From cbe82e140bb76e1aa9f808cc841654a25b70d4e5 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Sun, 3 Nov 2024 15:51:49 +0100 Subject: asm-generic: ticket-lock: Reuse arch_spinlock_t of qspinlock The arch_spinlock_t of qspinlock has contained the atomic_t val, which satisfies the ticket-lock requirement. Thus, unify the arch_spinlock_t into qspinlock_types.h. This is the preparation for the next combo spinlock. Reviewed-by: Leonardo Bras Suggested-by: Arnd Bergmann Link: https://lore.kernel.org/linux-riscv/CAK8P3a2rnz9mQqhN6-e0CGUUv9rntRELFdxt_weiD7FxH7fkfQ@mail.gmail.com/ Signed-off-by: Guo Ren Signed-off-by: Guo Ren Acked-by: Peter Zijlstra (Intel) Reviewed-by: Andrew Jones Reviewed-by: Andrea Parri Link: https://lore.kernel.org/r/20241103145153.105097-10-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- include/asm-generic/spinlock.h | 14 +++++++------- include/asm-generic/spinlock_types.h | 12 ++---------- 2 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h index 90803a826ba0..4773334ee638 100644 --- a/include/asm-generic/spinlock.h +++ b/include/asm-generic/spinlock.h @@ -32,7 +32,7 @@ static __always_inline void arch_spin_lock(arch_spinlock_t *lock) { - u32 val = atomic_fetch_add(1<<16, lock); + u32 val = atomic_fetch_add(1<<16, &lock->val); u16 ticket = val >> 16; if (ticket == (u16)val) @@ -46,31 +46,31 @@ static __always_inline void arch_spin_lock(arch_spinlock_t *lock) * have no outstanding writes due to the atomic_fetch_add() the extra * orderings are free. */ - atomic_cond_read_acquire(lock, ticket == (u16)VAL); + atomic_cond_read_acquire(&lock->val, ticket == (u16)VAL); smp_mb(); } static __always_inline bool arch_spin_trylock(arch_spinlock_t *lock) { - u32 old = atomic_read(lock); + u32 old = atomic_read(&lock->val); if ((old >> 16) != (old & 0xffff)) return false; - return atomic_try_cmpxchg(lock, &old, old + (1<<16)); /* SC, for RCsc */ + return atomic_try_cmpxchg(&lock->val, &old, old + (1<<16)); /* SC, for RCsc */ } static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) { u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); - u32 val = atomic_read(lock); + u32 val = atomic_read(&lock->val); smp_store_release(ptr, (u16)val + 1); } static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) { - u32 val = lock.counter; + u32 val = lock.val.counter; return ((val >> 16) == (val & 0xffff)); } @@ -84,7 +84,7 @@ static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock) static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock) { - u32 val = atomic_read(lock); + u32 val = atomic_read(&lock->val); return (s16)((val >> 16) - (val & 0xffff)) > 1; } diff --git a/include/asm-generic/spinlock_types.h b/include/asm-generic/spinlock_types.h index 8962bb730945..f534aa5de394 100644 --- a/include/asm-generic/spinlock_types.h +++ b/include/asm-generic/spinlock_types.h @@ -3,15 +3,7 @@ #ifndef __ASM_GENERIC_SPINLOCK_TYPES_H #define __ASM_GENERIC_SPINLOCK_TYPES_H -#include -typedef atomic_t arch_spinlock_t; - -/* - * qrwlock_types depends on arch_spinlock_t, so we must typedef that before the - * include. - */ -#include - -#define __ARCH_SPIN_LOCK_UNLOCKED ATOMIC_INIT(0) +#include +#include #endif /* __ASM_GENERIC_SPINLOCK_TYPES_H */ -- cgit v1.2.3 From 22c33321e260c8b4c1877b2cc0c4e26a0c74c23f Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Sun, 3 Nov 2024 15:51:50 +0100 Subject: asm-generic: ticket-lock: Add separate ticket-lock.h Add a separate ticket-lock.h to include multiple spinlock versions and select one at compile time or runtime. Reviewed-by: Leonardo Bras Suggested-by: Arnd Bergmann Link: https://lore.kernel.org/linux-riscv/CAK8P3a2rnz9mQqhN6-e0CGUUv9rntRELFdxt_weiD7FxH7fkfQ@mail.gmail.com/ Signed-off-by: Guo Ren