summaryrefslogtreecommitdiff
path: root/arch/powerpc/lib
AgeCommit message (Collapse)Author
2018-06-12treewide: kmalloc() -> kmalloc_array()Kees Cook
The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-07Merge tag 'powerpc-4.18-1' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux Pull powerpc updates from Michael Ellerman: "Notable changes: - Support for split PMD page table lock on 64-bit Book3S (Power8/9). - Add support for HAVE_RELIABLE_STACKTRACE, so we properly support live patching again. - Add support for patching barrier_nospec in copy_from_user() and syscall entry. - A couple of fixes for our data breakpoints on Book3S. - A series from Nick optimising TLB/mm handling with the Radix MMU. - Numerous small cleanups to squash sparse/gcc warnings from Mathieu Malaterre. - Several series optimising various parts of the 32-bit code from Christophe Leroy. - Removal of support for two old machines, "SBC834xE" and "C2K" ("GEFanuc,C2K"), which is why the diffstat has so many deletions. And many other small improvements & fixes. There's a few out-of-area changes. Some minor ftrace changes OK'ed by Steve, and a fix to our powernv cpuidle driver. Then there's a series touching mm, x86 and fs/proc/task_mmu.c, which cleans up some details around pkey support. It was ack'ed/reviewed by Ingo & Dave and has been in next for several weeks. Thanks to: Akshay Adiga, Alastair D'Silva, Alexey Kardashevskiy, Al Viro, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Arnd Bergmann, Balbir Singh, Cédric Le Goater, Christophe Leroy, Christophe Lombard, Colin Ian King, Dave Hansen, Fabio Estevam, Finn Thain, Frederic Barrat, Gautham R. Shenoy, Haren Myneni, Hari Bathini, Ingo Molnar, Jonathan Neuschäfer, Josh Poimboeuf, Kamalesh Babulal, Madhavan Srinivasan, Mahesh Salgaonkar, Mark Greer, Mathieu Malaterre, Matthew Wilcox, Michael Neuling, Michal Suchanek, Naveen N. Rao, Nicholas Piggin, Nicolai Stange, Olof Johansson, Paul Gortmaker, Paul Mackerras, Peter Rosin, Pridhiviraj Paidipeddi, Ram Pai, Rashmica Gupta, Ravi Bangoria, Russell Currey, Sam Bobroff, Samuel Mendoza-Jonas, Segher Boessenkool, Shilpasri G Bhat, Simon Guo, Souptick Joarder, Stewart Smith, Thiago Jung Bauermann, Torsten Duwe, Vaibhav Jain, Wei Yongjun, Wolfram Sang, Yisheng Xie, YueHaibing" * tag 'powerpc-4.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (251 commits) powerpc/64s/radix: Fix missing ptesync in flush_cache_vmap cpuidle: powernv: Fix promotion from snooze if next state disabled powerpc: fix build failure by disabling attribute-alias warning in pci_32 ocxl: Fix missing unlock on error in afu_ioctl_enable_p9_wait() powerpc-opal: fix spelling mistake "Uniterrupted" -> "Uninterrupted" powerpc: fix spelling mistake: "Usupported" -> "Unsupported" powerpc/pkeys: Detach execute_only key on !PROT_EXEC powerpc/powernv: copy/paste - Mask SO bit in CR powerpc: Remove core support for Marvell mv64x60 hostbridges powerpc/boot: Remove core support for Marvell mv64x60 hostbridges powerpc/boot: Remove support for Marvell mv64x60 i2c controller powerpc/boot: Remove support for Marvell MPSC serial controller powerpc/embedded6xx: Remove C2K board support powerpc/lib: optimise PPC32 memcmp powerpc/lib: optimise 32 bits __clear_user() powerpc/time: inline arch_vtime_task_switch() powerpc/Makefile: set -mcpu=860 flag for the 8xx powerpc: Implement csum_ipv6_magic in assembly powerpc/32: Optimise __csum_partial() powerpc/lib: Adjust .balign inside string functions for PPC32 ...
