xen: credit1: fix tickling when it happens from a remote pCPU
PATCH v2 1/1 xen: credit1: fix tickling when it happens from a remote pCPU
especially if that is also from a different cpupool than the processor of the vCPU that triggered the tickling.
In fact, it is possible that we get as far as calling vcpu_unblock()--> vcpu_wake()-->csched_vcpu_wake()-->__runq_tickle() for the vCPU 'vc', but all while running on a pCPU that is different from 'vc->processor'.
For instance, this can happen when an HVM domain runs in a cpupool, with a different scheduler than the default one, and issues IOREQs to Dom0, running in Pool-0 with the default scheduler. In fact, right in this case, the following crash can be observed:
(XEN) ----[ Xen-4.7-unstable x86_64 debug=y Tainted: C ]----
(XEN) CPU: 7
(XEN) RIP: e008:[<ffff82d0801230de>] __runq_tickle+0x18f/0x430
(XEN) RFLAGS: 0000000000010086 CONTEXT: hypervisor (d1v0)
(XEN) rax: 0000000000000001 rbx: ffff8303184fee00 rcx: 0000000000000000
(XEN) ... ... ...
(XEN) Xen stack trace from rsp=ffff83031fa57a08:
(XEN) ffff82d0801fe664 ffff82d08033c820 0000000100000002 0000000a00000001
(XEN) 0000000000006831 0000000000000000 0000000000000000 0000000000000000
(XEN) ... ... ...
(XEN) Xen call trace:
(XEN) [<ffff82d0801230de>] __runq_tickle+0x18f/0x430 (XEN) [<ffff82d08012348a>] csched_vcpu_wake+0x10b/0x110 (XEN) [<ffff82d08012b421>] vcpu_wake+0x20a/0x3ce (XEN) [<ffff82d08012b91c>] vcpu_unblock+0x4b/0x4e (XEN) [<ffff82d080167bd0>] vcpu_kick+0x17/0x61 (XEN) [<ffff82d080167c46>] vcpu_mark_events_pending+0x2c/0x2f (XEN) [<ffff82d08010ac35>] evtchn_fifo_set_pending+0x381/0x3f6 (XEN) [<ffff82d08010a0f6>] notify_via_xen_event_channel+0xc9/0xd6 (XEN) [<ffff82d0801c29ed>] hvm_send_ioreq+0x3e9/0x441 (XEN) [<ffff82d0801bba7d>] hvmemul_do_io+0x23f/0x2d2 (XEN) [<ffff82d0801bbb43>] hvmemul_do_io_buffer+0x33/0x64 (XEN) [<ffff82d0801bc92b>] hvmemul_do_pio_buffer+0x35/0x37 (XEN) [<ffff82d0801cc49f>] handle_pio+0x58/0x14c (XEN) [<ffff82d0801eabcb>] vmx_vmexit_handler+0x16b3/0x1bea (XEN) [<ffff82d0801efd21>] vmx_asm_vmexit_handler+0x41/0xc0
In this case, pCPU 7 is not in Pool-0, while the (Dom0's) vCPU being woken is. pCPU's 7 pool has a different scheduler than credit, but it is, however, right from pCPU 7 that we are waking the Dom0's vCPUs. Therefore, the current code tries to access csched_balance_mask for pCPU 7, but that is not defined, and hence the Oops.
(Note that, in case the two pools run the same scheduler we see no Oops, but things are still conceptually wrong.)
Cure things by making the csched_balance_mask macro accept a parameter for fetching a specific pCPU's mask (instead than always using smp_processor_id()).
