CPU(bool, trace_taskinfo_save); /* * Kill all tracing for good (never come back). @@ -2320,96 +2319,6 @@ void tracing_reset_all_online_cpus(void) mutex_unlock(&trace_types_lock); } -/* - * The tgid_map array maps from pid to tgid; i.e. the value stored at index i - * is the tgid last observed corresponding to pid=i. - */ -static int *tgid_map; - -/* The maximum valid index into tgid_map. */ -static size_t tgid_map_max; - -#define SAVED_CMDLINES_DEFAULT 128 -#define NO_CMDLINE_MAP UINT_MAX -/* - * Preemption must be disabled before acquiring trace_cmdline_lock. - * The various trace_arrays' max_lock must be acquired in a context - * where interrupt is disabled. - */ -static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; -struct saved_cmdlines_buffer { - unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; - unsigned *map_cmdline_to_pid; - unsigned cmdline_num; - int cmdline_idx; - char saved_cmdlines[]; -}; -static struct saved_cmdlines_buffer *savedcmd; - -/* Holds the size of a cmdline and pid element */ -#define SAVED_CMDLINE_MAP_ELEMENT_SIZE(s) \ - (TASK_COMM_LEN + sizeof((s)->map_cmdline_to_pid[0])) - -static inline char *get_saved_cmdlines(int idx) -{ - return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; -} - -static inline void set_cmdline(int idx, const char *cmdline) -{ - strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); -} - -static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) -{ - int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); - - kmemleak_free(s); - free_pages((unsigned long)s, order); -} - -static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) -{ - struct saved_cmdlines_buffer *s; - struct page *page; - int orig_size, size; - int order; - - /* Figure out how much is needed to hold the given number of cmdlines */ - orig_size = sizeof(*s) + val * SAVED_CMDLINE_MAP_ELEMENT_SIZE(s); - order = get_order(orig_size); - size = 1 << (order + PAGE_SHIFT); - page = alloc_pages(GFP_KERNEL, order); - if (!page) - return NULL; - - s = page_address(page); - kmemleak_alloc(s, size, 1, GFP_KERNEL); - memset(s, 0, sizeof(*s)); - - /* Round up to actual allocation */ - val = (size - sizeof(*s)) / SAVED_CMDLINE_MAP_ELEMENT_SIZE(s); - s->cmdline_num = val; - - /* Place map_cmdline_to_pid array right after saved_cmdlines */ - s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN]; - - s->cmdline_idx = 0; - memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, - sizeof(s->map_pid_to_cmdline)); - memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, - val * sizeof(*s->map_cmdline_to_pid)); - - return s; -} - -static int trace_create_savedcmd(void) -{ - savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT); - - return savedcmd ? 0 : -ENOMEM; -} - int is_tracing_stopped(void) { return global_trace.stop_count; @@ -2502,201 +2411,6 @@ void tracing_stop(void) return tracing_stop_tr(&global_trace); } -static int trace_save_cmdline(struct task_struct *tsk) -{ - unsigned tpid, idx; - - /* treat recording of idle task as a success */ - if (!tsk->pid) - return 1; - - tpid = tsk->pid & (PID_MAX_DEFAULT - 1); - - /* - * It's not the end of the world if we don't get - * the lock, but we also don't want to spin - * nor do we want to disable interrupts, - * so if we miss here, then better luck next time. - * - * This is called within the scheduler and wake up, so interrupts - * had better been disabled and run queue lock been held. - */ - lockdep_assert_preemption_disabled(); - if (!arch_spin_trylock(&trace_cmdline_lock)) - return 0; - - idx = savedcmd->map_pid_to_cmdline[tpid]; - if (idx == NO_CMDLINE_MAP) { - idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num; - - savedcmd->map_pid_to_cmdline[tpid] = idx; - savedcmd->cmdline_idx = idx; - } - - savedcmd->map_cmdline_to_pid[idx] = tsk->pid; - set_cmdline(idx, tsk->comm); - - arch_spin_unlock(&trace_cmdline_lock); - - return 1; -} - -static void __trace_find_cmdline(int pid, char comm[]) -{ - unsigned map; - int tpid; - - if (!pid) { - strcpy(comm, ""); - return; - } - - if (WARN_ON_ONCE(pid < 0)) { - strcpy(comm, ""); - return; - } - - tpid = pid & (PID_MAX_DEFAULT - 1); - map = savedcmd->map_pid_to_cmdline[tpid]; - if (map != NO_CMDLINE_MAP) { - tpid = savedcmd->map_cmdline_to_pid[map]; - if (tpid == pid) { - strscpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN); - return; - } - } - strcpy(comm, "<...>"); -} - -void trace_find_cmdline(int pid, char comm[]) -{ - preempt_disable(); - arch_spin_lock(&trace_cmdline_lock); - - __trace_find_cmdline(pid, comm); - - arch_spin_unlock(&trace_cmdline_lock); - preempt_enable(); -} - -static int *trace_find_tgid_ptr(int pid) -{ - /* - * Pairs with the smp_store_release in set_tracer_flag() to ensure that - * if we observe a non-NULL tgid_map then we also observe the correct - * tgid_map_max. - */ - int *map = smp_load_acquire(&tgid_map); - - if (unlikely(!map || pid > tgid_map_max)) - return NULL; - - return &map[pid]; -} - -int trace_find_tgid(int pid) -{ - int *ptr = trace_find_tgid_ptr(pid); - - return ptr ? *ptr : 0; -} - -static int trace_save_tgid(struct task_struct *tsk) -{ - int *ptr; - - /* treat recording of idle task as a success */ - if (!tsk->pid) - return 1; - - ptr = trace_find_tgid_ptr(tsk->pid); - if (!ptr) - return 0; - - *ptr = tsk->tgid; - return 1; -} - -static bool tracing_record_taskinfo_skip(int flags) -{ - if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) - return true; - if (!__this_cpu_read(trace_taskinfo_save)) - return true; - return false; -} - -/** - * tracing_record_taskinfo - record the task info of a task - * - * @task: task to record - * @flags: TRACE_RECORD_CMDLINE for recording comm - * TRACE_RECORD_TGID for recording tgid - */ -void tracing_record_taskinfo(struct task_struct *task, int flags) -{ - bool done; - - if (tracing_record_taskinfo_skip(flags)) - return; - - /* - * Record as much task information as possible. If some fail, continue - * to try to record the others. - */ - done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(task); - done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(task); - - /* If recording any information failed, retry again soon. */ - if (!done) - return; - - __this_cpu_write(trace_taskinfo_save, false); -} - -/** - * tracing_record_taskinfo_sched_switch - record task info for sched_switch - * - * @prev: previous task during sched_switch - * @next: next task during sched_switch - * @flags: TRACE_RECORD_CMDLINE for recording comm - * TRACE_RECORD_TGID for recording tgid - */ -void tracing_record_taskinfo_sched_switch(struct task_struct *prev, - struct task_struct *next, int flags) -{ - bool done; - - if (tracing_record_taskinfo_skip(flags)) - return; - - /* - * Record as much task information as possible. If some fail, continue - * to try to record the others. - */ - done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(prev); - done &= !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(next); - done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(prev); - done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(next); - - /* If recording any information failed, retry again soon. */ - if (!done) - return; - - __this_cpu_write(trace_taskinfo_save, false); -} - -/* Helpers to record a specific task information */ -void tracing_record_cmdline(struct task_struct *task) -{ - tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE); -} - -void tracing_record_tgid(struct task_struct *task) -{ - tracing_record_taskinfo(task, TRACE_RECORD_TGID); -} - /* * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function @@ -5453,29 +5167,6 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) return 0; } -static int trace_alloc_tgid_map(void) -{ - int *map; - - if (tgid_map) - return 0; - - tgid_map_max = pid_max; - map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map), - GFP_KERNEL); - if (!map) - return -ENOMEM; - - /* - * Pairs with smp_load_acquire() in - * trace_find_tgid_ptr() to ensure that if it observes - * the tgid_map we just allocated then it also observes - * the corresponding tgid_map_max value. - */ - smp_store_release(&tgid_map, map); - return 0; -} - int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { if ((mask == TRACE_ITER_RECORD_TGID) || @@ -5500,6 +5191,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) trace_event_enable_cmd_record(enabled); if (mask == TRACE_ITER_RECORD_TGID) { + if (trace_alloc_tgid_map() < 0) { tr->trace_flags &= ~TRACE_ITER_RECORD_TGID; return -ENOMEM; @@ -5944,207 +5636,6 @@ static const struct file_operations tracing_readme_fops = { .llseek = generic_file_llseek, }; -static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos) -{ - int pid = ++(*pos); - - return trace_find_tgid_ptr(pid); -} - -static void *saved_tgids_start(struct seq_file *m, loff_t *pos) -{ - int pid = *pos; - - return trace_find_tgid_ptr(pid); -} - -static void saved_tgids_stop(struct seq_file *m, void *v) -{ -} - -static int saved_tgids_show(struct seq_file *m, void *v) -{ - int *entry = (int *)v; - int pid = entry - tgid_map; - int tgid = *entry; - - if (tgid == 0) - return SEQ_SKIP; - - seq_printf(m, "%d %d\n", pid, tgid); - return 0; -} - -static const struct seq_operations tracing_saved_tgids_seq_ops = { - .start = saved_tgids_start, - .stop = saved_tgids_stop, - .next = saved_tgids_next, - .show = saved_tgids_show, -}; - -static int tracing_saved_tgids_open(struct inode *inode, struct file *filp) -{ - int ret; - - ret = tracing_check_open_get_tr(NULL); - if (ret) - return ret; - - return seq_open(filp, &tracing_saved_tgids_seq_ops); -} - - -static const struct file_operations tracing_saved_tgids_fops = { - .open = tracing_saved_tgids_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos) -{ - unsigned int *ptr = v; - - if (*pos || m->count) - ptr++; - - (*pos)++; - - for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num]; - ptr++) { - if (*ptr == -1 || *ptr == NO_CMDLINE_MAP) - continue; - - return ptr; - } - - return NULL; -} - -static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos) -{ - void *v; - loff_t l = 0; - - preempt_disable(); - arch_spin_lock(&trace_cmdline_lock); - - v = &savedcmd->map_cmdline_to_pid[0]; - while (l <= *pos) { - v = saved_cmdlines_next(m, v, &l); - if (!v) - return NULL; - } - - return v; -} - -static void saved_cmdlines_stop(struct seq_file *m, void *v) -{ - arch_spin_unlock(&trace_cmdline_lock); - preempt_enable(); -} - -static int saved_cmdlines_show(struct seq_file *m, void *v) -{ - char buf[TASK_COMM_LEN]; - unsigned int *pid = v; - - __trace_find_cmdline(*pid, buf); - seq_printf(m, "%d %s\n", *pid, buf); - return 0; -} - -static const struct seq_operations tracing_saved_cmdlines_seq_ops = { - .start = saved_cmdlines_start, - .next = saved_cmdlines_next, - .stop = saved_cmdlines_stop, - .show = saved_cmdlines_show, -}; - -static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp) -{ - int ret; - - ret = tracing_check_open_get_tr(NULL); - if (ret) - return ret; - - return seq_open(filp, &tracing_saved_cmdlines_seq_ops); -} - -static const struct file_operations tracing_saved_cmdlines_fops = { - .open = tracing_saved_cmdlines_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static ssize_t -tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - int r; - - preempt_disable(); - arch_spin_lock(&trace_cmdline_lock); - r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num); - arch_spin_unlock(&trace_cmdline_lock); - preempt_enable(); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - -static int tracing_resize_saved_cmdlines(unsigned int val) -{ - struct saved_cmdlines_buffer *s, *savedcmd_temp; - - s = allocate_cmdlines_buffer(val); - if (!s) - return -ENOMEM; - - preempt_disable(); - arch_spin_lock(&trace_cmdline_lock); - savedcmd_temp = savedcmd; - savedcmd = s; - arch_spin_unlock(&trace_cmdline_lock); - preempt_enable(); - free_saved_cmdlines_buffer(savedcmd_temp); - - return 0; -} - -static ssize_t -tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - unsigned long val; - int ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - return ret; - - /* must have at least 1 entry or less than PID_MAX_DEFAULT */ - if (!val || val > PID_MAX_DEFAULT) - return -EINVAL; - - ret = tracing_resize_saved_cmdlines((unsigned int)val); - if (ret < 0) - return ret; - - *ppos += cnt; - - return cnt; -} - -static const struct file_operations tracing_saved_cmdlines_size_fops = { - .open = tracing_open_generic, - .read = tracing_saved_cmdlines_size_read, - .write = tracing_saved_cmdlines_size_write, -}; - #ifdef CONFIG_TRACE_EVAL_MAP_FILE static union trace_eval_map_item * update_eval_map(union trace_eval_map_item *ptr) @@ -10720,7 +10211,7 @@ __init static int tracer_alloc_buffers(void) out_free_pipe_cpumask: free_cpumask_var(global_trace.pipe_cpumask); out_free_savedcmd: - free_saved_cmdlines_buffer(savedcmd); + trace_free_saved_cmdlines_buffer(); out_free_temp_buffer: ring_buffer_free(temp_buffer); out_rm_hp_state: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 00f873910c5d..e4f0714d7a49 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1375,6 +1375,16 @@ static inline void trace_buffer_unlock_commit(struct trace_array *tr, trace_buffer_unlock_commit_regs(tr, buffer, event, trace_ctx, NULL); } +DECLARE_PER_CPU(bool, trace_taskinfo_save); +int trace_save_cmdline(struct task_struct *tsk); +int trace_create_savedcmd(void); +int trace_alloc_tgid_map(void); +void trace_free_saved_cmdlines_buffer(void); + +extern const struct file_operations tracing_saved_cmdlines_fops; +extern const struct file_operations tracing_saved_tgids_fops; +extern const struct file_operations tracing_saved_cmdlines_size_fops; + DECLARE_PER_CPU(struct ring_buffer_event *, trace_buffered_event); DECLARE_PER_CPU(int, trace_buffered_event_cnt); void trace_buffered_event_disable(void); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index c9ffdcfe622e..8a407adb0e1c 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -148,3 +149,517 @@ void tracing_stop_tgid_record(void) { tracing_stop_sched_switch(RECORD_TGID); } + +/* + * The tgid_map array maps from pid to tgid; i.e. the value stored at index i + * is the tgid last observed corresponding to pid=i. + */ +static int *tgid_map; + +/* The maximum valid index into tgid_map. */ +static size_t tgid_map_max; + +#define SAVED_CMDLINES_DEFAULT 128 +#define NO_CMDLINE_MAP UINT_MAX +/* + * Preemption must be disabled before acquiring trace_cmdline_lock. + * The various trace_arrays' max_lock must be acquired in a context + * where interrupt is disabled. + */ +static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; +struct saved_cmdlines_buffer { + unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; + unsigned *map_cmdline_to_pid; + unsigned cmdline_num; + int cmdline_idx; + char saved_cmdlines[]; +}; +static struct saved_cmdlines_buffer *savedcmd; + +/* Holds the size of a cmdline and pid element */ +#define SAVED_CMDLINE_MAP_ELEMENT_SIZE(s) \ + (TASK_COMM_LEN + sizeof((s)->map_cmdline_to_pid[0])) + +static inline char *get_saved_cmdlines(int idx) +{ + return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; +} + +static inline void set_cmdline(int idx, const char *cmdline) +{ + strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); +} + +static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) +{ + int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); + + kmemleak_free(s); + free_pages((unsigned long)s, order); +} + +static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) +{ + struct saved_cmdlines_buffer *s; + struct page *page; + int orig_size, size; + int order; + + /* Figure out how much is needed to hold the given number of cmdlines */ + orig_size = sizeof(*s) + val * SAVED_CMDLINE_MAP_ELEMENT_SIZE(s); + order = get_order(orig_size); + size = 1 << (order + PAGE_SHIFT); + page = alloc_pages(GFP_KERNEL, order); + if (!page) + return NULL; + + s = page_address(page); + kmemleak_alloc(s, size, 1, GFP_KERNEL); + memset(s, 0, sizeof(*s)); + + /* Round up to actual allocation */ + val = (size - sizeof(*s)) / SAVED_CMDLINE_MAP_ELEMENT_SIZE(s); + s->cmdline_num = val; + + /* Place map_cmdline_to_pid array right after saved_cmdlines */ + s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN]; + + s->cmdline_idx = 0; + memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, + sizeof(s->map_pid_to_cmdline)); + memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, + val * sizeof(*s->map_cmdline_to_pid)); + + return s; +} + +int trace_create_savedcmd(void) +{ + savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT); + + return savedcmd ? 