Signed-off-by: Guo Ren Acked-by: Peter Zijlstra (Intel) Reviewed-by: Andrew Jones Reviewed-by: Andrea Parri Link: https://lore.kernel.org/r/20241103145153.105097-11-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- include/asm-generic/spinlock.h | 87 +--------------------------- include/asm-generic/ticket_spinlock.h | 103 ++++++++++++++++++++++++++++++++++ 2 files changed, 104 insertions(+), 86 deletions(-) create mode 100644 include/asm-generic/ticket_spinlock.h (limited to 'include/asm-generic') diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h index 4773334ee638..970590baf61b 100644 --- a/include/asm-generic/spinlock.h +++ b/include/asm-generic/spinlock.h @@ -1,94 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* - * 'Generic' ticket-lock implementation. - * - * It relies on atomic_fetch_add() having well defined forward progress - * guarantees under contention. If your architecture cannot provide this, stick - * to a test-and-set lock. - * - * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a - * sub-word of the value. This is generally true for anything LL/SC although - * you'd be hard pressed to find anything useful in architecture specifications - * about this. If your architecture cannot do this you might be better off with - * a test-and-set. - * - * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence - * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with - * a full fence after the spin to upgrade the otherwise-RCpc - * atomic_cond_read_acquire(). - * - * The implementation uses smp_cond_load_acquire() to spin, so if the - * architecture has WFE like instructions to sleep instead of poll for word - * modifications be sure to implement that (see ARM64 for example). - * - */ - #ifndef __ASM_GENERIC_SPINLOCK_H #define __ASM_GENERIC_SPINLOCK_H -#include -#include - -static __always_inline void arch_spin_lock(arch_spinlock_t *lock) -{ - u32 val = atomic_fetch_add(1<<16, &lock->val); - u16 ticket = val >> 16; - - if (ticket == (u16)val) - return; - - /* - * atomic_cond_read_acquire() is RCpc, but rather than defining a - * custom cond_read_rcsc() here we just emit a full fence. We only - * need the prior reads before subsequent writes ordering from - * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we - * have no outstanding writes due to the atomic_fetch_add() the extra - * orderings are free. - */ - atomic_cond_read_acquire(&lock->val, ticket == (u16)VAL); - smp_mb(); -} - -static __always_inline bool arch_spin_trylock(arch_spinlock_t *lock) -{ - u32 old = atomic_read(&lock->val); - - if ((old >> 16) != (old & 0xffff)) - return false; - - return atomic_try_cmpxchg(&lock->val, &old, old + (1<<16)); /* SC, for RCsc */ -} - -static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); - u32 val = atomic_read(&lock->val); - - smp_store_release(ptr, (u16)val + 1); -} - -static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) -{ - u32 val = lock.val.counter; - - return ((val >> 16) == (val & 0xffff)); -} - -static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock) -{ - arch_spinlock_t val = READ_ONCE(*lock); - - return !arch_spin_value_unlocked(val); -} - -static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock) -{ - u32 val = atomic_read(&lock->val); - - return (s16)((val >> 16) - (val & 0xffff)) > 1; -} - +#include #include #endif /* __ASM_GENERIC_SPINLOCK_H */ diff --git a/include/asm-generic/ticket_spinlock.h b/include/asm-generic/ticket_spinlock.h new file mode 100644 index 000000000000..cfcff22b37b3 --- /dev/null +++ b/include/asm-generic/ticket_spinlock.