search for: init_page_count

...ch/powerpc/kvm/book3s_hv_uvmem.c > +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c > @@ -711,7 +711,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) > > dpage = pfn_to_page(uvmem_pfn); > dpage->zone_device_data = pvt; > - get_page(dpage); > + init_page_count(dpage); > lock_page(dpage); > return dpage; > out_clear: > diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c > index 4e8112fde3e6..ca2e3c3edc36 100644 > --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c > +++ b/drivers/gpu/drm/nouveau/...

...c8be5..a0d08b1d8c1e 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -711,7 +711,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - get_page(dpage); + init_page_count(dpage); lock_page(dpage); return dpage; out_clear: @@ -1151,6 +1151,7 @@ int kvmppc_uvmem_init(void) struct resource *res; void *addr; unsigned long pfn_last, pfn_first; + unsigned long pfn; size = kvmppc_get_secmem_size(); if (!size) { @@ -1191,6 +1192,16 @@ int kvmppc_uvmem_init(...

Matthew Wilcox, Ira Weiny, and others have complained that ZONE_DEVICE struct page reference counting is ugly because they are "free" when the reference count is one instead of zero. This leads to explicit checks for ZONE_DEVICE pages in places like put_page(), GUP, THP splitting, and page migration which have to adjust the expected reference count when determining if the page is

...; count appear to be zero to the wider kernel but expect that drivers > get a fake reference on entry to their ->page_free() callbacks. Good point. Since set_page_refcounted() is defined in mm_interal.h I would have to move the definition to someplace like page_ref.h or have the drivers cal init_page_count() or set_page_count() since get_page() calls VM_BUG_ON_PAGE() if refcount == 0. I'll move set_page_refcounted() since that is what the page allocator uses and seems named for the purpose.

...e + else balloon_stats.balloon_low--; - totalram_pages++; + adjust_managed_page_count(page, 1); return page; } @@ -372,9 +361,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) #endif /* Relinquish the page back to the allocator. */ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); + __free_reserved_page(page); } balloon_stats.current_pages += rc; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeec..95c5a6b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1246,7 +1246,7 @@ static void __init gather_bootmem_prealloc(void) * side-effec...

...e + else balloon_stats.balloon_low--; - totalram_pages++; + adjust_managed_page_count(page, 1); return page; } @@ -372,9 +361,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) #endif /* Relinquish the page back to the allocator. */ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); + __free_reserved_page(page); } balloon_stats.current_pages += rc; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeec..95c5a6b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1246,7 +1246,7 @@ static void __init gather_bootmem_prealloc(void) * side-effec...

...e + else balloon_stats.balloon_low--; - totalram_pages++; + adjust_managed_page_count(page, 1); return page; } @@ -372,9 +361,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) #endif /* Relinquish the page back to the allocator. */ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); + __free_reserved_page(page); } balloon_stats.current_pages += rc; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeec..95c5a6b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1246,7 +1246,7 @@ static void __init gather_bootmem_prealloc(void) * side-effec...

...> + * have a reference count of zero while in the free state. > + */ > spin_lock(&mdevice->lock); > for (pfn = pfn_first; pfn < pfn_last; pfn++) { > struct page *page = pfn_to_page(pfn); > > + set_page_count(page, 0); This confuses me. How does this and init_page_count() not confuse the buddy allocator? Don't you have to reset the refcount somewhere after the test? > page->zone_device_data = mdevice->free_pages; > mdevice->free_pages = page; > } > @@ -561,7 +566,7 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_d...

...c8be5..a0d08b1d8c1e 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -711,7 +711,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - get_page(dpage); + init_page_count(dpage); lock_page(dpage); return dpage; out_clear: @@ -1151,6 +1151,7 @@ int kvmppc_uvmem_init(void) struct resource *res; void *addr; unsigned long pfn_last, pfn_first; + unsigned long pfn; size = kvmppc_get_secmem_size(); if (!size) { @@ -1191,6 +1192,16 @@ int kvmppc_uvmem_init(...

...57239..e6ec98325fab 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -711,7 +711,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - get_page(dpage); + init_page_count(dpage); lock_page(dpage); return dpage; out_clear: diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 4e8112fde3e6..ca2e3c3edc36 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -323,7 +323,7 @@...

