Switch from per mm_struct to per pmd page table lock by enabling
ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
large system.
I'm not sure if there is contention on mm->page_table_lock. Given
the option comes at no cost (apart from initializing more spin
locks), why not enable it now.
We only do so when pmd is not folded, so we don't mistakenly call
pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc().
Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
By selecting HAVE_RCU_TABLE_INVALIDATE, we can rely on tlb_flush() being
called if we fail to batch table pages for freeing. This in turn allows
us to postpone walk-cache invalidation until tlb_finish_mmu(), which
avoids lots of unnecessary DSBs and means we can shoot down the ASID if
the range is large enough.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Now that the core mmu_gather code keeps track of both the levels of page
table cleared and also whether or not these entries correspond to
intermediate entries, we can use this in our tlb_flush() callback to
reduce the number of invalidations we issue as well as their scope.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
If there's one thing the RCU-based table freeing doesn't need, it's more
ifdeffery.
Remove the redundant !CONFIG_HAVE_RCU_TABLE_FREE code, since this option
is unconditionally selected in our Kconfig.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
When we are unmapping intermediate page-table entries or huge pages, we
don't need to issue a TLBI instruction for every PAGE_SIZE chunk in the
VA range being unmapped.
Allow the invalidation stride to be passed to __flush_tlb_range(), and
adjust our "just nuke the ASID" heuristic to take this into account.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
As of commit fd1102f0aa ("mm: mmu_notifier fix for tlb_end_vma"),
asm-generic/tlb.h now calls tlb_flush() from a static inline function,
so we need to make sure that it's declared before #including the
asm-generic header in the arch header.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 2c4541e24c ("mm: use vma_init() to initialize VMAs on stack and
data segments") tried to initialize various left-over ad-hoc vma's
"properly", but actually made things worse for the temporary vma's used
for TLB flushing.
vma_init() doesn't actually initialize all of the vma, just a few
fields, so doing something like
- struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+ struct vm_area_struct vma;
+
+ vma_init(&vma, tlb->mm);
was actually very bad: instead of having a nicely initialized vma with
every field but "vm_mm" zeroed, you'd have an entirely uninitialized vma
with only a couple of fields initialized. And they weren't even fields
that the code in question mostly cared about.
The flush_tlb_range() function takes a "struct vma" rather than a
"struct mm_struct", because a few architectures actually care about what
kind of range it is - being able to only do an ITLB flush if it's a
range that doesn't have data accesses enabled, for example. And all the
normal users already have the vma for doing the range invalidation.
But a few people want to call flush_tlb_range() with a range they just
made up, so they also end up using a made-up vma. x86 just has a
special "flush_tlb_mm_range()" function for this, but other
architectures (arm and ia64) do the "use fake vma" thing instead, and
thus got caught up in the vma_init() changes.
At the same time, the TLB flushing code really doesn't care about most
other fields in the vma, so vma_init() is just unnecessary and
pointless.
This fixes things by having an explicit "this is just an initializer for
the TLB flush" initializer macro, which is used by the arm/arm64/ia64
people who mis-use this interface with just a dummy vma.
Fixes: 2c4541e24c ("mm: use vma_init() to initialize VMAs on stack and data segments")
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make sure to initialize all VMAs properly, not only those which come
from vm_area_cachep.
Link: http://lkml.kernel.org/r/20180724121139.62570-3-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The TLB gather code sets fullmm=1 when tearing down the entire address
space for an mm_struct on exit or execve. Given that the ASID allocator
will never re-allocate a dirty ASID, this flushing is not needed and can
simply be avoided in the flushing code.
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The flush_tlb_page() function is used on user address ranges when PTEs
(or PMDs/PUDs for huge pages) were changed (attributes or clearing). For
such cases, it is more efficient to invalidate only the last level of
the TLB with the "tlbi vale1is" instruction.
In the TLB shoot-down case, the TLB caching of the intermediate page
table levels (pmd, pud, pgd) is handled by __flush_tlb_pgtable() via the
__(pte|pmd|pud)_free_tlb() functions and it is not deferred to
tlb_finish_mmu() (as of commit 285994a62c - "arm64: Invalidate the TLB
corresponding to intermediate page table levels"). The tlb_flush()
function only needs to invalidate the TLB for the last level of page
tables; the __flush_tlb_range() function gains a fourth argument for
last level TLBI.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
We would want to use number of page table level to define mm_struct.
Let's expose it as CONFIG_PGTABLE_LEVELS.