---
Cc: George Dunlap <[email protected]>
Cc: Jan Beulich <[email protected]>
---
Changes from v1:
* get rid of the old macro and always use the new one, as suggested during review (Juergen)
--- xen/common/sched_credit.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
xen/common/sched_credit.c +10 -8
@@ -171,10 +171,10 @@ struct csched_pcpu {* Convenience macro for accessing the per-PCPU cpumask we need for * implementing the two steps (soft and hard affinity) balancing logic. * It is stored in csched_pcpu so that serialization is not an issue, -* as there is a csched_pcpu for each PCPU and we always hold the -* runqueue spin-lock when using this. +* as there is a csched_pcpu for each PCPU, and we always hold the +* runqueue lock for the proper PCPU when using this. */ -#define csched_balance_mask (CSCHED_PCPU(smp_processor_id())->balance_mask) +#define csched_balance_mask (c) (CSCHED_PCPU(c)->balance_mask)/* * Virtual CPU
@@ -412,9 +412,10 @@ __runq_tickle(unsigned int cpu, struct csched_vcpu *new)/* Are there idlers suitable for new (for this balance step)? */ csched_balance_cpumask (new->vcpu, balance_step, - csched_balance_mask); -cpumask_and (csched_balance_mask, csched_balance_mask, &idle_mask); - new_idlers_empty =cpumask_empty (csched_balance_mask); +csched_balance_mask (cpu)); +cpumask_and (csched_balance_mask (cpu), +csched_balance_mask (cpu), &idle_mask); + new_idlers_empty =cpumask_empty (csched_balance_mask (cpu));/* * Let's not be too harsh! If there aren't idlers suitable
@@ -1491,8 +1492,9 @@ csched_runq_steal(int peer_cpu, int cpu, int pri, int balance_step) && !__vcpu_has_soft_affinity(vc, vc->cpu_hard_affinity) ) continue; -csched_balance_cpumask (vc, balance_step, csched_balance_mask); -if (__csched_vcpu_is_migrateable (vc, cpu, csched_balance_mask) ) +csched_balance_cpumask (vc, balance_step,csched_balance_mask (cpu)); +if (__csched_vcpu_is_migrateable (vc, cpu, +csched_balance_mask (cpu)) ) {/* We got a candidate. Grab it! */ TRACE_3D(TRC_CSCHED_STOLEN_VCPU, peer_cpu,
Hey Wei,
Quoted 19 lines · Dario Faggioli
For instance, this can happen when an HVM domain runs in a cpupool, with a different scheduler than the default one, and issues IOREQs to Dom0, running in Pool-0 with the default scheduler. In fact, right in this case, the following crash can be observed:
(XEN) ----[ Xen-4.7-unstable
x86_64debug=y Tainted: C ]----
(XEN) CPU: 7
(XEN) RIP: e008:[<ffff82d0801230de>]__runq_tickle+0x18f/0x430
(XEN) RFLAGS: 0000000000010086 CONTEXT: hypervisor (d1v0)
(XEN) rax: 0000000000000001 rbx:ffff8303184fee00rcx:
0000000000000000
(XEN) ... ... ...
(XEN) Xen stack trace from rsp=ffff83031fa57a08:
(XEN)ffff82d0801fe664ffff82d08033c82000000001000000020000000a00000001
(XEN) 0000000000006831 0000000000000000 0000000000000000
0000000000000000
(XEN) ... ... ...
(XEN) Xen call trace:
Quoted 16 lines
(XEN) [<ffff82d0801230de>] __runq_tickle+0x18f/0x430 (XEN) [<ffff82d08012348a>] csched_vcpu_wake+0x10b/0x110 (XEN) [<ffff82d08012b421>] vcpu_wake+0x20a/0x3ce (XEN) [<ffff82d08012b91c>] vcpu_unblock+0x4b/0x4e (XEN) [<ffff82d080167bd0>] vcpu_kick+0x17/0x61 (XEN) [<ffff82d080167c46>] vcpu_mark_events_pending+0x2c/0x2f (XEN) [<ffff82d08010ac35>] evtchn_fifo_set_pending+0x381/0x3f6 (XEN) [<ffff82d08010a0f6>] notify_via_xen_event_channel+0xc9/0xd6 (XEN) [<ffff82d0801c29ed>] hvm_send_ioreq+0x3e9/0x441 (XEN) [<ffff82d0801bba7d>] hvmemul_do_io+0x23f/0x2d2 (XEN) [<ffff82d0801bbb43>] hvmemul_do_io_buffer+0x33/0x64 (XEN) [<ffff82d0801bc92b>] hvmemul_do_pio_buffer+0x35/0x37 (XEN) [<ffff82d0801cc49f>] handle_pio+0x58/0x14c (XEN) [<ffff82d0801eabcb>] vmx_vmexit_handler+0x16b3/0x1bea (XEN) [<ffff82d0801efd21>] vmx_asm_vmexit_handler+0x41/0xc0
This patch is a bugfix, so I think it should be included in 4.6.
