mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Will Deacon <will@kernel.org>
To: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org, "Will Deacon" <will@kernel.org>,
	"Thomas Gleixner" <tglx@kernel.org>,
	"Ben Horgan" <ben.horgan@arm.com>,
	"Ștefania Ion" <stefion@google.com>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Pankaj Patil" <pankaj.patil@oss.qualcomm.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Lorenzo Pieralisi" <lpieralisi@kernel.org>,
	"Jinjie Ruan" <ruanjinjie@huawei.com>,
	"Mark Rutland" <mark.rutland@arm.com>,
	"Tarun Sahu" <tarunsahu@google.com>,
	"Fuad Tabba" <fuad.tabba@linux.dev>,
	"David Woodhouse" <dwmw@amazon.co.uk>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Marc Zyngier" <maz@kernel.org>
Subject: [PATCH v2 23/23] arm64: smp: Harden parallel CPU bringup against broken PSCI firmware
Date: Fri,  9 Oct 2026 11:07:34 +0100	[thread overview]
Message-ID: <20261009100738.31288-24-will@kernel.org> (raw)
In-Reply-To: <20261009100738.31288-1-will@kernel.org>

Since firmware has occasionally been known to get things wrong, harden
our parallel CPU bringup code against a PSCI implementation that passes
the CPU_ON argument to an incorrect CPU.

The primary CPU writes the MPIDR of the incoming CPU to the penultimate
slot of its task stack and this is then checked against the MPIDR_EL1
register during early kernel entry. A mismatch is reported via the
existing failure reporting mechanism and the CPU is not brought online.

Suggested-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/smp.h    |  4 +++-
 arch/arm64/kernel/asm-offsets.c |  1 +
 arch/arm64/kernel/head.S        | 39 ++++++++++++++++++++++++++++-----
 arch/arm64/kernel/smp.c         | 12 ++++++++--
 4 files changed, 47 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 3decb42164aa..1ecfa4fa4f82 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -15,7 +15,9 @@
 /* Offsets for late (i.e. MMU-enabled) CPU boot reasons */
 /* Fatal system error detected by secondary CPU, crash the system */
 #define CPU_PANIC_KERNEL			(0)
-#define CPU_STATUS_FLAGS_MAX			(1)
+/* The PSCI v0.2+ implementation passed the wrong argument */
+#define CPU_BROKEN_PSCI_ARG			(1)
+#define CPU_STATUS_FLAGS_MAX			(2)
 
 #ifndef __ASSEMBLER__
 
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 9c853ed3ceab..0cbd10af13ac 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -97,6 +97,7 @@ int main(void)
   BLANK();
 #endif
   DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
+  DEFINE(CPU_BOOT_STATUS_FLAGS,	offsetof(struct secondary_data, status.flags));
   BLANK();
   DEFINE(FTR_OVR_VAL_OFFSET,	offsetof(struct arm64_ftr_override, val));
   DEFINE(FTR_OVR_MASK_OFFSET,	offsetof(struct arm64_ftr_override, mask));
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 031ff1d4fd29..3f005e226547 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -192,11 +192,21 @@ SYM_CODE_END(preserve_boot_args)
 	 * its location in the task stack. We reserve the entire pt_regs space
 	 * for consistency with user tasks and kthreads.
 	 */
-	.macro	init_cpu_task tsk, tmp1, tmp2
+	.macro	init_cpu_task tsk, tmp1, tmp2, check_mpidr=
 	msr	sp_el0, \tsk
 
 	ldr	\tmp1, [\tsk, #TSK_STACK]
-	add	sp, \tmp1, #THREAD_SIZE
+	mov	sp, \tmp1
+	.ifnb	\check_mpidr
+	mov_q	\tmp1, MPIDR_HWID_BITMASK
+	mrs	\tmp2, mpidr_el1
+	and	\tmp2, \tmp2, \tmp1
+	ldr	\tmp1, [sp, #8]
+	sub	\tmp1, \tmp1, \tmp2
+	cbnz	\tmp1, __cpu_secondary_broken_psci_arg
+	.endif
+
+	add	sp, sp, #THREAD_SIZE
 	sub	sp, sp, #PT_REGS_SIZE
 
 	stp	xzr, xzr, [sp, #S_STACKFRAME]
@@ -397,15 +407,16 @@ SYM_FUNC_START_LOCAL(__secondary_switched)
 	msr	vbar_el1, x5
 	isb
 
+	cbz	x19, 1f
 	mov	x2, x19
-	cbnz	x2, 1f
+	init_cpu_task x2, x1, x3, check_mpidr=1
+	b	2f
+1:
 	adr_l	x0, secondary_data
 	ldr	x2, [x0, #CPU_BOOT_TASK]
 	cbz	x2, __secondary_too_slow
-
-1:
 	init_cpu_task x2, x1, x3
-
+2:
 #ifdef CONFIG_ARM64_PTR_AUTH
 	ptrauth_keys_init_cpu x2, x3, x4, x5
 #endif
@@ -451,6 +462,22 @@ SYM_FUNC_END(set_cpu_boot_mode_flag)
 	dc	ivac, \tmp1			// Invalidate potentially stale cache line
 	.endm
 
