mm: add a call to flush_cache_vmap() in vmap_pfn()
authorAlexandre Ghiti <alexghiti@rivosinc.com>
Wed, 9 Aug 2023 16:46:33 +0000 (18:46 +0200)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Wed, 30 Aug 2023 14:11:06 +0000 (16:11 +0200)
commit07fad410aa6e90131cd1ba8d12bd1f9488f85af5
treefecc8bdb7982eb723d033f2d4a74300bf1e6721d
parenta8a60bc8027e099b8dd9e13b49b393db2d940004
mm: add a call to flush_cache_vmap() in vmap_pfn()

commit a50420c79731fc5cf27ad43719c1091e842a2606 upstream.

flush_cache_vmap() must be called after new vmalloc mappings are installed
in the page table in order to allow architectures to make sure the new
mapping is visible.

It could lead to a panic since on some architectures (like powerpc),
the page table walker could see the wrong pte value and trigger a
spurious page fault that can not be resolved (see commit f1cb8f9beba8
("powerpc/64s/radix: avoid ptesync after set_pte and
ptep_set_access_flags")).

But actually the patch is aiming at riscv: the riscv specification
allows the caching of invalid entries in the TLB, and since we recently
removed the vmalloc page fault handling, we now need to emit a tlb
shootdown whenever a new vmalloc mapping is emitted
(https://lore.kernel.org/linux-riscv/20230725132246.817726-1-alexghiti@rivosinc.com/).
That's a temporary solution, there are ways to avoid that :)

Link: https://lkml.kernel.org/r/20230809164633.1556126-1-alexghiti@rivosinc.com
Fixes: 3e9a9e256b1e ("mm: add a vmap_pfn function")
Reported-by: Dylan Jhong <dylan@andestech.com>
Closes: https://lore.kernel.org/linux-riscv/ZMytNY2J8iyjbPPy@atctrx.andestech.com/
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Dylan Jhong <dylan@andestech.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
mm/vmalloc.c