talos-op-linux/arch/x86/Makefile, branch master

x86/build: Add -Wnoaddress-of-packed-member to REALMODE_CFLAGS, to silence GCC9 build warning

2019-08-28T15:31:31+00:00

One of the very few warnings I have in the current build comes from arch/x86/boot/edd.c, where I get the following with a gcc9 build: arch/x86/boot/edd.c: In function ‘query_edd’: arch/x86/boot/edd.c:148:11: warning: taking address of packed member of ‘struct boot_params’ may result in an unaligned pointer value [-Waddress-of-packed-member] 148 | mbrptr = boot_params.edd_mbr_sig_buffer; | ^~~~~~~~~~~ This warning triggers because we throw away all the CFLAGS and then make a new set for REALMODE_CFLAGS, so the -Wno-address-of-packed-member we added in the following commit is not present: 6f303d60534c ("gcc-9: silence 'address-of-packed-member' warning") The simplest solution for now is to adjust the warning for this version of CFLAGS as well, but it would definitely make sense to examine whether REALMODE_CFLAGS could be derived from CFLAGS, so that it picks up changes in the compiler flags environment automatically. Signed-off-by: Linus Torvalds Acked-by: Borislav Petkov Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar

x86/build: Keep local relocations with ld.lld

2019-04-05T10:34:35+00:00

The LLVM linker (ld.lld) defaults to removing local relocations, which causes KASLR boot failures. ld.bfd and ld.gold already handle this correctly. This adds the explicit instruction "--discard-none" during the link phase. There is no change in output for ld.bfd and ld.gold, but ld.lld now produces an image with all the needed relocations. Signed-off-by: Kees Cook Signed-off-by: Borislav Petkov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Nick Desaulniers Cc: Thomas Gleixner Cc: clang-built-linux@googlegroups.com Cc: x86-ml Link: https://lkml.kernel.org/r/20190404214027.GA7324@beast Link: https://github.com/ClangBuiltLinux/linux/issues/404

x86/retpolines: Disable switch jump tables when retpolines are enabled

2019-03-28T12:39:48+00:00

Commit ce02ef06fcf7 ("x86, retpolines: Raise limit for generating indirect calls from switch-case") raised the limit under retpolines to 20 switch cases where gcc would only then start to emit jump tables, and therefore effectively disabling the emission of slow indirect calls in this area. After this has been brought to attention to gcc folks [0], Martin Liska has then fixed gcc to align with clang by avoiding to generate switch jump tables entirely under retpolines. This is taking effect in gcc starting from stable version 8.4.0. Given kernel supports compilation with older versions of gcc where the fix is not being available or backported anymore, we need to keep the extra KBUILD_CFLAGS around for some time and generally set the -fno-jump-tables to align with what more recent gcc is doing automatically today. More than 20 switch cases are not expected to be fast-path critical, but it would still be good to align with gcc behavior for versions < 8.4.0 in order to have consistency across supported gcc versions. vmlinux size is slightly growing by 0.27% for older gcc. This flag is only set to work around affected gcc, no change for clang. [0] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86952 Suggested-by: Martin Liska Signed-off-by: Daniel Borkmann Signed-off-by: Thomas Gleixner Cc: David Woodhouse Cc: Linus Torvalds Cc: Jesper Dangaard Brouer Cc: Björn Töpel Cc: Magnus Karlsson Cc: Alexei Starovoitov Cc: H.J. Lu Cc: Alexei Starovoitov Cc: David S. Miller Link: https://lkml.kernel.org/r/20190325135620.14882-1-daniel@iogearbox.net

Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2019-03-08T01:09:28+00:00

Pull x86 fpu updates from Ingo Molnar: "Three changes: - preparatory patch for AVX state tracking that computing-cluster folks would like to use for user-space batching - but we are not happy about the related ABI yet so this is only the kernel tracking side - a cleanup for CR0 handling in do_device_not_available() - plus we removed a workaround for an ancient binutils version" * 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/fpu: Track AVX-512 usage of tasks x86/fpu: Get rid of CONFIG_AS_FXSAVEQ x86/traps: Have read_cr0() only once in the #NM handler

