linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jia He <hejianet@gmail.com>
To: Russell King <linux@armlinux.org.uk>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will.deacon@arm.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Michal Hocko <mhocko@suse.com>
Cc: Wei Yang <richard.weiyang@gmail.com>,
	Kees Cook <keescook@chromium.org>,
	Laura Abbott <labbott@redhat.com>,
	Vladimir Murzin <vladimir.murzin@arm.com>,
	Philip Derrin <philip@cog.systems>,
	Grygorii Strashko <grygorii.strashko@linaro.org>,
	AKASHI Takahiro <takahiro.akashi@linaro.org>,
	James Morse <james.morse@arm.com>,
	Steve Capper <steve.capper@arm.com>,
	Pavel Tatashin <pasha.tatashin@oracle.com>,
	Gioh Kim <gi-oh.kim@profitbricks.com>,
	Vlastimil Babka <vbabka@suse.cz>, Mel Gorman <mgorman@suse.de>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Kemi Wang <kemi.wang@intel.com>, Petr Tesarik <ptesarik@suse.com>,
	YASUAKI ISHIMATSU <yasu.isimatu@gmail.com>,
	Andrey Ryabinin <aryabinin@virtuozzo.com>,
	Nikolay Borisov <nborisov@suse.com>,
	Daniel Jordan <daniel.m.jordan@oracle.com>,
	Daniel Vacek <neelx@redhat.com>,
	Eugeniu Rosca <erosca@de.adit-jv.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Jia He <hejianet@gmail.com>, Jia He <jia.he@hxt-semitech.com>
Subject: [PATCH v5 1/5] mm: page_alloc: remain memblock_next_valid_pfn() on arm and arm64
Date: Sun,  1 Apr 2018 19:30:32 -0700	[thread overview]
Message-ID: <1522636236-12625-2-git-send-email-hejianet@gmail.com> (raw)
In-Reply-To: <1522636236-12625-1-git-send-email-hejianet@gmail.com>

Commit b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns
where possible") optimized the loop in memmap_init_zone(). But it causes
possible panic bug. So Daniel Vacek reverted it later.

But as suggested by Daniel Vacek, it is fine to using memblock to skip
gaps and finding next valid frame with CONFIG_HAVE_ARCH_PFN_VALID.

On arm and arm64, memblock is used by default. But generic version of
pfn_valid() is based on mem sections and memblock_next_valid_pfn() does
not always return the next valid one but skips more resulting in some
valid frames to be skipped (as if they were invalid). And that's why
kernel was eventually crashing on some !arm machines.

And as verified by Eugeniu Rosca, arm can benifit from commit
b92df1de5d28. So remain the memblock_next_valid_pfn on arm{,64} and move
the related codes to arm64 arch directory.

Suggested-by: Daniel Vacek <neelx@redhat.com>
Signed-off-by: Jia He <jia.he@hxt-semitech.com>
---
 arch/arm/include/asm/page.h   |  2 ++
 arch/arm/mm/init.c            | 31 ++++++++++++++++++++++++++++++-
 arch/arm64/include/asm/page.h |  2 ++
 arch/arm64/mm/init.c          | 31 ++++++++++++++++++++++++++++++-
 include/linux/mmzone.h        |  1 +
 mm/page_alloc.c               |  4 +++-
 6 files changed, 68 insertions(+), 3 deletions(-)

diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 4355f0e..489875c 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -158,6 +158,8 @@ typedef struct page *pgtable_t;
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 extern int pfn_valid(unsigned long);
+extern unsigned long memblock_next_valid_pfn(unsigned long pfn);
+#define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1)
 #endif
 
 #include <asm/memory.h>
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index a1f11a7..0fb85ca 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -198,7 +198,36 @@ int pfn_valid(unsigned long pfn)
 	return memblock_is_map_memory(__pfn_to_phys(pfn));
 }
 EXPORT_SYMBOL(pfn_valid);
-#endif
+
+/* HAVE_MEMBLOCK is always enabled on arm */
+unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
+{
+	struct memblock_type *type = &memblock.memory;
+	unsigned int right = type->cnt;
+	unsigned int mid, left = 0;
+	phys_addr_t addr = PFN_PHYS(++pfn);
+
+	do {
+		mid = (right + left) / 2;
+
+		if (addr < type->regions[mid].base)
+			right = mid;
+		else if (addr >= (type->regions[mid].base +
+				  type->regions[mid].size))
+			left = mid + 1;
+		else {
+			/* addr is within the region, so pfn is valid */
+			return pfn;
+		}
+	} while (left < right);
+
+	if (right == type->cnt)
+		return -1UL;
+	else
+		return PHYS_PFN(type->regions[right].base);
+}
+EXPORT_SYMBOL(memblock_next_valid_pfn);
+#endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
 
 #ifndef CONFIG_SPARSEMEM
 static void __init arm_memory_present(void)
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 60d02c8..e57d3f2 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -39,6 +39,8 @@ typedef struct page *pgtable_t;
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 extern int pfn_valid(unsigned long);
+extern unsigned long memblock_next_valid_pfn(unsigned long pfn);
+#define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1)
 #endif
 
