PCDVD¼Æ¦ì¬ì§Þ°Q½×°Ï

PCDVD¼Æ¦ì¬ì§Þ°Q½×°Ï (https://www.pcdvd.com.tw/index.php)
-   ¨t²Î²Õ¥ó (https://www.pcdvd.com.tw/forumdisplay.php?f=19)
-   -   Intel CPUÃn¦w¥þBUG¡A­×´_bug«á·|«d®z¨t²Î30%ªº©Ê¯à (https://www.pcdvd.com.tw/showthread.php?t=1140120)

¸ô¹L 2018-01-04 01:16 AM

¤Þ¥Î:
§@ªÌflorance
AMD TLB bug ¸ò Intel ³o¦¸ªº¤ñ°_¨Ó¬O¤p§Å¨£¤j§Å¤F...
AMD TLB ¬O¦b¥X³f¤£¤[«áµo²{, ÁÙ¯à¥Î BIOS ­×¥¿...

Intel ³o­Ó¯à¾î¸ó10¦~ªº bug...

ªº½T
³o¦¸Intelªº¥]¤£¹³TLB BUG¨º»ò¦nÀ³¥I

²¦³º¬O¯A¤Î¼h¯Å(protection ring)¦¾¬Vªº°ÝÃD
¸òTLB bug¬Û¤ñ¯uªº¶q¯Å¦³®t
¦ý§Ú«e¤å·Q»¡ªº¨ä¹ê¬O³o¨â­Óbug³£¬O»P§Ö¨ú¦³Ãö

·Pı¹ï¤@¯ë®ø¶OªÌ¨Ó»¡
³Ì¦nªº¸Ñªk¡A´N¬O¥u¯àµ¥IntelÄÀ¥X·sªº¨B¶iªºCPU
¨Ó¸Ñ¨M³o­Óbug¤F

rockports 2018-01-04 01:38 AM

³Ì¦n¬Ointel §â¥«­±¤Wªºcpu ¥þ³¡¦^¦¬§ó´«¨S°ÝÃDªº²£«~....¡A¤£µM¤£ª¾¹D«ç»ò³B²z¤F⋯⋯

rockports 2018-01-04 01:49 AM

https://www.computerbase.de/2018-01...herheitsluecke/

§ó·s¤@¤U¡A¥Ø«e¬Ý°_¨Ó¤@¯ëuser¦pªG¤å®Ñ¥\¯àªº®t²§¤£¤j¡A¤£¹L­èÃzµo¥X¨Ó¡A¤@¤ÁÁÙ¬O¬Ý³o´X¤Ñ©ú®Ô

¤Æ§a⋯⋯

¦è¨ÈSkin 2018-01-04 02:31 AM

¤Þ¥Î:
§@ªÌrockports
https://www.computerbase.de/2018-01/intel-cpu-pti-sicherheitsluecke/

§ó·s¤@¤U¡A¥Ø«e¬Ý°_¨Ó¤@¯ëuser¦pªG¤å®Ñ¥\¯àªº®t²§¤£¤j¡A¤£¹L­èÃzµo¥X¨Ó¡A¤@¤ÁÁÙ¬O¬Ý³o´X¤Ñ©ú®Ô

¤Æ§a⋯⋯

¬O¥X¨Ó¬~¦a¶Ü :laugh:

moronNZ 2018-01-04 06:38 AM

³o¼Ë·|¤£·|Åýintel¶}©ñH110/B150¤§Ãþ¥i¥H¥Î·sªºª©¥»¤K¥N³B²z¾¹¡A³o¼Ë¥i¥H±Ï¤@ÂI¡C³o¼Ëª½±µ±Ï¤»¡B¤C¡B¤K¥N¨Ï¥ÎªÌ :ase

oversky. 2018-01-04 07:05 AM

½Ð°Ý¬O guest OS ¶¡·|¦³°ÝÃD¡A
ÁÙ¬O guest OS ¤]¥i¥H¼vÅT¨ì host OS?
¦b guest OS ùØ´ú¯f¬r·|¼vÅT¨ì host OS ¶Ü¡H

deanhu 2018-01-04 10:33 AM

¤Þ¥Î:
- Exclude AMD from the PTI enforcement. Not necessarily a fix, but if
AMD is so confident that they are not affected, then we should not
burden users with the overhead"