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * 'Generic' ticket-lock implementation. + * + * It relies on atomic_fetch_add() having well defined forward progress + * guarantees under contention. If your architecture cannot provide this, stick + * to a test-and-set lock. + * + * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a + * sub-word of the value. This is generally true for anything LL/SC although + * you'd be hard pressed to find anything useful in architecture specifications + * about this. If your architecture cannot do this you might be better off with + * a test-and-set. + * + * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence + * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with + * a full fence after the spin to upgrade the otherwise-RCpc + * atomic_cond_read_acquire(). + * + * The implementation uses smp_cond_load_acquire() to spin, so if the + * architecture has WFE like instructions to sleep instead of poll for word + * modifications be sure to implement that (see ARM64 for example). + * + */ + +#ifndef __ASM_GENERIC_TICKET_SPINLOCK_H +#define __ASM_GENERIC_TICKET_SPINLOCK_H + +#include +#include + +static __always_inline void ticket_spin_lock(arch_spinlock_t *lock) +{ + u32 val = atomic_fetch_add(1<<16, &lock->val); + u16 ticket = val >> 16; + + if (ticket == (u16)val) + return; + + /* + * atomic_cond_read_acquire() is RCpc, but rather than defining a + * custom cond_read_rcsc() here we just emit a full fence. We only + * need the prior reads before subsequent writes ordering from + * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we + * have no outstanding writes due to the atomic_fetch_add() the extra + * orderings are free. + */ + atomic_cond_read_acquire(&lock->val, ticket == (u16)VAL); + smp_mb(); +} + +static __always_inline bool ticket_spin_trylock(arch_spinlock_t *lock) +{ + u32 old = atomic_read(&lock->val); + + if ((old >> 16) != (old & 0xffff)) + return false; + + return atomic_try_cmpxchg(&lock->val, &old, old + (1<<16)); /* SC, for RCsc */ +} + +static __always_inline void ticket_spin_unlock(arch_spinlock_t *lock) +{ + u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + u32 val = atomic_read(&lock->val); + + smp_store_release(ptr, (u16)val + 1); +} + +static __always_inline int ticket_spin_value_unlocked(arch_spinlock_t lock) +{ + u32 val = lock.val.counter; + + return ((val >> 16) == (val & 0xffff)); +} + +static __always_inline int ticket_spin_is_locked(arch_spinlock_t *lock) +{ + arch_spinlock_t val = READ_ONCE(*lock); + + return !ticket_spin_value_unlocked(val); +} + +static __always_inline int ticket_spin_is_contended(arch_spinlock_t *lock) +{ + u32 val = atomic_read(&lock->val); + + return (s16)((val >> 16) - (val & 0xffff)) > 1; +} + +/* + * Remapping spinlock architecture specific functions to the corresponding + * ticket spinlock functions. + */ +#define arch_spin_is_locked(l) ticket_spin_is_locked(l) +#define arch_spin_is_contended(l) ticket_spin_is_contended(l) +#define arch_spin_value_unlocked(l) ticket_spin_value_unlocked(l) +#define arch_spin_lock(l) ticket_spin_lock(l) +#define arch_spin_trylock(l) ticket_spin_trylock(l) +#define arch_spin_unlock(l) ticket_spin_unlock(l) + +#endif /* __ASM_GENERIC_TICKET_SPINLOCK_H */ -- cgit v1.2.3 From ab83647fadae2f1f723119dc066b39a461d6d288 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Sun, 3 Nov 2024 15:51:53 +0100 Subject: riscv: Add qspinlock support In order to produce a generic kernel, a user can select CONFIG_COMBO_SPINLOCKS which will fallback at runtime to the ticket spinlock implementation if Zabha or Ziccrse are not present. Note that we can't use alternatives here because the discovery of extensions is done too late and we need to start with the qspinlock implementation because the ticket spinlock implementation would pollute the spinlock value, so let's use static