There are several places where ZONE_DEVICE struct pages assume a reference
count == 1 means the page is idle and free. Instead of open coding this,
add a helper function to hide this detail.
Signed-off-by: Ralph Campbell <[email protected]>
---
fs/dax.c | 8 ++++----
fs/ext4/inode.c | 2 +-
fs/xfs/xfs_file.c | 2 +-
include/linux/dax.h | 5 +++++
4 files changed, 11 insertions(+), 6 deletions(-)
diff --git a/fs/dax.c b/fs/dax.c
index 994ab66a9907..8eddbcc0e149 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -358,7 +358,7 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
- WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
+ WARN_ON_ONCE(trunc && !dax_layout_is_idle_page(page));
WARN_ON_ONCE(page->mapping && page->mapping != mapping);
page->mapping = NULL;
page->index = 0;
@@ -372,7 +372,7 @@ static struct page *dax_busy_page(void *entry)
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
- if (page_ref_count(page) > 1)
+ if (!dax_layout_is_idle_page(page))
return page;
}
return NULL;
@@ -560,11 +560,11 @@ static void *grab_mapping_entry(struct xa_state *xas,
/**
* dax_layout_busy_page - find first pinned page in @mapping
- * @mapping: address space to scan for a page with ref count > 1
+ * @mapping: address space to scan for a page with ref count > 0
*
* DAX requires ZONE_DEVICE mapped pages. These pages are never
* 'onlined' to the page allocator so they are considered idle when
- * page->count == 1. A filesystem uses this interface to determine if
+ * page->count == 0. A filesystem uses this interface to determine if
* any page in the mapping is busy, i.e. for DMA, or other
* get_user_pages() usages.
*
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index bf596467c234..d9f8ad55523a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3927,7 +3927,7 @@ int ext4_break_layouts(struct inode *inode)
return 0;
error = ___wait_var_event(&page->_refcount,
- atomic_read(&page->_refcount) == 1,
+ dax_layout_is_idle_page(page),
TASK_INTERRUPTIBLE, 0, 0,
ext4_wait_dax_page(ei));
} while (error == 0);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a29f78a663ca..29ab96541bc1 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -750,7 +750,7 @@ xfs_break_dax_layouts(
*retry = true;
return ___wait_var_event(&page->_refcount,
- atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
+ dax_layout_is_idle_page(page), TASK_INTERRUPTIBLE,
0, 0, xfs_wait_dax_page(inode));
}
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 43b39ab9de1a..3f78ed78d1d6 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -238,4 +238,9 @@ static inline bool dax_mapping(struct address_space *mapping)
return mapping->host && IS_DAX(mapping->host);
}
+static inline bool dax_layout_is_idle_page(struct page *page)
+{
+ return page_ref_count(page) <= 1;
+}
+
#endif
--
2.20.1
On Fri, Sep 25, 2020 at 1:45 PM Ralph Campbell <[email protected]> wrote:
>
> There are several places where ZONE_DEVICE struct pages assume a reference
> count == 1 means the page is idle and free. Instead of open coding this,
> add a helper function to hide this detail.
>
> Signed-off-by: Ralph Campbell <[email protected]>
> ---
> fs/dax.c | 8 ++++----
> fs/ext4/inode.c | 2 +-
> fs/xfs/xfs_file.c | 2 +-
> include/linux/dax.h | 5 +++++
> 4 files changed, 11 insertions(+), 6 deletions(-)
>
> diff --git a/fs/dax.c b/fs/dax.c
> index 994ab66a9907..8eddbcc0e149 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -358,7 +358,7 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
> for_each_mapped_pfn(entry, pfn) {
> struct page *page = pfn_to_page(pfn);
>
> - WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
> + WARN_ON_ONCE(trunc && !dax_layout_is_idle_page(page));
> WARN_ON_ONCE(page->mapping && page->mapping != mapping);
> page->mapping = NULL;
> page->index = 0;
> @@ -372,7 +372,7 @@ static struct page *dax_busy_page(void *entry)
> for_each_mapped_pfn(entry, pfn) {
> struct page *page = pfn_to_page(pfn);
>
> - if (page_ref_count(page) > 1)
> + if (!dax_layout_is_idle_page(page))
> return page;
> }
> return NULL;
> @@ -560,11 +560,11 @@ static void *grab_mapping_entry(struct xa_state *xas,
>
> /**
> * dax_layout_busy_page - find first pinned page in @mapping
> - * @mapping: address space to scan for a page with ref count > 1
> + * @mapping: address space to scan for a page with ref count > 0
> *
> * DAX requires ZONE_DEVICE mapped pages. These pages are never
> * 'onlined' to the page allocator so they are considered idle when
> - * page->count == 1. A filesystem uses this interface to determine if
> + * page->count == 0. A filesystem uses this interface to determine if
> * any page in the mapping is busy, i.e. for DMA, or other
> * get_user_pages() usages.