0 : -ENOMEM; +} + +int trace_save_cmdline(struct task_struct *tsk) +{ + unsigned tpid, idx; + + /* treat recording of idle task as a success */ + if (!tsk->pid) + return 1; + + tpid = tsk->pid & (PID_MAX_DEFAULT - 1); + + /* + * It's not the end of the world if we don't get + * the lock, but we also don't want to spin + * nor do we want to disable interrupts, + * so if we miss here, then better luck next time. + * + * This is called within the scheduler and wake up, so interrupts + * had better been disabled and run queue lock been held. + */ + lockdep_assert_preemption_disabled(); + if (!arch_spin_trylock(&trace_cmdline_lock)) + return 0; + + idx = savedcmd->map_pid_to_cmdline[tpid]; + if (idx == NO_CMDLINE_MAP) { + idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num; + + savedcmd->map_pid_to_cmdline[tpid] = idx; + savedcmd->cmdline_idx = idx; + } + + savedcmd->map_cmdline_to_pid[idx] = tsk->pid; + set_cmdline(idx, tsk->comm); + + arch_spin_unlock(&trace_cmdline_lock); + + return 1; +} + +static void __trace_find_cmdline(int pid, char comm[]) +{ + unsigned map; + int tpid; + + if (!pid) { + strcpy(comm, ""); + return; + } + + if (WARN_ON_ONCE(pid < 0)) { + strcpy(comm, ""); + return; + } + + tpid = pid & (PID_MAX_DEFAULT - 1); + map = savedcmd->map_pid_to_cmdline[tpid]; + if (map != NO_CMDLINE_MAP) { + tpid = savedcmd->map_cmdline_to_pid[map]; + if (tpid == pid) { + strscpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN); + return; + } + } + strcpy(comm, "<...>"); +} + +void trace_find_cmdline(int pid, char comm[]) +{ + preempt_disable(); + arch_spin_lock(&trace_cmdline_lock); + + __trace_find_cmdline(pid, comm); + + arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); +} + +static int *trace_find_tgid_ptr(int pid) +{ + /* + * Pairs with the smp_store_release in set_tracer_flag() to ensure that + * if we observe a non-NULL tgid_map then we also observe the correct + * tgid_map_max. + */ + int *map = smp_load_acquire(&tgid_map); + + if (unlikely(!map || pid > tgid_map_max)) + return NULL; + + return &map[pid]; +} + +int trace_find_tgid(int pid) +{ + int *ptr = trace_find_tgid_ptr(pid); + + return ptr ? *ptr : 0; +} + +static int trace_save_tgid(struct task_struct *tsk) +{ + int *ptr; + + /* treat recording of idle task as a success */ + if (!tsk->pid) + return 1; + + ptr = trace_find_tgid_ptr(tsk->pid); + if (!ptr) + return 0; + + *ptr = tsk->tgid; + return 1; +} + +static bool tracing_record_taskinfo_skip(int flags) +{ + if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) + return true; + if (!__this_cpu_read(trace_taskinfo_save)) + return true; + return false; +} + +/** + * tracing_record_taskinfo - record the task info of a task + * + * @task: task to record + * @flags: TRACE_RECORD_CMDLINE for recording comm + * TRACE_RECORD_TGID for recording tgid + */ +void tracing_record_taskinfo(struct task_struct *task, int flags) +{ + bool done; + + if (tracing_record_taskinfo_skip(flags)) + return; + + /* + * Record as much task information as possible. If some fail, continue + * to try to record the others. + */ + done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(task); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(task); + + /* If recording any information failed, retry again soon. */ + if (!done) + return; + + __this_cpu_write(trace_taskinfo_save, false); +} + +/** + * tracing_record_taskinfo_sched_switch - record task info for sched_switch + * + * @prev: previous task during sched_switch + * @next: next task during sched_switch + * @flags: TRACE_RECORD_CMDLINE for recording comm + * TRACE_RECORD_TGID for recording tgid + */ +void tracing_record_taskinfo_sched_switch(struct task_struct *prev, + struct task_struct *next, int flags) +{ + bool done; + + if (tracing_record_taskinfo_skip(flags)) + return; + + /* + * Record as much task information as possible. If some fail, continue + * to try to record the others. + */ + done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(prev); + done &= !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(next); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(prev); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(next); + + /* If recording any information failed, retry again soon. */ + if (!done) + return; + + __this_cpu_write(trace_taskinfo_save, false); +} + +/* Helpers to record a specific task information */ +void tracing_record_cmdline(struct task_struct *task) +{ + tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE); +} + +void tracing_record_tgid(struct task_struct *task) +{ + tracing_record_taskinfo(task, TRACE_RECORD_TGID); +} + +int trace_alloc_tgid_map(void) +{ + int *map; + + if (tgid_map) + return 0; + + tgid_map_max = pid_max; + map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map), + GFP_KERNEL); + if (!map) + return -ENOMEM; + + /* + * Pairs with smp_load_acquire() in + * trace_find_tgid_ptr() to ensure that if it observes + * the tgid_map we just allocated then it also observes + * the corresponding tgid_map_max value. + */ + smp_store_release(&tgid_map, map); + return 0; +} + +static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos) +{ + int pid = ++(*pos); + + return trace_find_tgid_ptr(pid); +} + +static void *saved_tgids_start(struct seq_file *m, loff_t *pos) +{ + int pid = *pos; + + return trace_find_tgid_ptr(pid); +} + +static void saved_tgids_stop(struct seq_file *m, void *v) +{ +} + +static int saved_tgids_show(struct seq_file *m, void *v) +{ + int *entry = (int *)v; + int pid = entry - tgid_map; + int tgid = *entry; + + if (tgid == 0) + return SEQ_SKIP; + + seq_printf(m, "%d %d\n", pid, tgid); + return 0; +} + +static const struct seq_operations tracing_saved_tgids_seq_ops = { + .start = saved_tgids_start, + .stop = saved_tgids_stop, + .next = saved_tgids_next, + .show = saved_tgids_show, +}; + +static int tracing_saved_tgids_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; + + return seq_open(filp, &tracing_saved_tgids_seq_ops); +} + + +const struct file_operations tracing_saved_tgids_fops = { + .open = tracing_saved_tgids_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos) +{ + unsigned int *ptr = v; + + if (*pos || m->count) + ptr++; + + (*pos)++; + + for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num]; + ptr++) { + if (*ptr == -1 || *ptr == NO_CMDLINE_MAP) + continue; + + return ptr; + } + + return NULL; +} + +static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos) +{ + void *v; + loff_t l = 0; + + preempt_disable(); + arch_spin_lock(&trace_cmdline_lock); + + v = &savedcmd->map_cmdline_to_pid[0]; + while (l <= *pos) { + v = saved_cmdlines_next(m, v, &l); + if (!v) + return NULL; + } + + return v; +} + +static void saved_cmdlines_stop(struct seq_file *m, void *v) +{ + arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); +} + +static int saved_cmdlines_show(struct seq_file *m, void *v) +{ + char buf[TASK_COMM_LEN]; + unsigned int *pid = v; + + __trace_find_cmdline(*pid, buf); + seq_printf(m, "%d %s\n", *pid, buf); + return 0; +} + +static const struct seq_operations tracing_saved_cmdlines_seq_ops = { + .start = saved_cmdlines_start, + .next = saved_cmdlines_next, + .stop = saved_cmdlines_stop, + .show = saved_cmdlines_show, +}; + +static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; + + return seq_open(filp, &tracing_saved_cmdlines_seq_ops); +} + +const struct file_operations tracing_saved_cmdlines_fops = { + .open = tracing_saved_cmdlines_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static ssize_t +tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + + preempt_disable(); + arch_spin_lock(&trace_cmdline_lock); + r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num); + arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +void trace_free_saved_cmdlines_buffer(void) +{ + free_saved_cmdlines_buffer(savedcmd); +} + +static int tracing_resize_saved_cmdlines(unsigned int val) +{ + struct saved_cmdlines_buffer *s, *savedcmd_temp; + + s = allocate_cmdlines_buffer(val); + if (!s) + return -ENOMEM; + + preempt_disable(); + arch_spin_lock(&trace_cmdline_lock); + savedcmd_temp = savedcmd; + savedcmd = s; + arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); + free_saved_cmdlines_buffer(savedcmd_temp); + + return 0; +} + +static ssize_t +tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + /* must have at least 1 entry or less than PID_MAX_DEFAULT */ + if (!val || val > PID_MAX_DEFAULT) + return -EINVAL; + + ret = tracing_resize_saved_cmdlines((unsigned int)val); + if (ret < 0) + return ret; + + *ppos += cnt; + + return cnt; +} + +const struct file_operations tracing_saved_cmdlines_size_fops = { + .open = tracing_open_generic, + .read = tracing_saved_cmdlines_size_read, + .write = tracing_saved_cmdlines_size_write, +}; -- cgit v1.2.3 From 6b76323e5a483e53568254146c3d141123f3b839 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Tue, 20 Feb 2024 20:23:05 +0000 Subject: ring-buffer: Zero ring-buffer sub-buffers In preparation for the ring-buffer memory mapping where each subbuf will be accessible to user-space, zero all the page allocations. Link: https://lore.kernel.org/linux-trace-kernel/20240220202310.2489614-2-vdonnefort@google.com Signed-off-by: Vincent Donnefort Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 09df645ab9c7..67d32af48640 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1515,7 +1515,8 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, list_add(&bpage->list, pages); - page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, + page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), + mflags | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) goto free_pages; @@ -1600,7 +1601,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) cpu_buffer->reader_page = bpage; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order); + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_ZERO, + cpu_buffer->buffer->subbuf_order); if (!page) goto fail_free_reader; bpage->page = page_address(page); @@ -5568,7 +5570,8 @@ ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) if (bpage->data) goto out; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, + page = alloc_pages_node(cpu_to_node(cpu), + GFP_KERNEL | __GFP_NORETRY | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) { kfree(bpage); -- cgit v1.2.3 From f1e30cb6369251c03f63c564006f96a54197dcc4 Mon Sep 17 00:00:00 2001 From: linke li Date: Sat, 2 Mar 2024 12:42:21 +0800 Subject: ring-buffer: use READ_ONCE() to read cpu_buffer->commit_page in concurrent environment In function ring_buffer_iter_empty(), cpu_buffer->commit_page is read while other threads may change it. It may cause the time_stamp that read in the next line come from a different page. Use READ_ONCE() to avoid having to reason about compiler optimizations now and in future. Link: https://lore.kernel.org/linux-trace-kernel/tencent_DFF7D3561A0686B5E8FC079150A02505180A@qq.com Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Signed-off-by: linke li Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 67d32af48640..788d321036bd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4382,7 +4382,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; - commit_page = cpu_buffer->commit_page; + commit_page = READ_ONCE(cpu_buffer->commit_page); commit_ts = commit_page->page->time_stamp; /* -- cgit v1.2.3 From b70f2938242a028f8e9473781ede175486a59dc8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Fri, 15 Mar 2024 06:31:15 -0400 Subject: ring-buffer: Make wake once of ring_buffer_wait() more robust The default behavior of ring_buffer_wait() when passed a NULL "cond" parameter is to exit the function the first time it is woken up. The current implementation uses a counter that starts at zero and when it is greater than one it exits the wait_event_interruptible(). But this relies on the internal working of wait_event_interruptible() as that code basically has: if (cond) return; prepare_to_wait(); if (!cond) schedule(); finish_wait(); That is, cond is called twice before it sleeps. The default cond of ring_buffer_wait() needs to account for that and wait for its counter to increment twice before exiting. Instead, use the seq/atomic_inc logic that is used by the tracing code that calls this function. Add an atomic_t seq to rb_irq_work and when cond is NULL, have the default callback take a descriptor as its data that holds the rbwork and the value of the seq when it started. The wakeups will now increment the rbwork->seq and the cond callback will simply check if that number is different, and no longer have to rely on the implementation of wait_event_interruptible(). Link: https://lore.kernel.org/linux-trace-kernel/20240315063115.6cb5d205@gandalf.local.home Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Fixes: 7af9ded0c2ca ("ring-buffer: Use wait_event_interruptible() in ring_buffer_wait()") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 788d321036bd..25476ead681b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -384,6 +384,7 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; + atomic_t seq; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -753,6 +754,9 @@ static void rb_wake_up_waiters(struct irq_work *work) { struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); + /* For waiters waiting for the first wake up */ + (void)atomic_fetch_inc_release(&rbwork->seq); + wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { /* Only cpu_buffer sets the above flags */ @@ -881,20 +885,21 @@ rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer, return false; } +struct rb_wait_data { + struct rb_irq_work *irq_work; + int seq; +}; + /* * The default wait condition for ring_buffer_wait() is to just to exit the * wait loop the first time it is woken up. */ static bool rb_wait_once(void *data) { - long *once = data; + struct rb_wait_data *rdata = data; + struct rb_irq_work *rbwork = rdata->irq_work; - /* wait_event() actually calls this twice before scheduling*/ - if (*once > 1) - return true; - - (*once)++; - return false; + return atomic_read_acquire(&rbwork->seq) != rdata->seq; } /** @@ -915,14 +920,9 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, struct ring_buffer_per_cpu *cpu_buffer; struct wait_queue_head *waitq; struct rb_irq_work *rbwork; - long once = 0; + struct rb_wait_data rdata; int ret = 0; - if (!cond) { - cond = rb_wait_once; - data = &once; - } - /* * Depending on what the caller is waiting for, either any * data in any cpu buffer, or a specific buffer, put the @@ -944,6 +944,14 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, else waitq = &rbwork->waiters; + /* Set up to exit loop as soon as it is woken */ + if (!cond) { + cond = rb_wait_once; + rdata.irq_work = rbwork; + rdata.seq = atomic_read_acquire(&rbwork->seq); + data = &rdata; + } + ret = wait_event_interruptible((*waitq), rb_wait_cond(rbwork, buffer, cpu, full, cond, data)); -- cgit v1.2.3 From 180e4e390978af9d0cc060e87920c462276453b9 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Tue, 20 Feb 2024 20:23:07 +0000 Subject: tracing: Add snapshot refcount When a ring-buffer is memory mapped by user-space, no trace or ring-buffer swap is possible. This means the snapshot feature is mutually exclusive with the memory mapping. Having a refcount on snapshot users will help to know if a mapping is possible or not. Instead of relying on the global trace_types_lock, a new spinlock is introduced to serialize accesses to trace_array->snapshot. This intends to allow access to that variable in a context where the mmap lock is already held. Link: https://lore.kernel.org/linux-trace-kernel/20240220202310.2489614-4-vdonnefort@google.com Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 99 ++++++++++++++++++++++++++++++------- kernel/trace/trace.h | 8 ++- kernel/trace/trace_events_trigger.c | 58 +++++++++++++++------- 3 files changed, 129 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1e5f80cda39a..c66ca2f6944e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1300,6 +1300,50 @@ static void free_snapshot(struct trace_array *tr) tr->allocated_snapshot = false; } +static int tracing_arm_snapshot_locked(struct trace_array *tr) +{ + int ret; + + lockdep_assert_held(&trace_types_lock); + + spin_lock(&tr->snapshot_trigger_lock); + if (tr->snapshot == UINT_MAX) { + spin_unlock(&tr->snapshot_trigger_lock); + return -EBUSY; + } + + tr->snapshot++; + spin_unlock(&tr->snapshot_trigger_lock); + + ret = tracing_alloc_snapshot_instance(tr); + if (ret) { + spin_lock(&tr->snapshot_trigger_lock); + tr->snapshot--; + spin_unlock(&tr->snapshot_trigger_lock); + } + + return ret; +} + +int tracing_arm_snapshot(struct trace_array *tr) +{ + int ret; + + mutex_lock(&trace_types_lock); + ret = tracing_arm_snapshot_locked(tr); + mutex_unlock(&trace_types_lock); + + return ret; +} + +void tracing_disarm_snapshot(struct trace_array *tr) +{ + spin_lock(&tr->snapshot_trigger_lock); + if (!WARN_ON(!tr->snapshot)) + tr->snapshot--; + spin_unlock(&tr->snapshot_trigger_lock); +} + /** * tracing_alloc_snapshot - allocate snapshot buffer. * @@ -1373,10 +1417,6 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, mutex_lock(&trace_types_lock); - ret = tracing_alloc_snapshot_instance(tr); - if (ret) - goto fail_unlock; - if (tr->current_trace->use_max_tr) { ret = -EBUSY; goto fail_unlock; @@ -1395,6 +1435,10 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, goto fail_unlock; } + ret = tracing_arm_snapshot_locked(tr); + if (ret) + goto fail_unlock; + local_irq_disable(); arch_spin_lock(&tr->max_lock); tr->cond_snapshot = cond_snapshot; @@ -1439,6 +1483,8 @@ int tracing_snapshot_cond_disable(struct trace_array *tr) arch_spin_unlock(&tr->max_lock); local_irq_enable(); + tracing_disarm_snapshot(tr); + return ret; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); @@ -1481,6 +1527,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr) } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); #define free_snapshot(tr) do { } while (0) +#define