ARM64_PGTABLE_LEVELS is renamed to PGTABLE_LEVELS and defined before
sourcing init/Kconfig: arch/Kconfig will define default value and it's
sourced from init/Kconfig.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The ARM architecture allows the caching of intermediate page table
levels and page table freeing requires a sequence like:
pmd_clear()
TLB invalidation
pte page freeing
With commit 5e5f6dc105 (arm64: mm: enable HAVE_RCU_TABLE_FREE logic),
the page table freeing batching was moved from tlb_remove_page() to
tlb_remove_table(). The former takes care of TLB invalidation as this is
also shared with pte clearing and page cache page freeing. The latter,
however, does not invalidate the TLBs for intermediate page table levels
as it probably relies on the architecture code to do it if required.
When the mm->mm_users < 2, tlb_remove_table() does not do any batching
and page table pages are freed before tlb_finish_mmu() which performs
the actual TLB invalidation.
This patch introduces __tlb_flush_pgtable() for arm64 and calls it from
the {pte,pmd,pud}_free_tlb() directly without relying on deferred page
table freeing.
Fixes: 5e5f6dc105 arm64: mm: enable HAVE_RCU_TABLE_FREE logic
Reported-by: Jon Masters <jcm@redhat.com>
Tested-by: Jon Masters <jcm@redhat.com>
Tested-by: Steve Capper <steve.capper@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
On architectures with hardware broadcasting of TLB invalidation messages
, it makes sense to reduce the range of the mmu_gather structure when
unmapping page ranges based on the dirty address information passed to
tlb_remove_tlb_entry.
arm64 already does this by directly manipulating the start/end fields
of the gather structure, but this confuses the generic code which
does not expect these fields to change and can end up calculating
invalid, negative ranges when forcing a flush in zap_pte_range.
This patch moves the minimal range calculation out of the arm64 code
and into the generic implementation, simplifying zap_pte_range in the
process (which no longer needs to care about start/end, since they will
point to the appropriate ranges already). With the range being tracked
by core code, the need_flush flag is dropped in favour of checking that
the end of the range has actually been set.
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King - ARM Linux <linux@arm.linux.org.uk>
Cc: Michal Simek <monstr@monstr.eu>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
In order to implement fast_get_user_pages we need to ensure that the page
table walker is protected from page table pages being freed from under it.
This patch enables HAVE_RCU_TABLE_FREE, any page table pages belonging to
address spaces with multiple users will be call_rcu_sched freed. Meaning
that disabling interrupts will block the free and protect the fast gup
page walker.
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Tested-by: Dann Frazier <dann.frazier@canonical.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rather than having several Kconfig options, define int
ARM64_PGTABLE_LEVELS which will be also useful in converting some of the
pgtable macros.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Jungseok Lee <jungseoklee85@gmail.com>
This patch implements 4 levels of translation tables since 3 levels
of page tables with 4KB pages cannot support 40-bit physical address
space described in [1] due to the following issue.
It is a restriction that kernel logical memory map with 4KB + 3 levels
(0xffffffc000000000-0xffffffffffffffff) cannot cover RAM region from
544GB to 1024GB in [1]. Specifically, ARM64 kernel fails to create
mapping for this region in map_mem function since __phys_to_virt for
this region reaches to address overflow.
If SoC design follows the document, [1], over 32GB RAM would be placed
from 544GB. Even 64GB system is supposed to use the region from 544GB
to 576GB for only 32GB RAM. Naturally, it would reach to enable 4 levels
of page tables to avoid hacking __virt_to_phys and __phys_to_virt.
However, it is recommended 4 levels of page table should be only enabled
if memory map is too sparse or there is about 512GB RAM.
References
----------
[1]: Principles of ARM Memory Maps, White Paper, Issue C
Signed-off-by: Jungseok Lee <jays.lee@samsung.com>
Reviewed-by: Sungjinn Chung <sungjinn.chung@samsung.com>
Acked-by: Kukjin Kim <kgene.kim@samsung.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: Steve Capper <steve.capper@linaro.org>
[catalin.marinas@arm.com: MEMBLOCK_INITIAL_LIMIT removed, same as PUD_SIZE]
[catalin.marinas@arm.com: early_ioremap_init() updated for 4 levels]
[catalin.marinas@arm.com: 48-bit VA depends on BROKEN until KVM is fixed]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Jungseok Lee <jungseoklee85@gmail.com>
This patch adds virtual address space size and a level of translation
tables to kernel configuration. It facilicates introduction of
different MMU options, such as 4KB + 4 levels, 16KB + 4 levels and
64KB + 3 levels, easily.
