LinuxPPC-Dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v4 44/46] KVM: PPC: Book3S HV P9: implement hash guest support
From: Nicholas Piggin @ 2021-03-23  1:03 UTC (permalink / raw)
  To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210323010305.1045293-1-npiggin@gmail.com>

Guest entry/exit has to restore and save/clear the SLB, plus several
other bits to accommodate hash guests in the P9 path.

Radix host, hash guest support is removed from the P7/8 path.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kvm/book3s_hv.c            |  20 ++-
 arch/powerpc/kvm/book3s_hv_interrupt.c  | 160 ++++++++++++++++--------
 arch/powerpc/kvm/book3s_hv_rm_mmu.c     |   4 +
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |  14 +--
 4 files changed, 131 insertions(+), 67 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5b3b6842d6b9..c151a60c0daa 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3828,7 +3828,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 		}
 		kvmppc_xive_pull_vcpu(vcpu);
 
-		vcpu->arch.slb_max = 0;
+		if (kvm_is_radix(vcpu->kvm))
+			vcpu->arch.slb_max = 0;
 	}
 
 	dec = mfspr(SPRN_DEC);
@@ -4061,7 +4062,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 /*
  * This never fails for a radix guest, as none of the operations it does
  * for a radix guest can fail or have a way to report failure.
- * kvmhv_run_single_vcpu() relies on this fact.
  */
 static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu)
 {
@@ -4240,8 +4240,15 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	vc->runner = vcpu;
 
 	/* See if the MMU is ready to go */
-	if (!kvm->arch.mmu_ready)
-		kvmhv_setup_mmu(vcpu);
+	if (!kvm->arch.mmu_ready) {
+		r = kvmhv_setup_mmu(vcpu);
+		if (r) {
+			run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+			run->fail_entry.hardware_entry_failure_reason = 0;
+			vcpu->arch.ret = r;
+			return r;
+		}
+	}
 
 	if (need_resched())
 		cond_resched();
@@ -4254,7 +4261,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	preempt_disable();
 	pcpu = smp_processor_id();
 	vc->pcpu = pcpu;
-	kvmppc_prepare_radix_vcpu(vcpu, pcpu);
+	if (kvm_is_radix(kvm))
+		kvmppc_prepare_radix_vcpu(vcpu, pcpu);
 
 	local_irq_disable();
 	hard_irq_disable();
@@ -4454,7 +4462,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
 	do {
-		if (kvm_is_radix(kvm))
+		if (radix_enabled())
 			r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
 						  vcpu->arch.vcore->lpcr);
 		else
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index cd84d2c37632..03fbfef708a8 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -55,6 +55,50 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator
 #define accumulate_time(vcpu, next) do {} while (0)
 #endif
 
+static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev)
+{
+	asm volatile("slbmfev  %0,%1" : "=r" (*slbev) : "r" (idx));
+	asm volatile("slbmfee  %0,%1" : "=r" (*slbee) : "r" (idx));
+}
+
+static inline void __mtslb(u64 slbee, u64 slbev)
+{
+	asm volatile("slbmte %0,%1" :: "r" (slbev), "r" (slbee));
+}
+
+static inline void mtslb(unsigned int idx, u64 slbee, u64 slbev)
+{
+	BUG_ON((slbee & 0xfff) != idx);
+
+	__mtslb(slbee, slbev);
+}
+
+static inline void slb_invalidate(unsigned int ih)
+{
+	asm volatile("slbia %0" :: "i"(ih));
+}
+
+/*
+ * Malicious or buggy radix guests may have inserted SLB entries
+ * (only 0..3 because radix always runs with UPRT=1), so these must
+ * be cleared here to avoid side-channels. slbmte is used rather
+ * than slbia, as it won't clear cached translations.
+ */
+static void radix_clear_slb(void)
+{
+	u64 slbee, slbev;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		mfslb(i, &slbee, &slbev);
+		if (unlikely(slbee || slbev)) {
+			slbee = i;
+			slbev = 0;
+			mtslb(i, slbee, slbev);
+		}
+	}
+}
+
 static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -80,6 +124,31 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6
 	kvmppc_check_need_tlb_flush(kvm, vc->pcpu, nested);
 }
 
+static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
+{
+	struct kvm_nested_guest *nested = vcpu->arch.nested;
+	u32 lpid;
+	int i;
+
+	BUG_ON(nested);
+
+	lpid = kvm->arch.lpid;
+
+	mtspr(SPRN_LPID, lpid);
+	mtspr(SPRN_LPCR, lpcr);
+	mtspr(SPRN_PID, vcpu->arch.pid);
+
+	for (i = 0; i < vcpu->arch.slb_max; i++)
+		__mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv);
+
+	isync();
+
+	/*
+	 * TLBIEL is not virtualised for HPT guests, so check_need_tlb_flush
+	 * is not required here.
+	 */
+}
+
 static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
 {
 	isync();
@@ -91,42 +160,30 @@ static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
 	isync();
 }
 
-static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev)
-{
-	asm volatile("slbmfev  %0,%1" : "=r" (*slbev) : "r" (idx));
-	asm volatile("slbmfee  %0,%1" : "=r" (*slbee) : "r" (idx));
-}
-
-static inline void mtslb(unsigned int idx, u64 slbee, u64 slbev)
-{
-	BUG_ON((slbee & 0xfff) != idx);
-
-	asm volatile("slbmte %0,%1" :: "r" (slbev), "r" (slbee));
-}
-
-static inline void slb_invalidate(unsigned int ih)
-{
-	asm volatile("slbia %0" :: "i"(ih));
-}
-
-/*
- * Malicious or buggy radix guests may have inserted SLB entries
- * (only 0..3 because radix always runs with UPRT=1), so these must
- * be cleared here to avoid side-channels. slbmte is used rather
- * than slbia, as it won't clear cached translations.
- */
-static void radix_clear_slb(void)
+static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu)
 {
-	u64 slbee, slbev;
-	int i;
+	if (kvm_is_radix(kvm)) {
+		radix_clear_slb();
+	} else {
+		int i;
+		int nr = 0;
 
-	for (i = 0; i < 4; i++) {
-		mfslb(i, &slbee, &slbev);
-		if (unlikely(slbee || slbev)) {
-			slbee = i;
-			slbev = 0;
-			mtslb(i, slbee, slbev);
+		/*
+		 * This must run before switching to host (radix host can't
+		 * access all SLBs).
+		 */
+		for (i = 0; i < vcpu->arch.slb_nr; i++) {
+			u64 slbee, slbev;
+			mfslb(i, &slbee, &slbev);
+			if (slbee & SLB_ESID_V) {
+				vcpu->arch.slb[nr].orige = slbee | i;
+				vcpu->arch.slb[nr].origv = slbev;
+				nr++;
+			}
 		}
+		vcpu->arch.slb_max = nr;
+		mtslb(0, 0, 0);
+		slb_invalidate(6);
 	}
 }
 
@@ -234,10 +291,18 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 
 	mtspr(SPRN_AMOR, ~0UL);
 
-	if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
-		__mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+	local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST_HV_FAST;
+	if (kvm_is_radix(kvm)) {
+		if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+			__mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+		switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
+		if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+			__mtmsrd(0, 1); /* clear RI */
 
-	switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
+	} else {
+		__mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+		switch_mmu_to_guest_hpt(kvm, vcpu, lpcr);
+	}
 
 	/*
 	 * P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
@@ -245,9 +310,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	 */
 	mtspr(SPRN_HDEC, hdec);
 
-	if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
-		__mtmsrd(0, 1); /* clear RI */
-
 	mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
 	mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
 	mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
@@ -255,10 +317,7 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 
 	accumulate_time(vcpu, &vcpu->arch.guest_time);
 
-	local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST_HV_FAST;
 	kvmppc_p9_enter_guest(vcpu);
-	// Radix host and guest means host never runs with guest MMU state
-	local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE;
 
 	accumulate_time(vcpu, &vcpu->arch.rm_intr);
 
@@ -359,8 +418,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 #endif
 	}
 
-	radix_clear_slb();
-
 	accumulate_time(vcpu, &vcpu->arch.rm_exit);
 
 	/* Advance host PURR/SPURR by the amount used by guest */
@@ -394,11 +451,14 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 		mtspr(SPRN_DAWRX1, host_dawrx1);
 	}
 
-	/*
-	 * Since this is radix, do a eieio; tlbsync; ptesync sequence in
-	 * case we interrupted the guest between a tlbie and a ptesync.
-	 */
-	asm volatile("eieio; tlbsync; ptesync");
+	if (kvm_is_radix(kvm)) {
+		/*
+		 * Since this is radix, do a eieio; tlbsync; ptesync sequence
+		 * in case we interrupted the guest between a tlbie and a
+		 * ptesync.
+		 */
+		asm volatile("eieio; tlbsync; ptesync");
+	}
 
 	/*
 	 * cp_abort is required if the processor supports local copy-paste
@@ -425,7 +485,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	/* HDEC must be at least as large as DEC, so decrementer_max fits */
 	mtspr(SPRN_HDEC, decrementer_max);
 
+	save_clear_guest_mmu(kvm, vcpu);
 	switch_mmu_to_host_radix(kvm, host_pidr);
+	local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE;
 
 	/*
 	 * If we are in real mode, only switch MMU on after the MMU is
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 8cc73abbf42b..f487ebb3a70a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -57,6 +57,10 @@ static int global_invalidates(struct kvm *kvm)
 	else
 		global = 1;
 
+	/* LPID has been switched to host if in virt mode so can't do local */
+	if (!global && (mfmsr() & (MSR_IR|MSR_DR)))
+		global = 1;
+
 	if (!global) {
 		/* any other core might now have stale TLB entries... */
 		smp_wmb();
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 564ca9feef35..5cbc26ebcf8e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -885,14 +885,11 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	cmpdi	r3, 512		/* 1 microsecond */
 	blt	hdec_soon
 
-	/* For hash guest, clear out and reload the SLB */
-BEGIN_MMU_FTR_SECTION
-	/* Radix host won't have populated the SLB, so no need to clear */
+	/* Clear out and reload the SLB */
 	li	r6, 0
 	slbmte	r6, r6
 	PPC_SLBIA(6)
 	ptesync
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	/* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
 	lwz	r5,VCPU_SLB_MAX(r4)
@@ -1394,9 +1391,6 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	stw	r5,VCPU_SLB_MAX(r9)
 
 	/* load host SLB entries */
-BEGIN_MMU_FTR_SECTION
-	b	guest_bypass
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	ld	r8,PACA_SLBSHADOWPTR(r13)
 
 	.rept	SLB_NUM_BOLTED
@@ -3148,10 +3142,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
 	PPC_SLBIA(6)
 	ptesync
 
-BEGIN_MMU_FTR_SECTION
-	b	4f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
-
 	/* load host SLB entries */
 	ld	r8, PACA_SLBSHADOWPTR(r13)
 	.rept	SLB_NUM_BOLTED
@@ -3165,7 +3155,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 3:	addi	r8, r8, 16
 	.endr
 
-4:	lwz	r7, KVM_HOST_LPID(r10)
+	lwz	r7, KVM_HOST_LPID(r10)
 	mtspr	SPRN_LPID, r7
 	mtspr	SPRN_PID, r0
 	ld	r8, KVM_HOST_LPCR(r10)
-- 
2.23.0


^ permalink raw reply related

* [PATCH v4 45/46] KVM: PPC: Book3S HV P9: implement hash host / hash guest support
From: Nicholas Piggin @ 2021-03-23  1:03 UTC (permalink / raw)
  To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210323010305.1045293-1-npiggin@gmail.com>

This additionally has to save and restore the host SLB, and also
ensure that the MMU is off while switching into the guest SLB.

P9 and later CPUs now always go via the P9 path.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kvm/book3s_64_entry.S     |  6 +++++
 arch/powerpc/kvm/book3s_hv.c           |  4 ++-
 arch/powerpc/kvm/book3s_hv_interrupt.c | 35 ++++++++++++++++++++++----
 3 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 845df5fefdbd..7cef6f5212d8 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -339,6 +339,12 @@ kvmppc_p9_exit_interrupt:
  * effort for a small bit of code. Lots of other things to do first.
  */
 kvmppc_p9_bad_interrupt:
+BEGIN_MMU_FTR_SECTION
+	/*
+	 * Hash host doesn't try to recover MMU (requires host SLB reload)
+	 */
+	b	.
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	/*
 	 * Set GUEST_MODE_NONE so the handler won't branch to KVM, and clear
 	 * MSR_RI in r12 ([H]SRR1) so the handler won't try to return.
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c151a60c0daa..e732d65772b1 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4462,7 +4462,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
 	do {
-		if (radix_enabled())
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
 			r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
 						  vcpu->arch.vcore->lpcr);
 		else
@@ -5543,6 +5543,8 @@ static int kvmhv_enable_nested(struct kvm *kvm)
 		return -EPERM;
 	if (!cpu_has_feature(CPU_FTR_ARCH_300))
 		return -ENODEV;
+	if (!radix_enabled())
+		return -ENODEV;
 
 	/* kvm == NULL means the caller is testing if the capability exists */
 	if (kvm)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index 03fbfef708a8..bd95d05219b7 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -149,7 +149,7 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64
 	 */
 }
 
-static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
+static void switch_mmu_to_host(struct kvm *kvm, u32 pid)
 {
 	isync();
 	mtspr(SPRN_PID, pid);
@@ -158,6 +158,23 @@ static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
 	isync();
 	mtspr(SPRN_LPCR, kvm->arch.host_lpcr);
 	isync();
+
+	if (!radix_enabled())
+		slb_restore_bolted_realmode();
+}
+
+static void save_clear_host_mmu(struct kvm *kvm)
+{
+	if (!radix_enabled()) {
+		/*
+		 * Hash host could save and restore host SLB entries to
+		 * reduce SLB fault overheads of VM exits, but for now the
+		 * existing code clears all entries and restores just the
+		 * bolted ones when switching back to host.
+		 */
+		mtslb(0, 0, 0);
+		slb_invalidate(6);
+	}
 }
 
 static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu)
@@ -292,15 +309,23 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	mtspr(SPRN_AMOR, ~0UL);
 
 	local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST_HV_FAST;
+
+	/*
+	 * Hash host, hash guest, or radix guest with prefetch bug, all have
+	 * to disable the MMU before switching to guest MMU state.
+	 */
+	if (!radix_enabled() || !kvm_is_radix(kvm) ||
+			cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+		__mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+
+	save_clear_host_mmu(kvm);
+
 	if (kvm_is_radix(kvm)) {
-		if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
-			__mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
 		switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
 		if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
 			__mtmsrd(0, 1); /* clear RI */
 
