All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sohil Mehta <sohil.mehta@intel.com>
To: x86@kernel.org
Cc: Sohil Mehta <sohil.mehta@intel.com>,
	Tony Luck <tony.luck@intel.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	"H . Peter Anvin" <hpa@zytor.com>,
	Andy Lutomirski <luto@kernel.org>, Jens Axboe <axboe@kernel.dk>,
	Christian Brauner <christian@brauner.io>,
	Peter Zijlstra <peterz@infradead.org>,
	Shuah Khan <shuah@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
	Jonathan Corbet <corbet@lwn.net>, Ashok Raj <ashok.raj@intel.com>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>,
	Gayatri Kammela <gayatri.kammela@intel.com>,
	Zeng Guang <guang.zeng@intel.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Randy E Witt <randy.e.witt@intel.com>,
	Ravi V Shankar <ravi.v.shankar@intel.com>,
	Ramesh Thomas <ramesh.thomas@intel.com>,
	linux-api@vger.kernel.org, linux-arch@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org
Subject: [RFC PATCH 05/13] x86/irq: Reserve a user IPI notification vector
Date: Mon, 13 Sep 2021 13:01:24 -0700	[thread overview]
Message-ID: <20210913200132.3396598-6-sohil.mehta@intel.com> (raw)
In-Reply-To: <20210913200132.3396598-1-sohil.mehta@intel.com>

A user interrupt notification vector is used on the receiver's cpu to
identify an interrupt as a user interrupt (and not a kernel interrupt).
Hardware uses the same notification vector to generate an IPI from a
sender's cpu core when the SENDUIPI instruction is executed.

Typically, the kernel shouldn't receive an interrupt with this vector.
However, it is possible that the kernel might receive this vector.

Scenario that can cause the spurious interrupt:

Step	cpu 0 (receiver task)		cpu 1 (sender task)
----	---------------------		-------------------
1	task is running
2					executes SENDUIPI
3					IPI sent
4	context switched out
5	IPI delivered
	(kernel interrupt detected)

A kernel interrupt can be detected, if a receiver task gets scheduled
out after the SENDUIPI-based IPI was sent but before the IPI was
delivered.

The kernel doesn't need to do anything in this case other than receiving
the interrupt and clearing the local APIC. The user interrupt is always
stored in the receiver's UPID before the IPI is generated. When the
receiver gets scheduled back the interrupt would be delivered based on
its UPID.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Sohil Mehta <sohil.mehta@intel.com>
---
 arch/x86/include/asm/hardirq.h     |  3 +++
 arch/x86/include/asm/idtentry.h    |  4 ++++
 arch/x86/include/asm/irq_vectors.h |  5 ++++-
 arch/x86/kernel/idt.c              |  3 +++
 arch/x86/kernel/irq.c              | 33 ++++++++++++++++++++++++++++++
 5 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 275e7fd20310..279afc01f1ac 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -19,6 +19,9 @@ typedef struct {
 	unsigned int kvm_posted_intr_ipis;
 	unsigned int kvm_posted_intr_wakeup_ipis;
 	unsigned int kvm_posted_intr_nested_ipis;
+#endif
+#ifdef CONFIG_X86_USER_INTERRUPTS
+	unsigned int uintr_spurious_count;
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 1345088e9902..5929a6f9eeee 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -671,6 +671,10 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR,	sysvec_kvm_posted_intr_wakeup
 DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,	sysvec_kvm_posted_intr_nested_ipi);
 #endif
 
+#ifdef CONFIG_X86_USER_INTERRUPTS
+DECLARE_IDTENTRY_SYSVEC(UINTR_NOTIFICATION_VECTOR,	sysvec_uintr_spurious_interrupt);
+#endif
+
 #if IS_ENABLED(CONFIG_HYPERV)
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
 DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 43dcb9284208..d26faa504931 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -104,7 +104,10 @@
 #define HYPERV_STIMER0_VECTOR		0xed
 #endif
 
-#define LOCAL_TIMER_VECTOR		0xec
+/* Vector for User interrupt notifications */
+#define UINTR_NOTIFICATION_VECTOR       0xec
+
+#define LOCAL_TIMER_VECTOR		0xeb
 
