[PATCH v7 00/14] x86: major paravirt cleanup

[PATCH v7 00/14] x86: major paravirt cleanup

[Juergen Gross]

This is a major cleanup of the paravirt infrastructure aiming at
eliminating all custom code patching via paravirt patching.

This is achieved by using ALTERNATIVE instead, leading to the ability
to give objtool access to the patched in instructions.

In order to remove most of the 32-bit special handling from pvops the
time related operations are switched to use static_call() instead.

At the end of this series all paravirt patching has to do is to
replace indirect calls with direct ones. In a further step this could
be switched to static_call(), too.

Changes in V7:
- dropped patch 3, as already applied on tip tree
- new patch 3 (patches 1 and 7 have been added to V6 late)
- addressed comments by Boris

Changes in V6:
- switched back to "not" bit in feature value for "not feature"
- other minor comments addressed

Changes in V5:
- patches 1-5 of V4 dropped, as already applied
- new patches 1+3
- fixed patch 2
- split V4 patch 8 into patches 4+5
- use flag byte instead of negative feature bit for "not feature"

Changes in V4:
- fixed several build failures
- removed objtool patch, as objtool patches are in tip now
- added patch 1 for making usage of static_call easier
- even more cleanup

Changes in V3:
- added patches 7 and 12
- addressed all comments

Changes in V2:
- added patches 5-12

Juergen Gross (14):
  x86/alternative: merge include files
  static_call: move struct static_call_key definition to
    static_call_types.h
  static_call: add function to query current function
  x86/paravirt: switch time pvops functions to use static_call()
  x86/alternative: support not-feature
  x86/alternative: support ALTERNATIVE_TERNARY
  x86/alternative: don't open code ALTERNATIVE_TERNARY() in
    _static_cpu_has()
  x86: add new features for paravirt patching
  x86/paravirt: remove no longer needed 32-bit pvops cruft
  x86/paravirt: simplify paravirt macros
  x86/paravirt: switch iret pvops to ALTERNATIVE
  x86/paravirt: add new macros PVOP_ALT* supporting pvops in
    ALTERNATIVEs
  x86/paravirt: switch functions with custom code to ALTERNATIVE
  x86/paravirt: have only one paravirt patch function

 arch/arm/include/asm/paravirt.h          |  14 +-
 arch/arm/kernel/paravirt.c               |   9 +-
 arch/arm64/include/asm/paravirt.h        |  14 +-
 arch/arm64/kernel/paravirt.c             |  13 +-
 arch/x86/Kconfig                         |   1 +
 arch/x86/entry/entry_32.S                |   6 +-
 arch/x86/entry/entry_64.S                |   2 +-
 arch/x86/entry/vdso/vdso32/system_call.S |   2 +-
 arch/x86/include/asm/alternative-asm.h   | 114 ------------
 arch/x86/include/asm/alternative.h       | 126 +++++++++++++-
 arch/x86/include/asm/cpufeature.h        |  41 +----
 arch/x86/include/asm/cpufeatures.h       |   2 +
 arch/x86/include/asm/irqflags.h          |   7 +-
 arch/x86/include/asm/mshyperv.h          |   2 +-
 arch/x86/include/asm/nospec-branch.h     |   1 -
 arch/x86/include/asm/paravirt.h          | 167 ++++++++----------
 arch/x86/include/asm/paravirt_types.h    | 210 +++++++++--------------
 arch/x86/include/asm/smap.h              |   5 +-
 arch/x86/kernel/Makefile                 |   3 +-
 arch/x86/kernel/alternative.c            |  52 +++++-
 arch/x86/kernel/asm-offsets.c            |   7 -
 arch/x86/kernel/cpu/vmware.c             |   5 +-
 arch/x86/kernel/kvm.c                    |   2 +-
 arch/x86/kernel/kvmclock.c               |   2 +-
 arch/x86/kernel/paravirt-spinlocks.c     |   9 +
 arch/x86/kernel/paravirt.c               |  75 ++------
 arch/x86/kernel/paravirt_patch.c         |  99 -----------
 arch/x86/kernel/tsc.c                    |   3 +-
 arch/x86/lib/atomic64_386_32.S           |   2 +-
 arch/x86/lib/atomic64_cx8_32.S           |   2 +-
 arch/x86/lib/copy_page_64.S              |   2 +-
 arch/x86/lib/copy_user_64.S              |   2 +-
 arch/x86/lib/memcpy_64.S                 |   2 +-
 arch/x86/lib/memmove_64.S                |   2 +-
 arch/x86/lib/memset_64.S                 |   2 +-
 arch/x86/lib/retpoline.S                 |   2 +-
 arch/x86/xen/enlighten_pv.c              |   4 +-
 arch/x86/xen/time.c                      |  26 +--
 drivers/xen/time.c                       |   3 +-
 include/linux/static_call.h              |  26 +--
 include/linux/static_call_types.h        |  18 ++
 tools/include/linux/static_call_types.h  |  18 ++
 42 files changed, 473 insertions(+), 631 deletions(-)
 delete mode 100644 arch/x86/include/asm/alternative-asm.h
 delete mode 100644 arch/x86/kernel/paravirt_patch.c

-- 
2.26.2

[PATCH v7 01/14] x86/alternative: merge include files

[Juergen Gross]

Merge arch/x86/include/asm/alternative-asm.h into
arch/x86/include/asm/alternative.h in order to make it easier to use
common definitions later.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V6:
- new patch
V7:
- moved to begin of series (Boris Petkov)
---
 arch/x86/entry/entry_32.S                |   2 +-
 arch/x86/entry/vdso/vdso32/system_call.S |   2 +-
 arch/x86/include/asm/alternative-asm.h   | 114 -----------------------
 arch/x86/include/asm/alternative.h       | 112 +++++++++++++++++++++-
 arch/x86/include/asm/nospec-branch.h     |   1 -
 arch/x86/include/asm/smap.h              |   5 +-
 arch/x86/lib/atomic64_386_32.S           |   2 +-
 arch/x86/lib/atomic64_cx8_32.S           |   2 +-
 arch/x86/lib/copy_page_64.S              |   2 +-
 arch/x86/lib/copy_user_64.S              |   2 +-
 arch/x86/lib/memcpy_64.S                 |   2 +-
 arch/x86/lib/memmove_64.S                |   2 +-
 arch/x86/lib/memset_64.S                 |   2 +-
 arch/x86/lib/retpoline.S                 |   2 +-
 14 files changed, 120 insertions(+), 132 deletions(-)
 delete mode 100644 arch/x86/include/asm/alternative-asm.h

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index df8c017e6161..4e079f250962 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -40,7 +40,7 @@
 #include <asm/processor-flags.h>
 #include <asm/irq_vectors.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/frame.h>
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index de1fff7188aa..d6a6080bade0 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -6,7 +6,7 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 	.text
 	.globl __kernel_vsyscall
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
deleted file mode 100644
index 464034db299f..000000000000
--- a/arch/x86/include/asm/alternative-asm.h
+++ /dev/null
@@ -1,114 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_ALTERNATIVE_ASM_H
-#define _ASM_X86_ALTERNATIVE_ASM_H
-
-#ifdef __ASSEMBLY__
-
-#include <asm/asm.h>
-
-#ifdef CONFIG_SMP
-	.macro LOCK_PREFIX
-672:	lock
-	.pushsection .smp_locks,"a"
-	.balign 4
-	.long 672b - .
-	.popsection
-	.endm
-#else
-	.macro LOCK_PREFIX
-	.endm
-#endif
-
-/*
- * objtool annotation to ignore the alternatives and only consider the original
- * instruction(s).
- */
-.macro ANNOTATE_IGNORE_ALTERNATIVE
-	.Lannotate_\@:
-	.pushsection .discard.ignore_alts
-	.long .Lannotate_\@ - .
-	.popsection
-.endm
-
-/*
- * Issue one struct alt_instr descriptor entry (need to put it into
- * the section .altinstructions, see below). This entry contains
- * enough information for the alternatives patching code to patch an
- * instruction. See apply_alternatives().
- */
-.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
-	.long \orig - .
-	.long \alt - .
-	.word \feature
-	.byte \orig_len
-	.byte \alt_len
-	.byte \pad_len
-.endm
-
-/*
- * Define an alternative between two instructions. If @feature is
- * present, early code in apply_alternatives() replaces @oldinstr with
- * @newinstr. ".skip" directive takes care of proper instruction padding
- * in case @newinstr is longer than @oldinstr.
- */
-.macro ALTERNATIVE oldinstr, newinstr, feature
-140:
-	\oldinstr
-141:
-	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
-	.popsection
-
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr
-144:
-	.popsection
-.endm
-
-#define old_len			141b-140b
-#define new_len1		144f-143f
-#define new_len2		145f-144f
-
-/*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
-
-
-/*
- * Same as ALTERNATIVE macro above but for two alternatives. If CPU
- * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
- * @feature2, it replaces @oldinstr with @feature2.
- */
-.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
-140:
-	\oldinstr
-141:
-	.skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
-		(alt_max_short(new_len1, new_len2) - (old_len)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
-	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
-	.popsection
-
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr1
-144:
-	\newinstr2
-145:
-	.popsection
-.endm
-
-#endif  /*  __ASSEMBLY__  */
-
-#endif /* _ASM_X86_ALTERNATIVE_ASM_H */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 5753fb2ac489..53f295f41c34 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -2,13 +2,14 @@
 #ifndef _ASM_X86_ALTERNATIVE_H
 #define _ASM_X86_ALTERNATIVE_H
 
-#ifndef __ASSEMBLY__
-
 #include <linux/types.h>
-#include <linux/stddef.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
 
+#ifndef __ASSEMBLY__
+
+#include <linux/stddef.h>
+
 /*
  * Alternative inline assembly for SMP.
  *
@@ -271,6 +272,111 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SMP
+	.macro LOCK_PREFIX
+672:	lock
+	.pushsection .smp_locks,"a"
+	.balign 4
+	.long 672b - .
+	.popsection
+	.endm
+#else
+	.macro LOCK_PREFIX
+	.endm
+#endif
+
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+	.Lannotate_\@:
+	.pushsection .discard.ignore_alts
+	.long .Lannotate_\@ - .
+	.popsection
+.endm
+
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
+.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
+	.long \orig - .
+	.long \alt - .
+	.word \feature
+	.byte \orig_len
+	.byte \alt_len
+	.byte \pad_len
+.endm
+
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
+.macro ALTERNATIVE oldinstr, newinstr, feature
+140:
+	\oldinstr
+141:
+	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr
+144:
+	.popsection
+.endm
+
+#define old_len			141b-140b
+#define new_len1		144f-143f
+#define new_len2		145f-144f
+
+/*
+ * gas compatible max based on the idea from:
+ * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ *
+ * The additional "-" is needed because gas uses a "true" value of -1.
+ */
+#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+140:
+	\oldinstr
+141:
+	.skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
+		(alt_max_short(new_len1, new_len2) - (old_len)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
+	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr1
+144:
+	\newinstr2
+145:
+	.popsection
+.endm
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index cb9ad6b73973..529f8e9380d8 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -7,7 +7,6 @@
 #include <linux/objtool.h>
 
 #include <asm/alternative.h>
-#include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 8b58d6975d5d..ea1d8eb644cb 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -11,6 +11,7 @@
 
 #include <asm/nops.h>
 #include <asm/cpufeatures.h>
+#include <asm/alternative.h>
 
 /* "Raw" instruction opcodes */
 #define __ASM_CLAC	".byte 0x0f,0x01,0xca"
@@ -18,8 +19,6 @@
 
 #ifdef __ASSEMBLY__
 
-#include <asm/alternative-asm.h>
-
 #ifdef CONFIG_X86_SMAP
 
 #define ASM_CLAC \
@@ -37,8 +36,6 @@
 
 #else /* __ASSEMBLY__ */
 
-#include <asm/alternative.h>
-
 #ifdef CONFIG_X86_SMAP
 
 static __always_inline void clac(void)
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 3b6544111ac9..16bc9130e7a5 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -6,7 +6,7 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 /* if you want SMP support, implement these with real spinlocks */
 .macro LOCK reg
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 1c5c81c16b06..ce6935690766 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -6,7 +6,7 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 .macro read64 reg
 	movl %ebx, %eax
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 2402d4c489d2..db4b4f9197c7 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -3,7 +3,7 @@
 
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 
 /*
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 77b9b2a3b5c8..57b79c577496 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -11,7 +11,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/export.h>
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 1e299ac73c86..1cc9da6e29c7 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -4,7 +4,7 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 
 .pushsection .noinstr.text, "ax"
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 41902fe8b859..64801010d312 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,7 +8,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 
 #undef memmove
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 0bfd26e4ca9e..9827ae267f96 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -3,7 +3,7 @@
 
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 
 /*
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index f6fb1d218dcc..6bb74b5c238c 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -4,7 +4,7 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
 #include <asm/unwind_hints.h>
-- 
2.26.2

[PATCH v7 02/14] static_call: move struct static_call_key definition to static_call_types.h

[Juergen Gross]

Having the definition of static_call() in static_call_types.h makes
no sense as long struct static_call_key isn't defined there, as the
generic implementation of static_call() is referencing this structure.

So move the definition of struct static_call_key to static_call_types.h.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V5:
- new patch
---
 include/linux/static_call.h             | 18 ------------------
 include/linux/static_call_types.h       | 18 ++++++++++++++++++
 tools/include/linux/static_call_types.h | 18 ++++++++++++++++++
 3 files changed, 36 insertions(+), 18 deletions(-)

diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 85ecc789f4ff..76b881259144 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -128,16 +128,6 @@ struct static_call_mod {
 	struct static_call_site *sites;
 };
 
-struct static_call_key {
-	void *func;
-	union {
-		/* bit 0: 0 = mods, 1 = sites */
-		unsigned long type;
-		struct static_call_mod *mods;
-		struct static_call_site *sites;
-	};
-};
-
 /* For finding the key associated with a trampoline */
 struct static_call_tramp_key {
 	s32 tramp;
@@ -187,10 +177,6 @@ extern long __static_call_return0(void);
 
 static inline int static_call_init(void) { return 0; }
 
-struct static_call_key {
-	void *func;
-};
-
 #define __DEFINE_STATIC_CALL(name, _func, _func_init)			\
 	DECLARE_STATIC_CALL(name, _func);				\
 	struct static_call_key STATIC_CALL_KEY(name) = {		\
@@ -243,10 +229,6 @@ static inline long __static_call_return0(void)
 
 static inline int static_call_init(void) { return 0; }
 
-struct static_call_key {
-	void *func;
-};
-
 static inline long __static_call_return0(void)
 {
 	return 0;
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
index ae5662d368b9..5a00b8b2cf9f 100644
--- a/include/linux/static_call_types.h
+++ b/include/linux/static_call_types.h
@@ -58,11 +58,25 @@ struct static_call_site {
 	__raw_static_call(name);					\
 })
 
+struct static_call_key {
+	void *func;
+	union {
+		/* bit 0: 0 = mods, 1 = sites */
+		unsigned long type;
+		struct static_call_mod *mods;
+		struct static_call_site *sites;
+	};
+};
+
 #else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
 
 #define __STATIC_CALL_ADDRESSABLE(name)
 #define __static_call(name)	__raw_static_call(name)
 
+struct static_call_key {
+	void *func;
+};
+
 #endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
 
 #ifdef MODULE
@@ -77,6 +91,10 @@ struct static_call_site {
 
 #else
 
+struct static_call_key {
+	void *func;
+};
+
 #define static_call(name)						\
 	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
 
diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h
index ae5662d368b9..5a00b8b2cf9f 100644
--- a/tools/include/linux/static_call_types.h
+++ b/tools/include/linux/static_call_types.h
@@ -58,11 +58,25 @@ struct static_call_site {
 	__raw_static_call(name);					\
 })
 
+struct static_call_key {
+	void *func;
+	union {
+		/* bit 0: 0 = mods, 1 = sites */
+		unsigned long type;
+		struct static_call_mod *mods;
+		struct static_call_site *sites;
+	};
+};
+
 #else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
 
 #define __STATIC_CALL_ADDRESSABLE(name)
 #define __static_call(name)	__raw_static_call(name)
 
+struct static_call_key {
+	void *func;
+};
+
 #endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
 
 #ifdef MODULE
@@ -77,6 +91,10 @@ struct static_call_site {
 
 #else
 
+struct static_call_key {
+	void *func;
+};
+
 #define static_call(name)						\
 	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
 
-- 
2.26.2

[PATCH v7 03/14] static_call: add function to query current function

[Juergen Gross]

Some users of paravirtualized functions need to query which function
has been specified in a pv_ops vector element. In order to be able to
switch such paravirtualized functions to static_calls instead, there
needs to be a function to query the function which will be called via
static_call().

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V7:
- new patch
---
 include/linux/static_call.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 76b881259144..e01b61ab86b1 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -20,6 +20,7 @@
  *   static_call(name)(args...);
  *   static_call_cond(name)(args...);
  *   static_call_update(name, func);
+ *   static_call_query(name);
  *
  * Usage example:
  *
@@ -91,6 +92,10 @@
  *
  *   which will include the required value tests to avoid NULL-pointer
  *   dereferences.
+ *
+ *   To query which function is currently set to be called, use:
+ *
+ *   func = static_call_query(name);
  */
 
 #include <linux/types.h>
@@ -118,6 +123,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 			     STATIC_CALL_TRAMP_ADDR(name), func);	\
 })
 
+#define static_call_query(name) (READ_ONCE(STATIC_CALL_KEY(name).func))
+
 #ifdef CONFIG_HAVE_STATIC_CALL_INLINE
 
 extern int __init static_call_init(void);
@@ -191,6 +198,7 @@ static inline int static_call_init(void) { return 0; }
 	};								\
 	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
 
+
 #define static_call_cond(name)	(void)__static_call(name)
 
 static inline
-- 
2.26.2

[PATCH v7 04/14] x86/paravirt: switch time pvops functions to use static_call()

[Juergen Gross]

The time pvops functions are the only ones left which might be
used in 32-bit mode and which return a 64-bit value.

