[PATCH v4 00/15] x86: major paravirt cleanup

[PATCH v4 00/15] x86: major paravirt cleanup

[Juergen Gross]

[Resend due to all the Cc:'s missing]

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, but that would require a major
header file disentangling.

For a clean build without any objtool warnings a modified objtool is
required. Currently this is available in the "tip" tree in the
objtool/core branch.

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/xen: use specific Xen pv interrupt entry for MCE
  x86/xen: use specific Xen pv interrupt entry for DF
  x86/pv: switch SWAPGS to ALTERNATIVE
  x86/xen: drop USERGS_SYSRET64 paravirt call
  x86: rework arch_local_irq_restore() to not use popf
  x86/paravirt: switch time pvops functions to use static_call()
  x86/alternative: support "not feature" and ALTERNATIVE_TERNARY
  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

Peter Zijlstra (1):
  static_call: Pull some static_call declarations to the type headers

 arch/x86/Kconfig                        |   1 +
 arch/x86/entry/entry_32.S               |   4 +-
 arch/x86/entry/entry_64.S               |  28 ++-
 arch/x86/include/asm/alternative-asm.h  |   4 +
 arch/x86/include/asm/alternative.h      |   7 +
 arch/x86/include/asm/cpufeatures.h      |   2 +
 arch/x86/include/asm/idtentry.h         |   6 +
 arch/x86/include/asm/irqflags.h         |  53 ++----
 arch/x86/include/asm/mshyperv.h         |   2 +-
 arch/x86/include/asm/paravirt.h         | 197 ++++++++------------
 arch/x86/include/asm/paravirt_types.h   | 227 +++++++++---------------
 arch/x86/kernel/Makefile                |   3 +-
 arch/x86/kernel/alternative.c           |  49 ++++-
 arch/x86/kernel/asm-offsets.c           |   7 -
 arch/x86/kernel/asm-offsets_64.c        |   3 -
 arch/x86/kernel/cpu/vmware.c            |   5 +-
 arch/x86/kernel/irqflags.S              |  11 --
 arch/x86/kernel/kvm.c                   |   2 +-
 arch/x86/kernel/kvmclock.c              |   2 +-
 arch/x86/kernel/paravirt-spinlocks.c    |   9 +
 arch/x86/kernel/paravirt.c              |  83 +++------
 arch/x86/kernel/paravirt_patch.c        | 109 ------------
 arch/x86/kernel/tsc.c                   |   2 +-
 arch/x86/xen/enlighten_pv.c             |  36 ++--
 arch/x86/xen/irq.c                      |  23 ---
 arch/x86/xen/time.c                     |  11 +-
 arch/x86/xen/xen-asm.S                  |  52 +-----
 arch/x86/xen/xen-ops.h                  |   3 -
 drivers/clocksource/hyperv_timer.c      |   5 +-
 drivers/xen/time.c                      |   2 +-
 include/linux/static_call.h             |  20 ---
 include/linux/static_call_types.h       |  27 +++
 tools/include/linux/static_call_types.h |  27 +++
 33 files changed, 376 insertions(+), 646 deletions(-)
 delete mode 100644 arch/x86/kernel/paravirt_patch.c

-- 
2.26.2

[PATCH v4 01/15] static_call: Pull some static_call declarations to the type headers

[Juergen Gross]

From: Peter Zijlstra <peterz@infradead.org>

Some static call declarations are going to be needed on low level header
files. Move the necessary material to the dedicated static call types
header to avoid inclusion dependency hell.

[jgross@suse.com: updated tools/include/linux/static_call_types.h, too]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 include/linux/static_call.h             | 20 ------------------
 include/linux/static_call_types.h       | 27 +++++++++++++++++++++++++
 tools/include/linux/static_call_types.h | 27 +++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 20 deletions(-)

diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 695da4c9b338..39f39920bb29 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -107,26 +107,11 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 
 #define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name)
 
-/*
- * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from
- * the symbol table so that objtool can reference it when it generates the
- * .static_call_sites section.
- */
-#define __static_call(name)						\
-({									\
-	__ADDRESSABLE(STATIC_CALL_KEY(name));				\
-	&STATIC_CALL_TRAMP(name);					\
-})
-
 #else
 #define STATIC_CALL_TRAMP_ADDR(name) NULL
 #endif
 
 
-#define DECLARE_STATIC_CALL(name, func)					\
-	extern struct static_call_key STATIC_CALL_KEY(name);		\
-	extern typeof(func) STATIC_CALL_TRAMP(name);
-
 #define static_call_update(name, func)					\
 ({									\
 	BUILD_BUG_ON(!__same_type(*(func), STATIC_CALL_TRAMP(name)));	\
@@ -174,7 +159,6 @@ extern int static_call_text_reserved(void *start, void *end);
 	};								\
 	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
 
-#define static_call(name)	__static_call(name)
 #define static_call_cond(name)	(void)__static_call(name)
 
 #define EXPORT_STATIC_CALL(name)					\
@@ -207,7 +191,6 @@ struct static_call_key {
 	};								\
 	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
 
-#define static_call(name)	__static_call(name)
 #define static_call_cond(name)	(void)__static_call(name)
 
 static inline
@@ -252,9 +235,6 @@ struct static_call_key {
 		.func = NULL,						\
 	}
 
-#define static_call(name)						\
-	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
-
 static inline void __static_call_nop(void) { }
 
 /*
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
index 89135bb35bf7..08f78b1b88b4 100644
--- a/include/linux/static_call_types.h
+++ b/include/linux/static_call_types.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/stringify.h>
+#include <linux/compiler.h>
 
 #define STATIC_CALL_KEY_PREFIX		__SCK__
 #define STATIC_CALL_KEY_PREFIX_STR	__stringify(STATIC_CALL_KEY_PREFIX)
@@ -32,4 +33,30 @@ struct static_call_site {
 	s32 key;
 };
 
+#define DECLARE_STATIC_CALL(name, func)					\
+	extern struct static_call_key STATIC_CALL_KEY(name);		\
+	extern typeof(func) STATIC_CALL_TRAMP(name);
+
+#ifdef CONFIG_HAVE_STATIC_CALL
+
+/*
+ * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from
+ * the symbol table so that objtool can reference it when it generates the
+ * .static_call_sites section.
+ */
+#define __static_call(name)						\
+({									\
+	__ADDRESSABLE(STATIC_CALL_KEY(name));				\
+	&STATIC_CALL_TRAMP(name);					\
+})
+
+#define static_call(name)	__static_call(name)
+
+#else
+
+#define static_call(name)						\
+	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
+
+#endif /* CONFIG_HAVE_STATIC_CALL */
+
 #endif /* _STATIC_CALL_TYPES_H */
diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h
index 89135bb35bf7..08f78b1b88b4 100644
--- a/tools/include/linux/static_call_types.h
+++ b/tools/include/linux/static_call_types.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/stringify.h>
+#include <linux/compiler.h>
 
 #define STATIC_CALL_KEY_PREFIX		__SCK__
 #define STATIC_CALL_KEY_PREFIX_STR	__stringify(STATIC_CALL_KEY_PREFIX)
@@ -32,4 +33,30 @@ struct static_call_site {
 	s32 key;
 };
 
+#define DECLARE_STATIC_CALL(name, func)					\
+	extern struct static_call_key STATIC_CALL_KEY(name);		\
+	extern typeof(func) STATIC_CALL_TRAMP(name);
+
+#ifdef CONFIG_HAVE_STATIC_CALL
+
+/*
+ * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from
+ * the symbol table so that objtool can reference it when it generates the
+ * .static_call_sites section.
+ */
+#define __static_call(name)						\
+({									\
+	__ADDRESSABLE(STATIC_CALL_KEY(name));				\
+	&STATIC_CALL_TRAMP(name);					\
+})
+
+#define static_call(name)	__static_call(name)
+
+#else
+
+#define static_call(name)						\
+	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
+
+#endif /* CONFIG_HAVE_STATIC_CALL */
+
 #endif /* _STATIC_CALL_TYPES_H */
-- 
2.26.2

[PATCH v4 02/15] x86/xen: use specific Xen pv interrupt entry for MCE

[Juergen Gross]

Xen PV guests don't use IST. For machine check interrupts switch to
the same model as debug interrupts.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/idtentry.h |  3 +++
 arch/x86/xen/enlighten_pv.c     | 16 +++++++++++++++-
 arch/x86/xen/xen-asm.S          |  2 +-
 3 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 247a60a47331..5dd64404715a 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -585,6 +585,9 @@ DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);
 #else
 DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	exc_machine_check);
 #endif
+#ifdef CONFIG_XEN_PV
+DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	xenpv_exc_machine_check);
+#endif
 #endif
 
 /* NMI */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 4409306364dc..9f5e44c1f70a 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -583,6 +583,20 @@ DEFINE_IDTENTRY_RAW(xenpv_exc_debug)
 		exc_debug(regs);
 }
 
+#ifdef CONFIG_X86_MCE
+DEFINE_IDTENTRY_RAW(xenpv_exc_machine_check)
+{
+	/*
+	 * There's no IST on Xen PV, but we still need to dispatch
+	 * to the correct handler.
+	 */
+	if (user_mode(regs))
+		noist_exc_machine_check(regs);
+	else
+		exc_machine_check(regs);
+}
+#endif
+
 struct trap_array_entry {
 	void (*orig)(void);
 	void (*xen)(void);
@@ -603,7 +617,7 @@ static struct trap_array_entry trap_array[] = {
 	TRAP_ENTRY_REDIR(exc_debug,			true  ),
 	TRAP_ENTRY(exc_double_fault,			true  ),
 #ifdef CONFIG_X86_MCE
-	TRAP_ENTRY(exc_machine_check,			true  ),
+	TRAP_ENTRY_REDIR(exc_machine_check,		true  ),
 #endif
 	TRAP_ENTRY_REDIR(exc_nmi,			true  ),
 	TRAP_ENTRY(exc_int3,				false ),
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1cb0e84b9161..bc2586730a5b 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -172,7 +172,7 @@ xen_pv_trap asm_exc_spurious_interrupt_bug
 xen_pv_trap asm_exc_coprocessor_error
 xen_pv_trap asm_exc_alignment_check
 #ifdef CONFIG_X86_MCE
-xen_pv_trap asm_exc_machine_check
+xen_pv_trap asm_xenpv_exc_machine_check
 #endif /* CONFIG_X86_MCE */
 xen_pv_trap asm_exc_simd_coprocessor_error
 #ifdef CONFIG_IA32_EMULATION
-- 
2.26.2

[PATCH v4 03/15] x86/xen: use specific Xen pv interrupt entry for DF

[Juergen Gross]

Xen PV guests don't use IST. For double fault interrupts switch to
the same model as NMI.