...c8be5..acee67710620 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -711,7 +711,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - get_page(dpage); + init_page_count(dpage); lock_page(dpage); return dpage; out_clear: diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 92987daa5e17..8bc7120e1216 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -324,7 +324,7 @@...

...e + else balloon_stats.balloon_low--; - totalram_pages++; + adjust_managed_page_count(page, 1); return page; } @@ -374,9 +363,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) #endif /* Relinquish the page back to the allocator. */ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); + __free_reserved_page(page); } balloon_stats.current_pages += rc; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeec..95c5a6b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1246,7 +1246,7 @@ static void __init gather_bootmem_prealloc(void) * side-effec...

...e + else balloon_stats.balloon_low--; - totalram_pages++; + adjust_managed_page_count(page, 1); return page; } @@ -374,9 +363,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) #endif /* Relinquish the page back to the allocator. */ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); + __free_reserved_page(page); } balloon_stats.current_pages += rc; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeec..95c5a6b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1246,7 +1246,7 @@ static void __init gather_bootmem_prealloc(void) * side-effec...

...e + else balloon_stats.balloon_low--; - totalram_pages++; + adjust_managed_page_count(page, 1); return page; } @@ -374,9 +363,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) #endif /* Relinquish the page back to the allocator. */ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); + __free_reserved_page(page); } balloon_stats.current_pages += rc; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeec..95c5a6b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1246,7 +1246,7 @@ static void __init gather_bootmem_prealloc(void) * side-effec...

This is still an RFC because after looking at the pmem/dax code some more, I realized that the ZONE_DEVICE struct pages are being inserted into the process' page tables with vmf_insert_mixed() and a zero refcount on the ZONE_DEVICE struct page. This is sort of OK because insert_pfn() increments the reference count on the pgmap which is what prevents memunmap_pages() from freeing the struct

On Mon, Sep 14, 2020 at 04:53:25PM -0700, Ralph Campbell wrote: > Since set_page_refcounted() is defined in mm_interal.h I would have to > move the definition to someplace like page_ref.h or have the drivers > cal init_page_count() or set_page_count() since get_page() calls > VM_BUG_ON_PAGE() if refcount == 0. > I'll move set_page_refcounted() since that is what the page allocator > uses and seems named for the purpose. I don't think any of the three ->page_free instances even cares about the page refco...

On 9/15/20 9:29 AM, Christoph Hellwig wrote: > On Mon, Sep 14, 2020 at 04:53:25PM -0700, Ralph Campbell wrote: >> Since set_page_refcounted() is defined in mm_interal.h I would have to >> move the definition to someplace like page_ref.h or have the drivers >> cal init_page_count() or set_page_count() since get_page() calls >> VM_BUG_ON_PAGE() if refcount == 0. >> I'll move set_page_refcounted() since that is what the page allocator >> uses and seems named for the purpose. > > I don't think any of the three ->page_free instances even care...

The original goal of this patchset is to fix the bug reported by https://bugzilla.kernel.org/show_bug.cgi?id=53501 Now it has also been expanded to reduce common code used by memory initializion. This is the first part, which applies to v3.9-rc1. It introduces following common helper functions to simplify free_initmem() and free_initrd_mem() on different architectures:

The original goal of this patchset is to fix the bug reported by https://bugzilla.kernel.org/show_bug.cgi?id=53501 Now it has also been expanded to reduce common code used by memory initializion. This is the first part, which applies to v3.9-rc1. It introduces following common helper functions to simplify free_initmem() and free_initrd_mem() on different architectures:

...tomic_dec_and_test(&page->_count); + return atomic_dec_and_test(&page->_count); +} + +static inline int put_page_testzero(struct page *page) +{ + int ret = put_page_testzero_nocheck(page); if (!ret) page_make_volatile(page, 1); return ret; @@ -356,6 +360,7 @@ static inline void init_page_count(struc } void put_page(struct page *page); +void put_page_nocheck(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); diff -urpN linux-2.6/include/linux/pagemap.h linux-2.6-patched/include/linux/pagemap.h --- linux-2.6/inc...