The idea is based on the discussion with Catalin Marinas:
http://www.spinics.net/linux/lists/arm-kernel/msg319552.html
Signed-off-by: Jungseok Lee <jays.lee@samsung.com>
Reviewed-by: Sungjinn Chung <sungjinn.chung@samsung.com>
Acked-by: Kukjin Kim <kgene.kim@samsung.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Jungseok Lee <jungseoklee85@gmail.com>
When arm64 moved over to the core mmu_gather, it lost the logic to
flush THP TLB entries (tlb_remove_pmd_tlb_entry was removed and the
core implementation only signals that the mmu_gather needs a flush).
This patch ensures that tlb_add_flush is called for THP TLB entries.
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Over the past couple of years, the generic mmu_gather gained range
tracking - 597e1c3580 (mm/mmu_gather: enable tlb flush range in generic
mmu_gather), 2b047252d0 (Fix TLB gather virtual address range
invalidation corner cases) - and tlb_fast_mode() has been removed -
29eb77825c (arch, mm: Remove tlb_fast_mode()).
The new mmu_gather structure is now suitable for arm64 and this patch
converts the arch asm/tlb.h to the generic code. One functional
difference is the shift_arg_pages() case where previously the code was
flushing the full mm (no tlb_start_vma call) but now it flushes the
range given to tlb_gather_mmu() (possibly slightly more efficient
previously).
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Ben Tebulin reported:
"Since v3.7.2 on two independent machines a very specific Git
repository fails in 9/10 cases on git-fsck due to an SHA1/memory
failures. This only occurs on a very specific repository and can be
reproduced stably on two independent laptops. Git mailing list ran
out of ideas and for me this looks like some very exotic kernel issue"
and bisected the failure to the backport of commit 53a59fc67f ("mm:
limit mmu_gather batching to fix soft lockups on !CONFIG_PREEMPT").
That commit itself is not actually buggy, but what it does is to make it
much more likely to hit the partial TLB invalidation case, since it
introduces a new case in tlb_next_batch() that previously only ever
happened when running out of memory.
The real bug is that the TLB gather virtual memory range setup is subtly
buggered. It was introduced in commit 597e1c3580 ("mm/mmu_gather:
enable tlb flush range in generic mmu_gather"), and the range handling
was already fixed at least once in commit e6c495a96c ("mm: fix the TLB
range flushed when __tlb_remove_page() runs out of slots"), but that fix
was not complete.
The problem with the TLB gather virtual address range is that it isn't
set up by the initial tlb_gather_mmu() initialization (which didn't get
the TLB range information), but it is set up ad-hoc later by the
functions that actually flush the TLB. And so any such case that forgot
to update the TLB range entries would potentially miss TLB invalidates.
Rather than try to figure out exactly which particular ad-hoc range
setup was missing (I personally suspect it's the hugetlb case in
zap_huge_pmd(), which didn't have the same logic as zap_pte_range()
did), this patch just gets rid of the problem at the source: make the
TLB range information available to tlb_gather_mmu(), and initialize it
when initializing all the other tlb gather fields.
This makes the patch larger, but conceptually much simpler. And the end
result is much more understandable; even if you want to play games with
partial ranges when invalidating the TLB contents in chunks, now the
range information is always there, and anybody who doesn't want to
bother with it won't introduce subtle bugs.
Ben verified that this fixes his problem.
Reported-bisected-and-tested-by: Ben Tebulin <tebulin@googlemail.com>
Build-testing-by: Stephen Rothwell <sfr@canb.auug.org.au>
Build-testing-by: Richard Weinberger <richard.weinberger@gmail.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Bring Transparent HugePage support to ARM. The size of a
transparent huge page depends on the normal page size. A
transparent huge page is always represented as a pmd.
If PAGE_SIZE is 4KB, THPs are 2MB.
If PAGE_SIZE is 64KB, THPs are 512MB.
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
This patch adds the TLB maintenance functions. There is no distinction
made between the I and D TLBs. TLB maintenance operations are
automatically broadcast between CPUs in hardware. The inner-shareable
operations are always present, even on UP systems.
NOTE: Large part of this patch to be dropped once Peter Z's generic
mmu_gather patches are merged.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Nicolas Pitre <nico@linaro.org>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