+	.macro	update_cpu_boot_status status, tmp1, tmp2
+	adr_l	\tmp1, secondary_data
+	add	\tmp1, \tmp1, #CPU_BOOT_STATUS_FLAGS + \status
+	mov	\tmp2, #1
+	strb	w\tmp2, [\tmp1]
+	.endm
+
+SYM_FUNC_START_LOCAL(__cpu_secondary_broken_psci_arg)
+	update_cpu_boot_status CPU_BROKEN_PSCI_ARG, x0, x1
+1:
+	wfe
+	wfi
+	b	1b
+SYM_FUNC_END(__cpu_secondary_broken_psci_arg)
+
+
 /*
  * Enable the MMU.
  *
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b3023557d789..8dc29bdef1a1 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -119,10 +119,13 @@ int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *idle)
 	 * We need to tell the secondary core where to find its stack and the
 	 * page tables.
 	 */
-	if (smp_parallel_bringup)
+	if (smp_parallel_bringup) {
+		/* Avoid clobbering STACK_END_MAGIC */
+		*(end_of_stack(idle) + 1) = cpu_logical_map(cpu);
 		arg = idle;
-	else
+	} else {
 		secondary_data.task = idle;
+	}
 
 	/* Now bring the CPU into our world */
 	if (ops->cpu_boot)
@@ -158,6 +161,11 @@ void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu, bool is_alive)
 	}
 
 	status = READ_ONCE(secondary_data.status);
+	if (status.flags[CPU_BROKEN_PSCI_ARG]) {
+		pr_crit_once("CPU%u detected broken PSCI v0.2+ CPU_ON argument passing\n",
+			     cpu);
+	}
+
 	if (status.flags[CPU_PANIC_KERNEL])
 		panic("CPU%u detected unsupported configuration\n", cpu);
 
-- 
2.56.0.385.gd3acb90ef8-goog


      parent reply	other threads:[~2026-10-09 10:09 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-09 10:07 [PATCH v2 00/23] arm64: Implement parallel CPU onlining with PSCI v0.2+ Will Deacon
2026-10-09 10:07 ` [PATCH v2 01/23] cpu/hotplug: Clean up cmpxchg() logic in cpuhp_can_boot_ap() Will Deacon
2026-10-09 10:07 ` [PATCH v2 02/23] cpu/hotplug: Avoid trying to bring up CPUs that are already online Will Deacon
2026-10-09 10:07 ` [PATCH v2 03/23] cpu/hotplug: Avoid busy-polling on archs where cpu_relax() is a no-op Will Deacon
2026-10-09 10:46   ` David Woodhouse
2026-10-09 11:07     ` Will Deacon
2026-10-09 10:07 ` [PATCH v2 04/23] cpu/hotplug: Propagate bring-up status to arch_cpuhp_cleanup_kick_cpu() Will Deacon
2026-10-09 10:07 ` [PATCH v2 05/23] arm64: cpufeature: Check arm64_ftr_regs[] before the first store Will Deacon
2026-10-09 10:07 ` [PATCH v2 06/23] arm64: cpufeature: Add read_cpuid_with_overrides() Will Deacon
2026-10-09 10:07 ` [PATCH v2 07/23] arm64: cpufeature: Read MPAMIDR_EL1 in __cpuinfo_store_cpu() Will Deacon
2026-10-09 15:44   ` Ben Horgan
2026-10-09 10:07 ` [PATCH v2 08/23] arm64: cpufeature: Store every ID register with its overrides applied Will Deacon
2026-10-09 15:51   ` Ben Horgan
2026-10-09 10:07 ` [PATCH v2 09/23] arm64: smp: Tidy up smp_prepare_cpus() Will Deacon
2026-10-09 10:07 ` [PATCH v2 10/23] arm64: smp: Tidy up cpuinfo init and cpufeature updates Will Deacon
2026-10-09 10:07 ` [PATCH v2 11/23] arm64: smp: Defer update of secondary CPU capabilities Will Deacon
2026-10-09 10:07 ` [PATCH v2 12/23] arm64: smp: Don't bother printing the I-cache policy for each CPU Will Deacon
2026-10-09 10:07 ` [PATCH v2 13/23] arm64: smp: Defer RCU registration during secondary CPU bringup Will Deacon
2026-10-09 10:07 ` [PATCH v2 14/23] arm64: smp: Use generic HOTPLUG_CORE_SYNC_FULL machinery for CPU onlining Will Deacon
2026-10-09 10:07 ` [PATCH v2 15/23] arm64: smp: Use generic HOTPLUG_SPLIT_STARTUP " Will Deacon
2026-10-09 10:07 ` [PATCH v2 16/23] arm64: cpu_ops: Make 'cpu_operations' pointer global instead of per-cpu Will Deacon
2026-10-09 10:07 ` [PATCH v2 17/23] arm64: cpu_ops: Introduce get_secondary_cpu_ops() Will Deacon
2026-10-09 10:07 ` [PATCH v2 18/23] firmware/psci: Cache PSCI v0.2+ version number to avoid redundant SMCs Will Deacon
2026-10-09 10:07 ` [PATCH v2 19/23] firmware/psci: Extend ->cpu_on() callback to take an additional argument Will Deacon
2026-10-09 10:07 ` [PATCH v2 20/23] arm64: cpu_ops: Expose optional argument to target cpu in ->cpu_boot() Will Deacon
2026-10-09 10:07 ` [PATCH v2 21/23] arm64: smp: Pass secondary CPU boot parameters via firmware if possible Will Deacon
2026-10-09 10:07 ` [PATCH v2 22/23] arm64: smp: Use generic HOTPLUG_PARALLEL machinery for CPU onlining Will Deacon
2026-10-09 10:07 ` Will Deacon [this message]

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=20261009100738.31288-24-will@kernel.org \
    --to=will@kernel.org \
    --cc=ben.horgan@arm.com \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=dwmw@amazon.co.uk \
    --cc=fuad.tabba@linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lpieralisi@kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=pankaj.patil@oss.qualcomm.com \
    --cc=peterz@infradead.org \
    --cc=ruanjinjie@huawei.com \
    --cc=stefion@google.com \
    --cc=tarunsahu@google.com \
    --cc=tglx@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

all inboxes | Powered by JetHome®