linux-stable/arch/powerpc/include/asm/hmi.h
Paul Mackerras d075745d89 KVM: PPC: Book3S HV: Improve handling of debug-trigger HMIs on POWER9
Hypervisor maintenance interrupts (HMIs) are generated by various
causes, signalled by bits in the hypervisor maintenance exception
register (HMER).  In most cases calling OPAL to handle the interrupt
is the correct thing to do, but the "debug trigger" HMIs signalled by
PPC bit 17 (bit 46) of HMER are used to invoke software workarounds
for hardware bugs, and OPAL does not have any code to handle this
cause.  The debug trigger HMI is used in POWER9 DD2.0 and DD2.1 chips
to work around a hardware bug in executing vector load instructions to
cache inhibited memory.  In POWER9 DD2.2 chips, it is generated when
conditions are detected relating to threads being in TM (transactional
memory) suspended mode when the core SMT configuration needs to be
reconfigured.

The kernel currently has code to detect the vector CI load condition,
but only when the HMI occurs in the host, not when it occurs in a
guest.  If a HMI occurs in the guest, it is always passed to OPAL, and
then we always re-sync the timebase, because the HMI cause might have
been a timebase error, for which OPAL would re-sync the timebase, thus
removing the timebase offset which KVM applied for the guest.  Since
we don't know what OPAL did, we don't know whether to subtract the
timebase offset from the timebase, so instead we re-sync the timebase.

This adds code to determine explicitly what the cause of a debug
trigger HMI will be.  This is based on a new device-tree property
under the CPU nodes called ibm,hmi-special-triggers, if it is
present, or otherwise based on the PVR (processor version register).
The handling of debug trigger HMIs is pulled out into a separate
function which can be called from the KVM guest exit code.  If this
function handles and clears the HMI, and no other HMI causes remain,
then we skip calling OPAL and we proceed to subtract the guest
timebase offset from the timebase.

The overall handling for HMIs that occur in the host (i.e. not in a
KVM guest) is largely unchanged, except that we now don't set the flag
for the vector CI load workaround on DD2.2 processors.

This also removes a BUG_ON in the KVM code.  BUG_ON is generally not
useful in KVM guest entry/exit code since it is difficult to handle
the resulting trap gracefully.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-01-18 15:31:25 +11:00

49 lines
1.5 KiB
C

/*
* Hypervisor Maintenance Interrupt header file.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program.
*
* Copyright 2015 IBM Corporation
* Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
*/
#ifndef __ASM_PPC64_HMI_H__
#define __ASM_PPC64_HMI_H__
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
#define CORE_TB_RESYNC_REQ_BIT 63
#define MAX_SUBCORE_PER_CORE 4
/*
* sibling_subcore_state structure is used to co-ordinate all threads
* during HMI to avoid TB corruption. This structure is allocated once
* per each core and shared by all threads on that core.
*/
struct sibling_subcore_state {
unsigned long flags;
u8 in_guest[MAX_SUBCORE_PER_CORE];
};
extern void wait_for_subcore_guest_exit(void);
extern void wait_for_tb_resync(void);
#else
static inline void wait_for_subcore_guest_exit(void) { }
static inline void wait_for_tb_resync(void) { }
#endif
struct pt_regs;
extern long hmi_handle_debugtrig(struct pt_regs *regs);
#endif /* __ASM_PPC64_HMI_H__ */