 	} else {
-		__mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
 		switch_mmu_to_guest_hpt(kvm, vcpu, lpcr);
 	}
 
@@ -486,7 +511,7 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	mtspr(SPRN_HDEC, decrementer_max);
 
 	save_clear_guest_mmu(kvm, vcpu);
-	switch_mmu_to_host_radix(kvm, host_pidr);
+	switch_mmu_to_host(kvm, host_pidr);
 	local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE;
 
 	/*
-- 
2.23.0


^ permalink raw reply related

* [PATCH v4 46/46] KVM: PPC: Book3S HV: remove ISA v3.0 and v3.1 support from P7/8 path
From: Nicholas Piggin @ 2021-03-23  1:03 UTC (permalink / raw)
  To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210323010305.1045293-1-npiggin@gmail.com>

POWER9 and later processors always go via the P9 guest entry path now.
Remove the remaining support from the P7/8 path.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kvm/book3s_hv.c            |  62 ++--
 arch/powerpc/kvm/book3s_hv_interrupts.S |   9 +-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 404 +-----------------------
 arch/powerpc/platforms/powernv/idle.c   |  52 +--
 4 files changed, 39 insertions(+), 488 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e732d65772b1..ad6a2501ab0f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -130,9 +130,6 @@ static inline bool nesting_enabled(struct kvm *kvm)
 	return kvm->arch.nested_enable && kvm_is_radix(kvm);
 }
 
-/* If set, the threads on each CPU core have to be in the same MMU mode */
-static bool no_mixing_hpt_and_radix __read_mostly;
-
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
 /*
@@ -3090,9 +3087,6 @@ static void prepare_threads(struct kvmppc_vcore *vc)
 	for_each_runnable_thread(i, vcpu, vc) {
 		if (signal_pending(vcpu->arch.run_task))
 			vcpu->arch.ret = -EINTR;
-		else if (no_mixing_hpt_and_radix &&
-			 kvm_is_radix(vc->kvm) != radix_enabled())
-			vcpu->arch.ret = -EINVAL;
 		else if (vcpu->arch.vpa.update_pending ||
 			 vcpu->arch.slb_shadow.update_pending ||
 			 vcpu->arch.dtl.update_pending)
@@ -3299,6 +3293,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	int trap;
 	bool is_power8;
 
+	if (WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)))
+		return;
+
 	/*
 	 * Remove from the list any threads that have a signal pending
 	 * or need a VPA update done
@@ -3326,9 +3323,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 * Make sure we are running on primary threads, and that secondary
 	 * threads are offline.  Also check if the number of threads in this
 	 * guest are greater than the current system threads per guest.
-	 * On POWER9, we need to be not in independent-threads mode if
-	 * this is a HPT guest on a radix host machine where the
-	 * CPU threads may not be in different MMU modes.
 	 */
 	if ((controlled_threads > 1) &&
 	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
@@ -3352,18 +3346,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	if (vc->num_threads < target_threads)
 		collect_piggybacks(&core_info, target_threads);
 
-	/*
-	 * On radix, arrange for TLB flushing if necessary.
-	 * This has to be done before disabling interrupts since
-	 * it uses smp_call_function().
-	 */
-	pcpu = smp_processor_id();
-	if (kvm_is_radix(vc->kvm)) {
-		for (sub = 0; sub < core_info.n_subcores; ++sub)
-			for_each_runnable_thread(i, vcpu, core_info.vc[sub])
-				kvmppc_prepare_radix_vcpu(vcpu, pcpu);
-	}
-
 	/*
 	 * Hard-disable interrupts, and check resched flag and signals.
 	 * If we need to reschedule or deliver a signal, clean up
@@ -3396,8 +3378,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	cmd_bit = stat_bit = 0;
 	split = core_info.n_subcores;
 	sip = NULL;
-	is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S)
-		&& !cpu_has_feature(CPU_FTR_ARCH_300);
+	is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S);
 
 	if (split > 1) {
 		sip = &split_info;
@@ -3691,8 +3672,7 @@ static inline bool hcall_is_xics(unsigned long req)
 }
 
 /*
- * Virtual-mode guest entry for POWER9 and later when the host and
- * guest are both using the radix MMU.  The LPIDR has already been set.
+ * Guest entry for POWER9 and later CPUs.
  */
 static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 			 unsigned long lpcr)
@@ -5706,11 +5686,25 @@ static int kvmhv_enable_dawr1(struct kvm *kvm)
 
 static bool kvmppc_hash_v3_possible(void)
 {
-	if (radix_enabled() && no_mixing_hpt_and_radix)
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
 		return false;
 
-	return cpu_has_feature(CPU_FTR_ARCH_300) &&
-		cpu_has_feature(CPU_FTR_HVMODE);
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return false;
+
+	/*
+	 * POWER9 chips before version 2.02 can't have some threads in
+	 * HPT mode and some in radix mode on the same core.
+	 */
+	if (radix_enabled()) {
+		unsigned int pvr = mfspr(SPRN_PVR);
+		if ((pvr >> 16) == PVR_POWER9 &&
+		    (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
+		     ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
+			return false;
+	}
+
+	return true;
 }
 
 static struct kvmppc_ops kvm_ops_hv = {
@@ -5854,18 +5848,6 @@ static int kvmppc_book3s_init_hv(void)
 	if (kvmppc_radix_possible())
 		r = kvmppc_radix_init();
 
-	/*
-	 * POWER9 chips before version 2.02 can't have some threads in
-	 * HPT mode and some in radix mode on the same core.
-	 */
-	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-		unsigned int pvr = mfspr(SPRN_PVR);
-		if ((pvr >> 16) == PVR_POWER9 &&
-		    (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
-		     ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
-			no_mixing_hpt_and_radix = true;
-	}
-
 	r = kvmppc_uvmem_init();
 	if (r < 0)
 		pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r);
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 327417d79eac..4444f83cb133 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -58,7 +58,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	/*
 	 * Put whatever is in the decrementer into the
 	 * hypervisor decrementer.
-	 * Because of a hardware deviation in P8 and P9,
+	 * Because of a hardware deviation in P8,
 	 * we need to set LPCR[HDICE] before writing HDEC.
 	 */
 	ld	r5, HSTATE_KVM_VCORE(r13)
@@ -67,15 +67,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	ori	r8, r9, LPCR_HDICE
 	mtspr	SPRN_LPCR, r8
 	isync
-	andis.	r0, r9, LPCR_LD@h
 	mfspr	r8,SPRN_DEC
 	mftb	r7
-BEGIN_FTR_SECTION
-	/* On POWER9, don't sign-extend if host LPCR[LD] bit is set */
-	bne	32f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	extsw	r8,r8
-32:	mtspr	SPRN_HDEC,r8
+	mtspr	SPRN_HDEC,r8
 	add	r8,r8,r7
 	std	r8,HSTATE_DECEXP(r13)
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 5cbc26ebcf8e..b2a71a1b48fe 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -25,7 +25,6 @@
 #include <asm/export.h>
 #include <asm/tm.h>
 #include <asm/opal.h>
-#include <asm/xive-regs.h>
 #include <asm/thread_info.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
@@ -34,9 +33,7 @@
 
 /* Sign-extend HDEC if not on POWER9 */
 #define EXTEND_HDEC(reg)			\
-BEGIN_FTR_SECTION;				\
-	extsw	reg, reg;			\
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+	extsw	reg, reg
 
 /* Values in HSTATE_NAPPING(r13) */
 #define NAPPING_CEDE	1
@@ -56,8 +53,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 #define STACK_SLOT_HFSCR	(SFS-72)
 #define STACK_SLOT_AMR		(SFS-80)
 #define STACK_SLOT_UAMOR	(SFS-88)
-#define STACK_SLOT_DAWR1	(SFS-96)
-#define STACK_SLOT_DAWRX1	(SFS-104)
 
 /*
  * Call kvmppc_hv_entry in real mode.
@@ -333,7 +328,6 @@ kvm_secondary_got_guest:
 	LOAD_REG_ADDR(r6, decrementer_max)
 	ld	r6, 0(r6)
 	mtspr	SPRN_HDEC, r6
-BEGIN_FTR_SECTION
 	/* and set per-LPAR registers, if doing dynamic micro-threading */
 	ld	r6, HSTATE_SPLIT_MODE(r13)
 	cmpdi	r6, 0
@@ -345,7 +339,6 @@ BEGIN_FTR_SECTION
 	ld	r0, KVM_SPLIT_LDBAR(r6)
 	mtspr	SPRN_LDBAR, r0
 	isync
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 63:
 	/* Order load of vcpu after load of vcore */
 	lwsync
@@ -416,7 +409,6 @@ kvm_no_guest:
 	blr
 
 53:
-BEGIN_FTR_SECTION
 	HMT_LOW
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	cmpdi	r5, 0
@@ -431,14 +423,6 @@ BEGIN_FTR_SECTION
 	b	kvm_unsplit_nap
 60:	HMT_MEDIUM
 	b	kvm_secondary_got_guest
-FTR_SECTION_ELSE
-	HMT_LOW
-	ld	r5, HSTATE_KVM_VCORE(r13)
-	cmpdi	r5, 0
-	beq	kvm_no_guest
-	HMT_MEDIUM
-	b	kvm_secondary_got_guest
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 
 54:	li	r0, KVM_HWTHREAD_IN_KVM
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
@@ -564,13 +548,11 @@ kvmppc_hv_entry:
 	bne	10f
 
 	lwz	r7,KVM_LPID(r9)
-BEGIN_FTR_SECTION
 	ld	r6,KVM_SDR1(r9)
 	li	r0,LPID_RSVD		/* switch to reserved LPID */
 	mtspr	SPRN_LPID,r0
 	ptesync
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPID,r7
 	isync
 
@@ -650,16 +632,6 @@ kvmppc_got_guest:
 	mtspr	SPRN_SPURR,r8
 
 	/* Save host values of some registers */
-BEGIN_FTR_SECTION
-	mfspr	r5, SPRN_TIDR
-	mfspr	r6, SPRN_PSSCR
-	mfspr	r7, SPRN_PID
-	std	r5, STACK_SLOT_TID(r1)
-	std	r6, STACK_SLOT_PSSCR(r1)
-	std	r7, STACK_SLOT_PID(r1)
-	mfspr	r5, SPRN_HFSCR
-	std	r5, STACK_SLOT_HFSCR(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_CIABR
 	mfspr	r6, SPRN_DAWR0
@@ -670,12 +642,6 @@ BEGIN_FTR_SECTION
 	std	r7, STACK_SLOT_DAWRX0(r1)
 	std	r8, STACK_SLOT_IAMR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
-	mfspr	r6, SPRN_DAWR1
-	mfspr	r7, SPRN_DAWRX1
-	std	r6, STACK_SLOT_DAWR1(r1)
-	std	r7, STACK_SLOT_DAWRX1(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S | CPU_FTR_DAWR1)
 
 	mfspr	r5, SPRN_AMR
 	std	r5, STACK_SLOT_AMR(r1)
@@ -693,13 +659,9 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Branch around the call if both CPU_FTR_TM and
- * CPU_FTR_P9_TM_HV_ASSIST are off.
- */
 BEGIN_FTR_SECTION
 	b	91f
-END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
 	 */
@@ -766,12 +728,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	ld	r6, VCPU_DAWRX0(r4)
 	mtspr	SPRN_DAWR0, r5
 	mtspr	SPRN_DAWRX0, r6
-BEGIN_FTR_SECTION
-	ld	r5, VCPU_DAWR1(r4)
-	ld	r6, VCPU_DAWRX1(r4)
-	mtspr	SPRN_DAWR1, r5
-	mtspr	SPRN_DAWRX1, r6
-END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
 1:
 	ld	r7, VCPU_CIABR(r4)
 	ld	r8, VCPU_TAR(r4)
@@ -789,7 +745,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
 	mtspr	SPRN_BESCR, r6
 	mtspr	SPRN_PID, r7
 	mtspr	SPRN_WORT, r8
-BEGIN_FTR_SECTION
 	/* POWER8-only registers */
 	ld	r5, VCPU_TCSCR(r4)
 	ld	r6, VCPU_ACOP(r4)
@@ -800,18 +755,6 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_CSIGR, r7
 	mtspr	SPRN_TACR, r8
 	nop
-FTR_SECTION_ELSE
-	/* POWER9-only registers */
-	ld	r5, VCPU_TID(r4)
-	ld	r6, VCPU_PSSCR(r4)
-	lbz	r8, HSTATE_FAKE_SUSPEND(r13)
-	oris	r6, r6, PSSCR_EC@h	/* This makes stop trap to HV */
-	rldimi	r6, r8, PSSCR_FAKE_SUSPEND_LG, 63 - PSSCR_FAKE_SUSPEND_LG
-	ld	r7, VCPU_HFSCR(r4)
-	mtspr	SPRN_TIDR, r5
-	mtspr	SPRN_PSSCR, r6
-	mtspr	SPRN_HFSCR, r7
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 8:
 
 	ld	r5, VCPU_SPRG0(r4)
@@ -904,93 +847,9 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	bdnz	1b
 9:
 