Correct a typo in a comment while copying it.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
---
V2:
- fix typo (Andy Lutomirski)
---
 arch/x86/include/asm/idtentry.h |  3 +++
 arch/x86/xen/enlighten_pv.c     | 10 ++++++++--
 arch/x86/xen/xen-asm.S          |  2 +-
 3 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 5dd64404715a..3ac84cb702fc 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -608,6 +608,9 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
 
 /* #DF */
 DECLARE_IDTENTRY_DF(X86_TRAP_DF,	exc_double_fault);
+#ifdef CONFIG_XEN_PV
+DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_DF,	xenpv_exc_double_fault);
+#endif
 
 /* #VC */
 #ifdef CONFIG_AMD_MEM_ENCRYPT
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 9f5e44c1f70a..76616024129e 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -567,10 +567,16 @@ void noist_exc_debug(struct pt_regs *regs);
 
 DEFINE_IDTENTRY_RAW(xenpv_exc_nmi)
 {
-	/* On Xen PV, NMI doesn't use IST.  The C part is the sane as native. */
+	/* On Xen PV, NMI doesn't use IST.  The C part is the same as native. */
 	exc_nmi(regs);
 }
 
+DEFINE_IDTENTRY_RAW_ERRORCODE(xenpv_exc_double_fault)
+{
+	/* On Xen PV, DF doesn't use IST.  The C part is the same as native. */
+	exc_double_fault(regs, error_code);
+}
+
 DEFINE_IDTENTRY_RAW(xenpv_exc_debug)
 {
 	/*
@@ -615,7 +621,7 @@ struct trap_array_entry {
 
 static struct trap_array_entry trap_array[] = {
 	TRAP_ENTRY_REDIR(exc_debug,			true  ),
-	TRAP_ENTRY(exc_double_fault,			true  ),
+	TRAP_ENTRY_REDIR(exc_double_fault,		true  ),
 #ifdef CONFIG_X86_MCE
 	TRAP_ENTRY_REDIR(exc_machine_check,		true  ),
 #endif
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index bc2586730a5b..1d054c915046 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -161,7 +161,7 @@ xen_pv_trap asm_exc_overflow
 xen_pv_trap asm_exc_bounds
 xen_pv_trap asm_exc_invalid_op
 xen_pv_trap asm_exc_device_not_available
-xen_pv_trap asm_exc_double_fault
+xen_pv_trap asm_xenpv_exc_double_fault
 xen_pv_trap asm_exc_coproc_segment_overrun
 xen_pv_trap asm_exc_invalid_tss
 xen_pv_trap asm_exc_segment_not_present
-- 
2.26.2

[PATCH v4 04/15] x86/pv: switch SWAPGS to ALTERNATIVE

[Juergen Gross]

SWAPGS is used only for interrupts coming from user mode or for
returning to user mode. So there is no reason to use the PARAVIRT
framework, as it can easily be replaced by an ALTERNATIVE depending
on X86_FEATURE_XENPV.

There are several instances using the PV-aware SWAPGS macro in paths
which are never executed in a Xen PV guest. Replace those with the
plain swapgs instruction. For SWAPGS_UNSAFE_STACK the same applies.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/entry/entry_64.S             | 10 +++++-----
 arch/x86/include/asm/irqflags.h       | 20 ++++++++------------
 arch/x86/include/asm/paravirt.h       | 20 --------------------
 arch/x86/include/asm/paravirt_types.h |  2 --
 arch/x86/kernel/asm-offsets_64.c      |  1 -
 arch/x86/kernel/paravirt.c            |  1 -
 arch/x86/kernel/paravirt_patch.c      |  3 ---
 arch/x86/xen/enlighten_pv.c           |  3 ---
 8 files changed, 13 insertions(+), 47 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index cad08703c4ad..a876204a73e0 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -669,7 +669,7 @@ native_irq_return_ldt:
 	 */
 
 	pushq	%rdi				/* Stash user RDI */
-	SWAPGS					/* to kernel GS */
+	swapgs					/* to kernel GS */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi	/* to kernel CR3 */
 
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
@@ -699,7 +699,7 @@ native_irq_return_ldt:
 	orq	PER_CPU_VAR(espfix_stack), %rax
 
 	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
-	SWAPGS					/* to user GS */
+	swapgs					/* to user GS */
 	popq	%rdi				/* Restore user RDI */
 
 	movq	%rax, %rsp
@@ -943,7 +943,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	ret
 
 .Lparanoid_entry_swapgs:
-	SWAPGS
+	swapgs
 
 	/*
 	 * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
@@ -1001,7 +1001,7 @@ SYM_CODE_START_LOCAL(paranoid_exit)
 	jnz		restore_regs_and_return_to_kernel
 
 	/* We are returning to a context with user GSBASE */
-	SWAPGS_UNSAFE_STACK
+	swapgs
 	jmp		restore_regs_and_return_to_kernel
 SYM_CODE_END(paranoid_exit)
 
@@ -1426,7 +1426,7 @@ nmi_no_fsgsbase:
 	jnz	nmi_restore
 
 nmi_swapgs:
-	SWAPGS_UNSAFE_STACK
+	swapgs
 
 nmi_restore:
 	POP_REGS
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 2dfc8d380dab..8c86edefa115 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -131,18 +131,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #define SAVE_FLAGS(x)		pushfq; popq %rax
 #endif
 
-#define SWAPGS	swapgs
-/*
- * Currently paravirt can't handle swapgs nicely when we
- * don't have a stack we can rely on (such as a user space
- * stack).  So we either find a way around these or just fault
- * and emulate if a guest tries to call swapgs directly.
- *
- * Either way, this is a good way to document that we don't
- * have a reliable stack. x86_64 only.
- */
-#define SWAPGS_UNSAFE_STACK	swapgs
-
 #define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
@@ -170,6 +158,14 @@ static __always_inline int arch_irqs_disabled(void)
 
 	return arch_irqs_disabled_flags(flags);
 }
+#else
+#ifdef CONFIG_X86_64
+#ifdef CONFIG_XEN_PV
+#define SWAPGS	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
+#else
+#define SWAPGS	swapgs
+#endif
+#endif
 #endif /* !__ASSEMBLY__ */
 
 #endif
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f8dce11d2bc1..f2ebe109a37e 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -776,26 +776,6 @@ extern void default_banner(void);
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
-/*
- * If swapgs is used while the userspace stack is still current,
- * there's no way to call a pvop.  The PV replacement *must* be
- * inlined, or the swapgs instruction must be trapped and emulated.
- */
-#define SWAPGS_UNSAFE_STACK						\
-	PARA_SITE(PARA_PATCH(PV_CPU_swapgs), swapgs)
-
-/*
- * Note: swapgs is very special, and in practise is either going to be
- * implemented with a single "swapgs" instruction or something very
- * special.  Either way, we don't need to save any registers for
- * it.
- */
-#define SWAPGS								\
-	PARA_SITE(PARA_PATCH(PV_CPU_swapgs),				\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_CPU_swapgs);		\
-		 )
-
 #define USERGS_SYSRET64							\
 	PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64),			\
 		  ANNOTATE_RETPOLINE_SAFE;				\
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index b6b02b7c19cc..130f428b0cc8 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -168,8 +168,6 @@ struct pv_cpu_ops {
 	   frame set up. */
 	void (*iret)(void);
 
-	void (*swapgs)(void);
-
 	void (*start_context_switch)(struct task_struct *prev);
 	void (*end_context_switch)(struct task_struct *next);
 #endif
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 828be792231e..1354bc30614d 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -15,7 +15,6 @@ int main(void)
 #ifdef CONFIG_PARAVIRT_XXL
 	OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
 	       cpu.usergs_sysret64);
-	OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs);
 #ifdef CONFIG_DEBUG_ENTRY
 	OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
 #endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 6c3407ba6ee9..5e5fcf5c376d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -312,7 +312,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.usergs_sysret64	= native_usergs_sysret64,
 	.cpu.iret		= native_iret,
-	.cpu.swapgs		= native_swapgs,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
 	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index ace6e334cb39..7c518b08aa3c 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -28,7 +28,6 @@ struct patch_xxl {
 	const unsigned char	irq_restore_fl[2];
 	const unsigned char	cpu_wbinvd[2];
 	const unsigned char	cpu_usergs_sysret64[6];
-	const unsigned char	cpu_swapgs[3];
 	const unsigned char	mov64[3];
 };
 
@@ -43,7 +42,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
 	.cpu_usergs_sysret64	= { 0x0f, 0x01, 0xf8,
 				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
-	.cpu_swapgs		= { 0x0f, 0x01, 0xf8 },	// swapgs
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
 };
 
@@ -86,7 +84,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
 
 	PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len);
-	PATCH_CASE(cpu, swapgs, xxl, insn_buff, len);
 	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
 #endif
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 76616024129e..44bb18adfb51 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1085,9 +1085,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 #endif
 	.io_delay = xen_io_delay,
 
-	/* Xen takes care of %gs when switching to usermode for us */
-	.swapgs = paravirt_nop,
-
 	.start_context_switch = paravirt_start_context_switch,
 	.end_context_switch = xen_end_context_switch,
 };
-- 
2.26.2

[PATCH v4 05/15] x86/xen: drop USERGS_SYSRET64 paravirt call

[Juergen Gross]

USERGS_SYSRET64 is used to return from a syscall via sysret, but
a Xen PV guest will nevertheless use the iret hypercall, as there
is no sysret PV hypercall defined.

So instead of testing all the prerequisites for doing a sysret and
then mangling the stack for Xen PV again for doing an iret just use
the iret exit from the beginning.

This can easily be done via an ALTERNATIVE like it is done for the
sysenter compat case already.

It should be noted that this drops the optimization in Xen for not
restoring a few registers when returning to user mode, but it seems
as if the saved instructions in the kernel more than compensate for
this drop (a kernel build in a Xen PV guest was slightly faster with
this patch applied).