Switch them to use the static_call() mechanism instead of pvops, as
this allows quite some simplification of the pvops implementation.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V4:
- drop paravirt_time.h again
- don't move Hyper-V code (Michael Kelley)
V5:
- drop no longer needed Hyper-V modification (Michael Kelley)
- switch Arm and Arm64 to static_call(), too (kernel test robot)
V6:
- factor out common parts in Xen pv/pvh initialization (Boris Petkov)
V7:
- use new function static_call_query()
---
 arch/arm/include/asm/paravirt.h       | 14 +++++---------
 arch/arm/kernel/paravirt.c            |  9 +++++++--
 arch/arm64/include/asm/paravirt.h     | 14 +++++---------
 arch/arm64/kernel/paravirt.c          | 13 +++++++++----
 arch/x86/Kconfig                      |  1 +
 arch/x86/include/asm/mshyperv.h       |  2 +-
 arch/x86/include/asm/paravirt.h       | 15 ++++++++++++---
 arch/x86/include/asm/paravirt_types.h |  6 ------
 arch/x86/kernel/cpu/vmware.c          |  5 +++--
 arch/x86/kernel/kvm.c                 |  2 +-
 arch/x86/kernel/kvmclock.c            |  2 +-
 arch/x86/kernel/paravirt.c            | 13 +++++++++----
 arch/x86/kernel/tsc.c                 |  3 ++-
 arch/x86/xen/time.c                   | 26 +++++++++++++-------------
 drivers/xen/time.c                    |  3 ++-
 15 files changed, 71 insertions(+), 57 deletions(-)

diff --git a/arch/arm/include/asm/paravirt.h b/arch/arm/include/asm/paravirt.h
index cdbf02d9c1d4..95d5b0d625cd 100644
--- a/arch/arm/include/asm/paravirt.h
+++ b/arch/arm/include/asm/paravirt.h
@@ -3,23 +3,19 @@
 #define _ASM_ARM_PARAVIRT_H
 
 #ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
 struct static_key;
 extern struct static_key paravirt_steal_enabled;
 extern struct static_key paravirt_steal_rq_enabled;
 
-struct pv_time_ops {
-	unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
-	struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
 
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return pv_ops.time.steal_clock(cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 #endif
 
diff --git a/arch/arm/kernel/paravirt.c b/arch/arm/kernel/paravirt.c
index 4cfed91fe256..7dd9806369fb 100644
--- a/arch/arm/kernel/paravirt.c
+++ b/arch/arm/kernel/paravirt.c
@@ -9,10 +9,15 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/types.h>
+#include <linux/static_call.h>
 #include <asm/paravirt.h>
 
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
index cf3a0fd7c1a7..9aa193e0e8f2 100644
--- a/arch/arm64/include/asm/paravirt.h
+++ b/arch/arm64/include/asm/paravirt.h
@@ -3,23 +3,19 @@
 #define _ASM_ARM64_PARAVIRT_H
 
 #ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
 struct static_key;
 extern struct static_key paravirt_steal_enabled;
 extern struct static_key paravirt_steal_rq_enabled;
 
-struct pv_time_ops {
-	unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
-	struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
 
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return pv_ops.time.steal_clock(cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 
 int __init pv_time_init(void);
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index c07d7a034941..75fed4460407 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -18,6 +18,7 @@
 #include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/static_call.h>
 
 #include <asm/paravirt.h>
 #include <asm/pvclock-abi.h>
@@ -26,8 +27,12 @@
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
 
 struct pv_time_stolen_time_region {
 	struct pvclock_vcpu_stolen_time *kaddr;
@@ -45,7 +50,7 @@ static int __init parse_no_stealacc(char *arg)
 early_param("no-steal-acc", parse_no_stealacc);
 
 /* return stolen time in ns by asking the hypervisor */
-static u64 pv_steal_clock(int cpu)
+static u64 para_steal_clock(int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 
@@ -150,7 +155,7 @@ int __init pv_time_init(void)
 	if (ret)
 		return ret;
 
-	pv_ops.time.steal_clock = pv_steal_clock;
+	static_call_update(pv_steal_clock, para_steal_clock);
 
 	static_key_slow_inc(&paravirt_steal_enabled);
 	if (steal_acc)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2792879d398e..107acc403b3b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -777,6 +777,7 @@ if HYPERVISOR_GUEST
 
 config PARAVIRT
 	bool "Enable paravirtualization code"
+	depends on HAVE_STATIC_CALL
 	help
 	  This changes the kernel so it can modify itself when it is run
 	  under a hypervisor, potentially improving performance significantly
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index ccf60a809a17..e7be720062a8 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -63,7 +63,7 @@ typedef int (*hyperv_fill_flush_list_func)(
 static __always_inline void hv_setup_sched_clock(void *sched_clock)
 {
 #ifdef CONFIG_PARAVIRT
-	pv_ops.time.sched_clock = sched_clock;
+	paravirt_set_sched_clock(sched_clock);
 #endif
 }
 
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 4abf110e2243..6408fd0f55ab 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -15,11 +15,20 @@
 #include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/cpumask.h>
+#include <linux/static_call_types.h>
 #include <asm/frame.h>
 
-static inline unsigned long long paravirt_sched_clock(void)
+u64 dummy_steal_clock(int cpu);
+u64 dummy_sched_clock(void);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void));
+
+static inline u64 paravirt_sched_clock(void)
 {
-	return PVOP_CALL0(unsigned long long, time.sched_clock);
+	return static_call(pv_sched_clock)();
 }
 
 struct static_key;
@@ -33,7 +42,7 @@ bool pv_is_native_vcpu_is_preempted(void);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return PVOP_CALL1(u64, time.steal_clock, cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 
 /* The paravirtualized I/O functions */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index de87087d3bde..1fff349e4792 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -95,11 +95,6 @@ struct pv_lazy_ops {
 } __no_randomize_layout;
 #endif
 
-struct pv_time_ops {
-	unsigned long long (*sched_clock)(void);
-	unsigned long long (*steal_clock)(int cpu);
-} __no_randomize_layout;
-
 struct pv_cpu_ops {
 	/* hooks for various privileged instructions */
 	void (*io_delay)(void);
@@ -291,7 +286,6 @@ struct pv_lock_ops {
  * what to patch. */
 struct paravirt_patch_template {
 	struct pv_init_ops	init;
-	struct pv_time_ops	time;
 	struct pv_cpu_ops	cpu;
 	struct pv_irq_ops	irq;
 	struct pv_mmu_ops	mmu;
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index c6ede3b3d302..84fb8e3f3d1b 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -27,6 +27,7 @@
 #include <linux/clocksource.h>
 #include <linux/cpu.h>
 #include <linux/reboot.h>
+#include <linux/static_call.h>
 #include <asm/div64.h>
 #include <asm/x86_init.h>
 #include <asm/hypervisor.h>
@@ -336,11 +337,11 @@ static void __init vmware_paravirt_ops_setup(void)
 	vmware_cyc2ns_setup();
 
 	if (vmw_sched_clock)
-		pv_ops.time.sched_clock = vmware_sched_clock;
+		paravirt_set_sched_clock(vmware_sched_clock);
 
 	if (vmware_is_stealclock_available()) {
 		has_steal_clock = true;
-		pv_ops.time.steal_clock = vmware_steal_clock;
+		static_call_update(pv_steal_clock, vmware_steal_clock);
 
 		/* We use reboot notifier only to disable steal clock */
 		register_reboot_notifier(&vmware_pv_reboot_nb);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5e78e01ca3b4..351ba99f6009 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -650,7 +650,7 @@ static void __init kvm_guest_init(void)
 
 	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		has_steal_clock = 1;
-		pv_ops.time.steal_clock = kvm_steal_clock;
+		static_call_update(pv_steal_clock, kvm_steal_clock);
 	}
 
 	if (pv_tlb_flush_supported()) {
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index aa593743acf6..01e7c1839ace 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -106,7 +106,7 @@ static inline void kvm_sched_clock_init(bool stable)
 	if (!stable)
 		clear_sched_clock_stable();
 	kvm_sched_clock_offset = kvm_clock_read();
-	pv_ops.time.sched_clock = kvm_sched_clock_read;
+	paravirt_set_sched_clock(kvm_sched_clock_read);
 
 	pr_info("kvm-clock: using sched offset of %llu cycles",
 		kvm_sched_clock_offset);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c60222ab8ab9..a688edf35e31 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -14,6 +14,7 @@
 #include <linux/highmem.h>
 #include <linux/kprobes.h>
 #include <linux/pgtable.h>
+#include <linux/static_call.h>
 
 #include <asm/bug.h>
 #include <asm/paravirt.h>
@@ -167,6 +168,14 @@ static u64 native_steal_clock(int cpu)
 	return 0;
 }
 
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void))
+{
+	static_call_update(pv_sched_clock, func);
+}
+
 /* These are in entry.S */
 extern void native_iret(void);
 
@@ -272,10 +281,6 @@ struct paravirt_patch_template pv_ops = {
 	/* Init ops. */
 	.init.patch		= native_patch,
 
-	/* Time ops. */
-	.time.sched_clock	= native_sched_clock,
-	.time.steal_clock	= native_steal_clock,
-
 	/* Cpu ops. */
 	.cpu.io_delay		= native_io_delay,
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index f70dffc2771f..9f592923f956 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/timex.h>
 #include <linux/static_key.h>
+#include <linux/static_call.h>
 
 #include <asm/hpet.h>
 #include <asm/timer.h>
@@ -254,7 +255,7 @@ unsigned long long sched_clock(void)
 
 bool using_native_sched_clock(void)
 {
-	return pv_ops.time.sched_clock == native_sched_clock;
+	return static_call_query(pv_sched_clock) == native_sched_clock;
 }
 #else
 unsigned long long
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 91f5b330dcc6..d9c945ee1100 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -379,11 +379,6 @@ void xen_timer_resume(void)
 	}
 }
 
-static const struct pv_time_ops xen_time_ops __initconst = {
-	.sched_clock = xen_sched_clock,
-	.steal_clock = xen_steal_clock,
-};
-
 static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
 static u64 xen_clock_value_saved;
 
@@ -525,17 +520,24 @@ static void __init xen_time_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 }
 
-void __init xen_init_time_ops(void)
+static void __init xen_init_time_common(void)
 {
 	xen_sched_clock_offset = xen_clocksource_read();
-	pv_ops.time = xen_time_ops;
+	static_call_update(pv_steal_clock, xen_steal_clock);
+	paravirt_set_sched_clock(xen_sched_clock);
+
+	x86_platform.calibrate_tsc = xen_tsc_khz;
+	x86_platform.get_wallclock = xen_get_wallclock;
+}
+
+void __init xen_init_time_ops(void)
+{
+	xen_init_time_common();
 
 	x86_init.timers.timer_init = xen_time_init;
 	x86_init.timers.setup_percpu_clockev = x86_init_noop;
 	x86_cpuinit.setup_percpu_clockev = x86_init_noop;
 
-	x86_platform.calibrate_tsc = xen_tsc_khz;
-	x86_platform.get_wallclock = xen_get_wallclock;
 	/* Dom0 uses the native method to set the hardware RTC. */
 	if (!xen_initial_domain())
 		x86_platform.set_wallclock = xen_set_wallclock;
@@ -569,13 +571,11 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 	}
 
-	xen_sched_clock_offset = xen_clocksource_read();
-	pv_ops.time = xen_time_ops;
+	xen_init_time_common();
+
 	x86_init.timers.setup_percpu_clockev = xen_time_init;
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
 
-	x86_platform.calibrate_tsc = xen_tsc_khz;
-	x86_platform.get_wallclock = xen_get_wallclock;
 	x86_platform.set_wallclock = xen_set_wallclock;
 }
 #endif
diff --git a/drivers/xen/time.c b/drivers/xen/time.c
index 108edbcbc040..152dd33bb223 100644
--- a/drivers/xen/time.c
+++ b/drivers/xen/time.c
@@ -7,6 +7,7 @@
 #include <linux/math64.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/static_call.h>
 
 #include <asm/paravirt.h>
 #include <asm/xen/hypervisor.h>
@@ -175,7 +176,7 @@ void __init xen_time_setup_guest(void)
 	xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable,
 					VMASST_TYPE_runstate_update_flag);
 
-	pv_ops.time.steal_clock = xen_steal_clock;
+	static_call_update(pv_steal_clock, xen_steal_clock);
 
 	static_key_slow_inc(&paravirt_steal_enabled);
 	if (xen_runstate_remote)
-- 
2.26.2

[PATCH v7 05/14] x86/alternative: support not-feature

[Juergen Gross]

Add support for alternative patching for the case a feature is not
present on the current cpu.

For users of ALTERNATIVE() and friends an inverted feature is specified
by applying the ALT_NOT() macro to it, e.g.:

ALTERNATIVE(old, new, ALT_NOT(feature))

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V5:
- split off from next patch
- reworked to use flag byte (Boris Petkov)
V6:
- rework again to not use flag byte (Boris Petkov)
V7:
- minor tweaks: move defines up, comment wording (Boris Petkov)
---
 arch/x86/include/asm/alternative.h |  3 +++
 arch/x86/kernel/alternative.c      | 20 +++++++++++++++-----
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 53f295f41c34..649e56f70889 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -6,6 +6,9 @@
 #include <linux/stringify.h>
 #include <asm/asm.h>
 
+#define ALTINSTR_FLAG_INV	(1 << 15)
+#define ALT_NOT(feat)		((feat) | ALTINSTR_FLAG_INV)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/stddef.h>
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8d778e46725d..133b549dc091 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -388,21 +388,31 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
+		/* Mask away "NOT" flag bit for feature to test. */
+		u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV;
 
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
 		BUG_ON(a->instrlen > sizeof(insn_buff));
-		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
-		if (!boot_cpu_has(a->cpuid)) {
+		BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32);
+
+		/*
+		 * Patch if either:
+		 * - feature is present
+		 * - feature not present but ALTINSTR_FLAG_INV is set to mean,
+		 *   patch if feature is *NOT* present.
+		 */
+		if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) {
 			if (a->padlen > 1)
 				optimize_nops(a, instr);
 
 			continue;
 		}
 
-		DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
-			a->cpuid >> 5,
-			a->cpuid & 0x1f,
+		DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
+			(a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
+			feature >> 5,
+			feature & 0x1f,
 			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->padlen);
 
-- 
2.26.2

[PATCH v7 06/14] x86/alternative: support ALTERNATIVE_TERNARY

[Juergen Gross]

Add ALTERNATIVE_TERNARY support for replacing an initial instruction
with either of two instructions depending on a feature:

  ALTERNATIVE_TERNARY "default_instr", FEATURE_NR,
                      "feature_on_instr", "feature_off_instr"

which will start with "default_instr" and at patch time will, depending
on FEATURE_NR being set or not, patch that with either
"feature_on_instr" or "feature_off_instr".

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V3:
- new patch
V4:
- use X86_FEATURE_ALWAYS instead of negated feature (Boris Petkov)
- unfortunately this isn't enough to get rid of the "not feature"
  support, as this is needed in the patch "x86/paravirt: switch
  functions with custom code to ALTERNATIVE", too
V5:
- carve out the "not feature" part
V7:
- rename parameter names (Boris Petkov)
---
 arch/x86/include/asm/alternative.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 649e56f70889..a044e59cbdf5 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -179,6 +179,10 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	ALTINSTR_REPLACEMENT(newinstr2, 2)				\
 	".popsection\n"
 
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+	ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
+		      newinstr_yes, feature)
+
 #define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \
 	OLDINSTR_3(oldinsn, 1, 2, 3)						\
 	".pushsection .altinstructions,\"a\"\n"					\
@@ -210,6 +214,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
 #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
 	asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")
 
+#define alternative_ternary(oldinstr, feature, newinstr_yes, newinstr_no) \
+	asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) ::: "memory")
+
 /*
  * Alternative inline assembly with input.
  *
@@ -380,6 +387,10 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	.popsection
 .endm
 
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+	ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
+	newinstr_yes, feature
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
-- 
2.26.2

[PATCH v7 07/14] x86/alternative: don't open code ALTERNATIVE_TERNARY() in _static_cpu_has()

[Juergen Gross]

_static_cpu_has() contains a completely open coded version of
ALTERNATIVE_TERNARY(). Replace that with the macro instead.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V6:
- new patch
V7:
- moved patch earlier in series (Boris Petkov)
---
 arch/x86/include/asm/cpufeature.h | 41 +++++++------------------------
 1 file changed, 9 insertions(+), 32 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1728d4ce5730..16a51e7288d5 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -8,6 +8,7 @@
 
 #include <asm/asm.h>
 #include <linux/bitops.h>
+#include <asm/alternative.h>
 
 enum cpuid_leafs
 {
@@ -175,39 +176,15 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
-		 "2:\n"
-		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
-			 "((5f-4f) - (2b-1b)),0x90\n"
-		 "3:\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 4f - .\n"		/* repl offset */
-		 " .word %P[always]\n"		/* always replace */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 5f - 4f\n"		/* repl len */
-		 " .byte 3b - 2b\n"		/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_replacement,\"ax\"\n"
-		 "4: jmp %l[t_no]\n"
-		 "5:\n"
-		 ".previous\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 0\n"			/* no replacement */
-		 " .word %P[feature]\n"		/* feature bit */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 0\n"			/* repl len */
-		 " .byte 0\n"			/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_aux,\"ax\"\n"
-		 "6:\n"
-		 " testb %[bitnum],%[cap_byte]\n"
-		 " jnz %l[t_yes]\n"
-		 " jmp %l[t_no]\n"
-		 ".previous\n"
+	asm_volatile_goto(
+		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
+		".section .altinstr_aux,\"ax\"\n"
+		"6:\n"
+		" testb %[bitnum],%[cap_byte]\n"
+		" jnz %l[t_yes]\n"
+		" jmp %l[t_no]\n"
+		".previous\n"
 		 : : [feature]  "i" (bit),
-		     [always]   "i" (X86_FEATURE_ALWAYS),
 		     [bitnum]   "i" (1 << (bit & 7)),
 		     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
 		 : : t_yes, t_no);
-- 
2.26.2

[PATCH v7 08/14] x86: add new features for paravirt patching

[Juergen Gross]

For being able to switch paravirt patching from special cased custom
code sequences to ALTERNATIVE handling some X86_FEATURE_* are needed
as new features. This enables to have the standard indirect pv call
as the default code and to patch that with the non-Xen custom code
sequence via ALTERNATIVE patching later.

Make sure paravirt patching is performed before alternative patching.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V3:
- add comment (Boris Petkov)
- no negative features (Boris Petkov)
V4:
- move paravirt_set_cap() to paravirt-spinlocks.c
---
 arch/x86/include/asm/cpufeatures.h   |  2 ++
 arch/x86/include/asm/paravirt.h      | 10 ++++++++++
 arch/x86/kernel/alternative.c        | 30 ++++++++++++++++++++++++++--
 arch/x86/kernel/paravirt-spinlocks.c |  9 +++++++++
 4 files changed, 49 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index cc96e26d69f7..b440c950246d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -236,6 +236,8 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_PVUNLOCK		( 8*32+20) /* "" PV unlock function */
+#define X86_FEATURE_VCPUPREEMPT		( 8*32+21) /* "" PV vcpu_is_preempted function */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 6408fd0f55ab..def450f46097 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -45,6 +45,10 @@ static inline u64 paravirt_steal_clock(int cpu)
 	return static_call(pv_steal_clock)(cpu);
 }
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init paravirt_set_cap(void);
+#endif
+
 /* The paravirtualized I/O functions */
 static inline void slow_down_io(void)
 {
@@ -809,5 +813,11 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 }
 #endif
+
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
+static inline void paravirt_set_cap(void)
+{
+}
+#endif
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 133b549dc091..76ad4ce454c0 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -28,6 +28,7 @@
 #include <asm/insn.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
+#include <asm/paravirt.h>
 
 int __read_mostly alternatives_patched;
 
@@ -733,6 +734,33 @@ void __init alternative_instructions(void)
 	 * patching.
 	 */
 
+	/*
+	 * Paravirt patching and alternative patching can be combined to
+	 * replace a function call with a short direct code sequence (e.g.
+	 * by setting a constant return value instead of doing that in an
+	 * external function).
+	 * In order to make this work the following sequence is required:
+	 * 1. set (artificial) features depending on used paravirt
+	 *    functions which can later influence alternative patching
+	 * 2. apply paravirt patching (generally replacing an indirect
+	 *    function call with a direct one)
+	 * 3. apply alternative patching (e.g. replacing a direct function
+	 *    call with a custom code sequence)
+	 * Doing paravirt patching after alternative patching would clobber
+	 * the optimization of the custom code with a function call again.
+	 */
+	paravirt_set_cap();
+
+	/*
+	 * First patch paravirt functions, such that we overwrite the indirect
+	 * call with the direct call.
+	 */
+	apply_paravirt(__parainstructions, __parainstructions_end);
+
+	/*
+	 * Then patch alternatives, such that those paravirt calls that are in
+	 * alternatives can be overwritten by their immediate fragments.
+	 */
 	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
 #ifdef CONFIG_SMP
@@ -751,8 +779,6 @@ void __init alternative_instructions(void)
 	}
 #endif
 
-	apply_paravirt(__parainstructions, __parainstructions_end);
-
 	restart_nmi();
 	alternatives_patched = 1;
 }
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 4f75d0cf6305..9e1ea99ad9df 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -32,3 +32,12 @@ bool pv_is_native_vcpu_is_preempted(void)
 	return pv_ops.lock.vcpu_is_preempted.func ==
 		__raw_callee_save___native_vcpu_is_preempted;
 }
+
+void __init paravirt_set_cap(void)
+{
+	if (!pv_is_native_spin_unlock())
+		setup_force_cpu_cap(X86_FEATURE_PVUNLOCK);
+
+	if (!pv_is_native_vcpu_is_preempted())
+		setup_force_cpu_cap(X86_FEATURE_VCPUPREEMPT);
+}
-- 
2.26.2

[PATCH v7 09/14] x86/paravirt: remove no longer needed 32-bit pvops cruft

[Juergen Gross]

PVOP_VCALL4() is only used for Xen PV, while PVOP_CALL4() isn't used
at all. Keep PVOP_CALL4() for 64 bits due to symmetry reasons.