-#ifdef CONFIG_KVM_XICS
-	/* We are entering the guest on that thread, push VCPU to XIVE */
-	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
-	li	r9, TM_QW1_OS
-	lwz	r8, VCPU_XIVE_CAM_WORD(r4)
-	cmpwi	r8, 0
-	beq	no_xive
-	li	r7, TM_QW1_OS + TM_WORD2
-	mfmsr	r0
-	andi.	r0, r0, MSR_DR		/* in real mode? */
-	beq	2f
-	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
-	cmpldi	cr1, r10, 0
-	beq     cr1, no_xive
-	eieio
-	stdx	r11,r9,r10
-	stwx	r8,r7,r10
-	b	3f
-2:	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
-	cmpldi	cr1, r10, 0
-	beq	cr1, no_xive
-	eieio
-	stdcix	r11,r9,r10
-	stwcix	r8,r7,r10
-3:	li	r9, 1
-	stb	r9, VCPU_XIVE_PUSHED(r4)
-	eieio
-
-	/*
-	 * We clear the irq_pending flag. There is a small chance of a
-	 * race vs. the escalation interrupt happening on another
-	 * processor setting it again, but the only consequence is to
-	 * cause a spurrious wakeup on the next H_CEDE which is not an
-	 * issue.
-	 */
-	li	r0,0
-	stb	r0, VCPU_IRQ_PENDING(r4)
-
-	/*
-	 * In single escalation mode, if the escalation interrupt is
-	 * on, we mask it.
-	 */
-	lbz	r0, VCPU_XIVE_ESC_ON(r4)
-	cmpwi	cr1, r0,0
-	beq	cr1, 1f
-	li	r9, XIVE_ESB_SET_PQ_01
-	beq	4f			/* in real mode? */
-	ld	r10, VCPU_XIVE_ESC_VADDR(r4)
-	ldx	r0, r10, r9
-	b	5f
-4:	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
-	ldcix	r0, r10, r9
-5:	sync
-
-	/* We have a possible subtle race here: The escalation interrupt might
-	 * have fired and be on its way to the host queue while we mask it,
-	 * and if we unmask it early enough (re-cede right away), there is
-	 * a theorical possibility that it fires again, thus landing in the
-	 * target queue more than once which is a big no-no.
-	 *
-	 * Fortunately, solving this is rather easy. If the above load setting
-	 * PQ to 01 returns a previous value where P is set, then we know the
-	 * escalation interrupt is somewhere on its way to the host. In that
-	 * case we simply don't clear the xive_esc_on flag below. It will be
-	 * eventually cleared by the handler for the escalation interrupt.
-	 *
-	 * Then, when doing a cede, we check that flag again before re-enabling
-	 * the escalation interrupt, and if set, we abort the cede.
-	 */
-	andi.	r0, r0, XIVE_ESB_VAL_P
-	bne-	1f
-
-	/* Now P is 0, we can clear the flag */
-	li	r0, 0
-	stb	r0, VCPU_XIVE_ESC_ON(r4)
-1:
-no_xive:
-#endif /* CONFIG_KVM_XICS */
-
 deliver_guest_interrupt:	/* r4 = vcpu, r13 = paca */
 	/* Check if we can deliver an external or decrementer interrupt now */
 	ld	r0, VCPU_PENDING_EXC(r4)
-BEGIN_FTR_SECTION
-	/* On POWER9, also check for emulated doorbell interrupt */
-	lbz	r3, VCPU_DBELL_REQ(r4)
-	or	r0, r0, r3
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	cmpdi	r0, 0
 	beq	71f
 	mr	r3, r4
@@ -1063,12 +922,6 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_PPR, r0
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
-/* Move canary into DSISR to check for later */
-BEGIN_FTR_SECTION
-	li	r0, 0x7fff
-	mtspr	SPRN_HDSISR, r0
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
 	ld	r6, VCPU_KVM(r4)
 	lbz	r7, KVM_SECURE_GUEST(r6)
 	cmpdi	r7, 0
@@ -1284,14 +1137,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	/* Hypervisor doorbell - exit only if host IPI flag set */
 	cmpwi	r12, BOOK3S_INTERRUPT_H_DOORBELL
 	bne	3f
-BEGIN_FTR_SECTION
-	PPC_MSGSYNC
-	lwsync
-	/* always exit if we're running a nested guest */
-	ld	r0, VCPU_NESTED(r9)
-	cmpdi	r0, 0
-	bne	guest_exit_cont
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
 	beq	maybe_reenter_guest
@@ -1321,43 +1166,6 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	mr	r4, r9
 	bl	kvmhv_accumulate_time
 #endif
-#ifdef CONFIG_KVM_XICS
-	/* We are exiting, pull the VP from the XIVE */
-	lbz	r0, VCPU_XIVE_PUSHED(r9)
-	cmpwi	cr0, r0, 0
-	beq	1f
-	li	r7, TM_SPC_PULL_OS_CTX
-	li	r6, TM_QW1_OS
-	mfmsr	r0
-	andi.	r0, r0, MSR_DR		/* in real mode? */
-	beq	2f
-	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
-	cmpldi	cr0, r10, 0
-	beq	1f
-	/* First load to pull the context, we ignore the value */
-	eieio
-	lwzx	r11, r7, r10
-	/* Second load to recover the context state (Words 0 and 1) */
-	ldx	r11, r6, r10
-	b	3f
-2:	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
-	cmpldi	cr0, r10, 0
-	beq	1f
-	/* First load to pull the context, we ignore the value */
-	eieio
-	lwzcix	r11, r7, r10
-	/* Second load to recover the context state (Words 0 and 1) */
-	ldcix	r11, r6, r10
-3:	std	r11, VCPU_XIVE_SAVED_STATE(r9)
-	/* Fixup some of the state for the next load */
-	li	r10, 0
-	li	r0, 0xff
-	stb	r10, VCPU_XIVE_PUSHED(r9)
-	stb	r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
-	stb	r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
-	eieio
-1:
-#endif /* CONFIG_KVM_XICS */
 
 	/*
 	 * Possibly flush the link stack here, before we do a blr in
@@ -1412,12 +1220,6 @@ guest_bypass:
 	ld	r3, HSTATE_KVM_VCORE(r13)
 	mfspr	r5,SPRN_DEC
 	mftb	r6
-	/* On P9, if the guest has large decr enabled, don't sign extend */
-BEGIN_FTR_SECTION
-	ld	r4, VCORE_LPCR(r3)
-	andis.	r4, r4, LPCR_LD@h
-	bne	16f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	extsw	r5,r5
 16:	add	r5,r5,r6
 	/* r5 is a guest timebase value here, convert to host TB */
@@ -1491,7 +1293,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	std	r6, VCPU_BESCR(r9)
 	stw	r7, VCPU_GUEST_PID(r9)
 	std	r8, VCPU_WORT(r9)
-BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_TCSCR
 	mfspr	r6, SPRN_ACOP
 	mfspr	r7, SPRN_CSIGR
@@ -1500,17 +1301,6 @@ BEGIN_FTR_SECTION
 	std	r6, VCPU_ACOP(r9)
 	std	r7, VCPU_CSIGR(r9)
 	std	r8, VCPU_TACR(r9)
-FTR_SECTION_ELSE
-	mfspr	r5, SPRN_TIDR
-	mfspr	r6, SPRN_PSSCR
-	std	r5, VCPU_TID(r9)
-	rldicl	r6, r6, 4, 50		/* r6 &= PSSCR_GUEST_VIS */
-	rotldi	r6, r6, 60
-	std	r6, VCPU_PSSCR(r9)
-	/* Restore host HFSCR value */
-	ld	r7, STACK_SLOT_HFSCR(r1)
-	mtspr	SPRN_HFSCR, r7
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	/*
 	 * Restore various registers to 0, where non-zero values
 	 * set by the guest could disrupt the host.
@@ -1518,13 +1308,11 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	li	r0, 0
 	mtspr	SPRN_PSPB, r0
 	mtspr	SPRN_WORT, r0
-BEGIN_FTR_SECTION
 	mtspr	SPRN_TCSCR, r0
 	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
 	li	r0, 1
 	sldi	r0, r0, 31
 	mtspr	SPRN_MMCRS, r0
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 
 	/* Save and restore AMR, IAMR and UAMOR before turning on the MMU */
 	ld	r8, STACK_SLOT_IAMR(r1)
@@ -1581,13 +1369,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	bl	kvmppc_save_fp
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Branch around the call if both CPU_FTR_TM and
- * CPU_FTR_P9_TM_HV_ASSIST are off.
- */
 BEGIN_FTR_SECTION
 	b	91f
-END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
 	 */
@@ -1633,28 +1417,6 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_DAWR0, r6
 	mtspr	SPRN_DAWRX0, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
-	ld	r6, STACK_SLOT_DAWR1(r1)
-	ld	r7, STACK_SLOT_DAWRX1(r1)
-	mtspr	SPRN_DAWR1, r6
-	mtspr	SPRN_DAWRX1, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S | CPU_FTR_DAWR1)
-BEGIN_FTR_SECTION
-	ld	r5, STACK_SLOT_TID(r1)
-	ld	r6, STACK_SLOT_PSSCR(r1)
-	ld	r7, STACK_SLOT_PID(r1)
-	mtspr	SPRN_TIDR, r5
-	mtspr	SPRN_PSSCR, r6
-	mtspr	SPRN_PID, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
-	/*
-	 * cp_abort is required if the processor supports local copy-paste
-	 * to clear the copy buffer that was under control of the guest.
-	 */
-BEGIN_FTR_SECTION
-	PPC_CP_ABORT
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
 
 	/*
 	 * POWER7/POWER8 guest -> host partition switch code.
@@ -1691,13 +1453,11 @@ kvmhv_switch_to_host:
 
 	/* Primary thread switches back to host partition */
 	lwz	r7,KVM_HOST_LPID(r4)
-BEGIN_FTR_SECTION
 	ld	r6,KVM_HOST_SDR1(r4)
 	li	r8,LPID_RSVD		/* switch to reserved LPID */
 	mtspr	SPRN_LPID,r8
 	ptesync
 	mtspr	SPRN_SDR1,r6		/* switch to host page table */
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPID,r7
 	isync
 
@@ -1908,20 +1668,11 @@ kvmppc_tm_emul:
 kvmppc_hdsi:
 	mfspr	r4, SPRN_HDAR
 	mfspr	r6, SPRN_HDSISR
-BEGIN_FTR_SECTION
-	/* Look for DSISR canary. If we find it, retry instruction */
-	cmpdi	r6, 0x7fff
-	beq	6f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	/* HPTE not found fault or protection fault? */
 	andis.	r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
 	beq	1f			/* if not, send it to the guest */
 	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
 	beq	3f
-BEGIN_FTR_SECTION
-	mfspr	r5, SPRN_ASDR		/* on POWER9, use ASDR to get VSID */
-	b	4f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	clrrdi	r0, r4, 28
 	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
 	li	r0, BOOK3S_INTERRUPT_DATA_SEGMENT
@@ -1998,10 +1749,6 @@ kvmppc_hisi:
 	beq	1f
 	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
 	beq	3f
-BEGIN_FTR_SECTION
-	mfspr	r5, SPRN_ASDR		/* on POWER9, use ASDR to get VSID */
-	b	4f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	clrrdi	r0, r10, 28
 	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
 	li	r0, BOOK3S_INTERRUPT_INST_SEGMENT
@@ -2049,10 +1796,6 @@ hcall_try_real_mode:
 	andi.	r0,r11,MSR_PR
 	/* sc 1 from userspace - reflect to guest syscall */
 	bne	sc_1_fast_return
-	/* sc 1 from nested guest - give it to L1 to handle */
-	ld	r0, VCPU_NESTED(r9)
-	cmpdi	r0, 0
-	bne	guest_exit_cont
 	clrrdi	r3,r3,2
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
 	bge	guest_exit_cont
@@ -2448,13 +2191,9 @@ _GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
 	bl	kvmppc_save_fp
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Branch around the call if both CPU_FTR_TM and
- * CPU_FTR_P9_TM_HV_ASSIST are off.
- */
 BEGIN_FTR_SECTION
 	b	91f
-END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
 	 */
@@ -2474,15 +2213,8 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	mfspr	r3, SPRN_DEC
 	mfspr	r4, SPRN_HDEC
 	mftb	r5
-BEGIN_FTR_SECTION
-	/* On P9 check whether the guest has large decrementer mode enabled */
-	ld	r6, HSTATE_KVM_VCORE(r13)
-	ld	r6, VCORE_LPCR(r6)
-	andis.	r6, r6, LPCR_LD@h
-	bne	68f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	extsw	r3, r3
-68:	EXTEND_HDEC(r4)
+	EXTEND_HDEC(r4)
 	cmpd	r3, r4
 	ble	67f
 	mtspr	SPRN_DEC, r4
@@ -2527,28 +2259,14 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 kvm_nap_sequence:		/* desired LPCR value in r5 */
-BEGIN_FTR_SECTION
-	/*
-	 * PSSCR bits:	exit criterion = 1 (wakeup based on LPCR at sreset)
-	 *		enable state loss = 1 (allow SMT mode switch)
-	 *		requested level = 0 (just stop dispatching)
-	 */
-	lis	r3, (PSSCR_EC | PSSCR_ESL)@h
 	/* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
 	li	r4, LPCR_PECE_HVEE@higher
 	sldi	r4, r4, 32
 	or	r5, r5, r4
-FTR_SECTION_ELSE
-	li	r3, PNV_THREAD_NAP
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPCR,r5
 	isync
 
-BEGIN_FTR_SECTION
-	bl	isa300_idle_stop_mayloss
-FTR_SECTION_ELSE
 	bl	isa206_idle_insn_mayloss
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 
 	mfspr	r0, SPRN_CTRLF
 	ori	r0, r0, 1
@@ -2567,10 +2285,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	beq	kvm_end_cede
 	cmpwi	r0, NAPPING_NOVCPU
 	beq	kvm_novcpu_wakeup
-BEGIN_FTR_SECTION
 	cmpwi	r0, NAPPING_UNSPLIT
 	beq	kvm_unsplit_wakeup
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	twi	31,0,0 /* Nap state must not be zero */
 
