On 2/18/21 9:34 AM, Mike Kravetz wrote:
> On 2/18/21 9:25 AM, Jason Gunthorpe wrote:
>> On Thu, Feb 18, 2021 at 02:45:54PM +0000, Matthew Wilcox wrote:
>>> On Wed, Feb 17, 2021 at 11:02:52AM -0800, Andrew Morton wrote:
>>>> On Wed, 17 Feb 2021 10:49:25 -0800 Mike Kravetz <mike.kravetz@xxxxxxxxxx> wrote:
>>>>> page structs are not guaranteed to be contiguous for gigantic pages. The
>>>>
>>>> June 2014. That's a long lurk time for a bug. I wonder if some later
>>>> commit revealed it.
>>>
>>> I would suggest that gigantic pages have not seen much use. Certainly
>>> performance with Intel CPUs on benchmarks that I've been involved with
>>> showed lower performance with 1GB pages than with 2MB pages until quite
>>> recently.
>>
>> I suggested in another thread that maybe it is time to consider
>> dropping this "feature"
>>
>> If it has been slightly broken for 7 years it seems a good bet it
>> isn't actually being used.
>>
>> The cost to fix GUP to be compatible with this will hurt normal
>> GUP performance - and again, that nobody has hit this bug in GUP
>> further suggests the feature isn't used..
>
> I was thinking that we could detect these 'unusual' configurations and only
> do the slower page struct walking in those cases. However, we would need to
> do some research to make sure we have taken into account all possible config
> options which can produce non-contiguous page structs. That should have zero
> performance impact in the 'normal' cases.
What about something like the following patch, and making all code that
wants to scan gigantic page subpages use mem_map_next()?
>From 95b0384bd5d7f0435546bdd3c01c478724ae0166 Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Date: Thu, 18 Feb 2021 13:35:02 -0800
Subject: [PATCH] mm: define PFN_PAGE_MAP_LINEAR to optimize gigantic page
scans
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
---
arch/ia64/include/asm/page.h | 1 +
arch/m68k/include/asm/page_no.h | 1 +
include/asm-generic/memory_model.h | 2 ++
mm/internal.h | 2 ++
4 files changed, 6 insertions(+)
diff --git a/arch/ia64/include/asm/page.h b/arch/ia64/include/asm/page.h
index b69a5499d75b..8f4288862ec8 100644
--- a/arch/ia64/include/asm/page.h
+++ b/arch/ia64/include/asm/page.h
@@ -106,6 +106,7 @@ extern struct page *vmem_map;
#ifdef CONFIG_DISCONTIGMEM
# define page_to_pfn(page) ((unsigned long) (page - vmem_map))
# define pfn_to_page(pfn) (vmem_map + (pfn))
+# define PFN_PAGE_MAP_LINEAR
# define __pfn_to_phys(pfn) PFN_PHYS(pfn)
#else
# include <asm-generic/memory_model.h>
diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index 6bbe52025de3..cafc0731a42c 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -28,6 +28,7 @@ extern unsigned long memory_end;
#define pfn_to_page(pfn) virt_to_page(pfn_to_virt(pfn))
#define page_to_pfn(page) virt_to_pfn(page_to_virt(page))
+#define PFN_PAGE_MAP_LINEAR
#define pfn_valid(pfn) ((pfn) < max_mapnr)
#define virt_addr_valid(kaddr) (((void *)(kaddr) >= (void *)PAGE_OFFSET) && \
diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index 7637fb46ba4f..8ac4c48dbf22 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -33,6 +33,7 @@
#define __pfn_to_page(pfn) (mem_map + ((pfn) - ARCH_PFN_OFFSET))
#define __page_to_pfn(page) ((unsigned long)((page) - mem_map) + \
ARCH_PFN_OFFSET)
+#define PFN_PAGE_MAP_LINEAR
#elif defined(CONFIG_DISCONTIGMEM)
#define __pfn_to_page(pfn) \
@@ -53,6 +54,7 @@
/* memmap is virtually contiguous. */
#define __pfn_to_page(pfn) (vmemmap + (pfn))
#define __page_to_pfn(page) (unsigned long)((page) - vmemmap)
+#define PFN_PAGE_MAP_LINEAR
#elif defined(CONFIG_SPARSEMEM)
/*
diff --git a/mm/internal.h b/mm/internal.h
index 25d2b2439f19..64cc5069047c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -454,12 +454,14 @@ static inline struct page *mem_map_offset(struct page *base, int offset)
static inline struct page *mem_map_next(struct page *iter,
struct page *base, int offset)
{
+#ifndef PFN_PAGE_MAP_LINEAR
if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
unsigned long pfn = page_to_pfn(base) + offset;
if (!pfn_valid(pfn))
return NULL;
return pfn_to_page(pfn);
}
+#endif
return iter + 1;
}
--
2.29.2
