linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Chang S. Bae" <chang.seok.bae@intel.com>
To: tglx@linutronix.de, mingo@kernel.org, bp@suse.de,
	luto@kernel.org, x86@kernel.org
Cc: len.brown@intel.com, dave.hansen@intel.com, jing2.liu@intel.com,
	ravi.v.shankar@intel.com, linux-kernel@vger.kernel.org,
	chang.seok.bae@intel.com
Subject: [RFC PATCH 13/22] x86/fpu/xstate: Expand dynamic user state area on first use
Date: Thu,  1 Oct 2020 13:39:04 -0700	[thread overview]
Message-ID: <20201001203913.9125-14-chang.seok.bae@intel.com> (raw)
In-Reply-To: <20201001203913.9125-1-chang.seok.bae@intel.com>

Intel's Extended Feature Disable (XFD) feature is an extension of the XSAVE
architecture. XFD allows the kernel to enable a feature state in XCR0 and
to receive a #NM trap when a task uses instructions accessing that state.
In this way, Linux can allocate the large task->fpu buffer only for tasks
that use it.

XFD introduces two MSRs: IA32_XFD to enable/disable the feature and
IA32_XFD_ERR to assist the #NM trap handler. Both use the same
state-component bitmap format, used by XCR0.

Use this hardware capability to find the right time to expand xstate area.
Introduce two sets of helper functions for that:

1. The first set is primarily for interacting with the XFD hardware
   feature. Helpers for configuring disablement, e.g. in context switching,
   are:
	xdisable_setbits()
	xdisable_getbits()
	xdisable_switch()

2. The second set is for managing the first-use status and handling #NM
   trap:
	xfirstuse_enabled()
	xfirstuse_not_detected()
	xfirstuse_event_handler()

The #NM handler induces the xstate area expansion to save the first-used
states.

No functional change until the kernel enables dynamic user states and XFD.

Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Cc: x86@kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/x86/include/asm/cpufeatures.h  |  1 +
 arch/x86/include/asm/fpu/internal.h | 53 ++++++++++++++++++++++++++++-
 arch/x86/include/asm/msr-index.h    |  2 ++
 arch/x86/kernel/fpu/core.c          | 37 ++++++++++++++++++++
 arch/x86/kernel/fpu/xstate.c        | 34 ++++++++++++++++--
 arch/x86/kernel/process.c           |  5 +++
 arch/x86/kernel/process_32.c        |  2 +-
 arch/x86/kernel/process_64.c        |  2 +-
 arch/x86/kernel/traps.c             |  3 ++
 9 files changed, 133 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 2901d5df4366..7d7fe1d82966 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -274,6 +274,7 @@
 #define X86_FEATURE_XSAVEC		(10*32+ 1) /* XSAVEC instruction */
 #define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
 #define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
+#define X86_FEATURE_XFD			(10*32+ 4) /* eXtended Feature Disabling */
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 3b03ead87a46..f5dbbaa060fb 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -572,11 +572,60 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
  * Misc helper functions:
  */
 
+/* The first-use detection helpers: */
+
+static inline void xdisable_setbits(u64 value)
+{
+	wrmsrl_safe(MSR_IA32_XFD, value);
+}
+
+static inline u64 xdisable_getbits(void)
+{
+	u64 value;
+
+	rdmsrl_safe(MSR_IA32_XFD, &value);
+	return value;
+}
+
+static inline u64 xfirstuse_enabled(void)
+{
+	/* All the dynamic user components are first-use enabled. */
+	return xfeatures_mask_user_dynamic;
+}
+
+/*
+ * Convert fpu->firstuse_bv to xdisable configuration in MSR IA32_XFD.
+ * xdisable_setbits() only uses this.
+ */
+static inline u64 xfirstuse_not_detected(struct fpu *fpu)
+{
+	u64 firstuse_bv = (fpu->state_mask & xfirstuse_enabled());
+
+	/*
+	 * If first-use is not detected, set the bit. If the detection is
+	 * not enabled, the bit is always zero in firstuse_bv. So, make
+	 * following conversion:
+	 */
+	return  (xfirstuse_enabled() ^ firstuse_bv);
+}
+
+/* Update MSR IA32_XFD based on fpu->firstuse_bv */
+static inline void xdisable_switch(struct fpu *prev, struct fpu *next)
+{
+	if (!static_cpu_has(X86_FEATURE_XFD) || !xfirstuse_enabled())
+		return;
+
+	if (unlikely(prev->state_mask != next->state_mask))
+		xdisable_setbits(xfirstuse_not_detected(next));
+}
+
+bool xfirstuse_event_handler(struct fpu *fpu);
+
 /*
  * Load PKRU from the FPU context if available. Delay loading of the
  * complete FPU state until the return to userland.
  */
-static inline void switch_fpu_finish(struct fpu *new_fpu)
+static inline void switch_fpu_finish(struct fpu *old_fpu, struct fpu *new_fpu)
 {
 	u32 pkru_val = init_pkru_value;
 	struct pkru_state *pk;
@@ -586,6 +635,8 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
 
 	set_thread_flag(TIF_NEED_FPU_LOAD);
 