 33:	mr	r4, r3
@@ -2590,13 +2306,9 @@ kvm_end_cede:
 #endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Branch around the call if both CPU_FTR_TM and
- * CPU_FTR_P9_TM_HV_ASSIST are off.
- */
 BEGIN_FTR_SECTION
 	b	91f
-END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
 	/*
 	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
 	 */
@@ -2686,47 +2398,7 @@ kvm_cede_prodded:
 	/* we've ceded but we want to give control to the host */
 kvm_cede_exit:
 	ld	r9, HSTATE_KVM_VCPU(r13)
-#ifdef CONFIG_KVM_XICS
-	/* are we using XIVE with single escalation? */
-	ld	r10, VCPU_XIVE_ESC_VADDR(r9)
-	cmpdi	r10, 0
-	beq	3f
-	li	r6, XIVE_ESB_SET_PQ_00
-	/*
-	 * If we still have a pending escalation, abort the cede,
-	 * and we must set PQ to 10 rather than 00 so that we don't
-	 * potentially end up with two entries for the escalation
-	 * interrupt in the XIVE interrupt queue.  In that case
-	 * we also don't want to set xive_esc_on to 1 here in
-	 * case we race with xive_esc_irq().
-	 */
-	lbz	r5, VCPU_XIVE_ESC_ON(r9)
-	cmpwi	r5, 0
-	beq	4f
-	li	r0, 0
-	stb	r0, VCPU_CEDED(r9)
-	/*
-	 * The escalation interrupts are special as we don't EOI them.
-	 * There is no need to use the load-after-store ordering offset
-	 * to set PQ to 10 as we won't use StoreEOI.
-	 */
-	li	r6, XIVE_ESB_SET_PQ_10
-	b	5f
-4:	li	r0, 1
-	stb	r0, VCPU_XIVE_ESC_ON(r9)
-	/* make sure store to xive_esc_on is seen before xive_esc_irq runs */
-	sync
-5:	/* Enable XIVE escalation */
-	mfmsr	r0
-	andi.	r0, r0, MSR_DR		/* in real mode? */
-	beq	1f
-	ldx	r0, r10, r6
-	b	2f
-1:	ld	r10, VCPU_XIVE_ESC_RADDR(r9)
-	ldcix	r0, r10, r6
-2:	sync
-#endif /* CONFIG_KVM_XICS */
-3:	b	guest_exit_cont
+	b	guest_exit_cont
 
 	/* Try to do machine check recovery in real mode */
 machine_check_realmode:
@@ -2803,10 +2475,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	PPC_MSGCLR(6)
 	/* see if it's a host IPI */
 	li	r3, 1
-BEGIN_FTR_SECTION
-	PPC_MSGSYNC
-	lwsync
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
 	bnelr
@@ -3115,70 +2783,12 @@ kvmppc_bad_host_intr:
 	std	r3, STACK_FRAME_OVERHEAD-16(r1)
 
 	/*
-	 * On POWER9 do a minimal restore of the MMU and call C code,
-	 * which will print a message and panic.
 	 * XXX On POWER7 and POWER8, we just spin here since we don't
 	 * know what the other threads are doing (and we don't want to
 	 * coordinate with them) - but at least we now have register state
 	 * in memory that we might be able to look at from another CPU.
 	 */
-BEGIN_FTR_SECTION
 	b	.
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-	ld	r9, HSTATE_KVM_VCPU(r13)
-	ld	r10, VCPU_KVM(r9)
-
-	li	r0, 0
-	mtspr	SPRN_AMR, r0
-	mtspr	SPRN_IAMR, r0
-	mtspr	SPRN_CIABR, r0
-	mtspr	SPRN_DAWRX0, r0
-BEGIN_FTR_SECTION
-	mtspr	SPRN_DAWRX1, r0
-END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
-
-	/* Clear guest SLB. */
-	slbmte	r0, r0
-	PPC_SLBIA(6)
-	ptesync
-
-	/* load host SLB entries */
-	ld	r8, PACA_SLBSHADOWPTR(r13)
-	.rept	SLB_NUM_BOLTED
-	li	r3, SLBSHADOW_SAVEAREA
-	LDX_BE	r5, r8, r3
-	addi	r3, r3, 8
-	LDX_BE	r6, r8, r3
-	andis.	r7, r5, SLB_ESID_V@h
-	beq	3f
-	slbmte	r6, r5
-3:	addi	r8, r8, 16
-	.endr
-
-	lwz	r7, KVM_HOST_LPID(r10)
-	mtspr	SPRN_LPID, r7
-	mtspr	SPRN_PID, r0
-	ld	r8, KVM_HOST_LPCR(r10)
-	mtspr	SPRN_LPCR, r8
-	isync
-	li	r0, KVM_GUEST_MODE_NONE
-	stb	r0, HSTATE_IN_GUEST(r13)
-
-	/*
-	 * Turn on the MMU and jump to C code
-	 */
-	bcl	20, 31, .+4
-5:	mflr	r3
-	addi	r3, r3, 9f - 5b
-	li	r4, -1
-	rldimi	r3, r4, 62, 0	/* ensure 0xc000000000000000 bits are set */
-	ld	r4, PACAKMSR(r13)
-	mtspr	SPRN_SRR0, r3
-	mtspr	SPRN_SRR1, r4
-	RFI_TO_KERNEL
-9:	addi	r3, r1, STACK_FRAME_OVERHEAD
-	bl	kvmppc_bad_interrupt
-	b	9b
 
 /*
  * This mimics the MSR transition on IRQ delivery.  The new guest MSR is taken
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 999997d9e9a9..528a7e0cf83a 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -604,7 +604,7 @@ struct p9_sprs {
 	u64 uamor;
 };
 
-static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
+static unsigned long power9_idle_stop(unsigned long psscr)
 {
 	int cpu = raw_smp_processor_id();
 	int first = cpu_first_thread_sibling(cpu);
@@ -620,8 +620,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
 	if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
 		/* EC=ESL=0 case */
 
-		BUG_ON(!mmu_on);
-
 		/*
 		 * Wake synchronously. SRESET via xscom may still cause
 		 * a 0x100 powersave wakeup with SRR1 reason!
@@ -803,8 +801,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
 		__slb_restore_bolted_realmode();
 
 out:
-	if (mmu_on)
-		mtmsr(MSR_KERNEL);
+	mtmsr(MSR_KERNEL);
 
 	return srr1;
 }
@@ -895,7 +892,7 @@ struct p10_sprs {
 	 */
 };
 
-static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
+static unsigned long power10_idle_stop(unsigned long psscr)
 {
 	int cpu = raw_smp_processor_id();
 	int first = cpu_first_thread_sibling(cpu);
@@ -909,8 +906,6 @@ static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
 	if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
 		/* EC=ESL=0 case */
 
-		BUG_ON(!mmu_on);
-
 		/*
 		 * Wake synchronously. SRESET via xscom may still cause
 		 * a 0x100 powersave wakeup with SRR1 reason!
@@ -991,8 +986,7 @@ static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
 		__slb_restore_bolted_realmode();
 
 out:
-	if (mmu_on)
-		mtmsr(MSR_KERNEL);
+	mtmsr(MSR_KERNEL);
 
 	return srr1;
 }
@@ -1002,40 +996,10 @@ static unsigned long arch300_offline_stop(unsigned long psscr)
 {
 	unsigned long srr1;
 
-#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	__ppc64_runlatch_off();
 	if (cpu_has_feature(CPU_FTR_ARCH_31))
-		srr1 = power10_idle_stop(psscr, true);
+		srr1 = power10_idle_stop(psscr);
 	else
-		srr1 = power9_idle_stop(psscr, true);
-	__ppc64_runlatch_on();
-#else
-	/*
-	 * Tell KVM we're entering idle.
-	 * This does not have to be done in real mode because the P9 MMU
-	 * is independent per-thread. Some steppings share radix/hash mode
-	 * between threads, but in that case KVM has a barrier sync in real
-	 * mode before and after switching between radix and hash.
-	 *
-	 * kvm_start_guest must still be called in real mode though, hence
-	 * the false argument.
-	 */
-	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE;
-
-	__ppc64_runlatch_off();
-	if (cpu_has_feature(CPU_FTR_ARCH_31))
-		srr1 = power10_idle_stop(psscr, false);
-	else
-		srr1 = power9_idle_stop(psscr, false);
-	__ppc64_runlatch_on();
-
-	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL;
-	/* Order setting hwthread_state vs. testing hwthread_req */
-	smp_mb();
-	if (local_paca->kvm_hstate.hwthread_req)
-		srr1 = idle_kvm_start_guest(srr1);
-	mtmsr(MSR_KERNEL);
-#endif
+		srr1 = power9_idle_stop(psscr);
 
 	return srr1;
 }
@@ -1055,9 +1019,9 @@ void arch300_idle_type(unsigned long stop_psscr_val,
 
 	__ppc64_runlatch_off();
 	if (cpu_has_feature(CPU_FTR_ARCH_31))
-		srr1 = power10_idle_stop(psscr, true);
+		srr1 = power10_idle_stop(psscr);
 	else
-		srr1 = power9_idle_stop(psscr, true);
+		srr1 = power9_idle_stop(psscr);
 	__ppc64_runlatch_on();
 
 	fini_irq_for_idle_irqsoff();
-- 
2.23.0


^ permalink raw reply related

* Re: [PATCH v11 0/6] KASAN for powerpc64 radix
From: Daniel Axtens @ 2021-03-23  1:21 UTC (permalink / raw)
  To: Christophe Leroy, linux-kernel, linux-mm, linuxppc-dev, kasan-dev,
	aneesh.kumar, bsingharora
In-Reply-To: <5a3b5952-b31f-42bf-eaf4-ea24444f8df6@csgroup.eu>

Hi Christophe,

> In the discussion we had long time ago, 
> https://patchwork.ozlabs.org/project/linuxppc-dev/patch/20190806233827.16454-5-dja@axtens.net/#2321067 
> , I challenged you on why it was not possible to implement things the same way as other 
> architectures, in extenso with an early mapping.
>
> Your first answer was that too many things were done in real mode at startup. After some discussion 
> you said that finally there was not that much things at startup but the issue was KVM.
>
> Now you say that instrumentation on KVM is fully disabled.
>
> So my question is, if KVM is not a problem anymore, why not go the standard way with an early shadow 
> ? Then you could also support inline instrumentation.

Fair enough, I've had some trouble both understanding the problem myself
and clearly articulating it. Let me try again.

We need translations on to access the shadow area.

We reach setup_64.c::early_setup() with translations off. At this point
we don't know what MMU we're running under, or our CPU features.

To determine our MMU and CPU features, early_setup() calls functions
(dt_cpu_ftrs_init, early_init_devtree) that call out to generic code
like of_scan_flat_dt. We need to do this before we turn on translations
because we can't set up the MMU until we know what MMU we have.

So this puts us in a bind:

 - We can't set up an early shadow until we have translations on, which
   requires that the MMU is set up.

 - We can't set up an MMU until we call out to generic code for FDT
   parsing.

So there will be calls to generic FDT parsing code that happen before the
early shadow is set up.

The setup code also prints a bunch of information about the platform
with printk() while translations are off, so it wouldn't even be enough
to disable instrumentation for bits of the generic DT code on ppc64.

Does that make sense? If you can figure out how to 'square the circle'
here I'm all ears.

Other notes:

 - There's a comment about printk() being 'safe' in early_setup(), that
   refers to having a valid PACA, it doesn't mean that it's safe in any
   other sense.

 - KVM does indeed also run stuff with translations off but we can catch
   all of that by disabling instrumentation on the real-mode handlers:
   it doesn't seem to leak out to generic code. So you are right that
   KVM is no longer an issue.

Kind regards,
Daniel


>
> Christophe


^ permalink raw reply

* Re: [PATCH v3 25/41] KVM: PPC: Book3S HV P9: Reduce irq_work vs guest decrementer races
From: Alexey Kardashevskiy @ 2021-03-23  1:43 UTC (permalink / raw)
  To: Nicholas Piggin, kvm-ppc; +Cc: linuxppc-dev
In-Reply-To: <20210305150638.2675513-26-npiggin@gmail.com>



On 06/03/2021 02:06, Nicholas Piggin wrote:
> irq_work's use of the DEC SPR is racy with guest<->host switch and guest
> entry which flips the DEC interrupt to guest, which could lose a host
> work interrupt.
> 
> This patch closes one race, and attempts to comment another class of
> races.
> 
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> ---
>   arch/powerpc/kvm/book3s_hv.c | 15 ++++++++++++++-
>   1 file changed, 14 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 6f3e3aed99aa..b7a88960ac49 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -3704,6 +3704,18 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
>   	if (!(vcpu->arch.ctrl & 1))
>   		mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
>   
> +	/*
> +	 * When setting DEC, we must always deal with irq_work_raise via NMI vs
> +	 * setting DEC. The problem occurs right as we switch into guest mode
> +	 * if a NMI hits and sets pending work and sets DEC, then that will
> +	 * apply to the guest and not bring us back to the host.
> +	 *
> +	 * irq_work_raise could check a flag (or possibly LPCR[HDICE] for
> +	 * example) and set HDEC to 1? That wouldn't solve the nested hv
> +	 * case which needs to abort the hcall or zero the time limit.
> +	 *
> +	 * XXX: Another day's problem.
> +	 */
>   	mtspr(SPRN_DEC, vcpu->arch.dec_expires - tb);
>   
>   	if (kvmhv_on_pseries()) {
> @@ -3838,7 +3850,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
>   	vc->entry_exit_map = 0x101;
>   	vc->in_guest = 0;
>   
> -	mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - tb);
> +	set_dec_or_work(local_paca->kvm_hstate.dec_expires - tb);

set_dec_or_work() will write local_paca->kvm_hstate.dec_expires - tb - 1 
to SPRN_DEC which is not exactly the same, is this still alright?


