diff mbox series

[v2] powerpc/mm: Update tlbiel loop on POWER10

Message ID 20201007053305.232879-1-aneesh.kumar@linux.ibm.com (mailing list archive)
State Accepted
Commit e80639405c40127727812a0e1f8a65ba9979f146
Headers show
Series [v2] powerpc/mm: Update tlbiel loop on POWER10 | expand

Checks

Context Check Description
snowpatch_ozlabs/apply_patch success Successfully applied on branch powerpc/merge (d1def5df359f3f1882cc29d8baa5cd2a4861a6c6)
snowpatch_ozlabs/build-ppc64le warning Upstream build failed, couldn't test patch
snowpatch_ozlabs/build-ppc64be warning Upstream build failed, couldn't test patch
snowpatch_ozlabs/build-ppc64e warning Upstream build failed, couldn't test patch
snowpatch_ozlabs/build-pmac32 warning Upstream build failed, couldn't test patch
snowpatch_ozlabs/checkpatch warning total: 0 errors, 0 warnings, 1 checks, 79 lines checked
snowpatch_ozlabs/needsstable success Patch has no Fixes tags

Commit Message

Aneesh Kumar K V Oct. 7, 2020, 5:33 a.m. UTC 
With POWER10, single tlbiel instruction invalidates all the congruence
class of the TLB and hence we need to issue only one tlbiel with SET=0.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/kvm/book3s_hv.c         |  7 ++++++-
 arch/powerpc/kvm/book3s_hv_builtin.c | 11 ++++++++++-
 arch/powerpc/mm/book3s64/radix_tlb.c | 23 ++++++++++++++++-------
 3 files changed, 32 insertions(+), 9 deletions(-)

Comments

Michael Ellerman Nov. 25, 2020, 11:57 a.m. UTC | #1 
On Wed, 7 Oct 2020 11:03:05 +0530, Aneesh Kumar K.V wrote:
> With POWER10, single tlbiel instruction invalidates all the congruence
> class of the TLB and hence we need to issue only one tlbiel with SET=0.

Applied to powerpc/next.

[1/1] powerpc/mm: Update tlbiel loop on POWER10
      https://git.kernel.org/powerpc/c/e80639405c40127727812a0e1f8a65ba9979f146

cheers
diff mbox series

Patch

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3bd3118c7633..00b5c5981db5 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4939,7 +4939,12 @@  static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	 * Work out how many sets the TLB has, for the use of
 	 * the TLB invalidation loop in book3s_hv_rmhandlers.S.
 	 */
-	if (radix_enabled())
+	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+		/*
+		 * P10 will flush all the congruence class with a single tlbiel
+		 */
+		kvm->arch.tlb_sets = 1;
+	} else if (radix_enabled())
 		kvm->arch.tlb_sets = POWER9_TLB_SETS_RADIX;	/* 128 */
 	else if (cpu_has_feature(CPU_FTR_ARCH_300))
 		kvm->arch.tlb_sets = POWER9_TLB_SETS_HASH;	/* 256 */
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 073617ce83e0..2803a4b01109 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -702,6 +702,7 @@  static void wait_for_sync(struct kvm_split_mode *sip, int phase)
 
 void kvmhv_p9_set_lpcr(struct kvm_split_mode *sip)
 {
+	int num_sets;
 	unsigned long rb, set;
 
 	/* wait for every other thread to get to real mode */
@@ -712,11 +713,19 @@  void kvmhv_p9_set_lpcr(struct kvm_split_mode *sip)
 	mtspr(SPRN_LPID, sip->lpidr_req);
 	isync();
 
+	/*
+	 * P10 will flush all the congruence class with a single tlbiel
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		num_sets =  1;
+	else
+		num_sets = POWER9_TLB_SETS_RADIX;
+
 	/* Invalidate the TLB on thread 0 */
 	if (local_paca->kvm_hstate.tid == 0) {
 		sip->do_set = 0;
 		asm volatile("ptesync" : : : "memory");
-		for (set = 0; set < POWER9_TLB_SETS_RADIX; ++set) {
+		for (set = 0; set < num_sets; ++set) {
 			rb = TLBIEL_INVAL_SET_LPID +
 				(set << TLBIEL_INVAL_SET_SHIFT);
 			asm volatile(PPC_TLBIEL(%0, %1, 0, 0, 0) : :
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 143b4fd396f0..9e76ba766b3c 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -56,14 +56,21 @@  static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
 	if (early_cpu_has_feature(CPU_FTR_HVMODE)) {
 		/* MSR[HV] should flush partition scope translations first. */
 		tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
-		for (set = 1; set < num_sets; set++)
-			tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
+
+		if (!early_cpu_has_feature(CPU_FTR_ARCH_31)) {
+			for (set = 1; set < num_sets; set++)
+				tlbiel_radix_set_isa300(set, is, 0,
+							RIC_FLUSH_TLB, 0);
+		}
 	}
 
 	/* Flush process scoped entries. */
 	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 1);
-	for (set = 1; set < num_sets; set++)
-		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);
+
+	if (!early_cpu_has_feature(CPU_FTR_ARCH_31)) {
+		for (set = 1; set < num_sets; set++)
+			tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);
+	}
 
 	asm volatile("ptesync": : :"memory");
 }
@@ -300,9 +307,11 @@  static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 		return;
 	}
 
-	/* For the remaining sets, just flush the TLB */
-	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
-		__tlbiel_pid(pid, set, RIC_FLUSH_TLB);
+	if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+		/* For the remaining sets, just flush the TLB */
+		for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
+			__tlbiel_pid(pid, set, RIC_FLUSH_TLB);
+	}
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_RADIX_INVALIDATE_ERAT_USER "; isync" : : :"memory");