lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240818063538.6651-11-alexghiti@rivosinc.com>
Date: Sun, 18 Aug 2024 08:35:35 +0200
From: Alexandre Ghiti <alexghiti@...osinc.com>
To: Jonathan Corbet <corbet@....net>,
	Paul Walmsley <paul.walmsley@...ive.com>,
	Palmer Dabbelt <palmer@...belt.com>,
	Albert Ou <aou@...s.berkeley.edu>,
	Conor Dooley <conor@...nel.org>,
	Rob Herring <robh@...nel.org>,
	Krzysztof Kozlowski <krzk+dt@...nel.org>,
	Andrea Parri <parri.andrea@...il.com>,
	Nathan Chancellor <nathan@...nel.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...hat.com>,
	Will Deacon <will@...nel.org>,
	Waiman Long <longman@...hat.com>,
	Boqun Feng <boqun.feng@...il.com>,
	Arnd Bergmann <arnd@...db.de>,
	Leonardo Bras <leobras@...hat.com>,
	Guo Ren <guoren@...nel.org>,
	linux-doc@...r.kernel.org,
	devicetree@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-riscv@...ts.infradead.org,
	linux-arch@...r.kernel.org
Cc: Guo Ren <guoren@...ux.alibaba.com>
Subject: [PATCH v5 10/13] asm-generic: ticket-lock: Add separate ticket-lock.h

From: Guo Ren <guoren@...ux.alibaba.com>

Add a separate ticket-lock.h to include multiple spinlock versions and
select one at compile time or runtime.

Reviewed-by: Leonardo Bras <leobras@...hat.com>
Suggested-by: Arnd Bergmann <arnd@...db.de>
Link: https://lore.kernel.org/linux-riscv/CAK8P3a2rnz9mQqhN6-e0CGUUv9rntRELFdxt_weiD7FxH7fkfQ@mail.gmail.com/
Signed-off-by: Guo Ren <guoren@...ux.alibaba.com>
Signed-off-by: Guo Ren <guoren@...nel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 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

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 <linux/atomic.h>
-#include <asm-generic/spinlock_types.h>
-
-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 <asm-generic/ticket_spinlock.h>
 #include <asm/qrwlock.h>
 
 #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 <linux/atomic.h>
+#include <asm-generic/spinlock_types.h>
+
+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 */
-- 
2.39.2


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