®Ú¾ÚAMD¦Û¤vµo¥X¨Óªº®ø®§¡ALinux Kernel 4.15ªºPTI patch¤w±NAMD CPU±Æ°£¦b¥~¡CAMD³o»ò¦³§â´¤¡H

sutl 2018-01-04 12:23 PM

¤Þ¥Î:
§@ªÌdeanhu
®Ú¾ÚAMD¦Û¤vµo¥X¨Óªº®ø®§¡ALinux Kernel 4.15ªºPTI patch¤w±NAMD CPU±Æ°£¦b¥~¡CAMD³o»ò¦³§â´¤¡H

¦pªG®Ö¤ß¾÷±K¸ê®Æ¦s¨ú§¹²¦¤§«á¡A´N±qCPU¼È¦s°Ï²¾°£ªº¸Ü¡A¨ºªº½T´NŪ¤£¨ì¤F¡C

¯ÊÂI´N¬O³t«×·|¤ñ¸ûºC¡A¦]¬°­n¦s¨ú®Ö¤ß¸ê®Æ®É¤S­n¥hŪ¥D¾÷ªO°O¾ÐÅé¡C

³¥¤f¶©¥v 2018-01-04 01:19 PM

¤Þ¥Î:
§@ªÌdeanhu
®Ú¾ÚAMD¦Û¤vµo¥X¨Óªº®ø®§¡ALinux Kernel 4.15ªºPTI patch¤w±NAMD CPU±Æ°£¦b¥~¡CAMD³o»ò¦³§â´¤¡H

§A¥i¥H¦Û¤v¬Ý¾ã­Ómergeªºpatches
https://github.com/torvalds/linux/c...40663af75f64R99

¬Ý°_¨Ó¨ä¹ê³o¨Ç¼gpatchesªº¤H®Ú¥»µLªk»¡¥XAMD¤@©w¨S°ÝÃD
¥u¬O³æ¯Â¬Û«HAMD½T»{¨S°ÝÃD¬O¯uªº¨S°ÝÃD

¤£¹L¦bPTI patches¸Ì­±¤]´£¨ìAMD¦³¥t¥~¤@­Ó°ÝÃD
¦b³o¸Ì¶¶«K­×¥¿
¤Þ¥Î:
User space process size. This is the first address outside the user range.
There are a few constraints that determine this:
+ *
On Intel CPUs, if a SYSCALL instruction is at the highest canonical
address, then that syscall will enter the kernel with a
non-canonical return address, and SYSRET will explode dangerously.
We avoid this particular problem by preventing anything executable
from being mapped at the maximum canonical address.
+ *
On AMD CPUs in the Ryzen family, there's a nasty bug in which the
CPUs malfunction if they execute code from the highest canonical page.
They'll speculate right off the end of the canonical space, and
bad things happen. This is worked around in the same way as the
Intel problem.

¬Ý°_¨Ó¬O¤Þµo°ÝÃDªº­ì¦] I ¸ò A ¨âªÌ¥»½è¤W¤£¦P
¥u¬O¾É­Pªºµ²ªG¦P¼Ë¥i¥H¨Ó§Q¥Î

rockports 2018-01-04 01:43 PM

https://www.ptt.cc/bbs/PC_Shopping/...9270.A.05D.html

https://www.ptt.cc/bbs/PC_Shopping/...3262.A.E55.html


©Ò¦³ªº®É¶¡§¡¬°GMT +8¡C ²{¦bªº®É¶¡¬O05:15 PM.

vBulletin Version 3.0.1
powered_by_vbulletin 2025¡C