From 9183c3f9ed710a8edf1a61e8a96d497258d26e08 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 18 Aug 2020 15:57:42 +0200 Subject: static_call: Add inline static call infrastructure Add infrastructure for an arch-specific CONFIG_HAVE_STATIC_CALL_INLINE option, which is a faster version of CONFIG_HAVE_STATIC_CALL. At runtime, the static call sites are patched directly, rather than using the out-of-line trampolines. Compared to out-of-line static calls, the performance benefits are more modest, but still measurable. Steven Rostedt did some tracepoint measurements: https://lkml.kernel.org/r/20181126155405.72b4f718@gandalf.local.home This code is heavily inspired by the jump label code (aka "static jumps"), as some of the concepts are very similar. For more details, see the comments in include/linux/static_call.h. [peterz: simplified interface; merged trampolines] Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Steven Rostedt (VMware) Cc: Linus Torvalds Link: https://lore.kernel.org/r/20200818135804.684334440@infradead.org --- include/linux/module.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/module.h') diff --git a/include/linux/module.h b/include/linux/module.h index e30ed5fa33a7..a29187f7c360 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -498,6 +499,10 @@ struct module { unsigned long *kprobe_blacklist; unsigned int num_kprobe_blacklist; #endif +#ifdef CONFIG_HAVE_STATIC_CALL_INLINE + int num_static_call_sites; + struct static_call_site *static_call_sites; +#endif #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ -- cgit v1.2.3 From 33def8498fdde180023444b08e12b72a9efed41d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 21 Oct 2020 19:36:07 -0700 Subject: treewide: Convert macro and uses of __section(foo) to __section("foo") Use a more generic form for __section that requires quotes to avoid complications with clang and gcc differences. Remove the quote operator # from compiler_attributes.h __section macro. Convert all unquoted __section(foo) uses to quoted __section("foo"). Also convert __attribute__((section("foo"))) uses to __section("foo") even if the __attribute__ has multiple list entry forms. Conversion done using the script at: https://lore.kernel.org/lkml/75393e5ddc272dc7403de74d645e6c6e0f4e70eb.camel@perches.com/2-convert_section.pl Signed-off-by: Joe Perches Reviewed-by: Nick Desaulniers Reviewed-by: Miguel Ojeda Signed-off-by: Linus Torvalds --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/module.h') diff --git a/include/linux/module.h b/include/linux/module.h index a29187f7c360..7ccdf87f376f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -278,7 +278,7 @@ extern typeof(name) __mod_##type##__##name##_device_table \ .version = _version, \ }; \ static const struct module_version_attribute \ - __used __attribute__ ((__section__ ("__modver"))) \ + __used __section("__modver") \ * __moduleparam_const __modver_attr = &___modver_attr #endif -- cgit v1.2.3 From 13150bc5416f45234c955e5bed91623d178c6117 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 27 Oct 2020 16:11:32 +0100 Subject: module: use hidden visibility for weak symbol references Geert reports that commit be2881824ae9eb92 ("arm64/build: Assert for unwanted sections") results in build errors on arm64 for configurations that have CONFIG_MODULES disabled. The commit in question added ASSERT()s to the arm64 linker script to ensure that linker generated sections such as .got.plt etc are empty, but as it turns out, there are corner cases where the linker does emit content into those sections. More specifically, weak references to function symbols (which can remain unsatisfied, and can therefore not be emitted as relative references) will be emitted as GOT and PLT entries when linking the kernel in PIE mode (which is the case when CONFIG_RELOCATABLE is enabled, which is on by default). What happens is that code such as struct device *(*fn)(struct device *dev); struct device *iommu_device; fn = symbol_get(mdev_get_iommu_device); if (fn) { iommu_device = fn(dev); essentially gets converted into the following when CONFIG_MODULES is off: struct device *iommu_device; if (&mdev_get_iommu_device) { iommu_device = mdev_get_iommu_device(dev); where mdev_get_iommu_device is emitted as a weak symbol reference into the object file. The first reference is decorated with an ordinary ABS64 data relocation (which yields 0x0 if the reference remains unsatisfied). However, the indirect call is turned into a direct call covered by a R_AARCH64_CALL26 relocation, which is converted into a call via a PLT entry taking the target address from the associated GOT entry. Given that such GOT and PLT entries are unnecessary for fully linked binaries such as the kernel, let's give these weak symbol references hidden visibility, so that the linker knows that the weak reference via R_AARCH64_CALL26 can simply remain unsatisfied. Signed-off-by: Ard Biesheuvel Tested-by: Geert Uytterhoeven Reviewed-by: Fangrui Song Acked-by: Jessica Yu Cc: Jessica Yu Cc: Kees Cook Cc: Geert Uytterhoeven Cc: Nick Desaulniers Link: https://lore.kernel.org/r/20201027151132.14066-1-ardb@kernel.org Signed-off-by: Will Deacon --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/module.h') diff --git a/include/linux/module.h b/include/linux/module.h index 7ccdf87f376f..6264617bab4d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -740,7 +740,7 @@ static inline bool within_module(unsigned long addr, const struct module *mod) } /* Get/put a kernel symbol (calls should be symmetric) */ -#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak)); &(x); }) +#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); }) #define symbol_put(x) do { } while (0) #define symbol_put_addr(x) do { } while (0) -- cgit v1.2.3