From: Mark Rutland <mark.rutland@arm.com>
To: linux-arm-kernel@lists.infradead.org
Cc: mark.rutland@arm.com, vladimir.murzin@arm.com,
peterz@infradead.org, catalin.marinas@arm.com, hca@linux.ibm.com,
linux-kernel@vger.kernel.org, ruanjinjie@huawei.com,
yang@os.amperecomputing.com, maz@kernel.org, will@kernel.org,
ardb@kernel.org
Subject: [RFC PATCH 06/13] arm64: percpu: Add infrastructure for preemptible this_cpu_*() ops
Date: Tue, 28 Jul 2026 13:38:52 +0100 [thread overview]
Message-ID: <20260728123859.2911495-7-mark.rutland@arm.com> (raw)
In-Reply-To: <20260728123859.2911495-1-mark.rutland@arm.com>
Currently arm64's this_cpu_*() ops transiently disable preemption in
order to guarantee that the address generation and memory access(es)
occur on the same CPU.
Transiently disabling preemption can be expensive. When re-enabling
preemption it is necessary to make a conditional function call to
preempt_schedule[_notrace]() in order to handle the rare case that the
task needs to be rescheduled. The potential function call has a number
of negative effects on code generation (e.g. due to the need to create a
stack frame and spill registers), and the conditionality can result in
poor code generation and/or poor branch prediction.
This patch adds infrastructure for a scheme where this_cpu_*() ops do
not need to transiently disable preemption, avoiding the negative
impacts described above.
Each operation registers a critical section during which the exception
return code will adjust the offset and addresses if preemption occurs
mid-sequence. The critical section is registered/unregistered with a
small prologue and epilogue which encodes three distinct GPRRs (<pcp>,
<off>, <addr>) into a new thread_info::pcp_gprs field:
// Prologue. Enable fixups for <off> and <addr>.
mrs <tsk>, sp_el0
mov <tmp>, #__VAL_PCPU_GPRS(<pcp>, <off>, <addr>)
strh <tmp>, [<tsk>, #TSK_TI_PCPU_GPRS]
// Generate cpu-specific address
mrs <off>, TPIDR_ELx
add <addr>, <pcp>, <off>
// Perform access sequence
ldr <val>, [<addr>]
// Epilogue. Disable fixups
strh wzr, [<tsk>, #TSK_TI_PCPU_GPRS]
If an exception is taken from within the critical section, the exception
return code will adjust <off> to be the current CPU's offset, and will
adjust <addr> to be (<pcp> + <off>). Distinct registers are used for
<pcp>, <off>, and <addr>, so that the fixup can be applied safely at any
point during the critical section.
To ensure that this_cpu_*() operations within exception handlers work
correctly and do not corrupt state, thread_info::pcpu_gprs is saved
into a new pt_regs::pcpu_gprs field upon exception entry, and restored
upon exception return.
Looking at a simple this_cpu_operation:
| void outline_this_cpu_add_u64(u64 __percpu *p, u64 v)
| {
| this_cpu_add(*p, v);
| }
Atop v7.2-rc4, with GCC 15.2.0 and defconfig, this is compiled as:
| <outline_this_cpu_add_u64>:
| paciasp
| stp x29, x30, [sp, #-16]!
| mrs x2, sp_el0
| mov x29, sp
| ldr w3, [x2, #8]
| add w3, w3, #0x1
| str w3, [x2, #8]
| mrs x3, tpidr_el1
| add x0, x0, x3
| 1: ldxr x5, [x0]
| add x5, x5, x1
| stxr w4, x5, [x0]
| cbnz w4, 1b
| ldr x0, [x2, #8]
| sub x0, x0, #0x1
| str w0, [x2, #8]
| cbz x0, 2f
| ldr x0, [x2, #8]
| cbnz x0, 3f
| 2: bl preempt_schedule_notrace
| 3: ldp x29, x30, [sp], #16
| autiasp
| ret
With the scheme added in this patch, this can be compiled as:
| <outline_this_cpu_add_u64>:
| mrs x2, sp_el0
| mov x4, #0xc80
| strh w4, [x2, #20]
| mrs x4, tpidr_el1
| add x3, x0, x4
| 1: ldxr x6, [x3]
| add x6, x6, x1
| stxr w5, x6, [x3]
| cbnz w5, 1b
| strh wzr, [x2, #20]
| ret
TODO: Save/restore the PCPU GPRs in __sdei_asm_handler(). This will
require some mechanical rework to the __sdei_asm_handler() assembly.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jinjie Ruan <ruanjinjie@huawei.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vladimir Murzin <vladimir.murzin@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
---
arch/arm64/include/asm/percpu.h | 43 ++++++++++++++++++++++++++++
arch/arm64/include/asm/ptrace.h | 5 ++++
arch/arm64/include/asm/thread_info.h | 1 +
arch/arm64/kernel/asm-offsets.c | 2 ++
arch/arm64/kernel/entry-common.c | 38 ++++++++++++++++++++++++
arch/arm64/kernel/entry.S | 13 +++++++++
6 files changed, 102 insertions(+)
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 98823c97d534c..0871dcc41d759 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -5,10 +5,12 @@
#ifndef __ASM_PERCPU_H
#define __ASM_PERCPU_H
+#include <linux/bits.h>
#include <linux/preempt.h>
#include <asm/alternative.h>
#include <asm/cmpxchg.h>
+#include <asm/gpr-num.h>
#include <asm/stack_pointer.h>
#include <asm/sysreg.h>
@@ -51,6 +53,47 @@ static inline unsigned long __kern_my_cpu_offset(void)
return off;
}
+#define PCPU_GPR_PCP GENMASK(4, 0)
+#define PCPU_GPR_OFF GENMASK(9, 5)
+#define PCPU_GPR_ADDR GENMASK(14, 10)
+
+#define __VAL_PCPU_GPRS(pcp, off, addr) \
+ "(" \
+ "(.L__gpr_num_" pcp " << 0) | " \
+ "(.L__gpr_num_" off " << 5) | " \
+ "(.L__gpr_num_" addr " << 10)" \
+ ")"
+
+#define ____PCPU_GPRS_BEGIN(gprs, pcp, off, addr) \
+ __DEFINE_ASM_GPR_NUMS \
+ __DEFINE_ASM_GPR_ALIASES \
+ " mov w" off ", #" __VAL_PCPU_GPRS(pcp, off, addr) "\n" \
+ " strh w" off ", " gprs "\n" \
+ __KERN_ASM_CPU_OFFSET(off) "\n"
+
+/*
+ * Begin a PCPU GPR critical section which requires <addr> (and <off>).