 #define NR_VECTORS			 256
 
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index df0fa695bb09..d8c45e0728f0 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -147,6 +147,9 @@ static const __initconst struct idt_data apic_idts[] = {
 	INTG(POSTED_INTR_WAKEUP_VECTOR,		asm_sysvec_kvm_posted_intr_wakeup_ipi),
 	INTG(POSTED_INTR_NESTED_VECTOR,		asm_sysvec_kvm_posted_intr_nested_ipi),
 # endif
+#ifdef CONFIG_X86_USER_INTERRUPTS
+	INTG(UINTR_NOTIFICATION_VECTOR,		asm_sysvec_uintr_spurious_interrupt),
+#endif
 # ifdef CONFIG_IRQ_WORK
 	INTG(IRQ_WORK_VECTOR,			asm_sysvec_irq_work),
 # endif
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index e28f6a5d14f1..e3c35668c7c5 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -181,6 +181,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ",
 			   irq_stats(j)->kvm_posted_intr_wakeup_ipis);
 	seq_puts(p, "  Posted-interrupt wakeup event\n");
+#endif
+#ifdef CONFIG_X86_USER_INTERRUPTS
+	seq_printf(p, "%*s: ", prec, "UIS");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->uintr_spurious_count);
+	seq_puts(p, "  User-interrupt spurious event\n");
 #endif
 	return 0;
 }
@@ -325,6 +331,33 @@ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi)
 }
 #endif
 
+#ifdef CONFIG_X86_USER_INTERRUPTS
+/*
+ * Handler for UINTR_NOTIFICATION_VECTOR.
+ *
+ * The notification vector is used by the cpu to detect a User Interrupt. In
+ * the typical usage, the cpu would handle this interrupt and clear the local
+ * apic.
+ *
+ * However, it is possible that the kernel might receive this vector. This can
+ * happen if the receiver thread was running when the interrupt was sent but it
+ * got scheduled out before the interrupt was delivered. The kernel doesn't
+ * need to do anything other than clearing the local APIC. A pending user
+ * interrupt is always saved in the receiver's UPID which can be referenced
+ * when the receiver gets scheduled back.
+ *
+ * If the kernel receives a storm of these, it could mean an issue with the
+ * kernel's saving and restoring of the User Interrupt MSR state; Specifically,
+ * the notification vector bits in the IA32_UINTR_MISC_MSR.
+ */
+DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_uintr_spurious_interrupt)
+{
+	/* TODO: Add entry-exit tracepoints */
+	ack_APIC_irq();
+	inc_irq_stat(uintr_spurious_count);
+}
+#endif
+
 
 #ifdef CONFIG_HOTPLUG_CPU
 /* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
-- 
2.33.0


  parent reply	other threads:[~2021-09-13 20:05 UTC|newest]

