diff options
Diffstat (limited to '0015-xen-sched-set-all-sched_resource-data-inside-locked-.patch')
| -rw-r--r-- | 0015-xen-sched-set-all-sched_resource-data-inside-locked-.patch | 84 |
1 files changed, 84 insertions, 0 deletions
diff --git a/0015-xen-sched-set-all-sched_resource-data-inside-locked-.patch b/0015-xen-sched-set-all-sched_resource-data-inside-locked-.patch new file mode 100644 index 0000000..a8090d4 --- /dev/null +++ b/0015-xen-sched-set-all-sched_resource-data-inside-locked-.patch @@ -0,0 +1,84 @@ +From 3999b675cad5b717274d6493899b0eea8896f4d7 Mon Sep 17 00:00:00 2001 +From: Juergen Gross <jgross@suse.com> +Date: Tue, 21 May 2024 10:24:26 +0200 +Subject: [PATCH 15/56] xen/sched: set all sched_resource data inside locked + region for new cpu + +When adding a cpu to a scheduler, set all data items of struct +sched_resource inside the locked region, as otherwise a race might +happen (e.g. when trying to access the cpupool of the cpu): + + (XEN) ----[ Xen-4.19.0-1-d x86_64 debug=y Tainted: H ]---- + (XEN) CPU: 45 + (XEN) RIP: e008:[<ffff82d040244cbf>] common/sched/credit.c#csched_load_balance+0x41/0x877 + (XEN) RFLAGS: 0000000000010092 CONTEXT: hypervisor + (XEN) rax: ffff82d040981618 rbx: ffff82d040981618 rcx: 0000000000000000 + (XEN) rdx: 0000003ff68cd000 rsi: 000000000000002d rdi: ffff83103723d450 + (XEN) rbp: ffff83207caa7d48 rsp: ffff83207caa7b98 r8: 0000000000000000 + (XEN) r9: ffff831037253cf0 r10: ffff83103767c3f0 r11: 0000000000000009 + (XEN) r12: ffff831037237990 r13: ffff831037237990 r14: ffff831037253720 + (XEN) r15: 0000000000000000 cr0: 000000008005003b cr4: 0000000000f526e0 + (XEN) cr3: 000000005bc2f000 cr2: 0000000000000010 + (XEN) fsb: 0000000000000000 gsb: 0000000000000000 gss: 0000000000000000 + (XEN) ds: 0000 es: 0000 fs: 0000 gs: 0000 ss: 0000 cs: e008 + (XEN) Xen code around <ffff82d040244cbf> (common/sched/credit.c#csched_load_balance+0x41/0x877): + (XEN) 48 8b 0c 10 48 8b 49 08 <48> 8b 79 10 48 89 bd b8 fe ff ff 49 8b 4e 28 48 + <snip> + (XEN) Xen call trace: + (XEN) [<ffff82d040244cbf>] R common/sched/credit.c#csched_load_balance+0x41/0x877 + (XEN) [<ffff82d040245a18>] F common/sched/credit.c#csched_schedule+0x36a/0x69f + (XEN) [<ffff82d040252644>] F common/sched/core.c#do_schedule+0xe8/0x433 + (XEN) [<ffff82d0402572dd>] F common/sched/core.c#schedule+0x2e5/0x2f9 + (XEN) [<ffff82d040232f35>] F common/softirq.c#__do_softirq+0x94/0xbe + (XEN) [<ffff82d040232fc8>] F do_softirq+0x13/0x15 + (XEN) [<ffff82d0403075ef>] F arch/x86/domain.c#idle_loop+0x92/0xe6 + (XEN) + (XEN) Pagetable walk from 0000000000000010: + (XEN) L4[0x000] = 000000103ff61063 ffffffffffffffff + (XEN) L3[0x000] = 000000103ff60063 ffffffffffffffff + (XEN) L2[0x000] = 0000001033dff063 ffffffffffffffff + (XEN) L1[0x000] = 0000000000000000 ffffffffffffffff + (XEN) + (XEN) **************************************** + (XEN) Panic on CPU 45: + (XEN) FATAL PAGE FAULT + (XEN) [error_code=0000] + (XEN) Faulting linear address: 0000000000000010 + (XEN) **************************************** + +Reported-by: Andrew Cooper <andrew.cooper3@citrix.com> +Fixes: a8c6c623192e ("sched: clarify use cases of schedule_cpu_switch()") +Signed-off-by: Juergen Gross <jgross@suse.com> +Acked-by: Andrew Cooper <andrew.cooper3@citrix.com> +Tested-by: Andrew Cooper <andrew.cooper3@citrix.com> +master commit: d104a07524ffc92ae7a70dfe192c291de2a563cc +master date: 2024-05-15 19:59:52 +0100 +--- + xen/common/sched/core.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/xen/common/sched/core.c b/xen/common/sched/core.c +index 34ad39b9ad..3c2403ebcf 100644 +--- a/xen/common/sched/core.c ++++ b/xen/common/sched/core.c +@@ -3179,6 +3179,8 @@ int schedule_cpu_add(unsigned int cpu, struct cpupool *c) + + sr->scheduler = new_ops; + sr->sched_priv = ppriv; ++ sr->granularity = cpupool_get_granularity(c); ++ sr->cpupool = c; + + /* + * Reroute the lock to the per pCPU lock as /last/ thing. In fact, +@@ -3191,8 +3193,6 @@ int schedule_cpu_add(unsigned int cpu, struct cpupool *c) + /* _Not_ pcpu_schedule_unlock(): schedule_lock has changed! */ + spin_unlock_irqrestore(old_lock, flags); + +- sr->granularity = cpupool_get_granularity(c); +- sr->cpupool = c; + /* The cpu is added to a pool, trigger it to go pick up some work */ + cpu_raise_softirq(cpu, SCHEDULE_SOFTIRQ); + +-- +2.45.2 + |