Thread (11 messages) 11 messages, 4 authors, 2022-11-28

Re: [PATCH v2 1/4] powerpc/64: Add INTERRUPT_SANITIZE_REGISTERS Kconfig

From: Christophe Leroy <hidden>
Date: 2022-11-07 14:30:16


Le 07/11/2022 à 04:31, Rohan McLure a écrit :
Add Kconfig option for enabling clearing of registers on arrival in an
interrupt handler. This reduces the speculation influence of registers
on kernel internals. The option will be consumed by 64-bit systems that
feature speculation and wish to implement this mitigation.

This patch only introduces the Kconfig option, no actual mitigations.
If that has to do with speculation, do we need a new Kconfig option ? 
Can't we use CONFIG_PPC_BARRIER_NOSPEC for that ?
quoted hunk ↗ jump to hunk
The primary overhead of this mitigation lies in an increased number of
registers that must be saved and restored by interrupt handlers on
Book3S systems. Enable by default on Book3E systems, which prior to
this patch eagerly save and restore register state, meaning that the
mitigation when implemented will have minimal overhead.

Acked-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Rohan McLure <redacted>
---
Resubmitting patches as their own series after v6 partially merged:
Link: https://lore.kernel.org/all/166488988686.779920.13794870102696416283.b4-ty@ellerman.id.au/t/ (local)
---
  arch/powerpc/Kconfig | 9 +++++++++
  1 file changed, 9 insertions(+)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2ca5418457ed..9d3d20c6f365 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -529,6 +529,15 @@ config HOTPLUG_CPU
  
  	  Say N if you are unsure.
  
+config INTERRUPT_SANITIZE_REGISTERS
+	bool "Clear gprs on interrupt arrival"
+	depends on PPC64 && ARCH_HAS_SYSCALL_WRAPPER
+	default PPC_BOOK3E_64
+	help
+	  Reduce the influence of user register state on interrupt handlers and
+	  syscalls through clearing user state from registers before handling
+	  the exception.
+
  config PPC_QUEUED_SPINLOCKS
  	bool "Queued spinlocks" if EXPERT
  	depends on SMP
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help