tracing_arm_snapshot_locked(tr) ({ -EBUSY; }) #endif /* CONFIG_TRACER_SNAPSHOT */ void tracer_tracing_off(struct trace_array *tr) @@ -6112,11 +6159,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) */ synchronize_rcu(); free_snapshot(tr); + tracing_disarm_snapshot(tr); } - if (t->use_max_tr && !tr->allocated_snapshot) { - ret = tracing_alloc_snapshot_instance(tr); - if (ret < 0) + if (t->use_max_tr) { + ret = tracing_arm_snapshot_locked(tr); + if (ret) goto out; } #else @@ -6125,8 +6173,13 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (t->init) { ret = tracer_init(t, tr); - if (ret) + if (ret) { +#ifdef CONFIG_TRACER_MAX_TRACE + if (t->use_max_tr) + tracing_disarm_snapshot(tr); +#endif goto out; + } } tr->current_trace = t; @@ -7228,10 +7281,11 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, if (tr->allocated_snapshot) ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->array_buffer, iter->cpu_file); - else - ret = tracing_alloc_snapshot_instance(tr); - if (ret < 0) + + ret = tracing_arm_snapshot_locked(tr); + if (ret) break; + /* Now, we're going to swap */ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { local_irq_disable(); @@ -7241,6 +7295,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer, (void *)tr, 1); } + tracing_disarm_snapshot(tr); break; default: if (tr->allocated_snapshot) { @@ -8372,8 +8427,13 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; - if (glob[0] == '!') - return unregister_ftrace_function_probe_func(glob+1, tr, ops); + if (glob[0] == '!') { + ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); + if (!ret) + tracing_disarm_snapshot(tr); + + return ret; + } if (!param) goto out_reg; @@ -8392,12 +8452,13 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, return ret; out_reg: - ret = tracing_alloc_snapshot_instance(tr); + ret = tracing_arm_snapshot(tr); if (ret < 0) goto out; ret = register_ftrace_function_probe(glob, tr, ops, count); - + if (ret < 0) + tracing_disarm_snapshot(tr); out: return ret < 0 ? ret : 0; } @@ -9204,7 +9265,9 @@ trace_array_create_systems(const char *name, const char *systems) raw_spin_lock_init(&tr->start_lock); tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; - +#ifdef CONFIG_TRACER_MAX_TRACE + spin_lock_init(&tr->snapshot_trigger_lock); +#endif tr->current_trace = &nop_trace; INIT_LIST_HEAD(&tr->systems); @@ -10174,7 +10237,9 @@ __init static int tracer_alloc_buffers(void) global_trace.current_trace = &nop_trace; global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; - +#ifdef CONFIG_TRACER_MAX_TRACE + spin_lock_init(&global_trace.snapshot_trigger_lock); +#endif ftrace_init_global_array_ops(&global_trace); init_trace_flags_index(&global_trace); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e4f0714d7a49..64450615ca0c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -334,8 +334,8 @@ struct trace_array { */ struct array_buffer max_buffer; bool allocated_snapshot; -#endif -#ifdef CONFIG_TRACER_MAX_TRACE + spinlock_t snapshot_trigger_lock; + unsigned int snapshot; unsigned long max_latency; #ifdef CONFIG_FSNOTIFY struct dentry *d_max_latency; @@ -1983,12 +1983,16 @@ static inline void trace_event_eval_update(struct trace_eval_map **map, int len) #ifdef CONFIG_TRACER_SNAPSHOT void tracing_snapshot_instance(struct trace_array *tr); int tracing_alloc_snapshot_instance(struct trace_array *tr); +int tracing_arm_snapshot(struct trace_array *tr); +void tracing_disarm_snapshot(struct trace_array *tr); #else static inline void tracing_snapshot_instance(struct trace_array *tr) { } static inline int tracing_alloc_snapshot_instance(struct trace_array *tr) { return 0; } +static inline int tracing_arm_snapshot(struct trace_array *tr) { return 0; } +static inline void tracing_disarm_snapshot(struct trace_array *tr) { } #endif #ifdef CONFIG_PREEMPT_TRACER diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index b33c3861fbbb..62e4f58b8671 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -597,20 +597,12 @@ out: return ret; } -/** - * unregister_trigger - Generic event_command @unreg implementation - * @glob: The raw string used to register the trigger - * @test: Trigger-specific data used to find the trigger to remove - * @file: The trace_event_file associated with the event - * - * Common implementation for event trigger unregistration. - * - * Usually used directly as the @unreg method in event command - * implementations. +/* + * True if the trigger was found and unregistered, else false. */ -static void unregister_trigger(char *glob, - struct event_trigger_data *test, - struct trace_event_file *file) +static bool try_unregister_trigger(char *glob, + struct event_trigger_data *test, + struct trace_event_file *file) { struct event_trigger_data *data = NULL, *iter; @@ -626,8 +618,32 @@ static void unregister_trigger(char *glob, } } - if (data && data->ops->free) - data->ops->free(data); + if (data) { + if (data->ops->free) + data->ops->free(data); + + return true; + } + + return false; +} + +/** + * unregister_trigger - Generic event_command @unreg implementation + * @glob: The raw string used to register the trigger + * @test: Trigger-specific data used to find the trigger to remove + * @file: The trace_event_file associated with the event + * + * Common implementation for event trigger unregistration. + * + * Usually used directly as the @unreg method in event command + * implementations. + */ +static void unregister_trigger(char *glob, + struct event_trigger_data *test, + struct trace_event_file *file) +{ + try_unregister_trigger(glob, test, file); } /* @@ -1470,7 +1486,7 @@ register_snapshot_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { - int ret = tracing_alloc_snapshot_instance(file->tr); + int ret = tracing_arm_snapshot(file->tr); if (ret < 0) return ret; @@ -1478,6 +1494,14 @@ register_snapshot_trigger(char *glob, return register_trigger(glob, data, file); } +static void unregister_snapshot_trigger(char *glob, + struct event_trigger_data *data, + struct trace_event_file *file) +{ + if (try_unregister_trigger(glob, data, file)) + tracing_disarm_snapshot(file->tr); +} + static int snapshot_trigger_print(struct seq_file *m, struct event_trigger_data *data) { @@ -1510,7 +1534,7 @@ static struct event_command trigger_snapshot_cmd = { .trigger_type = ETT_SNAPSHOT, .parse = event_trigger_parse, .reg = register_snapshot_trigger, - .unreg = unregister_trigger, + .unreg = unregister_snapshot_trigger, .get_trigger_ops = snapshot_get_trigger_ops, .set_filter = set_trigger_filter, }; -- cgit v1.2.3 From 1e953de9e9b4ca77a9ce0fc17a0778eba3a4ca64 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Thu, 22 Feb 2024 00:18:04 +0000 Subject: tracing/user_events: Prepare find/delete for same name events The current code for finding and deleting events assumes that there will never be cases when user_events are registered with the same name, but different formats. Scenarios exist where programs want to use the same name but have different formats. An example is multiple versions of a program running side-by-side using the same event name, but with updated formats in each version. This change does not yet allow for multi-format events. If user_events are registered with the same name but different arguments the programs see the same return values as before. This change simply makes it possible to easily accommodate for this. Update find_user_event() to take in argument parameters and register flags to accommodate future multi-format event scenarios. Have find validate argument matching and return error pointers to cover when an existing event has the same name but different format. Update callers to handle error pointer logic. Move delete_user_event() to use hash walking directly now that find_user_event() has changed. Delete all events found that match the register name, stop if an error occurs and report back to the user. Update user_fields_match() to cover list_empty() scenarios now that find_user_event() uses it directly. This makes the logic consistent across several callsites. Link: https://lore.kernel.org/linux-trace-kernel/20240222001807.1463-2-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 107 +++++++++++++++++++++------------------ 1 file changed, 59 insertions(+), 48 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index e76f5e1efdf2..fce5ed5fec50 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -202,6 +202,8 @@ static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm); static struct user_event_mm *user_event_mm_get_all(struct user_event *user); static void user_event_mm_put(struct user_event_mm *mm); static int destroy_user_event(struct user_event *user); +static bool user_fields_match(struct user_event *user, int argc, + const char **argv); static u32 user_event_key(char *name) { @@ -1493,17 +1495,24 @@ static int destroy_user_event(struct user_event *user) } static struct user_event *find_user_event(struct user_event_group *group, - char *name, u32 *outkey) + char *name, int argc, const char **argv, + u32 flags, u32 *outkey) { struct user_event *user; u32 key = user_event_key(name); *outkey = key; - hash_for_each_possible(group->register_table, user, node, key) - if (!strcmp(EVENT_NAME(user), name)) + hash_for_each_possible(group->register_table, user, node, key) { + if (strcmp(EVENT_NAME(user), name)) + continue; + + if (user_fields_match(user, argc, argv)) return user_event_get(user); + return ERR_PTR(-EADDRINUSE); + } + return NULL; } @@ -1860,6 +1869,9 @@ static bool user_fields_match(struct user_event *user, int argc, struct list_head *head = &user->fields; int i = 0; + if (argc == 0) + return list_empty(head); + list_for_each_entry_reverse(field, head, link) { if (!user_field_match(field, argc, argv, &i)) return false; @@ -1880,10 +1892,8 @@ static bool user_event_match(const char *system, const char *event, match = strcmp(EVENT_NAME(user), event) == 0 && (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0); - if (match && argc > 0) + if (match) match = user_fields_match(user, argc, argv); - else if (match && argc == 0) - match = list_empty(&user->fields); return match; } @@ -1922,11 +1932,11 @@ static int user_event_parse(struct user_event_group *group, char *name, char *args, char *flags, struct user_event **newuser, int reg_flags) { - int ret; - u32 key; struct user_event *user; + char **argv = NULL; int argc = 0; - char **argv; + int ret; + u32 key; /* Currently don't support any text based flags */ if (flags != NULL) @@ -1935,41 +1945,34 @@ static int user_event_parse(struct user_event_group *group, char *name, if (!user_event_capable(reg_flags)) return -EPERM; + if (args) { + argv = argv_split(GFP_KERNEL, args, &argc); + + if (!argv) + return -ENOMEM; + } + /* Prevent dyn_event from racing */ mutex_lock(&event_mutex); - user = find_user_event(group, name, &key); + user = find_user_event(group, name, argc, (const char **)argv, + reg_flags, &key); mutex_unlock(&event_mutex); - if (user) { - if (args) { - argv = argv_split(GFP_KERNEL, args, &argc); - if (!argv) { - ret = -ENOMEM; - goto error; - } + if (argv) + argv_free(argv); - ret = user_fields_match(user, argc, (const char **)argv); - argv_free(argv); - - } else - ret = list_empty(&user->fields); - - if (ret) { - *newuser = user; - /* - * Name is allocated by caller, free it since it already exists. - * Caller only worries about failure cases for freeing. - */ - kfree(name); - } else { - ret = -EADDRINUSE; - goto error; - } + if (IS_ERR(user)) + return PTR_ERR(user); + + if (user) { + *newuser = user; + /* + * Name is allocated by caller, free it since it already exists. + * Caller only worries about failure cases for freeing. + */ + kfree(name); return 0; -error: - user_event_put(user, false); - return ret; } user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT); @@ -2052,25 +2055,33 @@ put_user: } /* - * Deletes a previously created event if it is no longer being used. + * Deletes previously created events if they are no longer being used. */ static int delete_user_event(struct user_event_group *group, char *name) { - u32 key; - struct user_event *user = find_user_event(group, name, &key); + struct user_event *user; + struct hlist_node *tmp; + u32 key = user_event_key(name); + int ret = -ENOENT; - if (!user) - return -ENOENT; + /* Attempt to delete all event(s) with the name passed in */ + hash_for_each_possible_safe(group->register_table, user, tmp, node, key) { + if (strcmp(EVENT_NAME(user), name)) + continue; - user_event_put(user, true); + if (!user_event_last_ref(user)) + return -EBUSY; - if (!user_event_last_ref(user)) - return -EBUSY; + if (!user_event_capable(user->reg_flags)) + return -EPERM; - if (!user_event_capable(user->reg_flags)) - return -EPERM; + ret = destroy_user_event(user); - return destroy_user_event(user); + if (ret) + goto out; + } +out: + return ret; } /* -- cgit v1.2.3 From 64805e4039f1687b9857034123a9ec10bb9abddd Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Thu, 22 Feb 2024 00:18:05 +0000 Subject: tracing/user_events: Introduce multi-format events Currently user_events supports 1 event with the same name and must have the exact same format when referenced by multiple programs. This opens an opportunity for malicious or poorly thought through programs to create events that others use with different formats. Another scenario is user programs wishing to use the same event name but add more fields later when the software updates. Various versions of a program may be running side-by-side, which is prevented by the current single format requirement. Add a new register flag (USER_EVENT_REG_MULTI_FORMAT) which indicates the user program wishes to use the same user_event name, but may have several different formats of the event. When this flag is used, create the underlying tracepoint backing the user_event with a unique name per-version of the format. It's important that existing ABI users do not get this logic automatically, even if one of the multi format events matches the format. This ensures existing programs that create events and assume the tracepoint name will match exactly continue to work as expected. Add logic to only check multi-format events with other multi-format events and single-format events to only check single-format events during find. Change system name of the multi-format event tracepoint to ensure that multi-format events are isolated completely from single-format events. This prevents single-format names from conflicting with multi-format events if they end with the same suffix as the multi-format events. Add a register_name (reg_name) to the user_event struct which allows for split naming of events. We now have the name that was used to register within user_events as well as the unique name for the tracepoint. Upon registering events ensure matches based on first the reg_name, followed by the fields and format of the event. This allows for multiple events with the same registered name to have different formats. The underlying tracepoint will have a unique name in the format of {reg_name}.