Hi Charlie, On Thu, 2024-09-05 at 14:15 -0700, Charlie Jenkins wrote: > Some applications rely on placing data in free bits addresses allocated > by mmap. Various architectures (eg. x86, arm64, powerpc) restrict the > address returned by mmap to be less than the 48-bit address space, > unless the hint address uses more than 47 bits (the 48th bit is reserved > for the kernel address space). > > The riscv architecture needs a way to similarly restrict the virtual > address space. On the riscv port of OpenJDK an error is thrown if > attempted to run on the 57-bit address space, called sv57 [1]. golang > has a comment that sv57 support is not complete, but there are some > workarounds to get it to mostly work [2]. > > These applications work on x86 because x86 does an implicit 47-bit > restriction of mmap() address that contain a hint address that is less > than 48 bits. > > Instead of implicitly restricting the address space on riscv (or any > current/future architecture), provide a flag to the personality syscall > that can be used to ensure an application works in any arbitrary VA > space. A similar feature has already been implemented by the personality > syscall in ADDR_LIMIT_32BIT. > > This flag will also allow seemless compatibility between all > architectures, so applications like Go and OpenJDK that use bits in a > virtual address can request the exact number of bits they need in a > generic way. The flag can be checked inside of vm_unmapped_area() so > that this flag does not have to be handled individually by each > architecture. > > Link: > https://github.com/openjdk/jdk/blob/f080b4bb8a75284db1b6037f8c00ef3b1ef1add1/src/hotspot/cpu/riscv/vm_version_riscv.cpp#L79 > [1] > Link: > https://github.com/golang/go/blob/9e8ea567c838574a0f14538c0bbbd83c3215aa55/src/runtime/tagptr_64bit.go#L47 > [2] > > To: Arnd Bergmann <a...@arndb.de> > To: Richard Henderson <richard.hender...@linaro.org> > To: Ivan Kokshaysky <i...@jurassic.park.msu.ru> > To: Matt Turner <matts...@gmail.com> > To: Vineet Gupta <vgu...@kernel.org> > To: Russell King <li...@armlinux.org.uk> > To: Guo Ren <guo...@kernel.org> > To: Huacai Chen <chenhua...@kernel.org> > To: WANG Xuerui <ker...@xen0n.name> > To: Thomas Bogendoerfer <tsbog...@alpha.franken.de> > To: James E.J. Bottomley <james.bottom...@hansenpartnership.com> > To: Helge Deller <del...@gmx.de> > To: Michael Ellerman <m...@ellerman.id.au> > To: Nicholas Piggin <npig...@gmail.com> > To: Christophe Leroy <christophe.le...@csgroup.eu> > To: Naveen N Rao <nav...@kernel.org> > To: Alexander Gordeev <agord...@linux.ibm.com> > To: Gerald Schaefer <gerald.schae...@linux.ibm.com> > To: Heiko Carstens <h...@linux.ibm.com> > To: Vasily Gorbik <g...@linux.ibm.com> > To: Christian Borntraeger <borntrae...@linux.ibm.com> > To: Sven Schnelle <sv...@linux.ibm.com> > To: Yoshinori Sato <ys...@users.sourceforge.jp> > To: Rich Felker <dal...@libc.org> > To: John Paul Adrian Glaubitz <glaub...@physik.fu-berlin.de> > To: David S. Miller <da...@davemloft.net> > To: Andreas Larsson <andr...@gaisler.com> > To: Thomas Gleixner <t...@linutronix.de> > To: Ingo Molnar <mi...@redhat.com> > To: Borislav Petkov <b...@alien8.de> > To: Dave Hansen <dave.han...@linux.intel.com> > To: x...@kernel.org > To: H. Peter Anvin <h...@zytor.com> > To: Andy Lutomirski <l...@kernel.org> > To: Peter Zijlstra <pet...@infradead.org> > To: Muchun Song <muchun.s...@linux.dev> > To: Andrew Morton <a...@linux-foundation.org> > To: Liam R. Howlett <liam.howl...@oracle.com> > To: Vlastimil Babka <vba...@suse.cz> > To: Lorenzo Stoakes <lorenzo.stoa...@oracle.com> > To: Shuah Khan <sh...@kernel.org> > To: Christoph Hellwig <h...@infradead.org> > To: Michal Hocko <mho...@suse.com> > To: "Kirill A. Shutemov" <kir...@shutemov.name> > To: Chris Torek <chris.to...@gmail.com> > Cc: linux-a...@vger.kernel.org > Cc: linux-ker...@vger.kernel.org > Cc: linux-al...@vger.kernel.org > Cc: linux-snps-...@lists.infradead.org > Cc: linux-arm-ker...@lists.infradead.org > Cc: linux-c...@vger.kernel.org > Cc: loonga...@lists.linux.dev > Cc: linux-m...@vger.kernel.org > Cc: linux-par...@vger.kernel.org > Cc: linuxppc-dev@lists.ozlabs.org > Cc: linux-s...@vger.kernel.org > Cc: linux...@vger.kernel.org > Cc: sparcli...@vger.kernel.org > Cc: linux...@kvack.org > Cc: linux-kselft...@vger.kernel.org > Cc: linux-abi-de...@lists.sourceforge.net > Signed-off-by: Charlie Jenkins <char...@rivosinc.com> > > Changes in v2: > - Added much greater detail to cover letter > - Removed all code that touched architecture specific code and was able > to factor this out into all generic functions, except for flags that > needed to be added to vm_unmapped_area_info > - Made this an RFC since I have only tested it on riscv and x86 > - Link to v1: > https://lore.kernel.org/r/20240827-patches-below_hint_mmap-v1-0-46ff2eb90...@rivosinc.com > > Changes in v3: > - Use a personality flag instead of an mmap flag > - Link to v2: > https://lore.kernel.org/r/20240829-patches-below_hint_mmap-v2-0-638a28d9e...@rivosinc.com > > --- > Charlie Jenkins (2): > mm: Add personality flag to limit address to 47 bits > selftests/mm: Create ADDR_LIMIT_47BIT test > > include/uapi/linux/personality.h | 1 + > mm/mmap.c | 3 ++ > tools/testing/selftests/mm/.gitignore | 1 + > tools/testing/selftests/mm/Makefile | 1 + > tools/testing/selftests/mm/map_47bit_personality.c | 34 > ++++++++++++++++++++++ > 5 files changed, 40 insertions(+) > --- > base-commit: 5be63fc19fcaa4c236b307420483578a56986a37 > change-id: 20240827-patches-below_hint_mmap-b13d79ae1c55
Wow, this issue has been plaguing SPARC users for years already as the architecture uses a 52-bit virtual address space and Javascript engines such as the one in Firefox or Webkit have been crashing ever since. I should definitely give this series a try and see if that fixes Javascript crashes on SPARC. Thanks a lot for addressing this nasty long-standing problem! Adrian -- .''`. John Paul Adrian Glaubitz : :' : Debian Developer `. `' Physicist `- GPG: 62FF 8A75 84E0 2956 9546 0006 7426 3B37 F5B5 F913
