All of lore.kernel.org
 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, kvm@vger.kernel.org
Subject: [RFC PATCH 03/22] x86/fpu/xstate: Modify address finder prototypes to access all the possible areas
Date: Thu,  1 Oct 2020 13:38:54 -0700	[thread overview]
Message-ID: <20201001203913.9125-4-chang.seok.bae@intel.com> (raw)
In-Reply-To: <20201001203913.9125-1-chang.seok.bae@intel.com>

The xstate infrastructure is not flexible to support dynamic areas in
task->fpu. Change the prototype of some address finding functions to access
task->fpu directly. Make changes for both outer and inner helpers:
get_xsave_addr() and __raw_xsave_addr().

No functional change.

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
Cc: kvm@vger.kernel.org
---
 arch/x86/include/asm/fpu/internal.h |  2 +-
 arch/x86/include/asm/fpu/xstate.h   |  2 +-
 arch/x86/include/asm/pgtable.h      |  2 +-
 arch/x86/kernel/cpu/common.c        |  2 +-
 arch/x86/kernel/fpu/xstate.c        | 43 ++++++++++++++++++++---------
 arch/x86/kvm/x86.c                  | 26 +++++++++++------
 arch/x86/mm/pkeys.c                 |  2 +-
 7 files changed, 52 insertions(+), 27 deletions(-)

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index c404fedf1a75..baca80e877a6 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -578,7 +578,7 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
 	 * return to userland e.g. for a copy_to_user() operation.
 	 */
 	if (current->mm) {
-		pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU);
+		pk = get_xsave_addr(new_fpu, XFEATURE_PKRU);
 		if (pk)
 			pkru_val = pk->pkru;
 	}
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index a315b055212f..3fbf45727ad6 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -100,7 +100,7 @@ extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 extern void __init update_regset_xstate_info(unsigned int size,
 					     u64 xstate_mask);
 
-void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+void *get_xsave_addr(struct fpu *fpu, int xfeature_nr);
 const void *get_xsave_field_ptr(int xfeature_nr);
 int using_compacted_format(void);
 int xfeature_size(int xfeature_nr);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index b836138ce852..e24a8fb8f479 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -142,7 +142,7 @@ static inline void write_pkru(u32 pkru)
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
 		return;
 
-	pk = get_xsave_addr(&current->thread.fpu.state.xsave, XFEATURE_PKRU);
+	pk = get_xsave_addr(&current->thread.fpu, XFEATURE_PKRU);
 
 	/*
 	 * The PKRU value in xstate needs to be in sync with the value that is
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d0363e15ec2e..183ee7f77065 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -478,7 +478,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 		return;
 
 	cr4_set_bits(X86_CR4_PKE);
-	pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
+	pk = get_xsave_addr(NULL, XFEATURE_PKRU);
 	if (pk)
 		pk->pkru = init_pkru_value;
 	/*
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index e3a9bddc39d9..bab22766b79b 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -891,15 +891,23 @@ void fpu__resume_cpu(void)
  * buffer the state is.  Callers should ensure that the buffer
  * is valid.
  */
-static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
+static void *__raw_xsave_addr(struct fpu *fpu, int xfeature_nr)
 {
+	void *xsave;
+
 	if (!xfeature_enabled(xfeature_nr)) {
 		WARN_ON_FPU(1);
 		return NULL;
 	}
 
-	return (void *)xsave + xstate_comp_offsets[xfeature_nr];
+	if (fpu)
+		xsave = &fpu->state.xsave;
+	else
+		xsave = &init_fpstate.xsave;
+
+	return xsave + xstate_comp_offsets[xfeature_nr];
 }
+
 /*
  * Given the xsave area and a state inside, this function returns the
  * address of the state.
@@ -911,15 +919,18 @@ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
  * this will return NULL.
  *
  * Inputs:
- *	xstate: the thread's storage area for all FPU data
+ *	fpu: the thread's FPU data to access all the FPU state storages.
+	     (If a null pointer is given, assume the init_fpstate)
  *	xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP,
  *	XFEATURE_SSE, etc...)
  * Output:
  *	address of the state in the xsave area, or NULL if the
  *	field is not present in the xsave buffer.
  */
-void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
+void *get_xsave_addr(struct fpu *fpu, int xfeature_nr)
 {
+	struct xregs_state *xsave;
+
 	/*
 	 * Do we even *have* xsave state?
 	 */
@@ -932,6 +943,12 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 	 */
 	WARN_ONCE(!(xfeatures_mask_all & BIT_ULL(xfeature_nr)),
 		  "get of unsupported state");
+
+	if (fpu)
+		xsave = &fpu->state.xsave;
+	else
+		xsave = &init_fpstate.xsave;
+
 	/*
 	 * This assumes the last 'xsave*' instruction to
 	 * have requested that 'xfeature_nr' be saved.
@@ -946,7 +963,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 	if (!(xsave->header.xfeatures & BIT_ULL(xfeature_nr)))
 		return NULL;
 
-	return __raw_xsave_addr(xsave, xfeature_nr);
+	return __raw_xsave_addr(fpu, xfeature_nr);
 }
 EXPORT_SYMBOL_GPL(get_xsave_addr);
 
@@ -977,7 +994,7 @@ const void *get_xsave_field_ptr(int xfeature_nr)
 	 */
 	fpu__save(fpu);
 
-	return get_xsave_addr(&fpu->state.xsave, xfeature_nr);
+	return get_xsave_addr(fpu, xfeature_nr);
 }
 
