From: Ryan Roberts <ryan.roberts@arm.com>
To: Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Ard Biesheuvel <ardb@kernel.org>,
David Hildenbrand <david@redhat.com>,
Donald Dutile <ddutile@redhat.com>,
Eric Chanudet <echanude@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org,
Itaru Kitayama <itaru.kitayama@fujitsu.com>
Subject: [PATCH v2 2/4] arm64: mm: Batch dsb and isb when populating pgtables
Date: Thu, 4 Apr 2024 15:33:06 +0100 [thread overview]
Message-ID: <20240404143308.2224141-3-ryan.roberts@arm.com> (raw)
In-Reply-To: <20240404143308.2224141-1-ryan.roberts@arm.com>
After removing uneccessary TLBIs, the next bottleneck when creating the
page tables for the linear map is DSB and ISB, which were previously
issued per-pte in __set_pte(). Since we are writing multiple ptes in a
given pte table, we can elide these barriers and insert them once we
have finished writing to the table.
Execution time of map_mem(), which creates the kernel linear map page
tables, was measured on different machines with different RAM configs:
| Apple M2 VM | Ampere Altra| Ampere Altra| Ampere Altra
| VM, 16G | VM, 64G | VM, 256G | Metal, 512G
---------------|-------------|-------------|-------------|-------------
| ms (%) | ms (%) | ms (%) | ms (%)
---------------|-------------|-------------|-------------|-------------
before | 77 (0%) | 431 (0%) | 1727 (0%) | 3796 (0%)
after | 13 (-84%) | 162 (-62%) | 655 (-62%) | 1656 (-56%)
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: Itaru Kitayama <itaru.kitayama@fujitsu.com>
Tested-by: Eric Chanudet <echanude@redhat.com>
---
arch/arm64/include/asm/pgtable.h | 7 ++++++-
arch/arm64/mm/mmu.c | 13 ++++++++++++-
2 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index afdd56d26ad7..105a95a8845c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -271,9 +271,14 @@ static inline pte_t pte_mkdevmap(pte_t pte)
return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
}
-static inline void __set_pte(pte_t *ptep, pte_t pte)
+static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
{
WRITE_ONCE(*ptep, pte);
+}
+
+static inline void __set_pte(pte_t *ptep, pte_t pte)
+{
+ __set_pte_nosync(ptep, pte);
/*
* Only if the new pte is valid and kernel, otherwise TLB maintenance
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index fd91b5bdb514..dc86dceb0efe 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -178,7 +178,11 @@ static pte_t *init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
do {
pte_t old_pte = __ptep_get(ptep);
- __set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+ /*
+ * Required barriers to make this visible to the table walker
+ * are deferred to the end of alloc_init_cont_pte().
+ */
+ __set_pte_nosync(ptep, pfn_pte(__phys_to_pfn(phys), prot));
/*
* After the PTE entry has been populated once, we
@@ -234,6 +238,13 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
} while (addr = next, addr != end);
pte_clear_fixmap();
+
+ /*
+ * Ensure all previous pgtable writes are visible to the table walker.
+ * See init_pte().
+ */
+ dsb(ishst);
+ isb();
}
static pmd_t *init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
--
2.25.1
next prev parent reply other threads:[~2024-04-04 14:33 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-04 14:33 [PATCH v2 0/4] Speed up boot with faster linear map creation Ryan Roberts
2024-04-04 14:33 ` [PATCH v2 1/4] arm64: mm: Don't remap pgtables per-cont(pte|pmd) block Ryan Roberts
2024-04-10 9:46 ` Mark Rutland
2024-04-10 10:27 ` Ryan Roberts
2024-04-04 14:33 ` Ryan Roberts [this message]
2024-04-10 10:06 ` [PATCH v2 2/4] arm64: mm: Batch dsb and isb when populating pgtables Mark Rutland
2024-04-10 10:25 ` Ryan Roberts
2024-04-10 11:06 ` Mark Rutland
2024-04-04 14:33 ` [PATCH v2 3/4] arm64: mm: Don't remap pgtables for allocate vs populate Ryan Roberts
2024-04-11 13:02 ` Mark Rutland
2024-04-11 13:37 ` Ryan Roberts
2024-04-11 14:48 ` Mark Rutland
2024-04-11 14:57 ` Ryan Roberts
2024-04-11 15:25 ` Mark Rutland
2024-04-11 15:37 ` Ryan Roberts
2024-04-12 7:53 ` Ryan Roberts
2024-04-12 9:25 ` Mark Rutland
2024-04-04 14:33 ` [PATCH v2 4/4] arm64: mm: Lazily clear pte table mappings from fixmap Ryan Roberts
2024-04-11 13:24 ` Mark Rutland
2024-04-11 13:39 ` Ryan Roberts
2024-04-05 7:39 ` [PATCH v2 0/4] Speed up boot with faster linear map creation Itaru Kitayama
2024-04-06 8:32 ` Ryan Roberts
2024-04-06 10:31 ` Itaru Kitayama
2024-04-08 7:30 ` Ryan Roberts
2024-04-09 0:10 ` Itaru Kitayama
2024-04-09 10:04 ` Ryan Roberts
2024-04-09 10:13 ` Itaru Kitayama
2024-04-09 11:22 ` David Hildenbrand
2024-04-09 11:29 ` David Hildenbrand
2024-04-09 11:51 ` David Hildenbrand
2024-04-09 14:13 ` Ryan Roberts
2024-04-09 14:29 ` David Hildenbrand
2024-04-09 14:39 ` Ryan Roberts
2024-04-09 14:45 ` David Hildenbrand
2024-04-09 23:30 ` Itaru Kitayama
2024-04-10 6:47 ` Itaru Kitayama
2024-04-10 7:10 ` David Hildenbrand
2024-04-10 7:37 ` Itaru Kitayama
2024-04-10 7:45 ` David Hildenbrand
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=20240404143308.2224141-3-ryan.roberts@arm.com \
--to=ryan.roberts@arm.com \
--cc=ardb@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=david@redhat.com \
--cc=ddutile@redhat.com \
--cc=echanude@redhat.com \
--cc=itaru.kitayama@fujitsu.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=will@kernel.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