[Tarantool-patches] [PATCH luajit 2/2] Linux/ARM64: Make mremap() non-moving due to VA space woes.
imun at tarantool.org
Sun Aug 1 13:36:33 MSK 2021
Thanks for the fixes! LGTM, except the single typo.
On 28.07.21, Sergey Kaplun wrote:
> The new commit message is the following:
> Linux/ARM64: Make mremap() non-moving due to VA space woes.
> This reduces overall performance on ARM64, but we have no choice.
> Linux kernel default userspace VA is 48 bit, but we'd need 47 bit.
> mremap() ignores address hints due to a kernel API issue. The mapping
> may move to an undesired address which will cause an assert or crash.
> Reported by Raymond W. Ko.
> (cherry picked from commit 67dbec82f4f05a416a78a560a726553beaa7a223)
> 47-bit VA space is required by LuaJIT for keeping a GC object pointer in
> TValue. In case of huge blobs that are mapped directly, `mremap()` may
> move the chunk out of 47-bit range of VA space on ARM64. `mremap()`
> accepts the fifth argument (new address hint) only with MREMAP_FIXED
> flag. In that case it unmaps any other mapping to specified address.
> To avoid this behaviour this patch restricts `mremap()` to relocate
> the mapping to a new virtual address by set CALL_MREMAP_NOMOVE flag
> instead of CALL_MREMAP_MAYMOVE for arm64 architecture.
> Sergey Kaplun:
> * added the description and the test for the problem
> Needed for tarantool/tarantool#6154
Minor: Why #5629 is not mentioned?
> Best regards,
> Sergey Kaplun
More information about the Tarantool-patches