| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAPcyv4hH2733FEs4bAroa4zscM_PkshEWEmRw7LwXwVJb9pDWg@mail.gmail.com>
Date: Sat, 4 May 2019 12:26:13 -0700
From: Dan Williams <dan.j.williams@...el.com>
To: Pavel Tatashin <pasha.tatashin@...een.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Michal Hocko <mhocko@...e.com>,
Vlastimil Babka <vbabka@...e.cz>,
Logan Gunthorpe <logang@...tatee.com>,
linux-mm <linux-mm@...ck.org>,
linux-nvdimm <linux-nvdimm@...ts.01.org>,
LKML <linux-kernel@...r.kernel.org>,
David Hildenbrand <david@...hat.com>
Subject: Re: [PATCH v6 03/12] mm/sparsemem: Add helpers track active portions
of a section at boot
On Thu, May 2, 2019 at 9:12 AM Pavel Tatashin <pasha.tatashin@...een.com> wrote:
>
> On Wed, Apr 17, 2019 at 2:53 PM Dan Williams <dan.j.williams@...el.com> wrote:
> >
> > Prepare for hot{plug,remove} of sub-ranges of a section by tracking a
> > section active bitmask, each bit representing 2MB (SECTION_SIZE (128M) /
> > map_active bitmask length (64)). If it turns out that 2MB is too large
> > of an active tracking granularity it is trivial to increase the size of
> > the map_active bitmap.
>
> Please mention that 2M on Intel, and 16M on Arm64.
>
> >
> > The implications of a partially populated section is that pfn_valid()
> > needs to go beyond a valid_section() check and read the sub-section
> > active ranges from the bitmask.
> >
> > Cc: Michal Hocko <mhocko@...e.com>
> > Cc: Vlastimil Babka <vbabka@...e.cz>
> > Cc: Logan Gunthorpe <logang@...tatee.com>
> > Signed-off-by: Dan Williams <dan.j.williams@...el.com>
> > ---
> > include/linux/mmzone.h | 29 ++++++++++++++++++++++++++++-
> > mm/page_alloc.c | 4 +++-
> > mm/sparse.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
> > 3 files changed, 79 insertions(+), 2 deletions(-)
> >
> > diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> > index 6726fc175b51..cffde898e345 100644
> > --- a/include/linux/mmzone.h
> > +++ b/include/linux/mmzone.h
> > @@ -1175,6 +1175,8 @@ struct mem_section_usage {
> > unsigned long pageblock_flags[0];
> > };
> >
> > +void section_active_init(unsigned long pfn, unsigned long nr_pages);
> > +
> > struct page;
> > struct page_ext;
> > struct mem_section {
> > @@ -1312,12 +1314,36 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn)
> >
> > extern int __highest_present_section_nr;
> >
> > +static inline int section_active_index(phys_addr_t phys)
> > +{
> > + return (phys & ~(PA_SECTION_MASK)) / SECTION_ACTIVE_SIZE;
>
> How about also defining SECTION_ACTIVE_SHIFT like this:
>
> /* BITS_PER_LONG = 2^6 */
> #define BITS_PER_LONG_SHIFT 6
> #define SECTION_ACTIVE_SHIFT (SECTION_SIZE_BITS - BITS_PER_LONG_SHIFT)
> #define SECTION_ACTIVE_SIZE (1 << SECTION_ACTIVE_SHIFT)
>
> The return above would become:
> return (phys & ~(PA_SECTION_MASK)) >> SECTION_ACTIVE_SHIFT;
>
> > +}
> > +
> > +#ifdef CONFIG_SPARSEMEM_VMEMMAP
> > +static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
> > +{
> > + int idx = section_active_index(PFN_PHYS(pfn));
> > +
> > + return !!(ms->usage->map_active & (1UL << idx));
> > +}
> > +#else
> > +static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
> > +{
> > + return 1;
> > +}
> > +#endif
> > +
> > #ifndef CONFIG_HAVE_ARCH_PFN_VALID
> > static inline int pfn_valid(unsigned long pfn)
> > {
> > + struct mem_section *ms;
> > +
> > if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
> > return 0;
> > - return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
> > + ms = __nr_to_section(pfn_to_section_nr(pfn));
> > + if (!valid_section(ms))
> > + return 0;
> > + return pfn_section_valid(ms, pfn);
> > }
> > #endif
> >
> > @@ -1349,6 +1375,7 @@ void sparse_init(void);
> > #define sparse_init() do {} while (0)
> > #define sparse_index_init(_sec, _nid) do {} while (0)
> > #define pfn_present pfn_valid