While at it remove the stale sysret32 remnants.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V3:
- simplify ALTERNATIVE (Boris Petkov)
---
 arch/x86/entry/entry_64.S             | 16 +++++++---------
 arch/x86/include/asm/irqflags.h       |  6 ------
 arch/x86/include/asm/paravirt.h       |  5 -----
 arch/x86/include/asm/paravirt_types.h |  8 --------
 arch/x86/kernel/asm-offsets_64.c      |  2 --
 arch/x86/kernel/paravirt.c            |  5 +----
 arch/x86/kernel/paravirt_patch.c      |  4 ----
 arch/x86/xen/enlighten_pv.c           |  1 -
 arch/x86/xen/xen-asm.S                | 20 --------------------
 arch/x86/xen/xen-ops.h                |  2 --
 10 files changed, 8 insertions(+), 61 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a876204a73e0..ce0464d630a2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -46,14 +46,6 @@
 .code64
 .section .entry.text, "ax"
 
-#ifdef CONFIG_PARAVIRT_XXL
-SYM_CODE_START(native_usergs_sysret64)
-	UNWIND_HINT_EMPTY
-	swapgs
-	sysretq
-SYM_CODE_END(native_usergs_sysret64)
-#endif /* CONFIG_PARAVIRT_XXL */
-
 /*
  * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
  *
@@ -123,7 +115,12 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * Try to use SYSRET instead of IRET if we're returning to
 	 * a completely clean 64-bit userspace context.  If we're not,
 	 * go to the slow exit path.
+	 * In the Xen PV case we must use iret anyway.
 	 */
+
+	ALTERNATIVE "", "jmp	swapgs_restore_regs_and_return_to_usermode", \
+		X86_FEATURE_XENPV
+
 	movq	RCX(%rsp), %rcx
 	movq	RIP(%rsp), %r11
 
@@ -215,7 +212,8 @@ syscall_return_via_sysret:
 
 	popq	%rdi
 	popq	%rsp
-	USERGS_SYSRET64
+	swapgs
+	sysretq
 SYM_CODE_END(entry_SYSCALL_64)
 
 /*
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 8c86edefa115..e585a4705b8d 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -132,12 +132,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #endif
 
 #define INTERRUPT_RETURN	jmp native_iret
-#define USERGS_SYSRET64				\
-	swapgs;					\
-	sysretq;
-#define USERGS_SYSRET32				\
-	swapgs;					\
-	sysretl
 
 #else
 #define INTERRUPT_RETURN		iret
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f2ebe109a37e..dd43b1100a87 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -776,11 +776,6 @@ extern void default_banner(void);
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
-#define USERGS_SYSRET64							\
-	PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64),			\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);)
-
 #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 130f428b0cc8..0169365f1403 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -156,14 +156,6 @@ struct pv_cpu_ops {
 
 	u64 (*read_pmc)(int counter);
 
-	/*
-	 * Switch to usermode gs and return to 64-bit usermode using
-	 * sysret.  Only used in 64-bit kernels to return to 64-bit
-	 * processes.  Usermode register state, including %rsp, must
-	 * already be restored.
-	 */
-	void (*usergs_sysret64)(void);
-
 	/* Normal iret.  Jump to this with the standard iret stack
 	   frame set up. */
 	void (*iret)(void);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 1354bc30614d..b14533af7676 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -13,8 +13,6 @@ int main(void)
 {
 #ifdef CONFIG_PARAVIRT
 #ifdef CONFIG_PARAVIRT_XXL
-	OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
-	       cpu.usergs_sysret64);
 #ifdef CONFIG_DEBUG_ENTRY
 	OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
 #endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 5e5fcf5c376d..18560b71e717 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -135,8 +135,7 @@ 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) ||
-		 type == PARAVIRT_PATCH(cpu.usergs_sysret64))
+	else if (type == PARAVIRT_PATCH(cpu.iret))
 		/* If operation requires a jmp, then jmp */
 		ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
 #endif
@@ -170,7 +169,6 @@ static u64 native_steal_clock(int cpu)
 
 /* These are in entry.S */
 extern void native_iret(void);
-extern void native_usergs_sysret64(void);
 
 static struct resource reserve_ioports = {
 	.start = 0,
@@ -310,7 +308,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.load_sp0		= native_load_sp0,
 
-	.cpu.usergs_sysret64	= native_usergs_sysret64,
 	.cpu.iret		= native_iret,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index 7c518b08aa3c..2fada2c347c9 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -27,7 +27,6 @@ struct patch_xxl {
 	const unsigned char	mmu_write_cr3[3];
 	const unsigned char	irq_restore_fl[2];
 	const unsigned char	cpu_wbinvd[2];
-	const unsigned char	cpu_usergs_sysret64[6];
 	const unsigned char	mov64[3];
 };
 
@@ -40,8 +39,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
 	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
-	.cpu_usergs_sysret64	= { 0x0f, 0x01, 0xf8,
-				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
 };
 
@@ -83,7 +80,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
 	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
 
-	PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len);
 	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
 #endif
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 44bb18adfb51..5476423fc6d0 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1060,7 +1060,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_pmc = xen_read_pmc,
 
 	.iret = xen_iret,
-	.usergs_sysret64 = xen_sysret64,
 
 	.load_tr_desc = paravirt_nop,
 	.set_ldt = xen_set_ldt,
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1d054c915046..c0630fd9f44e 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -214,26 +214,6 @@ SYM_CODE_START(xen_iret)
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
 
-SYM_CODE_START(xen_sysret64)
-	/*
-	 * We're already on the usermode stack at this point, but
-	 * still with the kernel gs, so we can easily switch back.
-	 *
-	 * tss.sp2 is scratch space.
-	 */
-	movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
-	pushq $__USER_DS
-	pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	pushq %r11
-	pushq $__USER_CS
-	pushq %rcx
-
-	pushq $VGCF_in_syscall
-	jmp hypercall_iret
-SYM_CODE_END(xen_sysret64)
-
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
  * means we have:
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9546c3384c75..b2fd80a01a36 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -138,8 +138,6 @@ __visible unsigned long xen_read_cr2_direct(void);
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
-__visible void xen_sysret32(void);
-__visible void xen_sysret64(void);
 
 extern int xen_panic_handler_init(void);
 
-- 
2.26.2

[PATCH v4 06/15] x86: rework arch_local_irq_restore() to not use popf

[Juergen Gross]

"popf" is a rather expensive operation, so don't use it for restoring
irq flags. Instead test whether interrupts are enabled in the flags
parameter and enable interrupts via "sti" in that case.

This results in the restore_fl paravirt op to be no longer needed.

Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 arch/x86/include/asm/irqflags.h       | 20 ++++++-------------
 arch/x86/include/asm/paravirt.h       |  5 -----
 arch/x86/include/asm/paravirt_types.h |  7 ++-----
 arch/x86/kernel/irqflags.S            | 11 -----------
 arch/x86/kernel/paravirt.c            |  1 -
 arch/x86/kernel/paravirt_patch.c      |  3 ---
 arch/x86/xen/enlighten_pv.c           |  2 --
 arch/x86/xen/irq.c                    | 23 ----------------------
 arch/x86/xen/xen-asm.S                | 28 ---------------------------
 arch/x86/xen/xen-ops.h                |  1 -
 10 files changed, 8 insertions(+), 93 deletions(-)

diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index e585a4705b8d..144d70ea4393 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -35,15 +35,6 @@ extern __always_inline unsigned long native_save_fl(void)
 	return flags;
 }
 
-extern inline void native_restore_fl(unsigned long flags);
-extern inline void native_restore_fl(unsigned long flags)
-{
-	asm volatile("push %0 ; popf"
-		     : /* no output */
-		     :"g" (flags)
-		     :"memory", "cc");
-}
-
 static __always_inline void native_irq_disable(void)
 {
 	asm volatile("cli": : :"memory");
@@ -79,11 +70,6 @@ static __always_inline unsigned long arch_local_save_flags(void)
 	return native_save_fl();
 }
 
-static __always_inline void arch_local_irq_restore(unsigned long flags)
-{
-	native_restore_fl(flags);
-}
-
 static __always_inline void arch_local_irq_disable(void)
 {
 	native_irq_disable();
@@ -152,6 +138,12 @@ static __always_inline int arch_irqs_disabled(void)
 
 	return arch_irqs_disabled_flags(flags);
 }
+
+static __always_inline void arch_local_irq_restore(unsigned long flags)
+{
+	if (!arch_irqs_disabled_flags(flags))
+		arch_local_irq_enable();
+}
 #else
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_XEN_PV
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index dd43b1100a87..4abf110e2243 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -648,11 +648,6 @@ static inline notrace unsigned long arch_local_save_flags(void)
 	return PVOP_CALLEE0(unsigned long, irq.save_fl);
 }
 
-static inline notrace void arch_local_irq_restore(unsigned long f)
-{
-	PVOP_VCALLEE1(irq.restore_fl, f);
-}
-
 static inline notrace void arch_local_irq_disable(void)
 {
 	PVOP_VCALLEE0(irq.irq_disable);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0169365f1403..de87087d3bde 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -168,16 +168,13 @@ struct pv_cpu_ops {
 struct pv_irq_ops {
 #ifdef CONFIG_PARAVIRT_XXL
 	/*
-	 * Get/set interrupt state.  save_fl and restore_fl are only
-	 * expected to use X86_EFLAGS_IF; all other bits
-	 * returned from save_fl are undefined, and may be ignored by
-	 * restore_fl.
+	 * Get/set interrupt state.  save_fl is expected to use X86_EFLAGS_IF;
+	 * all other bits returned from save_fl are undefined.
 	 *
 	 * NOTE: These functions callers expect the callee to preserve
 	 * more registers than the standard C calling convention.
 	 */
 	struct paravirt_callee_save save_fl;
-	struct paravirt_callee_save restore_fl;
 	struct paravirt_callee_save irq_disable;
 	struct paravirt_callee_save irq_enable;
 
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 0db0375235b4..8ef35063964b 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -13,14 +13,3 @@ SYM_FUNC_START(native_save_fl)
 	ret
 SYM_FUNC_END(native_save_fl)
 EXPORT_SYMBOL(native_save_fl)
-
-/*
- * void native_restore_fl(unsigned long flags)
- * %eax/%rdi: flags
- */
-SYM_FUNC_START(native_restore_fl)
-	push %_ASM_ARG1
-	popf
-	ret
-SYM_FUNC_END(native_restore_fl)
-EXPORT_SYMBOL(native_restore_fl)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 18560b71e717..c60222ab8ab9 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -320,7 +320,6 @@ struct paravirt_patch_template pv_ops = {
 
 	/* Irq ops. */
 	.irq.save_fl		= __PV_IS_CALLEE_SAVE(native_save_fl),
-	.irq.restore_fl		= __PV_IS_CALLEE_SAVE(native_restore_fl),
 	.irq.irq_disable	= __PV_IS_CALLEE_SAVE(native_irq_disable),
 	.irq.irq_enable		= __PV_IS_CALLEE_SAVE(native_irq_enable),
 	.irq.safe_halt		= native_safe_halt,
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index 2fada2c347c9..abd27ec67397 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -25,7 +25,6 @@ struct patch_xxl {
 	const unsigned char	mmu_read_cr2[3];
 	const unsigned char	mmu_read_cr3[3];
 	const unsigned char	mmu_write_cr3[3];
-	const unsigned char	irq_restore_fl[2];
 	const unsigned char	cpu_wbinvd[2];
 	const unsigned char	mov64[3];
 };
@@ -37,7 +36,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.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
-	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
 };
@@ -71,7 +69,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	switch (type) {
 
 #ifdef CONFIG_PARAVIRT_XXL
-	PATCH_CASE(irq, restore_fl, xxl, insn_buff, len);
 	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);
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5476423fc6d0..32b295cc2716 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1022,8 +1022,6 @@ void __init xen_setup_vcpu_info_placement(void)
 	 */
 	if (xen_have_vcpu_info_placement) {
 		pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
-		pv_ops.irq.restore_fl =
-			__PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
 		pv_ops.irq.irq_disable =
 			__PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
 		pv_ops.irq.irq_enable =
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 850c93f346c7..dfa091d79c2e 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -42,28 +42,6 @@ asmlinkage __visible unsigned long xen_save_fl(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl);
 
