All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] KVM: PPC: Book3S HV: Add missing code for transaction reclaim on guest exit
@ 2014-04-13 22:56 ` Paul Mackerras
  0 siblings, 0 replies; 11+ messages in thread
From: Paul Mackerras @ 2014-04-13 22:56 UTC (permalink / raw)
  To: Alexander Graf, kvm-ppc, kvm

Testing by Michael Neuling revealed that commit e4e38121507a ("KVM:
PPC: Book3S HV: Add transactional memory support") is missing the code
that saves away the checkpointed state of the guest when switching to
the host.  This adds that code, which was in earlier versions of the
patch but went missing somehow.

Reported-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
Please send this along for inclusion in 3.15.  Without it, on POWER8
it is possible for the guest to cause the host to crash.

 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 104 ++++++++++++++++++++++++++++++++
 1 file changed, 104 insertions(+)

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 4963335..ec5ad6e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1312,6 +1312,110 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mr	r3, r9
 	bl	kvmppc_save_fp
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	b	2f
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	ld	r5, VCPU_MSR(r9)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	.store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	.store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+2:
+#endif
+
 	/* Increment yield count if they have a VPA */
 	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
 	cmpdi	r8, 0
-- 
1.9.rc1


^ permalink raw reply related	[flat|nested] 11+ messages in thread
* [PATCH] KVM: PPC: Book3S HV: Add missing HPTE unlock
@ 2014-10-20  9:25 ` Aneesh Kumar K.V
  0 siblings, 0 replies; 11+ messages in thread
From: Aneesh Kumar K.V @ 2014-10-20  9:25 UTC (permalink / raw)
  To: agraf, benh, paulus; +Cc: linuxppc-dev, kvm, kvm-ppc, Aneesh Kumar K.V

In kvm_test_clear_dirty_npages(), if we find an invalid HPTE we move on to the
next HPTE without unlocking the invalid one.  In fact we should never
find an invalid and unlocked HPTE in the rmap chain, but for robustness
we should unlock it.  This adds the missing unlock.

Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/kvm/book3s_64_mmu_hv.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index d40770248b6a..cebb86bc4a37 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1117,9 +1117,11 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp)
 		}
 
 		/* Now check and modify the HPTE */
-		if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID)))
+		if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID))) {
+			/* unlock and continue */
+			hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
 			continue;
-
+		}
 		/* need to make it temporarily absent so C is stable */
 		hptep[0] |= cpu_to_be64(HPTE_V_ABSENT);
 		kvmppc_invalidate_hpte(kvm, hptep, i);
-- 
1.9.1

^ permalink raw reply related	[flat|nested] 11+ messages in thread
end of thread, other threads:[~2014-11-20 17:23 UTC | newest]

Thread overview: 11+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-04-13 22:56 [PATCH] KVM: PPC: Book3S HV: Add missing code for transaction reclaim on guest exit Paul Mackerras
2014-04-13 22:56 ` Paul Mackerras
2014-04-16 12:39 ` Alexander Graf
2014-04-16 12:39   ` Alexander Graf
2014-11-05  1:21 ` [PATCH] KVM: PPC: Book3S HV: Add missing HPTE unlock Paul Mackerras
2014-11-05  1:21   ` Paul Mackerras
2014-11-20 17:23   ` Alexander Graf
2014-11-20 17:23     ` Alexander Graf
  -- strict thread matches above, loose matches on Subject: below --
2014-10-20  9:25 Aneesh Kumar K.V
2014-10-20  9:37 ` Aneesh Kumar K.V
2014-10-20  9:25 ` Aneesh Kumar K.V

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.