> `jdk.internal.foreign.SegmentFactories::allocateNativeInternal` assumes that > the underlying implementation of malloc aligns allocations on 16 byte > boundaries for 64 bit platforms, and 8 byte boundaries on 32 bit platforms. > So for any allocation where the requested alignment is less than or equal to > this default alignment it makes no adjustment. > > However, this assumption does not hold for all allocators. Specifically > jemallc, used by libc on FreeBSD will align small allocations on 8 or 4 byte > boundaries, respectively. This causes allocateNativeInternal to sometimes > return memory that is not properly aligned when the requested alignment is > exactly 16 bytes. > > To make sure we honour the requested alignment when it exaclty matches the > quantum as defined by MAX_MALLOC_ALIGN, this patch ensures that we adjust the > alignment also in this case. > > This should make no difference for platforms where malloc allready aligns on > the quantum, except for a few unnecessary trivial calculations. > > This work was sponsored by: The FreeBSD Foundation
Harald Eilertsen has updated the pull request incrementally with two additional commits since the last revision: - Second try to fix alignment for native segments Introducing a helper function as suggested by JornVernee to decide on the proper alignment based on the segment size. This work was sponsored by: The FreeBSD Foundation Co-authored-by: JornVernee - Test that native segments don't overlap This work was sponsored by: The FreeBSD Foundation ------------- Changes: - all: https://git.openjdk.org/jdk/pull/28235/files - new: https://git.openjdk.org/jdk/pull/28235/files/0d1bb665..2b8266f6 Webrevs: - full: https://webrevs.openjdk.org/?repo=jdk&pr=28235&range=01 - incr: https://webrevs.openjdk.org/?repo=jdk&pr=28235&range=00-01 Stats: 24 lines in 2 files changed: 17 ins; 4 del; 3 mod Patch: https://git.openjdk.org/jdk/pull/28235.diff Fetch: git fetch https://git.openjdk.org/jdk.git pull/28235/head:pull/28235 PR: https://git.openjdk.org/jdk/pull/28235
