All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lyude Paul <lyude@redhat.com>
To: rust-for-linux@vger.kernel.org, linux-kernel@vger.kernel.org,
	Thomas Gleixner <tglx@linutronix.de>
Cc: "Boqun Feng" <boqun.feng@gmail.com>,
	"Daniel Almeida" <daniel.almeida@collabora.com>,
	"Miguel Ojeda" <ojeda@kernel.org>,
	"Alex Gaynor" <alex.gaynor@gmail.com>,
	"Gary Guo" <gary@garyguo.net>,
	"Björn Roy Baron" <bjorn3_gh@protonmail.com>,
	"Benno Lossin" <lossin@kernel.org>,
	"Andreas Hindborg" <a.hindborg@kernel.org>,
	"Alice Ryhl" <aliceryhl@google.com>,
	"Trevor Gross" <tmgross@umich.edu>,
	"Danilo Krummrich" <dakr@kernel.org>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Ingo Molnar" <mingo@redhat.com>, "Will Deacon" <will@kernel.org>,
	"Waiman Long" <longman@redhat.com>,
	"Joel Fernandes" <joelagnelf@nvidia.com>
Subject: [PATCH v17 02/16] preempt: Track NMI nesting to separate per-CPU counter
Date: Wed, 21 Jan 2026 17:39:05 -0500	[thread overview]
Message-ID: <20260121223933.1568682-3-lyude@redhat.com> (raw)
In-Reply-To: <20260121223933.1568682-1-lyude@redhat.com>

From: Joel Fernandes <joelagnelf@nvidia.com>

Move NMI nesting tracking from the preempt_count bits to a separate per-CPU
counter (nmi_nesting). This is to free up the NMI bits in the preempt_count,
allowing those bits to be repurposed for other uses.  This also has the benefit
of tracking more than 16-levels deep if there is ever a need.

Reduce multiple bits in preempt_count for NMI tracking. Reduce NMI_BITS
from 3 to 1, using it only to detect if we're in an NMI.

Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Joel Fernandes <joelaf@google.com>
Signed-off-by: Lyude Paul <lyude@redhat.com>
---
 include/linux/hardirq.h | 16 ++++++++++++----
 include/linux/preempt.h | 13 +++++++++----
 kernel/softirq.c        |  2 ++
 3 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index d57cab4d4c06f..cc06bda52c3e5 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -10,6 +10,8 @@
 #include <linux/vtime.h>
 #include <asm/hardirq.h>
 
+DECLARE_PER_CPU(unsigned int, nmi_nesting);
+
 extern void synchronize_irq(unsigned int irq);
 extern bool synchronize_hardirq(unsigned int irq);
 
@@ -102,14 +104,16 @@ void irq_exit_rcu(void);
  */
 
 /*
- * nmi_enter() can nest up to 15 times; see NMI_BITS.
+ * nmi_enter() can nest - nesting is tracked in a per-CPU counter.
  */
 #define __nmi_enter()						\
 	do {							\
 		lockdep_off();					\
 		arch_nmi_enter();				\
-		BUG_ON(in_nmi() == NMI_MASK);			\
-		__preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		BUG_ON(__this_cpu_read(nmi_nesting) == UINT_MAX);	\
+		__this_cpu_inc(nmi_nesting);			\
+		__preempt_count_add(HARDIRQ_OFFSET);		\
+		preempt_count_set(preempt_count() | NMI_MASK);	\
 	} while (0)
 
 #define nmi_enter()						\
@@ -124,8 +128,12 @@ void irq_exit_rcu(void);
 
 #define __nmi_exit()						\
 	do {							\
+		unsigned int nesting;				\
 		BUG_ON(!in_nmi());				\
-		__preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		__preempt_count_sub(HARDIRQ_OFFSET);		\
+		nesting = __this_cpu_dec_return(nmi_nesting);	\
+		if (!nesting)					\
+			__preempt_count_sub(NMI_OFFSET);	\
 		arch_nmi_exit();				\
 		lockdep_on();					\
 	} while (0)
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index f07e7f37f3ca5..e2d3079d3f5f1 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -18,6 +18,8 @@
  * - bits 0-7 are the preemption count (max preemption depth: 256)
  * - bits 8-15 are the softirq count (max # of softirqs: 256)
  * - bits 16-23 are the hardirq disable count (max # of hardirq disable: 256)
+ * - bits 24-27 are the hardirq count (max # of hardirqs: 16)
+ * - bit 28 is the NMI flag (no nesting count, tracked separately)
  *
  * The hardirq count could in theory be the same as the number of
  * interrupts in the system, but we run all interrupt handlers with
@@ -25,18 +27,21 @@
  * there are a few palaeontologic drivers which reenable interrupts in
  * the handler, so we need more than one bit here.
  *
+ * NMI nesting depth is tracked in a separate per-CPU variable
+ * (nmi_nesting) to save bits in preempt_count.
+ *
  *         PREEMPT_MASK:	0x000000ff
  *         SOFTIRQ_MASK:	0x0000ff00
  * HARDIRQ_DISABLE_MASK:	0x00ff0000
- *         HARDIRQ_MASK:	0x07000000
- *             NMI_MASK:	0x38000000
+ *         HARDIRQ_MASK:	0x0f000000
+ *             NMI_MASK:	0x10000000
  * PREEMPT_NEED_RESCHED:	0x80000000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
 #define HARDIRQ_DISABLE_BITS	8
-#define HARDIRQ_BITS	3
-#define NMI_BITS	3
+#define HARDIRQ_BITS	4
+#define NMI_BITS	1
 
