diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-10-23 13:08:53 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-10-23 13:08:53 +0100 |
| commit | 0200fbdd431519d730b5d399a12840ec832b27cc (patch) | |
| tree | 2b58f9e24b61b00e0550f106c95bfabc3b52cfdd | |
| parent | de3fbb2aa802a267dee2213ae7d5a1e19eb4294a (diff) | |
| parent | 01a14bda11add9dcd4a59200f13834d634559935 (diff) | |
| download | linux-0200fbdd431519d730b5d399a12840ec832b27cc.tar.gz linux-0200fbdd431519d730b5d399a12840ec832b27cc.tar.bz2 linux-0200fbdd431519d730b5d399a12840ec832b27cc.zip | |
Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking and misc x86 updates from Ingo Molnar:
"Lots of changes in this cycle - in part because locking/core attracted
a number of related x86 low level work which was easier to handle in a
single tree:
- Linux Kernel Memory Consistency Model updates (Alan Stern, Paul E.
McKenney, Andrea Parri)
- lockdep scalability improvements and micro-optimizations (Waiman
Long)
- rwsem improvements (Waiman Long)
- spinlock micro-optimization (Matthew Wilcox)
- qspinlocks: Provide a liveness guarantee (more fairness) on x86.
(Peter Zijlstra)
- Add support for relative references in jump tables on arm64, x86
and s390 to optimize jump labels (Ard Biesheuvel, Heiko Carstens)
- Be a lot less permissive on weird (kernel address) uaccess faults
on x86: BUG() when uaccess helpers fault on kernel addresses (Jann
Horn)
- macrofy x86 asm statements to un-confuse the GCC inliner. (Nadav
Amit)
- ... and a handful of other smaller changes as well"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
locking/lockdep: Make global debug_locks* variables read-mostly
locking/lockdep: Fix debug_locks off performance problem
locking/pvqspinlock: Extend node size when pvqspinlock is configured
locking/qspinlock_stat: Count instances of nested lock slowpaths
locking/qspinlock, x86: Provide liveness guarantee
x86/asm: 'Simplify' GEN_*_RMWcc() macros
locking/qspinlock: Rework some comments
locking/qspinlock: Re-order code
locking/lockdep: Remove duplicated 'lock_class_ops' percpu array
x86/defconfig: Enable CONFIG_USB_XHCI_HCD=y
futex: Replace spin_is_locked() with lockdep
locking/lockdep: Make class->ops a percpu counter and move it under CONFIG_DEBUG_LOCKDEP=y
x86/jump-labels: Macrofy inline assembly code to work around GCC inlining bugs
x86/cpufeature: Macrofy inline assembly code to work around GCC inlining bugs
x86/extable: Macrofy inline assembly code to work around GCC inlining bugs
x86/paravirt: Work around GCC inlining bugs when compiling paravirt ops
x86/bug: Macrofy the BUG table section handling, to work around GCC inlining bugs
x86/alternatives: Macrofy lock prefixes to work around GCC inlining bugs
x86/refcount: Work around GCC inlining bug
x86/objtool: Use asm macros to work around GCC inlining bugs
...
95 files changed, 1522 insertions, 934 deletions
diff --git a/Documentation/locking/lockstat.txt b/Documentation/locking/lockstat.txt index 5786ad2cd5e6..fdbeb0c45ef3 100644 --- a/Documentation/locking/lockstat.txt +++ b/Documentation/locking/lockstat.txt @@ -91,7 +91,7 @@ Look at the current lock statistics: 07 &mm->mmap_sem-R: 37 100 1.31 299502.61 325629.52 3256.30 212344 34316685 0.10 7744.91 95016910.20 2.77 08 --------------- 09 &mm->mmap_sem 1 [<ffffffff811502a7>] khugepaged_scan_mm_slot+0x57/0x280 -19 &mm->mmap_sem 96 [<ffffffff815351c4>] __do_page_fault+0x1d4/0x510 +10 &mm->mmap_sem 96 [<ffffffff815351c4>] __do_page_fault+0x1d4/0x510 11 &mm->mmap_sem 34 [<ffffffff81113d77>] vm_mmap_pgoff+0x87/0xd0 12 &mm->mmap_sem 17 [<ffffffff81127e71>] vm_munmap+0x41/0x80 13 --------------- diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 0d8d7ef131e9..c1d913944ad8 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -471,8 +471,7 @@ And a couple of implicit varieties: operations after the ACQUIRE operation will appear to happen after the ACQUIRE operation with respect to the other components of the system. ACQUIRE operations include LOCK operations and both smp_load_acquire() - and smp_cond_acquire() operations. The later builds the necessary ACQUIRE - semantics from relying on a control dependency and smp_rmb(). + and smp_cond_load_acquire() operations. Memory operations that