I'm able to trigger the above Oops pretty reliably by running an HVM guest in a cpupool that has a scheduler different than Credit (by, e.g., starting some load in the guest itself, or even just simply doing `xl shutdown' on it).
It may not be the most common of the configurations, but I think it's worth.
Thanks and Regards,
Dario
Signature · 4 lines
<<This happens because I choose it to happen!>> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)
_______________________________________________
Xen-devel mailing list
[email protected]
http://lists.xen.org/xen-devel
Quoted 41 lines · Dario Faggioli
Hey Wei,
Quoted 19 lines · Dario Faggioli
For instance, this can happen when an HVM domain runs in a cpupool, with a different scheduler than the default one, and issues IOREQs to Dom0, running in Pool-0 with the default scheduler. In fact, right in this case, the following crash can be observed:
(XEN) ----[ Xen-4.7-unstable
x86_64debug=y Tainted: C ]----
(XEN) CPU: 7
(XEN) RIP: e008:[<ffff82d0801230de>]__runq_tickle+0x18f/0x430
(XEN) RFLAGS: 0000000000010086 CONTEXT: hypervisor (d1v0)
(XEN) rax: 0000000000000001 rbx:ffff8303184fee00rcx:
0000000000000000
(XEN) ... ... ...
(XEN) Xen stack trace from rsp=ffff83031fa57a08:
(XEN)ffff82d0801fe664ffff82d08033c82000000001000000020000000a00000001
(XEN) 0000000000006831 0000000000000000 0000000000000000
0000000000000000
(XEN) ... ... ...
(XEN) Xen call trace:Quoted 16 lines
(XEN) [<ffff82d0801230de>] __runq_tickle+0x18f/0x430 (XEN) [<ffff82d08012348a>] csched_vcpu_wake+0x10b/0x110 (XEN) [<ffff82d08012b421>] vcpu_wake+0x20a/0x3ce (XEN) [<ffff82d08012b91c>] vcpu_unblock+0x4b/0x4e (XEN) [<ffff82d080167bd0>] vcpu_kick+0x17/0x61 (XEN) [<ffff82d080167c46>] vcpu_mark_events_pending+0x2c/0x2f (XEN) [<ffff82d08010ac35>] evtchn_fifo_set_pending+0x381/0x3f6 (XEN) [<ffff82d08010a0f6>] notify_via_xen_event_channel+0xc9/0xd6 (XEN) [<ffff82d0801c29ed>] hvm_send_ioreq+0x3e9/0x441 (XEN) [<ffff82d0801bba7d>] hvmemul_do_io+0x23f/0x2d2 (XEN) [<ffff82d0801bbb43>] hvmemul_do_io_buffer+0x33/0x64 (XEN) [<ffff82d0801bc92b>] hvmemul_do_pio_buffer+0x35/0x37 (XEN) [<ffff82d0801cc49f>] handle_pio+0x58/0x14c (XEN) [<ffff82d0801eabcb>] vmx_vmexit_handler+0x16b3/0x1bea (XEN) [<ffff82d0801efd21>] vmx_asm_vmexit_handler+0x41/0xc0This patch is a bugfix, so I think it should be included in 4.6.