This allows to remove the 32-bit definitions of those macros leading
to a substantial simplification of the paravirt macros, as those were
the only ones needing non-empty "pre" and "post" parameters.

PVOP_CALLEE2() and PVOP_VCALLEE2() are used nowhere, so remove them.

Another no longer needed case is special handling of return types
larger than unsigned long. Replace that with a BUILD_BUG_ON().

DISABLE_INTERRUPTS() is used in 32-bit code only, so it can just be
replaced by cli.

INTERRUPT_RETURN in 32-bit code can be replaced by iret.

ENABLE_INTERRUPTS is used nowhere, so it can be removed.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/entry/entry_32.S             |   4 +-
 arch/x86/include/asm/irqflags.h       |   5 --
 arch/x86/include/asm/paravirt.h       |  35 +-------
 arch/x86/include/asm/paravirt_types.h | 112 ++++++++------------------
 arch/x86/kernel/asm-offsets.c         |   2 -
 5 files changed, 35 insertions(+), 123 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 4e079f250962..96f084868ec7 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -430,7 +430,7 @@
 	 * will soon execute iret and the tracer was already set to
 	 * the irqstate after the IRET:
 	 */
-	DISABLE_INTERRUPTS(CLBR_ANY)
+	cli
 	lss	(%esp), %esp			/* switch to espfix segment */
 .Lend_\@:
 #endif /* CONFIG_X86_ESPFIX32 */
@@ -1077,7 +1077,7 @@ restore_all_switch_stack:
 	 * when returning from IPI handler and when returning from
 	 * scheduler to user-space.
 	 */
-	INTERRUPT_RETURN
+	iret
 
 .section .fixup, "ax"
 SYM_CODE_START(asm_iret_error)
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 144d70ea4393..a0efbcd24b86 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -109,9 +109,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 }
 #else
 
-#define ENABLE_INTERRUPTS(x)	sti
-#define DISABLE_INTERRUPTS(x)	cli
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(x)		pushfq; popq %rax
@@ -119,8 +116,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 
 #define INTERRUPT_RETURN	jmp native_iret
 
-#else
-#define INTERRUPT_RETURN		iret
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index def450f46097..a780509186bd 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -719,6 +719,7 @@ extern void default_banner(void);
 	.if ((~(set)) & mask); pop %reg; .endif
 
 #ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT_XXL
 
 #define PV_SAVE_REGS(set)			\
 	COND_PUSH(set, CLBR_RAX, rax);		\
@@ -744,46 +745,12 @@ extern void default_banner(void);
 #define PARA_PATCH(off)		((off) / 8)
 #define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
-#else
-#define PV_SAVE_REGS(set)			\
-	COND_PUSH(set, CLBR_EAX, eax);		\
-	COND_PUSH(set, CLBR_EDI, edi);		\
-	COND_PUSH(set, CLBR_ECX, ecx);		\
-	COND_PUSH(set, CLBR_EDX, edx)
-#define PV_RESTORE_REGS(set)			\
-	COND_POP(set, CLBR_EDX, edx);		\
-	COND_POP(set, CLBR_ECX, ecx);		\
-	COND_POP(set, CLBR_EDI, edi);		\
-	COND_POP(set, CLBR_EAX, eax)
-
-#define PARA_PATCH(off)		((off) / 4)
-#define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .long, 4)
-#define PARA_INDIRECT(addr)	*%cs:addr
-#endif
 
-#ifdef CONFIG_PARAVIRT_XXL
 #define INTERRUPT_RETURN						\
 	PARA_SITE(PARA_PATCH(PV_CPU_iret),				\
 		  ANNOTATE_RETPOLINE_SAFE;				\
 		  jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
 
-#define DISABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable),			\
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable);	\
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-
-#define ENABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable),			\
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable);		\
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-#endif
-
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(clobbers)                                        \
 	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),			    \
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 1fff349e4792..42f9eef84131 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -470,55 +470,34 @@ int paravirt_disable_iospace(void);
 	})
 
 
-#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr,		\
-		      pre, post, ...)					\
+#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, ...)	\
 	({								\
-		rettype __ret;						\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		/* This is 32-bit specific, but is okay in 64-bit */	\
-		/* since this condition will never hold */		\
-		if (sizeof(rettype) > sizeof(unsigned long)) {		\
-			asm volatile(pre				\
-				     paravirt_alt(PARAVIRT_CALL)	\
-				     post				\
-				     : call_clbr, ASM_CALL_CONSTRAINT	\
-				     : paravirt_type(op),		\
-				       paravirt_clobber(clbr),		\
-				       ##__VA_ARGS__			\
-				     : "memory", "cc" extra_clbr);	\
-			__ret = (rettype)((((u64)__edx) << 32) | __eax); \
-		} else {						\
-			asm volatile(pre				\
-				     paravirt_alt(PARAVIRT_CALL)	\
-				     post				\
-				     : call_clbr, ASM_CALL_CONSTRAINT	\
-				     : paravirt_type(op),		\
-				       paravirt_clobber(clbr),		\
-				       ##__VA_ARGS__			\
-				     : "memory", "cc" extra_clbr);	\
-			__ret = (rettype)(__eax & PVOP_RETMASK(rettype));	\
-		}							\
-		__ret;							\
+		BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long));	\
+		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
+			     : call_clbr, ASM_CALL_CONSTRAINT		\
+			     : paravirt_type(op),			\
+			       paravirt_clobber(clbr),			\
+			       ##__VA_ARGS__				\
+			     : "memory", "cc" extra_clbr);		\
+		(rettype)(__eax & PVOP_RETMASK(rettype));		\
 	})
 
-#define __PVOP_CALL(rettype, op, pre, post, ...)			\
+#define __PVOP_CALL(rettype, op, ...)					\
 	____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS,	\
-		      EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
+		      EXTRA_CLOBBERS, ##__VA_ARGS__)
 
-#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...)			\
+#define __PVOP_CALLEESAVE(rettype, op, ...)				\
 	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
-		      PVOP_CALLEE_CLOBBERS, ,				\
-		      pre, post, ##__VA_ARGS__)
+		      PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 
-#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...)	\
+#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, ...)		\
 	({								\
 		PVOP_VCALL_ARGS;					\
 		PVOP_TEST_NULL(op);					\
-		asm volatile(pre					\
-			     paravirt_alt(PARAVIRT_CALL)		\
-			     post					\
+		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
 			     : paravirt_type(op),			\
 			       paravirt_clobber(clbr),			\
@@ -526,84 +505,57 @@ int paravirt_disable_iospace(void);
 			     : "memory", "cc" extra_clbr);		\
 	})
 
-#define __PVOP_VCALL(op, pre, post, ...)				\
+#define __PVOP_VCALL(op, ...)						\
 	____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS,		\
-		       VEXTRA_CLOBBERS,					\
-		       pre, post, ##__VA_ARGS__)
+		       VEXTRA_CLOBBERS, ##__VA_ARGS__)
 
-#define __PVOP_VCALLEESAVE(op, pre, post, ...)				\
+#define __PVOP_VCALLEESAVE(op, ...)					\
 	____PVOP_VCALL(op.func, CLBR_RET_REG,				\
-		      PVOP_VCALLEE_CLOBBERS, ,				\
-		      pre, post, ##__VA_ARGS__)
+		      PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 
 
 #define PVOP_CALL0(rettype, op)						\
-	__PVOP_CALL(rettype, op, "", "")
+	__PVOP_CALL(rettype, op)
 #define PVOP_VCALL0(op)							\
-	__PVOP_VCALL(op, "", "")
+	__PVOP_VCALL(op)
 
 #define PVOP_CALLEE0(rettype, op)					\
-	__PVOP_CALLEESAVE(rettype, op, "", "")
+	__PVOP_CALLEESAVE(rettype, op)
 #define PVOP_VCALLEE0(op)						\
-	__PVOP_VCALLEESAVE(op, "", "")
+	__PVOP_VCALLEESAVE(op)
 
 
 #define PVOP_CALL1(rettype, op, arg1)					\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALL1(op, arg1)						\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1))
 
 #define PVOP_CALLEE1(rettype, op, arg1)					\
-	__PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_CALLEESAVE(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALLEE1(op, arg1)						\
-	__PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_VCALLEESAVE(op, PVOP_CALL_ARG1(arg1))
 
 
 #define PVOP_CALL2(rettype, op, arg1, arg2)				\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),		\
-		    PVOP_CALL_ARG2(arg2))
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
 #define PVOP_VCALL2(op, arg1, arg2)					\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),			\
-		     PVOP_CALL_ARG2(arg2))
-
-#define PVOP_CALLEE2(rettype, op, arg1, arg2)				\
-	__PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1),	\
-			  PVOP_CALL_ARG2(arg2))
-#define PVOP_VCALLEE2(op, arg1, arg2)					\
-	__PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1),		\
-			   PVOP_CALL_ARG2(arg2))
-
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
 
 #define PVOP_CALL3(rettype, op, arg1, arg2, arg3)			\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),		\
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1),			\
 		    PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 #define PVOP_VCALL3(op, arg1, arg2, arg3)				\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),			\
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1),				\
 		     PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 
-/* This is the only difference in x86_64. We can make it much simpler */
-#ifdef CONFIG_X86_32
 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
 	__PVOP_CALL(rettype, op,					\
-		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),		\
-		    PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op,						\
-		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    "0" ((u32)(arg1)), "1" ((u32)(arg2)),		\
-		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
-#else
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
-	__PVOP_CALL(rettype, op, "", "",				\
 		    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),		\
 		    PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op, "", "",					\
-		     PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
 		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-#endif
 
 /* Lazy mode for batching updates / context switch */
 enum paravirt_lazy_mode {
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 60b9f42ce3c1..736508004b30 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -63,8 +63,6 @@ static void __used common(void)
 
 #ifdef CONFIG_PARAVIRT_XXL
 	BLANK();
-	OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
-	OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
 	OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
 #endif
 
-- 
2.26.2

[PATCH v7 10/14] x86/paravirt: simplify paravirt macros

[Juergen Gross]

The central pvops call macros ____PVOP_CALL() and ____PVOP_VCALL() are
looking very similar now.

The main differences are using PVOP_VCALL_ARGS or PVOP_CALL_ARGS, which
are identical, and the return value handling.

So drop PVOP_VCALL_ARGS and instead of ____PVOP_VCALL() just use
(void)____PVOP_CALL(long, ...).

Note that it isn't easily possible to just redefine ____PVOP_VCALL()
to use ____PVOP_CALL() instead, as this would require further hiding of
commas in macro parameters.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V3:
- new patch
V4:
- fix build warnings with clang (kernel test robot)
---
 arch/x86/include/asm/paravirt_types.h | 41 ++++++++-------------------
 1 file changed, 12 insertions(+), 29 deletions(-)

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 42f9eef84131..45bd21647dd8 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -408,11 +408,9 @@ int paravirt_disable_iospace(void);
  * makes sure the incoming and outgoing types are always correct.
  */
 #ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS							\
+#define PVOP_CALL_ARGS							\
 	unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
 
-#define PVOP_CALL_ARGS			PVOP_VCALL_ARGS
-
 #define PVOP_CALL_ARG1(x)		"a" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"d" ((unsigned long)(x))
 #define PVOP_CALL_ARG3(x)		"c" ((unsigned long)(x))
@@ -428,12 +426,10 @@ int paravirt_disable_iospace(void);
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
 /* [re]ax isn't an arg, but the return val */
-#define PVOP_VCALL_ARGS						\
+#define PVOP_CALL_ARGS						\
 	unsigned long __edi = __edi, __esi = __esi,		\
 		__edx = __edx, __ecx = __ecx, __eax = __eax;
 
-#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS
-
 #define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"S" ((unsigned long)(x))
 #define PVOP_CALL_ARG3(x)		"d" ((unsigned long)(x))
@@ -458,59 +454,46 @@ int paravirt_disable_iospace(void);
 #define PVOP_TEST_NULL(op)	((void)pv_ops.op)
 #endif
 
-#define PVOP_RETMASK(rettype)						\
+#define PVOP_RETVAL(rettype)						\
 	({	unsigned long __mask = ~0UL;				\
+		BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long));	\
 		switch (sizeof(rettype)) {				\
 		case 1: __mask =       0xffUL; break;			\
 		case 2: __mask =     0xffffUL; break;			\
 		case 4: __mask = 0xffffffffUL; break;			\
 		default: break;						\
 		}							\
-		__mask;							\
+		__mask & __eax;						\
 	})
 
 
-#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, ...)	\
+#define ____PVOP_CALL(ret, op, clbr, call_clbr, extra_clbr, ...)	\
 	({								\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long));	\
 		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
 			     : paravirt_type(op),			\
 			       paravirt_clobber(clbr),			\
 			       ##__VA_ARGS__				\
 			     : "memory", "cc" extra_clbr);		\
-		(rettype)(__eax & PVOP_RETMASK(rettype));		\
+		ret;							\
 	})
 
 #define __PVOP_CALL(rettype, op, ...)					\
-	____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS,	\
-		      EXTRA_CLOBBERS, ##__VA_ARGS__)
+	____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY,		\
+		      PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__)
 
 #define __PVOP_CALLEESAVE(rettype, op, ...)				\
-	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
+	____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG,	\
 		      PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
 
-
-#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, ...)		\
-	({								\
-		PVOP_VCALL_ARGS;					\
-		PVOP_TEST_NULL(op);					\
-		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
-			     : call_clbr, ASM_CALL_CONSTRAINT		\
-			     : paravirt_type(op),			\
-			       paravirt_clobber(clbr),			\
-			       ##__VA_ARGS__				\
-			     : "memory", "cc" extra_clbr);		\
-	})
-
 #define __PVOP_VCALL(op, ...)						\
-	____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS,		\
+	(void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS,	\
 		       VEXTRA_CLOBBERS, ##__VA_ARGS__)
 
 #define __PVOP_VCALLEESAVE(op, ...)					\
-	____PVOP_VCALL(op.func, CLBR_RET_REG,				\
+	(void)____PVOP_CALL(, op.func, CLBR_RET_REG,			\
 		      PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 
-- 
2.26.2

[PATCH v7 11/14] x86/paravirt: switch iret pvops to ALTERNATIVE

[Juergen Gross]

The iret paravirt op is rather special as it is using a jmp instead
of a call instruction. Switch it to ALTERNATIVE.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V3:
- use ALTERNATIVE_TERNARY
---
 arch/x86/include/asm/paravirt.h       |  6 +++---
 arch/x86/include/asm/paravirt_types.h |  5 +----
 arch/x86/kernel/asm-offsets.c         |  5 -----
 arch/x86/kernel/paravirt.c            | 26 ++------------------------
 arch/x86/xen/enlighten_pv.c           |  3 +--
 5 files changed, 7 insertions(+), 38 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a780509186bd..913acf7a0ebf 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -747,9 +747,9 @@ extern void default_banner(void);
 #define PARA_INDIRECT(addr)	*addr(%rip)
 
 #define INTERRUPT_RETURN						\
-	PARA_SITE(PARA_PATCH(PV_CPU_iret),				\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
+	ANNOTATE_RETPOLINE_SAFE;					\
+	ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);",		\
+		X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
 
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(clobbers)                                        \
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 45bd21647dd8..0afdac83f926 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -151,10 +151,6 @@ struct pv_cpu_ops {
 
 	u64 (*read_pmc)(int counter);
 
-	/* Normal iret.  Jump to this with the standard iret stack
-	   frame set up. */
-	void (*iret)(void);
-
 	void (*start_context_switch)(struct task_struct *prev);
 	void (*end_context_switch)(struct task_struct *next);
 #endif
@@ -294,6 +290,7 @@ struct paravirt_patch_template {
 
 extern struct pv_info pv_info;
 extern struct paravirt_patch_template pv_ops;
+extern void (*paravirt_iret)(void);
 
 #define PARAVIRT_PATCH(x)					\
 	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 736508004b30..ecd3fd6993d1 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -61,11 +61,6 @@ static void __used common(void)
 	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
 #endif
 
-#ifdef CONFIG_PARAVIRT_XXL
-	BLANK();
-	OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
-#endif
-
 #ifdef CONFIG_XEN
 	BLANK();
 	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index a688edf35e31..9b0f568b0200 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -86,25 +86,6 @@ u64 notrace _paravirt_ident_64(u64 x)
 {
 	return x;
 }
-
-static unsigned paravirt_patch_jmp(void *insn_buff, const void *target,
-				   unsigned long addr, unsigned len)
-{
-	struct branch *b = insn_buff;
-	unsigned long delta = (unsigned long)target - (addr+5);
-
-	if (len < 5) {
-#ifdef CONFIG_RETPOLINE
-		WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
-#endif
-		return len;	/* call too long for patch site */
-	}
-
-	b->opcode = 0xe9;	/* jmp */
-	b->delta = delta;
-
-	return 5;
-}
 #endif
 
 DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
@@ -136,9 +117,6 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	else if (opfunc == _paravirt_ident_64)
 		ret = paravirt_patch_ident_64(insn_buff, len);
 
-	else if (type == PARAVIRT_PATCH(cpu.iret))
-		/* If operation requires a jmp, then jmp */
-		ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
 #endif
 	else
 		/* Otherwise call the function. */
@@ -313,8 +291,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.load_sp0		= native_load_sp0,
 
-	.cpu.iret		= native_iret,
-
 #ifdef CONFIG_X86_IOPL_IOPERM
 	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
 	.cpu.update_io_bitmap		= native_tss_update_io_bitmap,
@@ -419,6 +395,8 @@ struct paravirt_patch_template pv_ops = {
 NOKPROBE_SYMBOL(native_get_debugreg);
 NOKPROBE_SYMBOL(native_set_debugreg);
 NOKPROBE_SYMBOL(native_load_idt);
+
+void (*paravirt_iret)(void) = native_iret;
 #endif
 
 EXPORT_SYMBOL(pv_ops);
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index dc0a337f985b..08dca7bebb30 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1070,8 +1070,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 
 	.read_pmc = xen_read_pmc,
 
-	.iret = xen_iret,
-
 	.load_tr_desc = paravirt_nop,
 	.set_ldt = xen_set_ldt,
 	.load_gdt = xen_load_gdt,
@@ -1235,6 +1233,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	pv_info = xen_info;
 	pv_ops.init.patch = paravirt_patch_default;
 	pv_ops.cpu = xen_cpu_ops;
+	paravirt_iret = xen_iret;
 	xen_init_irq_ops();
 
 	/*
-- 
2.26.2

[PATCH v7 12/14] x86/paravirt: add new macros PVOP_ALT* supporting pvops in ALTERNATIVEs

[Juergen Gross]

Instead of using paravirt patching for custom code sequences add
support for using ALTERNATIVE handling combined with paravirt call
patching.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V3:
- drop ____PVOP_ALT_VCALL() macro
---
 arch/x86/include/asm/paravirt_types.h | 49 ++++++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0afdac83f926..0ed976286d49 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -477,44 +477,91 @@ int paravirt_disable_iospace(void);
 		ret;							\
 	})
 
+#define ____PVOP_ALT_CALL(ret, op, alt, cond, clbr, call_clbr,		\
+			  extra_clbr, ...)				\
+	({								\
+		PVOP_CALL_ARGS;						\
+		PVOP_TEST_NULL(op);					\
+		asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL),	\
+					 alt, cond)			\
+			     : call_clbr, ASM_CALL_CONSTRAINT		\
+			     : paravirt_type(op),			\
+			       paravirt_clobber(clbr),			\
+			       ##__VA_ARGS__				\
+			     : "memory", "cc" extra_clbr);		\
+		ret;							\
+	})
+
 #define __PVOP_CALL(rettype, op, ...)					\
 	____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY,		\
 		      PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__)
 
+#define __PVOP_ALT_CALL(rettype, op, alt, cond, ...)			\
+	____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op, alt, cond, CLBR_ANY,\
+			  PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS,		\
+			  ##__VA_ARGS__)
+
 #define __PVOP_CALLEESAVE(rettype, op, ...)				\
 	____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG,	\
 		      PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
 
+#define __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, ...)		\
+	____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op.func, alt, cond,	\
+			  CLBR_RET_REG, PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
+
+
 #define __PVOP_VCALL(op, ...)						\
 	(void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS,	\
 		       VEXTRA_CLOBBERS, ##__VA_ARGS__)
 
+#define __PVOP_ALT_VCALL(op, alt, cond, ...)				\
+	(void)____PVOP_ALT_CALL(, op, alt, cond, CLBR_ANY,		\
+				PVOP_VCALL_CLOBBERS, VEXTRA_CLOBBERS,	\
+				##__VA_ARGS__)
+
 #define __PVOP_VCALLEESAVE(op, ...)					\
 	(void)____PVOP_CALL(, op.func, CLBR_RET_REG,			\
-		      PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
+			    PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
+#define __PVOP_ALT_VCALLEESAVE(op, alt, cond, ...)			\
+	(void)____PVOP_ALT_CALL(, op.func, alt, cond, CLBR_RET_REG,	\
+				PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 
 #define PVOP_CALL0(rettype, op)						\
 	__PVOP_CALL(rettype, op)
 #define PVOP_VCALL0(op)							\
 	__PVOP_VCALL(op)
+#define PVOP_ALT_CALL0(rettype, op, alt, cond)				\
+	__PVOP_ALT_CALL(rettype, op, alt, cond)
+#define PVOP_ALT_VCALL0(op, alt, cond)					\
+	__PVOP_ALT_VCALL(op, alt, cond)
 
 #define PVOP_CALLEE0(rettype, op)					\
 	__PVOP_CALLEESAVE(rettype, op)
 #define PVOP_VCALLEE0(op)						\
 	__PVOP_VCALLEESAVE(op)
+#define PVOP_ALT_CALLEE0(rettype, op, alt, cond)			\
+	__PVOP_ALT_CALLEESAVE(rettype, op, alt, cond)
+#define PVOP_ALT_VCALLEE0(op, alt, cond)				\
+	__PVOP_ALT_VCALLEESAVE(op, alt, cond)
 
 
 #define PVOP_CALL1(rettype, op, arg1)					\
 	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALL1(op, arg1)						\
 	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALL1(op, arg1, alt, cond)				\
+	__PVOP_ALT_VCALL(op, alt, cond, PVOP_CALL_ARG1(arg1))
 
 #define PVOP_CALLEE1(rettype, op, arg1)					\
 	__PVOP_CALLEESAVE(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALLEE1(op, arg1)						\
 	__PVOP_VCALLEESAVE(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_CALLEE1(rettype, op, arg1, alt, cond)			\
+	__PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALLEE1(op, arg1, alt, cond)				\
+	__PVOP_ALT_VCALLEESAVE(op, alt, cond, PVOP_CALL_ARG1(arg1))
 
 
 #define PVOP_CALL2(rettype, op, arg1, arg2)				\
-- 
2.26.2

[PATCH v7 13/14] x86/paravirt: switch functions with custom code to ALTERNATIVE

[Juergen Gross]

Instead of using paravirt patching for custom code sequences use
ALTERNATIVE for the functions with custom code replacements.