{unique_id}. For example, if both "test u32 value" and "test u64 value" are used with the USER_EVENT_REG_MULTI_FORMAT the system would have 2 unique tracepoints. The dynamic_events file would then show the following: u:test u64 count u:test u32 count The actual tracepoint names look like this: test.0 test.1 Both would be under the new user_events_multi system name to prevent the older ABI from being used to squat on multi-formatted events and block their use. Deleting events via "!u:test u64 count" would only delete the first tracepoint that matched that format. When the delete ABI is used all events with the same name will be attempted to be deleted. If per-version deletion is required, user programs should either not use persistent events or delete them via dynamic_events. Link: https://lore.kernel.org/linux-trace-kernel/20240222001807.1463-3-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/user_events.h | 6 ++- kernel/trace/trace_events_user.c | 102 ++++++++++++++++++++++++++++++++++----- 2 files changed, 95 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h index f74f3aedd49c..a03de03dccbc 100644 --- a/include/uapi/linux/user_events.h +++ b/include/uapi/linux/user_events.h @@ -12,6 +12,7 @@ #include #define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_MULTI_SYSTEM "user_events_multi" #define USER_EVENTS_PREFIX "u:" /* Create dynamic location entry within a 32-bit value */ @@ -22,8 +23,11 @@ enum user_reg_flag { /* Event will not delete upon last reference closing */ USER_EVENT_REG_PERSIST = 1U << 0, + /* Event will be allowed to have multiple formats */ + USER_EVENT_REG_MULTI_FORMAT = 1U << 1, + /* This value or above is currently non-ABI */ - USER_EVENT_REG_MAX = 1U << 1, + USER_EVENT_REG_MAX = 1U << 2, }; /* diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index fce5ed5fec50..70d428c394b6 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -34,7 +34,8 @@ /* Limit how long of an event name plus args within the subsystem. */ #define MAX_EVENT_DESC 512 -#define EVENT_NAME(user_event) ((user_event)->tracepoint.name) +#define EVENT_NAME(user_event) ((user_event)->reg_name) +#define EVENT_TP_NAME(user_event) ((user_event)->tracepoint.name) #define MAX_FIELD_ARRAY_SIZE 1024 /* @@ -54,10 +55,13 @@ * allows isolation for events by various means. */ struct user_event_group { - char *system_name; - struct hlist_node node; - struct mutex reg_mutex; + char *system_name; + char *system_multi_name; + struct hlist_node node; + struct mutex reg_mutex; DECLARE_HASHTABLE(register_table, 8); + /* ID that moves forward within the group for multi-event names */ + u64 multi_id; }; /* Group for init_user_ns mapping, top-most group */ @@ -78,6 +82,7 @@ static unsigned int current_user_events; */ struct user_event { struct user_event_group *group; + char *reg_name; struct tracepoint tracepoint; struct trace_event_call call; struct trace_event_class class; @@ -127,6 +132,8 @@ struct user_event_enabler { #define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK)) +#define EVENT_MULTI_FORMAT(f) ((f) & USER_EVENT_REG_MULTI_FORMAT) + /* Used for asynchronous faulting in of pages */ struct user_event_enabler_fault { struct work_struct work; @@ -330,6 +337,7 @@ out: static void user_event_group_destroy(struct user_event_group *group) { kfree(group->system_name); + kfree(group->system_multi_name); kfree(group); } @@ -348,6 +356,11 @@ static char *user_event_group_system_name(void) return system_name; } +static char *user_event_group_system_multi_name(void) +{ + return kstrdup(USER_EVENTS_MULTI_SYSTEM, GFP_KERNEL); +} + static struct user_event_group *current_user_event_group(void) { return init_group; @@ -367,6 +380,11 @@ static struct user_event_group *user_event_group_create(void) if (!group->system_name) goto error; + group->system_multi_name = user_event_group_system_multi_name(); + + if (!group->system_multi_name) + goto error; + mutex_init(&group->reg_mutex); hash_init(group->register_table); @@ -1482,6 +1500,11 @@ static int destroy_user_event(struct user_event *user) hash_del(&user->node); user_event_destroy_validators(user); + + /* If we have different names, both must be freed */ + if (EVENT_NAME(user) != EVENT_TP_NAME(user)) + kfree(EVENT_TP_NAME(user)); + kfree(user->call.print_fmt); kfree(EVENT_NAME(user)); kfree(user); @@ -1504,12 +1527,24 @@ static struct user_event *find_user_event(struct user_event_group *group, *outkey = key; hash_for_each_possible(group->register_table, user, node, key) { + /* + * Single-format events shouldn't return multi-format + * events. Callers expect the underlying tracepoint to match + * the name exactly in these cases. Only check like-formats. + */ + if (EVENT_MULTI_FORMAT(flags) != EVENT_MULTI_FORMAT(user->reg_flags)) + continue; + if (strcmp(EVENT_NAME(user), name)) continue; if (user_fields_match(user, argc, argv)) return user_event_get(user); + /* Scan others if this is a multi-format event */ + if (EVENT_MULTI_FORMAT(flags)) + continue; + return ERR_PTR(-EADDRINUSE); } @@ -1889,8 +1924,12 @@ static bool user_event_match(const char *system, const char *event, struct user_event *user = container_of(ev, struct user_event, devent); bool match; - match = strcmp(EVENT_NAME(user), event) == 0 && - (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0); + match = strcmp(EVENT_NAME(user), event) == 0; + + if (match && system) { + match = strcmp(system, user->group->system_name) == 0 || + strcmp(system, user->group->system_multi_name) == 0; + } if (match) match = user_fields_match(user, argc, argv); @@ -1923,6 +1962,33 @@ static int user_event_trace_register(struct user_event *user) return ret; } +static int user_event_set_tp_name(struct user_event *user) +{ + lockdep_assert_held(&user->group->reg_mutex); + + if (EVENT_MULTI_FORMAT(user->reg_flags)) { + char *multi_name; + + multi_name = kasprintf(GFP_KERNEL_ACCOUNT, "%s.%llx", + user->reg_name, user->group->multi_id); + + if (!multi_name) + return -ENOMEM; + + user->call.name = multi_name; + user->tracepoint.name = multi_name; + + /* Inc to ensure unique multi-event name next time */ + user->group->multi_id++; + } else { + /* Non Multi-format uses register name */ + user->call.name = user->reg_name; + user->tracepoint.name = user->reg_name; + } + + return 0; +} + /* * Parses the event name, arguments and flags then registers if successful. * The name buffer lifetime is owned by this method for success cases only. @@ -1985,7 +2051,13 @@ static int user_event_parse(struct user_event_group *group, char *name, INIT_LIST_HEAD(&user->validators); user->group = group; - user->tracepoint.name = name; + user->reg_name = name; + user->reg_flags = reg_flags; + + ret = user_event_set_tp_name(user); + + if (ret) + goto put_user; ret = user_event_parse_fields(user, args); @@ -1999,11 +2071,14 @@ static int user_event_parse(struct user_event_group *group, char *name, user->call.data = user; user->call.class = &user->class; - user->call.name = name; user->call.flags = TRACE_EVENT_FL_TRACEPOINT; user->call.tp = &user->tracepoint; user->call.event.funcs = &user_event_funcs; - user->class.system = group->system_name; + + if (EVENT_MULTI_FORMAT(user->reg_flags)) + user->class.system = group->system_multi_name; + else + user->class.system = group->system_name; user->class.fields_array = user_event_fields_array; user->class.get_fields = user_event_get_fields; @@ -2025,8 +2100,6 @@ static int user_event_parse(struct user_event_group *group, char *name, if (ret) goto put_user_lock; - user->reg_flags = reg_flags; - if (user->reg_flags & USER_EVENT_REG_PERSIST) { /* Ensure we track self ref and caller ref (2) */ refcount_set(&user->refcnt, 2); @@ -2050,6 +2123,11 @@ put_user: user_event_destroy_fields(user); user_event_destroy_validators(user); kfree(user->call.print_fmt); + + /* Caller frees reg_name on error, but not multi-name */ + if (EVENT_NAME(user) != EVENT_TP_NAME(user)) + kfree(EVENT_TP_NAME(user)); + kfree(user); return ret; } @@ -2639,7 +2717,7 @@ static int user_seq_show(struct seq_file *m, void *p) hash_for_each(group->register_table, i, user, node) { status = user->status; - seq_printf(m, "%s", EVENT_NAME(user)); + seq_printf(m, "%s", EVENT_TP_NAME(user)); if (status != 0) seq_puts(m, " #"); -- cgit v1.2.3 From ed89683763a12e8289cce6f233dd07b4eb42fb96 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 22 Feb 2024 12:46:39 +0000 Subject: tracing: Use init_utsname()->release Instead of using UTS_RELEASE, use init_utsname()->release, which means that we don't need to rebuild the code just for the git head commit changing. Link: https://lore.kernel.org/linux-trace-kernel/20240222124639.65629-1-john.g.garry@oracle.com Signed-off-by: John Garry Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c66ca2f6944e..a7c0dc0aaf14 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -13,7 +13,7 @@ * Copyright (C) 2004 Nadia Yvette Chambers */ #include -#include +#include #include #include #include @@ -4148,7 +4148,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) get_total_entries(buf, &total, &entries); seq_printf(m, "# %s latency trace v1.1.5 on %s\n", - name, UTS_RELEASE); + name, init_utsname()->release); seq_puts(m, "# -----------------------------------" "---------------------------------\n"); seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |" -- cgit v1.2.3 From cca990c7b565af0dc61a8f647c00833453cf5bff Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Thu, 22 Feb 2024 20:33:24 -0500 Subject: tracing: Fix snapshot counter going between two tracers that use it Running the ftrace selftests caused the ring buffer mapping test to fail. Investigating, I found that the snapshot counter would be incremented every time a tracer that uses the snapshot is enabled even if the snapshot was used by the previous tracer. That is: # cd /sys/kernel/tracing # echo wakeup_rt > current_tracer # echo wakeup_dl > current_tracer # echo nop > current_tracer would leave the snapshot counter at 1 and not zero. That's because the enabling of wakeup_dl would increment the counter again but the setting the tracer to nop would only decrement it once. Do not arm the snapshot for a tracer if the previous tracer already had it armed. Link: https://lore.kernel.org/linux-trace-kernel/20240223013344.570525723@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Vincent Donnefort Fixes: 16f7e48ffc53a ("tracing: Add snapshot refcount") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a7c0dc0aaf14..1e1fd377a1cf 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6162,7 +6162,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) tracing_disarm_snapshot(tr); } - if (t->use_max_tr) { + if (!had_max_tr && t->use_max_tr) { ret = tracing_arm_snapshot_locked(tr); if (ret) goto out; -- cgit v1.2.3 From 2048fdc27525c6b32c63f8429d9335b7fd2f90c2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Thu, 22 Feb 2024 20:33:25 -0500 Subject: tracing: Decrement the snapshot if the snapshot trigger fails to register Running the ftrace selftests caused the ring buffer mapping test to fail. Investigating, I found that the snapshot counter would be incremented every time a snapshot trigger was added, even if that snapshot trigger failed. # cd /sys/kernel/tracing # echo "snapshot" > events/sched/sched_process_fork/trigger # echo "snapshot" > events/sched/sched_process_fork/trigger -bash: echo: write error: File exists That second one that fails increments the snapshot counter but doesn't decrement it. It needs to be decremented when the snapshot fails. Link: https://lore.kernel.org/linux-trace-kernel/20240223013344.729055907@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Vincent Donnefort Fixes: 16f7e48ffc53a ("tracing: Add snapshot refcount") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_trigger.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 62e4f58b8671..4bec043c8690 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1491,7 +1491,10 @@ register_snapshot_trigger(char *glob, if (ret < 0) return ret; - return register_trigger(glob, data, file); + ret = register_trigger(glob, data, file); + if (ret < 0) + tracing_disarm_snapshot(file->tr); + return ret; } static void unregister_snapshot_trigger(char *glob, -- cgit v1.2.3 From d15304135c7f6cbcbf9e6e37814de495a56d51f8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 22 Feb 2024 21:48:33 -0800 Subject: ftrace: Fix most kernel-doc warnings Reduce the number of kernel-doc warnings from 52 down to 10, i.e., fix 42 kernel-doc warnings by (a) using the Returns: format for function return values or (b) using "@var:" instead of "@var -" for function parameter descriptions. Fix one return values list so that it is formatted correctly when rendered for output. Spell "non-zero" with a hyphen in several places. Link: https://lore.kernel.org/linux-trace-kernel/20240223054833.15471-1-rdunlap@infradead.org Cc: Mathieu Desnoyers Cc: Mark Rutland Link: https://lore.kernel.org/oe-kbuild-all/202312180518.X6fRyDSN-lkp@intel.com/ Reported-by: kernel test robot Acked-by: Masami Hiramatsu (Google) Signed-off-by: Randy Dunlap Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 90 ++++++++++++++++++++++++++------------------------- 1 file changed, 46 insertions(+), 44 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 83ba342aef31..da1710499698 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1160,7 +1160,7 @@ __ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) * Search a given @hash to see if a given instruction pointer (@ip) * exists in it. * - * Returns the entry that holds the @ip if found. NULL otherwise. + * Returns: the entry that holds the @ip if found. NULL otherwise. */ struct ftrace_func_entry * ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) @@ -1282,7 +1282,7 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) /** * ftrace_free_filter - remove all filters for an ftrace_ops - * @ops - the ops to remove the filters from + * @ops: the ops to remove the filters from */ void ftrace_free_filter(struct ftrace_ops *ops) { @@ -1587,7 +1587,7 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) * @end: end of range to search (inclusive). @end points to the last byte * to check. * - * Returns rec->ip if the related ftrace location is a least partly within + * Returns: rec->ip if the related ftrace location is a least partly within * the given address range. That is, the first address of the instruction * that is either a NOP or call to the function tracer. It checks the ftrace * internal tables to determine if the address belongs or not. @@ -1607,9 +1607,10 @@ unsigned long ftrace_location_range(unsigned long start, unsigned long end) * ftrace_location - return the ftrace location * @ip: the instruction pointer to check * - * If @ip matches the ftrace location, return @ip. - * If @ip matches sym+0, return sym's ftrace location. - * Otherwise, return 0. + * Returns: + * * If @ip matches the ftrace location, return @ip. + * * If @ip matches sym+0, return sym's ftrace location. + * * Otherwise, return 0. */ unsigned long ftrace_location(unsigned long ip) { @@ -1639,7 +1640,7 @@ out: * @start: start of range to search * @end: end of range to search (inclusive). @end points to the last byte to check. * - * Returns 1 if @start and @end contains a ftrace location. + * Returns: 1 if @start and @end contains a ftrace location. * That is, the instruction that is either a NOP or call to * the function tracer. It checks the ftrace internal tables to * determine if the address belongs or not. @@ -2574,7 +2575,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip, * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS * is not set, then it wants to convert to the normal callback. * - * Returns the address of the trampoline to set to + * Returns: the address of the trampoline to set to */ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) { @@ -2615,7 +2616,7 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) * a function that saves all the regs. Basically the '_EN' version * represents the current state of the function. * - * Returns the address of the trampoline that is currently being called + * Returns: the address of the trampoline that is currently being called */ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) { @@ -2719,7 +2720,7 @@ struct ftrace_rec_iter { /** * ftrace_rec_iter_start - start up iterating over traced functions * - * Returns an iterator handle that is used to iterate over all + * Returns: an iterator handle that is used to iterate over all * the records that represent address locations where functions * are traced. * @@ -2751,7 +2752,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_start(void) * ftrace_rec_iter_next - get the next record to process. * @iter: The handle to the iterator. * - * Returns the next iterator after the given iterator @iter. + * Returns: the next iterator after the given iterator @iter. */ struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter) { @@ -2776,7 +2777,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter) * ftrace_rec_iter_record - get the record at the iterator location * @iter: The current iterator location * - * Returns the record that the current @iter is at. + * Returns: the record that the current @iter is at. */ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter) { @@ -4010,6 +4011,8 @@ ftrace_avail_addrs_open(struct inode *inode, struct file *file) * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set. * tracing_lseek() should be used as the lseek routine, and * release must call ftrace_regex_release(). + * + * Returns: 0 on success or a negative errno value on failure */ int ftrace_regex_open(struct ftrace_ops *ops, int flag, @@ -4626,7 +4629,7 @@ struct ftrace_func_mapper { /** * allocate_ftrace_func_mapper - allocate a new ftrace_func_mapper * - * Returns a ftrace_func_mapper descriptor that can be used to map ips to data. + * Returns: a ftrace_func_mapper descriptor that can be used to map ips to data. */ struct ftrace_func_mapper *allocate_ftrace_func_mapper(void) { @@ -4646,7 +4649,7 @@ struct ftrace_func_mapper *allocate_ftrace_func_mapper(void) * @mapper: The mapper that has the ip maps * @ip: the instruction pointer to find the data for * - * Returns the data mapped to @ip if found otherwise NULL. The return + * Returns: the data mapped to @ip if found otherwise NULL. The return * is actually the address of the mapper data pointer. The address is * returned for use cases where the data is no bigger than a long, and * the user can use the data pointer as its data instead of having to @@ -4672,7 +4675,7 @@ void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper, * @ip: The instruction pointer address to map @data to * @data: The data to map to @ip * - * Returns 0 on success otherwise an error. + * Returns: 0 on success otherwise an error. */ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, unsigned long ip, void *data) @@ -4701,7 +4704,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, * @mapper: The mapper that has the ip maps * @ip: The instruction pointer address to remove the data from * - * Returns the data if it is found, otherwise NULL. + * Returns: the data if it is found, otherwise NULL. * Note, if the data pointer is used as the data itself, (see * ftrace_func_mapper_find_ip(), then the return value may be meaningless, * if the data pointer was set to zero. @@ -5625,10 +5628,10 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct); /** * ftrace_set_filter_ip - set a function to filter on in ftrace by address - * @ops - the ops to set the filter with - * @ip - the