2018-06-04powerpc/lib: optimise PPC32 memcmpChristophe Leroy
At the time being, memcmp() compares two chunks of memory byte per byte. This patch optimises the comparison by comparing word by word. On the same way as commit 15c2d45d17418 ("powerpc: Add 64bit optimised memcmp"), this patch moves memcmp() into a dedicated file named memcmp_32.S A small benchmark performed on an 8xx comparing two chuncks of 512 bytes performed 100000 times gives: Before : 5852274 TB ticks After: 1488638 TB ticks This is almost 4 times faster Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-04powerpc/lib: optimise 32 bits __clear_user()Christophe Leroy
Rewrite clear_user() on the same principle as memset(0), making use of dcbz to clear complete cache lines. This code is a copy/paste of memset(), with some modifications in order to retrieve remaining number of bytes to be cleared, as it needs to be returned in case of error. On the same way as done on PPC64 in commit 17968fbbd19f1 ("powerpc: 64bit optimised __clear_user"), the patch moves __clear_user() into a dedicated file string_32.S On a MPC885, throughput is almost doubled: Before: ~# dd if=/dev/zero of=/dev/null bs=1M count=1000 1048576000 bytes (1000.0MB) copied, 18.990779 seconds, 52.7MB/s After: ~# dd if=/dev/zero of=/dev/null bs=1M count=1000 1048576000 bytes (1000.0MB) copied, 9.611468 seconds, 104.0MB/s On a MPC8321, throughput is multiplied by 2.12: Before: root@vgoippro:~# dd if=/dev/zero of=/dev/null bs=1M count=1000 1048576000 bytes (1000.0MB) copied, 6.844352 seconds, 146.1MB/s After: root@vgoippro:~# dd if=/dev/zero of=/dev/null bs=1M count=1000 1048576000 bytes (1000.0MB) copied, 3.218854 seconds, 310.7MB/s Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-04powerpc: Implement csum_ipv6_magic in assemblyChristophe Leroy
The generic csum_ipv6_magic() generates a pretty bad result 00000000 <csum_ipv6_magic>: (PPC32) 0: 81 23 00 00 lwz r9,0(r3) 4: 81 03 00 04 lwz r8,4(r3) 8: 7c e7 4a 14 add r7,r7,r9 c: 7d 29 38 10 subfc r9,r9,r7 10: 7d 4a 51 10 subfe r10,r10,r10 14: 7d 27 42 14 add r9,r7,r8 18: 7d 2a 48 50 subf r9,r10,r9 1c: 80 e3 00 08 lwz r7,8(r3) 20: 7d 08 48 10 subfc r8,r8,r9 24: 7d 4a 51 10 subfe r10,r10,r10 28: 7d 29 3a 14 add r9,r9,r7 2c: 81 03 00 0c lwz r8,12(r3) 30: 7d 2a 48 50 subf r9,r10,r9 34: 7c e7 48 10 subfc r7,r7,r9 38: 7d 4a 51 10 subfe r10,r10,r10 3c: 7d 29 42 14 add r9,r9,r8 40: 7d 2a 48 50 subf r9,r10,r9 44: 80 e4 00 00 lwz r7,0(r4) 48: 7d 08 48 10 subfc r8,r8,r9 4c: 7d 4a 51 10 subfe r10,r10,r10 50: 7d 29 3a 14 add r9,r9,r7 54: 7d 2a 48 50 subf r9,r10,r9 58: 81 04 00 04 lwz r8,4(r4) 5c: 7c e7 48 10 subfc r7,r7,r9 60: 7d 4a 51 10 subfe r10,r10,r10 64: 7d 29 42 14 add r9,r9,r8 68: 7d 2a 48 50 subf r9,r10,r9 6c: 80 e4 00 08 lwz r7,8(r4) 70: 7d 08 48 10 subfc r8,r8,r9 74: 7d 4a 51 10 subfe r10,r10,r10 78: 7d 29 3a 14 add r9,r9,r7 7c: 7d 2a 48 50 subf r9,r10,r9 80: 81 04 00 0c lwz r8,12(r4) 84: 7c e7 48 10 subfc r7,r7,r9 88: 7d 4a 51 10 subfe r10,r10,r10 8c: 7d 29 42 14 add r9,r9,r8 90: 7d 2a 48 50 subf r9,r10,r9 94: 7d 08 48 10 subfc r8,r8,r9 98: 7d 4a 51 10 subfe r10,r10,r10 9c: 7d 29 2a 14 add r9,r9,r5 a0: 7d 2a 48 50 subf r9,r10,r9 a4: 7c a5 48 10 subfc r5,r5,r9 a8: 7c 63 19 10 subfe r3,r3,r3 ac: 7d 29 32 14 add r9,r9,r6 b0: 7d 23 48 50 subf r9,r3,r9 b4: 7c c6 48 10 subfc r6,r6,r9 b8: 7c 63 19 10 subfe r3,r3,r3 bc: 7c 63 48 50 subf r3,r3,r9 c0: 54 6a 80 3e rotlwi r10,r3,16 c4: 7c 63 52 14 add r3,r3,r10 c8: 7c 63 18 f8 not r3,r3 cc: 54 63 84 3e rlwinm r3,r3,16,16,31 d0: 4e 80 00 20 blr 0000000000000000 <.csum_ipv6_magic>: (PPC64) 0: 81 23 00 00 lwz r9,0(r3) 4: 80 03 00 04 lwz r0,4(r3) 8: 81 63 00 08 lwz r11,8(r3) c: 7c e7 4a 14 add r7,r7,r9 10: 7f 89 38 40 cmplw cr7,r9,r7 14: 7d 47 02 14 add r10,r7,r0 18: 7d 30 10 26 mfocrf r9,1 1c: 55 29 f7 fe rlwinm r9,r9,30,31,31 20: 7d 4a 4a 14 add r10,r10,r9 24: 7f 80 50 40 cmplw cr7,r0,r10 28: 7d 2a 5a 14 add r9,r10,r11 2c: 80 03 00 0c lwz r0,12(r3) 30: 81 44 00 00 lwz r10,0(r4) 34: 7d 10 10 26 mfocrf r8,1 38: 55 08 f7 fe rlwinm r8,r8,30,31,31 3c: 7d 29 42 14 add r9,r9,r8 40: 81 04 00 04 lwz r8,4(r4) 44: 7f 8b 48 40 cmplw cr7,r11,r9 48: 7d 29 02 14 add r9,r9,r0 4c: 7d 70 10 26 mfocrf r11,1 50: 55 6b f7 fe rlwinm r11,r11,30,31,31 54: 7d 29 5a 14 add r9,r9,r11 58: 7f 80 48 40 cmplw cr7,r0,r9 5c: 7d 29 52 14 add r9,r9,r10 60: 7c 10 10 26 mfocrf r0,1 64: 54 00 f7 fe rlwinm r0,r0,30,31,31 68: 7d 69 02 14 add r11,r9,r0 6c: 7f 8a 58 40 cmplw cr7,r10,r11 70: 7c 0b 42 14 add r0,r11,r8 74: 81 44 00 08 lwz r10,8(r4) 78: 7c f0 10 26 mfocrf r7,1 7c: 54 e7 f7 fe rlwinm r7,r7,30,31,31 80: 7c 00 3a 14 add r0,r0,r7 84: 7f 88 00 40 cmplw cr7,r8,r0 88: 7d 20 52 14 add r9,r0,r10 8c: 80 04 00 0c lwz r0,12(r4) 90: 7d 70 10 26 mfocrf r11,1 94: 55 6b f7 fe rlwinm r11,r11,30,31,31 98: 7d 29 5a 14 add r9,r9,r11 9c: 7f 8a 48 40 cmplw cr7,r10,r9 a0: 7d 29 02 14 add r9,r9,r0 a4: 7d 70 10 26 mfocrf r11,1 a8: 55 6b f7 fe rlwinm r11,r11,30,31,31 ac: 7d 29 5a 14 add r9,r9,r11 b0: 7f 80 48 40 cmplw cr7,r0,r9 b4: 7d 29 2a 14 add r9,r9,r5 b8: 7c 10 10 26 mfocrf r0,1 bc: 54 00 f7 fe rlwinm r0,r0,30,31,31 c0: 7d 29 02 14 add r9,r9,r0 c4: 7f 85 48 40 cmplw cr7,r5,r9 c8: 7c 09 32 14 add r0,r9,r6 cc: 7d 50 10 26 mfocrf r10,1 d0: 55 4a f7 fe rlwinm r10,r10,30,31,31 d4: 7c 00 52 14 add r0,r0,r10 d8: 7f 80 30 40 cmplw cr7,r0,r6 dc: 7d 30 10 26 mfocrf r9,1 e0: 55 29 ef fe rlwinm r9,r9,29,31,31 e4: 7c 09 02 14 add r0,r9,r0 e8: 54 03 80 3e rotlwi r3,r0,16 ec: 7c 03 02 14 add r0,r3,r0 f0: 7c 03 00 f8 not r3,r0 f4: 78 63 84 22 rldicl r3,r3,48,48 f8: 4e 80 00 20 blr This patch implements it in assembly for both PPC32 and PPC64 Link: https://github.com/linuxppc/linux/issues/9 Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-04powerpc/32: Optimise __csum_partial()Christophe Leroy