> > +#define section_active_init(_pfn, _nr_pages) do {} while (0)
> > #endif /* CONFIG_SPARSEMEM */
> >
> > /*
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index f671401a7c0b..c9ad28a78018 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -7273,10 +7273,12 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
> >
> > /* Print out the early node map */
> > pr_info("Early memory node ranges\n");
> > - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
> > + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
> > pr_info(" node %3d: [mem %#018Lx-%#018Lx]\n", nid,
> > (u64)start_pfn << PAGE_SHIFT,
> > ((u64)end_pfn << PAGE_SHIFT) - 1);
> > + section_active_init(start_pfn, end_pfn - start_pfn);
> > + }
> >
> > /* Initialise every node */
> > mminit_verify_pageflags_layout();
> > diff --git a/mm/sparse.c b/mm/sparse.c
> > index f87de7ad32c8..5ef2f884c4e1 100644
> > --- a/mm/sparse.c
> > +++ b/mm/sparse.c
> > @@ -210,6 +210,54 @@ static inline unsigned long first_present_section_nr(void)
> > return next_present_section_nr(-1);
> > }
> >
> > +static unsigned long section_active_mask(unsigned long pfn,
> > + unsigned long nr_pages)
> > +{
> > + int idx_start, idx_size;
> > + phys_addr_t start, size;
> > +
> > + if (!nr_pages)
> > + return 0;
> > +
> > + start = PFN_PHYS(pfn);
> > + size = PFN_PHYS(min(nr_pages, PAGES_PER_SECTION
> > + - (pfn & ~PAGE_SECTION_MASK)));
> > + size = ALIGN(size, SECTION_ACTIVE_SIZE);
> > +
> > + idx_start = section_active_index(start);
> > + idx_size = section_active_index(size);
> > +
> > + if (idx_size == 0)
> > + return -1;
> > + return ((1UL << idx_size) - 1) << idx_start;
> > +}
> > +
> > +void section_active_init(unsigned long pfn, unsigned long nr_pages)
> > +{
> > + int end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
> > + int i, start_sec = pfn_to_section_nr(pfn);
> > +
> > + if (!nr_pages)
> > + return;
> > +
> > + for (i = start_sec; i <= end_sec; i++) {
> > + struct mem_section *ms;
> > + unsigned long mask;
> > + unsigned long pfns;
> > +
> > + pfns = min(nr_pages, PAGES_PER_SECTION
> > + - (pfn & ~PAGE_SECTION_MASK));
> > + mask = section_active_mask(pfn, pfns);
> > +
> > + ms = __nr_to_section(i);
> > + pr_debug("%s: sec: %d mask: %#018lx\n", __func__, i, mask);
> > + ms->usage->map_active = mask;
> > +
> > + pfn += pfns;
> > + nr_pages -= pfns;
> > + }
> > +}
>
> For some reasons the above code is confusing to me. It seems all the
> code supposed to do is set all map_active to -1, and trim the first
> and last sections (can be the same section of course). So, I would
> replace the above two functions with one function like this:
>
> void section_active_init(unsigned long pfn, unsigned long nr_pages)
> {
> int end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
> int i, idx, start_sec = pfn_to_section_nr(pfn);
> struct mem_section *ms;
>
> if (!nr_pages)
> return;
>
> for (i = start_sec; i <= end_sec; i++) {
> ms = __nr_to_section(i);
> ms->usage->map_active = ~0ul;
> }
>
> /* Might need to trim active pfns from the beginning and end */
> idx = section_active_index(PFN_PHYS(pfn));
> ms = __nr_to_section(start_sec);
> ms->usage->map_active &= (~0ul << idx);
>
> idx = section_active_index(PFN_PHYS(pfn + nr_pages -1));
> ms = __nr_to_section(end_sec);
> ms->usage->map_active &= (~0ul >> (BITS_PER_LONG - idx - 1));
> }
I like the cleanup, but one of the fixes in v7 resulted in the
realization that a given section may be populated twice at init time.
For example, enabling that pr_debug() yields:
section_active_init: sec: 12 mask: 0x00000003ffffffff
section_active_init: sec: 12 mask: 0xe000000000000000
So, the implementation can't blindly clear bits based on the current
parameters. However, I'm switching this code over to use bitmap_*()
helpers which should help with the readability.
Powered by blists - more mailing lists