[Gnif] had a recent hard drive failure in his home server. When rebuilding his RAID array, he decided to update to the ZFS file system. While researching ZFS, [Gnif] learned that the file system allows for a small USB cache disk to greatly improve his disk performance. Since USB is rather slow, [Gnif] had an idea to try to use an old i-RAM PCI card instead.
The problem was that he didn’t have any free PCI slots left in his home server. It didn’t take long for [Gnif] to realize that the PCI card was only using the PCI slot for power. All of the data transfer is actually done via a SATA cable. [Gnif] decided that he could likely get by without an actual PCI slot with just a bit of hacking.
[Gnif] desoldered a PCI socket from an old faulty motherboard, losing half of the pins in the process. Luckily, the pins he needed still remained. [Gnif] knew that DDR memory can be very power-hungry. This meant that he couldn’t only solder one wire for each of the 3v, 5v, 12v, and ground pins. He had to connect all of them in order to share the current load. All in all, this ended up being about 20 pins. He later tested the current draw and found it reached as high as 1.2 amps, confirming his earlier decision. Finally, the reset pin needed to be pulled to 3.3V in order to make the disk accessible.
All of the wires from his adapter were run to Molex connectors. This allows [Gnif] to power the device from a computer power supply. All of the connections were covered in hot glue to prevent them from wriggling lose.
We missed the original announcement, but Apple unveiled more than just the iPad Mini at their last event. They’ve got a new storage system called Fusion Drive which is supposed to combine the access speeds of solid state with the storage density of platter drives. When you look just under the surface what you’re really seeing is a disc drive with grossly enlarged cache in the form of an SSD drive. How about moving from the 64 MB or so of cache seen on many large hard drives today to something like 64GB?
Well you don’t have to wait for Apple to do it. [Patrick Stein] gave it a shot using command line tools to combine an SSD with a physical drive. Sure, it’s not an all-in-one solution, but it is a pretty good proof. The linchpin that will really make it possible is a low-level driver that can handle the caching on the SDD, while ensuring that the data eventually makes it to the platter for long-term storage.
In modern computer systems, the biggest bottleneck of information tends to be in communicating with the hard disks. High seek times and relatively slow transmission rates when compared to RAM speeds can add up quickly. This was a necessary evil back when RAM space and costs were at a premium, but now it is not uncommon to see 4GB of RAM on laptops, and even 12GB on desktops. For users whose primary computer use is browsing the internet (either for work, writing articles, or lolcats) and have some extra RAM, moving the browser cache to the RAM from the hard disk is a definite option for increasing speed.
In Linux systems (specifically Fedora and Ubuntu systems), this can be achieved for Chrome and Firefox by creating a larger ramdisk, mounting the ramdisk after boot, and then setting the browser of choice to use that ramdisk as a cache. The necessary commands to do this are readily available on the internet, which makes life easy. Using ramdisks for performance boosts are not exclusive to browsers, and can be used for other software such as Nagios for example.
We have previously covered a tool called Espérance DV for moving cache to RAM in Mac OSX, and for any Windows users feeling left out, there are ways of making Firefox bend to your will. Obviously you will see an increase in RAM use (duh), but this shouldn’t be a problem unless you are running out of free RAM on your system. Remember, free RAM is wasted RAM.
Frozen Cache is a blog dedicated to a novel way to prevent cold boot attacks. Last year the cold boot team demonstrated that they could extract encryption keys from a machine’s RAM by placing it in another system (or the same machine by doing a quick reboot). Frozen Cache aims to prevent this by storing the encryption key in the CPU’s cache. It copies the key out of RAM into the CPU’s registers and then zeroes it in RAM. It then freezes the cache and attempts to write the key back to RAM. The key is pushed into the cache, but isn’t written back to RAM.
The first major issue with this is the performance hit. You end up kneecapping the processor when you freeze the cache and the author suggests that you’d only do this when the screen is locked. We asked cold boot team member [Jacob Appelbaum] what he thought of the approach. He pointed out that the current cold boot attack reconstructs the key from the full keyschedule, which according to the Frozen Cache blog, still remains in RAM. They aren’t grabbing the specific key bits, but recreating it from all this redundant information in memory. At best, Frozen Cache is attempting to build a ‘ghetto crypto co-processor’.
We stand by our initial response to the cold boot attacks: It’s going to take a fundamental redesign of RAM before this is solved.
This is unfortunately another story we missed out on while we were trying to keep things from burning down. We told you that [Jonathan Zdziarski] was going to demonstrate iPhone lock code bypassing in a webcast. The real surprise came when he pointed out that the iPhone takes a screenshot every time you use the home button. It does this so it can do the scaling animation. The image files are presumably deleted immediately, but as we’ve seen before it’s nearly impossible to guarantee deletion on a solid state device. There’s currently no way to disable this behavior. So, even privacy conscious people have no way to prevent their iPhone from filling up storage with screenshots of all their text message, email, and browsing activities. Hopefully Apple will address this problem just like they did with the previous secure erase issue. O’Reilly promises to publish the full webcast soon.
UPDATE: Full audio of the webcast is now available
Today Black Hat held a preview webcast with [Dan Kaminsky] about the massive DNS bug he discovered. On July 8th, multiple vendors announced a patch for an undisclosed DNS vulnerability. [Dan Kaminisky] did not release the details of the vulnerability at that time, but encouraged security researchers to not release their work, if they did happen to discover the bug. On the 21st, the full description of the vulnerability was leaked.
In today’s webcast, [Dan] covered how he felt about the handling of the vulnerability and answered a few questions about it. He started out by talking about how he stumbled across the bug; he was working on how to make content distribution faster by using DNS to find the server closest to the client. The new attack works because DNS servers not using port randomization make it easy for the attacker to forge a response. You can read the specifics of the attack here.
Continue reading “DNS cache poisoning webcast”
We’ve been tracking Metasploit commits since Matasano’s premature publication of [Dan Kaminsky]’s DNS cache poisoning flaw on Monday knowing full well that a functional exploit would be coming soon. Only two hours ago [HD Moore] and [I)ruid] added a module to the Metasploit Project that will let anyone test the vulnerability (with comment: “ZOMG. What is this? >:-)“). [HD] told Threat Level that it doesn’t work yet for domains that are already cached by the DNS server, but it will automatically wait for the cached entry to expire and then complete the attack. You can read more about the bailiwicked_host.rb module in CAU’s advisory. For a more detailed description of how the attack works, see this mirror of Matason’s post. You can check if the DNS server you are using is vulnerable by using the tool on [Dan]’s site.