search for: _asm_ptr

This series reverts the in-kernel workarounds for inlining issues. The commit description of 77b0bf55bc67 mentioned "We also hope that GCC will eventually get fixed,..." Now, GCC provides a solution. https://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html explains the new "asm inline" syntax. The performance issue will be eventually solved. [About Code cleanups] I know Nadam

This series reverts the in-kernel workarounds for inlining issues. The commit description of 77b0bf55bc67 mentioned "We also hope that GCC will eventually get fixed,..." Now, GCC provides a solution. https://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html explains the new "asm inline" syntax. The performance issue will be eventually solved. [About Code cleanups] I know Nadam

...EATURES_STR .ascii "!writable_page_tables" \ + "|pae_pgdir_above_4gb" \ + "\0" #endif __INIT @@ -104,7 +109,7 @@ NEXT_HYPERCALL(arch_6) #endif ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, _ASM_PTR startup_xen) ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page) - ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .asciz "!writable_page_tables|pae_pgdir_above_4gb"FEATURES_PVH) + ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, XEN_FEATURES_STR) ELFNOTE(Xen, XEN_ELFNOTE_PAE_MO...

..._\@: + .if \def + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .else + .byte STATIC_KEY_INIT_NOP + .endif .pushsection __jump_table, "aw" _ASM_ALIGN - .long .Lstatic_branch_nop_\@ - ., \l_yes - . - _ASM_PTR \key + \branch - . + .long .Lstatic_jump_\@ - ., \target - . + _ASM_PTR \key - . .popsection .endm -.macro STATIC_BRANCH_JMP l_yes:req key:req branch:req -.Lstatic_branch_jmp_\@: - .byte 0xe9 - .long \l_yes - .Lstatic_branch_jmp_after_\@ -.Lstatic_branch_jmp_after_\@: +.macro STATIC_JU...

...t; #from " to=" #to \ - " handler=\"" #handler "\"\n\t" - -/* For C file, we already have NOKPROBE_SYMBOL macro */ - -#endif /* __ASSEMBLY__ */ # define _ASM_EXTABLE(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) @@ -161,7 +148,6 @@ _ASM_PTR (entry); \ .popsection -#ifdef __ASSEMBLY__ .macro ALIGN_DESTINATION /* check for bad alignment of destination */ movl %edi,%ecx @@ -185,7 +171,34 @@ _ASM_EXTABLE_UA(100b, 103b) _ASM_EXTABLE_UA(101b, 103b) .endm -#endif /* __ASSEMBLY__ */ + +#else +# define _EXPAND_EXTABLE_HANDLE...

...t; #from " to=" #to \ - " handler=\"" #handler "\"\n\t" - -/* For C file, we already have NOKPROBE_SYMBOL macro */ - -#endif /* __ASSEMBLY__ */ # define _ASM_EXTABLE(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) @@ -161,7 +148,6 @@ _ASM_PTR (entry); \ .popsection -#ifdef __ASSEMBLY__ .macro ALIGN_DESTINATION /* check for bad alignment of destination */ movl %edi,%ecx @@ -185,7 +171,34 @@ _ASM_EXTABLE_UA(100b, 103b) _ASM_EXTABLE_UA(101b, 103b) .endm -#endif /* __ASSEMBLY__ */ + +#else +# define _EXPAND_EXTABLE_HANDLE...

...bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" ".long 1b - ., %l[l_yes] - . \n\t" _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } The error pointed to asm_volatile_goto("1:" I'm not sure whether this error is related to asm goto support.

...able_descriptor_tables|auto_translated_physmap|supervisor_mode_kernel|hvm_callback_vector" + #else -#define FEATURES_PVH /* Not supported */ +#define PVH_FEATURES_STR "" #endif __INIT @@ -104,7 +103,7 @@ NEXT_HYPERCALL(arch_6) #endif ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, _ASM_PTR startup_xen) ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page) - ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .asciz "!writable_page_tables|pae_pgdir_above_4gb"FEATURES_PVH) + ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .ascii "!writable_page_tables|pae_pgdir_above_...

...patchable by the + * apply_paravirt() alternate instruction patcher. + */ +#define _paravirt_alt(insn_string, type, clobber) \ + "771:\n\t" insn_string "\n" "772:\n" \ + ".pushsection .parainstructions,\"a\"\n" \ + _ASM_ALIGN "\n" \ + _ASM_PTR " 771b\n" \ + " .byte " type "\n" \ + " .byte 772b-771b\n" \ + " .short " clobber "\n" \ + ".popsection\n" + /* Generate patchable code, with the default asm parameters. */ -#define paravirt_call \ - "PA...

...patchable by the - * apply_paravirt() alternate instruction patcher. - */ -#define _paravirt_alt(insn_string, type, clobber) \ - "771:\n\t" insn_string "\n" "772:\n" \ - ".pushsection .parainstructions,\"a\"\n" \ - _ASM_ALIGN "\n" \ - _ASM_PTR " 771b\n" \ - " .byte " type "\n" \ - " .byte 772b-771b\n" \ - " .short " clobber "\n" \ - ".popsection\n" - -/* Generate patchable code, with the default asm parameters. */ -#define paravirt_alt(insn_string) \...