> +
>   	mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
>   
>   	kvmhv_load_host_pmu();
> 

-- 
Alexey

^ permalink raw reply

* Re: [PATCH v6 1/6] KVM: PPC: Book3S HV: Fix comments of H_RPT_INVALIDATE arguments
From: David Gibson @ 2021-03-23  1:19 UTC (permalink / raw)
  To: Bharata B Rao; +Cc: farosas, aneesh.kumar, npiggin, kvm-ppc, linuxppc-dev
In-Reply-To: <20210311083939.595568-2-bharata@linux.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 1761 bytes --]

On Thu, Mar 11, 2021 at 02:09:34PM +0530, Bharata B Rao wrote:
> From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
> 
> The type values H_RPTI_TYPE_PRT and H_RPTI_TYPE_PAT indicate
> invalidating the caching of process and partition scoped entries
> respectively.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>

Not sure the change really clarifies that much, but whatever

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  arch/powerpc/include/asm/hvcall.h | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
> index ed6086d57b22..6af7bb3c9121 100644
> --- a/arch/powerpc/include/asm/hvcall.h
> +++ b/arch/powerpc/include/asm/hvcall.h
> @@ -411,9 +411,9 @@
>  #define H_RPTI_TYPE_NESTED	0x0001	/* Invalidate nested guest partition-scope */
>  #define H_RPTI_TYPE_TLB		0x0002	/* Invalidate TLB */
>  #define H_RPTI_TYPE_PWC		0x0004	/* Invalidate Page Walk Cache */
> -/* Invalidate Process Table Entries if H_RPTI_TYPE_NESTED is clear */
> +/* Invalidate caching of Process Table Entries if H_RPTI_TYPE_NESTED is clear */
>  #define H_RPTI_TYPE_PRT		0x0008
> -/* Invalidate Partition Table Entries if H_RPTI_TYPE_NESTED is set */
> +/* Invalidate caching of Partition Table Entries if H_RPTI_TYPE_NESTED is set */
>  #define H_RPTI_TYPE_PAT		0x0008
>  #define H_RPTI_TYPE_ALL		(H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \
>  				 H_RPTI_TYPE_PRT)

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply

* Re: [PATCH v6 2/6] powerpc/book3s64/radix: Add H_RPT_INVALIDATE pgsize encodings to mmu_psize_def
From: David Gibson @ 2021-03-23  1:24 UTC (permalink / raw)
  To: Bharata B Rao; +Cc: farosas, aneesh.kumar, npiggin, kvm-ppc, linuxppc-dev
In-Reply-To: <20210311083939.595568-3-bharata@linux.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 2737 bytes --]

On Thu, Mar 11, 2021 at 02:09:35PM +0530, Bharata B Rao wrote:
> Add a field to mmu_psize_def to store the page size encodings
> of H_RPT_INVALIDATE hcall. Initialize this while scanning the radix
> AP encodings. This will be used when invalidating with required
> page size encoding in the hcall.
> 
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>

Having the table be the source of truth and implementing
psize_to_rpti_pgsize() in terms of it would be nicer.  But... I guess
you can't really do that, because you're dynamically initializing the
table from the device tree, but the device tree doesn't include the
RPTI encodings.  Oh well.

Reveiwed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  arch/powerpc/include/asm/book3s/64/mmu.h | 1 +
>  arch/powerpc/mm/book3s64/radix_pgtable.c | 5 +++++
>  2 files changed, 6 insertions(+)
> 
> diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
> index eace8c3f7b0a..c02f42d1031e 100644
> --- a/arch/powerpc/include/asm/book3s/64/mmu.h
> +++ b/arch/powerpc/include/asm/book3s/64/mmu.h
> @@ -19,6 +19,7 @@ struct mmu_psize_def {
>  	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
>  	unsigned int	tlbiel;	/* tlbiel supported for that page size */
>  	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
> +	unsigned long   h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */
>  	union {
>  		unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
>  		unsigned long ap;	/* Ap encoding used by PowerISA 3.0 */
> diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
> index 98f0b243c1ab..1b749899016b 100644
> --- a/arch/powerpc/mm/book3s64/radix_pgtable.c
> +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
> @@ -486,6 +486,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
>  		def = &mmu_psize_defs[idx];
>  		def->shift = shift;
>  		def->ap  = ap;
> +		def->h_rpt_pgsize = psize_to_rpti_pgsize(idx);
>  	}
>  
>  	/* needed ? */
> @@ -560,9 +561,13 @@ void __init radix__early_init_devtree(void)
>  		 */
>  		mmu_psize_defs[MMU_PAGE_4K].shift = 12;
>  		mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
> +		mmu_psize_defs[MMU_PAGE_4K].h_rpt_pgsize =
> +			psize_to_rpti_pgsize(MMU_PAGE_4K);
>  
>  		mmu_psize_defs[MMU_PAGE_64K].shift = 16;
>  		mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
> +		mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize =
> +			psize_to_rpti_pgsize(MMU_PAGE_64K);
>  	}
>  
>  	/*

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply

* Re: [PATCH v6 6/6] KVM: PPC: Book3S HV: Use H_RPT_INVALIDATE in nested KVM
From: David Gibson @ 2021-03-23  2:35 UTC (permalink / raw)
  To: Bharata B Rao; +Cc: farosas, aneesh.kumar, npiggin, kvm-ppc, linuxppc-dev
In-Reply-To: <20210311083939.595568-7-bharata@linux.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 3909 bytes --]

On Thu, Mar 11, 2021 at 02:09:39PM +0530, Bharata B Rao wrote:
> In the nested KVM case, replace H_TLB_INVALIDATE by the new hcall
> H_RPT_INVALIDATE if available. The availability of this hcall
> is determined from "hcall-rpt-invalidate" string in ibm,hypertas-functions
> DT property.
> 
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  arch/powerpc/kvm/book3s_64_mmu_radix.c | 27 +++++++++++++++++++++-----
>  arch/powerpc/kvm/book3s_hv_nested.c    | 12 ++++++++++--
>  2 files changed, 32 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
> index e603de7ade52..1e1e55fd0ee5 100644
> --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
> +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
> @@ -21,6 +21,7 @@
>  #include <asm/pte-walk.h>
>  #include <asm/ultravisor.h>
>  #include <asm/kvm_book3s_uvmem.h>
> +#include <asm/plpar_wrappers.h>
>  
>  /*
>   * Supported radix tree geometry.
> @@ -318,9 +319,19 @@ void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
>  	}
>  
>  	psi = shift_to_mmu_psize(pshift);
> -	rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
> -	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
> -				lpid, rb);
> +
> +	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) {
> +		rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
> +		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
> +					lpid, rb);
> +	} else {
> +		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
> +					    H_RPTI_TYPE_NESTED |
> +					    H_RPTI_TYPE_TLB,
> +					    psize_to_rpti_pgsize(psi),
> +					    addr, addr + psize);
> +	}
> +
>  	if (rc)
>  		pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
>  }
> @@ -334,8 +345,14 @@ static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
>  		return;
>  	}
>  
> -	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
> -				lpid, TLBIEL_INVAL_SET_LPID);
> +	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE))
> +		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
> +					lpid, TLBIEL_INVAL_SET_LPID);
> +	else
> +		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
> +					    H_RPTI_TYPE_NESTED |
> +					    H_RPTI_TYPE_PWC, H_RPTI_PAGE_ALL,
> +					    0, -1UL);
>  	if (rc)
>  		pr_err("KVM: TLB PWC invalidation hcall failed, rc=%ld\n", rc);
>  }
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> index adcc8e26ef22..5601b7eb9b89 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -19,6 +19,7 @@
>  #include <asm/pgalloc.h>
>  #include <asm/pte-walk.h>
>  #include <asm/reg.h>
> +#include <asm/plpar_wrappers.h>
>  
>  static struct patb_entry *pseries_partition_tb;
>  
> @@ -444,8 +445,15 @@ static void kvmhv_flush_lpid(unsigned int lpid)
>  		return;
>  	}
>  
> -	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
> -				lpid, TLBIEL_INVAL_SET_LPID);
> +	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE))
> +		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
> +					lpid, TLBIEL_INVAL_SET_LPID);
> +	else
> +		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
> +					    H_RPTI_TYPE_NESTED |
> +					    H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
> +					    H_RPTI_TYPE_PAT,
> +					    H_RPTI_PAGE_ALL, 0, -1UL);
>  	if (rc)
>  		pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
>  }

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply

* Re: [PATCH v6 4/6] KVM: PPC: Book3S HV: Nested support in H_RPT_INVALIDATE
From: David Gibson @ 2021-03-23  2:33 UTC (permalink / raw)
  To: Bharata B Rao; +Cc: farosas, aneesh.kumar, npiggin, kvm-ppc, linuxppc-dev
In-Reply-To: <20210311083939.595568-5-bharata@linux.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 8728 bytes --]

On Thu, Mar 11, 2021 at 02:09:37PM +0530, Bharata B Rao wrote:
> Enable support for process-scoped invalidations from nested
> guests and partition-scoped invalidations for nested guests.
> 
> Process-scoped invalidations for any level of nested guests
> are handled by implementing H_RPT_INVALIDATE handler in the
> nested guest exit path in L0.
> 
> Partition-scoped invalidation requests are forwarded to the
> right nested guest, handled there and passed down to L0
> for eventual handling.
> 
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> 	[Nested guest partition-scoped invalidation changes]

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  arch/powerpc/include/asm/kvm_book3s.h |   3 +
>  arch/powerpc/kvm/book3s_hv.c          |  71 +++++++++++++++++-
>  arch/powerpc/kvm/book3s_hv_nested.c   | 104 ++++++++++++++++++++++++++
>  3 files changed, 175 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
> index 2f5f919f6cd3..de8fc5a4d19c 100644
> --- a/arch/powerpc/include/asm/kvm_book3s.h
> +++ b/arch/powerpc/include/asm/kvm_book3s.h
> @@ -305,6 +305,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1);
>  void kvmhv_release_all_nested(struct kvm *kvm);
>  long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
>  long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
> +long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid,
> +			     unsigned long type, unsigned long pg_sizes,
> +			     unsigned long start, unsigned long end);
>  int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu,
>  			  u64 time_limit, unsigned long lpcr);
>  void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 5d008468347c..03755389efd1 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -922,6 +922,46 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
>  	return yield_count;
>  }
>  
> +/*
> + * H_RPT_INVALIDATE hcall handler for nested guests.
> + *
> + * Handles only nested process-scoped invalidation requests in L0.
> + */
> +static int kvmppc_nested_h_rpt_invalidate(struct kvm_vcpu *vcpu)
> +{
> +	unsigned long type = kvmppc_get_gpr(vcpu, 6);
> +	unsigned long pid, pg_sizes, start, end, psize;
> +	struct kvm_nested_guest *gp;
> +	struct mmu_psize_def *def;
> +
> +	/*
> +	 * The partition-scoped invalidations aren't handled here in L0.
> +	 */
> +	if (type & H_RPTI_TYPE_NESTED)
> +		return RESUME_HOST;
> +
> +	pid = kvmppc_get_gpr(vcpu, 4);
> +	pg_sizes = kvmppc_get_gpr(vcpu, 7);
> +	start = kvmppc_get_gpr(vcpu, 8);
> +	end = kvmppc_get_gpr(vcpu, 9);
> +
> +	gp = kvmhv_get_nested(vcpu->kvm, vcpu->kvm->arch.lpid, false);
> +	if (!gp)
> +		goto out;
> +
> +	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +		def = &mmu_psize_defs[psize];
> +		if (pg_sizes & def->h_rpt_pgsize)
> +			do_h_rpt_invalidate_prt(pid, gp->shadow_lpid, type,
> +						(1UL << def->shift), psize,
> +						start, end);
> +	}
> +	kvmhv_put_nested(gp);
> +out:
> +	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
> +	return RESUME_GUEST;
> +}
> +
>  static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
>  				    unsigned long id, unsigned long target,
>  				    unsigned long type, unsigned long pg_sizes,
> @@ -938,10 +978,18 @@ static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
>  
>  	/*
>  	 * Partition-scoped invalidation for nested guests.
> -	 * Not yet supported
>  	 */
> -	if (type & H_RPTI_TYPE_NESTED)
> -		return H_P3;
> +	if (type & H_RPTI_TYPE_NESTED) {
> +		if (!nesting_enabled(vcpu->kvm))
> +			return H_FUNCTION;
> +
> +		/* Support only cores as target */
> +		if (target != H_RPTI_TARGET_CMMU)
> +			return H_P2;
> +
> +		return do_h_rpt_invalidate_pat(vcpu, id, type, pg_sizes,
> +					       start, end);
> +	}
>  
>  	/*
>  	 * Process-scoped invalidation for L1 guests.
> @@ -1636,6 +1684,23 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
>  		if (!xics_on_xive())
>  			kvmppc_xics_rm_complete(vcpu, 0);
>  		break;
> +	case BOOK3S_INTERRUPT_SYSCALL:
> +	{
> +		unsigned long req = kvmppc_get_gpr(vcpu, 3);
> +
> +		/*
> +		 * The H_RPT_INVALIDATE hcalls issued by nested
> +		 * guests for process-scoped invalidations when
> +		 * GTSE=0, are handled here in L0.
> +		 */
> +		if (req == H_RPT_INVALIDATE) {
> +			r = kvmppc_nested_h_rpt_invalidate(vcpu);
> +			break;
> +		}
> +
> +		r = RESUME_HOST;
> +		break;
> +	}
>  	default:
>  		r = RESUME_HOST;
>  		break;
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> index 0cd0e7aad588..adcc8e26ef22 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -1191,6 +1191,110 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
>  	return H_SUCCESS;
>  }
>  
> +static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu,
> +					 unsigned long lpid,
> +					 unsigned long page_size,
> +					 unsigned long ap,
> +					 unsigned long start,
> +					 unsigned long end)
> +{
> +	unsigned long addr = start;
> +	int ret;
> +
> +	do {
> +		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap,
> +						   get_epn(addr));
> +		if (ret)
> +			return ret;
> +		addr += page_size;
> +	} while (addr < end);
> +
> +	return ret;
> +}
> +
> +static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu,
> +					 unsigned long lpid, unsigned long ric)
> +{
> +	struct kvm *kvm = vcpu->kvm;
> +	struct kvm_nested_guest *gp;
> +
> +	gp = kvmhv_get_nested(kvm, lpid, false);
> +	if (gp) {
> +		kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
> +		kvmhv_put_nested(gp);
> +	}
> +	return H_SUCCESS;
> +}
> +
> +/*
> + * Performs partition-scoped invalidations for nested guests
> + * as part of H_RPT_INVALIDATE hcall.
> + */
> +long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid,
> +			     unsigned long type, unsigned long pg_sizes,
> +			     unsigned long start, unsigned long end)
> +{
> +	struct kvm_nested_guest *gp;
> +	long ret;
> +	unsigned long psize, ap;
> +
> +	/*
> +	 * If L2 lpid isn't valid, we need to return H_PARAMETER.
> +	 *
> +	 * However, nested KVM issues a L2 lpid flush call when creating
> +	 * partition table entries for L2. This happens even before the
> +	 * corresponding shadow lpid is created in HV which happens in
> +	 * H_ENTER_NESTED call. Since we can't differentiate this case from
> +	 * the invalid case, we ignore such flush requests and return success.
> +	 */
> +	gp = kvmhv_find_nested(vcpu->kvm, lpid);
> +	if (!gp)
> +		return H_SUCCESS;
> +
> +	/*
> +	 * A flush all request can be handled by a full lpid flush only.
> +	 */
> +	if ((type & H_RPTI_TYPE_NESTED_ALL) == H_RPTI_TYPE_NESTED_ALL)
> +		return do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_ALL);
> +
> +#if 0
> +	/*
> +	 * We don't need to handle a PWC flush like process table here,
> +	 * because intermediate partition scoped table in nested guest doesn't
> +	 * really have PWC. Only level we have PWC is in L0 and for nested
> +	 * invalidate at L0 we always do kvm_flush_lpid() which does
> +	 * radix__flush_all_lpid(). For range invalidate at any level, we
> +	 * are not removing the higher level page tables and hence there is
> +	 * no PWC invalidate needed.
> +	 */
> +	if (type & H_RPTI_TYPE_PWC) {
> +		ret = do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_PWC);
> +		if (ret)
> +			return H_P4;
> +	}
> +#endif
> +
> +	if (start == 0 && end == -1)
> +		return do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_TLB);
> +
> +	if (type & H_RPTI_TYPE_TLB) {
> +		struct mmu_psize_def *def;
> +
> +		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +			def = &mmu_psize_defs[psize];
> +			if (!(pg_sizes & def->h_rpt_pgsize))
> +				continue;
> +
> +			ret = do_tlb_invalidate_nested_tlb(vcpu, lpid,
> +							   (1UL << def->shift),
> +							   ap, start, end);
> +			if (ret)
> +				return H_P4;
> +		}
> +	}
> +	return H_SUCCESS;
> +}
> +
>  /* Used to convert a nested guest real address to a L1 guest real address */
>  static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
>  				       struct kvm_nested_guest *gp,