x86, retpolines: Raise limit for generating indirect calls from switch-case

2019-02-28T11:10:31+00:00

From networking side, there are numerous attempts to get rid of indirect calls in fast-path wherever feasible in order to avoid the cost of retpolines, for example, just to name a few: * 283c16a2dfd3 ("indirect call wrappers: helpers to speed-up indirect calls of builtin") * aaa5d90b395a ("net: use indirect call wrappers at GRO network layer") * 028e0a476684 ("net: use indirect call wrappers at GRO transport layer") * 356da6d0cde3 ("dma-mapping: bypass indirect calls for dma-direct") * 09772d92cd5a ("bpf: avoid retpoline for lookup/update/delete calls on maps") * 10870dd89e95 ("netfilter: nf_tables: add direct calls for all builtin expressions") [...] Recent work on XDP from Björn and Magnus additionally found that manually transforming the XDP return code switch statement with more than 5 cases into if-else combination would result in a considerable speedup in XDP layer due to avoidance of indirect calls in CONFIG_RETPOLINE enabled builds. On i40e driver with XDP prog attached, a 20-26% speedup has been observed [0]. Aside from XDP, there are many other places later in the networking stack's critical path with similar switch-case processing. Rather than fixing every XDP-enabled driver and locations in stack by hand, it would be good to instead raise the limit where gcc would emit expensive indirect calls from the switch under retpolines and stick with the default as-is in case of !retpoline configured kernels. This would also have the advantage that for archs where this is not necessary, we let compiler select the underlying target optimization for these constructs and avoid potential slow-downs by if-else hand-rewrite. In case of gcc, this setting is controlled by case-values-threshold which has an architecture global default that selects 4 or 5 (latter if target does not have a case insn that compares the bounds) where some arch back ends like arm64 or s390 override it with their own target hooks, for example, in gcc commit db7a90aa0de5 ("S/390: Disable prediction of indirect branches") the threshold pretty much disables jump tables by limit of 20 under retpoline builds. Comparing gcc's and clang's default code generation on x86-64 under O2 level with retpoline build results in the following outcome for 5 switch cases: * gcc with -mindirect-branch=thunk-inline -mindirect-branch-register: # gdb -batch -ex 'disassemble dispatch' ./c-switch Dump of assembler code for function dispatch: 0x0000000000400be0 <+0>: cmp $0x4,%edi 0x0000000000400be3 <+3>: ja 0x400c35 0x0000000000400be5 <+5>: lea 0x915f8(%rip),%rdx # 0x4921e4 0x0000000000400bec <+12>: mov %edi,%edi 0x0000000000400bee <+14>: movslq (%rdx,%rdi,4),%rax 0x0000000000400bf2 <+18>: add %rdx,%rax 0x0000000000400bf5 <+21>: callq 0x400c01 0x0000000000400bfa <+26>: pause 0x0000000000400bfc <+28>: lfence 0x0000000000400bff <+31>: jmp 0x400bfa 0x0000000000400c01 <+33>: mov %rax,(%rsp) 0x0000000000400c05 <+37>: retq 0x0000000000400c06 <+38>: nopw %cs:0x0(%rax,%rax,1) 0x0000000000400c10 <+48>: jmpq 0x400c90 0x0000000000400c15 <+53>: nopl (%rax) 0x0000000000400c18 <+56>: jmpq 0x400c70 0x0000000000400c1d <+61>: nopl (%rax) 0x0000000000400c20 <+64>: jmpq 0x400c50 0x0000000000400c25 <+69>: nopl (%rax) 0x0000000000400c28 <+72>: jmpq 0x400c40 0x0000000000400c2d <+77>: nopl (%rax) 0x0000000000400c30 <+80>: jmpq 0x400cb0 0x0000000000400c35 <+85>: push %rax 0x0000000000400c36 <+86>: callq 0x40dd80 End of assembler dump. * clang with -mretpoline emitting search tree: # gdb -batch -ex 'disassemble dispatch' ./c-switch Dump of assembler code for function dispatch: 0x0000000000400b30 <+0>: cmp $0x1,%edi 0x0000000000400b33 <+3>: jle 0x400b44 0x0000000000400b35 <+5>: cmp $0x2,%edi 0x0000000000400b38 <+8>: je 0x400b4d 0x0000000000400b3a <+10>: cmp $0x3,%edi 0x0000000000400b3d <+13>: jne 0x400b52 0x0000000000400b3f <+15>: jmpq 0x400c50 0x0000000000400b44 <+20>: test %edi,%edi 0x0000000000400b46 <+22>: jne 0x400b5c 0x0000000000400b48 <+24>: jmpq 0x400c20 0x0000000000400b4d <+29>: jmpq 0x400c40 0x0000000000400b52 <+34>: cmp $0x4,%edi 0x0000000000400b55 <+37>: jne 0x400b66 0x0000000000400b57 <+39>: jmpq 0x400c60 0x0000000000400b5c <+44>: cmp $0x1,%edi 0x0000000000400b5f <+47>: jne 0x400b66 0x0000000000400b61 <+49>: jmpq 0x400c30 0x0000000000400b66 <+54>: push %rax 0x0000000000400b67 <+55>: callq 0x40dd20 End of assembler dump. For sake of comparison, clang without -mretpoline: # gdb -batch -ex 'disassemble dispatch' ./c-switch Dump of assembler code for function dispatch: 0x0000000000400b30 <+0>: cmp $0x4,%edi 0x0000000000400b33 <+3>: ja 0x400b57 0x0000000000400b35 <+5>: mov %edi,%eax 0x0000000000400b37 <+7>: jmpq *0x492148(,%rax,8) 0x0000000000400b3e <+14>: jmpq 0x400bf0 0x0000000000400b43 <+19>: jmpq 0x400c30 0x0000000000400b48 <+24>: jmpq 0x400c10 0x0000000000400b4d <+29>: jmpq 0x400c20 0x0000000000400b52 <+34>: jmpq 0x400c00 0x0000000000400b57 <+39>: push %rax 0x0000000000400b58 <+40>: callq 0x40dcf0 End of assembler dump. Raising the cases to a high number (e.g. 100) will still result in similar code generation pattern with clang and gcc as above, in other words clang generally turns off jump table emission by having an extra expansion pass under retpoline build to turn indirectbr instructions from their IR into switch instructions as a built-in -mno-jump-table lowering of a switch (in this case, even if IR input already contained an indirect branch). For gcc, adding --param=case-values-threshold=20 as in similar fashion as s390 in order to raise the limit for x86 retpoline enabled builds results in a small vmlinux size increase of only 0.13% (before=18,027,528 after=18,051,192). For clang this option is ignored due to i) not being needed as mentioned and ii) not having above cmdline parameter. Non-retpoline-enabled builds with gcc continue to use the default case-values-threshold setting, so nothing changes here. [0] https://lore.kernel.org/netdev/20190129095754.9390-1-bjorn.topel@gmail.com/ and "The Path to DPDK Speeds for AF_XDP", LPC 2018, networking track: - http://vger.kernel.org/lpc_net2018_talks/lpc18_pres_af_xdp_perf-v3.pdf - http://vger.kernel.org/lpc_net2018_talks/lpc18_paper_af_xdp_perf-v2.pdf Signed-off-by: Daniel Borkmann Signed-off-by: Thomas Gleixner Acked-by: Jesper Dangaard Brouer Acked-by: Björn Töpel Acked-by: Linus Torvalds Cc: netdev@vger.kernel.org Cc: David S. Miller Cc: Magnus Karlsson Cc: Alexei Starovoitov Cc: Peter Zijlstra Cc: David Woodhouse Cc: Andy Lutomirski Cc: Borislav Petkov Link: https://lkml.kernel.org/r/20190221221941.29358-1-daniel@iogearbox.net

