Wrong DTS reference #52
Comments
frank-w
added a commit
that referenced
this issue
Nov 20, 2018
|
thank you, can you verify it works now? |
|
I don't use your config, but as far as you changed reference, things should work. You can check yourself by |
|
which config relies to it? havn't used crypto yet...
? |
|
Yes. I suggest to build this as module to be able to check the difference (it's very unexpected, but anyway..) |
frank-w
pushed a commit
that referenced
this issue
Dec 17, 2018
Increase kasan instrumented kernel stack size from 32k to 64k. Other architectures seems to get away with just doubling kernel stack size under kasan, but on s390 this appears to be not enough due to bigger frame size. The particular pain point is kasan inlined checks (CONFIG_KASAN_INLINE vs CONFIG_KASAN_OUTLINE). With inlined checks one particular case hitting stack overflow is fs sync on xfs filesystem: #0 [9a0681e8] 704 bytes check_usage at 34b1fc #1 [9a0684a8] 432 bytes check_usage at 34c710 #2 [9a068658] 1048 bytes validate_chain at 35044a #3 [9a068a70] 312 bytes __lock_acquire at 3559fe #4 [9a068ba8] 440 bytes lock_acquire at 3576ee #5 [9a068d60] 104 bytes _raw_spin_lock at 21b44e0 #6 [9a068dc8] 1992 bytes enqueue_entity at 2dbf72 #7 [9a069590] 1496 bytes enqueue_task_fair at 2df5f0 #8 [9a069b68] 64 bytes ttwu_do_activate at 28f438 #9 [9a069ba8] 552 bytes try_to_wake_up at 298c4c #10 [9a069dd0] 168 bytes wake_up_worker at 23f97c #11 [9a069e78] 200 bytes insert_work at 23fc2e #12 [9a069f40] 648 bytes __queue_work at 2487c0 #13 [9a06a1c8] 200 bytes __queue_delayed_work at 24db28 #14 [9a06a290] 248 bytes mod_delayed_work_on at 24de84 #15 [9a06a388] 24 bytes kblockd_mod_delayed_work_on at 153e2a0 #16 [9a06a3a0] 288 bytes __blk_mq_delay_run_hw_queue at 158168c #17 [9a06a4c0] 192 bytes blk_mq_run_hw_queue at 1581a3c #18 [9a06a580] 184 bytes blk_mq_sched_insert_requests at 15a2192 #19 [9a06a638] 1024 bytes blk_mq_flush_plug_list at 1590f3a #20 [9a06aa38] 704 bytes blk_flush_plug_list at 1555028 #21 [9a06acf8] 320 bytes schedule at 219e476 #22 [9a06ae38] 760 bytes schedule_timeout at 21b0aac #23 [9a06b130] 408 bytes wait_for_common at 21a1706 #24 [9a06b2c8] 360 bytes xfs_buf_iowait at fa1540 #25 [9a06b430] 256 bytes __xfs_buf_submit at fadae6 #26 [9a06b530] 264 bytes xfs_buf_read_map at fae3f6 #27 [9a06b638] 656 bytes xfs_trans_read_buf_map at 10ac9a8 #28 [9a06b8c8] 304 bytes xfs_btree_kill_root at e72426 #29 [9a06b9f8] 288 bytes xfs_btree_lookup_get_block at e7bc5e #30 [9a06bb18] 624 bytes xfs_btree_lookup at e7e1a6 #31 [9a06bd88] 2664 bytes xfs_alloc_ag_vextent_near at dfa070 #32 [9a06c7f0] 144 bytes xfs_alloc_ag_vextent at dff3ca #33 [9a06c880] 1128 bytes xfs_alloc_vextent at e05fce #34 [9a06cce8] 584 bytes xfs_bmap_btalloc at e58342 #35 [9a06cf30] 1336 bytes xfs_bmapi_write at e618de #36 [9a06d468] 776 bytes xfs_iomap_write_allocate at ff678e #37 [9a06d770] 720 bytes xfs_map_blocks at f82af8 #38 [9a06da40] 928 bytes xfs_writepage_map at f83cd6 #39 [9a06dde0] 320 bytes xfs_do_writepage at f85872 #40 [9a06df20] 1320 bytes write_cache_pages at 73dfe8 #41 [9a06e448] 208 bytes xfs_vm_writepages at f7f892 #42 [9a06e518] 88 bytes do_writepages at 73fe6a #43 [9a06e570] 872 bytes __writeback_single_inode at a20cb6 #44 [9a06e8d8] 664 bytes writeback_sb_inodes at a23be2 #45 [9a06eb70] 296 bytes __writeback_inodes_wb at a242e0 #46 [9a06ec98] 928 bytes wb_writeback at a2500e #47 [9a06f038] 848 bytes wb_do_writeback at a260ae #48 [9a06f388] 536 bytes wb_workfn at a28228 #49 [9a06f5a0] 1088 bytes process_one_work at 24a234 #50 [9a06f9e0] 1120 bytes worker_thread at 24ba26 #51 [9a06fe40] 104 bytes kthread at 26545a #52 [9a06fea8] kernel_thread_starter at 21b6b62 To be able to increase the stack size to 64k reuse LLILL instruction in __switch_to function to load 64k - STACK_FRAME_OVERHEAD - __PT_SIZE (65192) value as unsigned. Reported-by: Benjamin Block <[email protected]> Reviewed-by: Heiko Carstens <[email protected]> Signed-off-by: Vasily Gorbik <[email protected]> Signed-off-by: Martin Schwidefsky <[email protected]>
with actual 4.14...this is how it should look,right? How to test performance (with/without)? |
|
