powerpc/64s: flush L1D after user accesses

commit 9a32a7e78bd0cd9a9b6332cbdc345ee5ffd0c5de upstream.

IBM Power9 processors can speculatively operate on data in the L1 cache before
it has been completely validated, via a way-prediction mechanism. It is not possible
for an attacker to determine the contents of impermissible memory using this method,
since these systems implement a combination of hardware and software security measures
to prevent scenarios where protected data could be leaked.

However these measures don't address the scenario where an attacker induces
the operating system to speculatively execute instructions using data that the
attacker controls. This can be used for example to speculatively bypass "kernel
user access prevention" techniques, as discovered by Anthony Steinhauser of
Google's Safeside Project. This is not an attack by itself, but there is a possibility
it could be used in conjunction with side-channels or other weaknesses in the
privileged code to construct an attack.

This issue can be mitigated by flushing the L1 cache between privilege boundaries
of concern. This patch flushes the L1 cache after user accesses.

This is part of the fix for CVE-2020-4788.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 26 insertions, 60 deletions

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 7715fd89bb94..7f8e1bdbe3e2 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1630,14 +1630,9 @@ stf_barrier_fallback:
 	.endr
 	blr
 
-	.globl rfi_flush_fallback
-rfi_flush_fallback:
-	SET_SCRATCH0(r13);
-	GET_PACA(r13);
-	std	r9,PACA_EXRFI+EX_R9(r13)
-	std	r10,PACA_EXRFI+EX_R10(r13)
-	std	r11,PACA_EXRFI+EX_R11(r13)
-	mfctr	r9
+
+/* Clobbers r10, r11, ctr */
+.macro L1D_DISPLACEMENT_FLUSH
 	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
 	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
 	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
@@ -1663,7 +1658,18 @@ rfi_flush_fallback:
 	ld	r11,(0x80 + 8)*7(r10)
 	addi	r10,r10,0x80*8
 	bdnz	1b
+.endm
+
 
+	.globl rfi_flush_fallback
+rfi_flush_fallback:
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	mfctr	r9
+	L1D_DISPLACEMENT_FLUSH
 	mtctr	r9
 	ld	r9,PACA_EXRFI+EX_R9(r13)
 	ld	r10,PACA_EXRFI+EX_R10(r13)
@@ -1679,32 +1685,7 @@ hrfi_flush_fallback:
 	std	r10,PACA_EXRFI+EX_R10(r13)
 	std	r11,PACA_EXRFI+EX_R11(r13)
 	mfctr	r9
-	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
-	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
-	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
-	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
-	/* order ld/st prior to dcbt stop all streams with flushing */
-	sync
-
-	/*
-	 * The load adresses are at staggered offsets within cachelines,
-	 * which suits some pipelines better (on others it should not
-	 * hurt).
-	 */
-1:
-	ld	r11,(0x80 + 8)*0(r10)
-	ld	r11,(0x80 + 8)*1(r10)
-	ld	r11,(0x80 + 8)*2(r10)
-	ld	r11,(0x80 + 8)*3(r10)
-	ld	r11,(0x80 + 8)*4(r10)
-	ld	r11,(0x80 + 8)*5(r10)
-	ld	r11,(0x80 + 8)*6(r10)
-	ld	r11,(0x80 + 8)*7(r10)
-	addi	r10,r10,0x80*8
-	bdnz	1b
-
+	L1D_DISPLACEMENT_FLUSH
 	mtctr	r9
 	ld	r9,PACA_EXRFI+EX_R9(r13)
 	ld	r10,PACA_EXRFI+EX_R10(r13)
@@ -1718,38 +1699,14 @@ entry_flush_fallback:
 	std	r10,PACA_EXRFI+EX_R10(r13)
 	std	r11,PACA_EXRFI+EX_R11(r13)
 	mfctr	r9
-	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
-	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
-	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
-	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
-	/* order ld/st prior to dcbt stop all streams with flushing */
-	sync
-
-	/*
-	 * The load addresses are at staggered offsets within cachelines,
-	 * which suits some pipelines better (on others it should not
-	 * hurt).
-	 */
-1:
-	ld	r11,(0x80 + 8)*0(r10)
-	ld	r11,(0x80 + 8)*1(r10)
-	ld	r11,(0x80 + 8)*2(r10)
-	ld	r11,(0x80 + 8)*3(r10)
-	ld	r11,(0x80 + 8)*4(r10)
-	ld	r11,(0x80 + 8)*5(r10)
-	ld	r11,(0x80 + 8)*6(r10)
-	ld	r11,(0x80 + 8)*7(r10)
-	addi	r10,r10,0x80*8
-	bdnz	1b
-
+	L1D_DISPLACEMENT_FLUSH
 	mtctr	r9
 	ld	r9,PACA_EXRFI+EX_R9(r13)
 	ld	r10,PACA_EXRFI+EX_R10(r13)
 	ld	r11,PACA_EXRFI+EX_R11(r13)
 	blr
 
+
 /*
  * Hash table stuff
  */
@@ -1909,3 +1866,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	kernel_bad_stack
 	b	1b
+
+_KPROBE(do_uaccess_flush)
+	UACCESS_FLUSH_FIXUP_SECTION
+	nop
+	nop
+	nop
+	blr
+	L1D_DISPLACEMENT_FLUSH
+	blr