linux

iv/linux

History

Linus Torvalds cfe1cb014b A set of patches to prevent crashes in SGX enclaves under heavy memory

pressure:
 
 SGX uses normal RAM allocated from special shmem files as backing storage
 when it runs out of SGX memory (EPC).  The code was overly aggressive when
 freeing shmem pages and was inadvertently freeing perfectly good data.
 This resulted in failures in the SGX instructions used to swap data back
 into SGX memory.
 
 This turned out to be really hard to trigger in mainline.  It was
 originally encountered testing the out-of-tree "SGX2" patches, but later
 reproduced on mainline.
 
 Fix the data loss by being more careful about truncating pages out of
 the backing storage and more judiciously setting pages dirty.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEV76QKkVc4xCGURexaDWVMHDJkrAFAmKLqcgACgkQaDWVMHDJ
 krA7rA//ZgNgOTzCp/jdntz2KSp9MPhwaSJg0MUnsa7wt0T/3sPXaEAu9wgSZod7
 xqxH17LKUc27SyALtPrkvm68aVZ/Z0Nhq2gDndspXd/Zcl/CD/Cy+GI+ZpdNoYhz
 Fuqiq1TrszzzqBksgiEal9S874+jum2uWqYBMHB45ODp+E7F479Zm42hI3dSp1VN
 6n5zOi5u+unHgDRQ/rwMovu2XU61ZXrycqkbZvu4P4tRbEUH+EhAMKG2RyZOB2V9
 XNqr1vBJ122CWMIxcdzEUEofPFFwVEtC9jK+rdgUW1ZYAPJDjVvcnXx7dpA9PHLb
 DytBSWyeISllJKbea1pIMsdCT/IE4I3s0US2ZA3Ru7YAMgUIi+IGu++JJ2dWdDvx
 GoJz6yBVw4r6cl7kLUfbtIUPsJLYkEMpTM4XODsxMwzd2/Jdbe2UfQskzEn9Auvc
 1qGRspu/3VbqE5WFz5Npd94+B+8BOo7kKLcizBHqmX8U2PBkMnhRatxDMCu8frfL
 DlrjosgUgMYQRkEp3Zugo33O8F2EAE0T1I9g7N4sullX0jGnFifjgiPipnWcnIB9
 RnF5NHdrTMPwqhvzz+3o1yJgve56juZxESqn1khEIQEqgUtxFaEnrmYzdLlVkoGg
 XbuY7TNp1hDC3s9OHeiCL2oUaSmyh0eKCokLiAuWowVzbuU69BU=
 =pTAC
 -----END PGP SIGNATURE-----

Merge tag 'x86_sgx_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 SGX updates from Dave Hansen:
 "A set of patches to prevent crashes in SGX enclaves under heavy memory
  pressure:

  SGX uses normal RAM allocated from special shmem files as backing
  storage when it runs out of SGX memory (EPC). The code was overly
  aggressive when freeing shmem pages and was inadvertently freeing
  perfectly good data. This resulted in failures in the SGX instructions
  used to swap data back into SGX memory.

  This turned out to be really hard to trigger in mainline. It was
  originally encountered testing the out-of-tree "SGX2" patches, but
  later reproduced on mainline.

  Fix the data loss by being more careful about truncating pages out of
  the backing storage and more judiciously setting pages dirty"

* tag 'x86_sgx_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/sgx: Ensure no data in PCMD page after truncate
  x86/sgx: Fix race between reclaimer and page fault handler
  x86/sgx: Obtain backing storage page with enclave mutex held
  x86/sgx: Mark PCMD page as dirty when modifying contents
  x86/sgx: Disconnect backing page references from dirty status

2022-05-23 20:34:58 -07:00

alpha

Merge branch 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

2022-04-01 19:57:03 -07:00

arc

ARC: remove redundant READ_ONCE() in cmpxchg loop

2022-04-18 14:47:05 -07:00

arm

Updates for interrupt core and drivers:

2022-05-23 16:58:49 -07:00

arm64

- Remove all the code around GS switching on 32-bit now that it is not