Quoted 8 lines
I'm able to trigger the above Oops pretty reliably by running an HVM guest in a cpupool that has a scheduler different than Credit (by, e.g., starting some load in the guest itself, or even just simply doing `xl shutdown' on it).
It may not be the most common of the configurations, but I think it's worth.
Quoted 8 lines
Thanks and Regards,
DarioSignature · 4 lines
<<This happens because I choose it to happen!>> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)
Quoted 48 lines · Dario Faggioli
especially if that is also from a different cpupool than the processor of the vCPU that triggered the tickling.
In fact, it is possible that we get as far as calling vcpu_unblock()--> vcpu_wake()-->csched_vcpu_wake()-->__runq_tickle() for the vCPU 'vc', but all while running on a pCPU that is different from '
vc->processor'.For instance, this can happen when an HVM domain runs in a cpupool, with a different scheduler than the default one, and issues IOREQs to Dom0, running in Pool-0 with the default scheduler. In fact, right in this case, the following crash can be observed:
(XEN) ----[ Xen-4.7-unstable
x86_64debug=y Tainted: C ]----
(XEN) CPU: 7
(XEN) RIP: e008:[<ffff82d0801230de>]__runq_tickle+0x18f/0x430
(XEN) RFLAGS: 0000000000010086 CONTEXT: hypervisor (d1v0)
(XEN) rax: 0000000000000001 rbx:ffff8303184fee00rcx: 0000000000000000
(XEN) ... ... ...
(XEN) Xen stack trace from rsp=ffff83031fa57a08:
(XEN)ffff82d0801fe664ffff82d08033c82000000001000000020000000a00000001
(XEN) 0000000000006831 0000000000000000 0000000000000000 0000000000000000
(XEN) ... ... ...
(XEN) Xen call trace:(XEN) [<ffff82d0801230de>] __runq_tickle+0x18f/0x430 (XEN) [<ffff82d08012348a>] csched_vcpu_wake+0x10b/0x110 (XEN) [<ffff82d08012b421>] vcpu_wake+0x20a/0x3ce (XEN) [<ffff82d08012b91c>] vcpu_unblock+0x4b/0x4e (XEN) [<ffff82d080167bd0>] vcpu_kick+0x17/0x61 (XEN) [<ffff82d080167c46>] vcpu_mark_events_pending+0x2c/0x2f (XEN) [<ffff82d08010ac35>] evtchn_fifo_set_pending+0x381/0x3f6 (XEN) [<ffff82d08010a0f6>] notify_via_xen_event_channel+0xc9/0xd6 (XEN) [<ffff82d0801c29ed>] hvm_send_ioreq+0x3e9/0x441 (XEN) [<ffff82d0801bba7d>] hvmemul_do_io+0x23f/0x2d2 (XEN) [<ffff82d0801bbb43>] hvmemul_do_io_buffer+0x33/0x64 (XEN) [<ffff82d0801bc92b>] hvmemul_do_pio_buffer+0x35/0x37 (XEN) [<ffff82d0801cc49f>] handle_pio+0x58/0x14c (XEN) [<ffff82d0801eabcb>] vmx_vmexit_handler+0x16b3/0x1bea (XEN) [<ffff82d0801efd21>] vmx_asm_vmexit_handler+0x41/0xc0In this case, pCPU 7 is not in Pool-0, while the (Dom0's) vCPU being woken is. pCPU's 7 pool has a different scheduler than credit, but it is, however, right from pCPU 7 that we are waking the Dom0's vCPUs. Therefore, the current code tries to access
csched_balance_maskfor pCPU 7, but that is not defined, and hence the Oops.(Note that, in case the two pools run the same scheduler we see no Oops, but things are still conceptually wrong.)
Quoted 6 lines
Cure things by making the
csched_balance_maskmacro accept a parameter for fetching a specific pCPU's mask (instead than always usingsmp_processor_id()).Signed-off-by Dario Faggioli <[email protected]>Reviewed-by Juergen Gross <[email protected]>
Looks good!