+ */
+#define __PCPU_GPRS_BEGIN(gprs, pcp, off, addr) \
+ ____PCPU_GPRS_BEGIN(gprs, pcp, off, addr) \
+ " add " addr ", " pcp ", " off "\n" \
+
+/*
+ * Begin a PCPU GPR critical section which only requires <off> and does not
+ * require <addr>.
+ *
+ * This is only for operations that can use register-offset addressing,
+ * e.g. STR <Xt>, [<Xn>, <Xm].
+ */
+#define __PCPU_GPRS_BEGIN_OFFSET(gprs, pcp, off) \
+ ____PCPU_GPRS_BEGIN(gprs, pcp, off, "xzr") \
+
+/*
+ * End a PCU GPR critical section.
+ */
+#define __PCPU_GPRS_END(gprs) \
+ " strh wzr, " gprs "\n"
+
#ifdef __KVM_NVHE_HYPERVISOR__
#define __my_cpu_offset __hyp_my_cpu_offset()
#else
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index a1aa668aad50e..962013df20c7a 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -169,6 +169,11 @@ struct pt_regs {
u64 sdei_ttbr1;
struct frame_record_meta stackframe;
+
+ u16 pcpu_gprs;
+ u16 __unused1;
+ u32 __unused2;
+ u64 __unused3;
};
/* For correct stack alignment, pt_regs has to be a multiple of 16 bytes. */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 5d7fe3e153c85..6db5fa72211d1 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -46,6 +46,7 @@ struct thread_info {
u64 mpam_partid_pmg;
#endif
u32 cpu;
+ u16 pcpu_gprs;
};
#define thread_saved_pc(tsk) \
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index b6367ff3a49ca..bde09e9fe3e64 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -36,6 +36,7 @@ int main(void)
DEFINE(TSK_TI_SCS_BASE, offsetof(struct task_struct, thread_info.scs_base));
DEFINE(TSK_TI_SCS_SP, offsetof(struct task_struct, thread_info.scs_sp));
#endif
+ DEFINE(TSK_TI_PCPU_GPRS, offsetof(struct task_struct, thread_info.pcpu_gprs));
DEFINE(TSK_STACK, offsetof(struct task_struct, stack));
#ifdef CONFIG_STACKPROTECTOR
DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary));
@@ -78,6 +79,7 @@ int main(void)
DEFINE(S_PMR, offsetof(struct pt_regs, pmr));
DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
DEFINE(S_STACKFRAME_TYPE, offsetof(struct pt_regs, stackframe.type));
+ DEFINE(S_PCPU_GPRS, offsetof(struct pt_regs, pcpu_gprs));
DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs));
BLANK();
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index ceb4eb11232a6..5bba1359280c3 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -25,12 +25,49 @@
#include <asm/irq_regs.h>
#include <asm/kprobes.h>
#include <asm/mmu.h>
+#include <asm/percpu.h>
#include <asm/processor.h>
#include <asm/sdei.h>
#include <asm/stacktrace.h>
#include <asm/sysreg.h>
#include <asm/system_misc.h>
+/*
+ * Where the context being returned to had an active percpu GPR critical
+ * section, ensure that the offset and address GPRs are updated to match the
+ * current CPU.
+ *
+ * For simplicity we always update the GPRs when a critical section is active
+ * and preemption was *possible*, regardless of whether preemption actually
+ * occurred. Where preemption did not occur, the updates are redundant but not
+ * harmful.