Improve __csum_partial by interleaving loads and adds. On a 8xx, it brings neither improvement nor degradation. On a 83xx, it brings a 25% improvement. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-04powerpc/lib: Adjust .balign inside string functions for PPC32Christophe Leroy
commit 87a156fb18fe1 ("Align hot loops of some string functions") degraded the performance of string functions by adding useless nops A simple benchmark on an 8xx calling 100000x a memchr() that matches the first byte runs in 41668 TB ticks before this patch and in 35986 TB ticks after this patch. So this gives an improvement of approx 10% Another benchmark doing the same with a memchr() matching the 128th byte runs in 1011365 TB ticks before this patch and 1005682 TB ticks after this patch, so regardless on the number of loops, removing those useless nops improves the test by 5683 TB ticks. Fixes: 87a156fb18fe1 ("Align hot loops of some string functions") Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-04powerpc/sstep: Fix emulate_step test if VSX not presentRavi Bangoria
emulate_step() tests are failing if VSX is not supported or disabled. emulate_step_test: lxvd2x : FAIL emulate_step_test: stxvd2x : FAIL If !CPU_FTR_VSX, emulate_step() failure is expected and testcase should PASS with a valid justification. After patch: emulate_step_test: lxvd2x : PASS (!CPU_FTR_VSX) emulate_step_test: stxvd2x : PASS (!CPU_FTR_VSX) Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-04powerpc/sstep: Fix kernel crash if VSX is not presentRavi Bangoria
emulate_step() is not checking runtime VSX feature flag before emulating an instruction. This is causing kernel crash when kernel is compiled with CONFIG_VSX=y but running on a machine where VSX is not supported or disabled. Ex, while running emulate_step tests on P6 machine: Oops: Exception in kernel mode, sig: 4 [#1] NIP [c000000000095c24] .load_vsrn+0x28/0x54 LR [c000000000094bdc] .emulate_loadstore+0x167c/0x17b0 Call Trace: 0x40fe240c7ae147ae (unreliable) .emulate_loadstore+0x167c/0x17b0 .emulate_step+0x25c/0x5bc .test_lxvd2x_stxvd2x+0x64/0x154 .test_emulate_step+0x38/0x4c .do_one_initcall+0x5c/0x2c0 .kernel_init_freeable+0x314/0x4cc .kernel_init+0x24/0x160 .ret_from_kernel_thread+0x58/0xb4 With fix: emulate_step_test: lxvd2x : FAIL emulate_step_test: stxvd2x : FAIL Reported-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-03powerpc/sstep: Introduce GETTYPE macroRavi Bangoria
Replace 'op->type & INSTR_TYPE_MASK' expression with GETTYPE(op->type) macro. Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-03powerpc/64s: Patch barrier_nospec in modulesMichal Suchanek
Note that unlike RFI which is patched only in kernel the nospec state reflects settings at the time the module was loaded. Iterating all modules and re-patching every time the settings change is not implemented. Based on lwsync patching. Signed-off-by: Michal Suchanek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-03powerpc/64s: Add support for ori barrier_nospec patchingMichal Suchanek
Based on the RFI patching. This is required to be able to disable the speculation barrier. Only one barrier type is supported and it does nothing when the firmware does not enable it. Also re-patching modules is not supported So the only meaningful thing that can be done is patching out the speculation barrier at boot when the user says it is not wanted. Signed-off-by: Michal Suchanek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-05-25powerpc/altivec: Add missing prototypes for altivecMathieu Malaterre
Some functions prototypes were missing for the non-altivec code. Add the missing prototypes in a new header file, fix warnings treated as errors with W=1: arch/powerpc/lib/xor_vmx_glue.c:18:6: error: no previous prototype for ‘xor_altivec_2’ [-Werror=missing-prototypes] arch/powerpc/lib/xor_vmx_glue.c:29:6: error: no previous prototype for ‘xor_altivec_3’ [-Werror=missing-prototypes] arch/powerpc/lib/xor_vmx_glue.c:40:6: error: no previous prototype for ‘xor_altivec_4’ [-Werror=missing-prototypes] arch/powerpc/lib/xor_vmx_glue.c:52:6: error: no previous prototype for ‘xor_altivec_5’ [-Werror=missing-prototypes] The prototypes were already present in <asm/xor.h> but this header file is meant to be included after <include/linux/raid/xor.h>. Trying to re-use <asm/xor.h> directly would lead to warnings such as: arch/powerpc/include/asm/xor.h:39:15: error: variable ‘xor_block_altivec’ has initializer but incomplete type Trying to re-use <asm/xor.h> after <include/linux/raid/xor.h> in xor_vmx_glue.c would in turn trigger the following warnings: include/asm-generic/xor.h:688:34: error: ‘xor_block_32regs’ defined but not used [-Werror=unused-variable] Signed-off-by: Mathieu Malaterre <malat@debian.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-05-21powerpc/64s: Add support for a store forwarding barrier at kernel entry/exitNicholas Piggin
On some CPUs we can prevent a vulnerability related to store-to-load forwarding by preventing store forwarding between privilege domains, by inserting a barrier in kernel entry and exit paths. This is known to be the case on at least Power7, Power8 and Power9 powerpc CPUs. Barriers must be inserted generally before the first load after moving to a higher privilege, and after the last store before moving to a lower privilege, HV and PR privilege transitions must be protected. Barriers are added as patch sections, with all kernel/hypervisor entry points patched, and the exit points to lower privilge levels patched similarly to the RFI flush patching. Firmware advertisement is not implemented yet, so CPU flush types are hard coded. Thanks to Michal Suchánek for bug fixes and review. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michal Suchánek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-05-18powerpc/lib: Fix "integer constant is too large" build failureFinn Thain
