public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Oliver Upton <oliver.upton@linux.dev>
To: kvmarm@lists.linux.dev
Cc: kvm@vger.kernel.org, Marc Zyngier <maz@kernel.org>,
	James Morse <james.morse@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Zenghui Yu <yuzenghui@huawei.com>,
	linux-kernel@vger.kernel.org,
	Oliver Upton <oliver.upton@linux.dev>
Subject: [PATCH v3 00/10] KVM: arm64: Avoid serializing LPI get() / put()
Date: Fri, 16 Feb 2024 18:41:43 +0000	[thread overview]
Message-ID: <20240216184153.2714504-1-oliver.upton@linux.dev> (raw)

As discussed, here is a slimmed-down series for addressing lock
serialization in the vgic_get_irq() / vgic_put_irq() path for LPIs. The
bulk of it is using an xarray to represent LPIs and leveraging RCU to
avoid serializing readers of the LPI configuration state.

There's a lot of potential for clean-up, but this is intentionally
deferred until after we fix up the LPI translation cache.

v2: https://lore.kernel.org/kvmarm/20240213093250.3960069-1-oliver.upton@linux.dev/

v2 -> v3:
 - Fix the stupid lock imbalance once and for all (Dan)
 - Drop the tracepoints / stats I used for debugging my own crap (Marc)

Oliver Upton (10):
  KVM: arm64: vgic: Store LPIs in an xarray
  KVM: arm64: vgic: Use xarray to find LPI in vgic_get_lpi()
  KVM: arm64: vgic-v3: Iterate the xarray to find pending LPIs
  KVM: arm64: vgic-its: Walk the LPI xarray in vgic_copy_lpi_list()
  KVM: arm64: vgic: Get rid of the LPI linked-list
  KVM: arm64: vgic: Use atomics to count LPIs
  KVM: arm64: vgic: Free LPI vgic_irq structs in an RCU-safe manner
  KVM: arm64: vgic: Rely on RCU protection in vgic_get_lpi()
  KVM: arm64: vgic: Ensure the irq refcount is nonzero when taking a ref
  KVM: arm64: vgic: Don't acquire the lpi_list_lock in vgic_put_irq()

 arch/arm64/kvm/vgic/vgic-debug.c |  2 +-
 arch/arm64/kvm/vgic/vgic-init.c  |  4 ++-
 arch/arm64/kvm/vgic/vgic-its.c   | 53 +++++++++++++++++++-----------
 arch/arm64/kvm/vgic/vgic-v3.c    |  3 +-
 arch/arm64/kvm/vgic/vgic.c       | 56 ++++++++++----------------------
 arch/arm64/kvm/vgic/vgic.h       | 15 ++++++---
 include/kvm/arm_vgic.h           |  9 ++---
 7 files changed, 73 insertions(+), 69 deletions(-)


base-commit: 6613476e225e090cc9aad49be7fa504e290dd33d
-- 
2.44.0.rc0.258.g7320e95886-goog


             reply	other threads:[~2024-02-16 18:42 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-16 18:41 Oliver Upton [this message]
2024-02-16 18:41 ` [PATCH v3 01/10] KVM: arm64: vgic: Store LPIs in an xarray Oliver Upton
2024-02-20 16:30   ` Zenghui Yu
2024-02-20 17:15     ` Oliver Upton
2024-02-21  5:11       ` Zenghui Yu
2024-02-21  5:13         ` Oliver Upton
2024-02-20 17:24     ` Marc Zyngier
2024-02-20 17:43       ` Oliver Upton
2024-02-20 17:53         ` Marc Zyngier
2024-02-20 17:57           ` Oliver Upton
2024-02-16 18:41 ` [PATCH v3 02/10] KVM: arm64: vgic: Use xarray to find LPI in vgic_get_lpi() Oliver Upton
2024-02-16 18:41 ` [PATCH v3 03/10] KVM: arm64: vgic-v3: Iterate the xarray to find pending LPIs Oliver Upton
2024-02-16 18:41 ` [PATCH v3 04/10] KVM: arm64: vgic-its: Walk the LPI xarray in vgic_copy_lpi_list() Oliver Upton
2024-02-18  8:46   ` Zenghui Yu
2024-02-18 10:28     ` Marc Zyngier
2024-02-18 18:05       ` Oliver Upton
2024-02-16 18:41 ` [PATCH v3 05/10] KVM: arm64: vgic: Get rid of the LPI linked-list Oliver Upton
2024-02-16 18:41 ` [PATCH v3 06/10] KVM: arm64: vgic: Use atomics to count LPIs Oliver Upton
2024-02-16 18:41 ` [PATCH v3 07/10] KVM: arm64: vgic: Free LPI vgic_irq structs in an RCU-safe manner Oliver Upton
2024-02-16 18:41 ` [PATCH v3 08/10] KVM: arm64: vgic: Rely on RCU protection in vgic_get_lpi() Oliver Upton
2024-02-16 18:41 ` [PATCH v3 09/10] KVM: arm64: vgic: Ensure the irq refcount is nonzero when taking a ref Oliver Upton
2024-02-16 18:41 ` [PATCH v3 10/10] KVM: arm64: vgic: Don't acquire the lpi_list_lock in vgic_put_irq() Oliver Upton

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=20240216184153.2714504-1-oliver.upton@linux.dev \
    --to=oliver.upton@linux.dev \
    --cc=james.morse@arm.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=suzuki.poulose@arm.com \
    --cc=yuzenghui@huawei.com \
    /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