You can check scripts in my fork of your fork :) Take actual cryptodev, and.or compile af_alg to the kernel. Then recompile openssl with cryptodev. They do have support for cryptodev for BSD, so you need manually add CFLAGS for that. In recent debian (testing) af_alg is present in the default package. Then you can use openssl speed for aes/sha. This unit has nice performance, but as with any hw module you should pass a lot there to have nice speed. In other case performance will be worse because of DMI interrupts, context switches etc. |
|
Also there are some stability issues with it. Maybe race conditions in DMA handler, or god knows where. To find this, you need load your system with something with interrupts. Run several benchmarks, then fill ram with /dev/urandom to make it swap, use iperf to load network and something with SATA. Likely in 10-20 mins something will die. |
|
Have you found out more? |
frank-w
pushed a commit
that referenced
this issue
Jun 3, 2021
[ Upstream commit d5027ca ] Ritesh reported a bug [1] against UML, noting that it crashed on startup. The backtrace shows the following (heavily redacted): (gdb) bt ... #26 0x0000000060015b5d in sem_init () at ipc/sem.c:268 #27 0x00007f89906d92f7 in ?? () from /lib/x86_64-linux-gnu/libcom_err.so.2 #28 0x00007f8990ab8fb2 in call_init (...) at dl-init.c:72 ... #40 0x00007f89909bf3a6 in nss_load_library (...) at nsswitch.c:359 ... #44 0x00007f8990895e35 in _nss_compat_getgrnam_r (...) at nss_compat/compat-grp.c:486 #45 0x00007f8990968b85 in __getgrnam_r [...] #46 0x00007f89909d6b77 in grantpt [...] #47 0x00007f8990a9394e in __GI_openpty [...] #48 0x00000000604a1f65 in openpty_cb (...) at arch/um/os-Linux/sigio.c:407 #49 0x00000000604a58d0 in start_idle_thread (...) at arch/um/os-Linux/skas/process.c:598 #50 0x0000000060004a3d in start_uml () at arch/um/kernel/skas/process.c:45 #51 0x00000000600047b2 in linux_main (...) at arch/um/kernel/um_arch.c:334 #52 0x000000006000574f in main (...) at arch/um/os-Linux/main.c:144 indicating that the UML function openpty_cb() calls openpty(), which internally calls __getgrnam_r(), which causes the nsswitch machinery to get started. This loads, through lots of indirection that I snipped, the libcom_err.so.2 library, which (in an unknown function, "??") calls sem_init(). Now, of course it wants to get libpthread's sem_init(), since it's linked against libpthread. However, the dynamic linker looks up that symbol against the binary first, and gets the kernel's sem_init(). Hajime Tazaki noted that "objcopy -L" can localize a symbol, so the dynamic linker wouldn't do the lookup this way. I tried, but for some reason that didn't seem to work. Doing the same thing in the linker script instead does seem to work, though I cannot entirely explain - it *also* works if I just add "VERSION { { global: *; }; }" instead, indicating that something else is happening that I don't really understand. It may be that explicitly doing that marks them with some kind of empty version, and that's different from the default. Explicitly marking them with a version breaks kallsyms, so that doesn't seem to be possible. Marking all the symbols as local seems correct, and does seem to address the issue, so do that. Also do it for static link, nsswitch libraries could still be loaded there. [1] https://bugs.debian.org/983379 Reported-by: Ritesh Raj Sarraf <[email protected]> Signed-off-by: Johannes Berg <[email protected]> Acked-By: Anton Ivanov <[email protected]> Tested-By: Ritesh Raj Sarraf <[email protected]> Signed-off-by: Richard Weinberger <[email protected]> Signed-off-by: Sasha Levin <[email protected]>
frank-w
pushed a commit
that referenced
this issue
Jun 3, 2021
[ Upstream commit d5027ca ] Ritesh reported a bug [1] against UML, noting that it crashed on startup. The backtrace shows the following (heavily redacted): (gdb) bt ... #26 0x0000000060015b5d in sem_init () at ipc/sem.c:268 #27 0x00007f89906d92f7 in ?? () from /lib/x86_64-linux-gnu/libcom_err.so.2 #28 0x00007f8990ab8fb2 in call_init (...) at dl-init.c:72 ... #40 0x00007f89909bf3a6 in nss_load_library (...) at nsswitch.c:359 ... #44 0x00007f8990895e35 in _nss_compat_getgrnam_r (...) at nss_compat/compat-grp.c:486 #45 0x00007f8990968b85 in __getgrnam_r [...] #46 0x00007f89909d6b77 in grantpt [...] #47 0x00007f8990a9394e in __GI_openpty [...] #48 0x00000000604a1f65 in openpty_cb (...) at arch/um/os-Linux/sigio.c:407 #49 0x00000000604a58d0 in start_idle_thread (...) at arch/um/os-Linux/skas/process.c:598 #50 0x0000000060004a3d in start_uml () at arch/um/kernel/skas/process.c:45 #51 0x00000000600047b2 in linux_main (...) at arch/um/kernel/um_arch.c:334 #52 0x000000006000574f in main (...) at arch/um/os-Linux/main.c:144 indicating that the UML function openpty_cb() calls openpty(), which internally calls __getgrnam_r(), which causes the nsswitch machinery to get started. This loads, through lots of indirection that I snipped, the libcom_err.so.2 library, which (in an unknown function, "??") calls sem_init(). Now, of course it wants to get libpthread's sem_init(), since it's linked against libpthread. However, the dynamic linker looks up that symbol against the binary first, and gets the kernel's sem_init(). Hajime Tazaki noted that "objcopy -L" can localize a symbol, so the dynamic linker wouldn't do the lookup this way. I tried, but for some reason that didn't seem to work. Doing the same thing in the linker script instead does seem to work, though I cannot entirely explain - it *also* works if I just add "VERSION { { global: *; }; }" instead, indicating that something else is happening that I don't really understand. It may be that explicitly doing that marks them with some kind of empty version, and that's different from the default. Explicitly marking them with a version breaks kallsyms, so that doesn't seem to be possible. Marking all the symbols as local seems correct, and does seem to address the issue, so do that. Also do it for static link, nsswitch libraries could still be loaded there. [1] https://bugs.debian.org/983379 Reported-by: Ritesh Raj Sarraf <[email protected]> Signed-off-by: Johannes Berg <[email protected]> Acked-By: Anton Ivanov <[email protected]> Tested-By: Ritesh Raj Sarraf <[email protected]> Signed-off-by: Richard Weinberger <[email protected]> Signed-off-by: Sasha Levin <[email protected]>
frank-w
pushed a commit
that referenced
this issue
Jun 3, 2021
[ Upstream commit d5027ca ] Ritesh reported a bug [1] against UML, noting that it crashed on startup. The backtrace shows the following (heavily redacted): (gdb) bt ... #26 0x0000000060015b5d in sem_init () at ipc/sem.c:268 #27 0x00007f89906d92f7 in ?? () from /lib/x86_64-linux-gnu/libcom_err.so.2 #28 0x00007f8990ab8fb2 in call_init (...) at dl-init.c:72 ... #40 0x00007f89909bf3a6 in nss_load_library (...) at nsswitch.c:359 ... #44 0x00007f8990895e35 in _nss_compat_getgrnam_r (...) at nss_compat/compat-grp.c:486 #45 0x00007f8990968b85 in __getgrnam_r [...] #46 0x00007f89909d6b77 in grantpt [...] #47 0x00007f8990a9394e in __GI_openpty [...] #48 0x00000000604a1f65 in openpty_cb (...) at arch/um/os-Linux/sigio.c:407 #49 0x00000000604a58d0 in start_idle_thread (...) at arch/um/os-Linux/skas/process.c:598 #50 0x0000000060004a3d in start_uml () at arch/um/kernel/skas/process.c:45 #51 0x00000000600047b2 in linux_main (...) at arch/um/kernel/um_arch.c:334 #52 0x000000006000574f in main (...) at arch/um/os-Linux/main.c:144 indicating that the UML function openpty_cb() calls openpty(), which internally calls __getgrnam_r(), which causes the nsswitch machinery to get started. This loads, through lots of indirection that I snipped, the libcom_err.so.2 library, which (in an unknown function, "??") calls sem_init(). Now, of course it wants to get libpthread's sem_init(), since it's linked against libpthread. However, the dynamic linker looks up that symbol against the binary first, and gets the kernel's sem_init(). Hajime Tazaki noted that "objcopy -L" can localize a symbol, so the dynamic linker wouldn't do the lookup this way. I tried, but for some reason that didn't seem to work. Doing the same thing in the linker script instead does seem to work, though I cannot entirely explain - it *also* works if I just add "VERSION { { global: *; }; }" instead, indicating that something else is happening that I don't really understand. It may be that explicitly doing that marks them with some kind of empty version, and that's different from the default. Explicitly marking them with a version breaks kallsyms, so that doesn't seem to be possible. Marking all the symbols as local seems correct, and does seem to address the issue, so do that. Also do it for static link, nsswitch libraries could still be loaded there. [1] https://bugs.debian.org/983379 Reported-by: Ritesh Raj Sarraf <[email protected]> Signed-off-by: Johannes Berg <[email protected]> Acked-By: Anton Ivanov <[email protected]> Tested-By: Ritesh Raj Sarraf <[email protected]> Signed-off-by: Richard Weinberger <[email protected]> Signed-off-by: Sasha Levin <[email protected]>
frank-w
pushed a commit
that referenced
