4.14-stable patches

added patches:
	sched-fair-optimize-select_idle_cpu.patch
	xen-pciback-redo-vf-placement-in-the-virtual-topology.patch

diff --git a/queue-4.14/sched-fair-optimize-select_idle_cpu.patch b/queue-4.14/sched-fair-optimize-select_idle_cpu.patch
new file mode 100644 (file)
index 0000000..a46dea1
--- /dev/null
+++ b/queue-4.14/sched-fair-optimize-select_idle_cpu.patch
@@ -0,0 +1,63 @@
+From 60588bfa223ff675b95f866249f90616613fbe31 Mon Sep 17 00:00:00 2001
+From: Cheng Jian <cj.chengjian@huawei.com>
+Date: Fri, 13 Dec 2019 10:45:30 +0800
+Subject: sched/fair: Optimize select_idle_cpu
+
+From: Cheng Jian <cj.chengjian@huawei.com>
+
+commit 60588bfa223ff675b95f866249f90616613fbe31 upstream.
+
+select_idle_cpu() will scan the LLC domain for idle CPUs,
+it's always expensive. so the next commit :
+
+       1ad3aaf3fcd2 ("sched/core: Implement new approach to scale select_idle_cpu()")
+
+introduces a way to limit how many CPUs we scan.
+
+But it consume some CPUs out of 'nr' that are not allowed
+for the task and thus waste our attempts. The function
+always return nr_cpumask_bits, and we can't find a CPU
+which our task is allowed to run.
+
+Cpumask may be too big, similar to select_idle_core(), use
+per_cpu_ptr 'select_idle_mask' to prevent stack overflow.
+
+Fixes: 1ad3aaf3fcd2 ("sched/core: Implement new approach to scale select_idle_cpu()")
+Signed-off-by: Cheng Jian <cj.chengjian@huawei.com>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
+Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
+Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
+Link: https://lkml.kernel.org/r/20191213024530.28052-1-cj.chengjian@huawei.com
+Signed-off-by: Yang Wei <yang.wei@linux.alibaba.com>
+Tested-by: Yang Wei <yang.wei@linux.alibaba.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/sched/fair.c |    7 ++++---
+ 1 file changed, 4 insertions(+), 3 deletions(-)
+
+--- a/kernel/sched/fair.c
++++ b/kernel/sched/fair.c
+@@ -5779,6 +5779,7 @@ static inline int select_idle_smt(struct
+  */
+ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
+ {
++      struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
+       struct sched_domain *this_sd;
+       u64 avg_cost, avg_idle;
+       u64 time, cost;
+@@ -5809,11 +5810,11 @@ static int select_idle_cpu(struct task_s
+ 
+       time = local_clock();
+ 
+-      for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
++      cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
++
++      for_each_cpu_wrap(cpu, cpus, target) {
+               if (!--nr)
+                       return -1;
+-              if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+-                      continue;
+               if (idle_cpu(cpu))
+                       break;
+       }

diff --git a/queue-4.14/series b/queue-4.14/series
index a5a8b31531db5c924b035e320f833082574fd8a2..844db37e3e825e83b95d46ced5593354a4a006ec 100644 (file)
--- a/queue-4.14/series
+++ b/queue-4.14/series
@@ -43,3 +43,5 @@ bpf-fix-mask-direction-swap-upon-off-reg-sign-change.patch
 bpf-no-need-to-simulate-speculative-domain-for-immediates.patch
 bnxt_en-remove-the-setting-of-dev_port.patch
 kvm-svm-truncate-gpr-value-for-dr-and-cr-accesses-in-64-bit-mode.patch
+sched-fair-optimize-select_idle_cpu.patch
+xen-pciback-redo-vf-placement-in-the-virtual-topology.patch