 #include <asm/memory.h>
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 00e7b90..13e43ff 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -290,7 +290,36 @@ int pfn_valid(unsigned long pfn)
 	return memblock_is_map_memory(pfn << PAGE_SHIFT);
 }
 EXPORT_SYMBOL(pfn_valid);
-#endif
+
+/* HAVE_MEMBLOCK is always enabled on arm64 */
+unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
+{
+	struct memblock_type *type = &memblock.memory;
+	unsigned int right = type->cnt;
+	unsigned int mid, left = 0;
+	phys_addr_t addr = PFN_PHYS(++pfn);
+
+	do {
+		mid = (right + left) / 2;
+
+		if (addr < type->regions[mid].base)
+			right = mid;
+		else if (addr >= (type->regions[mid].base +
+				  type->regions[mid].size))
+			left = mid + 1;
+		else {
+			/* addr is within the region, so pfn is valid */
+			return pfn;
+		}
+	} while (left < right);
+
+	if (right == type->cnt)
+		return -1UL;
+	else
+		return PHYS_PFN(type->regions[right].base);
+}
+EXPORT_SYMBOL(memblock_next_valid_pfn);
+#endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
 
 #ifndef CONFIG_SPARSEMEM
 static void __init arm64_memory_present(void)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d797716..f9c0c46 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1245,6 +1245,7 @@ static inline int pfn_valid(unsigned long pfn)
 		return 0;
 	return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
 }
+#define skip_to_last_invalid_pfn(pfn) (pfn)
 #endif
 
 static inline int pfn_present(unsigned long pfn)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c19f5ac..30f7d76 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5483,8 +5483,10 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		if (context != MEMMAP_EARLY)
 			goto not_early;
 
-		if (!early_pfn_valid(pfn))
+		if (!early_pfn_valid(pfn)) {
+			pfn = skip_to_last_invalid_pfn(pfn);
 			continue;
+		}
 		if (!early_pfn_in_nid(pfn, nid))
 			continue;
 		if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
-- 
2.7.4

  reply	other threads:[~2018-04-02  2:32 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-02  2:30 [PATCH v5 0/5] optimize memblock_next_valid_pfn and early_pfn_valid on arm and arm64 Jia He
2018-04-02  2:30 ` Jia He [this message]
2018-04-02  6:55   ` [PATCH v5 1/5] mm: page_alloc: remain memblock_next_valid_pfn() " Ard Biesheuvel
2018-04-02  7:49     ` Jia He
2018-04-02  7:53       ` Ard Biesheuvel
2018-04-03  3:07         ` Jia He
2018-04-11  4:47         ` Jia He
2018-04-02  7:50   ` kbuild test robot
2018-04-02  2:30 ` [PATCH v5 2/5] arm: arm64: page_alloc: reduce unnecessary binary search in memblock_next_valid_pfn() Jia He
2018-04-02  6:57   ` Ard Biesheuvel
2018-04-02  8:43     ` Daniel Vacek
2018-04-02  8:01   ` Daniel Vacek
2018-04-02 15:07   ` kbuild test robot
2018-04-02  2:30 ` [PATCH v5 3/5] mm/memblock: introduce memblock_search_pfn_regions() Jia He
2018-04-02  6:57   ` Ard Biesheuvel
2018-04-02  2:30 ` [PATCH v5 4/5] arm64: introduce pfn_valid_region() Jia He
2018-04-02  6:59   ` Ard Biesheuvel
2018-04-02 18:53   ` kbuild test robot
2018-04-02  2:30 ` [PATCH v5 5/5] mm: page_alloc: reduce unnecessary binary search in early_pfn_valid() Jia He
2018-04-02  7:00   ` Ard Biesheuvel
2018-04-02  8:15     ` Jia He

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=1522636236-12625-2-git-send-email-hejianet@gmail.com \
    --to=hejianet@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=ard.biesheuvel@linaro.org \
    --cc=aryabinin@virtuozzo.com \
    --cc=catalin.marinas@arm.com \
    --cc=daniel.m.jordan@oracle.com \
    --cc=erosca@de.adit-jv.com \
    --cc=gi-oh.kim@profitbricks.com \
    --cc=grygorii.strashko@linaro.org \
    --cc=hannes@cmpxchg.org \
    --cc=james.morse@arm.com \
    --cc=jia.he@hxt-semitech.com \
    --cc=keescook@chromium.org \
    --cc=kemi.wang@intel.com \
    --cc=labbott@redhat.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@armlinux.org.uk \
    --cc=mark.rutland@arm.com \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=nborisov@suse.com \
    --cc=neelx@redhat.com \
    --cc=pasha.tatashin@oracle.com \
    --cc=philip@cog.systems \
    --cc=ptesarik@suse.com \
    --cc=richard.weiyang@gmail.com \
    --cc=steve.capper@arm.com \
    --cc=takahiro.akashi@linaro.org \
    --cc=vbabka@suse.cz \
    --cc=vladimir.murzin@arm.com \
    --cc=will.deacon@arm.com \
    --cc=yasu.isimatu@gmail.com \
    /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).