> *
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index bf596467c234..d9f8ad55523a 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3927,7 +3927,7 @@ int ext4_break_layouts(struct inode *inode)
> return 0;
>
> error = ___wait_var_event(&page->_refcount,
> - atomic_read(&page->_refcount) == 1,
> + dax_layout_is_idle_page(page),
> TASK_INTERRUPTIBLE, 0, 0,
> ext4_wait_dax_page(ei));
> } while (error == 0);
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index a29f78a663ca..29ab96541bc1 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -750,7 +750,7 @@ xfs_break_dax_layouts(
>
> *retry = true;
> return ___wait_var_event(&page->_refcount,
> - atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
> + dax_layout_is_idle_page(page), TASK_INTERRUPTIBLE,
> 0, 0, xfs_wait_dax_page(inode));
> }
>
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 43b39ab9de1a..3f78ed78d1d6 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -238,4 +238,9 @@ static inline bool dax_mapping(struct address_space *mapping)
> return mapping->host && IS_DAX(mapping->host);
> }
>
> +static inline bool dax_layout_is_idle_page(struct page *page)
> +{
> + return page_ref_count(page) <= 1;
Why convert the check from "== 1" to "<= 1" and then back to the ==
operator in the next patch? A refcount < 1 in this path before your
other change is a bug.
On 9/25/20 1:51 PM, Dan Williams wrote:
> On Fri, Sep 25, 2020 at 1:45 PM Ralph Campbell <[email protected]> wrote:
>>
>> There are several places where ZONE_DEVICE struct pages assume a reference
>> count == 1 means the page is idle and free. Instead of open coding this,
>> add a helper function to hide this detail.
>>
>> Signed-off-by: Ralph Campbell <[email protected]>
>> ---
>> fs/dax.c | 8 ++++----
>> fs/ext4/inode.c | 2 +-
>> fs/xfs/xfs_file.c | 2 +-
>> include/linux/dax.h | 5 +++++
>> 4 files changed, 11 insertions(+), 6 deletions(-)
>>
>> diff --git a/fs/dax.c b/fs/dax.c
>> index 994ab66a9907..8eddbcc0e149 100644
>> --- a/fs/dax.c
>> +++ b/fs/dax.c
>> @@ -358,7 +358,7 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
>> for_each_mapped_pfn(entry, pfn) {
>> struct page *page = pfn_to_page(pfn);
>>
>> - WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
>> + WARN_ON_ONCE(trunc && !dax_layout_is_idle_page(page));
>> WARN_ON_ONCE(page->mapping && page->mapping != mapping);
>> page->mapping = NULL;
>> page->index = 0;
>> @@ -372,7 +372,7 @@ static struct page *dax_busy_page(void *entry)
>> for_each_mapped_pfn(entry, pfn) {
>> struct page *page = pfn_to_page(pfn);
>>
>> - if (page_ref_count(page) > 1)
>> + if (!dax_layout_is_idle_page(page))
>> return page;
>> }
>> return NULL;
>> @@ -560,11 +560,11 @@ static void *grab_mapping_entry(struct xa_state *xas,
>>
>> /**
>> * dax_layout_busy_page - find first pinned page in @mapping
>> - * @mapping: address space to scan for a page with ref count > 1
>> + * @mapping: address space to scan for a page with ref count > 0
>> *
>> * DAX requires ZONE_DEVICE mapped pages. These pages are never
>> * 'onlined' to the page allocator so they are considered idle when
>> - * page->count == 1. A filesystem uses this interface to determine if
>> + * page->count == 0. A filesystem uses this interface to determine if
>> * any page in the mapping is busy, i.e. for DMA, or other
>> * get_user_pages() usages.
