xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Feng Wu <feng.wu@intel.com>
To: xen-devel@lists.xen.org
Cc: Kevin Tian <kevin.tian@intel.com>, Feng Wu <feng.wu@intel.com>,
	Jan Beulich <jbeulich@suse.com>
Subject: [PATCH v6 03/18] iommu: Add iommu_intpost to control VT-d Posted-Interrupts feature
Date: Tue, 25 Aug 2015 09:57:42 +0800	[thread overview]
Message-ID: <1440467877-5116-4-git-send-email-feng.wu@intel.com> (raw)
In-Reply-To: <1440467877-5116-1-git-send-email-feng.wu@intel.com>

VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt.
With VT-d Posted-Interrupts enabled, external interrupts from
direct-assigned devices can be delivered to guests without VMM
intervention when guest is running in non-root mode.

This patch adds variable 'iommu_intpost' to control whether enable VT-d
posted-interrupt or not in the generic IOMMU code.

CC: Jan Beulich <jbeulich@suse.com>
CC: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Feng Wu <feng.wu@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
v5:
- Remove the "if no intremap then no intpost" logic in parse_iommu_param(), which
  can be covered in iommu_setup()

v3:
- Remove pointless initializer for 'iommu_intpost'.
- Some adjustment for "if no intremap then no intpost" logic.
    * For parse_iommu_param(), move it to the end of the function,
      so we don't need to add the some logic when introduing the
      new kernel parameter 'intpost' in later patch.
    * Add this logic in iommu_setup() after iommu_hardware_setup()
      is called.

 xen/drivers/passthrough/iommu.c | 13 ++++++++++++-
 xen/include/xen/iommu.h         |  2 +-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index fc7831e..36d5cc0 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -51,6 +51,14 @@ bool_t __read_mostly iommu_passthrough;
 bool_t __read_mostly iommu_snoop = 1;
 bool_t __read_mostly iommu_qinval = 1;
 bool_t __read_mostly iommu_intremap = 1;
+
+/*
+ * In the current implementation of VT-d posted interrupts, in some extreme
+ * cases, the per cpu list which saves the blocked vCPU will be very long,
+ * and this will affect the interrupt latency, so let this feature off by
+ * default until we find a good solution to resolve it.
+ */
+bool_t __read_mostly iommu_intpost;
 bool_t __read_mostly iommu_hap_pt_share = 1;
 bool_t __read_mostly iommu_debug;
 bool_t __read_mostly amd_iommu_perdev_intremap = 1;
@@ -307,6 +315,9 @@ int __init iommu_setup(void)
         panic("Couldn't enable %s and iommu=required/force",
               !iommu_enabled ? "IOMMU" : "Interrupt Remapping");
 
+    if ( !iommu_intremap )
+        iommu_intpost = 0;
+
     if ( !iommu_enabled )
     {
         iommu_snoop = 0;
@@ -374,7 +385,7 @@ void iommu_crash_shutdown(void)
     const struct iommu_ops *ops = iommu_get_ops();
     if ( iommu_enabled )
         ops->crash_shutdown();
-    iommu_enabled = iommu_intremap = 0;
+    iommu_enabled = iommu_intremap = iommu_intpost = 0;
 }
 
 int iommu_get_reserved_device_memory(iommu_grdm_t *func, void *ctxt)
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index 8f3a20e..1f5d04a 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -30,7 +30,7 @@
 extern bool_t iommu_enable, iommu_enabled;
 extern bool_t force_iommu, iommu_verbose;
 extern bool_t iommu_workaround_bios_bug, iommu_igfx, iommu_passthrough;
-extern bool_t iommu_snoop, iommu_qinval, iommu_intremap;
+extern bool_t iommu_snoop, iommu_qinval, iommu_intremap, iommu_intpost;
 extern bool_t iommu_hap_pt_share;
 extern bool_t iommu_debug;
 extern bool_t amd_iommu_perdev_intremap;
-- 
2.1.0

  parent reply	other threads:[~2015-08-25  1:57 UTC|newest]

