From: Juergen Gross <jgross@suse.com>
To: xen-devel@lists.xenproject.org, x86@kernel.org,
linux-kernel@vger.kernel.org,
virtualization@lists.linux-foundation.org
Cc: peterz@infradead.org, luto@kernel.org,
Juergen Gross <jgross@suse.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
"H. Peter Anvin" <hpa@zytor.com>, Deep Shah <sdeep@vmware.com>,
"VMware, Inc." <pv-drivers@vmware.com>,
Boris Ostrovsky <boris.ostrovsky@oracle.com>,
Stefano Stabellini <sstabellini@kernel.org>
Subject: [PATCH v2 04/12] x86/xen: drop USERGS_SYSRET64 paravirt call
Date: Fri, 20 Nov 2020 12:46:22 +0100 [thread overview]
Message-ID: <20201120114630.13552-5-jgross@suse.com> (raw)
In-Reply-To: <20201120114630.13552-1-jgross@suse.com>
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>
Acked-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
arch/x86/entry/entry_64.S | 22 +++++++++-------------
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, 10 insertions(+), 65 deletions(-)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a876204a73e0..df865eebd3d7 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.
*
@@ -123,12 +115,15 @@ 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.
*/
- movq RCX(%rsp), %rcx
- movq RIP(%rsp), %r11
- cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */
- jne swapgs_restore_regs_and_return_to_usermode
+ ALTERNATIVE __stringify( \
+ movq RCX(%rsp), %rcx; \
+ movq RIP(%rsp), %r11; \
+ cmpq %rcx, %r11; /* SYSRET requires RCX == RIP */ \
+ jne swapgs_restore_regs_and_return_to_usermode), \
+ "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
/*
* On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
@@ -215,7 +210,8 @@ 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 5647bcdba776..8121cf9b8d81 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 903d71884fa2..55d8b7950e61 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -157,14 +157,6 @@ 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
next prev parent reply other threads:[~2020-11-20 11:46 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-20 11:46 [PATCH v2 00/12] x86: major paravirt cleanup Juergen Gross
2020-11-20 11:46 ` [PATCH v2 01/12] x86/xen: use specific Xen pv interrupt entry for MCE Juergen Gross
2020-12-09 21:03 ` Thomas Gleixner
2020-11-20 11:46 ` [PATCH v2 02/12] x86/xen: use specific Xen pv interrupt entry for DF Juergen Gross
2020-12-09 21:03 ` Thomas Gleixner
2020-11-20 11:46 ` [PATCH v2 03/12] x86/pv: switch SWAPGS to ALTERNATIVE Juergen Gross
2020-11-27 11:31 ` Borislav Petkov
2020-12-09 21:07 ` Thomas Gleixner
2020-11-20 11:46 ` Juergen Gross [this message]
2020-12-02 12:32 ` [PATCH v2 04/12] x86/xen: drop USERGS_SYSRET64 paravirt call Borislav Petkov
2020-12-02 14:48 ` Jürgen Groß
2020-12-02 17:08 ` Borislav Petkov
2020-11-20 11:46 ` [PATCH v2 05/12] x86: rework arch_local_irq_restore() to not use popf Juergen Gross
2020-11-20 11:59 ` Peter Zijlstra
2020-11-20 12:05 ` Jürgen Groß
2020-11-22 6:55 ` Jürgen Groß
2020-11-22 21:44 ` Andy Lutomirski
2020-11-23 5:21 ` Jürgen Groß
2020-11-23 15:15 ` Andy Lutomirski
2020-12-09 13:27 ` Mark Rutland
2020-12-09 14:02 ` Mark Rutland
2020-12-09 14:05 ` Jürgen Groß
2020-12-09 18:15 ` Mark Rutland
2020-12-09 18:54 ` Thomas Gleixner
2020-12-10 11:10 ` Mark Rutland
2020-12-10 20:15 ` x86/ioapic: Cleanup the timer_works() irqflags mess Thomas Gleixner
2020-12-11 5:10 ` Jürgen Groß
2020-11-27 2:20 ` [x86] 97e8f0134a: fio.write_iops 8.6% improvement kernel test robot
2020-11-20 11:46 ` [PATCH v2 06/12] x86/paravirt: switch time pvops functions to use static_call() Juergen Gross
2020-11-20 12:01 ` Peter Zijlstra
2020-11-20 12:07 ` Jürgen Groß
2020-11-20 11:46 ` [PATCH v2 07/12] x86: add new features for paravirt patching Juergen Gross
2020-12-08 18:43 ` Borislav Petkov
2020-12-09 7:30 ` Jürgen Groß
2020-12-09 12:03 ` Borislav Petkov
2020-12-09 12:22 ` Jürgen Groß
2020-12-10 17:58 ` Borislav Petkov
2020-11-20 11:46 ` [PATCH v2 08/12] x86/paravirt: remove no longer needed 32-bit pvops cruft Juergen Gross
2020-11-20 12:08 ` Peter Zijlstra
2020-11-20 12:16 ` Jürgen Groß
2020-11-20 16:52 ` Arvind Sankar
2020-11-20 11:46 ` [PATCH v2 09/12] x86/paravirt: switch iret pvops to ALTERNATIVE Juergen Gross
2020-11-20 11:46 ` [PATCH v2 10/12] x86/paravirt: add new macros PVOP_ALT* supporting pvops in ALTERNATIVEs Juergen Gross
2020-11-20 11:46 ` [PATCH v2 11/12] x86/paravirt: switch functions with custom code to ALTERNATIVE Juergen Gross
2020-11-20 15:46 ` kernel test robot
2020-11-25 15:46 ` [x86/paravirt] fd8d46a7a2: kernel-selftests.livepatch.test-callbacks.sh.fail kernel test robot
2020-11-20 11:46 ` [PATCH v2 12/12] x86/paravirt: have only one paravirt patch function Juergen Gross
2020-11-20 14:18 ` kernel test robot
2020-11-20 12:53 ` [PATCH v2 00/12] x86: major paravirt cleanup Peter Zijlstra
2020-11-23 13:43 ` Peter Zijlstra
2020-12-15 11:42 ` Jürgen Groß
2020-12-15 14:18 ` Peter Zijlstra
2020-12-15 14:54 ` Peter Zijlstra
2020-12-15 15:07 ` Jürgen Groß
2020-12-16 0:38 ` Josh Poimboeuf
2020-12-16 8:40 ` Peter Zijlstra
2020-12-16 16:56 ` Josh Poimboeuf
2020-12-16 17:58 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201120114630.13552-5-jgross@suse.com \
--to=jgross@suse.com \
--cc=boris.ostrovsky@oracle.com \
--cc=bp@alien8.de \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=pv-drivers@vmware.com \
--cc=sdeep@vmware.com \
--cc=sstabellini@kernel.org \
--cc=tglx@linutronix.de \
--cc=virtualization@lists.linux-foundation.org \
--cc=x86@kernel.org \
--cc=xen-devel@lists.xenproject.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).