search for: obj_allocated_tag

Hello, On (03/30/16 16:12), Minchan Kim wrote: > @@ -1421,7 +1434,6 @@ static unsigned long obj_malloc(struct size_class *class, > unsigned long m_offset; > void *vaddr; > > - handle |= OBJ_ALLOCATED_TAG; a nitpick, why did you replace this ALLOCATED_TAG assignment with 2 'handle | OBJ_ALLOCATED_TAG'? -ss > obj = get_freeobj(first_page); > objidx_to_page_and_offset(class, first_page, obj, > &m_page, &m_offset); > @@ -1431,10 +1443,10 @@ static unsigned long...

Hello, On (03/30/16 16:12), Minchan Kim wrote: > @@ -1421,7 +1434,6 @@ static unsigned long obj_malloc(struct size_class *class, > unsigned long m_offset; > void *vaddr; > > - handle |= OBJ_ALLOCATED_TAG; a nitpick, why did you replace this ALLOCATED_TAG assignment with 2 'handle | OBJ_ALLOCATED_TAG'? -ss > obj = get_freeobj(first_page); > objidx_to_page_and_offset(class, first_page, obj, > &m_page, &m_offset); > @@ -1431,10 +1443,10 @@ static unsigned long...

For migration, we need to create sub-page chain of zspage dynamically so this patch factors it out from alloc_zspage. As a minor refactoring, it makes OBJ_ALLOCATED_TAG assign more clear in obj_malloc(it could be another patch but it's trivial so I want to put together in this patch). Signed-off-by: Minchan Kim <minchan at kernel.org> --- mm/zsmalloc.c | 78 ++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 45 insertions(+), 3...

For migration, we need to create sub-page chain of zspage dynamically so this patch factors it out from alloc_zspage. As a minor refactoring, it makes OBJ_ALLOCATED_TAG assign more clear in obj_malloc(it could be another patch but it's trivial so I want to put together in this patch). Signed-off-by: Minchan Kim <minchan at kernel.org> --- mm/zsmalloc.c | 80 ++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 46 insertions(+), 3...

On 2016/3/11 15:30, Minchan Kim wrote: > For migration, we need to create sub-page chain of zspage > dynamically so this patch factors it out from alloc_zspage. > > As a minor refactoring, it makes OBJ_ALLOCATED_TAG assign > more clear in obj_malloc(it could be another patch but it's > trivial so I want to put together in this patch). > > Signed-off-by: Minchan Kim <minchan at kernel.org> > --- > mm/zsmalloc.c | 78 ++++++++++++++++++++++++++++++++++------------------------- >...

On 2016/3/11 15:30, Minchan Kim wrote: > For migration, we need to create sub-page chain of zspage > dynamically so this patch factors it out from alloc_zspage. > > As a minor refactoring, it makes OBJ_ALLOCATED_TAG assign > more clear in obj_malloc(it could be another patch but it's > trivial so I want to put together in this patch). > > Signed-off-by: Minchan Kim <minchan at kernel.org> > --- > mm/zsmalloc.c | 78 ++++++++++++++++++++++++++++++++++------------------------- >...

...ff; @@ -976,7 +1000,7 @@ static void init_zspage(struct size_class *class, struct page *first_page) link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { - link->next = location_to_obj(page, i++); + link->next = freeobj++ << OBJ_ALLOCATED_TAG; link += class->size / sizeof(*link); } @@ -986,11 +1010,21 @@ static void init_zspage(struct size_class *class, struct page *first_page) * page (if present) */ next_page = get_next_page(page); - link->next = location_to_obj(next_page, 0); + if (next_page) { + link-&gt...

...off; @@ -972,7 +995,7 @@ static void init_zspage(struct size_class *class, struct page *first_page) link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { - link->next = location_to_obj(page, i++); + link->next = freeobj++ << OBJ_ALLOCATED_TAG; link += class->size / sizeof(*link); } @@ -982,11 +1005,21 @@ static void init_zspage(struct size_class *class, struct page *first_page) * page (if present) */ next_page = get_next_page(page); - link->next = location_to_obj(next_page, 0); + if (next_page) { + link-&gt...

...~PAGE_MASK); } all functions called "objidx_to_page_and_ofs" could use it like this, for example: static unsigned long handle_from_obj(struct size_class *class, struct page *first_page, int obj_idx) { unsigned long *head = map_handle(class, first_page, obj_idx); if (*head & OBJ_ALLOCATED_TAG) handle = *head & ~OBJ_ALLOCATED_TAG; unmap_handle(*head); return handle; } 'freeze_zspage', u'nfreeze_zspage' use it in the same way. but in 'obj_malloc', we still have to get the page to get obj. obj = location_to_obj(m_page, obj); > Indeed. I will cha...

...~PAGE_MASK); } all functions called "objidx_to_page_and_ofs" could use it like this, for example: static unsigned long handle_from_obj(struct size_class *class, struct page *first_page, int obj_idx) { unsigned long *head = map_handle(class, first_page, obj_idx); if (*head & OBJ_ALLOCATED_TAG) handle = *head & ~OBJ_ALLOCATED_TAG; unmap_handle(*head); return handle; } 'freeze_zspage', u'nfreeze_zspage' use it in the same way. but in 'obj_malloc', we still have to get the page to get obj. obj = location_to_obj(m_page, obj); > Indeed. I will cha...

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

On (03/11/16 16:30), Minchan Kim wrote: > -static void *location_to_obj(struct page *page, unsigned long obj_idx) > +static void objidx_to_page_and_ofs(struct size_class *class, > + struct page *first_page, > + unsigned long obj_idx, > + struct page **obj_page, > + unsigned long *ofs_in_page) this looks big; 5 params, function "returning" both page and

On (03/11/16 16:30), Minchan Kim wrote: > -static void *location_to_obj(struct page *page, unsigned long obj_idx) > +static void objidx_to_page_and_ofs(struct size_class *class, > + struct page *first_page, > + unsigned long obj_idx, > + struct page **obj_page, > + unsigned long *ofs_in_page) this looks big; 5 params, function "returning" both page and

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

...Sat, Mar 12, 2016 at 11:09:36AM +0800, xuyiping wrote: > > > On 2016/3/11 15:30, Minchan Kim wrote: > >For migration, we need to create sub-page chain of zspage > >dynamically so this patch factors it out from alloc_zspage. > > > >As a minor refactoring, it makes OBJ_ALLOCATED_TAG assign > >more clear in obj_malloc(it could be another patch but it's > >trivial so I want to put together in this patch). > > > >Signed-off-by: Minchan Kim <minchan at kernel.org> > >--- > > mm/zsmalloc.c | 78 ++++++++++++++++++++++++++++++++++-------...

...dle); obj_to_location(obj, &page, &obj_idx); get_zspage_mapping(get_first_page(page), &class_idx, &fg); @@ -1445,8 +1441,6 @@ static void obj_free(struct zs_pool *pool, struct size_class *class, unsigned long f_objidx, f_offset; void *vaddr; - BUG_ON(!obj); - obj &= ~OBJ_ALLOCATED_TAG; obj_to_location(obj, &f_page, &f_objidx); first_page = get_first_page(f_page); @@ -1546,7 +1540,6 @@ static void zs_object_copy(unsigned long dst, unsigned long src, kunmap_atomic(d_addr); kunmap_atomic(s_addr); s_page = get_next_page(s_page); - BUG_ON(!s_page); s_add...