My powerpc-linux-gnu-gcc v4.4.5 compiler can't build a 32-bit kernel any more: arch/powerpc/lib/sstep.c: In function 'do_popcnt': arch/powerpc/lib/sstep.c:1068: error: integer constant is too large for 'long' type arch/powerpc/lib/sstep.c:1069: error: integer constant is too large for 'long' type arch/powerpc/lib/sstep.c:1069: error: integer constant is too large for 'long' type arch/powerpc/lib/sstep.c:1070: error: integer constant is too large for 'long' type arch/powerpc/lib/sstep.c:1079: error: integer constant is too large for 'long' type arch/powerpc/lib/sstep.c: In function 'do_prty': arch/powerpc/lib/sstep.c:1117: error: integer constant is too large for 'long' type This file gets compiled with -std=gnu89 which means a constant can be given the type 'long' even if it won't fit. Fix the errors with a 'ULL' suffix on the relevant constants. Fixes: 2c979c489fee ("powerpc/lib/sstep: Add prty instruction emulation") Fixes: dcbd19b48d31 ("powerpc/lib/sstep: Add popcnt instruction emulation") Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-05-11powerpc/lib: Add alt patching test of branching past the last instructionMichael Ellerman
Add a test of the relative branch patching logic in the alternate section feature fixup code. This tests that if we branch past the last instruction of the alternate section, the branch is not patched. That's because the assembler will have created a branch that already points to the first instruction after the patched section, which is correct and needs no further patching. Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-05-11powerpc/lib: Rename ftr_fixup_test7 to ftr_fixup_test_too_bigMichael Ellerman
We want this to remain the last test (because it's disabled by default), so give it a non-numbered name so we don't have to renumber it when adding new tests before it. Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-05-11powerpc/lib: Fix the feature fixup tests to actually workMichael Ellerman
The code patching code has always been a bit confused about whether it's best to use void *, unsigned int *, char *, etc. to point to instructions. In fact in the feature fixups tests we use both unsigned int[] and u8[] in different places. Unfortunately the tests that use unsigned int[] calculate the size of the code blocks using subtraction of those unsigned int pointers, and then pass the result to memcmp(). This means we're only comparing 1/4 of the bytes we need to, because we need to multiply by sizeof(unsigned int) to get the number of *bytes*. The result is that the tests do all the patching and then only compare some of the resulting code, so patching bugs that only effect that last 3/4 of the code could slip through undetected. It turns out that hasn't been happening, although one test had a bad expected case (see previous commit). Fix it for now by multiplying the size by 4 in the affected functions. Fixes: 362e7701fd18 ("powerpc: Add self-tests of the feature fixup code") Epic-brown-paper-bag-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-05-11powerpc/lib: Fix feature fixup test of external branchMichael Ellerman
The expected case for this test was wrong, the source of the alternate code sequence is: FTR_SECTION_ELSE 2: or 2,2,2 PPC_LCMPI r3,1 beq 3f blt 2b b 3f b 1b ALT_FTR_SECTION_END(0, 1) 3: or 1,1,1 or 2,2,2 4: or 3,3,3 So when it's patched the '3' label should still be on the 'or 1,1,1', and the 4 label is irrelevant and can be removed. Fixes: 362e7701fd18 ("powerpc: Add self-tests of the feature fixup code") Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-04-17powerpc/lib: Fix off-by-one in alternate feature patchingMichael Ellerman
When we patch an alternate feature section, we have to adjust any relative branches that branch out of the alternate section. But currently we have a bug if we have a branch that points to past the last instruction of the alternate section, eg: FTR_SECTION_ELSE 1: b 2f or 6,6,6 2: ALT_FTR_SECTION_END(...) nop This will result in a relative branch at 1 with a target that equals the end of the alternate section. That branch does not need adjusting when it's moved to the non-else location. Currently we do adjust it, resulting in a branch that goes off into the link-time location of the else section, which is junk. The fix is to not patch branches that have a target == end of the alternate section. Fixes: d20fe50a7b3c ("KVM: PPC: Book3S HV: Branch inside feature section") Fixes: 9b1a735de64c ("powerpc: Add logic to patch alternative feature sections") Cc: stable@vger.kernel.org # v2.6.27+ Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-04-01powerpc/64s: Set assembler machine type to POWER4Nicholas Piggin
Rather than override the machine type in .S code (which can hide wrong or ambiguous code generation for the target), set the type to power4 for all assembly. This also means we need to be careful not to build power4-only code when we're not building for Book3S, such as the "power7" versions of copyuser/page/memcpy. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> [mpe: Fix Book3E build, don't build the "power7" variants for non-Book3S] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-03-27powerpc/rfi-flush: Differentiate enabled and patched flush typesMauricio Faria de Oliveira
Currently the rfi-flush messages print 'Using <type> flush' for all enabled_flush_types, but that is not necessarily true -- as now the fallback flush is always enabled on pseries, but the fixup function overwrites its nop/branch slot with other flush types, if available. So, replace the 'Using <type> flush' messages with '<type> flush is available'. Also, print the patched flush types in the fixup function, so users can know what is (not) being used (e.g., the slower, fallback flush, or no flush type at all if flush is disabled via the debugfs switch). Suggested-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-03-13powerpc/32: Move the inline keyword at the beginning of function declarationMathieu Malaterre
The inline keyword was not at the beginning of the function declaration. Fix the following warning (treated as error in W=1): arch/powerpc/lib/sstep.c:283:1: error: ‘inline’ is not at beginning of declaration static int nokprobe_inline copy_mem_in(u8 *dest, unsigned long ea, int nb, arch/powerpc/lib/sstep.c:388:1: error: ‘inline’ is not at beginning of declaration static int nokprobe_inline copy_mem_out(u8 *dest, unsigned long ea, int nb, Signed-off-by: Mathieu Malaterre <malat@debian.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-01-21Merge branch 'fixes' into nextMichael Ellerman
Merge our fixes branch from the 4.15 cycle. Unusually the fixes branch saw some significant features merged, notably the RFI flush patches, so we want the code in next to be tested against that, to avoid any surprises when the two are merged. There's also some other work on the panic handling that was reverted in fixes and we now want to do properly in next, which would conflict. And we also fix a few other minor merge conflicts.
2018-01-21powerpc/lib/feature-fixups: use raw_patch_instruction()Christophe Leroy
feature fixups need to use patch_instruction() early in the boot, even before the code is relocated to its final address, requiring patch_instruction() to use PTRRELOC() in order to address data. But feature fixups applies on code before it is set to read only, even for modules. Therefore, feature fixups can use raw_patch_instruction() instead. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-01-21powerpc/lib/code-patching: refactor patch_instruction()Christophe Leroy
patch_instruction() uses almost the same sequence as __patch_instruction() This patch refactor it so that patch_instruction() uses __patch_instruction() instead of duplicating code. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Acked-by: Balbir Singh <bsingharora@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-01-10powerpc/64s: Add support for RFI flush of L1-D cacheMichael Ellerman
On some CPUs we can prevent the Meltdown vulnerability by flushing the L1-D cache on exit from kernel to user mode, and from hypervisor to guest. This is known to be the case on at least Power7, Power8 and Power9. At this time we do not know the status of the vulnerability on other CPUs such as the 970 (Apple G5), pasemi CPUs (AmigaOne X1000) or Freescale CPUs. As more information comes to light we can enable this, or other mechanisms on those CPUs. The vulnerability occurs when the load of an architecturally inaccessible memory region (eg. userspace load of kernel memory) is speculatively executed to the point where its result can influence the address of a subsequent speculatively executed load. In order for that to happen, the first load must hit in the L1, because before the load is sent to the L2 the permission check is performed. Therefore if no kernel addresses hit in the L1 the vulnerability can not occur. We can ensure that is the case by flushing the L1 whenever we return to userspace. Similarly for hypervisor vs guest. In order to flush the L1-D cache on exit, we add a section of nops at each (h)rfi location that returns to a lower privileged context, and patch that with some sequence. Newer firmwares are able to advertise to us that there is a special nop instruction that flushes the L1-D. If we do not see that advertised, we fall back to doing a displacement flush in software. For guest kernels we support migration between some CPU versions, and different CPUs may use different flush instructions. So that we are prepared to migrate to a machine with a different flush instruction activated, we may have to patch more than one flush instruction at boot if the hypervisor tells us to. In the end this patch is mostly the work of Nicholas Piggin and Michael Ellerman. However a cast of thousands contributed to analysis of the issue, earlier versions of the patch, back ports testing etc. Many thanks to all of them. Tested-by: Jon Masters <jcm@redhat.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-12-11powerpc/modules: Don't try to restore r2 after a sibling callJosh Poimboeuf
When attempting to load a livepatch module, I got the following error: module_64: patch_module: Expect noop after relocate, got 3c820000 The error was triggered by the following code in unregister_netdevice_queue(): 14c: 00 00 00 48 b 14c <unregister_netdevice_queue+0x14c> 14c: R_PPC64_REL24 net_set_todo 150: 00 00 82 3c addis r4,r2,0 GCC didn't insert a nop after the branch to net_set_todo() because it's a sibling call, so it never returns. The nop isn't needed after the branch in that case. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Reviewed-and-tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-11-24Merge tag 'powerpc-4.15-2' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux Pull powerpc fixes from Michael Ellerman: "A small batch of fixes, about 50% tagged for stable and the rest for recently merged code. There's one more fix for the >128T handling on hash. Once a process had requested a single mmap above 128T we would then always search above 128T. The correct behaviour is to consider the hint address in isolation for each mmap request. Then a couple of fixes for the IMC PMU, a missing EXPORT_SYMBOL in VAS, a fix for STRICT_KERNEL_RWX on 32-bit, and a fix to correctly identify P9 DD2.1 but in code that is currently not used by default. Thanks to: Aneesh Kumar K.V, Christophe Leroy, Madhavan Srinivasan, Sukadev Bhattiprolu" * tag 'powerpc-4.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: powerpc/64s: Fix Power9 DD2.1 logic in DT CPU features powerpc/perf: Fix IMC_MAX_PMU macro powerpc/perf: Fix pmu_count to count only nest imc pmus powerpc: Fix boot on BOOK3S_32 with CONFIG_STRICT_KERNEL_RWX powerpc/perf/imc: Use cpu_to_node() not topology_physical_package_id() powerpc/vas: Export chip_to_vas_id() powerpc/64s/slice: Use addr limit when computing slice mask
2017-11-22powerpc: Fix boot on BOOK3S_32 with CONFIG_STRICT_KERNEL_RWXChristophe Leroy
On powerpc32, patch_instruction() is called by apply_feature_fixups() which is called from early_init() There is the following note in front of early_init(): * Note that the kernel may be running at an address which is different * from the address that it was linked at, so we must use RELOC/PTRRELOC * to access static data (including strings). -- paulus Therefore, slab_is_available() cannot be called yet, and text_poke_area must be addressed with PTRRELOC() Fixes: 95902e6c8864 ("powerpc/mm: Implement STRICT_KERNEL_RWX on PPC32") Cc: stable@vger.kernel.org # v4.14+ Reported-by: Meelis Roos <mroos@linux.ee> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-11-16Merge tag 'powerpc-4.15-1' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux Pull powerpc updates from Michael Ellerman: "A bit of a small release, I suspect in part due to me travelling for KS. But my backlog of patches to review is smaller than usual, so I think in part folks just didn't send as much this cycle. Non-highlights: - Five fixes for the >128T address space handling, both to fix bugs in our implementation and to bring the semantics exactly into line with x86. Highlights: - Support for a new OPAL call on bare metal machines which gives us a true NMI (ie. is not masked by MSR[EE]=0) for debugging etc. - Support for Power9 DD2 in the CXL driver. - Improvements to machine check handling so that uncorrectable errors can be reported into the generic memory_failure() machinery. - Some fixes and improvements for VPHN, which is used under PowerVM to notify the Linux partition of topology changes. - Plumbing to enable TM (transactional memory) without suspend on some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND). - Support for emulating vector loads form cache-inhibited memory, on some Power9 revisions. - Disable the fast-endian switch "syscall" by default (behind a CONFIG), we believe it has never had any users. - A major rework of the API drivers use when initiating and waiting for long running operations performed by OPAL firmware, and changes to the powernv_flash driver to use the new API. - Several fixes for the handling of FP/VMX/VSX while processes are using transactional memory. - Optimisations of TLB range flushes when using the radix MMU on Power9. - Improvements to the VAS facility used to access coprocessors on Power9, and related improvements to the way the NX crypto driver handles requests. - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit. Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard, Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley, Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu, Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee, Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A. Kennington III" * tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits) powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature powerpc/64s: Fix masking of SRR1 bits on instruction fault powerpc/64s: mm_context.addr_limit is only used on hash powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary powerpc/64s/hash: Fix fork() with 512TB process address space powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation powerpc/64s/hash: Fix 512T hint detection to use >= 128T powerpc: Fix DABR match on hash based systems powerpc/signal: Properly handle return value from uprobe_deny_signal() powerpc/fadump: use kstrtoint to handle sysfs store powerpc/lib: Implement UACCESS_FLUSHCACHE API powerpc/lib: Implement PMEM API powerpc/powernv/npu: Don't explicitly flush nmmu tlb powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm() powerpc/powernv/idle: Round up latency and residency values powerpc/kprobes: refactor kprobe_lookup_name for safer string operations powerpc/kprobes: Blacklist emulate_update_regs() from kprobes powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace powerpc/kprobes: Disable preemption before invoking probe handler for optprobes ...
2017-11-13powerpc/lib: Implement UACCESS_FLUSHCACHE APIOliver O'Halloran
Implement the architecture specific portitions of the UACCESS_FLUSHCACHE API. This provides functions for the copy_user_flushcache iterator that ensure that when the copy is finished the destination buffer contains a copy of the original and that the destination buffer is clean in the processor caches. Signed-off-by: Oliver O'Halloran <oohall@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-11-13powerpc/lib: Implement PMEM APIOliver O'Halloran
Implement the architecture specific cache maintence functions that make up the "PMEM API". Currently the writeback and invalidate functions are the same since the function of the DCBST (data cache block store) instruction is typically interpreted as "writeback to the point of coherency" rather than to memory. As a result implementing the API requires a full cache flush rather than just a cache write back. This will probably change in the not-too-distant future. Signed-off-by: Oliver O'Halloran <oohall@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-11-12powerpc/kprobes: Blacklist emulate_update_regs() from kprobesNaveen N. Rao
Commit 3cdfcbfd32b9d ("powerpc: Change analyse_instr so it doesn't modify *regs") introduced emulate_update_regs() to perform part of what emulate_step() was doing earlier. However, this function was not added to the kprobes blacklist. Add it so as to prevent it from being probed. Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-11-10Merge branch 'fixes' into nextMichael Ellerman
We have some dependencies & conflicts between patches in fixes and things to go in next, both in the radix TLB flush code and the IMC PMU driver. So merge fixes into next.
