Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit d75cd22f authored by Jeremy Fitzhardinge's avatar Jeremy Fitzhardinge Committed by Ingo Molnar
Browse files

x86/paravirt: split sysret and sysexit 



Don't conflate sysret and sysexit; they're different instructions with
different semantics, and may be in use at the same time (at least
within the same kernel, depending on whether its an Intel or AMD
system).

sysexit - just return to userspace, does no register restoration of
    any kind; must explicitly atomically enable interrupts.

sysret - reloads flags from r11, so no need to explicitly enable
    interrupts on 64-bit, responsible for restoring usermode %gs

Signed-off-by: default avatarJeremy Fitzhardinge <jeremy.fitzhardinge@citirx.com>
Cc: xen-devel <xen-devel@lists.xensource.com>
Cc: Stephen Tweedie <sct@redhat.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
parent e04e0a63

arch/x86/kernel/asm-offsets_32.c

+1 −1
Original line number Diff line number Diff line
@@ -111,7 +111,7 @@ void foo(void) 
	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);

	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);

	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);

	OFFSET(PV_CPU_irq_enable_syscall_ret, pv_cpu_ops, irq_enable_syscall_ret);

	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);

	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);

#endif

arch/x86/kernel/asm-offsets_64.c

+1 −1
Original line number Diff line number Diff line
@@ -62,7 +62,7 @@ int main(void) 
	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);

	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);

	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);

	OFFSET(PV_CPU_irq_enable_syscall_ret, pv_cpu_ops, irq_enable_syscall_ret);

	OFFSET(PV_CPU_usersp_sysret, pv_cpu_ops, usersp_sysret);

	OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);

	OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);

#endif

arch/x86/kernel/entry_32.S

+4 −4
Original line number Diff line number Diff line
@@ -58,7 +58,7 @@ 
 * for paravirtualization.  The following will never clobber any registers:

 *   INTERRUPT_RETURN (aka. "iret")

 *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")

 *   ENABLE_INTERRUPTS_SYSCALL_RET (aka "sti; sysexit").

 *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").

 *

 * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must

 * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
@@ -349,7 +349,7 @@ sysenter_past_esp: 
	xorl %ebp,%ebp

	TRACE_IRQS_ON

1:	mov  PT_FS(%esp), %fs

	ENABLE_INTERRUPTS_SYSCALL_RET

	ENABLE_INTERRUPTS_SYSEXIT

	CFI_ENDPROC

.pushsection .fixup,"ax"

2:	movl $0,PT_FS(%esp)
@@ -874,10 +874,10 @@ ENTRY(native_iret) 
.previous

END(native_iret)



ENTRY(native_irq_enable_syscall_ret)

ENTRY(native_irq_enable_sysexit)

	sti

	sysexit

END(native_irq_enable_syscall_ret)

END(native_irq_enable_sysexit)

#endif



KPROBE_ENTRY(int3)

arch/x86/kernel/entry_64.S

+2 −2
Original line number Diff line number Diff line
@@ -59,7 +59,7 @@ 
#endif	



#ifdef CONFIG_PARAVIRT

ENTRY(native_irq_enable_syscall_ret)

ENTRY(native_usersp_sysret)

	movq	%gs:pda_oldrsp,%rsp

	swapgs

	sysretq
@@ -275,7 +275,7 @@ sysret_check: 
	CFI_REGISTER	rip,rcx

	RESTORE_ARGS 0,-ARG_SKIP,1

	/*CFI_REGISTER	rflags,r11*/

	ENABLE_INTERRUPTS_SYSCALL_RET

	USERSP_SYSRET



	CFI_RESTORE_STATE

	/* Handle reschedules */

arch/x86/kernel/paravirt.c

+9 −3
Original line number Diff line number Diff line
@@ -140,7 +140,8 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, 
		/* If the operation is a nop, then nop the callsite */

		ret = paravirt_patch_nop();

	else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||

		 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_syscall_ret))

		 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||

		 type == PARAVIRT_PATCH(pv_cpu_ops.usersp_sysret))

		/* If operation requires a jmp, then jmp */

		ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);

	else
@@ -191,7 +192,8 @@ static void native_flush_tlb_single(unsigned long addr) 


/* These are in entry.S */

extern void native_iret(void);

extern void native_irq_enable_syscall_ret(void);

extern void native_irq_enable_sysexit(void);

extern void native_usersp_sysret(void);



static int __init print_banner(void)

{
@@ -327,7 +329,11 @@ struct pv_cpu_ops pv_cpu_ops = { 
	.write_idt_entry = native_write_idt_entry,

	.load_sp0 = native_load_sp0,



	.irq_enable_syscall_ret = native_irq_enable_syscall_ret,

#ifdef CONFIG_X86_32

	.irq_enable_sysexit = native_irq_enable_sysexit,

#else

	.usersp_sysret = native_usersp_sysret,

#endif

	.iret = native_iret,

	.swapgs = native_swapgs,