>> *
>> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
>> index bf596467c234..d9f8ad55523a 100644
>> --- a/fs/ext4/inode.c
>> +++ b/fs/ext4/inode.c
>> @@ -3927,7 +3927,7 @@ int ext4_break_layouts(struct inode *inode)
>> return 0;
>>
>> error = ___wait_var_event(&page->_refcount,
>> - atomic_read(&page->_refcount) == 1,
>> + dax_layout_is_idle_page(page),
>> TASK_INTERRUPTIBLE, 0, 0,
>> ext4_wait_dax_page(ei));
>> } while (error == 0);
>> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
>> index a29f78a663ca..29ab96541bc1 100644
>> --- a/fs/xfs/xfs_file.c
>> +++ b/fs/xfs/xfs_file.c
>> @@ -750,7 +750,7 @@ xfs_break_dax_layouts(
>>
>> *retry = true;
>> return ___wait_var_event(&page->_refcount,
>> - atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
>> + dax_layout_is_idle_page(page), TASK_INTERRUPTIBLE,
>> 0, 0, xfs_wait_dax_page(inode));
>> }
>>
>> diff --git a/include/linux/dax.h b/include/linux/dax.h
>> index 43b39ab9de1a..3f78ed78d1d6 100644
>> --- a/include/linux/dax.h
>> +++ b/include/linux/dax.h
>> @@ -238,4 +238,9 @@ static inline bool dax_mapping(struct address_space *mapping)
>> return mapping->host && IS_DAX(mapping->host);
>> }
>>
>> +static inline bool dax_layout_is_idle_page(struct page *page)
>> +{
>> + return page_ref_count(page) <= 1;
>
> Why convert the check from "== 1" to "<= 1" and then back to the ==
> operator in the next patch? A refcount < 1 in this path before your
> other change is a bug.
>
Mostly I was thinking > 1 was busy so <= 1 is idle. And yes, <=0 is never
supposed to happen. Checking for == 1 is probably better though.
On Fri, Sep 25, 2020 at 01:44:41PM -0700, Ralph Campbell wrote:
> error = ___wait_var_event(&page->_refcount,
> - atomic_read(&page->_refcount) == 1,
> + dax_layout_is_idle_page(page),
> TASK_INTERRUPTIBLE, 0, 0,
> ext4_wait_dax_page(ei));
> +++ b/fs/xfs/xfs_file.c
> @@ -750,7 +750,7 @@ xfs_break_dax_layouts(
>
> *retry = true;
> return ___wait_var_event(&page->_refcount,
> - atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
> + dax_layout_is_idle_page(page), TASK_INTERRUPTIBLE,
> 0, 0, xfs_wait_dax_page(inode));
> }
I still think a litte helper macro would be nice here:
#define dax_wait_page(_inode, _page, _wait_cb) \
___wait_var_event(&(_page)->_refcount, \
atomic_read(&(_page)->_refcount) == 1, \
TASK_INTERRUPTIBLE, dax_layout_is_idle_page(_page), \
TASK_INTERRUPTIBLE, 0, 0, _wait_cb(_inode));
On 9/25/20 11:35 PM, Christoph Hellwig wrote:
> On Fri, Sep 25, 2020 at 01:44:41PM -0700, Ralph Campbell wrote:
>> error = ___wait_var_event(&page->_refcount,
>> - atomic_read(&page->_refcount) == 1,
>> + dax_layout_is_idle_page(page),
>> TASK_INTERRUPTIBLE, 0, 0,
>> ext4_wait_dax_page(ei));
>
>> +++ b/fs/xfs/xfs_file.c
>> @@ -750,7 +750,7 @@ xfs_break_dax_layouts(
>>
>> *retry = true;
>> return ___wait_var_event(&page->_refcount,
>> - atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
>> + dax_layout_is_idle_page(page), TASK_INTERRUPTIBLE,
>> 0, 0, xfs_wait_dax_page(inode));
>> }
>
> I still think a litte helper macro would be nice here:
>
> #define dax_wait_page(_inode, _page, _wait_cb) \
> ___wait_var_event(&(_page)->_refcount, \
> atomic_read(&(_page)->_refcount) == 1, \
> TASK_INTERRUPTIBLE, dax_layout_is_idle_page(_page), \
> TASK_INTERRUPTIBLE, 0, 0, _wait_cb(_inode));
OK, I'll add it in v3.