this issue
Jun 3, 2021
[ Upstream commit d5027ca ] Ritesh reported a bug [1] against UML, noting that it crashed on startup. The backtrace shows the following (heavily redacted): (gdb) bt ... #26 0x0000000060015b5d in sem_init () at ipc/sem.c:268 #27 0x00007f89906d92f7 in ?? () from /lib/x86_64-linux-gnu/libcom_err.so.2 #28 0x00007f8990ab8fb2 in call_init (...) at dl-init.c:72 ... #40 0x00007f89909bf3a6 in nss_load_library (...) at nsswitch.c:359 ... #44 0x00007f8990895e35 in _nss_compat_getgrnam_r (...) at nss_compat/compat-grp.c:486 #45 0x00007f8990968b85 in __getgrnam_r [...] #46 0x00007f89909d6b77 in grantpt [...] #47 0x00007f8990a9394e in __GI_openpty [...] #48 0x00000000604a1f65 in openpty_cb (...) at arch/um/os-Linux/sigio.c:407 #49 0x00000000604a58d0 in start_idle_thread (...) at arch/um/os-Linux/skas/process.c:598 #50 0x0000000060004a3d in start_uml () at arch/um/kernel/skas/process.c:45 #51 0x00000000600047b2 in linux_main (...) at arch/um/kernel/um_arch.c:334 #52 0x000000006000574f in main (...) at arch/um/os-Linux/main.c:144 indicating that the UML function openpty_cb() calls openpty(), which internally calls __getgrnam_r(), which causes the nsswitch machinery to get started. This loads, through lots of indirection that I snipped, the libcom_err.so.2 library, which (in an unknown function, "??") calls sem_init(). Now, of course it wants to get libpthread's sem_init(), since it's linked against libpthread. However, the dynamic linker looks up that symbol against the binary first, and gets the kernel's sem_init(). Hajime Tazaki noted that "objcopy -L" can localize a symbol, so the dynamic linker wouldn't do the lookup this way. I tried, but for some reason that didn't seem to work. Doing the same thing in the linker script instead does seem to work, though I cannot entirely explain - it *also* works if I just add "VERSION { { global: *; }; }" instead, indicating that something else is happening that I don't really understand. It may be that explicitly doing that marks them with some kind of empty version, and that's different from the default. Explicitly marking them with a version breaks kallsyms, so that doesn't seem to be possible. Marking all the symbols as local seems correct, and does seem to address the issue, so do that. Also do it for static link, nsswitch libraries could still be loaded there. [1] https://bugs.debian.org/983379 Reported-by: Ritesh Raj Sarraf <[email protected]> Signed-off-by: Johannes Berg <[email protected]> Acked-By: Anton Ivanov <[email protected]> Tested-By: Ritesh Raj Sarraf <[email protected]> Signed-off-by: Richard Weinberger <[email protected]> Signed-off-by: Sasha Levin <[email protected]>
frank-w
pushed a commit
that referenced
this issue
Jan 22, 2023
The inline assembly for arm64's cmpxchg_double*() implementations use a +Q constraint to hazard against other accesses to the memory location being exchanged. However, the pointer passed to the constraint is a pointer to unsigned long, and thus the hazard only applies to the first 8 bytes of the location. GCC can take advantage of this, assuming that other portions of the location are unchanged, leading to a number of potential problems. This is similar to what we fixed back in commit: fee960b ("arm64: xchg: hazard against entire exchange variable") ... but we forgot to adjust cmpxchg_double*() similarly at the same time. The same problem applies, as demonstrated with the following test: | struct big { | u64 lo, hi; | } __aligned(128); | | unsigned long foo(struct big *b) | { | u64 hi_old, hi_new; | | hi_old = b->hi; | cmpxchg_double_local(&b->lo, &b->hi, 0x12, 0x34, 0x56, 0x78); | hi_new = b->hi; | | return hi_old ^ hi_new; | } ... which GCC 12.1.0 compiles as: | 0000000000000000 <foo>: | 0: d503233f paciasp | 4: aa0003e4 mov x4, x0 | 8: 1400000e b 40 <foo+0x40> | c: d2800240 mov x0, #0x12 // #18 | 10: d2800681 mov x1, #0x34 // #52 | 14: aa0003e5 mov x5, x0 | 18: aa0103e6 mov x6, x1 | 1c: d2800ac2 mov x2, #0x56 // #86 | 20: d2800f03 mov x3, #0x78 // #120 | 24: 48207c82 casp x0, x1, x2, x3, [x4] | 28: ca050000 eor x0, x0, x5 | 2c: ca060021 eor x1, x1, x6 | 30: aa010000 orr x0, x0, x1 | 34: d2800000 mov x0, #0x0 // #0 <--- BANG | 38: d50323bf autiasp | 3c: d65f03c0 ret | 40: d2800240 mov x0, #0x12 // #18 | 44: d2800681 mov x1, #0x34 // #52 | 48: d2800ac2 mov x2, #0x56 // #86 | 4c: d2800f03 mov x3, #0x78 // #120 | 50: f9800091 prfm pstl1strm, [x4] | 54: c87f1885 ldxp x5, x6, [x4] | 58: ca0000a5 eor x5, x5, x0 | 5c: ca0100c6 eor x6, x6, x1 | 60: aa0600a6 orr x6, x5, x6 | 64: b5000066 cbnz x6, 70 <foo+0x70> | 68: c8250c82 stxp w5, x2, x3, [x4] | 6c: 35ffff45 cbnz w5, 54 <foo+0x54> | 70: d2800000 mov x0, #0x0 // #0 <--- BANG | 74: d50323bf autiasp | 78: d65f03c0 ret Notice that at the lines with "BANG" comments, GCC has assumed that the higher 8 bytes are unchanged by the cmpxchg_double() call, and that `hi_old ^ hi_new` can be reduced to a constant zero, for both LSE and LL/SC versions of cmpxchg_double(). This patch fixes the issue by passing a pointer to __uint128_t into the +Q constraint, ensuring that the compiler hazards against the entire 16 bytes being modified. With this change, GCC 12.1.0 compiles the above test as: | 0000000000000000 <foo>: | 0: f9400407 ldr x7, [x0, #8] | 4: d503233f paciasp | 8: aa0003e4 mov x4, x0 | c: 1400000f b 48 <foo+0x48> | 10: d2800240 mov x0, #0x12 // #18 | 14: d2800681 mov x1, #0x34 // #52 | 18: aa0003e5 mov x5, x0 | 1c: aa0103e6 mov x6, x1 | 20: d2800ac2 mov x2, #0x56 // #86 | 24: d2800f03 mov x3, #0x78 // #120 | 28: 48207c82 casp x0, x1, x2, x3, [x4] | 2c: ca050000 eor x0, x0, x5 | 30: ca060021 eor x1, x1, x6 | 34: aa010000 orr x0, x0, x1 | 38: f9400480 ldr x0, [x4, #8] | 3c: d50323bf autiasp | 40: ca0000e0 eor x0, x7, x0 | 44: d65f03c0 ret | 48: d2800240 mov x0, #0x12 // #18 | 4c: d2800681 mov x1, #0x34 // #52 | 50: d2800ac2 mov x2, #0x56 // #86 | 54: d2800f03 mov x3, #0x78 // #120 | 58: f9800091 prfm pstl1strm, [x4] | 5c: c87f1885 ldxp x5, x6, [x4] | 60: ca0000a5 eor x5, x5, x0 | 64: ca0100c6 eor x6, x6, x1 | 68: aa0600a6 orr x6, x5, x6 | 6c: b5000066 cbnz x6, 78 <foo+0x78> | 70: c8250c82 stxp w5, x2, x3, [x4] | 74: 35ffff45 cbnz w5, 5c <foo+0x5c> | 78: f9400480 ldr x0, [x4, #8] | 7c: d50323bf autiasp | 80: ca0000e0 eor x0, x7, x0 | 84: d65f03c0 ret ... sampling the high 8 bytes before and after the cmpxchg, and performing an EOR, as we'd expect. For backporting, I've tested this atop linux-4.9.y with GCC 5.5.0. Note that linux-4.9.y is oldest currently supported stable release, and mandates GCC 5.1+. Unfortunately I couldn't get a GCC 5.1 binary to run on my machines due to library incompatibilities. I've also used a standalone test to check that we can use a __uint128_t pointer in a +Q constraint at least as far back as GCC 4.8.5 and LLVM 3.9.1. Fixes: 5284e1b ("arm64: xchg: Implement cmpxchg_double") Fixes: e9a4b79 ("arm64: cmpxchg_dbl: patch in lse instructions when supported by the CPU") Reported-by: Boqun Feng <[email protected]> Link: https://lore.kernel.org/lkml/Y6DEfQXymYVgL3oJ@boqun-archlinux/ Reported-by: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/lkml/[email protected]/ Signed-off-by: Mark Rutland <[email protected]> Cc: [email protected] Cc: Arnd Bergmann <[email protected]> Cc: Catalin Marinas <[email protected]> Cc: Steve Capper <[email protected]> Cc: Will Deacon <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Will Deacon <[email protected]>
frank-w
pushed a commit
that referenced
this issue
Feb 17, 2023
[ Upstream commit 031af50 ] The inline assembly for arm64's cmpxchg_double*() implementations use a +Q constraint to hazard against other accesses to the memory location being exchanged. However, the pointer passed to the constraint is a pointer to unsigned long, and thus the hazard only applies to the first 8 bytes of the location. GCC can take advantage of this, assuming that other portions of the location are unchanged, leading to a number of potential problems. This is similar to what we fixed back in commit: fee960b ("arm64: xchg: hazard against entire exchange variable") ... but we forgot to adjust cmpxchg_double*() similarly at the same time. The same problem applies, as demonstrated with the following test: | struct big { | u64 lo, hi; | } __aligned(128); | | unsigned long foo(struct big *b) | { | u64 hi_old, hi_new; | | hi_old = b->hi; | cmpxchg_double_local(&b->lo, &b->hi, 0x12, 0x34, 0x56, 0x78); | hi_new = b->hi; | | return hi_old ^ hi_new; | } ... which GCC 12.1.0 compiles as: | 0000000000000000 <foo>: | 0: d503233f paciasp | 4: aa0003e4 mov x4, x0 | 8: 1400000e b 40 <foo+0x40> | c: d2800240 mov x0, #0x12 // #18 | 10: d2800681 mov x1, #0x34 // #52 | 14: aa0003e5 mov x5, x0 | 18: aa0103e6 mov x6, x1 | 1c: d2800ac2 mov x2, #0x56 // #86 | 20: d2800f03 mov x3, #0x78 // #120 | 24: 48207c82 casp x0, x1, x2, x3, [x4] | 