 #ifdef CONFIG_ARCH_HAS_PKEYS
@@ -1112,7 +1129,7 @@ void copy_xstate_to_kernel(struct membuf to, struct fpu *fpu)
 		 * Copy only in-use xstates:
 		 */
 		if ((header.xfeatures >> i) & 1) {
-			void *src = __raw_xsave_addr(xsave, i);
+			void *src = __raw_xsave_addr(fpu, i);
 
 			copy_part(&to, &last, xstate_offsets[i],
 				  xstate_sizes[i], src);
@@ -1141,13 +1158,11 @@ int copy_kernel_to_xstate(struct fpu *fpu, const void *kbuf)
 	if (validate_user_xstate_header(&hdr))
 		return -EINVAL;
 
-	xsave = &fpu->state.xsave;
-
 	for (i = 0; i < XFEATURE_MAX; i++) {
 		u64 mask = ((u64)1 << i);
 
 		if (hdr.xfeatures & mask) {
-			void *dst = __raw_xsave_addr(xsave, i);
+			void *dst = __raw_xsave_addr(fpu, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
@@ -1156,6 +1171,8 @@ int copy_kernel_to_xstate(struct fpu *fpu, const void *kbuf)
 		}
 	}
 
+	xsave = &fpu->state.xsave;
+
 	if (xfeatures_mxcsr_quirk(hdr.xfeatures)) {
 		offset = offsetof(struct fxregs_state, mxcsr);
 		size = MXCSR_AND_FLAGS_SIZE;
@@ -1198,13 +1215,11 @@ int copy_user_to_xstate(struct fpu *fpu, const void __user *ubuf)
 	if (validate_user_xstate_header(&hdr))
 		return -EINVAL;
 
-	xsave = &fpu->state.xsave;
-
 	for (i = 0; i < XFEATURE_MAX; i++) {
 		u64 mask = ((u64)1 << i);
 
 		if (hdr.xfeatures & mask) {
-			void *dst = __raw_xsave_addr(xsave, i);
+			void *dst = __raw_xsave_addr(fpu, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
@@ -1214,6 +1229,8 @@ int copy_user_to_xstate(struct fpu *fpu, const void __user *ubuf)
 		}
 	}
 
+	xsave = &fpu->state.xsave;
+
 	if (xfeatures_mxcsr_quirk(hdr.xfeatures)) {
 		offset = offsetof(struct fxregs_state, mxcsr);
 		size = MXCSR_AND_FLAGS_SIZE;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9da8cb4b8589..c4b8d3705625 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4182,10 +4182,15 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 
 static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 {
-	struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave;
-	u64 xstate_bv = xsave->header.xfeatures;
+	struct xregs_state *xsave;
+	struct fpu *guest_fpu;
+	u64 xstate_bv;
 	u64 valid;
 
+	guest_fpu = vcpu->arch.guest_fpu;
+	xsave = &guest_fpu->state.xsave;
+	xstate_bv = xsave->header.xfeatures;
+
 	/*
 	 * Copy legacy XSAVE area, to avoid complications with CPUID
 	 * leaves 0 and 1 in the loop below.
@@ -4204,7 +4209,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 	while (valid) {
 		u64 xfeature_mask = valid & -valid;
 		int xfeature_nr = fls64(xfeature_mask) - 1;
-		void *src = get_xsave_addr(xsave, xfeature_nr);
+		void *src = get_xsave_addr(guest_fpu, xfeature_nr);
 
 		if (src) {
 			u32 size, offset, ecx, edx;
@@ -4224,10 +4229,14 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 
 static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 {
-	struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave;
 	u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
+	struct xregs_state *xsave;
+	struct fpu *guest_fpu;
 	u64 valid;
 
+	guest_fpu = vcpu->arch.guest_fpu;
+	xsave = &guest_fpu->state.xsave;
+
 	/*
 	 * Copy legacy XSAVE area, to avoid complications with CPUID
 	 * leaves 0 and 1 in the loop below.
@@ -4247,7 +4256,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 	while (valid) {
 		u64 xfeature_mask = valid & -valid;
 		int xfeature_nr = fls64(xfeature_mask) - 1;
-		void *dest = get_xsave_addr(xsave, xfeature_nr);
+		void *dest = get_xsave_addr(guest_fpu, xfeature_nr);
 
 		if (dest) {
 			u32 size, offset, ecx, edx;
@@ -9662,6 +9671,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vcpu->arch.apf.halted = false;
 
 	if (kvm_mpx_supported()) {
+		struct fpu *guest_fpu = vcpu->arch.guest_fpu;
 		void *mpx_state_buffer;
 
 		/*
@@ -9670,12 +9680,10 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		 */
 		if (init_event)
 			kvm_put_guest_fpu(vcpu);
-		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
-					XFEATURE_BNDREGS);
+		mpx_state_buffer = get_xsave_addr(guest_fpu, XFEATURE_BNDREGS);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state));
-		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
-					XFEATURE_BNDCSR);
+		mpx_state_buffer = get_xsave_addr(guest_fpu, XFEATURE_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
 		if (init_event)
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index 8873ed1438a9..772e8bc3d49d 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -177,7 +177,7 @@ static ssize_t init_pkru_write_file(struct file *file,
 		return -EINVAL;
 
 	WRITE_ONCE(init_pkru_value, new_init_pkru);
-	pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
+	pk = get_xsave_addr(NULL, XFEATURE_PKRU);
 	if (!pk)
 		return -EINVAL;
 	pk->pkru = new_init_pkru;
-- 
2.17.1


  parent reply	other threads:[~2020-10-01 20:44 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 ` Chang S. Bae [this message]
2020-10-01 20:38 ` [RFC PATCH 04/22] x86/fpu/xstate: Modify save and restore " 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 ` [RFC PATCH 13/22] x86/fpu/xstate: Expand dynamic user state area on first use Chang S. Bae
2020-10-01 23:39   ` 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=20201001203913.9125-4-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=kvm@vger.kernel.org \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.