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply

* Re: [PATCH v6 3/6] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
From: David Gibson @ 2021-03-23  2:26 UTC (permalink / raw)
  To: Bharata B Rao; +Cc: farosas, aneesh.kumar, npiggin, kvm-ppc, linuxppc-dev
In-Reply-To: <20210311083939.595568-4-bharata@linux.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 16472 bytes --]

On Thu, Mar 11, 2021 at 02:09:36PM +0530, Bharata B Rao wrote:
> H_RPT_INVALIDATE does two types of TLB invalidations:
> 
> 1. Process-scoped invalidations for guests when LPCR[GTSE]=0.
>    This is currently not used in KVM as GTSE is not usually
>    disabled in KVM.
> 2. Partition-scoped invalidations that an L1 hypervisor does on
>    behalf of an L2 guest. This is currently handled
>    by H_TLB_INVALIDATE hcall and this new replaces the old that.
> 
> This commit enables process-scoped invalidations for L1 guests.
> Support for process-scoped and partition-scoped invalidations
> from/for nested guests will be added separately.
> 
> Process scoped tlbie invalidations from L1 and nested guests
> need RS register for TLBIE instruction to contain both PID and
> LPID.  This patch introduces primitives that execute tlbie
> instruction with both PID and LPID set in prepartion for
> H_RPT_INVALIDATE hcall.
> 
> A description of H_RPT_INVALIDATE follows:
> 
> int64   /* H_Success: Return code on successful completion */
>         /* H_Busy - repeat the call with the same */
>         /* H_Parameter, H_P2, H_P3, H_P4, H_P5 : Invalid
> 	   parameters */
> hcall(const uint64 H_RPT_INVALIDATE, /* Invalidate RPT
> 					translation
> 					lookaside information */
>       uint64 id,        /* PID/LPID to invalidate */
>       uint64 target,    /* Invalidation target */
>       uint64 type,      /* Type of lookaside information */
>       uint64 pg_sizes,  /* Page sizes */
>       uint64 start,     /* Start of Effective Address (EA)
> 			   range (inclusive) */
>       uint64 end)       /* End of EA range (exclusive) */
> 
> Invalidation targets (target)
> -----------------------------
> Core MMU        0x01 /* All virtual processors in the
> 			partition */
> Core local MMU  0x02 /* Current virtual processor */
> Nest MMU        0x04 /* All nest/accelerator agents
> 			in use by the partition */
> 
> A combination of the above can be specified,
> except core and core local.
> 
> Type of translation to invalidate (type)
> ---------------------------------------
> NESTED       0x0001  /* invalidate nested guest partition-scope */
> TLB          0x0002  /* Invalidate TLB */
> PWC          0x0004  /* Invalidate Page Walk Cache */
> PRT          0x0008  /* Invalidate caching of Process Table
> 			Entries if NESTED is clear */
> PAT          0x0008  /* Invalidate caching of Partition Table
> 			Entries if NESTED is set */
> 
> A combination of the above can be specified.
> 
> Page size mask (pages)
> ----------------------
> 4K              0x01
> 64K             0x02
> 2M              0x04
> 1G              0x08
> All sizes       (-1UL)
> 
> A combination of the above can be specified.
> All page sizes can be selected with -1.
> 
> Semantics: Invalidate radix tree lookaside information
>            matching the parameters given.
> * Return H_P2, H_P3 or H_P4 if target, type, or pageSizes parameters
>   are different from the defined values.
> * Return H_PARAMETER if NESTED is set and pid is not a valid nested
>   LPID allocated to this partition
> * Return H_P5 if (start, end) doesn't form a valid range. Start and
>   end should be a valid Quadrant address and  end > start.
> * Return H_NotSupported if the partition is not in running in radix
>   translation mode.
> * May invalidate more translation information than requested.
> * If start = 0 and end = -1, set the range to cover all valid
>   addresses. Else start and end should be aligned to 4kB (lower 11
>   bits clear).
> * If NESTED is clear, then invalidate process scoped lookaside
>   information. Else pid specifies a nested LPID, and the invalidation
>   is performed   on nested guest partition table and nested guest
>   partition scope real addresses.
> * If pid = 0 and NESTED is clear, then valid addresses are quadrant 3
>   and quadrant 0 spaces, Else valid addresses are quadrant 0.
> * Pages which are fully covered by the range are to be invalidated.
>   Those which are partially covered are considered outside
>   invalidation range, which allows a caller to optimally invalidate
>   ranges that may   contain mixed page sizes.
> * Return H_SUCCESS on success.
> 
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

with the exception of one nit noted below.

> ---
>  .../include/asm/book3s/64/tlbflush-radix.h    |   4 +
>  arch/powerpc/include/asm/mmu_context.h        |  11 ++
>  arch/powerpc/kvm/book3s_hv.c                  |  46 ++++++
>  arch/powerpc/mm/book3s64/radix_tlb.c          | 152 +++++++++++++++++-
>  4 files changed, 209 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> index 8b33601cdb9d..a46fd37ad552 100644
> --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> @@ -4,6 +4,10 @@
>  
>  #include <asm/hvcall.h>
>  
> +#define RIC_FLUSH_TLB 0
> +#define RIC_FLUSH_PWC 1
> +#define RIC_FLUSH_ALL 2

Is there a reason for moving these?  You don't appear to be adding a
use of them outside the .c file they were in before.

> +
>  struct vm_area_struct;
>  struct mm_struct;
>  struct mmu_gather;
> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> index 652ce85f9410..da25aef657c6 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -124,8 +124,19 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
>  
>  #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
>  extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
> +void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid,
> +			     unsigned long type, unsigned long page_size,
> +			     unsigned long psize, unsigned long start,
> +			     unsigned long end);
>  #else
>  static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
> +static inline void do_h_rpt_invalidate_prt(unsigned long pid,
> +					   unsigned long lpid,
> +					   unsigned long type,
> +					   unsigned long page_size,
> +					   unsigned long psize,
> +					   unsigned long start,
> +					   unsigned long end) { }
>  #endif
>  
>  extern void switch_cop(struct mm_struct *next);
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 13bad6bf4c95..5d008468347c 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -76,6 +76,7 @@
>  #include <asm/kvm_book3s_uvmem.h>
>  #include <asm/ultravisor.h>
>  #include <asm/dtl.h>
> +#include <asm/plpar_wrappers.h>
>  
>  #include "book3s.h"
>  
> @@ -921,6 +922,42 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
>  	return yield_count;
>  }
>  
> +static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
> +				    unsigned long id, unsigned long target,
> +				    unsigned long type, unsigned long pg_sizes,
> +				    unsigned long start, unsigned long end)
> +{
> +	unsigned long psize;
> +	struct mmu_psize_def *def;
> +
> +	if (!kvm_is_radix(vcpu->kvm))
> +		return H_UNSUPPORTED;
> +
> +	if (end < start)
> +		return H_P5;
> +
> +	/*
> +	 * Partition-scoped invalidation for nested guests.
> +	 * Not yet supported
> +	 */
> +	if (type & H_RPTI_TYPE_NESTED)
> +		return H_P3;
> +
> +	/*
> +	 * Process-scoped invalidation for L1 guests.
> +	 */
> +	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +		def = &mmu_psize_defs[psize];
> +		if (!(pg_sizes & def->h_rpt_pgsize))
> +			continue;
> +
> +		do_h_rpt_invalidate_prt(id, vcpu->kvm->arch.lpid,
> +					type, (1UL << def->shift),
> +					psize, start, end);
> +	}
> +	return H_SUCCESS;
> +}
> +
>  int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
>  {
>  	unsigned long req = kvmppc_get_gpr(vcpu, 3);
> @@ -1129,6 +1166,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
>  		 */
>  		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
>  		break;
> +	case H_RPT_INVALIDATE:
> +		ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
> +					      kvmppc_get_gpr(vcpu, 5),
> +					      kvmppc_get_gpr(vcpu, 6),
> +					      kvmppc_get_gpr(vcpu, 7),
> +					      kvmppc_get_gpr(vcpu, 8),
> +					      kvmppc_get_gpr(vcpu, 9));
> +		break;
>  
>  	default:
>  		return RESUME_HOST;
> @@ -1175,6 +1220,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
>  	case H_XIRR_X:
>  #endif
>  	case H_PAGE_INIT:
> +	case H_RPT_INVALIDATE:
>  		return 1;
>  	}
>  
> diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
> index 409e61210789..613198c41006 100644
> --- a/arch/powerpc/mm/book3s64/radix_tlb.c
> +++ b/arch/powerpc/mm/book3s64/radix_tlb.c
> @@ -20,10 +20,6 @@
>  
>  #include "internal.h"
>  
> -#define RIC_FLUSH_TLB 0
> -#define RIC_FLUSH_PWC 1
> -#define RIC_FLUSH_ALL 2
> -
>  /*
>   * tlbiel instruction for radix, set invalidation
>   * i.e., r=1 and is=01 or is=10 or is=11
> @@ -130,6 +126,21 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
>  	trace_tlbie(0, 0, rb, rs, ric, prs, r);
>  }
>  
> +static __always_inline void __tlbie_pid_lpid(unsigned long pid,
> +					     unsigned long lpid,
> +					     unsigned long ric)
> +{
> +	unsigned long rb, rs, prs, r;
> +
> +	rb = PPC_BIT(53); /* IS = 1 */
> +	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
> +	prs = 1; /* process scoped */
> +	r = 1;   /* radix format */
> +
> +	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
> +		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
> +	trace_tlbie(0, 0, rb, rs, ric, prs, r);
> +}
>  static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
>  {
>  	unsigned long rb,rs,prs,r;
> @@ -190,6 +201,23 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
>  	trace_tlbie(0, 0, rb, rs, ric, prs, r);
>  }
>  
> +static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
> +					    unsigned long lpid,
> +					    unsigned long ap, unsigned long ric)
> +{
> +	unsigned long rb, rs, prs, r;
> +
> +	rb = va & ~(PPC_BITMASK(52, 63));
> +	rb |= ap << PPC_BITLSHIFT(58);
> +	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
> +	prs = 1; /* process scoped */
> +	r = 1;   /* radix format */
> +
> +	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
> +		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
> +	trace_tlbie(0, 0, rb, rs, ric, prs, r);
> +}
> +
>  static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
>  					    unsigned long ap, unsigned long ric)
>  {
> @@ -235,6 +263,22 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
>  	}
>  }
>  
> +static inline void fixup_tlbie_va_range_lpid(unsigned long va,
> +					     unsigned long pid,
> +					     unsigned long lpid,
> +					     unsigned long ap)
> +{
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
> +	}
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
> +	}
> +}
> +
>  static inline void fixup_tlbie_pid(unsigned long pid)
>  {
>  	/*
> @@ -254,6 +298,25 @@ static inline void fixup_tlbie_pid(unsigned long pid)
>  	}
>  }
>  
> +static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
> +{
> +	/*
> +	 * We can use any address for the invalidation, pick one which is
> +	 * probably unused as an optimisation.
> +	 */
> +	unsigned long va = ((1UL << 52) - 1);
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
> +	}
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
> +				RIC_FLUSH_TLB);
> +	}
> +}
>  
>  static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid,
>  				       unsigned long ap)
> @@ -344,6 +407,31 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
>  	asm volatile("eieio; tlbsync; ptesync": : :"memory");
>  }
>  
> +static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
> +				   unsigned long ric)
> +{
> +	asm volatile("ptesync" : : : "memory");
> +
> +	/*
> +	 * Workaround the fact that the "ric" argument to __tlbie_pid
> +	 * must be a compile-time contraint to match the "i" constraint
> +	 * in the asm statement.
> +	 */
> +	switch (ric) {
> +	case RIC_FLUSH_TLB:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> +		fixup_tlbie_pid_lpid(pid, lpid);
> +		break;
> +	case RIC_FLUSH_PWC:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +		break;
> +	case RIC_FLUSH_ALL:
> +	default:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
> +		fixup_tlbie_pid_lpid(pid, lpid);
> +	}
> +	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
> +}
>  struct tlbiel_pid {
>  	unsigned long pid;
>  	unsigned long ric;
> @@ -469,6 +557,20 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end,
>  	fixup_tlbie_va_range(addr - page_size, pid, ap);
>  }
>  
> +static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
> +					 unsigned long pid, unsigned long lpid,
> +					 unsigned long page_size,
> +					 unsigned long psize)
> +{
> +	unsigned long addr;
> +	unsigned long ap = mmu_get_ap(psize);
> +
> +	for (addr = start; addr < end; addr += page_size)
> +		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
> +
> +	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
> +}
> +
>  static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
>  				      unsigned long psize, unsigned long ric)
>  {
> @@ -549,6 +651,18 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
>  	asm volatile("eieio; tlbsync; ptesync": : :"memory");
>  }
>  
> +static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
> +					unsigned long pid, unsigned long lpid,
> +					unsigned long page_size,
> +					unsigned long psize, bool also_pwc)
> +{
> +	asm volatile("ptesync" : : : "memory");
> +	if (also_pwc)
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
> +	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
> +}
> +
>  static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
>  				unsigned long start, unsigned long end,
>  				unsigned long pid, unsigned long page_size,
> @@ -1381,4 +1495,34 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
>  	}
>  }
>  EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
> +
> +/*
> + * Performs process-scoped invalidations for a given LPID
> + * as part of H_RPT_INVALIDATE hcall.
> + */
> +void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid,
> +			     unsigned long type, unsigned long page_size,
> +			     unsigned long psize, unsigned long start,
> +			     unsigned long end)
> +{
> +	/*
> +	 * A H_RPTI_TYPE_ALL request implies RIC=3, hence
> +	 * do a single IS=1 based flush.
> +	 */
> +	if ((type & H_RPTI_TYPE_ALL) == H_RPTI_TYPE_ALL) {
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
> +		return;
> +	}
> +
> +	if (type & H_RPTI_TYPE_PWC)
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +
> +	if (start == 0 && end == -1) /* PID */
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> +	else /* EA */
> +		_tlbie_va_range_lpid(start, end, pid, lpid, page_size,
> +				     psize, false);
> +}
> +EXPORT_SYMBOL_GPL(do_h_rpt_invalidate_prt);
> +
>  #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply

* Re: [PATCH v6 5/6] KVM: PPC: Book3S HV: Add KVM_CAP_PPC_RPT_INVALIDATE capability
From: David Gibson @ 2021-03-23  2:34 UTC (permalink / raw)
  To: Bharata B Rao; +Cc: farosas, aneesh.kumar, npiggin, kvm-ppc, linuxppc-dev
In-Reply-To: <20210311083939.595568-6-bharata@linux.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 2737 bytes --]

On Thu, Mar 11, 2021 at 02:09:38PM +0530, Bharata B Rao wrote:
> Now that we have H_RPT_INVALIDATE fully implemented, enable
> support for the same via KVM_CAP_PPC_RPT_INVALIDATE KVM capability
> 
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  Documentation/virt/kvm/api.rst | 18 ++++++++++++++++++
>  arch/powerpc/kvm/powerpc.c     |  3 +++
>  include/uapi/linux/kvm.h       |  1 +
>  3 files changed, 22 insertions(+)
> 
> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> index 1a2b5210cdbf..d769cef5f904 100644
> --- a/Documentation/virt/kvm/api.rst
> +++ b/Documentation/virt/kvm/api.rst
> @@ -6227,6 +6227,24 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between them.
>  This capability can be used to check / enable 2nd DAWR feature provided
>  by POWER10 processor.
>  
> +7.24 KVM_CAP_PPC_RPT_INVALIDATE
> +------------------------------
> +
> +:Capability: KVM_CAP_PPC_RPT_INVALIDATE
> +:Architectures: ppc
> +:Type: vm
> +
> +This capability indicates that the kernel is capable of handling
> +H_RPT_INVALIDATE hcall.
> +
> +In order to enable the use of H_RPT_INVALIDATE in the guest,
> +user space might have to advertise it for the guest. For example,
> +IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
> +present in the "ibm,hypertas-functions" device-tree property.
> +
> +This capability is enabled for hypervisors on platforms like POWER9
> +that support radix MMU.
> +
>  8. Other capabilities.
>  ======================
>  
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index a2a68a958fa0..be33b5321a76 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -682,6 +682,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  		r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 &&
>  		       !kvmppc_hv_ops->enable_dawr1(NULL));
>  		break;
> +	case KVM_CAP_PPC_RPT_INVALIDATE:
> +		r = 1;
> +		break;
>  #endif
>  	default:
>  		r = 0;
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index f6afee209620..2b2370475cec 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1078,6 +1078,7 @@ struct kvm_ppc_resize_hpt {
>  #define KVM_CAP_DIRTY_LOG_RING 192
>  #define KVM_CAP_X86_BUS_LOCK_EXIT 193
>  #define KVM_CAP_PPC_DAWR1 194
> +#define KVM_CAP_PPC_RPT_INVALIDATE 195
>  
>  #ifdef KVM_CAP_IRQ_ROUTING
>  

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply

* [PATCH 0/4] Rust for Linux for ppc64le
From: Michael Ellerman @ 2021-03-23  3:26 UTC (permalink / raw)
  To: rust-for-linux; +Cc: linuxppc-dev, linux-kernel

Hi all,

Here's a first attempt at getting the kernel Rust support building on powerpc.

It's powerpc64le only for now, as that's what I can easily test given the
distros I have installed. Though powerpc and powerpc64 are also Tier 2 platforms
so in theory should work. Supporting those would require something more
complicated than just pointing rustc at arch/$(ARCH)/rust/target.json.

This is based on 832575d934a2 from the Rust-for-Linux tree. Anything newer gives
me errors about symbol name lengths. I figured I'd send this anyway, as it seems
like those errors are probably not powerpc specific.

I'm not sure that all the values in target.json are correct, or required (or if
any are missing), but what I have there seems to work. Would be happy for
someone to scrutinise it though.

Example output:

  # uname -r
  5.12.0-rc3-47689-ge4e12dd7cb75
  # uname -m
  ppc64le
  # modprobe rust_example
   Rust Example (init)
   Am I built-in? false
   Parameters:
     my_bool:    true
     my_i32:     42
     my_str:     default str val
     my_usize:   42
     my_array:   [0, 1]
   Value: 10
   Value: 10
   Large array has length: 514
   modprobe (1589) used greatest stack depth: 6800 bytes left
  # modprobe rust_example_2
   [2] Rust Example (init)
   [2] Am I built-in? false
   [2] Parameters:
   [2]   my_bool:    true
   [2]   my_i32:     42
   [2]   my_str:     default str val
   [2]   my_usize:   42
   [2]   my_array:   [0, 1]
   Large array has length: 1028
   modprobe (1593) used greatest stack depth: 3680 bytes left
  # modprobe rust_example_3
   [3] Rust Example (init)
   [3] Am I built-in? false
   [3] Parameters:
   [3]   my_bool:    true
   [3]   my_i32:     42
   [3]   my_str:     default str val
   [3]   my_usize:   42
   [3]   my_array:   [0, 1]
   Large array has length: 1028
  # modprobe rust_example_4
   [4] Rust Example (init)
   [4] Am I built-in? false
   [4] Parameters:
   [4]   my_bool:    true
   [4]   my_i32:     42
   [4]   my_str:     default str val
   [4]   my_usize:   42
   [4]   my_array:   [0, 1]
   Large array has length: 1028

cheers


Michael Ellerman (4):
  rust: Export symbols in initialized data section
  rust: Add powerpc64 as a 64-bit target_arch in c_types.rs
  powerpc/rust: Add target.json for ppc64le
  rust: Enable for ppc64le

 arch/powerpc/rust/target.json | 30 ++++++++++++++++++++++++++++++
 init/Kconfig                  |  2 +-
 rust/Makefile                 |  2 +-
 rust/kernel/c_types.rs        |  2 +-
 4 files changed, 33 insertions(+), 3 deletions(-)
 create mode 100644 arch/powerpc/rust/target.json


base-commit: 832575d934a2bc5e2fd0aa881d8e6b64bf062fd2
-- 
2.25.1


^ permalink raw reply

* [PATCH 1/4] rust: Export symbols in initialized data section
From: Michael Ellerman @ 2021-03-23  3:26 UTC (permalink / raw)
  To: rust-for-linux; +Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210323032624.1039422-1-mpe@ellerman.id.au>

On powerpc some symbols end up in the initialized data section, which
means they aren't detected by the logic in cmd_export, leading to errors
such as:

  ERROR: modpost: "_RNvNtCsbDqzXfLQacH_6kernel12module_param15PARAM_OPS_USIZE" [drivers/char/rust_example_4.ko] undefined!

nm represents the "initialized data section" with "D", so also look for
that when exporting symbols.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 rust/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/Makefile b/rust/Makefile
index eb8f12ce1644..4cddae9d4a25 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -73,7 +73,7 @@ $(objtree)/rust/bindings_generated.rs: $(srctree)/rust/kernel/bindings_helper.h
 quiet_cmd_exports = EXPORTS $@
       cmd_exports = \
 	$(NM) -p --defined-only $< \
-		| grep -E ' (T|R) ' | cut -d ' ' -f 3 | grep -E '^(__rust_|_R)' \
+		| grep -E ' (T|R|D) ' | cut -d ' ' -f 3 | grep -E '^(__rust_|_R)' \
 		| xargs -n1 -Isymbol \
 		echo 'EXPORT_SYMBOL$(exports_target_type)(symbol);' > $@
 
-- 
2.25.1


^ permalink raw reply related

* [PATCH 2/4] rust: Add powerpc64 as a 64-bit target_arch in c_types.rs
From: Michael Ellerman @ 2021-03-23  3:26 UTC (permalink / raw)
  To: rust-for-linux; +Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210323032624.1039422-1-mpe@ellerman.id.au>

powerpc kernel code uses int-ll64.h.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 rust/kernel/c_types.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/c_types.rs b/rust/kernel/c_types.rs
index 423ac1108ddb..988fd84b0d66 100644
--- a/rust/kernel/c_types.rs
+++ b/rust/kernel/c_types.rs
@@ -60,7 +60,7 @@ mod c {
     pub type c_size_t = usize;
 }
 
-#[cfg(any(target_arch = "aarch64", target_arch = "x86_64"))]
+#[cfg(any(target_arch = "aarch64", target_arch = "x86_64", target_arch = "powerpc64"))]
 mod c {
     /// C `void` type.
     pub type c_void = core::ffi::c_void;
-- 
2.25.1


^ permalink raw reply related

* [PATCH 3/4] powerpc/rust: Add target.json for ppc64le
From: Michael Ellerman @ 2021-03-23  3:26 UTC (permalink / raw)
  To: rust-for-linux; +Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210323032624.1039422-1-mpe@ellerman.id.au>

Based on the x86 and arm64 versions, as well as output from:

  $ rustc +nightly -Z unstable-options --target=powerpc64le-unknown-linux-gnu --print target-spec-json

Notably disables altivec, vsx and hard-float.

The very cryptic data-layout:

  "data-layout": "e-m:e-i64:64-n32:64-S128",

Has the following meaning:

  e:     little endian
  m:e    ELF name mangling
  i64:64 64-bit integers 64-bit aligned
  n32:64 Native integer widths, 32-bit and 64-bit.
  S128   16-byte stack alignment

Those all come from the rustc output, with the exception of the stack
alignment. We obviously do have 8-bit & 16-bit integer types, but I'm
not sure if there's any need to specify that.

ppc64le only for now. We'll eventually need to come up with some way to
change the target.json that's used based on more than just $(ARCH).

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/rust/target.json | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 arch/powerpc/rust/target.json

diff --git a/arch/powerpc/rust/target.json b/arch/powerpc/rust/target.json
new file mode 100644
index 000000000000..1e53f8308092
--- /dev/null
+++ b/arch/powerpc/rust/target.json
@@ -0,0 +1,30 @@
+{
+  "arch": "powerpc64",
+  "code-mode": "kernel",
+  "cpu": "ppc64le",
+  "data-layout": "e-m:e-i64:64-n32:64",
+  "env": "gnu",
+  "features": "-altivec,-vsx,-hard-float",
+  "function-sections": false,
+  "is-builtin": true,
+  "linker-flavor": "gcc",
+  "linker-is-gnu": true,
+  "llvm-target": "powerpc64le-elf",
+  "max-atomic-width": 64,
+  "os": "none",
+  "panic-strategy": "abort",
+  "position-independent-executables": true,
+  "pre-link-args": {
+    "gcc": [
+      "-Wl,--as-needed",
+      "-Wl,-z,noexecstack",
+      "-m64"
+    ]
+  },
+  "relocation-model": "static",
+  "relro-level": "full",
+  "target-family": "unix",
+  "target-mcount": "_mcount",
+  "target-endian": "little",
+  "target-pointer-width": "64"
+}
-- 
2.25.1


^ permalink raw reply related

* [PATCH 4/4] rust: Enable for ppc64le
From: Michael Ellerman @ 2021-03-23  3:26 UTC (permalink / raw)
  To: rust-for-linux; +Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210323032624.1039422-1-mpe@ellerman.id.au>

All the pieces are in place now for us to enable building rust support
on ppc64le.