+	xdisable_switch(old_fpu, new_fpu);
+
 	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
 		return;
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2859ee4f39a8..0ccbe8cc99ad 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -610,6 +610,8 @@
 #define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
 
 #define MSR_IA32_XSS			0x00000da0
+#define MSR_IA32_XFD			0x000001c4
+#define MSR_IA32_XFD_ERR		0x000001c5
 
 #define MSR_IA32_APICBASE		0x0000001b
 #define MSR_IA32_APICBASE_BSP		(1<<8)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index ece6428ba85b..2e07bfcd54b3 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -518,3 +518,40 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 	 */
 	return 0;
 }
+
+bool xfirstuse_event_handler(struct fpu *fpu)
+{
+	bool handled = false;
+	u64 event_mask;
+
+	/* Check whether the first-use detection is running. */
+	if (!static_cpu_has(X86_FEATURE_XFD) || !xfirstuse_enabled())
+		return handled;
+
+	rdmsrl_safe(MSR_IA32_XFD_ERR, &event_mask);
+
+	/* The trap event should happen to one of first-use enabled features */
+	WARN_ON(!(event_mask & xfirstuse_enabled()));
+
+	/* If IA32_XFD_ERR is empty, the current trap has nothing to do with. */
+	if (!event_mask)
+		return handled;
+
+	/*
+	 * The first-use event is presumed to be from userspace, so it should have
+	 * nothing to do with interrupt context.
+	 */
+	if (WARN_ON(in_interrupt()))
+		return handled;
+
+	if (alloc_xstate_area(fpu, event_mask, NULL))
+		return handled;
+
+	xdisable_setbits(xfirstuse_not_detected(fpu));
+
+	/* Clear the trap record. */
+	wrmsrl_safe(MSR_IA32_XFD_ERR, 0);
+	handled = true;
+
+	return handled;
+}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index b9261ab4e5e2..13e8eff7a23b 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -130,6 +130,18 @@ static bool xfeature_is_supervisor(int xfeature_nr)
 	return ecx & 1;
 }
 
+static bool xfeature_disable_supported(int xfeature_nr)
+{
+	u32 eax, ebx, ecx, edx;
+
+	/*
+	 * If state component 'i' supports xfeature disable (or first-use
+	 * detection, ECX[2] return 1; otherwise, 0.
+	 */
+	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
+	return ecx & 4;
+}
+
 /*
  * Available once those arrays for the offset, size, and alignment info are set up,
  * by setup_xstate_features().
@@ -313,6 +325,9 @@ void fpu__init_cpu_xstate(void)
 		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
 				     xfeatures_mask_supervisor_dynamic());
 	}
+
+	if (boot_cpu_has(X86_FEATURE_XFD))
+		xdisable_setbits(xfirstuse_enabled());
 }
 
 static bool xfeature_enabled(enum xfeature xfeature)
@@ -511,8 +526,9 @@ static void __init print_xstate_offset_size(void)
 	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 		if (!xfeature_enabled(i))
 			continue;
-		pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n",
-			 i, xstate_comp_offsets[i], i, xstate_sizes[i]);
+		pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d (%s)\n",
+			i, xstate_comp_offsets[i], i, xstate_sizes[i],
+			(xfeatures_mask_user_dynamic & BIT_ULL(i)) ? "on-demand" : "default");
 	}
 }
 
@@ -942,9 +958,18 @@ void __init fpu__init_system_xstate(void)
 	}
 
 	xfeatures_mask_all &= fpu__get_supported_xfeatures_mask();
-	/* Do not support the dynamically allocated area yet. */
 	xfeatures_mask_user_dynamic = 0;
 
+	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
+		u64 feature_mask = BIT_ULL(i);
+
+		if (!(xfeatures_mask_user() & feature_mask))
+			continue;
+
+		if (xfeature_disable_supported(i))
+			xfeatures_mask_user_dynamic |= feature_mask;
+	}
+
 	/* Enable xstate instructions to be able to continue with initialization: */
 	fpu__init_cpu_xstate();
 	err = init_xstate_size();
@@ -999,6 +1024,9 @@ void fpu__resume_cpu(void)
 		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
 				     xfeatures_mask_supervisor_dynamic());
 	}
+
+	if (boot_cpu_has(X86_FEATURE_XFD))
+		xdisable_setbits(xfirstuse_not_detected(&current->thread.fpu));
 }
 
 /*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 43d38bd09fb1..66850b63fe66 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -102,6 +102,11 @@ void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
 	*size = fpu_kernel_xstate_default_size;
 }
 
+void arch_release_task_struct(struct task_struct *tsk)
+{
+	free_xstate_area(&tsk->thread.fpu);
+}
+
 /*
  * Free thread data structures etc..
  */
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 4f2f54e1281c..7bd5d08eeb41 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -213,7 +213,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	this_cpu_write(current_task, next_p);
 
-	switch_fpu_finish(next_fpu);
+	switch_fpu_finish(prev_fpu, next_fpu);
 
