From 5d0489636352a26b9622ff1b1bf0c899f6a02805 Mon Sep 17 00:00:00 2001 From: fanglifei Date: Tue, 27 Aug 2024 17:29:07 +0800 Subject: [PATCH 159/219] feat: A series patch applyed for mmu Changelogs: Patch sync from below link: https://github.com/eswincomputing/linux-stable/pull/5/commits which are not adopted by official release. Signed-off-by: fanglifei --- .../membarrier-sync-core/arch-support.txt | 18 ++++++++- Documentation/scheduler/index.rst | 1 + Documentation/scheduler/membarrier.rst | 39 +++++++++++++++++++ MAINTAINERS | 2 + arch/riscv/Kconfig | 3 ++ arch/riscv/include/asm/membarrier.h | 19 +++++++++ arch/riscv/include/asm/sync_core.h | 29 ++++++++++++++ arch/riscv/mm/pgtable.c | 2 + include/linux/sync_core.h | 16 +++++++- init/Kconfig | 3 ++ kernel/sched/core.c | 11 +++++- kernel/sched/membarrier.c | 13 +++++-- 12 files changed, 149 insertions(+), 7 deletions(-) create mode 100644 Documentation/scheduler/membarrier.rst create mode 100644 arch/riscv/include/asm/sync_core.h diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt index 23260ca44946..76597adfb7d5 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. @@ -44,7 +60,7 @@ | openrisc: | TODO | | parisc: | TODO | | powerpc: | ok | - | riscv: | TODO | + | riscv: | ok | | s390: | ok | | sh: | TODO | | sparc: | TODO | 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 ae4c0cec5073..574a2c203380 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13702,7 +13702,9 @@ 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: 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 1db237dc24cf..37e9be504566 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/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c index ef887efcb679..21ea6ed76470 100644 --- a/arch/riscv/mm/pgtable.c +++ b/arch/riscv/mm/pgtable.c @@ -36,6 +36,7 @@ pud_t *pud_offset(p4d_t *p4d, unsigned long address) return (pud_t *)p4d; } +EXPORT_SYMBOL_GPL(pud_offset); p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { @@ -44,6 +45,7 @@ p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) return (p4d_t *)pgd; } +EXPORT_SYMBOL_GPL(p4d_offset); #endif #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP 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 60ed7713b5ee..18176301c6b9 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1994,6 +1994,9 @@ 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/core.c b/kernel/sched/core.c index 228f7c07da72..278d7390594e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6605,7 +6605,9 @@ 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(); @@ -6683,6 +6685,13 @@ 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. + * + * 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 4e715b9b278e..809194cd779f 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -254,7 +254,7 @@ 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. */ @@ -304,7 +304,7 @@ 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 */ @@ -324,6 +324,7 @@ 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; @@ -343,8 +344,12 @@ 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. + * + * 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. */ @@ -420,7 +425,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) /* * 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 */ -- 2.47.0