keys. This is largely based on Guo's work and Leonardo reviews at [1]. Link: https://lore.kernel.org/linux-riscv/20231225125847.2778638-1-guoren@kernel.org/ [1] Signed-off-by: Guo Ren Signed-off-by: Alexandre Ghiti Reviewed-by: Andrea Parri Link: https://lore.kernel.org/r/20241103145153.105097-14-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- .../locking/queued-spinlocks/arch-support.txt | 2 +- arch/riscv/Kconfig | 34 ++++++++++++++++ arch/riscv/include/asm/Kbuild | 4 +- arch/riscv/include/asm/spinlock.h | 47 ++++++++++++++++++++++ arch/riscv/kernel/setup.c | 37 +++++++++++++++++ include/asm-generic/qspinlock.h | 2 + include/asm-generic/ticket_spinlock.h | 2 + 7 files changed, 126 insertions(+), 2 deletions(-) create mode 100644 arch/riscv/include/asm/spinlock.h (limited to 'include/asm-generic') diff --git a/Documentation/features/locking/queued-spinlocks/arch-support.txt b/Documentation/features/locking/queued-spinlocks/arch-support.txt index 22f2990392ff..cf26042480e2 100644 --- a/Documentation/features/locking/queued-spinlocks/arch-support.txt +++ b/Documentation/features/locking/queued-spinlocks/arch-support.txt @@ -20,7 +20,7 @@ | openrisc: | ok | | parisc: | TODO | | powerpc: | ok | - | riscv: | TODO | + | riscv: | ok | | s390: | TODO | | sh: | TODO | | sparc: | ok | diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 093ee6537331..f5698ecc5ccc 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -82,6 +82,7 @@ config RISCV select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_NO_INSTR select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE + select ARCH_WEAK_RELEASE_ACQUIRE if ARCH_USE_QUEUED_SPINLOCKS select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU select BUILDTIME_TABLE_SORT if MMU select CLINT_TIMER if RISCV_M_MODE @@ -507,6 +508,39 @@ config NODES_SHIFT Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. +choice + prompt "RISC-V spinlock type" + default RISCV_COMBO_SPINLOCKS + +config RISCV_TICKET_SPINLOCKS + bool "Using ticket spinlock" + +config RISCV_QUEUED_SPINLOCKS + bool "Using queued spinlock" + depends on SMP && MMU && NONPORTABLE + select ARCH_USE_QUEUED_SPINLOCKS + help + The queued spinlock implementation requires the forward progress + guarantee of cmpxchg()/xchg() atomic operations: CAS with Zabha or + LR/SC with Ziccrse provide such guarantee. + + Select this if and only if Zabha or Ziccrse is available on your + platform, RISCV_QUEUED_SPINLOCKS must not be selected for platforms + without one of those extensions. + + If unsure, select RISCV_COMBO_SPINLOCKS, which will use qspinlocks + when supported and otherwise ticket spinlocks. + +config RISCV_COMBO_SPINLOCKS + bool "Using combo spinlock" + depends on SMP && MMU + select ARCH_USE_QUEUED_SPINLOCKS + help + Embed both queued spinlock and ticket lock so that the spinlock + implementation can be chosen at runtime. + +endchoice + config RISCV_ALTERNATIVE bool depends on !XIP_KERNEL diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 1461af12da6e..de13d5a234f8 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -6,10 +6,12 @@ generic-y += early_ioremap.h generic-y += flat.h generic-y += kvm_para.h generic-y += mmzone.h +generic-y += mcs_spinlock.h generic-y += parport.h -generic-y += spinlock.h generic-y += spinlock_types.h +generic-y += ticket_spinlock.h generic-y += qrwlock.h generic-y += qrwlock_types.h +generic-y += qspinlock.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h new file mode 100644 index 000000000000..e5121b89acea --- /dev/null +++ b/arch/riscv/include/asm/spinlock.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_RISCV_SPINLOCK_H +#define __ASM_RISCV_SPINLOCK_H + +#ifdef CONFIG_RISCV_COMBO_SPINLOCKS +#define _Q_PENDING_LOOPS (1 << 9) + +#define __no_arch_spinlock_redefine +#include +#include +#include + +/* + * TODO: Use an alternative instead of a static key when we are able to parse + * the extensions string earlier in the boot process. + */ +DECLARE_STATIC_KEY_TRUE(qspinlock_key); + +#define SPINLOCK_BASE_DECLARE(op, type, type_lock) \ +static __always_inline type arch_spin_##op(type_lock lock) \ +{ \ + if (static_branch_unlikely(&qspinlock_key)) \ + return queued_spin_##op(lock); \ + return ticket_spin_##op(lock); \ +} + +SPINLOCK_BASE_DECLARE(lock, void, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(unlock, void, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(is_locked, int, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(is_contended, int, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(trylock, bool, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(value_unlocked, int, arch_spinlock_t) + +#elif defined(CONFIG_RISCV_QUEUED_SPINLOCKS) + +#include + +#else + +#include + +#endif + +#include + +#endif /* __ASM_RISCV_SPINLOCK_H */ diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index a2cde65b69e9..438e4f6ad2ad 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -244,6 +244,42 @@ static void __init parse_dtb(void) #endif } +#if defined(CONFIG_RISCV_COMBO_SPINLOCKS) +DEFINE_STATIC_KEY_TRUE(qspinlock_key); +EXPORT_SYMBOL(qspinlock_key); +#endif + +static void __init riscv_spinlock_init(void) +{ + char *using_ext = NULL; + + if (IS_ENABLED(CONFIG_RISCV_TICKET_SPINLOCKS)) { + pr_info("Ticket spinlock: enabled\n"); + return; + } + + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && + IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && + riscv_isa_extension_available(NULL, ZABHA) && + riscv_isa_extension_available(NULL, ZACAS)) { + using_ext = "using Zabha"; + } else if (riscv_isa_extension_available(NULL, ZICCRSE)) { + using_ext = "using Ziccrse"; + } +#if defined(CONFIG_RISCV_COMBO_SPINLOCKS) + else { + static_branch_disable(&qspinlock_key); + pr_info("Ticket spinlock: enabled\n"); + return; + } +#endif + + if (!using_ext) + pr_err("Queued spinlock without Zabha or Ziccrse"); + else + pr_info("Queued spinlock %s: enabled\n", using_ext); +} + extern void __init init_rt_signal_env(void); void __init setup_arch(char **cmdline_p) @@ -297,6 +333,7 @@ void __init setup_arch(char **cmdline_p) riscv_set_dma_cache_alignment(); riscv_user_isa_enable(); + riscv_spinlock_init(); } bool arch_cpu_is_hotpluggable(int cpu) diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index 0655aa5b57b2..bf47cca2c375 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -136,6 +136,7 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock) } #endif +#ifndef __no_arch_spinlock_redefine /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. @@ -146,5 +147,6 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) +#endif #endif /* __ASM_GENERIC_QSPINLOCK_H */ diff --git a/include/asm-generic/ticket_spinlock.h b/include/asm-generic/ticket_spinlock.h index cfcff22b37b3..325779970d8a 100644 --- a/include/asm-generic/ticket_spinlock.h +++ b/include/asm-generic/ticket_spinlock.h @@ -89,6 +89,7 @@ static __always_inline int ticket_spin_is_contended(arch_spinlock_t *lock) return (s16)((val >> 16) - (val & 0xffff)) > 1; } +#ifndef __no_arch_spinlock_redefine /* * Remapping spinlock architecture specific functions to the corresponding * ticket spinlock functions. @@ -99,5 +100,6 @@ static __always_inline int ticket_spin_is_contended(arch_spinlock_t *lock) #define arch_spin_lock(l) ticket_spin_lock(l) #define arch_spin_trylock(l) ticket_spin_trylock(l) #define arch_spin_unlock(l) ticket_spin_unlock(l) +#endif #endif /* __ASM_GENERIC_TICKET_SPINLOCK_H */ -- cgit v1.2.3