Instead of patching an ud2 instruction for unpopulated vector entries
into the caller site, use a simple function just calling BUG() as a
replacement.

Simplify the register defines for assembler paravirt calling, as there
isn't much usage left.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V4:
- fixed SAVE_FLAGS() (kernel test robot)
- added assembler paravirt cleanup
---
 arch/x86/entry/entry_64.S             |   2 +-
 arch/x86/include/asm/irqflags.h       |   2 +-
 arch/x86/include/asm/paravirt.h       | 101 +++++++++++++-------------
 arch/x86/include/asm/paravirt_types.h |   6 --
 arch/x86/kernel/paravirt.c            |  16 ++--
 arch/x86/kernel/paravirt_patch.c      |  88 ----------------------
 6 files changed, 58 insertions(+), 157 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 400908dff42e..12e2e3cd58be 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -305,7 +305,7 @@ SYM_CODE_END(ret_from_fork)
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
 	pushq %rax
-	SAVE_FLAGS(CLBR_RAX)
+	SAVE_FLAGS
 	testl $X86_EFLAGS_IF, %eax
 	jz .Lokay_\@
 	ud2
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index a0efbcd24b86..c5ce9845c999 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -111,7 +111,7 @@ static __always_inline unsigned long arch_local_irq_save(void)
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(x)		pushfq; popq %rax
+#define SAVE_FLAGS		pushfq; popq %rax
 #endif
 
 #define INTERRUPT_RETURN	jmp native_iret
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 913acf7a0ebf..43992e5c52c2 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -135,7 +135,9 @@ static inline void write_cr0(unsigned long x)
 
 static inline unsigned long read_cr2(void)
 {
-	return PVOP_CALLEE0(unsigned long, mmu.read_cr2);
+	return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
+				"mov %%cr2, %%rax;",
+				ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void write_cr2(unsigned long x)
@@ -145,12 +147,14 @@ static inline void write_cr2(unsigned long x)
 
 static inline unsigned long __read_cr3(void)
 {
-	return PVOP_CALL0(unsigned long, mmu.read_cr3);
+	return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3,
+			      "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void write_cr3(unsigned long x)
 {
-	PVOP_VCALL1(mmu.write_cr3, x);
+	PVOP_ALT_VCALL1(mmu.write_cr3, x,
+			"mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void __write_cr4(unsigned long x)
@@ -170,7 +174,7 @@ static inline void halt(void)
 
 static inline void wbinvd(void)
 {
-	PVOP_VCALL0(cpu.wbinvd);
+	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline u64 paravirt_read_msr(unsigned msr)
@@ -384,22 +388,28 @@ static inline void paravirt_release_p4d(unsigned long pfn)
 
 static inline pte_t __pte(pteval_t val)
 {
-	return (pte_t) { PVOP_CALLEE1(pteval_t, mmu.make_pte, val) };
+	return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pteval_t pte_val(pte_t pte)
 {
-	return PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
+	return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline pgd_t __pgd(pgdval_t val)
 {
-	return (pgd_t) { PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val) };
+	return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pgdval_t pgd_val(pgd_t pgd)
 {
-	return PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
+	return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -432,12 +442,15 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 static inline pmd_t __pmd(pmdval_t val)
 {
-	return (pmd_t) { PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val) };
+	return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pmdval_t pmd_val(pmd_t pmd)
 {
-	return PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
+	return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -449,14 +462,16 @@ static inline pud_t __pud(pudval_t val)
 {
 	pudval_t ret;
 
-	ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
+	ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val,
+			       "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 
 	return (pud_t) { ret };
 }
 
 static inline pudval_t pud_val(pud_t pud)
 {
-	return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
+	return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -475,14 +490,17 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 
 static inline p4d_t __p4d(p4dval_t val)
 {
-	p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val);
+	p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
+					"mov %%rdi, %%rax",
+					ALT_NOT(X86_FEATURE_XENPV));
 
 	return (p4d_t) { ret };
 }
 
 static inline p4dval_t p4d_val(p4d_t p4d)
 {
-	return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d);
+	return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
@@ -569,7 +587,9 @@ static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
 
 static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
 {
-	PVOP_VCALLEE1(lock.queued_spin_unlock, lock);
+	PVOP_ALT_VCALLEE1(lock.queued_spin_unlock, lock,
+			  "movb $0, (%%" _ASM_ARG1 ");",
+			  ALT_NOT(X86_FEATURE_PVUNLOCK));
 }
 
 static __always_inline void pv_wait(u8 *ptr, u8 val)
@@ -584,7 +604,9 @@ static __always_inline void pv_kick(int cpu)
 
 static __always_inline bool pv_vcpu_is_preempted(long cpu)
 {
-	return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu);
+	return PVOP_ALT_CALLEE1(bool, lock.vcpu_is_preempted, cpu,
+				"xor %%" _ASM_AX ", %%" _ASM_AX ";",
+				ALT_NOT(X86_FEATURE_VCPUPREEMPT));
 }
 
 void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
@@ -658,17 +680,18 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 #ifdef CONFIG_PARAVIRT_XXL
 static inline notrace unsigned long arch_local_save_flags(void)
 {
-	return PVOP_CALLEE0(unsigned long, irq.save_fl);
+	return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
+				ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace void arch_local_irq_disable(void)
 {
-	PVOP_VCALLEE0(irq.irq_disable);
+	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace void arch_local_irq_enable(void)
 {
-	PVOP_VCALLEE0(irq.irq_enable);
+	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace unsigned long arch_local_irq_save(void)
@@ -713,35 +736,9 @@ extern void default_banner(void);
 	.popsection
 
 
-#define COND_PUSH(set, mask, reg)			\
-	.if ((~(set)) & mask); push %reg; .endif
-#define COND_POP(set, mask, reg)			\
-	.if ((~(set)) & mask); pop %reg; .endif
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
 
-#define PV_SAVE_REGS(set)			\
-	COND_PUSH(set, CLBR_RAX, rax);		\
-	COND_PUSH(set, CLBR_RCX, rcx);		\
-	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, CLBR_R9, r9);		\
-	COND_PUSH(set, CLBR_R10, r10);		\
-	COND_PUSH(set, CLBR_R11, r11)
-#define PV_RESTORE_REGS(set)			\
-	COND_POP(set, CLBR_R11, r11);		\
-	COND_POP(set, CLBR_R10, r10);		\
-	COND_POP(set, CLBR_R9, r9);		\
-	COND_POP(set, CLBR_R8, r8);		\
-	COND_POP(set, CLBR_RDI, rdi);		\
-	COND_POP(set, CLBR_RSI, rsi);		\
-	COND_POP(set, CLBR_RDX, rdx);		\
-	COND_POP(set, CLBR_RCX, rcx);		\
-	COND_POP(set, CLBR_RAX, rax)
-
 #define PARA_PATCH(off)		((off) / 8)
 #define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
@@ -752,12 +749,14 @@ extern void default_banner(void);
 		X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
 
 #ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(clobbers)                                        \
-	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),			    \
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
-		  ANNOTATE_RETPOLINE_SAFE;			    \
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);	    \
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+.macro PARA_IRQ_save_fl
+	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),
+		  ANNOTATE_RETPOLINE_SAFE;
+		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);)
+.endm
+
+#define SAVE_FLAGS	ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \
+				    ALT_NOT(X86_FEATURE_XENPV)
 #endif
 #endif /* CONFIG_PARAVIRT_XXL */
 #endif	/* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0ed976286d49..588ff14ce969 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -3,7 +3,6 @@
 #define _ASM_X86_PARAVIRT_TYPES_H
 
 /* Bitmask of what can be clobbered: usually at least eax. */
-#define CLBR_NONE 0
 #define CLBR_EAX  (1 << 0)
 #define CLBR_ECX  (1 << 1)
 #define CLBR_EDX  (1 << 2)
@@ -15,7 +14,6 @@
 
 #define CLBR_ARG_REGS	(CLBR_EAX | CLBR_EDX | CLBR_ECX)
 #define CLBR_RET_REG	(CLBR_EAX | CLBR_EDX)
-#define CLBR_SCRATCH	(0)
 #else
 #define CLBR_RAX  CLBR_EAX
 #define CLBR_RCX  CLBR_ECX
@@ -32,12 +30,9 @@
 #define CLBR_ARG_REGS	(CLBR_RDI | CLBR_RSI | CLBR_RDX | \
 			 CLBR_RCX | CLBR_R8 | CLBR_R9)
 #define CLBR_RET_REG	(CLBR_RAX)
-#define CLBR_SCRATCH	(CLBR_R10 | CLBR_R11)
 
 #endif /* X86_64 */
 
-#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
-
 #ifndef __ASSEMBLY__
 
 #include <asm/desc_defs.h>
@@ -322,7 +317,6 @@ extern void (*paravirt_iret)(void);
 /* Simple instruction patching code. */
 #define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
 
-unsigned paravirt_patch_ident_64(void *insn_buff, unsigned len);
 unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned long addr, unsigned len);
 unsigned paravirt_patch_insns(void *insn_buff, unsigned len, const char *start, const char *end);
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9b0f568b0200..855ae08a05a1 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -53,7 +53,10 @@ void __init default_banner(void)
 }
 
 /* Undefined instruction for dealing with missing ops pointers. */
-static const unsigned char ud2a[] = { 0x0f, 0x0b };
+static void paravirt_BUG(void)
+{
+	BUG();
+}
 
 struct branch {
 	unsigned char opcode;
@@ -107,17 +110,10 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	unsigned ret;
 
 	if (opfunc == NULL)
-		/* If there's no function, patch it with a ud2a (BUG) */
-		ret = paravirt_patch_insns(insn_buff, len, ud2a, ud2a+sizeof(ud2a));
+		/* If there's no function, patch it with paravirt_BUG() */
+		ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len);
 	else if (opfunc == _paravirt_nop)
 		ret = 0;
-
-#ifdef CONFIG_PARAVIRT_XXL
-	/* identity functions just return their single argument */
-	else if (opfunc == _paravirt_ident_64)
-		ret = paravirt_patch_ident_64(insn_buff, len);
-
-#endif
 	else
 		/* Otherwise call the function. */
 		ret = paravirt_patch_call(insn_buff, opfunc, addr, len);
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index abd27ec67397..10543dcc8211 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -4,96 +4,8 @@
 #include <asm/paravirt.h>
 #include <asm/asm-offsets.h>
 
-#define PSTART(d, m)							\
-	patch_data_##d.m
-
-#define PEND(d, m)							\
-	(PSTART(d, m) + sizeof(patch_data_##d.m))
-
-#define PATCH(d, m, insn_buff, len)						\
-	paravirt_patch_insns(insn_buff, len, PSTART(d, m), PEND(d, m))
-
-#define PATCH_CASE(ops, m, data, insn_buff, len)				\
-	case PARAVIRT_PATCH(ops.m):					\
-		return PATCH(data, ops##_##m, insn_buff, len)
-
-#ifdef CONFIG_PARAVIRT_XXL
-struct patch_xxl {
-	const unsigned char	irq_irq_disable[1];
-	const unsigned char	irq_irq_enable[1];
-	const unsigned char	irq_save_fl[2];
-	const unsigned char	mmu_read_cr2[3];
-	const unsigned char	mmu_read_cr3[3];
-	const unsigned char	mmu_write_cr3[3];
-	const unsigned char	cpu_wbinvd[2];
-	const unsigned char	mov64[3];
-};
-
-static const struct patch_xxl patch_data_xxl = {
-	.irq_irq_disable	= { 0xfa },		// cli
-	.irq_irq_enable		= { 0xfb },		// sti
-	.irq_save_fl		= { 0x9c, 0x58 },	// pushf; pop %[re]ax
-	.mmu_read_cr2		= { 0x0f, 0x20, 0xd0 },	// mov %cr2, %[re]ax
-	.mmu_read_cr3		= { 0x0f, 0x20, 0xd8 },	// mov %cr3, %[re]ax
-	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
-	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
-	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
-};
-
-unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len)
-{
-	return PATCH(xxl, mov64, insn_buff, len);
-}
-# endif /* CONFIG_PARAVIRT_XXL */
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-struct patch_lock {
-	unsigned char queued_spin_unlock[3];
-	unsigned char vcpu_is_preempted[2];
-};
-
-static const struct patch_lock patch_data_lock = {
-	.vcpu_is_preempted	= { 0x31, 0xc0 },	// xor %eax, %eax
-
-# ifdef CONFIG_X86_64
-	.queued_spin_unlock	= { 0xc6, 0x07, 0x00 },	// movb $0, (%rdi)
-# else
-	.queued_spin_unlock	= { 0xc6, 0x00, 0x00 },	// movb $0, (%eax)
-# endif
-};
-#endif /* CONFIG_PARAVIRT_SPINLOCKS */
-
 unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 			  unsigned int len)
 {
-	switch (type) {
-
-#ifdef CONFIG_PARAVIRT_XXL
-	PATCH_CASE(irq, save_fl, xxl, insn_buff, len);
-	PATCH_CASE(irq, irq_enable, xxl, insn_buff, len);
-	PATCH_CASE(irq, irq_disable, xxl, insn_buff, len);
-
-	PATCH_CASE(mmu, read_cr2, xxl, insn_buff, len);
-	PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
-	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
-
-	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
-#endif
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-	case PARAVIRT_PATCH(lock.queued_spin_unlock):
-		if (pv_is_native_spin_unlock())
-			return PATCH(lock, queued_spin_unlock, insn_buff, len);
-		break;
-
-	case PARAVIRT_PATCH(lock.vcpu_is_preempted):
-		if (pv_is_native_vcpu_is_preempted())
-			return PATCH(lock, vcpu_is_preempted, insn_buff, len);
-		break;
-#endif
-	default:
-		break;
-	}
-
 	return paravirt_patch_default(type, insn_buff, addr, len);
 }
-- 
2.26.2

[PATCH v7 14/14] x86/paravirt: have only one paravirt patch function

[Juergen Gross]

There is no need any longer to have different paravirt patch functions
for native and Xen. Eliminate native_patch() and rename
paravirt_patch_default() to paravirt_patch().

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V3:
- remove paravirt_patch_insns() (kernel test robot)
---
 arch/x86/include/asm/paravirt_types.h | 19 +------------------
 arch/x86/kernel/Makefile              |  3 +--
 arch/x86/kernel/alternative.c         |  2 +-
 arch/x86/kernel/paravirt.c            | 20 ++------------------
 arch/x86/kernel/paravirt_patch.c      | 11 -----------
 arch/x86/xen/enlighten_pv.c           |  1 -
 6 files changed, 5 insertions(+), 51 deletions(-)
 delete mode 100644 arch/x86/kernel/paravirt_patch.c

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 588ff14ce969..9d1ddb7b4350 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -68,19 +68,6 @@ struct pv_info {
 	const char *name;
 };
 
-struct pv_init_ops {
-	/*
-	 * Patch may replace one of the defined code sequences with
-	 * arbitrary code, subject to the same register constraints.
-	 * This generally means the code is not free to clobber any
-	 * registers other than EAX.  The patch function should return
-	 * the number of bytes of code generated, as we nop pad the
-	 * rest in generic code.
-	 */
-	unsigned (*patch)(u8 type, void *insn_buff,
-			  unsigned long addr, unsigned len);
-} __no_randomize_layout;
-
 #ifdef CONFIG_PARAVIRT_XXL
 struct pv_lazy_ops {
 	/* Set deferred update mode, used for batching operations. */
@@ -276,7 +263,6 @@ struct pv_lock_ops {
  * number for each function using the offset which we use to indicate
  * what to patch. */
 struct paravirt_patch_template {
-	struct pv_init_ops	init;
 	struct pv_cpu_ops	cpu;
 	struct pv_irq_ops	irq;
 	struct pv_mmu_ops	mmu;
@@ -317,10 +303,7 @@ extern void (*paravirt_iret)(void);
 /* Simple instruction patching code. */
 #define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
 
-unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned long addr, unsigned len);
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len, const char *start, const char *end);
-
-unsigned native_patch(u8 type, void *insn_buff, unsigned long addr, unsigned len);
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len);
 
 int paravirt_disable_iospace(void);
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 2ddf08351f0b..0704c2a94272 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -35,7 +35,6 @@ KASAN_SANITIZE_sev-es.o					:= n
 KCSAN_SANITIZE := n
 
 OBJECT_FILES_NON_STANDARD_test_nx.o			:= y
-OBJECT_FILES_NON_STANDARD_paravirt_patch.o		:= y
 
 ifdef CONFIG_FRAME_POINTER
 OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o		:= y
@@ -121,7 +120,7 @@ obj-$(CONFIG_AMD_NB)		+= amd_nb.o
 obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
 
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
-obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 76ad4ce454c0..f810e6fececd 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -616,7 +616,7 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
 		BUG_ON(p->len > MAX_PATCH_LEN);
 		/* prep the buffer with the original instructions */
 		memcpy(insn_buff, p->instr, p->len);
-		used = pv_ops.init.patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
+		used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
 
 		BUG_ON(used > p->len);
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 855ae08a05a1..d0730264786b 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -99,8 +99,8 @@ void __init native_pv_lock_init(void)
 		static_branch_disable(&virt_spin_lock_key);
 }
 
-unsigned paravirt_patch_default(u8 type, void *insn_buff,
-				unsigned long addr, unsigned len)
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr,
+			    unsigned int len)
 {
 	/*
 	 * Neat trick to map patch type back to the call within the
@@ -121,19 +121,6 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	return ret;
 }
 
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len,
-			      const char *start, const char *end)
-{
-	unsigned insn_len = end - start;
-
-	/* Alternative instruction is too large for the patch site and we cannot continue: */
-	BUG_ON(insn_len > len || start == NULL);
-
-	memcpy(insn_buff, start, insn_len);
-
-	return insn_len;
-}
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -252,9 +239,6 @@ struct pv_info pv_info = {
 #define PTE_IDENT	__PV_IS_CALLEE_SAVE(_paravirt_ident_64)
 
 struct paravirt_patch_template pv_ops = {
-	/* Init ops. */
-	.init.patch		= native_patch,
-
 	/* Cpu ops. */
 	.cpu.io_delay		= native_io_delay,
 
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
deleted file mode 100644
index 10543dcc8211..000000000000
--- a/arch/x86/kernel/paravirt_patch.c
+++ /dev/null
@@ -1,11 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/stringify.h>
-
-#include <asm/paravirt.h>
-#include <asm/asm-offsets.h>
-
-unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
-			  unsigned int len)
-{
-	return paravirt_patch_default(type, insn_buff, addr, len);
-}
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 08dca7bebb30..4f18cd9eacd8 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1231,7 +1231,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
-	pv_ops.init.patch = paravirt_patch_default;
 	pv_ops.cpu = xen_cpu_ops;
 	paravirt_iret = xen_iret;
 	xen_init_irq_ops();
-- 
2.26.2

[tip: x86/alternatives] x86/paravirt: Have only one paravirt patch function

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     054ac8ad5ebe4a69e1f0e842483821ddbe560121
Gitweb:        https://git.kernel.org/tip/054ac8ad5ebe4a69e1f0e842483821ddbe560121
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:19 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 20:11:09 +01:00

x86/paravirt: Have only one paravirt patch function

There is no need any longer to have different paravirt patch functions
for native and Xen. Eliminate native_patch() and rename
paravirt_patch_default() to paravirt_patch().

