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>] [day] [month] [year] [list]
Message-ID: <175413713418.1420.12184653889719341688.tip-bot2@tip-bot2>
Date: Sat, 02 Aug 2025 12:18:54 -0000
From: "tip-bot2 for Thomas Gleixner" <tip-bot2@...utronix.de>
To: linux-tip-commits@...r.kernel.org
Cc: Hogan Wang <hogan.wang@...wei.com>, Thomas Gleixner <tglx@...utronix.de>,
 x86@...nel.org, linux-kernel@...r.kernel.org
Subject: [tip: x86/urgent] x86/irq: Plug vector setup race

The following commit has been merged into the x86/urgent branch of tip:

Commit-ID:     69adc077da4c247dd39a8a0e3a898a25924e98d0
Gitweb:        https://git.kernel.org/tip/69adc077da4c247dd39a8a0e3a898a25924e98d0
Author:        Thomas Gleixner <tglx@...utronix.de>
AuthorDate:    Thu, 24 Jul 2025 12:49:30 +02:00
Committer:     Thomas Gleixner <tglx@...utronix.de>
CommitterDate: Sat, 02 Aug 2025 14:09:38 +02:00

x86/irq: Plug vector setup race

Hogan reported a vector setup race, which overwrites the interrupt
descriptor in the per CPU vector array resulting in a disfunctional device.

CPU0				CPU1
				interrupt is raised in APIC IRR
				but not handled
  free_irq()
    per_cpu(vector_irq, CPU1)[vector] = VECTOR_SHUTDOWN;

  request_irq()			common_interrupt()
  				  d = this_cpu_read(vector_irq[vector]);

    per_cpu(vector_irq, CPU1)[vector] = desc;

    				  if (d == VECTOR_SHUTDOWN)
				    this_cpu_write(vector_irq[vector], VECTOR_UNUSED);

free_irq() cannot observe the pending vector in the CPU1 APIC as there is
no way to query the remote CPUs APIC IRR.

This requires that request_irq() uses the same vector/CPU as the one which
was freed, but this also can be triggered by a spurious interrupt.

Prevent this by reevaluating vector_irq under the vector lock, which is
held by the interrupt activation code when vector_irq is updated.

Interestingly enough this problem managed to be hidden for more than a
decade.

Fixes: 9345005f4eed ("x86/irq: Fix do_IRQ() interrupt warning for cpu hotplug retriggered irqs")
Reported-by: Hogan Wang <hogan.wang@...wei.com>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Tested-by: Hogan Wang <hogan.wang@...wei.com>
Link: https://lore.kernel.org/all/draft-87ikjhrhhh.ffs@tglx
---
 arch/x86/kernel/irq.c | 63 ++++++++++++++++++++++++++++++++----------
 1 file changed, 48 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 9ed29ff..10721a1 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -256,26 +256,59 @@ static __always_inline void handle_irq(struct irq_desc *desc,
 		__handle_irq(desc, regs);
 }
 
-static __always_inline int call_irq_handler(int vector, struct pt_regs *regs)
+static struct irq_desc *reevaluate_vector(int vector)
 {
-	struct irq_desc *desc;
-	int ret = 0;
+	struct irq_desc *desc = __this_cpu_read(vector_irq[vector]);
+
+	if (!IS_ERR_OR_NULL(desc))
+		return desc;
+
+	if (desc == VECTOR_UNUSED)
+		pr_emerg_ratelimited("No irq handler for %d.%u\n", smp_processor_id(), vector);
+	else
+		__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+	return NULL;
+}
+
+static __always_inline bool call_irq_handler(int vector, struct pt_regs *regs)
+{
+	struct irq_desc *desc = __this_cpu_read(vector_irq[vector]);
 
-	desc = __this_cpu_read(vector_irq[vector]);
 	if (likely(!IS_ERR_OR_NULL(desc))) {
 		handle_irq(desc, regs);
-	} else {
-		ret = -EINVAL;
-		if (desc == VECTOR_UNUSED) {
-			pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n",
-					     __func__, smp_processor_id(),
-					     vector);
-		} else {
-			__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
-		}
+		return true;
 	}
 
-	return ret;
+	/*
+	 * Reevaluate with vector_lock held to prevent a race against
+	 * request_irq() setting up the vector:
+	 *
+	 * CPU0				CPU1
+	 *				interrupt is raised in APIC IRR
+	 *				but not handled
+	 * free_irq()
+	 *   per_cpu(vector_irq, CPU1)[vector] = VECTOR_SHUTDOWN;
+	 *
+	 * request_irq()		common_interrupt()
+	 *				  d = this_cpu_read(vector_irq[vector]);
+	 *
+	 * per_cpu(vector_irq, CPU1)[vector] = desc;
+	 *
+	 *				  if (d == VECTOR_SHUTDOWN)
+	 *				    this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+	 *
+	 * This requires that the same vector on the same target CPU is
+	 * handed out or that a spurious interrupt hits that CPU/vector.
+	 */
+	lock_vector_lock();
+	desc = reevaluate_vector(vector);
+	unlock_vector_lock();
+
+	if (!desc)
+		return false;
+
+	handle_irq(desc, regs);
+	return true;
 }
 
 /*
@@ -289,7 +322,7 @@ DEFINE_IDTENTRY_IRQ(common_interrupt)
 	/* entry code tells RCU that we're not quiescent.  Check it. */
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
 
-	if (unlikely(call_irq_handler(vector, regs)))
+	if (unlikely(!call_irq_handler(vector, regs)))
 		apic_eoi();
 
 	set_irq_regs(old_regs);

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