Only works with clang for now.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 init/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index d73ac9de186d..ddc2fda1a22c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -58,7 +58,7 @@ config LLD_VERSION
 	default 0
 
 config HAS_RUST
-	depends on ARM64 || X86_64
+	depends on ARM64 || X86_64 || (PPC64 && CPU_LITTLE_ENDIAN && CC_IS_CLANG)
 	def_bool $(success,$(RUSTC) --version)
 
 config RUSTC_VERSION
-- 
2.25.1


^ permalink raw reply related

* Re: [PATCH v6 3/6] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
From: Bharata B Rao @ 2021-03-23  4:05 UTC (permalink / raw)
  To: David Gibson; +Cc: farosas, aneesh.kumar, npiggin, kvm-ppc, linuxppc-dev
In-Reply-To: <YFlR8BROYwX0i0A9@yekko.fritz.box>

On Tue, Mar 23, 2021 at 01:26:56PM +1100, David Gibson wrote:
> On Thu, Mar 11, 2021 at 02:09:36PM +0530, Bharata B Rao wrote:
> > H_RPT_INVALIDATE does two types of TLB invalidations:
> > 
> > 1. Process-scoped invalidations for guests when LPCR[GTSE]=0.
> >    This is currently not used in KVM as GTSE is not usually
> >    disabled in KVM.
> > 2. Partition-scoped invalidations that an L1 hypervisor does on
> >    behalf of an L2 guest. This is currently handled
> >    by H_TLB_INVALIDATE hcall and this new replaces the old that.
> > 
> > This commit enables process-scoped invalidations for L1 guests.
> > Support for process-scoped and partition-scoped invalidations
> > from/for nested guests will be added separately.
> > 
> > Process scoped tlbie invalidations from L1 and nested guests
> > need RS register for TLBIE instruction to contain both PID and
> > LPID.  This patch introduces primitives that execute tlbie
> > instruction with both PID and LPID set in prepartion for
> > H_RPT_INVALIDATE hcall.
> > 
> > A description of H_RPT_INVALIDATE follows:
> > 
> > int64   /* H_Success: Return code on successful completion */
> >         /* H_Busy - repeat the call with the same */
> >         /* H_Parameter, H_P2, H_P3, H_P4, H_P5 : Invalid
> > 	   parameters */
> > hcall(const uint64 H_RPT_INVALIDATE, /* Invalidate RPT
> > 					translation
> > 					lookaside information */
> >       uint64 id,        /* PID/LPID to invalidate */
> >       uint64 target,    /* Invalidation target */
> >       uint64 type,      /* Type of lookaside information */
> >       uint64 pg_sizes,  /* Page sizes */
> >       uint64 start,     /* Start of Effective Address (EA)
> > 			   range (inclusive) */
> >       uint64 end)       /* End of EA range (exclusive) */
> > 
> > Invalidation targets (target)
> > -----------------------------
> > Core MMU        0x01 /* All virtual processors in the
> > 			partition */
> > Core local MMU  0x02 /* Current virtual processor */
> > Nest MMU        0x04 /* All nest/accelerator agents
> > 			in use by the partition */
> > 
> > A combination of the above can be specified,
> > except core and core local.
> > 
> > Type of translation to invalidate (type)
> > ---------------------------------------
> > NESTED       0x0001  /* invalidate nested guest partition-scope */
> > TLB          0x0002  /* Invalidate TLB */
> > PWC          0x0004  /* Invalidate Page Walk Cache */
> > PRT          0x0008  /* Invalidate caching of Process Table
> > 			Entries if NESTED is clear */
> > PAT          0x0008  /* Invalidate caching of Partition Table
> > 			Entries if NESTED is set */
> > 
> > A combination of the above can be specified.
> > 
> > Page size mask (pages)
> > ----------------------
> > 4K              0x01
> > 64K             0x02
> > 2M              0x04
> > 1G              0x08
> > All sizes       (-1UL)
> > 
> > A combination of the above can be specified.
> > All page sizes can be selected with -1.
> > 
> > Semantics: Invalidate radix tree lookaside information
> >            matching the parameters given.
> > * Return H_P2, H_P3 or H_P4 if target, type, or pageSizes parameters
> >   are different from the defined values.
> > * Return H_PARAMETER if NESTED is set and pid is not a valid nested
> >   LPID allocated to this partition
> > * Return H_P5 if (start, end) doesn't form a valid range. Start and
> >   end should be a valid Quadrant address and  end > start.
> > * Return H_NotSupported if the partition is not in running in radix
> >   translation mode.
> > * May invalidate more translation information than requested.
> > * If start = 0 and end = -1, set the range to cover all valid
> >   addresses. Else start and end should be aligned to 4kB (lower 11
> >   bits clear).
> > * If NESTED is clear, then invalidate process scoped lookaside
> >   information. Else pid specifies a nested LPID, and the invalidation
> >   is performed   on nested guest partition table and nested guest
> >   partition scope real addresses.
> > * If pid = 0 and NESTED is clear, then valid addresses are quadrant 3
> >   and quadrant 0 spaces, Else valid addresses are quadrant 0.
> > * Pages which are fully covered by the range are to be invalidated.
> >   Those which are partially covered are considered outside
> >   invalidation range, which allows a caller to optimally invalidate
> >   ranges that may   contain mixed page sizes.
> > * Return H_SUCCESS on success.
> > 
> > Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> 
> Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
> 
> with the exception of one nit noted below.
> 
> > ---
> >  .../include/asm/book3s/64/tlbflush-radix.h    |   4 +
> >  arch/powerpc/include/asm/mmu_context.h        |  11 ++
> >  arch/powerpc/kvm/book3s_hv.c                  |  46 ++++++
> >  arch/powerpc/mm/book3s64/radix_tlb.c          | 152 +++++++++++++++++-
> >  4 files changed, 209 insertions(+), 4 deletions(-)
> > 
> > diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > index 8b33601cdb9d..a46fd37ad552 100644
> > --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > @@ -4,6 +4,10 @@
> >  
> >  #include <asm/hvcall.h>
> >  
> > +#define RIC_FLUSH_TLB 0
> > +#define RIC_FLUSH_PWC 1
> > +#define RIC_FLUSH_ALL 2
> 
> Is there a reason for moving these?  You don't appear to be adding a
> use of them outside the .c file they were in before.

They are used in arch/powerpc/kvm/book3s_hv_nested.c. It was all in the
same patchset earlier, but during reorgazing the hcall into 3 separate patches,
this change remained here. May be I should move this change to the next patch
where it is used.

Thanks for your review.

Regards,
Bharata.

^ permalink raw reply

* [PATCH] arch/powerpc/kernel: Duplicate include asm/interrupt.h
From: zhouchuangao @ 2021-03-23  1:57 UTC (permalink / raw)
  To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
	Nicholas Piggin, Christophe Leroy, Michal Suchanek,
	Aneesh Kumar K.V, linuxppc-dev, linux-kernel
  Cc: zhouchuangao

asm/interrupt.h is repeatedly in the file interrupt.c.

Signed-off-by: zhouchuangao <zhouchuangao@vivo.com>
---
 arch/powerpc/kernel/interrupt.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index c475a22..6deaccc 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -9,7 +9,6 @@
 #include <asm/cputime.h>
 #include <asm/interrupt.h>
 #include <asm/hw_irq.h>
-#include <asm/interrupt.h>
 #include <asm/kprobes.h>
 #include <asm/paca.h>
 #include <asm/ptrace.h>
-- 
2.7.4


^ permalink raw reply related

* [PATCH] arch: powerpc: bug.h is included twice
From: Wan Jiabing @ 2021-03-23  2:23 UTC (permalink / raw)
  To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
	Aneesh Kumar K.V, Nicholas Piggin, Cédric Le Goater,
	Wan Jiabing, Ganesh Goudar, Randy Dunlap, linuxppc-dev,
	linux-kernel
  Cc: kael_w

asm/bug.h has been included at line 12, so remove 
the duplicate one at line 21.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
---
 arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index f911bdb68d8b..3004f3323144 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -18,7 +18,6 @@
  * complete pgtable.h but only a portion of it.
  */
 #include <asm/book3s/64/pgtable.h>
-#include <asm/bug.h>
 #include <asm/task_size_64.h>
 #include <asm/cpu_has_feature.h>
 
-- 
2.25.1


^ permalink raw reply related

* [PATCH] arch: powerpc: Remove duplicate include of interrupt.h
From: Wan Jiabing @ 2021-03-23  2:41 UTC (permalink / raw)
  To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
	Nicholas Piggin, Christophe Leroy, Michal Suchanek,
	Aneesh Kumar K.V, linuxppc-dev, linux-kernel
  Cc: kael_w, Wan Jiabing

asm/interrupt.h has been included at line 12. According to 
alphabetic order,we remove the duplicate one at line 10.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
---
 arch/powerpc/kernel/interrupt.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index c475a229a42a..11d456896772 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -7,7 +7,6 @@
 #include <asm/asm-prototypes.h>
 #include <asm/kup.h>
 #include <asm/cputime.h>
-#include <asm/interrupt.h>
 #include <asm/hw_irq.h>
 #include <asm/interrupt.h>
 #include <asm/kprobes.h>
-- 
2.25.1


^ permalink raw reply related

* [PATCH] arch: powerpc: Remove duplicate include of clock.h
From: Wan Jiabing @ 2021-03-23  3:04 UTC (permalink / raw)
  To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
	Nicholas Piggin, Christophe Leroy, Peter Zijlstra, Stephen Boyd,
	Pingfan Liu, Frederic Weisbecker, linuxppc-dev, linux-kernel
  Cc: kael_w, Wan Jiabing

linux/sched/clock.h has been included at line 33.
So we remove the duplicate one at line 56. For better 
understanding, we also move sched/cputime.h under the 
sched including segment.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
---
 arch/powerpc/kernel/time.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index b67d93a609a2..e2766e0e2a3a 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -31,6 +31,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/cputime.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
@@ -52,8 +53,6 @@
 #include <linux/irq_work.h>
 #include <linux/of_clk.h>
 #include <linux/suspend.h>
-#include <linux/sched/cputime.h>
-#include <linux/sched/clock.h>
 #include <linux/processor.h>
 #include <asm/trace.h>
 
-- 
2.25.1


^ permalink raw reply related

* [PATCH] tools: testing: Remove duplicate include of sched.h
From: Wan Jiabing @ 2021-03-23  3:34 UTC (permalink / raw)
  To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
	Shuah Khan, Wan Jiabing, linuxppc-dev, linux-kselftest,
	linux-kernel
  Cc: kael_w

sched.h has been included at line 33.
So we remove the duplicate one at line 36.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
---
 tools/testing/selftests/powerpc/mm/tlbie_test.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/powerpc/mm/tlbie_test.c b/tools/testing/selftests/powerpc/mm/tlbie_test.c
index f85a0938ab25..48344a74b212 100644
--- a/tools/testing/selftests/powerpc/mm/tlbie_test.c
+++ b/tools/testing/selftests/powerpc/mm/tlbie_test.c
@@ -33,7 +33,6 @@
 #include <sched.h>
 #include <time.h>
 #include <stdarg.h>
-#include <sched.h>
 #include <pthread.h>
 #include <signal.h>
 #include <sys/prctl.h>
-- 
2.25.1


^ permalink raw reply related

* [PATCH] tools: testing: pthread.h is included twice
From: Wan Jiabing @ 2021-03-23  3:39 UTC (permalink / raw)
  To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
	Shuah Khan, Wan Jiabing, linuxppc-dev, linux-kselftest,
	linux-kernel
  Cc: kael_w

pthread.h has been included at line 17.
So we remove the duplicate one at line 20.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
---
 tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c
index e2a0c07e8362..9ef37a9836ac 100644
--- a/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c
+++ b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c
@@ -17,7 +17,6 @@
 #include <pthread.h>
 #include <sys/mman.h>
 #include <unistd.h>
-#include <pthread.h>
 
 #include "tm.h"
 #include "utils.h"
-- 
2.25.1


^ permalink raw reply related

* [PATCH] tools: testing: inttypes.h is included twice
From: Wan Jiabing @ 2021-03-23  3:43 UTC (permalink / raw)
  To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
	Shuah Khan, Wan Jiabing, linuxppc-dev, linux-kselftest,
	linux-kernel
  Cc: kael_w

inttypes.h has been included at line 19.
So we remove the duplicate one at line 23.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
---
 tools/testing/selftests/powerpc/tm/tm-poison.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/powerpc/tm/tm-poison.c b/tools/testing/selftests/powerpc/tm/tm-poison.c
index 29e5f26af7b9..27c083a03d1f 100644
--- a/tools/testing/selftests/powerpc/tm/tm-poison.c
+++ b/tools/testing/selftests/powerpc/tm/tm-poison.c
@@ -20,7 +20,6 @@
 #include <sched.h>
 #include <sys/types.h>
 #include <signal.h>
-#include <inttypes.h>
 
 #include "tm.h"
 
-- 
2.25.1


^ permalink raw reply related

* Re: [PATCH] arch: powerpc: Remove duplicate include of interrupt.h
From: Christophe Leroy @ 2021-03-23  5:41 UTC (permalink / raw)
  To: Wan Jiabing, zhouchuangao
  Cc: linux-kernel, Nicholas Piggin, Paul Mackerras, Aneesh Kumar K.V,
	kael_w, Michal Suchanek, linuxppc-dev, Qiang Zhao
In-Reply-To: <20210323024126.237840-1-wanjiabing@vivo.com>



Le 23/03/2021 à 03:41, Wan Jiabing a écrit :
> asm/interrupt.h has been included at line 12. According to
> alphabetic order,we remove the duplicate one at line 10.

Could you please cook a single patch for all files in arch/powerpc/

Thanks
Christophe

> 
> Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
> ---
>   arch/powerpc/kernel/interrupt.c | 1 -
>   1 file changed, 1 deletion(-)
> 
> diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
> index c475a229a42a..11d456896772 100644
> --- a/arch/powerpc/kernel/interrupt.c
> +++ b/arch/powerpc/kernel/interrupt.c
> @@ -7,7 +7,6 @@
>   #include <asm/asm-prototypes.h>
>   #include <asm/kup.h>
>   #include <asm/cputime.h>
> -#include <asm/interrupt.h>
>   #include <asm/hw_irq.h>
>   #include <asm/interrupt.h>
>   #include <asm/kprobes.h>
> 

^ permalink raw reply


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox