From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Andy Lutomirski <luto@kernel.org>,
Rik van Riel <riel@redhat.com>, Borislav Petkov <bp@alien8.de>,
Brian Gerst <brgerst@gmail.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
Denys Vlasenko <dvlasenk@redhat.com>,
Fenghua Yu <fenghua.yu@intel.com>,
"H. Peter Anvin" <hpa@zytor.com>,
Josh Poimboeuf <jpoimboe@redhat.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Oleg Nesterov <oleg@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Quentin Casasnovas <quentin.casasnovas@oracle.com>,
Thomas Gleixner <tglx@linutronix.de>,
pbonzini@redhat.com, Ingo Molnar <mingo@kernel.org>,
Daniel Sangorrin <daniel.sangorrin@toshiba.co.jp>
Subject: [PATCH 4.9 32/35] x86/fpu: Remove use_eager_fpu()
Date: Thu, 11 Oct 2018 17:35:34 +0200 [thread overview]
Message-ID: <20181011152521.462158381@linuxfoundation.org> (raw)
In-Reply-To: <20181011152520.174949126@linuxfoundation.org>
4.9-stable review patch. If anyone has any objections, please let me know.
------------------
From: Andy Lutomirski <luto@kernel.org>
commit c592b57347069abfc0dcad3b3a302cf882602597 upstream.
This removes all the obvious code paths that depend on lazy FPU mode.
It shouldn't change the generated code at all.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: pbonzini@redhat.com
Link: http://lkml.kernel.org/r/1475627678-20788-5-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Daniel Sangorrin <daniel.sangorrin@toshiba.co.jp>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/x86/crypto/crc32c-intel_glue.c | 17 ++++-------------
arch/x86/include/asm/fpu/internal.h | 34 +---------------------------------
arch/x86/kernel/fpu/core.c | 36 ++++--------------------------------
arch/x86/kernel/fpu/signal.c | 8 +++-----
arch/x86/kernel/fpu/xstate.c | 9 ---------
arch/x86/kvm/cpuid.c | 4 +---
arch/x86/kvm/x86.c | 10 ----------
7 files changed, 13 insertions(+), 105 deletions(-)
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -48,21 +48,13 @@
#ifdef CONFIG_X86_64
/*
* use carryless multiply version of crc32c when buffer
- * size is >= 512 (when eager fpu is enabled) or
- * >= 1024 (when eager fpu is disabled) to account
+ * size is >= 512 to account
* for fpu state save/restore overhead.
*/
-#define CRC32C_PCL_BREAKEVEN_EAGERFPU 512
-#define CRC32C_PCL_BREAKEVEN_NOEAGERFPU 1024
+#define CRC32C_PCL_BREAKEVEN 512
asmlinkage unsigned int crc_pcl(const u8 *buffer, int len,
unsigned int crc_init);
-static int crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_EAGERFPU;
-#define set_pcl_breakeven_point() \
-do { \
- if (!use_eager_fpu()) \
- crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU; \
-} while (0)
#endif /* CONFIG_X86_64 */
static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length)
@@ -185,7 +177,7 @@ static int crc32c_pcl_intel_update(struc
* use faster PCL version if datasize is large enough to
* overcome kernel fpu state save/restore overhead
*/
- if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) {
+ if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) {
kernel_fpu_begin();
*crcp = crc_pcl(data, len, *crcp);
kernel_fpu_end();
@@ -197,7 +189,7 @@ static int crc32c_pcl_intel_update(struc
static int __crc32c_pcl_intel_finup(u32 *crcp, const u8 *data, unsigned int len,
u8 *out)
{
- if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) {
+ if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) {
kernel_fpu_begin();
*(__le32 *)out = ~cpu_to_le32(crc_pcl(data, len, *crcp));
kernel_fpu_end();
@@ -257,7 +249,6 @@ static int __init crc32c_intel_mod_init(
alg.update = crc32c_pcl_intel_update;
alg.finup = crc32c_pcl_intel_finup;
alg.digest = crc32c_pcl_intel_digest;
- set_pcl_breakeven_point();
}
#endif
return crypto_register_shash(&alg);
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -60,11 +60,6 @@ extern u64 fpu__get_supported_xfeatures_
/*
* FPU related CPU feature flag helper routines:
*/
-static __always_inline __pure bool use_eager_fpu(void)
-{
- return true;
-}
-
static __always_inline __pure bool use_xsaveopt(void)
{
return static_cpu_has(X86_FEATURE_XSAVEOPT);
@@ -501,24 +496,6 @@ static inline int fpu_want_lazy_restore(
}
-/*
- * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
- * idiom, which is then paired with the sw-flag (fpregs_active) later on:
- */
-
-static inline void __fpregs_activate_hw(void)
-{
- if (!use_eager_fpu())
- clts();
-}
-
-static inline void __fpregs_deactivate_hw(void)
-{
- if (!use_eager_fpu())
- stts();
-}
-
-/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
static inline void __fpregs_deactivate(struct fpu *fpu)
{
WARN_ON_FPU(!fpu->fpregs_active);
@@ -528,7 +505,6 @@ static inline void __fpregs_deactivate(s
trace_x86_fpu_regs_deactivated(fpu);
}
-/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
static inline void __fpregs_activate(struct fpu *fpu)
{
WARN_ON_FPU(fpu->fpregs_active);
@@ -554,22 +530,17 @@ static inline int fpregs_active(void)
}
/*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
* These generally need preemption protection to work,
* do try to avoid using these on their own.
