x86/mm/tlb: Ignore f->new_tlb_gen when zero
authorNadav Amit <namit@vmware.com>
Sun, 10 Jul 2022 23:28:37 +0000 (16:28 -0700)
committerDave Hansen <dave.hansen@linux.intel.com>
Tue, 19 Jul 2022 16:04:52 +0000 (09:04 -0700)
commit8f1d56f64f8d6b80dea2d1978d10071132a695c5
treec2cdb5350b9b76f53f5e9ee653d47b16ca9dbac1
parent54ee1844047c1df015ab2679a4f55564a3aa1fa1
x86/mm/tlb: Ignore f->new_tlb_gen when zero

Commit aa44284960d5 ("x86/mm/tlb: Avoid reading mm_tlb_gen when
possible") introduced an optimization to skip superfluous TLB
flushes based on the generation provided in flush_tlb_info.

However, arch_tlbbatch_flush() does not provide any generation in
flush_tlb_info and populates the flush_tlb_info generation with
0.  This 0 is causes the flush_tlb_info to be interpreted as a
superfluous, old flush.  As a result, try_to_unmap_one() would
not perform any TLB flushes.

Fix it by checking whether f->new_tlb_gen is nonzero. Zero value
is anyhow is an invalid generation value. To avoid future
confusion, introduce TLB_GENERATION_INVALID constant and use it
properly. Add warnings to ensure no partial flushes are done with
TLB_GENERATION_INVALID or when f->mm is NULL, since this does not
make any sense.

In addition, add the missing unlikely().

[ dhansen: change VM_BUG_ON() -> VM_WARN_ON(), clarify changelog ]

Fixes: aa44284960d5 ("x86/mm/tlb: Avoid reading mm_tlb_gen when possible")
Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Hugh Dickins <hughd@google.com>
Link: https://lkml.kernel.org/r/20220710232837.3618-1-namit@vmware.com
arch/x86/include/asm/tlbflush.h
arch/x86/mm/tlb.c