Thread overview: 105+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-08-25  1:57 [PATCH v6 00/18] Add VT-d Posted-Interrupts support Feng Wu
2015-08-25  1:57 ` [PATCH v6 01/18] VT-d Posted-intterrupt (PI) design Feng Wu
2015-08-25  1:57 ` [PATCH v6 02/18] Add cmpxchg16b support for x86-64 Feng Wu
2015-09-04 14:22   ` Jan Beulich
2015-09-06  6:07     ` Wu, Feng
2015-09-06  6:32       ` Wu, Feng
2015-09-07 10:36         ` Jan Beulich
2015-09-08  7:37           ` Wu, Feng
2015-09-08  8:52             ` Jan Beulich
2015-09-08  8:57               ` Wu, Feng
2015-09-08  9:19                 ` Jan Beulich
2015-09-08  9:30                   ` Wu, Feng
2015-09-07 10:34       ` Jan Beulich
2015-09-07 10:39       ` Jan Beulich
2015-09-04 15:12   ` Jan Beulich
2015-08-25  1:57 ` Feng Wu [this message]
2015-09-04 14:26   ` [PATCH v6 03/18] iommu: Add iommu_intpost to control VT-d Posted-Interrupts feature Jan Beulich
2015-08-25  1:57 ` [PATCH v6 04/18] vt-d: VT-d Posted-Interrupts feature detection Feng Wu
2015-09-04 14:31   ` Jan Beulich
2015-09-06  1:49     ` Wu, Feng
2015-09-07 10:43       ` Jan Beulich
2015-09-08  2:35         ` Wu, Feng
2015-09-08  5:18           ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 05/18] vmx: Extend struct pi_desc to support VT-d Posted-Interrupts Feng Wu
2015-09-04 14:32   ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 06/18] vmx: Add some helper functions for Posted-Interrupts Feng Wu
2015-09-04 14:40   ` Jan Beulich
2015-09-06  2:05     ` Wu, Feng
2015-09-07 10:46       ` Jan Beulich
2015-09-08  2:39         ` Wu, Feng
2015-09-08  5:22           ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 07/18] vmx: Initialize VT-d Posted-Interrupts Descriptor Feng Wu
2015-09-04 14:47   ` Jan Beulich
2015-09-06  2:22     ` Wu, Feng
2015-09-07 10:49       ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 08/18] vmx: Suppress posting interrupts when 'SN' is set Feng Wu
2015-09-04 14:53   ` Jan Beulich
2015-09-06  2:33     ` Wu, Feng
2015-09-07 10:51       ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 09/18] VT-d: Remove pointless casts Feng Wu
2015-09-04 14:55   ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 10/18] vt-d: Extend struct iremap_entry to support VT-d Posted-Interrupts Feng Wu
2015-08-25  1:57 ` [PATCH v6 11/18] vt-d: Add API to update IRTE when VT-d PI is used Feng Wu
2015-09-04 15:11   ` Jan Beulich
2015-09-06  5:24     ` Wu, Feng
2015-09-07 10:54       ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 12/18] x86: move some APIC related macros to apicdef.h Feng Wu
2015-09-04 15:15   ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 13/18] Update IRTE according to guest interrupt config changes Feng Wu
2015-09-04 15:59   ` Jan Beulich
2015-09-06  4:54     ` Wu, Feng
2015-09-07 11:03       ` Jan Beulich
2015-09-08  4:47         ` Wu, Feng
2015-09-08  9:02           ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 14/18] vmx: posted-interrupt handling when vCPU is blocked Feng Wu
2015-09-07 11:47   ` Jan Beulich
2015-09-08  8:50     ` Wu, Feng
2015-09-08  9:08       ` Jan Beulich
2015-09-08  9:14         ` Wu, Feng
2015-08-25  1:57 ` [PATCH v6 15/18] vmx: Properly handle notification event when vCPU is running Feng Wu
2015-09-07 12:10   ` Jan Beulich
2015-09-07 13:00     ` Zhang, Yang Z
2015-09-07 13:12       ` Jan Beulich
2015-09-08  1:38         ` Zhang, Yang Z
2015-09-08  8:57           ` Jan Beulich
2015-09-08  5:18     ` Wu, Feng
2015-09-08  9:13       ` Jan Beulich
2015-09-08  9:23         ` Wu, Feng
2015-09-08  9:31           ` Jan Beulich
2015-09-08  9:36             ` Wu, Feng
2015-09-08 10:13               ` Jan Beulich
2015-09-08 10:15                 ` Wu, Feng
2015-08-25  1:57 ` [PATCH v6 16/18] vmx: Add some scheduler hooks for VT-d posted interrupts Feng Wu
2015-09-07 12:54   ` Jan Beulich
2015-09-09  8:56     ` Wu, Feng
2015-09-09 10:26       ` Jan Beulich
2015-09-10  2:07         ` Wu, Feng
2015-09-10  8:27           ` Jan Beulich
2015-09-10  8:59             ` Wu, Feng
2015-09-10  9:26               ` Jan Beulich
2015-09-10  9:41                 ` Wu, Feng
2015-09-10 10:01                   ` Jan Beulich
2015-09-10 12:34                     ` Wu, Feng
2015-09-10 12:44                       ` Jan Beulich
2015-09-10 12:58                         ` Wu, Feng
2015-09-10 13:15                           ` Jan Beulich
2015-09-10 13:27                             ` Wu, Feng
2015-09-10 14:01                               ` Jan Beulich
2015-09-16  8:56                 ` Wu, Feng
2015-09-16 17:08               ` George Dunlap
2015-09-17  6:26                 ` Wu, Feng
2015-09-16 16:56     ` George Dunlap
2015-09-17  6:15       ` Wu, Feng
2015-09-21  8:23       ` Jan Beulich
2015-09-21  9:28         ` George Dunlap
2015-09-21 11:56           ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 17/18] VT-d: Dump the posted format IRTE Feng Wu
2015-09-07 13:04   ` Jan Beulich
2015-09-08  5:38     ` Wu, Feng
2015-09-08  9:16       ` Jan Beulich
2015-08-25  1:57 ` [PATCH v6 18/18] Add a command line parameter for VT-d posted-interrupts Feng Wu
2015-09-07 13:05   ` Jan Beulich
2015-09-01  5:13 ` [PATCH v6 00/18] Add VT-d Posted-Interrupts support Wu, Feng
2015-09-01  5:20   ` Jan Beulich
2015-09-01  5:32     ` Wu, 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=1440467877-5116-4-git-send-email-feng.wu@intel.com \
    --to=feng.wu@intel.com \
    --cc=jbeulich@suse.com \
    --cc=kevin.tian@intel.com \
    --cc=xen-devel@lists.xen.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;
as well as URLs for NNTP newsgroup(s).