linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Christophe Leroy <christophe.leroy@c-s.fr>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Paul Mackerras <paulus@samba.org>,
	Michael Ellerman <mpe@ellerman.id.au>
Cc: linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Subject: [PATCH v9 17/20] powerpc/8xx: Enable 512k hugepage support with HW assistance
Date: Thu, 29 Nov 2018 14:07:19 +0000 (UTC)	[thread overview]
Message-ID: <7f705dc6b125f0f8147258a97fe6a61277702db4.1543499865.git.christophe.leroy@c-s.fr> (raw)
In-Reply-To: <cover.1543499860.git.christophe.leroy@c-s.fr>

For using 512k pages with hardware assistance, the PTEs have to be spread
every 128 bytes in the L2 table.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
 arch/powerpc/include/asm/hugetlb.h |  4 +++-
 arch/powerpc/mm/hugetlbpage.c      | 10 +++++++++-
 arch/powerpc/mm/tlb_nohash.c       |  3 +++
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index dfb8bf236586..62a0ca02ca7d 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -74,7 +74,9 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
 	unsigned long idx = 0;
 
 	pte_t *dir = hugepd_page(hpd);
-#ifndef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC_8xx
+	idx = (addr & ((1UL << pdshift) - 1)) >> PAGE_SHIFT;
+#elif !defined(CONFIG_PPC_FSL_BOOK3E)
 	idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
 #endif
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index bc97874d7c74..5b236621d302 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -65,6 +65,9 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	if (pshift >= pdshift) {
 		cachep = PGT_CACHE(PTE_T_ORDER);
 		num_hugepd = 1 << (pshift - pdshift);
+	} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
+		cachep = PGT_CACHE(PTE_INDEX_SIZE);
+		num_hugepd = 1;
 	} else {
 		cachep = PGT_CACHE(pdshift - pshift);
 		num_hugepd = 1;
@@ -331,6 +334,9 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 
 	if (shift >= pdshift)
 		hugepd_free(tlb, hugepte);
+	else if (IS_ENABLED(CONFIG_PPC_8xx))
+		pgtable_free_tlb(tlb, hugepte,
+				 get_hugepd_cache_index(PTE_INDEX_SIZE));
 	else
 		pgtable_free_tlb(tlb, hugepte,
 				 get_hugepd_cache_index(pdshift - shift));
@@ -700,7 +706,9 @@ static int __init hugetlbpage_init(void)
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.
 		 */
-		if (pdshift > shift)
+		if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx))
+			pgtable_cache_add(PTE_INDEX_SIZE);
+		else if (pdshift > shift)
 			pgtable_cache_add(pdshift - shift);
 #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 		else
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 8ad7aab150b7..ae5d568e267f 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -97,6 +97,9 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 		.shift	= 14,
 	},
 #endif
+	[MMU_PAGE_512K] = {
+		.shift	= 19,
+	},
 	[MMU_PAGE_8M] = {
 		.shift	= 23,
 	},
-- 
2.13.3


  parent reply	other threads:[~2018-11-29 14:07 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-29 14:06 [PATCH v9 00/20] Implement use of HW assistance on TLB table walk on 8xx Christophe Leroy
2018-11-29 14:06 ` [PATCH v9 01/20] powerpc/book3s32: Remove CONFIG_BOOKE dependent code Christophe Leroy
2018-12-07 13:06   ` [v9,01/20] " Michael Ellerman
2018-11-29 14:06 ` [PATCH v9 02/20] powerpc/8xx: Remove PTE_ATOMIC_UPDATES Christophe Leroy
2018-11-29 14:06 ` [PATCH v9 03/20] powerpc/mm: Move pte_fragment_alloc() to a common location Christophe Leroy
2018-11-29 14:06 ` [PATCH v9 04/20] powerpc/mm: Avoid useless lock with single page fragments Christophe Leroy
2018-11-29 14:06 ` [PATCH v9 05/20] powerpc/mm: move platform specific mmu-xxx.h in platform directories Christophe Leroy
2018-11-29 14:06 ` [PATCH v9 06/20] powerpc/mm: Move pgtable_t into platform headers Christophe Leroy
2018-11-29 14:06 ` [PATCH v9 07/20] powerpc/mm: add helpers to get/set mm.context->pte_frag Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 08/20] powerpc/mm: Extend pte_fragment functionality to PPC32 Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 09/20] powerpc/mm: enable the use of page table cache of order 0 Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 10/20] powerpc/mm: replace hugetlb_cache by PGT_CACHE(PTE_T_ORDER) Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 11/20] powerpc/mm: fix a warning when a cache is common to PGD and hugepages Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 12/20] powerpc/mm: remove unnecessary test in pgtable_cache_init() Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 13/20] powerpc/8xx: Move SW perf counters in first 32kb of memory Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 14/20] powerpc/8xx: Temporarily disable 16k pages and hugepages Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 15/20] powerpc/8xx: Use hardware assistance in TLB handlers Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 16/20] powerpc/8xx: Enable 8M hugepage support with HW assistance Christophe Leroy
2018-11-29 14:07 ` Christophe Leroy [this message]
2018-11-29 14:07 ` [PATCH v9 18/20] powerpc/8xx: reintroduce 16K pages " Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 19/20] powerpc/8xx: don't use r12/SPRN_SPRG_SCRATCH2 in TLB Miss handlers Christophe Leroy
2018-11-29 14:07 ` [PATCH v9 20/20] powerpc/8xx: regroup TLB handler routines Christophe Leroy

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=7f705dc6b125f0f8147258a97fe6a61277702db4.1543499865.git.christophe.leroy@c-s.fr \
    --to=christophe.leroy@c-s.fr \
    --cc=benh@kernel.crashing.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=paulus@samba.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).