Re: 2.6.19 file content corruption on ext3


Hmm, should we not flush after clearing the dirty bit? That is, why does
ptep_clear_flush_dirty() need a flush after clearing that bit? does it
leak through in the tlb copy?

afaics you need to
1) clear
2) flush
3) check and go to 1) if needed

to be race free.



-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • Re: [patch -mm] i386: use pte_update_defer in ptep_test_and_clear_{dirty,young}
    ... that is why I think I did the original hack of having #defines without implementations - to ensure the flush stayed coupled with the use of pte_update_defer. ... If the preemption runs a kernel thread, which accesses the same memory for which you just modified the page table mappings, the TLB could still have a stale entry. ... Now, for regular user memory access, that might not be a problem, but if it is the kernel touching user memory through kmap, the kernel virtual address might well .. ...
    (Linux-Kernel)
  • Re: Page aging broken in 2.6
    ... >> responsible for the flush on archs where it is necessary, ... tlb that Manfred mentioned, the snoops can't get past a cr3 overwrite, ... SMP due the flood of broadcast IPIs it generates (I actually did that ... I believe flushing the tlb for every pte is reasonable only under ...
    (Linux-Kernel)
  • [PATCH/RFC] remove flush_tlb_pgtables
    ... -/* Flush a specified range of user mapping page tables from TLB. ... static inline void flush_tlb ...
    (Linux-Kernel)
  • [RFC/PATCH 2/12] remove flush_tlb_pgtables
    ... -/* Flush a specified range of user mapping page tables from TLB. ... static inline void flush_tlb ...
    (Linux-Kernel)
  • Re: Page aging broken in 2.6
    ... > the hash, not accessed = not in the hash. ... Returning to the "how to flush the tlb after clearing the young bit", ... clearing the pte in smp while we clear the dirty bit. ...
    (Linux-Kernel)