+ */
+static __always_inline void irqentry_exit_pcpu_adjust(struct pt_regs *regs)
+{
+ int reg_pcp, reg_off, reg_addr;
+ unsigned long pcp, off, addr;
+ u16 gprs = regs->pcpu_gprs;
+
+ /*
+ * Zero means no active PCPU GPRs. As the PCPU GPRs must be distinct,
+ * a PCPU critical section cannot possibly use {x0,x0,x0}.
+ */
+ if (likely(!gprs))
+ return;
+
+ reg_pcp = FIELD_GET(PCPU_GPR_PCP, gprs);
+ reg_off = FIELD_GET(PCPU_GPR_OFF, gprs);
+ reg_addr = FIELD_GET(PCPU_GPR_ADDR, gprs);
+
+ pcp = pt_regs_read_reg(regs, reg_pcp);
+
+ off = __kern_my_cpu_offset();
+ pt_regs_write_reg(regs, reg_off, off);
+
+ addr = pcp + off;
+ pt_regs_write_reg(regs, reg_addr, addr);
+}
+
/*
* Handle IRQ/context state management when entering from kernel mode.
* Before this function is called it is not safe to call regular kernel code,
@@ -58,6 +95,7 @@ static void noinstr arm64_exit_to_kernel_mode(struct pt_regs *regs,
local_irq_disable();
irqentry_exit_to_kernel_mode_preempt(regs, state);
local_daif_mask();
+ irqentry_exit_pcpu_adjust(regs);
mte_check_tfsr_exit();
irqentry_exit_to_kernel_mode_after_preempt(regs, state);
}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e0db14e9c843a..d26648cd7f280 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -194,6 +194,17 @@ alternative_cb_end
#endif
.endm
+ .macro pcpu_gprs_entry, tsk, regs, tmp
+ ldrh w\tmp, [\tsk, #TSK_TI_PCPU_GPRS]
+ strh w\tmp, [\regs, #S_PCPU_GPRS]
+ strh wzr, [\tsk, #TSK_TI_PCPU_GPRS]
+ .endm
+
+ .macro pcpu_gprs_exit, tsk, regs, tmp
+ ldrh w\tmp, [\regs, #S_PCPU_GPRS]
+ strh w\tmp, [\tsk, #TSK_TI_PCPU_GPRS]
+ .endm
+
.macro kernel_entry, el, regsize = 64
.if \el == 0
alternative_insn nop, SET_PSTATE_DIT(1), ARM64_HAS_DIT
@@ -277,6 +288,7 @@ alternative_else_nop_endif
.else
add x21, sp, #PT_REGS_SIZE
get_current_task tsk
+ pcpu_gprs_entry tsk, sp, x0
.endif /* \el == 0 */
mrs x22, elr_el1
mrs x23, spsr_el1
@@ -335,6 +347,7 @@ alternative_else_nop_endif
.macro kernel_exit, el
.if \el != 0
disable_daif
+ pcpu_gprs_exit tsk, sp, x0
.endif
#ifdef CONFIG_ARM64_PSEUDO_NMI
--
2.30.2
next prev parent reply other threads:[~2026-07-28 12:40 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-28 12:38 [RFC PATCH 00/13] arm64: Preemptible this_cpu_*() operations Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 01/13] arm64: preempt: Simplify and optimize __preempt_count_dec_and_test() Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 02/13] arm64: preempt: Treat should_resched() as unlikely Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 03/13] arm64: ptrace: Always inline pt_regs_[read,write}_reg() Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 04/13] arm64: percpu: Factor out percpu offset asm Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 05/13] arm64: gpr-num: Add wxN aliases for wN registers Mark Rutland
2026-07-28 12:38 ` Mark Rutland [this message]
2026-07-28 14:19 ` [RFC PATCH 06/13] arm64: percpu: Add infrastructure for preemptible this_cpu_*() ops Peter Zijlstra
2026-07-28 14:30 ` Peter Zijlstra
2026-07-28 16:03 ` Mark Rutland
2026-07-28 16:49 ` Peter Zijlstra
2026-07-28 15:53 ` Mark Rutland
2026-07-28 16:46 ` Peter Zijlstra
2026-07-28 16:49 ` Peter Zijlstra
2026-07-28 16:51 ` Heiko Carstens
2026-07-28 12:38 ` [RFC PATCH 07/13] arm64: percpu: Implement preemptible read/write ops Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 08/13] arm64: percpu: Implement preemptible void RMW ops Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 09/13] arm64: percpu: Implement preemptible return " Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 10/13] arm64: percpu: Implement preemptible XCHG ops Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 11/13] arm64: percpu: Implement preemptible CMPXCHG ops Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 12/13] arm64: percpu: Implement preemptible CMPXCHG128 ops Mark Rutland
2026-07-28 12:38 ` [RFC PATCH 13/13] arm64: percpu: Remove _pcp_protect*() wrappers Mark Rutland
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=20260728123859.2911495-7-mark.rutland@arm.com \
--to=mark.rutland@arm.com \
--cc=ardb@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=hca@linux.ibm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maz@kernel.org \
--cc=peterz@infradead.org \
--cc=ruanjinjie@huawei.com \
--cc=vladimir.murzin@arm.com \
--cc=will@kernel.org \
--cc=yang@os.amperecomputing.com \
/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