 #define PREEMPT_SHIFT	0
 #define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 77198911b8dd4..af47ea23aba3b 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -88,6 +88,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirqs_enabled);
 EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
 #endif
 
+DEFINE_PER_CPU(unsigned int, nmi_nesting);
+
 /*
  * SOFTIRQ_OFFSET usage:
  *
-- 
2.52.0


  parent reply	other threads:[~2026-01-21 22:40 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-21 22:39 [PATCH v17 00/16] Refcounted interrupts, SpinLockIrq for rust Lyude Paul
2026-01-21 22:39 ` [PATCH v17 01/16] preempt: Introduce HARDIRQ_DISABLE_BITS Lyude Paul
2026-01-21 22:39 ` Lyude Paul [this message]
2026-02-03 11:44   ` [PATCH v17 02/16] preempt: Track NMI nesting to separate per-CPU counter Peter Zijlstra
2026-02-06  1:22     ` Joel Fernandes
2026-02-03 12:15   ` Peter Zijlstra
2026-02-04 11:12     ` Peter Zijlstra
2026-02-04 12:32       ` Gary Guo
2026-02-04 13:00         ` Peter Zijlstra
2026-02-05 21:40       ` Boqun Feng
2026-02-05 22:17         ` Joel Fernandes
2026-02-06  0:50           ` Joel Fernandes
2026-02-06  1:14             ` Boqun Feng
2026-02-06  1:24               ` Joel Fernandes
2026-02-06  2:51                 ` Boqun Feng
2026-02-06  8:13                   ` Joel Fernandes
2026-02-06 15:28                     ` Boqun Feng
2026-02-06 16:00                       ` Joel Fernandes
2026-02-06 16:16                         ` Boqun Feng
2026-02-07 22:11                           ` Joel Fernandes
2026-02-06  8:42                 ` Peter Zijlstra
2026-02-05 22:07       ` Boqun Feng
2026-02-06  8:45         ` Peter Zijlstra
2026-01-21 22:39 ` [PATCH v17 03/16] preempt: Introduce __preempt_count_{sub, add}_return() Lyude Paul
2026-01-21 22:39 ` [PATCH v17 04/16] openrisc: Include <linux/cpumask.h> in smp.h Lyude Paul
2026-01-21 22:39 ` [PATCH v17 05/16] irq & spin_lock: Add counted interrupt disabling/enabling Lyude Paul
2026-01-21 22:39 ` [PATCH v17 06/16] irq: Add KUnit test for refcounted interrupt enable/disable Lyude Paul
2026-01-30  7:43   ` David Gow
2026-01-21 22:39 ` [PATCH v17 07/16] rust: Introduce interrupt module Lyude Paul
2026-01-21 22:39 ` [PATCH v17 08/16] rust: helper: Add spin_{un,}lock_irq_{enable,disable}() helpers Lyude Paul
2026-01-26 13:25   ` Gary Guo
2026-01-21 22:39 ` [PATCH v17 09/16] rust: sync: Add SpinLockIrq Lyude Paul
2026-01-23 22:26   ` Benno Lossin
2026-01-21 22:39 ` [PATCH v17 10/16] rust: sync: Introduce lock::Lock::lock_with() and friends Lyude Paul
2026-01-22 11:56   ` kernel test robot
2026-01-23 22:55   ` Benno Lossin
2026-01-26 13:31   ` Gary Guo
2026-01-21 22:39 ` [PATCH v17 11/16] rust: sync: Expose lock::Backend Lyude Paul
2026-01-23 22:56   ` Benno Lossin
2026-01-21 22:39 ` [PATCH v17 12/16] rust: sync: lock/global: Rename B to G in trait bounds Lyude Paul
2026-01-21 22:39 ` [PATCH v17 13/16] rust: sync: Add a lifetime parameter to lock::global::GlobalGuard Lyude Paul
2026-01-21 22:39 ` [PATCH v17 14/16] rust: sync: lock/global: Add Backend parameter to GlobalGuard Lyude Paul
2026-01-21 22:39 ` [PATCH v17 15/16] rust: sync: lock/global: Add ContextualBackend support to GlobalLock Lyude Paul
2026-01-21 22:39 ` [PATCH v17 16/16] locking: Switch to _irq_{disable,enable}() variants in cleanup guards Lyude Paul
2026-01-26 13:24 ` [PATCH v17 00/16] Refcounted interrupts, SpinLockIrq for rust Gary Guo
2026-01-26 16:17 ` Boqun Feng
2026-02-03  0:36   ` Boqun Feng

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=20260121223933.1568682-3-lyude@redhat.com \
    --to=lyude@redhat.com \
    --cc=a.hindborg@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alex.gaynor@gmail.com \
    --cc=aliceryhl@google.com \
    --cc=bjorn3_gh@protonmail.com \
    --cc=boqun.feng@gmail.com \
    --cc=dakr@kernel.org \
    --cc=daniel.almeida@collabora.com \
    --cc=gary@garyguo.net \
    --cc=joelagnelf@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longman@redhat.com \
    --cc=lossin@kernel.org \
    --cc=mingo@redhat.com \
    --cc=ojeda@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rust-for-linux@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=tmgross@umich.edu \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.