x86/fpu: Get rid of CONFIG_AS_FXSAVEQ

2019-01-22T13:16:39+00:00

This was a "workaround" to probe for binutils which could generate FXSAVEQ, apparently gas with min version 2.16. In the meantime, minimal required gas version is 2.20 so all those workarounds for older binutils can be dropped. Signed-off-by: Borislav Petkov Acked-by: Sebastian Andrzej Siewior Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Andy Lutomirski Link: https://lkml.kernel.org/r/20190117232408.GH5023@zn.tnic

jump_label: move 'asm goto' support test to Kconfig

2019-01-06T00:46:51+00:00

Currently, CONFIG_JUMP_LABEL just means "I _want_ to use jump label". The jump label is controlled by HAVE_JUMP_LABEL, which is defined like this: #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) # define HAVE_JUMP_LABEL #endif We can improve this by testing 'asm goto' support in Kconfig, then make JUMP_LABEL depend on CC_HAS_ASM_GOTO. Ugly #ifdef HAVE_JUMP_LABEL will go away, and CONFIG_JUMP_LABEL will match to the real kernel capability. Signed-off-by: Masahiro Yamada Acked-by: Michael Ellerman (powerpc) Tested-by: Sedat Dilek

Merge branch 'x86-build-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2018-12-27T00:57:27+00:00

Pull x86 build updates from Ingo Molnar: - Resolve LLVM build bug by removing redundant GNU specific flag - Remove obsolete -funit-at-a-time and -fno-unit-at-a-time use from x86 PowerPC and UM. The UML change was seen and acked by UML maintainer Richard Weinberger. * 'x86-build-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/um/vdso: Drop implicit common-page-size linker flag x86, powerpc: Remove -funit-at-a-time compiler option entirely x86/um: Remove -fno-unit-at-a-time workaround for pre-4.0 GCC

Revert "kbuild/Makefile: Prepare for using macros in inline assembly code to work around asm() related GCC inlining bugs"

2018-12-19T11:00:28+00:00

This reverts commit 77b0bf55bc675233d22cd5df97605d516d64525e. See this commit for details about the revert: e769742d3584 ("Revert "x86/jump-labels: Macrofy inline assembly code to work around GCC inlining bugs"") Conflicts: arch/x86/Makefile Reported-by: Masahiro Yamada Reviewed-by: Borislav Petkov Reviewed-by: Thomas Gleixner Cc: Juergen Gross Cc: Richard Biener Cc: Kees Cook Cc: Segher Boessenkool Cc: Ard Biesheuvel Cc: Peter Zijlstra Cc: Josh Poimboeuf Cc: Nadav Amit Cc: Linus Torvalds Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar

x86, powerpc: Remove -funit-at-a-time compiler option entirely

2018-12-09T10:55:32+00:00

GCC 4.6 manual says: -funit-at-a-time This option is left for compatibility reasons. -funit-at-a-time has no effect, while -fno-unit-at-a-time implies -fno-toplevel-reorder and -fno-section-anchors. Enabled by default. Remove it. Signed-off-by: Masahiro Yamada Signed-off-by: Borislav Petkov Acked-by: Ingo Molnar Acked-by: Michael Ellerman Cc: "H. Peter Anvin" Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Richard Weinberger Cc: Thomas Gleixner Cc: linuxppc-dev@lists.ozlabs.org Cc: x86-ml Link: https://lkml.kernel.org/r/1541990120-9643-3-git-send-email-yamada.masahiro@socionext.com