*/
static inline void fpregs_activate(struct fpu *fpu)
{
- __fpregs_activate_hw();
__fpregs_activate(fpu);
}
static inline void fpregs_deactivate(struct fpu *fpu)
{
__fpregs_deactivate(fpu);
- __fpregs_deactivate_hw();
}
/*
@@ -596,8 +567,7 @@ switch_fpu_prepare(struct fpu *old_fpu,
* or if the past 5 consecutive context-switches used math.
*/
fpu.preload = static_cpu_has(X86_FEATURE_FPU) &&
- new_fpu->fpstate_active &&
- (use_eager_fpu() || new_fpu->counter > 5);
+ new_fpu->fpstate_active;
if (old_fpu->fpregs_active) {
if (!copy_fpregs_to_fpstate(old_fpu))
@@ -615,8 +585,6 @@ switch_fpu_prepare(struct fpu *old_fpu,
__fpregs_activate(new_fpu);
trace_x86_fpu_regs_activated(new_fpu);
prefetch(&new_fpu->state);
- } else {
- __fpregs_deactivate_hw();
}
} else {
old_fpu->counter = 0;
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -59,27 +59,9 @@ static bool kernel_fpu_disabled(void)
return this_cpu_read(in_kernel_fpu);
}
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- *
- * Except for the eagerfpu case when we return true; in the likely case
- * the thread has FPU but we are not going to set/clear TS.
- */
static bool interrupted_kernel_fpu_idle(void)
{
- if (kernel_fpu_disabled())
- return false;
-
- if (use_eager_fpu())
- return true;
-
- return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS);
+ return !kernel_fpu_disabled();
}
/*
@@ -127,7 +109,6 @@ void __kernel_fpu_begin(void)
copy_fpregs_to_fpstate(fpu);
} else {
this_cpu_write(fpu_fpregs_owner_ctx, NULL);
- __fpregs_activate_hw();
}
}
EXPORT_SYMBOL(__kernel_fpu_begin);
@@ -138,8 +119,6 @@ void __kernel_fpu_end(void)
if (fpu->fpregs_active)
copy_kernel_to_fpregs(&fpu->state);
- else
- __fpregs_deactivate_hw();
kernel_fpu_enable();
}
@@ -201,10 +180,7 @@ void fpu__save(struct fpu *fpu)
trace_x86_fpu_before_save(fpu);
if (fpu->fpregs_active) {
if (!copy_fpregs_to_fpstate(fpu)) {
- if (use_eager_fpu())
- copy_kernel_to_fpregs(&fpu->state);
- else
- fpregs_deactivate(fpu);
+ copy_kernel_to_fpregs(&fpu->state);
}
}
trace_x86_fpu_after_save(fpu);
@@ -262,8 +238,7 @@ int fpu__copy(struct fpu *dst_fpu, struc
* Don't let 'init optimized' areas of the XSAVE area
* leak into the child task:
*/
- if (use_eager_fpu())
- memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
+ memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
/*
* Save current FPU registers directly into the child
@@ -285,10 +260,7 @@ int fpu__copy(struct fpu *dst_fpu, struc
memcpy(&src_fpu->state, &dst_fpu->state,
fpu_kernel_xstate_size);
- if (use_eager_fpu())
- copy_kernel_to_fpregs(&src_fpu->state);
- else
- fpregs_deactivate(src_fpu);
+ copy_kernel_to_fpregs(&src_fpu->state);
}
preempt_enable();
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -344,11 +344,9 @@ static int __fpu__restore_sig(void __use
}
fpu->fpstate_active = 1;
- if (use_eager_fpu()) {
- preempt_disable();
- fpu__restore(fpu);
- preempt_enable();
- }
+ preempt_disable();
+ fpu__restore(fpu);
+ preempt_enable();
return err;
} else {
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -890,15 +890,6 @@ int arch_set_user_pkey_access(struct tas
*/
if (!boot_cpu_has(X86_FEATURE_OSPKE))
return -EINVAL;
- /*
- * For most XSAVE components, this would be an arduous task:
- * brining fpstate up to date with fpregs, updating fpstate,
- * then re-populating fpregs. But, for components that are
- * never lazily managed, we can just access the fpregs
- * directly. PKRU is never managed lazily, so we can just
- * manipulate it directly. Make sure it stays that way.