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-15-jgross@suse.com
---
 arch/x86/include/asm/paravirt_types.h | 19 +------------------
 arch/x86/kernel/Makefile              |  3 +--
 arch/x86/kernel/alternative.c         |  2 +-
 arch/x86/kernel/paravirt.c            | 20 ++------------------
 arch/x86/kernel/paravirt_patch.c      | 11 -----------
 arch/x86/xen/enlighten_pv.c           |  1 -
 6 files changed, 5 insertions(+), 51 deletions(-)
 delete mode 100644 arch/x86/kernel/paravirt_patch.c

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 588ff14..9d1ddb7 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -68,19 +68,6 @@ struct pv_info {
 	const char *name;
 };
 
-struct pv_init_ops {
-	/*
-	 * Patch may replace one of the defined code sequences with
-	 * arbitrary code, subject to the same register constraints.
-	 * This generally means the code is not free to clobber any
-	 * registers other than EAX.  The patch function should return
-	 * the number of bytes of code generated, as we nop pad the
-	 * rest in generic code.
-	 */
-	unsigned (*patch)(u8 type, void *insn_buff,
-			  unsigned long addr, unsigned len);
-} __no_randomize_layout;
-
 #ifdef CONFIG_PARAVIRT_XXL
 struct pv_lazy_ops {
 	/* Set deferred update mode, used for batching operations. */
@@ -276,7 +263,6 @@ struct pv_lock_ops {
  * number for each function using the offset which we use to indicate
  * what to patch. */
 struct paravirt_patch_template {
-	struct pv_init_ops	init;
 	struct pv_cpu_ops	cpu;
 	struct pv_irq_ops	irq;
 	struct pv_mmu_ops	mmu;
@@ -317,10 +303,7 @@ extern void (*paravirt_iret)(void);
 /* Simple instruction patching code. */
 #define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
 
-unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned long addr, unsigned len);
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len, const char *start, const char *end);
-
-unsigned native_patch(u8 type, void *insn_buff, unsigned long addr, unsigned len);
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len);
 
 int paravirt_disable_iospace(void);
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 2ddf083..0704c2a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -35,7 +35,6 @@ KASAN_SANITIZE_sev-es.o					:= n
 KCSAN_SANITIZE := n
 
 OBJECT_FILES_NON_STANDARD_test_nx.o			:= y
-OBJECT_FILES_NON_STANDARD_paravirt_patch.o		:= y
 
 ifdef CONFIG_FRAME_POINTER
 OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o		:= y
@@ -121,7 +120,7 @@ obj-$(CONFIG_AMD_NB)		+= amd_nb.o
 obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
 
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
-obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 76ad4ce..f810e6f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -616,7 +616,7 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
 		BUG_ON(p->len > MAX_PATCH_LEN);
 		/* prep the buffer with the original instructions */
 		memcpy(insn_buff, p->instr, p->len);
-		used = pv_ops.init.patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
+		used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
 
 		BUG_ON(used > p->len);
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 855ae08..d073026 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -99,8 +99,8 @@ void __init native_pv_lock_init(void)
 		static_branch_disable(&virt_spin_lock_key);
 }
 
-unsigned paravirt_patch_default(u8 type, void *insn_buff,
-				unsigned long addr, unsigned len)
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr,
+			    unsigned int len)
 {
 	/*
 	 * Neat trick to map patch type back to the call within the
@@ -121,19 +121,6 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	return ret;
 }
 
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len,
-			      const char *start, const char *end)
-{
-	unsigned insn_len = end - start;
-
-	/* Alternative instruction is too large for the patch site and we cannot continue: */
-	BUG_ON(insn_len > len || start == NULL);
-
-	memcpy(insn_buff, start, insn_len);
-
-	return insn_len;
-}
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -252,9 +239,6 @@ struct pv_info pv_info = {
 #define PTE_IDENT	__PV_IS_CALLEE_SAVE(_paravirt_ident_64)
 
 struct paravirt_patch_template pv_ops = {
-	/* Init ops. */
-	.init.patch		= native_patch,
-
 	/* Cpu ops. */
 	.cpu.io_delay		= native_io_delay,
 
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
deleted file mode 100644
index 10543dc..0000000
--- a/arch/x86/kernel/paravirt_patch.c
+++ /dev/null
@@ -1,11 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/stringify.h>
-
-#include <asm/paravirt.h>
-#include <asm/asm-offsets.h>
-
-unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
-			  unsigned int len)
-{
-	return paravirt_patch_default(type, insn_buff, addr, len);
-}
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 08dca7b..4f18cd9 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1231,7 +1231,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
-	pv_ops.init.patch = paravirt_patch_default;
 	pv_ops.cpu = xen_cpu_ops;
 	paravirt_iret = xen_iret;
 	xen_init_irq_ops();

[tip: x86/alternatives] x86/paravirt: Switch functions with custom code to ALTERNATIVE

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     fafe5e74229fd3f425e3cbfc68b90e615aa6d62f
Gitweb:        https://git.kernel.org/tip/fafe5e74229fd3f425e3cbfc68b90e615aa6d62f
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:18 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 20:07:01 +01:00

x86/paravirt: Switch functions with custom code to ALTERNATIVE

Instead of using paravirt patching for custom code sequences use
ALTERNATIVE for the functions with custom code replacements.

Instead of patching an ud2 instruction for unpopulated vector entries
into the caller site, use a simple function just calling BUG() as a
replacement.

Simplify the register defines for assembler paravirt calling, as there
isn't much usage left.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-14-jgross@suse.com
---
 arch/x86/entry/entry_64.S             |   2 +-
 arch/x86/include/asm/irqflags.h       |   2 +-
 arch/x86/include/asm/paravirt.h       | 101 ++++++++++++-------------
 arch/x86/include/asm/paravirt_types.h |   6 +-
 arch/x86/kernel/paravirt.c            |  16 +---
 arch/x86/kernel/paravirt_patch.c      |  88 +----------------------
 6 files changed, 58 insertions(+), 157 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 400908d..12e2e3c 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -305,7 +305,7 @@ SYM_CODE_END(ret_from_fork)
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
 	pushq %rax
-	SAVE_FLAGS(CLBR_RAX)
+	SAVE_FLAGS
 	testl $X86_EFLAGS_IF, %eax
 	jz .Lokay_\@
 	ud2
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index a0efbcd..c5ce984 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -111,7 +111,7 @@ static __always_inline unsigned long arch_local_irq_save(void)
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(x)		pushfq; popq %rax
+#define SAVE_FLAGS		pushfq; popq %rax
 #endif
 
 #define INTERRUPT_RETURN	jmp native_iret
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 913acf7..43992e5 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -135,7 +135,9 @@ static inline void write_cr0(unsigned long x)
 
 static inline unsigned long read_cr2(void)
 {
-	return PVOP_CALLEE0(unsigned long, mmu.read_cr2);
+	return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
+				"mov %%cr2, %%rax;",
+				ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void write_cr2(unsigned long x)
@@ -145,12 +147,14 @@ static inline void write_cr2(unsigned long x)
 
 static inline unsigned long __read_cr3(void)
 {
-	return PVOP_CALL0(unsigned long, mmu.read_cr3);
+	return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3,
+			      "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void write_cr3(unsigned long x)
 {
-	PVOP_VCALL1(mmu.write_cr3, x);
+	PVOP_ALT_VCALL1(mmu.write_cr3, x,
+			"mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void __write_cr4(unsigned long x)
@@ -170,7 +174,7 @@ static inline void halt(void)
 
 static inline void wbinvd(void)
 {
-	PVOP_VCALL0(cpu.wbinvd);
+	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline u64 paravirt_read_msr(unsigned msr)
@@ -384,22 +388,28 @@ static inline void paravirt_release_p4d(unsigned long pfn)
 
 static inline pte_t __pte(pteval_t val)
 {
-	return (pte_t) { PVOP_CALLEE1(pteval_t, mmu.make_pte, val) };
+	return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pteval_t pte_val(pte_t pte)
 {
-	return PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
+	return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline pgd_t __pgd(pgdval_t val)
 {
-	return (pgd_t) { PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val) };
+	return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pgdval_t pgd_val(pgd_t pgd)
 {
-	return PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
+	return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -432,12 +442,15 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 static inline pmd_t __pmd(pmdval_t val)
 {
-	return (pmd_t) { PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val) };
+	return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pmdval_t pmd_val(pmd_t pmd)
 {
-	return PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
+	return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -449,14 +462,16 @@ static inline pud_t __pud(pudval_t val)
 {
 	pudval_t ret;
 
-	ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
+	ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val,
+			       "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 
 	return (pud_t) { ret };
 }
 
 static inline pudval_t pud_val(pud_t pud)
 {
-	return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
+	return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -475,14 +490,17 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 
 static inline p4d_t __p4d(p4dval_t val)
 {
-	p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val);
+	p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
+					"mov %%rdi, %%rax",
+					ALT_NOT(X86_FEATURE_XENPV));
 
 	return (p4d_t) { ret };
 }
 
 static inline p4dval_t p4d_val(p4d_t p4d)
 {
-	return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d);
+	return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
@@ -569,7 +587,9 @@ static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
 
 static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
 {
-	PVOP_VCALLEE1(lock.queued_spin_unlock, lock);
+	PVOP_ALT_VCALLEE1(lock.queued_spin_unlock, lock,
+			  "movb $0, (%%" _ASM_ARG1 ");",
+			  ALT_NOT(X86_FEATURE_PVUNLOCK));
 }
 
 static __always_inline void pv_wait(u8 *ptr, u8 val)
@@ -584,7 +604,9 @@ static __always_inline void pv_kick(int cpu)
 
 static __always_inline bool pv_vcpu_is_preempted(long cpu)
 {
-	return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu);
+	return PVOP_ALT_CALLEE1(bool, lock.vcpu_is_preempted, cpu,
+				"xor %%" _ASM_AX ", %%" _ASM_AX ";",
+				ALT_NOT(X86_FEATURE_VCPUPREEMPT));
 }
 
 void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
@@ -658,17 +680,18 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 #ifdef CONFIG_PARAVIRT_XXL
 static inline notrace unsigned long arch_local_save_flags(void)
 {
-	return PVOP_CALLEE0(unsigned long, irq.save_fl);
+	return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
+				ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace void arch_local_irq_disable(void)
 {
-	PVOP_VCALLEE0(irq.irq_disable);
+	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace void arch_local_irq_enable(void)
 {
-	PVOP_VCALLEE0(irq.irq_enable);
+	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace unsigned long arch_local_irq_save(void)
@@ -713,35 +736,9 @@ extern void default_banner(void);
 	.popsection
 
 
-#define COND_PUSH(set, mask, reg)			\
-	.if ((~(set)) & mask); push %reg; .endif
-#define COND_POP(set, mask, reg)			\
-	.if ((~(set)) & mask); pop %reg; .endif
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
 
-#define PV_SAVE_REGS(set)			\
-	COND_PUSH(set, CLBR_RAX, rax);		\
-	COND_PUSH(set, CLBR_RCX, rcx);		\
-	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, CLBR_R9, r9);		\
-	COND_PUSH(set, CLBR_R10, r10);		\
-	COND_PUSH(set, CLBR_R11, r11)
-#define PV_RESTORE_REGS(set)			\
-	COND_POP(set, CLBR_R11, r11);		\
-	COND_POP(set, CLBR_R10, r10);		\
-	COND_POP(set, CLBR_R9, r9);		\
-	COND_POP(set, CLBR_R8, r8);		\
-	COND_POP(set, CLBR_RDI, rdi);		\
-	COND_POP(set, CLBR_RSI, rsi);		\
-	COND_POP(set, CLBR_RDX, rdx);		\
-	COND_POP(set, CLBR_RCX, rcx);		\
-	COND_POP(set, CLBR_RAX, rax)
-
 #define PARA_PATCH(off)		((off) / 8)
 #define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
@@ -752,12 +749,14 @@ extern void default_banner(void);
 		X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
 
 #ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(clobbers)                                        \
-	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),			    \
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
-		  ANNOTATE_RETPOLINE_SAFE;			    \
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);	    \
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+.macro PARA_IRQ_save_fl
+	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),
+		  ANNOTATE_RETPOLINE_SAFE;
+		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);)
+.endm
+
+#define SAVE_FLAGS	ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \
+				    ALT_NOT(X86_FEATURE_XENPV)
 #endif
 #endif /* CONFIG_PARAVIRT_XXL */
 #endif	/* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0ed9762..588ff14 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -3,7 +3,6 @@
 #define _ASM_X86_PARAVIRT_TYPES_H
 
 /* Bitmask of what can be clobbered: usually at least eax. */
-#define CLBR_NONE 0
 #define CLBR_EAX  (1 << 0)
 #define CLBR_ECX  (1 << 1)
 #define CLBR_EDX  (1 << 2)
@@ -15,7 +14,6 @@
 
 #define CLBR_ARG_REGS	(CLBR_EAX | CLBR_EDX | CLBR_ECX)
 #define CLBR_RET_REG	(CLBR_EAX | CLBR_EDX)
-#define CLBR_SCRATCH	(0)
 #else
 #define CLBR_RAX  CLBR_EAX
 #define CLBR_RCX  CLBR_ECX
@@ -32,12 +30,9 @@
 #define CLBR_ARG_REGS	(CLBR_RDI | CLBR_RSI | CLBR_RDX | \
 			 CLBR_RCX | CLBR_R8 | CLBR_R9)
 #define CLBR_RET_REG	(CLBR_RAX)
-#define CLBR_SCRATCH	(CLBR_R10 | CLBR_R11)
 
 #endif /* X86_64 */
 
-#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
-
 #ifndef __ASSEMBLY__
 
 #include <asm/desc_defs.h>
@@ -322,7 +317,6 @@ extern void (*paravirt_iret)(void);
 /* Simple instruction patching code. */
 #define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
 
-unsigned paravirt_patch_ident_64(void *insn_buff, unsigned len);
 unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned long addr, unsigned len);
 unsigned paravirt_patch_insns(void *insn_buff, unsigned len, const char *start, const char *end);
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9b0f568..855ae08 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -53,7 +53,10 @@ void __init default_banner(void)
 }
 
 /* Undefined instruction for dealing with missing ops pointers. */
-static const unsigned char ud2a[] = { 0x0f, 0x0b };
+static void paravirt_BUG(void)
+{
+	BUG();
+}
 
 struct branch {
 	unsigned char opcode;
@@ -107,17 +110,10 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	unsigned ret;
 
 	if (opfunc == NULL)
-		/* If there's no function, patch it with a ud2a (BUG) */
-		ret = paravirt_patch_insns(insn_buff, len, ud2a, ud2a+sizeof(ud2a));
+		/* If there's no function, patch it with paravirt_BUG() */
+		ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len);
 	else if (opfunc == _paravirt_nop)
 		ret = 0;
-
-#ifdef CONFIG_PARAVIRT_XXL
-	/* identity functions just return their single argument */
-	else if (opfunc == _paravirt_ident_64)
-		ret = paravirt_patch_ident_64(insn_buff, len);
-
-#endif
 	else
 		/* Otherwise call the function. */
 		ret = paravirt_patch_call(insn_buff, opfunc, addr, len);
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index abd27ec..10543dc 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -4,96 +4,8 @@
 #include <asm/paravirt.h>
 #include <asm/asm-offsets.h>
 
-#define PSTART(d, m)							\
-	patch_data_##d.m
-
-#define PEND(d, m)							\
-	(PSTART(d, m) + sizeof(patch_data_##d.m))
-
-#define PATCH(d, m, insn_buff, len)						\
-	paravirt_patch_insns(insn_buff, len, PSTART(d, m), PEND(d, m))
-
-#define PATCH_CASE(ops, m, data, insn_buff, len)				\
-	case PARAVIRT_PATCH(ops.m):					\
-		return PATCH(data, ops##_##m, insn_buff, len)
-
-#ifdef CONFIG_PARAVIRT_XXL
-struct patch_xxl {
-	const unsigned char	irq_irq_disable[1];
-	const unsigned char	irq_irq_enable[1];
-	const unsigned char	irq_save_fl[2];
-	const unsigned char	mmu_read_cr2[3];
-	const unsigned char	mmu_read_cr3[3];
-	const unsigned char	mmu_write_cr3[3];
-	const unsigned char	cpu_wbinvd[2];
-	const unsigned char	mov64[3];
-};
-
-static const struct patch_xxl patch_data_xxl = {
-	.irq_irq_disable	= { 0xfa },		// cli
-	.irq_irq_enable		= { 0xfb },		// sti
-	.irq_save_fl		= { 0x9c, 0x58 },	// pushf; pop %[re]ax
-	.mmu_read_cr2		= { 0x0f, 0x20, 0xd0 },	// mov %cr2, %[re]ax
-	.mmu_read_cr3		= { 0x0f, 0x20, 0xd8 },	// mov %cr3, %[re]ax
-	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
-	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
-	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
-};
-
-unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len)
-{
-	return PATCH(xxl, mov64, insn_buff, len);
-}
-# endif /* CONFIG_PARAVIRT_XXL */
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-struct patch_lock {
-	unsigned char queued_spin_unlock[3];
-	unsigned char vcpu_is_preempted[2];
-};
-
-static const struct patch_lock patch_data_lock = {
-	.vcpu_is_preempted	= { 0x31, 0xc0 },	// xor %eax, %eax
-
-# ifdef CONFIG_X86_64
-	.queued_spin_unlock	= { 0xc6, 0x07, 0x00 },	// movb $0, (%rdi)
-# else
-	.queued_spin_unlock	= { 0xc6, 0x00, 0x00 },	// movb $0, (%eax)
-# endif
-};
-#endif /* CONFIG_PARAVIRT_SPINLOCKS */
-
 unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 			  unsigned int len)
 {
-	switch (type) {
-
-#ifdef CONFIG_PARAVIRT_XXL
-	PATCH_CASE(irq, save_fl, xxl, insn_buff, len);
-	PATCH_CASE(irq, irq_enable, xxl, insn_buff, len);
-	PATCH_CASE(irq, irq_disable, xxl, insn_buff, len);
-
-	PATCH_CASE(mmu, read_cr2, xxl, insn_buff, len);
-	PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
-	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
-
-	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
-#endif
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-	case PARAVIRT_PATCH(lock.queued_spin_unlock):
-		if (pv_is_native_spin_unlock())
-			return PATCH(lock, queued_spin_unlock, insn_buff, len);
-		break;
-
-	case PARAVIRT_PATCH(lock.vcpu_is_preempted):
-		if (pv_is_native_vcpu_is_preempted())
-			return PATCH(lock, vcpu_is_preempted, insn_buff, len);
-		break;
-#endif
-	default:
-		break;
-	}
-
 	return paravirt_patch_default(type, insn_buff, addr, len);
 }

