powerpc/mm: handle hugepage size correctly when invalidating hpte entries

If a hash bucket gets full, we "evict" a more/less random entry from it.
When we do that we don't invalidate the TLB (hpte_remove) because we assume
the old translation is still technically "valid". This implies that when
we are invalidating or updating pte, even if HPTE entry is not valid
we should do a tlb invalidate. With hugepages, we need to pass the correct
actual page size value for tlb invalidation.

This change update the patch 0608d692463598c1d6e826d9dd7283381b4f246c
"powerpc/mm: Always invalidate tlb on hpte invalidate and update" to handle
transparent hugepages correctly.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/include/asm/machdep.h

@@ -36,13 +36,13 @@ struct machdep_calls {
 #ifdef CONFIG_PPC64
 	void            (*hpte_invalidate)(unsigned long slot,
 					   unsigned long vpn,
-					   int psize, int ssize,
-					   int local);
+					   int bpsize, int apsize,
+					   int ssize, int local);
 	long		(*hpte_updatepp)(unsigned long slot, 
 					 unsigned long newpp, 
 					 unsigned long vpn,
-					 int psize, int ssize,
-					 int local);
+					 int bpsize, int apsize,
+					 int ssize, int local);
 	void            (*hpte_updateboltedpp)(unsigned long newpp, 
 					       unsigned long ea,
 					       int psize, int ssize);

arch/powerpc/kvm/book3s_64_mmu_host.c

@@ -34,7 +34,7 @@
 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	ppc_md.hpte_invalidate(pte->slot, pte->host_vpn,
-			       MMU_PAGE_4K, MMU_SEGSIZE_256M,
+			       MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M,
 			       false);
 }
 

arch/powerpc/mm/hash_low_64.S

@@ -289,9 +289,10 @@ htab_modify_pte:
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_4K		/* page size */
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_4K		/* base page size */
+	li	r7,MMU_PAGE_4K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(htab_call_hpte_updatepp)
 	bl	.			/* Patched by htab_finish_init() */
 
@@ -649,9 +650,10 @@ htab_modify_pte:
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_4K		/* page size */
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_4K		/* base page size */
+	li	r7,MMU_PAGE_4K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(htab_call_hpte_updatepp)
 	bl	.			/* patched by htab_finish_init() */
 
@@ -937,9 +939,10 @@ ht64_modify_pte:
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_64K
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_64K		/* base page size */
+	li	r7,MMU_PAGE_64K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(ht64_call_hpte_updatepp)
 	bl	.			/* patched by htab_finish_init() */
 

arch/powerpc/mm/hash_native_64.c

@@ -273,61 +273,15 @@ static long native_hpte_remove(unsigned long hpte_group)
 	return i;
 }
 
-static inline int __hpte_actual_psize(unsigned int lp, int psize)
-{
-	int i, shift;
-	unsigned int mask;
-
-	/* start from 1 ignoring MMU_PAGE_4K */
-	for (i = 1; i < MMU_PAGE_COUNT; i++) {
-
-		/* invalid penc */
-		if (mmu_psize_defs[psize].penc[i] == -1)
-			continue;
-		/*
-		 * encoding bits per actual page size
-		 *        PTE LP     actual page size
-		 *    rrrr rrrz		>=8KB
-		 *    rrrr rrzz		>=16KB
-		 *    rrrr rzzz		>=32KB
-		 *    rrrr zzzz		>=64KB
-		 * .......
-		 */
-		shift = mmu_psize_defs[i].shift - LP_SHIFT;
-		if (shift > LP_BITS)
-			shift = LP_BITS;
-		mask = (1 << shift) - 1;
-		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
-			return i;
-	}
-	return -1;
-}
-
-static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
-{
-	/* Look at the 8 bit LP value */
-	unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
-
-	if (!(hptep->v & HPTE_V_VALID))
-		return -1;
-
-	/* First check if it is large page */
-	if (!(hptep->v & HPTE_V_LARGE))
-		return MMU_PAGE_4K;
-
-	return __hpte_actual_psize(lp, psize);
-}
-
 static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
-				 unsigned long vpn, int psize, int ssize,
-				 int local)
+				 unsigned long vpn, int bpsize,
+				 int apsize, int ssize, int local)
 {
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
 	int ret = 0;
-	int actual_psize;
 