-__visible void xen_restore_fl(unsigned long flags)
-{
-	struct vcpu_info *vcpu;
-
-	/* convert from IF type flag */
-	flags = !(flags & X86_EFLAGS_IF);
-
-	/* See xen_irq_enable() for why preemption must be disabled. */
-	preempt_disable();
-	vcpu = this_cpu_read(xen_vcpu);
-	vcpu->evtchn_upcall_mask = flags;
-
-	if (flags == 0) {
-		barrier(); /* unmask then check (avoid races) */
-		if (unlikely(vcpu->evtchn_upcall_pending))
-			xen_force_evtchn_callback();
-		preempt_enable();
-	} else
-		preempt_enable_no_resched();
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
-
 asmlinkage __visible void xen_irq_disable(void)
 {
 	/* There's a one instruction preempt window here.  We need to
@@ -118,7 +96,6 @@ static void xen_halt(void)
 
 static const struct pv_irq_ops xen_irq_ops __initconst = {
 	.save_fl = PV_CALLEE_SAVE(xen_save_fl),
-	.restore_fl = PV_CALLEE_SAVE(xen_restore_fl),
 	.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
 	.irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
 
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index c0630fd9f44e..1ea7e41044b5 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -72,34 +72,6 @@ SYM_FUNC_START(xen_save_fl_direct)
 	ret
 SYM_FUNC_END(xen_save_fl_direct)
 
-
-/*
- * In principle the caller should be passing us a value return from
- * xen_save_fl_direct, but for robustness sake we test only the
- * X86_EFLAGS_IF flag rather than the whole byte. After setting the
- * interrupt mask state, it checks for unmasked pending events and
- * enters the hypervisor to get them delivered if so.
- */
-SYM_FUNC_START(xen_restore_fl_direct)
-	FRAME_BEGIN
-	testw $X86_EFLAGS_IF, %di
-	setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
-	/*
-	 * Preempt here doesn't matter because that will deal with any
-	 * pending interrupts.  The pending check may end up being run
-	 * on the wrong CPU, but that doesn't hurt.
-	 */
-
-	/* check for unmasked and pending */
-	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
-	jnz 1f
-	call check_events
-1:
-	FRAME_END
-	ret
-SYM_FUNC_END(xen_restore_fl_direct)
-
-
 /*
  * Force an event check by making a hypercall, but preserve regs
  * before making the call.
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index b2fd80a01a36..8d7ec49a35fb 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -131,7 +131,6 @@ static inline void __init xen_efi_init(struct boot_params *boot_params)
 __visible void xen_irq_enable_direct(void);
 __visible void xen_irq_disable_direct(void);
 __visible unsigned long xen_save_fl_direct(void);
-__visible void xen_restore_fl_direct(unsigned long);
 
 __visible unsigned long xen_read_cr2(void);
 __visible unsigned long xen_read_cr2_direct(void);
-- 
2.26.2

[PATCH v4 07/15] 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>
---
V4:
- drop paravirt_time.h again
- don't move Hyper-V code (Michael Kelley)
---
 arch/x86/Kconfig                      |  1 +
 arch/x86/include/asm/mshyperv.h       |  2 +-
 arch/x86/include/asm/paravirt.h       | 17 ++++++++++++++---
 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            | 16 ++++++++++++----
 arch/x86/kernel/tsc.c                 |  2 +-
 arch/x86/xen/time.c                   | 11 ++++-------
 drivers/clocksource/hyperv_timer.c    |  5 +++--
 drivers/xen/time.c                    |  2 +-
 12 files changed, 42 insertions(+), 29 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 21f851179ff0..7ccd4a80788c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -771,6 +771,7 @@ 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 30f76b966857..b4ee331d29a7 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..1e45b46fae84 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -15,11 +15,22 @@
 #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);
+
+extern bool paravirt_using_native_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 +44,7 @@ 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..44e5b0fe28cb 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 +168,17 @@ 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);
+
+bool paravirt_using_native_sched_clock = true;
+
+void paravirt_set_sched_clock(u64 (*func)(void))
+{
+	static_call_update(pv_sched_clock, func);
+	paravirt_using_native_sched_clock = (func == native_sched_clock);
+}
+
 /* These are in entry.S */
 extern void native_iret(void);
 
@@ -272,10 +284,6 @@ 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..b6f7853d8077 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -254,7 +254,7 @@ unsigned long long sched_clock(void)
 
 bool using_native_sched_clock(void)
 {
-	return pv_ops.time.sched_clock == native_sched_clock;
+	return paravirt_using_native_sched_clock;
 }
 #else
 unsigned long long
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 91f5b330dcc6..01930e182e99 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;
 
@@ -528,7 +523,8 @@ static void __init xen_time_init(void)
 void __init xen_init_time_ops(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_init.timers.timer_init = xen_time_init;
 	x86_init.timers.setup_percpu_clockev = x86_init_noop;
@@ -570,7 +566,8 @@ void __init xen_hvm_init_time_ops(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_init.timers.setup_percpu_clockev = xen_time_init;
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
 
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index ba04cb381cd3..bf3bf20bc6bd 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -18,6 +18,7 @@
 #include <linux/sched_clock.h>
 #include <linux/mm.h>
 #include <linux/cpuhotplug.h>
+#include <linux/static_call.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
@@ -445,7 +446,7 @@ static bool __init hv_init_tsc_clocksource(void)
 	clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 
 	hv_sched_clock_offset = hv_read_reference_counter();
-	hv_setup_sched_clock(read_hv_sched_clock_tsc);
+	paravirt_set_sched_clock(read_hv_sched_clock_tsc);
 
 	return true;
 }
@@ -470,6 +471,6 @@ void __init hv_init_clocksource(void)
 	clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
 
 	hv_sched_clock_offset = hv_read_reference_counter();
-	hv_setup_sched_clock(read_hv_sched_clock_msr);
+	static_call_update(pv_sched_clock, read_hv_sched_clock_msr);
 }
 EXPORT_SYMBOL_GPL(hv_init_clocksource);
diff --git a/drivers/xen/time.c b/drivers/xen/time.c
index 108edbcbc040..199c016834ed 100644
--- a/drivers/xen/time.c
+++ b/drivers/xen/time.c
@@ -175,7 +175,7 @@ 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 v4 08/15] x86/alternative: support "not feature" and ALTERNATIVE_TERNARY

[Juergen Gross]

Instead of only supporting to modify instructions when a specific
feature is set, support doing so for the case a feature is not set.

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>
---
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
---
 arch/x86/include/asm/alternative-asm.h |  4 ++++
 arch/x86/include/asm/alternative.h     |  7 +++++++
 arch/x86/kernel/alternative.c          | 17 ++++++++++++-----
 3 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 464034db299f..a0768e880976 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -109,6 +109,10 @@
 	.popsection
 .endm
 
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr1, newinstr2)	\
+	ALTERNATIVE_2 oldinstr, newinstr2, X86_FEATURE_ALWAYS,		\
+	newinstr1, feature
+
 #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 13adca37c99a..7412653182dd 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -59,6 +59,7 @@ struct alt_instr {
 	s32 instr_offset;	/* original instruction */
 	s32 repl_offset;	/* offset to replacement instruction */
 	u16 cpuid;		/* cpuid bit set for replacement */
+#define ALT_INSTR_CPUID_INV	0x8000	/* patch if ~cpuid bit is NOT set */
 	u8  instrlen;		/* length of original instruction */
 	u8  replacementlen;	/* length of new instruction */
 	u8  padlen;		/* length of build-time padding */
@@ -175,6 +176,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
 	".popsection\n"
 
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr1, newinstr2)	\
+	ALTERNATIVE_2(oldinstr, newinstr2, X86_FEATURE_ALWAYS, newinstr1, feature)
+
 #define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \
 	OLDINSTR_3(oldinsn, 1, 2, 3)						\
 	".pushsection .altinstructions,\"a\"\n"					\
@@ -206,6 +210,9 @@ 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, newinstr1, newinstr2)	\
+	asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr1, newinstr2) ::: "memory")
+
 /*
  * Alternative inline assembly with input.
  *
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8d778e46725d..0a904fb2678b 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -388,21 +388,28 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
+		u16 feature;
+		bool not_feature;
 
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
+		feature = a->cpuid;
+		not_feature = feature & ALT_INSTR_CPUID_INV;
+		if (not_feature)
+			feature = ~feature;
 		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);
+		if (!!boot_cpu_has(feature) == not_feature) {
 			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",
+			not_feature ? "~" : "",
+			feature >> 5,
+			feature & 0x1f,
 			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->padlen);
 
-- 
2.26.2

[PATCH v4 09/15] 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>
---
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 84b887825f12..3ae8944b253a 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -238,6 +238,8 @@
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
 #define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
 #define X86_FEATURE_VM_PAGE_FLUSH	( 8*32+21) /* "" VM Page Flush MSR is supported */
+#define X86_FEATURE_PVUNLOCK		( 8*32+22) /* "" PV unlock function */
+#define X86_FEATURE_VCPUPREEMPT		( 8*32+23) /* "" 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 1e45b46fae84..8c354099d9c3 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -47,6 +47,10 @@ 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)
 {
@@ -811,5 +815,11 @@ 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 0a904fb2678b..221acb2b868a 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;
 
@@ -730,6 +731,33 @@ 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
@@ -748,8 +776,6 @@ 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 v4 10/15] 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>
---
 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 df8c017e6161..765487e57d6e 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 8c354099d9c3..c6496a82fad1 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -721,6 +721,7 @@ 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);		\
@@ -746,46 +747,12 @@ 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 v4 11/15] 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>
---
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 v4 12/15] 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>
---
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 c6496a82fad1..36cd71fa097f 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -749,9 +749,9 @@ 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 44e5b0fe28cb..0553a339d850 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. */
@@ -316,8 +294,6 @@ 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,
@@ -422,6 +398,8 @@ 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 32b295cc2716..4716383c64a9 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1057,8 +1057,6 @@ 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,
@@ -1222,6 +1220,7 @@ 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 v4 13/15] 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>
---
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 v4 14/15] 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>
---
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       | 99 +++++++++++++--------------
 arch/x86/include/asm/paravirt_types.h |  6 --
 arch/x86/kernel/paravirt.c            | 16 ++---
 arch/x86/kernel/paravirt_patch.c      | 88 ------------------------
 6 files changed, 56 insertions(+), 157 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index ce0464d630a2..714af508fe30 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 36cd71fa097f..04b3067f31b5 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -137,7 +137,8 @@ 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;", ~X86_FEATURE_XENPV);
 }
 
 static inline void write_cr2(unsigned long x)
@@ -147,12 +148,14 @@ 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;", ~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", ~X86_FEATURE_XENPV);
 }
 
 static inline void __write_cr4(unsigned long x)
@@ -172,7 +175,7 @@ static inline void halt(void)
 
 static inline void wbinvd(void)
 {
-	PVOP_VCALL0(cpu.wbinvd);
+	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ~X86_FEATURE_XENPV);
 }
 
 static inline u64 paravirt_read_msr(unsigned msr)
@@ -386,22 +389,28 @@ 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",
+					  ~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", ~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",
+					  ~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", ~X86_FEATURE_XENPV);
 }
 