28: ca050000 eor x0, x0, x5 | 2c: ca060021 eor x1, x1, x6 | 30: aa010000 orr x0, x0, x1 | 34: d2800000 mov x0, #0x0 // #0 <--- BANG | 38: d50323bf autiasp | 3c: d65f03c0 ret | 40: d2800240 mov x0, #0x12 // #18 | 44: d2800681 mov x1, #0x34 // #52 | 48: d2800ac2 mov x2, #0x56 // #86 | 4c: d2800f03 mov x3, #0x78 // #120 | 50: f9800091 prfm pstl1strm, [x4] | 54: c87f1885 ldxp x5, x6, [x4] | 58: ca0000a5 eor x5, x5, x0 | 5c: ca0100c6 eor x6, x6, x1 | 60: aa0600a6 orr x6, x5, x6 | 64: b5000066 cbnz x6, 70 <foo+0x70> | 68: c8250c82 stxp w5, x2, x3, [x4] | 6c: 35ffff45 cbnz w5, 54 <foo+0x54> | 70: d2800000 mov x0, #0x0 // #0 <--- BANG | 74: d50323bf autiasp | 78: d65f03c0 ret Notice that at the lines with "BANG" comments, GCC has assumed that the higher 8 bytes are unchanged by the cmpxchg_double() call, and that `hi_old ^ hi_new` can be reduced to a constant zero, for both LSE and LL/SC versions of cmpxchg_double(). This patch fixes the issue by passing a pointer to __uint128_t into the +Q constraint, ensuring that the compiler hazards against the entire 16 bytes being modified. With this change, GCC 12.1.0 compiles the above test as: | 0000000000000000 <foo>: | 0: f9400407 ldr x7, [x0, #8] | 4: d503233f paciasp | 8: aa0003e4 mov x4, x0 | c: 1400000f b 48 <foo+0x48> | 10: d2800240 mov x0, #0x12 // #18 | 14: d2800681 mov x1, #0x34 // #52 | 18: aa0003e5 mov x5, x0 | 1c: aa0103e6 mov x6, x1 | 20: d2800ac2 mov x2, #0x56 // #86 | 24: d2800f03 mov x3, #0x78 // #120 | 28: 48207c82 casp x0, x1, x2, x3, [x4] | 2c: ca050000 eor x0, x0, x5 | 30: ca060021 eor x1, x1, x6 | 34: aa010000 orr x0, x0, x1 | 38: f9400480 ldr x0, [x4, #8] | 3c: d50323bf autiasp | 40: ca0000e0 eor x0, x7, x0 | 44: d65f03c0 ret | 48: d2800240 mov x0, #0x12 // #18 | 4c: d2800681 mov x1, #0x34 // #52 | 50: d2800ac2 mov x2, #0x56 // #86 | 54: d2800f03 mov x3, #0x78 // #120 | 58: f9800091 prfm pstl1strm, [x4] | 5c: c87f1885 ldxp x5, x6, [x4] | 60: ca0000a5 eor x5, x5, x0 | 64: ca0100c6 eor x6, x6, x1 | 68: aa0600a6 orr x6, x5, x6 | 6c: b5000066 cbnz x6, 78 <foo+0x78> | 70: c8250c82 stxp w5, x2, x3, [x4] | 74: 35ffff45 cbnz w5, 5c <foo+0x5c> | 78: f9400480 ldr x0, [x4, #8] | 7c: d50323bf autiasp | 80: ca0000e0 eor x0, x7, x0 | 84: d65f03c0 ret ... sampling the high 8 bytes before and after the cmpxchg, and performing an EOR, as we'd expect. For backporting, I've tested this atop linux-4.9.y with GCC 5.5.0. Note that linux-4.9.y is oldest currently supported stable release, and mandates GCC 5.1+. Unfortunately I couldn't get a GCC 5.1 binary to run on my machines due to library incompatibilities. I've also used a standalone test to check that we can use a __uint128_t pointer in a +Q constraint at least as far back as GCC 4.8.5 and LLVM 3.9.1. Fixes: 5284e1b ("arm64: xchg: Implement cmpxchg_double") Fixes: e9a4b79 ("arm64: cmpxchg_dbl: patch in lse instructions when supported by the CPU") Reported-by: Boqun Feng <[email protected]> Link: https://lore.kernel.org/lkml/Y6DEfQXymYVgL3oJ@boqun-archlinux/ Reported-by: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/lkml/[email protected]/ Signed-off-by: Mark Rutland <[email protected]> Cc: [email protected] Cc: Arnd Bergmann <[email protected]> Cc: Catalin Marinas <[email protected]> Cc: Steve Capper <[email protected]> Cc: Will Deacon <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Sasha Levin <[email protected]>
frank-w
pushed a commit
that referenced
this issue
Feb 17, 2023
[ Upstream commit 031af50 ] The inline assembly for arm64's cmpxchg_double*() implementations use a +Q constraint to hazard against other accesses to the memory location being exchanged. However, the pointer passed to the constraint is a pointer to unsigned long, and thus the hazard only applies to the first 8 bytes of the location. GCC can take advantage of this, assuming that other portions of the location are unchanged, leading to a number of potential problems. This is similar to what we fixed back in commit: fee960b ("arm64: xchg: hazard against entire exchange variable") ... but we forgot to adjust cmpxchg_double*() similarly at the same time. The same problem applies, as demonstrated with the following test: | struct big { | u64 lo, hi; | } __aligned(128); | | unsigned long foo(struct big *b) | { | u64 hi_old, hi_new; | | hi_old = b->hi; | cmpxchg_double_local(&b->lo, &b->hi, 0x12, 0x34, 0x56, 0x78); | hi_new = b->hi; | | return hi_old ^ hi_new; | } ... which