linux_dsm_epyc7002/arch
Nicholas Piggin 75d9fc7fd9 powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C
The OPAL call wrapper gets interrupt disabling wrong. It disables
interrupts just by clearing MSR[EE], which has two problems:

- It doesn't call into the IRQ tracing subsystem, which means tracing
  across OPAL calls does not always notice IRQs have been disabled.

- It doesn't go through the IRQ soft-mask code, which causes a minor
  bug. MSR[EE] can not be restored by saving the MSR then clearing
  MSR[EE], because a racing interrupt while soft-masked could clear
  MSR[EE] between the two steps. This can cause MSR[EE] to be
  incorrectly enabled when the OPAL call returns. Fortunately that
  should only result in another masked interrupt being taken to
  disable MSR[EE] again, but it's a bit sloppy.

The existing code also saves MSR to PACA, which is not re-entrant if
there is a nested OPAL call from different MSR contexts, which can
happen these days with SRESET interrupts on bare metal.

To fix these issues, move the tracing and IRQ handling code to C, and
call into asm just for the low level call when everything is ready to
go. Save the MSR on stack rather than PACA.

Performance cost is kept to a minimum with a few optimisations:

- The endian switch upon return is combined with the MSR restore,
  which avoids an expensive context synchronizing operation for LE
  kernels. This makes up for the additional mtmsrd to enable
  interrupts with local_irq_enable().

- blr is now used to return from the opal_* functions that are called
  as C functions, to avoid link stack corruption. This requires a
  skiboot fix as well to keep the call stack balanced.

A NULL call is more costly after this, (410ns->430ns on POWER9), but
OPAL calls are generally not performance critical at this scale.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-02-26 23:55:09 +11:00
..
alpha Kbuild late updates for v4.21 2019-01-06 16:33:10 -08:00
arc arch: remove redundant UAPI generic-y defines 2019-01-06 10:22:15 +09:00
arm Late reset controller changes for v5.0 2019-01-12 22:06:54 -08:00
arm64 ARM: SoC fixes 2019-01-14 10:34:14 +12:00
c6x arch: restore generic-y += shmparam.h for some architectures 2019-01-06 18:16:11 -08:00
csky csky: fixup compile error with CPU 810. 2019-01-10 04:37:37 -08:00
h8300 arch: restore generic-y += shmparam.h for some architectures 2019-01-06 18:16:11 -08:00
hexagon arch: restore generic-y += shmparam.h for some architectures 2019-01-06 18:16:11 -08:00
ia64 arch: remove redundant UAPI generic-y defines 2019-01-06 10:22:15 +09:00
m68k arch: restore generic-y += shmparam.h for some architectures 2019-01-06 18:16:11 -08:00
microblaze arch: restore generic-y += shmparam.h for some architectures 2019-01-06 18:16:11 -08:00
mips cross-tree: phase out dma_zalloc_coherent() 2019-01-08 07:58:37 -05:00
nds32 arch: remove redundant UAPI generic-y defines 2019-01-06 10:22:15 +09:00
nios2 arch: remove redundant UAPI generic-y defines 2019-01-06 10:22:15 +09:00
openrisc arch/openrisc: Fix issues with access_ok() 2019-01-08 18:22:30 -08:00
parisc arch: remove redundant UAPI generic-y defines 2019-01-06 10:22:15 +09:00
powerpc powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C 2019-02-26 23:55:09 +11:00
riscv Fix a handful of audit-related issue 2019-01-07 08:45:47 -08:00
s390 Kbuild late updates for v4.21 2019-01-06 16:33:10 -08:00
sh Kbuild late updates for v4.21 2019-01-06 16:33:10 -08:00
sparc arch: remove redundant UAPI generic-y defines 2019-01-06 10:22:15 +09:00
um Merge branch 'akpm' (patches from Andrew) 2019-01-05 09:16:18 -08:00
unicore32 arch: restore generic-y += shmparam.h for some architectures 2019-01-06 18:16:11 -08:00
x86 KVM fixes for 5.0-rc2 2019-01-12 10:39:43 -08:00
xtensa arch: remove redundant UAPI generic-y defines 2019-01-06 10:22:15 +09:00
.gitignore
Kconfig jump_label: move 'asm goto' support test to Kconfig 2019-01-06 09:46:51 +09:00