occur before an ACQUIRE operation may appear to happen after it completes. @@ -1073,7 +1073,7 @@ scripts: scripts_basic asm-generic gcc-plugins $(autoksyms_h) # version.h and scripts_basic is processed / created. # Listed in dependency order -PHONY += prepare archprepare prepare0 prepare1 prepare2 prepare3 +PHONY += prepare archprepare macroprepare prepare0 prepare1 prepare2 prepare3 # prepare3 is used to check if we are building in a separate output directory, # and if so do: @@ -1096,7 +1096,9 @@ prepare2: prepare3 outputmakefile asm-generic prepare1: prepare2 $(version_h) $(autoksyms_h) include/generated/utsrelease.h $(cmd_crmodverdir) -archprepare: archheaders archscripts prepare1 scripts_basic +macroprepare: prepare1 archmacros + +archprepare: archheaders archscripts macroprepare scripts_basic prepare0: archprepare gcc-plugins $(Q)$(MAKE) $(build)=. @@ -1164,6 +1166,9 @@ archheaders: PHONY += archscripts archscripts: +PHONY += archmacros +archmacros: + PHONY += __headers __headers: $(version_h) scripts_basic uapi-asm-generic archheaders archscripts $(Q)$(MAKE) $(build)=scripts build_unifdef diff --git a/arch/Kconfig b/arch/Kconfig index 6801123932a5..9d329608913e 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -359,6 +359,9 @@ config HAVE_PERF_USER_STACK_DUMP config HAVE_ARCH_JUMP_LABEL bool +config HAVE_ARCH_JUMP_LABEL_RELATIVE + bool + config HAVE_RCU_TABLE_FREE bool diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a8ae30fab508..c03cd0d765d3 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -105,6 +105,7 @@ config ARM64 select HAVE_ARCH_BITREVERSE select HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48) select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 7e2b3e360086..472023498d71 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -26,13 +26,16 @@ #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE -static __always_inline bool arch_static_branch(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch(struct static_key *key, + bool branch) { - asm_volatile_goto("1: nop\n\t" - ".pushsection __jump_table, \"aw\"\n\t" - ".align 3\n\t" - ".quad 1b, %l[l_yes], %c0\n\t" - ".popsection\n\t" + asm_volatile_goto( + "1: nop \n\t" + " .pushsection __jump_table, \"aw\" \n\t" + " .align 3 \n\t" + " .long 1b - ., %l[l_yes] - . \n\t" + " .quad %c0 - . \n\t" + " .popsection \n\t" : : "i"(&((char *)key)[branch]) : : l_yes); return false; @@ -40,13 +43,16 @@ l_yes: return true; } -static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch_jump(struct static_key *key, + bool branch) { - asm_volatile_goto("1: b %l[l_yes]\n\t" - ".pushsection __jump_table, \"aw\"\n\t" - ".align 3\n\t" - ".quad 1b, %l[l_yes], %c0\n\t" - ".popsection\n\t" + asm_volatile_goto( + "1: b %l[l_yes] \n\t" + " .pushsection __jump_table, \"aw\" \n\t" + " .align 3 \n\t" + " .long 1b - ., %l[l_yes] - . \n\t" + " .quad %c0 - . \n\t" + " .popsection \n\t" : : "i"(&((char *)key)[branch]) : : l_yes); return false; @@ -54,13 +60,5 @@ l_yes: return true; } -typedef u64 jump_label_t; - -struct jump_entry { - jump_label_t code; - jump_label_t target; - jump_label_t key; -}; - #endif /* __ASSEMBLY__ */ #endif /* __ASM_JUMP_LABEL_H */ diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c index e0756416e567..646b9562ee64 100644 --- a/arch/arm64/kernel/jump_label.c +++ b/arch/arm64/kernel/jump_label.c @@ -25,12 +25,12 @@ void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { - void *addr = (void *)entry->code; + void *addr = (void *)jump_entry_code(entry); u32 insn; if (type == JUMP_LABEL_JMP) { - insn = aarch64_insn_gen_branch_imm(entry->code, - entry->target, + insn = aarch64_insn_gen_branch_imm(jump_entry_code(entry), + jump_entry_target(entry), AARCH64_INSN_BRANCH_NOLINK); } else { insn = aarch64_insn_gen_nop(); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index cc8313550493..039a3417dfc4 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -126,6 +126,7 @@ config S390 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES select HAVE_ARCH_SECCOMP_FILTER diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 40f651292aa7..e2d3e6c43395 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -14,41 +14,33 @@ * We use a brcl 0,2 instruction for jump labels at compil |