...t; #from " to=" #to \ - " handler=\"" #handler "\"\n\t" - -/* For C file, we already have NOKPROBE_SYMBOL macro */ - -#endif /* __ASSEMBLY__ */ # define _ASM_EXTABLE(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) @@ -161,7 +148,6 @@ _ASM_PTR (entry); \ .popsection -#ifdef __ASSEMBLY__ .macro ALIGN_DESTINATION /* check for bad alignment of destination */ movl %edi,%ecx @@ -185,7 +171,34 @@ _ASM_EXTABLE_UA(100b, 103b) _ASM_EXTABLE_UA(101b, 103b) .endm -#endif /* __ASSEMBLY__ */ + +#else +# define _EXPAND_EXTABLE_HANDLE...

...e:req clobber:req pv_opptr:req Unlike the marcro maze you replaced, this has the CALL hardcoded in. So maybe name this PARAVIRT_CALL instead of PARAVIRT_ALT ? > +771: ANNOTATE_RETPOLINE_SAFE > + call *\pv_opptr > +772: .pushsection .parainstructions,"a" > + _ASM_ALIGN > + _ASM_PTR 771b > + .byte \type > + .byte 772b-771b > + .short \clobber > + .popsection > +.endm

...@@ -21,6 +21,16 @@ .short clobbers; \ .popsection +#define PV_ALT_SITE(oldinstr, newinstr, ops, off, clobbers) \ + __ALTERNATIVE(.pv_altinstructions, oldinstr, newinstr, \ + X86_FEATURE_PV_OPS); \ + .pushsection .parainstructions, "a"; \ + _ASM_ALIGN; \ + _ASM_PTR 140b; \ + .byte PV_TYPE(ops, off); \ + .byte 142b-140b; \ + .short clobbers; \ + .popsection #define COND_PUSH(set, mask, reg) \ .if ((~(set)) & mask); push %reg; .endif diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 5...

...772b-771b; \ - .short clobbers; \ +#define PV_TYPE(ops, off) ((PARAVIRT_PATCH_##ops + (off)) / __ASM_SEL(4, 8)) + +#define PV_SITE(insns, ops, off, clobbers) \ +771:; \ + insns; \ +772:; \ + .pushsection .parainstructions, "a"; \ + _ASM_ALIGN; \ + _ASM_PTR 771b; \ + .byte PV_TYPE(ops, off); \ + .byte 772b-771b; \ + .short clobbers; \ .popsection @@ -33,62 +35,65 @@ COND_PUSH(set, CLBR_RDX, rdx); \ COND_PUSH(set, CLBR_RSI, rsi); \ COND_PUSH(set, CLBR_RDI, rdi); \ - COND_PUSH(set, CLBR_R8, r8); \ - COND_PUSH(set,...

This changes the pv ops code generation to more closely match reality. For example, instead of: callq *0xffffffff81e3a400 (pv_irq_ops.save_fl) vmlinux will now show: pushfq pop %rax nop nop nop nop nop which is what the runtime version of the code will show in most cases. This idea was suggested by Andy Lutomirski. The benefits are: - For the most common runtime cases

This changes the pv ops code generation to more closely match reality. For example, instead of: callq *0xffffffff81e3a400 (pv_irq_ops.save_fl) vmlinux will now show: pushfq pop %rax nop nop nop nop nop which is what the runtime version of the code will show in most cases. This idea was suggested by Andy Lutomirski. The benefits are: - For the most common runtime cases

Changes: - patch v2: - Adapt patch to work post KPTI and compiler changes - Redo all performance testing with latest configs and compilers - Simplify mov macro on PIE (MOVABS now) - Reduce GOT footprint - patch v1: - Simplify ftrace implementation. - Use gcc mstack-protector-guard-reg=%gs with PIE when possible. - rfc v3: - Use --emit-relocs instead of -pie to reduce

Changes: - patch v2: - Adapt patch to work post KPTI and compiler changes - Redo all performance testing with latest configs and compilers - Simplify mov macro on PIE (MOVABS now) - Reduce GOT footprint - patch v1: - Simplify ftrace implementation. - Use gcc mstack-protector-guard-reg=%gs with PIE when possible. - rfc v3: - Use --emit-relocs instead of -pie to reduce

These patches make the changes necessary to build the kernel as Position Independent Executable (PIE) on x86_64. A PIE kernel can be relocated below the top 2G of the virtual address space. It allows to optionally extend the KASLR randomization range from 1G to 3G. Thanks a lot to Ard Biesheuvel & Kees Cook on their feedback on compiler changes, PIE support and KASLR in general. Thanks to

These patches make the changes necessary to build the kernel as Position Independent Executable (PIE) on x86_64. A PIE kernel can be relocated below the top 2G of the virtual address space. It allows to optionally extend the KASLR randomization range from 1G to 3G. Thanks a lot to Ard Biesheuvel & Kees Cook on their feedback on compiler changes, PIE support and KASLR in general. Thanks to