address to add to or remove from the filter. - * @remove - non zero to remove the ip from the filter - * @reset - non zero to reset all filters before applying this filter. + * @ops: the ops to set the filter with + * @ip: the address to add to or remove from the filter. + * @remove: non zero to remove the ip from the filter + * @reset: non zero to reset all filters before applying this filter. * * Filters denote which functions should be enabled when tracing is enabled * If @ip is NULL, it fails to update filter. @@ -5647,11 +5650,11 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); /** * ftrace_set_filter_ips - set functions to filter on in ftrace by addresses - * @ops - the ops to set the filter with - * @ips - the array of addresses to add to or remove from the filter. - * @cnt - the number of addresses in @ips - * @remove - non zero to remove ips from the filter - * @reset - non zero to reset all filters before applying this filter. + * @ops: the ops to set the filter with + * @ips: the array of addresses to add to or remove from the filter. + * @cnt: the number of addresses in @ips + * @remove: non zero to remove ips from the filter + * @reset: non zero to reset all filters before applying this filter. * * Filters denote which functions should be enabled when tracing is enabled * If @ips array or any ip specified within is NULL , it fails to update filter. @@ -5670,7 +5673,7 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ips); /** * ftrace_ops_set_global_filter - setup ops to use global filters - * @ops - the ops which will use the global filters + * @ops: the ops which will use the global filters * * ftrace users who need global function trace filtering should call this. * It can set the global filter only if ops were not initialized before. @@ -5694,10 +5697,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, /** * ftrace_set_filter - set a function to filter on in ftrace - * @ops - the ops to set the filter with - * @buf - the string that holds the function filter text. - * @len - the length of the string. - * @reset - non zero to reset all filters before applying this filter. + * @ops: the ops to set the filter with + * @buf: the string that holds the function filter text. + * @len: the length of the string. + * @reset: non-zero to reset all filters before applying this filter. * * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. @@ -5716,10 +5719,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter); /** * ftrace_set_notrace - set a function to not trace in ftrace - * @ops - the ops to set the notrace filter with - * @buf - the string that holds the function notrace text. - * @len - the length of the string. - * @reset - non zero to reset all filters before applying this filter. + * @ops: the ops to set the notrace filter with + * @buf: the string that holds the function notrace text. + * @len: the length of the string. + * @reset: non-zero to reset all filters before applying this filter. * * Notrace Filters denote which functions should not be enabled when tracing * is enabled. If @buf is NULL and reset is set, all functions will be enabled @@ -5738,9 +5741,9 @@ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, EXPORT_SYMBOL_GPL(ftrace_set_notrace); /** * ftrace_set_global_filter - set a function to filter on with global tracers - * @buf - the string that holds the function filter text. - * @len - the length of the string. - * @reset - non zero to reset all filters before applying this filter. + * @buf: the string that holds the function filter text. + * @len: the length of the string. + * @reset: non-zero to reset all filters before applying this filter. * * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. @@ -5753,9 +5756,9 @@ EXPORT_SYMBOL_GPL(ftrace_set_global_filter); /** * ftrace_set_global_notrace - set a function to not trace with global tracers - * @buf - the string that holds the function notrace text. - * @len - the length of the string. - * @reset - non zero to reset all filters before applying this filter. + * @buf: the string that holds the function notrace text. + * @len: the length of the string. + * @reset: non-zero to reset all filters before applying this filter. * * Notrace Filters denote which functions should not be enabled when tracing * is enabled. If @buf is NULL and reset is set, all functions will be enabled @@ -7443,7 +7446,7 @@ NOKPROBE_SYMBOL(ftrace_ops_assist_func); * have its own recursion protection, then it should call the * ftrace_ops_assist_func() instead. * - * Returns the function that the trampoline should call for @ops. + * Returns: the function that the trampoline should call for @ops. */ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) { @@ -7897,7 +7900,7 @@ void ftrace_kill(void) /** * ftrace_is_dead - Test if ftrace is dead or not. * - * Returns 1 if ftrace is "dead", zero otherwise. + * Returns: 1 if ftrace is "dead", zero otherwise. */ int ftrace_is_dead(void) { @@ -8142,8 +8145,7 @@ static int kallsyms_callback(void *data, const char *name, unsigned long addr) * @addrs array, which needs to be big enough to store at least @cnt * addresses. * - * This function returns 0 if all provided symbols are found, - * -ESRCH otherwise. + * Returns: 0 if all provided symbols are found, -ESRCH otherwise. */ int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs) { -- cgit v1.2.3 From 19f0423fd55c301c8edaea286e568ec657f42750 Mon Sep 17 00:00:00 2001 From: Huang Yiwei Date: Fri, 23 Feb 2024 16:31:26 +0800 Subject: tracing: Support to dump instance traces by ftrace_dump_on_oops Currently ftrace only dumps the global trace buffer on an OOPs. For debugging a production usecase, instance trace will be helpful to check specific problems since global trace buffer may be used for other purposes. This patch extend the ftrace_dump_on_oops parameter to dump a specific or multiple trace instances: - ftrace_dump_on_oops=0: as before -- don't dump - ftrace_dump_on_oops[=1]: as before -- dump the global trace buffer on all CPUs - ftrace_dump_on_oops=2 or =orig_cpu: as before -- dump the global trace buffer on CPU that triggered the oops - ftrace_dump_on_oops=: new behavior -- dump the tracing instance matching - ftrace_dump_on_oops[=2/orig_cpu],[=2/orig_cpu], [=2/orig_cpu]: new behavior -- dump the global trace buffer and multiple instance buffer on all CPUs, or only dump on CPU that triggered the oops if =2 or =orig_cpu is given Also, the sysctl node can handle the input accordingly. Link: https://lore.kernel.org/linux-trace-kernel/20240223083126.1817731-1-quic_hyiwei@quicinc.com Cc: Ross Zwisler Cc: Cc: Cc: Cc: Cc: Cc: Cc: Signed-off-by: Huang Yiwei Signed-off-by: Steven Rostedt (Google) --- Documentation/admin-guide/kernel-parameters.txt | 26 +++- Documentation/admin-guide/sysctl/kernel.rst | 30 ++++- include/linux/ftrace.h | 4 +- include/linux/kernel.h | 1 + kernel/sysctl.c | 4 +- kernel/trace/trace.c | 156 ++++++++++++++++++------ kernel/trace/trace_selftest.c | 2 +- 7 files changed, 168 insertions(+), 55 deletions(-) (limited to 'kernel') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 479ff1737c2f..fa871d53641c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1572,12 +1572,28 @@ The above will cause the "foo" tracing instance to trigger a snapshot at the end of boot up. - ftrace_dump_on_oops[=orig_cpu] + ftrace_dump_on_oops[=2(orig_cpu) | =][, | + ,=2(orig_cpu)] [FTRACE] will dump the trace buffers on oops. - If no parameter is passed, ftrace will dump - buffers of all CPUs, but if you pass orig_cpu, it will - dump only the buffer of the CPU that triggered the - oops. + If no parameter is passed, ftrace will dump global + buffers of all CPUs, if you pass 2 or orig_cpu, it + will dump only the buffer of the CPU that triggered + the oops, or the specific instance will be dumped if + its name is passed. Multiple instance dump is also + supported, and instances are separated by commas. Each + instance supports only dump on CPU that triggered the + oops by passing 2 or orig_cpu to it. + + ftrace_dump_on_oops=foo=orig_cpu + + The above will dump only the buffer of "foo" instance + on CPU that triggered the oops. + + ftrace_dump_on_oops,foo,bar=orig_cpu + + The above will dump global buffer on all CPUs, the + buffer of "foo" instance on all CPUs and the buffer + of "bar" instance on CPU that triggered the oops. ftrace_filter=[function-list] [FTRACE] Limit the functions traced by the function diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 6584a1f9bfe3..ea8e5f152edc 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -296,12 +296,30 @@ kernel panic). This will output the contents of the ftrace buffers to the console. This is very useful for capturing traces that lead to crashes and outputting them to a serial console. -= =================================================== -0 Disabled (default). -1 Dump buffers of all CPUs. -2 Dump the buffer of the CPU that triggered the oops. -= =================================================== - +======================= =========================================== +0 Disabled (default). +1 Dump buffers of all CPUs. +2(orig_cpu) Dump the buffer of the CPU that triggered the + oops. + Dump the specific instance buffer on all CPUs. +=2(orig_cpu) Dump the specific instance buffer on the CPU + that triggered the oops. +======================= =========================================== + +Multiple instance dump is also supported, and instances are separated +by commas. If global buffer also needs to be dumped, please specify +the dump mode (1/2/orig_cpu) first for global buffer. + +So for example to dump "foo" and "bar" instance buffer on all CPUs, +user can:: + + echo "foo,bar" > /proc/sys/kernel/ftrace_dump_on_oops + +To dump global buffer and "foo" instance buffer on all +CPUs along with the "bar" instance buffer on CPU that triggered the +oops, user can:: + + echo "1,foo,bar=2" > /proc/sys/kernel/ftrace_dump_on_oops ftrace_enabled, stack_tracer_enabled ==================================== diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e8921871ef9a..54d53f345d14 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1151,7 +1151,9 @@ static inline void unpause_graph_tracing(void) { } #ifdef CONFIG_TRACING enum ftrace_dump_mode; -extern enum ftrace_dump_mode ftrace_dump_on_oops; +#define MAX_TRACER_SIZE 100 +extern char ftrace_dump_on_oops[]; +extern int ftrace_dump_on_oops_enabled(void); extern int tracepoint_printk; extern void disable_trace_on_warning(void); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d718fbec72dd..be2e8c0a187e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -215,6 +215,7 @@ enum ftrace_dump_mode { DUMP_NONE, DUMP_ALL, DUMP_ORIG, + DUMP_PARAM, }; #ifdef CONFIG_TRACING diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 157f7ce2942d..81cc974913bb 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1710,9 +1710,9 @@ static struct ctl_table kern_table[] = { { .procname = "ftrace_dump_on_oops", .data = &ftrace_dump_on_oops, - .maxlen = sizeof(int), + .maxlen = MAX_TRACER_SIZE, .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dostring, }, { .procname = "traceoff_on_warning", diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1e1fd377a1cf..233d1af39fff 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -130,9 +130,12 @@ cpumask_var_t __read_mostly tracing_buffer_mask; * /proc/sys/kernel/ftrace_dump_on_oops * Set 1 if you want to dump buffers of all CPUs * Set 2 if you want to dump the buffer of the CPU that triggered oops + * Set instance name if you want to dump the specific trace instance + * Multiple instance dump is also supported, and instances are seperated + * by commas. */ - -enum ftrace_dump_mode ftrace_dump_on_oops; +/* Set to string format zero to disable by default */ +char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0"; /* When set, tracing will stop when a WARN*() is hit */ int __disable_trace_on_warning; @@ -178,7 +181,6 @@ static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx); -#define MAX_TRACER_SIZE 100 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; @@ -201,19 +203,33 @@ static int __init set_cmdline_ftrace(char *str) } __setup("ftrace=", set_cmdline_ftrace); +int ftrace_dump_on_oops_enabled(void) +{ + if (!strcmp("0", ftrace_dump_on_oops)) + return 0; + else + return 1; +} + static int __init set_ftrace_dump_on_oops(char *str) { - if (*str++ != '=' || !*str || !strcmp("1", str)) { - ftrace_dump_on_oops = DUMP_ALL; + if (!*str) { + strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE); return 1; } - if (!strcmp("orig_cpu", str) || !strcmp("2", str)) { - ftrace_dump_on_oops = DUMP_ORIG; - return 1; - } + if (*str == ',') { + strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE); + strscpy(ftrace_dump_on_oops + 1, str, MAX_TRACER_SIZE - 1); + return 1; + } + + if (*str++ == '=') { + strscpy(ftrace_dump_on_oops, str, MAX_TRACER_SIZE); + return 1; + } - return 0; + return 0; } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); @@ -9832,14 +9848,14 @@ static struct notifier_block trace_die_notifier = { static int trace_die_panic_handler(struct notifier_block *self, unsigned long ev, void *unused) { - if (!ftrace_dump_on_oops) + if (!ftrace_dump_on_oops_enabled()) return NOTIFY_DONE; /* The die notifier requires DIE_OOPS to trigger */ if (self == &trace_die_notifier && ev != DIE_OOPS) return NOTIFY_DONE; - ftrace_dump(ftrace_dump_on_oops); + ftrace_dump(DUMP_PARAM); return NOTIFY_DONE; } @@ -9880,12 +9896,12 @@ trace_printk_seq(struct trace_seq *s) trace_seq_init(s); } -void trace_init_global_iter(struct trace_iterator *iter) +static void trace_init_iter(struct trace_iterator *iter, struct trace_array *tr) { - iter->tr = &global_trace; + iter->tr = tr; iter->trace = iter->tr->current_trace; iter->cpu_file = RING_BUFFER_ALL_CPUS; - iter->array_buffer = &global_trace.array_buffer; + iter->array_buffer = &tr->array_buffer; if (iter->trace && iter->trace->open) iter->trace->open(iter); @@ -9905,22 +9921,19 @@ void trace_init_global_iter(struct trace_iterator *iter) iter->fmt_size = STATIC_FMT_BUF_SIZE; } -void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) +void trace_init_global_iter(struct trace_iterator *iter) +{ + trace_init_iter(iter, &global_trace); +} + +static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_mode) { /* use static because iter can be a bit big for the stack */ static struct trace_iterator iter; - static atomic_t dump_running; - struct trace_array *tr = &global_trace; unsigned int old_userobj; unsigned long flags; int cnt = 0, cpu; - /* Only allow one dump user at a time. */ - if (atomic_inc_return(&dump_running) != 1) { - atomic_dec(&dump_running); - return; - } - /* * Always turn off tracing when we dump. * We don't need to show trace output of what happens @@ -9929,12 +9942,12 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) * If the user does a sysrq-z, then they can re-enable * tracing with echo 1 > tracing_on. */ - tracing_off(); + tracer_tracing_off(tr); local_irq_save(flags); /* Simulate the iterator */ - trace_init_global_iter(&iter); + trace_init_iter(&iter, tr); for_each_tracing_cpu(cpu) { atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); @@ -9945,21 +9958,15 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) /* don't look at user memory in panic mode */ tr->trace_flags &= ~TRACE_ITER_SYM_USEROBJ; - switch (oops_dump_mode) { - case DUMP_ALL: - iter.cpu_file = RING_BUFFER_ALL_CPUS; - break; - case DUMP_ORIG: + if (dump_mode == DUMP_ORIG) iter.cpu_file = raw_smp_processor_id(); - break; - case DUMP_NONE: - goto out_enable; - default: - printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n"); + else iter.cpu_file = RING_BUFFER_ALL_CPUS; - } - printk(KERN_TRACE "Dumping ftrace buffer:\n"); + if (tr == &global_trace) + printk(KERN_TRACE "Dumping ftrace buffer:\n"); + else + printk(KERN_TRACE "Dumping ftrace instance %s buffer:\n", tr->name); /* Did function tracer already get disabled? */ if (ftrace_is_dead()) { @@ -10001,15 +10008,84 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) else printk(KERN_TRACE "---------------------------------\n"); - out_enable: tr->trace_flags |= old_userobj; for_each_tracing_cpu(cpu) { atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); } - atomic_dec(&dump_running); local_irq_restore(flags); } + +static void ftrace_dump_by_param(void) +{ + bool first_param = true; + char dump_param[MAX_TRACER_SIZE]; + char *buf, *token, *inst_name; + struct trace_array *tr; + + strscpy(dump_param, ftrace_dump_on_oops, MAX_TRACER_SIZE); + buf = dump_param; + + while ((token = strsep(&buf, ",")) != NULL) { + if (first_param) { + first_param = false; + if (!strcmp("0", token)) + continue; + else if (!strcmp("1", token)) { + ftrace_dump_one(&global_trace, DUMP_ALL); + continue; + } + else if (!strcmp("2", token) || + !strcmp("orig_cpu", token)) { + ftrace_dump_one(&global_trace, DUMP_ORIG); + continue; + } + } + + inst_name = strsep(&token, "="); + tr = trace_array_find(inst_name); + if (!tr) { + printk(KERN_TRACE "Instance %s not found\n", inst_name); + continue; + } + + if (token && (!strcmp("2", token) || + !strcmp("orig_cpu", token))) + ftrace_dump_one(tr, DUMP_ORIG); + else + ftrace_dump_one(tr, DUMP_ALL); + } +} + +void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) +{ + static atomic_t dump_running; + + /* Only allow one dump user at a time. */ + if (atomic_inc_return(&dump_running) != 1) { + atomic_dec(&dump_running); + return; + } + + switch (oops_dump_mode) { + case DUMP_ALL: + ftrace_dump_one(&global_trace, DUMP_ALL); + break; + case DUMP_ORIG: + ftrace_dump_one(&global_trace, DUMP_ORIG); + break; + case DUMP_PARAM: + ftrace_dump_by_param(); + break; + case DUMP_NONE: + break; + default: + printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n"); + ftrace_dump_one(&global_trace, DUMP_ALL); + } + + atomic_dec(&dump_running); +} EXPORT_SYMBOL_GPL(ftrace_dump); #define WRITE_BUFSIZE 4096 diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 529590499b1f..e9c5058a8efd 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -768,7 +768,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace) if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { ftrace_graph_stop(); printk(KERN_WARNING "BUG: Function graph tracer hang!