From: Quentin Perret <qperret@google.com>
To: Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
James Morse <james.morse@arm.com>,
Julien Thierry <julien.thierry.kdev@gmail.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
Rob Herring <robh+dt@kernel.org>,
Frank Rowand <frowand.list@gmail.com>
Cc: devicetree@vger.kernel.org, android-kvm@google.com,
linux-kernel@vger.kernel.org, kernel-team@android.com,
kvmarm@lists.cs.columbia.edu,
linux-arm-kernel@lists.infradead.org,
Fuad Tabba <tabba@google.com>,
Mark Rutland <mark.rutland@arm.com>,
David Brazdil <dbrazdil@google.com>
Subject: [RFC PATCH v2 03/26] arm64: kvm: Add standalone ticket spinlock implementation for use at hyp
Date: Fri, 8 Jan 2021 12:15:01 +0000 [thread overview]
Message-ID: <20210108121524.656872-4-qperret@google.com> (raw)
In-Reply-To: <20210108121524.656872-1-qperret@google.com>
From: Will Deacon <will@kernel.org>
We will soon need to synchronise multiple CPUs in the hyp text at EL2.
The qspinlock-based locking used by the host is overkill for this purpose
and relies on the kernel's "percpu" implementation for the MCS nodes.
Implement a simple ticket locking scheme based heavily on the code removed
by commit c11090474d70 ("arm64: locking: Replace ticket lock implementation
with qspinlock").
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Quentin Perret <qperret@google.com>
---
arch/arm64/kvm/hyp/include/nvhe/spinlock.h | 92 ++++++++++++++++++++++
1 file changed, 92 insertions(+)
create mode 100644 arch/arm64/kvm/hyp/include/nvhe/spinlock.h
diff --git a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h
new file mode 100644
index 000000000000..7584c397bbac
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * A stand-alone ticket spinlock implementation for use by the non-VHE
+ * KVM hypervisor code running at EL2.
+ *
+ * Copyright (C) 2020 Google LLC
+ * Author: Will Deacon <will@kernel.org>
+ *
+ * Heavily based on the implementation removed by c11090474d70 which was:
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __ARM64_KVM_NVHE_SPINLOCK_H__
+#define __ARM64_KVM_NVHE_SPINLOCK_H__
+
+#include <asm/alternative.h>
+#include <asm/lse.h>
+
+typedef union hyp_spinlock {
+ u32 __val;
+ struct {
+#ifdef __AARCH64EB__
+ u16 next, owner;
+#else
+ u16 owner, next;
+ };
+#endif
+} hyp_spinlock_t;
+
+#define hyp_spin_lock_init(l) \
+do { \
+ *(l) = (hyp_spinlock_t){ .__val = 0 }; \
+} while (0)
+
+static inline void hyp_spin_lock(hyp_spinlock_t *lock)
+{
+ u32 tmp;
+ hyp_spinlock_t lockval, newval;
+
+ asm volatile(
+ /* Atomically increment the next ticket. */
+ ARM64_LSE_ATOMIC_INSN(
+ /* LL/SC */
+" prfm pstl1strm, %3\n"
+"1: ldaxr %w0, %3\n"
+" add %w1, %w0, #(1 << 16)\n"
+" stxr %w2, %w1, %3\n"
+" cbnz %w2, 1b\n",
+ /* LSE atomics */
+" mov %w2, #(1 << 16)\n"
+" ldadda %w2, %w0, %3\n"
+ __nops(3))
+
+ /* Did we get the lock? */
+" eor %w1, %w0, %w0, ror #16\n"
+" cbz %w1, 3f\n"
+ /*
+ * No: spin on the owner. Send a local event to avoid missing an
+ * unlock before the exclusive load.
+ */
+" sevl\n"
+"2: wfe\n"
+" ldaxrh %w2, %4\n"
+" eor %w1, %w2, %w0, lsr #16\n"
+" cbnz %w1, 2b\n"
+ /* We got the lock. Critical section starts here. */
+"3:"
+ : "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
+ : "Q" (lock->owner)
+ : "memory");
+}
+
+static inline void hyp_spin_unlock(hyp_spinlock_t *lock)
+{
+ u64 tmp;
+
+ asm volatile(
+ ARM64_LSE_ATOMIC_INSN(
+ /* LL/SC */
+ " ldrh %w1, %0\n"
+ " add %w1, %w1, #1\n"
+ " stlrh %w1, %0",
+ /* LSE atomics */
+ " mov %w1, #1\n"
+ " staddlh %w1, %0\n"
+ __nops(1))
+ : "=Q" (lock->owner), "=&r" (tmp)
+ :
+ : "memory");
+}
+
+#endif /* __ARM64_KVM_NVHE_SPINLOCK_H__ */
--
2.30.0.284.gd98b1dd5eaa7-goog
next prev parent reply other threads:[~2021-01-08 12:17 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-08 12:14 [RFC PATCH v2 00/26] KVM/arm64: A stage 2 for the host Quentin Perret
2021-01-08 12:14 ` [RFC PATCH v2 01/26] arm64: lib: Annotate {clear,copy}_page() as position-independent Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 02/26] KVM: arm64: Link position-independent string routines into .hyp.text Quentin Perret
2021-01-08 12:15 ` Quentin Perret [this message]
2021-02-01 17:28 ` [RFC PATCH v2 03/26] arm64: kvm: Add standalone ticket spinlock implementation for use at hyp Will Deacon
2021-02-01 17:40 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 04/26] KVM: arm64: Initialize kvm_nvhe_init_params early Quentin Perret
2021-02-01 17:41 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 05/26] KVM: arm64: Avoid free_page() in page-table allocator Quentin Perret
2021-02-01 17:46 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 06/26] KVM: arm64: Factor memory allocation out of pgtable.c Quentin Perret
2021-02-01 18:16 ` Will Deacon
2021-02-01 18:32 ` Quentin Perret