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -434,12 +443,15 @@ 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",
+					  ~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", ~X86_FEATURE_XENPV);
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -451,14 +463,16 @@ 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", ~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", ~X86_FEATURE_XENPV);
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -477,14 +491,16 @@ 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", ~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", ~X86_FEATURE_XENPV);
 }
 
 static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
@@ -571,7 +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 ");",
+			  ~X86_FEATURE_PVUNLOCK);
 }
 
 static __always_inline void pv_wait(u8 *ptr, u8 val)
@@ -586,7 +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 ";",
+				~X86_FEATURE_VCPUPREEMPT);
 }
 
 void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
@@ -660,17 +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;", ~X86_FEATURE_XENPV);
 }
 
 static inline notrace void arch_local_irq_disable(void)
 {
-	PVOP_VCALLEE0(irq.irq_disable);
+	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ~X86_FEATURE_XENPV);
 }
 
 static inline notrace void arch_local_irq_enable(void)
 {
-	PVOP_VCALLEE0(irq.irq_enable);
+	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ~X86_FEATURE_XENPV);
 }
 
 static inline notrace unsigned long arch_local_irq_save(void)
@@ -715,35 +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)
@@ -754,12 +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;", \
+				    ~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 0553a339d850..082954930809 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 v4 15/15] 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>
---
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..62efbf8bd8f0 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 paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned len);
 
 int paravirt_disable_iospace(void);
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5eeb808eb024..853a83503120 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_$(BITS).o		:= y
@@ -122,7 +121,7 @@ obj-$(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 221acb2b868a..fb0b83c85de7 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -613,7 +613,7 @@ 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 082954930809..3d7b989ed6be 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;
 
@@ -255,9 +242,6 @@ 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 4716383c64a9..66f83de4d9e0 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1218,7 +1218,6 @@ 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

RE: [PATCH v4 07/15] x86/paravirt: switch time pvops functions to use static_call()

[Michael Kelley]

From: Juergen Gross <jgross@suse.com> Sent: Wednesday, January 20, 2021 5:56 AM
> 
> 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>
> ---
> V4:
> - drop paravirt_time.h again
> - don't move Hyper-V code (Michael Kelley)
> ---
>  arch/x86/Kconfig                      |  1 +
>  arch/x86/include/asm/mshyperv.h       |  2 +-
>  arch/x86/include/asm/paravirt.h       | 17 ++++++++++++++---
>  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            | 16 ++++++++++++----
>  arch/x86/kernel/tsc.c                 |  2 +-
>  arch/x86/xen/time.c                   | 11 ++++-------
>  drivers/clocksource/hyperv_timer.c    |  5 +++--
>  drivers/xen/time.c                    |  2 +-
>  12 files changed, 42 insertions(+), 29 deletions(-)
> 

[snip]

> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index 30f76b966857..b4ee331d29a7 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
>  }
> 

This looks fine.

[snip]

> diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
> index ba04cb381cd3..bf3bf20bc6bd 100644
> --- a/drivers/clocksource/hyperv_timer.c
> +++ b/drivers/clocksource/hyperv_timer.c
> @@ -18,6 +18,7 @@
>  #include <linux/sched_clock.h>
>  #include <linux/mm.h>
>  #include <linux/cpuhotplug.h>
> +#include <linux/static_call.h>
>  #include <clocksource/hyperv_timer.h>
>  #include <asm/hyperv-tlfs.h>
>  #include <asm/mshyperv.h>
> @@ -445,7 +446,7 @@ static bool __init hv_init_tsc_clocksource(void)
>  	clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
> 
>  	hv_sched_clock_offset = hv_read_reference_counter();
> -	hv_setup_sched_clock(read_hv_sched_clock_tsc);
> +	paravirt_set_sched_clock(read_hv_sched_clock_tsc);
> 
>  	return true;
>  }
> @@ -470,6 +471,6 @@ void __init hv_init_clocksource(void)
>  	clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
> 
>  	hv_sched_clock_offset = hv_read_reference_counter();
> -	hv_setup_sched_clock(read_hv_sched_clock_msr);
> +	static_call_update(pv_sched_clock, read_hv_sched_clock_msr);
>  }
>  EXPORT_SYMBOL_GPL(hv_init_clocksource);

The changes to hyperv_timer.c aren't needed and shouldn't be
there, so as to preserve hyperv_timer.c as architecture neutral.  With
your update to hv_setup_sched_clock() in mshyperv.h, the original
code works correctly.  While there are two call sites for
hv_setup_sched_clock(), only one is called.  And once the sched clock
function is set, it is never changed or overridden.

Michael

Re: [PATCH v4 07/15] x86/paravirt: switch time pvops functions to use static_call()

[Borislav Petkov]

On Wed, Jan 20, 2021 at 02:55:47PM +0100, Juergen Gross wrote:
> 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>
> ---
> V4:
> - drop paravirt_time.h again
> - don't move Hyper-V code (Michael Kelley)
> ---
>  arch/x86/Kconfig                      |  1 +
>  arch/x86/include/asm/mshyperv.h       |  2 +-
>  arch/x86/include/asm/paravirt.h       | 17 ++++++++++++++---
>  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            | 16 ++++++++++++----
>  arch/x86/kernel/tsc.c                 |  2 +-
>  arch/x86/xen/time.c                   | 11 ++++-------
>  drivers/clocksource/hyperv_timer.c    |  5 +++--
>  drivers/xen/time.c                    |  2 +-
>  12 files changed, 42 insertions(+), 29 deletions(-)
> 
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index 21f851179ff0..7ccd4a80788c 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -771,6 +771,7 @@ 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 30f76b966857..b4ee331d29a7 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..1e45b46fae84 100644
> --- a/arch/x86/include/asm/paravirt.h
> +++ b/arch/x86/include/asm/paravirt.h
> @@ -15,11 +15,22 @@
>  #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);

Did you build this before sending?

I'm test-applying this on rc6 + tip/master so I probably am using a
different tree so it looks like something has changed in the meantime.
-rc6 has a couple of Xen changes which made applying those to need some
wiggling in...

Maybe you should redo them ontop of tip/master. That is, *if* they're
going to eventually go through tip. The diffstat has Xen stuff too so we
might need some synchronization here what goes where how...

./arch/x86/include/asm/paravirt.h:24:1: warning: data definition has no type or storage class
   24 | DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
      | ^~~~~~~~~~~~~~~~~~~
./arch/x86/include/asm/paravirt.h:24:1: error: type defaults to ‘int’ in declaration of ‘DECLARE_STATIC_CALL’ [-Werror=implicit-int]
./arch/x86/include/asm/paravirt.h:24:1: warning: parameter names (without types) in function declaration
./arch/x86/include/asm/paravirt.h:25:1: warning: data definition has no type or storage class
   25 | DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock);
      | ^~~~~~~~~~~~~~~~~~~
./arch/x86/include/asm/paravirt.h:25:1: error: type defaults to ‘int’ in declaration of ‘DECLARE_STATIC_CALL’ [-Werror=implicit-int]
./arch/x86/include/asm/paravirt.h:25:1: warning: parameter names (without types) in function declaration
./arch/x86/include/asm/paravirt.h: In function ‘paravirt_sched_clock’:
./arch/x86/include/asm/paravirt.h:33:9: error: implicit declaration of function ‘static_call’ [-Werror=implicit-function-declaration]
   33 |  return static_call(pv_sched_clock)();
      |         ^~~~~~~~~~~
./arch/x86/include/asm/paravirt.h:33:21: error: ‘pv_sched_clock’ undeclared (first use in this function); did you mean ‘dummy_sched_clock’?
   33 |  return static_call(pv_sched_clock)();
      |                     ^~~~~~~~~~~~~~
      |                     dummy_sched_clock
./arch/x86/include/asm/paravirt.h:33:21: note: each undeclared identifier is reported only once for each function it appears in
./arch/x86/include/asm/paravirt.h: In function ‘paravirt_steal_clock’:
./arch/x86/include/asm/paravirt.h:47:21: error: ‘pv_steal_clock’ undeclared (first use in this function); did you mean ‘dummy_steal_clock’?
   47 |  return static_call(pv_steal_clock)(cpu);
      |                     ^~~~~~~~~~~~~~
      |                     dummy_steal_clock
cc1: some warnings being treated as errors
make[1]: *** [scripts/Makefile.build:117: arch/x86/kernel/asm-offsets.s] Error 1
make: *** [Makefile:1200: prepare0] Error 2

Thx.

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

[tip: x86/paravirt] x86/pv: Rework arch_local_irq_restore() to not use popf

[tip-bot2 for Juergen Gross]

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

Commit-ID:     ab234a260b1f625b26cbefa93ca365b0ae66df33
Gitweb:        https://git.kernel.org/tip/ab234a260b1f625b26cbefa93ca365b0ae66df33
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Wed, 20 Jan 2021 14:55:46 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Wed, 10 Feb 2021 12:36:45 +01:00

x86/pv: Rework arch_local_irq_restore() to not use popf

POPF is a rather expensive operation, so don't use it for restoring
irq flags. Instead, test whether interrupts are enabled in the flags
parameter and enable interrupts via STI in that case.

This results in the restore_fl paravirt op to be no longer needed.

Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210120135555.32594-7-jgross@suse.com
---
 arch/x86/include/asm/irqflags.h       | 20 +++++--------------
 arch/x86/include/asm/paravirt.h       |  5 +-----
 arch/x86/include/asm/paravirt_types.h |  7 ++-----
 arch/x86/kernel/irqflags.S            | 11 +----------
 arch/x86/kernel/paravirt.c            |  1 +-
 arch/x86/kernel/paravirt_patch.c      |  3 +---
 arch/x86/xen/enlighten_pv.c           |  2 +--
 arch/x86/xen/irq.c                    | 23 +---------------------
 arch/x86/xen/xen-asm.S                | 28 +--------------------------
 arch/x86/xen/xen-ops.h                |  1 +-
 10 files changed, 8 insertions(+), 93 deletions(-)

diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index e585a47..144d70e 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -35,15 +35,6 @@ extern __always_inline unsigned long native_save_fl(void)
 	return flags;
 }
 
-extern inline void native_restore_fl(unsigned long flags);
-extern inline void native_restore_fl(unsigned long flags)
-{
-	asm volatile("push %0 ; popf"
-		     : /* no output */
-		     :"g" (flags)
-		     :"memory", "cc");
-}
-
 static __always_inline void native_irq_disable(void)
 {
 	asm volatile("cli": : :"memory");
@@ -79,11 +70,6 @@ static __always_inline unsigned long arch_local_save_flags(void)
 	return native_save_fl();
 }
 
-static __always_inline void arch_local_irq_restore(unsigned long flags)
-{
-	native_restore_fl(flags);
-}
-
 static __always_inline void arch_local_irq_disable(void)
 {
 	native_irq_disable();
@@ -152,6 +138,12 @@ static __always_inline int arch_irqs_disabled(void)
 
 	return arch_irqs_disabled_flags(flags);
 }
+
+static __always_inline void arch_local_irq_restore(unsigned long flags)
+{
+	if (!arch_irqs_disabled_flags(flags))
+		arch_local_irq_enable();
+}
 #else
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_XEN_PV
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index dd43b11..4abf110 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -648,11 +648,6 @@ static inline notrace unsigned long arch_local_save_flags(void)
 	return PVOP_CALLEE0(unsigned long, irq.save_fl);
 }
 