diff --git a/queue-4.14/xen-pciback-redo-vf-placement-in-the-virtual-topology.patch b/queue-4.14/xen-pciback-redo-vf-placement-in-the-virtual-topology.patch
new file mode 100644 (file)
index 0000000..1b5b3d3
--- /dev/null
+++ b/queue-4.14/xen-pciback-redo-vf-placement-in-the-virtual-topology.patch
@@ -0,0 +1,82 @@
+From foo@baz Tue Jun  8 07:08:15 PM CEST 2021
+From: Jan Beulich <jbeulich@suse.com>
+Date: Tue, 18 May 2021 18:13:42 +0200
+Subject: xen-pciback: redo VF placement in the virtual topology
+
+From: Jan Beulich <jbeulich@suse.com>
+
+The commit referenced below was incomplete: It merely affected what
+would get written to the vdev-<N> xenstore node. The guest would still
+find the function at the original function number as long as
+__xen_pcibk_get_pci_dev() wouldn't be in sync. The same goes for AER wrt
+__xen_pcibk_get_pcifront_dev().
+
+Undo overriding the function to zero and instead make sure that VFs at
+function zero remain alone in their slot. This has the added benefit of
+improving overall capacity, considering that there's only a total of 32
+slots available right now (PCI segment and bus can both only ever be
+zero at present).
+
+This is upstream commit 4ba50e7c423c29639878c00573288869aa627068.
+
+Fixes: 8a5248fe10b1 ("xen PV passthru: assign SR-IOV virtual functions to 
+separate virtual slots")
+Signed-off-by: Jan Beulich <jbeulich@suse.com>
+Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
+Link: https://lore.kernel.org/r/8def783b-404c-3452-196d-3f3fd4d72c9e@suse.com
+Signed-off-by: Juergen Gross <jgross@suse.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/xen/xen-pciback/vpci.c |   14 ++++++++------
+ 1 file changed, 8 insertions(+), 6 deletions(-)
+
+--- a/drivers/xen/xen-pciback/vpci.c
++++ b/drivers/xen/xen-pciback/vpci.c
+@@ -69,7 +69,7 @@ static int __xen_pcibk_add_pci_dev(struc
+                                  struct pci_dev *dev, int devid,
+                                  publish_pci_dev_cb publish_cb)
+ {
+-      int err = 0, slot, func = -1;
++      int err = 0, slot, func = PCI_FUNC(dev->devfn);
+       struct pci_dev_entry *t, *dev_entry;
+       struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+ 
+@@ -94,23 +94,26 @@ static int __xen_pcibk_add_pci_dev(struc
+ 
+       /*
+        * Keep multi-function devices together on the virtual PCI bus, except
+-       * virtual functions.
++       * that we want to keep virtual functions at func 0 on their own. They
++       * aren't multi-function devices and hence their presence at func 0
++       * may cause guests to not scan the other functions.
+        */
+-      if (!dev->is_virtfn) {
++      if (!dev->is_virtfn || func) {
+               for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+                       if (list_empty(&vpci_dev->dev_list[slot]))
+                               continue;
+ 
+                       t = list_entry(list_first(&vpci_dev->dev_list[slot]),
+                                      struct pci_dev_entry, list);
++                      if (t->dev->is_virtfn && !PCI_FUNC(t->dev->devfn))
++                              continue;
+ 
+                       if (match_slot(dev, t->dev)) {
+                               pr_info("vpci: %s: assign to virtual slot %d func %d\n",
+                                       pci_name(dev), slot,
+-                                      PCI_FUNC(dev->devfn));
++                                      func);
+                               list_add_tail(&dev_entry->list,
+                                             &vpci_dev->dev_list[slot]);
+-                              func = PCI_FUNC(dev->devfn);
+                               goto unlock;
+                       }
+               }
+@@ -123,7 +126,6 @@ static int __xen_pcibk_add_pci_dev(struc
+                               pci_name(dev), slot);
+                       list_add_tail(&dev_entry->list,
+                                     &vpci_dev->dev_list[slot]);
+-                      func = dev->is_virtfn ? 0 : PCI_FUNC(dev->devfn);
+                       goto unlock;
+               }
+       }