-	want_v = hpte_encode_avpn(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 
 	DBG_LOW("    update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
 		vpn, want_v & HPTE_V_AVPN, slot, newpp);
@@ -335,7 +289,6 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	native_lock_hpte(hptep);
 
 	hpte_v = hptep->v;
-	actual_psize = hpte_actual_psize(hptep, psize);
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
 	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
@@ -343,12 +296,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	 * (hpte_remove) because we assume the old translation is still
 	 * technically "valid".
 	 */
-	if (actual_psize < 0) {
-		actual_psize = psize;
-		ret = -1;
-		goto err_out;
-	}
-	if (!HPTE_V_COMPARE(hpte_v, want_v)) {
+	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
 		DBG_LOW(" -> miss\n");
 		ret = -1;
 	} else {
@@ -357,11 +305,10 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 			(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C));
 	}
-err_out:
 	native_unlock_hpte(hptep);
 
 	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, actual_psize, ssize, local);
+	tlbie(vpn, bpsize, apsize, ssize, local);
 
 	return ret;
 }
@@ -402,7 +349,6 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
 static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 				       int psize, int ssize)
 {
-	int actual_psize;
 	unsigned long vpn;
 	unsigned long vsid;
 	long slot;
@@ -415,36 +361,33 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	if (slot == -1)
 		panic("could not find page to bolt\n");
 	hptep = htab_address + slot;
-	actual_psize = hpte_actual_psize(hptep, psize);
-	if (actual_psize < 0)
-		actual_psize = psize;
 
 	/* Update the HPTE */
 	hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 		(newpp & (HPTE_R_PP | HPTE_R_N));
-
-	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, actual_psize, ssize, 0);
+	/*
+	 * Ensure it is out of the tlb too. Bolted entries base and
+	 * actual page size will be same.
+	 */
+	tlbie(vpn, psize, psize, ssize, 0);
 }
 
 static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
-				   int psize, int ssize, int local)
+				   int bpsize, int apsize, int ssize, int local)
 {
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v;
 	unsigned long want_v;
 	unsigned long flags;
-	int actual_psize;
 
 	local_irq_save(flags);
 
 	DBG_LOW("    invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
 
-	want_v = hpte_encode_avpn(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 	native_lock_hpte(hptep);
 	hpte_v = hptep->v;
 
-	actual_psize = hpte_actual_psize(hptep, psize);
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
 	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
@@ -452,23 +395,48 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	 * (hpte_remove) because we assume the old translation is still
 	 * technically "valid".
 	 */
-	if (actual_psize < 0) {
-		actual_psize = psize;
-		native_unlock_hpte(hptep);
-		goto err_out;
-	}
-	if (!HPTE_V_COMPARE(hpte_v, want_v))
+	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
 		native_unlock_hpte(hptep);
 	else
 		/* Invalidate the hpte. NOTE: this also unlocks it */
 		hptep->v = 0;
 
-err_out:
 	/* Invalidate the TLB */
-	tlbie(vpn, psize, actual_psize, ssize, local);
+	tlbie(vpn, bpsize, apsize, ssize, local);
+
 	local_irq_restore(flags);
 }
 
+static inline int __hpte_actual_psize(unsigned int lp, int psize)
+{
+	int i, shift;
+	unsigned int mask;
+
+	/* start from 1 ignoring MMU_PAGE_4K */
+	for (i = 1; i < MMU_PAGE_COUNT; i++) {
+
+		/* invalid penc */
+		if (mmu_psize_defs[psize].penc[i] == -1)
+			continue;
+		/*
+		 * encoding bits per actual page size
+		 *        PTE LP     actual page size
+		 *    rrrr rrrz		>=8KB
+		 *    rrrr rrzz		>=16KB
+		 *    rrrr rzzz		>=32KB
+		 *    rrrr zzzz		>=64KB
+		 * .......
+		 */
+		shift = mmu_psize_defs[i].shift - LP_SHIFT;
+		if (shift > LP_BITS)
+			shift = LP_BITS;
+		mask = (1 << shift) - 1;
+		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
+			return i;
+	}
+	return -1;
+}
+
 static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			int *psize, int *apsize, int *ssize, unsigned long *vpn)
 {

