From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug alb_break_llc() decides whether to break LLC preference during active load balance. It does so by testing that every runnable fair task on the source rq prefers its LLC: env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable But the two counters cover different sets. nr_pref_llc_running is updated in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued, so it follows queued tasks. h_nr_runnable is updated in set_delayed()/ clear_delayed() and drops delay-dequeued tasks. So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks, alb_break_llc() returns false, and active balance is free to pull a task off its preferred LLC. Active balance only moves runnable tasks, and this is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB skips the per-task test in can_migrate_task(). The runnable set is the one we want. Fix it on the counter side. A task should be counted in nr_pref_llc_running exactly while it is both queued on its preferred LLC (pref_llc_queued) and runnable (!sched_delayed). Define that membership once in task_pref_llc_runnable(), and adjust the counter only through pref_llc_running_inc()/pref_llc_running_dec() from the four sites that change either input: account_llc_enqueue(), account_llc_dequeue(), set_delayed() and clear_delayed(). Gating every update on the same predicate keeps the delay, wake and dequeue paths from double-counting or underflowing; see the comments at those sites for the ordering. nr_llc_running and sd->llc_counts are not touched and stay on queued semantics. Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC") Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/ Reported-by: Zhan Xusheng Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- Documentation/devicetree/bindings/virtio/mmio.yaml | 67 +++++++++++++++ .../devicetree/bindings/virtio/pci-iommu.yaml | 99 ++++++++++++++++++++++ .../devicetree/bindings/virtio/virtio-device.yaml | 41 +++++++++ 3 files changed, 207 insertions(+) create mode 100644 Documentation/devicetree/bindings/virtio/mmio.yaml create mode 100644 Documentation/devicetree/bindings/virtio/pci-iommu.yaml create mode 100644 Documentation/devicetree/bindings/virtio/virtio-device.yaml (limited to 'Documentation/devicetree/bindings/virtio') diff --git a/Documentation/devicetree/bindings/virtio/mmio.yaml b/Documentation/devicetree/bindings/virtio/mmio.yaml new file mode 100644 index 000000000..0aa8433f0 --- /dev/null +++ b/Documentation/devicetree/bindings/virtio/mmio.yaml @@ -0,0 +1,67 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/virtio/mmio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: virtio memory mapped devices + +maintainers: + - Jean-Philippe Brucker + +description: + See https://www.oasis-open.org/committees/tc_home.php?wg_abbrev=virtio for + more details. + +properties: + compatible: + const: virtio,mmio + + reg: + maxItems: 1 + + dma-coherent: true + + interrupts: + maxItems: 1 + + '#iommu-cells': + description: Required when the node corresponds to a virtio-iommu device. + const: 1 + + iommus: + description: Required for devices making accesses thru an IOMMU. + maxItems: 1 + + wakeup-source: + type: boolean + description: Required for setting irq of a virtio_mmio device as wakeup source. + +required: + - compatible + - reg + - interrupts + +additionalProperties: + type: object + +examples: + - | + virtio@3000 { + compatible = "virtio,mmio"; + reg = <0x3000 0x100>; + interrupts = <41>; + + /* Device has endpoint ID 23 */ + iommus = <&viommu 23>; + }; + + viommu: iommu@3100 { + compatible = "virtio,mmio"; + reg = <0x3100 0x100>; + interrupts = <42>; + + #iommu-cells = <1>; + }; + +... diff --git a/Documentation/devicetree/bindings/virtio/pci-iommu.yaml b/Documentation/devicetree/bindings/virtio/pci-iommu.yaml new file mode 100644 index 000000000..8bd6ad72a --- /dev/null +++ b/Documentation/devicetree/bindings/virtio/pci-iommu.yaml @@ -0,0 +1,99 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/virtio/pci-iommu.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: virtio-iommu device using the virtio-pci transport + +maintainers: + - Jean-Philippe Brucker + +description: | + When virtio-iommu uses the PCI transport, its programming interface is + discovered dynamically by the PCI probing infrastructure. However the + device tree statically describes the relation between IOMMU and DMA + masters. Therefore, the PCI root complex that hosts the virtio-iommu + contains a child node representing the IOMMU device explicitly. + + DMA from the IOMMU device isn't managed by another IOMMU. Therefore the + virtio-iommu node doesn't have an "iommus" property, and is omitted from + the iommu-map property of the root complex. + +allOf: + - $ref: /schemas/pci/pci-device.yaml# + +properties: + # If compatible is present, it should contain the vendor and device ID + # according to the PCI Bus Binding specification. Since PCI provides + # built-in identification methods, compatible is not actually required. + compatible: + oneOf: + - items: + - const: virtio,pci-iommu + - const: pci1af4,1057 + - items: + - const: pci1af4,1057 + + reg: + maxItems: 1 + + '#iommu-cells': + const: 1 + +required: + - compatible + - reg + - '#iommu-cells' + +additionalProperties: false + +examples: + - | + bus { + #address-cells = <2>; + #size-cells = <2>; + + pcie@40000000 { + device_type = "pci"; + #address-cells = <3>; + #size-cells = <2>; + reg = <0x0 0x40000000 0x0 0x1000000>; + ranges = <0x02000000 0x0 0x41000000 0x0 0x41000000 0x0 0x0f000000>; + + /* + * The IOMMU manages all functions in this PCI domain except + * itself. Omit BDF 00:01.0. + */ + iommu-map = <0x0 &iommu0 0x0 0x8 + 0x9 &iommu0 0x9 0xfff7>; + + /* The IOMMU programming interface uses slot 00:01.0 */ + iommu0: iommu@1,0 { + compatible = "pci1af4,1057"; + reg = <0x800 0 0 0 0>; + #iommu-cells = <1>; + }; + }; + + pcie@50000000 { + device_type = "pci"; + #address-cells = <3>; + #size-cells = <2>; + reg = <0x0 0x50000000 0x0 0x1000000>; + ranges = <0x02000000 0x0 0x51000000 0x0 0x51000000 0x0 0x0f000000>; + + /* + * The IOMMU also manages all functions from this domain, + * with endpoint IDs 0x10000 - 0x1ffff + */ + iommu-map = <0x0 &iommu0 0x10000 0x10000>; + }; + + ethernet { + /* The IOMMU manages this platform device with endpoint ID 0x20000 */ + iommus = <&iommu0 0x20000>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/virtio/virtio-device.yaml b/Documentation/devicetree/bindings/virtio/virtio-device.yaml new file mode 100644 index 000000000..8c6919ba9 --- /dev/null +++ b/Documentation/devicetree/bindings/virtio/virtio-device.yaml @@ -0,0 +1,41 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/virtio/virtio-device.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Virtio device + +maintainers: + - Viresh Kumar + +description: + These bindings are applicable to virtio devices irrespective of the bus they + are bound to, like mmio or pci. + +# We need a select here so we don't match all nodes with 'virtio,mmio' +properties: + compatible: + pattern: "^virtio,device[0-9a-f]{1,8}$" + description: Virtio device nodes. + "virtio,deviceID", where ID is the virtio device id. The textual + representation of ID shall be in lower case hexadecimal with leading + zeroes suppressed. + +required: + - compatible + +additionalProperties: true + +examples: + - | + virtio@3000 { + compatible = "virtio,mmio"; + reg = <0x3000 0x100>; + interrupts = <43>; + + i2c { + compatible = "virtio,device22"; + }; + }; +... -- cgit v1.3.1