-static inline notrace void arch_local_irq_restore(unsigned long f)
-{
-	PVOP_VCALLEE1(irq.restore_fl, f);
-}
-
 static inline notrace void arch_local_irq_disable(void)
 {
 	PVOP_VCALLEE0(irq.irq_disable);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0169365..de87087 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -168,16 +168,13 @@ struct pv_cpu_ops {
 struct pv_irq_ops {
 #ifdef CONFIG_PARAVIRT_XXL
 	/*
-	 * Get/set interrupt state.  save_fl and restore_fl are only
-	 * expected to use X86_EFLAGS_IF; all other bits
-	 * returned from save_fl are undefined, and may be ignored by
-	 * restore_fl.
+	 * Get/set interrupt state.  save_fl is expected to use X86_EFLAGS_IF;
+	 * all other bits returned from save_fl are undefined.
 	 *
 	 * NOTE: These functions callers expect the callee to preserve
 	 * more registers than the standard C calling convention.
 	 */
 	struct paravirt_callee_save save_fl;
-	struct paravirt_callee_save restore_fl;
 	struct paravirt_callee_save irq_disable;
 	struct paravirt_callee_save irq_enable;
 
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 0db0375..8ef3506 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -13,14 +13,3 @@ SYM_FUNC_START(native_save_fl)
 	ret
 SYM_FUNC_END(native_save_fl)
 EXPORT_SYMBOL(native_save_fl)
-
-/*
- * void native_restore_fl(unsigned long flags)
- * %eax/%rdi: flags
- */
-SYM_FUNC_START(native_restore_fl)
-	push %_ASM_ARG1
-	popf
-	ret
-SYM_FUNC_END(native_restore_fl)
-EXPORT_SYMBOL(native_restore_fl)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 18560b7..c60222a 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -320,7 +320,6 @@ struct paravirt_patch_template pv_ops = {
 
 	/* Irq ops. */
 	.irq.save_fl		= __PV_IS_CALLEE_SAVE(native_save_fl),
-	.irq.restore_fl		= __PV_IS_CALLEE_SAVE(native_restore_fl),
 	.irq.irq_disable	= __PV_IS_CALLEE_SAVE(native_irq_disable),
 	.irq.irq_enable		= __PV_IS_CALLEE_SAVE(native_irq_enable),
 	.irq.safe_halt		= native_safe_halt,
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index 2fada2c..abd27ec 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -25,7 +25,6 @@ struct patch_xxl {
 	const unsigned char	mmu_read_cr2[3];
 	const unsigned char	mmu_read_cr3[3];
 	const unsigned char	mmu_write_cr3[3];
-	const unsigned char	irq_restore_fl[2];
 	const unsigned char	cpu_wbinvd[2];
 	const unsigned char	mov64[3];
 };
@@ -37,7 +36,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.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
-	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
 };
@@ -71,7 +69,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	switch (type) {
 
 #ifdef CONFIG_PARAVIRT_XXL
-	PATCH_CASE(irq, restore_fl, xxl, insn_buff, len);
 	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);
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 6abf3f2..dc0a337 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1035,8 +1035,6 @@ void __init xen_setup_vcpu_info_placement(void)
 	 */
 	if (xen_have_vcpu_info_placement) {
 		pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
-		pv_ops.irq.restore_fl =
-			__PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
 		pv_ops.irq.irq_disable =
 			__PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
 		pv_ops.irq.irq_enable =
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 850c93f..dfa091d 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -42,28 +42,6 @@ asmlinkage __visible unsigned long xen_save_fl(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl);
 
-__visible void xen_restore_fl(unsigned long flags)
-{
-	struct vcpu_info *vcpu;
-
-	/* convert from IF type flag */
-	flags = !(flags & X86_EFLAGS_IF);
-
-	/* See xen_irq_enable() for why preemption must be disabled. */
-	preempt_disable();
-	vcpu = this_cpu_read(xen_vcpu);
-	vcpu->evtchn_upcall_mask = flags;
-
-	if (flags == 0) {
-		barrier(); /* unmask then check (avoid races) */
-		if (unlikely(vcpu->evtchn_upcall_pending))
-			xen_force_evtchn_callback();
-		preempt_enable();
-	} else
-		preempt_enable_no_resched();
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
-
 asmlinkage __visible void xen_irq_disable(void)
 {
 	/* There's a one instruction preempt window here.  We need to
@@ -118,7 +96,6 @@ static void xen_halt(void)
 
 static const struct pv_irq_ops xen_irq_ops __initconst = {
 	.save_fl = PV_CALLEE_SAVE(xen_save_fl),
-	.restore_fl = PV_CALLEE_SAVE(xen_restore_fl),
 	.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
 	.irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
 
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1d738c5..02f3134 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -72,34 +72,6 @@ SYM_FUNC_START(xen_save_fl_direct)
 	ret
 SYM_FUNC_END(xen_save_fl_direct)
 
-
-/*
- * In principle the caller should be passing us a value return from
- * xen_save_fl_direct, but for robustness sake we test only the
- * X86_EFLAGS_IF flag rather than the whole byte. After setting the
- * interrupt mask state, it checks for unmasked pending events and
- * enters the hypervisor to get them delivered if so.
- */
-SYM_FUNC_START(xen_restore_fl_direct)
-	FRAME_BEGIN
-	testw $X86_EFLAGS_IF, %di
-	setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
-	/*
-	 * Preempt here doesn't matter because that will deal with any
-	 * pending interrupts.  The pending check may end up being run
-	 * on the wrong CPU, but that doesn't hurt.
-	 */
-
-	/* check for unmasked and pending */
-	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
-	jnz 1f
-	call check_events
-1:
-	FRAME_END
-	ret
-SYM_FUNC_END(xen_restore_fl_direct)
-
-
 /*
  * Force an event check by making a hypercall, but preserve regs
  * before making the call.
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index b2fd80a..8d7ec49 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -131,7 +131,6 @@ static inline void __init xen_efi_init(struct boot_params *boot_params)
 __visible void xen_irq_enable_direct(void);
 __visible void xen_irq_disable_direct(void);
 __visible unsigned long xen_save_fl_direct(void);
-__visible void xen_restore_fl_direct(unsigned long);
 
 __visible unsigned long xen_read_cr2(void);
 __visible unsigned long xen_read_cr2_direct(void);

[tip: x86/paravirt] x86/xen: Use specific Xen pv interrupt entry for DF

[tip-bot2 for Juergen Gross]

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

Commit-ID:     5b4c6d65019bff65757f61adbbad5e45a333b800
Gitweb:        https://git.kernel.org/tip/5b4c6d65019bff65757f61adbbad5e45a333b800
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Wed, 20 Jan 2021 14:55:43 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Wed, 10 Feb 2021 12:13:40 +01:00

x86/xen: Use specific Xen pv interrupt entry for DF

Xen PV guests don't use IST. For double fault interrupts, switch to
the same model as NMI.

Correct a typo in a comment while copying it.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210120135555.32594-4-jgross@suse.com
---
 arch/x86/include/asm/idtentry.h |  3 +++
 arch/x86/xen/enlighten_pv.c     | 10 ++++++++--
 arch/x86/xen/xen-asm.S          |  2 +-
 3 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 616909e..41e2e2e 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -608,6 +608,9 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
 
 /* #DF */
 DECLARE_IDTENTRY_DF(X86_TRAP_DF,	exc_double_fault);
+#ifdef CONFIG_XEN_PV
+DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_DF,	xenpv_exc_double_fault);
+#endif
 
 /* #VC */
 #ifdef CONFIG_AMD_MEM_ENCRYPT
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 9db1d31..1fec2ee 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -567,10 +567,16 @@ void noist_exc_debug(struct pt_regs *regs);
 
 DEFINE_IDTENTRY_RAW(xenpv_exc_nmi)
 {
-	/* On Xen PV, NMI doesn't use IST.  The C part is the sane as native. */
+	/* On Xen PV, NMI doesn't use IST.  The C part is the same as native. */
 	exc_nmi(regs);
 }
 
+DEFINE_IDTENTRY_RAW_ERRORCODE(xenpv_exc_double_fault)
+{
+	/* On Xen PV, DF doesn't use IST.  The C part is the same as native. */
+	exc_double_fault(regs, error_code);
+}
+
 DEFINE_IDTENTRY_RAW(xenpv_exc_debug)
 {
 	/*
@@ -622,7 +628,7 @@ struct trap_array_entry {
 
 static struct trap_array_entry trap_array[] = {
 	TRAP_ENTRY_REDIR(exc_debug,			true  ),
-	TRAP_ENTRY(exc_double_fault,			true  ),
+	TRAP_ENTRY_REDIR(exc_double_fault,		true  ),
 #ifdef CONFIG_X86_MCE
 	TRAP_ENTRY_REDIR(exc_machine_check,		true  ),
 #endif
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index cd330ce..eac9dac 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -161,7 +161,7 @@ xen_pv_trap asm_exc_overflow
 xen_pv_trap asm_exc_bounds
 xen_pv_trap asm_exc_invalid_op
 xen_pv_trap asm_exc_device_not_available
-xen_pv_trap asm_exc_double_fault
+xen_pv_trap asm_xenpv_exc_double_fault
 xen_pv_trap asm_exc_coproc_segment_overrun
 xen_pv_trap asm_exc_invalid_tss
 xen_pv_trap asm_exc_segment_not_present

[tip: x86/paravirt] x86/xen: Use specific Xen pv interrupt entry for MCE

[tip-bot2 for Juergen Gross]

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

Commit-ID:     c3d7fa6684b5b3a07a48fc379d27bfb8a96661d9
Gitweb:        https://git.kernel.org/tip/c3d7fa6684b5b3a07a48fc379d27bfb8a96661d9
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Wed, 20 Jan 2021 14:55:42 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Wed, 10 Feb 2021 12:07:10 +01:00

x86/xen: Use specific Xen pv interrupt entry for MCE

Xen PV guests don't use IST. For machine check interrupts, switch to the
same model as debug interrupts.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210120135555.32594-3-jgross@suse.com
---
 arch/x86/include/asm/idtentry.h |  3 +++
 arch/x86/xen/enlighten_pv.c     | 16 +++++++++++++++-
 arch/x86/xen/xen-asm.S          |  2 +-
 3 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index f656aab..616909e 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -585,6 +585,9 @@ DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);
 #else
 DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	exc_machine_check);
 #endif
+#ifdef CONFIG_XEN_PV
+DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	xenpv_exc_machine_check);
+#endif
 #endif
 
 /* NMI */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 9a5a50c..9db1d31 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -590,6 +590,20 @@ DEFINE_IDTENTRY_RAW(exc_xen_unknown_trap)
 	BUG();
 }
 