[tip: x86/alternatives] x86/paravirt: Switch iret pvops to ALTERNATIVE

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     ae755b5a45482b5de4d96d6f35823076af77445e
Gitweb:        https://git.kernel.org/tip/ae755b5a45482b5de4d96d6f35823076af77445e
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:16 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 19:58:54 +01:00

x86/paravirt: Switch iret pvops to ALTERNATIVE

The iret paravirt op is rather special as it is using a jmp instead
of a call instruction. Switch it to ALTERNATIVE.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-12-jgross@suse.com
---
 arch/x86/include/asm/paravirt.h       |  6 +++---
 arch/x86/include/asm/paravirt_types.h |  5 +----
 arch/x86/kernel/asm-offsets.c         |  5 +-----
 arch/x86/kernel/paravirt.c            | 26 ++------------------------
 arch/x86/xen/enlighten_pv.c           |  3 +--
 5 files changed, 7 insertions(+), 38 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a780509..913acf7 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -747,9 +747,9 @@ extern void default_banner(void);
 #define PARA_INDIRECT(addr)	*addr(%rip)
 
 #define INTERRUPT_RETURN						\
-	PARA_SITE(PARA_PATCH(PV_CPU_iret),				\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
+	ANNOTATE_RETPOLINE_SAFE;					\
+	ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);",		\
+		X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
 
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(clobbers)                                        \
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 45bd216..0afdac8 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -151,10 +151,6 @@ struct pv_cpu_ops {
 
 	u64 (*read_pmc)(int counter);
 
-	/* Normal iret.  Jump to this with the standard iret stack
-	   frame set up. */
-	void (*iret)(void);
-
 	void (*start_context_switch)(struct task_struct *prev);
 	void (*end_context_switch)(struct task_struct *next);
 #endif
@@ -294,6 +290,7 @@ struct paravirt_patch_template {
 
 extern struct pv_info pv_info;
 extern struct paravirt_patch_template pv_ops;
+extern void (*paravirt_iret)(void);
 
 #define PARAVIRT_PATCH(x)					\
 	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 7365080..ecd3fd6 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -61,11 +61,6 @@ static void __used common(void)
 	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
 #endif
 
-#ifdef CONFIG_PARAVIRT_XXL
-	BLANK();
-	OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
-#endif
-
 #ifdef CONFIG_XEN
 	BLANK();
 	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index a688edf..9b0f568 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -86,25 +86,6 @@ u64 notrace _paravirt_ident_64(u64 x)
 {
 	return x;
 }
-
-static unsigned paravirt_patch_jmp(void *insn_buff, const void *target,
-				   unsigned long addr, unsigned len)
-{
-	struct branch *b = insn_buff;
-	unsigned long delta = (unsigned long)target - (addr+5);
-
-	if (len < 5) {
-#ifdef CONFIG_RETPOLINE
-		WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
-#endif
-		return len;	/* call too long for patch site */
-	}
-
-	b->opcode = 0xe9;	/* jmp */
-	b->delta = delta;
-
-	return 5;
-}
 #endif
 
 DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
@@ -136,9 +117,6 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	else if (opfunc == _paravirt_ident_64)
 		ret = paravirt_patch_ident_64(insn_buff, len);
 
-	else if (type == PARAVIRT_PATCH(cpu.iret))
-		/* If operation requires a jmp, then jmp */
-		ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
 #endif
 	else
 		/* Otherwise call the function. */
@@ -313,8 +291,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.load_sp0		= native_load_sp0,
 
-	.cpu.iret		= native_iret,
-
 #ifdef CONFIG_X86_IOPL_IOPERM
 	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
 	.cpu.update_io_bitmap		= native_tss_update_io_bitmap,
@@ -419,6 +395,8 @@ struct paravirt_patch_template pv_ops = {
 NOKPROBE_SYMBOL(native_get_debugreg);
 NOKPROBE_SYMBOL(native_set_debugreg);
 NOKPROBE_SYMBOL(native_load_idt);
+
+void (*paravirt_iret)(void) = native_iret;
 #endif
 
 EXPORT_SYMBOL(pv_ops);
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index dc0a337..08dca7b 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1070,8 +1070,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 
 	.read_pmc = xen_read_pmc,
 
-	.iret = xen_iret,
-
 	.load_tr_desc = paravirt_nop,
 	.set_ldt = xen_set_ldt,
 	.load_gdt = xen_load_gdt,
@@ -1235,6 +1233,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	pv_info = xen_info;
 	pv_ops.init.patch = paravirt_patch_default;
 	pv_ops.cpu = xen_cpu_ops;
+	paravirt_iret = xen_iret;
 	xen_init_irq_ops();
 
 	/*

[tip: x86/alternatives] x86/paravirt: Add new PVOP_ALT* macros to support pvops in ALTERNATIVEs

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     00aa3193ab7a04b25bb8c68e377815696eb5bf56
Gitweb:        https://git.kernel.org/tip/00aa3193ab7a04b25bb8c68e377815696eb5bf56
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:17 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 20:05:44 +01:00

x86/paravirt: Add new PVOP_ALT* macros to support pvops in ALTERNATIVEs

Instead of using paravirt patching for custom code sequences add
support for using ALTERNATIVE handling combined with paravirt call
patching.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-13-jgross@suse.com
---
 arch/x86/include/asm/paravirt_types.h | 49 +++++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0afdac8..0ed9762 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -477,44 +477,91 @@ int paravirt_disable_iospace(void);
 		ret;							\
 	})
 
+#define ____PVOP_ALT_CALL(ret, op, alt, cond, clbr, call_clbr,		\
+			  extra_clbr, ...)				\
+	({								\
+		PVOP_CALL_ARGS;						\
+		PVOP_TEST_NULL(op);					\
+		asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL),	\
+					 alt, cond)			\
+			     : call_clbr, ASM_CALL_CONSTRAINT		\
+			     : paravirt_type(op),			\
+			       paravirt_clobber(clbr),			\
+			       ##__VA_ARGS__				\
+			     : "memory", "cc" extra_clbr);		\
+		ret;							\
+	})
+
 #define __PVOP_CALL(rettype, op, ...)					\
 	____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY,		\
 		      PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__)
 
+#define __PVOP_ALT_CALL(rettype, op, alt, cond, ...)			\
+	____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op, alt, cond, CLBR_ANY,\
+			  PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS,		\
+			  ##__VA_ARGS__)
+
 #define __PVOP_CALLEESAVE(rettype, op, ...)				\
 	____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG,	\
 		      PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
 
+#define __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, ...)		\
+	____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op.func, alt, cond,	\
+			  CLBR_RET_REG, PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
+
+
 #define __PVOP_VCALL(op, ...)						\
 	(void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS,	\
 		       VEXTRA_CLOBBERS, ##__VA_ARGS__)
 
+#define __PVOP_ALT_VCALL(op, alt, cond, ...)				\
+	(void)____PVOP_ALT_CALL(, op, alt, cond, CLBR_ANY,		\
+				PVOP_VCALL_CLOBBERS, VEXTRA_CLOBBERS,	\
+				##__VA_ARGS__)
+
 #define __PVOP_VCALLEESAVE(op, ...)					\
 	(void)____PVOP_CALL(, op.func, CLBR_RET_REG,			\
-		      PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
+			    PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
+#define __PVOP_ALT_VCALLEESAVE(op, alt, cond, ...)			\
+	(void)____PVOP_ALT_CALL(, op.func, alt, cond, CLBR_RET_REG,	\
+				PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 
 #define PVOP_CALL0(rettype, op)						\
 	__PVOP_CALL(rettype, op)
 #define PVOP_VCALL0(op)							\
 	__PVOP_VCALL(op)
+#define PVOP_ALT_CALL0(rettype, op, alt, cond)				\
+	__PVOP_ALT_CALL(rettype, op, alt, cond)
+#define PVOP_ALT_VCALL0(op, alt, cond)					\
+	__PVOP_ALT_VCALL(op, alt, cond)
 
 #define PVOP_CALLEE0(rettype, op)					\
 	__PVOP_CALLEESAVE(rettype, op)
 #define PVOP_VCALLEE0(op)						\
 	__PVOP_VCALLEESAVE(op)
+#define PVOP_ALT_CALLEE0(rettype, op, alt, cond)			\
+	__PVOP_ALT_CALLEESAVE(rettype, op, alt, cond)
+#define PVOP_ALT_VCALLEE0(op, alt, cond)				\
+	__PVOP_ALT_VCALLEESAVE(op, alt, cond)
 
 
 #define PVOP_CALL1(rettype, op, arg1)					\
 	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALL1(op, arg1)						\
 	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALL1(op, arg1, alt, cond)				\
+	__PVOP_ALT_VCALL(op, alt, cond, PVOP_CALL_ARG1(arg1))
 
 #define PVOP_CALLEE1(rettype, op, arg1)					\
 	__PVOP_CALLEESAVE(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALLEE1(op, arg1)						\
 	__PVOP_VCALLEESAVE(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_CALLEE1(rettype, op, arg1, alt, cond)			\
+	__PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALLEE1(op, arg1, alt, cond)				\
+	__PVOP_ALT_VCALLEESAVE(op, alt, cond, PVOP_CALL_ARG1(arg1))
 
 
 #define PVOP_CALL2(rettype, op, arg1, arg2)				\

[tip: x86/alternatives] x86/paravirt: Simplify paravirt macros

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     0b8d366a942fd48a83dfa728e9f8a8d8b20e735f
Gitweb:        https://git.kernel.org/tip/0b8d366a942fd48a83dfa728e9f8a8d8b20e735f
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:15 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 19:52:52 +01:00

x86/paravirt: Simplify paravirt macros

The central pvops call macros ____PVOP_CALL() and ____PVOP_VCALL() are
looking very similar now.

The main differences are using PVOP_VCALL_ARGS or PVOP_CALL_ARGS, which
are identical, and the return value handling.

So drop PVOP_VCALL_ARGS and instead of ____PVOP_VCALL() just use
(void)____PVOP_CALL(long, ...).

Note that it isn't easily possible to just redefine ____PVOP_VCALL()
to use ____PVOP_CALL() instead, as this would require further hiding of
commas in macro parameters.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-11-jgross@suse.com
---
 arch/x86/include/asm/paravirt_types.h | 41 +++++++-------------------
 1 file changed, 12 insertions(+), 29 deletions(-)

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 42f9eef..45bd216 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -408,11 +408,9 @@ int paravirt_disable_iospace(void);
  * makes sure the incoming and outgoing types are always correct.
  */
 #ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS							\
+#define PVOP_CALL_ARGS							\
 	unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
 
-#define PVOP_CALL_ARGS			PVOP_VCALL_ARGS
-
 #define PVOP_CALL_ARG1(x)		"a" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"d" ((unsigned long)(x))
 #define PVOP_CALL_ARG3(x)		"c" ((unsigned long)(x))
@@ -428,12 +426,10 @@ int paravirt_disable_iospace(void);
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
 /* [re]ax isn't an arg, but the return val */
-#define PVOP_VCALL_ARGS						\
+#define PVOP_CALL_ARGS						\
 	unsigned long __edi = __edi, __esi = __esi,		\
 		__edx = __edx, __ecx = __ecx, __eax = __eax;
 
-#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS
-
 #define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"S" ((unsigned long)(x))
 #define PVOP_CALL_ARG3(x)		"d" ((unsigned long)(x))
@@ -458,59 +454,46 @@ int paravirt_disable_iospace(void);
 #define PVOP_TEST_NULL(op)	((void)pv_ops.op)
 #endif
 
-#define PVOP_RETMASK(rettype)						\
+#define PVOP_RETVAL(rettype)						\
 	({	unsigned long __mask = ~0UL;				\
+		BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long));	\
 		switch (sizeof(rettype)) {				\
 		case 1: __mask =       0xffUL; break;			\
 		case 2: __mask =     0xffffUL; break;			\
 		case 4: __mask = 0xffffffffUL; break;			\
 		default: break;						\
 		}							\
-		__mask;							\
+		__mask & __eax;						\
 	})
 
 
-#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, ...)	\
+#define ____PVOP_CALL(ret, op, clbr, call_clbr, extra_clbr, ...)	\
 	({								\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long));	\
 		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
 			     : paravirt_type(op),			\
 			       paravirt_clobber(clbr),			\
 			       ##__VA_ARGS__				\
 			     : "memory", "cc" extra_clbr);		\
-		(rettype)(__eax & PVOP_RETMASK(rettype));		\
+		ret;							\
 	})
 
 #define __PVOP_CALL(rettype, op, ...)					\
-	____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS,	\
-		      EXTRA_CLOBBERS, ##__VA_ARGS__)
+	____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY,		\
+		      PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__)
 
 #define __PVOP_CALLEESAVE(rettype, op, ...)				\
-	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
+	____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG,	\
 		      PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
 
-
-#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, ...)		\
-	({								\
-		PVOP_VCALL_ARGS;					\
-		PVOP_TEST_NULL(op);					\
-		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
-			     : call_clbr, ASM_CALL_CONSTRAINT		\
-			     : paravirt_type(op),			\
-			       paravirt_clobber(clbr),			\
-			       ##__VA_ARGS__				\
-			     : "memory", "cc" extra_clbr);		\
-	})
-
 #define __PVOP_VCALL(op, ...)						\
-	____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS,		\
+	(void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS,	\
 		       VEXTRA_CLOBBERS, ##__VA_ARGS__)
 
 #define __PVOP_VCALLEESAVE(op, ...)					\
-	____PVOP_VCALL(op.func, CLBR_RET_REG,				\
+	(void)____PVOP_CALL(, op.func, CLBR_RET_REG,			\
 		      PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 

[tip: x86/alternatives] x86/paravirt: Add new features for paravirt patching

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     4e6292114c741221479046515b1aa8145cf1e3f6
Gitweb:        https://git.kernel.org/tip/4e6292114c741221479046515b1aa8145cf1e3f6
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:13 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 19:51:49 +01:00

x86/paravirt: Add new features for paravirt patching

For being able to switch paravirt patching from special cased custom
code sequences to ALTERNATIVE handling some X86_FEATURE_* are needed
as new features. This enables to have the standard indirect pv call
as the default code and to patch that with the non-Xen custom code
sequence via ALTERNATIVE patching later.

Make sure paravirt patching is performed before alternatives patching.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-9-jgross@suse.com
---
 arch/x86/include/asm/cpufeatures.h   |  2 ++-
 arch/x86/include/asm/paravirt.h      | 10 +++++++++-
 arch/x86/kernel/alternative.c        | 30 +++++++++++++++++++++++++--
 arch/x86/kernel/paravirt-spinlocks.c |  9 ++++++++-
 4 files changed, 49 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index cc96e26..b440c95 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -236,6 +236,8 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_PVUNLOCK		( 8*32+20) /* "" PV unlock function */
+#define X86_FEATURE_VCPUPREEMPT		( 8*32+21) /* "" PV vcpu_is_preempted function */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 6408fd0..def450f 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -45,6 +45,10 @@ static inline u64 paravirt_steal_clock(int cpu)
 	return static_call(pv_steal_clock)(cpu);
 }
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init paravirt_set_cap(void);
+#endif
+
 /* The paravirtualized I/O functions */
 static inline void slow_down_io(void)
 {
@@ -809,5 +813,11 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 }
 #endif
+
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
+static inline void paravirt_set_cap(void)
+{
+}
+#endif
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 133b549..76ad4ce 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -28,6 +28,7 @@
 #include <asm/insn.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
+#include <asm/paravirt.h>
 
 int __read_mostly alternatives_patched;
 
@@ -733,6 +734,33 @@ void __init alternative_instructions(void)
 	 * patching.
 	 */
 
+	/*
+	 * Paravirt patching and alternative patching can be combined to
+	 * replace a function call with a short direct code sequence (e.g.
+	 * by setting a constant return value instead of doing that in an
+	 * external function).
+	 * In order to make this work the following sequence is required:
+	 * 1. set (artificial) features depending on used paravirt
+	 *    functions which can later influence alternative patching
+	 * 2. apply paravirt patching (generally replacing an indirect
+	 *    function call with a direct one)
+	 * 3. apply alternative patching (e.g. replacing a direct function
+	 *    call with a custom code sequence)
+	 * Doing paravirt patching after alternative patching would clobber
+	 * the optimization of the custom code with a function call again.
+	 */
+	paravirt_set_cap();
+
+	/*
+	 * First patch paravirt functions, such that we overwrite the indirect
+	 * call with the direct call.
+	 */
+	apply_paravirt(__parainstructions, __parainstructions_end);
+
+	/*
+	 * Then patch alternatives, such that those paravirt calls that are in
+	 * alternatives can be overwritten by their immediate fragments.
+	 */
 	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
 #ifdef CONFIG_SMP
@@ -751,8 +779,6 @@ void __init alternative_instructions(void)
 	}
 #endif
 
-	apply_paravirt(__parainstructions, __parainstructions_end);
-
 	restart_nmi();
 	alternatives_patched = 1;
 }
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 4f75d0c..9e1ea99 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -32,3 +32,12 @@ bool pv_is_native_vcpu_is_preempted(void)
 	return pv_ops.lock.vcpu_is_preempted.func ==
 		__raw_callee_save___native_vcpu_is_preempted;
 }
+
+void __init paravirt_set_cap(void)
+{
+	if (!pv_is_native_spin_unlock())
+		setup_force_cpu_cap(X86_FEATURE_PVUNLOCK);
+
+	if (!pv_is_native_vcpu_is_preempted())
+		setup_force_cpu_cap(X86_FEATURE_VCPUPREEMPT);
+}

[tip: x86/alternatives] x86/paravirt: Remove no longer needed 32-bit pvops cruft

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     33634e42e38be61f320183dfc264b9caba292d4e
Gitweb:        https://git.kernel.org/tip/33634e42e38be61f320183dfc264b9caba292d4e
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:14 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 19:51:55 +01:00

x86/paravirt: Remove no longer needed 32-bit pvops cruft

PVOP_VCALL4() is only used for Xen PV, while PVOP_CALL4() isn't used
at all. Keep PVOP_CALL4() for 64 bits due to symmetry reasons.

This allows to remove the 32-bit definitions of those macros leading
to a substantial simplification of the paravirt macros, as those were
the only ones needing non-empty "pre" and "post" parameters.

PVOP_CALLEE2() and PVOP_VCALLEE2() are used nowhere, so remove them.

Another no longer needed case is special handling of return types
larger than unsigned long. Replace that with a BUILD_BUG_ON().

DISABLE_INTERRUPTS() is used in 32-bit code only, so it can just be
replaced by cli.

INTERRUPT_RETURN in 32-bit code can be replaced by iret.