GCC 12.1.0 compiles as: | 0000000000000000 <foo>: | 0: d503233f paciasp | 4: aa0003e4 mov x4, x0 | 8: 1400000e b 40 <foo+0x40> | c: d2800240 mov x0, #0x12 // #18 | 10: d2800681 mov x1, #0x34 // #52 | 14: aa0003e5 mov x5, x0 | 18: aa0103e6 mov x6, x1 | 1c: d2800ac2 mov x2, #0x56 // #86 | 20: d2800f03 mov x3, #0x78 // #120 | 24: 48207c82 casp x0, x1, x2, x3, [x4] | 28: ca050000 eor x0, x0, x5 | 2c: ca060021 eor x1, x1, x6 | 30: aa010000 orr x0, x0, x1 | 34: d2800000 mov x0, #0x0 // #0 <--- BANG | 38: d50323bf autiasp | 3c: d65f03c0 ret | 40: d2800240 mov x0, #0x12 // #18 | 44: d2800681 mov x1, #0x34 // #52 | 48: d2800ac2 mov x2, #0x56 // #86 | 4c: d2800f03 mov x3, #0x78 // #120 | 50: f9800091 prfm pstl1strm, [x4] | 54: c87f1885 ldxp x5, x6, [x4] | 58: ca0000a5 eor x5, x5, x0 | 5c: ca0100c6 eor x6, x6, x1 | 60: aa0600a6 orr x6, x5, x6 | 64: b5000066 cbnz x6, 70 <foo+0x70> | 68: c8250c82 stxp w5, x2, x3, [x4] | 6c: 35ffff45 cbnz w5, 54 <foo+0x54> | 70: d2800000 mov x0, #0x0 // #0 <--- BANG | 74: d50323bf autiasp | 78: d65f03c0 ret Notice that at the lines with "BANG" comments, GCC has assumed that the higher 8 bytes are unchanged by the cmpxchg_double() call, and that `hi_old ^ hi_new` can be reduced to a constant zero, for both LSE and LL/SC versions of cmpxchg_double(). This patch fixes the issue by passing a pointer to __uint128_t into the +Q constraint, ensuring that the compiler hazards against the entire 16 bytes being modified. With this change, GCC 12.1.0 compiles the above test as: | 0000000000000000 <foo>: | 0: f9400407 ldr x7, [x0, #8] | 4: d503233f paciasp | 8: aa0003e4 mov x4, x0 | c: 1400000f b 48 <foo+0x48> | 10: d2800240 mov x0, #0x12 // #18 | 14: d2800681 mov x1, #0x34 // #52 | 18: aa0003e5 mov x5, x0 | 1c: aa0103e6 mov x6, x1 | 20: d2800ac2 mov x2, #0x56 // #86 | 24: d2800f03 mov x3, #0x78 // #120 | 28: 48207c82 casp x0, x1, x2, x3, [x4] | 2c: ca050000 eor x0, x0, x5 | 30: ca060021 eor x1, x1, x6 | 34: aa010000 orr x0, x0, x1 | 38: f9400480 ldr x0, [x4, #8] | 3c: d50323bf autiasp | 40: ca0000e0 eor x0, x7, x0 | 44: d65f03c0 ret | 48: d2800240 mov x0, #0x12 // #18 | 4c: d2800681 mov x1, #0x34 // #52 | 50: d2800ac2 mov x2, #0x56 // #86 | 54: d2800f03 mov x3, #0x78 // #120 | 58: f9800091 prfm pstl1strm, [x4] | 5c: c87f1885 ldxp x5, x6, [x4] | 60: ca0000a5 eor x5, x5, x0 | 64: ca0100c6 eor x6, x6, x1 | 68: aa0600a6 orr x6, x5, x6 | 6c: b5000066 cbnz x6, 78 <foo+0x78> | 70: c8250c82 stxp w5, x2, x3, [x4] | 74: 35ffff45 cbnz w5, 5c <foo+0x5c> | 78: f9400480 ldr x0, [x4, #8] | 7c: d50323bf autiasp | 80: ca0000e0 eor x0, x7, x0 | 84: d65f03c0 ret ... sampling the high 8 bytes before and after the cmpxchg, and performing an EOR, as we'd expect. For backporting, I've tested this atop linux-4.9.y with GCC 5.5.0. Note that linux-4.9.y is oldest currently supported stable release, and mandates GCC 5.1+. Unfortunately I couldn't get a GCC 5.1 binary to run on my machines due to library incompatibilities. I've also used a standalone test to check that we can use a __uint128_t pointer in a +Q constraint at least as far back as GCC 4.8.5 and LLVM 3.9.1. Fixes: 5284e1b ("arm64: xchg: Implement cmpxchg_double") Fixes: e9a4b79 ("arm64: cmpxchg_dbl: patch in lse instructions when supported by the CPU") Reported-by: Boqun Feng <[email protected]> Link: https://lore.kernel.org/lkml/Y6DEfQXymYVgL3oJ@boqun-archlinux/ Reported-by: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/lkml/[email protected]/ Signed-off-by: Mark Rutland <[email protected]> Cc: [email protected] Cc: Arnd Bergmann <[email protected]> Cc: Catalin Marinas <[email protected]> Cc: Steve Capper <[email protected]> Cc: Will Deacon <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Sasha Levin <[email protected]>
frank-w
pushed a commit
that referenced
this issue
Feb 17, 2023
