On March 19, 2017 1:26:58 AM PDT, "Kirill A. Shutemov" [off-list ref] wrote:

On Mar 19, 2017 09:25, "Aneesh Kumar K.V"
[off-list ref]
wrote:

"Kirill A. Shutemov" [off-list ref] writes:

quoted

On Fri, Mar 17, 2017 at 11:23:54PM +0530, Aneesh Kumar K.V wrote:

quoted

"Kirill A. Shutemov" [off-list ref] writes:

quoted

On x86, 5-level paging enables 56-bit userspace virtual address

space.

quoted

quoted

quoted

Not all user space is ready to handle wide addresses. It's known

that

quoted

quoted

quoted

at least some JIT compilers use higher bits in pointers to encode

their

quoted

quoted

quoted

information. It collides with valid pointers with 5-level paging

and

quoted

quoted

quoted

leads to crashes.

To mitigate this, we are not going to allocate virtual address

space

quoted

quoted

quoted

above 47-bit by default.

But userspace can ask for allocation from full address space by
specifying hint address (with or without MAP_FIXED) above 47-bits.

If hint address set above 47-bit, but MAP_FIXED is not specified,

we
try

quoted

quoted

quoted

to look for unmapped area by specified address. If it's already
occupied, we look for unmapped area in *full* address space,

rather
than

quoted

quoted

quoted

from 47-bit window.

This approach helps to easily make application's memory allocator

aware

quoted

quoted

quoted

about large address space without manually tracking allocated

virtual

quoted

quoted

quoted

address space.

So if I have done a successful mmap which returned > 128TB what

should a

quoted

quoted

following mmap(0,...) return ? Should that now search the *full*

address

quoted

quoted

space or below 128TB ?

No, I don't think so. And this implementation doesn't do this.

It's safer this way: if an library can't handle high addresses, it's
better not to switch it automagically to full address space if other

part

quoted

of the process requested high address.

What is the epectation when the hint addr is below 128TB but addr + len

quoted

128TB ? Should such mmap request fail ?


Yes, I believe so.

This *better* be conditional on some kind of settable limit.  Having a barrier in the middle of the address space for no apparent reason to "clean" software is insane.
-- 
Sent from my Android device with K-9 Mail. Please excuse my brevity.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>