ENABLE_INTERRUPTS is used nowhere, so it can be removed.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-10-jgross@suse.com
---
 arch/x86/entry/entry_32.S             |   4 +-
 arch/x86/include/asm/irqflags.h       |   5 +-
 arch/x86/include/asm/paravirt.h       |  35 +--------
 arch/x86/include/asm/paravirt_types.h | 112 +++++++------------------
 arch/x86/kernel/asm-offsets.c         |   2 +-
 5 files changed, 35 insertions(+), 123 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 4e079f2..96f0848 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -430,7 +430,7 @@
 	 * will soon execute iret and the tracer was already set to
 	 * the irqstate after the IRET:
 	 */
-	DISABLE_INTERRUPTS(CLBR_ANY)
+	cli
 	lss	(%esp), %esp			/* switch to espfix segment */
 .Lend_\@:
 #endif /* CONFIG_X86_ESPFIX32 */
@@ -1077,7 +1077,7 @@ restore_all_switch_stack:
 	 * when returning from IPI handler and when returning from
 	 * scheduler to user-space.
 	 */
-	INTERRUPT_RETURN
+	iret
 
 .section .fixup, "ax"
 SYM_CODE_START(asm_iret_error)
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 144d70e..a0efbcd 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -109,9 +109,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 }
 #else
 
-#define ENABLE_INTERRUPTS(x)	sti
-#define DISABLE_INTERRUPTS(x)	cli
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(x)		pushfq; popq %rax
@@ -119,8 +116,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 
 #define INTERRUPT_RETURN	jmp native_iret
 
-#else
-#define INTERRUPT_RETURN		iret
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index def450f..a780509 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -719,6 +719,7 @@ extern void default_banner(void);
 	.if ((~(set)) & mask); pop %reg; .endif
 
 #ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT_XXL
 
 #define PV_SAVE_REGS(set)			\
 	COND_PUSH(set, CLBR_RAX, rax);		\
@@ -744,46 +745,12 @@ extern void default_banner(void);
 #define PARA_PATCH(off)		((off) / 8)
 #define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
-#else
-#define PV_SAVE_REGS(set)			\
-	COND_PUSH(set, CLBR_EAX, eax);		\
-	COND_PUSH(set, CLBR_EDI, edi);		\
-	COND_PUSH(set, CLBR_ECX, ecx);		\
-	COND_PUSH(set, CLBR_EDX, edx)
-#define PV_RESTORE_REGS(set)			\
-	COND_POP(set, CLBR_EDX, edx);		\
-	COND_POP(set, CLBR_ECX, ecx);		\
-	COND_POP(set, CLBR_EDI, edi);		\
-	COND_POP(set, CLBR_EAX, eax)
-
-#define PARA_PATCH(off)		((off) / 4)
-#define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .long, 4)
-#define PARA_INDIRECT(addr)	*%cs:addr
-#endif
 
-#ifdef CONFIG_PARAVIRT_XXL
 #define INTERRUPT_RETURN						\
 	PARA_SITE(PARA_PATCH(PV_CPU_iret),				\
 		  ANNOTATE_RETPOLINE_SAFE;				\
 		  jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
 
-#define DISABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable),			\
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable);	\
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-
-#define ENABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable),			\
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable);		\
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-#endif
-
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(clobbers)                                        \
 	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),			    \
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 1fff349..42f9eef 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -470,55 +470,34 @@ int paravirt_disable_iospace(void);
 	})
 
 
-#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr,		\
-		      pre, post, ...)					\
+#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, ...)	\
 	({								\
-		rettype __ret;						\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		/* This is 32-bit specific, but is okay in 64-bit */	\
-		/* since this condition will never hold */		\
-		if (sizeof(rettype) > sizeof(unsigned long)) {		\
-			asm volatile(pre				\
-				     paravirt_alt(PARAVIRT_CALL)	\
-				     post				\
-				     : call_clbr, ASM_CALL_CONSTRAINT	\
-				     : paravirt_type(op),		\
-				       paravirt_clobber(clbr),		\
-				       ##__VA_ARGS__			\
-				     : "memory", "cc" extra_clbr);	\
-			__ret = (rettype)((((u64)__edx) << 32) | __eax); \
-		} else {						\
-			asm volatile(pre				\
-				     paravirt_alt(PARAVIRT_CALL)	\
-				     post				\
-				     : call_clbr, ASM_CALL_CONSTRAINT	\
-				     : paravirt_type(op),		\
-				       paravirt_clobber(clbr),		\
-				       ##__VA_ARGS__			\
-				     : "memory", "cc" extra_clbr);	\
-			__ret = (rettype)(__eax & PVOP_RETMASK(rettype));	\
-		}							\
-		__ret;							\
+		BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long));	\
+		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
+			     : call_clbr, ASM_CALL_CONSTRAINT		\
+			     : paravirt_type(op),			\
+			       paravirt_clobber(clbr),			\
+			       ##__VA_ARGS__				\
+			     : "memory", "cc" extra_clbr);		\
+		(rettype)(__eax & PVOP_RETMASK(rettype));		\
 	})
 
-#define __PVOP_CALL(rettype, op, pre, post, ...)			\
+#define __PVOP_CALL(rettype, op, ...)					\
 	____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS,	\
-		      EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
+		      EXTRA_CLOBBERS, ##__VA_ARGS__)
 
-#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...)			\
+#define __PVOP_CALLEESAVE(rettype, op, ...)				\
 	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
-		      PVOP_CALLEE_CLOBBERS, ,				\
-		      pre, post, ##__VA_ARGS__)
+		      PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 
-#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...)	\
+#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, ...)		\
 	({								\
 		PVOP_VCALL_ARGS;					\
 		PVOP_TEST_NULL(op);					\
-		asm volatile(pre					\
-			     paravirt_alt(PARAVIRT_CALL)		\
-			     post					\
+		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
 			     : paravirt_type(op),			\
 			       paravirt_clobber(clbr),			\
@@ -526,84 +505,57 @@ int paravirt_disable_iospace(void);
 			     : "memory", "cc" extra_clbr);		\
 	})
 
-#define __PVOP_VCALL(op, pre, post, ...)				\
+#define __PVOP_VCALL(op, ...)						\
 	____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS,		\
-		       VEXTRA_CLOBBERS,					\
-		       pre, post, ##__VA_ARGS__)
+		       VEXTRA_CLOBBERS, ##__VA_ARGS__)
 
-#define __PVOP_VCALLEESAVE(op, pre, post, ...)				\
+#define __PVOP_VCALLEESAVE(op, ...)					\
 	____PVOP_VCALL(op.func, CLBR_RET_REG,				\
-		      PVOP_VCALLEE_CLOBBERS, ,				\
-		      pre, post, ##__VA_ARGS__)
+		      PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 
 
 #define PVOP_CALL0(rettype, op)						\
-	__PVOP_CALL(rettype, op, "", "")
+	__PVOP_CALL(rettype, op)
 #define PVOP_VCALL0(op)							\
-	__PVOP_VCALL(op, "", "")
+	__PVOP_VCALL(op)
 
 #define PVOP_CALLEE0(rettype, op)					\
-	__PVOP_CALLEESAVE(rettype, op, "", "")
+	__PVOP_CALLEESAVE(rettype, op)
 #define PVOP_VCALLEE0(op)						\
-	__PVOP_VCALLEESAVE(op, "", "")
+	__PVOP_VCALLEESAVE(op)
 
 
 #define PVOP_CALL1(rettype, op, arg1)					\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALL1(op, arg1)						\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1))
 
 #define PVOP_CALLEE1(rettype, op, arg1)					\
-	__PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_CALLEESAVE(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALLEE1(op, arg1)						\
-	__PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_VCALLEESAVE(op, PVOP_CALL_ARG1(arg1))
 
 
 #define PVOP_CALL2(rettype, op, arg1, arg2)				\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),		\
-		    PVOP_CALL_ARG2(arg2))
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
 #define PVOP_VCALL2(op, arg1, arg2)					\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),			\
-		     PVOP_CALL_ARG2(arg2))
-
-#define PVOP_CALLEE2(rettype, op, arg1, arg2)				\
-	__PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1),	\
-			  PVOP_CALL_ARG2(arg2))
-#define PVOP_VCALLEE2(op, arg1, arg2)					\
-	__PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1),		\
-			   PVOP_CALL_ARG2(arg2))
-
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
 
 #define PVOP_CALL3(rettype, op, arg1, arg2, arg3)			\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),		\
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1),			\
 		    PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 #define PVOP_VCALL3(op, arg1, arg2, arg3)				\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),			\
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1),				\
 		     PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 
-/* This is the only difference in x86_64. We can make it much simpler */
-#ifdef CONFIG_X86_32
 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
 	__PVOP_CALL(rettype, op,					\
-		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),		\
-		    PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op,						\
-		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    "0" ((u32)(arg1)), "1" ((u32)(arg2)),		\
-		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
-#else
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
-	__PVOP_CALL(rettype, op, "", "",				\
 		    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),		\
 		    PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op, "", "",					\
-		     PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
 		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-#endif
 
 /* Lazy mode for batching updates / context switch */
 enum paravirt_lazy_mode {
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 60b9f42..7365080 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -63,8 +63,6 @@ static void __used common(void)
 
 #ifdef CONFIG_PARAVIRT_XXL
 	BLANK();
-	OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
-	OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
 	OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
 #endif
 

[tip: x86/alternatives] x86/alternative: Use ALTERNATIVE_TERNARY() in _static_cpu_has()

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     2fe2a2c7a97c9bc32acc79154b75e754280f7867
Gitweb:        https://git.kernel.org/tip/2fe2a2c7a97c9bc32acc79154b75e754280f7867
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:12 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 19:33:43 +01:00

x86/alternative: Use ALTERNATIVE_TERNARY() in _static_cpu_has()

_static_cpu_has() contains a completely open coded version of
ALTERNATIVE_TERNARY(). Replace that with the macro instead.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210311142319.4723-8-jgross@suse.com
---
 arch/x86/include/asm/cpufeature.h | 41 ++++++------------------------
 1 file changed, 9 insertions(+), 32 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1728d4c..16a51e7 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -8,6 +8,7 @@
 
 #include <asm/asm.h>
 #include <linux/bitops.h>
+#include <asm/alternative.h>
 
 enum cpuid_leafs
 {
@@ -175,39 +176,15 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
-		 "2:\n"
-		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
-			 "((5f-4f) - (2b-1b)),0x90\n"
-		 "3:\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 4f - .\n"		/* repl offset */
-		 " .word %P[always]\n"		/* always replace */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 5f - 4f\n"		/* repl len */
-		 " .byte 3b - 2b\n"		/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_replacement,\"ax\"\n"
-		 "4: jmp %l[t_no]\n"
-		 "5:\n"
-		 ".previous\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 0\n"			/* no replacement */
-		 " .word %P[feature]\n"		/* feature bit */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 0\n"			/* repl len */
-		 " .byte 0\n"			/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_aux,\"ax\"\n"
-		 "6:\n"
-		 " testb %[bitnum],%[cap_byte]\n"
-		 " jnz %l[t_yes]\n"
-		 " jmp %l[t_no]\n"
-		 ".previous\n"
+	asm_volatile_goto(
+		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
+		".section .altinstr_aux,\"ax\"\n"
+		"6:\n"
+		" testb %[bitnum],%[cap_byte]\n"
+		" jnz %l[t_yes]\n"
+		" jmp %l[t_no]\n"
+		".previous\n"
 		 : : [feature]  "i" (bit),
-		     [always]   "i" (X86_FEATURE_ALWAYS),
 		     [bitnum]   "i" (1 << (bit & 7)),
 		     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
 		 : : t_yes, t_no);

[tip: x86/alternatives] x86/alternative: Support ALTERNATIVE_TERNARY

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     e208b3c4a9748b2c17aa09ba663b5096ccf82dce
Gitweb:        https://git.kernel.org/tip/e208b3c4a9748b2c17aa09ba663b5096ccf82dce
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:11 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 16:57:31 +01:00

x86/alternative: Support ALTERNATIVE_TERNARY

Add ALTERNATIVE_TERNARY support for replacing an initial instruction
with either of two instructions depending on a feature:

  ALTERNATIVE_TERNARY "default_instr", FEATURE_NR,
                      "feature_on_instr", "feature_off_instr"

which will start with "default_instr" and at patch time will,
depending on FEATURE_NR being set or not, patch that with either
"feature_on_instr" or "feature_off_instr".

 [ bp: Add comment ontop. ]

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-7-jgross@suse.com
---
 arch/x86/include/asm/alternative.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 649e56f..17b3609 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -179,6 +179,11 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	ALTINSTR_REPLACEMENT(newinstr2, 2)				\
 	".popsection\n"
 
+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+	ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
+		      newinstr_yes, feature)
+
 #define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \
 	OLDINSTR_3(oldinsn, 1, 2, 3)						\
 	".pushsection .altinstructions,\"a\"\n"					\
@@ -210,6 +215,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
 #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
 	asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")
 
+#define alternative_ternary(oldinstr, feature, newinstr_yes, newinstr_no) \
+	asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) ::: "memory")
+
 /*
  * Alternative inline assembly with input.
  *
@@ -380,6 +388,11 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	.popsection
 .endm
 
+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+	ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
+	newinstr_yes, feature
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */

[tip: x86/alternatives] x86/alternative: Support not-feature

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     dda7bb76484978316bb412a353789ebc5901de36
Gitweb:        https://git.kernel.org/tip/dda7bb76484978316bb412a353789ebc5901de36
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:10 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 16:44:01 +01:00

x86/alternative: Support not-feature

Add support for alternative patching for the case a feature is not
present on the current CPU. For users of ALTERNATIVE() and friends, an
inverted feature is specified by applying the ALT_NOT() macro to it,
e.g.:

  ALTERNATIVE(old, new, ALT_NOT(feature));

Committer note:

The decision to encode the NOT-bit in the feature bit itself is because
a future change which would make objtool generate such alternative
calls, would keep the code in objtool itself fairly simple.

Also, this allows for the alternative macros to support the NOT feature
without having to change them.

Finally, the u16 cpuid member encoding the X86_FEATURE_ flags is not an
ABI so if more bits are needed, cpuid itself can be enlarged or a flags
field can be added to struct alt_instr after having considered the size
growth in either cases.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210311142319.4723-6-jgross@suse.com
---
 arch/x86/include/asm/alternative.h |  3 +++
 arch/x86/kernel/alternative.c      | 20 +++++++++++++++-----
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 53f295f..649e56f 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -6,6 +6,9 @@
 #include <linux/stringify.h>
 #include <asm/asm.h>
 
+#define ALTINSTR_FLAG_INV	(1 << 15)
+#define ALT_NOT(feat)		((feat) | ALTINSTR_FLAG_INV)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/stddef.h>
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8d778e4..133b549 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -388,21 +388,31 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
+		/* Mask away "NOT" flag bit for feature to test. */
+		u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV;
 
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
 		BUG_ON(a->instrlen > sizeof(insn_buff));
-		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
-		if (!boot_cpu_has(a->cpuid)) {
+		BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32);
+
+		/*
+		 * Patch if either:
+		 * - feature is present
+		 * - feature not present but ALTINSTR_FLAG_INV is set to mean,
+		 *   patch if feature is *NOT* present.
+		 */
+		if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) {
 			if (a->padlen > 1)
 				optimize_nops(a, instr);
 
 			continue;
 		}
 
-		DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
-			a->cpuid >> 5,
-			a->cpuid & 0x1f,
+		DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
+			(a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
+			feature >> 5,
+			feature & 0x1f,
 			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->padlen);
 

[tip: x86/alternatives] x86/paravirt: Switch time pvops functions to use static_call()

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     a0e2bf7cb7006b5a58ee81f4da4fe575875f2781
Gitweb:        https://git.kernel.org/tip/a0e2bf7cb7006b5a58ee81f4da4fe575875f2781
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:09 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 16:17:52 +01:00

x86/paravirt: Switch time pvops functions to use static_call()

The time pvops functions are the only ones left which might be
used in 32-bit mode and which return a 64-bit value.

Switch them to use the static_call() mechanism instead of pvops, as
this allows quite some simplification of the pvops implementation.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-5-jgross@suse.com
---
 arch/arm/include/asm/paravirt.h       | 14 +++++---------
 arch/arm/kernel/paravirt.c            |  9 +++++++--
 arch/arm64/include/asm/paravirt.h     | 14 +++++---------
 arch/arm64/kernel/paravirt.c          | 13 +++++++++----
 arch/x86/Kconfig                      |  1 +-
 arch/x86/include/asm/mshyperv.h       |  2 +-
 arch/x86/include/asm/paravirt.h       | 15 ++++++++++++---
 arch/x86/include/asm/paravirt_types.h |  6 +------
 arch/x86/kernel/cpu/vmware.c          |  5 +++--
 arch/x86/kernel/kvm.c                 |  2 +-
 arch/x86/kernel/kvmclock.c            |  2 +-
 arch/x86/kernel/paravirt.c            | 13 +++++++++----
 arch/x86/kernel/tsc.c                 |  3 ++-
 arch/x86/xen/time.c                   | 26 +++++++++++++-------------
 drivers/xen/time.c                    |  3 ++-
 15 files changed, 71 insertions(+), 57 deletions(-)

diff --git a/arch/arm/include/asm/paravirt.h b/arch/arm/include/asm/paravirt.h
index cdbf02d..95d5b0d 100644
--- a/arch/arm/include/asm/paravirt.h
+++ b/arch/arm/include/asm/paravirt.h
@@ -3,23 +3,19 @@
 #define _ASM_ARM_PARAVIRT_H
 
 #ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
 struct static_key;
 extern struct static_key paravirt_steal_enabled;
 extern struct static_key paravirt_steal_rq_enabled;
 
-struct pv_time_ops {
-	unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
-	struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
 
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return pv_ops.time.steal_clock(cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 #endif
 
diff --git a/arch/arm/kernel/paravirt.c b/arch/arm/kernel/paravirt.c
index 4cfed91..7dd9806 100644
--- a/arch/arm/kernel/paravirt.c
+++ b/arch/arm/kernel/paravirt.c
@@ -9,10 +9,15 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/types.h>
+#include <linux/static_call.h>
 #include <asm/paravirt.h>
 
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
index cf3a0fd..9aa193e 100644
--- a/arch/arm64/include/asm/paravirt.h
+++ b/arch/arm64/include/asm/paravirt.h
@@ -3,23 +3,19 @@
 #define _ASM_ARM64_PARAVIRT_H
 
 #ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
 struct static_key;
 extern struct static_key paravirt_steal_enabled;
 extern struct static_key paravirt_steal_rq_enabled;
 
-struct pv_time_ops {
-	unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
-	struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
 
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return pv_ops.time.steal_clock(cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 
 int __init pv_time_init(void);
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index c07d7a0..75fed44 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -18,6 +18,7 @@
 #include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/static_call.h>
 
 #include <asm/paravirt.h>
 #include <asm/pvclock-abi.h>
@@ -26,8 +27,12 @@
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
 
 struct pv_time_stolen_time_region {
 	struct pvclock_vcpu_stolen_time *kaddr;
@@ -45,7 +50,7 @@ static int __init parse_no_stealacc(char *arg)
 early_param("no-steal-acc", parse_no_stealacc);
 
 /* return stolen time in ns by asking the hypervisor */
-static u64 pv_steal_clock(int cpu)
+static u64 para_steal_clock(int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 
@@ -150,7 +155,7 @@ int __init pv_time_init(void)
 	if (ret)
 		return ret;
 
-	pv_ops.time.steal_clock = pv_steal_clock;
+	static_call_update(pv_steal_clock, para_steal_clock);
 
 	static_key_slow_inc(&paravirt_steal_enabled);
 	if (steal_acc)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2792879..107acc4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -777,6 +777,7 @@ if HYPERVISOR_GUEST
 
 config PARAVIRT
 	bool "Enable paravirtualization code"
+	depends on HAVE_STATIC_CALL
 	help
 	  This changes the kernel so it can modify itself when it is run
 	  under a hypervisor, potentially improving performance significantly
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index ccf60a8..e7be720 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -63,7 +63,7 @@ typedef int (*hyperv_fill_flush_list_func)(
 static __always_inline void hv_setup_sched_clock(void *sched_clock)
 {
 #ifdef CONFIG_PARAVIRT
-	pv_ops.time.sched_clock = sched_clock;
+	paravirt_set_sched_clock(sched_clock);
 #endif
 }
 
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 4abf110..6408fd0 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -15,11 +15,20 @@
 #include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/cpumask.h>
+#include <linux/static_call_types.h>
 #include <asm/frame.h>
 
-static inline unsigned long long paravirt_sched_clock(void)
+u64 dummy_steal_clock(int cpu);
+u64 dummy_sched_clock(void);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void));
+
+static inline u64 paravirt_sched_clock(void)
 {
-	return PVOP_CALL0(unsigned long long, time.sched_clock);
+	return static_call(pv_sched_clock)();
 }
 
 struct static_key;
@@ -33,7 +42,7 @@ bool pv_is_native_vcpu_is_preempted(void);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return PVOP_CALL1(u64, time.steal_clock, cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 
 /* The paravirtualized I/O functions */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index de87087..1fff349 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -95,11 +95,6 @@ struct pv_lazy_ops {
 } __no_randomize_layout;
 #endif
 
-struct pv_time_ops {
-	unsigned long long (*sched_clock)(void);
-	unsigned long long (*steal_clock)(int cpu);
-} __no_randomize_layout;
-
 struct pv_cpu_ops {
 	/* hooks for various privileged instructions */
 	void (*io_delay)(void);
@@ -291,7 +286,6 @@ struct pv_lock_ops {
  * what to patch. */
 struct paravirt_patch_template {
 	struct pv_init_ops	init;
-	struct pv_time_ops	time;
 	struct pv_cpu_ops	cpu;
 	struct pv_irq_ops	irq;
 	struct pv_mmu_ops	mmu;
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index c6ede3b..84fb8e3 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -27,6 +27,7 @@
 #include <linux/clocksource.h>
 #include <linux/cpu.h>
 #include <linux/reboot.h>
+#include <linux/static_call.h>
 #include <asm/div64.h>
 #include <asm/x86_init.h>
 #include <asm/hypervisor.h>
@@ -336,11 +337,11 @@ static void __init vmware_paravirt_ops_setup(void)
 	vmware_cyc2ns_setup();
 
 	if (vmw_sched_clock)
-		pv_ops.time.sched_clock = vmware_sched_clock;
+		paravirt_set_sched_clock(vmware_sched_clock);
 
 	if (vmware_is_stealclock_available()) {
 		has_steal_clock = true;
-		pv_ops.time.steal_clock = vmware_steal_clock;
+		static_call_update(pv_steal_clock, vmware_steal_clock);
 
 		/* We use reboot notifier only to disable steal clock */
 		register_reboot_notifier(&vmware_pv_reboot_nb);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5e78e01..351ba99 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -650,7 +650,7 @@ static void __init kvm_guest_init(void)
 
 	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		has_steal_clock = 1;
-		pv_ops.time.steal_clock = kvm_steal_clock;
+		static_call_update(pv_steal_clock, kvm_steal_clock);
 	}
 
 	if (pv_tlb_flush_supported()) {
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index aa59374..01e7c18 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -106,7 +106,7 @@ static inline void kvm_sched_clock_init(bool stable)
 	if (!stable)
 		clear_sched_clock_stable();
 	kvm_sched_clock_offset = kvm_clock_read();
-	pv_ops.time.sched_clock = kvm_sched_clock_read;
+	paravirt_set_sched_clock(kvm_sched_clock_read);
 
 	pr_info("kvm-clock: using sched offset of %llu cycles",
 		kvm_sched_clock_offset);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c60222a..a688edf 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -14,6 +14,7 @@
 #include <linux/highmem.h>
 #include <linux/kprobes.h>
 #include <linux/pgtable.h>
+#include <linux/static_call.h>
 
 #include <asm/bug.h>
 #include <asm/paravirt.h>
@@ -167,6 +168,14 @@ static u64 native_steal_clock(int cpu)
 	return 0;
 }
 
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void))
+{
+	static_call_update(pv_sched_clock, func);
+}
+
 /* These are in entry.S */
 extern void native_iret(void);
 
@@ -272,10 +281,6 @@ struct paravirt_patch_template pv_ops = {
 	/* Init ops. */
 	.init.patch		= native_patch,
 
-	/* Time ops. */
-	.time.sched_clock	= native_sched_clock,
-	.time.steal_clock	= native_steal_clock,
-
 	/* Cpu ops. */
 	.cpu.io_delay		= native_io_delay,
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index f70dffc..9f59292 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/timex.h>
 #include <linux/static_key.h>
+#include <linux/static_call.h>
 
 #include <asm/hpet.h>
 #include <asm/timer.h>
@@ -254,7 +255,7 @@ unsigned long long sched_clock(void)
 
 bool using_native_sched_clock(void)
 {
-	return pv_ops.time.sched_clock == native_sched_clock;
+	return static_call_query(pv_sched_clock) == native_sched_clock;
 }
 #else
 unsigned long long
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 91f5b33..d9c945e 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -379,11 +379,6 @@ void xen_timer_resume(void)
 	}
 }
 
-static const struct pv_time_ops xen_time_ops __initconst = {
-	.sched_clock = xen_sched_clock,
-	.steal_clock = xen_steal_clock,
-};
-
 static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
 static u64 xen_clock_value_saved;
 
@@ -525,17 +520,24 @@ static void __init xen_time_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 }
 
-void __init xen_init_time_ops(void)
+static void __init xen_init_time_common(void)
 {
 	xen_sched_clock_offset = xen_clocksource_read();
-	pv_ops.time = xen_time_ops;
+	static_call_update(pv_steal_clock, xen_steal_clock);
+	paravirt_set_sched_clock(xen_sched_clock);
+
+	x86_platform.calibrate_tsc = xen_tsc_khz;
+	x86_platform.get_wallclock = xen_get_wallclock;
+}
+
+void __init xen_init_time_ops(void)
+{
+	xen_init_time_common();
 
 	x86_init.timers.timer_init = xen_time_init;
 	x86_init.timers.setup_percpu_clockev = x86_init_noop;
 	x86_cpuinit.setup_percpu_clockev = x86_init_noop;
 
-	x86_platform.calibrate_tsc = xen_tsc_khz;
-	x86_platform.get_wallclock = xen_get_wallclock;
 	/* Dom0 uses the native method to set the hardware RTC. */
 	if (!xen_initial_domain())
 		x86_platform.set_wallclock = xen_set_wallclock;
@@ -569,13 +571,11 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 	}
 
-	xen_sched_clock_offset = xen_clocksource_read();
-	pv_ops.time = xen_time_ops;
+	xen_init_time_common();
+
 	x86_init.timers.setup_percpu_clockev = xen_time_init;
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
 
-	x86_platform.calibrate_tsc = xen_tsc_khz;
-	x86_platform.get_wallclock = xen_get_wallclock;
 	x86_platform.set_wallclock = xen_set_wallclock;
 }
 #endif
diff --git a/drivers/xen/time.c b/drivers/xen/time.c
index 108edbc..152dd33 100644
--- a/drivers/xen/time.c
+++ b/drivers/xen/time.c
@@ -7,6 +7,7 @@
 #include <linux/math64.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/static_call.h>
 
 #include <asm/paravirt.h>
 #include <asm/xen/hypervisor.h>
@@ -175,7 +176,7 @@ void __init xen_time_setup_guest(void)
 	xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable,
 					VMASST_TYPE_runstate_update_flag);
 
-	pv_ops.time.steal_clock = xen_steal_clock;
+	static_call_update(pv_steal_clock, xen_steal_clock);
 
 	static_key_slow_inc(&paravirt_steal_enabled);
 	if (xen_runstate_remote)

[tip: x86/alternatives] static_call: Move struct static_call_key definition to static_call_types.h

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     b046664872dd78a8bebe3d5f3bb9da9baa93f5ca
Gitweb:        https://git.kernel.org/tip/b046664872dd78a8bebe3d5f3bb9da9baa93f5ca
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:07 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 16:04:39 +01:00

static_call: Move struct static_call_key definition to static_call_types.h

Having the definition of static_call() in static_call_types.h makes
no sense as long struct static_call_key isn't defined there, as the
generic implementation of static_call() is referencing this structure.

So move the definition of struct static_call_key to static_call_types.h.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-3-jgross@suse.com
---
 include/linux/static_call.h             | 18 ------------------
 include/linux/static_call_types.h       | 18 ++++++++++++++++++
 tools/include/linux/static_call_types.h | 18 ++++++++++++++++++
 3 files changed, 36 insertions(+), 18 deletions(-)

diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 85ecc78..76b8812 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -128,16 +128,6 @@ struct static_call_mod {
 	struct static_call_site *sites;
 };
 
-struct static_call_key {
-	void *func;
-	union {
-		/* bit 0: 0 = mods, 1 = sites */
-		unsigned long type;
-		struct static_call_mod *mods;
-		struct static_call_site *sites;
-	};
-};
-
 /* For finding the key associated with a trampoline */
 struct static_call_tramp_key {
 	s32 tramp;
@@ -187,10 +177,6 @@ extern long __static_call_return0(void);
 
 static inline int static_call_init(void) { return 0; }
 
-struct static_call_key {
-	void *func;
-};
-
 #define __DEFINE_STATIC_CALL(name, _func, _func_init)			\
 	DECLARE_STATIC_CALL(name, _func);				\
 	struct static_call_key STATIC_CALL_KEY(name) = {		\
@@ -243,10 +229,6 @@ static inline long __static_call_return0(void)
 
 static inline int static_call_init(void) { return 0; }
 
-struct static_call_key {
-	void *func;
-};
-
 static inline long __static_call_return0(void)
 {
 	return 0;
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
index ae5662d..5a00b8b 100644
--- a/include/linux/static_call_types.h
+++ b/include/linux/static_call_types.h
@@ -58,11 +58,25 @@ struct static_call_site {
 	__raw_static_call(name);					\
 })
 
+struct static_call_key {
+	void *func;
+	union {
+		/* bit 0: 0 = mods, 1 = sites */
+		unsigned long type;
+		struct static_call_mod *mods;
+		struct static_call_site *sites;
+	};
+};
+
 #else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
 
 #define __STATIC_CALL_ADDRESSABLE(name)
 #define __static_call(name)	__raw_static_call(name)
 
+struct static_call_key {
+	void *func;
+};
+
 #endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
 
 #ifdef MODULE
@@ -77,6 +91,10 @@ struct static_call_site {
 
 #else
 
+struct static_call_key {
+	void *func;
+};
+
 #define static_call(name)						\
 	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
 
diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h
index ae5662d..5a00b8b 100644
--- a/tools/include/linux/static_call_types.h
+++ b/tools/include/linux/static_call_types.h
@@ -58,11 +58,25 @@ struct static_call_site {
 	__raw_static_call(name);					\
 })
 
+struct static_call_key {
+	void *func;
+	union {
+		/* bit 0: 0 = mods, 1 = sites */
+		unsigned long type;
+		struct static_call_mod *mods;
+		struct static_call_site *sites;
+	};
+};
+
 #else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
 
 #define __STATIC_CALL_ADDRESSABLE(name)
 #define __static_call(name)	__raw_static_call(name)
 
+struct static_call_key {
+	void *func;
+};
+
 #endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
 
 #ifdef MODULE
@@ -77,6 +91,10 @@ struct static_call_site {
 
 #else
 
+struct static_call_key {
+	void *func;
+};
+
 #define static_call(name)						\
 	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
 

[tip: x86/alternatives] static_call: Add function to query current function

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     6ea312d95e0226b306bb4b8ee3a0727d880378cb
Gitweb:        https://git.kernel.org/tip/6ea312d95e0226b306bb4b8ee3a0727d880378cb
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:08 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 16:12:33 +01:00

static_call: Add function to query current function

Some users of paravirtualized functions need to query which function
has been specified in a pv_ops vector element. In order to be able to
switch such paravirtualized functions to static_calls instead, there
needs to be a function to query the function which will be called via
static_call().

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210311142319.4723-4-jgross@suse.com
---
 include/linux/static_call.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 76b8812..e01b61a 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -20,6 +20,7 @@
  *   static_call(name)(args...);
  *   static_call_cond(name)(args...);
  *   static_call_update(name, func);
+ *   static_call_query(name);
  *
  * Usage example:
  *
@@ -91,6 +92,10 @@
  *
  *   which will include the required value tests to avoid NULL-pointer
  *   dereferences.
+ *
+ *   To query which function is currently set to be called, use:
+ *
+ *   func = static_call_query(name);
  */
 
 #include <linux/types.h>
@@ -118,6 +123,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 			     STATIC_CALL_TRAMP_ADDR(name), func);	\
 })
 
+#define static_call_query(name) (READ_ONCE(STATIC_CALL_KEY(name).func))
+
 #ifdef CONFIG_HAVE_STATIC_CALL_INLINE
 
 extern int __init static_call_init(void);
@@ -191,6 +198,7 @@ static inline int static_call_init(void) { return 0; }
 	};								\
 	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
 
+
 #define static_call_cond(name)	(void)__static_call(name)
 
 static inline

[tip: x86/alternatives] x86/alternative: Merge include files

[tip-bot2 for Juergen Gross]

The following commit has been merged into the x86/alternatives branch of tip:

Commit-ID:     5e21a3ecad1500e35b46701e7f3f232e15d78e69
Gitweb:        https://git.kernel.org/tip/5e21a3ecad1500e35b46701e7f3f232e15d78e69
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Thu, 11 Mar 2021 15:23:06 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Thu, 11 Mar 2021 15:58:02 +01:00

x86/alternative: Merge include files

Merge arch/x86/include/asm/alternative-asm.h into
arch/x86/include/asm/alternative.h in order to make it easier to use
common definitions later.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210311142319.4723-2-jgross@suse.com
---
 arch/x86/entry/entry_32.S                |   2 +-
 arch/x86/entry/vdso/vdso32/system_call.S |   2 +-
 arch/x86/include/asm/alternative-asm.h   | 114 +----------------------
 arch/x86/include/asm/alternative.h       | 112 +++++++++++++++++++++-
 arch/x86/include/asm/nospec-branch.h     |   1 +-
 arch/x86/include/asm/smap.h              |   5 +-
 arch/x86/lib/atomic64_386_32.S           |   2 +-
 arch/x86/lib/atomic64_cx8_32.S           |   2 +-
 arch/x86/lib/copy_page_64.S              |   2 +-
 arch/x86/lib/copy_user_64.S              |   2 +-
 arch/x86/lib/memcpy_64.S                 |   2 +-
 arch/x86/lib/memmove_64.S                |   2 +-
 arch/x86/lib/memset_64.S                 |   2 +-
 arch/x86/lib/retpoline.S                 |   2 +-
 14 files changed, 120 insertions(+), 132 deletions(-)
 delete mode 100644 arch/x86/include/asm/alternative-asm.h

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index df8c017..4e079f2 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -40,7 +40,7 @@
 #include <asm/processor-flags.h>
 #include <asm/irq_vectors.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/frame.h>
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index de1fff7..d6a6080 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -6,7 +6,7 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 	.text
 	.globl __kernel_vsyscall
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
deleted file mode 100644
index 464034d..0000000
--- a/arch/x86/include/asm/alternative-asm.h
+++ /dev/null
@@ -1,114 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_ALTERNATIVE_ASM_H
-#define _ASM_X86_ALTERNATIVE_ASM_H
-
-#ifdef __ASSEMBLY__
-
-#include <asm/asm.h>
-
-#ifdef CONFIG_SMP
-	.macro LOCK_PREFIX
-672:	lock
-	.pushsection .smp_locks,"a"
-	.balign 4
-	.long 672b - .
-	.popsection
-	.endm
-#else
-	.macro LOCK_PREFIX
-	.endm
-#endif
-
-/*
- * objtool annotation to ignore the alternatives and only consider the original
- * instruction(s).
- */
-.macro ANNOTATE_IGNORE_ALTERNATIVE
-	.Lannotate_\@:
-	.pushsection .discard.ignore_alts
-	.long .Lannotate_\@ - .
-	.popsection
-.endm
-
-/*
- * Issue one struct alt_instr descriptor entry (need to put it into
- * the section .altinstructions, see below). This entry contains
- * enough information for the alternatives patching code to patch an
- * instruction. See apply_alternatives().
- */
-.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
-	.long \orig - .
-	.long \alt - .
-	.word \feature
-	.byte \orig_len
-	.byte \alt_len
-	.byte \pad_len
-.endm
-
-/*
- * Define an alternative between two instructions. If @feature is
- * present, early code in apply_alternatives() replaces @oldinstr with
- * @newinstr. ".skip" directive takes care of proper instruction padding
- * in case @newinstr is longer than @oldinstr.
- */
-.macro ALTERNATIVE oldinstr, newinstr, feature
-140:
-	\oldinstr
-141:
-	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
-	.popsection
-
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr
-144:
-	.popsection
-.endm
-
-#define old_len			141b-140b
-#define new_len1		144f-143f
-#define new_len2		145f-144f
-
-/*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
-
-
-/*
- * Same as ALTERNATIVE macro above but for two alternatives. If CPU
- * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
- * @feature2, it replaces @oldinstr with @feature2.
- */
-.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
-140:
-	\oldinstr
-141:
-	.skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
-		(alt_max_short(new_len1, new_len2) - (old_len)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
-	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
-	.popsection
-
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr1
-144:
-	\newinstr2
-145:
-	.popsection
-.endm
-
-#endif  /*  __ASSEMBLY__  */
-
-#endif /* _ASM_X86_ALTERNATIVE_ASM_H */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 5753fb2..53f295f 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -2,13 +2,14 @@
 #ifndef _ASM_X86_ALTERNATIVE_H
 #define _ASM_X86_ALTERNATIVE_H
 
-#ifndef __ASSEMBLY__
-
 #include <linux/types.h>
-#include <linux/stddef.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
 
+#ifndef __ASSEMBLY__
+
+#include <linux/stddef.h>
+
 /*
  * Alternative inline assembly for SMP.
  *
@@ -271,6 +272,111 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SMP
+	.macro LOCK_PREFIX
+672:	lock
+	.pushsection .smp_locks,"a"
+	.balign 4
+	.long 672b - .
+	.popsection
+	.endm
+#else
+	.macro LOCK_PREFIX
+	.endm
+#endif
+
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+	.Lannotate_\@:
+	.pushsection .discard.ignore_alts
+	.long .Lannotate_\@ - .
+	.popsection
+.endm
+
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
+.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
+	.long \orig - .
+	.long \alt - .
+	.word \feature
+	.byte \orig_len
+	.byte \alt_len
+	.byte \pad_len
+.endm
+
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
+.macro ALTERNATIVE oldinstr, newinstr, feature
+140:
+	\oldinstr
+141:
+	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr
+144:
+	.popsection
+.endm
+
+#define old_len			141b-140b
+#define new_len1		144f-143f
+#define new_len2		145f-144f
+
+/*
+ * gas compatible max based on the idea from:
+ * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ *
+ * The additional "-" is needed because gas uses a "true" value of -1.
+ */
+#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+140:
+	\oldinstr
+141:
+	.skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
+		(alt_max_short(new_len1, new_len2) - (old_len)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
+	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr1
+144:
+	\newinstr2
+145:
+	.popsection
+.endm
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index cb9ad6b..529f8e9 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -7,7 +7,6 @@
 #include <linux/objtool.h>
 
 #include <asm/alternative.h>
-#include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 8b58d69..ea1d8eb 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -11,6 +11,7 @@
 
 #include <asm/nops.h>
 #include <asm/cpufeatures.h>
+#include <asm/alternative.h>
 
 /* "Raw" instruction opcodes */
 #define __ASM_CLAC	".byte 0x0f,0x01,0xca"
@@ -18,8 +19,6 @@
 
 #ifdef __ASSEMBLY__
 
-#include <asm/alternative-asm.h>
-
 #ifdef CONFIG_X86_SMAP
 
 #define ASM_CLAC \
@@ -37,8 +36,6 @@
 
 #else /* __ASSEMBLY__ */
 
-#include <asm/alternative.h>
-
 #ifdef CONFIG_X86_SMAP
 
 static __always_inline void clac(void)
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 3b65441..16bc913 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -6,7 +6,7 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 /* if you want SMP support, implement these with real spinlocks */
 .macro LOCK reg
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 1c5c81c..ce69356 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -6,7 +6,7 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 .macro read64 reg
 	movl %ebx, %eax
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 2402d4c..db4b4f9 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -3,7 +3,7 @@
 
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 
 /*
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 77b9b2a..57b79c5 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -11,7 +11,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/export.h>
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 1e299ac..1cc9da6 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -4,7 +4,7 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 
 .pushsection .noinstr.text, "ax"
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 41902fe..6480101 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,7 +8,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 
 #undef memmove
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 0bfd26e..9827ae2 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -3,7 +3,7 @@
 
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 
 /*
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index f6fb1d2..6bb74b5 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -4,7 +4,7 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
 #include <asm/unwind_hints.h>