 	/* Load the Intel cache allocation PQR MSR. */
 	resctrl_sched_in();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9afefe325acb..3970367c02c0 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -595,7 +595,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(current_task, next_p);
 	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
-	switch_fpu_finish(next_fpu);
+	switch_fpu_finish(prev_fpu, next_fpu);
 
 	/* Reload sp0. */
 	update_task_stack(next_p);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 81a2fb711091..0eebcae99938 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -1028,6 +1028,9 @@ DEFINE_IDTENTRY(exc_device_not_available)
 {
 	unsigned long cr0 = read_cr0();
 
+	if (xfirstuse_event_handler(&current->thread.fpu))
+		return;
+
 #ifdef CONFIG_MATH_EMULATION
 	if (!boot_cpu_has(X86_FEATURE_FPU) && (cr0 & X86_CR0_EM)) {
 		struct math_emu_info info = { };
-- 
2.17.1


  parent reply	other threads:[~2020-10-01 20:43 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-01 20:38 [RFC PATCH 00/22] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
2020-10-01 20:38 ` [RFC PATCH 01/22] x86/fpu/xstate: Modify area init helper prototypes to access all the possible areas Chang S. Bae
2020-10-01 20:38 ` [RFC PATCH 02/22] x86/fpu/xstate: Modify xstate copy " Chang S. Bae
2020-10-01 20:38 ` [RFC PATCH 03/22] x86/fpu/xstate: Modify address finder " Chang S. Bae
2020-10-01 20:38 ` [RFC PATCH 04/22] x86/fpu/xstate: Modify save and restore helper " Chang S. Bae
2020-10-01 20:38 ` [RFC PATCH 05/22] x86/fpu/xstate: Introduce a new variable for dynamic user states Chang S. Bae
2020-10-01 20:38 ` [RFC PATCH 06/22] x86/fpu/xstate: Outline dynamic xstate area size in the task context Chang S. Bae
2020-10-01 20:38 ` [RFC PATCH 07/22] x86/fpu/xstate: Introduce helpers to manage an xstate area dynamically Chang S. Bae
2020-10-01 23:41   ` Andy Lutomirski
2020-10-13 22:00     ` Brown, Len
2020-10-01 20:38 ` [RFC PATCH 08/22] x86/fpu/xstate: Define the scope of the initial xstate data Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 09/22] x86/fpu/xstate: Introduce wrapper functions for organizing xstate area access Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 10/22] x86/fpu/xstate: Update xstate save function for supporting dynamic user xstate Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 11/22] x86/fpu/xstate: Update xstate area address finder " Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 12/22] x86/fpu/xstate: Update xstate context copy function for supporting dynamic area Chang S. Bae
2020-10-01 20:39 ` Chang S. Bae [this message]
2020-10-01 23:39   ` [RFC PATCH 13/22] x86/fpu/xstate: Expand dynamic user state area on first use Andy Lutomirski
2020-10-13 22:31     ` Brown, Len
2020-10-13 22:43       ` Dave Hansen
2020-10-14  1:11         ` Andy Lutomirski
2020-10-14  6:03           ` Dave Hansen
2020-10-14 16:10             ` Andy Lutomirski
2020-10-14 16:29               ` Dave Hansen
2020-11-03 21:32                 ` Bae, Chang Seok
2020-11-03 21:41                   ` Dave Hansen
2020-11-03 21:53                     ` Bae, Chang Seok
2020-10-14 10:41         ` Peter Zijlstra
2020-10-14  1:47       ` Andy Lutomirski
2020-10-01 20:39 ` [RFC PATCH 14/22] x86/fpu/xstate: Inherit dynamic user state when used in the parent Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 15/22] x86/fpu/xstate: Support ptracer-induced xstate area expansion Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 16/22] x86/fpu/xstate: Support dynamic user state in the signal handling path Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 17/22] x86/fpu/xstate: Extend the table for mapping xstate components with features Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 18/22] x86/cpufeatures/amx: Enumerate Advanced Matrix Extension (AMX) feature bits Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 19/22] x86/fpu/amx: Define AMX state components and have it used for boot-time checks Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 20/22] x86/fpu/amx: Enable the AMX feature in 64-bit mode Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 21/22] selftest/x86/amx: Include test cases for the AMX state management Chang S. Bae
2020-10-01 20:39 ` [RFC PATCH 22/22] x86/fpu/xstate: Introduce boot-parameters for control some state component support Chang S. Bae
2020-10-02  2:09   ` Randy Dunlap
2020-10-13 23:00     ` Brown, Len
2020-10-02 17:15   ` Andy Lutomirski
2020-10-02 17:26     ` Dave Hansen
2020-10-13 23:38     ` Brown, Len
2020-10-02 17:25   ` Dave Hansen

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=20201001203913.9125-14-chang.seok.bae@intel.com \
    --to=chang.seok.bae@intel.com \
    --cc=bp@suse.de \
    --cc=dave.hansen@intel.com \
    --cc=jing2.liu@intel.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mingo@kernel.org \
    --cc=ravi.v.shankar@intel.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.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).