+#ifdef CONFIG_X86_MCE
+DEFINE_IDTENTRY_RAW(xenpv_exc_machine_check)
+{
+	/*
+	 * There's no IST on Xen PV, but we still need to dispatch
+	 * to the correct handler.
+	 */
+	if (user_mode(regs))
+		noist_exc_machine_check(regs);
+	else
+		exc_machine_check(regs);
+}
+#endif
+
 struct trap_array_entry {
 	void (*orig)(void);
 	void (*xen)(void);
@@ -610,7 +624,7 @@ static struct trap_array_entry trap_array[] = {
 	TRAP_ENTRY_REDIR(exc_debug,			true  ),
 	TRAP_ENTRY(exc_double_fault,			true  ),
 #ifdef CONFIG_X86_MCE
-	TRAP_ENTRY(exc_machine_check,			true  ),
+	TRAP_ENTRY_REDIR(exc_machine_check,		true  ),
 #endif
 	TRAP_ENTRY_REDIR(exc_nmi,			true  ),
 	TRAP_ENTRY(exc_int3,				false ),
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 53cf8aa..cd330ce 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -172,7 +172,7 @@ xen_pv_trap asm_exc_spurious_interrupt_bug
 xen_pv_trap asm_exc_coprocessor_error
 xen_pv_trap asm_exc_alignment_check
 #ifdef CONFIG_X86_MCE
-xen_pv_trap asm_exc_machine_check
+xen_pv_trap asm_xenpv_exc_machine_check
 #endif /* CONFIG_X86_MCE */
 xen_pv_trap asm_exc_simd_coprocessor_error
 #ifdef CONFIG_IA32_EMULATION

[tip: x86/paravirt] x86/pv: Switch SWAPGS to ALTERNATIVE

[tip-bot2 for Juergen Gross]

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

Commit-ID:     53c9d9240944088274aadbbbafc6138ca462db4f
Gitweb:        https://git.kernel.org/tip/53c9d9240944088274aadbbbafc6138ca462db4f
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Wed, 20 Jan 2021 14:55:44 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Wed, 10 Feb 2021 12:25:49 +01:00

x86/pv: Switch SWAPGS to ALTERNATIVE

SWAPGS is used only for interrupts coming from user mode or for
returning to user mode. So there is no reason to use the PARAVIRT
framework, as it can easily be replaced by an ALTERNATIVE depending
on X86_FEATURE_XENPV.

There are several instances using the PV-aware SWAPGS macro in paths
which are never executed in a Xen PV guest. Replace those with the
plain swapgs instruction. For SWAPGS_UNSAFE_STACK the same applies.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210120135555.32594-5-jgross@suse.com
---
 arch/x86/entry/entry_64.S             | 10 +++++-----
 arch/x86/include/asm/irqflags.h       | 20 ++++++++------------
 arch/x86/include/asm/paravirt.h       | 20 --------------------
 arch/x86/include/asm/paravirt_types.h |  2 --
 arch/x86/kernel/asm-offsets_64.c      |  1 -
 arch/x86/kernel/paravirt.c            |  1 -
 arch/x86/kernel/paravirt_patch.c      |  3 ---
 arch/x86/xen/enlighten_pv.c           |  3 ---
 8 files changed, 13 insertions(+), 47 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index cad0870..a876204 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -669,7 +669,7 @@ native_irq_return_ldt:
 	 */
 
 	pushq	%rdi				/* Stash user RDI */
-	SWAPGS					/* to kernel GS */
+	swapgs					/* to kernel GS */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi	/* to kernel CR3 */
 
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
@@ -699,7 +699,7 @@ native_irq_return_ldt:
 	orq	PER_CPU_VAR(espfix_stack), %rax
 
 	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
-	SWAPGS					/* to user GS */
+	swapgs					/* to user GS */
 	popq	%rdi				/* Restore user RDI */
 
 	movq	%rax, %rsp
@@ -943,7 +943,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	ret
 
 .Lparanoid_entry_swapgs:
-	SWAPGS
+	swapgs
 
 	/*
 	 * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
@@ -1001,7 +1001,7 @@ SYM_CODE_START_LOCAL(paranoid_exit)
 	jnz		restore_regs_and_return_to_kernel
 
 	/* We are returning to a context with user GSBASE */
-	SWAPGS_UNSAFE_STACK
+	swapgs
 	jmp		restore_regs_and_return_to_kernel
 SYM_CODE_END(paranoid_exit)
 
@@ -1426,7 +1426,7 @@ nmi_no_fsgsbase:
 	jnz	nmi_restore
 
 nmi_swapgs:
-	SWAPGS_UNSAFE_STACK
+	swapgs
 
 nmi_restore:
 	POP_REGS
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 2dfc8d3..8c86ede 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -131,18 +131,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #define SAVE_FLAGS(x)		pushfq; popq %rax
 #endif
 
-#define SWAPGS	swapgs
-/*
- * Currently paravirt can't handle swapgs nicely when we
- * don't have a stack we can rely on (such as a user space
- * stack).  So we either find a way around these or just fault
- * and emulate if a guest tries to call swapgs directly.
- *
- * Either way, this is a good way to document that we don't
- * have a reliable stack. x86_64 only.
- */
-#define SWAPGS_UNSAFE_STACK	swapgs
-
 #define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
@@ -170,6 +158,14 @@ static __always_inline int arch_irqs_disabled(void)
 
 	return arch_irqs_disabled_flags(flags);
 }
+#else
+#ifdef CONFIG_X86_64
+#ifdef CONFIG_XEN_PV
+#define SWAPGS	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
+#else
+#define SWAPGS	swapgs
+#endif
+#endif
 #endif /* !__ASSEMBLY__ */
 
 #endif
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f8dce11..f2ebe10 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -776,26 +776,6 @@ extern void default_banner(void);
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
-/*
- * If swapgs is used while the userspace stack is still current,
- * there's no way to call a pvop.  The PV replacement *must* be
- * inlined, or the swapgs instruction must be trapped and emulated.
- */
-#define SWAPGS_UNSAFE_STACK						\
-	PARA_SITE(PARA_PATCH(PV_CPU_swapgs), swapgs)
-
-/*
- * Note: swapgs is very special, and in practise is either going to be
- * implemented with a single "swapgs" instruction or something very
- * special.  Either way, we don't need to save any registers for
- * it.
- */
-#define SWAPGS								\
-	PARA_SITE(PARA_PATCH(PV_CPU_swapgs),				\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_CPU_swapgs);		\
-		 )
-
 #define USERGS_SYSRET64							\
 	PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64),			\
 		  ANNOTATE_RETPOLINE_SAFE;				\
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index b6b02b7..130f428 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -168,8 +168,6 @@ struct pv_cpu_ops {
 	   frame set up. */
 	void (*iret)(void);
 
-	void (*swapgs)(void);
-
 	void (*start_context_switch)(struct task_struct *prev);
 	void (*end_context_switch)(struct task_struct *next);
 #endif
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 828be79..1354bc3 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -15,7 +15,6 @@ int main(void)
 #ifdef CONFIG_PARAVIRT_XXL
 	OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
 	       cpu.usergs_sysret64);
-	OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs);
 #ifdef CONFIG_DEBUG_ENTRY
 	OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
 #endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 6c3407b..5e5fcf5 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -312,7 +312,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.usergs_sysret64	= native_usergs_sysret64,
 	.cpu.iret		= native_iret,
-	.cpu.swapgs		= native_swapgs,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
 	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index ace6e33..7c518b0 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -28,7 +28,6 @@ struct patch_xxl {
 	const unsigned char	irq_restore_fl[2];
 	const unsigned char	cpu_wbinvd[2];
 	const unsigned char	cpu_usergs_sysret64[6];
-	const unsigned char	cpu_swapgs[3];
 	const unsigned char	mov64[3];
 };
 
@@ -43,7 +42,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
 	.cpu_usergs_sysret64	= { 0x0f, 0x01, 0xf8,
 				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
-	.cpu_swapgs		= { 0x0f, 0x01, 0xf8 },	// swapgs
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
 };
 
@@ -86,7 +84,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
 
 	PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len);
-	PATCH_CASE(cpu, swapgs, xxl, insn_buff, len);
 	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
 #endif
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 1fec2ee..95f3799 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1098,9 +1098,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 #endif
 	.io_delay = xen_io_delay,
 
-	/* Xen takes care of %gs when switching to usermode for us */
-	.swapgs = paravirt_nop,
-
 	.start_context_switch = paravirt_start_context_switch,
 	.end_context_switch = xen_end_context_switch,
 };

[tip: x86/paravirt] x86/xen: Drop USERGS_SYSRET64 paravirt call

[tip-bot2 for Juergen Gross]

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

Commit-ID:     afd30525a659ac0ae0904f0cb4a2ca75522c3123
Gitweb:        https://git.kernel.org/tip/afd30525a659ac0ae0904f0cb4a2ca75522c3123
Author:        Juergen Gross <jgross@suse.com>
AuthorDate:    Wed, 20 Jan 2021 14:55:45 +01:00
Committer:     Borislav Petkov <bp@suse.de>
CommitterDate: Wed, 10 Feb 2021 12:32:07 +01:00

x86/xen: Drop USERGS_SYSRET64 paravirt call

USERGS_SYSRET64 is used to return from a syscall via SYSRET, but
a Xen PV guest will nevertheless use the IRET hypercall, as there
is no sysret PV hypercall defined.

So instead of testing all the prerequisites for doing a sysret and
then mangling the stack for Xen PV again for doing an iret just use
the iret exit from the beginning.

This can easily be done via an ALTERNATIVE like it is done for the
sysenter compat case already.

It should be noted that this drops the optimization in Xen for not
restoring a few registers when returning to user mode, but it seems
as if the saved instructions in the kernel more than compensate for
this drop (a kernel build in a Xen PV guest was slightly faster with
this patch applied).

While at it remove the stale sysret32 remnants.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210120135555.32594-6-jgross@suse.com
---
 arch/x86/entry/entry_64.S             | 16 +++++++---------
 arch/x86/include/asm/irqflags.h       |  6 ------
 arch/x86/include/asm/paravirt.h       |  5 -----
 arch/x86/include/asm/paravirt_types.h |  8 --------
 arch/x86/kernel/asm-offsets_64.c      |  2 --
 arch/x86/kernel/paravirt.c            |  5 +----
 arch/x86/kernel/paravirt_patch.c      |  4 ----
 arch/x86/xen/enlighten_pv.c           |  1 -
 arch/x86/xen/xen-asm.S                | 20 --------------------
 arch/x86/xen/xen-ops.h                |  2 --
 10 files changed, 8 insertions(+), 61 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a876204..ce0464d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -46,14 +46,6 @@
 .code64
 .section .entry.text, "ax"
 
-#ifdef CONFIG_PARAVIRT_XXL
-SYM_CODE_START(native_usergs_sysret64)
-	UNWIND_HINT_EMPTY
-	swapgs
-	sysretq
-SYM_CODE_END(native_usergs_sysret64)
-#endif /* CONFIG_PARAVIRT_XXL */
-
 /*
  * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
  *
@@ -123,7 +115,12 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * Try to use SYSRET instead of IRET if we're returning to
 	 * a completely clean 64-bit userspace context.  If we're not,
 	 * go to the slow exit path.
+	 * In the Xen PV case we must use iret anyway.
 	 */
+
+	ALTERNATIVE "", "jmp	swapgs_restore_regs_and_return_to_usermode", \
+		X86_FEATURE_XENPV
+
 	movq	RCX(%rsp), %rcx
 	movq	RIP(%rsp), %r11
 
@@ -215,7 +212,8 @@ syscall_return_via_sysret:
 
 	popq	%rdi
 	popq	%rsp
-	USERGS_SYSRET64
+	swapgs
+	sysretq
 SYM_CODE_END(entry_SYSCALL_64)
 
 /*
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 8c86ede..e585a47 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -132,12 +132,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #endif
 
 #define INTERRUPT_RETURN	jmp native_iret
-#define USERGS_SYSRET64				\
-	swapgs;					\
-	sysretq;
-#define USERGS_SYSRET32				\
-	swapgs;					\
-	sysretl
 
 #else
 #define INTERRUPT_RETURN		iret
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f2ebe10..dd43b11 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -776,11 +776,6 @@ extern void default_banner(void);
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
-#define USERGS_SYSRET64							\
-	PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64),			\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);)
-
 #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 130f428..0169365 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -156,14 +156,6 @@ struct pv_cpu_ops {
 
 	u64 (*read_pmc)(int counter);
 
-	/*
-	 * Switch to usermode gs and return to 64-bit usermode using
-	 * sysret.  Only used in 64-bit kernels to return to 64-bit
-	 * processes.  Usermode register state, including %rsp, must
-	 * already be restored.
-	 */
-	void (*usergs_sysret64)(void);
-
 	/* Normal iret.  Jump to this with the standard iret stack
 	   frame set up. */
 	void (*iret)(void);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 1354bc3..b14533a 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -13,8 +13,6 @@ int main(void)
 {
 #ifdef CONFIG_PARAVIRT
 #ifdef CONFIG_PARAVIRT_XXL
-	OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
-	       cpu.usergs_sysret64);
 #ifdef CONFIG_DEBUG_ENTRY
 	OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
 #endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 5e5fcf5..18560b7 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -135,8 +135,7 @@ 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) ||
-		 type == PARAVIRT_PATCH(cpu.usergs_sysret64))
+	else if (type == PARAVIRT_PATCH(cpu.iret))
 		/* If operation requires a jmp, then jmp */
 		ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
 #endif
@@ -170,7 +169,6 @@ static u64 native_steal_clock(int cpu)
 
 /* These are in entry.S */
 extern void native_iret(void);
-extern void native_usergs_sysret64(void);
 
 static struct resource reserve_ioports = {
 	.start = 0,
@@ -310,7 +308,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.load_sp0		= native_load_sp0,
 
-	.cpu.usergs_sysret64	= native_usergs_sysret64,
 	.cpu.iret		= native_iret,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index 7c518b0..2fada2c 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -27,7 +27,6 @@ struct patch_xxl {
 	const unsigned char	mmu_write_cr3[3];
 	const unsigned char	irq_restore_fl[2];
 	const unsigned char	cpu_wbinvd[2];
-	const unsigned char	cpu_usergs_sysret64[6];
 	const unsigned char	mov64[3];
 };
 
@@ -40,8 +39,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
 	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
-	.cpu_usergs_sysret64	= { 0x0f, 0x01, 0xf8,
-				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
 };
 
@@ -83,7 +80,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
 	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
 
-	PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len);
 	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
 #endif
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 95f3799..6abf3f2 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1073,7 +1073,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_pmc = xen_read_pmc,
 
 	.iret = xen_iret,
-	.usergs_sysret64 = xen_sysret64,
 
 	.load_tr_desc = paravirt_nop,
 	.set_ldt = xen_set_ldt,
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index eac9dac..1d738c5 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -215,26 +215,6 @@ SYM_CODE_START(xen_iret)
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
 
-SYM_CODE_START(xen_sysret64)
-	/*
-	 * We're already on the usermode stack at this point, but
-	 * still with the kernel gs, so we can easily switch back.
-	 *
-	 * tss.sp2 is scratch space.
-	 */
-	movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
-	pushq $__USER_DS
-	pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	pushq %r11
-	pushq $__USER_CS
-	pushq %rcx
-
-	pushq $VGCF_in_syscall
-	jmp hypercall_iret
-SYM_CODE_END(xen_sysret64)
-
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
  * means we have:
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9546c33..b2fd80a 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -138,8 +138,6 @@ __visible unsigned long xen_read_cr2_direct(void);
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
-__visible void xen_sysret32(void);
-__visible void xen_sysret64(void);
 
 extern int xen_panic_handler_init(void);
 

[PATCH v4 05/15] x86/xen: drop USERGS_SYSRET64 paravirt call

[Juergen Gross]

USERGS_SYSRET64 is used to return from a syscall via sysret, but
a Xen PV guest will nevertheless use the iret hypercall, as there
is no sysret PV hypercall defined.

So instead of testing all the prerequisites for doing a sysret and
then mangling the stack for Xen PV again for doing an iret just use
the iret exit from the beginning.

This can easily be done via an ALTERNATIVE like it is done for the
sysenter compat case already.

It should be noted that this drops the optimization in Xen for not
restoring a few registers when returning to user mode, but it seems
as if the saved instructions in the kernel more than compensate for
this drop (a kernel build in a Xen PV guest was slightly faster with
this patch applied).

While at it remove the stale sysret32 remnants.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V3:
- simplify ALTERNATIVE (Boris Petkov)
---
 arch/x86/entry/entry_64.S             | 16 +++++++---------
 arch/x86/include/asm/irqflags.h       |  6 ------
 arch/x86/include/asm/paravirt.h       |  5 -----
 arch/x86/include/asm/paravirt_types.h |  8 --------
 arch/x86/kernel/asm-offsets_64.c      |  2 --
 arch/x86/kernel/paravirt.c            |  5 +----
 arch/x86/kernel/paravirt_patch.c      |  4 ----
 arch/x86/xen/enlighten_pv.c           |  1 -
 arch/x86/xen/xen-asm.S                | 20 --------------------
 arch/x86/xen/xen-ops.h                |  2 --
 10 files changed, 8 insertions(+), 61 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a876204a73e0..ce0464d630a2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -46,14 +46,6 @@
 .code64
 .section .entry.text, "ax"
 
-#ifdef CONFIG_PARAVIRT_XXL
-SYM_CODE_START(native_usergs_sysret64)
-	UNWIND_HINT_EMPTY
-	swapgs
-	sysretq
-SYM_CODE_END(native_usergs_sysret64)
-#endif /* CONFIG_PARAVIRT_XXL */
-
 /*
  * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
  *
@@ -123,7 +115,12 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * Try to use SYSRET instead of IRET if we're returning to
 	 * a completely clean 64-bit userspace context.  If we're not,
 	 * go to the slow exit path.
+	 * In the Xen PV case we must use iret anyway.
 	 */
+
+	ALTERNATIVE "", "jmp	swapgs_restore_regs_and_return_to_usermode", \
+		X86_FEATURE_XENPV
+
 	movq	RCX(%rsp), %rcx
 	movq	RIP(%rsp), %r11
 
@@ -215,7 +212,8 @@ syscall_return_via_sysret:
 
 	popq	%rdi
 	popq	%rsp
-	USERGS_SYSRET64
+	swapgs
+	sysretq
 SYM_CODE_END(entry_SYSCALL_64)
 
 /*
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 8c86edefa115..e585a4705b8d 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -132,12 +132,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #endif
 
 #define INTERRUPT_RETURN	jmp native_iret
-#define USERGS_SYSRET64				\
-	swapgs;					\
-	sysretq;
-#define USERGS_SYSRET32				\
-	swapgs;					\
-	sysretl
 
 #else
 #define INTERRUPT_RETURN		iret
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f2ebe109a37e..dd43b1100a87 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -776,11 +776,6 @@ extern void default_banner(void);
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
-#define USERGS_SYSRET64							\
-	PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64),			\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);)
-
 #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 130f428b0cc8..0169365f1403 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -156,14 +156,6 @@ struct pv_cpu_ops {
 
 	u64 (*read_pmc)(int counter);
 
-	/*
-	 * Switch to usermode gs and return to 64-bit usermode using
-	 * sysret.  Only used in 64-bit kernels to return to 64-bit
-	 * processes.  Usermode register state, including %rsp, must
-	 * already be restored.
-	 */
-	void (*usergs_sysret64)(void);
-
 	/* Normal iret.  Jump to this with the standard iret stack
 	   frame set up. */
 	void (*iret)(void);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 1354bc30614d..b14533af7676 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -13,8 +13,6 @@ int main(void)
 {
 #ifdef CONFIG_PARAVIRT
 #ifdef CONFIG_PARAVIRT_XXL
-	OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
-	       cpu.usergs_sysret64);
 #ifdef CONFIG_DEBUG_ENTRY
 	OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
 #endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 5e5fcf5c376d..18560b71e717 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -135,8 +135,7 @@ 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) ||
-		 type == PARAVIRT_PATCH(cpu.usergs_sysret64))
+	else if (type == PARAVIRT_PATCH(cpu.iret))
 		/* If operation requires a jmp, then jmp */
 		ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
 #endif
@@ -170,7 +169,6 @@ static u64 native_steal_clock(int cpu)
 
 /* These are in entry.S */
 extern void native_iret(void);
-extern void native_usergs_sysret64(void);
 
 static struct resource reserve_ioports = {
 	.start = 0,
@@ -310,7 +308,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.load_sp0		= native_load_sp0,
 
-	.cpu.usergs_sysret64	= native_usergs_sysret64,
 	.cpu.iret		= native_iret,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index 7c518b08aa3c..2fada2c347c9 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -27,7 +27,6 @@ struct patch_xxl {
 	const unsigned char	mmu_write_cr3[3];
 	const unsigned char	irq_restore_fl[2];
 	const unsigned char	cpu_wbinvd[2];
-	const unsigned char	cpu_usergs_sysret64[6];
 	const unsigned char	mov64[3];
 };
 
@@ -40,8 +39,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
 	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
-	.cpu_usergs_sysret64	= { 0x0f, 0x01, 0xf8,
-				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
 };
 
@@ -83,7 +80,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
 	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
 
-	PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len);
 	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
 #endif
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 44bb18adfb51..5476423fc6d0 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1060,7 +1060,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_pmc = xen_read_pmc,
 
 	.iret = xen_iret,
-	.usergs_sysret64 = xen_sysret64,
 
 	.load_tr_desc = paravirt_nop,
 	.set_ldt = xen_set_ldt,
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1d054c915046..c0630fd9f44e 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -214,26 +214,6 @@ SYM_CODE_START(xen_iret)
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
 
-SYM_CODE_START(xen_sysret64)
-	/*
-	 * We're already on the usermode stack at this point, but
-	 * still with the kernel gs, so we can easily switch back.
-	 *
-	 * tss.sp2 is scratch space.
-	 */
-	movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
-	pushq $__USER_DS
-	pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	pushq %r11
-	pushq $__USER_CS
-	pushq %rcx
-
-	pushq $VGCF_in_syscall
-	jmp hypercall_iret
-SYM_CODE_END(xen_sysret64)
-
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
  * means we have:
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9546c3384c75..b2fd80a01a36 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -138,8 +138,6 @@ __visible unsigned long xen_read_cr2_direct(void);
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
-__visible void xen_sysret32(void);
-__visible void xen_sysret64(void);
 
 extern int xen_panic_handler_init(void);
 
-- 
2.26.2