\n"); - if (ftrace_dump_on_oops) { + if (ftrace_dump_on_oops_enabled()) { ftrace_dump(DUMP_ALL); /* ftrace_dump() disables tracing */ tracing_on(); -- cgit v1.2.3 From d6cb38e10810743addf8cac0b277861d614de1e9 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Sun, 25 Feb 2024 17:45:08 +0100 Subject: tracing: Use div64_u64() instead of do_div() Fixes Coccinelle/coccicheck warnings reported by do_div.cocci. Compared to do_div(), div64_u64() does not implicitly cast the divisor and does not unnecessarily calculate the remainder. Link: https://lore.kernel.org/linux-trace-kernel/20240225164507.232942-2-thorsten.blum@toblux.com Cc: Mathieu Desnoyers Signed-off-by: Thorsten Blum Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_benchmark.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index 54d5fa35c90a..811b08439406 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -92,7 +92,6 @@ static void trace_do_benchmark(void) bm_total += delta; bm_totalsq += delta * delta; - if (bm_cnt > 1) { /* * Apply Welford's method to calculate standard deviation: @@ -105,7 +104,7 @@ static void trace_do_benchmark(void) stddev = 0; delta = bm_total; - do_div(delta, bm_cnt); + delta = div64_u64(delta, bm_cnt); avg = delta; if (stddev > 0) { @@ -127,7 +126,7 @@ static void trace_do_benchmark(void) seed = stddev; if (!last_seed) break; - do_div(seed, last_seed); + seed = div64_u64(seed, last_seed); seed += last_seed; do_div(seed, 2); } while (i++ < 10 && last_seed != seed); -- cgit v1.2.3 From f55acb1e44f3d4bf1ca7926d777895a67d4ec606 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 19 Mar 2024 00:07:28 +0100 Subject: timers/migration: Fix endless timer requeue after idle interrupts When a CPU is an idle migrator, but another CPU wakes up before it, becomes an active migrator and handles the queue, the initial idle migrator may end up endlessly reprogramming its clockevent, chasing ghost timers forever such as in the following scenario: [GRP0:0] migrator = 0 active = 0 nextevt = T1 / \ 0 1 active idle (T1) 0) CPU 1 is idle and has a timer queued (T1), CPU 0 is active and is the active migrator. [GRP0:0] migrator = NONE active = NONE nextevt = T1 / \ 0 1 idle idle (T1) wakeup = T1 1) CPU 0 is now idle and is therefore the idle migrator. It has programmed its next timer interrupt to handle T1. [GRP0:0] migrator = 1 active = 1 nextevt = KTIME_MAX / \ 0 1 idle active wakeup = T1 2) CPU 1 has woken up, it is now active and it has just handled its own timer T1. 3) CPU 0 gets a timer interrupt to handle T1 but tmigr_handle_remote() realize it is not the migrator anymore. So it early returns without observing that T1 has been expired already and therefore without updating its ->wakeup value. 4) CPU 0 goes into tmigr_cpu_new_timer() which also early returns because it doesn't queue a timer of its own. So ->wakeup is left unchanged and the next timer is programmed to fire now. 5) goto 3) forever This results in timer interrupt storms in idle and also in nohz_full (as observed in rcutorture's TREE07 scenario). Fix this with forcing a re-evaluation of tmc->wakeup while trying remote timer handling when the CPU isn't the migrator anymmore. The check is inherently racy but in the worst case the CPU just races setting the KTIME_MAX value that a remote expiry also tries to set. Fixes: 7ee988770326 ("timers: Implement the hierarchical pull model") Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240318230729.15497-2-frederic@kernel.org --- kernel/time/timer_migration.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 611cd904f035..c63a0afdcebe 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1038,8 +1038,15 @@ void tmigr_handle_remote(void) * in tmigr_handle_remote_up() anyway. Keep this check to speed up the * return when nothing has to be done. */ - if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) - return; + if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) { + /* + * If this CPU was an idle migrator, make sure to clear its wakeup + * value so it won't chase timers that have already expired elsewhere. + * This avoids endless requeue from tmigr_new_timer(). + */ + if (READ_ONCE(tmc->wakeup) == KTIME_MAX) + return; + } data.now = get_jiffies_update(&data.basej); -- cgit v1.2.3 From 03877039863be021a19fda307136657bb6d61f75 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 19 Mar 2024 00:07:29 +0100 Subject: timers: Fix removed self-IPI on global timer's enqueue in nohz_full While running in nohz_full mode, a task may enqueue a timer while the tick is stopped. However the only places where the timer wheel, alongside the timer migration machinery's decision, may reprogram the next event accordingly with that new timer's expiry are the idle loop or any IRQ tail. However neither the idle task nor an interrupt may run on the CPU if it resumes busy work in userspace for a long while in full dynticks mode. To solve this, the timer enqueue path raises a self-IPI that will re-evaluate the timer wheel on its IRQ tail. This asynchronous solution avoids potential locking inversion. This is supposed to happen both for local and global timers but commit: b2cf7507e186 ("timers: Always queue timers on the local CPU") broke the global timers case with removing the ->is_idle field handling for the global base. As a result, global timers enqueue may go unnoticed in nohz_full. Fix this with restoring the idle tracking of the global timer's base, allowing self-IPIs again on enqueue time. Fixes: b2cf7507e186 ("timers: Always queue timers on the local CPU") Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20240318230729.15497-3-frederic@kernel.org --- kernel/time/timer.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index e69e75d3858c..dee29f1f5b75 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -642,7 +642,8 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) * the base lock: */ if (base->is_idle) { - WARN_ON_ONCE(!(timer->flags & TIMER_PINNED)); + WARN_ON_ONCE(!(timer->flags & TIMER_PINNED || + tick_nohz_full_cpu(base->cpu))); wake_up_nohz_cpu(base->cpu); } } @@ -2292,6 +2293,13 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, */ if (!base_local->is_idle && time_after(nextevt, basej + 1)) { base_local->is_idle = true; + /* + * Global timers queued locally while running in a task + * in nohz_full mode need a self-IPI to kick reprogramming + * in IRQ tail. + */ + if (tick_nohz_full_cpu(base_local->cpu)) + base_global->is_idle = true; trace_timer_base_idle(true, base_local->cpu); } *idle = base_local->is_idle; @@ -2364,6 +2372,8 @@ void timer_clear_idle(void) * path. Required for BASE_LOCAL only. */ __this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false); + if (tick_nohz_full_cpu(smp_processor_id())) + __this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false); trace_timer_base_idle(false, smp_processor_id()); /* Activate without holding the timer_base->lock */ -- cgit v1.2.3 From 00bf63122459e87193ee7f1bc6161c83a525569f Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Tue, 19 Mar 2024 13:44:40 -0700 Subject: bpf: report RCU QS in cpumap kthread When there are heavy load, cpumap kernel threads can be busy polling packets from redirect queues and block out RCU tasks from reaching quiescent states. It is insufficient to just call cond_resched() in such context. Periodically raise a consolidated RCU QS before cond_resched fixes the problem. Fixes: 6710e1126934 ("bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP") Reviewed-by: Jesper Dangaard Brouer Signed-off-by: Yan Zhai Acked-by: Paul E. McKenney Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/c17b9f1517e19d813da3ede5ed33ee18496bb5d8.1710877680.git.yan@cloudflare.com Signed-off-by: Jakub Kicinski --- kernel/bpf/cpumap.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 9ee8da477465..a8e34416e960 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -263,6 +263,7 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + unsigned long last_qs = jiffies; complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); @@ -288,10 +289,12 @@ static int cpu_map_kthread_run(void *data) if (__ptr_ring_empty(rcpu->queue)) { schedule(); sched = 1; + last_qs = jiffies; } else { __set_current_state(TASK_RUNNING); } } else { + rcu_softirq_qs_periodic(last_qs); sched = cond_resched(); } -- cgit v1.2.3 From 203a6763ab699da0568fd2b76303d03bb121abd4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 13 Mar 2024 16:32:27 -0700 Subject: Revert "crypto: pkcs7 - remove sha1 support" This reverts commit 16ab7cb5825fc3425c16ad2c6e53d827f382d7c6 because it broke iwd. iwd uses the KEYCTL_PKEY_* UAPIs via its dependency libell, and apparently it is relying on SHA-1 signature support. These UAPIs are fairly obscure, and their documentation does not mention which algorithms they support. iwd really should be using a properly supported userspace crypto library instead. Regardless, since something broke we have to revert the change. It may be possible that some parts of this commit can be reinstated without breaking iwd (e.g. probably the removal of MODULE_SIG_SHA1), but for now this just does a full revert to get things working again. Reported-by: Karel Balej Closes: https://lore.kernel.org/r/CZSHRUIJ4RKL.34T4EASV5DNJM@matfyz.cz Cc: Dimitri John Ledkov Signed-off-by: Eric Biggers Tested-by: Karel Balej Signed-off-by: Herbert Xu --- crypto/asymmetric_keys/mscode_parser.c | 3 ++ crypto/asymmetric_keys/pkcs7_parser.c | 4 ++ crypto/asymmetric_keys/public_key.c | 3 +- crypto/asymmetric_keys/signature.c | 2 +- crypto/asymmetric_keys/x509_cert_parser.c | 8 ++++ crypto/testmgr.h | 80 +++++++++++++++++++++++++++++++ include/linux/oid_registry.h | 4 ++ kernel/module/Kconfig | 5 ++ 8 files changed, 107 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/crypto/asymmetric_keys/mscode_parser.c b/crypto/asymmetric_keys/mscode_parser.c index 05402ef8964e..8aecbe4637f3 100644 --- a/crypto/asymmetric_keys/mscode_parser.c +++ b/crypto/asymmetric_keys/mscode_parser.c @@ -75,6 +75,9 @@ int mscode_note_digest_algo(void *context, size_t hdrlen, oid = look_up_OID(value, vlen); switch (oid) { + case OID_sha1: + ctx->digest_algo = "sha1"; + break; case OID_sha256: ctx->digest_algo = "sha256"; break; diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c index 5b08c50722d0..231ad7b3789d 100644 --- a/crypto/asymmetric_keys/pkcs7_parser.c +++ b/crypto/asymmetric_keys/pkcs7_parser.c @@ -227,6 +227,9 @@ int pkcs7_sig_note_digest_algo(void *context, size_t hdrlen, struct pkcs7_parse_context *ctx = context; switch (ctx->last_oid) { + case OID_sha1: + ctx->sinfo->sig->hash_algo = "sha1"; + break; case OID_sha256: ctx->sinfo->sig->hash_algo = "sha256"; break; @@ -278,6 +281,7 @@ int pkcs7_sig_note_pkey_algo(void *context, size_t hdrlen, ctx->sinfo->sig->pkey_algo = "rsa"; ctx->sinfo->sig->encoding = "pkcs1"; break; + case OID_id_ecdsa_with_sha1: case OID_id_ecdsa_with_sha224: case OID_id_ecdsa_with_sha256: case OID_id_ecdsa_with_sha384: diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index e5f22691febd..e314fd57e6f8 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -115,7 +115,8 @@ software_key_determine_akcipher(const struct public_key *pkey, */ if (!hash_algo) return -EINVAL; - if (strcmp(hash_algo, "sha224") != 0 && + if (strcmp(hash_algo, "sha1") != 0 && + strcmp(hash_algo, "sha224") != 0 && strcmp(hash_algo, "sha256") != 0 && strcmp(hash_algo, "sha384") != 0 && strcmp(hash_algo, "sha512") != 0 && diff --git a/crypto/asymmetric_keys/signature.c b/crypto/asymmetric_keys/signature.c index 398983be77e8..2deff81f8af5 100644 --- a/crypto/asymmetric_keys/signature.c +++ b/crypto/asymmetric_keys/signature.c @@ -115,7 +115,7 @@ EXPORT_SYMBOL_GPL(decrypt_blob); * Sign the specified data blob using the private key specified by params->key. * The signature is wrapped in an encoding if params->encoding is specified * (eg. "pkcs1"). If the encoding needs to know the digest type, this can be - * passed through params->hash_algo (eg. "sha512"). + * passed through params->hash_algo (eg. "sha1"). * * Returns the length of the data placed in the signature buffer or an error. */ diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 487204d39426..bb0bffa271b5 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -198,6 +198,10 @@ int x509_note_sig_algo(void *context, size_t hdrlen, unsigned char tag, default: return -ENOPKG; /* Unsupported combination */ + case OID_sha1WithRSAEncryption: + ctx->cert->sig->hash_algo = "sha1"; + goto rsa_pkcs1; + case OID_sha256WithRSAEncryption: ctx->cert->sig->hash_algo = "sha256"; goto rsa_pkcs1; @@ -214,6 +218,10 @@ int x509_note_sig_algo(void *context, size_t hdrlen, unsigned char tag, ctx->cert->sig->hash_algo = "sha224"; goto rsa_pkcs1; + case OID_id_ecdsa_with_sha1: + ctx->cert->sig->hash_algo = "sha1"; + goto ecdsa; + case OID_id_rsassa_pkcs1_v1_5_with_sha3_256: ctx->cert->sig->hash_algo = "sha3-256"; goto rsa_pkcs1; diff --git a/crypto/testmgr.h b/crypto/testmgr.h index 986f331a5fc2..12e1c892f366 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -653,6 +653,30 @@ static const struct akcipher_testvec rsa_tv_template[] = { static const struct akcipher_testvec ecdsa_nist_p192_tv_template[] = { { .key = + "\x04\xf7\x46\xf8\x2f\x15\xf6\x22\x8e\xd7\x57\x4f\xcc\xe7\xbb\xc1" + "\xd4\x09\x73\xcf\xea\xd0\x15\x07\x3d\xa5\x8a\x8a\x95\x43\xe4\x68" + "\xea\xc6\x25\xc1\xc1\x01\x25\x4c\x7e\xc3\x3c\xa6\x04\x0a\xe7\x08" + "\x98", + .key_len = 49, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x01", + .param_len = 21, + .m = + "\xcd\xb9\xd2\x1c\xb7\x6f\xcd\x44\xb3\xfd\x63\xea\xa3\x66\x7f\xae" + "\x63\x85\xe7\x82", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x35\x02\x19\x00\xba\xe5\x93\x83\x6e\xb6\x3b\x63\xa0\x27\x91" + "\xc6\xf6\x7f\xc3\x09\xad\x59\xad\x88\x27\xd6\x92\x6b\x02\x18\x10" + "\x68\x01\x9d\xba\xce\x83\x08\xef\x95\x52\x7b\xa0\x0f\xe4\x18\x86" + "\x80\x6f\xa5\x79\x77\xda\xd0", + .c_size = 55, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = "\x04\xb6\x4b\xb1\xd1\xac\xba\x24\x8f\x65\xb2\x60\x00\x90\xbf\xbd" "\x78\x05\x73\xe9\x79\x1d\x6f\x7c\x0b\xd2\xc3\x93\xa7\x28\xe1\x75" "\xf7\xd5\x95\x1d\x28\x10\xc0\x75\x50\x5c\x1a\x4f\x3f\x8f\xa5\xee" @@ -756,6 +780,32 @@ static const struct akcipher_testvec ecdsa_nist_p192_tv_template[] = { static const struct akcipher_testvec ecdsa_nist_p256_tv_template[] = { { .key = + "\x04\xb9\x7b\xbb\xd7\x17\x64\xd2\x7e\xfc\x81\x5d\x87\x06\x83\x41" + "\x22\xd6\x9a\xaa\x87\x17\xec\x4f\x63\x55\x2f\x94\xba\xdd\x83\xe9" + "\x34\x4b\xf3\xe9\x91\x13\x50\xb6\xcb\xca\x62\x08\xe7\x3b\x09\xdc" + "\xc3\x63\x4b\x2d\xb9\x73\x53\xe4\x45\xe6\x7c\xad\xe7\x6b\xb0\xe8" + "\xaf", + .key_len = 65, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x07", + .param_len = 21, + .m = + "\xc2\x2b\x5f\x91\x78\x34\x26\x09\x42\x8d\x6f\x51\xb2\xc5\xaf\x4c" + "\x0b\xde\x6a\x42", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x46\x02\x21\x00\xf9\x25\xce\x9f\x3a\xa6\x35\x81\xcf\xd4\xe7" + "\xb7\xf0\x82\x56\x41\xf7\xd4\xad\x8d\x94\x5a\x69\x89\xee\xca\x6a" + "\x52\x0e\x48\x4d\xcc\x02\x21\x00\xd7\xe4\xef\x52\x66\xd3\x5b\x9d" + "\x8a\xfa\x54\x93\x29\xa7\x70\x86\xf1\x03\x03\xf3\x3b\xe2\x73\xf7" + "\xfb\x9d\x8b\xde\xd4\x8d\x6f\xad", + .c_size = 72, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = "\x04\x8b\x6d\xc0\x33\x8e\x2d\x8b\x67\xf5\xeb\xc4\x7f\xa0\xf5\xd9" "\x7b\x03\xa5\x78\x9a\xb5\xea\x14\xe4\x23\xd0\xaf\xd7\x0e\x2e\xa0" "\xc9\x8b\xdb\x95\xf8\xb3\xaf\xac\x00\x2c\x2c\x1f\x7a\xfd\x95\x88" @@ -866,6 +916,36 @@ static const struct akcipher_testvec ecdsa_nist_p256_tv_template[] = { static const struct akcipher_testvec ecdsa_nist_p384_tv_template[] = { { + .key = /* secp384r1(sha1) */ + "\x04\x89\x25\xf3\x97\x88\xcb\xb0\x78\xc5\x72\x9a\x14\x6e\x7a\xb1" + "\x5a\xa5\x24\xf1\x95\x06\x9e\x28\xfb\xc4\xb9\xbe\x5a\x0d\xd9\x9f" + "\xf3\xd1\x4d\x2d\x07\x99\xbd\xda\xa7\x66\xec\xbb\xea\xba\x79\x42" + "\xc9\x34\x89\x6a\xe7\x0b\xc3\xf2\xfe\x32\x30\xbe\xba\xf9\xdf\x7e" + "\x4b\x6a\x07\x8e\x26\x66\x3f\x1d\xec\xa2\x57\x91\x51\xdd\x17\x0e" + "\x0b\x25\xd6\x80\x5c\x3b\xe6\x1a\x98\x48\x91\x45\x7a\x73\xb0\xc3" + "\xf1", + .key_len = 97, + .params = + "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04" + "\x00\x22", + .param_len = 18, + .m = + "\x12\x55\x28\xf0\x77\xd5\xb6\x21\x71\x32\x48\xcd\x28\xa8\x25\x22" + "\x3a\x69\xc1\x93", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x66\x02\x31\x00\xf5\x0f\x24\x4c\x07\x93\x6f\x21\x57\x55\x07" + "\x20\x43\x30\xde\xa0\x8d\x26\x8e\xae\x63\x3f\xbc\x20\x3a\xc6\xf1" + "\x32\x3c\xce\x70\x2b\x78\xf1\x4c\x26\xe6\x5b\x86\xcf\xec\x7c\x7e" + "\xd0\x87\xd7\xd7\x6e\x02\x31\x00\xcd\xbb\x7e\x81\x5d\x8f\x63\xc0" + "\x5f\x63\xb1\xbe\x5e\x4c\x0e\xa1\xdf\x28\x8c\x1b\xfa\xf9\x95\x88" + "\x74\xa0\x0f\xbf\xaf\xc3\x36\x76\x4a\xa1\x59\xf1\x1c\xa4\x58\x26" + "\x79\x12\x2a\xb7\xc5\x15\x92\xc5", + .c_size = 104, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { .key = /* secp384r1(sha224) */ "\x04\x69\x6c\xcf\x62\xee\xd0\x0d\xe5\xb5\x2f\x70\x54\xcf\x26\xa0" "\xd9\x98\x8d\x92\x2a\xab\x9b\x11\xcb\x48\x18\xa1\xa9\x0d\xd5\x18" diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 3921fbed0b28..51421fdbb0ba 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -17,10 +17,12 @@ * build_OID_registry.pl to generate the data for look_up_OID(). */ enum OID { + OID_id_dsa_with_sha1, /* 1.2.840.10030.4.3 */ OID_id_dsa, /* 1.2.840.10040.4.1 */ OID_id_ecPublicKey, /* 1.2.840.10045.2.1 */ OID_id_prime192v1, /* 1.2.840.10045.3.1.1 */ OID_id_prime256v1, /* 1.2.840.10045.3.1.7 */ + OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */ OID_id_ecdsa_with_sha224, /* 1.2.840.10045.4.3.1 */ OID_id_ecdsa_with_sha256, /* 1.2.840.10045.4.3.2 */ OID_id_ecdsa_with_sha384, /* 1.2.840.10045.4.3.3 */ @@ -28,6 +30,7 @@ enum OID { /* PKCS#1 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-1(1)} */ OID_rsaEncryption, /* 1.2.840.113549.1.1.1 */ + OID_sha1WithRSAEncryption, /* 1.2.840.113549.1.1.5 */ OID_sha256WithRSAEncryption, /* 1.2.840.113549.1.1.11 */ OID_sha384WithRSAEncryption, /* 1.2.840.113549.1.1.12 */ OID_sha512WithRSAEncryption, /* 1.2.840.113549.1.1.13 */ @@ -64,6 +67,7 @@ enum OID { OID_PKU2U, /* 1.3.5.1.5.2.7 */ OID_Scram, /* 1.3.6.1.5.5.14 */ OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ + OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 0ea1b2970a23..28db5b7589eb 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -236,6 +236,10 @@ choice possible to load a signed module containing the algorithm to check the signature on that module. +config MODULE_SIG_SHA1 + bool "Sign modules with SHA-1" + select CRYPTO_SHA1 + config MODULE_SIG_SHA256 bool "Sign modules with SHA-256" select CRYPTO_SHA256 @@ -265,6 +269,7 @@ endchoice config MODULE_SIG_HASH string depends on MODULE_SIG || IMA_APPRAISE_MODSIG + default "sha1" if MODULE_SIG_SHA1 default "sha256" if MODULE_SIG_SHA256 default "sha384" if MODULE_SIG_SHA384 default "sha512" if MODULE_SIG_SHA512 -- cgit v1.2.3 From f7f5d1808b1b66935a24dd796dd1a0612ca9c147 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Thu, 21 Mar 2024 15:39:39 +0000 Subject: bpf: verifier: fix addr_space_cast from as(1) to as(0) The verifier currently converts addr_space_cast from as(1) to as(0) that is: BPF_ALU64 | BPF_MOV | BPF_X with off=1 and imm=1 to BPF_ALU | BPF_MOV | BPF_X with imm=1 (32-bit mov) Because of this imm=1, the JITs that have bpf_jit_needs_zext() == true, interpret the converted instruction as BPF_ZEXT_REG(DST) which is a special form of mov32, used for doing explicit zero extension on dst. These JITs will just zero extend the dst reg and will not move the src to dst before the zext. Fix do_misc_fixups() to set imm=0 when converting addr_space_cast to a normal mov32. The JITs that have bpf_jit_needs_zext() == true rely on the verifier to emit zext instructions. Mark dst_reg as subreg when doing cast from as(1) to as(0) so the verifier emits a zext instruction after the mov. Fixes: 6082b6c328b5 ("bpf: Recognize addr_space_cast instruction in the verifier.") Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20240321153939.113996-1-puranjay12@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1dd3b99d1bb9..2cd7e0e79283 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14054,8 +14054,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (insn->imm) { /* off == BPF_ADDR_SPACE_CAST */ mark_reg_unknown(env, regs, insn->dst_reg); - if (insn->imm == 1) /* cast from as(1) to as(0) */ + if (insn->imm == 1) { /* cast from as(1) to as(0) */ dst_reg->type = PTR_TO_ARENA; + /* PTR_TO_ARENA is 32-bit */ + dst_reg->subreg_def = env->insn_idx + 1; + } } else if (insn->off == 0) { /* case: R1 = R2 * copy register state to dest reg @@ -19609,8 +19612,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env) (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) { /* convert to 32-bit mov that clears upper 32-bit */ insn->code = BPF_ALU | BPF_MOV | BPF_X; - /* clear off, so it's a normal 'wX = wY' from JIT pov */ + /* clear off and imm, so it's a normal 'wX = wY' from JIT pov */ insn->off = 0; + insn->imm = 0; } /* cast from as(0) to as(1) should be handled by JIT */ goto next_insn; } -- cgit v1.2.3 From 122fdbd2a030a95128737fc77e47df15a8f170c3 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Fri, 22 Mar 2024 15:35:18 +0000 Subject: bpf: verifier: reject addr_space_cast insn without arena The verifier allows using the addr_space_cast instruction in a program that doesn't have an associated arena. This was caught in the form an invalid memory access in do_misc_fixups() when while converting addr_space_cast to a normal 32-bit mov, env->prog->aux->arena was dereferenced to check for BPF_F_NO_USER_CONV flag. Reject programs that include the addr_space_cast instruction but don't have an associated arena. root@rv-tester:~# ./reproducer Unable to handle kernel access to user memory without uaccess routines at virtual address 0000000000000030 Oops [#1] [] do_misc_fixups+0x43c/0x1168 [] bpf_check+0xda8/0x22b6 [] bpf_prog_load+0x486/0x8dc [] __sys_bpf+0xbd8/0x214e [] __riscv_sys_bpf+0x22/0x2a [] do_trap_ecall_u+0x102/0x17c [] ret_from_exception+0x0/0x64 Fixes: 6082b6c328b5 ("bpf: Recognize addr_space_cast instruction in the verifier.") Reported-by: xingwei lee Reported-by: yue sun Closes: https://lore.kernel.org/bpf/CABOYnLz09O1+2gGVJuCxd_24a-7UueXzV-Ff+Fr+h5EKFDiYCQ@mail.gmail.com/ Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20240322153518.11555-1-puranjay12@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2cd7e0e79283..0bfc0050db28 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14022,6 +14022,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n"); return -EINVAL; } + if (!env->prog->aux->arena) { + verbose(env, "addr_space_cast insn can only be used in a program that has an associated arena\n"); + return -EINVAL; + } } else { if ((insn->off != 0 && insn->off != 8 && insn->off != 16 && insn->off != 32) || insn->imm) { -- cgit v1.2.3 From 0add699ad068d26e5b1da9ff28b15461fc4005df Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu (Google) Date: Wed, 20 Mar 2024 17:10:38 +0900 Subject: tracing: probes: Fix to zero initialize a local variable Fix to initialize 'val' local variable with zero. Dan reported that Smatch static code checker reports an error that a local 'val' variable needs to be initialized. Actually, the 'val' is expected to be initialized by FETCH_OP_ARG in the same loop, but it is not obvious. So initialize it with zero. Link: https://lore.kernel.org/all/171092223833.237219.17304490075697026697.stgit@devnote2/ Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/b010488e-68aa-407c-add0-3e059254aaa0@moroto.mountain/ Fixes: 25f00e40ce79 ("tracing/probes: Support $argN in return probe (kprobe and fprobe)") Reviewed-by: Steven Rostedt (Google) Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_probe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 217169de0920..dfe3ee6035ec 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -839,7 +839,7 @@ out: void store_trace_entry_data(void *edata, struct trace_probe *tp, struct pt_regs *regs) { struct probe_entry_arg *earg = tp->entry_arg; - unsigned long val; + unsigned long val = 0; int i; if (!earg) -- cgit v1.2.3 From c2ddeb29612f7ca84ed10c6d4f3ac99705135447 Mon Sep 17 00:00:00 2001 From: Rafael J. Wysocki Date: Mon, 25 Mar 2024 13:58:08 +0100 Subject: genirq: Introduce IRQF_COND_ONESHOT and use it in pinctrl-amd There is a problem when a driver requests a shared interrupt line to run a threaded handler on it without IRQF_ONESHOT set if that flag has been set already for the IRQ in question by somebody else. Namely, the request fails which usually leads to a probe failure even though the driver might have worked just fine with IRQF_ONESHOT, but it does not want to use it by default. Currently, the only way to handle this is to try to request the IRQ without IRQF_ONESHOT, but with IRQF_PROBE_SHARED set and if this fails, try again with IRQF_ONESHOT set. However, this is a bit cumbersome and not very clean. When commit 7a36b901a6eb ("ACPI: OSL: Use a threaded interrupt handler for SCI") switched the ACPI subsystem over to using a threaded interrupt handler for the SCI, it had to use IRQF_ONESHOT for it because that's required due to the way the SCI handler works (it needs to walk all of the enabled GPEs before the interrupt line can be unmasked). The SCI interrupt line is not shared with other users very often due to the SCI handling overhead, but on sone systems it is shared and when the other user of it attempts to install a threaded handler, a flags mismatch related to IRQF_ONESHOT may occur. As it turned out, that happened to the pinctrl-amd driver and so commit 4451e8e8415e ("pinctrl: amd: Add IRQF_ONESHOT to the interrupt request") attempted to address the issue by adding IRQF_ONESHOT to the interrupt flags in that driver, but this is now causing an IRQF_ONESHOT-related mismatch to occur on another system which cannot boot as a result of it. Clearly, pinctrl-amd can work with IRQF_ONESHOT if need be, but it should not set that flag by default, so it needs a way to indicate that to the interrupt subsystem. To that end, introdcuce a new interrupt flag, IRQF_COND_ONESHOT, which will only have effect when the IRQ line is shared and IRQF_ONESHOT has been set for it already, in which case it will be promoted to the latter. This is sufficient for drivers sharing the interrupt line with the SCI as it is requested by the ACPI subsystem before any drivers are probed, so they will always see IRQF_ONESHOT set for the interrupt in question. Fixes: 4451e8e8415e ("pinctrl: amd: Add IRQF_ONESHOT to the interrupt request") Reported-by: Francisco Ayala Le Brun Signed-off-by: Rafael J. Wysocki Signed-off-by: Thomas Gleixner Reviewed-by: Linus Walleij Cc: 6.8+ # 6.8+ Closes: https://lore.kernel.org/lkml/CAN-StX1HqWqi+YW=t+V52-38Mfp5fAz7YHx4aH-CQjgyNiKx3g@mail.gmail.com/ Link: https://lore.kernel.org/r/12417336.O9o76ZdvQC@kreacher --- drivers/pinctrl/pinctrl-amd.c | 2 +- include/linux/interrupt.h | 3 +++ kernel/irq/manage.c | 9 +++++++-- 3 files changed, 11 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 49f89b70dcec..7f66ec73199a 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -1159,7 +1159,7 @@ static int amd_gpio_probe(struct platform_device *pdev) } ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler, - IRQF_SHARED | IRQF_ONESHOT, KBUILD_MODNAME, gpio_dev); + IRQF_SHARED | IRQF_COND_ONESHOT, KBUILD_MODNAME, gpio_dev); if (ret) goto out2; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 76121c2bb4f8..5c9bdd3ffccc 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -67,6 +67,8 @@ * later. * IRQF_NO_DEBUG - Exclude from runnaway detection for IPI and similar handlers, * depends on IRQF_PERCPU. + * IRQF_COND_ONESHOT - Agree to do IRQF_ONESHOT if already set for a shared + * interrupt. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 @@ -82,6 +84,7 @@ #define IRQF_COND_SUSPEND 0x00040000 #define IRQF_NO_AUTOEN 0x00080000 #define IRQF_NO_DEBUG 0x00100000 +#define IRQF_COND_ONESHOT 0x00200000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ad3eaf2ab959..bf9ae8a8686f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1643,8 +1643,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!((old->flags & new->flags) & IRQF_SHARED) || - (oldtype != (new->flags & IRQF_TRIGGER_MASK)) || - ((old->flags ^ new->flags) & IRQF_ONESHOT)) + (oldtype != (new->flags & IRQF_TRIGGER_MASK))) + goto mismatch; + + if ((old->flags & IRQF_ONESHOT) && + (new->flags & IRQF_COND_ONESHOT)) + new->flags |= IRQF_ONESHOT; + else if ((old->flags ^ new->flags) & IRQF_ONESHOT) goto mismatch; /* All handlers must agree on per-cpuness */ -- cgit v1.2.3 From d5aad4c2ca057e760a92a9a7d65bd38d72963f27 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Mon, 26 Feb 2024 17:35:41 -0800 Subject: prctl: generalize PR_SET_MDWE support check to be per-arch Patch series "ARM: prctl: Reject PR_SET_MDWE where not supported". I noticed after a recent kernel update that my ARM926 system started segfaulting on any execve() after calling prctl(PR_SET_MDWE). After some investigation it appears that ARMv5 is incapable of providing the appropriate protections for MDWE, since any readable memory is also implicitly executable. The prctl_set_mdwe() function already had some special-case logic added disabling it on PARISC (commit 793838138c15, "prctl: Disable prctl(PR_SET_MDWE) on parisc"); this patch series (1) generalizes that check to use an arch_*() function, and (2) adds a corresponding override for ARM to disable MDWE on pre-ARMv6 CPUs. With the series applied, prctl(PR_SET_MDWE) is rejected on ARMv5 and subsequent execve() calls (as well as mmap(PROT_READ|PROT_WRITE)) can succeed instead of unconditionally failing; on ARMv6 the prctl works as it did previously. [0] https://lore.kernel.org/all/2023112456-linked-nape-bf19@gregkh/ This patch (of 2): There exist systems other than PARISC where MDWE may not be feasible to support; rather than cluttering up the generic code with additional arch-specific logic let's add a generic function for checking MDWE support and allow each arch to override it as needed. Link: https://lkml.kernel.org/r/20240227013546.15769-4-zev@bewilderbeest.net Link: https://lkml.kernel.org/r/20240227013546.15769-5-zev@bewilderbeest.net Signed-off-by: Zev Weiss Acked-by: Helge Deller [parisc] Cc: Borislav Petkov Cc: David Hildenbrand Cc: Florent Revest Cc: "James E.J. Bottomley" Cc: Josh Triplett Cc: Kees Cook Cc: Miguel Ojeda Cc: Mike Rapoport (IBM) Cc: Oleg Nesterov Cc: Ondrej Mosnacek Cc: Rick Edgecombe Cc: Russell King (Oracle) Cc: Sam James Cc: Stefan Roesch Cc: Yang Shi Cc: Yin Fengwei Cc: [6.3+] Signed-off-by: Andrew Morton --- arch/parisc/include/asm/mman.h | 14 ++++++++++++++ include/linux/mman.h | 8 ++++++++ kernel/sys.c | 7 +++++-- 3 files changed, 27 insertions(+), 2 deletions(-) create mode 100644 arch/parisc/include/asm/mman.h (limited to 'kernel') diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h new file mode 100644 index 000000000000..47c5a1991d10 --- /dev/null +++ b/arch/parisc/include/asm/mman.