On Thu, Sep 28, 2017 at 03:09:49PM +0100, Will Deacon wrote:

When booting at EL2, ensure that we permit the EL1 host to sample
physical addresses and physical counter values using SPE.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
arch/arm64/kernel/head.S | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 7434ec0c7a27..c370e270ae55 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -479,14 +479,21 @@ set_hcr:

/* Statistical profiling */
ubfx x0, x1, #32, #4 // Check ID_AA64DFR0_EL1 PMSVer - cbz x0, 6f // Skip if SPE not present
- cbnz x2, 5f // VHE?
+ cbz x0, 7f // Skip if SPE not present
+ cbnz x2, 6f // VHE?
+ mrs_s x4, SYS_PMBIDR_EL1 // If SPE available at EL2,
+ and x4, x4, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
+ cbnz x4, 5f // then permit sampling of physical
+ mov x4, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
+ 1 << SYS_PMSCR_EL2_PA_SHIFT)
+ msr_s SYS_PMSCR_EL2, x4 // addresses and physical counter

As a general note, I find these right-hand-side comments difficult to
read, especially here with multiple line gaps mid-sentence.

If I'm alone in that view, there's no reason to change them, but
otherwise it might make sense to replace the more complex comments with
/* */ comment blocks on their own lines...

The logic looks fine to me, so FWIW:

Acked-by: Mark Rutland <mark.rutland@arm.com>

Mark.

+5:
mov x1, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
orr x3, x3, x1 // If we don't have VHE, then
- b 6f // use EL1&0 translation.
-5: // For VHE, use EL2 translation + b 7f // use EL1&0 translation.
+6: // For VHE, use EL2 translation
orr x3, x3, #MDCR_EL2_TPMS // and disable access from EL1 -6:
+7:
msr mdcr_el2, x3 // Configure debug traps

/* Stage-2 translation */
--
2.1.4

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)