arch/powerpc/mm/hash_utils_64.c

@@ -1232,7 +1232,11 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
 		DBG_LOW(" sub %ld: hash=%lx, hidx=%lx\n", index, slot, hidx);
-		ppc_md.hpte_invalidate(slot, vpn, psize, ssize, local);
+		/*
+		 * We use same base page size and actual psize, because we don't
+		 * use these functions for hugepage
+		 */
+		ppc_md.hpte_invalidate(slot, vpn, psize, psize, ssize, local);
 	} pte_iterate_hashed_end();
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1365,7 +1369,8 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 		hash = ~hash;
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 	slot += hidx & _PTEIDX_GROUP_IX;
-	ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_kernel_ssize, 0);
+	ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_linear_psize,
+			       mmu_kernel_ssize, 0);
 }
 
 void kernel_map_pages(struct page *page, int numpages, int enable)

arch/powerpc/mm/hugetlbpage-hash64.c

@@ -81,7 +81,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot += (old_pte & _PAGE_F_GIX) >> 12;
 
 		if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
-					 ssize, local) == -1)
+					 mmu_psize, ssize, local) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 

arch/powerpc/platforms/cell/beat_htab.c

@@ -185,7 +185,8 @@ static void beat_lpar_hptab_clear(void)
 static long beat_lpar_hpte_updatepp(unsigned long slot,
 				    unsigned long newpp,
 				    unsigned long vpn,
-				    int psize, int ssize, int local)
+				    int psize, int apsize,
+				    int ssize, int local)
 {
 	unsigned long lpar_rc;
 	u64 dummy0, dummy1;
@@ -274,7 +275,8 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
 }
 
 static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+				      int psize, int apsize,
+				      int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
@@ -364,9 +366,10 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
  * already zero.  For now I am paranoid.
  */
 static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
-				    unsigned long newpp,
-				    unsigned long vpn,
-				    int psize, int ssize, int local)
+				       unsigned long newpp,
+				       unsigned long vpn,
+				       int psize, int apsize,
+				       int ssize, int local)
 {
 	unsigned long lpar_rc;
 	unsigned long want_v;
@@ -394,7 +397,8 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
 }
 
 static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+					 int psize, int apsize,
+					 int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;

arch/powerpc/platforms/ps3/htab.c

@@ -109,7 +109,8 @@ static long ps3_hpte_remove(unsigned long hpte_group)
 }
 
 static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
-	unsigned long vpn, int psize, int ssize, int local)
+			      unsigned long vpn, int psize, int apsize,
+			      int ssize, int local)
 {
 	int result;
 	u64 hpte_v, want_v, hpte_rs;
@@ -162,7 +163,7 @@ static void ps3_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 }
 
 static void ps3_hpte_invalidate(unsigned long slot, unsigned long vpn,
-	int psize, int ssize, int local)
+				int psize, int apsize, int ssize, int local)
 {
 	unsigned long flags;
 	int result;

arch/powerpc/platforms/pseries/lpar.c

@@ -240,7 +240,8 @@ static void pSeries_lpar_hptab_clear(void)
 static long pSeries_lpar_hpte_updatepp(unsigned long slot,
 				       unsigned long newpp,
 				       unsigned long vpn,
-				       int psize, int ssize, int local)
+				       int psize, int apsize,
+				       int ssize, int local)
 {
 	unsigned long lpar_rc;
 	unsigned long flags = (newpp & 7) | H_AVPN;
@@ -328,7 +329,8 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
 }
 
 static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+					 int psize, int apsize,
+					 int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
@@ -356,8 +358,10 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea,
 
 	slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
 	BUG_ON(slot == -1);
-
-	pSeries_lpar_hpte_invalidate(slot, vpn, psize, ssize, 0);
+	/*
+	 * lpar doesn't use the passed actual page size
+	 */
+	pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0);
 }
 
 /* Flag bits for H_BULK_REMOVE */
@@ -400,8 +404,11 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 			slot += hidx & _PTEIDX_GROUP_IX;
 			if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+				/*
+				 * lpar doesn't use the passed actual page size
+				 */
 				pSeries_lpar_hpte_invalidate(slot, vpn, psize,
-							     ssize, local);
+							     0, ssize, local);
 			} else {
 				param[pix] = HBR_REQUEST | HBR_AVPN | slot;
 				param[pix+1] = hpte_encode_avpn(vpn, psize,