How much/what hardware does the rowhammer DRAM bug affects?
Georgi Guninski
guninski at guninski.com
Fri Sep 18 00:03:42 PDT 2015
On Fri, Sep 18, 2015 at 06:54:58AM +0000, jim bell wrote:
> From: Georgi Guninski <guninski at guninski.com>
>
> On Wed, Sep 16, 2015 at 11:46:26PM -0400, grarpamp wrote:
>
> >http://users.ece.cmu.edu/~omutlu/pub/dram-row-hammer_kim_talk_isca14.pdf
> >p. 32 of the PDF:
> >.– Simple ECC (e.g., SECDED) cannot prevent all errors
> >From wikipedia: Tests show that simple ECC solutions, providing
> >single-error correction and double-error detection (SECDED)
> >capabilities, are not able to correct or detect all observed
> >disturbance errors because some of them include more than two flipped
> >bits per memory word.[1]:8[11]:32
> >https://en.wikipedia.org/wiki/Row_hammer#cite_ref-isca14-talk_11-0
>
> But all single-bit and triple-bit errors are detectable by parity, and so are all double-bit errors using ECC. https://en.wikipedia.org/wiki/Dynamic_random-access_memory#Errors%5Fand%5Ferror%5Fcorrection
>
> Jim Bell
AFAICT Rowhammer (non-weaponized) publicly appeared in:
http://users.ece.cmu.edu/~yoonguk/papers/kim-isca14.pdf
Flipping Bits in Memory Without Accessing Them:
An Experimental Study of DRAM Disturbance Errors
(from 2014)
On p. 8:
Therefore, we conclude that SECDED is not failsafe against disturbance
errors.
Table 5. Uncorrectable multi-bit errors (in bold)
Consider publishing your claim as counterexample to the paper
(possibly on arxiv.org).
More information about the cypherpunks
mailing list