2017-11-02License cleanup: add SPDX GPL-2.0 license identifier to files with no licenseGreg Kroah-Hartman
Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-10-10powerpc/lib/sstep: Fix count leading zeros instructionsSandipan Das
According to the GCC documentation, the behaviour of __builtin_clz() and __builtin_clzl() is undefined if the value of the input argument is zero. Without handling this special case, these builtins have been used for emulating the following instructions: * Count Leading Zeros Word (cntlzw[.]) * Count Leading Zeros Doubleword (cntlzd[.]) This fixes the emulated behaviour of these instructions by adding an additional check for this special case. Fixes: 3cdfcbfd32b9d ("powerpc: Change analyse_instr so it doesn't modify *regs") Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com> Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-10-04powerpc/lib/sstep: Fix fixed-point shift instructions that set CA32Sandipan Das
This fixes the emulated behaviour of existing fixed-point shift right algebraic instructions that are supposed to set both the CA and CA32 bits of XER when running on a system that is compliant with POWER ISA v3.0 independent of whether the system is executing in 32-bit mode or 64-bit mode. The following instructions are affected: * Shift Right Algebraic Word Immediate (srawi[.]) * Shift Right Algebraic Word (sraw[.]) * Shift Right Algebraic Doubleword Immediate (sradi[.]) * Shift Right Algebraic Doubleword (srad[.]) Fixes: 0016a4cf5582 ("powerpc: Emulate most Book I instructions in emulate_step()") Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-10-04powerpc/lib/sstep: Fix fixed-point arithmetic instructions that set CA32Sandipan Das
There are existing fixed-point arithmetic instructions that always set the CA bit of XER to reflect the carry out of bit 0 in 64-bit mode and out of bit 32 in 32-bit mode. In ISA v3.0, these instructions also always set the CA32 bit of XER to reflect the carry out of bit 32. This fixes the emulated behaviour of such instructions when running on a system that is compliant with POWER ISA v3.0. The following instructions are affected: * Add Immediate Carrying (addic) * Add Immediate Carrying and Record (addic.) * Subtract From Immediate Carrying (subfic) * Add Carrying (addc[.]) * Subtract From Carrying (subfc[.]) * Add Extended (adde[.]) * Subtract From Extended (subfe[.]) * Add to Minus One Extended (addme[.]) * Subtract From Minus One Extended (subfme[.]) * Add to Zero Extended (addze[.]) * Subtract From Zero Extended (subfze[.]) Fixes: 0016a4cf5582 ("powerpc: Emulate most Book I instructions in emulate_step()") Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-10-04powerpc/lib/sstep: Add XER bits introduced in POWER ISA v3.0Sandipan Das
This adds definitions for the OV32 and CA32 bits of XER that were introduced in POWER ISA v3.0. There are some existing instructions that currently set the OV and CA bits based on certain conditions. The emulation behaviour of all these instructions needs to be updated to set these new bits accordingly. Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com> Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-20powerpc/sstep: mullw should calculate a 64 bit signed resultAnton Blanchard
mullw should do a 32 bit signed multiply and create a 64 bit signed result. It currently truncates the result to 32 bits. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-20powerpc/sstep: Fix issues with mcrfAnton Blanchard
mcrf broke when we changed analyse_instr() to not modify the register state. The instruction writes to the CR, so we need to store the result in op->ccval, not op->val. Fixes: 3cdfcbfd32b9 ("powerpc: Change analyse_instr so it doesn't modify *regs") Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-20powerpc/sstep: Fix issues with set_cr0()Anton Blanchard
set_cr0() broke when we changed analyse_instr() to not modify the register state. Instead of looking at regs->gpr[x] which has not been updated yet, we need to look at op->val. Fixes: 3cdfcbfd32b9 ("powerpc: Change analyse_instr so it doesn't modify *regs") Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-04powerpc: Fix kernel crash in emulation of vector loads and storesPaul Mackerras
Commit 350779a29f11 ("powerpc: Handle most loads and stores in instruction emulation code", 2017-08-30) changed the register usage in get_vr and put_vr with the aim of leaving the register number in r3 untouched on return. Unfortunately, r6 was not a good choice, as the callers as of 350779a29f11 store a MSR value in r6. Then, in commit c22435a5f3d8 ("powerpc: Emulate FP/vector/VSX loads/stores correctly when regs not live", 2017-08-30), the saving and restoring of the MSR got moved into get_vr and put_vr. Either way, the effect is that we put a value in MSR that only has the 0x3f8 bits non-zero, meaning that we are switching to 32-bit mode. That leads to a crash like this: Unable to handle kernel paging request for instruction fetch Faulting instruction address: 0x0007bea0 Oops: Kernel access of bad area, sig: 11 [#12] LE SMP NR_CPUS=2048 NUMA PowerNV Modules linked in: vmx_crypto binfmt_misc ip_tables x_tables autofs4 crc32c_vpmsum CPU: 6 PID: 32659 Comm: trashy_testcase Tainted: G D 4.13.0-rc2-00313-gf3026f57e6ed-dirty #23 task: c000000f1bb9e780 task.stack: c000000f1ba98000 NIP: 000000000007bea0 LR: c00000000007b054 CTR: c00000000007be70 REGS: c000000f1ba9b960 TRAP: 0400 Tainted: G D (4.13.0-rc2-00313-gf3026f57e6ed-dirty) MSR: 10000000400010a1 <HV,ME,IR,LE> CR: 48000228 XER: 00000000 CFAR: c00000000007be74 SOFTE: 1 GPR00: c00000000007b054 c000000f1ba9bbe0 c000000000e6e000 000000000000001d GPR04: c000000f1ba9bc00 c00000000007be70 00000000000000e8 9000000002009033 GPR08: 0000000002000000 100000000282f033 000000000b0a0900 0000000000001009 GPR12: 0000000000000000 c00000000fd42100 0706050303020100 a5a5a5a5a5a5a5a5 GPR16: 2e2e2e2e2e2de70c 2e2e2e2e2e2e2e2d 0000000000ff00ff 0606040202020000 GPR20: 000000000000005b ffffffffffffffff 0000000003020100 0000000000000000 GPR24: c000000f1ab90020 c000000f1ba9bc00 0000000000000001 0000000000000001 GPR28: c000000f1ba9bc90 c000000f1ba9bea0 000000000b0a0908 0000000000000001 NIP [000000000007bea0] 0x7bea0 LR [c00000000007b054] emulate_loadstore+0x1044/0x1280 Call Trace: [c000000f1ba9bbe0] [c000000000076b80] analyse_instr+0x60/0x34f0 (unreliable) [c000000f1ba9bc70] [c00000000007b7ec] emulate_step+0x23c/0x544 [c000000f1ba9bce0] [c000000000053424] arch_uprobe_skip_sstep+0x24/0x40 [c000000f1ba9bd00] [c00000000024b2f8] uprobe_notify_resume+0x598/0xba0 [c000000f1ba9be00] [c00000000001c284] do_notify_resume+0xd4/0xf0 [c000000f1ba9be30] [c00000000000bd44] ret_from_except_lite+0x70/0x74 Instruction dump: XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX ---[ end trace a7ae7a7f3e0256b5 ]--- To fix this, we just revert to using r3 as before, since the callers don't rely on r3 being left unmodified. Fortunately, this can't be triggered by a misaligned load or store, because vector loads and stores truncate misaligned addresses rather than taking an alignment interrupt. It can be triggered using uprobes. Fixes: 350779a29f11 ("powerpc: Handle most loads and stores in instruction emulation code") Reported-by: Anton Blanchard <anton@ozlabs.org> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Tested-by: Anton Blanchard <anton@samba.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-02powerpc/sstep: Avoid used uninitialized errorMichael Ellerman
Older compilers think val may be used uninitialized: arch/powerpc/lib/sstep.c: In function 'emulate_loadstore': arch/powerpc/lib/sstep.c:2758:23: error: 'val' may be used uninitialized in this function We know better, but initialise val to 0 to avoid breaking the build. Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-01powerpc/32: remove a NOP from memset()Christophe Leroy
memset() is patched after initialisation to activate the optimised part which uses cache instructions. Today we have a 'b 2f' to skip the optimised patch, which then gets replaced by a NOP, implying a useless cycle consumption. As we have a 'bne 2f' just before, we could use that instruction for the live patching, hence removing the need to have a dedicated 'b 2f' to be replaced by a NOP. This patch changes the 'bne 2f' by a 'b 2f'. During init, that 'b 2f' is then replaced by 'bne 2f' Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-01powerpc/32: optimise memset()Christophe Leroy
There is no need to extend the set value to an int when the length is lower than 4 as in that case we only do byte stores. We can therefore immediately branch to the part handling it. By separating it from the normal case, we are able to eliminate a few actions on the destination pointer. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-01powerpc: fix location of two EXPORT_SYMBOLChristophe Leroy
Commit 9445aa1a3062a ("ppc: move exports to definitions") added EXPORT_SYMBOL() for memset() and flush_hash_pages() in the middle of the functions. This patch moves them at the end of the two functions. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-01powerpc/32: add memset16()Christophe Leroy
Commit 694fc88ce271f ("powerpc/string: Implement optimized memset variants") added memset16(), memset32() and memset64() for the 64 bits PPC. On 32 bits, memset64() is not relevant, and as shown below, the generic version of memset32() gives a good code, so only memset16() is candidate for an optimised version. 000009c0 <memset32>: 9c0: 2c 05 00 00 cmpwi r5,0 9c4: 39 23 ff fc addi r9,r3,-4 9c8: 4d 82 00 20 beqlr 9cc: 7c a9 03 a6 mtctr r5 9d0: 94 89 00 04 stwu r4,4(r9) 9d4: 42 00 ff fc bdnz 9d0 <memset32+0x10> 9d8: 4e 80 00 20 blr The last part of memset() handling the not 4-bytes multiples operates on bytes, making it unsuitable for handling word without modification. As it would increase memset() complexity, it is better to implement memset16() from scratch. In addition it has the advantage of allowing a more optimised memset16() than what we would have by using the memset() function. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-01powerpc: Wrap register number correctly for string load/store instructionsPaul Mackerras
Michael Ellerman reported that emulate_loadstore() was trying to access element 32 of regs->gpr[], which doesn't exist, when emulating a string store instruction. This is because the string load and store instructions (lswi, lswx, stswi and stswx) are defined to wrap around from register 31 to register 0 if the number of bytes being loaded or stored is sufficiently large. This wrapping was not implemented in the emulation code. To fix it, we mask the register number after incrementing it. Reported-by: Michael Ellerman <mpe@ellerman.id.au> Fixes: c9f6f4ed95d4 ("powerpc: Implement emulation of string loads and stores") Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
generated by cgit (git 2.34.1) at 2024-06-08 17:05:02 +0000