2021-02-01 18:39 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 07/26] KVM: arm64: Introduce a BSS section for use at Hyp Quentin Perret
2021-02-01 18:32 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 08/26] KVM: arm64: Make kvm_call_hyp() a function call " Quentin Perret
2021-02-01 18:41 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 09/26] KVM: arm64: Allow using kvm_nvhe_sym() in hyp code Quentin Perret
2021-02-01 18:43 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 10/26] KVM: arm64: Introduce an early Hyp page allocator Quentin Perret
2021-02-01 19:00 ` Will Deacon
2021-02-02 9:44 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 11/26] KVM: arm64: Stub CONFIG_DEBUG_LIST at Hyp Quentin Perret
2021-02-01 19:06 ` Will Deacon
2021-02-02 9:57 ` Quentin Perret
2021-02-02 10:00 ` Will Deacon
2021-02-02 10:14 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 12/26] KVM: arm64: Introduce a Hyp buddy page allocator Quentin Perret
2021-02-02 18:13 ` Will Deacon
2021-02-03 18:33 ` Quentin Perret
2021-02-04 14:31 ` Will Deacon
2021-02-04 14:52 ` Quentin Perret
2021-02-04 17:48 ` Will Deacon
2021-02-04 18:01 ` Quentin Perret
2021-02-04 18:13 ` Will Deacon
2021-02-04 18:24 ` Quentin Perret
2021-02-04 18:19 ` Quentin Perret
2021-02-04 18:24 ` Will Deacon
2021-02-04 18:32 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 13/26] KVM: arm64: Enable access to sanitized CPU features at EL2 Quentin Perret
2021-01-13 11:33 ` Marc Zyngier
2021-01-13 14:23 ` Quentin Perret
2021-01-13 14:35 ` Quentin Perret
2021-01-13 17:27 ` Marc Zyngier
2021-01-13 18:28 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 14/26] KVM: arm64: Factor out vector address calculation Quentin Perret
2021-02-02 18:24 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 15/26] of/fdt: Introduce early_init_dt_add_memory_hyp() Quentin Perret
2021-01-11 14:45 ` Rob Herring
2021-01-12 9:51 ` Quentin Perret
2021-01-12 14:10 ` Rob Herring
2021-01-12 14:26 ` Quentin Perret
2021-01-12 15:53 ` Rob Herring
2021-01-12 16:15 ` Quentin Perret
2021-01-12 16:45 ` Rob Herring
2021-01-12 16:50 ` Quentin Perret
2021-01-15 11:49 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 16/26] KVM: arm64: Prepare Hyp memory protection Quentin Perret
2021-02-03 14:37 ` Will Deacon
2021-02-04 10:47 ` Quentin Perret
2021-02-05 17:56 ` Will Deacon
2021-02-09 10:00 ` Quentin Perret
2021-02-09 12:23 ` Will Deacon
2021-02-19 18:32 ` Sean Christopherson
2021-02-22 11:04 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 17/26] KVM: arm64: Elevate Hyp mappings creation at EL2 Quentin Perret
2021-02-03 15:31 ` Will Deacon
2021-02-04 11:08 ` Quentin Perret
2021-02-05 18:01 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 18/26] KVM: arm64: Use kvm_arch for stage 2 pgtable Quentin Perret
2021-02-03 15:34 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 19/26] KVM: arm64: Use kvm_arch in kvm_s2_mmu Quentin Perret
2021-02-03 15:38 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 20/26] KVM: arm64: Set host stage 2 using kvm_nvhe_init_params Quentin Perret
2021-02-03 16:05 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 21/26] KVM: arm64: Refactor kvm_arm_setup_stage2() Quentin Perret
2021-02-03 15:53 ` Will Deacon
2021-02-04 14:07 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 22/26] KVM: arm64: Refactor __load_guest_stage2() Quentin Perret
2021-02-03 15:54 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 23/26] KVM: arm64: Refactor __populate_fault_info() Quentin Perret
2021-02-03 15:58 ` Will Deacon
2021-02-04 14:18 ` Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 24/26] KVM: arm64: Make memcache anonymous in pgtable allocator Quentin Perret
2021-02-03 15:59 ` Will Deacon
2021-02-04 14:24 ` Quentin Perret
2021-02-04 14:36 ` Will Deacon
2021-01-08 12:15 ` [RFC PATCH v2 25/26] KVM: arm64: Reserve memory for host stage 2 Quentin Perret
2021-01-08 12:15 ` [RFC PATCH v2 26/26] KVM: arm64: Wrap the host with a " Quentin Perret
2021-02-03 16:11 ` Will Deacon
2021-02-04 14:26 ` Quentin Perret
2021-02-04 14:37 ` Will Deacon
2021-02-17 16:27 ` [RFC PATCH v2 00/26] KVM/arm64: A stage 2 for the host Mate Toth-Pal
2021-02-17 17:24 ` Quentin Perret
2021-02-19 17:54 ` Sean Christopherson
2021-02-19 17:57 ` Quentin Perret
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210108121524.656872-4-qperret@google.com \
--to=qperret@google.com \
--cc=android-kvm@google.com \
--cc=catalin.marinas@arm.com \
--cc=dbrazdil@google.com \
--cc=devicetree@vger.kernel.org \
--cc=frowand.list@gmail.com \
--cc=james.morse@arm.com \
--cc=julien.thierry.kdev@gmail.com \
--cc=kernel-team@android.com \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=maz@kernel.org \
--cc=robh+dt@kernel.org \
--cc=suzuki.poulose@arm.com \
--cc=tabba@google.com \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).