CVE-2022-50118

In the Linux kernel, the following vulnerability has been resolved:

powerpc/perf: Optimize clearing the pending PMI and remove WARNON for PMI check in powerpmu_disable

commit 2c9ac51b850d ("powerpc/perf: Fix PMU callbacks to clear pending PMI before resetting an overflown PMC") added a new function "pmiirqpending" in hwirq.h. This function is to check if there is a PMI marked as pending in Paca (PACAIRQPMI).This is used in powerpmudisable in a WARNON. The intention here is to provide a warning if there is PMI pending, but no counter is found overflown.

During some of the perf runs, below warning is hit:

WARNING: CPU: 36 PID: 0 at arch/powerpc/perf/core-book3s.c:1332 powerpmudisable+0x25c/0x2c0 Modules linked in:

NIP [c000000000141c3c] powerpmudisable+0x25c/0x2c0 LR [c000000000141c8c] powerpmudisable+0x2ac/0x2c0 Call Trace: [c000000baffcfb90] [c000000000141c8c] powerpmudisable+0x2ac/0x2c0 (unreliable) [c000000baffcfc10] [c0000000003e2f8c] perfpmudisable+0x4c/0x60 [c000000baffcfc30] [c0000000003e3344] groupschedout.part.124+0x44/0x100 [c000000baffcfc80] [c0000000003e353c] _perfeventdisable+0x13c/0x240 [c000000baffcfcd0] [c0000000003dd334] eventfunction+0xc4/0x140 [c000000baffcfd20] [c0000000003d855c] remotefunction+0x7c/0xa0 [c000000baffcfd50] [c00000000026c394] flushsmpcallfunctionqueue+0xd4/0x300 [c000000baffcfde0] [c000000000065b24] smpipidemuxrelaxed+0xa4/0x100 [c000000baffcfe20] [c0000000000cb2b0] xivemuxedipiaction+0x20/0x40 [c000000baffcfe40] [c000000000207c3c] _handleirqeventpercpu+0x8c/0x250 [c000000baffcfee0] [c000000000207e2c] handleirqeventpercpu+0x2c/0xa0 [c000000baffcff10] [c000000000210a04] handlepercpuirq+0x84/0xc0 [c000000baffcff40] [c000000000205f14] generichandleirq+0x54/0x80 [c000000baffcff60] [c000000000015740] _doirq+0x90/0x1d0 [c000000baffcff90] [c000000000016990] _doIRQ+0xc0/0x140 [c0000009732f3940] [c000000bafceaca8] 0xc000000bafceaca8 [c0000009732f39d0] [c000000000016b78] doIRQ+0x168/0x1c0 [c0000009732f3a00] [c0000000000090c8] hardwareinterruptcommonvirt+0x218/0x220

This means that there is no PMC overflown among the active events in the PMU, but there is a PMU pending in Paca. The function "anypmcoverflown" checks the PMCs on active events in cpuhw->n_events. Code snippet:

<<>> if (anypmcoverflown(cpuhw)) clearpmiirqpending(); else WARNON(pmiirqpending()); <<>>

Here the PMC overflown is not from active event. Example: When we do perf record, default cycles and instructions will be running on PMC6 and PMC5 respectively. It could happen that overflowed event is currently not active and pending PMI is for the inactive event. Debug logs from trace_printk:

<<>> anypmcoverflown: idx is 5: pmc value is 0xd9a powerpmudisable: PMC1: 0x0, PMC2: 0x0, PMC3: 0x0, PMC4: 0x0, PMC5: 0xd9a, PMC6: 0x80002011 <<>>

Here active PMC (from idx) is PMC5 , but overflown PMC is PMC6(0x80002011). When we handle PMI interrupt for such cases, if the PMC overflown is from inactive event, it will be ignored. Reference commit: commit bc09c219b2e6 ("powerpc/perf: Fix finding overflowed PMC in interrupt")

Patch addresses two changes: 1) Fix 1 : Removal of warning ( WARNON(pmiirqpending()); ) We were printing warning if no PMC is found overflown among active PMU events, but PMI pending in PACA. But this could happen in cases where PMC overflown is not in active PMC. An inactive event could have caused the overflow. Hence the warning is not needed. To know pending PMI is from an inactive event, we need to loop through all PMC's which will cause more SPR reads via mfspr and increase in context switch. Also in existing function: perfevent_interrupt, already we ignore PMI's overflown when it is from an inactive PMC.

2) Fix 2: optimization in clearing pending PMI. Currently we check for any active PMC overflown before clearing PMI pending in Paca. This is causing additional SP ---truncated---