Thread overview: 89+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-13 20:01 [RFC PATCH 00/13] x86 User Interrupts support Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 01/13] x86/uintr/man-page: Include man pages draft for reference Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 02/13] Documentation/x86: Add documentation for User Interrupts Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 03/13] x86/cpu: Enumerate User Interrupts support Sohil Mehta
2021-09-23 22:24   ` Thomas Gleixner
2021-09-24 19:59     ` Sohil Mehta
2021-09-27 20:42     ` Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 04/13] x86/fpu/xstate: Enumerate User Interrupts supervisor state Sohil Mehta
2021-09-23 22:34   ` Thomas Gleixner
2021-09-27 22:25     ` Sohil Mehta
2021-09-13 20:01 ` Sohil Mehta [this message]
2021-09-23 23:07   ` [RFC PATCH 05/13] x86/irq: Reserve a user IPI notification vector Thomas Gleixner
2021-09-25 13:30     ` Thomas Gleixner
2021-09-26 12:39       ` Thomas Gleixner
2021-09-27 19:07         ` Sohil Mehta
2021-09-28  8:11           ` Thomas Gleixner
2021-09-27 19:26     ` Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 06/13] x86/uintr: Introduce uintr receiver syscalls Sohil Mehta
2021-09-23 12:26   ` Greg KH
2021-09-24  0:05     ` Thomas Gleixner
2021-09-27 23:20     ` Sohil Mehta
2021-09-28  4:39       ` Greg KH
2021-09-28 16:47         ` Sohil Mehta
2021-09-23 23:52   ` Thomas Gleixner
2021-09-27 23:57     ` Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 07/13] x86/process/64: Add uintr task context switch support Sohil Mehta
2021-09-24  0:41   ` Thomas Gleixner
2021-09-28  0:30     ` Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 08/13] x86/process/64: Clean up uintr task fork and exit paths Sohil Mehta
2021-09-24  1:02   ` Thomas Gleixner
2021-09-28  1:23     ` Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 09/13] x86/uintr: Introduce vector registration and uintr_fd syscall Sohil Mehta
2021-09-24 10:33   ` Thomas Gleixner
2021-09-28 20:40     ` Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 10/13] x86/uintr: Introduce user IPI sender syscalls Sohil Mehta
2021-09-23 12:28   ` Greg KH
2021-09-28 18:01     ` Sohil Mehta
2021-09-29  7:04       ` Greg KH
2021-09-29 14:27         ` Sohil Mehta
2021-09-24 10:54   ` Thomas Gleixner
2021-09-13 20:01 ` [RFC PATCH 11/13] x86/uintr: Introduce uintr_wait() syscall Sohil Mehta
2021-09-24 11:04   ` Thomas Gleixner
2021-09-25 12:08     ` Thomas Gleixner
2021-09-28 23:13       ` Sohil Mehta
2021-09-28 23:08     ` Sohil Mehta
2021-09-26 14:41   ` Thomas Gleixner
2021-09-29  1:09     ` Sohil Mehta
2021-09-29  3:30   ` Andy Lutomirski
2021-09-29  4:56     ` Sohil Mehta
2021-09-30 18:08       ` Andy Lutomirski
2021-09-30 19:29         ` Thomas Gleixner
2021-09-30 22:01           ` Andy Lutomirski
2021-10-01  0:01             ` Thomas Gleixner
2021-10-01  4:41               ` Andy Lutomirski
2021-10-01  9:56                 ` Thomas Gleixner
2021-10-01 15:13                   ` Andy Lutomirski
2021-10-01 18:04                     ` Sohil Mehta
2021-10-01 21:29                     ` Thomas Gleixner
2021-10-01 23:00                       ` Sohil Mehta
2021-10-01 23:04                       ` Andy Lutomirski
2021-09-13 20:01 ` [RFC PATCH 12/13] x86/uintr: Wire up the user interrupt syscalls Sohil Mehta
2021-09-13 20:01 ` [RFC PATCH 13/13] selftests/x86: Add basic tests for User IPI Sohil Mehta
2021-09-13 20:27 ` [RFC PATCH 00/13] x86 User Interrupts support Dave Hansen
2021-09-14 19:03   ` Mehta, Sohil
2021-09-23 12:19     ` Greg KH
2021-09-23 14:09       ` Greg KH
2021-09-23 14:46         ` Dave Hansen
2021-09-23 15:07           ` Greg KH
2021-09-23 23:24         ` Sohil Mehta
2021-09-23 23:09       ` Sohil Mehta
2021-09-24  0:17       ` Sohil Mehta
2021-09-23 14:39 ` Jens Axboe
2021-09-29  4:31 ` Andy Lutomirski
2021-09-30 16:30   ` Stefan Hajnoczi
2021-09-30 17:24     ` Sohil Mehta
2021-09-30 17:26       ` Andy Lutomirski
2021-10-01 16:35       ` Stefan Hajnoczi
2021-10-01 16:35         ` Stefan Hajnoczi
2021-10-01 16:41         ` Richard Henderson
2021-10-01 16:41           ` Richard Henderson
2021-09-30 16:26 ` Stefan Hajnoczi
2021-10-01  0:40   ` Sohil Mehta
2021-10-01  8:19 ` Pavel Machek
2021-11-18 22:19   ` Sohil Mehta
2021-11-16  3:49 ` Prakash Sangappa
2021-11-18 21:44   ` Sohil Mehta
2021-12-22 16:17 ` Chrisma Pakha
2022-01-07  2:08   ` Sohil Mehta
2022-01-17  1:14     ` Chrisma Pakha

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=20210913200132.3396598-6-sohil.mehta@intel.com \
    --to=sohil.mehta@intel.com \
    --cc=arnd@arndb.de \
    --cc=ashok.raj@intel.com \
    --cc=axboe@kernel.dk \
    --cc=bp@alien8.de \
    --cc=christian@brauner.io \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=gayatri.kammela@intel.com \
    --cc=guang.zeng@intel.com \
    --cc=hpa@zytor.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=ramesh.thomas@intel.com \
    --cc=randy.e.witt@intel.com \
    --cc=ravi.v.shankar@intel.com \
    --cc=shuah@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=tony.luck@intel.com \
    --cc=x86@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.