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include + +/* PARISC cannot allow mdwe as it needs writable stacks */ +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return false; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported + +#endif /* __ASM_MMAN_H__ */ diff --git a/include/linux/mman.h b/include/linux/mman.h index dc7048824be8..bcb201ab7a41 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -162,6 +162,14 @@ calc_vm_flag_bits(unsigned long flags) unsigned long vm_commit_limit(void); +#ifndef arch_memory_deny_write_exec_supported +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return true; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported +#endif + /* * Denies creating a writable executable mapping or gaining executable permissions. * diff --git a/kernel/sys.c b/kernel/sys.c index f8e543f1e38a..8bb106a56b3a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2408,8 +2408,11 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; - /* PARISC cannot allow mdwe as it needs writable stacks */ - if (IS_ENABLED(CONFIG_PARISC)) + /* + * EOPNOTSUPP might be more appropriate here in principle, but + * existing userspace depends on EINVAL specifically. + */ + if (!arch_memory_deny_write_exec_supported()) return -EINVAL; current_bits = get_current_mdwe(); -- cgit v1.2.3 From 32fbe5246582af4f611ccccee33fd6e559087252 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Mon, 25 Mar 2024 09:50:50 +0800 Subject: crash: use macro to add crashk_res into iomem early for specific arch There are regression reports[1][2] that crashkernel region on x86_64 can't be added into iomem tree sometime. This causes the later failure of kdump loading. This happened after commit 4a693ce65b18 ("kdump: defer the insertion of crashkernel resources") was merged. Even though, these reported issues are proved to be related to other component, they are just exposed after above commmit applied, I still would like to keep crashk_res and crashk_low_res being added into iomem early as before because the early adding has been always there on x86_64 and working very well. For safety of kdump, Let's change it back. Here, add a macro HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY to limit that only ARCH defining the macro can have the early adding crashk_res/_low_res into iomem. Then define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY on x86 to enable it. Note: In reserve_crashkernel_low(), there's a remnant of crashk_low_res handling which was mistakenly added back in commit 85fcde402db1 ("kexec: split crashkernel reservation code out from crash_core.c"). [1] [PATCH V2] x86/kexec: do not update E820 kexec table for setup_data https://lore.kernel.org/all/Zfv8iCL6CT2JqLIC@darkstar.users.ipa.redhat.com/T/#u [2] Question about Address Range Validation in Crash Kernel Allocation https://lore.kernel.org/all/4eeac1f733584855965a2ea62fa4da58@huawei.com/T/#u Link: https://lkml.kernel.org/r/ZgDYemRQ2jxjLkq+@MiWiFi-R3L-srv Fixes: 4a693ce65b18 ("kdump: defer the insertion of crashkernel resources") Signed-off-by: Baoquan He Cc: Dave Young Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiri Bohac Cc: Li Huafei Cc: Signed-off-by: Andrew Morton --- arch/x86/include/asm/crash_reserve.h | 2 ++ kernel/crash_reserve.c | 7 +++++++ 2 files changed, 9 insertions(+) (limited to 'kernel') diff --git a/arch/x86/include/asm/crash_reserve.h b/arch/x86/include/asm/crash_reserve.h index 152239f95541..7835b2cdff04 100644 --- a/arch/x86/include/asm/crash_reserve.h +++ b/arch/x86/include/asm/crash_reserve.h @@ -39,4 +39,6 @@ static inline unsigned long crash_low_size_default(void) #endif } +#define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY + #endif /* _X86_CRASH_RESERVE_H */ diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index bbb6c3cb00e4..066668799f75 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -366,7 +366,9 @@ static int __init reserve_crashkernel_low(unsigned long long low_size) crashk_low_res.start = low_base; crashk_low_res.end = low_base + low_size - 1; +#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY insert_resource(&iomem_resource, &crashk_low_res); +#endif #endif return 0; } @@ -448,8 +450,12 @@ retry: crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; +#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY + insert_resource(&iomem_resource, &crashk_res); +#endif } +#ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY static __init int insert_crashkernel_resources(void) { if (crashk_res.start < crashk_res.end) @@ -462,3 +468,4 @@ static __init int insert_crashkernel_resources(void) } early_initcall(insert_crashkernel_resources); #endif +#endif -- cgit v1.2.3 From 96b98a6552a90690d7bc18dd71b66312c9ded1fb Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 19 Mar 2024 13:31:52 +0530 Subject: bpf: fix warning for crash_kexec With [1], crash dump specific code is moved out of CONFIG_KEXEC_CORE and placed under CONFIG_CRASH_DUMP, where it is more appropriate. And since CONFIG_KEXEC & !CONFIG_CRASH_DUMP build option is supported with that, it led to the below warning: "WARN: resolve_btfids: unresolved symbol crash_kexec" Fix it by using the appropriate #ifdef. [1] https://lore.kernel.org/all/20240124051254.67105-1-bhe@redhat.com/ Acked-by: Baoquan He Fixes: 02aff8480533 ("crash: split crash dumping code out from kexec_core.c") Acked-by: Jiri Olsa Acked-by: Stanislav Fomichev Signed-off-by: Hari Bathini Link: https://lore.kernel.org/r/20240319080152.36987-1-hbathini@linux.ibm.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/helpers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a89587859571..449b9a5d3fe3 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2548,7 +2548,7 @@ __bpf_kfunc void bpf_throw(u64 cookie) __bpf_kfunc_end_defs(); BTF_KFUNCS_START(generic_btf_ids) -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) #endif BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL) -- cgit v1.2.3 From 5b4cdd9c5676559b8a7c944ac5269b914b8c0bb8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 26 Mar 2024 14:59:48 -0700 Subject: Fix memory leak in posix_clock_open() If the clk ops.open() function returns an error, we don't release the pccontext we allocated for this clock. Re-organize the code slightly to make it all more obvious. Reported-by: Rohit Keshri Acked-by: Oleg Nesterov Fixes: 60c6946675fc ("posix-clock: introduce posix_clock_context concept") Cc: Jakub Kicinski Cc: David S. Miller Cc: Thomas Gleixner Signed-off-by: Linus Torvalds --- kernel/time/posix-clock.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 9de66bbbb3d1..4782edcbe7b9 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -129,15 +129,17 @@ static int posix_clock_open(struct inode *inode, struct file *fp) goto out; } pccontext->clk = clk; - fp->private_data = pccontext; - if (clk->ops.open) + if (clk->ops.open) { err = clk->ops.open(pccontext, fp->f_mode); - else - err = 0; - - if (!err) { - get_device(clk->dev); + if (err) { + kfree(pccontext); + goto out; + } } + + fp->private_data = pccontext; + get_device(clk->dev); + err = 0; out: up_read(&clk->rwsem); return err; -- cgit v1.2.3 From a8d89feba7e54e691ca7c4efc2a6264fa83f3687 Mon Sep 17 00:00:00 2001 From: Andrei Matei Date: Tue, 26 Mar 2024 22:42:44 -0400 Subject: bpf: Check bloom filter map value size This patch adds a missing check to bloom filter creating, rejecting values above KMALLOC_MAX_SIZE. This brings the bloom map in line with many other map types. The lack of this protection can cause kernel crashes for value sizes that overflow int's. Such a crash was caught by syzkaller. The next patch adds more guard-rails at a lower level. Signed-off-by: Andrei Matei Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240327024245.318299-2-andreimatei1@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/bloom_filter.c | 13 +++++++++++++ tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c | 6 ++++++ 2 files changed, 19 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index addf3dd57b59..35e1ddca74d2 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -80,6 +80,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key return -EOPNOTSUPP; } +/* Called from syscall */ +static int bloom_map_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; @@ -191,6 +203,7 @@ static u64 bloom_map_mem_usage(const struct bpf_map *map) BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bloom_map_alloc_check, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index 053f4d6da77a..cc184e4420f6 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -2,6 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include +#include #include #include "bloom_filter_map.skel.h" @@ -21,6 +22,11 @@ static void test_fail_cases(void) if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0")) close(fd); + /* Invalid value size: too big */ + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, INT32_MAX, 100, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value too large")) + close(fd); + /* Invalid max entries size */ fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL); if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size")) -- cgit v1.2.3 From ecc6a2101840177e57c925c102d2d29f260d37c8 Mon Sep 17 00:00:00 2001 From: Andrei Matei Date: Tue, 26 Mar 2024 22:42:45 -0400 Subject: bpf: Protect against int overflow for stack access size This patch re-introduces protection against the size of access to stack memory being negative; the access size can appear negative as a result of overflowing its signed int representation. This should not actually happen, as there are other protections along the way, but we should protect against it anyway. One code path was missing such protections (fixed in the previous patch in the series), causing out-of-bounds array accesses in check_stack_range_initialized(). This patch causes the verification of a program with such a non-sensical access size to fail. This check used to exist in a more indirect way, but was inadvertendly removed in a833a17aeac7. Fixes: a833a17aeac7 ("bpf: Fix verification of indirect var-off stack access") Reported-by: syzbot+33f4297b5f927648741a@syzkaller.appspotmail.com Reported-by: syzbot+aafd0513053a1cbf52ef@syzkaller.appspotmail.com Closes: https://lore.kernel.org/bpf/CAADnVQLORV5PT0iTAhRER+iLBTkByCYNBYyvBSgjN1T31K+gOw@mail.gmail.com/ Acked-by: Andrii Nakryiko Signed-off-by: Andrei Matei Link: https://lore.kernel.org/r/20240327024245.318299-3-andreimatei1@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0bfc0050db28..353985b2b6a2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6701,6 +6701,11 @@ static int check_stack_access_within_bounds( err = check_stack_slot_within_bounds(env, min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ + if (!err && access_size < 0) + /* access_size should not be negative (or overflow an int); others checks + * along the way should have prevented such an access. + */ + err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { -- cgit v1.2.3 From c40845e3195d074b34f8f8e400e28c9403a06588 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 26 Mar 2024 15:47:16 +0100 Subject: kbuild: make -Woverride-init warnings more consistent The -Woverride-init warn about code that may be intentional or not, but the inintentional ones tend to be real bugs, so there is a bit of disagreement on whether this warning option should be enabled by default and we have multiple settings in scripts/Makefile.extrawarn as well as individual subsystems. Older versions of clang only supported -Wno-initializer-overrides with the same meaning as gcc's -Woverride-init, though all supported versions now work with both. Because of this difference, an earlier cleanup of mine accidentally turned the clang warning off for W=1 builds and only left it on for W=2, while it's still enabled for gcc with W=1. There is also one driver that only turns the warning off for newer versions of gcc but not other compilers, and some but not all the Makefiles still use a cc-disable-warning conditional that is no longer needed with supported compilers here. Address all of the above by removing the special cases for clang and always turning the warning off unconditionally where it got in the way, using the syntax that is supported by both compilers. Fixes: 2cd3271b7a31 ("kbuild: avoid duplicate warning options") Signed-off-by: Arnd Bergmann Acked-by: Hamza Mahfooz Acked-by: Jani Nikula Acked-by: Andrew Jeffery Signed-off-by: Jani Nikula Reviewed-by: Linus Walleij Signed-off-by: Masahiro Yamada --- drivers/gpu/drm/amd/display/dc/dce110/Makefile | 2 +- drivers/gpu/drm/amd/display/dc/dce112/Makefile | 2 +- drivers/gpu/drm/amd/display/dc/dce120/Makefile | 2 +- drivers/gpu/drm/amd/display/dc/dce60/Makefile | 2 +- drivers/gpu/drm/amd/display/dc/dce80/Makefile | 2 +- drivers/gpu/drm/i915/Makefile | 6 +++--- drivers/gpu/drm/xe/Makefile | 4 ++-- drivers/net/ethernet/renesas/sh_eth.c | 2 +- drivers/pinctrl/aspeed/Makefile | 2 +- fs/proc/Makefile | 2 +- kernel/bpf/Makefile | 2 +- mm/Makefile | 3 +-- scripts/Makefile.extrawarn | 10 +++------- 13 files changed, 18 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/drivers/gpu/drm/amd/display/dc/dce110/Makefile b/drivers/gpu/drm/amd/display/dc/dce110/Makefile index f0777d61c2cb..c307f040e48f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce110/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'controller' sub-component of DAL. # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = -Wno-override-init DCE110 = dce110_timing_generator.o \ dce110_compressor.o dce110_opp_regamma_v.o \ diff --git a/drivers/gpu/drm/amd/display/dc/dce112/Makefile b/drivers/gpu/drm/amd/display/dc/dce112/Makefile index 7e92effec894..683866797709 100644 --- a/drivers/gpu/drm/amd/display/dc/dce112/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce112/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'controller' sub-component of DAL. # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = -Wno-override-init DCE112 = dce112_compressor.o diff --git a/drivers/gpu/drm/amd/display/dc/dce120/Makefile b/drivers/gpu/drm/amd/display/dc/dce120/Makefile index 1e3ef68a452a..8f508e662748 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce120/Makefile @@ -24,7 +24,7 @@ # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = -Wno-override-init DCE120 = dce120_timing_generator.o diff --git a/drivers/gpu/drm/amd/display/dc/dce60/Makefile b/drivers/gpu/drm/amd/display/dc/dce60/Makefile index fee331accc0e..eede83ad91fa 100644 --- a/drivers/gpu/drm/amd/display/dc/dce60/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce60/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'controller' sub-component of DAL. # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = -Wno-override-init DCE60 = dce60_timing_generator.o dce60_hw_sequencer.o \ dce60_resource.o diff --git a/drivers/gpu/drm/amd/display/dc/dce80/Makefile b/drivers/gpu/drm/amd/display/dc/dce80/Makefile index 7eefffbdc925..fba189d26652 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce80/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'controller' sub-component of DAL. # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = -Wno-override-init DCE80 = dce80_timing_generator.o diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 3ef6ed41e62b..4c2f85632391 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -33,9 +33,9 @@ endif subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror # Fine grained warnings disable -CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init) -CFLAGS_display/intel_display_device.o = $(call cc-disable-warning, override-init) -CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init) +CFLAGS_i915_pci.o = -Wno-override-init +CFLAGS_display/intel_display_device.o = -Wno-override-init +CFLAGS_display/intel_fbdev.o = -Wno-override-init # Support compiling the display code separately for both i915 and xe # drivers. Define I915 when building i915. diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 5a428ca00f10..c29a850859ad 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -172,8 +172,8 @@ subdir-ccflags-$(CONFIG_DRM_XE_DISPLAY) += \ -Ddrm_i915_gem_object=xe_bo \ -Ddrm_i915_private=xe_device -CFLAGS_i915-display/intel_fbdev.o = $(call cc-disable-warning, override-init) -CFLAGS_i915-display/intel_display_device.o = $(call cc-disable-warning, override-init) +CFLAGS_i915-display/intel_fbdev.o = -Wno-override-init +CFLAGS_i915-display/intel_display_device.o = -Wno-override-init # Rule to build SOC code shared with i915 $(obj)/i915-soc/%.o: $(srctree)/drivers/gpu/drm/i915/soc/%.c FORCE diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 475e1e8c1d35..0786eb0da391 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -50,7 +50,7 @@ * the macros available to do this only define GCC 8. */ __diag_push(); -__diag_ignore(GCC, 8, "-Woverride-init", +__diag_ignore_all("-Woverride-init", "logic to initialize all and then override some is OK"); static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = { SH_ETH_OFFSET_DEFAULTS, diff --git a/drivers/pinctrl/aspeed/Makefile b/drivers/pinctrl/aspeed/Makefile index 489ea1778353..db2a7600ae2b 100644 --- a/drivers/pinctrl/aspeed/Makefile +++ b/drivers/pinctrl/aspeed/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only # Aspeed pinctrl support -ccflags-y += $(call cc-option,-Woverride-init) +ccflags-y += -Woverride-init obj-$(CONFIG_PINCTRL_ASPEED) += pinctrl-aspeed.o pinmux-aspeed.o obj-$(CONFIG_PINCTRL_ASPEED_G4) += pinctrl-aspeed-g4.o obj-$(CONFIG_PINCTRL_ASPEED_G5) += pinctrl-aspeed-g5.o diff --git a/fs/proc/Makefile b/fs/proc/Makefile index bd08616ed8ba..7b4db9c56e6a 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -5,7 +5,7 @@ obj-y += proc.o -CFLAGS_task_mmu.o += $(call cc-option,-Wno-override-init,) +CFLAGS_task_mmu.o += -Wno-override-init proc-y := nommu.o task_nommu.o proc-$(CONFIG_MMU) := task_mmu.o diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 368c5d86b5b7..e497011261b8 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,7 +4,7 @@ ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y) # ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif -CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) +CFLAGS_core.o += -Wno-override-init $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o diff --git a/mm/Makefile b/mm/Makefile index e4b5b75aaec9..4abb40b911ec 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -29,8 +29,7 @@ KCOV_INSTRUMENT_mmzone.o := n KCOV_INSTRUMENT_vmstat.o := n KCOV_INSTRUMENT_failslab.o := n -CFLAGS_init-mm.o += $(call cc-disable-warning, override-init) -CFLAGS_init-mm.o += $(call cc-disable-warning, initializer-overrides) +CFLAGS_init-mm.o += -Wno-override-init mmu-y := nommu.o mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \ diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 3ce5d503a6da..c5af566e911a 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -114,6 +114,8 @@ KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) +KBUILD_CFLAGS += -Wno-override-init # alias for -Wno-initializer-overrides in clang + ifdef CONFIG_CC_IS_CLANG # Clang before clang-16 would warn on default argument promotions. ifneq ($(call clang-min-version, 160000),y) @@ -151,10 +153,6 @@ KBUILD_CFLAGS += -Wtype-limits KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized) KBUILD_CFLAGS += $(call cc-option, -Wunused-macros) -ifdef CONFIG_CC_IS_CLANG -KBUILD_CFLAGS += -Winitializer-overrides -endif - KBUILD_CPPFLAGS += -DKBUILD_EXTRA_WARN2 else @@ -164,9 +162,7 @@ KBUILD_CFLAGS += -Wno-missing-field-initializers KBUILD_CFLAGS += -Wno-type-limits KBUILD_CFLAGS += -Wno-shift-negative-value -ifdef CONFIG_CC_IS_CLANG -KBUILD_CFLAGS += -Wno-initializer-overrides -else +ifdef CONFIG_CC_IS_GCC KBUILD_CFLAGS += -Wno-maybe-uninitialized endif -- cgit v1.2.3