- */
- WARN_ON_ONCE(!use_eager_fpu());
/* Set the bits we need in PKRU: */
if (init_val & PKEY_DISABLE_ACCESS)
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,7 +16,6 @@
#include <linux/export.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
-#include <asm/fpu/internal.h> /* For use_eager_fpu. Ugh! */
#include <asm/user.h>
#include <asm/fpu/xstate.h>
#include "cpuid.h"
@@ -114,8 +113,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vc
if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
- if (use_eager_fpu())
- kvm_x86_ops->fpu_activate(vcpu);
+ kvm_x86_ops->fpu_activate(vcpu);
/*
* The existing code assumes virtual address is 48-bit in the canonical
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7631,16 +7631,6 @@ void kvm_put_guest_fpu(struct kvm_vcpu *
copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
__kernel_fpu_end();
++vcpu->stat.fpu_reload;
- /*
- * If using eager FPU mode, or if the guest is a frequent user
- * of the FPU, just leave the FPU active for next time.
- * Every 255 times fpu_counter rolls over to 0; a guest that uses
- * the FPU in bursts will revert to loading it on demand.
- */
- if (!use_eager_fpu()) {
- if (++vcpu->fpu_counter < 5)
- kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
- }
trace_kvm_fpu(0);
}
next prev parent reply other threads:[~2018-10-11 15:44 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-11 15:35 [PATCH 4.9 00/35] 4.9.133-stable review Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 01/35] mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 02/35] fbdev/omapfb: fix omapfb_memory_read infoleak Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 03/35] xen-netback: fix input validation in xenvif_set_hash_mapping() Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 04/35] x86/vdso: Fix asm constraints on vDSO syscall fallbacks Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 05/35] x86/vdso: Fix vDSO syscall fallback asm constraint regression Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 06/35] PCI: Reprogram bridge prefetch registers on resume Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 07/35] mac80211: fix setting IEEE80211_KEY_FLAG_RX_MGMT for AP mode keys Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 08/35] PM / core: Clear the direct_complete flag on errors Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 09/35] dm cache metadata: ignore hints array being too small during resize Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 10/35] dm cache: fix resize crash if user doesnt reload cache table Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 11/35] xhci: Add missing CAS workaround for Intel Sunrise Point xHCI Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 12/35] usb: xhci-mtk: resume USB3 roothub first Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 13/35] USB: serial: simple: add Motorola Tetra MTP6550 id Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 14/35] tty: Drop tty->count on tty_reopen() failure Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 15/35] of: unittest: Disable interrupt node tests for old world MAC systems Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 16/35] ext4: add corruption check in ext4_xattr_set_entry() Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 17/35] ext4: always verify the magic number in xattr blocks Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 18/35] cgroup: Fix deadlock in cpu hotplug path Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 19/35] ath10k: fix use-after-free in ath10k_wmi_cmd_send_nowait Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 20/35] ath10k: fix kernel panic issue during pci probe Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 21/35] powerpc/fadump: Return error when fadump registration fails Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 22/35] ARC: clone syscall to setp r25 as thread pointer Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 23/35] x86/mm: Expand static page table for fixmap space Greg Kroah-Hartman
2018-11-01 22:25 ` Ben Hutchings
2018-11-02 3:38 ` Feng Tang
2018-11-02 13:56 ` Sasha Levin
2018-10-11 15:35 ` [PATCH 4.9 24/35] f2fs: fix invalid memory access Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 25/35] ucma: fix a use-after-free in ucma_resolve_ip() Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 26/35] ubifs: Check for name being NULL while mounting Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 27/35] sched/cputime: Convert kcpustat to nsecs Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 28/35] sched/cputime: Increment kcpustat directly on irqtime account Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 29/35] sched/cputime: Fix ksoftirqd cputime accounting regression Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 30/35] ath10k: fix scan crash due to incorrect length calculation Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 31/35] ebtables: arpreply: Add the standard target sanity check Greg Kroah-Hartman
2018-10-11 15:35 ` Greg Kroah-Hartman [this message]
2018-10-11 15:35 ` [PATCH 4.9 33/35] x86/fpu: Remove struct fpu::counter Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 34/35] Revert "perf: sync up x86/.../cpufeatures.h" Greg Kroah-Hartman
2018-10-11 15:35 ` [PATCH 4.9 35/35] x86/fpu: Finish excising eagerfpu Greg Kroah-Hartman
2018-10-11 22:40 ` [PATCH 4.9 00/35] 4.9.133-stable review Shuah Khan
2018-10-12 4:33 ` Naresh Kamboju
2018-10-12 12:20 ` Guenter Roeck
2018-10-12 13:52 ` Greg Kroah-Hartman
2018-10-12 14:44 ` Greg Kroah-Hartman
2018-10-12 17:07 ` Nathan Chancellor
2018-10-12 17:50 ` Guenter Roeck
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=20181011152521.462158381@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=bp@alien8.de \
--cc=brgerst@gmail.com \
--cc=daniel.sangorrin@toshiba.co.jp \
--cc=dave.hansen@linux.intel.com \
--cc=dvlasenk@redhat.com \
--cc=fenghua.yu@intel.com \
--cc=hpa@zytor.com \
--cc=jpoimboe@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=quentin.casasnovas@oracle.com \
--cc=riel@redhat.com \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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).