[ Upstream commit 031af50 ] The inline assembly for arm64's cmpxchg_double*() implementations use a +Q constraint to hazard against other accesses to the memory location being exchanged. However, the pointer passed to the constraint is a pointer to unsigned long, and thus the hazard only applies to the first 8 bytes of the location. GCC can take advantage of this, assuming that other portions of the location are unchanged, leading to a number of potential problems. This is similar to what we fixed back in commit: fee960b ("arm64: xchg: hazard against entire exchange variable") ... but we forgot to adjust cmpxchg_double*() similarly at the same time. The same problem applies, as demonstrated with the following test: | struct big { | u64 lo, hi; | } __aligned(128); | | unsigned long foo(struct big *b) | { | u64 hi_old, hi_new; | | hi_old = b->hi; | cmpxchg_double_local(&b->lo, &b->hi, 0x12, 0x34, 0x56, 0x78); | hi_new = b->hi; | | return hi_old ^ hi_new; | } ... which GCC 12.1.0 compiles as: | 0000000000000000 <foo>: | 0: d503233f paciasp | 4: aa0003e4 mov x4, x0 | 8: 1400000e b 40 <foo+0x40> | c: d2800240 mov x0, #0x12 // #18 | 10: d2800681 mov x1, #0x34 // #52 | 14: aa0003e5 mov x5, x0 | 18: aa0103e6 mov x6, x1 | 1c: d2800ac2 mov x2, #0x56 // #86 | 20: d2800f03 mov x3, #0x78 // #120 | 24: 48207c82 casp x0, x1, x2, x3, [x4] | 28: ca050000 eor x0, x0, x5 | 2c: ca060021 eor x1, x1, x6 | 30: aa010000 orr x0, x0, x1 | 34: d2800000 mov x0, #0x0 // #0 <--- BANG | 38: d50323bf autiasp | 3c: d65f03c0 ret | 40: d2800240 mov x0, #0x12 // #18 | 44: d2800681 mov x1, #0x34 // #52 | 48: d2800ac2 mov x2, #0x56 // #86 | 4c: d2800f03 mov x3, #0x78 // #120 | 50: f9800091 prfm pstl1strm, [x4] | 54: c87f1885 ldxp x5, x6, [x4] | 58: ca0000a5 eor x5, x5, x0 | 5c: ca0100c6 eor x6, x6, x1 | 60: aa0600a6 orr x6, x5, x6 | 64: b5000066 cbnz x6, 70 <foo+0x70> | 68: c8250c82 stxp w5, x2, x3, [x4] | 6c: 35ffff45 cbnz w5, 54 <foo+0x54> | 70: d2800000 mov x0, #0x0 // #0 <--- BANG | 74: d50323bf autiasp | 78: d65f03c0 ret Notice that at the lines with "BANG" comments, GCC has assumed that the higher 8 bytes are unchanged by the cmpxchg_double() call, and that `hi_old ^ hi_new` can be reduced to a constant zero, for both LSE and LL/SC versions of cmpxchg_double(). This patch fixes the issue by passing a pointer to __uint128_t into the +Q constraint, ensuring that the compiler hazards against the entire 16 bytes being modified. With this change, GCC 12.1.0 compiles the above test as: | 0000000000000000 <foo>: | 0: f9400407 ldr x7, [x0, #8] | 4: d503233f paciasp | 8: aa0003e4 mov x4, x0 | c: 1400000f b 48 <foo+0x48> | 10: d2800240 mov x0, #0x12 // #18 | 14: d2800681 mov x1, #0x34 // #52 | 18: aa0003e5 mov x5, x0 | 1c: aa0103e6 mov x6, x1 | 20: d2800ac2 mov x2, #0x56 // #86 | 24: d2800f03 mov x3, #0x78 // #120 | 28: 48207c82 casp x0, x1, x2, x3, [x4] | 2c: ca050000 eor x0, x0, x5 | 30: ca060021 eor x1, x1, x6 | 34: aa010000 orr x0, x0, x1 | 38: f9400480 ldr x0, [x4, #8] | 3c: d50323bf autiasp | 40: ca0000e0 eor x0, x7, x0 | 44: d65f03c0 ret | 48: d2800240 mov x0, #0x12 // #18 | 4c: d2800681 mov x1, #0x34 // #52 | 50: d2800ac2 mov x2, #0x56 // #86 | 54: d2800f03 mov x3, #0x78 // #120 | 58: f9800091 prfm pstl1strm, [x4] | 5c: c87f1885 ldxp x5, x6, [x4] | 60: ca0000a5 eor x5, x5, x0 | 64: ca0100c6 eor x6, x6, x1 | 68: aa0600a6 orr x6, x5, x6 | 6c: b5000066 cbnz x6, 78 <foo+0x78> | 70: c8250c82 stxp w5, x2, x3, [x4] | 74: 35ffff45 cbnz w5, 5c <foo+0x5c> | 78: f9400480 ldr x0, [x4, #8] | 7c: d50323bf autiasp | 80: ca0000e0 eor x0, x7, x0 | 84: d65f03c0 ret ... sampling the high 8 bytes before and after the cmpxchg, and performing an EOR, as we'd expect. For backporting, I've tested this atop linux-4.9.y with GCC 5.5.0. Note that linux-4.9.y is oldest currently supported stable release, and mandates GCC 5.1+. Unfortunately I couldn't get a GCC 5.1 binary to run on my machines due to library incompatibilities. I've also used a standalone test to check that we can use a __uint128_t pointer in a +Q constraint at least as far back as GCC 4.8.5 and LLVM 3.9.1. Fixes: 5284e1b ("arm64: xchg: Implement cmpxchg_double") Fixes: e9a4b79 ("arm64: cmpxchg_dbl: patch in lse instructions when supported by the CPU") Reported-by: Boqun Feng <[email protected]> Link: https://lore.kernel.org/lkml/Y6DEfQXymYVgL3oJ@boqun-archlinux/ Reported-by: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/lkml/[email protected]/ Signed-off-by: Mark Rutland <[email protected]> Cc: [email protected] Cc: Arnd Bergmann <[email protected]> Cc: Catalin Marinas <[email protected]> Cc: Steve Capper <[email protected]> Cc: Will Deacon <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Sasha Levin <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
https://github.com/frank-w/BPI-R2-4.14/blob/ee7516478dafaa8ccf7f6e763d88a8e03758af37/drivers/crypto/mediatek/mtk-platform.c#L581
https://github.com/frank-w/BPI-R2-4.14/blob/4.14-main/arch/arm/boot/dts/mt7623.dtsi#L1222
The text was updated successfully, but these errors were encountered: